diff options
author | Andrew McDermott <andrew.mcdermott@linaro.org> | 2014-02-12 16:59:54 +0000 |
---|---|---|
committer | Andrew McDermott <andrew.mcdermott@linaro.org> | 2014-02-12 16:59:54 +0000 |
commit | 86a9909c577bdd641e7483f56ffbec998ea421eb (patch) | |
tree | 3f67536f5008b7d434d0a25e2d1aa97d9179b74b /aarch64/share/hadoop/common/jdiff/hadoop_0.17.0.xml |
Initial import
Signed-off-by: Andrew McDermott <andrew.mcdermott@linaro.org>
Diffstat (limited to 'aarch64/share/hadoop/common/jdiff/hadoop_0.17.0.xml')
-rw-r--r-- | aarch64/share/hadoop/common/jdiff/hadoop_0.17.0.xml | 43272 |
1 files changed, 43272 insertions, 0 deletions
diff --git a/aarch64/share/hadoop/common/jdiff/hadoop_0.17.0.xml b/aarch64/share/hadoop/common/jdiff/hadoop_0.17.0.xml new file mode 100644 index 0000000..69dded3 --- /dev/null +++ b/aarch64/share/hadoop/common/jdiff/hadoop_0.17.0.xml @@ -0,0 +1,43272 @@ +<?xml version="1.0" encoding="iso-8859-1" standalone="no"?> +<!-- Generated by the JDiff Javadoc doclet --> +<!-- (http://www.jdiff.org) --> +<!-- on Tue Jun 10 22:31:49 UTC 2008 --> + +<api + xmlns:xsi='http://www.w3.org/2001/XMLSchema-instance' + xsi:noNamespaceSchemaLocation='api.xsd' + name="hadoop 0.17.0" + jdversion="1.1.0"> + +<!-- Command line arguments = -doclet jdiff.JDiff -docletpath /home/oom/tools/src/jdiff-1.1.0-src/jdiff.jar:/home/oom/tools/src/jdiff-1.1.0-src/lib/xerces.jar -classpath /home/oom/work/eclipse/hadoop-17/lib/commons-cli-2.0-SNAPSHOT.jar:/home/oom/work/eclipse/hadoop-17/lib/commons-codec-1.3.jar:/home/oom/work/eclipse/hadoop-17/lib/commons-httpclient-3.0.1.jar:/home/oom/work/eclipse/hadoop-17/lib/commons-logging-1.0.4.jar:/home/oom/work/eclipse/hadoop-17/lib/commons-logging-api-1.0.4.jar:/home/oom/work/eclipse/hadoop-17/lib/jets3t-0.5.0.jar:/home/oom/work/eclipse/hadoop-17/lib/jetty-5.1.4.jar:/home/oom/work/eclipse/hadoop-17/lib/jetty-ext/commons-el.jar:/home/oom/work/eclipse/hadoop-17/lib/jetty-ext/jasper-compiler.jar:/home/oom/work/eclipse/hadoop-17/lib/jetty-ext/jasper-runtime.jar:/home/oom/work/eclipse/hadoop-17/lib/jetty-ext/jsp-api.jar:/home/oom/work/eclipse/hadoop-17/lib/junit-3.8.1.jar:/home/oom/work/eclipse/hadoop-17/lib/kfs-0.1.jar:/home/oom/work/eclipse/hadoop-17/lib/log4j-1.2.13.jar:/home/oom/work/eclipse/hadoop-17/lib/servlet-api.jar:/home/oom/work/eclipse/hadoop-17/lib/xmlenc-0.52.jar:/home/oom/work/eclipse/hadoop-17/conf:/usr/releng/share/java/ant/1.6.5/lib/ant-launcher.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-antlr.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-apache-bcel.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-apache-bsf.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-apache-log4j.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-apache-oro.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-apache-regexp.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-apache-resolver.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-commons-logging.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-commons-net.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-icontract.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-jai.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-javamail.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-jdepend.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-jmf.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-jsch.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-junit.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-netrexx.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-nodeps.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-starteam.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-stylebook.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-swing.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-trax.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-vaj.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-weblogic.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-xalan1.jar:/usr/releng/share/java/ant/1.6.5/lib/ant-xslp.jar:/usr/releng/share/java/ant/1.6.5/lib/ant.jar:/usr/releng/share/java/ant/1.6.5/lib/xercesImpl.jar:/usr/releng/share/java/ant/1.6.5/lib/xml-apis.jar:/usr/releng/share/java/ant/1.6.5/lib/junit-3.8.1.jar:/nfs/ystools/vol/ystools/releng/build/Linux_2.6_rh4_x86_64/tools/java/jdk1.6.0_i586/lib/tools.jar -sourcepath /home/oom/work/eclipse/hadoop-17/src/java -apidir /home/oom/work/eclipse/hadoop-17/build -apiname hadoop 0.17.0 --> +<package name="org.apache.hadoop"> + <!-- start class org.apache.hadoop.HadoopVersionAnnotation --> + <class name="HadoopVersionAnnotation" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="java.lang.annotation.Annotation"/> + <doc> + <![CDATA[A package attribute that captures the version of Hadoop that was compiled.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.HadoopVersionAnnotation --> +</package> +<package name="org.apache.hadoop.conf"> + <!-- start interface org.apache.hadoop.conf.Configurable --> + <interface name="Configurable" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="setConf" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[Set the configuration to be used by this object.]]> + </doc> + </method> + <method name="getConf" return="org.apache.hadoop.conf.Configuration" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the configuration used by this object.]]> + </doc> + </method> + <doc> + <![CDATA[Something that may be configured with a {@link Configuration}.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.conf.Configurable --> + <!-- start class org.apache.hadoop.conf.Configuration --> + <class name="Configuration" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="java.lang.Iterable<java.util.Map.Entry<java.lang.String, java.lang.String>>"/> + <constructor name="Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[A new configuration.]]> + </doc> + </constructor> + <constructor name="Configuration" type="org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[A new configuration with the same settings cloned from another. + + @param other the configuration from which to clone settings.]]> + </doc> + </constructor> + <method name="addResource" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <doc> + <![CDATA[Add a configuration resource. + + The properties of this resource will override properties of previously + added resources, unless they were marked <a href="#Final">final</a>. + + @param name resource to be added, the classpath is examined for a file + with that name.]]> + </doc> + </method> + <method name="addResource" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="url" type="java.net.URL"/> + <doc> + <![CDATA[Add a configuration resource. + + The properties of this resource will override properties of previously + added resources, unless they were marked <a href="#Final">final</a>. + + @param url url of the resource to be added, the local filesystem is + examined directly to find the resource, without referring to + the classpath.]]> + </doc> + </method> + <method name="addResource" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="file" type="org.apache.hadoop.fs.Path"/> + <doc> + <![CDATA[Add a configuration resource. + + The properties of this resource will override properties of previously + added resources, unless they were marked <a href="#Final">final</a>. + + @param file file-path of resource to be added, the local filesystem is + examined directly to find the resource, without referring to + the classpath.]]> + </doc> + </method> + <method name="get" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <doc> + <![CDATA[Get the value of the <code>name</code> property, <code>null</code> if + no such property exists. + + Values are processed for <a href="#VariableExpansion">variable expansion</a> + before being returned. + + @param name the property name. + @return the value of the <code>name</code> property, + or null if no such property exists.]]> + </doc> + </method> + <method name="getRaw" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <doc> + <![CDATA[Get the value of the <code>name</code> property, without doing + <a href="#VariableExpansion">variable expansion</a>. + + @param name the property name. + @return the value of the <code>name</code> property, + or null if no such property exists.]]> + </doc> + </method> + <method name="set" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <param name="value" type="java.lang.String"/> + <doc> + <![CDATA[Set the <code>value</code> of the <code>name</code> property. + + @param name property name. + @param value property value.]]> + </doc> + </method> + <method name="get" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <param name="defaultValue" type="java.lang.String"/> + <doc> + <![CDATA[Get the value of the <code>name</code> property. If no such property + exists, then <code>defaultValue</code> is returned. + + @param name property name. + @param defaultValue default value. + @return property value, or <code>defaultValue</code> if the property + doesn't exist.]]> + </doc> + </method> + <method name="getInt" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <param name="defaultValue" type="int"/> + <doc> + <![CDATA[Get the value of the <code>name</code> property as an <code>int</code>. + + If no such property exists, or if the specified value is not a valid + <code>int</code>, then <code>defaultValue</code> is returned. + + @param name property name. + @param defaultValue default value. + @return property value as an <code>int</code>, + or <code>defaultValue</code>.]]> + </doc> + </method> + <method name="setInt" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <param name="value" type="int"/> + <doc> + <![CDATA[Set the value of the <code>name</code> property to an <code>int</code>. + + @param name property name. + @param value <code>int</code> value of the property.]]> + </doc> + </method> + <method name="getLong" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <param name="defaultValue" type="long"/> + <doc> + <![CDATA[Get the value of the <code>name</code> property as a <code>long</code>. + If no such property is specified, or if the specified value is not a valid + <code>long</code>, then <code>defaultValue</code> is returned. + + @param name property name. + @param defaultValue default value. + @return property value as a <code>long</code>, + or <code>defaultValue</code>.]]> + </doc> + </method> + <method name="setLong" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <param name="value" type="long"/> + <doc> + <![CDATA[Set the value of the <code>name</code> property to a <code>long</code>. + + @param name property name. + @param value <code>long</code> value of the property.]]> + </doc> + </method> + <method name="getFloat" return="float" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <param name="defaultValue" type="float"/> + <doc> + <![CDATA[Get the value of the <code>name</code> property as a <code>float</code>. + If no such property is specified, or if the specified value is not a valid + <code>float</code>, then <code>defaultValue</code> is returned. + + @param name property name. + @param defaultValue default value. + @return property value as a <code>float</code>, + or <code>defaultValue</code>.]]> + </doc> + </method> + <method name="getBoolean" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <param name="defaultValue" type="boolean"/> + <doc> + <![CDATA[Get the value of the <code>name</code> property as a <code>boolean</code>. + If no such property is specified, or if the specified value is not a valid + <code>boolean</code>, then <code>defaultValue</code> is returned. + + @param name property name. + @param defaultValue default value. + @return property value as a <code>boolean</code>, + or <code>defaultValue</code>.]]> + </doc> + </method> + <method name="setBoolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <param name="value" type="boolean"/> + <doc> + <![CDATA[Set the value of the <code>name</code> property to a <code>boolean</code>. + + @param name property name. + @param value <code>boolean</code> value of the property.]]> + </doc> + </method> + <method name="getRange" return="org.apache.hadoop.conf.Configuration.IntegerRanges" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <param name="defaultValue" type="java.lang.String"/> + <doc> + <![CDATA[Parse the given attribute as a set of integer ranges + @param name the attribute name + @param defaultValue the default value if it is not set + @return a new set of ranges from the configured value]]> + </doc> + </method> + <method name="getStrings" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <doc> + <![CDATA[Get the comma delimited values of the <code>name</code> property as + an array of <code>String</code>s. + If no such property is specified then <code>null</code> is returned. + + @param name property name. + @return property value as an array of <code>String</code>s, + or <code>null</code>.]]> + </doc> + </method> + <method name="getStrings" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <param name="defaultValue" type="java.lang.String[]"/> + <doc> + <![CDATA[Get the comma delimited values of the <code>name</code> property as + an array of <code>String</code>s. + If no such property is specified then default value is returned. + + @param name property name. + @param defaultValue The default value + @return property value as an array of <code>String</code>s, + or default value.]]> + </doc> + </method> + <method name="setStrings" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <param name="values" type="java.lang.String[]"/> + <doc> + <![CDATA[Set the array of string values for the <code>name</code> property as + as comma delimited values. + + @param name property name. + @param values The values]]> + </doc> + </method> + <method name="getClassByName" return="java.lang.Class<?>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/> + <doc> + <![CDATA[Load a class by name. + + @param name the class name. + @return the class object. + @throws ClassNotFoundException if the class is not found.]]> + </doc> + </method> + <method name="getClass" return="java.lang.Class<?>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <param name="defaultValue" type="java.lang.Class<?>"/> + <doc> + <![CDATA[Get the value of the <code>name</code> property as a <code>Class</code>. + If no such property is specified, then <code>defaultValue</code> is + returned. + + @param name the class name. + @param defaultValue default value. + @return property value as a <code>Class</code>, + or <code>defaultValue</code>.]]> + </doc> + </method> + <method name="getClass" return="java.lang.Class<? extends U>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <param name="defaultValue" type="java.lang.Class<? extends U>"/> + <param name="xface" type="java.lang.Class<U>"/> + <doc> + <![CDATA[Get the value of the <code>name</code> property as a <code>Class</code> + implementing the interface specified by <code>xface</code>. + + If no such property is specified, then <code>defaultValue</code> is + returned. + + An exception is thrown if the returned class does not implement the named + interface. + + @param name the class name. + @param defaultValue default value. + @param xface the interface implemented by the named class. + @return property value as a <code>Class</code>, + or <code>defaultValue</code>.]]> + </doc> + </method> + <method name="setClass" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <param name="theClass" type="java.lang.Class<?>"/> + <param name="xface" type="java.lang.Class<?>"/> + <doc> + <![CDATA[Set the value of the <code>name</code> property to the name of a + <code>theClass</code> implementing the given interface <code>xface</code>. + + An exception is thrown if <code>theClass</code> does not implement the + interface <code>xface</code>. + + @param name property name. + @param theClass property value. + @param xface the interface implemented by the named class.]]> + </doc> + </method> + <method name="getLocalPath" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dirsProp" type="java.lang.String"/> + <param name="path" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get a local file under a directory named by <i>dirsProp</i> with + the given <i>path</i>. If <i>dirsProp</i> contains multiple directories, + then one is chosen based on <i>path</i>'s hash code. If the selected + directory does not exist, an attempt is made to create it. + + @param dirsProp directory in which to locate the file. + @param path file-path. + @return local file under the directory with the given path.]]> + </doc> + </method> + <method name="getFile" return="java.io.File" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dirsProp" type="java.lang.String"/> + <param name="path" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get a local file name under a directory named in <i>dirsProp</i> with + the given <i>path</i>. If <i>dirsProp</i> contains multiple directories, + then one is chosen based on <i>path</i>'s hash code. If the selected + directory does not exist, an attempt is made to create it. + + @param dirsProp directory in which to locate the file. + @param path file-path. + @return local file under the directory with the given path.]]> + </doc> + </method> + <method name="getResource" return="java.net.URL" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <doc> + <![CDATA[Get the {@link URL} for the named resource. + + @param name resource name. + @return the url for the named resource.]]> + </doc> + </method> + <method name="getConfResourceAsInputStream" return="java.io.InputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <doc> + <![CDATA[Get an input stream attached to the configuration resource with the + given <code>name</code>. + + @param name configuration resource name. + @return an input stream attached to the resource.]]> + </doc> + </method> + <method name="getConfResourceAsReader" return="java.io.Reader" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <doc> + <![CDATA[Get a {@link Reader} attached to the configuration resource with the + given <code>name</code>. + + @param name configuration resource name. + @return a reader attached to the resource.]]> + </doc> + </method> + <method name="iterator" return="java.util.Iterator<java.util.Map.Entry<java.lang.String, java.lang.String>>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get an {@link Iterator} to go through the list of <code>String</code> + key-value pairs in the configuration. + + @return an iterator over the entries.]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.OutputStream"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Write out the non-default properties in this configuration to the give + {@link OutputStream}. + + @param out the output stream to write to.]]> + </doc> + </method> + <method name="getClassLoader" return="java.lang.ClassLoader" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the {@link ClassLoader} for this job. + + @return the correct class loader.]]> + </doc> + </method> + <method name="setClassLoader" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="classLoader" type="java.lang.ClassLoader"/> + <doc> + <![CDATA[Set the class loader that will be used to load the various objects. + + @param classLoader the new class loader.]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="setQuietMode" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="quietmode" type="boolean"/> + <doc> + <![CDATA[Set the quiteness-mode. + + In the quite-mode error and informational messages might not be logged. + + @param quietmode <code>true</code> to set quiet-mode on, <code>false</code> + to turn it off.]]> + </doc> + </method> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + <doc> + <![CDATA[For debugging. List non-default properties to the terminal and exit.]]> + </doc> + </method> + <doc> + <![CDATA[Provides access to configuration parameters. + + <h4 id="Resources">Resources</h4> + + <p>Configurations are specified by resources. A resource contains a set of + name/value pairs as XML data. Each resource is named by either a + <code>String</code> or by a {@link Path}. If named by a <code>String</code>, + then the classpath is examined for a file with that name. If named by a + <code>Path</code>, then the local filesystem is examined directly, without + referring to the classpath. + + <p>Hadoop by default specifies two resources, loaded in-order from the + classpath: <ol> + <li><tt><a href="{@docRoot}/../hadoop-default.html">hadoop-default.xml</a> + </tt>: Read-only defaults for hadoop.</li> + <li><tt>hadoop-site.xml</tt>: Site-specific configuration for a given hadoop + installation.</li> + </ol> + Applications may add additional resources, which are loaded + subsequent to these resources in the order they are added. + + <h4 id="FinalParams">Final Parameters</h4> + + <p>Configuration parameters may be declared <i>final</i>. + Once a resource declares a value final, no subsequently-loaded + resource can alter that value. + For example, one might define a final parameter with: + <tt><pre> + <property> + <name>dfs.client.buffer.dir</name> + <value>/tmp/hadoop/dfs/client</value> + <b><final>true</final></b> + </property></pre></tt> + + Administrators typically define parameters as final in + <tt>hadoop-site.xml</tt> for values that user applications may not alter. + + <h4 id="VariableExpansion">Variable Expansion</h4> + + <p>Value strings are first processed for <i>variable expansion</i>. The + available properties are:<ol> + <li>Other properties defined in this Configuration; and, if a name is + undefined here,</li> + <li>Properties in {@link System#getProperties()}.</li> + </ol> + + <p>For example, if a configuration resource contains the following property + definitions: + <tt><pre> + <property> + <name>basedir</name> + <value>/user/${<i>user.name</i>}</value> + </property> + + <property> + <name>tempdir</name> + <value>${<i>basedir</i>}/tmp</value> + </property></pre></tt> + + When <tt>conf.get("tempdir")</tt> is called, then <tt>${<i>basedir</i>}</tt> + will be resolved to another property in this Configuration, while + <tt>${<i>user.name</i>}</tt> would then ordinarily be resolved to the value + of the System property with that name.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.conf.Configuration --> + <!-- start class org.apache.hadoop.conf.Configuration.IntegerRanges --> + <class name="Configuration.IntegerRanges" extends="java.lang.Object" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="Configuration.IntegerRanges" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="Configuration.IntegerRanges" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="isIncluded" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="value" type="int"/> + <doc> + <![CDATA[Is the given value in the set of ranges + @param value the value to check + @return is the value in the ranges?]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[A class that represents a set of positive integer ranges. It parses + strings of the form: "2-3,5,7-" where ranges are separated by comma and + the lower/upper bounds are separated by dash. Either the lower or upper + bound may be omitted meaning all values up to or over. So the string + above means 2, 3, 5, and 7, 8, 9, ...]]> + </doc> + </class> + <!-- end class org.apache.hadoop.conf.Configuration.IntegerRanges --> + <!-- start class org.apache.hadoop.conf.Configured --> + <class name="Configured" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.conf.Configurable"/> + <constructor name="Configured" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct a Configured.]]> + </doc> + </constructor> + <constructor name="Configured" type="org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct a Configured.]]> + </doc> + </constructor> + <method name="setConf" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + </method> + <method name="getConf" return="org.apache.hadoop.conf.Configuration" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[Base class for things that may be configured with a {@link Configuration}.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.conf.Configured --> + <doc> + <![CDATA[Configuration of system parameters.]]> + </doc> +</package> +<package name="org.apache.hadoop.dfs"> + <!-- start class org.apache.hadoop.dfs.AlreadyBeingCreatedException --> + <class name="AlreadyBeingCreatedException" extends="java.io.IOException" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="AlreadyBeingCreatedException" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <doc> + <![CDATA[The exception that happens when you ask to create a file that already + is being created, but is not closed yet.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.AlreadyBeingCreatedException --> + <!-- start class org.apache.hadoop.dfs.Balancer --> + <class name="Balancer" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.util.Tool"/> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <doc> + <![CDATA[Run a balancer + @param args]]> + </doc> + </method> + <method name="run" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + <doc> + <![CDATA[main method of Balancer + @param args arguments to a Balancer + @exception any exception occurs during datanode balancing]]> + </doc> + </method> + <method name="getConf" return="org.apache.hadoop.conf.Configuration" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[return this balancer's configuration]]> + </doc> + </method> + <method name="setConf" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[set this balancer's configuration]]> + </doc> + </method> + <field name="SUCCESS" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="ALREADY_RUNNING" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="NO_MOVE_BLOCK" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="NO_MOVE_PROGRESS" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="IO_EXCEPTION" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="ILLEGAL_ARGS" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[<p>The balancer is a tool that balances disk space usage on an HDFS cluster + when some datanodes become full or when new empty nodes join the cluster. + The tool is deployed as an application program that can be run by the + cluster administrator on a live HDFS cluster while applications + adding and deleting files. + + <p>SYNOPSIS + <pre> + To start: + bin/start-balancer.sh [-threshold <threshold>] + Example: bin/ start-balancer.sh + start the balancer with a default threshold of 10% + bin/ start-balancer.sh -threshold 5 + start the balancer with a threshold of 5% + To stop: + bin/ stop-balancer.sh + </pre> + + <p>DESCRIPTION + <p>The threshold parameter is a fraction in the range of (0%, 100%) with a + default value of 10%. The threshold sets a target for whether the cluster + is balanced. A cluster is balanced if for each datanode, the utilization + of the node (ratio of used space at the node to total capacity of the node) + differs from the utilization of the (ratio of used space in the cluster + to total capacity of the cluster) by no more than the threshold value. + The smaller the threshold, the more balanced a cluster will become. + It takes more time to run the balancer for small threshold values. + Also for a very small threshold the cluster may not be able to reach the + balanced state when applications write and delete files concurrently. + + <p>The tool moves blocks from highly utilized datanodes to poorly + utilized datanodes iteratively. In each iteration a datanode moves or + receives no more than the lesser of 10G bytes or the threshold fraction + of its capacity. Each iteration runs no more than 20 minutes. + At the end of each iteration, the balancer obtains updated datanodes + information from the namenode. + + <p>A system property that limits the balancer's use of bandwidth is + defined in the default configuration file: + <pre> + <property> + <name>dfs.balance.bandwidthPerSec</name> + <value>1048576</value> + <description> Specifies the maximum bandwidth that each datanode + can utilize for the balancing purpose in term of the number of bytes + per second. </description> + </property> + </pre> + + <p>This property determines the maximum speed at which a block will be + moved from one datanode to another. The default value is 1MB/s. The higher + the bandwidth, the faster a cluster can reach the balanced state, + but with greater competition with application processes. If an + administrator changes the value of this property in the configuration + file, the change is observed when HDFS is next restarted. + + <p>MONITERING BALANCER PROGRESS + <p>After the balancer is started, an output file name where the balancer + progress will be recorded is printed on the screen. The administrator + can monitor the running of the balancer by reading the output file. + The output shows the balancer's status iteration by iteration. In each + iteration it prints the starting time, the iteration number, the total + number of bytes that have been moved in the previous iterations, + the total number of bytes that are left to move in order for the cluster + to be balanced, and the number of bytes that are being moved in this + iteration. Normally "Bytes Already Moved" is increasing while "Bytes Left + To Move" is decreasing. + + <p>Running multiple instances of the balancer in an HDFS cluster is + prohibited by the tool. + + <p>The balancer automatically exits when any of the following five + conditions is satisfied: + <ol> + <li>The cluster is balanced; + <li>No block can be moved; + <li>No block has been moved for five consecutive iterations; + <li>An IOException occurs while communicating with the namenode; + <li>Another balancer is running. + </ol> + + <p>Upon exit, a balancer returns an exit code and prints one of the + following messages to the output file in corresponding to the above exit + reasons: + <ol> + <li>The cluster is balanced. Exiting + <li>No block can be moved. Exiting... + <li>No block has been moved for 3 iterations. Exiting... + <li>Received an IO exception: failure reason. Exiting... + <li>Another balancer is running. Exiting... + </ol> + + <p>The administrator can interrupt the execution of the balancer at any + time by running the command "stop-balancer.sh" on the machine where the + balancer is running.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.Balancer --> + <!-- start class org.apache.hadoop.dfs.ChecksumDistributedFileSystem --> + <class name="ChecksumDistributedFileSystem" extends="org.apache.hadoop.fs.ChecksumFileSystem" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="ChecksumDistributedFileSystem" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="ChecksumDistributedFileSystem" type="java.net.InetSocketAddress, org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="deprecated, no comment"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[@deprecated]]> + </doc> + </constructor> + <method name="getContentLength" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getRawCapacity" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return the total raw capacity of the filesystem, disregarding + replication .]]> + </doc> + </method> + <method name="getRawUsed" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return the total raw used space in the filesystem, disregarding + replication .]]> + </doc> + </method> + <method name="getDataNodeStats" return="org.apache.hadoop.dfs.DatanodeInfo[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return statistics for each datanode.]]> + </doc> + </method> + <method name="setSafeMode" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="action" type="org.apache.hadoop.dfs.FSConstants.SafeModeAction"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Enter, leave or get safe mode. + + @see org.apache.hadoop.dfs.ClientProtocol#setSafeMode(FSConstants.SafeModeAction)]]> + </doc> + </method> + <method name="refreshNodes" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="finalizeUpgrade" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Finalize previously upgraded files system state.]]> + </doc> + </method> + <method name="distributedUpgradeProgress" return="org.apache.hadoop.dfs.UpgradeStatusReport" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="action" type="org.apache.hadoop.dfs.FSConstants.UpgradeAction"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="metaSave" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="pathname" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="reportChecksumFailure" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="in" type="org.apache.hadoop.fs.FSDataInputStream"/> + <param name="inPos" type="long"/> + <param name="sums" type="org.apache.hadoop.fs.FSDataInputStream"/> + <param name="sumsPos" type="long"/> + <doc> + <![CDATA[We need to find the blocks that didn't match. Likely only one + is corrupt but we will report both to the namenode. In the future, + we can consider figuring out exactly which block is corrupt.]]> + </doc> + </method> + <method name="getFileStatus" return="org.apache.hadoop.fs.FileStatus" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns the stat information about the file.]]> + </doc> + </method> + <doc> + <![CDATA[An implementation of ChecksumFileSystem over DistributedFileSystem. + Note that as of now (May 07), DistributedFileSystem natively checksums + all of its data. Using this class is not be necessary in most cases. + Currently provided mainly for backward compatibility and testing.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.ChecksumDistributedFileSystem --> + <!-- start class org.apache.hadoop.dfs.DataBlockScanner --> + <class name="DataBlockScanner" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="java.lang.Runnable"/> + <method name="run" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <field name="LOG" type="org.apache.commons.logging.Log" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + </class> + <!-- end class org.apache.hadoop.dfs.DataBlockScanner --> + <!-- start class org.apache.hadoop.dfs.DataBlockScanner.Servlet --> + <class name="DataBlockScanner.Servlet" extends="javax.servlet.http.HttpServlet" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="DataBlockScanner.Servlet" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="doGet" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="request" type="javax.servlet.http.HttpServletRequest"/> + <param name="response" type="javax.servlet.http.HttpServletResponse"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + </class> + <!-- end class org.apache.hadoop.dfs.DataBlockScanner.Servlet --> + <!-- start class org.apache.hadoop.dfs.DataChecksum --> + <class name="DataChecksum" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="java.util.zip.Checksum"/> + <method name="newDataChecksum" return="org.apache.hadoop.dfs.DataChecksum" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="type" type="int"/> + <param name="bytesPerChecksum" type="int"/> + </method> + <method name="newDataChecksum" return="org.apache.hadoop.dfs.DataChecksum" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="bytes" type="byte[]"/> + <param name="offset" type="int"/> + <doc> + <![CDATA[Creates a DataChecksum from HEADER_LEN bytes from arr[offset]. + @return DataChecksum of the type in the array or null in case of an error.]]> + </doc> + </method> + <method name="newDataChecksum" return="org.apache.hadoop.dfs.DataChecksum" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInputStream"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[This constructucts a DataChecksum by reading HEADER_LEN bytes from + input stream <i>in</i>]]> + </doc> + </method> + <method name="writeHeader" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutputStream"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Writes the checksum header to the output stream <i>out</i>.]]> + </doc> + </method> + <method name="getHeader" return="byte[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="writeValue" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutputStream"/> + <param name="reset" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Writes the current checksum to the stream. + If <i>reset</i> is true, then resets the checksum. + @return number of bytes written. Will be equal to getChecksumSize();]]> + </doc> + </method> + <method name="writeValue" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="buf" type="byte[]"/> + <param name="offset" type="int"/> + <param name="reset" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Writes the current checksum to a buffer. + If <i>reset</i> is true, then resets the checksum. + @return number of bytes written. Will be equal to getChecksumSize();]]> + </doc> + </method> + <method name="compare" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="buf" type="byte[]"/> + <param name="offset" type="int"/> + <doc> + <![CDATA[Compares the checksum located at buf[offset] with the current checksum. + @return true if the checksum matches and false otherwise.]]> + </doc> + </method> + <method name="getChecksumType" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getChecksumSize" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getBytesPerChecksum" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getNumBytesInSum" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getChecksumHeaderSize" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getValue" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="reset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="update" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + </method> + <method name="update" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="int"/> + </method> + <field name="HEADER_LEN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="CHECKSUM_NULL" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="CHECKSUM_CRC32" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[This class provides inteface and utilities for processing checksums for + DFS data transfers.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.DataChecksum --> + <!-- start class org.apache.hadoop.dfs.DataNode --> + <class name="DataNode" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.dfs.FSConstants"/> + <implements name="java.lang.Runnable"/> + <method name="createSocketAddr" return="java.net.InetSocketAddress" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="target" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Use {@link NetUtils#createSocketAddr(String)} instead.]]> + </doc> + </method> + <method name="getDataNode" return="org.apache.hadoop.dfs.DataNode" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the DataNode object]]> + </doc> + </method> + <method name="getNameNodeAddr" return="java.net.InetSocketAddress" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getSelfAddr" return="java.net.InetSocketAddress" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getNamenode" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the namenode's identifier]]> + </doc> + </method> + <method name="shutdown" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Shut down this instance of the datanode. + Returns only after shutdown is complete.]]> + </doc> + </method> + <method name="offerService" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="Exception" type="java.lang.Exception"/> + <doc> + <![CDATA[Main loop for the DataNode. Runs until shutdown, + forever calling remote NameNode functions.]]> + </doc> + </method> + <method name="run" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[No matter what kind of exception we get, keep retrying to offerService(). + That's the loop that connects to the NameNode and provides basic DataNode + functionality. + + Only stop when "shouldRun" is turned off (which can only happen at shutdown).]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="scheduleBlockReport" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="delay" type="long"/> + <doc> + <![CDATA[This methods arranges for the data node to send the block report at the next heartbeat.]]> + </doc> + </method> + <method name="getFSDataset" return="org.apache.hadoop.dfs.FSDatasetInterface" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[This method is used for testing. + Examples are adding and deleting blocks directly. + The most common usage will be when the data node's storage is similated. + + @return the fsdataset that stores the blocks]]> + </doc> + </method> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + </method> + <field name="LOG" type="org.apache.commons.logging.Log" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[DataNode is a class (and program) that stores a set of + blocks for a DFS deployment. A single deployment can + have one or many DataNodes. Each DataNode communicates + regularly with a single NameNode. It also communicates + with client code and other DataNodes from time to time. + + DataNodes store a series of named blocks. The DataNode + allows client code to read these blocks, or to write new + block data. The DataNode may also, in response to instructions + from its NameNode, delete blocks or copy blocks to/from other + DataNodes. + + The DataNode maintains just one critical table: + block-> stream of bytes (of BLOCK_SIZE or less) + + This info is stored on a local disk. The DataNode + reports the table's contents to the NameNode upon startup + and every so often afterwards. + + DataNodes spend their lives in an endless loop of asking + the NameNode for something to do. A NameNode cannot connect + to a DataNode directly; a NameNode simply returns values from + functions invoked by a DataNode. + + DataNodes maintain an open server socket so that client code + or other DataNodes can read/write data. The host/port for + this server is reported to the NameNode, which then sends that + information to clients or other DataNodes that might be interested.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.DataNode --> + <!-- start class org.apache.hadoop.dfs.DatanodeDescriptor --> + <class name="DatanodeDescriptor" extends="org.apache.hadoop.dfs.DatanodeInfo" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="DatanodeDescriptor" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Default constructor]]> + </doc> + </constructor> + <constructor name="DatanodeDescriptor" type="org.apache.hadoop.dfs.DatanodeID" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[DatanodeDescriptor constructor + @param nodeID id of the data node]]> + </doc> + </constructor> + <constructor name="DatanodeDescriptor" type="org.apache.hadoop.dfs.DatanodeID, java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[DatanodeDescriptor constructor + + @param nodeID id of the data node + @param networkLocation location of the data node in network]]> + </doc> + </constructor> + <constructor name="DatanodeDescriptor" type="org.apache.hadoop.dfs.DatanodeID, java.lang.String, java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[DatanodeDescriptor constructor + + @param nodeID id of the data node + @param networkLocation location of the data node in network + @param hostName it could be different from host specified for DatanodeID]]> + </doc> + </constructor> + <constructor name="DatanodeDescriptor" type="org.apache.hadoop.dfs.DatanodeID, long, long, long, int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[DatanodeDescriptor constructor + + @param nodeID id of the data node + @param capacity capacity of the data node + @param dfsUsed space used by the data node + @param remaining remaing capacity of the data node + @param xceiverCount # of data transfers at the data node]]> + </doc> + </constructor> + <constructor name="DatanodeDescriptor" type="org.apache.hadoop.dfs.DatanodeID, java.lang.String, java.lang.String, long, long, long, int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[DatanodeDescriptor constructor + + @param nodeID id of the data node + @param networkLocation location of the data node in network + @param capacity capacity of the data node, including space used by non-dfs + @param dfsUsed the used space by dfs datanode + @param remaining remaing capacity of the data node + @param xceiverCount # of data transfers at the data node]]> + </doc> + </constructor> + <field name="isAlive" type="boolean" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[DatanodeDescriptor tracks stats on a given DataNode, + such as available storage capacity, last update time, etc., + and maintains a set of blocks stored on the datanode. + + This data structure is a data structure that is internal + to the namenode. It is *not* sent over-the-wire to the Client + or the Datnodes. Neither is it stored persistently in the + fsImage.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.DatanodeDescriptor --> + <!-- start class org.apache.hadoop.dfs.DatanodeID --> + <class name="DatanodeID" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.WritableComparable"/> + <constructor name="DatanodeID" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[DatanodeID default constructor]]> + </doc> + </constructor> + <constructor name="DatanodeID" type="org.apache.hadoop.dfs.DatanodeID" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[DatanodeID copy constructor + + @param from]]> + </doc> + </constructor> + <constructor name="DatanodeID" type="java.lang.String, java.lang.String, int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Create DatanodeID + + @param nodeName (hostname:portNumber) + @param storageID data storage ID]]> + </doc> + </constructor> + <method name="getName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return hostname:portNumber.]]> + </doc> + </method> + <method name="getStorageID" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return data storage ID.]]> + </doc> + </method> + <method name="getInfoPort" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return infoPort (the port at which the HTTP server bound to)]]> + </doc> + </method> + <method name="getHost" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return hostname and no :portNumber.]]> + </doc> + </method> + <method name="getPort" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="to" type="java.lang.Object"/> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="compareTo" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + <doc> + <![CDATA[Comparable. + Basis of compare is the String name (host:portNumber) only. + @param o + @return as specified by Comparable.]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <field name="name" type="java.lang.String" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="storageID" type="java.lang.String" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="infoPort" type="int" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[DatanodeID is composed of the data node + name (hostname:portNumber) and the data storage ID, + which it currently represents.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.DatanodeID --> + <!-- start class org.apache.hadoop.dfs.DatanodeInfo --> + <class name="DatanodeInfo" extends="org.apache.hadoop.dfs.DatanodeID" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.net.Node"/> + <method name="getCapacity" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The raw capacity.]]> + </doc> + </method> + <method name="getDfsUsed" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The used space by the data node.]]> + </doc> + </method> + <method name="getRemaining" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The raw free space.]]> + </doc> + </method> + <method name="getLastUpdate" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The time when this information was accurate.]]> + </doc> + </method> + <method name="getXceiverCount" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[number of active connections]]> + </doc> + </method> + <method name="getNetworkLocation" return="java.lang.String" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[rack name]]> + </doc> + </method> + <method name="setNetworkLocation" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="location" type="java.lang.String"/> + <doc> + <![CDATA[Sets the rack name]]> + </doc> + </method> + <method name="getHostName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="setHostName" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="host" type="java.lang.String"/> + </method> + <method name="getDatanodeReport" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[A formatted string for reporting the status of the DataNode.]]> + </doc> + </method> + <method name="getParent" return="org.apache.hadoop.net.Node" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return this node's parent]]> + </doc> + </method> + <method name="setParent" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="parent" type="org.apache.hadoop.net.Node"/> + </method> + <method name="getLevel" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return this node's level in the tree. + E.g. the root of a tree returns 0 and its children return 1]]> + </doc> + </method> + <method name="setLevel" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="level" type="int"/> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <field name="capacity" type="long" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="dfsUsed" type="long" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="remaining" type="long" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="lastUpdate" type="long" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="xceiverCount" type="int" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="adminState" type="org.apache.hadoop.dfs.DatanodeInfo.AdminStates" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[DatanodeInfo represents the status of a DataNode. + This object is used for communication in the + Datanode Protocol and the Client Protocol.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.DatanodeInfo --> + <!-- start class org.apache.hadoop.dfs.DatanodeInfo.AdminStates --> + <class name="DatanodeInfo.AdminStates" extends="java.lang.Enum<org.apache.hadoop.dfs.DatanodeInfo.AdminStates>" + abstract="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <method name="values" return="org.apache.hadoop.dfs.DatanodeInfo.AdminStates[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="valueOf" return="org.apache.hadoop.dfs.DatanodeInfo.AdminStates" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + </class> + <!-- end class org.apache.hadoop.dfs.DatanodeInfo.AdminStates --> + <!-- start class org.apache.hadoop.dfs.DFSAdmin --> + <class name="DFSAdmin" extends="org.apache.hadoop.fs.FsShell" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="DFSAdmin" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct a DFSAdmin object.]]> + </doc> + </constructor> + <constructor name="DFSAdmin" type="org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct a DFSAdmin object.]]> + </doc> + </constructor> + <method name="report" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Gives a report on how the FileSystem is doing. + @exception IOException if the filesystem does not exist.]]> + </doc> + </method> + <method name="setSafeMode" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="argv" type="java.lang.String[]"/> + <param name="idx" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Safe mode maintenance command. + Usage: java DFSAdmin -safemode [enter | leave | get] + @param argv List of of command line parameters. + @param idx The index of the command that is being processed. + @exception IOException if the filesystem does not exist.]]> + </doc> + </method> + <method name="refreshNodes" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Command to ask the namenode to reread the hosts and excluded hosts + file. + Usage: java DFSAdmin -refreshNodes + @exception IOException]]> + </doc> + </method> + <method name="finalizeUpgrade" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Command to ask the namenode to finalize previously performed upgrade. + Usage: java DFSAdmin -finalizeUpgrade + @exception IOException]]> + </doc> + </method> + <method name="upgradeProgress" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="argv" type="java.lang.String[]"/> + <param name="idx" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Command to request current distributed upgrade status, + a detailed status, or to force the upgrade to proceed. + + Usage: java DFSAdmin -upgradeProgress [status | details | force] + @exception IOException]]> + </doc> + </method> + <method name="metaSave" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="argv" type="java.lang.String[]"/> + <param name="idx" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Dumps DFS data structures into specified file. + Usage: java DFSAdmin -metasave filename + @param argv List of of command line parameters. + @param idx The index of the command that is being processed. + @exception IOException if an error accoured wile accessing + the file or path.]]> + </doc> + </method> + <method name="printUsage" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="cmd" type="java.lang.String"/> + <doc> + <![CDATA[Displays format of commands. + @param cmd The command that is being executed.]]> + </doc> + </method> + <method name="run" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="argv" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + <doc> + <![CDATA[@param argv The parameters passed to this program. + @exception Exception if the filesystem does not exist. + @return 0 on success, non zero on error.]]> + </doc> + </method> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="argv" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + <doc> + <![CDATA[main() has some simple utility methods. + @param argv Command line parameters. + @exception Exception if the filesystem does not exist.]]> + </doc> + </method> + <doc> + <![CDATA[This class provides some DFS administrative access.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.DFSAdmin --> + <!-- start class org.apache.hadoop.dfs.DFSck --> + <class name="DFSck" extends="org.apache.hadoop.conf.Configured" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.util.Tool"/> + <constructor name="DFSck" type="org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="Exception" type="java.lang.Exception"/> + <doc> + <![CDATA[Filesystem checker. + @param conf current Configuration + @throws Exception]]> + </doc> + </constructor> + <method name="run" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + <doc> + <![CDATA[@param args]]> + </doc> + </method> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + </method> + <doc> + <![CDATA[This class provides rudimentary checking of DFS volumes for errors and + sub-optimal conditions. + <p>The tool scans all files and directories, starting from an indicated + root path. The following abnormal conditions are detected and handled:</p> + <ul> + <li>files with blocks that are completely missing from all datanodes.<br/> + In this case the tool can perform one of the following actions: + <ul> + <li>none ({@link NamenodeFsck#FIXING_NONE})</li> + <li>move corrupted files to /lost+found directory on DFS + ({@link NamenodeFsck#FIXING_MOVE}). Remaining data blocks are saved as a + block chains, representing longest consecutive series of valid blocks.</li> + <li>delete corrupted files ({@link NamenodeFsck#FIXING_DELETE})</li> + </ul> + </li> + <li>detect files with under-replicated or over-replicated blocks</li> + </ul> + Additionally, the tool collects a detailed overall DFS statistics, and + optionally can print detailed statistics on block locations and replication + factors of each file.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.DFSck --> + <!-- start class org.apache.hadoop.dfs.DistributedFileSystem --> + <class name="DistributedFileSystem" extends="org.apache.hadoop.fs.FileSystem" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="DistributedFileSystem" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="DistributedFileSystem" type="java.net.InetSocketAddress, org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="deprecated, no comment"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[@deprecated]]> + </doc> + </constructor> + <method name="getName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="deprecated, no comment"> + <doc> + <![CDATA[@deprecated]]> + </doc> + </method> + <method name="getUri" return="java.net.URI" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="initialize" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="uri" type="java.net.URI"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getWorkingDirectory" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getDefaultBlockSize" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getDefaultReplication" return="short" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="setWorkingDirectory" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dir" type="org.apache.hadoop.fs.Path"/> + </method> + <method name="getHomeDirectory" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="getFileBlockLocations" return="org.apache.hadoop.fs.BlockLocation[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="start" type="long"/> + <param name="len" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="setVerifyChecksum" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="verifyChecksum" type="boolean"/> + </method> + <method name="open" return="org.apache.hadoop.fs.FSDataInputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="bufferSize" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="create" return="org.apache.hadoop.fs.FSDataOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="permission" type="org.apache.hadoop.fs.permission.FsPermission"/> + <param name="overwrite" type="boolean"/> + <param name="bufferSize" type="int"/> + <param name="replication" type="short"/> + <param name="blockSize" type="long"/> + <param name="progress" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="setReplication" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="replication" type="short"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="rename" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Rename files/dirs]]> + </doc> + </method> + <method name="delete" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get rid of Path f, whether a true file or dir.]]> + </doc> + </method> + <method name="delete" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="recursive" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[requires a boolean check to delete a non + empty directory recursively.]]> + </doc> + </method> + <method name="getContentLength" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="getContentSummary" return="org.apache.hadoop.fs.ContentSummary" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="listStatus" return="org.apache.hadoop.fs.FileStatus[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="p" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="mkdirs" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="permission" type="org.apache.hadoop.fs.permission.FsPermission"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getDiskStatus" return="org.apache.hadoop.dfs.DistributedFileSystem.DiskStatus" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return the disk usage of the filesystem, including total capacity, + used space, and remaining space]]> + </doc> + </method> + <method name="getRawCapacity" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return the total raw capacity of the filesystem, disregarding + replication .]]> + </doc> + </method> + <method name="getRawUsed" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return the total raw used space in the filesystem, disregarding + replication .]]> + </doc> + </method> + <method name="getDataNodeStats" return="org.apache.hadoop.dfs.DatanodeInfo[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return statistics for each datanode.]]> + </doc> + </method> + <method name="setSafeMode" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="action" type="org.apache.hadoop.dfs.FSConstants.SafeModeAction"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Enter, leave or get safe mode. + + @see org.apache.hadoop.dfs.ClientProtocol#setSafeMode( + FSConstants.SafeModeAction)]]> + </doc> + </method> + <method name="refreshNodes" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="finalizeUpgrade" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Finalize previously upgraded files system state. + @throws IOException]]> + </doc> + </method> + <method name="distributedUpgradeProgress" return="org.apache.hadoop.dfs.UpgradeStatusReport" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="action" type="org.apache.hadoop.dfs.FSConstants.UpgradeAction"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="metaSave" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="pathname" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="reportChecksumFailure" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="in" type="org.apache.hadoop.fs.FSDataInputStream"/> + <param name="inPos" type="long"/> + <param name="sums" type="org.apache.hadoop.fs.FSDataInputStream"/> + <param name="sumsPos" type="long"/> + <doc> + <![CDATA[We need to find the blocks that didn't match. Likely only one + is corrupt but we will report both to the namenode. In the future, + we can consider figuring out exactly which block is corrupt.]]> + </doc> + </method> + <method name="getFileStatus" return="org.apache.hadoop.fs.FileStatus" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns the stat information about the file. + @throws FileNotFoundException if the file does not exist.]]> + </doc> + </method> + <method name="setPermission" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="p" type="org.apache.hadoop.fs.Path"/> + <param name="permission" type="org.apache.hadoop.fs.permission.FsPermission"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc }]]> + </doc> + </method> + <method name="setOwner" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="p" type="org.apache.hadoop.fs.Path"/> + <param name="username" type="java.lang.String"/> + <param name="groupname" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc }]]> + </doc> + </method> + <doc> + <![CDATA[Implementation of the abstract FileSystem for the DFS system. + This object is the way end-user code interacts with a Hadoop + DistributedFileSystem.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.DistributedFileSystem --> + <!-- start class org.apache.hadoop.dfs.DistributedFileSystem.DiskStatus --> + <class name="DistributedFileSystem.DiskStatus" extends="java.lang.Object" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="DistributedFileSystem.DiskStatus" type="long, long, long" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getCapacity" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getDfsUsed" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getRemaining" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + </class> + <!-- end class org.apache.hadoop.dfs.DistributedFileSystem.DiskStatus --> + <!-- start class org.apache.hadoop.dfs.FileDataServlet --> + <class name="FileDataServlet" extends="org.apache.hadoop.dfs.DfsServlet" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="FileDataServlet" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="doGet" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="request" type="javax.servlet.http.HttpServletRequest"/> + <param name="response" type="javax.servlet.http.HttpServletResponse"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Service a GET request as described below. + Request: + {@code + GET http://<nn>:<port>/data[/<path>] HTTP/1.1 + }]]> + </doc> + </method> + <doc> + <![CDATA[Redirect queries about the hosted filesystem to an appropriate datanode. + @see org.apache.hadoop.dfs.HftpFileSystem]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.FileDataServlet --> + <!-- start class org.apache.hadoop.dfs.FsckServlet --> + <class name="FsckServlet" extends="javax.servlet.http.HttpServlet" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="FsckServlet" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="doGet" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="request" type="javax.servlet.http.HttpServletRequest"/> + <param name="response" type="javax.servlet.http.HttpServletResponse"/> + <exception name="ServletException" type="javax.servlet.ServletException"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[This class is used in Namesystem's jetty to do fsck on namenode.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.FsckServlet --> + <!-- start interface org.apache.hadoop.dfs.FSConstants --> + <interface name="FSConstants" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <field name="MIN_BLOCKS_FOR_WRITE" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_ERROR" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_HEARTBEAT" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_BLOCKRECEIVED" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_BLOCKREPORT" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_TRANSFERDATA" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_OPEN" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_STARTFILE" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_ADDBLOCK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_RENAMETO" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_DELETE" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_COMPLETEFILE" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_LISTING" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_OBTAINLOCK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_RELEASELOCK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_EXISTS" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_ISDIR" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_MKDIRS" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_RENEW_LEASE" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_ABANDONBLOCK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_RAWSTATS" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_DATANODEREPORT" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_DATANODE_HINTS" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_ACK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_TRANSFERBLOCKS" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_INVALIDATE_BLOCKS" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_FAILURE" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_OPEN_ACK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_STARTFILE_ACK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_ADDBLOCK_ACK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_RENAMETO_ACK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_DELETE_ACK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_COMPLETEFILE_ACK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_TRYAGAIN" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_LISTING_ACK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_OBTAINLOCK_ACK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_RELEASELOCK_ACK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_EXISTS_ACK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_ISDIR_ACK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_MKDIRS_ACK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_RENEW_LEASE_ACK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_ABANDONBLOCK_ACK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_RAWSTATS_ACK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_DATANODEREPORT_ACK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_CLIENT_DATANODE_HINTS_ACK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_WRITE_BLOCK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_READ_BLOCK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_READ_METADATA" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_REPLACE_BLOCK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_COPY_BLOCK" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_STATUS_SUCCESS" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_STATUS_ERROR" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_STATUS_ERROR_CHECKSUM" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_STATUS_ERROR_INVALID" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_STATUS_ERROR_EXISTS" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="OP_STATUS_CHECKSUM_OK" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="DATA_TRANSFER_VERSION" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Version for data transfers between clients and datanodes + This should change when serialization of DatanodeInfo, not just + when protocol changes. It is not very obvious.]]> + </doc> + </field> + <field name="OPERATION_FAILED" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="STILL_WAITING" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="COMPLETE_SUCCESS" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="BLOCK_INVALIDATE_CHUNK" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="HEARTBEAT_INTERVAL" type="long" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="BLOCKREPORT_INTERVAL" type="long" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="BLOCKREPORT_INITIAL_DELAY" type="long" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="LEASE_SOFTLIMIT_PERIOD" type="long" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="LEASE_HARDLIMIT_PERIOD" type="long" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="READ_TIMEOUT" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="WRITE_TIMEOUT" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="WRITE_TIMEOUT_EXTENSION" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="MAX_PATH_LENGTH" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="MAX_PATH_DEPTH" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="BUFFER_SIZE" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="SMALL_BUFFER_SIZE" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="DEFAULT_BLOCK_SIZE" type="long" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="DEFAULT_DATA_SOCKET_SIZE" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="SIZE_OF_INTEGER" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="LAYOUT_VERSION" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[Some handy constants]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.dfs.FSConstants --> + <!-- start class org.apache.hadoop.dfs.FSConstants.CheckpointStates --> + <class name="FSConstants.CheckpointStates" extends="java.lang.Enum<org.apache.hadoop.dfs.FSConstants.CheckpointStates>" + abstract="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <method name="values" return="org.apache.hadoop.dfs.FSConstants.CheckpointStates[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="valueOf" return="org.apache.hadoop.dfs.FSConstants.CheckpointStates" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + </class> + <!-- end class org.apache.hadoop.dfs.FSConstants.CheckpointStates --> + <!-- start class org.apache.hadoop.dfs.FSConstants.DatanodeReportType --> + <class name="FSConstants.DatanodeReportType" extends="java.lang.Enum<org.apache.hadoop.dfs.FSConstants.DatanodeReportType>" + abstract="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <method name="values" return="org.apache.hadoop.dfs.FSConstants.DatanodeReportType[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="valueOf" return="org.apache.hadoop.dfs.FSConstants.DatanodeReportType" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + </class> + <!-- end class org.apache.hadoop.dfs.FSConstants.DatanodeReportType --> + <!-- start class org.apache.hadoop.dfs.FSConstants.NodeType --> + <class name="FSConstants.NodeType" extends="java.lang.Enum<org.apache.hadoop.dfs.FSConstants.NodeType>" + abstract="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <method name="values" return="org.apache.hadoop.dfs.FSConstants.NodeType[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="valueOf" return="org.apache.hadoop.dfs.FSConstants.NodeType" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + <doc> + <![CDATA[Type of the node]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.FSConstants.NodeType --> + <!-- start class org.apache.hadoop.dfs.FSConstants.SafeModeAction --> + <class name="FSConstants.SafeModeAction" extends="java.lang.Enum<org.apache.hadoop.dfs.FSConstants.SafeModeAction>" + abstract="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <method name="values" return="org.apache.hadoop.dfs.FSConstants.SafeModeAction[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="valueOf" return="org.apache.hadoop.dfs.FSConstants.SafeModeAction" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + </class> + <!-- end class org.apache.hadoop.dfs.FSConstants.SafeModeAction --> + <!-- start class org.apache.hadoop.dfs.FSConstants.StartupOption --> + <class name="FSConstants.StartupOption" extends="java.lang.Enum<org.apache.hadoop.dfs.FSConstants.StartupOption>" + abstract="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <method name="values" return="org.apache.hadoop.dfs.FSConstants.StartupOption[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="valueOf" return="org.apache.hadoop.dfs.FSConstants.StartupOption" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + </class> + <!-- end class org.apache.hadoop.dfs.FSConstants.StartupOption --> + <!-- start class org.apache.hadoop.dfs.FSConstants.UpgradeAction --> + <class name="FSConstants.UpgradeAction" extends="java.lang.Enum<org.apache.hadoop.dfs.FSConstants.UpgradeAction>" + abstract="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <method name="values" return="org.apache.hadoop.dfs.FSConstants.UpgradeAction[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="valueOf" return="org.apache.hadoop.dfs.FSConstants.UpgradeAction" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + <doc> + <![CDATA[Distributed upgrade actions: + + 1. Get upgrade status. + 2. Get detailed upgrade status. + 3. Proceed with the upgrade if it is stuck, no matter what the status is.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.FSConstants.UpgradeAction --> + <!-- start interface org.apache.hadoop.dfs.FSDatasetInterface --> + <interface name="FSDatasetInterface" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.dfs.datanode.metrics.FSDatasetMBean"/> + <method name="getMetaDataLength" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="org.apache.hadoop.dfs.Block"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns the length of the metadata file of the specified block + @param b - the block for which the metadata length is desired + @return the length of the metadata file for the specified block. + @throws IOException]]> + </doc> + </method> + <method name="getMetaDataInputStream" return="org.apache.hadoop.dfs.FSDatasetInterface.MetaDataInputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="org.apache.hadoop.dfs.Block"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns metaData of block b as an input stream (and its length) + @param b - the block + @return the metadata input stream; + @throws IOException]]> + </doc> + </method> + <method name="metaFileExists" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="org.apache.hadoop.dfs.Block"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Does the meta file exist for this block? + @param b - the block + @return true of the metafile for specified block exits + @throws IOException]]> + </doc> + </method> + <method name="getLength" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="org.apache.hadoop.dfs.Block"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns the specified block's on-disk length (excluding metadata) + @param b + @return the specified block's on-disk length (excluding metadta) + @throws IOException]]> + </doc> + </method> + <method name="getBlockInputStream" return="java.io.InputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="org.apache.hadoop.dfs.Block"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns an input stream to read the contents of the specified block + @param b + @return an input stream to read the contents of the specified block + @throws IOException]]> + </doc> + </method> + <method name="getBlockInputStream" return="java.io.InputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="org.apache.hadoop.dfs.Block"/> + <param name="seekOffset" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns an input stream at specified offset of the specified block + @param b + @param seekOffset + @return an input stream to read the contents of the specified block, + starting at the offset + @throws IOException]]> + </doc> + </method> + <method name="writeToBlock" return="org.apache.hadoop.dfs.FSDatasetInterface.BlockWriteStreams" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="org.apache.hadoop.dfs.Block"/> + <param name="isRecovery" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Creates the block and returns output streams to write data and CRC + @param b + @param isRecovery True if this is part of erro recovery, otherwise false + @return a BlockWriteStreams object to allow writing the block data + and CRC + @throws IOException]]> + </doc> + </method> + <method name="finalizeBlock" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="org.apache.hadoop.dfs.Block"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Finalizes the block previously opened for writing using writeToBlock. + The block size is what is in the parameter b and it must match the amount + of data written + @param b + @throws IOException]]> + </doc> + </method> + <method name="unfinalizeBlock" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="org.apache.hadoop.dfs.Block"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Unfinalizes the block previously opened for writing using writeToBlock. + The temporary file associated with this block is deleted. + @param b + @throws IOException]]> + </doc> + </method> + <method name="getBlockReport" return="org.apache.hadoop.dfs.Block[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the block report - the full list of blocks stored + @return - the block report - the full list of blocks stored]]> + </doc> + </method> + <method name="isValidBlock" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="org.apache.hadoop.dfs.Block"/> + <doc> + <![CDATA[Is the block valid? + @param b + @return - true if the specified block is valid]]> + </doc> + </method> + <method name="invalidate" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="invalidBlks" type="org.apache.hadoop.dfs.Block[]"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Invalidates the specified blocks + @param invalidBlks - the blocks to be invalidated + @throws IOException]]> + </doc> + </method> + <method name="checkDataDir" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="DiskChecker.DiskErrorException" type="org.apache.hadoop.util.DiskChecker.DiskErrorException"/> + <doc> + <![CDATA[Check if all the data directories are healthy + @throws DiskErrorException]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Stringifies the name of the storage]]> + </doc> + </method> + <method name="shutdown" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Shutdown the FSDataset]]> + </doc> + </method> + <method name="getChannelPosition" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="org.apache.hadoop.dfs.Block"/> + <param name="stream" type="org.apache.hadoop.dfs.FSDatasetInterface.BlockWriteStreams"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns the current offset in the data stream. + @param b + @param stream The stream to the data file and checksum file + @return the position of the file pointer in the data stream + @throws IOException]]> + </doc> + </method> + <method name="setChannelPosition" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="org.apache.hadoop.dfs.Block"/> + <param name="stream" type="org.apache.hadoop.dfs.FSDatasetInterface.BlockWriteStreams"/> + <param name="dataOffset" type="long"/> + <param name="ckOffset" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Sets the file pointer of the data stream and checksum stream to + the specified values. + @param b + @param stream The stream for the data file and checksum file + @param dataOffset The position to which the file pointre for the data stream + should be set + @param ckOffset The position to which the file pointre for the checksum stream + should be set + @throws IOException]]> + </doc> + </method> + <doc> + <![CDATA[This is an interface for the underlying storage that stores blocks for + a data node. + Examples are the FSDataset (which stores blocks on dirs) and + SimulatedFSDataset (which simulates data).]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.dfs.FSDatasetInterface --> + <!-- start class org.apache.hadoop.dfs.FSDatasetInterface.BlockWriteStreams --> + <class name="FSDatasetInterface.BlockWriteStreams" extends="java.lang.Object" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[This class contains the output streams for the data and checksum + of a block]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.FSDatasetInterface.BlockWriteStreams --> + <!-- start class org.apache.hadoop.dfs.FSDatasetInterface.MetaDataInputStream --> + <class name="FSDatasetInterface.MetaDataInputStream" extends="java.io.FilterInputStream" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <method name="getLength" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[This class provides the input stream and length of the metadata + of a block]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.FSDatasetInterface.MetaDataInputStream --> + <!-- start class org.apache.hadoop.dfs.GetImageServlet --> + <class name="GetImageServlet" extends="javax.servlet.http.HttpServlet" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="GetImageServlet" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="doGet" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="request" type="javax.servlet.http.HttpServletRequest"/> + <param name="response" type="javax.servlet.http.HttpServletResponse"/> + <exception name="ServletException" type="javax.servlet.ServletException"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[This class is used in Namesystem's jetty to retrieve a file. + Typically used by the Secondary NameNode to retrieve image and + edit file for periodic checkpointing.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.GetImageServlet --> + <!-- start class org.apache.hadoop.dfs.HftpFileSystem --> + <class name="HftpFileSystem" extends="org.apache.hadoop.fs.FileSystem" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="HftpFileSystem" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="initialize" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.net.URI"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getUri" return="java.net.URI" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="openConnection" return="java.net.HttpURLConnection" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="path" type="java.lang.String"/> + <param name="query" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Open an HTTP connection to the namenode to read file data and metadata. + @param path The path component of the URL + @param query The query component of the URL]]> + </doc> + </method> + <method name="open" return="org.apache.hadoop.fs.FSDataInputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="buffersize" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="listStatus" return="org.apache.hadoop.fs.FileStatus[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getFileStatus" return="org.apache.hadoop.fs.FileStatus" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getWorkingDirectory" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="setWorkingDirectory" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + </method> + <method name="create" return="org.apache.hadoop.fs.FSDataOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="permission" type="org.apache.hadoop.fs.permission.FsPermission"/> + <param name="overwrite" type="boolean"/> + <param name="bufferSize" type="int"/> + <param name="replication" type="short"/> + <param name="blockSize" type="long"/> + <param name="progress" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="rename" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="delete" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="delete" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="recursive" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="mkdirs" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="permission" type="org.apache.hadoop.fs.permission.FsPermission"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <field name="nnAddr" type="java.net.InetSocketAddress" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="ugi" type="org.apache.hadoop.security.UserGroupInformation" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="df" type="java.text.SimpleDateFormat" + transient="false" volatile="false" + static="true" final="true" visibility="protected" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[An implementation of a protocol for accessing filesystems over HTTP. + The following implementation provides a limited, read-only interface + to a filesystem over HTTP. + @see org.apache.hadoop.dfs.ListPathsServlet + @see org.apache.hadoop.dfs.FileDataServlet]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.HftpFileSystem --> + <!-- start class org.apache.hadoop.dfs.HsftpFileSystem --> + <class name="HsftpFileSystem" extends="org.apache.hadoop.dfs.HftpFileSystem" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="HsftpFileSystem" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="openConnection" return="java.net.HttpURLConnection" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="path" type="java.lang.String"/> + <param name="query" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getUri" return="java.net.URI" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[An implementation of a protocol for accessing filesystems over HTTPS. + The following implementation provides a limited, read-only interface + to a filesystem over HTTPS. + @see org.apache.hadoop.dfs.ListPathsServlet + @see org.apache.hadoop.dfs.FileDataServlet]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.HsftpFileSystem --> + <!-- start class org.apache.hadoop.dfs.JspHelper --> + <class name="JspHelper" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JspHelper" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="randomNode" return="org.apache.hadoop.dfs.DatanodeID" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="bestNode" return="org.apache.hadoop.dfs.DatanodeInfo" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="blk" type="org.apache.hadoop.dfs.LocatedBlock"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="streamBlockInAscii" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="addr" type="java.net.InetSocketAddress"/> + <param name="blockId" type="long"/> + <param name="blockSize" type="long"/> + <param name="offsetIntoBlock" type="long"/> + <param name="chunkSizeToView" type="long"/> + <param name="out" type="javax.servlet.jsp.JspWriter"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="DFSNodesStatus" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="live" type="java.util.ArrayList<org.apache.hadoop.dfs.DatanodeDescriptor>"/> + <param name="dead" type="java.util.ArrayList<org.apache.hadoop.dfs.DatanodeDescriptor>"/> + </method> + <method name="addTableHeader" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="javax.servlet.jsp.JspWriter"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="addTableRow" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="javax.servlet.jsp.JspWriter"/> + <param name="columns" type="java.lang.String[]"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="addTableRow" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="javax.servlet.jsp.JspWriter"/> + <param name="columns" type="java.lang.String[]"/> + <param name="row" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="addTableFooter" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="javax.servlet.jsp.JspWriter"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getSafeModeText" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getInodeLimitText" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getUpgradeStatusText" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="sortNodeList" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="nodes" type="java.util.ArrayList<org.apache.hadoop.dfs.DatanodeDescriptor>"/> + <param name="field" type="java.lang.String"/> + <param name="order" type="java.lang.String"/> + </method> + <method name="printPathWithLinks" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dir" type="java.lang.String"/> + <param name="out" type="javax.servlet.jsp.JspWriter"/> + <param name="namenodeInfoPort" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="printGotoForm" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="javax.servlet.jsp.JspWriter"/> + <param name="namenodeInfoPort" type="int"/> + <param name="file" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="createTitle" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="javax.servlet.jsp.JspWriter"/> + <param name="req" type="javax.servlet.http.HttpServletRequest"/> + <param name="file" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="percentageGraph" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="perc" type="int"/> + <param name="width" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="percentageGraph" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="perc" type="float"/> + <param name="width" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <field name="WEB_UGI_PROPERTY_NAME" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="conf" type="org.apache.hadoop.conf.Configuration" + transient="false" volatile="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="webUGI" type="org.apache.hadoop.security.UnixUserGroupInformation" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + </class> + <!-- end class org.apache.hadoop.dfs.JspHelper --> + <!-- start class org.apache.hadoop.dfs.LeaseExpiredException --> + <class name="LeaseExpiredException" extends="java.io.IOException" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="LeaseExpiredException" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <doc> + <![CDATA[The lease that was being used to create this file has expired.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.LeaseExpiredException --> + <!-- start class org.apache.hadoop.dfs.ListPathsServlet --> + <class name="ListPathsServlet" extends="org.apache.hadoop.dfs.DfsServlet" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="ListPathsServlet" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="buildRoot" return="java.util.Map<java.lang.String, java.lang.String>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="request" type="javax.servlet.http.HttpServletRequest"/> + <param name="doc" type="org.znerd.xmlenc.XMLOutputter"/> + <doc> + <![CDATA[Build a map from the query string, setting values and defaults.]]> + </doc> + </method> + <method name="doGet" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="request" type="javax.servlet.http.HttpServletRequest"/> + <param name="response" type="javax.servlet.http.HttpServletResponse"/> + <exception name="ServletException" type="javax.servlet.ServletException"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Service a GET request as described below. + Request: + {@code + GET http://<nn>:<port>/listPaths[/<path>][<?option>[&option]*] HTTP/1.1 + } + + Where <i>option</i> (default) in: + recursive ("no") + filter (".*") + exclude ("\..*\.crc") + + Response: A flat list of files/directories in the following format: + {@code + <listing path="..." recursive="(yes|no)" filter="..." + time="yyyy-MM-dd hh:mm:ss UTC" version="..."> + <directory path="..." modified="yyyy-MM-dd hh:mm:ss"/> + <file path="..." modified="yyyy-MM-dd'T'hh:mm:ssZ" blocksize="..." + replication="..." size="..."/> + </listing> + }]]> + </doc> + </method> + <doc> + <![CDATA[Obtain meta-information about a filesystem. + @see org.apache.hadoop.dfs.HftpFileSystem]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.ListPathsServlet --> + <!-- start class org.apache.hadoop.dfs.LocatedBlocks --> + <class name="LocatedBlocks" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <method name="getLocatedBlocks" return="java.util.List<org.apache.hadoop.dfs.LocatedBlock>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get located blocks.]]> + </doc> + </method> + <method name="get" return="org.apache.hadoop.dfs.LocatedBlock" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="index" type="int"/> + <doc> + <![CDATA[Get located block.]]> + </doc> + </method> + <method name="locatedBlockCount" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get number of located blocks.]]> + </doc> + </method> + <method name="getFileLength" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[Collection of blocks with their locations and the file length.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.LocatedBlocks --> + <!-- start class org.apache.hadoop.dfs.NameNode --> + <class name="NameNode" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.dfs.ClientProtocol"/> + <implements name="org.apache.hadoop.dfs.DatanodeProtocol"/> + <implements name="org.apache.hadoop.dfs.NamenodeProtocol"/> + <implements name="org.apache.hadoop.dfs.FSConstants"/> + <constructor name="NameNode" type="org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Start NameNode. + <p> + The name-node can be started with one of the following startup options: + <ul> + <li>{@link FSConstants.StartupOption#REGULAR REGULAR} - normal startup</li> + <li>{@link FSConstants.StartupOption#FORMAT FORMAT} - format name node</li> + <li>{@link FSConstants.StartupOption#UPGRADE UPGRADE} - start the cluster + upgrade and create a snapshot of the current file system state</li> + <li>{@link FSConstants.StartupOption#ROLLBACK ROLLBACK} - roll the + cluster back to the previous state</li> + </ul> + The option is passed via configuration field: + <tt>dfs.namenode.startup</tt> + + The conf will be modified to reflect the actual ports on which + the NameNode is up and running if the user passes the port as + <code>zero</code> in the conf. + + @param conf confirguration + @throws IOException]]> + </doc> + </constructor> + <constructor name="NameNode" type="java.lang.String, org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create a NameNode at the specified location and start it. + + The conf will be modified to reflect the actual ports on which + the NameNode is up and running if the user passes the port as + <code>zero</code>.]]> + </doc> + </constructor> + <method name="getProtocolVersion" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="protocol" type="java.lang.String"/> + <param name="clientVersion" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="format" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Format a new filesystem. Destroys any filesystem that may already + exist at this location.]]> + </doc> + </method> + <method name="getNameNodeMetrics" return="org.apache.hadoop.dfs.NameNodeMetrics" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="join" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Wait for service to finish. + (Normally, it runs forever.)]]> + </doc> + </method> + <method name="stop" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Stop all NameNode threads and wait for all to finish.]]> + </doc> + </method> + <method name="getBlocks" return="org.apache.hadoop.dfs.BlocksWithLocations" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="datanode" type="org.apache.hadoop.dfs.DatanodeInfo"/> + <param name="size" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[return a list of blocks & their locations on <code>datanode</code> whose + total size is <code>size</code> + + @param datanode on which blocks are located + @param size total size of blocks]]> + </doc> + </method> + <method name="getBlockLocations" return="org.apache.hadoop.dfs.LocatedBlocks" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="java.lang.String"/> + <param name="offset" type="long"/> + <param name="length" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="create" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="java.lang.String"/> + <param name="masked" type="org.apache.hadoop.fs.permission.FsPermission"/> + <param name="clientName" type="java.lang.String"/> + <param name="overwrite" type="boolean"/> + <param name="replication" type="short"/> + <param name="blockSize" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="setReplication" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="java.lang.String"/> + <param name="replication" type="short"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="setPermission" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="java.lang.String"/> + <param name="permissions" type="org.apache.hadoop.fs.permission.FsPermission"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="setOwner" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="java.lang.String"/> + <param name="username" type="java.lang.String"/> + <param name="groupname" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="addBlock" return="org.apache.hadoop.dfs.LocatedBlock" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="java.lang.String"/> + <param name="clientName" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="abandonBlock" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="org.apache.hadoop.dfs.Block"/> + <param name="src" type="java.lang.String"/> + <param name="holder" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[The client needs to give up on the block.]]> + </doc> + </method> + <method name="abandonFileInProgress" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="java.lang.String"/> + <param name="holder" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="complete" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="java.lang.String"/> + <param name="clientName" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="reportBadBlocks" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="blocks" type="org.apache.hadoop.dfs.LocatedBlock[]"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[The client has detected an error on the specified located blocks + and is reporting them to the server. For now, the namenode will + delete the blocks from the datanodes. In the future we might + check the blocks are actually corrupt.]]> + </doc> + </method> + <method name="getPreferredBlockSize" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="filename" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="rename" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="java.lang.String"/> + <param name="dst" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="delete" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="delete" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="java.lang.String"/> + <param name="recursive" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="exists" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="Use getFileInfo(String) instead"> + <param name="src" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[@deprecated Use getFileInfo(String) instead]]> + </doc> + </method> + <method name="mkdirs" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="java.lang.String"/> + <param name="masked" type="org.apache.hadoop.fs.permission.FsPermission"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="renewLease" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="clientName" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getListing" return="org.apache.hadoop.dfs.DFSFileInfo[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getFileInfo" return="org.apache.hadoop.dfs.DFSFileInfo" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get the file info for a specific file. + @param src The string representation of the path to the file + @throws IOException if permission to access file is denied by the system + @return object containing information regarding the file + or null if file not found]]> + </doc> + </method> + <method name="getStats" return="long[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getDatanodeReport" return="org.apache.hadoop.dfs.DatanodeInfo[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="type" type="org.apache.hadoop.dfs.FSConstants.DatanodeReportType"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="setSafeMode" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="action" type="org.apache.hadoop.dfs.FSConstants.SafeModeAction"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="isInSafeMode" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Is the cluster currently in safe mode?]]> + </doc> + </method> + <method name="refreshNodes" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getEditLogSize" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns the size of the current edit log.]]> + </doc> + </method> + <method name="rollEditLog" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Roll the edit log.]]> + </doc> + </method> + <method name="rollFsImage" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Roll the image]]> + </doc> + </method> + <method name="finalizeUpgrade" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="distributedUpgradeProgress" return="org.apache.hadoop.dfs.UpgradeStatusReport" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="action" type="org.apache.hadoop.dfs.FSConstants.UpgradeAction"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="metaSave" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="filename" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Dumps namenode state into specified file]]> + </doc> + </method> + <method name="getContentSummary" return="org.apache.hadoop.fs.ContentSummary" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="fsync" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="java.lang.String"/> + <param name="clientName" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="register" return="org.apache.hadoop.dfs.DatanodeRegistration" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="nodeReg" type="org.apache.hadoop.dfs.DatanodeRegistration"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="sendHeartbeat" return="org.apache.hadoop.dfs.DatanodeCommand" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="nodeReg" type="org.apache.hadoop.dfs.DatanodeRegistration"/> + <param name="capacity" type="long"/> + <param name="dfsUsed" type="long"/> + <param name="remaining" type="long"/> + <param name="xmitsInProgress" type="int"/> + <param name="xceiverCount" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Data node notify the name node that it is alive + Return a block-oriented command for the datanode to execute. + This will be either a transfer or a delete operation.]]> + </doc> + </method> + <method name="blockReport" return="org.apache.hadoop.dfs.DatanodeCommand" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="nodeReg" type="org.apache.hadoop.dfs.DatanodeRegistration"/> + <param name="blocks" type="long[]"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="blockReceived" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="nodeReg" type="org.apache.hadoop.dfs.DatanodeRegistration"/> + <param name="blocks" type="org.apache.hadoop.dfs.Block[]"/> + <param name="delHints" type="java.lang.String[]"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="errorReport" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="nodeReg" type="org.apache.hadoop.dfs.DatanodeRegistration"/> + <param name="errorCode" type="int"/> + <param name="msg" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="versionRequest" return="org.apache.hadoop.dfs.NamespaceInfo" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="processUpgradeCommand" return="org.apache.hadoop.dfs.UpgradeCommand" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="comm" type="org.apache.hadoop.dfs.UpgradeCommand"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="blockCrcUpgradeGetBlockLocations" return="org.apache.hadoop.dfs.BlockCrcInfo" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="block" type="org.apache.hadoop.dfs.Block"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="verifyRequest" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="nodeReg" type="org.apache.hadoop.dfs.DatanodeRegistration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Verify request. + + Verifies correctness of the datanode version, registration ID, and + if the datanode does not need to be shutdown. + + @param nodeReg data node registration + @throws IOException]]> + </doc> + </method> + <method name="verifyVersion" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="version" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Verify version. + + @param version + @throws IOException]]> + </doc> + </method> + <method name="getFsImageName" return="java.io.File" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns the name of the fsImage file]]> + </doc> + </method> + <method name="getFsImageNameCheckpoint" return="java.io.File[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns the name of the fsImage file uploaded by periodic + checkpointing]]> + </doc> + </method> + <method name="validateCheckpointUpload" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="token" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Validates that this is a valid checkpoint upload request]]> + </doc> + </method> + <method name="checkpointUploadDone" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Indicates that a new checkpoint has been successfully uploaded.]]> + </doc> + </method> + <method name="getFsEditName" return="java.io.File" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns the name of the edits file]]> + </doc> + </method> + <method name="getNameNodeAddress" return="java.net.InetSocketAddress" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the address on which the NameNodes is listening to. + @return the address on which the NameNodes is listening to.]]> + </doc> + </method> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="argv" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + </method> + <field name="LOG" type="org.apache.commons.logging.Log" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="stateChangeLog" type="org.apache.commons.logging.Log" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[NameNode serves as both directory namespace manager and + "inode table" for the Hadoop DFS. There is a single NameNode + running in any DFS deployment. (Well, except when there + is a second backup/failover NameNode.) + + The NameNode controls two critical tables: + 1) filename->blocksequence (namespace) + 2) block->machinelist ("inodes") + + The first table is stored on disk and is very precious. + The second table is rebuilt every time the NameNode comes + up. + + 'NameNode' refers to both this class as well as the 'NameNode server'. + The 'FSNamesystem' class actually performs most of the filesystem + management. The majority of the 'NameNode' class itself is concerned + with exposing the IPC interface to the outside world, plus some + configuration management. + + NameNode implements the ClientProtocol interface, which allows + clients to ask for DFS services. ClientProtocol is not + designed for direct use by authors of DFS client code. End-users + should instead use the org.apache.nutch.hadoop.fs.FileSystem class. + + NameNode also implements the DatanodeProtocol interface, used by + DataNode programs that actually store DFS data blocks. These + methods are invoked repeatedly and automatically by all the + DataNodes in a DFS deployment. + + NameNode also implements the NamenodeProtocol interface, used by + secondary namenodes or rebalancing processes to get partial namenode's + state, for example partial blocksMap etc.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.NameNode --> + <!-- start class org.apache.hadoop.dfs.NamenodeFsck --> + <class name="NamenodeFsck" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="NamenodeFsck" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.dfs.NameNode, java.util.Map<java.lang.String, java.lang.String[]>, javax.servlet.http.HttpServletResponse" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Filesystem checker. + @param conf configuration (namenode config) + @param nn namenode that this fsck is going to use + @param pmap key=value[] map that is passed to the http servlet as url parameters + @param response the object into which this servelet writes the url contents + @throws IOException]]> + </doc> + </constructor> + <method name="fsck" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Check files on DFS, starting from the indicated path. + @throws Exception]]> + </doc> + </method> + <method name="run" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + <doc> + <![CDATA[@param args]]> + </doc> + </method> + <field name="LOG" type="org.apache.commons.logging.Log" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="FIXING_NONE" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Don't attempt any fixing .]]> + </doc> + </field> + <field name="FIXING_MOVE" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Move corrupted files to /lost+found .]]> + </doc> + </field> + <field name="FIXING_DELETE" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Delete corrupted files.]]> + </doc> + </field> + <doc> + <![CDATA[This class provides rudimentary checking of DFS volumes for errors and + sub-optimal conditions. + <p>The tool scans all files and directories, starting from an indicated + root path. The following abnormal conditions are detected and handled:</p> + <ul> + <li>files with blocks that are completely missing from all datanodes.<br/> + In this case the tool can perform one of the following actions: + <ul> + <li>none ({@link #FIXING_NONE})</li> + <li>move corrupted files to /lost+found directory on DFS + ({@link #FIXING_MOVE}). Remaining data blocks are saved as a + block chains, representing longest consecutive series of valid blocks.</li> + <li>delete corrupted files ({@link #FIXING_DELETE})</li> + </ul> + </li> + <li>detect files with under-replicated or over-replicated blocks</li> + </ul> + Additionally, the tool collects a detailed overall DFS statistics, and + optionally can print detailed statistics on block locations and replication + factors of each file.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.NamenodeFsck --> + <!-- start class org.apache.hadoop.dfs.NamenodeFsck.FsckResult --> + <class name="NamenodeFsck.FsckResult" extends="java.lang.Object" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="NamenodeFsck.FsckResult" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="isHealthy" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[DFS is considered healthy if there are no missing blocks.]]> + </doc> + </method> + <method name="addMissing" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="id" type="java.lang.String"/> + <param name="size" type="long"/> + <doc> + <![CDATA[Add a missing block name, plus its size.]]> + </doc> + </method> + <method name="getMissingIds" return="java.util.ArrayList<java.lang.String>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return a list of missing block names (as list of Strings).]]> + </doc> + </method> + <method name="getMissingSize" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return total size of missing data, in bytes.]]> + </doc> + </method> + <method name="setMissingSize" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="missingSize" type="long"/> + </method> + <method name="getExcessiveReplicas" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the number of over-replicated blocks.]]> + </doc> + </method> + <method name="setExcessiveReplicas" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="overReplicatedBlocks" type="long"/> + </method> + <method name="getReplicationFactor" return="float" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the actual replication factor.]]> + </doc> + </method> + <method name="getMissingReplicas" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the number of under-replicated blocks. Note: missing blocks are not counted here.]]> + </doc> + </method> + <method name="setMissingReplicas" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="underReplicatedBlocks" type="long"/> + </method> + <method name="getTotalDirs" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return total number of directories encountered during this scan.]]> + </doc> + </method> + <method name="setTotalDirs" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="totalDirs" type="long"/> + </method> + <method name="getTotalFiles" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return total number of files encountered during this scan.]]> + </doc> + </method> + <method name="setTotalFiles" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="totalFiles" type="long"/> + </method> + <method name="getTotalSize" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return total size of scanned data, in bytes.]]> + </doc> + </method> + <method name="setTotalSize" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="totalSize" type="long"/> + </method> + <method name="getReplication" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the intended replication factor, against which the over/under- + replicated blocks are counted. Note: this values comes from the current + Configuration supplied for the tool, so it may be different from the + value in DFS Configuration.]]> + </doc> + </method> + <method name="setReplication" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="replication" type="int"/> + </method> + <method name="getTotalBlocks" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the total number of blocks in the scanned area.]]> + </doc> + </method> + <method name="setTotalBlocks" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="totalBlocks" type="long"/> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getCorruptFiles" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the number of currupted files.]]> + </doc> + </method> + <method name="setCorruptFiles" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="corruptFiles" type="long"/> + </method> + <doc> + <![CDATA[FsckResult of checking, plus overall DFS statistics.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.NamenodeFsck.FsckResult --> + <!-- start class org.apache.hadoop.dfs.NameNodeMetrics --> + <class name="NameNodeMetrics" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.metrics.Updater"/> + <method name="shutdown" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="doUpdates" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="unused" type="org.apache.hadoop.metrics.MetricsContext"/> + <doc> + <![CDATA[Since this object is a registered updater, this method will be called + periodically, e.g. every 5 seconds.]]> + </doc> + </method> + <method name="resetAllMinMax" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <field name="numFilesCreated" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingInt" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="numGetBlockLocations" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingInt" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="numFilesRenamed" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingInt" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="numFilesListed" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingInt" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="transactions" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingRate" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="syncs" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingRate" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="blockReport" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingRate" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="safeModeTime" type="org.apache.hadoop.metrics.util.MetricsIntValue" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="fsImageLoadTime" type="org.apache.hadoop.metrics.util.MetricsIntValue" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[This class is for maintaining the various NameNode statistics + and publishing them through the metrics interfaces. + This also registers the JMX MBean for RPC. + <p> + This class has a number of metrics variables that are publicly accessible; + these variables (objects) have methods to update their values; + for example: + <p> {@link #syncs}.inc()]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.NameNodeMetrics --> + <!-- start class org.apache.hadoop.dfs.NotReplicatedYetException --> + <class name="NotReplicatedYetException" extends="java.io.IOException" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="NotReplicatedYetException" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <doc> + <![CDATA[The file has not finished being written to enough datanodes yet.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.NotReplicatedYetException --> + <!-- start class org.apache.hadoop.dfs.SafeModeException --> + <class name="SafeModeException" extends="java.io.IOException" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="SafeModeException" type="java.lang.String, org.apache.hadoop.dfs.FSNamesystem.SafeModeInfo" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <doc> + <![CDATA[This exception is thrown when the name node is in safe mode. + Client cannot modified namespace until the safe mode is off.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.SafeModeException --> + <!-- start class org.apache.hadoop.dfs.SecondaryNameNode --> + <class name="SecondaryNameNode" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.dfs.FSConstants"/> + <implements name="java.lang.Runnable"/> + <constructor name="SecondaryNameNode" type="org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create a connection to the primary namenode.]]> + </doc> + </constructor> + <method name="shutdown" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Shut down this instance of the datanode. + Returns only after shutdown is complete.]]> + </doc> + </method> + <method name="run" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="argv" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + <doc> + <![CDATA[main() has some simple utility methods. + @param argv Command line parameters. + @exception Exception if the filesystem does not exist.]]> + </doc> + </method> + <field name="LOG" type="org.apache.commons.logging.Log" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[The Secondary NameNode is a helper to the primary NameNode. + The Secondary is responsible for supporting periodic checkpoints + of the HDFS metadata. The current design allows only one Secondary + NameNode per HDFs cluster. + + The Secondary NameNode is a daemon that periodically wakes + up (determined by the schedule specified in the configuration), + triggers a periodic checkpoint and then goes back to sleep. + The Secondary NameNode uses the ClientProtocol to talk to the + primary NameNode.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.SecondaryNameNode --> + <!-- start class org.apache.hadoop.dfs.SecondaryNameNode.GetImageServlet --> + <class name="SecondaryNameNode.GetImageServlet" extends="javax.servlet.http.HttpServlet" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="SecondaryNameNode.GetImageServlet" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="doGet" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="request" type="javax.servlet.http.HttpServletRequest"/> + <param name="response" type="javax.servlet.http.HttpServletResponse"/> + <exception name="ServletException" type="javax.servlet.ServletException"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[This class is used in Namesystem's jetty to retrieve a file. + Typically used by the Secondary NameNode to retrieve image and + edit file for periodic checkpointing.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.SecondaryNameNode.GetImageServlet --> + <!-- start class org.apache.hadoop.dfs.StreamFile --> + <class name="StreamFile" extends="org.apache.hadoop.dfs.DfsServlet" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="StreamFile" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="doGet" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="request" type="javax.servlet.http.HttpServletRequest"/> + <param name="response" type="javax.servlet.http.HttpServletResponse"/> + <exception name="ServletException" type="javax.servlet.ServletException"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + </class> + <!-- end class org.apache.hadoop.dfs.StreamFile --> + <!-- start interface org.apache.hadoop.dfs.Upgradeable --> + <interface name="Upgradeable" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="java.lang.Comparable<org.apache.hadoop.dfs.Upgradeable>"/> + <method name="getVersion" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the layout version of the upgrade object. + @return layout version]]> + </doc> + </method> + <method name="getType" return="org.apache.hadoop.dfs.FSConstants.NodeType" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the type of the software component, which this object is upgrading. + @return type]]> + </doc> + </method> + <method name="getDescription" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Description of the upgrade object for displaying. + @return description]]> + </doc> + </method> + <method name="getUpgradeStatus" return="short" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Upgrade status determines a percentage of the work done out of the total + amount required by the upgrade. + + 100% means that the upgrade is completed. + Any value < 100 means it is not complete. + + The return value should provide at least 2 values, e.g. 0 and 100. + @return integer value in the range [0, 100].]]> + </doc> + </method> + <method name="startUpgrade" return="org.apache.hadoop.dfs.UpgradeCommand" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Prepare for the upgrade. + E.g. initialize upgrade data structures and set status to 0. + + Returns an upgrade command that is used for broadcasting to other cluster + components. + E.g. name-node informs data-nodes that they must perform a distributed upgrade. + + @return an UpgradeCommand for broadcasting. + @throws IOException]]> + </doc> + </method> + <method name="completeUpgrade" return="org.apache.hadoop.dfs.UpgradeCommand" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Complete upgrade. + E.g. cleanup upgrade data structures or write metadata to disk. + + Returns an upgrade command that is used for broadcasting to other cluster + components. + E.g. data-nodes inform the name-node that they completed the upgrade + while other data-nodes are still upgrading. + + @throws IOException]]> + </doc> + </method> + <method name="getUpgradeStatusReport" return="org.apache.hadoop.dfs.UpgradeStatusReport" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="details" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get status report for the upgrade. + + @param details true if upgradeStatus details need to be included, + false otherwise + @return {@link UpgradeStatusReport} + @throws IOException]]> + </doc> + </method> + <doc> + <![CDATA[Common interface for distributed upgrade objects. + + Each upgrade object corresponds to a layout version, + which is the latest version that should be upgraded using this object. + That is all components whose layout version is greater or equal to the + one returned by {@link #getVersion()} must be upgraded with this object.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.dfs.Upgradeable --> + <!-- start class org.apache.hadoop.dfs.UpgradeStatusReport --> + <class name="UpgradeStatusReport" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <constructor name="UpgradeStatusReport" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="UpgradeStatusReport" type="int, short, boolean" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getVersion" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the layout version of the currently running upgrade. + @return layout version]]> + </doc> + </method> + <method name="getUpgradeStatus" return="short" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get upgrade upgradeStatus as a percentage of the total upgrade done. + + @see Upgradeable#getUpgradeStatus()]]> + </doc> + </method> + <method name="isFinalized" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Is current upgrade finalized. + @return true if finalized or false otherwise.]]> + </doc> + </method> + <method name="getStatusText" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="details" type="boolean"/> + <doc> + <![CDATA[Get upgradeStatus data as a text for reporting. + Should be overloaded for a particular upgrade specific upgradeStatus data. + + @param details true if upgradeStatus details need to be included, + false otherwise + @return text]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Print basic upgradeStatus details.]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <field name="version" type="int" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="upgradeStatus" type="short" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="finalized" type="boolean" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[Base upgrade upgradeStatus class. + Overload this class if specific status fields need to be reported. + + Describes status of current upgrade.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.UpgradeStatusReport --> + <doc> + <![CDATA[<p>A distributed implementation of {@link +org.apache.hadoop.fs.FileSystem}. This is loosely modelled after +Google's <a href="http://labs.google.com/papers/gfs.html">GFS</a>.</p> + +<p>The most important difference is that unlike GFS, Hadoop DFS files +have strictly one writer at any one time. Bytes are always appended +to the end of the writer's stream. There is no notion of "record appends" +or "mutations" that are then checked or reordered. Writers simply emit +a byte stream. That byte stream is guaranteed to be stored in the +order written.</p>]]> + </doc> +</package> +<package name="org.apache.hadoop.dfs.datanode.metrics"> + <!-- start class org.apache.hadoop.dfs.datanode.metrics.DataNodeMetrics --> + <class name="DataNodeMetrics" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.metrics.Updater"/> + <constructor name="DataNodeMetrics" type="org.apache.hadoop.conf.Configuration, java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="shutdown" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="doUpdates" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="unused" type="org.apache.hadoop.metrics.MetricsContext"/> + <doc> + <![CDATA[Since this object is a registered updater, this method will be called + periodically, e.g. every 5 seconds.]]> + </doc> + </method> + <method name="resetAllMinMax" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <field name="bytesWritten" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingInt" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="bytesRead" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingInt" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="blocksWritten" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingInt" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="blocksRead" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingInt" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="blocksReplicated" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingInt" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="blocksRemoved" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingInt" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="blocksVerified" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingInt" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="blockVerificationFailures" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingInt" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="readsFromLocalClient" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingInt" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="readsFromRemoteClient" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingInt" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="writesFromLocalClient" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingInt" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="writesFromRemoteClient" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingInt" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="readBlockOp" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingRate" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="writeBlockOp" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingRate" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="readMetadataOp" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingRate" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="copyBlockOp" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingRate" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="replaceBlockOp" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingRate" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="heartbeats" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingRate" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="blockReports" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingRate" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[This class is for maintaining the various DataNode statistics + and publishing them through the metrics interfaces. + This also registers the JMX MBean for RPC. + <p> + This class has a number of metrics variables that are publicly accessible; + these variables (objects) have methods to update their values; + for example: + <p> {@link #blocksRead}.inc()]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.datanode.metrics.DataNodeMetrics --> + <!-- start class org.apache.hadoop.dfs.datanode.metrics.DataNodeStatistics --> + <class name="DataNodeStatistics" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.dfs.datanode.metrics.DataNodeStatisticsMBean"/> + <method name="shutdown" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Shuts down the statistics + - unregisters the mbean]]> + </doc> + </method> + <method name="resetAllMinMax" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getBlocksRead" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getBlocksRemoved" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getBlocksReplicated" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getBlocksWritten" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getBytesRead" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getBlockVerificationFailures" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getBlocksVerified" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getReadsFromLocalClient" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getReadsFromRemoteClient" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getWritesFromLocalClient" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getWritesFromRemoteClient" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getReadBlockOpAverageTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getReadBlockOpMaxTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getReadBlockOpMinTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getReadBlockOpNum" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getReadMetadataOpAverageTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getReadMetadataOpMaxTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getReadMetadataOpMinTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getReadMetadataOpNum" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getReplaceBlockOpAverageTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getReplaceBlockOpMaxTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getReplaceBlockOpMinTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getReplaceBlockOpNum" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getWriteBlockOpAverageTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getWriteBlockOpMaxTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getWriteBlockOpMinTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getWriteBlockOpNum" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getCopyBlockOpAverageTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getCopyBlockOpMaxTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getCopyBlockOpMinTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getCopyBlockOpNum" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getBlockReportsAverageTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getBlockReportsMaxTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getBlockReportsMinTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getBlockReportsNum" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getHeartbeatsAverageTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getHeartbeatsMaxTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getHeartbeatsMinTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getHeartbeatsNum" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + </class> + <!-- end class org.apache.hadoop.dfs.datanode.metrics.DataNodeStatistics --> + <!-- start interface org.apache.hadoop.dfs.datanode.metrics.DataNodeStatisticsMBean --> + <interface name="DataNodeStatisticsMBean" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="getBytesRead" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of bytes read in the last interval + @return number of bytes read]]> + </doc> + </method> + <method name="getBlocksWritten" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of blocks written in the last interval + @return number of blocks written]]> + </doc> + </method> + <method name="getBlocksRead" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of blocks read in the last interval + @return number of blocks read]]> + </doc> + </method> + <method name="getBlocksReplicated" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of blocks replicated in the last interval + @return number of blocks replicated]]> + </doc> + </method> + <method name="getBlocksRemoved" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of blocks removed in the last interval + @return number of blocks removed]]> + </doc> + </method> + <method name="getBlocksVerified" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of blocks verified in the last interval + @return number of blocks verified]]> + </doc> + </method> + <method name="getBlockVerificationFailures" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of block verification failures in the last interval + @return number of block verification failures]]> + </doc> + </method> + <method name="getReadsFromLocalClient" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of reads from local clients in the last interval + @return number of reads from local clients]]> + </doc> + </method> + <method name="getReadsFromRemoteClient" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of reads from remote clients in the last interval + @return number of reads from remote clients]]> + </doc> + </method> + <method name="getWritesFromLocalClient" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of writes from local clients in the last interval + @return number of writes from local clients]]> + </doc> + </method> + <method name="getWritesFromRemoteClient" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of writes from remote clients in the last interval + @return number of writes from remote clients]]> + </doc> + </method> + <method name="getReadBlockOpNum" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of ReadBlock Operation in last interval + @return number of operations]]> + </doc> + </method> + <method name="getReadBlockOpAverageTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Average time for ReadBlock Operation in last interval + @return time in msec]]> + </doc> + </method> + <method name="getReadBlockOpMinTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Minimum ReadBlock Operation Time since reset was called + @return time in msec]]> + </doc> + </method> + <method name="getReadBlockOpMaxTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Maximum ReadBlock Operation Time since reset was called + @return time in msec]]> + </doc> + </method> + <method name="getWriteBlockOpNum" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of WriteBlock Operation in last interval + @return number of operations]]> + </doc> + </method> + <method name="getWriteBlockOpAverageTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Average time for WriteBlock Operation in last interval + @return time in msec]]> + </doc> + </method> + <method name="getWriteBlockOpMinTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Minimum WriteBlock Operation Time since reset was called + @return time in msec]]> + </doc> + </method> + <method name="getWriteBlockOpMaxTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Maximum WriteBlock Operation Time since reset was called + @return time in msec]]> + </doc> + </method> + <method name="getReadMetadataOpNum" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of ReadMetadata Operation in last interval + @return number of operations]]> + </doc> + </method> + <method name="getReadMetadataOpAverageTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Average time for ReadMetadata Operation in last interval + @return time in msec]]> + </doc> + </method> + <method name="getReadMetadataOpMinTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Minimum ReadMetadata Operation Time since reset was called + @return time in msec]]> + </doc> + </method> + <method name="getReadMetadataOpMaxTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Maximum ReadMetadata Operation Time since reset was called + @return time in msec]]> + </doc> + </method> + <method name="getCopyBlockOpNum" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of CopyBlock Operation in last interval + @return number of operations]]> + </doc> + </method> + <method name="getCopyBlockOpAverageTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Average time for CopyBlock Operation in last interval + @return time in msec]]> + </doc> + </method> + <method name="getCopyBlockOpMinTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Minimum CopyBlock Operation Time since reset was called + @return time in msec]]> + </doc> + </method> + <method name="getCopyBlockOpMaxTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Maximum CopyBlock Operation Time since reset was called + @return time in msec]]> + </doc> + </method> + <method name="getReplaceBlockOpNum" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of ReplaceBlock Operation in last interval + @return number of operations]]> + </doc> + </method> + <method name="getReplaceBlockOpAverageTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Average time for ReplaceBlock Operation in last interval + @return time in msec]]> + </doc> + </method> + <method name="getReplaceBlockOpMinTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Minimum ReplaceBlock Operation Time since reset was called + @return time in msec]]> + </doc> + </method> + <method name="getReplaceBlockOpMaxTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Maximum ReplaceBlock Operation Time since reset was called + @return time in msec]]> + </doc> + </method> + <method name="getBlockReportsNum" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of Block Reports sent in last interval + @return number of operations]]> + </doc> + </method> + <method name="getBlockReportsAverageTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Average time for Block Reports Operation in last interval + @return time in msec]]> + </doc> + </method> + <method name="getBlockReportsMinTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Minimum Block Reports Operation Time since reset was called + @return time in msec]]> + </doc> + </method> + <method name="getBlockReportsMaxTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Maximum Block Reports Operation Time since reset was called + @return time in msec]]> + </doc> + </method> + <method name="getHeartbeatsNum" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of Heartbeat Operation in last interval + @return number of operations]]> + </doc> + </method> + <method name="getHeartbeatsAverageTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Average time for Heartbeat Operation in last interval + @return time in msec]]> + </doc> + </method> + <method name="getHeartbeatsMinTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Minimum Heartbeat Operation Time since reset was called + @return time in msec]]> + </doc> + </method> + <method name="getHeartbeatsMaxTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Maximum Heartbeat Operation Time since reset was called + @return time in msec]]> + </doc> + </method> + <method name="resetAllMinMax" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Reset all min max times]]> + </doc> + </method> + <doc> + <![CDATA[This is the JMX interface for the runtime statistics for the data node. + Many of the statistics are sampled and averaged on an interval + which can be specified in the config file. + <p> + For the statistics that are sampled and averaged, one must specify + a metrics context that does periodic update calls. Most do. + The default Null metrics context however does NOT. So if you aren't + using any other metrics context then you can turn on the viewing and averaging + of sampled metrics by specifying the following two lines + in the hadoop-meterics.properties file: + <pre> + dfs.class=org.apache.hadoop.metrics.spi.NullContextWithUpdateThread + dfs.period=10 + </pre> +<p> + Note that the metrics are collected regardless of the context used. + The context with the update thread is used to average the data periodically. + <p> + Name Node Status info is reported in another MBean + @see org.apache.hadoop.dfs.datanode.metrics.FSDatasetMBean]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.dfs.datanode.metrics.DataNodeStatisticsMBean --> + <!-- start interface org.apache.hadoop.dfs.datanode.metrics.FSDatasetMBean --> + <interface name="FSDatasetMBean" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="getDfsUsed" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns the total space (in bytes) used by dfs datanode + @return the total space used by dfs datanode + @throws IOException]]> + </doc> + </method> + <method name="getCapacity" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns total capacity (in bytes) of storage (used and unused) + @return total capacity of storage (used and unused) + @throws IOException]]> + </doc> + </method> + <method name="getRemaining" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns the amount of free storage space (in bytes) + @return The amount of free storage space + @throws IOException]]> + </doc> + </method> + <method name="getStorageInfo" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the storage id of the underlying storage]]> + </doc> + </method> + <doc> + <![CDATA[This Interface defines the methods to get the status of a the FSDataset of + a data node. + It is also used for publishing via JMX (hence we follow the JMX naming + convention.) + <p> + Data Node runtime statistic info is report in another MBean + @see org.apache.hadoop.dfs.datanode.metrics.DataNodeStatisticsMBean]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.dfs.datanode.metrics.FSDatasetMBean --> +</package> +<package name="org.apache.hadoop.dfs.namenode.metrics"> + <!-- start interface org.apache.hadoop.dfs.namenode.metrics.FSNamesystemMBean --> + <interface name="FSNamesystemMBean" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="getFSState" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The state of the file system: Safemode or Operational + @return the state]]> + </doc> + </method> + <method name="getBlocksTotal" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of allocated blocks in the system + @return - number of allocated blocks]]> + </doc> + </method> + <method name="getCapacityTotal" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Total storage capacity + @return - total capacity in bytes]]> + </doc> + </method> + <method name="getCapacityRemaining" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Free (unused) storage capacity + @return - free capacity in bytes]]> + </doc> + </method> + <method name="getCapacityUsed" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Used storage capacity + @return - used capacity in bytes]]> + </doc> + </method> + <method name="getFilesTotal" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Total number of files and directories + @return - num of files and directories]]> + </doc> + </method> + <method name="numLiveDataNodes" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of Live data nodes + @return number of live data nodes]]> + </doc> + </method> + <method name="numDeadDataNodes" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of dead data nodes + @return number of dead data nodes]]> + </doc> + </method> + <doc> + <![CDATA[This Interface defines the methods to get the status of a the FSNamesystem of + a name node. + It is also used for publishing via JMX (hence we follow the JMX naming + convention.) + + <p> + Name Node runtime statistic info is report in another MBean + @see org.apache.hadoop.dfs.namenode.metrics.NameNodeStatisticsMBean]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.dfs.namenode.metrics.FSNamesystemMBean --> + <!-- start class org.apache.hadoop.dfs.namenode.metrics.NameNodeStatistics --> + <class name="NameNodeStatistics" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.dfs.namenode.metrics.NameNodeStatisticsMBean"/> + <constructor name="NameNodeStatistics" type="org.apache.hadoop.dfs.NameNodeMetrics" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[This constructs and registers the NameNodeStatisticsMBean + @param nameNodeMetrics - the metrics from which the mbean gets its info]]> + </doc> + </constructor> + <method name="shutdown" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Shuts down the statistics + - unregisters the mbean]]> + </doc> + </method> + <method name="getBlockReportAverageTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getBlockReportMaxTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getBlockReportMinTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getBlockReportNum" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getJournalTransactionAverageTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getJournalTransactionNum" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getJournalTransactionMaxTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getJournalTransactionMinTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getJournalSyncAverageTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getJournalSyncMaxTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getJournalSyncMinTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getJournalSyncNum" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getSafemodeTime" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getFSImageLoadTime" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="resetAllMinMax" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getNumFilesCreated" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getNumFilesListed" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getNumGetBlockLocations" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <method name="getNumFilesRenamed" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@inheritDoc]]> + </doc> + </method> + <doc> + <![CDATA[This is the implementation of the Name Node JMX MBean]]> + </doc> + </class> + <!-- end class org.apache.hadoop.dfs.namenode.metrics.NameNodeStatistics --> + <!-- start interface org.apache.hadoop.dfs.namenode.metrics.NameNodeStatisticsMBean --> + <interface name="NameNodeStatisticsMBean" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="getSafemodeTime" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The time spent in the Safemode at startup + @return time in msec]]> + </doc> + </method> + <method name="getFSImageLoadTime" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Time spent loading the FS Image at startup + @return time in msec]]> + </doc> + </method> + <method name="getJournalTransactionNum" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of Journal Transactions in the last interval + @return number of operations]]> + </doc> + </method> + <method name="getJournalTransactionAverageTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Average time for Journal transactions in last interval + @return time in msec]]> + </doc> + </method> + <method name="getJournalTransactionMinTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Minimum Journal Transaction Time since reset was called + @return time in msec]]> + </doc> + </method> + <method name="getJournalTransactionMaxTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Maximum Journal Transaction Time since reset was called + @return time in msec]]> + </doc> + </method> + <method name="getBlockReportNum" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of block Reports processed in the last interval + @return number of operations]]> + </doc> + </method> + <method name="getBlockReportAverageTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Average time for Block Report Processing in last interval + @return time in msec]]> + </doc> + </method> + <method name="getBlockReportMinTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Minimum Block Report Processing Time since reset was called + @return time in msec]]> + </doc> + </method> + <method name="getBlockReportMaxTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Maximum Block Report Processing Time since reset was called + @return time in msec]]> + </doc> + </method> + <method name="getJournalSyncNum" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of Journal Syncs in the last interval + @return number of operations]]> + </doc> + </method> + <method name="getJournalSyncAverageTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Average time for Journal Sync in last interval + @return time in msec]]> + </doc> + </method> + <method name="getJournalSyncMinTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Minimum Journal Sync Time since reset was called + @return time in msec]]> + </doc> + </method> + <method name="getJournalSyncMaxTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Maximum Journal Sync Time since reset was called + @return time in msec]]> + </doc> + </method> + <method name="resetAllMinMax" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Reset all min max times]]> + </doc> + </method> + <method name="getNumFilesCreated" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of files created in the last interval + @return number of operations]]> + </doc> + </method> + <method name="getNumGetBlockLocations" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of + {@link org.apache.hadoop.dfs.NameNode#getBlockLocations(String,long,long)} + @return number of operations]]> + </doc> + </method> + <method name="getNumFilesRenamed" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of files renamed in the last interval + @return number of operations]]> + </doc> + </method> + <method name="getNumFilesListed" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of files listed in the last interval + @return number of operations]]> + </doc> + </method> + <doc> + <![CDATA[This is the JMX management interface for getting runtime statistics of + the name node. + Many of the statistics are sampled and averaged on an interval + which can be specified in the config file. + <p> + For the statistics that are sampled and averaged, one must specify + a metrics context that does periodic update calls. Most do. + The default Null metrics context however does NOT. So if you aren't + using any other metrics context then you can turn on the viewing and averaging + of sampled metrics by specifying the following two lines + in the hadoop-meterics.properties file: + <pre> + dfs.class=org.apache.hadoop.metrics.spi.NullContextWithUpdateThread + dfs.period=10 + </pre> +<p> + Note that the metrics are collected regardless of the context used. + The context with the update thread is used to average the data periodically. + <p> + Name Node Status info is report in another MBean + @see org.apache.hadoop.dfs.namenode.metrics.FSNamesystemMBean]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.dfs.namenode.metrics.NameNodeStatisticsMBean --> +</package> +<package name="org.apache.hadoop.filecache"> + <!-- start class org.apache.hadoop.filecache.DistributedCache --> + <class name="DistributedCache" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="DistributedCache" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getLocalCache" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="cache" type="java.net.URI"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="baseDir" type="org.apache.hadoop.fs.Path"/> + <param name="fileStatus" type="org.apache.hadoop.fs.FileStatus"/> + <param name="isArchive" type="boolean"/> + <param name="confFileStamp" type="long"/> + <param name="currentWorkDir" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get the locally cached file or archive; it could either be + previously cached (and valid) or copy it from the {@link FileSystem} now. + + @param cache the cache to be localized, this should be specified as + new URI(hdfs://hostname:port/absolute_path_to_file#LINKNAME). If no schema + or hostname:port is provided the file is assumed to be in the filesystem + being used in the Configuration + @param conf The Confguration file which contains the filesystem + @param baseDir The base cache Dir where you wnat to localize the files/archives + @param fileStatus The file status on the dfs. + @param isArchive if the cache is an archive or a file. In case it is an archive + with a .zip or .jar extension it will be unzipped/unjarred automatically + and the directory where the archive is unjarred is returned as the Path. + In case of a file, the path to the file is returned + @param confFileStamp this is the hdfs file modification timestamp to verify that the + file to be cached hasn't changed since the job started + @param currentWorkDir this is the directory where you would want to create symlinks + for the locally cached files/archives + @return the path to directory where the archives are unjarred in case of archives, + the path to the file where the file is copied locally + @throws IOException]]> + </doc> + </method> + <method name="getLocalCache" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="cache" type="java.net.URI"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="baseDir" type="org.apache.hadoop.fs.Path"/> + <param name="isArchive" type="boolean"/> + <param name="confFileStamp" type="long"/> + <param name="currentWorkDir" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get the locally cached file or archive; it could either be + previously cached (and valid) or copy it from the {@link FileSystem} now. + + @param cache the cache to be localized, this should be specified as + new URI(hdfs://hostname:port/absolute_path_to_file#LINKNAME). If no schema + or hostname:port is provided the file is assumed to be in the filesystem + being used in the Configuration + @param conf The Confguration file which contains the filesystem + @param baseDir The base cache Dir where you wnat to localize the files/archives + @param isArchive if the cache is an archive or a file. In case it is an archive + with a .zip or .jar extension it will be unzipped/unjarred automatically + and the directory where the archive is unjarred is returned as the Path. + In case of a file, the path to the file is returned + @param confFileStamp this is the hdfs file modification timestamp to verify that the + file to be cached hasn't changed since the job started + @param currentWorkDir this is the directory where you would want to create symlinks + for the locally cached files/archives + @return the path to directory where the archives are unjarred in case of archives, + the path to the file where the file is copied locally + @throws IOException]]> + </doc> + </method> + <method name="releaseCache" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="cache" type="java.net.URI"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[This is the opposite of getlocalcache. When you are done with + using the cache, you need to release the cache + @param cache The cache URI to be released + @param conf configuration which contains the filesystem the cache + is contained in. + @throws IOException]]> + </doc> + </method> + <method name="makeRelative" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="cache" type="java.net.URI"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getTimestamp" return="long" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="cache" type="java.net.URI"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns mtime of a given cache file on hdfs. + @param conf configuration + @param cache cache file + @return mtime of a given cache file on hdfs + @throws IOException]]> + </doc> + </method> + <method name="createAllSymlink" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="jobCacheDir" type="java.io.File"/> + <param name="workDir" type="java.io.File"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[This method create symlinks for all files in a given dir in another directory + @param conf the configuration + @param jobCacheDir the target directory for creating symlinks + @param workDir the directory in which the symlinks are created + @throws IOException]]> + </doc> + </method> + <method name="setCacheArchives" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="archives" type="java.net.URI[]"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[Set the configuration with the given set of archives + @param archives The list of archives that need to be localized + @param conf Configuration which will be changed]]> + </doc> + </method> + <method name="setCacheFiles" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="files" type="java.net.URI[]"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[Set the configuration with the given set of files + @param files The list of files that need to be localized + @param conf Configuration which will be changed]]> + </doc> + </method> + <method name="getCacheArchives" return="java.net.URI[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get cache archives set in the Configuration + @param conf The configuration which contains the archives + @return A URI array of the caches set in the Configuration + @throws IOException]]> + </doc> + </method> + <method name="getCacheFiles" return="java.net.URI[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get cache files set in the Configuration + @param conf The configuration which contains the files + @return A URI array of the files set in the Configuration + @throws IOException]]> + </doc> + </method> + <method name="getLocalCacheArchives" return="org.apache.hadoop.fs.Path[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return the path array of the localized caches + @param conf Configuration that contains the localized archives + @return A path array of localized caches + @throws IOException]]> + </doc> + </method> + <method name="getLocalCacheFiles" return="org.apache.hadoop.fs.Path[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return the path array of the localized files + @param conf Configuration that contains the localized files + @return A path array of localized files + @throws IOException]]> + </doc> + </method> + <method name="getArchiveTimestamps" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[Get the timestamps of the archives + @param conf The configuration which stored the timestamps + @return a string array of timestamps + @throws IOException]]> + </doc> + </method> + <method name="getFileTimestamps" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[Get the timestamps of the files + @param conf The configuration which stored the timestamps + @return a string array of timestamps + @throws IOException]]> + </doc> + </method> + <method name="setArchiveTimestamps" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="timestamps" type="java.lang.String"/> + <doc> + <![CDATA[This is to check the timestamp of the archives to be localized + @param conf Configuration which stores the timestamp's + @param timestamps comma separated list of timestamps of archives. + The order should be the same as the order in which the archives are added.]]> + </doc> + </method> + <method name="setFileTimestamps" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="timestamps" type="java.lang.String"/> + <doc> + <![CDATA[This is to check the timestamp of the files to be localized + @param conf Configuration which stores the timestamp's + @param timestamps comma separated list of timestamps of files. + The order should be the same as the order in which the files are added.]]> + </doc> + </method> + <method name="setLocalArchives" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="str" type="java.lang.String"/> + <doc> + <![CDATA[Set the conf to contain the location for localized archives + @param conf The conf to modify to contain the localized caches + @param str a comma separated list of local archives]]> + </doc> + </method> + <method name="setLocalFiles" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="str" type="java.lang.String"/> + <doc> + <![CDATA[Set the conf to contain the location for localized files + @param conf The conf to modify to contain the localized caches + @param str a comma separated list of local files]]> + </doc> + </method> + <method name="addCacheArchive" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="uri" type="java.net.URI"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[Add a archives to be localized to the conf + @param uri The uri of the cache to be localized + @param conf Configuration to add the cache to]]> + </doc> + </method> + <method name="addCacheFile" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="uri" type="java.net.URI"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[Add a file to be localized to the conf + @param uri The uri of the cache to be localized + @param conf Configuration to add the cache to]]> + </doc> + </method> + <method name="addFileToClassPath" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="file" type="org.apache.hadoop.fs.Path"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Add an file path to the current set of classpath entries It adds the file + to cache as well. + + @param file Path of the file to be added + @param conf Configuration that contains the classpath setting]]> + </doc> + </method> + <method name="getFileClassPaths" return="org.apache.hadoop.fs.Path[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[Get the file entries in classpath as an array of Path + + @param conf Configuration that contains the classpath setting]]> + </doc> + </method> + <method name="addArchiveToClassPath" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="archive" type="org.apache.hadoop.fs.Path"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Add an archive path to the current set of classpath entries. It adds the + archive to cache as well. + + @param archive Path of the archive to be added + @param conf Configuration that contains the classpath setting]]> + </doc> + </method> + <method name="getArchiveClassPaths" return="org.apache.hadoop.fs.Path[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[Get the archive entries in classpath as an array of Path + + @param conf Configuration that contains the classpath setting]]> + </doc> + </method> + <method name="createSymlink" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[This method allows you to create symlinks in the current working directory + of the task to all the cache files/archives + @param conf the jobconf]]> + </doc> + </method> + <method name="getSymlink" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[This method checks to see if symlinks are to be create for the + localized cache files in the current working directory + @param conf the jobconf + @return true if symlinks are to be created- else return false]]> + </doc> + </method> + <method name="checkURIs" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="uriFiles" type="java.net.URI[]"/> + <param name="uriArchives" type="java.net.URI[]"/> + <doc> + <![CDATA[This method checks if there is a conflict in the fragment names + of the uris. Also makes sure that each uri has a fragment. It + is only to be called if you want to create symlinks for + the various archives and files. + @param uriFiles The uri array of urifiles + @param uriArchives the uri array of uri archives]]> + </doc> + </method> + <method name="purgeCache" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Clear the entire contents of the cache and delete the backing files. This + should only be used when the server is reinitializing, because the users + are going to lose their files.]]> + </doc> + </method> + <doc> + <![CDATA[Distribute application-specific large, read-only files efficiently. + + <p><code>DistributedCache</code> is a facility provided by the Map-Reduce + framework to cache files (text, archives, jars etc.) needed by applications. + </p> + + <p>Applications specify the files, via urls (hdfs:// or http://) to be cached + via the {@link JobConf}. The <code>DistributedCache</code> assumes that the + files specified via hdfs:// urls are already present on the + {@link FileSystem} at the path specified by the url.</p> + + <p>The framework will copy the necessary files on to the slave node before + any tasks for the job are executed on that node. Its efficiency stems from + the fact that the files are only copied once per job and the ability to + cache archives which are un-archived on the slaves.</p> + + <p><code>DistributedCache</code> can be used to distribute simple, read-only + data/text files and/or more complex types such as archives, jars etc. + Archives (zip files) are un-archived at the slave nodes. Jars maybe be + optionally added to the classpath of the tasks, a rudimentary software + distribution mechanism. Files have execution permissions. Optionally users + can also direct it to symlink the distributed cache file(s) into + the working directory of the task.</p> + + <p><code>DistributedCache</code> tracks modification timestamps of the cache + files. Clearly the cache files should not be modified by the application + or externally while the job is executing.</p> + + <p>Here is an illustrative example on how to use the + <code>DistributedCache</code>:</p> + <p><blockquote><pre> + // Setting up the cache for the application + + 1. Copy the requisite files to the <code>FileSystem</code>: + + $ bin/hadoop fs -copyFromLocal lookup.dat /myapp/lookup.dat + $ bin/hadoop fs -copyFromLocal map.zip /myapp/map.zip + $ bin/hadoop fs -copyFromLocal mylib.jar /myapp/mylib.jar + + 2. Setup the application's <code>JobConf</code>: + + JobConf job = new JobConf(); + DistributedCache.addCacheFile(new URI("/myapp/lookup.dat#lookup.dat"), + job); + DistributedCache.addCacheArchive(new URI("/myapp/map.zip", job); + DistributedCache.addFileToClassPath(new Path("/myapp/mylib.jar"), job); + + 3. Use the cached files in the {@link Mapper} or {@link Reducer}: + + public static class MapClass extends MapReduceBase + implements Mapper<K, V, K, V> { + + private Path[] localArchives; + private Path[] localFiles; + + public void configure(JobConf job) { + // Get the cached archives/files + localArchives = DistributedCache.getLocalCacheArchives(job); + localFiles = DistributedCache.getLocalCacheFiles(job); + } + + public void map(K key, V value, + OutputCollector<K, V> output, Reporter reporter) + throws IOException { + // Use data from the cached archives/files here + // ... + // ... + output.collect(k, v); + } + } + + </pre></blockquote></p> + + @see JobConf + @see JobClient]]> + </doc> + </class> + <!-- end class org.apache.hadoop.filecache.DistributedCache --> +</package> +<package name="org.apache.hadoop.fs"> + <!-- start class org.apache.hadoop.fs.BlockLocation --> + <class name="BlockLocation" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <constructor name="BlockLocation" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Default Constructor]]> + </doc> + </constructor> + <constructor name="BlockLocation" type="java.lang.String[], java.lang.String[], long, long" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Constructor with host, name, offset and length]]> + </doc> + </constructor> + <method name="getHosts" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get the list of hosts (hostname) hosting this block]]> + </doc> + </method> + <method name="getNames" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get the list of names (hostname:port) hosting this block]]> + </doc> + </method> + <method name="getOffset" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the start offset of file associated with this block]]> + </doc> + </method> + <method name="getLength" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the length of the block]]> + </doc> + </method> + <method name="setOffset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="offset" type="long"/> + <doc> + <![CDATA[Set the start offset of file associated with this block]]> + </doc> + </method> + <method name="setLength" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="length" type="long"/> + <doc> + <![CDATA[Set the length of block]]> + </doc> + </method> + <method name="setHosts" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="hosts" type="java.lang.String[]"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Set the hosts hosting this block]]> + </doc> + </method> + <method name="setNames" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="names" type="java.lang.String[]"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Set the names (host:port) hosting this block]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Implement write of Writable]]> + </doc> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Implement readFields of Writable]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + </class> + <!-- end class org.apache.hadoop.fs.BlockLocation --> + <!-- start class org.apache.hadoop.fs.BufferedFSInputStream --> + <class name="BufferedFSInputStream" extends="java.io.BufferedInputStream" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.fs.Seekable"/> + <implements name="org.apache.hadoop.fs.PositionedReadable"/> + <constructor name="BufferedFSInputStream" type="org.apache.hadoop.fs.FSInputStream, int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a <code>BufferedFSInputStream</code> + with the specified buffer size, + and saves its argument, the input stream + <code>in</code>, for later use. An internal + buffer array of length <code>size</code> + is created and stored in <code>buf</code>. + + @param in the underlying input stream. + @param size the buffer size. + @exception IllegalArgumentException if size <= 0.]]> + </doc> + </constructor> + <method name="getPos" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="skip" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="n" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="seek" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="pos" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="seekToNewSource" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="targetPos" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="read" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="position" type="long"/> + <param name="buffer" type="byte[]"/> + <param name="offset" type="int"/> + <param name="length" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFully" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="position" type="long"/> + <param name="buffer" type="byte[]"/> + <param name="offset" type="int"/> + <param name="length" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFully" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="position" type="long"/> + <param name="buffer" type="byte[]"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[A class optimizes reading from FSInputStream by bufferring]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.BufferedFSInputStream --> + <!-- start class org.apache.hadoop.fs.ChecksumException --> + <class name="ChecksumException" extends="java.io.IOException" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="ChecksumException" type="java.lang.String, long" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getPos" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[Thrown for checksum errors.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.ChecksumException --> + <!-- start class org.apache.hadoop.fs.ChecksumFileSystem --> + <class name="ChecksumFileSystem" extends="org.apache.hadoop.fs.FilterFileSystem" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="ChecksumFileSystem" type="org.apache.hadoop.fs.FileSystem" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getApproxChkSumLength" return="double" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="size" type="long"/> + </method> + <method name="setConf" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + </method> + <method name="getRawFileSystem" return="org.apache.hadoop.fs.FileSystem" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[get the raw file system]]> + </doc> + </method> + <method name="getChecksumFile" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="file" type="org.apache.hadoop.fs.Path"/> + <doc> + <![CDATA[Return the name of the checksum file associated with a file.]]> + </doc> + </method> + <method name="isChecksumFile" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="file" type="org.apache.hadoop.fs.Path"/> + <doc> + <![CDATA[Return true iff file is a checksum file name.]]> + </doc> + </method> + <method name="getChecksumFileLength" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="file" type="org.apache.hadoop.fs.Path"/> + <param name="fileSize" type="long"/> + <doc> + <![CDATA[Return the length of the checksum file given the size of the + actual file.]]> + </doc> + </method> + <method name="getBytesPerSum" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the bytes Per Checksum]]> + </doc> + </method> + <method name="open" return="org.apache.hadoop.fs.FSDataInputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="bufferSize" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Opens an FSDataInputStream at the indicated Path. + @param f the file name to open + @param bufferSize the size of the buffer to be used.]]> + </doc> + </method> + <method name="getChecksumLength" return="long" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="size" type="long"/> + <param name="bytesPerSum" type="int"/> + <doc> + <![CDATA[Calculated the length of the checksum file in bytes. + @param size the length of the data file in bytes + @param bytesPerSum the number of bytes in a checksum block + @return the number of bytes in the checksum file]]> + </doc> + </method> + <method name="create" return="org.apache.hadoop.fs.FSDataOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="overwrite" type="boolean"/> + <param name="bufferSize" type="int"/> + <param name="replication" type="short"/> + <param name="blockSize" type="long"/> + <param name="progress" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Opens an FSDataOutputStream at the indicated Path with write-progress + reporting. + @param f the file name to open + @param overwrite if a file with this name already exists, then if true, + the file will be overwritten, and if false an error will be thrown. + @param bufferSize the size of the buffer to be used. + @param replication required block replication for the file.]]> + </doc> + </method> + <method name="setReplication" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="replication" type="short"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Set replication for an existing file. + Implement the abstract <tt>setReplication</tt> of <tt>FileSystem</tt> + @param src file name + @param replication new replication + @throws IOException + @return true if successful; + false if file does not exist or is a directory]]> + </doc> + </method> + <method name="rename" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Rename files/dirs]]> + </doc> + </method> + <method name="delete" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="recursive" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Implement the delete(Path, boolean) in checksum + file system.]]> + </doc> + </method> + <method name="listStatus" return="org.apache.hadoop.fs.FileStatus[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[List the statuses of the files/directories in the given path if the path is + a directory. + + @param f + given path + @return the statuses of the files/directories in the given patch + @throws IOException]]> + </doc> + </method> + <method name="mkdirs" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="copyFromLocalFile" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="delSrc" type="boolean"/> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="copyToLocalFile" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="delSrc" type="boolean"/> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[The src file is under FS, and the dst is on the local disk. + Copy it from FS control to the local dst name.]]> + </doc> + </method> + <method name="copyToLocalFile" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <param name="copyCrc" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[The src file is under FS, and the dst is on the local disk. + Copy it from FS control to the local dst name. + If src and dst are directories, the copyCrc parameter + determines whether to copy CRC files.]]> + </doc> + </method> + <method name="startLocalOutput" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fsOutputFile" type="org.apache.hadoop.fs.Path"/> + <param name="tmpLocalFile" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="completeLocalOutput" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fsOutputFile" type="org.apache.hadoop.fs.Path"/> + <param name="tmpLocalFile" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="reportChecksumFailure" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="in" type="org.apache.hadoop.fs.FSDataInputStream"/> + <param name="inPos" type="long"/> + <param name="sums" type="org.apache.hadoop.fs.FSDataInputStream"/> + <param name="sumsPos" type="long"/> + <doc> + <![CDATA[Report a checksum error to the file system. + @param f the file name containing the error + @param in the stream open on the file + @param inPos the position of the beginning of the bad data in the file + @param sums the stream open on the checksum file + @param sumsPos the position of the beginning of the bad data in the checksum file + @return if retry is neccessary]]> + </doc> + </method> + <doc> + <![CDATA[Abstract Checksumed FileSystem. + It provide a basice implementation of a Checksumed FileSystem, + which creates a checksum file for each raw file. + It generates & verifies checksums at the client side.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.ChecksumFileSystem --> + <!-- start class org.apache.hadoop.fs.ContentSummary --> + <class name="ContentSummary" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <constructor name="ContentSummary" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Constructor]]> + </doc> + </constructor> + <constructor name="ContentSummary" type="long, long, long" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Constructor]]> + </doc> + </constructor> + <method name="getLength" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the length]]> + </doc> + </method> + <method name="getDirectoryCount" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the directory count]]> + </doc> + </method> + <method name="getFileCount" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the file count]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <doc> + <![CDATA[Store the summary of a content (a directory or a file).]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.ContentSummary --> + <!-- start class org.apache.hadoop.fs.DF --> + <class name="DF" extends="org.apache.hadoop.util.Shell" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="DF" type="java.io.File, org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </constructor> + <constructor name="DF" type="java.io.File, long" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </constructor> + <method name="getDirPath" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getFilesystem" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getCapacity" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getUsed" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getAvailable" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getPercentUsed" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getMount" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getExecString" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </method> + <method name="parseExecResult" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="lines" type="java.io.BufferedReader"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + </method> + <field name="DF_INTERVAL_DEFAULT" type="long" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[Filesystem disk space usage statistics. Uses the unix 'df' program. + Tested on Linux, FreeBSD, Cygwin.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.DF --> + <!-- start class org.apache.hadoop.fs.DU --> + <class name="DU" extends="org.apache.hadoop.util.Shell" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="DU" type="java.io.File, long" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </constructor> + <constructor name="DU" type="java.io.File, org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </constructor> + <method name="decDfsUsed" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="value" type="long"/> + </method> + <method name="incDfsUsed" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="value" type="long"/> + </method> + <method name="getUsed" return="long" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getDirPath" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getExecString" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </method> + <method name="parseExecResult" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="lines" type="java.io.BufferedReader"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + </method> + <doc> + <![CDATA[Filesystem disk space usage statistics. Uses the unix 'du' program]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.DU --> + <!-- start class org.apache.hadoop.fs.FileStatus --> + <class name="FileStatus" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <implements name="java.lang.Comparable"/> + <constructor name="FileStatus" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="FileStatus" type="long, boolean, int, long, long, org.apache.hadoop.fs.Path" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="FileStatus" type="long, boolean, int, long, long, org.apache.hadoop.fs.permission.FsPermission, java.lang.String, java.lang.String, org.apache.hadoop.fs.Path" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getLen" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="isDir" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Is this a directory? + @return true if this is a directory]]> + </doc> + </method> + <method name="getBlockSize" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the block size of the file. + @return the number of bytes]]> + </doc> + </method> + <method name="getReplication" return="short" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the replication factor of a file. + @return the replication factor of a file.]]> + </doc> + </method> + <method name="getModificationTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the modification time of the file. + @return the modification time of file in milliseconds since January 1, 1970 UTC.]]> + </doc> + </method> + <method name="getPermission" return="org.apache.hadoop.fs.permission.FsPermission" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get FsPermission associated with the file. + @return permssion. If a filesystem does not have a notion of permissions + or if permissions could not be determined, then default + permissions equivalent of "rwxrwxrwx" is returned.]]> + </doc> + </method> + <method name="getOwner" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the owner of the file. + @return owner of the file. The string could be empty if there is no + notion of owner of a file in a filesystem or if it could not + be determined (rare).]]> + </doc> + </method> + <method name="getGroup" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the group associated with the file. + @return group for the file. The string could be empty if there is no + notion of group of a file in a filesystem or if it could not + be determined (rare).]]> + </doc> + </method> + <method name="getPath" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="setPermission" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="permission" type="org.apache.hadoop.fs.permission.FsPermission"/> + <doc> + <![CDATA[Sets permission. + @param permission if permission is null, default value is set]]> + </doc> + </method> + <method name="setOwner" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="owner" type="java.lang.String"/> + <doc> + <![CDATA[Sets owner. + @param owner if it is null, default value is set]]> + </doc> + </method> + <method name="setGroup" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="group" type="java.lang.String"/> + <doc> + <![CDATA[Sets group. + @param group if it is null, default value is set]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="compareTo" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + <doc> + <![CDATA[Compare this object to another object + + @param o the object to be compared. + @return a negative integer, zero, or a positive integer as this object + is less than, equal to, or greater than the specified object. + + @throws ClassCastException if the specified object's is not of + type FileStatus]]> + </doc> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + <doc> + <![CDATA[Compare if this object is equal to another object + @param o the object to be compared. + @return true if two file status has the same path name; false if not.]]> + </doc> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns a hash code value for the object, which is defined as + the hash code of the path name. + + @return a hash code value for the path name.]]> + </doc> + </method> + <doc> + <![CDATA[Interface that represents the client side information for a file.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.FileStatus --> + <!-- start class org.apache.hadoop.fs.FileSystem --> + <class name="FileSystem" extends="org.apache.hadoop.conf.Configured" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="java.io.Closeable"/> + <constructor name="FileSystem" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </constructor> + <method name="parseArgs" return="org.apache.hadoop.fs.FileSystem" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="argv" type="java.lang.String[]"/> + <param name="i" type="int"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Parse the cmd-line args, starting at i. Remove consumed args + from array. We expect param in the form: + '-local | -dfs <namenode:port>']]> + </doc> + </method> + <method name="get" return="org.apache.hadoop.fs.FileSystem" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns the configured filesystem implementation.]]> + </doc> + </method> + <method name="getDefaultUri" return="java.net.URI" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[Get the default filesystem URI from a configuration. + @param conf the configuration to access + @return the uri of the default filesystem]]> + </doc> + </method> + <method name="setDefaultUri" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="uri" type="java.net.URI"/> + <doc> + <![CDATA[Set the default filesystem URI in a configuration. + @param conf the configuration to alter + @param uri the new default filesystem uri]]> + </doc> + </method> + <method name="setDefaultUri" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="uri" type="java.lang.String"/> + <doc> + <![CDATA[Set the default filesystem URI in a configuration. + @param conf the configuration to alter + @param uri the new default filesystem uri]]> + </doc> + </method> + <method name="initialize" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.net.URI"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Called after a new FileSystem instance is constructed. + @param name a uri whose authority section names the host, port, etc. + for this FileSystem + @param conf the configuration]]> + </doc> + </method> + <method name="getUri" return="java.net.URI" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns a URI whose scheme and authority identify this FileSystem.]]> + </doc> + </method> + <method name="getName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="call #getUri() instead."> + <doc> + <![CDATA[@deprecated call #getUri() instead.]]> + </doc> + </method> + <method name="getNamed" return="org.apache.hadoop.fs.FileSystem" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="call #get(URI,Configuration) instead."> + <param name="name" type="java.lang.String"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[@deprecated call #get(URI,Configuration) instead.]]> + </doc> + </method> + <method name="getLocal" return="org.apache.hadoop.fs.LocalFileSystem" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get the local file syste + @param conf the configuration to configure the file system with + @return a LocalFileSystem]]> + </doc> + </method> + <method name="get" return="org.apache.hadoop.fs.FileSystem" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="uri" type="java.net.URI"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns the FileSystem for this URI's scheme and authority. The scheme + of the URI determines a configuration property name, + <tt>fs.<i>scheme</i>.class</tt> whose value names the FileSystem class. + The entire URI is passed to the FileSystem instance's initialize method.]]> + </doc> + </method> + <method name="closeAll" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Close all cached filesystems. Be sure those filesystems are not + used anymore. + + @throws IOException]]> + </doc> + </method> + <method name="makeQualified" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <doc> + <![CDATA[Make sure that a path specifies a FileSystem.]]> + </doc> + </method> + <method name="create" return="org.apache.hadoop.fs.FSDataOutputStream" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <param name="file" type="org.apache.hadoop.fs.Path"/> + <param name="permission" type="org.apache.hadoop.fs.permission.FsPermission"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[create a file with the provided permission + The permission of the file is set to be the provided permission as in + setPermission, not permission&~umask + + It is implemented using two RPCs. It is understood that it is inefficient, + but the implementation is thread-safe. The other option is to change the + value of umask in configuration to be 0, but it is not thread-safe. + + @param fs file system handle + @param file the name of the file to be created + @param permission the permission of the file + @return an output stream + @throws IOException]]> + </doc> + </method> + <method name="mkdirs" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <param name="dir" type="org.apache.hadoop.fs.Path"/> + <param name="permission" type="org.apache.hadoop.fs.permission.FsPermission"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[create a directory with the provided permission + The permission of the directory is set to be the provided permission as in + setPermission, not permission&~umask + + @see #create(FileSystem, Path, FsPermission) + + @param fs file system handle + @param dir the name of the directory to be created + @param permission the permission of the directory + @return true if the directory creation succeeds; false otherwise + @throws IOException]]> + </doc> + </method> + <method name="checkPath" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <doc> + <![CDATA[Check that a Path belongs to this FileSystem.]]> + </doc> + </method> + <method name="getFileCacheHints" return="java.lang.String[][]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="Use getFileBlockLocations() instead + + Return a 2D array of size 1x1 or greater, containing hostnames + where portions of the given file can be found. For a nonexistent + file or regions, null will be returned. + + This call is most helpful with DFS, where it returns + hostnames of machines that contain the given file. + + The FileSystem will simply return an elt containing 'localhost'."> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="start" type="long"/> + <param name="len" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[@deprecated Use getFileBlockLocations() instead + + Return a 2D array of size 1x1 or greater, containing hostnames + where portions of the given file can be found. For a nonexistent + file or regions, null will be returned. + + This call is most helpful with DFS, where it returns + hostnames of machines that contain the given file. + + The FileSystem will simply return an elt containing 'localhost'.]]> + </doc> + </method> + <method name="getFileBlockLocations" return="org.apache.hadoop.fs.BlockLocation[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="start" type="long"/> + <param name="len" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return an array containing hostnames, offset and size of + portions of the given file. For a nonexistent + file or regions, null will be returned. + + This call is most helpful with DFS, where it returns + hostnames of machines that contain the given file. + + The FileSystem will simply return an elt containing 'localhost'.]]> + </doc> + </method> + <method name="open" return="org.apache.hadoop.fs.FSDataInputStream" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="bufferSize" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Opens an FSDataInputStream at the indicated Path. + @param f the file name to open + @param bufferSize the size of the buffer to be used.]]> + </doc> + </method> + <method name="open" return="org.apache.hadoop.fs.FSDataInputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Opens an FSDataInputStream at the indicated Path. + @param f the file to open]]> + </doc> + </method> + <method name="create" return="org.apache.hadoop.fs.FSDataOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Opens an FSDataOutputStream at the indicated Path. + Files are overwritten by default.]]> + </doc> + </method> + <method name="create" return="org.apache.hadoop.fs.FSDataOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="overwrite" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Opens an FSDataOutputStream at the indicated Path.]]> + </doc> + </method> + <method name="create" return="org.apache.hadoop.fs.FSDataOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="progress" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create an FSDataOutputStream at the indicated Path with write-progress + reporting. + Files are overwritten by default.]]> + </doc> + </method> + <method name="create" return="org.apache.hadoop.fs.FSDataOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="replication" type="short"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Opens an FSDataOutputStream at the indicated Path. + Files are overwritten by default.]]> + </doc> + </method> + <method name="create" return="org.apache.hadoop.fs.FSDataOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="replication" type="short"/> + <param name="progress" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Opens an FSDataOutputStream at the indicated Path with write-progress + reporting. + Files are overwritten by default.]]> + </doc> + </method> + <method name="create" return="org.apache.hadoop.fs.FSDataOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="overwrite" type="boolean"/> + <param name="bufferSize" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Opens an FSDataOutputStream at the indicated Path. + @param f the file name to open + @param overwrite if a file with this name already exists, then if true, + the file will be overwritten, and if false an error will be thrown. + @param bufferSize the size of the buffer to be used.]]> + </doc> + </method> + <method name="create" return="org.apache.hadoop.fs.FSDataOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="overwrite" type="boolean"/> + <param name="bufferSize" type="int"/> + <param name="progress" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Opens an FSDataOutputStream at the indicated Path with write-progress + reporting. + @param f the file name to open + @param overwrite if a file with this name already exists, then if true, + the file will be overwritten, and if false an error will be thrown. + @param bufferSize the size of the buffer to be used.]]> + </doc> + </method> + <method name="create" return="org.apache.hadoop.fs.FSDataOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="overwrite" type="boolean"/> + <param name="bufferSize" type="int"/> + <param name="replication" type="short"/> + <param name="blockSize" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Opens an FSDataOutputStream at the indicated Path. + @param f the file name to open + @param overwrite if a file with this name already exists, then if true, + the file will be overwritten, and if false an error will be thrown. + @param bufferSize the size of the buffer to be used. + @param replication required block replication for the file.]]> + </doc> + </method> + <method name="create" return="org.apache.hadoop.fs.FSDataOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="overwrite" type="boolean"/> + <param name="bufferSize" type="int"/> + <param name="replication" type="short"/> + <param name="blockSize" type="long"/> + <param name="progress" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Opens an FSDataOutputStream at the indicated Path with write-progress + reporting. + @param f the file name to open + @param overwrite if a file with this name already exists, then if true, + the file will be overwritten, and if false an error will be thrown. + @param bufferSize the size of the buffer to be used. + @param replication required block replication for the file.]]> + </doc> + </method> + <method name="create" return="org.apache.hadoop.fs.FSDataOutputStream" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="permission" type="org.apache.hadoop.fs.permission.FsPermission"/> + <param name="overwrite" type="boolean"/> + <param name="bufferSize" type="int"/> + <param name="replication" type="short"/> + <param name="blockSize" type="long"/> + <param name="progress" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Opens an FSDataOutputStream at the indicated Path with write-progress + reporting. + @param f the file name to open + @param permission + @param overwrite if a file with this name already exists, then if true, + the file will be overwritten, and if false an error will be thrown. + @param bufferSize the size of the buffer to be used. + @param replication required block replication for the file. + @param blockSize + @param progress + @throws IOException + @see #setPermission(Path, FsPermission)]]> + </doc> + </method> + <method name="createNewFile" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Creates the given Path as a brand-new zero-length file. If + create fails, or if it already existed, return false.]]> + </doc> + </method> + <method name="getReplication" return="short" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="Use getFileStatus() instead"> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get replication. + + @deprecated Use getFileStatus() instead + @param src file name + @return file replication + @throws IOException]]> + </doc> + </method> + <method name="setReplication" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="replication" type="short"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Set replication for an existing file. + + @param src file name + @param replication new replication + @throws IOException + @return true if successful; + false if file does not exist or is a directory]]> + </doc> + </method> + <method name="rename" return="boolean" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Renames Path src to Path dst. Can take place on local fs + or remote DFS.]]> + </doc> + </method> + <method name="delete" return="boolean" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="Use delete(Path, boolean) instead"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[@deprecated Use delete(Path, boolean) instead]]> + </doc> + </method> + <method name="delete" return="boolean" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="recursive" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Delete a file. + + @param f the path to delete. + @param recursive if path is a directory and set to + true, the directory is deleted else throws an exception. In + case of a file the recursive can be set to either true or false. + @return true if delete is successful else false. + @throws IOException]]> + </doc> + </method> + <method name="exists" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Check if exists. + @param f source file]]> + </doc> + </method> + <method name="isDirectory" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="Use getFileStatus() instead"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[@deprecated Use getFileStatus() instead]]> + </doc> + </method> + <method name="isFile" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[True iff the named path is a regular file.]]> + </doc> + </method> + <method name="getLength" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="Use getFileStatus() instead"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[@deprecated Use getFileStatus() instead]]> + </doc> + </method> + <method name="getContentLength" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="Use {@link #getContentSummary(Path)}."> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return the number of bytes of the given path + If <i>f</i> is a file, return the size of the file; + If <i>f</i> is a directory, return the size of the directory tree + @deprecated Use {@link #getContentSummary(Path)}.]]> + </doc> + </method> + <method name="getContentSummary" return="org.apache.hadoop.fs.ContentSummary" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return the {@link ContentSummary} of a given {@link Path}.]]> + </doc> + </method> + <method name="listStatus" return="org.apache.hadoop.fs.FileStatus[]" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[List the statuses of the files/directories in the given path if the path is + a directory. + + @param f + given path + @return the statuses of the files/directories in the given patch + @throws IOException]]> + </doc> + </method> + <method name="listStatus" return="org.apache.hadoop.fs.FileStatus[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="filter" type="org.apache.hadoop.fs.PathFilter"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Filter files/directories in the given path using the user-supplied path + filter. + + @param f + a path name + @param filter + the user-supplied path filter + @return an array of FileStatus objects for the files under the given path + after applying the filter + @throws IOException + if encounter any problem while fetching the status]]> + </doc> + </method> + <method name="listStatus" return="org.apache.hadoop.fs.FileStatus[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="files" type="org.apache.hadoop.fs.Path[]"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Filter files/directories in the given list of paths using default + path filter. + + @param files + a list of paths + @return a list of statuses for the files under the given paths after + applying the filter default Path filter + @exception IOException]]> + </doc> + </method> + <method name="listStatus" return="org.apache.hadoop.fs.FileStatus[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="files" type="org.apache.hadoop.fs.Path[]"/> + <param name="filter" type="org.apache.hadoop.fs.PathFilter"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Filter files/directories in the given list of paths using user-supplied + path filter. + + @param files + a list of paths + @param filter + the user-supplied path filter + @return a list of statuses for the files under the given paths after + applying the filter + @exception IOException]]> + </doc> + </method> + <method name="globStatus" return="org.apache.hadoop.fs.FileStatus[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="pathPattern" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[<p>Return all the files that match filePattern and are not checksum + files. Results are sorted by their names. + + <p> + A filename pattern is composed of <i>regular</i> characters and + <i>special pattern matching</i> characters, which are: + + <dl> + <dd> + <dl> + <p> + <dt> <tt> ? </tt> + <dd> Matches any single character. + + <p> + <dt> <tt> * </tt> + <dd> Matches zero or more characters. + + <p> + <dt> <tt> [<i>abc</i>] </tt> + <dd> Matches a single character from character set + <tt>{<i>a,b,c</i>}</tt>. + + <p> + <dt> <tt> [<i>a</i>-<i>b</i>] </tt> + <dd> Matches a single character from the character range + <tt>{<i>a...b</i>}</tt>. Note that character <tt><i>a</i></tt> must be + lexicographically less than or equal to character <tt><i>b</i></tt>. + + <p> + <dt> <tt> [^<i>a</i>] </tt> + <dd> Matches a single character that is not from character set or range + <tt>{<i>a</i>}</tt>. Note that the <tt>^</tt> character must occur + immediately to the right of the opening bracket. + + <p> + <dt> <tt> \<i>c</i> </tt> + <dd> Removes (escapes) any special meaning of character <i>c</i>. + + <p> + <dt> <tt> {ab,cd} </tt> + <dd> Matches a string from the string set <tt>{<i>ab, cd</i>} </tt> + + <p> + <dt> <tt> {ab,c{de,fh}} </tt> + <dd> Matches a string from the string set <tt>{<i>ab, cde, cfh</i>}</tt> + + </dl> + </dd> + </dl> + + @param pathPattern a regular expression specifying a pth pattern + + @return an array of paths that match the path pattern + @throws IOException]]> + </doc> + </method> + <method name="globStatus" return="org.apache.hadoop.fs.FileStatus[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="pathPattern" type="org.apache.hadoop.fs.Path"/> + <param name="filter" type="org.apache.hadoop.fs.PathFilter"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return an array of FileStatus objects whose path names match pathPattern + and is accepted by the user-supplied path filter. Results are sorted by + their path names. + Return null if pathPattern has no glob and the path does not exist. + Return an empty array if pathPattern has a glob and no path matches it. + + @param pathPattern + a regular expression specifying the path pattern + @param filter + a user-supplied path filter + @return an array of FileStatus objects + @throws IOException if any I/O error occurs when fetching file status]]> + </doc> + </method> + <method name="getHomeDirectory" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the current user's home directory in this filesystem. + The default implementation returns "/user/$USER/".]]> + </doc> + </method> + <method name="setWorkingDirectory" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="new_dir" type="org.apache.hadoop.fs.Path"/> + <doc> + <![CDATA[Set the current working directory for the given file system. All relative + paths will be resolved relative to it. + + @param new_dir]]> + </doc> + </method> + <method name="getWorkingDirectory" return="org.apache.hadoop.fs.Path" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the current working directory for the given file system + @return the directory pathname]]> + </doc> + </method> + <method name="mkdirs" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Call {@link #mkdirs(Path, FsPermission)} with default permission.]]> + </doc> + </method> + <method name="mkdirs" return="boolean" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="permission" type="org.apache.hadoop.fs.permission.FsPermission"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Make the given file and all non-existent parents into + directories. Has the semantics of Unix 'mkdir -p'. + Existence of the directory hierarchy is not an error.]]> + </doc> + </method> + <method name="copyFromLocalFile" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[The src file is on the local disk. Add it to FS at + the given dst name and the source is kept intact afterwards]]> + </doc> + </method> + <method name="moveFromLocalFile" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="srcs" type="org.apache.hadoop.fs.Path[]"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[The src files is on the local disk. Add it to FS at + the given dst name, removing the source afterwards.]]> + </doc> + </method> + <method name="moveFromLocalFile" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[The src file is on the local disk. Add it to FS at + the given dst name, removing the source afterwards.]]> + </doc> + </method> + <method name="copyFromLocalFile" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="delSrc" type="boolean"/> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[The src file is on the local disk. Add it to FS at + the given dst name. + delSrc indicates if the source should be removed]]> + </doc> + </method> + <method name="copyFromLocalFile" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="delSrc" type="boolean"/> + <param name="overwrite" type="boolean"/> + <param name="srcs" type="org.apache.hadoop.fs.Path[]"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[The src files are on the local disk. Add it to FS at + the given dst name. + delSrc indicates if the source should be removed]]> + </doc> + </method> + <method name="copyFromLocalFile" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="delSrc" type="boolean"/> + <param name="overwrite" type="boolean"/> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[The src file is on the local disk. Add it to FS at + the given dst name. + delSrc indicates if the source should be removed]]> + </doc> + </method> + <method name="copyToLocalFile" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[The src file is under FS, and the dst is on the local disk. + Copy it from FS control to the local dst name.]]> + </doc> + </method> + <method name="moveToLocalFile" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[The src file is under FS, and the dst is on the local disk. + Copy it from FS control to the local dst name. + Remove the source afterwards]]> + </doc> + </method> + <method name="copyToLocalFile" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="delSrc" type="boolean"/> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[The src file is under FS, and the dst is on the local disk. + Copy it from FS control to the local dst name. + delSrc indicates if the src will be removed or not.]]> + </doc> + </method> + <method name="startLocalOutput" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fsOutputFile" type="org.apache.hadoop.fs.Path"/> + <param name="tmpLocalFile" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns a local File that the user can write output to. The caller + provides both the eventual FS target name and the local working + file. If the FS is local, we write directly into the target. If + the FS is remote, we write into the tmp local area.]]> + </doc> + </method> + <method name="completeLocalOutput" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fsOutputFile" type="org.apache.hadoop.fs.Path"/> + <param name="tmpLocalFile" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Called when we're all done writing to the target. A local FS will + do nothing, because we've written to exactly the right place. A remote + FS will copy the contents of tmpLocalFile to the correct target at + fsOutputFile.]]> + </doc> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[No more filesystem operations are needed. Will + release any held locks.]]> + </doc> + </method> + <method name="getUsed" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return the total size of all files in the filesystem.]]> + </doc> + </method> + <method name="getBlockSize" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="Use getFileStatus() instead"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[@deprecated Use getFileStatus() instead]]> + </doc> + </method> + <method name="getDefaultBlockSize" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the number of bytes that large input files should be optimally + be split into to minimize i/o time.]]> + </doc> + </method> + <method name="getDefaultReplication" return="short" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the default replication.]]> + </doc> + </method> + <method name="getFileStatus" return="org.apache.hadoop.fs.FileStatus" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return a file status object that represents the path. + @param f The path we want information from + @return a FileStatus object + @throws FileNotFoundException when the path does not exist; + IOException see specific implementation]]> + </doc> + </method> + <method name="setPermission" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="p" type="org.apache.hadoop.fs.Path"/> + <param name="permission" type="org.apache.hadoop.fs.permission.FsPermission"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Set permission of a path. + @param p + @param permission]]> + </doc> + </method> + <method name="setOwner" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="p" type="org.apache.hadoop.fs.Path"/> + <param name="username" type="java.lang.String"/> + <param name="groupname" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Set owner of a path (i.e. a file or a directory). + The parameters username and groupname cannot both be null. + @param p The path + @param username If it is null, the original username remains unchanged. + @param groupname If it is null, the original groupname remains unchanged.]]> + </doc> + </method> + <method name="getStatistics" return="org.apache.hadoop.fs.FileSystem.Statistics" + abstract="false" native="false" synchronized="true" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="cls" type="java.lang.Class<? extends org.apache.hadoop.fs.FileSystem>"/> + <doc> + <![CDATA[Get the statistics for a particular file system + @param cls the class to lookup + @return a statistics object]]> + </doc> + </method> + <method name="printStatistics" + abstract="false" native="false" synchronized="true" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <field name="LOG" type="org.apache.commons.logging.Log" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="statistics" type="org.apache.hadoop.fs.FileSystem.Statistics" + transient="false" volatile="false" + static="false" final="true" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[The statistics for this file system.]]> + </doc> + </field> + <doc> + <![CDATA[An abstract base class for a fairly generic filesystem. It + may be implemented as a distributed filesystem, or as a "local" + one that reflects the locally-connected disk. The local version + exists for small Hadoop instances and for testing. + + <p> + + All user code that may potentially use the Hadoop Distributed + File System should be written to use a FileSystem object. The + Hadoop DFS is a multi-machine system that appears as a single + disk. It's useful because of its fault tolerance and potentially + very large capacity. + + <p> + The local implementation is {@link LocalFileSystem} and distributed + implementation is {@link DistributedFileSystem}.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.FileSystem --> + <!-- start class org.apache.hadoop.fs.FileSystem.Statistics --> + <class name="FileSystem.Statistics" extends="java.lang.Object" + abstract="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <constructor name="FileSystem.Statistics" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="incrementBytesRead" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="newBytes" type="long"/> + <doc> + <![CDATA[Increment the bytes read in the statistics + @param newBytes the additional bytes read]]> + </doc> + </method> + <method name="incrementBytesWritten" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="newBytes" type="long"/> + <doc> + <![CDATA[Increment the bytes written in the statistics + @param newBytes the additional bytes written]]> + </doc> + </method> + <method name="getBytesRead" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the total number of bytes read + @return the number of bytes]]> + </doc> + </method> + <method name="getBytesWritten" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the total number of bytes written + @return the number of bytes]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + </class> + <!-- end class org.apache.hadoop.fs.FileSystem.Statistics --> + <!-- start class org.apache.hadoop.fs.FileUtil --> + <class name="FileUtil" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="FileUtil" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="stat2Paths" return="org.apache.hadoop.fs.Path[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="stats" type="org.apache.hadoop.fs.FileStatus[]"/> + <doc> + <![CDATA[convert an array of FileStatus to an array of Path + + @param stats + an array of FileStatus objects + @return an array of paths corresponding to the input]]> + </doc> + </method> + <method name="stat2Paths" return="org.apache.hadoop.fs.Path[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="stats" type="org.apache.hadoop.fs.FileStatus[]"/> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <doc> + <![CDATA[convert an array of FileStatus to an array of Path. + If stats if null, return path + @param stats + an array of FileStatus objects + @param path + default path to return in stats is null + @return an array of paths corresponding to the input]]> + </doc> + </method> + <method name="fullyDelete" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dir" type="java.io.File"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Delete a directory and all its contents. If + we return false, the directory may be partially-deleted.]]> + </doc> + </method> + <method name="fullyDelete" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <param name="dir" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Recursively delete a directory. + + @param fs {@link FileSystem} on which the path is present + @param dir directory to recursively delete + @throws IOException]]> + </doc> + </method> + <method name="copy" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="srcFS" type="org.apache.hadoop.fs.FileSystem"/> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dstFS" type="org.apache.hadoop.fs.FileSystem"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <param name="deleteSource" type="boolean"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Copy files between FileSystems.]]> + </doc> + </method> + <method name="copy" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="srcFS" type="org.apache.hadoop.fs.FileSystem"/> + <param name="srcs" type="org.apache.hadoop.fs.Path[]"/> + <param name="dstFS" type="org.apache.hadoop.fs.FileSystem"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <param name="deleteSource" type="boolean"/> + <param name="overwrite" type="boolean"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="copy" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="srcFS" type="org.apache.hadoop.fs.FileSystem"/> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dstFS" type="org.apache.hadoop.fs.FileSystem"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <param name="deleteSource" type="boolean"/> + <param name="overwrite" type="boolean"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Copy files between FileSystems.]]> + </doc> + </method> + <method name="copyMerge" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="srcFS" type="org.apache.hadoop.fs.FileSystem"/> + <param name="srcDir" type="org.apache.hadoop.fs.Path"/> + <param name="dstFS" type="org.apache.hadoop.fs.FileSystem"/> + <param name="dstFile" type="org.apache.hadoop.fs.Path"/> + <param name="deleteSource" type="boolean"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="addString" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Copy all files in a directory to one output file (merge).]]> + </doc> + </method> + <method name="copy" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="java.io.File"/> + <param name="dstFS" type="org.apache.hadoop.fs.FileSystem"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <param name="deleteSource" type="boolean"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Copy local files to a FileSystem.]]> + </doc> + </method> + <method name="copy" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="srcFS" type="org.apache.hadoop.fs.FileSystem"/> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="java.io.File"/> + <param name="deleteSource" type="boolean"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Copy FileSystem files to local files.]]> + </doc> + </method> + <method name="makeShellPath" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="filename" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Convert a os-native filename to a path that works for the shell. + @param filename The filename to convert + @return The unix pathname + @throws IOException on windows, there can be problems with the subprocess]]> + </doc> + </method> + <method name="makeShellPath" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="file" type="java.io.File"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Convert a os-native filename to a path that works for the shell. + @param file The filename to convert + @return The unix pathname + @throws IOException on windows, there can be problems with the subprocess]]> + </doc> + </method> + <method name="getDU" return="long" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dir" type="java.io.File"/> + <doc> + <![CDATA[Takes an input dir and returns the du on that local directory. Very basic + implementation. + + @param dir + The input dir to get the disk space of this local dir + @return The total disk space of the input local directory]]> + </doc> + </method> + <method name="unZip" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="inFile" type="java.io.File"/> + <param name="unzipDir" type="java.io.File"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Given a File input it will unzip the file in a the unzip directory + passed as the second parameter + @param inFile The zip file as input + @param unzipDir The unzip directory where to unzip the zip file. + @throws IOException]]> + </doc> + </method> + <method name="symLink" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="target" type="java.lang.String"/> + <param name="linkname" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create a soft link between a src and destination + only on a local disk. HDFS does not support this + @param target the target for symlink + @param linkname the symlink + @return value returned by the command]]> + </doc> + </method> + <method name="chmod" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="filename" type="java.lang.String"/> + <param name="perm" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <exception name="InterruptedException" type="java.lang.InterruptedException"/> + <doc> + <![CDATA[Change the permissions on a filename. + @param filename the name of the file to change + @param perm the permission string + @return the exit code from the command + @throws IOException + @throws InterruptedException]]> + </doc> + </method> + <method name="createLocalTempFile" return="java.io.File" + abstract="false" native="false" synchronized="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <param name="basefile" type="java.io.File"/> + <param name="prefix" type="java.lang.String"/> + <param name="isDeleteOnExit" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create a tmp file for a base file. + @param basefile the base file of the tmp + @param prefix file name prefix of tmp + @param isDeleteOnExit if true, the tmp will be deleted when the VM exits + @return a newly created tmp file + @exception IOException If a tmp file cannot created + @see java.io.File#createTempFile(String, String, File) + @see java.io.File#deleteOnExit()]]> + </doc> + </method> + <method name="replaceFile" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="java.io.File"/> + <param name="target" type="java.io.File"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Move the src file to the name specified by target. + @param src the source file + @param target the target file + @exception IOException If this operation fails]]> + </doc> + </method> + <doc> + <![CDATA[A collection of file-processing util methods]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.FileUtil --> + <!-- start class org.apache.hadoop.fs.FileUtil.HardLink --> + <class name="FileUtil.HardLink" extends="java.lang.Object" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="FileUtil.HardLink" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="createHardLink" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="target" type="java.io.File"/> + <param name="linkName" type="java.io.File"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Creates a hardlink]]> + </doc> + </method> + <method name="getLinkCount" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fileName" type="java.io.File"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Retrieves the number of links to the specified file.]]> + </doc> + </method> + <doc> + <![CDATA[Class for creating hardlinks. + Supports Unix, Cygwin, WindXP.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.FileUtil.HardLink --> + <!-- start class org.apache.hadoop.fs.FilterFileSystem --> + <class name="FilterFileSystem" extends="org.apache.hadoop.fs.FileSystem" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="FilterFileSystem" type="org.apache.hadoop.fs.FileSystem" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="initialize" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.net.URI"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Called after a new FileSystem instance is constructed. + @param name a uri whose authority section names the host, port, etc. + for this FileSystem + @param conf the configuration]]> + </doc> + </method> + <method name="getUri" return="java.net.URI" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns a URI whose scheme and authority identify this FileSystem.]]> + </doc> + </method> + <method name="getName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="call #getUri() instead."> + <doc> + <![CDATA[@deprecated call #getUri() instead.]]> + </doc> + </method> + <method name="makeQualified" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <doc> + <![CDATA[Make sure that a path specifies a FileSystem.]]> + </doc> + </method> + <method name="checkPath" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <doc> + <![CDATA[Check that a Path belongs to this FileSystem.]]> + </doc> + </method> + <method name="getFileBlockLocations" return="org.apache.hadoop.fs.BlockLocation[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="start" type="long"/> + <param name="len" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return an array containing hostnames, offset and size of + portions of the given file. For a nonexistent + file or regions, null will be returned. + + This call is most helpful with DFS, where it returns + hostnames of machines that contain the given file. + + The FileSystem will simply return an elt containing 'localhost'.]]> + </doc> + </method> + <method name="open" return="org.apache.hadoop.fs.FSDataInputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="bufferSize" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Opens an FSDataInputStream at the indicated Path. + @param f the file name to open + @param bufferSize the size of the buffer to be used.]]> + </doc> + </method> + <method name="create" return="org.apache.hadoop.fs.FSDataOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="permission" type="org.apache.hadoop.fs.permission.FsPermission"/> + <param name="overwrite" type="boolean"/> + <param name="bufferSize" type="int"/> + <param name="replication" type="short"/> + <param name="blockSize" type="long"/> + <param name="progress" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="setReplication" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="replication" type="short"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Set replication for an existing file. + + @param src file name + @param replication new replication + @throws IOException + @return true if successful; + false if file does not exist or is a directory]]> + </doc> + </method> + <method name="rename" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Renames Path src to Path dst. Can take place on local fs + or remote DFS.]]> + </doc> + </method> + <method name="delete" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Delete a file]]> + </doc> + </method> + <method name="delete" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="recursive" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Delete a file]]> + </doc> + </method> + <method name="listStatus" return="org.apache.hadoop.fs.FileStatus[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[List files in a directory.]]> + </doc> + </method> + <method name="getHomeDirectory" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="setWorkingDirectory" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="newDir" type="org.apache.hadoop.fs.Path"/> + <doc> + <![CDATA[Set the current working directory for the given file system. All relative + paths will be resolved relative to it. + + @param newDir]]> + </doc> + </method> + <method name="getWorkingDirectory" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the current working directory for the given file system + + @return the directory pathname]]> + </doc> + </method> + <method name="mkdirs" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="permission" type="org.apache.hadoop.fs.permission.FsPermission"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="copyFromLocalFile" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="delSrc" type="boolean"/> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[The src file is on the local disk. Add it to FS at + the given dst name. + delSrc indicates if the source should be removed]]> + </doc> + </method> + <method name="copyToLocalFile" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="delSrc" type="boolean"/> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[The src file is under FS, and the dst is on the local disk. + Copy it from FS control to the local dst name. + delSrc indicates if the src will be removed or not.]]> + </doc> + </method> + <method name="startLocalOutput" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fsOutputFile" type="org.apache.hadoop.fs.Path"/> + <param name="tmpLocalFile" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns a local File that the user can write output to. The caller + provides both the eventual FS target name and the local working + file. If the FS is local, we write directly into the target. If + the FS is remote, we write into the tmp local area.]]> + </doc> + </method> + <method name="completeLocalOutput" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fsOutputFile" type="org.apache.hadoop.fs.Path"/> + <param name="tmpLocalFile" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Called when we're all done writing to the target. A local FS will + do nothing, because we've written to exactly the right place. A remote + FS will copy the contents of tmpLocalFile to the correct target at + fsOutputFile.]]> + </doc> + </method> + <method name="getDefaultBlockSize" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the number of bytes that large input files should be optimally + be split into to minimize i/o time.]]> + </doc> + </method> + <method name="getDefaultReplication" return="short" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the default replication.]]> + </doc> + </method> + <method name="getFileStatus" return="org.apache.hadoop.fs.FileStatus" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get file status.]]> + </doc> + </method> + <method name="getConf" return="org.apache.hadoop.conf.Configuration" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="setOwner" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="p" type="org.apache.hadoop.fs.Path"/> + <param name="username" type="java.lang.String"/> + <param name="groupname" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="setPermission" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="p" type="org.apache.hadoop.fs.Path"/> + <param name="permission" type="org.apache.hadoop.fs.permission.FsPermission"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <field name="fs" type="org.apache.hadoop.fs.FileSystem" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[A <code>FilterFileSystem</code> contains + some other file system, which it uses as + its basic file system, possibly transforming + the data along the way or providing additional + functionality. The class <code>FilterFileSystem</code> + itself simply overrides all methods of + <code>FileSystem</code> with versions that + pass all requests to the contained file + system. Subclasses of <code>FilterFileSystem</code> + may further override some of these methods + and may also provide additional methods + and fields.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.FilterFileSystem --> + <!-- start class org.apache.hadoop.fs.FSDataInputStream --> + <class name="FSDataInputStream" extends="java.io.DataInputStream" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.fs.Seekable"/> + <implements name="org.apache.hadoop.fs.PositionedReadable"/> + <constructor name="FSDataInputStream" type="java.io.InputStream" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </constructor> + <method name="seek" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="desired" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getPos" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="read" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="position" type="long"/> + <param name="buffer" type="byte[]"/> + <param name="offset" type="int"/> + <param name="length" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFully" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="position" type="long"/> + <param name="buffer" type="byte[]"/> + <param name="offset" type="int"/> + <param name="length" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFully" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="position" type="long"/> + <param name="buffer" type="byte[]"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="seekToNewSource" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="targetPos" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[Utility that wraps a {@link FSInputStream} in a {@link DataInputStream} + and buffers input through a {@link BufferedInputStream}.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.FSDataInputStream --> + <!-- start class org.apache.hadoop.fs.FSDataOutputStream --> + <class name="FSDataOutputStream" extends="java.io.DataOutputStream" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="FSDataOutputStream" type="java.io.OutputStream" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </constructor> + <constructor name="FSDataOutputStream" type="java.io.OutputStream, org.apache.hadoop.fs.FileSystem.Statistics" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </constructor> + <method name="getPos" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getWrappedStream" return="java.io.OutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[Utility that wraps a {@link OutputStream} in a {@link DataOutputStream}, + buffers output through a {@link BufferedOutputStream} and creates a checksum + file.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.FSDataOutputStream --> + <!-- start class org.apache.hadoop.fs.FSError --> + <class name="FSError" extends="java.lang.Error" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Thrown for unexpected filesystem errors, presumed to reflect disk errors + in the native filesystem.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.FSError --> + <!-- start class org.apache.hadoop.fs.FSInputChecker --> + <class name="FSInputChecker" extends="org.apache.hadoop.fs.FSInputStream" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="FSInputChecker" type="org.apache.hadoop.fs.Path, int" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[Constructor + + @param file The name of the file to be read + @param numOfRetries Number of read retries when ChecksumError occurs]]> + </doc> + </constructor> + <constructor name="FSInputChecker" type="org.apache.hadoop.fs.Path, int, boolean, java.util.zip.Checksum, int, int" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[Constructor + + @param file The name of the file to be read + @param numOfRetries Number of read retries when ChecksumError occurs + @param sum the type of Checksum engine + @param chunkSize maximun chunk size + @param checksumSize the number byte of each checksum]]> + </doc> + </constructor> + <method name="readChunk" return="int" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="pos" type="long"/> + <param name="buf" type="byte[]"/> + <param name="offset" type="int"/> + <param name="len" type="int"/> + <param name="checksum" type="byte[]"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Reads in next checksum chunk data into <code>buf</code> at <code>offset</code> + and checksum into <code>checksum</code>. + The method is used for implementing read, therefore, it should be optimized + for sequential reading + @param pos chunkPos + @param buf desitination buffer + @param offset offset in buf at which to store data + @param len maximun number of bytes to read + @return number of bytes read]]> + </doc> + </method> + <method name="getChunkPosition" return="long" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="pos" type="long"/> + <doc> + <![CDATA[Return position of beginning of chunk containing pos. + + @param pos a postion in the file + @return the starting position of the chunk which contains the byte]]> + </doc> + </method> + <method name="needChecksum" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[Return true if there is a need for checksum verification]]> + </doc> + </method> + <method name="read" return="int" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read one checksum-verified byte + + @return the next byte of data, or <code>-1</code> if the end of the + stream is reached. + @exception IOException if an I/O error occurs.]]> + </doc> + </method> + <method name="read" return="int" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read checksum verified bytes from this byte-input stream into + the specified byte array, starting at the given offset. + + <p> This method implements the general contract of the corresponding + <code>{@link InputStream#read(byte[], int, int) read}</code> method of + the <code>{@link InputStream}</code> class. As an additional + convenience, it attempts to read as many bytes as possible by repeatedly + invoking the <code>read</code> method of the underlying stream. This + iterated <code>read</code> continues until one of the following + conditions becomes true: <ul> + + <li> The specified number of bytes have been read, + + <li> The <code>read</code> method of the underlying stream returns + <code>-1</code>, indicating end-of-file. + + </ul> If the first <code>read</code> on the underlying stream returns + <code>-1</code> to indicate end-of-file then this method returns + <code>-1</code>. Otherwise this method returns the number of bytes + actually read. + + @param b destination buffer. + @param off offset at which to start storing bytes. + @param len maximum number of bytes to read. + @return the number of bytes read, or <code>-1</code> if the end of + the stream has been reached. + @exception IOException if an I/O error occurs. + ChecksumException if any checksum error occurs]]> + </doc> + </method> + <method name="getPos" return="long" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="available" return="int" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="skip" return="long" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="n" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Skips over and discards <code>n</code> bytes of data from the + input stream. + + <p>This method may skip more bytes than are remaining in the backing + file. This produces no exception and the number of bytes skipped + may include some number of bytes that were beyond the EOF of the + backing file. Attempting to read from the stream after skipping past + the end will result in -1 indicating the end of the file. + +<p>If <code>n</code> is negative, no bytes are skipped. + + @param n the number of bytes to be skipped. + @return the actual number of bytes skipped. + @exception IOException if an I/O error occurs. + ChecksumException if the chunk to skip to is corrupted]]> + </doc> + </method> + <method name="seek" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="pos" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Seek to the given position in the stream. + The next read() will be from that position. + + <p>This method may seek past the end of the file. + This produces no exception and an attempt to read from + the stream will result in -1 indicating the end of the file. + + @param pos the postion to seek to. + @exception IOException if an I/O error occurs. + ChecksumException if the chunk to seek to is corrupted]]> + </doc> + </method> + <method name="readFully" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="stm" type="java.io.InputStream"/> + <param name="buf" type="byte[]"/> + <param name="offset" type="int"/> + <param name="len" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[A utility function that tries to read up to <code>len</code> bytes from + <code>stm</code> + + @param stm an input stream + @param buf destiniation buffer + @param offset offset at which to store data + @param len number of bytes to read + @return actual number of bytes read + @throws IOException if there is any IO error]]> + </doc> + </method> + <method name="set" + abstract="false" native="false" synchronized="true" + static="false" final="true" visibility="protected" + deprecated="not deprecated"> + <param name="sum" type="java.util.zip.Checksum"/> + <param name="maxChunkSize" type="int"/> + <param name="checksumSize" type="int"/> + <doc> + <![CDATA[Set the checksum related parameters + @param sum which type of checksum to use + @param maxChunkSize maximun chunk size + @param checksumSize checksum size]]> + </doc> + </method> + <method name="markSupported" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + </method> + <method name="mark" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <param name="readlimit" type="int"/> + </method> + <method name="reset" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <field name="LOG" type="org.apache.commons.logging.Log" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="file" type="org.apache.hadoop.fs.Path" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[The file name from which data is read from]]> + </doc> + </field> + <doc> + <![CDATA[This is a generic input stream for verifying checksums for + data before it is read by a user.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.FSInputChecker --> + <!-- start class org.apache.hadoop.fs.FSInputStream --> + <class name="FSInputStream" extends="java.io.InputStream" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.fs.Seekable"/> + <implements name="org.apache.hadoop.fs.PositionedReadable"/> + <constructor name="FSInputStream" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="seek" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="pos" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Seek to the given offset from the start of the file. + The next read() will be from that location. Can't + seek past the end of the file.]]> + </doc> + </method> + <method name="getPos" return="long" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return the current offset from the start of the file]]> + </doc> + </method> + <method name="seekToNewSource" return="boolean" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="targetPos" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Seeks a different copy of the data. Returns true if + found a new source, false otherwise.]]> + </doc> + </method> + <method name="read" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="position" type="long"/> + <param name="buffer" type="byte[]"/> + <param name="offset" type="int"/> + <param name="length" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFully" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="position" type="long"/> + <param name="buffer" type="byte[]"/> + <param name="offset" type="int"/> + <param name="length" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFully" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="position" type="long"/> + <param name="buffer" type="byte[]"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[FSInputStream is a generic old InputStream with a little bit + of RAF-style seek ability.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.FSInputStream --> + <!-- start class org.apache.hadoop.fs.FSOutputSummer --> + <class name="FSOutputSummer" extends="java.io.OutputStream" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="FSOutputSummer" type="java.util.zip.Checksum, int, int" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </constructor> + <method name="writeChunk" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="offset" type="int"/> + <param name="len" type="int"/> + <param name="checksum" type="byte[]"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="write" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Write one byte]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Writes <code>len</code> bytes from the specified byte array + starting at offset <code>off</code> and generate a checksum for + each data chunk. + + <p> This method stores bytes from the given array into this + stream's buffer before it gets checksumed. The buffer gets checksumed + and flushed to the underlying output stream when all data + in a checksum chunk are in the buffer. If the buffer is empty and + requested length is at least as large as the size of next checksum chunk + size, this method will checksum and write the chunk directly + to the underlying output stream. Thus it avoids uneccessary data copy. + + @param b the data. + @param off the start offset in the data. + @param len the number of bytes to write. + @exception IOException if an I/O error occurs.]]> + </doc> + </method> + <method name="flushBuffer" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="flushBuffer" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="keep" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[This is a generic output stream for generating checksums for + data before it is written to the underlying stream]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.FSOutputSummer --> + <!-- start class org.apache.hadoop.fs.FsShell --> + <class name="FsShell" extends="org.apache.hadoop.conf.Configured" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.util.Tool"/> + <constructor name="FsShell" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="FsShell" type="org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="init" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getCurrentTrashDir" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the Trash object associated with this shell.]]> + </doc> + </method> + <method name="byteDesc" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="len" type="long"/> + <doc> + <![CDATA[Return an abbreviated English-language desc of the byte length]]> + </doc> + </method> + <method name="limitDecimalTo2" return="java.lang.String" + abstract="false" native="false" synchronized="true" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="d" type="double"/> + </method> + <method name="run" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="argv" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + <doc> + <![CDATA[run]]> + </doc> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="argv" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + <doc> + <![CDATA[main() has some simple utility methods]]> + </doc> + </method> + <field name="fs" type="org.apache.hadoop.fs.FileSystem" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="dateForm" type="java.text.SimpleDateFormat" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="modifFmt" type="java.text.SimpleDateFormat" + transient="false" volatile="false" + static="true" final="true" visibility="protected" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[Provide command line access to a FileSystem.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.FsShell --> + <!-- start class org.apache.hadoop.fs.InMemoryFileSystem --> + <class name="InMemoryFileSystem" extends="org.apache.hadoop.fs.ChecksumFileSystem" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="InMemoryFileSystem" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="InMemoryFileSystem" type="java.net.URI, org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="reserveSpaceWithCheckSum" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="size" type="long"/> + <doc> + <![CDATA[Register a file with its size. This will also register a checksum for the + file that the user is trying to create. This is required since none of + the FileSystem APIs accept the size of the file as argument. But since it + is required for us to apriori know the size of the file we are going to + create, the user must call this method for each file he wants to create + and reserve memory for that file. We either succeed in reserving memory + for both the main file and the checksum file and return true, or return + false.]]> + </doc> + </method> + <method name="getFiles" return="org.apache.hadoop.fs.Path[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="filter" type="org.apache.hadoop.fs.PathFilter"/> + </method> + <method name="getNumFiles" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="filter" type="org.apache.hadoop.fs.PathFilter"/> + </method> + <method name="getFSSize" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getPercentUsed" return="float" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[An implementation of the in-memory filesystem. This implementation assumes + that the file lengths are known ahead of time and the total lengths of all + the files is below a certain number (like 100 MB, configurable). Use the API + reserveSpaceWithCheckSum(Path f, int size) (see below for a description of + the API for reserving space in the FS. The uri of this filesystem starts with + ramfs:// .]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.InMemoryFileSystem --> + <!-- start class org.apache.hadoop.fs.LocalDirAllocator --> + <class name="LocalDirAllocator" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="LocalDirAllocator" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Create an allocator object + @param contextCfgItemName]]> + </doc> + </constructor> + <method name="getLocalPathForWrite" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="pathStr" type="java.lang.String"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get a path from the local FS. This method should be used if the size of + the file is not known apriori. We go round-robin over the set of disks + (via the configured dirs) and return the first complete path where + we could create the parent directory of the passed path. + @param pathStr the requested path (this will be created on the first + available disk) + @param conf the Configuration object + @return the complete path to the file on a local disk + @throws IOException]]> + </doc> + </method> + <method name="getLocalPathForWrite" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="pathStr" type="java.lang.String"/> + <param name="size" type="long"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get a path from the local FS. Pass size as -1 if not known apriori. We + round-robin over the set of disks (via the configured dirs) and return + the first complete path which has enough space + @param pathStr the requested path (this will be created on the first + available disk) + @param size the size of the file that is going to be written + @param conf the Configuration object + @return the complete path to the file on a local disk + @throws IOException]]> + </doc> + </method> + <method name="getLocalPathToRead" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="pathStr" type="java.lang.String"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get a path from the local FS for reading. We search through all the + configured dirs for the file's existence and return the complete + path to the file when we find one + @param pathStr the requested file (this will be searched) + @param conf the Configuration object + @return the complete path to the file on a local disk + @throws IOException]]> + </doc> + </method> + <method name="createTmpFileForWrite" return="java.io.File" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="pathStr" type="java.lang.String"/> + <param name="size" type="long"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Creates a temporary file in the local FS. Pass size as -1 if not known + apriori. We round-robin over the set of disks (via the configured dirs) + and select the first complete path which has enough space. A file is + created on this directory. The file is guaranteed to go away when the + JVM exits. + @param pathStr prefix for the temporary file + @param size the size of the file that is going to be written + @param conf the Configuration object + @return a unique temporary file + @throws IOException]]> + </doc> + </method> + <method name="isContextValid" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="contextCfgItemName" type="java.lang.String"/> + <doc> + <![CDATA[Method to check whether a context is valid + @param contextCfgItemName + @return true/false]]> + </doc> + </method> + <method name="ifExists" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="pathStr" type="java.lang.String"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[We search through all the configured dirs for the file's existence + and return true when we find + @param pathStr the requested file (this will be searched) + @param conf the Configuration object + @return true if files exist. false otherwise + @throws IOException]]> + </doc> + </method> + <doc> + <![CDATA[An implementation of a round-robin scheme for disk allocation for creating + files. The way it works is that it is kept track what disk was last + allocated for a file write. For the current request, the next disk from + the set of disks would be allocated if the free space on the disk is + sufficient enough to accomodate the file that is being considered for + creation. If the space requirements cannot be met, the next disk in order + would be tried and so on till a disk is found with sufficient capacity. + Once a disk with sufficient space is identified, a check is done to make + sure that the disk is writable. Also, there is an API provided that doesn't + take the space requirements into consideration but just checks whether the + disk under consideration is writable (this should be used for cases where + the file size is not known apriori). An API is provided to read a path that + was created earlier. That API works by doing a scan of all the disks for the + input pathname. + This implementation also provides the functionality of having multiple + allocators per JVM (one for each unique functionality or context, like + mapred, dfs-client, etc.). It ensures that there is only one instance of + an allocator per context per JVM. + Note: + 1. The contexts referred above are actually the configuration items defined + in the Configuration class like "mapred.local.dir" (for which we want to + control the dir allocations). The context-strings are exactly those + configuration items. + 2. This implementation does not take into consideration cases where + a disk becomes read-only or goes out of space while a file is being written + to (disks are shared between multiple processes, and so the latter situation + is probable). + 3. In the class implementation, "Disk" is referred to as "Dir", which + actually points to the configured directory on the Disk which will be the + parent for all file write/read allocations.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.LocalDirAllocator --> + <!-- start class org.apache.hadoop.fs.LocalFileSystem --> + <class name="LocalFileSystem" extends="org.apache.hadoop.fs.ChecksumFileSystem" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="LocalFileSystem" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="LocalFileSystem" type="org.apache.hadoop.fs.FileSystem" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="pathToFile" return="java.io.File" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <doc> + <![CDATA[Convert a path to a File.]]> + </doc> + </method> + <method name="copyFromLocalFile" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="delSrc" type="boolean"/> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="copyToLocalFile" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="delSrc" type="boolean"/> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="reportChecksumFailure" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="p" type="org.apache.hadoop.fs.Path"/> + <param name="in" type="org.apache.hadoop.fs.FSDataInputStream"/> + <param name="inPos" type="long"/> + <param name="sums" type="org.apache.hadoop.fs.FSDataInputStream"/> + <param name="sumsPos" type="long"/> + <doc> + <![CDATA[Moves files to a bad file directory on the same device, so that their + storage will not be reused.]]> + </doc> + </method> + <doc> + <![CDATA[Implement the FileSystem API for the checksumed local filesystem.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.LocalFileSystem --> + <!-- start class org.apache.hadoop.fs.Path --> + <class name="Path" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="java.lang.Comparable"/> + <constructor name="Path" type="java.lang.String, java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Resolve a child path against a parent path.]]> + </doc> + </constructor> + <constructor name="Path" type="org.apache.hadoop.fs.Path, java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Resolve a child path against a parent path.]]> + </doc> + </constructor> + <constructor name="Path" type="java.lang.String, org.apache.hadoop.fs.Path" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Resolve a child path against a parent path.]]> + </doc> + </constructor> + <constructor name="Path" type="org.apache.hadoop.fs.Path, org.apache.hadoop.fs.Path" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Resolve a child path against a parent path.]]> + </doc> + </constructor> + <constructor name="Path" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct a path from a String. Path strings are URIs, but with + unescaped elements and some additional normalization.]]> + </doc> + </constructor> + <constructor name="Path" type="java.lang.String, java.lang.String, java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct a Path from components.]]> + </doc> + </constructor> + <method name="toUri" return="java.net.URI" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Convert this to a URI.]]> + </doc> + </method> + <method name="getFileSystem" return="org.apache.hadoop.fs.FileSystem" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return the FileSystem that owns this Path.]]> + </doc> + </method> + <method name="isAbsolute" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[True if the directory of this path is absolute.]]> + </doc> + </method> + <method name="getName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the final component of this path.]]> + </doc> + </method> + <method name="getParent" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the parent of a path or null if at root.]]> + </doc> + </method> + <method name="suffix" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="suffix" type="java.lang.String"/> + <doc> + <![CDATA[Adds a suffix to the final name in the path.]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="compareTo" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + </method> + <method name="depth" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the number of elements in this path.]]> + </doc> + </method> + <method name="makeQualified" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <doc> + <![CDATA[Returns a qualified path object.]]> + </doc> + </method> + <field name="SEPARATOR" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The directory separator, a slash.]]> + </doc> + </field> + <field name="SEPARATOR_CHAR" type="char" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="CUR_DIR" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[Names a file or directory in a {@link FileSystem}. + Path strings use slash as the directory separator. A path string is + absolute if it begins with a slash.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.Path --> + <!-- start interface org.apache.hadoop.fs.PathFilter --> + <interface name="PathFilter" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="accept" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <doc> + <![CDATA[Tests whether or not the specified abstract pathname should be + included in a pathname list. + + @param path The abstract pathname to be tested + @return <code>true</code> if and only if <code>pathname</code> + should be included]]> + </doc> + </method> + </interface> + <!-- end interface org.apache.hadoop.fs.PathFilter --> + <!-- start interface org.apache.hadoop.fs.PositionedReadable --> + <interface name="PositionedReadable" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="read" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="position" type="long"/> + <param name="buffer" type="byte[]"/> + <param name="offset" type="int"/> + <param name="length" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read upto the specified number of bytes, from a given + position within a file, and return the number of bytes read. This does not + change the current offset of a file, and is thread-safe.]]> + </doc> + </method> + <method name="readFully" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="position" type="long"/> + <param name="buffer" type="byte[]"/> + <param name="offset" type="int"/> + <param name="length" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read the specified number of bytes, from a given + position within a file. This does not + change the current offset of a file, and is thread-safe.]]> + </doc> + </method> + <method name="readFully" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="position" type="long"/> + <param name="buffer" type="byte[]"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read number of bytes equalt to the length of the buffer, from a given + position within a file. This does not + change the current offset of a file, and is thread-safe.]]> + </doc> + </method> + <doc> + <![CDATA[Stream that permits positional reading.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.fs.PositionedReadable --> + <!-- start class org.apache.hadoop.fs.RawLocalFileSystem --> + <class name="RawLocalFileSystem" extends="org.apache.hadoop.fs.FileSystem" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="RawLocalFileSystem" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="pathToFile" return="java.io.File" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <doc> + <![CDATA[Convert a path to a File.]]> + </doc> + </method> + <method name="getName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="deprecated, no comment"> + <doc> + <![CDATA[@deprecated]]> + </doc> + </method> + <method name="getUri" return="java.net.URI" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="initialize" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="uri" type="java.net.URI"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + </method> + <method name="open" return="org.apache.hadoop.fs.FSDataInputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="bufferSize" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="create" return="org.apache.hadoop.fs.FSDataOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="overwrite" type="boolean"/> + <param name="bufferSize" type="int"/> + <param name="replication" type="short"/> + <param name="blockSize" type="long"/> + <param name="progress" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="create" return="org.apache.hadoop.fs.FSDataOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="permission" type="org.apache.hadoop.fs.permission.FsPermission"/> + <param name="overwrite" type="boolean"/> + <param name="bufferSize" type="int"/> + <param name="replication" type="short"/> + <param name="blockSize" type="long"/> + <param name="progress" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="rename" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="delete" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="p" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="delete" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="p" type="org.apache.hadoop.fs.Path"/> + <param name="recursive" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="listStatus" return="org.apache.hadoop.fs.FileStatus[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="mkdirs" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Creates the specified directory hierarchy. Does not + treat existence as an error.]]> + </doc> + </method> + <method name="mkdirs" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="permission" type="org.apache.hadoop.fs.permission.FsPermission"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="getHomeDirectory" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="setWorkingDirectory" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="newDir" type="org.apache.hadoop.fs.Path"/> + <doc> + <![CDATA[Set the working directory to the given directory.]]> + </doc> + </method> + <method name="getWorkingDirectory" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="lock" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="deprecated, no comment"> + <param name="p" type="org.apache.hadoop.fs.Path"/> + <param name="shared" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[@deprecated]]> + </doc> + </method> + <method name="release" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="deprecated, no comment"> + <param name="p" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[@deprecated]]> + </doc> + </method> + <method name="moveFromLocalFile" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="startLocalOutput" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fsOutputFile" type="org.apache.hadoop.fs.Path"/> + <param name="tmpLocalFile" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="completeLocalOutput" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fsWorkingFile" type="org.apache.hadoop.fs.Path"/> + <param name="tmpLocalFile" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getFileStatus" return="org.apache.hadoop.fs.FileStatus" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="setOwner" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="p" type="org.apache.hadoop.fs.Path"/> + <param name="username" type="java.lang.String"/> + <param name="groupname" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Use the command chown to set owner.]]> + </doc> + </method> + <method name="setPermission" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="p" type="org.apache.hadoop.fs.Path"/> + <param name="permission" type="org.apache.hadoop.fs.permission.FsPermission"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Use the command chmod to set permission.]]> + </doc> + </method> + <doc> + <![CDATA[Implement the FileSystem API for the raw local filesystem.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.RawLocalFileSystem --> + <!-- start interface org.apache.hadoop.fs.Seekable --> + <interface name="Seekable" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="seek" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="pos" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Seek to the given offset from the start of the file. + The next read() will be from that location. Can't + seek past the end of the file.]]> + </doc> + </method> + <method name="getPos" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return the current offset from the start of the file]]> + </doc> + </method> + <method name="seekToNewSource" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="targetPos" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Seeks a different copy of the data. Returns true if + found a new source, false otherwise.]]> + </doc> + </method> + <doc> + <![CDATA[Stream that permits seeking.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.fs.Seekable --> + <!-- start class org.apache.hadoop.fs.ShellCommand --> + <class name="ShellCommand" extends="org.apache.hadoop.util.Shell" + abstract="true" + static="false" final="false" visibility="public" + deprecated="Use {@link Shell} instead."> + <constructor name="ShellCommand" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <doc> + <![CDATA[A base class for running a unix command like du or df. + @deprecated Use {@link Shell} instead.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.ShellCommand --> + <!-- start class org.apache.hadoop.fs.Trash --> + <class name="Trash" extends="org.apache.hadoop.conf.Configured" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="Trash" type="org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct a trash can accessor. + @param conf a Configuration]]> + </doc> + </constructor> + <method name="moveToTrash" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Move a file or directory to the current trash directory. + @return false if the item is already in the trash or trash is disabled]]> + </doc> + </method> + <method name="checkpoint" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create a trash checkpoint.]]> + </doc> + </method> + <method name="expunge" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Delete old checkpoints.]]> + </doc> + </method> + <method name="getEmptier" return="java.lang.Runnable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return a {@link Runnable} that periodically empties the trash of all + users, intended to be run by the superuser. Only one checkpoint is kept + at a time.]]> + </doc> + </method> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + <doc> + <![CDATA[Run an emptier.]]> + </doc> + </method> + <doc> + <![CDATA[Provides a <i>trash</i> feature. Files are moved to a user's trash + directory, a subdirectory of their home directory named ".Trash". Files are + initially moved to a <i>current</i> sub-directory of the trash directory. + Within that sub-directory their original path is preserved. Periodically + one may checkpoint the current trash and remove older checkpoints. (This + design permits trash management without enumeration of the full trash + content, without date support in the filesystem, and without clock + synchronization.)]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.Trash --> + <doc> + <![CDATA[An abstract file system API.]]> + </doc> +</package> +<package name="org.apache.hadoop.fs.kfs"> + <!-- start class org.apache.hadoop.fs.kfs.KosmosFileSystem --> + <class name="KosmosFileSystem" extends="org.apache.hadoop.fs.FileSystem" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="KosmosFileSystem" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getUri" return="java.net.URI" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="initialize" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="uri" type="java.net.URI"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getWorkingDirectory" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="setWorkingDirectory" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dir" type="org.apache.hadoop.fs.Path"/> + </method> + <method name="mkdirs" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <param name="permission" type="org.apache.hadoop.fs.permission.FsPermission"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="isDirectory" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="isFile" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getContentLength" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="listStatus" return="org.apache.hadoop.fs.FileStatus[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getFileStatus" return="org.apache.hadoop.fs.FileStatus" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="create" return="org.apache.hadoop.fs.FSDataOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="file" type="org.apache.hadoop.fs.Path"/> + <param name="permission" type="org.apache.hadoop.fs.permission.FsPermission"/> + <param name="overwrite" type="boolean"/> + <param name="bufferSize" type="int"/> + <param name="replication" type="short"/> + <param name="blockSize" type="long"/> + <param name="progress" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="open" return="org.apache.hadoop.fs.FSDataInputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <param name="bufferSize" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="rename" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="delete" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <param name="recursive" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="delete" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getLength" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getReplication" return="short" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getDefaultReplication" return="short" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="setReplication" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <param name="replication" type="short"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getDefaultBlockSize" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="lock" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <param name="shared" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="release" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getBlockLocations" return="org.apache.hadoop.fs.BlockLocation[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <param name="start" type="long"/> + <param name="len" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return null if the file doesn't exist; otherwise, get the + locations of the various chunks of the file file from KFS.]]> + </doc> + </method> + <method name="copyFromLocalFile" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="delSrc" type="boolean"/> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="copyToLocalFile" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="delSrc" type="boolean"/> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="startLocalOutput" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fsOutputFile" type="org.apache.hadoop.fs.Path"/> + <param name="tmpLocalFile" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="completeLocalOutput" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fsOutputFile" type="org.apache.hadoop.fs.Path"/> + <param name="tmpLocalFile" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[A FileSystem backed by KFS.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.kfs.KosmosFileSystem --> + <doc> + <![CDATA[<h1>A client for the Kosmos filesystem (KFS)</h1> + +<h3>Introduction</h3> + +This pages describes how to use Kosmos Filesystem +(<a href="http://kosmosfs.sourceforge.net"> KFS </a>) as a backing +store with Hadoop. This page assumes that you have downloaded the +KFS software and installed necessary binaries as outlined in the KFS +documentation. + +<h3>Steps</h3> + + <ul> + <li>In the Hadoop conf directory edit hadoop-default.xml, + add the following: + <pre> +<property> + <name>fs.kfs.impl</name> + <value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value> + <description>The FileSystem for kfs: uris.</description> +</property> + </pre> + + <li>In the Hadoop conf directory edit hadoop-site.xml, + adding the following (with appropriate values for + <server> and <port>): + <pre> +<property> + <name>fs.default.name</name> + <value>kfs://<server:port></value> +</property> + +<property> + <name>fs.kfs.metaServerHost</name> + <value><server></value> + <description>The location of the KFS meta server.</description> +</property> + +<property> + <name>fs.kfs.metaServerPort</name> + <value><port></value> + <description>The location of the meta server's port.</description> +</property> + +</pre> + </li> + + <li>Copy KFS's <i> kfs-0.1.jar </i> to Hadoop's lib directory. This step + enables Hadoop's to load the KFS specific modules. Note + that, kfs-0.1.jar was built when you compiled KFS source + code. This jar file contains code that calls KFS's client + library code via JNI; the native code is in KFS's <i> + libkfsClient.so </i> library. + </li> + + <li> When the Hadoop map/reduce trackers start up, those +processes (on local as well as remote nodes) will now need to load +KFS's <i> libkfsClient.so </i> library. To simplify this process, it is advisable to +store libkfsClient.so in an NFS accessible directory (similar to where +Hadoop binaries/scripts are stored); then, modify Hadoop's +conf/hadoop-env.sh adding the following line and providing suitable +value for <path>: +<pre> +export LD_LIBRARY_PATH=<path> +</pre> + + + <li>Start only the map/reduce trackers + <br /> + example: execute Hadoop's bin/start-mapred.sh</li> + </ul> +<br/> + +If the map/reduce job trackers start up, all file-I/O is done to KFS.]]> + </doc> +</package> +<package name="org.apache.hadoop.fs.permission"> + <!-- start class org.apache.hadoop.fs.permission.AccessControlException --> + <class name="AccessControlException" extends="java.io.IOException" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="AccessControlException" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Default constructor is needed for unwrapping from + {@link org.apache.hadoop.ipc.RemoteException}.]]> + </doc> + </constructor> + <constructor name="AccessControlException" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Constructs an {@link AccessControlException} + with the specified detail message. + @param s the detail message.]]> + </doc> + </constructor> + <doc> + <![CDATA[An exception class for access control related issues.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.permission.AccessControlException --> + <!-- start class org.apache.hadoop.fs.permission.FsAction --> + <class name="FsAction" extends="java.lang.Enum<org.apache.hadoop.fs.permission.FsAction>" + abstract="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <method name="values" return="org.apache.hadoop.fs.permission.FsAction[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="valueOf" return="org.apache.hadoop.fs.permission.FsAction" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + <method name="implies" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="that" type="org.apache.hadoop.fs.permission.FsAction"/> + <doc> + <![CDATA[Return true if this action implies that action. + @param that]]> + </doc> + </method> + <method name="and" return="org.apache.hadoop.fs.permission.FsAction" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="that" type="org.apache.hadoop.fs.permission.FsAction"/> + <doc> + <![CDATA[AND operation.]]> + </doc> + </method> + <method name="or" return="org.apache.hadoop.fs.permission.FsAction" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="that" type="org.apache.hadoop.fs.permission.FsAction"/> + <doc> + <![CDATA[OR operation.]]> + </doc> + </method> + <method name="not" return="org.apache.hadoop.fs.permission.FsAction" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[NOT operation.]]> + </doc> + </method> + <field name="INDEX" type="int" + transient="false" volatile="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Octal representation]]> + </doc> + </field> + <field name="SYMBOL" type="java.lang.String" + transient="false" volatile="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Symbolic representation]]> + </doc> + </field> + <doc> + <![CDATA[File system actions, e.g. read, write, etc.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.permission.FsAction --> + <!-- start class org.apache.hadoop.fs.permission.FsPermission --> + <class name="FsPermission" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <constructor name="FsPermission" type="org.apache.hadoop.fs.permission.FsAction, org.apache.hadoop.fs.permission.FsAction, org.apache.hadoop.fs.permission.FsAction" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct by the given {@link FsAction}. + @param u user action + @param g group action + @param o other action]]> + </doc> + </constructor> + <constructor name="FsPermission" type="short" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct by the given mode. + @param mode + @see #toShort()]]> + </doc> + </constructor> + <constructor name="FsPermission" type="org.apache.hadoop.fs.permission.FsPermission" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Copy constructor + + @param other other permission]]> + </doc> + </constructor> + <method name="createImmutable" return="org.apache.hadoop.fs.permission.FsPermission" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="permission" type="short"/> + <doc> + <![CDATA[Create an immutable {@link FsPermission} object.]]> + </doc> + </method> + <method name="getUserAction" return="org.apache.hadoop.fs.permission.FsAction" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return user {@link FsAction}.]]> + </doc> + </method> + <method name="getGroupAction" return="org.apache.hadoop.fs.permission.FsAction" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return group {@link FsAction}.]]> + </doc> + </method> + <method name="getOtherAction" return="org.apache.hadoop.fs.permission.FsAction" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return other {@link FsAction}.]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="read" return="org.apache.hadoop.fs.permission.FsPermission" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create and initialize a {@link FsPermission} from {@link DataInput}.]]> + </doc> + </method> + <method name="toShort" return="short" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Encode the object to a short.]]> + </doc> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="obj" type="java.lang.Object"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="applyUMask" return="org.apache.hadoop.fs.permission.FsPermission" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="umask" type="org.apache.hadoop.fs.permission.FsPermission"/> + <doc> + <![CDATA[Apply a umask to this permission and return a new one]]> + </doc> + </method> + <method name="getUMask" return="org.apache.hadoop.fs.permission.FsPermission" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[Get the user file creation mask (umask)]]> + </doc> + </method> + <method name="setUMask" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="umask" type="org.apache.hadoop.fs.permission.FsPermission"/> + <doc> + <![CDATA[Set the user file creation mask (umask)]]> + </doc> + </method> + <method name="getDefault" return="org.apache.hadoop.fs.permission.FsPermission" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the default permission.]]> + </doc> + </method> + <method name="valueOf" return="org.apache.hadoop.fs.permission.FsPermission" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="unixSymbolicPermission" type="java.lang.String"/> + <doc> + <![CDATA[Create a FsPermission from a Unix symbolic permission string + @param unixSymbolicPermission e.g. "-rw-rw-rw-"]]> + </doc> + </method> + <field name="UMASK_LABEL" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[umask property label]]> + </doc> + </field> + <field name="DEFAULT_UMASK" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[A class for file/directory permissions.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.permission.FsPermission --> + <!-- start class org.apache.hadoop.fs.permission.PermissionStatus --> + <class name="PermissionStatus" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <constructor name="PermissionStatus" type="java.lang.String, java.lang.String, org.apache.hadoop.fs.permission.FsPermission" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Constructor]]> + </doc> + </constructor> + <method name="createImmutable" return="org.apache.hadoop.fs.permission.PermissionStatus" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="user" type="java.lang.String"/> + <param name="group" type="java.lang.String"/> + <param name="permission" type="org.apache.hadoop.fs.permission.FsPermission"/> + <doc> + <![CDATA[Create an immutable {@link PermissionStatus} object.]]> + </doc> + </method> + <method name="getUserName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return user name]]> + </doc> + </method> + <method name="getGroupName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return group name]]> + </doc> + </method> + <method name="getPermission" return="org.apache.hadoop.fs.permission.FsPermission" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return permission]]> + </doc> + </method> + <method name="applyUMask" return="org.apache.hadoop.fs.permission.PermissionStatus" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="umask" type="org.apache.hadoop.fs.permission.FsPermission"/> + <doc> + <![CDATA[Apply umask. + @see FsPermission#applyUMask(FsPermission)]]> + </doc> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="read" return="org.apache.hadoop.fs.permission.PermissionStatus" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create and initialize a {@link PermissionStatus} from {@link DataInput}.]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <doc> + <![CDATA[Store permission related information.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.permission.PermissionStatus --> +</package> +<package name="org.apache.hadoop.fs.s3"> + <!-- start class org.apache.hadoop.fs.s3.Block --> + <class name="Block" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="Block" type="long, long" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getId" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getLength" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[Holds metadata about a block of data being stored in a {@link FileSystemStore}.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.s3.Block --> + <!-- start interface org.apache.hadoop.fs.s3.FileSystemStore --> + <interface name="FileSystemStore" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="initialize" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="uri" type="java.net.URI"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getVersion" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="storeINode" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <param name="inode" type="org.apache.hadoop.fs.s3.INode"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="storeBlock" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="block" type="org.apache.hadoop.fs.s3.Block"/> + <param name="file" type="java.io.File"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="inodeExists" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="blockExists" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="blockId" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="retrieveINode" return="org.apache.hadoop.fs.s3.INode" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="retrieveBlock" return="java.io.File" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="block" type="org.apache.hadoop.fs.s3.Block"/> + <param name="byteRangeStart" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="deleteINode" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="deleteBlock" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="block" type="org.apache.hadoop.fs.s3.Block"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="listSubPaths" return="java.util.Set<org.apache.hadoop.fs.Path>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="listDeepSubPaths" return="java.util.Set<org.apache.hadoop.fs.Path>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="purge" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Delete everything. Used for testing. + @throws IOException]]> + </doc> + </method> + <method name="dump" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Diagnostic method to dump all INodes to the console. + @throws IOException]]> + </doc> + </method> + <doc> + <![CDATA[A facility for storing and retrieving {@link INode}s and {@link Block}s.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.fs.s3.FileSystemStore --> + <!-- start class org.apache.hadoop.fs.s3.INode --> + <class name="INode" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="INode" type="org.apache.hadoop.fs.s3.INode.FileType, org.apache.hadoop.fs.s3.Block[]" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getBlocks" return="org.apache.hadoop.fs.s3.Block[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getFileType" return="org.apache.hadoop.fs.s3.INode.FileType" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="isDirectory" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="isFile" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getSerializedLength" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="serialize" return="java.io.InputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="deserialize" return="org.apache.hadoop.fs.s3.INode" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.InputStream"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <field name="FILE_TYPES" type="org.apache.hadoop.fs.s3.INode.FileType[]" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="DIRECTORY_INODE" type="org.apache.hadoop.fs.s3.INode" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[Holds file metadata including type (regular file, or directory), + and the list of blocks that are pointers to the data.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.s3.INode --> + <!-- start class org.apache.hadoop.fs.s3.MigrationTool --> + <class name="MigrationTool" extends="org.apache.hadoop.conf.Configured" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.util.Tool"/> + <constructor name="MigrationTool" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + </method> + <method name="run" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + </method> + <method name="initialize" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="uri" type="java.net.URI"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[<p> + This class is a tool for migrating data from an older to a newer version + of an S3 filesystem. + </p> + <p> + All files in the filesystem are migrated by re-writing the block metadata + - no datafiles are touched. + </p>]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.s3.MigrationTool --> + <!-- start class org.apache.hadoop.fs.s3.S3Exception --> + <class name="S3Exception" extends="java.lang.RuntimeException" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="S3Exception" type="java.lang.Throwable" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <doc> + <![CDATA[Thrown if there is a problem communicating with Amazon S3.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.s3.S3Exception --> + <!-- start class org.apache.hadoop.fs.s3.S3FileSystem --> + <class name="S3FileSystem" extends="org.apache.hadoop.fs.FileSystem" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="S3FileSystem" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="S3FileSystem" type="org.apache.hadoop.fs.s3.FileSystemStore" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getUri" return="java.net.URI" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="initialize" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="uri" type="java.net.URI"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getWorkingDirectory" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="setWorkingDirectory" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dir" type="org.apache.hadoop.fs.Path"/> + </method> + <method name="mkdirs" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <param name="permission" type="org.apache.hadoop.fs.permission.FsPermission"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[@param permission Currently ignored.]]> + </doc> + </method> + <method name="isFile" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="listStatus" return="org.apache.hadoop.fs.FileStatus[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="create" return="org.apache.hadoop.fs.FSDataOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="file" type="org.apache.hadoop.fs.Path"/> + <param name="permission" type="org.apache.hadoop.fs.permission.FsPermission"/> + <param name="overwrite" type="boolean"/> + <param name="bufferSize" type="int"/> + <param name="replication" type="short"/> + <param name="blockSize" type="long"/> + <param name="progress" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[@param permission Currently ignored.]]> + </doc> + </method> + <method name="open" return="org.apache.hadoop.fs.FSDataInputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <param name="bufferSize" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="rename" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="org.apache.hadoop.fs.Path"/> + <param name="dst" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="delete" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <param name="recursive" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="delete" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getFileStatus" return="org.apache.hadoop.fs.FileStatus" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[FileStatus for S3 file systems.]]> + </doc> + </method> + <doc> + <![CDATA[<p> + A {@link FileSystem} backed by <a href="http://aws.amazon.com/s3">Amazon S3</a>. + </p>]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.s3.S3FileSystem --> + <!-- start class org.apache.hadoop.fs.s3.S3FileSystemException --> + <class name="S3FileSystemException" extends="java.io.IOException" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="S3FileSystemException" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <doc> + <![CDATA[Thrown when there is a fatal exception while using {@link S3FileSystem}.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.s3.S3FileSystemException --> + <!-- start class org.apache.hadoop.fs.s3.VersionMismatchException --> + <class name="VersionMismatchException" extends="org.apache.hadoop.fs.s3.S3FileSystemException" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="VersionMismatchException" type="java.lang.String, java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <doc> + <![CDATA[Thrown when Hadoop cannot read the version of the data stored + in {@link S3FileSystem}.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.s3.VersionMismatchException --> + <doc> + <![CDATA[<p>A distributed implementation of {@link +org.apache.hadoop.fs.FileSystem} that uses <a href="http://aws.amazon.com/s3">Amazon S3</a>.</p> + +<p> +Files are stored in S3 as blocks (represented by +{@link org.apache.hadoop.fs.s3.Block}), which have an ID and a length. +Block metadata is stored in S3 as a small record (represented by +{@link org.apache.hadoop.fs.s3.INode}) using the URL-encoded +path string as a key. Inodes record the file type (regular file or directory) and the list of blocks. +This design makes it easy to seek to any given position in a file by reading the inode data to compute +which block to access, then using S3's support for +<a href="http://www.w3.org/Protocols/rfc2616/rfc2616-sec14.html#sec14.35.2">HTTP Range</a> headers +to start streaming from the correct position. +Renames are also efficient since only the inode is moved (by a DELETE followed by a PUT since +S3 does not support renames). +</p> +<p> +For a single file <i>/dir1/file1</i> which takes two blocks of storage, the file structure in S3 +would be something like this: +</p> +<pre> +/ +/dir1 +/dir1/file1 +block-6415776850131549260 +block-3026438247347758425 +</pre> +<p> +Inodes start with a leading <code>/</code>, while blocks are prefixed with <code>block-</code>. +</p>]]> + </doc> +</package> +<package name="org.apache.hadoop.fs.shell"> + <!-- start class org.apache.hadoop.fs.shell.Count --> + <class name="Count" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="Count" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="matches" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="cmd" type="java.lang.String"/> + </method> + <method name="count" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="java.lang.String"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="out" type="java.io.PrintStream"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <field name="NAME" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="USAGE" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="DESCRIPTION" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[Count the number of directories, files and bytes.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.fs.shell.Count --> +</package> +<package name="org.apache.hadoop.io"> + <!-- start class org.apache.hadoop.io.AbstractMapWritable --> + <class name="AbstractMapWritable" extends="java.lang.Object" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <implements name="org.apache.hadoop.conf.Configurable"/> + <constructor name="AbstractMapWritable" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[constructor.]]> + </doc> + </constructor> + <method name="addToMap" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="clazz" type="java.lang.Class"/> + <doc> + <![CDATA[Add a Class to the maps if it is not already present.]]> + </doc> + </method> + <method name="getClass" return="java.lang.Class" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="id" type="byte"/> + <doc> + <![CDATA[@return the Class class for the specified id]]> + </doc> + </method> + <method name="getId" return="byte" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="clazz" type="java.lang.Class"/> + <doc> + <![CDATA[@return the id for the specified Class]]> + </doc> + </method> + <method name="copy" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="other" type="org.apache.hadoop.io.Writable"/> + <doc> + <![CDATA[Used by child copy constructors.]]> + </doc> + </method> + <method name="getConf" return="org.apache.hadoop.conf.Configuration" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the conf]]> + </doc> + </method> + <method name="setConf" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[@param conf the conf to set]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <doc> + <![CDATA[Abstract base class for MapWritable and SortedMapWritable + + Unlike org.apache.nutch.crawl.MapWritable, this class allows creation of + MapWritable<Writable, MapWritable> so the CLASS_TO_ID and ID_TO_CLASS + maps travel with the class instead of being static. + + Class ids range from 1 to 127 so there can be at most 127 distinct classes + in any specific map instance.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.AbstractMapWritable --> + <!-- start class org.apache.hadoop.io.ArrayFile --> + <class name="ArrayFile" extends="org.apache.hadoop.io.MapFile" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="ArrayFile" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </constructor> + <doc> + <![CDATA[A dense file-based mapping from integers to values.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.ArrayFile --> + <!-- start class org.apache.hadoop.io.ArrayFile.Reader --> + <class name="ArrayFile.Reader" extends="org.apache.hadoop.io.MapFile.Reader" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="ArrayFile.Reader" type="org.apache.hadoop.fs.FileSystem, java.lang.String, org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct an array reader for the named file.]]> + </doc> + </constructor> + <method name="seek" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="n" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Positions the reader before its <code>n</code>th value.]]> + </doc> + </method> + <method name="next" return="org.apache.hadoop.io.Writable" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="value" type="org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read and return the next value in the file.]]> + </doc> + </method> + <method name="key" return="long" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns the key associated with the most recent call to {@link + #seek(long)}, {@link #next(Writable)}, or {@link + #get(long,Writable)}.]]> + </doc> + </method> + <method name="get" return="org.apache.hadoop.io.Writable" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="n" type="long"/> + <param name="value" type="org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return the <code>n</code>th value in the file.]]> + </doc> + </method> + <doc> + <![CDATA[Provide access to an existing array file.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.ArrayFile.Reader --> + <!-- start class org.apache.hadoop.io.ArrayFile.Writer --> + <class name="ArrayFile.Writer" extends="org.apache.hadoop.io.MapFile.Writer" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="ArrayFile.Writer" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.fs.FileSystem, java.lang.String, java.lang.Class" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create the named file for values of the named class.]]> + </doc> + </constructor> + <constructor name="ArrayFile.Writer" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.fs.FileSystem, java.lang.String, java.lang.Class, org.apache.hadoop.io.SequenceFile.CompressionType, org.apache.hadoop.util.Progressable" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create the named file for values of the named class.]]> + </doc> + </constructor> + <method name="append" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="value" type="org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Append a value to the file.]]> + </doc> + </method> + <doc> + <![CDATA[Write a new array file.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.ArrayFile.Writer --> + <!-- start class org.apache.hadoop.io.ArrayWritable --> + <class name="ArrayWritable" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <constructor name="ArrayWritable" type="java.lang.Class" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="ArrayWritable" type="java.lang.Class, org.apache.hadoop.io.Writable[]" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="ArrayWritable" type="java.lang.String[]" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getValueClass" return="java.lang.Class" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="toStrings" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="toArray" return="java.lang.Object" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="set" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="values" type="org.apache.hadoop.io.Writable[]"/> + </method> + <method name="get" return="org.apache.hadoop.io.Writable[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[A Writable for arrays containing instances of a class. The elements of this + writable must all be instances of the same class. If this writable will be + the input for a Reducer, you will need to create a subclass that sets the + value to be of the proper type. + + For example: + <code> + public class IntArrayWritable extends ArrayWritable { + public IntArrayWritable() { + super(IntWritable.class); + } + } + </code>]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.ArrayWritable --> + <!-- start class org.apache.hadoop.io.BooleanWritable --> + <class name="BooleanWritable" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.WritableComparable"/> + <constructor name="BooleanWritable" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="BooleanWritable" type="boolean" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="set" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="value" type="boolean"/> + <doc> + <![CDATA[Set the value of the BooleanWritable]]> + </doc> + </method> + <method name="get" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the value of the BooleanWritable]]> + </doc> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="compareTo" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[A WritableComparable for booleans.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.BooleanWritable --> + <!-- start class org.apache.hadoop.io.BooleanWritable.Comparator --> + <class name="BooleanWritable.Comparator" extends="org.apache.hadoop.io.WritableComparator" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="BooleanWritable.Comparator" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="compare" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b1" type="byte[]"/> + <param name="s1" type="int"/> + <param name="l1" type="int"/> + <param name="b2" type="byte[]"/> + <param name="s2" type="int"/> + <param name="l2" type="int"/> + </method> + <doc> + <![CDATA[A Comparator optimized for BooleanWritable.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.BooleanWritable.Comparator --> + <!-- start class org.apache.hadoop.io.BytesWritable --> + <class name="BytesWritable" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.WritableComparable"/> + <constructor name="BytesWritable" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Create a zero-size sequence.]]> + </doc> + </constructor> + <constructor name="BytesWritable" type="byte[]" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Create a BytesWritable using the byte array as the initial value. + @param bytes This array becomes the backing storage for the object.]]> + </doc> + </constructor> + <method name="get" return="byte[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the data from the BytesWritable. + @return The data is only valid between 0 and getSize() - 1.]]> + </doc> + </method> + <method name="getSize" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the current size of the buffer.]]> + </doc> + </method> + <method name="setSize" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="size" type="int"/> + <doc> + <![CDATA[Change the size of the buffer. The values in the old range are preserved + and any new values are undefined. The capacity is changed if it is + necessary. + @param size The new number of bytes]]> + </doc> + </method> + <method name="getCapacity" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the capacity, which is the maximum size that could handled without + resizing the backing storage. + @return The number of bytes]]> + </doc> + </method> + <method name="setCapacity" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="new_cap" type="int"/> + <doc> + <![CDATA[Change the capacity of the backing storage. + The data is preserved. + @param new_cap The new capacity in bytes.]]> + </doc> + </method> + <method name="set" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="newData" type="org.apache.hadoop.io.BytesWritable"/> + <doc> + <![CDATA[Set the BytesWritable to the contents of the given newData. + @param newData the value to set this BytesWritable to.]]> + </doc> + </method> + <method name="set" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="newData" type="byte[]"/> + <param name="offset" type="int"/> + <param name="length" type="int"/> + <doc> + <![CDATA[Set the value to a copy of the given byte range + @param newData the new values to copy in + @param offset the offset in newData to start at + @param length the number of bytes to copy]]> + </doc> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="compareTo" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="right_obj" type="java.lang.Object"/> + <doc> + <![CDATA[Define the sort order of the BytesWritable. + @param right_obj The other bytes writable + @return Positive if left is bigger than right, 0 if they are equal, and + negative if left is smaller than right.]]> + </doc> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="right_obj" type="java.lang.Object"/> + <doc> + <![CDATA[Are the two byte sequences equal?]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Generate the stream of bytes as hex pairs separated by ' '.]]> + </doc> + </method> + <doc> + <![CDATA[A byte sequence that is usable as a key or value. + It is resizable and distinguishes between the size of the seqeunce and + the current capacity. The hash function is the front of the md5 of the + buffer. The sort order is the same as memcmp.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.BytesWritable --> + <!-- start class org.apache.hadoop.io.BytesWritable.Comparator --> + <class name="BytesWritable.Comparator" extends="org.apache.hadoop.io.WritableComparator" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="BytesWritable.Comparator" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="compare" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b1" type="byte[]"/> + <param name="s1" type="int"/> + <param name="l1" type="int"/> + <param name="b2" type="byte[]"/> + <param name="s2" type="int"/> + <param name="l2" type="int"/> + <doc> + <![CDATA[Compare the buffers in serialized form.]]> + </doc> + </method> + <doc> + <![CDATA[A Comparator optimized for BytesWritable.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.BytesWritable.Comparator --> + <!-- start interface org.apache.hadoop.io.Closeable --> + <interface name="Closeable" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Called after the last call to any other method on this object to free + and/or flush resources. Typical implementations do nothing.]]> + </doc> + </method> + <doc> + <![CDATA[That which can be closed.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.io.Closeable --> + <!-- start class org.apache.hadoop.io.CompressedWritable --> + <class name="CompressedWritable" extends="java.lang.Object" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <constructor name="CompressedWritable" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="ensureInflated" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[Must be called by all methods which access fields to ensure that the data + has been uncompressed.]]> + </doc> + </method> + <method name="readFieldsCompressed" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Subclasses implement this instead of {@link #readFields(DataInput)}.]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeCompressed" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Subclasses implement this instead of {@link #write(DataOutput)}.]]> + </doc> + </method> + <doc> + <![CDATA[A base-class for Writables which store themselves compressed and lazily + inflate on field access. This is useful for large objects whose fields are + not be altered during a map or reduce operation: leaving the field data + compressed makes copying the instance from one file to another much + faster.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.CompressedWritable --> + <!-- start class org.apache.hadoop.io.DataInputBuffer --> + <class name="DataInputBuffer" extends="java.io.DataInputStream" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="DataInputBuffer" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Constructs a new empty buffer.]]> + </doc> + </constructor> + <method name="reset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="input" type="byte[]"/> + <param name="length" type="int"/> + <doc> + <![CDATA[Resets the data that the buffer reads.]]> + </doc> + </method> + <method name="reset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="input" type="byte[]"/> + <param name="start" type="int"/> + <param name="length" type="int"/> + <doc> + <![CDATA[Resets the data that the buffer reads.]]> + </doc> + </method> + <method name="getPosition" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the current position in the input.]]> + </doc> + </method> + <method name="getLength" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the length of the input.]]> + </doc> + </method> + <doc> + <![CDATA[A reusable {@link DataInput} implementation that reads from an in-memory + buffer. + + <p>This saves memory over creating a new DataInputStream and + ByteArrayInputStream each time data is read. + + <p>Typical usage is something like the following:<pre> + + DataInputBuffer buffer = new DataInputBuffer(); + while (... loop condition ...) { + byte[] data = ... get data ...; + int dataLength = ... get data length ...; + buffer.reset(data, dataLength); + ... read buffer using DataInput methods ... + } + </pre>]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.DataInputBuffer --> + <!-- start class org.apache.hadoop.io.DataOutputBuffer --> + <class name="DataOutputBuffer" extends="java.io.DataOutputStream" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="DataOutputBuffer" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Constructs a new empty buffer.]]> + </doc> + </constructor> + <method name="getData" return="byte[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the current contents of the buffer. + Data is only valid to {@link #getLength()}.]]> + </doc> + </method> + <method name="getLength" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the length of the valid data currently in the buffer.]]> + </doc> + </method> + <method name="reset" return="org.apache.hadoop.io.DataOutputBuffer" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Resets the buffer to empty.]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <param name="length" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Writes bytes from a DataInput directly into the buffer.]]> + </doc> + </method> + <doc> + <![CDATA[A reusable {@link DataOutput} implementation that writes to an in-memory + buffer. + + <p>This saves memory over creating a new DataOutputStream and + ByteArrayOutputStream each time data is written. + + <p>Typical usage is something like the following:<pre> + + DataOutputBuffer buffer = new DataOutputBuffer(); + while (... loop condition ...) { + buffer.reset(); + ... write buffer using DataOutput methods ... + byte[] data = buffer.getData(); + int dataLength = buffer.getLength(); + ... write data to its ultimate destination ... + } + </pre>]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.DataOutputBuffer --> + <!-- start class org.apache.hadoop.io.DefaultStringifier --> + <class name="DefaultStringifier" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Stringifier<T>"/> + <constructor name="DefaultStringifier" type="org.apache.hadoop.conf.Configuration, java.lang.Class<T>" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="fromString" return="T" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="str" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="obj" type="T"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="store" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="item" type="K"/> + <param name="keyName" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Stores the item in the configuration with the given keyName. + + @param <K> the class of the item + @param conf the configuration to store + @param item the object to be stored + @param keyName the name of the key to use + @throws IOException : forwards Exceptions from the underlying + {@link Serialization} classes.]]> + </doc> + </method> + <method name="load" return="K" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="keyName" type="java.lang.String"/> + <param name="itemClass" type="java.lang.Class<K>"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Restores the object from the configuration. + + @param <K> the class of the item + @param conf the configuration to use + @param keyName the name of the key to use + @param itemClass the class of the item + @return restored object + @throws IOException : forwards Exceptions from the underlying + {@link Serialization} classes.]]> + </doc> + </method> + <method name="storeArray" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="items" type="K[]"/> + <param name="keyName" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Stores the array of items in the configuration with the given keyName. + + @param <K> the class of the item + @param conf the configuration to use + @param items the objects to be stored + @param keyName the name of the key to use + @throws IndexOutOfBoundsException if the items array is empty + @throws IOException : forwards Exceptions from the underlying + {@link Serialization} classes.]]> + </doc> + </method> + <method name="loadArray" return="K[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="keyName" type="java.lang.String"/> + <param name="itemClass" type="java.lang.Class<K>"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Restores the array of objects from the configuration. + + @param <K> the class of the item + @param conf the configuration to use + @param keyName the name of the key to use + @param itemClass the class of the item + @return restored object + @throws IOException : forwards Exceptions from the underlying + {@link Serialization} classes.]]> + </doc> + </method> + <doc> + <![CDATA[DefaultStringifier is the default implementation of the {@link Stringifier} + interface which stringifies the objects using base64 encoding of the + serialized version of the objects. The {@link Serializer} and + {@link Deserializer} are obtained from the {@link SerializationFactory}. + <br> + DefaultStringifier offers convenience methods to store/load objects to/from + the configuration. + + @param <T> the class of the objects to stringify]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.DefaultStringifier --> + <!-- start class org.apache.hadoop.io.FloatWritable --> + <class name="FloatWritable" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.WritableComparable"/> + <constructor name="FloatWritable" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="FloatWritable" type="float" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="set" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="value" type="float"/> + <doc> + <![CDATA[Set the value of this FloatWritable.]]> + </doc> + </method> + <method name="get" return="float" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the value of this FloatWritable.]]> + </doc> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + <doc> + <![CDATA[Returns true iff <code>o</code> is a FloatWritable with the same value.]]> + </doc> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="compareTo" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + <doc> + <![CDATA[Compares two FloatWritables.]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[A WritableComparable for floats.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.FloatWritable --> + <!-- start class org.apache.hadoop.io.FloatWritable.Comparator --> + <class name="FloatWritable.Comparator" extends="org.apache.hadoop.io.WritableComparator" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="FloatWritable.Comparator" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="compare" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b1" type="byte[]"/> + <param name="s1" type="int"/> + <param name="l1" type="int"/> + <param name="b2" type="byte[]"/> + <param name="s2" type="int"/> + <param name="l2" type="int"/> + </method> + <doc> + <![CDATA[A Comparator optimized for FloatWritable.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.FloatWritable.Comparator --> + <!-- start class org.apache.hadoop.io.GenericWritable --> + <class name="GenericWritable" extends="java.lang.Object" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <implements name="org.apache.hadoop.conf.Configurable"/> + <constructor name="GenericWritable" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="set" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="obj" type="org.apache.hadoop.io.Writable"/> + <doc> + <![CDATA[Set the instance that is wrapped. + + @param obj]]> + </doc> + </method> + <method name="get" return="org.apache.hadoop.io.Writable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the wrapped instance.]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getTypes" return="java.lang.Class[]" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[Return all classes that may be wrapped. Subclasses should implement this + to return a constant array of classes.]]> + </doc> + </method> + <method name="getConf" return="org.apache.hadoop.conf.Configuration" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="setConf" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + </method> + <doc> + <![CDATA[A wrapper for Writable instances. + <p> + When two sequence files, which have same Key type but different Value + types, are mapped out to reduce, multiple Value types is not allowed. + In this case, this class can help you wrap instances with different types. + </p> + + <p> + Compared with <code>ObjectWritable</code>, this class is much more effective, + because <code>ObjectWritable</code> will append the class declaration as a String + into the output file in every Key-Value pair. + </p> + + <p> + Generic Writable implements {@link Configurable} interface, so that it will be + configured by the framework. The configuration is passed to the wrapped objects + implementing {@link Configurable} interface <i>before deserialization</i>. + </p> + + how to use it: <br> + 1. Write your own class, such as GenericObject, which extends GenericWritable.<br> + 2. Implements the abstract method <code>getTypes()</code>, defines + the classes which will be wrapped in GenericObject in application. + Attention: this classes defined in <code>getTypes()</code> method, must + implement <code>Writable</code> interface. + <br><br> + + The code looks like this: + <blockquote><pre> + public class GenericObject extends GenericWritable { + + private static Class[] CLASSES = { + ClassType1.class, + ClassType2.class, + ClassType3.class, + }; + + protected Class[] getTypes() { + return CLASSES; + } + + } + </pre></blockquote> + + @since Nov 8, 2006]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.GenericWritable --> + <!-- start class org.apache.hadoop.io.InputBuffer --> + <class name="InputBuffer" extends="java.io.FilterInputStream" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="InputBuffer" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Constructs a new empty buffer.]]> + </doc> + </constructor> + <method name="reset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="input" type="byte[]"/> + <param name="length" type="int"/> + <doc> + <![CDATA[Resets the data that the buffer reads.]]> + </doc> + </method> + <method name="reset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="input" type="byte[]"/> + <param name="start" type="int"/> + <param name="length" type="int"/> + <doc> + <![CDATA[Resets the data that the buffer reads.]]> + </doc> + </method> + <method name="getPosition" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the current position in the input.]]> + </doc> + </method> + <method name="getLength" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the length of the input.]]> + </doc> + </method> + <doc> + <![CDATA[A reusable {@link InputStream} implementation that reads from an in-memory + buffer. + + <p>This saves memory over creating a new InputStream and + ByteArrayInputStream each time data is read. + + <p>Typical usage is something like the following:<pre> + + InputBuffer buffer = new InputBuffer(); + while (... loop condition ...) { + byte[] data = ... get data ...; + int dataLength = ... get data length ...; + buffer.reset(data, dataLength); + ... read buffer using InputStream methods ... + } + </pre> + @see DataInputBuffer + @see DataOutput]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.InputBuffer --> + <!-- start class org.apache.hadoop.io.IntWritable --> + <class name="IntWritable" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.WritableComparable"/> + <constructor name="IntWritable" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="IntWritable" type="int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="set" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="value" type="int"/> + <doc> + <![CDATA[Set the value of this IntWritable.]]> + </doc> + </method> + <method name="get" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the value of this IntWritable.]]> + </doc> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + <doc> + <![CDATA[Returns true iff <code>o</code> is a IntWritable with the same value.]]> + </doc> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="compareTo" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + <doc> + <![CDATA[Compares two IntWritables.]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[A WritableComparable for ints.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.IntWritable --> + <!-- start class org.apache.hadoop.io.IntWritable.Comparator --> + <class name="IntWritable.Comparator" extends="org.apache.hadoop.io.WritableComparator" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="IntWritable.Comparator" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="compare" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b1" type="byte[]"/> + <param name="s1" type="int"/> + <param name="l1" type="int"/> + <param name="b2" type="byte[]"/> + <param name="s2" type="int"/> + <param name="l2" type="int"/> + </method> + <doc> + <![CDATA[A Comparator optimized for IntWritable.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.IntWritable.Comparator --> + <!-- start class org.apache.hadoop.io.IOUtils --> + <class name="IOUtils" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="IOUtils" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="copyBytes" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.InputStream"/> + <param name="out" type="java.io.OutputStream"/> + <param name="buffSize" type="int"/> + <param name="close" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Copies from one stream to another. + @param in InputStrem to read from + @param out OutputStream to write to + @param buffSize the size of the buffer + @param close whether or not close the InputStream and + OutputStream at the end. The streams are closed in the finally clause.]]> + </doc> + </method> + <method name="copyBytes" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.InputStream"/> + <param name="out" type="java.io.OutputStream"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Copies from one stream to another. <strong>closes the input and output streams + at the end</strong>. + @param in InputStrem to read from + @param out OutputStream to write to + @param conf the Configuration object]]> + </doc> + </method> + <method name="copyBytes" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.InputStream"/> + <param name="out" type="java.io.OutputStream"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="close" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Copies from one stream to another. + @param in InputStrem to read from + @param out OutputStream to write to + @param conf the Configuration object + @param close whether or not close the InputStream and + OutputStream at the end. The streams are closed in the finally clause.]]> + </doc> + </method> + <method name="readFully" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.InputStream"/> + <param name="buf" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Reads len bytes in a loop. + @param in The InputStream to read from + @param buf The buffer to fill + @param off offset from the buffer + @param len the length of bytes to read + @throws IOException if it could not read requested number of bytes + for any reason (including EOF)]]> + </doc> + </method> + <method name="skipFully" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.InputStream"/> + <param name="len" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Similar to readFully(). Skips bytes in a loop. + @param in The InputStream to skip bytes from + @param len number of bytes to skip. + @throws IOException if it could not skip requested number of bytes + for any reason (including EOF)]]> + </doc> + </method> + <method name="closeStream" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="stream" type="java.io.Closeable"/> + <doc> + <![CDATA[Closes the stream ignoring {@link IOException} + @param stream the Stream to close]]> + </doc> + </method> + <method name="closeSocket" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="sock" type="java.net.Socket"/> + <doc> + <![CDATA[Closes the socket ignoring {@link IOException} + @param sock the Socket to close]]> + </doc> + </method> + <doc> + <![CDATA[An utility class for I/O related functionality.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.IOUtils --> + <!-- start class org.apache.hadoop.io.IOUtils.NullOutputStream --> + <class name="IOUtils.NullOutputStream" extends="java.io.OutputStream" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="IOUtils.NullOutputStream" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[/dev/null of OutputStreams.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.IOUtils.NullOutputStream --> + <!-- start class org.apache.hadoop.io.LongWritable --> + <class name="LongWritable" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.WritableComparable"/> + <constructor name="LongWritable" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="LongWritable" type="long" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="set" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="value" type="long"/> + <doc> + <![CDATA[Set the value of this LongWritable.]]> + </doc> + </method> + <method name="get" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the value of this LongWritable.]]> + </doc> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + <doc> + <![CDATA[Returns true iff <code>o</code> is a LongWritable with the same value.]]> + </doc> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="compareTo" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + <doc> + <![CDATA[Compares two LongWritables.]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[A WritableComparable for longs.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.LongWritable --> + <!-- start class org.apache.hadoop.io.LongWritable.Comparator --> + <class name="LongWritable.Comparator" extends="org.apache.hadoop.io.WritableComparator" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="LongWritable.Comparator" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="compare" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b1" type="byte[]"/> + <param name="s1" type="int"/> + <param name="l1" type="int"/> + <param name="b2" type="byte[]"/> + <param name="s2" type="int"/> + <param name="l2" type="int"/> + </method> + <doc> + <![CDATA[A Comparator optimized for LongWritable.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.LongWritable.Comparator --> + <!-- start class org.apache.hadoop.io.LongWritable.DecreasingComparator --> + <class name="LongWritable.DecreasingComparator" extends="org.apache.hadoop.io.LongWritable.Comparator" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="LongWritable.DecreasingComparator" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="compare" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="a" type="org.apache.hadoop.io.WritableComparable"/> + <param name="b" type="org.apache.hadoop.io.WritableComparable"/> + </method> + <method name="compare" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b1" type="byte[]"/> + <param name="s1" type="int"/> + <param name="l1" type="int"/> + <param name="b2" type="byte[]"/> + <param name="s2" type="int"/> + <param name="l2" type="int"/> + </method> + <doc> + <![CDATA[A decreasing Comparator optimized for LongWritable.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.LongWritable.DecreasingComparator --> + <!-- start class org.apache.hadoop.io.MapFile --> + <class name="MapFile" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="MapFile" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </constructor> + <method name="rename" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <param name="oldName" type="java.lang.String"/> + <param name="newName" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Renames an existing map directory.]]> + </doc> + </method> + <method name="delete" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <param name="name" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Deletes the named map file.]]> + </doc> + </method> + <method name="fix" return="long" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <param name="dir" type="org.apache.hadoop.fs.Path"/> + <param name="keyClass" type="java.lang.Class"/> + <param name="valueClass" type="java.lang.Class"/> + <param name="dryrun" type="boolean"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="Exception" type="java.lang.Exception"/> + <doc> + <![CDATA[This method attempts to fix a corrupt MapFile by re-creating its index. + @param fs filesystem + @param dir directory containing the MapFile data and index + @param keyClass key class (has to be a subclass of Writable) + @param valueClass value class (has to be a subclass of Writable) + @param dryrun do not perform any changes, just report what needs to be done + @return number of valid entries in this MapFile, or -1 if no fixing was needed + @throws Exception]]> + </doc> + </method> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + </method> + <field name="INDEX_FILE_NAME" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The name of the index file.]]> + </doc> + </field> + <field name="DATA_FILE_NAME" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The name of the data file.]]> + </doc> + </field> + <doc> + <![CDATA[A file-based map from keys to values. + + <p>A map is a directory containing two files, the <code>data</code> file, + containing all keys and values in the map, and a smaller <code>index</code> + file, containing a fraction of the keys. The fraction is determined by + {@link Writer#getIndexInterval()}. + + <p>The index file is read entirely into memory. Thus key implementations + should try to keep themselves small. + + <p>Map files are created by adding entries in-order. To maintain a large + database, perform updates by copying the previous version of a database and + merging in a sorted change list, to create a new version of the database in + a new file. Sorting large change lists can be done with {@link + SequenceFile.Sorter}.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.MapFile --> + <!-- start class org.apache.hadoop.io.MapFile.Reader --> + <class name="MapFile.Reader" extends="java.lang.Object" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="MapFile.Reader" type="org.apache.hadoop.fs.FileSystem, java.lang.String, org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct a map reader for the named map.]]> + </doc> + </constructor> + <constructor name="MapFile.Reader" type="org.apache.hadoop.fs.FileSystem, java.lang.String, org.apache.hadoop.io.WritableComparator, org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct a map reader for the named map using the named comparator.]]> + </doc> + </constructor> + <constructor name="MapFile.Reader" type="org.apache.hadoop.fs.FileSystem, java.lang.String, org.apache.hadoop.io.WritableComparator, org.apache.hadoop.conf.Configuration, boolean" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Hook to allow subclasses to defer opening streams until further + initialization is complete. + @see #createDataFileReader(FileSystem, Path, Configuration)]]> + </doc> + </constructor> + <method name="getKeyClass" return="java.lang.Class" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the class of keys in this file.]]> + </doc> + </method> + <method name="getValueClass" return="java.lang.Class" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the class of values in this file.]]> + </doc> + </method> + <method name="open" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <param name="dirName" type="java.lang.String"/> + <param name="comparator" type="org.apache.hadoop.io.WritableComparator"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="createDataFileReader" return="org.apache.hadoop.io.SequenceFile.Reader" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <param name="dataFile" type="org.apache.hadoop.fs.Path"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Override this method to specialize the type of + {@link SequenceFile.Reader} returned.]]> + </doc> + </method> + <method name="reset" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Re-positions the reader before its first key.]]> + </doc> + </method> + <method name="midKey" return="org.apache.hadoop.io.WritableComparable" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get the key at approximately the middle of the file. + + @throws IOException]]> + </doc> + </method> + <method name="finalKey" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.WritableComparable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Reads the final key from the file. + + @param key key to read into]]> + </doc> + </method> + <method name="seek" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.WritableComparable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Positions the reader at the named key, or if none such exists, at the + first entry after the named key. Returns true iff the named key exists + in this map.]]> + </doc> + </method> + <method name="next" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.WritableComparable"/> + <param name="val" type="org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read the next key/value pair in the map into <code>key</code> and + <code>val</code>. Returns true if such a pair exists and false when at + the end of the map]]> + </doc> + </method> + <method name="get" return="org.apache.hadoop.io.Writable" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.WritableComparable"/> + <param name="val" type="org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return the value for the named key, or null if none exists.]]> + </doc> + </method> + <method name="getClosest" return="org.apache.hadoop.io.WritableComparable" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.WritableComparable"/> + <param name="val" type="org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Finds the record that is the closest match to the specified key. + Returns <code>key</code> or if it does not exist, at the first entry + after the named key. + +- * @param key - key that we're trying to find +- * @param val - data value if key is found +- * @return - the key that was the closest match or null if eof.]]> + </doc> + </method> + <method name="getClosest" return="org.apache.hadoop.io.WritableComparable" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.WritableComparable"/> + <param name="val" type="org.apache.hadoop.io.Writable"/> + <param name="before" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Finds the record that is the closest match to the specified key. + + @param key - key that we're trying to find + @param val - data value if key is found + @param before - IF true, and <code>key</code> does not exist, return + the first entry that falls just before the <code>key</code>. Otherwise, + return the record that sorts just after. + @return - the key that was the closest match or null if eof.]]> + </doc> + </method> + <method name="close" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Close the map.]]> + </doc> + </method> + <doc> + <![CDATA[Provide access to an existing map.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.MapFile.Reader --> + <!-- start class org.apache.hadoop.io.MapFile.Writer --> + <class name="MapFile.Writer" extends="java.lang.Object" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="MapFile.Writer" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.fs.FileSystem, java.lang.String, java.lang.Class, java.lang.Class" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create the named map for keys of the named class.]]> + </doc> + </constructor> + <constructor name="MapFile.Writer" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.fs.FileSystem, java.lang.String, java.lang.Class, java.lang.Class, org.apache.hadoop.io.SequenceFile.CompressionType, org.apache.hadoop.util.Progressable" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create the named map for keys of the named class.]]> + </doc> + </constructor> + <constructor name="MapFile.Writer" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.fs.FileSystem, java.lang.String, java.lang.Class, java.lang.Class, org.apache.hadoop.io.SequenceFile.CompressionType, org.apache.hadoop.io.compress.CompressionCodec, org.apache.hadoop.util.Progressable" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create the named map for keys of the named class.]]> + </doc> + </constructor> + <constructor name="MapFile.Writer" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.fs.FileSystem, java.lang.String, java.lang.Class, java.lang.Class, org.apache.hadoop.io.SequenceFile.CompressionType" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create the named map for keys of the named class.]]> + </doc> + </constructor> + <constructor name="MapFile.Writer" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.fs.FileSystem, java.lang.String, org.apache.hadoop.io.WritableComparator, java.lang.Class" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create the named map using the named key comparator.]]> + </doc> + </constructor> + <constructor name="MapFile.Writer" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.fs.FileSystem, java.lang.String, org.apache.hadoop.io.WritableComparator, java.lang.Class, org.apache.hadoop.io.SequenceFile.CompressionType" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create the named map using the named key comparator.]]> + </doc> + </constructor> + <constructor name="MapFile.Writer" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.fs.FileSystem, java.lang.String, org.apache.hadoop.io.WritableComparator, java.lang.Class, org.apache.hadoop.io.SequenceFile.CompressionType, org.apache.hadoop.util.Progressable" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create the named map using the named key comparator.]]> + </doc> + </constructor> + <constructor name="MapFile.Writer" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.fs.FileSystem, java.lang.String, org.apache.hadoop.io.WritableComparator, java.lang.Class, org.apache.hadoop.io.SequenceFile.CompressionType, org.apache.hadoop.io.compress.CompressionCodec, org.apache.hadoop.util.Progressable" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create the named map using the named key comparator.]]> + </doc> + </constructor> + <method name="getIndexInterval" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The number of entries that are added before an index entry is added.]]> + </doc> + </method> + <method name="setIndexInterval" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="interval" type="int"/> + <doc> + <![CDATA[Sets the index interval. + @see #getIndexInterval()]]> + </doc> + </method> + <method name="setIndexInterval" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="interval" type="int"/> + <doc> + <![CDATA[Sets the index interval and stores it in conf + @see #getIndexInterval()]]> + </doc> + </method> + <method name="close" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Close the map.]]> + </doc> + </method> + <method name="append" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.WritableComparable"/> + <param name="val" type="org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Append a key/value pair to the map. The key must be greater or equal + to the previous key added to the map.]]> + </doc> + </method> + <doc> + <![CDATA[Writes a new map.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.MapFile.Writer --> + <!-- start class org.apache.hadoop.io.MapWritable --> + <class name="MapWritable" extends="org.apache.hadoop.io.AbstractMapWritable" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="java.util.Map<org.apache.hadoop.io.Writable, org.apache.hadoop.io.Writable>"/> + <constructor name="MapWritable" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Default constructor.]]> + </doc> + </constructor> + <constructor name="MapWritable" type="org.apache.hadoop.io.MapWritable" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Copy constructor. + + @param other the map to copy from]]> + </doc> + </constructor> + <method name="clear" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="containsKey" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="java.lang.Object"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="containsValue" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="value" type="java.lang.Object"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="entrySet" return="java.util.Set<java.util.Map.Entry<org.apache.hadoop.io.Writable, org.apache.hadoop.io.Writable>>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="get" return="org.apache.hadoop.io.Writable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="java.lang.Object"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="isEmpty" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="keySet" return="java.util.Set<org.apache.hadoop.io.Writable>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="put" return="org.apache.hadoop.io.Writable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.Writable"/> + <param name="value" type="org.apache.hadoop.io.Writable"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="putAll" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="t" type="java.util.Map<? extends org.apache.hadoop.io.Writable, ? extends org.apache.hadoop.io.Writable>"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="remove" return="org.apache.hadoop.io.Writable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="java.lang.Object"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="size" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="values" return="java.util.Collection<org.apache.hadoop.io.Writable>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <doc> + <![CDATA[A Writable Map.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.MapWritable --> + <!-- start class org.apache.hadoop.io.MD5Hash --> + <class name="MD5Hash" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.WritableComparable"/> + <constructor name="MD5Hash" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Constructs an MD5Hash.]]> + </doc> + </constructor> + <constructor name="MD5Hash" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Constructs an MD5Hash from a hex string.]]> + </doc> + </constructor> + <constructor name="MD5Hash" type="byte[]" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Constructs an MD5Hash with a specified value.]]> + </doc> + </constructor> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="read" return="org.apache.hadoop.io.MD5Hash" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Constructs, reads and returns an instance.]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="set" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="that" type="org.apache.hadoop.io.MD5Hash"/> + <doc> + <![CDATA[Copy the contents of another instance into this instance.]]> + </doc> + </method> + <method name="getDigest" return="byte[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the digest bytes.]]> + </doc> + </method> + <method name="digest" return="org.apache.hadoop.io.MD5Hash" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="data" type="byte[]"/> + <doc> + <![CDATA[Construct a hash value for a byte array.]]> + </doc> + </method> + <method name="digest" return="org.apache.hadoop.io.MD5Hash" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="data" type="byte[]"/> + <param name="start" type="int"/> + <param name="len" type="int"/> + <doc> + <![CDATA[Construct a hash value for a byte array.]]> + </doc> + </method> + <method name="digest" return="org.apache.hadoop.io.MD5Hash" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="string" type="java.lang.String"/> + <doc> + <![CDATA[Construct a hash value for a String.]]> + </doc> + </method> + <method name="digest" return="org.apache.hadoop.io.MD5Hash" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="utf8" type="org.apache.hadoop.io.UTF8"/> + <doc> + <![CDATA[Construct a hash value for a String.]]> + </doc> + </method> + <method name="halfDigest" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct a half-sized version of this MD5. Fits in a long]]> + </doc> + </method> + <method name="quarterDigest" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return a 32-bit digest of the MD5. + @return the first 4 bytes of the md5]]> + </doc> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + <doc> + <![CDATA[Returns true iff <code>o</code> is an MD5Hash whose digest contains the + same values.]]> + </doc> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns a hash code value for this object. + Only uses the first 4 bytes, since md5s are evenly distributed.]]> + </doc> + </method> + <method name="compareTo" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + <doc> + <![CDATA[Compares this object with the specified object for order.]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns a string representation of this object.]]> + </doc> + </method> + <method name="setDigest" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="hex" type="java.lang.String"/> + <doc> + <![CDATA[Sets the digest value from a hex string.]]> + </doc> + </method> + <field name="MD5_LEN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[A Writable for MD5 hash values.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.MD5Hash --> + <!-- start class org.apache.hadoop.io.MD5Hash.Comparator --> + <class name="MD5Hash.Comparator" extends="org.apache.hadoop.io.WritableComparator" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="MD5Hash.Comparator" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="compare" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b1" type="byte[]"/> + <param name="s1" type="int"/> + <param name="l1" type="int"/> + <param name="b2" type="byte[]"/> + <param name="s2" type="int"/> + <param name="l2" type="int"/> + </method> + <doc> + <![CDATA[A WritableComparator optimized for MD5Hash keys.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.MD5Hash.Comparator --> + <!-- start class org.apache.hadoop.io.MultipleIOException --> + <class name="MultipleIOException" extends="java.io.IOException" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="getExceptions" return="java.util.List<java.io.IOException>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the underlying exceptions]]> + </doc> + </method> + <method name="createIOException" return="java.io.IOException" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="exceptions" type="java.util.List<java.io.IOException>"/> + <doc> + <![CDATA[A convenient method to create an {@link IOException}.]]> + </doc> + </method> + <doc> + <![CDATA[Encapsulate a list of {@link IOException} into an {@link IOException}]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.MultipleIOException --> + <!-- start class org.apache.hadoop.io.NullWritable --> + <class name="NullWritable" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.WritableComparable"/> + <method name="get" return="org.apache.hadoop.io.NullWritable" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the single instance of this class.]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="compareTo" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="other" type="java.lang.Object"/> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="other" type="java.lang.Object"/> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[Singleton Writable with no data.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.NullWritable --> + <!-- start class org.apache.hadoop.io.ObjectWritable --> + <class name="ObjectWritable" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <implements name="org.apache.hadoop.conf.Configurable"/> + <constructor name="ObjectWritable" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="ObjectWritable" type="java.lang.Object" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="ObjectWritable" type="java.lang.Class, java.lang.Object" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="get" return="java.lang.Object" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the instance, or null if none.]]> + </doc> + </method> + <method name="getDeclaredClass" return="java.lang.Class" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the class this is meant to be.]]> + </doc> + </method> + <method name="set" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="instance" type="java.lang.Object"/> + <doc> + <![CDATA[Reset the instance.]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeObject" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <param name="instance" type="java.lang.Object"/> + <param name="declaredClass" type="java.lang.Class"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Write a {@link Writable}, {@link String}, primitive type, or an array of + the preceding.]]> + </doc> + </method> + <method name="readObject" return="java.lang.Object" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read a {@link Writable}, {@link String}, primitive type, or an array of + the preceding.]]> + </doc> + </method> + <method name="readObject" return="java.lang.Object" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <param name="objectWritable" type="org.apache.hadoop.io.ObjectWritable"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read a {@link Writable}, {@link String}, primitive type, or an array of + the preceding.]]> + </doc> + </method> + <method name="setConf" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + </method> + <method name="getConf" return="org.apache.hadoop.conf.Configuration" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[A polymorphic Writable that writes an instance with it's class name. + Handles arrays, strings and primitive types without a Writable wrapper.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.ObjectWritable --> + <!-- start class org.apache.hadoop.io.OutputBuffer --> + <class name="OutputBuffer" extends="java.io.FilterOutputStream" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="OutputBuffer" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Constructs a new empty buffer.]]> + </doc> + </constructor> + <method name="getData" return="byte[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the current contents of the buffer. + Data is only valid to {@link #getLength()}.]]> + </doc> + </method> + <method name="getLength" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the length of the valid data currently in the buffer.]]> + </doc> + </method> + <method name="reset" return="org.apache.hadoop.io.OutputBuffer" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Resets the buffer to empty.]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.InputStream"/> + <param name="length" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Writes bytes from a InputStream directly into the buffer.]]> + </doc> + </method> + <doc> + <![CDATA[A reusable {@link OutputStream} implementation that writes to an in-memory + buffer. + + <p>This saves memory over creating a new OutputStream and + ByteArrayOutputStream each time data is written. + + <p>Typical usage is something like the following:<pre> + + OutputBuffer buffer = new OutputBuffer(); + while (... loop condition ...) { + buffer.reset(); + ... write buffer using OutputStream methods ... + byte[] data = buffer.getData(); + int dataLength = buffer.getLength(); + ... write data to its ultimate destination ... + } + </pre> + @see DataOutputBuffer + @see InputBuffer]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.OutputBuffer --> + <!-- start interface org.apache.hadoop.io.RawComparator --> + <interface name="RawComparator" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="java.util.Comparator<T>"/> + <method name="compare" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b1" type="byte[]"/> + <param name="s1" type="int"/> + <param name="l1" type="int"/> + <param name="b2" type="byte[]"/> + <param name="s2" type="int"/> + <param name="l2" type="int"/> + </method> + <doc> + <![CDATA[<p> + A {@link Comparator} that operates directly on byte representations of + objects. + </p> + @param <T> + @see DeserializerComparator]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.io.RawComparator --> + <!-- start class org.apache.hadoop.io.SequenceFile --> + <class name="SequenceFile" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="getCompressionType" return="org.apache.hadoop.io.SequenceFile.CompressionType" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="Use {@link org.apache.hadoop.mapred.JobConf#getMapOutputCompressionType()} + to get {@link CompressionType} for intermediate map-outputs or + {@link org.apache.hadoop.mapred.SequenceFileOutputFormat#getOutputCompressionType(org.apache.hadoop.mapred.JobConf)} + to get {@link CompressionType} for job-outputs."> + <param name="job" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[Get the compression type for the reduce outputs + @param job the job config to look in + @return the kind of compression to use + @deprecated Use {@link org.apache.hadoop.mapred.JobConf#getMapOutputCompressionType()} + to get {@link CompressionType} for intermediate map-outputs or + {@link org.apache.hadoop.mapred.SequenceFileOutputFormat#getOutputCompressionType(org.apache.hadoop.mapred.JobConf)} + to get {@link CompressionType} for job-outputs.]]> + </doc> + </method> + <method name="setCompressionType" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="Use the one of the many SequenceFile.createWriter methods to specify + the {@link CompressionType} while creating the {@link SequenceFile} or + {@link org.apache.hadoop.mapred.JobConf#setMapOutputCompressionType(org.apache.hadoop.io.SequenceFile.CompressionType)} + to specify the {@link CompressionType} for intermediate map-outputs or + {@link org.apache.hadoop.mapred.SequenceFileOutputFormat#setOutputCompressionType(org.apache.hadoop.mapred.JobConf, org.apache.hadoop.io.SequenceFile.CompressionType)} + to specify the {@link CompressionType} for job-outputs. + or"> + <param name="job" type="org.apache.hadoop.conf.Configuration"/> + <param name="val" type="org.apache.hadoop.io.SequenceFile.CompressionType"/> + <doc> + <![CDATA[Set the compression type for sequence files. + @param job the configuration to modify + @param val the new compression type (none, block, record) + @deprecated Use the one of the many SequenceFile.createWriter methods to specify + the {@link CompressionType} while creating the {@link SequenceFile} or + {@link org.apache.hadoop.mapred.JobConf#setMapOutputCompressionType(org.apache.hadoop.io.SequenceFile.CompressionType)} + to specify the {@link CompressionType} for intermediate map-outputs or + {@link org.apache.hadoop.mapred.SequenceFileOutputFormat#setOutputCompressionType(org.apache.hadoop.mapred.JobConf, org.apache.hadoop.io.SequenceFile.CompressionType)} + to specify the {@link CompressionType} for job-outputs. + or]]> + </doc> + </method> + <method name="createWriter" return="org.apache.hadoop.io.SequenceFile.Writer" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="name" type="org.apache.hadoop.fs.Path"/> + <param name="keyClass" type="java.lang.Class"/> + <param name="valClass" type="java.lang.Class"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct the preferred type of SequenceFile Writer. + @param fs The configured filesystem. + @param conf The configuration. + @param name The name of the file. + @param keyClass The 'key' type. + @param valClass The 'value' type. + @return Returns the handle to the constructed SequenceFile Writer. + @throws IOException]]> + </doc> + </method> + <method name="createWriter" return="org.apache.hadoop.io.SequenceFile.Writer" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="name" type="org.apache.hadoop.fs.Path"/> + <param name="keyClass" type="java.lang.Class"/> + <param name="valClass" type="java.lang.Class"/> + <param name="compressionType" type="org.apache.hadoop.io.SequenceFile.CompressionType"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct the preferred type of SequenceFile Writer. + @param fs The configured filesystem. + @param conf The configuration. + @param name The name of the file. + @param keyClass The 'key' type. + @param valClass The 'value' type. + @param compressionType The compression type. + @return Returns the handle to the constructed SequenceFile Writer. + @throws IOException]]> + </doc> + </method> + <method name="createWriter" return="org.apache.hadoop.io.SequenceFile.Writer" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="name" type="org.apache.hadoop.fs.Path"/> + <param name="keyClass" type="java.lang.Class"/> + <param name="valClass" type="java.lang.Class"/> + <param name="compressionType" type="org.apache.hadoop.io.SequenceFile.CompressionType"/> + <param name="progress" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct the preferred type of SequenceFile Writer. + @param fs The configured filesystem. + @param conf The configuration. + @param name The name of the file. + @param keyClass The 'key' type. + @param valClass The 'value' type. + @param compressionType The compression type. + @param progress The Progressable object to track progress. + @return Returns the handle to the constructed SequenceFile Writer. + @throws IOException]]> + </doc> + </method> + <method name="createWriter" return="org.apache.hadoop.io.SequenceFile.Writer" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="name" type="org.apache.hadoop.fs.Path"/> + <param name="keyClass" type="java.lang.Class"/> + <param name="valClass" type="java.lang.Class"/> + <param name="compressionType" type="org.apache.hadoop.io.SequenceFile.CompressionType"/> + <param name="codec" type="org.apache.hadoop.io.compress.CompressionCodec"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct the preferred type of SequenceFile Writer. + @param fs The configured filesystem. + @param conf The configuration. + @param name The name of the file. + @param keyClass The 'key' type. + @param valClass The 'value' type. + @param compressionType The compression type. + @param codec The compression codec. + @return Returns the handle to the constructed SequenceFile Writer. + @throws IOException]]> + </doc> + </method> + <method name="createWriter" return="org.apache.hadoop.io.SequenceFile.Writer" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="name" type="org.apache.hadoop.fs.Path"/> + <param name="keyClass" type="java.lang.Class"/> + <param name="valClass" type="java.lang.Class"/> + <param name="compressionType" type="org.apache.hadoop.io.SequenceFile.CompressionType"/> + <param name="codec" type="org.apache.hadoop.io.compress.CompressionCodec"/> + <param name="progress" type="org.apache.hadoop.util.Progressable"/> + <param name="metadata" type="org.apache.hadoop.io.SequenceFile.Metadata"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct the preferred type of SequenceFile Writer. + @param fs The configured filesystem. + @param conf The configuration. + @param name The name of the file. + @param keyClass The 'key' type. + @param valClass The 'value' type. + @param compressionType The compression type. + @param codec The compression codec. + @param progress The Progressable object to track progress. + @param metadata The metadata of the file. + @return Returns the handle to the constructed SequenceFile Writer. + @throws IOException]]> + </doc> + </method> + <method name="createWriter" return="org.apache.hadoop.io.SequenceFile.Writer" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="name" type="org.apache.hadoop.fs.Path"/> + <param name="keyClass" type="java.lang.Class"/> + <param name="valClass" type="java.lang.Class"/> + <param name="bufferSize" type="int"/> + <param name="replication" type="short"/> + <param name="blockSize" type="long"/> + <param name="compressionType" type="org.apache.hadoop.io.SequenceFile.CompressionType"/> + <param name="codec" type="org.apache.hadoop.io.compress.CompressionCodec"/> + <param name="progress" type="org.apache.hadoop.util.Progressable"/> + <param name="metadata" type="org.apache.hadoop.io.SequenceFile.Metadata"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct the preferred type of SequenceFile Writer. + @param fs The configured filesystem. + @param conf The configuration. + @param name The name of the file. + @param keyClass The 'key' type. + @param valClass The 'value' type. + @param bufferSize buffer size for the underlaying outputstream. + @param replication replication factor for the file. + @param blockSize block size for the file. + @param compressionType The compression type. + @param codec The compression codec. + @param progress The Progressable object to track progress. + @param metadata The metadata of the file. + @return Returns the handle to the constructed SequenceFile Writer. + @throws IOException]]> + </doc> + </method> + <method name="createWriter" return="org.apache.hadoop.io.SequenceFile.Writer" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="name" type="org.apache.hadoop.fs.Path"/> + <param name="keyClass" type="java.lang.Class"/> + <param name="valClass" type="java.lang.Class"/> + <param name="compressionType" type="org.apache.hadoop.io.SequenceFile.CompressionType"/> + <param name="codec" type="org.apache.hadoop.io.compress.CompressionCodec"/> + <param name="progress" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct the preferred type of SequenceFile Writer. + @param fs The configured filesystem. + @param conf The configuration. + @param name The name of the file. + @param keyClass The 'key' type. + @param valClass The 'value' type. + @param compressionType The compression type. + @param codec The compression codec. + @param progress The Progressable object to track progress. + @return Returns the handle to the constructed SequenceFile Writer. + @throws IOException]]> + </doc> + </method> + <method name="createWriter" return="org.apache.hadoop.io.SequenceFile.Writer" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="out" type="org.apache.hadoop.fs.FSDataOutputStream"/> + <param name="keyClass" type="java.lang.Class"/> + <param name="valClass" type="java.lang.Class"/> + <param name="compressionType" type="org.apache.hadoop.io.SequenceFile.CompressionType"/> + <param name="codec" type="org.apache.hadoop.io.compress.CompressionCodec"/> + <param name="metadata" type="org.apache.hadoop.io.SequenceFile.Metadata"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct the preferred type of 'raw' SequenceFile Writer. + @param conf The configuration. + @param out The stream on top which the writer is to be constructed. + @param keyClass The 'key' type. + @param valClass The 'value' type. + @param compressionType The compression type. + @param codec The compression codec. + @param metadata The metadata of the file. + @return Returns the handle to the constructed SequenceFile Writer. + @throws IOException]]> + </doc> + </method> + <method name="createWriter" return="org.apache.hadoop.io.SequenceFile.Writer" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="out" type="org.apache.hadoop.fs.FSDataOutputStream"/> + <param name="keyClass" type="java.lang.Class"/> + <param name="valClass" type="java.lang.Class"/> + <param name="compressionType" type="org.apache.hadoop.io.SequenceFile.CompressionType"/> + <param name="codec" type="org.apache.hadoop.io.compress.CompressionCodec"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct the preferred type of 'raw' SequenceFile Writer. + @param conf The configuration. + @param out The stream on top which the writer is to be constructed. + @param keyClass The 'key' type. + @param valClass The 'value' type. + @param compressionType The compression type. + @param codec The compression codec. + @return Returns the handle to the constructed SequenceFile Writer. + @throws IOException]]> + </doc> + </method> + <field name="SYNC_INTERVAL" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The number of bytes between sync points.]]> + </doc> + </field> + <doc> + <![CDATA[<code>SequenceFile</code>s are flat files consisting of binary key/value + pairs. + + <p><code>SequenceFile</code> provides {@link Writer}, {@link Reader} and + {@link Sorter} classes for writing, reading and sorting respectively.</p> + + There are three <code>SequenceFile</code> <code>Writer</code>s based on the + {@link CompressionType} used to compress key/value pairs: + <ol> + <li> + <code>Writer</code> : Uncompressed records. + </li> + <li> + <code>RecordCompressWriter</code> : Record-compressed files, only compress + values. + </li> + <li> + <code>BlockCompressWriter</code> : Block-compressed files, both keys & + values are collected in 'blocks' + separately and compressed. The size of + the 'block' is configurable. + </ol> + + <p>The actual compression algorithm used to compress key and/or values can be + specified by using the appropriate {@link CompressionCodec}.</p> + + <p>The recommended way is to use the static <tt>createWriter</tt> methods + provided by the <code>SequenceFile</code> to chose the preferred format.</p> + + <p>The {@link Reader} acts as the bridge and can read any of the above + <code>SequenceFile</code> formats.</p> + + <h4 id="Formats">SequenceFile Formats</h4> + + <p>Essentially there are 3 different formats for <code>SequenceFile</code>s + depending on the <code>CompressionType</code> specified. All of them share a + <a href="#Header">common header</a> described below. + + <h5 id="Header">SequenceFile Header</h5> + <ul> + <li> + version - 3 bytes of magic header <b>SEQ</b>, followed by 1 byte of actual + version number (e.g. SEQ4 or SEQ6) + </li> + <li> + keyClassName -key class + </li> + <li> + valueClassName - value class + </li> + <li> + compression - A boolean which specifies if compression is turned on for + keys/values in this file. + </li> + <li> + blockCompression - A boolean which specifies if block-compression is + turned on for keys/values in this file. + </li> + <li> + compression codec - <code>CompressionCodec</code> class which is used for + compression of keys and/or values (if compression is + enabled). + </li> + <li> + metadata - {@link Metadata} for this file. + </li> + <li> + sync - A sync marker to denote end of the header. + </li> + </ul> + + <h5 id="#UncompressedFormat">Uncompressed SequenceFile Format</h5> + <ul> + <li> + <a href="#Header">Header</a> + </li> + <li> + Record + <ul> + <li>Record length</li> + <li>Key length</li> + <li>Key</li> + <li>Value</li> + </ul> + </li> + <li> + A sync-marker every few <code>100</code> bytes or so. + </li> + </ul> + + <h5 id="#RecordCompressedFormat">Record-Compressed SequenceFile Format</h5> + <ul> + <li> + <a href="#Header">Header</a> + </li> + <li> + Record + <ul> + <li>Record length</li> + <li>Key length</li> + <li>Key</li> + <li><i>Compressed</i> Value</li> + </ul> + </li> + <li> + A sync-marker every few <code>100</code> bytes or so. + </li> + </ul> + + <h5 id="#BlockCompressedFormat">Block-Compressed SequenceFile Format</h5> + <ul> + <li> + <a href="#Header">Header</a> + </li> + <li> + Record <i>Block</i> + <ul> + <li>Compressed key-lengths block-size</li> + <li>Compressed key-lengths block</li> + <li>Compressed keys block-size</li> + <li>Compressed keys block</li> + <li>Compressed value-lengths block-size</li> + <li>Compressed value-lengths block</li> + <li>Compressed values block-size</li> + <li>Compressed values block</li> + </ul> + </li> + <li> + A sync-marker every few <code>100</code> bytes or so. + </li> + </ul> + + <p>The compressed blocks of key lengths and value lengths consist of the + actual lengths of individual keys/values encoded in ZeroCompressedInteger + format.</p> + + @see CompressionCodec]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.SequenceFile --> + <!-- start class org.apache.hadoop.io.SequenceFile.CompressionType --> + <class name="SequenceFile.CompressionType" extends="java.lang.Enum<org.apache.hadoop.io.SequenceFile.CompressionType>" + abstract="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <method name="values" return="org.apache.hadoop.io.SequenceFile.CompressionType[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="valueOf" return="org.apache.hadoop.io.SequenceFile.CompressionType" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + <doc> + <![CDATA[The compression type used to compress key/value pairs in the + {@link SequenceFile}. + + @see SequenceFile.Writer]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.SequenceFile.CompressionType --> + <!-- start class org.apache.hadoop.io.SequenceFile.Metadata --> + <class name="SequenceFile.Metadata" extends="java.lang.Object" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <constructor name="SequenceFile.Metadata" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="SequenceFile.Metadata" type="java.util.TreeMap<org.apache.hadoop.io.Text, org.apache.hadoop.io.Text>" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="get" return="org.apache.hadoop.io.Text" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="org.apache.hadoop.io.Text"/> + </method> + <method name="set" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="org.apache.hadoop.io.Text"/> + <param name="value" type="org.apache.hadoop.io.Text"/> + </method> + <method name="getMetadata" return="java.util.TreeMap<org.apache.hadoop.io.Text, org.apache.hadoop.io.Text>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="other" type="org.apache.hadoop.io.SequenceFile.Metadata"/> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[The class encapsulating with the metadata of a file. + The metadata of a file is a list of attribute name/value + pairs of Text type.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.SequenceFile.Metadata --> + <!-- start class org.apache.hadoop.io.SequenceFile.Reader --> + <class name="SequenceFile.Reader" extends="java.lang.Object" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="java.io.Closeable"/> + <constructor name="SequenceFile.Reader" type="org.apache.hadoop.fs.FileSystem, org.apache.hadoop.fs.Path, org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Open the named file.]]> + </doc> + </constructor> + <method name="openFile" return="org.apache.hadoop.fs.FSDataInputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <param name="file" type="org.apache.hadoop.fs.Path"/> + <param name="bufferSize" type="int"/> + <param name="length" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Override this method to specialize the type of + {@link FSDataInputStream} returned.]]> + </doc> + </method> + <method name="close" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Close the file.]]> + </doc> + </method> + <method name="getKeyClassName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the name of the key class.]]> + </doc> + </method> + <method name="getKeyClass" return="java.lang.Class" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the class of keys in this file.]]> + </doc> + </method> + <method name="getValueClassName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the name of the value class.]]> + </doc> + </method> + <method name="getValueClass" return="java.lang.Class" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the class of values in this file.]]> + </doc> + </method> + <method name="isCompressed" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns true if values are compressed.]]> + </doc> + </method> + <method name="isBlockCompressed" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns true if records are block-compressed.]]> + </doc> + </method> + <method name="getCompressionCodec" return="org.apache.hadoop.io.compress.CompressionCodec" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the compression codec of data in this file.]]> + </doc> + </method> + <method name="getMetadata" return="org.apache.hadoop.io.SequenceFile.Metadata" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the metadata object of the file]]> + </doc> + </method> + <method name="getCurrentValue" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get the 'value' corresponding to the last read 'key'. + @param val : The 'value' to be read. + @throws IOException]]> + </doc> + </method> + <method name="next" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read the next key in the file into <code>key</code>, skipping its + value. True if another entry exists, and false at end of file.]]> + </doc> + </method> + <method name="next" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.Writable"/> + <param name="val" type="org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read the next key/value pair in the file into <code>key</code> and + <code>val</code>. Returns true if such a pair exists and false when at + end of file]]> + </doc> + </method> + <method name="next" return="int" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="Call {@link #nextRaw(DataOutputBuffer,SequenceFile.ValueBytes)}."> + <param name="buffer" type="org.apache.hadoop.io.DataOutputBuffer"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[@deprecated Call {@link #nextRaw(DataOutputBuffer,SequenceFile.ValueBytes)}.]]> + </doc> + </method> + <method name="createValueBytes" return="org.apache.hadoop.io.SequenceFile.ValueBytes" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="nextRaw" return="int" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.DataOutputBuffer"/> + <param name="val" type="org.apache.hadoop.io.SequenceFile.ValueBytes"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read 'raw' records. + @param key - The buffer into which the key is read + @param val - The 'raw' value + @return Returns the total record length or -1 for end of file + @throws IOException]]> + </doc> + </method> + <method name="nextRawKey" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.DataOutputBuffer"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read 'raw' keys. + @param key - The buffer into which the key is read + @return Returns the key length or -1 for end of file + @throws IOException]]> + </doc> + </method> + <method name="nextRawValue" return="int" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="org.apache.hadoop.io.SequenceFile.ValueBytes"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read 'raw' values. + @param val - The 'raw' value + @return Returns the value length + @throws IOException]]> + </doc> + </method> + <method name="seek" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="position" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Set the current byte position in the input file. + + <p>The position passed must be a position returned by {@link + SequenceFile.Writer#getLength()} when writing this file. To seek to an arbitrary + position, use {@link SequenceFile.Reader#sync(long)}.]]> + </doc> + </method> + <method name="sync" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="position" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Seek to the next sync mark past a given position.]]> + </doc> + </method> + <method name="syncSeen" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns true iff the previous call to next passed a sync mark.]]> + </doc> + </method> + <method name="getPosition" return="long" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return the current byte position in the input file.]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the name of the file.]]> + </doc> + </method> + <doc> + <![CDATA[Reads key/value pairs from a sequence-format file.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.SequenceFile.Reader --> + <!-- start class org.apache.hadoop.io.SequenceFile.Sorter --> + <class name="SequenceFile.Sorter" extends="java.lang.Object" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="SequenceFile.Sorter" type="org.apache.hadoop.fs.FileSystem, java.lang.Class, java.lang.Class, org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Sort and merge files containing the named classes.]]> + </doc> + </constructor> + <constructor name="SequenceFile.Sorter" type="org.apache.hadoop.fs.FileSystem, org.apache.hadoop.io.RawComparator, java.lang.Class, java.lang.Class, org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Sort and merge using an arbitrary {@link RawComparator}.]]> + </doc> + </constructor> + <method name="setFactor" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="factor" type="int"/> + <doc> + <![CDATA[Set the number of streams to merge at once.]]> + </doc> + </method> + <method name="getFactor" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the number of streams to merge at once.]]> + </doc> + </method> + <method name="setMemory" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="memory" type="int"/> + <doc> + <![CDATA[Set the total amount of buffer memory, in bytes.]]> + </doc> + </method> + <method name="getMemory" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the total amount of buffer memory, in bytes.]]> + </doc> + </method> + <method name="setProgressable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="progressable" type="org.apache.hadoop.util.Progressable"/> + <doc> + <![CDATA[Set the progressable object in order to report progress.]]> + </doc> + </method> + <method name="sort" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="inFiles" type="org.apache.hadoop.fs.Path[]"/> + <param name="outFile" type="org.apache.hadoop.fs.Path"/> + <param name="deleteInput" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Perform a file sort from a set of input files into an output file. + @param inFiles the files to be sorted + @param outFile the sorted output file + @param deleteInput should the input files be deleted as they are read?]]> + </doc> + </method> + <method name="sortAndIterate" return="org.apache.hadoop.io.SequenceFile.Sorter.RawKeyValueIterator" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="inFiles" type="org.apache.hadoop.fs.Path[]"/> + <param name="tempDir" type="org.apache.hadoop.fs.Path"/> + <param name="deleteInput" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Perform a file sort from a set of input files and return an iterator. + @param inFiles the files to be sorted + @param tempDir the directory where temp files are created during sort + @param deleteInput should the input files be deleted as they are read? + @return iterator the RawKeyValueIterator]]> + </doc> + </method> + <method name="sort" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="inFile" type="org.apache.hadoop.fs.Path"/> + <param name="outFile" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[The backwards compatible interface to sort. + @param inFile the input file to sort + @param outFile the sorted output file]]> + </doc> + </method> + <method name="merge" return="org.apache.hadoop.io.SequenceFile.Sorter.RawKeyValueIterator" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="segments" type="java.util.List<org.apache.hadoop.io.SequenceFile.Sorter.SegmentDescriptor>"/> + <param name="tmpDir" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Merges the list of segments of type <code>SegmentDescriptor</code> + @param segments the list of SegmentDescriptors + @param tmpDir the directory to write temporary files into + @return RawKeyValueIterator + @throws IOException]]> + </doc> + </method> + <method name="merge" return="org.apache.hadoop.io.SequenceFile.Sorter.RawKeyValueIterator" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="inNames" type="org.apache.hadoop.fs.Path[]"/> + <param name="deleteInputs" type="boolean"/> + <param name="tmpDir" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Merges the contents of files passed in Path[] using a max factor value + that is already set + @param inNames the array of path names + @param deleteInputs true if the input files should be deleted when + unnecessary + @param tmpDir the directory to write temporary files into + @return RawKeyValueIteratorMergeQueue + @throws IOException]]> + </doc> + </method> + <method name="merge" return="org.apache.hadoop.io.SequenceFile.Sorter.RawKeyValueIterator" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="inNames" type="org.apache.hadoop.fs.Path[]"/> + <param name="deleteInputs" type="boolean"/> + <param name="factor" type="int"/> + <param name="tmpDir" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Merges the contents of files passed in Path[] + @param inNames the array of path names + @param deleteInputs true if the input files should be deleted when + unnecessary + @param factor the factor that will be used as the maximum merge fan-in + @param tmpDir the directory to write temporary files into + @return RawKeyValueIteratorMergeQueue + @throws IOException]]> + </doc> + </method> + <method name="merge" return="org.apache.hadoop.io.SequenceFile.Sorter.RawKeyValueIterator" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="inNames" type="org.apache.hadoop.fs.Path[]"/> + <param name="tempDir" type="org.apache.hadoop.fs.Path"/> + <param name="deleteInputs" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Merges the contents of files passed in Path[] + @param inNames the array of path names + @param tempDir the directory for creating temp files during merge + @param deleteInputs true if the input files should be deleted when + unnecessary + @return RawKeyValueIteratorMergeQueue + @throws IOException]]> + </doc> + </method> + <method name="cloneFileAttributes" return="org.apache.hadoop.io.SequenceFile.Writer" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="inputFile" type="org.apache.hadoop.fs.Path"/> + <param name="outputFile" type="org.apache.hadoop.fs.Path"/> + <param name="prog" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Clones the attributes (like compression of the input file and creates a + corresponding Writer + @param inputFile the path of the input file whose attributes should be + cloned + @param outputFile the path of the output file + @param prog the Progressable to report status during the file write + @return Writer + @throws IOException]]> + </doc> + </method> + <method name="writeFile" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="records" type="org.apache.hadoop.io.SequenceFile.Sorter.RawKeyValueIterator"/> + <param name="writer" type="org.apache.hadoop.io.SequenceFile.Writer"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Writes records from RawKeyValueIterator into a file represented by the + passed writer + @param records the RawKeyValueIterator + @param writer the Writer created earlier + @throws IOException]]> + </doc> + </method> + <method name="merge" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="inFiles" type="org.apache.hadoop.fs.Path[]"/> + <param name="outFile" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Merge the provided files. + @param inFiles the array of input path names + @param outFile the final output file + @throws IOException]]> + </doc> + </method> + <doc> + <![CDATA[Sorts key/value pairs in a sequence-format file. + + <p>For best performance, applications should make sure that the {@link + Writable#readFields(DataInput)} implementation of their keys is + very efficient. In particular, it should avoid allocating memory.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.SequenceFile.Sorter --> + <!-- start interface org.apache.hadoop.io.SequenceFile.Sorter.RawKeyValueIterator --> + <interface name="SequenceFile.Sorter.RawKeyValueIterator" abstract="true" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <method name="getKey" return="org.apache.hadoop.io.DataOutputBuffer" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Gets the current raw key + @return DataOutputBuffer + @throws IOException]]> + </doc> + </method> + <method name="getValue" return="org.apache.hadoop.io.SequenceFile.ValueBytes" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Gets the current raw value + @return ValueBytes + @throws IOException]]> + </doc> + </method> + <method name="next" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Sets up the current key and value (for getKey and getValue) + @return true if there exists a key/value, false otherwise + @throws IOException]]> + </doc> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[closes the iterator so that the underlying streams can be closed + @throws IOException]]> + </doc> + </method> + <method name="getProgress" return="org.apache.hadoop.util.Progress" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Gets the Progress object; this has a float (0.0 - 1.0) + indicating the bytes processed by the iterator so far]]> + </doc> + </method> + <doc> + <![CDATA[The interface to iterate over raw keys/values of SequenceFiles.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.io.SequenceFile.Sorter.RawKeyValueIterator --> + <!-- start class org.apache.hadoop.io.SequenceFile.Sorter.SegmentDescriptor --> + <class name="SequenceFile.Sorter.SegmentDescriptor" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="java.lang.Comparable"/> + <constructor name="SequenceFile.Sorter.SegmentDescriptor" type="long, long, org.apache.hadoop.fs.Path" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Constructs a segment + @param segmentOffset the offset of the segment in the file + @param segmentLength the length of the segment + @param segmentPathName the path name of the file containing the segment]]> + </doc> + </constructor> + <method name="doSync" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Do the sync checks]]> + </doc> + </method> + <method name="preserveInput" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="preserve" type="boolean"/> + <doc> + <![CDATA[Whether to delete the files when no longer needed]]> + </doc> + </method> + <method name="shouldPreserveInput" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="compareTo" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="nextRawKey" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Fills up the rawKey object with the key returned by the Reader + @return true if there is a key returned; false, otherwise + @throws IOException]]> + </doc> + </method> + <method name="nextRawValue" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="rawValue" type="org.apache.hadoop.io.SequenceFile.ValueBytes"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Fills up the passed rawValue with the value corresponding to the key + read earlier + @param rawValue + @return the length of the value + @throws IOException]]> + </doc> + </method> + <method name="getKey" return="org.apache.hadoop.io.DataOutputBuffer" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the stored rawKey]]> + </doc> + </method> + <method name="cleanup" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[The default cleanup. Subclasses can override this with a custom + cleanup]]> + </doc> + </method> + <doc> + <![CDATA[This class defines a merge segment. This class can be subclassed to + provide a customized cleanup method implementation. In this + implementation, cleanup closes the file handle and deletes the file]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.SequenceFile.Sorter.SegmentDescriptor --> + <!-- start interface org.apache.hadoop.io.SequenceFile.ValueBytes --> + <interface name="SequenceFile.ValueBytes" abstract="true" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <method name="writeUncompressedBytes" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="outStream" type="java.io.DataOutputStream"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Writes the uncompressed bytes to the outStream. + @param outStream : Stream to write uncompressed bytes into. + @throws IOException]]> + </doc> + </method> + <method name="writeCompressedBytes" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="outStream" type="java.io.DataOutputStream"/> + <exception name="IllegalArgumentException" type="java.lang.IllegalArgumentException"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Write compressed bytes to outStream. + Note: that it will NOT compress the bytes if they are not compressed. + @param outStream : Stream to write compressed bytes into.]]> + </doc> + </method> + <method name="getSize" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Size of stored data.]]> + </doc> + </method> + <doc> + <![CDATA[The interface to 'raw' values of SequenceFiles.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.io.SequenceFile.ValueBytes --> + <!-- start class org.apache.hadoop.io.SequenceFile.Writer --> + <class name="SequenceFile.Writer" extends="java.lang.Object" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="java.io.Closeable"/> + <constructor name="SequenceFile.Writer" type="org.apache.hadoop.fs.FileSystem, org.apache.hadoop.conf.Configuration, org.apache.hadoop.fs.Path, java.lang.Class, java.lang.Class" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create the named file.]]> + </doc> + </constructor> + <constructor name="SequenceFile.Writer" type="org.apache.hadoop.fs.FileSystem, org.apache.hadoop.conf.Configuration, org.apache.hadoop.fs.Path, java.lang.Class, java.lang.Class, org.apache.hadoop.util.Progressable, org.apache.hadoop.io.SequenceFile.Metadata" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create the named file with write-progress reporter.]]> + </doc> + </constructor> + <constructor name="SequenceFile.Writer" type="org.apache.hadoop.fs.FileSystem, org.apache.hadoop.conf.Configuration, org.apache.hadoop.fs.Path, java.lang.Class, java.lang.Class, int, short, long, org.apache.hadoop.util.Progressable, org.apache.hadoop.io.SequenceFile.Metadata" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create the named file with write-progress reporter.]]> + </doc> + </constructor> + <method name="getKeyClass" return="java.lang.Class" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the class of keys in this file.]]> + </doc> + </method> + <method name="getValueClass" return="java.lang.Class" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the class of values in this file.]]> + </doc> + </method> + <method name="getCompressionCodec" return="org.apache.hadoop.io.compress.CompressionCodec" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the compression codec of data in this file.]]> + </doc> + </method> + <method name="sync" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[create a sync point]]> + </doc> + </method> + <method name="close" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Close the file.]]> + </doc> + </method> + <method name="append" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.Writable"/> + <param name="val" type="org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Append a key/value pair.]]> + </doc> + </method> + <method name="append" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="java.lang.Object"/> + <param name="val" type="java.lang.Object"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Append a key/value pair.]]> + </doc> + </method> + <method name="appendRaw" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="keyData" type="byte[]"/> + <param name="keyOffset" type="int"/> + <param name="keyLength" type="int"/> + <param name="val" type="org.apache.hadoop.io.SequenceFile.ValueBytes"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getLength" return="long" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns the current length of the output file. + + <p>This always returns a synchronized position. In other words, + immediately after calling {@link SequenceFile.Reader#seek(long)} with a position + returned by this method, {@link SequenceFile.Reader#next(Writable)} may be called. However + the key may be earlier in the file than key last written when this + method was called (e.g., with block-compression, it may be the first key + in the block that was being written when this method was called).]]> + </doc> + </method> + <field name="keySerializer" type="org.apache.hadoop.io.serializer.Serializer" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="uncompressedValSerializer" type="org.apache.hadoop.io.serializer.Serializer" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="compressedValSerializer" type="org.apache.hadoop.io.serializer.Serializer" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[Write key/value pairs to a sequence-format file.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.SequenceFile.Writer --> + <!-- start class org.apache.hadoop.io.SetFile --> + <class name="SetFile" extends="org.apache.hadoop.io.MapFile" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="SetFile" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </constructor> + <doc> + <![CDATA[A file-based set of keys.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.SetFile --> + <!-- start class org.apache.hadoop.io.SetFile.Reader --> + <class name="SetFile.Reader" extends="org.apache.hadoop.io.MapFile.Reader" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="SetFile.Reader" type="org.apache.hadoop.fs.FileSystem, java.lang.String, org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct a set reader for the named set.]]> + </doc> + </constructor> + <constructor name="SetFile.Reader" type="org.apache.hadoop.fs.FileSystem, java.lang.String, org.apache.hadoop.io.WritableComparator, org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct a set reader for the named set using the named comparator.]]> + </doc> + </constructor> + <method name="seek" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.WritableComparable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="next" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.WritableComparable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read the next key in a set into <code>key</code>. Returns + true if such a key exists and false when at the end of the set.]]> + </doc> + </method> + <method name="get" return="org.apache.hadoop.io.WritableComparable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.WritableComparable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read the matching key from a set into <code>key</code>. + Returns <code>key</code>, or null if no match exists.]]> + </doc> + </method> + <doc> + <![CDATA[Provide access to an existing set file.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.SetFile.Reader --> + <!-- start class org.apache.hadoop.io.SetFile.Writer --> + <class name="SetFile.Writer" extends="org.apache.hadoop.io.MapFile.Writer" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="SetFile.Writer" type="org.apache.hadoop.fs.FileSystem, java.lang.String, java.lang.Class" + static="false" final="false" visibility="public" + deprecated="pass a Configuration too"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create the named set for keys of the named class. + @deprecated pass a Configuration too]]> + </doc> + </constructor> + <constructor name="SetFile.Writer" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.fs.FileSystem, java.lang.String, java.lang.Class, org.apache.hadoop.io.SequenceFile.CompressionType" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create a set naming the element class and compression type.]]> + </doc> + </constructor> + <constructor name="SetFile.Writer" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.fs.FileSystem, java.lang.String, org.apache.hadoop.io.WritableComparator, org.apache.hadoop.io.SequenceFile.CompressionType" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create a set naming the element comparator and compression type.]]> + </doc> + </constructor> + <method name="append" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.WritableComparable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Append a key to a set. The key must be strictly greater than the + previous key added to the set.]]> + </doc> + </method> + <doc> + <![CDATA[Write a new set file.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.SetFile.Writer --> + <!-- start class org.apache.hadoop.io.SortedMapWritable --> + <class name="SortedMapWritable" extends="org.apache.hadoop.io.AbstractMapWritable" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="java.util.SortedMap<org.apache.hadoop.io.WritableComparable, org.apache.hadoop.io.Writable>"/> + <constructor name="SortedMapWritable" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[default constructor.]]> + </doc> + </constructor> + <constructor name="SortedMapWritable" type="org.apache.hadoop.io.SortedMapWritable" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Copy constructor. + + @param other the map to copy from]]> + </doc> + </constructor> + <method name="comparator" return="java.util.Comparator<? super org.apache.hadoop.io.WritableComparable>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="firstKey" return="org.apache.hadoop.io.WritableComparable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="headMap" return="java.util.SortedMap<org.apache.hadoop.io.WritableComparable, org.apache.hadoop.io.Writable>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="toKey" type="org.apache.hadoop.io.WritableComparable"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="lastKey" return="org.apache.hadoop.io.WritableComparable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="subMap" return="java.util.SortedMap<org.apache.hadoop.io.WritableComparable, org.apache.hadoop.io.Writable>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fromKey" type="org.apache.hadoop.io.WritableComparable"/> + <param name="toKey" type="org.apache.hadoop.io.WritableComparable"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="tailMap" return="java.util.SortedMap<org.apache.hadoop.io.WritableComparable, org.apache.hadoop.io.Writable>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fromKey" type="org.apache.hadoop.io.WritableComparable"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="clear" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="containsKey" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="java.lang.Object"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="containsValue" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="value" type="java.lang.Object"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="entrySet" return="java.util.Set<java.util.Map.Entry<org.apache.hadoop.io.WritableComparable, org.apache.hadoop.io.Writable>>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="get" return="org.apache.hadoop.io.Writable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="java.lang.Object"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="isEmpty" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="keySet" return="java.util.Set<org.apache.hadoop.io.WritableComparable>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="put" return="org.apache.hadoop.io.Writable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.WritableComparable"/> + <param name="value" type="org.apache.hadoop.io.Writable"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="putAll" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="t" type="java.util.Map<? extends org.apache.hadoop.io.WritableComparable, ? extends org.apache.hadoop.io.Writable>"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="remove" return="org.apache.hadoop.io.Writable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="java.lang.Object"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="size" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="values" return="java.util.Collection<org.apache.hadoop.io.Writable>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <doc> + <![CDATA[A Writable SortedMap.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.SortedMapWritable --> + <!-- start interface org.apache.hadoop.io.Stringifier --> + <interface name="Stringifier" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="java.io.Closeable"/> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="obj" type="T"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Converts the object to a string representation + @param obj the object to convert + @return the string representation of the object + @throws IOException if the object cannot be converted]]> + </doc> + </method> + <method name="fromString" return="T" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="str" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Restores the object from its string representation. + @param str the string representation of the object + @return restored object + @throws IOException if the object cannot be restored]]> + </doc> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Closes this object. + @throws IOException if an I/O error occurs]]> + </doc> + </method> + <doc> + <![CDATA[Stringifier interface offers two methods to convert an object + to a string representation and restore the object given its + string representation. + @param <T> the class of the objects to stringify]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.io.Stringifier --> + <!-- start class org.apache.hadoop.io.Text --> + <class name="Text" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.WritableComparable"/> + <constructor name="Text" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="Text" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct from a string.]]> + </doc> + </constructor> + <constructor name="Text" type="org.apache.hadoop.io.Text" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct from another text.]]> + </doc> + </constructor> + <constructor name="Text" type="byte[]" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct from a byte array.]]> + </doc> + </constructor> + <method name="getBytes" return="byte[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Retuns the raw bytes.]]> + </doc> + </method> + <method name="getLength" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the number of bytes in the byte array]]> + </doc> + </method> + <method name="charAt" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="position" type="int"/> + <doc> + <![CDATA[Returns the Unicode Scalar Value (32-bit integer value) + for the character at <code>position</code>. Note that this + method avoids using the converter or doing String instatiation + @return the Unicode scalar value at position or -1 + if the position is invalid or points to a + trailing byte]]> + </doc> + </method> + <method name="find" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="what" type="java.lang.String"/> + </method> + <method name="find" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="what" type="java.lang.String"/> + <param name="start" type="int"/> + <doc> + <![CDATA[Finds any occurence of <code>what</code> in the backing + buffer, starting as position <code>start</code>. The starting + position is measured in bytes and the return value is in + terms of byte position in the buffer. The backing buffer is + not converted to a string for this operation. + @return byte position of the first occurence of the search + string in the UTF-8 buffer or -1 if not found]]> + </doc> + </method> + <method name="set" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="string" type="java.lang.String"/> + <doc> + <![CDATA[Set to contain the contents of a string.]]> + </doc> + </method> + <method name="set" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="utf8" type="byte[]"/> + <doc> + <![CDATA[Set to a utf8 byte array]]> + </doc> + </method> + <method name="set" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="other" type="org.apache.hadoop.io.Text"/> + <doc> + <![CDATA[copy a text.]]> + </doc> + </method> + <method name="set" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="utf8" type="byte[]"/> + <param name="start" type="int"/> + <param name="len" type="int"/> + <doc> + <![CDATA[Set the Text to range of bytes + @param utf8 the data to copy from + @param start the first position of the new string + @param len the number of bytes of the new string]]> + </doc> + </method> + <method name="append" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="utf8" type="byte[]"/> + <param name="start" type="int"/> + <param name="len" type="int"/> + <doc> + <![CDATA[Append a range of bytes to the end of the given text + @param utf8 the data to copy from + @param start the first position to append from utf8 + @param len the number of bytes to append]]> + </doc> + </method> + <method name="clear" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Clear the string to empty.]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Convert text back to string + @see java.lang.Object#toString()]]> + </doc> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[deserialize]]> + </doc> + </method> + <method name="skip" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Skips over one Text in the input.]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[serialize + write this object to out + length uses zero-compressed encoding + @see Writable#write(DataOutput)]]> + </doc> + </method> + <method name="compareTo" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + <doc> + <![CDATA[Compare two Texts bytewise using standard UTF8 ordering.]]> + </doc> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + <doc> + <![CDATA[Returns true iff <code>o</code> is a Text with the same contents.]]> + </doc> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[hash function]]> + </doc> + </method> + <method name="decode" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="utf8" type="byte[]"/> + <exception name="CharacterCodingException" type="java.nio.charset.CharacterCodingException"/> + <doc> + <![CDATA[Converts the provided byte array to a String using the + UTF-8 encoding. If the input is malformed, + replace by a default value.]]> + </doc> + </method> + <method name="decode" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="utf8" type="byte[]"/> + <param name="start" type="int"/> + <param name="length" type="int"/> + <exception name="CharacterCodingException" type="java.nio.charset.CharacterCodingException"/> + </method> + <method name="decode" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="utf8" type="byte[]"/> + <param name="start" type="int"/> + <param name="length" type="int"/> + <param name="replace" type="boolean"/> + <exception name="CharacterCodingException" type="java.nio.charset.CharacterCodingException"/> + <doc> + <![CDATA[Converts the provided byte array to a String using the + UTF-8 encoding. If <code>replace</code> is true, then + malformed input is replaced with the + substitution character, which is U+FFFD. Otherwise the + method throws a MalformedInputException.]]> + </doc> + </method> + <method name="encode" return="java.nio.ByteBuffer" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="string" type="java.lang.String"/> + <exception name="CharacterCodingException" type="java.nio.charset.CharacterCodingException"/> + <doc> + <![CDATA[Converts the provided String to bytes using the + UTF-8 encoding. If the input is malformed, + invalid chars are replaced by a default value. + @return ByteBuffer: bytes stores at ByteBuffer.array() + and length is ByteBuffer.limit()]]> + </doc> + </method> + <method name="encode" return="java.nio.ByteBuffer" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="string" type="java.lang.String"/> + <param name="replace" type="boolean"/> + <exception name="CharacterCodingException" type="java.nio.charset.CharacterCodingException"/> + <doc> + <![CDATA[Converts the provided String to bytes using the + UTF-8 encoding. If <code>replace</code> is true, then + malformed input is replaced with the + substitution character, which is U+FFFD. Otherwise the + method throws a MalformedInputException. + @return ByteBuffer: bytes stores at ByteBuffer.array() + and length is ByteBuffer.limit()]]> + </doc> + </method> + <method name="readString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read a UTF8 encoded string from in]]> + </doc> + </method> + <method name="writeString" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <param name="s" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Write a UTF8 encoded string to out]]> + </doc> + </method> + <method name="validateUTF8" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="utf8" type="byte[]"/> + <exception name="MalformedInputException" type="java.nio.charset.MalformedInputException"/> + <doc> + <![CDATA[Check if a byte array contains valid utf-8 + @param utf8 byte array + @throws MalformedInputException if the byte array contains invalid utf-8]]> + </doc> + </method> + <method name="validateUTF8" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="utf8" type="byte[]"/> + <param name="start" type="int"/> + <param name="len" type="int"/> + <exception name="MalformedInputException" type="java.nio.charset.MalformedInputException"/> + <doc> + <![CDATA[Check to see if a byte array is valid utf-8 + @param utf8 the array of bytes + @param start the offset of the first byte in the array + @param len the length of the byte sequence + @throws MalformedInputException if the byte array contains invalid bytes]]> + </doc> + </method> + <method name="bytesToCodePoint" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="bytes" type="java.nio.ByteBuffer"/> + <doc> + <![CDATA[Returns the next code point at the current position in + the buffer. The buffer's position will be incremented. + Any mark set on this buffer will be changed by this method!]]> + </doc> + </method> + <method name="utf8Length" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="string" type="java.lang.String"/> + <doc> + <![CDATA[For the given string, returns the number of UTF-8 bytes + required to encode the string. + @param string text to encode + @return number of UTF-8 bytes required to encode]]> + </doc> + </method> + <doc> + <![CDATA[This class stores text using standard UTF8 encoding. It provides methods + to serialize, deserialize, and compare texts at byte level. The type of + length is integer and is serialized using zero-compressed format. <p>In + addition, it provides methods for string traversal without converting the + byte array to a string. <p>Also includes utilities for + serializing/deserialing a string, coding/decoding a string, checking if a + byte array contains valid UTF8 code, calculating the length of an encoded + string.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.Text --> + <!-- start class org.apache.hadoop.io.Text.Comparator --> + <class name="Text.Comparator" extends="org.apache.hadoop.io.WritableComparator" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="Text.Comparator" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="compare" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b1" type="byte[]"/> + <param name="s1" type="int"/> + <param name="l1" type="int"/> + <param name="b2" type="byte[]"/> + <param name="s2" type="int"/> + <param name="l2" type="int"/> + </method> + <doc> + <![CDATA[A WritableComparator optimized for Text keys.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.Text.Comparator --> + <!-- start class org.apache.hadoop.io.TwoDArrayWritable --> + <class name="TwoDArrayWritable" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <constructor name="TwoDArrayWritable" type="java.lang.Class" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="TwoDArrayWritable" type="java.lang.Class, org.apache.hadoop.io.Writable[][]" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="toArray" return="java.lang.Object" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="set" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="values" type="org.apache.hadoop.io.Writable[][]"/> + </method> + <method name="get" return="org.apache.hadoop.io.Writable[][]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[A Writable for 2D arrays containing a matrix of instances of a class.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.TwoDArrayWritable --> + <!-- start class org.apache.hadoop.io.UTF8 --> + <class name="UTF8" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="replaced by Text"> + <implements name="org.apache.hadoop.io.WritableComparable"/> + <constructor name="UTF8" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="UTF8" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct from a given string.]]> + </doc> + </constructor> + <constructor name="UTF8" type="org.apache.hadoop.io.UTF8" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct from a given string.]]> + </doc> + </constructor> + <method name="getBytes" return="byte[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The raw bytes.]]> + </doc> + </method> + <method name="getLength" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The number of bytes in the encoded string.]]> + </doc> + </method> + <method name="set" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="string" type="java.lang.String"/> + <doc> + <![CDATA[Set to contain the contents of a string.]]> + </doc> + </method> + <method name="set" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="other" type="org.apache.hadoop.io.UTF8"/> + <doc> + <![CDATA[Set to contain the contents of a string.]]> + </doc> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="skip" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Skips over one UTF8 in the input.]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="compareTo" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + <doc> + <![CDATA[Compare two UTF8s.]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Convert to a String.]]> + </doc> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + <doc> + <![CDATA[Returns true iff <code>o</code> is a UTF8 with the same contents.]]> + </doc> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getBytes" return="byte[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="string" type="java.lang.String"/> + <doc> + <![CDATA[Convert a string to a UTF-8 encoded byte array. + @see String#getBytes(String)]]> + </doc> + </method> + <method name="readString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read a UTF-8 encoded string. + + @see DataInput#readUTF()]]> + </doc> + </method> + <method name="writeString" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <param name="s" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Write a UTF-8 encoded string. + + @see DataOutput#writeUTF(String)]]> + </doc> + </method> + <doc> + <![CDATA[A WritableComparable for strings that uses the UTF8 encoding. + + <p>Also includes utilities for efficiently reading and writing UTF-8. + + @deprecated replaced by Text]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.UTF8 --> + <!-- start class org.apache.hadoop.io.UTF8.Comparator --> + <class name="UTF8.Comparator" extends="org.apache.hadoop.io.WritableComparator" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="UTF8.Comparator" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="compare" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b1" type="byte[]"/> + <param name="s1" type="int"/> + <param name="l1" type="int"/> + <param name="b2" type="byte[]"/> + <param name="s2" type="int"/> + <param name="l2" type="int"/> + </method> + <doc> + <![CDATA[A WritableComparator optimized for UTF8 keys.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.UTF8.Comparator --> + <!-- start class org.apache.hadoop.io.VersionedWritable --> + <class name="VersionedWritable" extends="java.lang.Object" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <constructor name="VersionedWritable" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getVersion" return="byte" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the version number of the current implementation.]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[A base class for Writables that provides version checking. + + <p>This is useful when a class may evolve, so that instances written by the + old version of the class may still be processed by the new version. To + handle this situation, {@link #readFields(DataInput)} + implementations should catch {@link VersionMismatchException}.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.VersionedWritable --> + <!-- start class org.apache.hadoop.io.VersionMismatchException --> + <class name="VersionMismatchException" extends="java.io.IOException" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="VersionMismatchException" type="byte, byte" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns a string representation of this object.]]> + </doc> + </method> + <doc> + <![CDATA[Thrown by {@link VersionedWritable#readFields(DataInput)} when the + version of an object being read does not match the current implementation + version as returned by {@link VersionedWritable#getVersion()}.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.VersionMismatchException --> + <!-- start class org.apache.hadoop.io.VIntWritable --> + <class name="VIntWritable" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.WritableComparable"/> + <constructor name="VIntWritable" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="VIntWritable" type="int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="set" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="value" type="int"/> + <doc> + <![CDATA[Set the value of this VIntWritable.]]> + </doc> + </method> + <method name="get" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the value of this VIntWritable.]]> + </doc> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + <doc> + <![CDATA[Returns true iff <code>o</code> is a VIntWritable with the same value.]]> + </doc> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="compareTo" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + <doc> + <![CDATA[Compares two VIntWritables.]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[A WritableComparable for integer values stored in variable-length format. + Such values take between one and five bytes. Smaller values take fewer bytes. + + @see org.apache.hadoop.io.WritableUtils#readVInt(DataInput)]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.VIntWritable --> + <!-- start class org.apache.hadoop.io.VLongWritable --> + <class name="VLongWritable" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.WritableComparable"/> + <constructor name="VLongWritable" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="VLongWritable" type="long" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="set" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="value" type="long"/> + <doc> + <![CDATA[Set the value of this LongWritable.]]> + </doc> + </method> + <method name="get" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the value of this LongWritable.]]> + </doc> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + <doc> + <![CDATA[Returns true iff <code>o</code> is a VLongWritable with the same value.]]> + </doc> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="compareTo" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + <doc> + <![CDATA[Compares two VLongWritables.]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[A WritableComparable for longs in a variable-length format. Such values take + between one and five bytes. Smaller values take fewer bytes. + + @see org.apache.hadoop.io.WritableUtils#readVLong(DataInput)]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.VLongWritable --> + <!-- start interface org.apache.hadoop.io.Writable --> + <interface name="Writable" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Serialize the fields of this object to <code>out</code>. + + @param out <code>DataOuput</code> to serialize this object into. + @throws IOException]]> + </doc> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Deserialize the fields of this object from <code>in</code>. + + <p>For efficiency, implementations should attempt to re-use storage in the + existing object where possible.</p> + + @param in <code>DataInput</code> to deseriablize this object from. + @throws IOException]]> + </doc> + </method> + <doc> + <![CDATA[A serializable object which implements a simple, efficient, serialization + protocol, based on {@link DataInput} and {@link DataOutput}. + + <p>Any <code>key</code> or <code>value</code> type in the Hadoop Map-Reduce + framework implements this interface.</p> + + <p>Implementations typically implement a static <code>read(DataInput)</code> + method which constructs a new instance, calls {@link #readFields(DataInput)} + and returns the instance.</p> + + <p>Example:</p> + <p><blockquote><pre> + public class MyWritable implements Writable { + // Some data + private int counter; + private long timestamp; + + public void write(DataOutput out) throws IOException { + out.writeInt(counter); + out.writeLong(timestamp); + } + + public void readFields(DataInput in) throws IOException { + counter = in.readInt(); + timestamp = in.readLong(); + } + + public static MyWritable read(DataInput in) throws IOException { + MyWritable w = new MyWritable(); + w.readFields(in); + return w; + } + } + </pre></blockquote></p>]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.io.Writable --> + <!-- start interface org.apache.hadoop.io.WritableComparable --> + <interface name="WritableComparable" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <implements name="java.lang.Comparable"/> + <doc> + <![CDATA[A {@link Writable} which is also {@link Comparable}. + + <p><code>WritableComparable</code>s can be compared to each other, typically + via <code>Comparator</code>s. Any type which is to be used as a + <code>key</code> in the Hadoop Map-Reduce framework should implement this + interface.</p> + + <p>Example:</p> + <p><blockquote><pre> + public class MyWritableComparable implements WritableComparable { + // Some data + private int counter; + private long timestamp; + + public void write(DataOutput out) throws IOException { + out.writeInt(counter); + out.writeLong(timestamp); + } + + public void readFields(DataInput in) throws IOException { + counter = in.readInt(); + timestamp = in.readLong(); + } + + public int compareTo(MyWritableComparable w) { + int thisValue = this.value; + int thatValue = ((IntWritable)o).value; + return (thisValue < thatValue ? -1 : (thisValue==thatValue ? 0 : 1)); + } + } + </pre></blockquote></p>]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.io.WritableComparable --> + <!-- start class org.apache.hadoop.io.WritableComparator --> + <class name="WritableComparator" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.RawComparator"/> + <constructor name="WritableComparator" type="java.lang.Class" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct for a {@link WritableComparable} implementation.]]> + </doc> + </constructor> + <method name="get" return="org.apache.hadoop.io.WritableComparator" + abstract="false" native="false" synchronized="true" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="c" type="java.lang.Class"/> + <doc> + <![CDATA[Get a comparator for a {@link WritableComparable} implementation.]]> + </doc> + </method> + <method name="define" + abstract="false" native="false" synchronized="true" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="c" type="java.lang.Class"/> + <param name="comparator" type="org.apache.hadoop.io.WritableComparator"/> + <doc> + <![CDATA[Register an optimized comparator for a {@link WritableComparable} + implementation.]]> + </doc> + </method> + <method name="getKeyClass" return="java.lang.Class" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the WritableComparable implementation class.]]> + </doc> + </method> + <method name="newKey" return="org.apache.hadoop.io.WritableComparable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct a new {@link WritableComparable} instance.]]> + </doc> + </method> + <method name="compare" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b1" type="byte[]"/> + <param name="s1" type="int"/> + <param name="l1" type="int"/> + <param name="b2" type="byte[]"/> + <param name="s2" type="int"/> + <param name="l2" type="int"/> + <doc> + <![CDATA[Optimization hook. Override this to make SequenceFile.Sorter's scream. + + <p>The default implementation reads the data into two {@link + WritableComparable}s (using {@link + Writable#readFields(DataInput)}, then calls {@link + #compare(WritableComparable,WritableComparable)}.]]> + </doc> + </method> + <method name="compare" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="a" type="org.apache.hadoop.io.WritableComparable"/> + <param name="b" type="org.apache.hadoop.io.WritableComparable"/> + <doc> + <![CDATA[Compare two WritableComparables. + + <p> The default implementation uses the natural ordering, calling {@link + Comparable#compareTo(Object)}.]]> + </doc> + </method> + <method name="compare" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="a" type="java.lang.Object"/> + <param name="b" type="java.lang.Object"/> + </method> + <method name="compareBytes" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b1" type="byte[]"/> + <param name="s1" type="int"/> + <param name="l1" type="int"/> + <param name="b2" type="byte[]"/> + <param name="s2" type="int"/> + <param name="l2" type="int"/> + <doc> + <![CDATA[Lexicographic order of binary data.]]> + </doc> + </method> + <method name="hashBytes" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="bytes" type="byte[]"/> + <param name="length" type="int"/> + <doc> + <![CDATA[Compute hash for binary data.]]> + </doc> + </method> + <method name="readUnsignedShort" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="bytes" type="byte[]"/> + <param name="start" type="int"/> + <doc> + <![CDATA[Parse an unsigned short from a byte array.]]> + </doc> + </method> + <method name="readInt" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="bytes" type="byte[]"/> + <param name="start" type="int"/> + <doc> + <![CDATA[Parse an integer from a byte array.]]> + </doc> + </method> + <method name="readFloat" return="float" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="bytes" type="byte[]"/> + <param name="start" type="int"/> + <doc> + <![CDATA[Parse a float from a byte array.]]> + </doc> + </method> + <method name="readLong" return="long" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="bytes" type="byte[]"/> + <param name="start" type="int"/> + <doc> + <![CDATA[Parse a long from a byte array.]]> + </doc> + </method> + <method name="readDouble" return="double" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="bytes" type="byte[]"/> + <param name="start" type="int"/> + <doc> + <![CDATA[Parse a double from a byte array.]]> + </doc> + </method> + <method name="readVLong" return="long" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="bytes" type="byte[]"/> + <param name="start" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Reads a zero-compressed encoded long from a byte array and returns it. + @param bytes byte array with decode long + @param start starting index + @throws java.io.IOException + @return deserialized long]]> + </doc> + </method> + <method name="readVInt" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="bytes" type="byte[]"/> + <param name="start" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Reads a zero-compressed encoded integer from a byte array and returns it. + @param bytes byte array with the encoded integer + @param start start index + @throws java.io.IOException + @return deserialized integer]]> + </doc> + </method> + <doc> + <![CDATA[A Comparator for {@link WritableComparable}s. + + <p>This base implemenation uses the natural ordering. To define alternate + orderings, override {@link #compare(WritableComparable,WritableComparable)}. + + <p>One may optimize compare-intensive operations by overriding + {@link #compare(byte[],int,int,byte[],int,int)}. Static utility methods are + provided to assist in optimized implementations of this method.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.WritableComparator --> + <!-- start class org.apache.hadoop.io.WritableFactories --> + <class name="WritableFactories" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="setFactory" + abstract="false" native="false" synchronized="true" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="c" type="java.lang.Class"/> + <param name="factory" type="org.apache.hadoop.io.WritableFactory"/> + <doc> + <![CDATA[Define a factory for a class.]]> + </doc> + </method> + <method name="getFactory" return="org.apache.hadoop.io.WritableFactory" + abstract="false" native="false" synchronized="true" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="c" type="java.lang.Class"/> + <doc> + <![CDATA[Define a factory for a class.]]> + </doc> + </method> + <method name="newInstance" return="org.apache.hadoop.io.Writable" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="c" type="java.lang.Class"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[Create a new instance of a class with a defined factory.]]> + </doc> + </method> + <method name="newInstance" return="org.apache.hadoop.io.Writable" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="c" type="java.lang.Class"/> + <doc> + <![CDATA[Create a new instance of a class with a defined factory.]]> + </doc> + </method> + <doc> + <![CDATA[Factories for non-public writables. Defining a factory permits {@link + ObjectWritable} to be able to construct instances of non-public classes.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.WritableFactories --> + <!-- start interface org.apache.hadoop.io.WritableFactory --> + <interface name="WritableFactory" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="newInstance" return="org.apache.hadoop.io.Writable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return a new instance.]]> + </doc> + </method> + <doc> + <![CDATA[A factory for a class of Writable. + @see WritableFactories]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.io.WritableFactory --> + <!-- start class org.apache.hadoop.io.WritableName --> + <class name="WritableName" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="setName" + abstract="false" native="false" synchronized="true" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="writableClass" type="java.lang.Class"/> + <param name="name" type="java.lang.String"/> + <doc> + <![CDATA[Set the name that a class should be known as to something other than the + class name.]]> + </doc> + </method> + <method name="addName" + abstract="false" native="false" synchronized="true" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="writableClass" type="java.lang.Class"/> + <param name="name" type="java.lang.String"/> + <doc> + <![CDATA[Add an alternate name for a class.]]> + </doc> + </method> + <method name="getName" return="java.lang.String" + abstract="false" native="false" synchronized="true" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="writableClass" type="java.lang.Class"/> + <doc> + <![CDATA[Return the name for a class. Default is {@link Class#getName()}.]]> + </doc> + </method> + <method name="getClass" return="java.lang.Class" + abstract="false" native="false" synchronized="true" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return the class for a name. Default is {@link Class#forName(String)}.]]> + </doc> + </method> + <doc> + <![CDATA[Utility to permit renaming of Writable implementation classes without + invalidiating files that contain their class name.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.WritableName --> + <!-- start class org.apache.hadoop.io.WritableUtils --> + <class name="WritableUtils" extends="java.lang.Object" + abstract="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <constructor name="WritableUtils" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="readCompressedByteArray" return="byte[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="skipCompressedByteArray" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeCompressedByteArray" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <param name="bytes" type="byte[]"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readCompressedString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeCompressedString" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <param name="s" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeString" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <param name="s" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeStringArray" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <param name="s" type="java.lang.String[]"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeCompressedStringArray" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <param name="s" type="java.lang.String[]"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readStringArray" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readCompressedStringArray" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="displayByteArray" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="record" type="byte[]"/> + </method> + <method name="clone" return="org.apache.hadoop.io.Writable" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="orig" type="org.apache.hadoop.io.Writable"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[Make a copy of a writable object using serialization to a buffer. + @param orig The object to copy + @return The copied object]]> + </doc> + </method> + <method name="cloneInto" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dst" type="org.apache.hadoop.io.Writable"/> + <param name="src" type="org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Make a copy of the writable object using serialiation to a buffer + @param dst the object to copy from + @param src the object to copy into, which is destroyed + @throws IOException]]> + </doc> + </method> + <method name="writeVInt" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="stream" type="java.io.DataOutput"/> + <param name="i" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Serializes an integer to a binary stream with zero-compressed encoding. + For -120 <= i <= 127, only one byte is used with the actual value. + For other values of i, the first byte value indicates whether the + integer is positive or negative, and the number of bytes that follow. + If the first byte value v is between -121 and -124, the following integer + is positive, with number of bytes that follow are -(v+120). + If the first byte value v is between -125 and -128, the following integer + is negative, with number of bytes that follow are -(v+124). Bytes are + stored in the high-non-zero-byte-first order. + + @param stream Binary output stream + @param i Integer to be serialized + @throws java.io.IOException]]> + </doc> + </method> + <method name="writeVLong" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="stream" type="java.io.DataOutput"/> + <param name="i" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Serializes a long to a binary stream with zero-compressed encoding. + For -112 <= i <= 127, only one byte is used with the actual value. + For other values of i, the first byte value indicates whether the + long is positive or negative, and the number of bytes that follow. + If the first byte value v is between -113 and -120, the following long + is positive, with number of bytes that follow are -(v+112). + If the first byte value v is between -121 and -128, the following long + is negative, with number of bytes that follow are -(v+120). Bytes are + stored in the high-non-zero-byte-first order. + + @param stream Binary output stream + @param i Long to be serialized + @throws java.io.IOException]]> + </doc> + </method> + <method name="readVLong" return="long" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="stream" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Reads a zero-compressed encoded long from input stream and returns it. + @param stream Binary input stream + @throws java.io.IOException + @return deserialized long from stream.]]> + </doc> + </method> + <method name="readVInt" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="stream" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Reads a zero-compressed encoded integer from input stream and returns it. + @param stream Binary input stream + @throws java.io.IOException + @return deserialized integer from stream.]]> + </doc> + </method> + <method name="isNegativeVInt" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="value" type="byte"/> + <doc> + <![CDATA[Given the first byte of a vint/vlong, determine the sign + @param value the first byte + @return is the value negative]]> + </doc> + </method> + <method name="decodeVIntSize" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="value" type="byte"/> + <doc> + <![CDATA[Parse the first byte of a vint/vlong to determine the number of bytes + @param value the first byte of the vint/vlong + @return the total number of bytes (1 to 9)]]> + </doc> + </method> + <method name="getVIntSize" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="i" type="long"/> + <doc> + <![CDATA[Get the encoded length if an integer is stored in a variable-length format + @return the encoded length]]> + </doc> + </method> + <method name="readEnum" return="T extends java.lang.Enum<T>" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <param name="enumType" type="java.lang.Class<T>"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read an Enum value from DataInput, Enums are read and written + using String values. + @param <T> Enum type + @param in DataInput to read from + @param enumType Class type of Enum + @return Enum represented by String read from DataInput + @throws IOException]]> + </doc> + </method> + <method name="writeEnum" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <param name="enumVal" type="java.lang.Enum"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[writes String value of enum to DataOutput. + @param out Dataoutput stream + @param enumVal enum value + @throws IOException]]> + </doc> + </method> + <method name="skipFully" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <param name="len" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Skip <i>len</i> number of bytes in input stream<i>in</i> + @param in input stream + @param len number of bytes to skip + @throws IOException when skipped less number of bytes]]> + </doc> + </method> + </class> + <!-- end class org.apache.hadoop.io.WritableUtils --> + <doc> + <![CDATA[Generic i/o code for use when reading and writing data to the network, +to databases, and to files.]]> + </doc> +</package> +<package name="org.apache.hadoop.io.compress"> + <!-- start interface org.apache.hadoop.io.compress.CompressionCodec --> + <interface name="CompressionCodec" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="createOutputStream" return="org.apache.hadoop.io.compress.CompressionOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.OutputStream"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create a {@link CompressionOutputStream} that will write to the given + {@link OutputStream}. + + @param out the location for the final output stream + @return a stream the user can write uncompressed data to have it compressed + @throws IOException]]> + </doc> + </method> + <method name="createOutputStream" return="org.apache.hadoop.io.compress.CompressionOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.OutputStream"/> + <param name="compressor" type="org.apache.hadoop.io.compress.Compressor"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create a {@link CompressionOutputStream} that will write to the given + {@link OutputStream} with the given {@link Compressor}. + + @param out the location for the final output stream + @param compressor compressor to use + @return a stream the user can write uncompressed data to have it compressed + @throws IOException]]> + </doc> + </method> + <method name="getCompressorType" return="java.lang.Class" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the type of {@link Compressor} needed by this {@link CompressionCodec}. + + @return the type of compressor needed by this codec.]]> + </doc> + </method> + <method name="createCompressor" return="org.apache.hadoop.io.compress.Compressor" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Create a new {@link Compressor} for use by this {@link CompressionCodec}. + + @return a new compressor for use by this codec]]> + </doc> + </method> + <method name="createInputStream" return="org.apache.hadoop.io.compress.CompressionInputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.InputStream"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create a stream decompressor that will read from the given input stream. + + @param in the stream to read compressed bytes from + @return a stream to read uncompressed bytes from + @throws IOException]]> + </doc> + </method> + <method name="createInputStream" return="org.apache.hadoop.io.compress.CompressionInputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.InputStream"/> + <param name="decompressor" type="org.apache.hadoop.io.compress.Decompressor"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create a {@link CompressionInputStream} that will read from the given + {@link InputStream} with the given {@link Decompressor}. + + @param in the stream to read compressed bytes from + @param decompressor decompressor to use + @return a stream to read uncompressed bytes from + @throws IOException]]> + </doc> + </method> + <method name="getDecompressorType" return="java.lang.Class" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the type of {@link Decompressor} needed by this {@link CompressionCodec}. + + @return the type of decompressor needed by this codec.]]> + </doc> + </method> + <method name="createDecompressor" return="org.apache.hadoop.io.compress.Decompressor" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Create a new {@link Decompressor} for use by this {@link CompressionCodec}. + + @return a new decompressor for use by this codec]]> + </doc> + </method> + <method name="getDefaultExtension" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the default filename extension for this kind of compression. + @return the extension including the '.']]> + </doc> + </method> + <doc> + <![CDATA[This class encapsulates a streaming compression/decompression pair.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.io.compress.CompressionCodec --> + <!-- start class org.apache.hadoop.io.compress.CompressionCodecFactory --> + <class name="CompressionCodecFactory" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="CompressionCodecFactory" type="org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Find the codecs specified in the config value io.compression.codecs + and register them. Defaults to gzip and zip.]]> + </doc> + </constructor> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Print the extension map out as a string.]]> + </doc> + </method> + <method name="getCodecClasses" return="java.util.List<java.lang.Class>" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[Get the list of codecs listed in the configuration + @param conf the configuration to look in + @return a list of the Configuration classes or null if the attribute + was not set]]> + </doc> + </method> + <method name="setCodecClasses" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="classes" type="java.util.List<java.lang.Class>"/> + <doc> + <![CDATA[Sets a list of codec classes in the configuration. + @param conf the configuration to modify + @param classes the list of classes to set]]> + </doc> + </method> + <method name="getCodec" return="org.apache.hadoop.io.compress.CompressionCodec" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="file" type="org.apache.hadoop.fs.Path"/> + <doc> + <![CDATA[Find the relevant compression codec for the given file based on its + filename suffix. + @param file the filename to check + @return the codec object]]> + </doc> + </method> + <method name="removeSuffix" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="filename" type="java.lang.String"/> + <param name="suffix" type="java.lang.String"/> + <doc> + <![CDATA[Removes a suffix from a filename, if it has it. + @param filename the filename to strip + @param suffix the suffix to remove + @return the shortened filename]]> + </doc> + </method> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + <doc> + <![CDATA[A little test program. + @param args]]> + </doc> + </method> + <field name="LOG" type="org.apache.commons.logging.Log" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[A factory that will find the correct codec for a given filename.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.compress.CompressionCodecFactory --> + <!-- start class org.apache.hadoop.io.compress.CompressionInputStream --> + <class name="CompressionInputStream" extends="java.io.InputStream" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="CompressionInputStream" type="java.io.InputStream" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[Create a compression input stream that reads + the decompressed bytes from the given stream. + + @param in The input stream to be compressed.]]> + </doc> + </constructor> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="read" return="int" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read bytes from the stream. + Made abstract to prevent leakage to underlying stream.]]> + </doc> + </method> + <method name="resetState" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Reset the decompressor to its initial state and discard any buffered data, + as the underlying stream may have been repositioned.]]> + </doc> + </method> + <field name="in" type="java.io.InputStream" + transient="false" volatile="false" + static="false" final="true" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[The input stream to be compressed.]]> + </doc> + </field> + <doc> + <![CDATA[A compression input stream. + + <p>Implementations are assumed to be buffered. This permits clients to + reposition the underlying input stream then call {@link #resetState()}, + without having to also synchronize client buffers.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.compress.CompressionInputStream --> + <!-- start class org.apache.hadoop.io.compress.CompressionOutputStream --> + <class name="CompressionOutputStream" extends="java.io.OutputStream" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="CompressionOutputStream" type="java.io.OutputStream" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[Create a compression output stream that writes + the compressed bytes to the given stream. + @param out]]> + </doc> + </constructor> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="flush" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="write" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Write compressed bytes to the stream. + Made abstract to prevent leakage to underlying stream.]]> + </doc> + </method> + <method name="finish" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Finishes writing compressed data to the output stream + without closing the underlying stream.]]> + </doc> + </method> + <method name="resetState" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Reset the compression to the initial state. + Does not reset the underlying stream.]]> + </doc> + </method> + <field name="out" type="java.io.OutputStream" + transient="false" volatile="false" + static="false" final="true" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[The output stream to be compressed.]]> + </doc> + </field> + <doc> + <![CDATA[A compression output stream.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.compress.CompressionOutputStream --> + <!-- start interface org.apache.hadoop.io.compress.Compressor --> + <interface name="Compressor" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="setInput" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + <doc> + <![CDATA[Sets input data for compression. + This should be called whenever #needsInput() returns + <code>true</code> indicating that more input data is required. + + @param b Input data + @param off Start offset + @param len Length]]> + </doc> + </method> + <method name="needsInput" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns true if the input data buffer is empty and + #setInput() should be called to provide more input. + + @return <code>true</code> if the input data buffer is empty and + #setInput() should be called in order to provide more input.]]> + </doc> + </method> + <method name="setDictionary" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + <doc> + <![CDATA[Sets preset dictionary for compression. A preset dictionary + is used when the history buffer can be predetermined. + + @param b Dictionary data bytes + @param off Start offset + @param len Length]]> + </doc> + </method> + <method name="getBytesRead" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return number of uncompressed bytes input so far.]]> + </doc> + </method> + <method name="getBytesWritten" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return number of compressed bytes output so far.]]> + </doc> + </method> + <method name="finish" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[When called, indicates that compression should end + with the current contents of the input buffer.]]> + </doc> + </method> + <method name="finished" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns true if the end of the compressed + data output stream has been reached. + @return <code>true</code> if the end of the compressed + data output stream has been reached.]]> + </doc> + </method> + <method name="compress" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Fills specified buffer with compressed data. Returns actual number + of bytes of compressed data. A return value of 0 indicates that + needsInput() should be called in order to determine if more input + data is required. + + @param b Buffer for the compressed data + @param off Start offset of the data + @param len Size of the buffer + @return The actual number of bytes of compressed data.]]> + </doc> + </method> + <method name="reset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Resets compressor so that a new set of input data can be processed.]]> + </doc> + </method> + <method name="end" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Closes the compressor and discards any unprocessed input.]]> + </doc> + </method> + <doc> + <![CDATA[Specification of a stream-based 'compressor' which can be + plugged into a {@link CompressionOutputStream} to compress data. + This is modelled after {@link java.util.zip.Deflater}]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.io.compress.Compressor --> + <!-- start interface org.apache.hadoop.io.compress.Decompressor --> + <interface name="Decompressor" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="setInput" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + <doc> + <![CDATA[Sets input data for decompression. + This should be called whenever #needsInput() returns + <code>true</code> indicating that more input data is required. + + @param b Input data + @param off Start offset + @param len Length]]> + </doc> + </method> + <method name="needsInput" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns true if the input data buffer is empty and + #setInput() should be called to provide more input. + + @return <code>true</code> if the input data buffer is empty and + #setInput() should be called in order to provide more input.]]> + </doc> + </method> + <method name="setDictionary" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + <doc> + <![CDATA[Sets preset dictionary for compression. A preset dictionary + is used when the history buffer can be predetermined. + + @param b Dictionary data bytes + @param off Start offset + @param len Length]]> + </doc> + </method> + <method name="needsDictionary" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns <code>true</code> if a preset dictionary is needed for decompression. + @return <code>true</code> if a preset dictionary is needed for decompression]]> + </doc> + </method> + <method name="finished" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns true if the end of the compressed + data output stream has been reached. + @return <code>true</code> if the end of the compressed + data output stream has been reached.]]> + </doc> + </method> + <method name="decompress" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Fills specified buffer with uncompressed data. Returns actual number + of bytes of uncompressed data. A return value of 0 indicates that + #needsInput() should be called in order to determine if more input + data is required. + + @param b Buffer for the compressed data + @param off Start offset of the data + @param len Size of the buffer + @return The actual number of bytes of compressed data. + @throws IOException]]> + </doc> + </method> + <method name="reset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Resets decompressor so that a new set of input data can be processed.]]> + </doc> + </method> + <method name="end" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Closes the decompressor and discards any unprocessed input.]]> + </doc> + </method> + <doc> + <![CDATA[Specification of a stream-based 'de-compressor' which can be + plugged into a {@link CompressionInputStream} to compress data. + This is modelled after {@link java.util.zip.Inflater}]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.io.compress.Decompressor --> + <!-- start class org.apache.hadoop.io.compress.DefaultCodec --> + <class name="DefaultCodec" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.conf.Configurable"/> + <implements name="org.apache.hadoop.io.compress.CompressionCodec"/> + <constructor name="DefaultCodec" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="setConf" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + </method> + <method name="getConf" return="org.apache.hadoop.conf.Configuration" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="createOutputStream" return="org.apache.hadoop.io.compress.CompressionOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.OutputStream"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="createOutputStream" return="org.apache.hadoop.io.compress.CompressionOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.OutputStream"/> + <param name="compressor" type="org.apache.hadoop.io.compress.Compressor"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getCompressorType" return="java.lang.Class" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="createCompressor" return="org.apache.hadoop.io.compress.Compressor" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="createInputStream" return="org.apache.hadoop.io.compress.CompressionInputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.InputStream"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="createInputStream" return="org.apache.hadoop.io.compress.CompressionInputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.InputStream"/> + <param name="decompressor" type="org.apache.hadoop.io.compress.Decompressor"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getDecompressorType" return="java.lang.Class" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="createDecompressor" return="org.apache.hadoop.io.compress.Decompressor" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getDefaultExtension" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + </class> + <!-- end class org.apache.hadoop.io.compress.DefaultCodec --> + <!-- start class org.apache.hadoop.io.compress.GzipCodec --> + <class name="GzipCodec" extends="org.apache.hadoop.io.compress.DefaultCodec" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="GzipCodec" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="createOutputStream" return="org.apache.hadoop.io.compress.CompressionOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.OutputStream"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="createOutputStream" return="org.apache.hadoop.io.compress.CompressionOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.OutputStream"/> + <param name="compressor" type="org.apache.hadoop.io.compress.Compressor"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="createCompressor" return="org.apache.hadoop.io.compress.Compressor" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getCompressorType" return="java.lang.Class" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="createInputStream" return="org.apache.hadoop.io.compress.CompressionInputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.InputStream"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="createInputStream" return="org.apache.hadoop.io.compress.CompressionInputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.InputStream"/> + <param name="decompressor" type="org.apache.hadoop.io.compress.Decompressor"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="createDecompressor" return="org.apache.hadoop.io.compress.Decompressor" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getDecompressorType" return="java.lang.Class" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getDefaultExtension" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[This class creates gzip compressors/decompressors.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.compress.GzipCodec --> + <!-- start class org.apache.hadoop.io.compress.GzipCodec.GzipInputStream --> + <class name="GzipCodec.GzipInputStream" extends="org.apache.hadoop.io.compress.DecompressorStream" + abstract="false" + static="true" final="false" visibility="protected" + deprecated="not deprecated"> + <constructor name="GzipCodec.GzipInputStream" type="java.io.InputStream" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </constructor> + <constructor name="GzipCodec.GzipInputStream" type="org.apache.hadoop.io.compress.DecompressorStream" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[Allow subclasses to directly set the inflater stream.]]> + </doc> + </constructor> + <method name="available" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="read" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="read" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="data" type="byte[]"/> + <param name="offset" type="int"/> + <param name="len" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="skip" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="offset" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="resetState" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + </class> + <!-- end class org.apache.hadoop.io.compress.GzipCodec.GzipInputStream --> + <!-- start class org.apache.hadoop.io.compress.GzipCodec.GzipOutputStream --> + <class name="GzipCodec.GzipOutputStream" extends="org.apache.hadoop.io.compress.CompressorStream" + abstract="false" + static="true" final="false" visibility="protected" + deprecated="not deprecated"> + <constructor name="GzipCodec.GzipOutputStream" type="java.io.OutputStream" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </constructor> + <constructor name="GzipCodec.GzipOutputStream" type="org.apache.hadoop.io.compress.CompressorStream" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[Allow children types to put a different type in here. + @param out the Deflater stream to use]]> + </doc> + </constructor> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="flush" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="data" type="byte[]"/> + <param name="offset" type="int"/> + <param name="length" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="finish" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="resetState" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[A bridge that wraps around a DeflaterOutputStream to make it + a CompressionOutputStream.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.compress.GzipCodec.GzipOutputStream --> + <!-- start class org.apache.hadoop.io.compress.LzoCodec --> + <class name="LzoCodec" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.conf.Configurable"/> + <implements name="org.apache.hadoop.io.compress.CompressionCodec"/> + <constructor name="LzoCodec" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="setConf" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + </method> + <method name="getConf" return="org.apache.hadoop.conf.Configuration" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="isNativeLzoLoaded" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[Check if native-lzo library is loaded & initialized. + + @param conf configuration + @return <code>true</code> if native-lzo library is loaded & initialized; + else <code>false</code>]]> + </doc> + </method> + <method name="createOutputStream" return="org.apache.hadoop.io.compress.CompressionOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.OutputStream"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="createOutputStream" return="org.apache.hadoop.io.compress.CompressionOutputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.OutputStream"/> + <param name="compressor" type="org.apache.hadoop.io.compress.Compressor"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getCompressorType" return="java.lang.Class" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="createCompressor" return="org.apache.hadoop.io.compress.Compressor" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="createInputStream" return="org.apache.hadoop.io.compress.CompressionInputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.InputStream"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="createInputStream" return="org.apache.hadoop.io.compress.CompressionInputStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.InputStream"/> + <param name="decompressor" type="org.apache.hadoop.io.compress.Decompressor"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getDecompressorType" return="java.lang.Class" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="createDecompressor" return="org.apache.hadoop.io.compress.Decompressor" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getDefaultExtension" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the default filename extension for this kind of compression. + @return the extension including the '.']]> + </doc> + </method> + <doc> + <![CDATA[A {@link org.apache.hadoop.io.compress.CompressionCodec} for a streaming + <b>lzo</b> compression/decompression pair. + http://www.oberhumer.com/opensource/lzo/]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.compress.LzoCodec --> +</package> +<package name="org.apache.hadoop.io.compress.lzo"> + <!-- start class org.apache.hadoop.io.compress.lzo.LzoCompressor --> + <class name="LzoCompressor" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.compress.Compressor"/> + <constructor name="LzoCompressor" type="org.apache.hadoop.io.compress.lzo.LzoCompressor.CompressionStrategy, int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new compressor using the specified {@link CompressionStrategy}. + + @param strategy lzo compression algorithm to use + @param directBufferSize size of the direct buffer to be used.]]> + </doc> + </constructor> + <constructor name="LzoCompressor" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new compressor with the default lzo1x_1 compression.]]> + </doc> + </constructor> + <method name="isNativeLzoLoaded" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Check if lzo compressors are loaded and initialized. + + @return <code>true</code> if lzo compressors are loaded & initialized, + else <code>false</code>]]> + </doc> + </method> + <method name="setInput" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + </method> + <method name="setDictionary" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + </method> + <method name="needsInput" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="finish" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="finished" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="compress" return="int" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="reset" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getBytesRead" return="long" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return number of bytes given to this compressor since last reset.]]> + </doc> + </method> + <method name="getBytesWritten" return="long" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return number of bytes consumed by callers of compress since last reset.]]> + </doc> + </method> + <method name="end" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Noop.]]> + </doc> + </method> + <doc> + <![CDATA[A {@link Compressor} based on the lzo algorithm. + http://www.oberhumer.com/opensource/lzo/]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.compress.lzo.LzoCompressor --> + <!-- start class org.apache.hadoop.io.compress.lzo.LzoCompressor.CompressionStrategy --> + <class name="LzoCompressor.CompressionStrategy" extends="java.lang.Enum<org.apache.hadoop.io.compress.lzo.LzoCompressor.CompressionStrategy>" + abstract="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <method name="values" return="org.apache.hadoop.io.compress.lzo.LzoCompressor.CompressionStrategy[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="valueOf" return="org.apache.hadoop.io.compress.lzo.LzoCompressor.CompressionStrategy" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + <doc> + <![CDATA[The compression algorithm for lzo library.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.compress.lzo.LzoCompressor.CompressionStrategy --> + <!-- start class org.apache.hadoop.io.compress.lzo.LzoDecompressor --> + <class name="LzoDecompressor" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.compress.Decompressor"/> + <constructor name="LzoDecompressor" type="org.apache.hadoop.io.compress.lzo.LzoDecompressor.CompressionStrategy, int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new lzo decompressor. + + @param strategy lzo decompression algorithm + @param directBufferSize size of the direct-buffer]]> + </doc> + </constructor> + <constructor name="LzoDecompressor" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new lzo decompressor.]]> + </doc> + </constructor> + <method name="isNativeLzoLoaded" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Check if lzo decompressors are loaded and initialized. + + @return <code>true</code> if lzo decompressors are loaded & initialized, + else <code>false</code>]]> + </doc> + </method> + <method name="setInput" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + </method> + <method name="setDictionary" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + </method> + <method name="needsInput" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="needsDictionary" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="finished" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="decompress" return="int" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="reset" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="end" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="finalize" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[A {@link Decompressor} based on the lzo algorithm. + http://www.oberhumer.com/opensource/lzo/]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.compress.lzo.LzoDecompressor --> + <!-- start class org.apache.hadoop.io.compress.lzo.LzoDecompressor.CompressionStrategy --> + <class name="LzoDecompressor.CompressionStrategy" extends="java.lang.Enum<org.apache.hadoop.io.compress.lzo.LzoDecompressor.CompressionStrategy>" + abstract="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <method name="values" return="org.apache.hadoop.io.compress.lzo.LzoDecompressor.CompressionStrategy[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="valueOf" return="org.apache.hadoop.io.compress.lzo.LzoDecompressor.CompressionStrategy" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + </class> + <!-- end class org.apache.hadoop.io.compress.lzo.LzoDecompressor.CompressionStrategy --> +</package> +<package name="org.apache.hadoop.io.compress.zlib"> + <!-- start class org.apache.hadoop.io.compress.zlib.BuiltInZlibDeflater --> + <class name="BuiltInZlibDeflater" extends="java.util.zip.Deflater" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.compress.Compressor"/> + <constructor name="BuiltInZlibDeflater" type="int, boolean" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="BuiltInZlibDeflater" type="int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="BuiltInZlibDeflater" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="compress" return="int" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[A wrapper around java.util.zip.Deflater to make it conform + to org.apache.hadoop.io.compress.Compressor interface.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.compress.zlib.BuiltInZlibDeflater --> + <!-- start class org.apache.hadoop.io.compress.zlib.BuiltInZlibInflater --> + <class name="BuiltInZlibInflater" extends="java.util.zip.Inflater" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.compress.Decompressor"/> + <constructor name="BuiltInZlibInflater" type="boolean" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="BuiltInZlibInflater" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="decompress" return="int" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[A wrapper around java.util.zip.Inflater to make it conform + to org.apache.hadoop.io.compress.Decompressor interface.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.compress.zlib.BuiltInZlibInflater --> + <!-- start class org.apache.hadoop.io.compress.zlib.ZlibCompressor --> + <class name="ZlibCompressor" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.compress.Compressor"/> + <constructor name="ZlibCompressor" type="org.apache.hadoop.io.compress.zlib.ZlibCompressor.CompressionLevel, org.apache.hadoop.io.compress.zlib.ZlibCompressor.CompressionStrategy, org.apache.hadoop.io.compress.zlib.ZlibCompressor.CompressionHeader, int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new compressor using the specified compression level. + Compressed data will be generated in ZLIB format. + + @param level Compression level #CompressionLevel + @param strategy Compression strategy #CompressionStrategy + @param header Compression header #CompressionHeader + @param directBufferSize Size of the direct buffer to be used.]]> + </doc> + </constructor> + <constructor name="ZlibCompressor" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new compressor with the default compression level. + Compressed data will be generated in ZLIB format.]]> + </doc> + </constructor> + <method name="setInput" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + </method> + <method name="setDictionary" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + </method> + <method name="needsInput" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="finish" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="finished" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="compress" return="int" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getBytesWritten" return="long" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the total number of compressed bytes output so far. + + @return the total (non-negative) number of compressed bytes output so far]]> + </doc> + </method> + <method name="getBytesRead" return="long" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the total number of uncompressed bytes input so far.</p> + + @return the total (non-negative) number of uncompressed bytes input so far]]> + </doc> + </method> + <method name="reset" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="end" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[A {@link Compressor} based on the popular + zlib compression algorithm. + http://www.zlib.net/]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.compress.zlib.ZlibCompressor --> + <!-- start class org.apache.hadoop.io.compress.zlib.ZlibCompressor.CompressionHeader --> + <class name="ZlibCompressor.CompressionHeader" extends="java.lang.Enum<org.apache.hadoop.io.compress.zlib.ZlibCompressor.CompressionHeader>" + abstract="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <method name="values" return="org.apache.hadoop.io.compress.zlib.ZlibCompressor.CompressionHeader[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="valueOf" return="org.apache.hadoop.io.compress.zlib.ZlibCompressor.CompressionHeader" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + <method name="windowBits" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[The type of header for compressed data.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.compress.zlib.ZlibCompressor.CompressionHeader --> + <!-- start class org.apache.hadoop.io.compress.zlib.ZlibCompressor.CompressionLevel --> + <class name="ZlibCompressor.CompressionLevel" extends="java.lang.Enum<org.apache.hadoop.io.compress.zlib.ZlibCompressor.CompressionLevel>" + abstract="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <method name="values" return="org.apache.hadoop.io.compress.zlib.ZlibCompressor.CompressionLevel[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="valueOf" return="org.apache.hadoop.io.compress.zlib.ZlibCompressor.CompressionLevel" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + <doc> + <![CDATA[The compression level for zlib library.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.compress.zlib.ZlibCompressor.CompressionLevel --> + <!-- start class org.apache.hadoop.io.compress.zlib.ZlibCompressor.CompressionStrategy --> + <class name="ZlibCompressor.CompressionStrategy" extends="java.lang.Enum<org.apache.hadoop.io.compress.zlib.ZlibCompressor.CompressionStrategy>" + abstract="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <method name="values" return="org.apache.hadoop.io.compress.zlib.ZlibCompressor.CompressionStrategy[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="valueOf" return="org.apache.hadoop.io.compress.zlib.ZlibCompressor.CompressionStrategy" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + <doc> + <![CDATA[The compression level for zlib library.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.compress.zlib.ZlibCompressor.CompressionStrategy --> + <!-- start class org.apache.hadoop.io.compress.zlib.ZlibDecompressor --> + <class name="ZlibDecompressor" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.compress.Decompressor"/> + <constructor name="ZlibDecompressor" type="org.apache.hadoop.io.compress.zlib.ZlibDecompressor.CompressionHeader, int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new decompressor.]]> + </doc> + </constructor> + <constructor name="ZlibDecompressor" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="setInput" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + </method> + <method name="setDictionary" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + </method> + <method name="needsInput" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="needsDictionary" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="finished" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="decompress" return="int" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getBytesWritten" return="long" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the total number of compressed bytes output so far. + + @return the total (non-negative) number of compressed bytes output so far]]> + </doc> + </method> + <method name="getBytesRead" return="long" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the total number of uncompressed bytes input so far.</p> + + @return the total (non-negative) number of uncompressed bytes input so far]]> + </doc> + </method> + <method name="reset" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="end" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="finalize" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[A {@link Decompressor} based on the popular + zlib compression algorithm. + http://www.zlib.net/]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.compress.zlib.ZlibDecompressor --> + <!-- start class org.apache.hadoop.io.compress.zlib.ZlibDecompressor.CompressionHeader --> + <class name="ZlibDecompressor.CompressionHeader" extends="java.lang.Enum<org.apache.hadoop.io.compress.zlib.ZlibDecompressor.CompressionHeader>" + abstract="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <method name="values" return="org.apache.hadoop.io.compress.zlib.ZlibDecompressor.CompressionHeader[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="valueOf" return="org.apache.hadoop.io.compress.zlib.ZlibDecompressor.CompressionHeader" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + <method name="windowBits" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[The headers to detect from compressed data.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.compress.zlib.ZlibDecompressor.CompressionHeader --> + <!-- start class org.apache.hadoop.io.compress.zlib.ZlibFactory --> + <class name="ZlibFactory" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="ZlibFactory" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="isNativeZlibLoaded" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[Check if native-zlib code is loaded & initialized correctly and + can be loaded for this job. + + @param conf configuration + @return <code>true</code> if native-zlib is loaded & initialized + and can be loaded for this job, else <code>false</code>]]> + </doc> + </method> + <method name="getZlibCompressorType" return="java.lang.Class" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[Return the appropriate type of the zlib compressor. + + @param conf configuration + @return the appropriate type of the zlib compressor.]]> + </doc> + </method> + <method name="getZlibCompressor" return="org.apache.hadoop.io.compress.Compressor" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[Return the appropriate implementation of the zlib compressor. + + @param conf configuration + @return the appropriate implementation of the zlib compressor.]]> + </doc> + </method> + <method name="getZlibDecompressorType" return="java.lang.Class" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[Return the appropriate type of the zlib decompressor. + + @param conf configuration + @return the appropriate type of the zlib decompressor.]]> + </doc> + </method> + <method name="getZlibDecompressor" return="org.apache.hadoop.io.compress.Decompressor" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[Return the appropriate implementation of the zlib decompressor. + + @param conf configuration + @return the appropriate implementation of the zlib decompressor.]]> + </doc> + </method> + <doc> + <![CDATA[A collection of factories to create the right + zlib/gzip compressor/decompressor instances.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.compress.zlib.ZlibFactory --> +</package> +<package name="org.apache.hadoop.io.retry"> + <!-- start class org.apache.hadoop.io.retry.RetryPolicies --> + <class name="RetryPolicies" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="RetryPolicies" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="retryUpToMaximumCountWithFixedSleep" return="org.apache.hadoop.io.retry.RetryPolicy" + abstract="false" native="false" synchronized="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <param name="maxRetries" type="int"/> + <param name="sleepTime" type="long"/> + <param name="timeUnit" type="java.util.concurrent.TimeUnit"/> + <doc> + <![CDATA[<p> + Keep trying a limited number of times, waiting a fixed time between attempts, + and then fail by re-throwing the exception. + </p>]]> + </doc> + </method> + <method name="retryUpToMaximumTimeWithFixedSleep" return="org.apache.hadoop.io.retry.RetryPolicy" + abstract="false" native="false" synchronized="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <param name="maxTime" type="long"/> + <param name="sleepTime" type="long"/> + <param name="timeUnit" type="java.util.concurrent.TimeUnit"/> + <doc> + <![CDATA[<p> + Keep trying for a maximum time, waiting a fixed time between attempts, + and then fail by re-throwing the exception. + </p>]]> + </doc> + </method> + <method name="retryUpToMaximumCountWithProportionalSleep" return="org.apache.hadoop.io.retry.RetryPolicy" + abstract="false" native="false" synchronized="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <param name="maxRetries" type="int"/> + <param name="sleepTime" type="long"/> + <param name="timeUnit" type="java.util.concurrent.TimeUnit"/> + <doc> + <![CDATA[<p> + Keep trying a limited number of times, waiting a growing amount of time between attempts, + and then fail by re-throwing the exception. + The time between attempts is <code>sleepTime</code> mutliplied by the number of tries so far. + </p>]]> + </doc> + </method> + <method name="exponentialBackoffRetry" return="org.apache.hadoop.io.retry.RetryPolicy" + abstract="false" native="false" synchronized="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <param name="maxRetries" type="int"/> + <param name="sleepTime" type="long"/> + <param name="timeUnit" type="java.util.concurrent.TimeUnit"/> + <doc> + <![CDATA[<p> + Keep trying a limited number of times, waiting a growing amount of time between attempts, + and then fail by re-throwing the exception. + The time between attempts is <code>sleepTime</code> mutliplied by a random + number in the range of [0, 2 to the number of retries) + </p>]]> + </doc> + </method> + <method name="retryByException" return="org.apache.hadoop.io.retry.RetryPolicy" + abstract="false" native="false" synchronized="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <param name="defaultPolicy" type="org.apache.hadoop.io.retry.RetryPolicy"/> + <param name="exceptionToPolicyMap" type="java.util.Map<java.lang.Class<? extends java.lang.Exception>, org.apache.hadoop.io.retry.RetryPolicy>"/> + <doc> + <![CDATA[<p> + Set a default policy with some explicit handlers for specific exceptions. + </p>]]> + </doc> + </method> + <method name="retryByRemoteException" return="org.apache.hadoop.io.retry.RetryPolicy" + abstract="false" native="false" synchronized="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <param name="defaultPolicy" type="org.apache.hadoop.io.retry.RetryPolicy"/> + <param name="exceptionToPolicyMap" type="java.util.Map<java.lang.Class<? extends java.lang.Exception>, org.apache.hadoop.io.retry.RetryPolicy>"/> + <doc> + <![CDATA[<p> + A retry policy for RemoteException + Set a default policy with some explicit handlers for specific exceptions. + </p>]]> + </doc> + </method> + <field name="TRY_ONCE_THEN_FAIL" type="org.apache.hadoop.io.retry.RetryPolicy" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[<p> + Try once, and fail by re-throwing the exception. + This corresponds to having no retry mechanism in place. + </p>]]> + </doc> + </field> + <field name="TRY_ONCE_DONT_FAIL" type="org.apache.hadoop.io.retry.RetryPolicy" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[<p> + Try once, and fail silently for <code>void</code> methods, or by + re-throwing the exception for non-<code>void</code> methods. + </p>]]> + </doc> + </field> + <field name="RETRY_FOREVER" type="org.apache.hadoop.io.retry.RetryPolicy" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[<p> + Keep trying forever. + </p>]]> + </doc> + </field> + <doc> + <![CDATA[<p> + A collection of useful implementations of {@link RetryPolicy}. + </p>]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.retry.RetryPolicies --> + <!-- start interface org.apache.hadoop.io.retry.RetryPolicy --> + <interface name="RetryPolicy" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="shouldRetry" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="e" type="java.lang.Exception"/> + <param name="retries" type="int"/> + <exception name="Exception" type="java.lang.Exception"/> + <doc> + <![CDATA[<p> + Determines whether the framework should retry a + method for the given exception, and the number + of retries that have been made for that operation + so far. + </p> + @param e The exception that caused the method to fail. + @param retries The number of times the method has been retried. + @return <code>true</code> if the method should be retried, + <code>false</code> if the method should not be retried + but shouldn't fail with an exception (only for void methods). + @throws Exception The re-thrown exception <code>e</code> indicating + that the method failed and should not be retried further.]]> + </doc> + </method> + <doc> + <![CDATA[<p> + Specifies a policy for retrying method failures. + Implementations of this interface should be immutable. + </p>]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.io.retry.RetryPolicy --> + <!-- start class org.apache.hadoop.io.retry.RetryProxy --> + <class name="RetryProxy" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="RetryProxy" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="create" return="java.lang.Object" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="iface" type="java.lang.Class<?>"/> + <param name="implementation" type="java.lang.Object"/> + <param name="retryPolicy" type="org.apache.hadoop.io.retry.RetryPolicy"/> + <doc> + <![CDATA[<p> + Create a proxy for an interface of an implementation class + using the same retry policy for each method in the interface. + </p> + @param iface the interface that the retry will implement + @param implementation the instance whose methods should be retried + @param retryPolicy the policy for retirying method call failures + @return the retry proxy]]> + </doc> + </method> + <method name="create" return="java.lang.Object" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="iface" type="java.lang.Class<?>"/> + <param name="implementation" type="java.lang.Object"/> + <param name="methodNameToPolicyMap" type="java.util.Map<java.lang.String, org.apache.hadoop.io.retry.RetryPolicy>"/> + <doc> + <![CDATA[<p> + Create a proxy for an interface of an implementation class + using the a set of retry policies specified by method name. + If no retry policy is defined for a method then a default of + {@link RetryPolicies#TRY_ONCE_THEN_FAIL} is used. + </p> + @param iface the interface that the retry will implement + @param implementation the instance whose methods should be retried + @param methodNameToPolicyMap a map of method names to retry policies + @return the retry proxy]]> + </doc> + </method> + <doc> + <![CDATA[<p> + A factory for creating retry proxies. + </p>]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.retry.RetryProxy --> + <doc> + <![CDATA[<p> +A mechanism for selectively retrying methods that throw exceptions under certain circumstances. +</p> + +<p> +Typical usage is +</p> + +<pre> +UnreliableImplementation unreliableImpl = new UnreliableImplementation(); +UnreliableInterface unreliable = (UnreliableInterface) + RetryProxy.create(UnreliableInterface.class, unreliableImpl, + RetryPolicies.retryUpToMaximumCountWithFixedSleep(4, 10, TimeUnit.SECONDS)); +unreliable.call(); +</pre> + +<p> +This will retry any method called on <code>unreliable</code> four times - in this case the <code>call()</code> +method - sleeping 10 seconds between +each retry. There are a number of {@link org.apache.hadoop.io.retry.RetryPolicies retry policies} +available, or you can implement a custom one by implementing {@link org.apache.hadoop.io.retry.RetryPolicy}. +It is also possible to specify retry policies on a +{@link org.apache.hadoop.io.retry.RetryProxy#create(Class, Object, Map) per-method basis}. +</p>]]> + </doc> +</package> +<package name="org.apache.hadoop.io.serializer"> + <!-- start interface org.apache.hadoop.io.serializer.Deserializer --> + <interface name="Deserializer" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="open" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.InputStream"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[<p>Prepare the deserializer for reading.</p>]]> + </doc> + </method> + <method name="deserialize" return="T" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="t" type="T"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[<p> + Deserialize the next object from the underlying input stream. + If the object <code>t</code> is non-null then this deserializer + <i>may</i> set its internal state to the next object read from the input + stream. Otherwise, if the object <code>t</code> is null a new + deserialized object will be created. + </p> + @return the deserialized object]]> + </doc> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[<p>Close the underlying input stream and clear up any resources.</p>]]> + </doc> + </method> + <doc> + <![CDATA[<p> + Provides a facility for deserializing objects of type <T> from an + {@link InputStream}. + </p> + + <p> + Deserializers are stateful, but must not buffer the input since + other producers may read from the input between calls to + {@link #deserialize(Object)}. + </p> + @param <T>]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.io.serializer.Deserializer --> + <!-- start class org.apache.hadoop.io.serializer.DeserializerComparator --> + <class name="DeserializerComparator" extends="java.lang.Object" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.RawComparator<T>"/> + <constructor name="DeserializerComparator" type="org.apache.hadoop.io.serializer.Deserializer<T>" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </constructor> + <method name="compare" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b1" type="byte[]"/> + <param name="s1" type="int"/> + <param name="l1" type="int"/> + <param name="b2" type="byte[]"/> + <param name="s2" type="int"/> + <param name="l2" type="int"/> + </method> + <doc> + <![CDATA[<p> + A {@link RawComparator} that uses a {@link Deserializer} to deserialize + the objects to be compared so that the standard {@link Comparator} can + be used to compare them. + </p> + <p> + One may optimize compare-intensive operations by using a custom + implementation of {@link RawComparator} that operates directly + on byte representations. + </p> + @param <T>]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.serializer.DeserializerComparator --> + <!-- start class org.apache.hadoop.io.serializer.JavaSerialization --> + <class name="JavaSerialization" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.serializer.Serialization<java.io.Serializable>"/> + <constructor name="JavaSerialization" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="accept" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="c" type="java.lang.Class<?>"/> + </method> + <method name="getDeserializer" return="org.apache.hadoop.io.serializer.Deserializer<java.io.Serializable>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="c" type="java.lang.Class<java.io.Serializable>"/> + </method> + <method name="getSerializer" return="org.apache.hadoop.io.serializer.Serializer<java.io.Serializable>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="c" type="java.lang.Class<java.io.Serializable>"/> + </method> + <doc> + <![CDATA[<p> + An experimental {@link Serialization} for Java {@link Serializable} classes. + </p> + @see JavaSerializationComparator]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.serializer.JavaSerialization --> + <!-- start class org.apache.hadoop.io.serializer.JavaSerializationComparator --> + <class name="JavaSerializationComparator" extends="org.apache.hadoop.io.serializer.DeserializerComparator<T>" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JavaSerializationComparator" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </constructor> + <method name="compare" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o1" type="T extends java.io.Serializable & java.lang.Comparable<T>"/> + <param name="o2" type="T extends java.io.Serializable & java.lang.Comparable<T>"/> + </method> + <doc> + <![CDATA[<p> + A {@link RawComparator} that uses a {@link JavaSerialization} + {@link Deserializer} to deserialize objects that are then compared via + their {@link Comparable} interfaces. + </p> + @param <T> + @see JavaSerialization]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.serializer.JavaSerializationComparator --> + <!-- start interface org.apache.hadoop.io.serializer.Serialization --> + <interface name="Serialization" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="accept" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="c" type="java.lang.Class<?>"/> + <doc> + <![CDATA[Allows clients to test whether this {@link Serialization} + supports the given class.]]> + </doc> + </method> + <method name="getSerializer" return="org.apache.hadoop.io.serializer.Serializer<T>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="c" type="java.lang.Class<T>"/> + <doc> + <![CDATA[@return a {@link Serializer} for the given class.]]> + </doc> + </method> + <method name="getDeserializer" return="org.apache.hadoop.io.serializer.Deserializer<T>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="c" type="java.lang.Class<T>"/> + <doc> + <![CDATA[@return a {@link Deserializer} for the given class.]]> + </doc> + </method> + <doc> + <![CDATA[<p> + Encapsulates a {@link Serializer}/{@link Deserializer} pair. + </p> + @param <T>]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.io.serializer.Serialization --> + <!-- start class org.apache.hadoop.io.serializer.SerializationFactory --> + <class name="SerializationFactory" extends="org.apache.hadoop.conf.Configured" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="SerializationFactory" type="org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[<p> + Serializations are found by reading the <code>io.serializations</code> + property from <code>conf</code>, which is a comma-delimited list of + classnames. + </p>]]> + </doc> + </constructor> + <method name="getSerializer" return="org.apache.hadoop.io.serializer.Serializer<T>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="c" type="java.lang.Class<T>"/> + </method> + <method name="getDeserializer" return="org.apache.hadoop.io.serializer.Deserializer<T>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="c" type="java.lang.Class<T>"/> + </method> + <method name="getSerialization" return="org.apache.hadoop.io.serializer.Serialization<T>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="c" type="java.lang.Class<T>"/> + </method> + <doc> + <![CDATA[<p> + A factory for {@link Serialization}s. + </p>]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.serializer.SerializationFactory --> + <!-- start interface org.apache.hadoop.io.serializer.Serializer --> + <interface name="Serializer" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="open" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.OutputStream"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[<p>Prepare the serializer for writing.</p>]]> + </doc> + </method> + <method name="serialize" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="t" type="T"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[<p>Serialize <code>t</code> to the underlying output stream.</p>]]> + </doc> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[<p>Close the underlying output stream and clear up any resources.</p>]]> + </doc> + </method> + <doc> + <![CDATA[<p> + Provides a facility for serializing objects of type <T> to an + {@link OutputStream}. + </p> + + <p> + Serializers are stateful, but must not buffer the output since + other producers may write to the output between calls to + {@link #serialize(Object)}. + </p> + @param <T>]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.io.serializer.Serializer --> + <!-- start class org.apache.hadoop.io.serializer.WritableSerialization --> + <class name="WritableSerialization" extends="org.apache.hadoop.conf.Configured" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.serializer.Serialization<org.apache.hadoop.io.Writable>"/> + <constructor name="WritableSerialization" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="accept" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="c" type="java.lang.Class<?>"/> + </method> + <method name="getDeserializer" return="org.apache.hadoop.io.serializer.Deserializer<org.apache.hadoop.io.Writable>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="c" type="java.lang.Class<org.apache.hadoop.io.Writable>"/> + </method> + <method name="getSerializer" return="org.apache.hadoop.io.serializer.Serializer<org.apache.hadoop.io.Writable>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="c" type="java.lang.Class<org.apache.hadoop.io.Writable>"/> + </method> + <doc> + <![CDATA[A {@link Serialization} for {@link Writable}s that delegates to + {@link Writable#write(java.io.DataOutput)} and + {@link Writable#readFields(java.io.DataInput)}.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.io.serializer.WritableSerialization --> + <doc> + <![CDATA[<p> +This package provides a mechanism for using different serialization frameworks +in Hadoop. The property "io.serializations" defines a list of +{@link org.apache.hadoop.io.serializer.Serialization}s that know how to create +{@link org.apache.hadoop.io.serializer.Serializer}s and +{@link org.apache.hadoop.io.serializer.Deserializer}s. +</p> + +<p> +To add a new serialization framework write an implementation of +{@link org.apache.hadoop.io.serializer.Serialization} and add its name to the +"io.serializations" property. +</p>]]> + </doc> +</package> +<package name="org.apache.hadoop.ipc"> + <!-- start class org.apache.hadoop.ipc.Client --> + <class name="Client" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="Client" type="java.lang.Class, org.apache.hadoop.conf.Configuration, javax.net.SocketFactory" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct an IPC client whose values are of the given {@link Writable} + class.]]> + </doc> + </constructor> + <constructor name="Client" type="java.lang.Class<?>, org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct an IPC client with the default SocketFactory + @param valueClass + @param conf]]> + </doc> + </constructor> + <method name="stop" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Stop all threads related to this client. No further calls may be made + using this client.]]> + </doc> + </method> + <method name="setTimeout" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="timeout" type="int"/> + <doc> + <![CDATA[Sets the timeout used for network i/o.]]> + </doc> + </method> + <method name="call" return="org.apache.hadoop.io.Writable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="param" type="org.apache.hadoop.io.Writable"/> + <param name="address" type="java.net.InetSocketAddress"/> + <exception name="InterruptedException" type="java.lang.InterruptedException"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Make a call, passing <code>param</code>, to the IPC server running at + <code>address</code>, returning the value. Throws exceptions if there are + network problems or if the remote code threw an exception.]]> + </doc> + </method> + <method name="call" return="org.apache.hadoop.io.Writable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="param" type="org.apache.hadoop.io.Writable"/> + <param name="addr" type="java.net.InetSocketAddress"/> + <param name="ticket" type="org.apache.hadoop.security.UserGroupInformation"/> + <exception name="InterruptedException" type="java.lang.InterruptedException"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="call" return="org.apache.hadoop.io.Writable[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="params" type="org.apache.hadoop.io.Writable[]"/> + <param name="addresses" type="java.net.InetSocketAddress[]"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Makes a set of calls in parallel. Each parameter is sent to the + corresponding address. When all values are available, or have timed out + or errored, the collected results are returned in an array. The array + contains nulls for calls that timed out or errored.]]> + </doc> + </method> + <field name="LOG" type="org.apache.commons.logging.Log" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[A client for an IPC service. IPC calls take a single {@link Writable} as a + parameter, and return a {@link Writable} as their value. A service runs on + a port and is defined by a parameter class and a value class. + + @see Server]]> + </doc> + </class> + <!-- end class org.apache.hadoop.ipc.Client --> + <!-- start class org.apache.hadoop.ipc.RemoteException --> + <class name="RemoteException" extends="java.io.IOException" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="RemoteException" type="java.lang.String, java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getClassName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="unwrapRemoteException" return="java.io.IOException" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="lookupTypes" type="java.lang.Class[]"/> + <doc> + <![CDATA[If this remote exception wraps up one of the lookupTypes + then return this exception. + <p> + Unwraps any IOException. + + @param lookupTypes the desired exception class. + @return IOException, which is either the lookupClass exception or this.]]> + </doc> + </method> + <method name="unwrapRemoteException" return="java.io.IOException" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Instantiate and return the exception wrapped up by this remote exception. + + <p> This unwraps any <code>Throwable</code> that has a constructor taking + a <code>String</code> as a parameter. + Otherwise it returns this. + + @return <code>Throwable]]> + </doc> + </method> + </class> + <!-- end class org.apache.hadoop.ipc.RemoteException --> + <!-- start class org.apache.hadoop.ipc.RPC --> + <class name="RPC" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="waitForProxy" return="org.apache.hadoop.ipc.VersionedProtocol" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="protocol" type="java.lang.Class"/> + <param name="clientVersion" type="long"/> + <param name="addr" type="java.net.InetSocketAddress"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getProxy" return="org.apache.hadoop.ipc.VersionedProtocol" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="protocol" type="java.lang.Class<?>"/> + <param name="clientVersion" type="long"/> + <param name="addr" type="java.net.InetSocketAddress"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="factory" type="javax.net.SocketFactory"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct a client-side proxy object that implements the named protocol, + talking to a server at the named address.]]> + </doc> + </method> + <method name="getProxy" return="org.apache.hadoop.ipc.VersionedProtocol" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="protocol" type="java.lang.Class<?>"/> + <param name="clientVersion" type="long"/> + <param name="addr" type="java.net.InetSocketAddress"/> + <param name="ticket" type="org.apache.hadoop.security.UserGroupInformation"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="factory" type="javax.net.SocketFactory"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct a client-side proxy object that implements the named protocol, + talking to a server at the named address.]]> + </doc> + </method> + <method name="getProxy" return="org.apache.hadoop.ipc.VersionedProtocol" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="protocol" type="java.lang.Class<?>"/> + <param name="clientVersion" type="long"/> + <param name="addr" type="java.net.InetSocketAddress"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct a client-side proxy object with the default SocketFactory + + @param protocol + @param clientVersion + @param addr + @param conf + @return a proxy instance + @throws IOException]]> + </doc> + </method> + <method name="stopProxy" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="proxy" type="org.apache.hadoop.ipc.VersionedProtocol"/> + <doc> + <![CDATA[Stop this proxy and release its invoker's resource + @param proxy the proxy to be stopped]]> + </doc> + </method> + <method name="call" return="java.lang.Object[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="method" type="java.lang.reflect.Method"/> + <param name="params" type="java.lang.Object[][]"/> + <param name="addrs" type="java.net.InetSocketAddress[]"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Expert: Make multiple, parallel calls to a set of servers.]]> + </doc> + </method> + <method name="getServer" return="org.apache.hadoop.ipc.RPC.Server" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="instance" type="java.lang.Object"/> + <param name="bindAddress" type="java.lang.String"/> + <param name="port" type="int"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct a server for a protocol implementation instance listening on a + port and address.]]> + </doc> + </method> + <method name="getServer" return="org.apache.hadoop.ipc.RPC.Server" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="instance" type="java.lang.Object"/> + <param name="bindAddress" type="java.lang.String"/> + <param name="port" type="int"/> + <param name="numHandlers" type="int"/> + <param name="verbose" type="boolean"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct a server for a protocol implementation instance listening on a + port and address.]]> + </doc> + </method> + <doc> + <![CDATA[A simple RPC mechanism. + + A <i>protocol</i> is a Java interface. All parameters and return types must + be one of: + + <ul> <li>a primitive type, <code>boolean</code>, <code>byte</code>, + <code>char</code>, <code>short</code>, <code>int</code>, <code>long</code>, + <code>float</code>, <code>double</code>, or <code>void</code>; or</li> + + <li>a {@link String}; or</li> + + <li>a {@link Writable}; or</li> + + <li>an array of the above types</li> </ul> + + All methods in the protocol should throw only IOException. No field data of + the protocol instance is transmitted.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.ipc.RPC --> + <!-- start class org.apache.hadoop.ipc.RPC.Server --> + <class name="RPC.Server" extends="org.apache.hadoop.ipc.Server" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="RPC.Server" type="java.lang.Object, org.apache.hadoop.conf.Configuration, java.lang.String, int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct an RPC server. + @param instance the instance whose methods will be called + @param conf the configuration to use + @param bindAddress the address to bind on to listen for connection + @param port the port to listen for connections on]]> + </doc> + </constructor> + <constructor name="RPC.Server" type="java.lang.Object, org.apache.hadoop.conf.Configuration, java.lang.String, int, int, boolean" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct an RPC server. + @param instance the instance whose methods will be called + @param conf the configuration to use + @param bindAddress the address to bind on to listen for connection + @param port the port to listen for connections on + @param numHandlers the number of method handler threads to run + @param verbose whether each call should be logged]]> + </doc> + </constructor> + <method name="call" return="org.apache.hadoop.io.Writable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="param" type="org.apache.hadoop.io.Writable"/> + <param name="receivedTime" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[An RPC Server.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.ipc.RPC.Server --> + <!-- start class org.apache.hadoop.ipc.RPC.VersionMismatch --> + <class name="RPC.VersionMismatch" extends="java.io.IOException" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="RPC.VersionMismatch" type="java.lang.String, long, long" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Create a version mismatch exception + @param interfaceName the name of the protocol mismatch + @param clientVersion the client's version of the protocol + @param serverVersion the server's version of the protocol]]> + </doc> + </constructor> + <method name="getInterfaceName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the interface name + @return the java class name + (eg. org.apache.hadoop.mapred.InterTrackerProtocol)]]> + </doc> + </method> + <method name="getClientVersion" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the client's preferred version]]> + </doc> + </method> + <method name="getServerVersion" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the server's agreed to version.]]> + </doc> + </method> + <doc> + <![CDATA[A version mismatch for the RPC protocol.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.ipc.RPC.VersionMismatch --> + <!-- start class org.apache.hadoop.ipc.Server --> + <class name="Server" extends="java.lang.Object" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="Server" type="java.lang.String, int, java.lang.Class, int, org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </constructor> + <constructor name="Server" type="java.lang.String, int, java.lang.Class, int, org.apache.hadoop.conf.Configuration, java.lang.String" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Constructs a server listening on the named port and address. Parameters passed must + be of the named class. The <code>handlerCount</handlerCount> determines + the number of handler threads that will be used to process calls.]]> + </doc> + </constructor> + <method name="get" return="org.apache.hadoop.ipc.Server" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the server instance called under or null. May be called under + {@link #call(Writable, long)} implementations, and under {@link Writable} + methods of paramters and return values. Permits applications to access + the server context.]]> + </doc> + </method> + <method name="getRemoteIp" return="java.net.InetAddress" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the remote side ip address when invoked inside an RPC + Returns null incase of an error.]]> + </doc> + </method> + <method name="getRemoteAddress" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns remote address as a string when invoked inside an RPC. + Returns null in case of an error.]]> + </doc> + </method> + <method name="bind" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="socket" type="java.net.ServerSocket"/> + <param name="address" type="java.net.InetSocketAddress"/> + <param name="backlog" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[A convience method to bind to a given address and report + better exceptions if the address is not a valid host. + @param socket the socket to bind + @param address the address to bind to + @param backlog the number of connections allowed in the queue + @throws BindException if the address can't be bound + @throws UnknownHostException if the address isn't a valid host name + @throws IOException other random errors from bind]]> + </doc> + </method> + <method name="setTimeout" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="timeout" type="int"/> + <doc> + <![CDATA[Sets the timeout used for network i/o.]]> + </doc> + </method> + <method name="setSocketSendBufSize" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="size" type="int"/> + <doc> + <![CDATA[Sets the socket buffer size used for responding to RPCs]]> + </doc> + </method> + <method name="start" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Starts the service. Must be called before any calls will be handled.]]> + </doc> + </method> + <method name="stop" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Stops the service. No new calls will be handled after this is called.]]> + </doc> + </method> + <method name="join" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="InterruptedException" type="java.lang.InterruptedException"/> + <doc> + <![CDATA[Wait for the server to be stopped. + Does not wait for all subthreads to finish. + See {@link #stop()}.]]> + </doc> + </method> + <method name="getListenerAddress" return="java.net.InetSocketAddress" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the socket (ip+port) on which the RPC server is listening to. + @return the socket (ip+port) on which the RPC server is listening to.]]> + </doc> + </method> + <method name="call" return="org.apache.hadoop.io.Writable" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="param" type="org.apache.hadoop.io.Writable"/> + <param name="receiveTime" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Called for each call.]]> + </doc> + </method> + <method name="getNumOpenConnections" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The number of open RPC conections + @return the number of open rpc connections]]> + </doc> + </method> + <method name="getCallQueueLen" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The number of rpc calls in the queue. + @return The number of rpc calls in the queue.]]> + </doc> + </method> + <field name="HEADER" type="java.nio.ByteBuffer" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The first four bytes of Hadoop RPC connections]]> + </doc> + </field> + <field name="CURRENT_VERSION" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="LOG" type="org.apache.commons.logging.Log" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="rpcMetrics" type="org.apache.hadoop.ipc.metrics.RpcMetrics" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[An abstract IPC service. IPC calls take a single {@link Writable} as a + parameter, and return a {@link Writable} as their value. A service runs on + a port and is defined by a parameter class and a value class. + + @see Client]]> + </doc> + </class> + <!-- end class org.apache.hadoop.ipc.Server --> + <!-- start interface org.apache.hadoop.ipc.VersionedProtocol --> + <interface name="VersionedProtocol" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="getProtocolVersion" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="protocol" type="java.lang.String"/> + <param name="clientVersion" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return protocol version corresponding to protocol interface. + @param protocol The classname of the protocol interface + @param clientVersion The version of the protocol that the client speaks + @return the version that the server will speak]]> + </doc> + </method> + <doc> + <![CDATA[Superclass of all protocols that use Hadoop RPC. + Subclasses of this interface are also supposed to have + a static final long versionID field.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.ipc.VersionedProtocol --> + <doc> + <![CDATA[Tools to help define network clients and servers.]]> + </doc> +</package> +<package name="org.apache.hadoop.ipc.metrics"> + <!-- start class org.apache.hadoop.ipc.metrics.RpcMetrics --> + <class name="RpcMetrics" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.metrics.Updater"/> + <constructor name="RpcMetrics" type="java.lang.String, java.lang.String, org.apache.hadoop.ipc.Server" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="doUpdates" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="context" type="org.apache.hadoop.metrics.MetricsContext"/> + <doc> + <![CDATA[Push the metrics to the monitoring subsystem on doUpdate() call.]]> + </doc> + </method> + <method name="shutdown" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <field name="rpcQueueTime" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingRate" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The metrics variables are public: + - they can be set directly by calling their set/inc methods + -they can also be read directly - e.g. JMX does this.]]> + </doc> + </field> + <field name="rpcProcessingTime" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingRate" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="rpcDiscardedOps" type="org.apache.hadoop.metrics.util.MetricsTimeVaryingRate" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="metricsList" type="java.util.Map<java.lang.String, org.apache.hadoop.metrics.util.MetricsTimeVaryingRate>" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[This class is for maintaining the various RPC statistics + and publishing them through the metrics interfaces. + This also registers the JMX MBean for RPC. + <p> + This class has a number of metrics variables that are publicly accessible; + these variables (objects) have methods to update their values; + for example: + <p> {@link #rpcDiscardedOps}.inc(time)]]> + </doc> + </class> + <!-- end class org.apache.hadoop.ipc.metrics.RpcMetrics --> + <!-- start interface org.apache.hadoop.ipc.metrics.RpcMgtMBean --> + <interface name="RpcMgtMBean" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="getRpcOpsNumber" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of RPC Operations in the last interval + @return number of operations]]> + </doc> + </method> + <method name="getRpcOpsAvgProcessingTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Average time for RPC Operations in last interval + @return time in msec]]> + </doc> + </method> + <method name="getRpcOpsAvgProcessingTimeMin" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Minimum RPC Operation Processing Time since reset was called + @return time in msec]]> + </doc> + </method> + <method name="getRpcOpsAvgProcessingTimeMax" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Maximum RPC Operation Processing Time since reset was called + @return time in msec]]> + </doc> + </method> + <method name="getRpcOpsAvgQueueTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Average RPC Operation Queued Time in the last interval + @return time in msec]]> + </doc> + </method> + <method name="getRpcOpsAvgQueueTimeMin" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Minimum RPC Operation Queued Time since reset was called + @return time in msec]]> + </doc> + </method> + <method name="getRpcOpsAvgQueueTimeMax" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Maximum RPC Operation Queued Time since reset was called + @return time in msec]]> + </doc> + </method> + <method name="getRpcOpsDiscardedOpsNum" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Number of Discarded RPC operations due to timeout in the last interval + @return number of operations]]> + </doc> + </method> + <method name="getRpcOpsDiscardedOpsQtime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Average Queued time for Discarded RPC Operations in last interval + @return time in msec]]> + </doc> + </method> + <method name="resetAllMinMax" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Reset all min max times]]> + </doc> + </method> + <method name="getNumOpenConnections" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The number of open RPC conections + @return the number of open rpc connections]]> + </doc> + </method> + <method name="getCallQueueLen" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The number of rpc calls in the queue. + @return The number of rpc calls in the queue.]]> + </doc> + </method> + <doc> + <![CDATA[This is the JMX management interface for the RPC layer. + Many of the statistics are sampled and averaged on an interval + which can be specified in the metrics config file. + <p> + For the statistics that are sampled and averaged, one must specify + a metrics context that does periodic update calls. Most do. + The default Null metrics context however does NOT. So if you aren't + using any other metrics context then you can turn on the viewing and averaging + of sampled metrics by specifying the following two lines + in the hadoop-meterics.properties file: + <pre> + rpc.class=org.apache.hadoop.metrics.spi.NullContextWithUpdateThread + rpc.period=10 + </pre> +<p> + Note that the metrics are collected regardless of the context used. + The context with the update thread is used to average the data periodically]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.ipc.metrics.RpcMgtMBean --> +</package> +<package name="org.apache.hadoop.log"> + <!-- start class org.apache.hadoop.log.LogLevel --> + <class name="LogLevel" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="LogLevel" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <doc> + <![CDATA[A command line implementation]]> + </doc> + </method> + <field name="USAGES" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[Change log level in runtime.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.log.LogLevel --> + <!-- start class org.apache.hadoop.log.LogLevel.Servlet --> + <class name="LogLevel.Servlet" extends="javax.servlet.http.HttpServlet" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="LogLevel.Servlet" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="doGet" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="request" type="javax.servlet.http.HttpServletRequest"/> + <param name="response" type="javax.servlet.http.HttpServletResponse"/> + <exception name="ServletException" type="javax.servlet.ServletException"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[A servlet implementation]]> + </doc> + </class> + <!-- end class org.apache.hadoop.log.LogLevel.Servlet --> +</package> +<package name="org.apache.hadoop.mapred"> + <!-- start class org.apache.hadoop.mapred.ClusterStatus --> + <class name="ClusterStatus" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <method name="getTaskTrackers" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the number of task trackers in the cluster. + + @return the number of task trackers in the cluster.]]> + </doc> + </method> + <method name="getMapTasks" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the number of currently running map tasks in the cluster. + + @return the number of currently running map tasks in the cluster.]]> + </doc> + </method> + <method name="getReduceTasks" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the number of currently running reduce tasks in the cluster. + + @return the number of currently running reduce tasks in the cluster.]]> + </doc> + </method> + <method name="getMaxMapTasks" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the maximum capacity for running map tasks in the cluster. + + @return the maximum capacity for running map tasks in the cluster.]]> + </doc> + </method> + <method name="getMaxReduceTasks" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the maximum capacity for running reduce tasks in the cluster. + + @return the maximum capacity for running reduce tasks in the cluster.]]> + </doc> + </method> + <method name="getJobTrackerState" return="org.apache.hadoop.mapred.JobTracker.State" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the current state of the <code>JobTracker</code>, + as {@link JobTracker.State} + + @return the current state of the <code>JobTracker</code>.]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[Status information on the current state of the Map-Reduce cluster. + + <p><code>ClusterStatus</code> provides clients with information such as: + <ol> + <li> + Size of the cluster. + </li> + <li> + Task capacity of the cluster. + </li> + <li> + The number of currently running map & reduce tasks. + </li> + <li> + State of the <code>JobTracker</code>. + </li> + </ol></p> + + <p>Clients can query for the latest <code>ClusterStatus</code>, via + {@link JobClient#getClusterStatus()}.</p> + + @see JobClient]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.ClusterStatus --> + <!-- start class org.apache.hadoop.mapred.CompletedJobStatusStore --> + <class name="CompletedJobStatusStore" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="java.lang.Runnable"/> + <method name="isActive" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Indicates if job status persistency is active or not. + + @return TRUE if active, FALSE otherwise.]]> + </doc> + </method> + <method name="run" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="store" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobInProgress"/> + <doc> + <![CDATA[Persists a job in DFS. + + @param job the job about to be 'retired']]> + </doc> + </method> + <method name="readJobStatus" return="org.apache.hadoop.mapred.JobStatus" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <doc> + <![CDATA[This method retrieves JobStatus information from DFS stored using + store method. + + @param jobId the jobId for which jobStatus is queried + @return JobStatus object, null if not able to retrieve]]> + </doc> + </method> + <method name="readJobProfile" return="org.apache.hadoop.mapred.JobProfile" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <doc> + <![CDATA[This method retrieves JobProfile information from DFS stored using + store method. + + @param jobId the jobId for which jobProfile is queried + @return JobProfile object, null if not able to retrieve]]> + </doc> + </method> + <method name="readCounters" return="org.apache.hadoop.mapred.Counters" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <doc> + <![CDATA[This method retrieves Counters information from DFS stored using + store method. + + @param jobId the jobId for which Counters is queried + @return Counters object, null if not able to retrieve]]> + </doc> + </method> + <method name="readJobTaskCompletionEvents" return="org.apache.hadoop.mapred.TaskCompletionEvent[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <param name="fromEventId" type="int"/> + <param name="maxEvents" type="int"/> + <doc> + <![CDATA[This method retrieves TaskCompletionEvents information from DFS stored + using store method. + + @param jobId the jobId for which TaskCompletionEvents is queried + @param fromEventId events offset + @param maxEvents max number of events + @return TaskCompletionEvent[], empty array if not able to retrieve]]> + </doc> + </method> + <field name="LOG" type="org.apache.commons.logging.Log" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[Persists and retrieves the Job info of a job into/from DFS. + <p/> + If the retain time is zero jobs are not persisted. + <p/> + A daemon thread cleans up job info files older than the retain time + <p/> + The retain time can be set with the 'persist.jobstatus.hours' + configuration variable (it is in hours).]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.CompletedJobStatusStore --> + <!-- start class org.apache.hadoop.mapred.Counters --> + <class name="Counters" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <implements name="java.lang.Iterable<org.apache.hadoop.mapred.Counters.Group>"/> + <constructor name="Counters" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getGroupNames" return="java.util.Collection<java.lang.String>" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the names of all counter classes. + @return Set of counter names.]]> + </doc> + </method> + <method name="iterator" return="java.util.Iterator<org.apache.hadoop.mapred.Counters.Group>" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getGroup" return="org.apache.hadoop.mapred.Counters.Group" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="groupName" type="java.lang.String"/> + <doc> + <![CDATA[Returns the named counter group, or an empty group if there is none + with the specified name.]]> + </doc> + </method> + <method name="findCounter" return="org.apache.hadoop.mapred.Counters.Counter" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="java.lang.Enum"/> + <doc> + <![CDATA[Find the counter for the given enum. The same enum will always return the + same counter. + @param key the counter key + @return the matching counter object]]> + </doc> + </method> + <method name="findCounter" return="org.apache.hadoop.mapred.Counters.Counter" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="group" type="java.lang.String"/> + <param name="id" type="int"/> + <param name="name" type="java.lang.String"/> + <doc> + <![CDATA[Find a counter by using strings + @param group the name of the group + @param id the id of the counter within the group (0 to N-1) + @param name the internal name of the counter + @return the counter for that name]]> + </doc> + </method> + <method name="incrCounter" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="java.lang.Enum"/> + <param name="amount" type="long"/> + <doc> + <![CDATA[Increments the specified counter by the specified amount, creating it if + it didn't already exist. + @param key identifies a counter + @param amount amount by which counter is to be incremented]]> + </doc> + </method> + <method name="getCounter" return="long" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="java.lang.Enum"/> + <doc> + <![CDATA[Returns current value of the specified counter, or 0 if the counter + does not exist.]]> + </doc> + </method> + <method name="incrAllCounters" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="other" type="org.apache.hadoop.mapred.Counters"/> + <doc> + <![CDATA[Increments multiple counters by their amounts in another Counters + instance. + @param other the other Counters instance]]> + </doc> + </method> + <method name="sum" return="org.apache.hadoop.mapred.Counters" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="a" type="org.apache.hadoop.mapred.Counters"/> + <param name="b" type="org.apache.hadoop.mapred.Counters"/> + <doc> + <![CDATA[Convenience method for computing the sum of two sets of counters.]]> + </doc> + </method> + <method name="size" return="int" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the total number of counters, by summing the number of counters + in each group.]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Write the set of groups. + The external format is: + #groups (groupName group)* + + i.e. the number of groups followed by 0 or more groups, where each + group is of the form: + + groupDisplayName #counters (false | true counter)* + + where each counter is of the form: + + name value]]> + </doc> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read a set of groups.]]> + </doc> + </method> + <method name="log" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="log" type="org.apache.commons.logging.Log"/> + <doc> + <![CDATA[Logs the current counter values. + @param log The log to use.]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return textual representation of the counter values.]]> + </doc> + </method> + <method name="makeCompactString" return="java.lang.String" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Convert a counters object into a single line that is easy to parse. + @return the string with "name=value" for each counter and separated by ","]]> + </doc> + </method> + <doc> + <![CDATA[A set of named counters. + + <p><code>Counters</code> represent global counters, defined either by the + Map-Reduce framework or applications. Each <code>Counter</code> can be of + any {@link Enum} type.</p> + + <p><code>Counters</code> are bunched into {@link Group}s, each comprising of + counters from a particular <code>Enum</code> class.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.Counters --> + <!-- start class org.apache.hadoop.mapred.Counters.Counter --> + <class name="Counters.Counter" extends="java.lang.Object" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <method name="readFields" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read the binary representation of the counter]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Write the binary representation of the counter]]> + </doc> + </method> + <method name="getDisplayName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the name of the counter. + @return the user facing name of the counter]]> + </doc> + </method> + <method name="getCounter" return="long" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[What is the current value of this counter? + @return the current value]]> + </doc> + </method> + <method name="increment" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="incr" type="long"/> + <doc> + <![CDATA[Increment this counter by the given value + @param incr the value to increase this counter by]]> + </doc> + </method> + <doc> + <![CDATA[A counter record, comprising its name and value.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.Counters.Counter --> + <!-- start class org.apache.hadoop.mapred.Counters.Group --> + <class name="Counters.Group" extends="java.lang.Object" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <implements name="java.lang.Iterable<org.apache.hadoop.mapred.Counters.Counter>"/> + <method name="getName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns raw name of the group. This is the name of the enum class + for this group of counters.]]> + </doc> + </method> + <method name="getDisplayName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns localized name of the group. This is the same as getName() by + default, but different if an appropriate ResourceBundle is found.]]> + </doc> + </method> + <method name="getCounter" return="long" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="counterName" type="java.lang.String"/> + <doc> + <![CDATA[Returns the value of the specified counter, or 0 if the counter does + not exist.]]> + </doc> + </method> + <method name="getCounter" return="org.apache.hadoop.mapred.Counters.Counter" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="id" type="int"/> + <param name="name" type="java.lang.String"/> + <doc> + <![CDATA[Get the counter for the given id and create it if it doesn't exist. + @param id the numeric id of the counter within the group + @param name the internal counter name + @return the counter]]> + </doc> + </method> + <method name="size" return="int" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the number of counters in this group.]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="iterator" return="java.util.Iterator<org.apache.hadoop.mapred.Counters.Counter>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[<code>Group</code> of counters, comprising of counters from a particular + counter {@link Enum} class. + + <p><code>Group</code>handles localization of the class name and the + counter names.</p>]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.Counters.Group --> + <!-- start class org.apache.hadoop.mapred.DefaultJobHistoryParser --> + <class name="DefaultJobHistoryParser" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="DefaultJobHistoryParser" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="parseJobTasks" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobHistoryFile" type="java.lang.String"/> + <param name="job" type="org.apache.hadoop.mapred.JobHistory.JobInfo"/> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Populates a JobInfo object from the job's history log file. + @param jobHistoryFile history file for this job. + @param job a precreated JobInfo object, should be non-null. + @param fs FileSystem where historyFile is present. + @throws IOException]]> + </doc> + </method> + <doc> + <![CDATA[Default parser for job history files. It creates object model from + job history file.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.DefaultJobHistoryParser --> + <!-- start class org.apache.hadoop.mapred.FileAlreadyExistsException --> + <class name="FileAlreadyExistsException" extends="java.io.IOException" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="FileAlreadyExistsException" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="FileAlreadyExistsException" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <doc> + <![CDATA[Used when target file already exists for any operation and + is not configured to be overwritten.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.FileAlreadyExistsException --> + <!-- start class org.apache.hadoop.mapred.FileInputFormat --> + <class name="FileInputFormat" extends="java.lang.Object" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.InputFormat<K, V>"/> + <constructor name="FileInputFormat" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="setMinSplitSize" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="minSplitSize" type="long"/> + </method> + <method name="isSplitable" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <param name="filename" type="org.apache.hadoop.fs.Path"/> + <doc> + <![CDATA[Is the given filename splitable? Usually, true, but if the file is + stream compressed, it will not be. + + <code>FileInputFormat</code> implementations can override this and return + <code>false</code> to ensure that individual input files are never split-up + so that {@link Mapper}s process entire files. + + @param fs the file system that the file is on + @param filename the file name to check + @return is this file splitable?]]> + </doc> + </method> + <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader<K, V>" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="split" type="org.apache.hadoop.mapred.InputSplit"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="setInputPathFilter" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <param name="filter" type="java.lang.Class<? extends org.apache.hadoop.fs.PathFilter>"/> + <doc> + <![CDATA[Set a PathFilter to be applied to the input paths for the map-reduce job. + + @param filter the PathFilter class use for filtering the input paths.]]> + </doc> + </method> + <method name="getInputPathFilter" return="org.apache.hadoop.fs.PathFilter" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <doc> + <![CDATA[Get a PathFilter instance of the filter set for the input paths. + + @return the PathFilter instance set for the job, NULL if none has been set.]]> + </doc> + </method> + <method name="listPaths" return="org.apache.hadoop.fs.Path[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[List input directories. + Subclasses may override to, e.g., select only files matching a regular + expression. + + @param job the job to list input paths for + @return array of Path objects + @throws IOException if zero items.]]> + </doc> + </method> + <method name="validateInput" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getSplits" return="org.apache.hadoop.mapred.InputSplit[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="numSplits" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Splits files returned by {@link #listPaths(JobConf)} when + they're too big.]]> + </doc> + </method> + <method name="computeSplitSize" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="goalSize" type="long"/> + <param name="minSize" type="long"/> + <param name="blockSize" type="long"/> + </method> + <method name="getBlockIndex" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="blkLocations" type="org.apache.hadoop.fs.BlockLocation[]"/> + <param name="offset" type="long"/> + </method> + <method name="setInputPaths" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <param name="commaSeparatedPaths" type="java.lang.String"/> + <doc> + <![CDATA[Sets the given comma separated paths as the list of inputs + for the map-reduce job. + + @param conf Configuration of the job + @param commaSeparatedPaths Comma separated paths to be set as + the list of inputs for the map-reduce job.]]> + </doc> + </method> + <method name="addInputPaths" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <param name="commaSeparatedPaths" type="java.lang.String"/> + <doc> + <![CDATA[Add the given comma separated paths to the list of inputs for + the map-reduce job. + + @param conf The configuration of the job + @param commaSeparatedPaths Comma separated paths to be added to + the list of inputs for the map-reduce job.]]> + </doc> + </method> + <method name="setInputPaths" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <param name="inputPaths" type="org.apache.hadoop.fs.Path[]"/> + <doc> + <![CDATA[Set the array of {@link Path}s as the list of inputs + for the map-reduce job. + + @param conf Configuration of the job. + @param inputPaths the {@link Path}s of the input directories/files + for the map-reduce job.]]> + </doc> + </method> + <method name="addInputPath" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <param name="path" type="org.apache.hadoop.fs.Path"/> + <doc> + <![CDATA[Add a {@link Path} to the list of inputs for the map-reduce job. + + @param conf The configuration of the job + @param path {@link Path} to be added to the list of inputs for + the map-reduce job.]]> + </doc> + </method> + <method name="getInputPaths" return="org.apache.hadoop.fs.Path[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <doc> + <![CDATA[Get the list of input {@link Path}s for the map-reduce job. + + @param conf The configuration of the job + @return the list of input {@link Path}s for the map-reduce job.]]> + </doc> + </method> + <field name="LOG" type="org.apache.commons.logging.Log" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[A base class for file-based {@link InputFormat}. + + <p><code>FileInputFormat</code> is the base class for all file-based + <code>InputFormat</code>s. This provides generic implementations of + {@link #validateInput(JobConf)} and {@link #getSplits(JobConf, int)}. + Implementations fo <code>FileInputFormat</code> can also override the + {@link #isSplitable(FileSystem, Path)} method to ensure input-files are + not split-up and are processed as a whole by {@link Mapper}s.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.FileInputFormat --> + <!-- start class org.apache.hadoop.mapred.FileOutputFormat --> + <class name="FileOutputFormat" extends="java.lang.Object" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.OutputFormat<K, V>"/> + <constructor name="FileOutputFormat" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="setCompressOutput" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <param name="compress" type="boolean"/> + <doc> + <![CDATA[Set whether the output of the job is compressed. + @param conf the {@link JobConf} to modify + @param compress should the output of the job be compressed?]]> + </doc> + </method> + <method name="getCompressOutput" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <doc> + <![CDATA[Is the job output compressed? + @param conf the {@link JobConf} to look in + @return <code>true</code> if the job output should be compressed, + <code>false</code> otherwise]]> + </doc> + </method> + <method name="setOutputCompressorClass" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <param name="codecClass" type="java.lang.Class<? extends org.apache.hadoop.io.compress.CompressionCodec>"/> + <doc> + <![CDATA[Set the {@link CompressionCodec} to be used to compress job outputs. + @param conf the {@link JobConf} to modify + @param codecClass the {@link CompressionCodec} to be used to + compress the job outputs]]> + </doc> + </method> + <method name="getOutputCompressorClass" return="java.lang.Class<? extends org.apache.hadoop.io.compress.CompressionCodec>" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <param name="defaultValue" type="java.lang.Class<? extends org.apache.hadoop.io.compress.CompressionCodec>"/> + <doc> + <![CDATA[Get the {@link CompressionCodec} for compressing the job outputs. + @param conf the {@link JobConf} to look in + @param defaultValue the {@link CompressionCodec} to return if not set + @return the {@link CompressionCodec} to be used to compress the + job outputs + @throws IllegalArgumentException if the class was specified, but not found]]> + </doc> + </method> + <method name="getRecordWriter" return="org.apache.hadoop.mapred.RecordWriter<K, V>" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="name" type="java.lang.String"/> + <param name="progress" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="checkOutputSpecs" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <exception name="FileAlreadyExistsException" type="org.apache.hadoop.mapred.FileAlreadyExistsException"/> + <exception name="InvalidJobConfException" type="org.apache.hadoop.mapred.InvalidJobConfException"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="setOutputPath" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <param name="outputDir" type="org.apache.hadoop.fs.Path"/> + <doc> + <![CDATA[Set the {@link Path} of the output directory for the map-reduce job. + + @param conf The configuration of the job. + @param outputDir the {@link Path} of the output directory for + the map-reduce job.]]> + </doc> + </method> + <method name="getOutputPath" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <doc> + <![CDATA[Get the {@link Path} to the output directory for the map-reduce job. + + @return the {@link Path} to the output directory for the map-reduce job. + @see FileOutputFormat#getWorkOutputPath(JobConf)]]> + </doc> + </method> + <method name="getWorkOutputPath" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <doc> + <![CDATA[Get the {@link Path} to the task's temporary output directory + for the map-reduce job + + <h4 id="SideEffectFiles">Tasks' Side-Effect Files</h4> + + <p>Some applications need to create/write-to side-files, which differ from + the actual job-outputs. + + <p>In such cases there could be issues with 2 instances of the same TIP + (running simultaneously e.g. speculative tasks) trying to open/write-to the + same file (path) on HDFS. Hence the application-writer will have to pick + unique names per task-attempt (e.g. using the taskid, say + <tt>task_200709221812_0001_m_000000_0</tt>), not just per TIP.</p> + + <p>To get around this the Map-Reduce framework helps the application-writer + out by maintaining a special + <tt>${mapred.output.dir}/_temporary/_${taskid}</tt> + sub-directory for each task-attempt on HDFS where the output of the + task-attempt goes. On successful completion of the task-attempt the files + in the <tt>${mapred.output.dir}/_temporary/_${taskid}</tt> (only) + are <i>promoted</i> to <tt>${mapred.output.dir}</tt>. Of course, the + framework discards the sub-directory of unsuccessful task-attempts. This + is completely transparent to the application.</p> + + <p>The application-writer can take advantage of this by creating any + side-files required in <tt>${mapred.work.output.dir}</tt> during execution + of his reduce-task i.e. via {@link #getWorkOutputPath(JobConf)}, and the + framework will move them out similarly - thus she doesn't have to pick + unique paths per task-attempt.</p> + + <p><i>Note</i>: the value of <tt>${mapred.work.output.dir}</tt> during + execution of a particular task-attempt is actually + <tt>${mapred.output.dir}/_temporary/_{$taskid}</tt>, and this value is + set by the map-reduce framework. So, just create any side-files in the + path returned by {@link #getWorkOutputPath(JobConf)} from map/reduce + task to take advantage of this feature.</p> + + <p>The entire discussion holds true for maps of jobs with + reducer=NONE (i.e. 0 reduces) since output of the map, in that case, + goes directly to HDFS.</p> + + @return the {@link Path} to the task's temporary output directory + for the map-reduce job.]]> + </doc> + </method> + <doc> + <![CDATA[A base class for {@link OutputFormat}.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.FileOutputFormat --> + <!-- start class org.apache.hadoop.mapred.FileSplit --> + <class name="FileSplit" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.InputSplit"/> + <constructor name="FileSplit" type="org.apache.hadoop.fs.Path, long, long, org.apache.hadoop.mapred.JobConf" + static="false" final="false" visibility="public" + deprecated="deprecated, no comment"> + <doc> + <![CDATA[Constructs a split. + @deprecated + @param file the file name + @param start the position of the first byte in the file to process + @param length the number of bytes in the file to process]]> + </doc> + </constructor> + <constructor name="FileSplit" type="org.apache.hadoop.fs.Path, long, long, java.lang.String[]" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Constructs a split with host information + + @param file the file name + @param start the position of the first byte in the file to process + @param length the number of bytes in the file to process + @param hosts the list of hosts containing the block, possibly null]]> + </doc> + </constructor> + <method name="getPath" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The file containing this split's data.]]> + </doc> + </method> + <method name="getStart" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The position of the first byte in the file to process.]]> + </doc> + </method> + <method name="getLength" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The number of bytes in the file to process.]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getLocations" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[A section of an input file. Returned by {@link + InputFormat#getSplits(JobConf, int)} and passed to + {@link InputFormat#getRecordReader(InputSplit,JobConf,Reporter)}.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.FileSplit --> + <!-- start interface org.apache.hadoop.mapred.InputFormat --> + <interface name="InputFormat" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="validateInput" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Check for validity of the input-specification for the job. + + <p>This method is used to validate the input directories when a job is + submitted so that the {@link JobClient} can fail early, with an useful + error message, in case of errors. For e.g. input directory does not exist. + </p> + + @param job job configuration. + @throws InvalidInputException if the job does not have valid input]]> + </doc> + </method> + <method name="getSplits" return="org.apache.hadoop.mapred.InputSplit[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="numSplits" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Logically split the set of input files for the job. + + <p>Each {@link InputSplit} is then assigned to an individual {@link Mapper} + for processing.</p> + + <p><i>Note</i>: The split is a <i>logical</i> split of the inputs and the + input files are not physically split into chunks. For e.g. a split could + be <i><input-file-path, start, offset></i> tuple. + + @param job job configuration. + @param numSplits the desired number of splits, a hint. + @return an array of {@link InputSplit}s for the job.]]> + </doc> + </method> + <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader<K, V>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="split" type="org.apache.hadoop.mapred.InputSplit"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get the {@link RecordReader} for the given {@link InputSplit}. + + <p>It is the responsibility of the <code>RecordReader</code> to respect + record boundaries while processing the logical split to present a + record-oriented view to the individual task.</p> + + @param split the {@link InputSplit} + @param job the job that this split belongs to + @return a {@link RecordReader}]]> + </doc> + </method> + <doc> + <![CDATA[<code>InputFormat</code> describes the input-specification for a + Map-Reduce job. + + <p>The Map-Reduce framework relies on the <code>InputFormat</code> of the + job to:<p> + <ol> + <li> + Validate the input-specification of the job. + <li> + Split-up the input file(s) into logical {@link InputSplit}s, each of + which is then assigned to an individual {@link Mapper}. + </li> + <li> + Provide the {@link RecordReader} implementation to be used to glean + input records from the logical <code>InputSplit</code> for processing by + the {@link Mapper}. + </li> + </ol> + + <p>The default behavior of file-based {@link InputFormat}s, typically + sub-classes of {@link FileInputFormat}, is to split the + input into <i>logical</i> {@link InputSplit}s based on the total size, in + bytes, of the input files. However, the {@link FileSystem} blocksize of + the input files is treated as an upper bound for input splits. A lower bound + on the split size can be set via + <a href="{@docRoot}/../hadoop-default.html#mapred.min.split.size"> + mapred.min.split.size</a>.</p> + + <p>Clearly, logical splits based on input-size is insufficient for many + applications since record boundaries are to respected. In such cases, the + application has to also implement a {@link RecordReader} on whom lies the + responsibilty to respect record-boundaries and present a record-oriented + view of the logical <code>InputSplit</code> to the individual task. + + @see InputSplit + @see RecordReader + @see JobClient + @see FileInputFormat]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.mapred.InputFormat --> + <!-- start interface org.apache.hadoop.mapred.InputSplit --> + <interface name="InputSplit" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <method name="getLength" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get the total number of bytes in the data of the <code>InputSplit</code>. + + @return the number of bytes in the input split. + @throws IOException]]> + </doc> + </method> + <method name="getLocations" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get the list of hostnames where the input split is located. + + @return list of hostnames where data of the <code>InputSplit</code> is + located as an array of <code>String</code>s. + @throws IOException]]> + </doc> + </method> + <doc> + <![CDATA[<code>InputSplit</code> represents the data to be processed by an + individual {@link Mapper}. + + <p>Typically, it presents a byte-oriented view on the input and is the + responsibility of {@link RecordReader} of the job to process this and present + a record-oriented view. + + @see InputFormat + @see RecordReader]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.mapred.InputSplit --> + <!-- start class org.apache.hadoop.mapred.InvalidFileTypeException --> + <class name="InvalidFileTypeException" extends="java.io.IOException" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="InvalidFileTypeException" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="InvalidFileTypeException" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <doc> + <![CDATA[Used when file type differs from the desired file type. like + getting a file when a directory is expected. Or a wrong file type.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.InvalidFileTypeException --> + <!-- start class org.apache.hadoop.mapred.InvalidInputException --> + <class name="InvalidInputException" extends="java.io.IOException" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="InvalidInputException" type="java.util.List<java.io.IOException>" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Create the exception with the given list. + @param probs the list of problems to report. this list is not copied.]]> + </doc> + </constructor> + <method name="getProblems" return="java.util.List<java.io.IOException>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the complete list of the problems reported. + @return the list of problems, which must not be modified]]> + </doc> + </method> + <method name="getMessage" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get a summary message of the problems found. + @return the concatenated messages from all of the problems.]]> + </doc> + </method> + <doc> + <![CDATA[This class wraps a list of problems with the input, so that the user + can get a list of problems together instead of finding and fixing them one + by one.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.InvalidInputException --> + <!-- start class org.apache.hadoop.mapred.InvalidJobConfException --> + <class name="InvalidJobConfException" extends="java.io.IOException" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="InvalidJobConfException" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="InvalidJobConfException" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <doc> + <![CDATA[This exception is thrown when jobconf misses some mendatory attributes + or value of some attributes is invalid.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.InvalidJobConfException --> + <!-- start class org.apache.hadoop.mapred.IsolationRunner --> + <class name="IsolationRunner" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="IsolationRunner" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Run a single task + @param args the first argument is the task directory]]> + </doc> + </method> + </class> + <!-- end class org.apache.hadoop.mapred.IsolationRunner --> + <!-- start class org.apache.hadoop.mapred.JobClient --> + <class name="JobClient" extends="org.apache.hadoop.conf.Configured" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.MRConstants"/> + <implements name="org.apache.hadoop.util.Tool"/> + <constructor name="JobClient" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Create a job client.]]> + </doc> + </constructor> + <constructor name="JobClient" type="org.apache.hadoop.mapred.JobConf" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Build a job client with the given {@link JobConf}, and connect to the + default {@link JobTracker}. + + @param conf the job configuration. + @throws IOException]]> + </doc> + </constructor> + <constructor name="JobClient" type="java.net.InetSocketAddress, org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Build a job client, connect to the indicated job tracker. + + @param jobTrackAddr the job tracker to connect to. + @param conf configuration.]]> + </doc> + </constructor> + <method name="getCommandLineConfig" return="org.apache.hadoop.conf.Configuration" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[return the command line configuration]]> + </doc> + </method> + <method name="init" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Connect to the default {@link JobTracker}. + @param conf the job configuration. + @throws IOException]]> + </doc> + </method> + <method name="close" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Close the <code>JobClient</code>.]]> + </doc> + </method> + <method name="getFs" return="org.apache.hadoop.fs.FileSystem" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get a filesystem handle. We need this to prepare jobs + for submission to the MapReduce system. + + @return the filesystem handle.]]> + </doc> + </method> + <method name="submitJob" return="org.apache.hadoop.mapred.RunningJob" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobFile" type="java.lang.String"/> + <exception name="FileNotFoundException" type="java.io.FileNotFoundException"/> + <exception name="InvalidJobConfException" type="org.apache.hadoop.mapred.InvalidJobConfException"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Submit a job to the MR system. + + This returns a handle to the {@link RunningJob} which can be used to track + the running-job. + + @param jobFile the job configuration. + @return a handle to the {@link RunningJob} which can be used to track the + running-job. + @throws FileNotFoundException + @throws InvalidJobConfException + @throws IOException]]> + </doc> + </method> + <method name="submitJob" return="org.apache.hadoop.mapred.RunningJob" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <exception name="FileNotFoundException" type="java.io.FileNotFoundException"/> + <exception name="InvalidJobConfException" type="org.apache.hadoop.mapred.InvalidJobConfException"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Submit a job to the MR system. + This returns a handle to the {@link RunningJob} which can be used to track + the running-job. + + @param job the job configuration. + @return a handle to the {@link RunningJob} which can be used to track the + running-job. + @throws FileNotFoundException + @throws InvalidJobConfException + @throws IOException]]> + </doc> + </method> + <method name="getJob" return="org.apache.hadoop.mapred.RunningJob" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobid" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get an {@link RunningJob} object to track an ongoing job. Returns + null if the id does not correspond to any known job. + + @param jobid the jobid of the job. + @return the {@link RunningJob} handle to track the job, null if the + <code>jobid</code> doesn't correspond to any known job. + @throws IOException]]> + </doc> + </method> + <method name="getMapTaskReports" return="org.apache.hadoop.mapred.TaskReport[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get the information of the current state of the map tasks of a job. + + @param jobId the job to query. + @return the list of all of the map tips. + @throws IOException]]> + </doc> + </method> + <method name="getReduceTaskReports" return="org.apache.hadoop.mapred.TaskReport[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get the information of the current state of the reduce tasks of a job. + + @param jobId the job to query. + @return the list of all of the reduce tips. + @throws IOException]]> + </doc> + </method> + <method name="getClusterStatus" return="org.apache.hadoop.mapred.ClusterStatus" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get status information about the Map-Reduce cluster. + + @return the status information about the Map-Reduce cluster as an object + of {@link ClusterStatus}. + @throws IOException]]> + </doc> + </method> + <method name="jobsToComplete" return="org.apache.hadoop.mapred.JobStatus[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get the jobs that are not completed and not failed. + + @return array of {@link JobStatus} for the running/to-be-run jobs. + @throws IOException]]> + </doc> + </method> + <method name="getAllJobs" return="org.apache.hadoop.mapred.JobStatus[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get the jobs that are submitted. + + @return array of {@link JobStatus} for the submitted jobs. + @throws IOException]]> + </doc> + </method> + <method name="runJob" return="org.apache.hadoop.mapred.RunningJob" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Utility that submits a job, then polls for progress until the job is + complete. + + @param job the job configuration. + @throws IOException]]> + </doc> + </method> + <method name="setTaskOutputFilter" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="newValue" type="org.apache.hadoop.mapred.JobClient.TaskStatusFilter"/> + <doc> + <![CDATA[Sets the output filter for tasks. only those tasks are printed whose + output matches the filter. + @param newValue task filter.]]> + </doc> + </method> + <method name="getTaskOutputFilter" return="org.apache.hadoop.mapred.JobClient.TaskStatusFilter" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <doc> + <![CDATA[Get the task output filter out of the JobConf. + + @param job the JobConf to examine. + @return the filter level.]]> + </doc> + </method> + <method name="setTaskOutputFilter" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="newValue" type="org.apache.hadoop.mapred.JobClient.TaskStatusFilter"/> + <doc> + <![CDATA[Modify the JobConf to set the task output filter. + + @param job the JobConf to modify. + @param newValue the value to set.]]> + </doc> + </method> + <method name="getTaskOutputFilter" return="org.apache.hadoop.mapred.JobClient.TaskStatusFilter" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns task output filter. + @return task filter.]]> + </doc> + </method> + <method name="run" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="argv" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + </method> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="argv" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + </method> + <doc> + <![CDATA[<code>JobClient</code> is the primary interface for the user-job to interact + with the {@link JobTracker}. + + <code>JobClient</code> provides facilities to submit jobs, track their + progress, access component-tasks' reports/logs, get the Map-Reduce cluster + status information etc. + + <p>The job submission process involves: + <ol> + <li> + Checking the input and output specifications of the job. + </li> + <li> + Computing the {@link InputSplit}s for the job. + </li> + <li> + Setup the requisite accounting information for the {@link DistributedCache} + of the job, if necessary. + </li> + <li> + Copying the job's jar and configuration to the map-reduce system directory + on the distributed file-system. + </li> + <li> + Submitting the job to the <code>JobTracker</code> and optionally monitoring + it's status. + </li> + </ol></p> + + Normally the user creates the application, describes various facets of the + job via {@link JobConf} and then uses the <code>JobClient</code> to submit + the job and monitor its progress. + + <p>Here is an example on how to use <code>JobClient</code>:</p> + <p><blockquote><pre> + // Create a new JobConf + JobConf job = new JobConf(new Configuration(), MyJob.class); + + // Specify various job-specific parameters + job.setJobName("myjob"); + + job.setInputPath(new Path("in")); + job.setOutputPath(new Path("out")); + + job.setMapperClass(MyJob.MyMapper.class); + job.setReducerClass(MyJob.MyReducer.class); + + // Submit the job, then poll for progress until the job is complete + JobClient.runJob(job); + </pre></blockquote></p> + + <h4 id="JobControl">Job Control</h4> + + <p>At times clients would chain map-reduce jobs to accomplish complex tasks + which cannot be done via a single map-reduce job. This is fairly easy since + the output of the job, typically, goes to distributed file-system and that + can be used as the input for the next job.</p> + + <p>However, this also means that the onus on ensuring jobs are complete + (success/failure) lies squarely on the clients. In such situations the + various job-control options are: + <ol> + <li> + {@link #runJob(JobConf)} : submits the job and returns only after + the job has completed. + </li> + <li> + {@link #submitJob(JobConf)} : only submits the job, then poll the + returned handle to the {@link RunningJob} to query status and make + scheduling decisions. + </li> + <li> + {@link JobConf#setJobEndNotificationURI(String)} : setup a notification + on job-completion, thus avoiding polling. + </li> + </ol></p> + + @see JobConf + @see ClusterStatus + @see Tool + @see DistributedCache]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.JobClient --> + <!-- start class org.apache.hadoop.mapred.JobClient.TaskStatusFilter --> + <class name="JobClient.TaskStatusFilter" extends="java.lang.Enum<org.apache.hadoop.mapred.JobClient.TaskStatusFilter>" + abstract="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <method name="values" return="org.apache.hadoop.mapred.JobClient.TaskStatusFilter[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="valueOf" return="org.apache.hadoop.mapred.JobClient.TaskStatusFilter" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + </class> + <!-- end class org.apache.hadoop.mapred.JobClient.TaskStatusFilter --> + <!-- start class org.apache.hadoop.mapred.JobConf --> + <class name="JobConf" extends="org.apache.hadoop.conf.Configuration" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JobConf" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct a map/reduce job configuration.]]> + </doc> + </constructor> + <constructor name="JobConf" type="java.lang.Class" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct a map/reduce job configuration. + + @param exampleClass a class whose containing jar is used as the job's jar.]]> + </doc> + </constructor> + <constructor name="JobConf" type="org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct a map/reduce job configuration. + + @param conf a Configuration whose settings will be inherited.]]> + </doc> + </constructor> + <constructor name="JobConf" type="org.apache.hadoop.conf.Configuration, java.lang.Class" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct a map/reduce job configuration. + + @param conf a Configuration whose settings will be inherited. + @param exampleClass a class whose containing jar is used as the job's jar.]]> + </doc> + </constructor> + <constructor name="JobConf" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct a map/reduce configuration. + + @param config a Configuration-format XML job description file.]]> + </doc> + </constructor> + <constructor name="JobConf" type="org.apache.hadoop.fs.Path" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct a map/reduce configuration. + + @param config a Configuration-format XML job description file.]]> + </doc> + </constructor> + <method name="getJar" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the user jar for the map-reduce job. + + @return the user jar for the map-reduce job.]]> + </doc> + </method> + <method name="setJar" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jar" type="java.lang.String"/> + <doc> + <![CDATA[Set the user jar for the map-reduce job. + + @param jar the user jar for the map-reduce job.]]> + </doc> + </method> + <method name="setJarByClass" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="cls" type="java.lang.Class"/> + <doc> + <![CDATA[Set the job's jar file by finding an example class location. + + @param cls the example class.]]> + </doc> + </method> + <method name="getSystemDir" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the system directory where job-specific files are to be placed. + + @return the system directory where job-specific files are to be placed.]]> + </doc> + </method> + <method name="getLocalDirs" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="deleteLocalFiles" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="deleteLocalFiles" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="subdir" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getLocalPath" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="pathString" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Constructs a local file name. Files are distributed among configured + local directories.]]> + </doc> + </method> + <method name="setInputPath" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="Use {@link FileInputFormat#setInputPaths(JobConf, Path...)} or + {@link FileInputFormat#setInputPaths(JobConf, String)}"> + <param name="dir" type="org.apache.hadoop.fs.Path"/> + <doc> + <![CDATA[Set the {@link Path} of the input directory for the map-reduce job. + + @param dir the {@link Path} of the input directory for the map-reduce job. + @deprecated Use {@link FileInputFormat#setInputPaths(JobConf, Path...)} or + {@link FileInputFormat#setInputPaths(JobConf, String)}]]> + </doc> + </method> + <method name="addInputPath" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="Use {@link FileInputFormat#addInputPath(JobConf, Path)} or + {@link FileInputFormat#addInputPaths(JobConf, String)}"> + <param name="dir" type="org.apache.hadoop.fs.Path"/> + <doc> + <![CDATA[Add a {@link Path} to the list of inputs for the map-reduce job. + + @param dir {@link Path} to be added to the list of inputs for + the map-reduce job. + @deprecated Use {@link FileInputFormat#addInputPath(JobConf, Path)} or + {@link FileInputFormat#addInputPaths(JobConf, String)}]]> + </doc> + </method> + <method name="getInputPaths" return="org.apache.hadoop.fs.Path[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="Use {@link FileInputFormat#getInputPaths(JobConf)}"> + <doc> + <![CDATA[Get the list of input {@link Path}s for the map-reduce job. + + @return the list of input {@link Path}s for the map-reduce job. + @deprecated Use {@link FileInputFormat#getInputPaths(JobConf)}]]> + </doc> + </method> + <method name="getUser" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the reported username for this job. + + @return the username]]> + </doc> + </method> + <method name="setUser" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="user" type="java.lang.String"/> + <doc> + <![CDATA[Set the reported username for this job. + + @param user the username for this job.]]> + </doc> + </method> + <method name="setKeepFailedTaskFiles" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="keep" type="boolean"/> + <doc> + <![CDATA[Set whether the framework should keep the intermediate files for + failed tasks. + + @param keep <code>true</code> if framework should keep the intermediate files + for failed tasks, <code>false</code> otherwise.]]> + </doc> + </method> + <method name="getKeepFailedTaskFiles" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Should the temporary files for failed tasks be kept? + + @return should the files be kept?]]> + </doc> + </method> + <method name="setKeepTaskFilesPattern" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="pattern" type="java.lang.String"/> + <doc> + <![CDATA[Set a regular expression for task names that should be kept. + The regular expression ".*_m_000123_0" would keep the files + for the first instance of map 123 that ran. + + @param pattern the java.util.regex.Pattern to match against the + task names.]]> + </doc> + </method> + <method name="getKeepTaskFilesPattern" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the regular expression that is matched against the task names + to see if we need to keep the files. + + @return the pattern as a string, if it was set, othewise null.]]> + </doc> + </method> + <method name="setWorkingDirectory" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dir" type="org.apache.hadoop.fs.Path"/> + <doc> + <![CDATA[Set the current working directory for the default file system. + + @param dir the new current working directory.]]> + </doc> + </method> + <method name="getWorkingDirectory" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the current working directory for the default file system. + + @return the directory name.]]> + </doc> + </method> + <method name="getOutputPath" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="Use {@link FileOutputFormat#getOutputPath(JobConf)} or + {@link FileOutputFormat#getWorkOutputPath(JobConf)} + Get the {@link Path} to the output directory for the map-reduce job."> + <doc> + <![CDATA[@deprecated Use {@link FileOutputFormat#getOutputPath(JobConf)} or + {@link FileOutputFormat#getWorkOutputPath(JobConf)} + Get the {@link Path} to the output directory for the map-reduce job. + + @return the {@link Path} to the output directory for the map-reduce job.]]> + </doc> + </method> + <method name="setOutputPath" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="Use {@link FileOutputFormat#setOutputPath(JobConf, Path)} + Set the {@link Path} of the output directory for the map-reduce job. + + lEsS_tHaNp>lEsS_tHaNi>NotelEsS_tHaN/i>: + lEsS_tHaN/p>"> + <param name="dir" type="org.apache.hadoop.fs.Path"/> + <doc> + <![CDATA[@deprecated Use {@link FileOutputFormat#setOutputPath(JobConf, Path)} + Set the {@link Path} of the output directory for the map-reduce job. + + <p><i>Note</i>: + </p> + @param dir the {@link Path} of the output directory for the map-reduce job.]]> + </doc> + </method> + <method name="getInputFormat" return="org.apache.hadoop.mapred.InputFormat" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the {@link InputFormat} implementation for the map-reduce job, + defaults to {@link TextInputFormat} if not specified explicity. + + @return the {@link InputFormat} implementation for the map-reduce job.]]> + </doc> + </method> + <method name="setInputFormat" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="theClass" type="java.lang.Class<? extends org.apache.hadoop.mapred.InputFormat>"/> + <doc> + <![CDATA[Set the {@link InputFormat} implementation for the map-reduce job. + + @param theClass the {@link InputFormat} implementation for the map-reduce + job.]]> + </doc> + </method> + <method name="getOutputFormat" return="org.apache.hadoop.mapred.OutputFormat" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the {@link OutputFormat} implementation for the map-reduce job, + defaults to {@link TextOutputFormat} if not specified explicity. + + @return the {@link OutputFormat} implementation for the map-reduce job.]]> + </doc> + </method> + <method name="setOutputFormat" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="theClass" type="java.lang.Class<? extends org.apache.hadoop.mapred.OutputFormat>"/> + <doc> + <![CDATA[Set the {@link OutputFormat} implementation for the map-reduce job. + + @param theClass the {@link OutputFormat} implementation for the map-reduce + job.]]> + </doc> + </method> + <method name="setCompressMapOutput" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="compress" type="boolean"/> + <doc> + <![CDATA[Should the map outputs be compressed before transfer? + Uses the SequenceFile compression. + + @param compress should the map outputs be compressed?]]> + </doc> + </method> + <method name="getCompressMapOutput" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Are the outputs of the maps be compressed? + + @return <code>true</code> if the outputs of the maps are to be compressed, + <code>false</code> otherwise.]]> + </doc> + </method> + <method name="setMapOutputCompressionType" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="style" type="org.apache.hadoop.io.SequenceFile.CompressionType"/> + <doc> + <![CDATA[Set the {@link CompressionType} for the map outputs. + + @param style the {@link CompressionType} to control how the map outputs + are compressed.]]> + </doc> + </method> + <method name="getMapOutputCompressionType" return="org.apache.hadoop.io.SequenceFile.CompressionType" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the {@link CompressionType} for the map outputs. + + @return the {@link CompressionType} for map outputs, defaulting to + {@link CompressionType#RECORD}.]]> + </doc> + </method> + <method name="setMapOutputCompressorClass" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="codecClass" type="java.lang.Class<? extends org.apache.hadoop.io.compress.CompressionCodec>"/> + <doc> + <![CDATA[Set the given class as the {@link CompressionCodec} for the map outputs. + + @param codecClass the {@link CompressionCodec} class that will compress + the map outputs.]]> + </doc> + </method> + <method name="getMapOutputCompressorClass" return="java.lang.Class<? extends org.apache.hadoop.io.compress.CompressionCodec>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="defaultValue" type="java.lang.Class<? extends org.apache.hadoop.io.compress.CompressionCodec>"/> + <doc> + <![CDATA[Get the {@link CompressionCodec} for compressing the map outputs. + + @param defaultValue the {@link CompressionCodec} to return if not set + @return the {@link CompressionCodec} class that should be used to compress the + map outputs. + @throws IllegalArgumentException if the class was specified, but not found]]> + </doc> + </method> + <method name="getMapOutputKeyClass" return="java.lang.Class<?>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the key class for the map output data. If it is not set, use the + (final) output key class. This allows the map output key class to be + different than the final output key class. + + @return the map output key class.]]> + </doc> + </method> + <method name="setMapOutputKeyClass" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="theClass" type="java.lang.Class<?>"/> + <doc> + <![CDATA[Set the key class for the map output data. This allows the user to + specify the map output key class to be different than the final output + value class. + + @param theClass the map output key class.]]> + </doc> + </method> + <method name="getMapOutputValueClass" return="java.lang.Class<?>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the value class for the map output data. If it is not set, use the + (final) output value class This allows the map output value class to be + different than the final output value class. + + @return the map output value class.]]> + </doc> + </method> + <method name="setMapOutputValueClass" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="theClass" type="java.lang.Class<?>"/> + <doc> + <![CDATA[Set the value class for the map output data. This allows the user to + specify the map output value class to be different than the final output + value class. + + @param theClass the map output value class.]]> + </doc> + </method> + <method name="getOutputKeyClass" return="java.lang.Class<?>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the key class for the job output data. + + @return the key class for the job output data.]]> + </doc> + </method> + <method name="setOutputKeyClass" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="theClass" type="java.lang.Class<?>"/> + <doc> + <![CDATA[Set the key class for the job output data. + + @param theClass the key class for the job output data.]]> + </doc> + </method> + <method name="getOutputKeyComparator" return="org.apache.hadoop.io.RawComparator" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the {@link RawComparator} comparator used to compare keys. + + @return the {@link RawComparator} comparator used to compare keys.]]> + </doc> + </method> + <method name="setOutputKeyComparatorClass" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="theClass" type="java.lang.Class<? extends org.apache.hadoop.io.RawComparator>"/> + <doc> + <![CDATA[Set the {@link RawComparator} comparator used to compare keys. + + @param theClass the {@link RawComparator} comparator used to + compare keys. + @see #setOutputValueGroupingComparator(Class)]]> + </doc> + </method> + <method name="getOutputValueGroupingComparator" return="org.apache.hadoop.io.RawComparator" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the user defined {@link WritableComparable} comparator for + grouping keys of inputs to the reduce. + + @return comparator set by the user for grouping values. + @see #setOutputValueGroupingComparator(Class) for details.]]> + </doc> + </method> + <method name="setOutputValueGroupingComparator" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="theClass" type="java.lang.Class<? extends org.apache.hadoop.io.RawComparator>"/> + <doc> + <![CDATA[Set the user defined {@link RawComparator} comparator for + grouping keys in the input to the reduce. + + <p>This comparator should be provided if the equivalence rules for keys + for sorting the intermediates are different from those for grouping keys + before each call to + {@link Reducer#reduce(Object, java.util.Iterator, OutputCollector, Reporter)}.</p> + + <p>For key-value pairs (K1,V1) and (K2,V2), the values (V1, V2) are passed + in a single call to the reduce function if K1 and K2 compare as equal.</p> + + <p>Since {@link #setOutputKeyComparatorClass(Class)} can be used to control + how keys are sorted, this can be used in conjunction to simulate + <i>secondary sort on values</i>.</p> + + <p><i>Note</i>: This is not a guarantee of the reduce sort being + <i>stable</i> in any sense. (In any case, with the order of available + map-outputs to the reduce being non-deterministic, it wouldn't make + that much sense.)</p> + + @param theClass the comparator class to be used for grouping keys. + It should implement <code>RawComparator</code>. + @see #setOutputKeyComparatorClass(Class)]]> + </doc> + </method> + <method name="getOutputValueClass" return="java.lang.Class<?>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the value class for job outputs. + + @return the value class for job outputs.]]> + </doc> + </method> + <method name="setOutputValueClass" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="theClass" type="java.lang.Class<?>"/> + <doc> + <![CDATA[Set the value class for job outputs. + + @param theClass the value class for job outputs.]]> + </doc> + </method> + <method name="getMapperClass" return="java.lang.Class<? extends org.apache.hadoop.mapred.Mapper>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the {@link Mapper} class for the job. + + @return the {@link Mapper} class for the job.]]> + </doc> + </method> + <method name="setMapperClass" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="theClass" type="java.lang.Class<? extends org.apache.hadoop.mapred.Mapper>"/> + <doc> + <![CDATA[Set the {@link Mapper} class for the job. + + @param theClass the {@link Mapper} class for the job.]]> + </doc> + </method> + <method name="getMapRunnerClass" return="java.lang.Class<? extends org.apache.hadoop.mapred.MapRunnable>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the {@link MapRunnable} class for the job. + + @return the {@link MapRunnable} class for the job.]]> + </doc> + </method> + <method name="setMapRunnerClass" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="theClass" type="java.lang.Class<? extends org.apache.hadoop.mapred.MapRunnable>"/> + <doc> + <![CDATA[Expert: Set the {@link MapRunnable} class for the job. + + Typically used to exert greater control on {@link Mapper}s. + + @param theClass the {@link MapRunnable} class for the job.]]> + </doc> + </method> + <method name="getPartitionerClass" return="java.lang.Class<? extends org.apache.hadoop.mapred.Partitioner>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the {@link Partitioner} used to partition {@link Mapper}-outputs + to be sent to the {@link Reducer}s. + + @return the {@link Partitioner} used to partition map-outputs.]]> + </doc> + </method> + <method name="setPartitionerClass" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="theClass" type="java.lang.Class<? extends org.apache.hadoop.mapred.Partitioner>"/> + <doc> + <![CDATA[Set the {@link Partitioner} class used to partition + {@link Mapper}-outputs to be sent to the {@link Reducer}s. + + @param theClass the {@link Partitioner} used to partition map-outputs.]]> + </doc> + </method> + <method name="getReducerClass" return="java.lang.Class<? extends org.apache.hadoop.mapred.Reducer>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the {@link Reducer} class for the job. + + @return the {@link Reducer} class for the job.]]> + </doc> + </method> + <method name="setReducerClass" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="theClass" type="java.lang.Class<? extends org.apache.hadoop.mapred.Reducer>"/> + <doc> + <![CDATA[Set the {@link Reducer} class for the job. + + @param theClass the {@link Reducer} class for the job.]]> + </doc> + </method> + <method name="getCombinerClass" return="java.lang.Class<? extends org.apache.hadoop.mapred.Reducer>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the user-defined <i>combiner</i> class used to combine map-outputs + before being sent to the reducers. Typically the combiner is same as the + the {@link Reducer} for the job i.e. {@link #getReducerClass()}. + + @return the user-defined combiner class used to combine map-outputs.]]> + </doc> + </method> + <method name="setCombinerClass" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="theClass" type="java.lang.Class<? extends org.apache.hadoop.mapred.Reducer>"/> + <doc> + <![CDATA[Set the user-defined <i>combiner</i> class used to combine map-outputs + before being sent to the reducers. + + <p>The combiner is a task-level aggregation operation which, in some cases, + helps to cut down the amount of data transferred from the {@link Mapper} to + the {@link Reducer}, leading to better performance.</p> + + <p>Typically the combiner is same as the <code>Reducer</code> for the + job i.e. {@link #setReducerClass(Class)}.</p> + + @param theClass the user-defined combiner class used to combine + map-outputs.]]> + </doc> + </method> + <method name="getSpeculativeExecution" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Should speculative execution be used for this job? + Defaults to <code>true</code>. + + @return <code>true</code> if speculative execution be used for this job, + <code>false</code> otherwise.]]> + </doc> + </method> + <method name="setSpeculativeExecution" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="speculativeExecution" type="boolean"/> + <doc> + <![CDATA[Turn speculative execution on or off for this job. + + @param speculativeExecution <code>true</code> if speculative execution + should be turned on, else <code>false</code>.]]> + </doc> + </method> + <method name="getMapSpeculativeExecution" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Should speculative execution be used for this job for map tasks? + Defaults to <code>true</code>. + + @return <code>true</code> if speculative execution be + used for this job for map tasks, + <code>false</code> otherwise.]]> + </doc> + </method> + <method name="setMapSpeculativeExecution" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="speculativeExecution" type="boolean"/> + <doc> + <![CDATA[Turn speculative execution on or off for this job for map tasks. + + @param speculativeExecution <code>true</code> if speculative execution + should be turned on for map tasks, + else <code>false</code>.]]> + </doc> + </method> + <method name="getReduceSpeculativeExecution" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Should speculative execution be used for this job for reduce tasks? + Defaults to <code>true</code>. + + @return <code>true</code> if speculative execution be used + for reduce tasks for this job, + <code>false</code> otherwise.]]> + </doc> + </method> + <method name="setReduceSpeculativeExecution" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="speculativeExecution" type="boolean"/> + <doc> + <![CDATA[Turn speculative execution on or off for this job for reduce tasks. + + @param speculativeExecution <code>true</code> if speculative execution + should be turned on for reduce tasks, + else <code>false</code>.]]> + </doc> + </method> + <method name="getNumMapTasks" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get configured the number of reduce tasks for this job. + Defaults to <code>1</code>. + + @return the number of reduce tasks for this job.]]> + </doc> + </method> + <method name="setNumMapTasks" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="n" type="int"/> + <doc> + <![CDATA[Set the number of map tasks for this job. + + <p><i>Note</i>: This is only a <i>hint</i> to the framework. The actual + number of spawned map tasks depends on the number of {@link InputSplit}s + generated by the job's {@link InputFormat#getSplits(JobConf, int)}. + + A custom {@link InputFormat} is typically used to accurately control + the number of map tasks for the job.</p> + + <h4 id="NoOfMaps">How many maps?</h4> + + <p>The number of maps is usually driven by the total size of the inputs + i.e. total number of blocks of the input files.</p> + + <p>The right level of parallelism for maps seems to be around 10-100 maps + per-node, although it has been set up to 300 or so for very cpu-light map + tasks. Task setup takes awhile, so it is best if the maps take at least a + minute to execute.</p> + + <p>The default behavior of file-based {@link InputFormat}s is to split the + input into <i>logical</i> {@link InputSplit}s based on the total size, in + bytes, of input files. However, the {@link FileSystem} blocksize of the + input files is treated as an upper bound for input splits. A lower bound + on the split size can be set via + <a href="{@docRoot}/../hadoop-default.html#mapred.min.split.size"> + mapred.min.split.size</a>.</p> + + <p>Thus, if you expect 10TB of input data and have a blocksize of 128MB, + you'll end up with 82,000 maps, unless {@link #setNumMapTasks(int)} is + used to set it even higher.</p> + + @param n the number of map tasks for this job. + @see InputFormat#getSplits(JobConf, int) + @see FileInputFormat + @see FileSystem#getDefaultBlockSize() + @see FileStatus#getBlockSize()]]> + </doc> + </method> + <method name="getNumReduceTasks" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get configured the number of reduce tasks for this job. Defaults to + <code>1</code>. + + @return the number of reduce tasks for this job.]]> + </doc> + </method> + <method name="setNumReduceTasks" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="n" type="int"/> + <doc> + <![CDATA[Set the requisite number of reduce tasks for this job. + + <h4 id="NoOfReduces">How many reduces?</h4> + + <p>The right number of reduces seems to be <code>0.95</code> or + <code>1.75</code> multiplied by (<<i>no. of nodes</i>> * + <a href="{@docRoot}/../hadoop-default.html#mapred.tasktracker.reduce.tasks.maximum"> + mapred.tasktracker.reduce.tasks.maximum</a>). + </p> + + <p>With <code>0.95</code> all of the reduces can launch immediately and + start transfering map outputs as the maps finish. With <code>1.75</code> + the faster nodes will finish their first round of reduces and launch a + second wave of reduces doing a much better job of load balancing.</p> + + <p>Increasing the number of reduces increases the framework overhead, but + increases load balancing and lowers the cost of failures.</p> + + <p>The scaling factors above are slightly less than whole numbers to + reserve a few reduce slots in the framework for speculative-tasks, failures + etc.</p> + + <h4 id="ReducerNone">Reducer NONE</h4> + + <p>It is legal to set the number of reduce-tasks to <code>zero</code>.</p> + + <p>In this case the output of the map-tasks directly go to distributed + file-system, to the path set by + {@link FileOutputFormat#setOutputPath(JobConf, Path)}. Also, the + framework doesn't sort the map-outputs before writing it out to HDFS.</p> + + @param n the number of reduce tasks for this job.]]> + </doc> + </method> + <method name="getMaxMapAttempts" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the configured number of maximum attempts that will be made to run a + map task, as specified by the <code>mapred.map.max.attempts</code> + property. If this property is not already set, the default is 4 attempts. + + @return the max number of attempts per map task.]]> + </doc> + </method> + <method name="setMaxMapAttempts" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="n" type="int"/> + <doc> + <![CDATA[Expert: Set the number of maximum attempts that will be made to run a + map task. + + @param n the number of attempts per map task.]]> + </doc> + </method> + <method name="getMaxReduceAttempts" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the configured number of maximum attempts that will be made to run a + reduce task, as specified by the <code>mapred.reduce.max.attempts</code> + property. If this property is not already set, the default is 4 attempts. + + @return the max number of attempts per reduce task.]]> + </doc> + </method> + <method name="setMaxReduceAttempts" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="n" type="int"/> + <doc> + <![CDATA[Expert: Set the number of maximum attempts that will be made to run a + reduce task. + + @param n the number of attempts per reduce task.]]> + </doc> + </method> + <method name="getJobName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the user-specified job name. This is only used to identify the + job to the user. + + @return the job's name, defaulting to "".]]> + </doc> + </method> + <method name="setJobName" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <doc> + <![CDATA[Set the user-specified job name. + + @param name the job's new name.]]> + </doc> + </method> + <method name="getSessionId" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the user-specified session identifier. The default is the empty string. + + The session identifier is used to tag metric data that is reported to some + performance metrics system via the org.apache.hadoop.metrics API. The + session identifier is intended, in particular, for use by Hadoop-On-Demand + (HOD) which allocates a virtual Hadoop cluster dynamically and transiently. + HOD will set the session identifier by modifying the hadoop-site.xml file + before starting the cluster. + + When not running under HOD, this identifer is expected to remain set to + the empty string. + + @return the session identifier, defaulting to "".]]> + </doc> + </method> + <method name="setSessionId" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="sessionId" type="java.lang.String"/> + <doc> + <![CDATA[Set the user-specified session identifier. + + @param sessionId the new session id.]]> + </doc> + </method> + <method name="setMaxTaskFailuresPerTracker" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="noFailures" type="int"/> + <doc> + <![CDATA[Set the maximum no. of failures of a given job per tasktracker. + If the no. of task failures exceeds <code>noFailures</code>, the + tasktracker is <i>blacklisted</i> for this job. + + @param noFailures maximum no. of failures of a given job per tasktracker.]]> + </doc> + </method> + <method name="getMaxTaskFailuresPerTracker" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Expert: Get the maximum no. of failures of a given job per tasktracker. + If the no. of task failures exceeds this, the tasktracker is + <i>blacklisted</i> for this job. + + @return the maximum no. of failures of a given job per tasktracker.]]> + </doc> + </method> + <method name="getMaxMapTaskFailuresPercent" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the maximum percentage of map tasks that can fail without + the job being aborted. + + Each map task is executed a minimum of {@link #getMaxMapAttempts()} + attempts before being declared as <i>failed</i>. + + Defaults to <code>zero</code>, i.e. <i>any</i> failed map-task results in + the job being declared as {@link JobStatus#FAILED}. + + @return the maximum percentage of map tasks that can fail without + the job being aborted.]]> + </doc> + </method> + <method name="setMaxMapTaskFailuresPercent" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="percent" type="int"/> + <doc> + <![CDATA[Expert: Set the maximum percentage of map tasks that can fail without the + job being aborted. + + Each map task is executed a minimum of {@link #getMaxMapAttempts} attempts + before being declared as <i>failed</i>. + + @param percent the maximum percentage of map tasks that can fail without + the job being aborted.]]> + </doc> + </method> + <method name="getMaxReduceTaskFailuresPercent" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the maximum percentage of reduce tasks that can fail without + the job being aborted. + + Each reduce task is executed a minimum of {@link #getMaxReduceAttempts()} + attempts before being declared as <i>failed</i>. + + Defaults to <code>zero</code>, i.e. <i>any</i> failed reduce-task results + in the job being declared as {@link JobStatus#FAILED}. + + @return the maximum percentage of reduce tasks that can fail without + the job being aborted.]]> + </doc> + </method> + <method name="setMaxReduceTaskFailuresPercent" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="percent" type="int"/> + <doc> + <![CDATA[Set the maximum percentage of reduce tasks that can fail without the job + being aborted. + + Each reduce task is executed a minimum of {@link #getMaxReduceAttempts()} + attempts before being declared as <i>failed</i>. + + @param percent the maximum percentage of reduce tasks that can fail without + the job being aborted.]]> + </doc> + </method> + <method name="setJobPriority" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="prio" type="org.apache.hadoop.mapred.JobPriority"/> + <doc> + <![CDATA[Set {@link JobPriority} for this job. + + @param prio the {@link JobPriority} for this job.]]> + </doc> + </method> + <method name="getJobPriority" return="org.apache.hadoop.mapred.JobPriority" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the {@link JobPriority} for this job. + + @return the {@link JobPriority} for this job.]]> + </doc> + </method> + <method name="getProfileEnabled" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get whether the task profiling is enabled. + @return true if some tasks will be profiled]]> + </doc> + </method> + <method name="setProfileEnabled" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="newValue" type="boolean"/> + <doc> + <![CDATA[Set whether the system should collect profiler information for some of + the tasks in this job? The information is stored in the user log + directory. + @param newValue true means it should be gathered]]> + </doc> + </method> + <method name="getProfileParams" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the profiler configuration arguments. + + The default value for this property is + "-agentlib:hprof=cpu=samples,heap=sites,force=n,thread=y,verbose=n,file=%s" + + @return the parameters to pass to the task child to configure profiling]]> + </doc> + </method> + <method name="setProfileParams" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="value" type="java.lang.String"/> + <doc> + <![CDATA[Set the profiler configuration arguments. If the string contains a '%s' it + will be replaced with the name of the profiling output file when the task + runs. + + This value is passed to the task child JVM on the command line. + + @param value the configuration string]]> + </doc> + </method> + <method name="getProfileTaskRange" return="org.apache.hadoop.conf.Configuration.IntegerRanges" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="isMap" type="boolean"/> + <doc> + <![CDATA[Get the range of maps or reduces to profile. + @param isMap is the task a map? + @return the task ranges]]> + </doc> + </method> + <method name="setProfileTaskRange" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="isMap" type="boolean"/> + <param name="newValue" type="java.lang.String"/> + <doc> + <![CDATA[Set the ranges of maps or reduces to profile. setProfileEnabled(true) + must also be called. + @param newValue a set of integer ranges of the map ids]]> + </doc> + </method> + <method name="setMapDebugScript" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="mDbgScript" type="java.lang.String"/> + <doc> + <![CDATA[Set the debug script to run when the map tasks fail. + + <p>The debug script can aid debugging of failed map tasks. The script is + given task's stdout, stderr, syslog, jobconf files as arguments.</p> + + <p>The debug command, run on the node where the map failed, is:</p> + <p><pre><blockquote> + $script $stdout $stderr $syslog $jobconf. + </blockquote></pre></p> + + <p> The script file is distributed through {@link DistributedCache} + APIs. The script needs to be symlinked. </p> + + <p>Here is an example on how to submit a script + <p><blockquote><pre> + job.setMapDebugScript("./myscript"); + DistributedCache.createSymlink(job); + DistributedCache.addCacheFile("/debug/scripts/myscript#myscript"); + </pre></blockquote></p> + + @param mDbgScript the script name]]> + </doc> + </method> + <method name="getMapDebugScript" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the map task's debug script. + + @return the debug Script for the mapred job for failed map tasks. + @see #setMapDebugScript(String)]]> + </doc> + </method> + <method name="setReduceDebugScript" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="rDbgScript" type="java.lang.String"/> + <doc> + <![CDATA[Set the debug script to run when the reduce tasks fail. + + <p>The debug script can aid debugging of failed reduce tasks. The script + is given task's stdout, stderr, syslog, jobconf files as arguments.</p> + + <p>The debug command, run on the node where the map failed, is:</p> + <p><pre><blockquote> + $script $stdout $stderr $syslog $jobconf. + </blockquote></pre></p> + + <p> The script file is distributed through {@link DistributedCache} + APIs. The script file needs to be symlinked </p> + + <p>Here is an example on how to submit a script + <p><blockquote><pre> + job.setReduceDebugScript("./myscript"); + DistributedCache.createSymlink(job); + DistributedCache.addCacheFile("/debug/scripts/myscript#myscript"); + </pre></blockquote></p> + + @param rDbgScript the script name]]> + </doc> + </method> + <method name="getReduceDebugScript" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the reduce task's debug Script + + @return the debug script for the mapred job for failed reduce tasks. + @see #setReduceDebugScript(String)]]> + </doc> + </method> + <method name="getJobEndNotificationURI" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the uri to be invoked in-order to send a notification after the job + has completed (success/failure). + + @return the job end notification uri, <code>null</code> if it hasn't + been set. + @see #setJobEndNotificationURI(String)]]> + </doc> + </method> + <method name="setJobEndNotificationURI" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="uri" type="java.lang.String"/> + <doc> + <![CDATA[Set the uri to be invoked in-order to send a notification after the job + has completed (success/failure). + + <p>The uri can contain 2 special parameters: <tt>$jobId</tt> and + <tt>$jobStatus</tt>. Those, if present, are replaced by the job's + identifier and completion-status respectively.</p> + + <p>This is typically used by application-writers to implement chaining of + Map-Reduce jobs in an <i>asynchronous manner</i>.</p> + + @param uri the job end notification uri + @see JobStatus + @see <a href="{@docRoot}/org/apache/hadoop/mapred/JobClient.html#JobCompletionAndChaining">Job Completion and Chaining</a>]]> + </doc> + </method> + <method name="getJobLocalDir" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get job-specific shared directory for use as scratch space + + <p> + When a job starts, a shared directory is created at location + <code> + ${mapred.local.dir}/taskTracker/jobcache/$jobid/work/ </code>. + This directory is exposed to the users through + <code>job.local.dir </code>. + So, the tasks can use this space + as scratch space and share files among them. </p> + This value is available as System property also. + + @return The localized job specific shared directory]]> + </doc> + </method> + <doc> + <![CDATA[A map/reduce job configuration. + + <p><code>JobConf</code> is the primary interface for a user to describe a + map-reduce job to the Hadoop framework for execution. The framework tries to + faithfully execute the job as-is described by <code>JobConf</code>, however: + <ol> + <li> + Some configuration parameters might have been marked as + <a href="{@docRoot}/org/apache/hadoop/conf/Configuration.html#FinalParams"> + final</a> by administrators and hence cannot be altered. + </li> + <li> + While some job parameters are straight-forward to set + (e.g. {@link #setNumReduceTasks(int)}), some parameters interact subtly + rest of the framework and/or job-configuration and is relatively more + complex for the user to control finely (e.g. {@link #setNumMapTasks(int)}). + </li> + </ol></p> + + <p><code>JobConf</code> typically specifies the {@link Mapper}, combiner + (if any), {@link Partitioner}, {@link Reducer}, {@link InputFormat} and + {@link OutputFormat} implementations to be used etc. + + <p>Optionally <code>JobConf</code> is used to specify other advanced facets + of the job such as <code>Comparator</code>s to be used, files to be put in + the {@link DistributedCache}, whether or not intermediate and/or job outputs + are to be compressed (and how), debugability via user-provided scripts + ( {@link #setMapDebugScript(String)}/{@link #setReduceDebugScript(String)}), + for doing post-processing on task logs, task's stdout, stderr, syslog. + and etc.</p> + + <p>Here is an example on how to configure a job via <code>JobConf</code>:</p> + <p><blockquote><pre> + // Create a new JobConf + JobConf job = new JobConf(new Configuration(), MyJob.class); + + // Specify various job-specific parameters + job.setJobName("myjob"); + + FileInputFormat.setInputPaths(job, new Path("in")); + FileOutputFormat.setOutputPath(job, new Path("out")); + + job.setMapperClass(MyJob.MyMapper.class); + job.setCombinerClass(MyJob.MyReducer.class); + job.setReducerClass(MyJob.MyReducer.class); + + job.setInputFormat(SequenceFileInputFormat.class); + job.setOutputFormat(SequenceFileOutputFormat.class); + </pre></blockquote></p> + + @see JobClient + @see ClusterStatus + @see Tool + @see DistributedCache]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.JobConf --> + <!-- start interface org.apache.hadoop.mapred.JobConfigurable --> + <interface name="JobConfigurable" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="configure" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <doc> + <![CDATA[Initializes a new instance from a {@link JobConf}. + + @param job the configuration]]> + </doc> + </method> + <doc> + <![CDATA[That what may be configured.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.mapred.JobConfigurable --> + <!-- start class org.apache.hadoop.mapred.JobEndNotifier --> + <class name="JobEndNotifier" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JobEndNotifier" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="startNotifier" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="stopNotifier" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="registerNotification" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobConf" type="org.apache.hadoop.mapred.JobConf"/> + <param name="status" type="org.apache.hadoop.mapred.JobStatus"/> + </method> + <method name="localRunnerNotification" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <param name="status" type="org.apache.hadoop.mapred.JobStatus"/> + </method> + </class> + <!-- end class org.apache.hadoop.mapred.JobEndNotifier --> + <!-- start class org.apache.hadoop.mapred.JobHistory --> + <class name="JobHistory" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JobHistory" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="init" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <param name="hostname" type="java.lang.String"/> + <doc> + <![CDATA[Initialize JobHistory files. + @param conf Jobconf of the job tracker. + @param hostname jobtracker's hostname + @return true if intialized properly + false otherwise]]> + </doc> + </method> + <method name="parseHistoryFromFS" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="java.lang.String"/> + <param name="l" type="org.apache.hadoop.mapred.JobHistory.Listener"/> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Parses history file and invokes Listener.handle() for + each line of history. It can be used for looking through history + files for specific items without having to keep whole history in memory. + @param path path to history file + @param l Listener for history events + @param fs FileSystem where history file is present + @throws IOException]]> + </doc> + </method> + <method name="isDisableHistory" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns history disable status. by default history is enabled so this + method returns false. + @return true if history logging is disabled, false otherwise.]]> + </doc> + </method> + <method name="setDisableHistory" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="disableHistory" type="boolean"/> + <doc> + <![CDATA[Enable/disable history logging. Default value is false, so history + is enabled by default. + @param disableHistory true if history should be disabled, false otherwise.]]> + </doc> + </method> + <field name="LOG" type="org.apache.commons.logging.Log" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="JOBTRACKER_START_TIME" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[Provides methods for writing to and reading from job history. + Job History works in an append mode, JobHistory and its inner classes provide methods + to log job events. + + JobHistory is split into multiple files, format of each file is plain text where each line + is of the format [type (key=value)*], where type identifies the type of the record. + Type maps to UID of one of the inner classes of this class. + + Job history is maintained in a master index which contains star/stop times of all jobs with + a few other job level properties. Apart from this each job's history is maintained in a seperate history + file. name of job history files follows the format jobtrackerId_jobid + + For parsing the job history it supports a listener based interface where each line is parsed + and passed to listener. The listener can create an object model of history or look for specific + events and discard rest of the history.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.JobHistory --> + <!-- start class org.apache.hadoop.mapred.JobHistory.HistoryCleaner --> + <class name="JobHistory.HistoryCleaner" extends="java.lang.Object" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="java.lang.Runnable"/> + <constructor name="JobHistory.HistoryCleaner" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="run" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Cleans up history data.]]> + </doc> + </method> + <doc> + <![CDATA[Delete history files older than one month. Update master index and remove all + jobs older than one month. Also if a job tracker has no jobs in last one month + remove reference to the job tracker.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.JobHistory.HistoryCleaner --> + <!-- start class org.apache.hadoop.mapred.JobHistory.JobInfo --> + <class name="JobHistory.JobInfo" extends="org.apache.hadoop.mapred.JobHistory.KeyValuePair" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JobHistory.JobInfo" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Create new JobInfo]]> + </doc> + </constructor> + <method name="getAllTasks" return="java.util.Map<java.lang.String, org.apache.hadoop.mapred.JobHistory.Task>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns all map and reduce tasks <taskid-Task>.]]> + </doc> + </method> + <method name="getLocalJobFilePath" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <doc> + <![CDATA[Get the path of the locally stored job file + @param jobId id of the job + @return the path of the job file on the local file system]]> + </doc> + </method> + <method name="encodeJobHistoryFilePath" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="logFile" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Helper function to encode the URL of the path of the job-history + log file. + + @param logFile path of the job-history file + @return URL encoded path + @throws IOException]]> + </doc> + </method> + <method name="encodeJobHistoryFileName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="logFileName" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Helper function to encode the URL of the filename of the job-history + log file. + + @param logFileName file name of the job-history file + @return URL encoded filename + @throws IOException]]> + </doc> + </method> + <method name="decodeJobHistoryFileName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="logFileName" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Helper function to decode the URL of the filename of the job-history + log file. + + @param logFileName file name of the job-history file + @return URL decoded filename + @throws IOException]]> + </doc> + </method> + <method name="logSubmitted" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <param name="jobConf" type="org.apache.hadoop.mapred.JobConf"/> + <param name="jobConfPath" type="java.lang.String"/> + <param name="submitTime" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Log job submitted event to history. Creates a new file in history + for the job. if history file creation fails, it disables history + for all other events. + @param jobId job id assigned by job tracker. + @param jobConf job conf of the job + @param jobConfPath path to job conf xml file in HDFS. + @param submitTime time when job tracker received the job + @throws IOException]]> + </doc> + </method> + <method name="logStarted" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <param name="startTime" type="long"/> + <param name="totalMaps" type="int"/> + <param name="totalReduces" type="int"/> + <doc> + <![CDATA[Logs launch time of job. + @param jobId job id, assigned by jobtracker. + @param startTime start time of job. + @param totalMaps total maps assigned by jobtracker. + @param totalReduces total reduces.]]> + </doc> + </method> + <method name="logFinished" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <param name="finishTime" type="long"/> + <param name="finishedMaps" type="int"/> + <param name="finishedReduces" type="int"/> + <param name="failedMaps" type="int"/> + <param name="failedReduces" type="int"/> + <param name="counters" type="org.apache.hadoop.mapred.Counters"/> + <doc> + <![CDATA[Log job finished. closes the job file in history. + @param jobId job id, assigned by jobtracker. + @param finishTime finish time of job in ms. + @param finishedMaps no of maps successfully finished. + @param finishedReduces no of reduces finished sucessfully. + @param failedMaps no of failed map tasks. + @param failedReduces no of failed reduce tasks. + @param counters the counters from the job]]> + </doc> + </method> + <method name="logFailed" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobid" type="java.lang.String"/> + <param name="timestamp" type="long"/> + <param name="finishedMaps" type="int"/> + <param name="finishedReduces" type="int"/> + <doc> + <![CDATA[Logs job failed event. Closes the job history log file. + @param jobid job id + @param timestamp time when job failure was detected in ms. + @param finishedMaps no finished map tasks. + @param finishedReduces no of finished reduce tasks.]]> + </doc> + </method> + <doc> + <![CDATA[Helper class for logging or reading back events related to job start, finish or failure.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.JobHistory.JobInfo --> + <!-- start class org.apache.hadoop.mapred.JobHistory.Keys --> + <class name="JobHistory.Keys" extends="java.lang.Enum<org.apache.hadoop.mapred.JobHistory.Keys>" + abstract="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <method name="values" return="org.apache.hadoop.mapred.JobHistory.Keys[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="valueOf" return="org.apache.hadoop.mapred.JobHistory.Keys" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + <doc> + <![CDATA[Job history files contain key="value" pairs, where keys belong to this enum. + It acts as a global namespace for all keys.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.JobHistory.Keys --> + <!-- start interface org.apache.hadoop.mapred.JobHistory.Listener --> + <interface name="JobHistory.Listener" abstract="true" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <method name="handle" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="recType" type="org.apache.hadoop.mapred.JobHistory.RecordTypes"/> + <param name="values" type="java.util.Map<org.apache.hadoop.mapred.JobHistory.Keys, java.lang.String>"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Callback method for history parser. + @param recType type of record, which is the first entry in the line. + @param values a map of key-value pairs as thry appear in history. + @throws IOException]]> + </doc> + </method> + <doc> + <![CDATA[Callback interface for reading back log events from JobHistory. This interface + should be implemented and passed to JobHistory.parseHistory()]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.mapred.JobHistory.Listener --> + <!-- start class org.apache.hadoop.mapred.JobHistory.MapAttempt --> + <class name="JobHistory.MapAttempt" extends="org.apache.hadoop.mapred.JobHistory.TaskAttempt" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JobHistory.MapAttempt" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="logStarted" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <param name="taskId" type="java.lang.String"/> + <param name="taskAttemptId" type="java.lang.String"/> + <param name="startTime" type="long"/> + <param name="hostName" type="java.lang.String"/> + <doc> + <![CDATA[Log start time of this map task attempt. + @param jobId job id + @param taskId task id + @param taskAttemptId task attempt id + @param startTime start time of task attempt as reported by task tracker. + @param hostName host name of the task attempt.]]> + </doc> + </method> + <method name="logFinished" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <param name="taskId" type="java.lang.String"/> + <param name="taskAttemptId" type="java.lang.String"/> + <param name="finishTime" type="long"/> + <param name="hostName" type="java.lang.String"/> + <doc> + <![CDATA[Log finish time of map task attempt. + @param jobId job id + @param taskId task id + @param taskAttemptId task attempt id + @param finishTime finish time + @param hostName host name]]> + </doc> + </method> + <method name="logFailed" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <param name="taskId" type="java.lang.String"/> + <param name="taskAttemptId" type="java.lang.String"/> + <param name="timestamp" type="long"/> + <param name="hostName" type="java.lang.String"/> + <param name="error" type="java.lang.String"/> + <doc> + <![CDATA[Log task attempt failed event. + @param jobId jobid + @param taskId taskid + @param taskAttemptId task attempt id + @param timestamp timestamp + @param hostName hostname of this task attempt. + @param error error message if any for this task attempt.]]> + </doc> + </method> + <method name="logKilled" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <param name="taskId" type="java.lang.String"/> + <param name="taskAttemptId" type="java.lang.String"/> + <param name="timestamp" type="long"/> + <param name="hostName" type="java.lang.String"/> + <param name="error" type="java.lang.String"/> + <doc> + <![CDATA[Log task attempt killed event. + @param jobId jobid + @param taskId taskid + @param taskAttemptId task attempt id + @param timestamp timestamp + @param hostName hostname of this task attempt. + @param error error message if any for this task attempt.]]> + </doc> + </method> + <doc> + <![CDATA[Helper class for logging or reading back events related to start, finish or failure of + a Map Attempt on a node.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.JobHistory.MapAttempt --> + <!-- start class org.apache.hadoop.mapred.JobHistory.RecordTypes --> + <class name="JobHistory.RecordTypes" extends="java.lang.Enum<org.apache.hadoop.mapred.JobHistory.RecordTypes>" + abstract="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <method name="values" return="org.apache.hadoop.mapred.JobHistory.RecordTypes[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="valueOf" return="org.apache.hadoop.mapred.JobHistory.RecordTypes" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + <doc> + <![CDATA[Record types are identifiers for each line of log in history files. + A record type appears as the first token in a single line of log.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.JobHistory.RecordTypes --> + <!-- start class org.apache.hadoop.mapred.JobHistory.ReduceAttempt --> + <class name="JobHistory.ReduceAttempt" extends="org.apache.hadoop.mapred.JobHistory.TaskAttempt" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JobHistory.ReduceAttempt" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="logStarted" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <param name="taskId" type="java.lang.String"/> + <param name="taskAttemptId" type="java.lang.String"/> + <param name="startTime" type="long"/> + <param name="hostName" type="java.lang.String"/> + <doc> + <![CDATA[Log start time of Reduce task attempt. + @param jobId job id + @param taskId task id (tip) + @param taskAttemptId task attempt id + @param startTime start time + @param hostName host name]]> + </doc> + </method> + <method name="logFinished" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <param name="taskId" type="java.lang.String"/> + <param name="taskAttemptId" type="java.lang.String"/> + <param name="shuffleFinished" type="long"/> + <param name="sortFinished" type="long"/> + <param name="finishTime" type="long"/> + <param name="hostName" type="java.lang.String"/> + <doc> + <![CDATA[Log finished event of this task. + @param jobId job id + @param taskId task id + @param taskAttemptId task attempt id + @param shuffleFinished shuffle finish time + @param sortFinished sort finish time + @param finishTime finish time of task + @param hostName host name where task attempt executed]]> + </doc> + </method> + <method name="logFailed" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <param name="taskId" type="java.lang.String"/> + <param name="taskAttemptId" type="java.lang.String"/> + <param name="timestamp" type="long"/> + <param name="hostName" type="java.lang.String"/> + <param name="error" type="java.lang.String"/> + <doc> + <![CDATA[Log failed reduce task attempt. + @param jobId job id + @param taskId task id + @param taskAttemptId task attempt id + @param timestamp time stamp when task failed + @param hostName host name of the task attempt. + @param error error message of the task.]]> + </doc> + </method> + <method name="logKilled" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <param name="taskId" type="java.lang.String"/> + <param name="taskAttemptId" type="java.lang.String"/> + <param name="timestamp" type="long"/> + <param name="hostName" type="java.lang.String"/> + <param name="error" type="java.lang.String"/> + <doc> + <![CDATA[Log killed reduce task attempt. + @param jobId job id + @param taskId task id + @param taskAttemptId task attempt id + @param timestamp time stamp when task failed + @param hostName host name of the task attempt. + @param error error message of the task.]]> + </doc> + </method> + <doc> + <![CDATA[Helper class for logging or reading back events related to start, finish or failure of + a Map Attempt on a node.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.JobHistory.ReduceAttempt --> + <!-- start class org.apache.hadoop.mapred.JobHistory.Task --> + <class name="JobHistory.Task" extends="org.apache.hadoop.mapred.JobHistory.KeyValuePair" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JobHistory.Task" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="logStarted" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <param name="taskId" type="java.lang.String"/> + <param name="taskType" type="java.lang.String"/> + <param name="startTime" type="long"/> + <doc> + <![CDATA[Log start time of task (TIP). + @param jobId job id + @param taskId task id + @param taskType MAP or REDUCE + @param startTime startTime of tip.]]> + </doc> + </method> + <method name="logFinished" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <param name="taskId" type="java.lang.String"/> + <param name="taskType" type="java.lang.String"/> + <param name="finishTime" type="long"/> + <param name="counters" type="org.apache.hadoop.mapred.Counters"/> + <doc> + <![CDATA[Log finish time of task. + @param jobId job id + @param taskId task id + @param taskType MAP or REDUCE + @param finishTime finish timeof task in ms]]> + </doc> + </method> + <method name="logFailed" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <param name="taskId" type="java.lang.String"/> + <param name="taskType" type="java.lang.String"/> + <param name="time" type="long"/> + <param name="error" type="java.lang.String"/> + <doc> + <![CDATA[Log job failed event. + @param jobId jobid + @param taskId task id + @param taskType MAP or REDUCE. + @param time timestamp when job failed detected. + @param error error message for failure.]]> + </doc> + </method> + <method name="getTaskAttempts" return="java.util.Map<java.lang.String, org.apache.hadoop.mapred.JobHistory.TaskAttempt>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns all task attempts for this task. <task attempt id - TaskAttempt>]]> + </doc> + </method> + <doc> + <![CDATA[Helper class for logging or reading back events related to Task's start, finish or failure. + All events logged by this class are logged in a separate file per job in + job tracker history. These events map to TIPs in jobtracker.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.JobHistory.Task --> + <!-- start class org.apache.hadoop.mapred.JobHistory.TaskAttempt --> + <class name="JobHistory.TaskAttempt" extends="org.apache.hadoop.mapred.JobHistory.Task" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JobHistory.TaskAttempt" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <doc> + <![CDATA[Base class for Map and Reduce TaskAttempts.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.JobHistory.TaskAttempt --> + <!-- start class org.apache.hadoop.mapred.JobHistory.Values --> + <class name="JobHistory.Values" extends="java.lang.Enum<org.apache.hadoop.mapred.JobHistory.Values>" + abstract="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <method name="values" return="org.apache.hadoop.mapred.JobHistory.Values[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="valueOf" return="org.apache.hadoop.mapred.JobHistory.Values" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + <doc> + <![CDATA[This enum contains some of the values commonly used by history log events. + since values in history can only be strings - Values.name() is used in + most places in history file.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.JobHistory.Values --> + <!-- start class org.apache.hadoop.mapred.JobPriority --> + <class name="JobPriority" extends="java.lang.Enum<org.apache.hadoop.mapred.JobPriority>" + abstract="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <method name="values" return="org.apache.hadoop.mapred.JobPriority[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="valueOf" return="org.apache.hadoop.mapred.JobPriority" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + <doc> + <![CDATA[Used to describe the priority of the running job.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.JobPriority --> + <!-- start class org.apache.hadoop.mapred.JobProfile --> + <class name="JobProfile" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <constructor name="JobProfile" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct an empty {@link JobProfile}.]]> + </doc> + </constructor> + <constructor name="JobProfile" type="java.lang.String, java.lang.String, java.lang.String, java.lang.String, java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct a {@link JobProfile} the userid, jobid, + job config-file, job-details url and job name. + + @param user userid of the person who submitted the job. + @param jobid id of the job. + @param jobFile job configuration file. + @param url link to the web-ui for details of the job. + @param name user-specified job name.]]> + </doc> + </constructor> + <method name="getUser" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the user id.]]> + </doc> + </method> + <method name="getJobId" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the job id.]]> + </doc> + </method> + <method name="getJobFile" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the configuration file for the job.]]> + </doc> + </method> + <method name="getURL" return="java.net.URL" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the link to the web-ui for details of the job.]]> + </doc> + </method> + <method name="getJobName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the user-specified job name.]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[A JobProfile is a MapReduce primitive. Tracks a job, + whether living or dead.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.JobProfile --> + <!-- start class org.apache.hadoop.mapred.JobShell --> + <class name="JobShell" extends="org.apache.hadoop.conf.Configured" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.util.Tool"/> + <constructor name="JobShell" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="JobShell" type="org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="init" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="run" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="argv" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + <doc> + <![CDATA[run method from Tool]]> + </doc> + </method> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="argv" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + </method> + <field name="LOG" type="org.apache.commons.logging.Log" + transient="false" volatile="false" + static="true" final="true" visibility="protected" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[Provide command line parsing for JobSubmission + job submission looks like + hadoop jar -libjars <comma seperated jars> -archives <comma seperated archives> + -files <comma seperated files> inputjar args]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.JobShell --> + <!-- start class org.apache.hadoop.mapred.JobStatus --> + <class name="JobStatus" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <constructor name="JobStatus" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="JobStatus" type="java.lang.String, float, float, int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Create a job status object for a given jobid. + @param jobid The jobid of the job + @param mapProgress The progress made on the maps + @param reduceProgress The progress made on the reduces + @param runState The current state of the job]]> + </doc> + </constructor> + <method name="getJobId" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return The jobid of the Job]]> + </doc> + </method> + <method name="mapProgress" return="float" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return Percentage of progress in maps]]> + </doc> + </method> + <method name="reduceProgress" return="float" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return Percentage of progress in reduce]]> + </doc> + </method> + <method name="getRunState" return="int" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return running state of the job]]> + </doc> + </method> + <method name="setRunState" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="state" type="int"/> + <doc> + <![CDATA[Change the current run state of the job.]]> + </doc> + </method> + <method name="getStartTime" return="long" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return start time of the job]]> + </doc> + </method> + <method name="getUsername" return="java.lang.String" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the username of the job]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <field name="RUNNING" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="SUCCEEDED" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="FAILED" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="PREP" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[Describes the current status of a job. This is + not intended to be a comprehensive piece of data. + For that, look at JobProfile.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.JobStatus --> + <!-- start interface org.apache.hadoop.mapred.JobSubmissionProtocol --> + <interface name="JobSubmissionProtocol" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.ipc.VersionedProtocol"/> + <method name="getNewJobId" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Allocate a name for the job. + @return a unique job name for submitting jobs. + @throws IOException]]> + </doc> + </method> + <method name="submitJob" return="org.apache.hadoop.mapred.JobStatus" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobName" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Submit a Job for execution. Returns the latest profile for + that job. + The job files should be submitted in <b>system-dir</b>/<b>jobName</b>.]]> + </doc> + </method> + <method name="getClusterStatus" return="org.apache.hadoop.mapred.ClusterStatus" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get the current status of the cluster + @return summary of the state of the cluster]]> + </doc> + </method> + <method name="killJob" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobid" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Kill the indicated job]]> + </doc> + </method> + <method name="killTask" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="taskId" type="java.lang.String"/> + <param name="shouldFail" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Kill indicated task attempt. + @param taskId the id of the task to kill. + @param shouldFail if true the task is failed and added to failed tasks list, otherwise + it is just killed, w/o affecting job failure status.]]> + </doc> + </method> + <method name="getJobProfile" return="org.apache.hadoop.mapred.JobProfile" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobid" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Grab a handle to a job that is already known to the JobTracker. + @return Profile of the job, or null if not found.]]> + </doc> + </method> + <method name="getJobStatus" return="org.apache.hadoop.mapred.JobStatus" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobid" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Grab a handle to a job that is already known to the JobTracker. + @return Status of the job, or null if not found.]]> + </doc> + </method> + <method name="getJobCounters" return="org.apache.hadoop.mapred.Counters" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobid" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Grab the current job counters]]> + </doc> + </method> + <method name="getMapTaskReports" return="org.apache.hadoop.mapred.TaskReport[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobid" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Grab a bunch of info on the map tasks that make up the job]]> + </doc> + </method> + <method name="getReduceTaskReports" return="org.apache.hadoop.mapred.TaskReport[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobid" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Grab a bunch of info on the reduce tasks that make up the job]]> + </doc> + </method> + <method name="getFilesystemName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[A MapReduce system always operates on a single filesystem. This + function returns the fs name. ('local' if the localfs; 'addr:port' + if dfs). The client can then copy files into the right locations + prior to submitting the job.]]> + </doc> + </method> + <method name="jobsToComplete" return="org.apache.hadoop.mapred.JobStatus[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get the jobs that are not completed and not failed + @return array of JobStatus for the running/to-be-run + jobs.]]> + </doc> + </method> + <method name="getAllJobs" return="org.apache.hadoop.mapred.JobStatus[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get all the jobs submitted. + @return array of JobStatus for the submitted jobs]]> + </doc> + </method> + <method name="getTaskCompletionEvents" return="org.apache.hadoop.mapred.TaskCompletionEvent[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobid" type="java.lang.String"/> + <param name="fromEventId" type="int"/> + <param name="maxEvents" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get task completion events for the jobid, starting from fromEventId. + Returns empty aray if no events are available. + @param jobid job id + @param fromEventId event id to start from. + @param maxEvents the max number of events we want to look at + @return array of task completion events. + @throws IOException]]> + </doc> + </method> + <method name="getTaskDiagnostics" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <param name="tipId" type="java.lang.String"/> + <param name="taskId" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get the diagnostics for a given task in a given job + @param jobId the id of the job + @return an array of the diagnostic messages]]> + </doc> + </method> + <field name="versionID" type="long" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[Protocol that a JobClient and the central JobTracker use to communicate. The + JobClient can use these methods to submit a Job for execution, and learn about + the current system status.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.mapred.JobSubmissionProtocol --> + <!-- start class org.apache.hadoop.mapred.JobTracker --> + <class name="JobTracker" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.MRConstants"/> + <implements name="org.apache.hadoop.mapred.InterTrackerProtocol"/> + <implements name="org.apache.hadoop.mapred.JobSubmissionProtocol"/> + <method name="startTracker" return="org.apache.hadoop.mapred.JobTracker" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <exception name="IOException" type="java.io.IOException"/> + <exception name="InterruptedException" type="java.lang.InterruptedException"/> + <doc> + <![CDATA[Start the JobTracker with given configuration. + + The conf will be modified to reflect the actual ports on which + the JobTracker is up and running if the user passes the port as + <code>zero</code>. + + @param conf configuration for the JobTracker. + @throws IOException]]> + </doc> + </method> + <method name="stopTracker" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getProtocolVersion" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="protocol" type="java.lang.String"/> + <param name="clientVersion" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getAddress" return="java.net.InetSocketAddress" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + </method> + <method name="offerService" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="InterruptedException" type="java.lang.InterruptedException"/> + <doc> + <![CDATA[Run forever]]> + </doc> + </method> + <method name="getTotalSubmissions" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getJobTrackerMachine" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getTrackerIdentifier" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the unique identifier (ie. timestamp) of this job tracker start. + @return a string with a unique identifier]]> + </doc> + </method> + <method name="getTrackerPort" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getInfoPort" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getStartTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="runningJobs" return="java.util.Vector<org.apache.hadoop.mapred.JobInProgress>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getRunningJobs" return="java.util.List<org.apache.hadoop.mapred.JobInProgress>" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Version that is called from a timer thread, and therefore needs to be + careful to synchronize.]]> + </doc> + </method> + <method name="failedJobs" return="java.util.Vector<org.apache.hadoop.mapred.JobInProgress>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="completedJobs" return="java.util.Vector<org.apache.hadoop.mapred.JobInProgress>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="taskTrackers" return="java.util.Collection" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getTaskTracker" return="org.apache.hadoop.mapred.TaskTrackerStatus" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="trackerID" type="java.lang.String"/> + </method> + <method name="resolveAndAddToTopology" return="org.apache.hadoop.net.Node" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + <method name="getNodesAtMaxLevel" return="java.util.Collection<org.apache.hadoop.net.Node>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns a collection of nodes at the max level]]> + </doc> + </method> + <method name="getParentNode" return="org.apache.hadoop.net.Node" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="node" type="org.apache.hadoop.net.Node"/> + <param name="level" type="int"/> + </method> + <method name="getNode" return="org.apache.hadoop.net.Node" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <doc> + <![CDATA[Return the Node in the network topology that corresponds to the hostname]]> + </doc> + </method> + <method name="getNumTaskCacheLevels" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getNumResolvedTaskTrackers" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="heartbeat" return="org.apache.hadoop.mapred.HeartbeatResponse" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="status" type="org.apache.hadoop.mapred.TaskTrackerStatus"/> + <param name="initialContact" type="boolean"/> + <param name="acceptNewTasks" type="boolean"/> + <param name="responseId" type="short"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[The periodic heartbeat mechanism between the {@link TaskTracker} and + the {@link JobTracker}. + + The {@link JobTracker} processes the status information sent by the + {@link TaskTracker} and responds with instructions to start/stop + tasks or jobs, and also 'reset' instructions during contingencies.]]> + </doc> + </method> + <method name="getFilesystemName" return="java.lang.String" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Grab the local fs name]]> + </doc> + </method> + <method name="reportTaskTrackerError" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="taskTracker" type="java.lang.String"/> + <param name="errorClass" type="java.lang.String"/> + <param name="errorMessage" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getNewJobId" return="java.lang.String" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Allocates a new JobId string.]]> + </doc> + </method> + <method name="submitJob" return="org.apache.hadoop.mapred.JobStatus" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[JobTracker.submitJob() kicks off a new job. + + Create a 'JobInProgress' object, which contains both JobProfile + and JobStatus. Those two sub-objects are sometimes shipped outside + of the JobTracker. But JobInProgress adds info that's useful for + the JobTracker alone. + + We add the JIP to the jobInitQueue, which is processed + asynchronously to handle split-computation and build up + the right TaskTracker/Block mapping.]]> + </doc> + </method> + <method name="getClusterStatus" return="org.apache.hadoop.mapred.ClusterStatus" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="killJob" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobid" type="java.lang.String"/> + </method> + <method name="getJobProfile" return="org.apache.hadoop.mapred.JobProfile" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobid" type="java.lang.String"/> + </method> + <method name="getJobStatus" return="org.apache.hadoop.mapred.JobStatus" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobid" type="java.lang.String"/> + </method> + <method name="getJobCounters" return="org.apache.hadoop.mapred.Counters" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobid" type="java.lang.String"/> + </method> + <method name="getMapTaskReports" return="org.apache.hadoop.mapred.TaskReport[]" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobid" type="java.lang.String"/> + </method> + <method name="getReduceTaskReports" return="org.apache.hadoop.mapred.TaskReport[]" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobid" type="java.lang.String"/> + </method> + <method name="getTaskCompletionEvents" return="org.apache.hadoop.mapred.TaskCompletionEvent[]" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobid" type="java.lang.String"/> + <param name="fromEventId" type="int"/> + <param name="maxEvents" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getTaskDiagnostics" return="java.lang.String[]" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <param name="tipId" type="java.lang.String"/> + <param name="taskId" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get the diagnostics for a given task + @param jobId the id of the job + @param tipId the id of the tip + @param taskId the id of the task + @return an array of the diagnostic messages]]> + </doc> + </method> + <method name="killTask" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="taskid" type="java.lang.String"/> + <param name="shouldFail" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Mark a Task to be killed]]> + </doc> + </method> + <method name="getAssignedTracker" return="java.lang.String" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="taskId" type="java.lang.String"/> + <doc> + <![CDATA[Get tracker name for a given task id. + @param taskId the name of the task + @return The name of the task tracker]]> + </doc> + </method> + <method name="jobsToComplete" return="org.apache.hadoop.mapred.JobStatus[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getAllJobs" return="org.apache.hadoop.mapred.JobStatus[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getJob" return="org.apache.hadoop.mapred.JobInProgress" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobid" type="java.lang.String"/> + </method> + <method name="getLocalJobFilePath" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <doc> + <![CDATA[Get the localized job file path on the job trackers local file system + @param jobId id of the job + @return the path of the job conf file on the local file system]]> + </doc> + </method> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="argv" type="java.lang.String[]"/> + <exception name="IOException" type="java.io.IOException"/> + <exception name="InterruptedException" type="java.lang.InterruptedException"/> + <doc> + <![CDATA[Start the JobTracker process. This is used only for debugging. As a rule, + JobTracker should be run as part of the DFS Namenode process.]]> + </doc> + </method> + <field name="LOG" type="org.apache.commons.logging.Log" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[JobTracker is the central location for submitting and + tracking MR jobs in a network environment.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.JobTracker --> + <!-- start class org.apache.hadoop.mapred.JobTracker.IllegalStateException --> + <class name="JobTracker.IllegalStateException" extends="java.io.IOException" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JobTracker.IllegalStateException" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <doc> + <![CDATA[A client tried to submit a job before the Job Tracker was ready.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.JobTracker.IllegalStateException --> + <!-- start class org.apache.hadoop.mapred.JobTracker.State --> + <class name="JobTracker.State" extends="java.lang.Enum<org.apache.hadoop.mapred.JobTracker.State>" + abstract="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <method name="values" return="org.apache.hadoop.mapred.JobTracker.State[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="valueOf" return="org.apache.hadoop.mapred.JobTracker.State" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + </class> + <!-- end class org.apache.hadoop.mapred.JobTracker.State --> + <!-- start class org.apache.hadoop.mapred.KeyValueLineRecordReader --> + <class name="KeyValueLineRecordReader" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.Text, org.apache.hadoop.io.Text>"/> + <constructor name="KeyValueLineRecordReader" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.mapred.FileSplit" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </constructor> + <method name="getKeyClass" return="java.lang.Class" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="createKey" return="org.apache.hadoop.io.Text" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="createValue" return="org.apache.hadoop.io.Text" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="findSeparator" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="utf" type="byte[]"/> + <param name="start" type="int"/> + <param name="length" type="int"/> + <param name="sep" type="byte"/> + </method> + <method name="next" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.Text"/> + <param name="value" type="org.apache.hadoop.io.Text"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read key/value pair in a line.]]> + </doc> + </method> + <method name="getProgress" return="float" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getPos" return="long" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="close" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[This class treats a line in the input as a key/value pair separated by a + separator character. The separator can be specified in config file + under the attribute name key.value.separator.in.input.line. The default + separator is the tab character ('\t').]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.KeyValueLineRecordReader --> + <!-- start class org.apache.hadoop.mapred.KeyValueTextInputFormat --> + <class name="KeyValueTextInputFormat" extends="org.apache.hadoop.mapred.FileInputFormat<org.apache.hadoop.io.Text, org.apache.hadoop.io.Text>" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.JobConfigurable"/> + <constructor name="KeyValueTextInputFormat" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="configure" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + </method> + <method name="isSplitable" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <param name="file" type="org.apache.hadoop.fs.Path"/> + </method> + <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.Text, org.apache.hadoop.io.Text>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="genericSplit" type="org.apache.hadoop.mapred.InputSplit"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[An {@link InputFormat} for plain text files. Files are broken into lines. + Either linefeed or carriage-return are used to signal end of line. Each line + is divided into key and value parts by a separator byte. If no such a byte + exists, the key will be the entire line and value will be empty.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.KeyValueTextInputFormat --> + <!-- start class org.apache.hadoop.mapred.LineRecordReader --> + <class name="LineRecordReader" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.LongWritable, org.apache.hadoop.io.Text>"/> + <constructor name="LineRecordReader" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.mapred.FileSplit" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </constructor> + <constructor name="LineRecordReader" type="java.io.InputStream, long, long" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="LineRecordReader" type="java.io.InputStream, long, long, org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </constructor> + <method name="createKey" return="org.apache.hadoop.io.LongWritable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="createValue" return="org.apache.hadoop.io.Text" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="next" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.LongWritable"/> + <param name="value" type="org.apache.hadoop.io.Text"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read a line.]]> + </doc> + </method> + <method name="getProgress" return="float" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the progress within the split]]> + </doc> + </method> + <method name="getPos" return="long" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="close" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[Treats keys as offset in file and value as line.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.LineRecordReader --> + <!-- start class org.apache.hadoop.mapred.LineRecordReader.LineReader --> + <class name="LineRecordReader.LineReader" extends="java.lang.Object" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="LineRecordReader.LineReader" type="java.io.InputStream, org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create a line reader that reads from the given stream using the + <code>io.file.buffer.size</code> specified in the given + <code>Configuration</code>. + @param in input stream + @param conf configuration + @throws IOException]]> + </doc> + </constructor> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Close the underlying stream. + @throws IOException]]> + </doc> + </method> + <method name="readLine" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="str" type="org.apache.hadoop.io.Text"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read from the InputStream into the given Text. + @param str the object to store the given line + @return the number of bytes read including the newline + @throws IOException if the underlying stream throws]]> + </doc> + </method> + <doc> + <![CDATA[A class that provides a line reader from an input stream.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.LineRecordReader.LineReader --> + <!-- start class org.apache.hadoop.mapred.MapFileOutputFormat --> + <class name="MapFileOutputFormat" extends="org.apache.hadoop.mapred.FileOutputFormat<org.apache.hadoop.io.WritableComparable, org.apache.hadoop.io.Writable>" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="MapFileOutputFormat" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getRecordWriter" return="org.apache.hadoop.mapred.RecordWriter<org.apache.hadoop.io.WritableComparable, org.apache.hadoop.io.Writable>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="name" type="java.lang.String"/> + <param name="progress" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getReaders" return="org.apache.hadoop.io.MapFile.Reader[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/> + <param name="dir" type="org.apache.hadoop.fs.Path"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Open the output generated by this format.]]> + </doc> + </method> + <method name="getEntry" return="org.apache.hadoop.io.Writable" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="readers" type="org.apache.hadoop.io.MapFile.Reader[]"/> + <param name="partitioner" type="org.apache.hadoop.mapred.Partitioner<K, V>"/> + <param name="key" type="K extends org.apache.hadoop.io.WritableComparable"/> + <param name="value" type="V extends org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get an entry from output generated by this class.]]> + </doc> + </method> + <doc> + <![CDATA[An {@link OutputFormat} that writes {@link MapFile}s.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.MapFileOutputFormat --> + <!-- start interface org.apache.hadoop.mapred.Mapper --> + <interface name="Mapper" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.JobConfigurable"/> + <implements name="org.apache.hadoop.io.Closeable"/> + <method name="map" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K1"/> + <param name="value" type="V1"/> + <param name="output" type="org.apache.hadoop.mapred.OutputCollector<K2, V2>"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Maps a single input key/value pair into an intermediate key/value pair. + + <p>Output pairs need not be of the same types as input pairs. A given + input pair may map to zero or many output pairs. Output pairs are + collected with calls to + {@link OutputCollector#collect(Object,Object)}.</p> + + <p>Applications can use the {@link Reporter} provided to report progress + or just indicate that they are alive. In scenarios where the application + takes an insignificant amount of time to process individual key/value + pairs, this is crucial since the framework might assume that the task has + timed-out and kill that task. The other way of avoiding this is to set + <a href="{@docRoot}/../hadoop-default.html#mapred.task.timeout"> + mapred.task.timeout</a> to a high-enough value (or even zero for no + time-outs).</p> + + @param key the input key. + @param value the input value. + @param output collects mapped keys and values. + @param reporter facility to report progress.]]> + </doc> + </method> + <doc> + <![CDATA[Maps input key/value pairs to a set of intermediate key/value pairs. + + <p>Maps are the individual tasks which transform input records into a + intermediate records. The transformed intermediate records need not be of + the same type as the input records. A given input pair may map to zero or + many output pairs.</p> + + <p>The Hadoop Map-Reduce framework spawns one map task for each + {@link InputSplit} generated by the {@link InputFormat} for the job. + <code>Mapper</code> implementations can access the {@link JobConf} for the + job via the {@link JobConfigurable#configure(JobConf)} and initialize + themselves. Similarly they can use the {@link Closeable#close()} method for + de-initialization.</p> + + <p>The framework then calls + {@link #map(Object, Object, OutputCollector, Reporter)} + for each key/value pair in the <code>InputSplit</code> for that task.</p> + + <p>All intermediate values associated with a given output key are + subsequently grouped by the framework, and passed to a {@link Reducer} to + determine the final output. Users can control the grouping by specifying + a <code>Comparator</code> via + {@link JobConf#setOutputKeyComparatorClass(Class)}.</p> + + <p>The grouped <code>Mapper</code> outputs are partitioned per + <code>Reducer</code>. Users can control which keys (and hence records) go to + which <code>Reducer</code> by implementing a custom {@link Partitioner}. + + <p>Users can optionally specify a <code>combiner</code>, via + {@link JobConf#setCombinerClass(Class)}, to perform local aggregation of the + intermediate outputs, which helps to cut down the amount of data transferred + from the <code>Mapper</code> to the <code>Reducer</code>. + + <p>The intermediate, grouped outputs are always stored in + {@link SequenceFile}s. Applications can specify if and how the intermediate + outputs are to be compressed and which {@link CompressionCodec}s are to be + used via the <code>JobConf</code>.</p> + + <p>If the job has + <a href="{@docRoot}/org/apache/hadoop/mapred/JobConf.html#ReducerNone">zero + reduces</a> then the output of the <code>Mapper</code> is directly written + to the {@link FileSystem} without grouping by keys.</p> + + <p>Example:</p> + <p><blockquote><pre> + public class MyMapper<K extends WritableComparable, V extends Writable> + extends MapReduceBase implements Mapper<K, V, K, V> { + + static enum MyCounters { NUM_RECORDS } + + private String mapTaskId; + private String inputFile; + private int noRecords = 0; + + public void configure(JobConf job) { + mapTaskId = job.get("mapred.task.id"); + inputFile = job.get("mapred.input.file"); + } + + public void map(K key, V val, + OutputCollector<K, V> output, Reporter reporter) + throws IOException { + // Process the <key, value> pair (assume this takes a while) + // ... + // ... + + // Let the framework know that we are alive, and kicking! + // reporter.progress(); + + // Process some more + // ... + // ... + + // Increment the no. of <key, value> pairs processed + ++noRecords; + + // Increment counters + reporter.incrCounter(NUM_RECORDS, 1); + + // Every 100 records update application-level status + if ((noRecords%100) == 0) { + reporter.setStatus(mapTaskId + " processed " + noRecords + + " from input-file: " + inputFile); + } + + // Output the result + output.collect(key, val); + } + } + </pre></blockquote></p> + + <p>Applications may write a custom {@link MapRunnable} to exert greater + control on map processing e.g. multi-threaded <code>Mapper</code>s etc.</p> + + @see JobConf + @see InputFormat + @see Partitioner + @see Reducer + @see MapReduceBase + @see MapRunnable + @see SequenceFile]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.mapred.Mapper --> + <!-- start class org.apache.hadoop.mapred.MapReduceBase --> + <class name="MapReduceBase" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Closeable"/> + <implements name="org.apache.hadoop.mapred.JobConfigurable"/> + <constructor name="MapReduceBase" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Default implementation that does nothing.]]> + </doc> + </method> + <method name="configure" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <doc> + <![CDATA[Default implementation that does nothing.]]> + </doc> + </method> + <doc> + <![CDATA[Base class for {@link Mapper} and {@link Reducer} implementations. + + <p>Provides default no-op implementations for a few methods, most non-trivial + applications need to override some of them.</p>]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.MapReduceBase --> + <!-- start interface org.apache.hadoop.mapred.MapRunnable --> + <interface name="MapRunnable" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.JobConfigurable"/> + <method name="run" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="input" type="org.apache.hadoop.mapred.RecordReader<K1, V1>"/> + <param name="output" type="org.apache.hadoop.mapred.OutputCollector<K2, V2>"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Start mapping input <tt><key, value></tt> pairs. + + <p>Mapping of input records to output records is complete when this method + returns.</p> + + @param input the {@link RecordReader} to read the input records. + @param output the {@link OutputCollector} to collect the outputrecords. + @param reporter {@link Reporter} to report progress, status-updates etc. + @throws IOException]]> + </doc> + </method> + <doc> + <![CDATA[Expert: Generic interface for {@link Mapper}s. + + <p>Custom implementations of <code>MapRunnable</code> can exert greater + control on map processing e.g. multi-threaded, asynchronous mappers etc.</p> + + @see Mapper]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.mapred.MapRunnable --> + <!-- start class org.apache.hadoop.mapred.MapRunner --> + <class name="MapRunner" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.MapRunnable<K1, V1, K2, V2>"/> + <constructor name="MapRunner" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="configure" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + </method> + <method name="run" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="input" type="org.apache.hadoop.mapred.RecordReader<K1, V1>"/> + <param name="output" type="org.apache.hadoop.mapred.OutputCollector<K2, V2>"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[Default {@link MapRunnable} implementation.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.MapRunner --> + <!-- start class org.apache.hadoop.mapred.MapTaskStatus --> + <class name="MapTaskStatus" extends="org.apache.hadoop.mapred.TaskStatus" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="MapTaskStatus" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="MapTaskStatus" type="java.lang.String, float, org.apache.hadoop.mapred.TaskStatus.State, java.lang.String, java.lang.String, java.lang.String, org.apache.hadoop.mapred.TaskStatus.Phase, org.apache.hadoop.mapred.Counters" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getIsMap" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getShuffleFinishTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getSortFinishTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + </class> + <!-- end class org.apache.hadoop.mapred.MapTaskStatus --> + <!-- start class org.apache.hadoop.mapred.MultiFileInputFormat --> + <class name="MultiFileInputFormat" extends="org.apache.hadoop.mapred.FileInputFormat<K, V>" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="MultiFileInputFormat" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getSplits" return="org.apache.hadoop.mapred.InputSplit[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="numSplits" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader<K, V>" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="split" type="org.apache.hadoop.mapred.InputSplit"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[An abstract {@link InputFormat} that returns {@link MultiFileSplit}'s + in {@link #getSplits(JobConf, int)} method. Splits are constructed from + the files under the input paths. Each split returned contains <i>nearly</i> + equal content length. <br> + Subclasses implement {@link #getRecordReader(InputSplit, JobConf, Reporter)} + to construct <code>RecordReader</code>'s for <code>MultiFileSplit</code>'s. + @see MultiFileSplit]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.MultiFileInputFormat --> + <!-- start class org.apache.hadoop.mapred.MultiFileSplit --> + <class name="MultiFileSplit" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.InputSplit"/> + <constructor name="MultiFileSplit" type="org.apache.hadoop.mapred.JobConf, org.apache.hadoop.fs.Path[], long[]" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getLength" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getLengths" return="long[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns an array containing the lengths of the files in + the split]]> + </doc> + </method> + <method name="getLength" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="i" type="int"/> + <doc> + <![CDATA[Returns the length of the i<sup>th</sup> Path]]> + </doc> + </method> + <method name="getNumPaths" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the number of Paths in the split]]> + </doc> + </method> + <method name="getPath" return="org.apache.hadoop.fs.Path" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="i" type="int"/> + <doc> + <![CDATA[Returns the i<sup>th</sup> Path]]> + </doc> + </method> + <method name="getPaths" return="org.apache.hadoop.fs.Path[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns all the Paths in the split]]> + </doc> + </method> + <method name="getLocations" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[A sub-collection of input files. Unlike {@link FileSplit}, MultiFileSplit + class does not represent a split of a file, but a split of input files + into smaller sets. The atomic unit of split is a file. <br> + MultiFileSplit can be used to implement {@link RecordReader}'s, with + reading one record per file. + @see FileSplit + @see MultiFileInputFormat]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.MultiFileSplit --> + <!-- start interface org.apache.hadoop.mapred.OutputCollector --> + <interface name="OutputCollector" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="collect" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K"/> + <param name="value" type="V"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Adds a key/value pair to the output. + + @param key the key to collect. + @param value to value to collect. + @throws IOException]]> + </doc> + </method> + <doc> + <![CDATA[Collects the <code><key, value></code> pairs output by {@link Mapper}s + and {@link Reducer}s. + + <p><code>OutputCollector</code> is the generalization of the facility + provided by the Map-Reduce framework to collect data output by either the + <code>Mapper</code> or the <code>Reducer</code> i.e. intermediate outputs + or the output of the job.</p>]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.mapred.OutputCollector --> + <!-- start interface org.apache.hadoop.mapred.OutputFormat --> + <interface name="OutputFormat" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="getRecordWriter" return="org.apache.hadoop.mapred.RecordWriter<K, V>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="name" type="java.lang.String"/> + <param name="progress" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get the {@link RecordWriter} for the given job. + + @param ignored + @param job configuration for the job whose output is being written. + @param name the unique name for this part of the output. + @param progress mechanism for reporting progress while writing to file. + @return a {@link RecordWriter} to write the output for the job. + @throws IOException]]> + </doc> + </method> + <method name="checkOutputSpecs" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Check for validity of the output-specification for the job. + + <p>This is to validate the output specification for the job when it is + a job is submitted. Typically checks that it does not already exist, + throwing an exception when it already exists, so that output is not + overwritten.</p> + + @param ignored + @param job job configuration. + @throws IOException when output should not be attempted]]> + </doc> + </method> + <doc> + <![CDATA[<code>OutputFormat</code> describes the output-specification for a + Map-Reduce job. + + <p>The Map-Reduce framework relies on the <code>OutputFormat</code> of the + job to:<p> + <ol> + <li> + Validate the output-specification of the job. For e.g. check that the + output directory doesn't already exist. + <li> + Provide the {@link RecordWriter} implementation to be used to write out + the output files of the job. Output files are stored in a + {@link FileSystem}. + </li> + </ol> + + @see RecordWriter + @see JobConf]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.mapred.OutputFormat --> + <!-- start class org.apache.hadoop.mapred.OutputFormatBase --> + <class name="OutputFormatBase" extends="java.lang.Object" + abstract="true" + static="false" final="false" visibility="public" + deprecated="Use {@link FileOutputFormat}"> + <implements name="org.apache.hadoop.mapred.OutputFormat<K, V>"/> + <constructor name="OutputFormatBase" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="setCompressOutput" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <param name="compress" type="boolean"/> + <doc> + <![CDATA[Set whether the output of the job is compressed. + @param conf the {@link JobConf} to modify + @param compress should the output of the job be compressed?]]> + </doc> + </method> + <method name="getCompressOutput" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <doc> + <![CDATA[Is the job output compressed? + @param conf the {@link JobConf} to look in + @return <code>true</code> if the job output should be compressed, + <code>false</code> otherwise]]> + </doc> + </method> + <method name="setOutputCompressorClass" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <param name="codecClass" type="java.lang.Class<? extends org.apache.hadoop.io.compress.CompressionCodec>"/> + <doc> + <![CDATA[Set the {@link CompressionCodec} to be used to compress job outputs. + @param conf the {@link JobConf} to modify + @param codecClass the {@link CompressionCodec} to be used to + compress the job outputs]]> + </doc> + </method> + <method name="getOutputCompressorClass" return="java.lang.Class<? extends org.apache.hadoop.io.compress.CompressionCodec>" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <param name="defaultValue" type="java.lang.Class<? extends org.apache.hadoop.io.compress.CompressionCodec>"/> + <doc> + <![CDATA[Get the {@link CompressionCodec} for compressing the job outputs. + @param conf the {@link JobConf} to look in + @param defaultValue the {@link CompressionCodec} to return if not set + @return the {@link CompressionCodec} to be used to compress the + job outputs + @throws IllegalArgumentException if the class was specified, but not found]]> + </doc> + </method> + <method name="getRecordWriter" return="org.apache.hadoop.mapred.RecordWriter<K, V>" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="name" type="java.lang.String"/> + <param name="progress" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="checkOutputSpecs" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <exception name="FileAlreadyExistsException" type="org.apache.hadoop.mapred.FileAlreadyExistsException"/> + <exception name="InvalidJobConfException" type="org.apache.hadoop.mapred.InvalidJobConfException"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[A base class for {@link OutputFormat}. + @deprecated Use {@link FileOutputFormat}]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.OutputFormatBase --> + <!-- start class org.apache.hadoop.mapred.OutputLogFilter --> + <class name="OutputLogFilter" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.fs.PathFilter"/> + <constructor name="OutputLogFilter" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="accept" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="org.apache.hadoop.fs.Path"/> + </method> + <doc> + <![CDATA[This class filters log files from directory given + It doesnt accept paths having _logs. + This can be used to list paths of output directory as follows: + Path[] fileList = FileUtil.stat2Paths(fs.listStatus(outDir, + new OutputLogFilter()));]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.OutputLogFilter --> + <!-- start interface org.apache.hadoop.mapred.Partitioner --> + <interface name="Partitioner" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.JobConfigurable"/> + <method name="getPartition" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K2"/> + <param name="value" type="V2"/> + <param name="numPartitions" type="int"/> + <doc> + <![CDATA[Get the paritition number for a given key (hence record) given the total + number of partitions i.e. number of reduce-tasks for the job. + + <p>Typically a hash function on a all or a subset of the key.</p> + + @param key the key to be paritioned. + @param value the entry value. + @param numPartitions the total number of partitions. + @return the partition number for the <code>key</code>.]]> + </doc> + </method> + <doc> + <![CDATA[Partitions the key space. + + <p><code>Partitioner</code> controls the partitioning of the keys of the + intermediate map-outputs. The key (or a subset of the key) is used to derive + the partition, typically by a hash function. The total number of partitions + is the same as the number of reduce tasks for the job. Hence this controls + which of the <code>m</code> reduce tasks the intermediate key (and hence the + record) is sent for reduction.</p> + + @see Reducer]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.mapred.Partitioner --> + <!-- start interface org.apache.hadoop.mapred.RecordReader --> + <interface name="RecordReader" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="next" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K"/> + <param name="value" type="V"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Reads the next key/value pair from the input for processing. + + @param key the key to read data into + @param value the value to read data into + @return true iff a key/value was read, false if at EOF]]> + </doc> + </method> + <method name="createKey" return="K" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Create an object of the appropriate type to be used as a key. + + @return a new key object.]]> + </doc> + </method> + <method name="createValue" return="V" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Create an object of the appropriate type to be used as a value. + + @return a new value object.]]> + </doc> + </method> + <method name="getPos" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns the current position in the input. + + @return the current position in the input. + @throws IOException]]> + </doc> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Close this {@link InputSplit} to future operations. + + @throws IOException]]> + </doc> + </method> + <method name="getProgress" return="float" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[How much of the input has the {@link RecordReader} consumed i.e. + has been processed by? + + @return progress from <code>0.0</code> to <code>1.0</code>. + @throws IOException]]> + </doc> + </method> + <doc> + <![CDATA[<code>RecordReader</code> reads <key, value> pairs from an + {@link InputSplit}. + + <p><code>RecordReader</code>, typically, converts the byte-oriented view of + the input, provided by the <code>InputSplit</code>, and presents a + record-oriented view for the {@link Mapper} & {@link Reducer} tasks for + processing. It thus assumes the responsibility of processing record + boundaries and presenting the tasks with keys and values.</p> + + @see InputSplit + @see InputFormat]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.mapred.RecordReader --> + <!-- start interface org.apache.hadoop.mapred.RecordWriter --> + <interface name="RecordWriter" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K"/> + <param name="value" type="V"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Writes a key/value pair. + + @param key the key to write. + @param value the value to write. + @throws IOException]]> + </doc> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Close this <code>RecordWriter</code> to future operations. + + @param reporter facility to report progress. + @throws IOException]]> + </doc> + </method> + <doc> + <![CDATA[<code>RecordWriter</code> writes the output <key, value> pairs + to an output file. + + <p><code>RecordWriter</code> implementations write the job outputs to the + {@link FileSystem}. + + @see OutputFormat]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.mapred.RecordWriter --> + <!-- start interface org.apache.hadoop.mapred.Reducer --> + <interface name="Reducer" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.JobConfigurable"/> + <implements name="org.apache.hadoop.io.Closeable"/> + <method name="reduce" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K2"/> + <param name="values" type="java.util.Iterator<V2>"/> + <param name="output" type="org.apache.hadoop.mapred.OutputCollector<K3, V3>"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[<i>Reduces</i> values for a given key. + + <p>The framework calls this method for each + <code><key, (list of values)></code> pair in the grouped inputs. + Output values must be of the same type as input values. Input keys must + not be altered. Typically all values are combined into zero or one value. + </p> + + <p>Output pairs are collected with calls to + {@link OutputCollector#collect(Object,Object)}.</p> + + <p>Applications can use the {@link Reporter} provided to report progress + or just indicate that they are alive. In scenarios where the application + takes an insignificant amount of time to process individual key/value + pairs, this is crucial since the framework might assume that the task has + timed-out and kill that task. The other way of avoiding this is to set + <a href="{@docRoot}/../hadoop-default.html#mapred.task.timeout"> + mapred.task.timeout</a> to a high-enough value (or even zero for no + time-outs).</p> + + @param key the key. + @param values the list of values to reduce. + @param output to collect keys and combined values. + @param reporter facility to report progress.]]> + </doc> + </method> + <doc> + <![CDATA[Reduces a set of intermediate values which share a key to a smaller set of + values. + + <p>The number of <code>Reducer</code>s for the job is set by the user via + {@link JobConf#setNumReduceTasks(int)}. <code>Reducer</code> implementations + can access the {@link JobConf} for the job via the + {@link JobConfigurable#configure(JobConf)} method and initialize themselves. + Similarly they can use the {@link Closeable#close()} method for + de-initialization.</p> + + <p><code>Reducer</code> has 3 primary phases:</p> + <ol> + <li> + + <h4 id="Shuffle">Shuffle</h4> + + <p><code>Reducer</code> is input the grouped output of a {@link Mapper}. + In the phase the framework, for each <code>Reducer</code>, fetches the + relevant partition of the output of all the <code>Mapper</code>s, via HTTP. + </p> + </li> + + <li> + <h4 id="Sort">Sort</h4> + + <p>The framework groups <code>Reducer</code> inputs by <code>key</code>s + (since different <code>Mapper</code>s may have output the same key) in this + stage.</p> + + <p>The shuffle and sort phases occur simultaneously i.e. while outputs are + being fetched they are merged.</p> + + <h5 id="SecondarySort">SecondarySort</h5> + + <p>If equivalence rules for keys while grouping the intermediates are + different from those for grouping keys before reduction, then one may + specify a <code>Comparator</code> via + {@link JobConf#setOutputValueGroupingComparator(Class)}.Since + {@link JobConf#setOutputKeyComparatorClass(Class)} can be used to + control how intermediate keys are grouped, these can be used in conjunction + to simulate <i>secondary sort on values</i>.</p> + + + For example, say that you want to find duplicate web pages and tag them + all with the url of the "best" known example. You would set up the job + like: + <ul> + <li>Map Input Key: url</li> + <li>Map Input Value: document</li> + <li>Map Output Key: document checksum, url pagerank</li> + <li>Map Output Value: url</li> + <li>Partitioner: by checksum</li> + <li>OutputKeyComparator: by checksum and then decreasing pagerank</li> + <li>OutputValueGroupingComparator: by checksum</li> + </ul> + </li> + + <li> + <h4 id="Reduce">Reduce</h4> + + <p>In this phase the + {@link #reduce(Object, Iterator, OutputCollector, Reporter)} + method is called for each <code><key, (list of values)></code> pair in + the grouped inputs.</p> + <p>The output of the reduce task is typically written to the + {@link FileSystem} via + {@link OutputCollector#collect(Object, Object)}.</p> + </li> + </ol> + + <p>The output of the <code>Reducer</code> is <b>not re-sorted</b>.</p> + + <p>Example:</p> + <p><blockquote><pre> + public class MyReducer<K extends WritableComparable, V extends Writable> + extends MapReduceBase implements Reducer<K, V, K, V> { + + static enum MyCounters { NUM_RECORDS } + + private String reduceTaskId; + private int noKeys = 0; + + public void configure(JobConf job) { + reduceTaskId = job.get("mapred.task.id"); + } + + public void reduce(K key, Iterator<V> values, + OutputCollector<K, V> output, + Reporter reporter) + throws IOException { + + // Process + int noValues = 0; + while (values.hasNext()) { + V value = values.next(); + + // Increment the no. of values for this key + ++noValues; + + // Process the <key, value> pair (assume this takes a while) + // ... + // ... + + // Let the framework know that we are alive, and kicking! + if ((noValues%10) == 0) { + reporter.progress(); + } + + // Process some more + // ... + // ... + + // Output the <key, value> + output.collect(key, value); + } + + // Increment the no. of <key, list of values> pairs processed + ++noKeys; + + // Increment counters + reporter.incrCounter(NUM_RECORDS, 1); + + // Every 100 keys update application-level status + if ((noKeys%100) == 0) { + reporter.setStatus(reduceTaskId + " processed " + noKeys); + } + } + } + </pre></blockquote></p> + + @see Mapper + @see Partitioner + @see Reporter + @see MapReduceBase]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.mapred.Reducer --> + <!-- start class org.apache.hadoop.mapred.ReduceTaskStatus --> + <class name="ReduceTaskStatus" extends="org.apache.hadoop.mapred.TaskStatus" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="ReduceTaskStatus" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="ReduceTaskStatus" type="java.lang.String, float, org.apache.hadoop.mapred.TaskStatus.State, java.lang.String, java.lang.String, java.lang.String, org.apache.hadoop.mapred.TaskStatus.Phase, org.apache.hadoop.mapred.Counters" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="clone" return="java.lang.Object" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getIsMap" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getShuffleFinishTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getSortFinishTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getFetchFailedMaps" return="java.util.List<java.lang.String>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + </class> + <!-- end class org.apache.hadoop.mapred.ReduceTaskStatus --> + <!-- start interface org.apache.hadoop.mapred.Reporter --> + <interface name="Reporter" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.util.Progressable"/> + <method name="setStatus" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="status" type="java.lang.String"/> + <doc> + <![CDATA[Set the status description for the task. + + @param status brief description of the current status.]]> + </doc> + </method> + <method name="incrCounter" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="java.lang.Enum"/> + <param name="amount" type="long"/> + <doc> + <![CDATA[Increments the counter identified by the key, which can be of + any {@link Enum} type, by the specified amount. + + @param key key to identify the counter to be incremented. The key can be + be any <code>Enum</code>. + @param amount A non-negative amount by which the counter is to + be incremented.]]> + </doc> + </method> + <method name="getInputSplit" return="org.apache.hadoop.mapred.InputSplit" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="UnsupportedOperationException" type="java.lang.UnsupportedOperationException"/> + <doc> + <![CDATA[Get the {@link InputSplit} object for a map. + + @return the <code>InputSplit</code> that the map is reading from. + @throws UnsupportedOperationException if called outside a mapper]]> + </doc> + </method> + <field name="NULL" type="org.apache.hadoop.mapred.Reporter" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[A constant of Reporter type that does nothing.]]> + </doc> + </field> + <doc> + <![CDATA[A facility for Map-Reduce applications to report progress and update + counters, status information etc. + + <p>{@link Mapper} and {@link Reducer} can use the <code>Reporter</code> + provided to report progress or just indicate that they are alive. In + scenarios where the application takes an insignificant amount of time to + process individual key/value pairs, this is crucial since the framework + might assume that the task has timed-out and kill that task. + + <p>Applications can also update {@link Counters} via the provided + <code>Reporter</code> .</p> + + @see Progressable + @see Counters]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.mapred.Reporter --> + <!-- start interface org.apache.hadoop.mapred.RunningJob --> + <interface name="RunningJob" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="getJobID" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the job identifier. + + @return the job identifier.]]> + </doc> + </method> + <method name="getJobName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the name of the job. + + @return the name of the job.]]> + </doc> + </method> + <method name="getJobFile" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the path of the submitted job configuration. + + @return the path of the submitted job configuration.]]> + </doc> + </method> + <method name="getTrackingURL" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the URL where some job progress information will be displayed. + + @return the URL where some job progress information will be displayed.]]> + </doc> + </method> + <method name="mapProgress" return="float" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get the <i>progress</i> of the job's map-tasks, as a float between 0.0 + and 1.0. When all map tasks have completed, the function returns 1.0. + + @return the progress of the job's map-tasks. + @throws IOException]]> + </doc> + </method> + <method name="reduceProgress" return="float" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get the <i>progress</i> of the job's reduce-tasks, as a float between 0.0 + and 1.0. When all reduce tasks have completed, the function returns 1.0. + + @return the progress of the job's reduce-tasks. + @throws IOException]]> + </doc> + </method> + <method name="isComplete" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Check if the job is finished or not. + This is a non-blocking call. + + @return <code>true</code> if the job is complete, else <code>false</code>. + @throws IOException]]> + </doc> + </method> + <method name="isSuccessful" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Check if the job completed successfully. + + @return <code>true</code> if the job succeeded, else <code>false</code>. + @throws IOException]]> + </doc> + </method> + <method name="waitForCompletion" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Blocks until the job is complete. + + @throws IOException]]> + </doc> + </method> + <method name="killJob" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Kill the running job. Blocks until all job tasks have been + killed as well. If the job is no longer running, it simply returns. + + @throws IOException]]> + </doc> + </method> + <method name="getTaskCompletionEvents" return="org.apache.hadoop.mapred.TaskCompletionEvent[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="startFrom" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get events indicating completion (success/failure) of component tasks. + + @param startFrom index to start fetching events from + @return an array of {@link TaskCompletionEvent}s + @throws IOException]]> + </doc> + </method> + <method name="killTask" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="taskId" type="java.lang.String"/> + <param name="shouldFail" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Kill indicated task attempt. + + @param taskId the id of the task to be terminated. + @param shouldFail if true the task is failed and added to failed tasks + list, otherwise it is just killed, w/o affecting + job failure status. + @throws IOException]]> + </doc> + </method> + <method name="getCounters" return="org.apache.hadoop.mapred.Counters" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Gets the counters for this job. + + @return the counters for this job. + @throws IOException]]> + </doc> + </method> + <doc> + <![CDATA[<code>RunningJob</code> is the user-interface to query for details on a + running Map-Reduce job. + + <p>Clients can get hold of <code>RunningJob</code> via the {@link JobClient} + and then query the running-job for details such as name, configuration, + progress etc.</p> + + @see JobClient]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.mapred.RunningJob --> + <!-- start class org.apache.hadoop.mapred.SequenceFileAsBinaryInputFormat --> + <class name="SequenceFileAsBinaryInputFormat" extends="org.apache.hadoop.mapred.SequenceFileInputFormat<org.apache.hadoop.io.BytesWritable, org.apache.hadoop.io.BytesWritable>" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="SequenceFileAsBinaryInputFormat" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.BytesWritable, org.apache.hadoop.io.BytesWritable>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="split" type="org.apache.hadoop.mapred.InputSplit"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[InputFormat reading keys, values from SequenceFiles in binary (raw) + format.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.SequenceFileAsBinaryInputFormat --> + <!-- start class org.apache.hadoop.mapred.SequenceFileAsBinaryInputFormat.SequenceFileAsBinaryRecordReader --> + <class name="SequenceFileAsBinaryInputFormat.SequenceFileAsBinaryRecordReader" extends="java.lang.Object" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.BytesWritable, org.apache.hadoop.io.BytesWritable>"/> + <constructor name="SequenceFileAsBinaryInputFormat.SequenceFileAsBinaryRecordReader" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.mapred.FileSplit" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </constructor> + <method name="createKey" return="org.apache.hadoop.io.BytesWritable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="createValue" return="org.apache.hadoop.io.BytesWritable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getKeyClassName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Retrieve the name of the key class for this SequenceFile. + @see org.apache.hadoop.io.SequenceFile.Reader#getKeyClassName]]> + </doc> + </method> + <method name="getValueClassName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Retrieve the name of the value class for this SequenceFile. + @see org.apache.hadoop.io.SequenceFile.Reader#getValueClassName]]> + </doc> + </method> + <method name="next" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.BytesWritable"/> + <param name="val" type="org.apache.hadoop.io.BytesWritable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read raw bytes from a SequenceFile.]]> + </doc> + </method> + <method name="getPos" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getProgress" return="float" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return the progress within the input split + @return 0.0 to 1.0 of the input byte range]]> + </doc> + </method> + <doc> + <![CDATA[Read records from a SequenceFile as binary (raw) bytes.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.SequenceFileAsBinaryInputFormat.SequenceFileAsBinaryRecordReader --> + <!-- start class org.apache.hadoop.mapred.SequenceFileAsTextInputFormat --> + <class name="SequenceFileAsTextInputFormat" extends="org.apache.hadoop.mapred.SequenceFileInputFormat<org.apache.hadoop.io.Text, org.apache.hadoop.io.Text>" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="SequenceFileAsTextInputFormat" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.Text, org.apache.hadoop.io.Text>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="split" type="org.apache.hadoop.mapred.InputSplit"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[This class is similar to SequenceFileInputFormat, except it generates SequenceFileAsTextRecordReader + which converts the input keys and values to their String forms by calling toString() method.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.SequenceFileAsTextInputFormat --> + <!-- start class org.apache.hadoop.mapred.SequenceFileAsTextRecordReader --> + <class name="SequenceFileAsTextRecordReader" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.Text, org.apache.hadoop.io.Text>"/> + <constructor name="SequenceFileAsTextRecordReader" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.mapred.FileSplit" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </constructor> + <method name="createKey" return="org.apache.hadoop.io.Text" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="createValue" return="org.apache.hadoop.io.Text" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="next" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.Text"/> + <param name="value" type="org.apache.hadoop.io.Text"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read key/value pair in a line.]]> + </doc> + </method> + <method name="getProgress" return="float" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getPos" return="long" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="close" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[This class converts the input keys and values to their String forms by calling toString() + method. This class to SequenceFileAsTextInputFormat class is as LineRecordReader + class to TextInputFormat class.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.SequenceFileAsTextRecordReader --> + <!-- start class org.apache.hadoop.mapred.SequenceFileInputFilter --> + <class name="SequenceFileInputFilter" extends="org.apache.hadoop.mapred.SequenceFileInputFormat<K, V>" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="SequenceFileInputFilter" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader<K, V>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="split" type="org.apache.hadoop.mapred.InputSplit"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create a record reader for the given split + @param split file split + @param job job configuration + @param reporter reporter who sends report to task tracker + @return RecordReader]]> + </doc> + </method> + <method name="setFilterClass" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="filterClass" type="java.lang.Class"/> + <doc> + <![CDATA[set the filter class + + @param conf application configuration + @param filterClass filter class]]> + </doc> + </method> + <doc> + <![CDATA[A class that allows a map/red job to work on a sample of sequence files. + The sample is decided by the filter class set by the job.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.SequenceFileInputFilter --> + <!-- start interface org.apache.hadoop.mapred.SequenceFileInputFilter.Filter --> + <interface name="SequenceFileInputFilter.Filter" abstract="true" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.conf.Configurable"/> + <method name="accept" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.Writable"/> + <doc> + <![CDATA[filter function + Decide if a record should be filtered or not + @param key record key + @return true if a record is accepted; return false otherwise]]> + </doc> + </method> + <doc> + <![CDATA[filter interface]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.mapred.SequenceFileInputFilter.Filter --> + <!-- start class org.apache.hadoop.mapred.SequenceFileInputFilter.FilterBase --> + <class name="SequenceFileInputFilter.FilterBase" extends="java.lang.Object" + abstract="true" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.SequenceFileInputFilter.Filter"/> + <constructor name="SequenceFileInputFilter.FilterBase" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getConf" return="org.apache.hadoop.conf.Configuration" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[base calss for Filters]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.SequenceFileInputFilter.FilterBase --> + <!-- start class org.apache.hadoop.mapred.SequenceFileInputFilter.MD5Filter --> + <class name="SequenceFileInputFilter.MD5Filter" extends="org.apache.hadoop.mapred.SequenceFileInputFilter.FilterBase" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="SequenceFileInputFilter.MD5Filter" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="setFrequency" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="frequency" type="int"/> + <doc> + <![CDATA[set the filtering frequency in configuration + + @param conf configuration + @param frequency filtering frequency]]> + </doc> + </method> + <method name="setConf" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[configure the filter according to configuration + + @param conf configuration]]> + </doc> + </method> + <method name="accept" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.Writable"/> + <doc> + <![CDATA[Filtering method + If MD5(key) % frequency==0, return true; otherwise return false + @see org.apache.hadoop.mapred.SequenceFileInputFilter.Filter#accept(org.apache.hadoop.io.Writable)]]> + </doc> + </method> + <field name="MD5_LEN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[This class returns a set of records by examing the MD5 digest of its + key against a filtering frequency <i>f</i>. The filtering criteria is + MD5(key) % f == 0.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.SequenceFileInputFilter.MD5Filter --> + <!-- start class org.apache.hadoop.mapred.SequenceFileInputFilter.PercentFilter --> + <class name="SequenceFileInputFilter.PercentFilter" extends="org.apache.hadoop.mapred.SequenceFileInputFilter.FilterBase" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="SequenceFileInputFilter.PercentFilter" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="setFrequency" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="frequency" type="int"/> + <doc> + <![CDATA[set the frequency and stores it in conf + @param conf configuration + @param frequency filtering frequencey]]> + </doc> + </method> + <method name="setConf" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[configure the filter by checking the configuration + + @param conf configuration]]> + </doc> + </method> + <method name="accept" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.Writable"/> + <doc> + <![CDATA[Filtering method + If record# % frequency==0, return true; otherwise return false + @see org.apache.hadoop.mapred.SequenceFileInputFilter.Filter#accept(org.apache.hadoop.io.Writable)]]> + </doc> + </method> + <doc> + <![CDATA[This class returns a percentage of records + The percentage is determined by a filtering frequency <i>f</i> using + the criteria record# % f == 0. + For example, if the frequency is 10, one out of 10 records is returned.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.SequenceFileInputFilter.PercentFilter --> + <!-- start class org.apache.hadoop.mapred.SequenceFileInputFilter.RegexFilter --> + <class name="SequenceFileInputFilter.RegexFilter" extends="org.apache.hadoop.mapred.SequenceFileInputFilter.FilterBase" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="SequenceFileInputFilter.RegexFilter" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="setPattern" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="regex" type="java.lang.String"/> + <exception name="PatternSyntaxException" type="java.util.regex.PatternSyntaxException"/> + <doc> + <![CDATA[Define the filtering regex and stores it in conf + @param conf where the regex is set + @param regex regex used as a filter]]> + </doc> + </method> + <method name="setConf" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[configure the Filter by checking the configuration]]> + </doc> + </method> + <method name="accept" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.Writable"/> + <doc> + <![CDATA[Filtering method + If key matches the regex, return true; otherwise return false + @see org.apache.hadoop.mapred.SequenceFileInputFilter.Filter#accept(org.apache.hadoop.io.Writable)]]> + </doc> + </method> + <doc> + <![CDATA[Records filter by matching key to regex]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.SequenceFileInputFilter.RegexFilter --> + <!-- start class org.apache.hadoop.mapred.SequenceFileInputFormat --> + <class name="SequenceFileInputFormat" extends="org.apache.hadoop.mapred.FileInputFormat<K, V>" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="SequenceFileInputFormat" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="listPaths" return="org.apache.hadoop.fs.Path[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader<K, V>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="split" type="org.apache.hadoop.mapred.InputSplit"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[An {@link InputFormat} for {@link SequenceFile}s.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.SequenceFileInputFormat --> + <!-- start class org.apache.hadoop.mapred.SequenceFileOutputFormat --> + <class name="SequenceFileOutputFormat" extends="org.apache.hadoop.mapred.FileOutputFormat<org.apache.hadoop.io.WritableComparable, org.apache.hadoop.io.Writable>" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="SequenceFileOutputFormat" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getRecordWriter" return="org.apache.hadoop.mapred.RecordWriter<org.apache.hadoop.io.WritableComparable, org.apache.hadoop.io.Writable>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="name" type="java.lang.String"/> + <param name="progress" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getReaders" return="org.apache.hadoop.io.SequenceFile.Reader[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="dir" type="org.apache.hadoop.fs.Path"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Open the output generated by this format.]]> + </doc> + </method> + <method name="getOutputCompressionType" return="org.apache.hadoop.io.SequenceFile.CompressionType" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <doc> + <![CDATA[Get the {@link CompressionType} for the output {@link SequenceFile}. + @param conf the {@link JobConf} + @return the {@link CompressionType} for the output {@link SequenceFile}, + defaulting to {@link CompressionType#RECORD}]]> + </doc> + </method> + <method name="setOutputCompressionType" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <param name="style" type="org.apache.hadoop.io.SequenceFile.CompressionType"/> + <doc> + <![CDATA[Set the {@link CompressionType} for the output {@link SequenceFile}. + @param conf the {@link JobConf} to modify + @param style the {@link CompressionType} for the output + {@link SequenceFile}]]> + </doc> + </method> + <doc> + <![CDATA[An {@link OutputFormat} that writes {@link SequenceFile}s.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.SequenceFileOutputFormat --> + <!-- start class org.apache.hadoop.mapred.SequenceFileRecordReader --> + <class name="SequenceFileRecordReader" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.RecordReader<K, V>"/> + <constructor name="SequenceFileRecordReader" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.mapred.FileSplit" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </constructor> + <method name="getKeyClass" return="java.lang.Class" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The class of key that must be passed to {@link + #next(WritableComparable,Writable)}..]]> + </doc> + </method> + <method name="getValueClass" return="java.lang.Class" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The class of value that must be passed to {@link + #next(WritableComparable,Writable)}..]]> + </doc> + </method> + <method name="createKey" return="K extends org.apache.hadoop.io.WritableComparable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="createValue" return="V extends org.apache.hadoop.io.Writable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="next" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K extends org.apache.hadoop.io.WritableComparable"/> + <param name="value" type="V extends org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="next" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="key" type="K extends org.apache.hadoop.io.WritableComparable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getCurrentValue" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="value" type="V extends org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getProgress" return="float" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return the progress within the input split + @return 0.0 to 1.0 of the input byte range]]> + </doc> + </method> + <method name="getPos" return="long" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="seek" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="pos" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="close" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <field name="conf" type="org.apache.hadoop.conf.Configuration" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[An {@link RecordReader} for {@link SequenceFile}s.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.SequenceFileRecordReader --> + <!-- start class org.apache.hadoop.mapred.StatusHttpServer --> + <class name="StatusHttpServer" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="StatusHttpServer" type="java.lang.String, java.lang.String, int, boolean" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create a status server on the given port. + The jsp scripts are taken from src/webapps/<name>. + @param name The name of the server + @param port The port to use on the server + @param findPort whether the server should start at the given port and + increment by 1 until it finds a free port.]]> + </doc> + </constructor> + <method name="setAttribute" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <param name="value" type="java.lang.Object"/> + <doc> + <![CDATA[Set a value in the webapp context. These values are available to the jsp + pages as "application.getAttribute(name)". + @param name The name of the attribute + @param value The value of the attribute]]> + </doc> + </method> + <method name="addServlet" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <param name="pathSpec" type="java.lang.String"/> + <param name="servletClass" type="java.lang.Class<T>"/> + <doc> + <![CDATA[Add a servlet in the server. + @param name The name of the servlet (can be passed as null) + @param pathSpec The path spec for the servlet + @param servletClass The servlet class]]> + </doc> + </method> + <method name="getAttribute" return="java.lang.Object" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <doc> + <![CDATA[Get the value in the webapp context. + @param name The name of the attribute + @return The value of the attribute]]> + </doc> + </method> + <method name="getPort" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the port that the server is on + @return the port]]> + </doc> + </method> + <method name="setThreads" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="min" type="int"/> + <param name="max" type="int"/> + </method> + <method name="addSslListener" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="addr" type="java.net.InetSocketAddress"/> + <param name="keystore" type="java.lang.String"/> + <param name="storPass" type="java.lang.String"/> + <param name="keyPass" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Configure an ssl listener on the server. + @param addr address to listen on + @param keystore location of the keystore + @param storPass password for the keystore + @param keyPass password for the key]]> + </doc> + </method> + <method name="start" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Start the server. Does not wait for the server to start.]]> + </doc> + </method> + <method name="stop" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="InterruptedException" type="java.lang.InterruptedException"/> + <doc> + <![CDATA[stop the server]]> + </doc> + </method> + <doc> + <![CDATA[Create a Jetty embedded server to answer http requests. The primary goal + is to serve up status information for the server. + There are three contexts: + "/logs/" -> points to the log directory + "/static/" -> points to common static files (src/webapps/static) + "/" -> the jsp server code from (src/webapps/<name>)]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.StatusHttpServer --> + <!-- start class org.apache.hadoop.mapred.StatusHttpServer.StackServlet --> + <class name="StatusHttpServer.StackServlet" extends="javax.servlet.http.HttpServlet" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="StatusHttpServer.StackServlet" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="doGet" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="request" type="javax.servlet.http.HttpServletRequest"/> + <param name="response" type="javax.servlet.http.HttpServletResponse"/> + <exception name="ServletException" type="javax.servlet.ServletException"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[A very simple servlet to serve up a text representation of the current + stack traces. It both returns the stacks to the caller and logs them. + Currently the stack traces are done sequentially rather than exactly the + same data.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.StatusHttpServer.StackServlet --> + <!-- start class org.apache.hadoop.mapred.StatusHttpServer.TaskGraphServlet --> + <class name="StatusHttpServer.TaskGraphServlet" extends="javax.servlet.http.HttpServlet" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="StatusHttpServer.TaskGraphServlet" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="doGet" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="request" type="javax.servlet.http.HttpServletRequest"/> + <param name="response" type="javax.servlet.http.HttpServletResponse"/> + <exception name="ServletException" type="javax.servlet.ServletException"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <field name="width" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[height of the graph w/o margins]]> + </doc> + </field> + <field name="height" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[height of the graph w/o margins]]> + </doc> + </field> + <field name="ymargin" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[margin space on y axis]]> + </doc> + </field> + <field name="xmargin" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[margin space on x axis]]> + </doc> + </field> + <doc> + <![CDATA[The servlet that outputs svg graphics for map / reduce task + statuses]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.StatusHttpServer.TaskGraphServlet --> + <!-- start class org.apache.hadoop.mapred.TaskCompletionEvent --> + <class name="TaskCompletionEvent" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <constructor name="TaskCompletionEvent" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Default constructor for Writable.]]> + </doc> + </constructor> + <constructor name="TaskCompletionEvent" type="int, java.lang.String, int, boolean, org.apache.hadoop.mapred.TaskCompletionEvent.Status, java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Constructor. eventId should be created externally and incremented + per event for each job. + @param eventId event id, event id should be unique and assigned in + incrementally, starting from 0. + @param taskId task id + @param status task's status + @param taskTrackerHttp task tracker's host:port for http.]]> + </doc> + </constructor> + <method name="getEventId" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns event Id. + @return event id]]> + </doc> + </method> + <method name="getTaskId" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns task id. + @return task id]]> + </doc> + </method> + <method name="getTaskStatus" return="org.apache.hadoop.mapred.TaskCompletionEvent.Status" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns enum Status.SUCESS or Status.FAILURE. + @return task tracker status]]> + </doc> + </method> + <method name="getTaskTrackerHttp" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[http location of the tasktracker where this task ran. + @return http location of tasktracker user logs]]> + </doc> + </method> + <method name="getTaskRunTime" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns time (in millisec) the task took to complete.]]> + </doc> + </method> + <method name="setTaskRunTime" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="taskCompletionTime" type="int"/> + <doc> + <![CDATA[Set the task completion time + @param taskCompletionTime time (in millisec) the task took to complete]]> + </doc> + </method> + <method name="setEventId" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="eventId" type="int"/> + <doc> + <![CDATA[set event Id. should be assigned incrementally starting from 0. + @param eventId]]> + </doc> + </method> + <method name="setTaskId" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="taskId" type="java.lang.String"/> + <doc> + <![CDATA[Sets task id. + @param taskId]]> + </doc> + </method> + <method name="setTaskStatus" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="status" type="org.apache.hadoop.mapred.TaskCompletionEvent.Status"/> + <doc> + <![CDATA[Set task status. + @param status]]> + </doc> + </method> + <method name="setTaskTrackerHttp" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="taskTrackerHttp" type="java.lang.String"/> + <doc> + <![CDATA[Set task tracker http location. + @param taskTrackerHttp]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="isMapTask" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="idWithinJob" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <field name="EMPTY_ARRAY" type="org.apache.hadoop.mapred.TaskCompletionEvent[]" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[This is used to track task completion events on + job tracker.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.TaskCompletionEvent --> + <!-- start class org.apache.hadoop.mapred.TaskCompletionEvent.Status --> + <class name="TaskCompletionEvent.Status" extends="java.lang.Enum<org.apache.hadoop.mapred.TaskCompletionEvent.Status>" + abstract="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <method name="values" return="org.apache.hadoop.mapred.TaskCompletionEvent.Status[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="valueOf" return="org.apache.hadoop.mapred.TaskCompletionEvent.Status" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + </class> + <!-- end class org.apache.hadoop.mapred.TaskCompletionEvent.Status --> + <!-- start class org.apache.hadoop.mapred.TaskLog --> + <class name="TaskLog" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="TaskLog" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getTaskLogFile" return="java.io.File" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="taskid" type="java.lang.String"/> + <param name="filter" type="org.apache.hadoop.mapred.TaskLog.LogName"/> + </method> + <method name="cleanup" + abstract="false" native="false" synchronized="true" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="logsRetainHours" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Purge old user logs. + + @throws IOException]]> + </doc> + </method> + <method name="getTaskLogLength" return="long" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <doc> + <![CDATA[Get the desired maximum length of task's logs. + @param conf the job to look in + @return the number of bytes to cap the log files at]]> + </doc> + </method> + <method name="captureOutAndError" return="java.util.List<java.lang.String>" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="cmd" type="java.util.List<java.lang.String>"/> + <param name="stdoutFilename" type="java.io.File"/> + <param name="stderrFilename" type="java.io.File"/> + <param name="tailLength" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Wrap a command in a shell to capture stdout and stderr to files. + If the tailLength is 0, the entire output will be saved. + @param cmd The command and the arguments that should be run + @param stdoutFilename The filename that stdout should be saved to + @param stderrFilename The filename that stderr should be saved to + @param tailLength The length of the tail to be saved. + @return the modified command that should be run]]> + </doc> + </method> + <method name="captureOutAndError" return="java.util.List<java.lang.String>" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="setup" type="java.util.List<java.lang.String>"/> + <param name="cmd" type="java.util.List<java.lang.String>"/> + <param name="stdoutFilename" type="java.io.File"/> + <param name="stderrFilename" type="java.io.File"/> + <param name="tailLength" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Wrap a command in a shell to capture stdout and stderr to files. + Setup commands such as setting memory limit can be passed which + will be executed before exec. + If the tailLength is 0, the entire output will be saved. + @param setup The setup commands for the execed process. + @param cmd The command and the arguments that should be run + @param stdoutFilename The filename that stdout should be saved to + @param stderrFilename The filename that stderr should be saved to + @param tailLength The length of the tail to be saved. + @return the modified command that should be run]]> + </doc> + </method> + <method name="addCommand" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="cmd" type="java.util.List<java.lang.String>"/> + <param name="isExecutable" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Add quotes to each of the command strings and + return as a single string + @param cmd The command to be quoted + @param isExecutable makes shell path if the first + argument is executable + @return returns The quoted string. + @throws IOException]]> + </doc> + </method> + <method name="captureDebugOut" return="java.util.List<java.lang.String>" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="cmd" type="java.util.List<java.lang.String>"/> + <param name="debugoutFilename" type="java.io.File"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Wrap a command in a shell to capture debug script's + stdout and stderr to debugout. + @param cmd The command and the arguments that should be run + @param debugoutFilename The filename that stdout and stderr + should be saved to. + @return the modified command that should be run + @throws IOException]]> + </doc> + </method> + <doc> + <![CDATA[A simple logger to handle the task-specific user logs. + This class uses the system property <code>hadoop.log.dir</code>.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.TaskLog --> + <!-- start class org.apache.hadoop.mapred.TaskLog.LogName --> + <class name="TaskLog.LogName" extends="java.lang.Enum<org.apache.hadoop.mapred.TaskLog.LogName>" + abstract="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <method name="values" return="org.apache.hadoop.mapred.TaskLog.LogName[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="valueOf" return="org.apache.hadoop.mapred.TaskLog.LogName" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[The filter for userlogs.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.TaskLog.LogName --> + <!-- start class org.apache.hadoop.mapred.TaskLog.Reader --> + <class name="TaskLog.Reader" extends="java.io.InputStream" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="TaskLog.Reader" type="java.lang.String, org.apache.hadoop.mapred.TaskLog.LogName, long, long" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read a log file from start to end positions. The offsets may be negative, + in which case they are relative to the end of the file. For example, + Reader(taskid, kind, 0, -1) is the entire file and + Reader(taskid, kind, -4197, -1) is the last 4196 bytes. + @param taskid the id of the task to read the log file for + @param kind the kind of log to read + @param start the offset to read from (negative is relative to tail) + @param end the offset to read upto (negative is relative to tail) + @throws IOException]]> + </doc> + </constructor> + <method name="read" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="read" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="buffer" type="byte[]"/> + <param name="offset" type="int"/> + <param name="length" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="available" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + </class> + <!-- end class org.apache.hadoop.mapred.TaskLog.Reader --> + <!-- start class org.apache.hadoop.mapred.TaskLogAppender --> + <class name="TaskLogAppender" extends="org.apache.log4j.FileAppender" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="TaskLogAppender" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="activateOptions" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="append" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="event" type="org.apache.log4j.spi.LoggingEvent"/> + </method> + <method name="close" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getTaskId" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Getter/Setter methods for log4j.]]> + </doc> + </method> + <method name="setTaskId" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="taskId" type="java.lang.String"/> + </method> + <method name="getTotalLogFileSize" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="setTotalLogFileSize" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="logSize" type="long"/> + </method> + <doc> + <![CDATA[A simple log4j-appender for the task child's + map-reduce system logs.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.TaskLogAppender --> + <!-- start class org.apache.hadoop.mapred.TaskLogServlet --> + <class name="TaskLogServlet" extends="javax.servlet.http.HttpServlet" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="TaskLogServlet" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="doGet" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="request" type="javax.servlet.http.HttpServletRequest"/> + <param name="response" type="javax.servlet.http.HttpServletResponse"/> + <exception name="ServletException" type="javax.servlet.ServletException"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get the logs via http.]]> + </doc> + </method> + <doc> + <![CDATA[A servlet that is run by the TaskTrackers to provide the task logs via http.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.TaskLogServlet --> + <!-- start class org.apache.hadoop.mapred.TaskReport --> + <class name="TaskReport" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <constructor name="TaskReport" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getTaskId" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The id of the task.]]> + </doc> + </method> + <method name="getProgress" return="float" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The amount completed, between zero and one.]]> + </doc> + </method> + <method name="getState" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The most recent state, reported by a {@link Reporter}.]]> + </doc> + </method> + <method name="getDiagnostics" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[A list of error messages.]]> + </doc> + </method> + <method name="getCounters" return="org.apache.hadoop.mapred.Counters" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[A table of counters.]]> + </doc> + </method> + <method name="getFinishTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get finish time of task. + @return 0, if finish time was not set else returns finish time.]]> + </doc> + </method> + <method name="getStartTime" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get start time of task. + @return 0 if start time was not set, else start time.]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[A report on the state of a task.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.TaskReport --> + <!-- start class org.apache.hadoop.mapred.TaskTracker --> + <class name="TaskTracker" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.MRConstants"/> + <implements name="org.apache.hadoop.mapred.TaskUmbilicalProtocol"/> + <implements name="java.lang.Runnable"/> + <constructor name="TaskTracker" type="org.apache.hadoop.mapred.JobConf" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Start with the local machine name, and the default JobTracker]]> + </doc> + </constructor> + <method name="getTaskTrackerMetrics" return="org.apache.hadoop.mapred.TaskTracker.TaskTrackerMetrics" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getProtocolVersion" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="protocol" type="java.lang.String"/> + <param name="clientVersion" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="cleanupStorage" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Removes all contents of temporary storage. Called upon + startup, to remove any leftovers from previous run.]]> + </doc> + </method> + <method name="shutdown" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="close" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Close down the TaskTracker and all its components. We must also shutdown + any running tasks or threads, and cleanup disk space. A new TaskTracker + within the same process space might be restarted, so everything must be + clean.]]> + </doc> + </method> + <method name="getJobClient" return="org.apache.hadoop.mapred.InterTrackerProtocol" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The connection to the JobTracker, used by the TaskRunner + for locating remote files.]]> + </doc> + </method> + <method name="getTaskTrackerReportAddress" return="java.net.InetSocketAddress" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the port at which the tasktracker bound to]]> + </doc> + </method> + <method name="run" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The server retry loop. + This while-loop attempts to connect to the JobTracker. It only + loops when the old TaskTracker has gone bad (its state is + stale somehow) and we need to reinitialize everything.]]> + </doc> + </method> + <method name="getTask" return="org.apache.hadoop.mapred.Task" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="taskid" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Called upon startup by the child process, to fetch Task data.]]> + </doc> + </method> + <method name="statusUpdate" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="taskid" type="java.lang.String"/> + <param name="taskStatus" type="org.apache.hadoop.mapred.TaskStatus"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Called periodically to report Task progress, from 0.0 to 1.0.]]> + </doc> + </method> + <method name="reportDiagnosticInfo" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="taskid" type="java.lang.String"/> + <param name="info" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Called when the task dies before completion, and we want to report back + diagnostic info]]> + </doc> + </method> + <method name="ping" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="taskid" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Child checking to see if we're alive. Normally does nothing.]]> + </doc> + </method> + <method name="done" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="taskid" type="java.lang.String"/> + <param name="shouldPromote" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[The task is done.]]> + </doc> + </method> + <method name="shuffleError" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="taskId" type="java.lang.String"/> + <param name="message" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[A reduce-task failed to shuffle the map-outputs. Kill the task.]]> + </doc> + </method> + <method name="fsError" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="taskId" type="java.lang.String"/> + <param name="message" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[A child task had a local filesystem error. Kill the task.]]> + </doc> + </method> + <method name="getMapCompletionEvents" return="org.apache.hadoop.mapred.TaskCompletionEvent[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobId" type="java.lang.String"/> + <param name="fromEventId" type="int"/> + <param name="maxLocs" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="mapOutputLost" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="taskid" type="java.lang.String"/> + <param name="errorMsg" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[A completed map task's output has been lost.]]> + </doc> + </method> + <method name="isIdle" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Is this task tracker idle? + @return has this task tracker finished and cleaned up all of its tasks?]]> + </doc> + </method> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="argv" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + <doc> + <![CDATA[Start the TaskTracker, point toward the indicated JobTracker]]> + </doc> + </method> + <field name="LOG" type="org.apache.commons.logging.Log" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[TaskTracker is a process that starts and tracks MR Tasks + in a networked environment. It contacts the JobTracker + for Task assignments and reporting results.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.TaskTracker --> + <!-- start class org.apache.hadoop.mapred.TaskTracker.Child --> + <class name="TaskTracker.Child" extends="java.lang.Object" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="TaskTracker.Child" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <exception name="Throwable" type="java.lang.Throwable"/> + </method> + <doc> + <![CDATA[The main() for child processes.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.TaskTracker.Child --> + <!-- start class org.apache.hadoop.mapred.TaskTracker.MapOutputServlet --> + <class name="TaskTracker.MapOutputServlet" extends="javax.servlet.http.HttpServlet" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="TaskTracker.MapOutputServlet" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="doGet" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="request" type="javax.servlet.http.HttpServletRequest"/> + <param name="response" type="javax.servlet.http.HttpServletResponse"/> + <exception name="ServletException" type="javax.servlet.ServletException"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[This class is used in TaskTracker's Jetty to serve the map outputs + to other nodes.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.TaskTracker.MapOutputServlet --> + <!-- start class org.apache.hadoop.mapred.TaskTracker.TaskTrackerMetrics --> + <class name="TaskTracker.TaskTrackerMetrics" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.metrics.Updater"/> + <method name="doUpdates" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="unused" type="org.apache.hadoop.metrics.MetricsContext"/> + <doc> + <![CDATA[Since this object is a registered updater, this method will be called + periodically, e.g. every 5 seconds.]]> + </doc> + </method> + </class> + <!-- end class org.apache.hadoop.mapred.TaskTracker.TaskTrackerMetrics --> + <!-- start class org.apache.hadoop.mapred.TextInputFormat --> + <class name="TextInputFormat" extends="org.apache.hadoop.mapred.FileInputFormat<org.apache.hadoop.io.LongWritable, org.apache.hadoop.io.Text>" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.JobConfigurable"/> + <constructor name="TextInputFormat" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="configure" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + </method> + <method name="isSplitable" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <param name="file" type="org.apache.hadoop.fs.Path"/> + </method> + <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.LongWritable, org.apache.hadoop.io.Text>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="genericSplit" type="org.apache.hadoop.mapred.InputSplit"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[An {@link InputFormat} for plain text files. Files are broken into lines. + Either linefeed or carriage-return are used to signal end of line. Keys are + the position in the file, and values are the line of text..]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.TextInputFormat --> + <!-- start class org.apache.hadoop.mapred.TextOutputFormat --> + <class name="TextOutputFormat" extends="org.apache.hadoop.mapred.FileOutputFormat<K, V>" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="TextOutputFormat" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getRecordWriter" return="org.apache.hadoop.mapred.RecordWriter<K, V>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="name" type="java.lang.String"/> + <param name="progress" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[An {@link OutputFormat} that writes plain text files.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.TextOutputFormat --> + <!-- start class org.apache.hadoop.mapred.TextOutputFormat.LineRecordWriter --> + <class name="TextOutputFormat.LineRecordWriter" extends="java.lang.Object" + abstract="false" + static="true" final="false" visibility="protected" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.RecordWriter<K, V>"/> + <constructor name="TextOutputFormat.LineRecordWriter" type="java.io.DataOutputStream" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="write" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K"/> + <param name="value" type="V"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="close" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + </class> + <!-- end class org.apache.hadoop.mapred.TextOutputFormat.LineRecordWriter --> + <doc> + <![CDATA[<p>A software framework for easily writing applications which process vast +amounts of data (multi-terabyte data-sets) parallelly on large clusters +(thousands of nodes) built of commodity hardware in a reliable, fault-tolerant +manner.</p> + +<p>A Map-Reduce <i>job</i> usually splits the input data-set into independent +chunks which processed by <i>map</i> tasks in completely parallel manner, +followed by <i>reduce</i> tasks which aggregating their output. Typically both +the input and the output of the job are stored in a +{@link org.apache.hadoop.fs.FileSystem}. The framework takes care of monitoring +tasks and re-executing failed ones. Since, usually, the compute nodes and the +storage nodes are the same i.e. Hadoop's Map-Reduce framework and Distributed +FileSystem are running on the same set of nodes, tasks are effectively scheduled +on the nodes where data is already present, resulting in very high aggregate +bandwidth across the cluster.</p> + +<p>The Map-Reduce framework operates exclusively on <tt><key, value></tt> +pairs i.e. the input to the job is viewed as a set of <tt><key, value></tt> +pairs and the output as another, possibly different, set of +<tt><key, value></tt> pairs. The <tt>key</tt>s and <tt>value</tt>s have to +be serializable as {@link org.apache.hadoop.io.Writable}s and additionally the +<tt>key</tt>s have to be {@link org.apache.hadoop.io.WritableComparable}s in +order to facilitate grouping by the framework.</p> + +<p>Data flow:</p> +<pre> + (input) + <tt><k1, v1></tt> + + | + V + + <b>map</b> + + | + V + + <tt><k2, v2></tt> + + | + V + + <b>combine</b> + + | + V + + <tt><k2, v2></tt> + + | + V + + <b>reduce</b> + + | + V + + <tt><k3, v3></tt> + (output) +</pre> + +<p>Applications typically implement +{@link org.apache.hadoop.mapred.Mapper#map(Object, Object, OutputCollector, Reporter)} +and +{@link org.apache.hadoop.mapred.Reducer#reduce(Object, Iterator, OutputCollector, Reporter)} +methods. The application-writer also specifies various facets of the job such +as input and output locations, the <tt>Partitioner</tt>, <tt>InputFormat</tt> +& <tt>OutputFormat</tt> implementations to be used etc. as +a {@link org.apache.hadoop.mapred.JobConf}. The client program, +{@link org.apache.hadoop.mapred.JobClient}, then submits the job to the framework +and optionally monitors it.</p> + +<p>The framework spawns one map task per +{@link org.apache.hadoop.mapred.InputSplit} generated by the +{@link org.apache.hadoop.mapred.InputFormat} of the job and calls +{@link org.apache.hadoop.mapred.Mapper#map(Object, Object, OutputCollector, Reporter)} +with each <key, value> pair read by the +{@link org.apache.hadoop.mapred.RecordReader} from the <tt>InputSplit</tt> for +the task. The intermediate outputs of the maps are then grouped by <tt>key</tt>s +and optionally aggregated by <i>combiner</i>. The key space of intermediate +outputs are paritioned by the {@link org.apache.hadoop.mapred.Partitioner}, where +the number of partitions is exactly the number of reduce tasks for the job.</p> + +<p>The reduce tasks fetch the sorted intermediate outputs of the maps, via http, +merge the <key, value> pairs and call +{@link org.apache.hadoop.mapred.Reducer#reduce(Object, Iterator, OutputCollector, Reporter)} +for each <key, list of values> pair. The output of the reduce tasks' is +stored on the <tt>FileSystem</tt> by the +{@link org.apache.hadoop.mapred.RecordWriter} provided by the +{@link org.apache.hadoop.mapred.OutputFormat} of the job.</p> + +<p>Map-Reduce application to perform a distributed <i>grep</i>:</p> +<pre><tt> +public class Grep extends Configured implements Tool { + + // <i>map: Search for the pattern specified by 'grep.mapper.regex' &</i> + // <i>'grep.mapper.regex.group'</i> + + class GrepMapper<K, Text> + extends MapReduceBase implements Mapper<K, Text, Text, LongWritable> { + + private Pattern pattern; + private int group; + + public void configure(JobConf job) { + pattern = Pattern.compile(job.get("grep.mapper.regex")); + group = job.getInt("grep.mapper.regex.group", 0); + } + + public void map(K key, Text value, + OutputCollector<Text, LongWritable> output, + Reporter reporter) + throws IOException { + String text = value.toString(); + Matcher matcher = pattern.matcher(text); + while (matcher.find()) { + output.collect(new Text(matcher.group(group)), new LongWritable(1)); + } + } + } + + // <i>reduce: Count the number of occurrences of the pattern</i> + + class GrepReducer<K> extends MapReduceBase + implements Reducer<K, LongWritable, K, LongWritable> { + + public void reduce(K key, Iterator<LongWritable> values, + OutputCollector<K, LongWritable> output, + Reporter reporter) + throws IOException { + + // sum all values for this key + long sum = 0; + while (values.hasNext()) { + sum += values.next().get(); + } + + // output sum + output.collect(key, new LongWritable(sum)); + } + } + + public int run(String[] args) throws Exception { + if (args.length < 3) { + System.out.println("Grep <inDir> <outDir> <regex> [<group>]"); + ToolRunner.printGenericCommandUsage(System.out); + return -1; + } + + JobConf grepJob = new JobConf(getConf(), Grep.class); + + grepJob.setJobName("grep"); + + grepJob.setInputPath(new Path(args[0])); + grepJob.setOutputPath(args[1]); + + grepJob.setMapperClass(GrepMapper.class); + grepJob.setCombinerClass(GrepReducer.class); + grepJob.setReducerClass(GrepReducer.class); + + grepJob.set("mapred.mapper.regex", args[2]); + if (args.length == 4) + grepJob.set("mapred.mapper.regex.group", args[3]); + + grepJob.setOutputFormat(SequenceFileOutputFormat.class); + grepJob.setOutputKeyClass(Text.class); + grepJob.setOutputValueClass(LongWritable.class); + + JobClient.runJob(grepJob); + + return 0; + } + + public static void main(String[] args) throws Exception { + int res = ToolRunner.run(new Configuration(), new Grep(), args); + System.exit(res); + } + +} +</tt></pre> + +<p>Notice how the data-flow of the above grep job is very similar to doing the +same via the unix pipeline:</p> + +<pre> +cat input/* | grep | sort | uniq -c > out +</pre> + +<pre> + input | map | shuffle | reduce > out +</pre> + +<p>Hadoop Map-Reduce applications need not be written in +Java<small><sup>TM</sup></small> only. +<a href="../streaming/package-summary.html">Hadoop Streaming</a> is a utility +which allows users to create and run jobs with any executables (e.g. shell +utilities) as the mapper and/or the reducer. +<a href="pipes/package-summary.html">Hadoop Pipes</a> is a +<a href="http://www.swig.org/">SWIG</a>-compatible <em>C++ API</em> to implement +Map-Reduce applications (non JNI<small><sup>TM</sup></small> based).</p> + +<p>See <a href="http://labs.google.com/papers/mapreduce.html">Google's original +Map/Reduce paper</a> for background information.</p> + +<p><i>Java and JNI are trademarks or registered trademarks of +Sun Microsystems, Inc. in the United States and other countries.</i></p>]]> + </doc> +</package> +<package name="org.apache.hadoop.mapred.jobcontrol"> + <!-- start class org.apache.hadoop.mapred.jobcontrol.Job --> + <class name="Job" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="Job" type="org.apache.hadoop.mapred.JobConf, java.util.ArrayList<org.apache.hadoop.mapred.jobcontrol.Job>" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct a job. + @param jobConf a mapred job configuration representing a job to be executed. + @param dependingJobs an array of jobs the current job depends on]]> + </doc> + </constructor> + <constructor name="Job" type="org.apache.hadoop.mapred.JobConf" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct a job. + + @param jobConf mapred job configuration representing a job to be executed. + @throws IOException]]> + </doc> + </constructor> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getJobName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the job name of this job]]> + </doc> + </method> + <method name="setJobName" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobName" type="java.lang.String"/> + <doc> + <![CDATA[Set the job name for this job. + @param jobName the job name]]> + </doc> + </method> + <method name="getJobID" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the job ID of this job]]> + </doc> + </method> + <method name="setJobID" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="id" type="java.lang.String"/> + <doc> + <![CDATA[Set the job ID for this job. + @param id the job ID]]> + </doc> + </method> + <method name="getMapredJobID" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the mapred ID of this job]]> + </doc> + </method> + <method name="setMapredJobID" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="mapredJobID" type="java.lang.String"/> + <doc> + <![CDATA[Set the mapred ID for this job. + @param mapredJobID the mapred job ID for this job.]]> + </doc> + </method> + <method name="getJobConf" return="org.apache.hadoop.mapred.JobConf" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the mapred job conf of this job]]> + </doc> + </method> + <method name="setJobConf" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobConf" type="org.apache.hadoop.mapred.JobConf"/> + <doc> + <![CDATA[Set the mapred job conf for this job. + @param jobConf the mapred job conf for this job.]]> + </doc> + </method> + <method name="getState" return="int" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the state of this job]]> + </doc> + </method> + <method name="setState" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="state" type="int"/> + <doc> + <![CDATA[Set the state for this job. + @param state the new state for this job.]]> + </doc> + </method> + <method name="getMessage" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the message of this job]]> + </doc> + </method> + <method name="setMessage" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="message" type="java.lang.String"/> + <doc> + <![CDATA[Set the message for this job. + @param message the message for this job.]]> + </doc> + </method> + <method name="getDependingJobs" return="java.util.ArrayList<org.apache.hadoop.mapred.jobcontrol.Job>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the depending jobs of this job]]> + </doc> + </method> + <method name="addDependingJob" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dependingJob" type="org.apache.hadoop.mapred.jobcontrol.Job"/> + <doc> + <![CDATA[Add a job to this jobs' dependency list. Dependent jobs can only be added while a Job + is waiting to run, not during or afterwards. + + @param dependingJob Job that this Job depends on. + @return <tt>true</tt> if the Job was added.]]> + </doc> + </method> + <method name="isCompleted" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return true if this job is in a complete state]]> + </doc> + </method> + <method name="isReady" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return true if this job is in READY state]]> + </doc> + </method> + <method name="submit" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[Submit this job to mapred. The state becomes RUNNING if submission + is successful, FAILED otherwise.]]> + </doc> + </method> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <doc> + <![CDATA[@param args]]> + </doc> + </method> + <field name="SUCCESS" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="WAITING" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="RUNNING" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="READY" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="FAILED" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="DEPENDENT_FAILED" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[This class encapsulates a MapReduce job and its dependency. It monitors + the states of the depending jobs and updates the state of this job. + A job stats in the WAITING state. If it does not have any deoending jobs, or + all of the depending jobs are in SUCCESS state, then the job state will become + READY. If any depending jobs fail, the job will fail too. + When in READY state, the job can be submitted to Hadoop for execution, with + the state changing into RUNNING state. From RUNNING state, the job can get into + SUCCESS or FAILED state, depending the status of the jon execution.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.jobcontrol.Job --> + <!-- start class org.apache.hadoop.mapred.jobcontrol.JobControl --> + <class name="JobControl" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="java.lang.Runnable"/> + <constructor name="JobControl" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct a job control for a group of jobs. + @param groupName a name identifying this group]]> + </doc> + </constructor> + <method name="getWaitingJobs" return="java.util.ArrayList<org.apache.hadoop.mapred.jobcontrol.Job>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the jobs in the waiting state]]> + </doc> + </method> + <method name="getRunningJobs" return="java.util.ArrayList<org.apache.hadoop.mapred.jobcontrol.Job>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the jobs in the running state]]> + </doc> + </method> + <method name="getReadyJobs" return="java.util.ArrayList<org.apache.hadoop.mapred.jobcontrol.Job>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the jobs in the ready state]]> + </doc> + </method> + <method name="getSuccessfulJobs" return="java.util.ArrayList<org.apache.hadoop.mapred.jobcontrol.Job>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the jobs in the success state]]> + </doc> + </method> + <method name="getFailedJobs" return="java.util.ArrayList<org.apache.hadoop.mapred.jobcontrol.Job>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="addJob" return="java.lang.String" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="aJob" type="org.apache.hadoop.mapred.jobcontrol.Job"/> + <doc> + <![CDATA[Add a new job. + @param aJob the new job]]> + </doc> + </method> + <method name="addJobs" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobs" type="java.util.Collection<org.apache.hadoop.mapred.jobcontrol.Job>"/> + <doc> + <![CDATA[Add a collection of jobs + + @param jobs]]> + </doc> + </method> + <method name="getState" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the thread state]]> + </doc> + </method> + <method name="stop" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[set the thread state to STOPPING so that the + thread will stop when it wakes up.]]> + </doc> + </method> + <method name="suspend" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[suspend the running thread]]> + </doc> + </method> + <method name="resume" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[resume the suspended thread]]> + </doc> + </method> + <method name="allFinished" return="boolean" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="run" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The main loop for the thread. + The loop does the following: + Check the states of the running jobs + Update the states of waiting jobs + Submit the jobs in ready state]]> + </doc> + </method> + <doc> + <![CDATA[This class encapsulates a set of MapReduce jobs and its dependency. It tracks + the states of the jobs by placing them into different tables according to their + states. + + This class provides APIs for the client app to add a job to the group and to get + the jobs in the group in different states. When a + job is added, an ID unique to the group is assigned to the job. + + This class has a thread that submits jobs when they become ready, monitors the + states of the running jobs, and updates the states of jobs based on the state changes + of their depending jobs states. The class provides APIs for suspending/resuming + the thread,and for stopping the thread.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.jobcontrol.JobControl --> + <doc> + <![CDATA[<p>Utilities for managing dependent jobs.</p>]]> + </doc> +</package> +<package name="org.apache.hadoop.mapred.join"> + <!-- start class org.apache.hadoop.mapred.join.ArrayListBackedIterator --> + <class name="ArrayListBackedIterator" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.join.ResetableIterator<X>"/> + <constructor name="ArrayListBackedIterator" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="ArrayListBackedIterator" type="java.util.ArrayList<X>" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="hasNext" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="next" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="X extends org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="replay" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="X extends org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="reset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="add" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="item" type="X extends org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="clear" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[This class provides an implementation of ResetableIterator. The + implementation uses an {@link java.util.ArrayList} to store elements + added to it, replaying them as requested. + Prefer {@link StreamBackedIterator}.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.join.ArrayListBackedIterator --> + <!-- start interface org.apache.hadoop.mapred.join.ComposableInputFormat --> + <interface name="ComposableInputFormat" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.InputFormat<K, V>"/> + <method name="getRecordReader" return="org.apache.hadoop.mapred.join.ComposableRecordReader<K, V>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="split" type="org.apache.hadoop.mapred.InputSplit"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[Refinement of InputFormat requiring implementors to provide + ComposableRecordReader instead of RecordReader.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.mapred.join.ComposableInputFormat --> + <!-- start interface org.apache.hadoop.mapred.join.ComposableRecordReader --> + <interface name="ComposableRecordReader" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.RecordReader<K, V>"/> + <implements name="java.lang.Comparable<org.apache.hadoop.mapred.join.ComposableRecordReader<K, ?>>"/> + <method name="id" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the position in the collector this class occupies.]]> + </doc> + </method> + <method name="key" return="K extends org.apache.hadoop.io.WritableComparable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the key this RecordReader would supply on a call to next(K,V)]]> + </doc> + </method> + <method name="key" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K extends org.apache.hadoop.io.WritableComparable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Clone the key at the head of this RecordReader into the object provided.]]> + </doc> + </method> + <method name="hasNext" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns true if the stream is not empty, but provides no guarantee that + a call to next(K,V) will succeed.]]> + </doc> + </method> + <method name="skip" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K extends org.apache.hadoop.io.WritableComparable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Skip key-value pairs with keys less than or equal to the key provided.]]> + </doc> + </method> + <method name="accept" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jc" type="org.apache.hadoop.mapred.join.CompositeRecordReader.JoinCollector"/> + <param name="key" type="K extends org.apache.hadoop.io.WritableComparable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[While key-value pairs from this RecordReader match the given key, register + them with the JoinCollector provided.]]> + </doc> + </method> + <doc> + <![CDATA[Additional operations required of a RecordReader to participate in a join.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.mapred.join.ComposableRecordReader --> + <!-- start class org.apache.hadoop.mapred.join.CompositeInputFormat --> + <class name="CompositeInputFormat" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.join.ComposableInputFormat<K, org.apache.hadoop.mapred.join.TupleWritable>"/> + <constructor name="CompositeInputFormat" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="setFormat" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Interpret a given string as a composite expression. + {@code + func ::= <ident>([<func>,]*<func>) + func ::= tbl(<class>,"<path>") + class ::= @see java.lang.Class#forName(java.lang.String) + path ::= @see org.apache.hadoop.fs.Path#Path(java.lang.String) + } + Reads expression from the <tt>mapred.join.expr</tt> property and + user-supplied join types from <tt>mapred.join.define.<ident></tt> + types. Paths supplied to <tt>tbl</tt> are given as input paths to the + InputFormat class listed. + @see #compose(java.lang.String, java.lang.Class, java.lang.String...)]]> + </doc> + </method> + <method name="addDefaults" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[Adds the default set of identifiers to the parser.]]> + </doc> + </method> + <method name="validateInput" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Verify that this composite has children and that all its children + can validate their input.]]> + </doc> + </method> + <method name="getSplits" return="org.apache.hadoop.mapred.InputSplit[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="numSplits" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Build a CompositeInputSplit from the child InputFormats by assigning the + ith split from each child to the ith composite split.]]> + </doc> + </method> + <method name="getRecordReader" return="org.apache.hadoop.mapred.join.ComposableRecordReader<K, org.apache.hadoop.mapred.join.TupleWritable>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="split" type="org.apache.hadoop.mapred.InputSplit"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Construct a CompositeRecordReader for the children of this InputFormat + as defined in the init expression. + The outermost join need only be composable, not necessarily a composite. + Mandating TupleWritable isn't strictly correct.]]> + </doc> + </method> + <method name="compose" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="inf" type="java.lang.Class<? extends org.apache.hadoop.mapred.InputFormat>"/> + <param name="path" type="java.lang.String"/> + <doc> + <![CDATA[Convenience method for constructing composite formats. + Given InputFormat class (inf), path (p) return: + {@code tbl(<inf>, <p>) }]]> + </doc> + </method> + <method name="compose" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="op" type="java.lang.String"/> + <param name="inf" type="java.lang.Class<? extends org.apache.hadoop.mapred.InputFormat>"/> + <param name="path" type="java.lang.String[]"/> + <doc> + <![CDATA[Convenience method for constructing composite formats. + Given operation (op), Object class (inf), set of paths (p) return: + {@code <op>(tbl(<inf>,<p1>),tbl(<inf>,<p2>),...,tbl(<inf>,<pn>)) }]]> + </doc> + </method> + <method name="compose" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="op" type="java.lang.String"/> + <param name="inf" type="java.lang.Class<? extends org.apache.hadoop.mapred.InputFormat>"/> + <param name="path" type="org.apache.hadoop.fs.Path[]"/> + <doc> + <![CDATA[Convenience method for constructing composite formats. + Given operation (op), Object class (inf), set of paths (p) return: + {@code <op>(tbl(<inf>,<p1>),tbl(<inf>,<p2>),...,tbl(<inf>,<pn>)) }]]> + </doc> + </method> + <doc> + <![CDATA[An InputFormat capable of performing joins over a set of data sources sorted + and partitioned the same way. + @see #setFormat + + A user may define new join types by setting the property + <tt>mapred.join.define.<ident></tt> to a classname. In the expression + <tt>mapred.join.expr</tt>, the identifier will be assumed to be a + ComposableRecordReader. + <tt>mapred.join.keycomparator</tt> can be a classname used to compare keys + in the join. + @see JoinRecordReader + @see MultiFilterRecordReader]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.join.CompositeInputFormat --> + <!-- start class org.apache.hadoop.mapred.join.CompositeInputSplit --> + <class name="CompositeInputSplit" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.InputSplit"/> + <constructor name="CompositeInputSplit" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="CompositeInputSplit" type="int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="add" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="s" type="org.apache.hadoop.mapred.InputSplit"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Add an InputSplit to this collection. + @throws IOException If capacity was not specified during construction + or if capacity has been reached.]]> + </doc> + </method> + <method name="get" return="org.apache.hadoop.mapred.InputSplit" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="i" type="int"/> + <doc> + <![CDATA[Get ith child InputSplit.]]> + </doc> + </method> + <method name="getLength" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Return the aggregate length of all child InputSplits currently added.]]> + </doc> + </method> + <method name="getLength" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="i" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Get the length of ith child InputSplit.]]> + </doc> + </method> + <method name="getLocations" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Collect a set of hosts from all child InputSplits.]]> + </doc> + </method> + <method name="getLocation" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="i" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[getLocations from ith InputSplit.]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Write splits in the following format. + {@code + <count><class1><class2>...<classn><split1><split2>...<splitn> + }]]> + </doc> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc} + @throws IOException If the child InputSplit cannot be read, typically + for faliing access checks.]]> + </doc> + </method> + <doc> + <![CDATA[This InputSplit contains a set of child InputSplits. Any InputSplit inserted + into this collection must have a public default constructor.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.join.CompositeInputSplit --> + <!-- start class org.apache.hadoop.mapred.join.CompositeRecordReader --> + <class name="CompositeRecordReader" extends="java.lang.Object" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.conf.Configurable"/> + <constructor name="CompositeRecordReader" type="int, int, java.lang.Class<? extends org.apache.hadoop.io.WritableComparator>" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create a RecordReader with <tt>capacity</tt> children to position + <tt>id</tt> in the parent reader. + The id of a root CompositeRecordReader is -1 by convention, but relying + on this is not recommended.]]> + </doc> + </constructor> + <method name="combine" return="boolean" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="srcs" type="java.lang.Object[]"/> + <param name="value" type="org.apache.hadoop.mapred.join.TupleWritable"/> + </method> + <method name="id" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the position in the collector this class occupies.]]> + </doc> + </method> + <method name="setConf" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="getConf" return="org.apache.hadoop.conf.Configuration" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="getRecordReaderQueue" return="java.util.PriorityQueue<org.apache.hadoop.mapred.join.ComposableRecordReader<K, ?>>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[Return sorted list of RecordReaders for this composite.]]> + </doc> + </method> + <method name="getComparator" return="org.apache.hadoop.io.WritableComparator" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[Return comparator defining the ordering for RecordReaders in this + composite.]]> + </doc> + </method> + <method name="add" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="rr" type="org.apache.hadoop.mapred.join.ComposableRecordReader<K, ? extends V>"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Add a RecordReader to this collection. + The id() of a RecordReader determines where in the Tuple its + entry will appear. Adding RecordReaders with the same id has + undefined behavior.]]> + </doc> + </method> + <method name="key" return="K extends org.apache.hadoop.io.WritableComparable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the key for the current join or the value at the top of the + RecordReader heap.]]> + </doc> + </method> + <method name="key" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K extends org.apache.hadoop.io.WritableComparable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Clone the key at the top of this RR into the given object.]]> + </doc> + </method> + <method name="hasNext" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return true if it is possible that this could emit more values.]]> + </doc> + </method> + <method name="skip" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K extends org.apache.hadoop.io.WritableComparable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Pass skip key to child RRs.]]> + </doc> + </method> + <method name="getDelegate" return="org.apache.hadoop.mapred.join.ResetableIterator<X>" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[Obtain an iterator over the child RRs apropos of the value type + ultimately emitted from this join.]]> + </doc> + </method> + <method name="accept" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jc" type="org.apache.hadoop.mapred.join.CompositeRecordReader.JoinCollector"/> + <param name="key" type="K extends org.apache.hadoop.io.WritableComparable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[If key provided matches that of this Composite, give JoinCollector + iterator over values it may emit.]]> + </doc> + </method> + <method name="fillJoinCollector" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="iterkey" type="K extends org.apache.hadoop.io.WritableComparable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[For all child RRs offering the key provided, obtain an iterator + at that position in the JoinCollector.]]> + </doc> + </method> + <method name="compareTo" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="other" type="org.apache.hadoop.mapred.join.ComposableRecordReader<K, ?>"/> + <doc> + <![CDATA[Implement Comparable contract (compare key of join or head of heap + with that of another).]]> + </doc> + </method> + <method name="createKey" return="K extends org.apache.hadoop.io.WritableComparable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Create a new key value common to all child RRs. + @throws ClassCastException if key classes differ.]]> + </doc> + </method> + <method name="createInternalValue" return="org.apache.hadoop.mapred.join.TupleWritable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[Create a value to be used internally for joins.]]> + </doc> + </method> + <method name="getPos" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Unsupported (returns zero in all cases).]]> + </doc> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Close all child RRs.]]> + </doc> + </method> + <method name="getProgress" return="float" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Report progress as the minimum of all child RR progress.]]> + </doc> + </method> + <field name="jc" type="org.apache.hadoop.mapred.join.CompositeRecordReader<K, V, X>.JoinCollector" + transient="false" volatile="false" + static="false" final="true" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="kids" type="org.apache.hadoop.mapred.join.ComposableRecordReader[]" + transient="false" volatile="false" + static="false" final="true" visibility="protected" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[A RecordReader that can effect joins of RecordReaders sharing a common key + type and partitioning.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.join.CompositeRecordReader --> + <!-- start class org.apache.hadoop.mapred.join.InnerJoinRecordReader --> + <class name="InnerJoinRecordReader" extends="org.apache.hadoop.mapred.join.JoinRecordReader<K>" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="combine" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="srcs" type="java.lang.Object[]"/> + <param name="dst" type="org.apache.hadoop.mapred.join.TupleWritable"/> + <doc> + <![CDATA[Return true iff the tuple is full (all data sources contain this key).]]> + </doc> + </method> + <doc> + <![CDATA[Full inner join.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.join.InnerJoinRecordReader --> + <!-- start class org.apache.hadoop.mapred.join.JoinRecordReader --> + <class name="JoinRecordReader" extends="org.apache.hadoop.mapred.join.CompositeRecordReader<K, org.apache.hadoop.io.Writable, org.apache.hadoop.mapred.join.TupleWritable>" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.join.ComposableRecordReader<K, org.apache.hadoop.mapred.join.TupleWritable>"/> + <constructor name="JoinRecordReader" type="int, org.apache.hadoop.mapred.JobConf, int, java.lang.Class<? extends org.apache.hadoop.io.WritableComparator>" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </constructor> + <method name="next" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K extends org.apache.hadoop.io.WritableComparable"/> + <param name="value" type="org.apache.hadoop.mapred.join.TupleWritable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Emit the next set of key, value pairs as defined by the child + RecordReaders and operation associated with this composite RR.]]> + </doc> + </method> + <method name="createValue" return="org.apache.hadoop.mapred.join.TupleWritable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="getDelegate" return="org.apache.hadoop.mapred.join.ResetableIterator<org.apache.hadoop.mapred.join.TupleWritable>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[Return an iterator wrapping the JoinCollector.]]> + </doc> + </method> + <doc> + <![CDATA[Base class for Composite joins returning Tuples of arbitrary Writables.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.join.JoinRecordReader --> + <!-- start class org.apache.hadoop.mapred.join.JoinRecordReader.JoinDelegationIterator --> + <class name="JoinRecordReader.JoinDelegationIterator" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.join.ResetableIterator<org.apache.hadoop.mapred.join.TupleWritable>"/> + <constructor name="JoinRecordReader.JoinDelegationIterator" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </constructor> + <method name="hasNext" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="next" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="org.apache.hadoop.mapred.join.TupleWritable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="replay" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="org.apache.hadoop.mapred.join.TupleWritable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="reset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="add" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="item" type="org.apache.hadoop.mapred.join.TupleWritable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="clear" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[Since the JoinCollector is effecting our operation, we need only + provide an iterator proxy wrapping its operation.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.join.JoinRecordReader.JoinDelegationIterator --> + <!-- start class org.apache.hadoop.mapred.join.MultiFilterRecordReader --> + <class name="MultiFilterRecordReader" extends="org.apache.hadoop.mapred.join.CompositeRecordReader<K, V, V>" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.join.ComposableRecordReader<K, V>"/> + <constructor name="MultiFilterRecordReader" type="int, org.apache.hadoop.mapred.JobConf, int, java.lang.Class<? extends org.apache.hadoop.io.WritableComparator>" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </constructor> + <method name="emit" return="V extends org.apache.hadoop.io.Writable" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="dst" type="org.apache.hadoop.mapred.join.TupleWritable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[For each tuple emitted, return a value (typically one of the values + in the tuple). + Modifying the Writables in the tuple is permitted and unlikely to affect + join behavior in most cases, but it is not recommended. It's safer to + clone first.]]> + </doc> + </method> + <method name="combine" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="srcs" type="java.lang.Object[]"/> + <param name="dst" type="org.apache.hadoop.mapred.join.TupleWritable"/> + <doc> + <![CDATA[Default implementation offers {@link #emit} every Tuple from the + collector (the outer join of child RRs).]]> + </doc> + </method> + <method name="next" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K extends org.apache.hadoop.io.WritableComparable"/> + <param name="value" type="V extends org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="createValue" return="V extends org.apache.hadoop.io.Writable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="getDelegate" return="org.apache.hadoop.mapred.join.ResetableIterator<V>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[Return an iterator returning a single value from the tuple. + @see MultiFilterDelegationIterator]]> + </doc> + </method> + <doc> + <![CDATA[Base class for Composite join returning values derived from multiple + sources, but generally not tuples.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.join.MultiFilterRecordReader --> + <!-- start class org.apache.hadoop.mapred.join.MultiFilterRecordReader.MultiFilterDelegationIterator --> + <class name="MultiFilterRecordReader.MultiFilterDelegationIterator" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.join.ResetableIterator<V>"/> + <constructor name="MultiFilterRecordReader.MultiFilterDelegationIterator" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </constructor> + <method name="hasNext" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="next" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="V extends org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="replay" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="V extends org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="reset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="add" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="item" type="V extends org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="clear" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[Proxy the JoinCollector, but include callback to emit.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.join.MultiFilterRecordReader.MultiFilterDelegationIterator --> + <!-- start class org.apache.hadoop.mapred.join.OuterJoinRecordReader --> + <class name="OuterJoinRecordReader" extends="org.apache.hadoop.mapred.join.JoinRecordReader<K>" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="combine" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="srcs" type="java.lang.Object[]"/> + <param name="dst" type="org.apache.hadoop.mapred.join.TupleWritable"/> + <doc> + <![CDATA[Emit everything from the collector.]]> + </doc> + </method> + <doc> + <![CDATA[Full outer join.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.join.OuterJoinRecordReader --> + <!-- start class org.apache.hadoop.mapred.join.OverrideRecordReader --> + <class name="OverrideRecordReader" extends="org.apache.hadoop.mapred.join.MultiFilterRecordReader<K, V>" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="emit" return="V extends org.apache.hadoop.io.Writable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="dst" type="org.apache.hadoop.mapred.join.TupleWritable"/> + <doc> + <![CDATA[Emit the value with the highest position in the tuple.]]> + </doc> + </method> + <method name="fillJoinCollector" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="iterkey" type="K extends org.apache.hadoop.io.WritableComparable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Instead of filling the JoinCollector with iterators from all + data sources, fill only the rightmost for this key. + This not only saves space by discarding the other sources, but + it also emits the number of key-value pairs in the preferred + RecordReader instead of repeating that stream n times, where + n is the cardinality of the cross product of the discarded + streams for the given key.]]> + </doc> + </method> + <doc> + <![CDATA[Prefer the "rightmost" data source for this key. + For example, <tt>override(S1,S2,S3)</tt> will prefer values + from S3 over S2, and values from S2 over S1 for all keys + emitted from all sources.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.join.OverrideRecordReader --> + <!-- start class org.apache.hadoop.mapred.join.Parser --> + <class name="Parser" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="Parser" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <doc> + <![CDATA[Very simple shift-reduce parser for join expressions. + + This should be sufficient for the user extension permitted now, but ought to + be replaced with a parser generator if more complex grammars are supported. + In particular, this "shift-reduce" parser has no states. Each set + of formals requires a different internal node type, which is responsible for + interpreting the list of tokens it receives. This is sufficient for the + current grammar, but it has several annoying properties that might inhibit + extension. In particular, parenthesis are always function calls; an + algebraic or filter grammar would not only require a node type, but must + also work around the internals of this parser. + + For most other cases, adding classes to the hierarchy- particularly by + extending JoinRecordReader and MultiFilterRecordReader- is fairly + straightforward. One need only override the relevant method(s) (usually only + {@link CompositeRecordReader#combine}) and include a property to map its + value to an identifier in the parser.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.join.Parser --> + <!-- start class org.apache.hadoop.mapred.join.Parser.Node --> + <class name="Parser.Node" extends="java.lang.Object" + abstract="true" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.join.ComposableInputFormat"/> + <constructor name="Parser.Node" type="java.lang.String" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </constructor> + <method name="addIdentifier" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="ident" type="java.lang.String"/> + <param name="mcstrSig" type="java.lang.Class[]"/> + <param name="nodetype" type="java.lang.Class<? extends org.apache.hadoop.mapred.join.Parser.Node>"/> + <param name="cl" type="java.lang.Class<? extends org.apache.hadoop.mapred.join.ComposableRecordReader>"/> + <exception name="NoSuchMethodException" type="java.lang.NoSuchMethodException"/> + <doc> + <![CDATA[For a given identifier, add a mapping to the nodetype for the parse + tree and to the ComposableRecordReader to be created, including the + formals required to invoke the constructor. + The nodetype and constructor signature should be filled in from the + child node.]]> + </doc> + </method> + <method name="setID" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="id" type="int"/> + </method> + <method name="setKeyComparator" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="cmpcl" type="java.lang.Class<? extends org.apache.hadoop.io.WritableComparator>"/> + </method> + <field name="rrCstrMap" type="java.util.Map<java.lang.String, java.lang.reflect.Constructor<? extends org.apache.hadoop.mapred.join.ComposableRecordReader>>" + transient="false" volatile="false" + static="true" final="true" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="id" type="int" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="ident" type="java.lang.String" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="cmpcl" type="java.lang.Class<? extends org.apache.hadoop.io.WritableComparator>" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + </class> + <!-- end class org.apache.hadoop.mapred.join.Parser.Node --> + <!-- start class org.apache.hadoop.mapred.join.Parser.NodeToken --> + <class name="Parser.NodeToken" extends="org.apache.hadoop.mapred.join.Parser.Token" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <method name="getNode" return="org.apache.hadoop.mapred.join.Parser.Node" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + </class> + <!-- end class org.apache.hadoop.mapred.join.Parser.NodeToken --> + <!-- start class org.apache.hadoop.mapred.join.Parser.NumToken --> + <class name="Parser.NumToken" extends="org.apache.hadoop.mapred.join.Parser.Token" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="Parser.NumToken" type="double" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getNum" return="double" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + </class> + <!-- end class org.apache.hadoop.mapred.join.Parser.NumToken --> + <!-- start class org.apache.hadoop.mapred.join.Parser.StrToken --> + <class name="Parser.StrToken" extends="org.apache.hadoop.mapred.join.Parser.Token" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="Parser.StrToken" type="org.apache.hadoop.mapred.join.Parser.TType, java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getStr" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + </class> + <!-- end class org.apache.hadoop.mapred.join.Parser.StrToken --> + <!-- start class org.apache.hadoop.mapred.join.Parser.Token --> + <class name="Parser.Token" extends="java.lang.Object" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <method name="getType" return="org.apache.hadoop.mapred.join.Parser.TType" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getNode" return="org.apache.hadoop.mapred.join.Parser.Node" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getNum" return="double" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getStr" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[Tagged-union type for tokens from the join expression. + @see Parser.TType]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.join.Parser.Token --> + <!-- start class org.apache.hadoop.mapred.join.Parser.TType --> + <class name="Parser.TType" extends="java.lang.Enum<org.apache.hadoop.mapred.join.Parser.TType>" + abstract="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <method name="values" return="org.apache.hadoop.mapred.join.Parser.TType[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="valueOf" return="org.apache.hadoop.mapred.join.Parser.TType" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + </method> + </class> + <!-- end class org.apache.hadoop.mapred.join.Parser.TType --> + <!-- start interface org.apache.hadoop.mapred.join.ResetableIterator --> + <interface name="ResetableIterator" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="hasNext" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[True iff a call to next will succeed.]]> + </doc> + </method> + <method name="next" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="T extends org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Assign next value to actual. + It is required that elements added to a ResetableIterator be returned in + the same order after a call to {@link #reset} (FIFO). + + Note that a call to this may fail for nested joins (i.e. more elements + available, but none satisfying the constraints of the join)]]> + </doc> + </method> + <method name="replay" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="T extends org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Assign last value returned to actual.]]> + </doc> + </method> + <method name="reset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Set iterator to return to the start of its range. Must be called after + calling {@link #add} to avoid a ConcurrentModificationException.]]> + </doc> + </method> + <method name="add" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="item" type="T extends org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Add an element to the collection of elements to iterate over.]]> + </doc> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Close datasources and release resources. Calling methods on the iterator + after calling close has undefined behavior.]]> + </doc> + </method> + <method name="clear" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Close datasources, but do not release internal resources. Calling this + method should permit the object to be reused with a different datasource.]]> + </doc> + </method> + <doc> + <![CDATA[This defines an interface to a stateful Iterator that can replay elements + added to it directly. + Note that this does not extend {@link java.util.Iterator}.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.mapred.join.ResetableIterator --> + <!-- start class org.apache.hadoop.mapred.join.ResetableIterator.EMPTY --> + <class name="ResetableIterator.EMPTY" extends="java.lang.Object" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.join.ResetableIterator<U>"/> + <constructor name="ResetableIterator.EMPTY" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="hasNext" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="reset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="clear" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="next" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="U extends org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="replay" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="U extends org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="add" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="item" type="U extends org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + </class> + <!-- end class org.apache.hadoop.mapred.join.ResetableIterator.EMPTY --> + <!-- start class org.apache.hadoop.mapred.join.StreamBackedIterator --> + <class name="StreamBackedIterator" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.join.ResetableIterator<X>"/> + <constructor name="StreamBackedIterator" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="hasNext" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="next" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="X extends org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="replay" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="X extends org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="reset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="add" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="item" type="X extends org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="clear" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[This class provides an implementation of ResetableIterator. This + implementation uses a byte array to store elements added to it.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.join.StreamBackedIterator --> + <!-- start class org.apache.hadoop.mapred.join.TupleWritable --> + <class name="TupleWritable" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <implements name="java.lang.Iterable<org.apache.hadoop.io.Writable>"/> + <constructor name="TupleWritable" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Create an empty tuple with no allocated storage for writables.]]> + </doc> + </constructor> + <constructor name="TupleWritable" type="org.apache.hadoop.io.Writable[]" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Initialize tuple with storage; unknown whether any of them contain + "written" values.]]> + </doc> + </constructor> + <method name="has" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="i" type="int"/> + <doc> + <![CDATA[Return true if tuple has an element at the position provided.]]> + </doc> + </method> + <method name="get" return="org.apache.hadoop.io.Writable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="i" type="int"/> + <doc> + <![CDATA[Get ith Writable from Tuple.]]> + </doc> + </method> + <method name="size" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The number of children in this Tuple.]]> + </doc> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="other" type="java.lang.Object"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="iterator" return="java.util.Iterator<org.apache.hadoop.io.Writable>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return an iterator over the elements in this tuple. + Note that this doesn't flatten the tuple; one may receive tuples + from this iterator.]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Convert Tuple to String as in the following. + <tt>[<child1>,<child2>,...,<childn>]</tt>]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Writes each Writable to <code>out</code>. + TupleWritable format: + {@code + <count><type1><type2>...<typen><obj1><obj2>...<objn> + }]]> + </doc> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <doc> + <![CDATA[Writable type storing multiple {@link org.apache.hadoop.io.Writable}s.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.join.TupleWritable --> + <!-- start class org.apache.hadoop.mapred.join.WrappedRecordReader --> + <class name="WrappedRecordReader" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.join.ComposableRecordReader<K, U>"/> + <method name="id" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[{@inheritDoc}]]> + </doc> + </method> + <method name="key" return="K extends org.apache.hadoop.io.WritableComparable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the key at the head of this RR.]]> + </doc> + </method> + <method name="key" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="qkey" type="K extends org.apache.hadoop.io.WritableComparable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Clone the key at the head of this RR into the object supplied.]]> + </doc> + </method> + <method name="hasNext" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return true if the RR- including the k,v pair stored in this object- + is exhausted.]]> + </doc> + </method> + <method name="skip" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K extends org.apache.hadoop.io.WritableComparable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Skip key-value pairs with keys less than or equal to the key provided.]]> + </doc> + </method> + <method name="next" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read the next k,v pair into the head of this object; return true iff + the RR and this are exhausted.]]> + </doc> + </method> + <method name="accept" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="i" type="org.apache.hadoop.mapred.join.CompositeRecordReader.JoinCollector"/> + <param name="key" type="K extends org.apache.hadoop.io.WritableComparable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Add an iterator to the collector at the position occupied by this + RecordReader over the values in this stream paired with the key + provided (ie register a stream of values from this source matching K + with a collector).]]> + </doc> + </method> + <method name="next" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K extends org.apache.hadoop.io.WritableComparable"/> + <param name="value" type="U extends org.apache.hadoop.io.Writable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Write key-value pair at the head of this stream to the objects provided; + get next key-value pair from proxied RR.]]> + </doc> + </method> + <method name="createKey" return="K extends org.apache.hadoop.io.WritableComparable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Request new key from proxied RR.]]> + </doc> + </method> + <method name="createValue" return="U extends org.apache.hadoop.io.Writable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Request new value from proxied RR.]]> + </doc> + </method> + <method name="getProgress" return="float" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Request progress from proxied RR.]]> + </doc> + </method> + <method name="getPos" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Request position from proxied RR.]]> + </doc> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Forward close request to proxied RR.]]> + </doc> + </method> + <method name="compareTo" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="other" type="org.apache.hadoop.mapred.join.ComposableRecordReader<K, ?>"/> + <doc> + <![CDATA[Implement Comparable contract (compare key at head of proxied RR + with that of another).]]> + </doc> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="other" type="java.lang.Object"/> + <doc> + <![CDATA[Return true iff compareTo(other) retn true.]]> + </doc> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[Proxy class for a RecordReader participating in the join framework. + This class keeps track of the "head" key-value pair for the + provided RecordReader and keeps a store of values matching a key when + this source is participating in a join.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.join.WrappedRecordReader --> + <doc> + <![CDATA[<p>Given a set of sorted datasets keyed with the same class and yielding equal +partitions, it is possible to effect a join of those datasets prior to the map. +This could save costs in re-partitioning, sorting, shuffling, and writing out +data required in the general case.</p> + +<h3><a name="Interface"></a>Interface</h3> + +<p>The attached code offers the following interface to users of these +classes.</p> + +<table> +<tr><th>property</th><th>required</th><th>value</th></tr> +<tr><td>mapred.join.expr</td><td>yes</td> + <td>Join expression to effect over input data</td></tr> +<tr><td>mapred.join.keycomparator</td><td>no</td> + <td><tt>WritableComparator</tt> class to use for comparing keys</td></tr> +<tr><td>mapred.join.define.<ident></td><td>no</td> + <td>Class mapped to identifier in join expression</td></tr> +</table> + +<p>The join expression understands the following grammar:</p> + +<pre>func ::= <ident>([<func>,]*<func>) +func ::= tbl(<class>,"<path>"); + +</pre> + +<p>Operations included in this patch are partitioned into one of two types: +join operations emitting tuples and "multi-filter" operations emitting a +single value from (but not necessarily included in) a set of input values. +For a given key, each operation will consider the cross product of all +values for all sources at that node.</p> + +<p>Identifiers supported by default:</p> + +<table> +<tr><th>identifier</th><th>type</th><th>description</th></tr> +<tr><td>inner</td><td>Join</td><td>Full inner join</td></tr> +<tr><td>outer</td><td>Join</td><td>Full outer join</td></tr> +<tr><td>override</td><td>MultiFilter</td> + <td>For a given key, prefer values from the rightmost source</td></tr> +</table> + +<p>A user of this class must set the <tt>InputFormat</tt> for the job to +<tt>CompositeInputFormat</tt> and define a join expression accepted by the +preceding grammar. For example, both of the following are acceptable:</p> + +<pre>inner(tbl(org.apache.hadoop.mapred.SequenceFileInputFormat.class, + "hdfs://host:8020/foo/bar"), + tbl(org.apache.hadoop.mapred.SequenceFileInputFormat.class, + "hdfs://host:8020/foo/baz")) + +outer(override(tbl(org.apache.hadoop.mapred.SequenceFileInputFormat.class, + "hdfs://host:8020/foo/bar"), + tbl(org.apache.hadoop.mapred.SequenceFileInputFormat.class, + "hdfs://host:8020/foo/baz")), + tbl(org.apache.hadoop.mapred/SequenceFileInputFormat.class, + "hdfs://host:8020/foo/rab")) +</pre> + +<p><tt>CompositeInputFormat</tt> includes a handful of convenience methods to +aid construction of these verbose statements.</p> + +<p>As in the second example, joins may be nested. Users may provide a +comparator class in the <tt>mapred.join.keycomparator</tt> property to specify +the ordering of their keys, or accept the default comparator as returned by +<tt>WritableComparator.get(keyclass)</tt>.</p> + +<p>Users can specify their own join operations, typically by overriding +<tt>JoinRecordReader</tt> or <tt>MultiFilterRecordReader</tt> and mapping that +class to an identifier in the join expression using the +<tt>mapred.join.define.<em>ident</em></tt> property, where <em>ident</em> is +the identifier appearing in the join expression. Users may elect to emit- or +modify- values passing through their join operation. Consulting the existing +operations for guidance is recommended. Adding arguments is considerably more +complex (and only partially supported), as one must also add a <tt>Node</tt> +type to the parse tree. One is probably better off extending +<tt>RecordReader</tt> in most cases.</p> + +<a href="http://issues.apache.org/jira/browse/HADOOP-2085">JIRA</a>]]> + </doc> +</package> +<package name="org.apache.hadoop.mapred.lib"> + <!-- start class org.apache.hadoop.mapred.lib.FieldSelectionMapReduce --> + <class name="FieldSelectionMapReduce" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.Mapper<K, V, org.apache.hadoop.io.Text, org.apache.hadoop.io.Text>"/> + <implements name="org.apache.hadoop.mapred.Reducer<org.apache.hadoop.io.Text, org.apache.hadoop.io.Text, org.apache.hadoop.io.Text, org.apache.hadoop.io.Text>"/> + <constructor name="FieldSelectionMapReduce" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="map" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K"/> + <param name="val" type="V"/> + <param name="output" type="org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.Text, org.apache.hadoop.io.Text>"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[The identify function. Input key/value pair is written directly to output.]]> + </doc> + </method> + <method name="configure" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="reduce" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.Text"/> + <param name="values" type="java.util.Iterator<org.apache.hadoop.io.Text>"/> + <param name="output" type="org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.Text, org.apache.hadoop.io.Text>"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <field name="LOG" type="org.apache.commons.logging.Log" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[This class implements a mapper/reducer class that can be used to perform + field selections in a manner similar to unix cut. The input data is treated + as fields separated by a user specified separator (the default value is + "\t"). The user can specify a list of fields that form the map output keys, + and a list of fields that form the map output values. If the inputformat is + TextInputFormat, the mapper will ignore the key to the map function. and the + fields are from the value only. Otherwise, the fields are the union of those + from the key and those from the value. + + The field separator is under attribute "mapred.data.field.separator" + + The map output field list spec is under attribute "map.output.key.value.fields.spec". + The value is expected to be like "keyFieldsSpec:valueFieldsSpec" + key/valueFieldsSpec are comma (,) separated field spec: fieldSpec,fieldSpec,fieldSpec ... + Each field spec can be a simple number (e.g. 5) specifying a specific field, or a range + (like 2-5) to specify a range of fields, or an open range (like 3-) specifying all + the fields starting from field 3. The open range field spec applies value fields only. + They have no effect on the key fields. + + Here is an example: "4,3,0,1:6,5,1-3,7-". It specifies to use fields 4,3,0 and 1 for keys, + and use fields 6,5,1,2,3,7 and above for values. + + The reduce output field list spec is under attribute "reduce.output.key.value.fields.spec". + + The reducer extracts output key/value pairs in a similar manner, except that + the key is never ignored.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.FieldSelectionMapReduce --> + <!-- start class org.apache.hadoop.mapred.lib.HashPartitioner --> + <class name="HashPartitioner" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.Partitioner<K2, V2>"/> + <constructor name="HashPartitioner" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="configure" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + </method> + <method name="getPartition" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K2"/> + <param name="value" type="V2"/> + <param name="numReduceTasks" type="int"/> + <doc> + <![CDATA[Use {@link Object#hashCode()} to partition.]]> + </doc> + </method> + <doc> + <![CDATA[Partition keys by their {@link Object#hashCode()}.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.HashPartitioner --> + <!-- start class org.apache.hadoop.mapred.lib.IdentityMapper --> + <class name="IdentityMapper" extends="org.apache.hadoop.mapred.MapReduceBase" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.Mapper<K, V, K, V>"/> + <constructor name="IdentityMapper" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="map" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K"/> + <param name="val" type="V"/> + <param name="output" type="org.apache.hadoop.mapred.OutputCollector<K, V>"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[The identify function. Input key/value pair is written directly to + output.]]> + </doc> + </method> + <doc> + <![CDATA[Implements the identity function, mapping inputs directly to outputs.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.IdentityMapper --> + <!-- start class org.apache.hadoop.mapred.lib.IdentityReducer --> + <class name="IdentityReducer" extends="org.apache.hadoop.mapred.MapReduceBase" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.Reducer<K, V, K, V>"/> + <constructor name="IdentityReducer" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="reduce" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K"/> + <param name="values" type="java.util.Iterator<V>"/> + <param name="output" type="org.apache.hadoop.mapred.OutputCollector<K, V>"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Writes all keys and values directly to output.]]> + </doc> + </method> + <doc> + <![CDATA[Performs no reduction, writing all input values directly to the output.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.IdentityReducer --> + <!-- start class org.apache.hadoop.mapred.lib.InverseMapper --> + <class name="InverseMapper" extends="org.apache.hadoop.mapred.MapReduceBase" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.Mapper<K, V, V, K>"/> + <constructor name="InverseMapper" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="map" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K"/> + <param name="value" type="V"/> + <param name="output" type="org.apache.hadoop.mapred.OutputCollector<V, K>"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[The inverse function. Input keys and values are swapped.]]> + </doc> + </method> + <doc> + <![CDATA[A {@link Mapper} that swaps keys and values.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.InverseMapper --> + <!-- start class org.apache.hadoop.mapred.lib.KeyFieldBasedPartitioner --> + <class name="KeyFieldBasedPartitioner" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.Partitioner<K2, V2>"/> + <constructor name="KeyFieldBasedPartitioner" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="configure" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + </method> + <method name="getPartition" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K2"/> + <param name="value" type="V2"/> + <param name="numReduceTasks" type="int"/> + <doc> + <![CDATA[Use {@link Object#hashCode()} to partition.]]> + </doc> + </method> + </class> + <!-- end class org.apache.hadoop.mapred.lib.KeyFieldBasedPartitioner --> + <!-- start class org.apache.hadoop.mapred.lib.LongSumReducer --> + <class name="LongSumReducer" extends="org.apache.hadoop.mapred.MapReduceBase" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.Reducer<K, org.apache.hadoop.io.LongWritable, K, org.apache.hadoop.io.LongWritable>"/> + <constructor name="LongSumReducer" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="reduce" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K"/> + <param name="values" type="java.util.Iterator<org.apache.hadoop.io.LongWritable>"/> + <param name="output" type="org.apache.hadoop.mapred.OutputCollector<K, org.apache.hadoop.io.LongWritable>"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[A {@link Reducer} that sums long values.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.LongSumReducer --> + <!-- start class org.apache.hadoop.mapred.lib.MultipleOutputFormat --> + <class name="MultipleOutputFormat" extends="org.apache.hadoop.mapred.FileOutputFormat<K, V>" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="MultipleOutputFormat" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getRecordWriter" return="org.apache.hadoop.mapred.RecordWriter<K, V>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="name" type="java.lang.String"/> + <param name="arg3" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create a composite record writer that can write key/value data to different + output files + + @param fs + the file system to use + @param job + the job conf for the job + @param name + the leaf file name for the output file (such as part-00000") + @param arg3 + a progressable for reporting progress. + @return a composite record writer + @throws IOException]]> + </doc> + </method> + <method name="generateLeafFileName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <doc> + <![CDATA[Generate the leaf name for the output file name. The default behavior does + not change the leaf file name (such as part-00000) + + @param name + the leaf file name for the output file + @return the given leaf file name]]> + </doc> + </method> + <method name="generateFileNameForKeyValue" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="key" type="K extends org.apache.hadoop.io.WritableComparable"/> + <param name="value" type="V extends org.apache.hadoop.io.Writable"/> + <param name="name" type="java.lang.String"/> + <doc> + <![CDATA[Generate the file output file name based on the given key and the leaf file + name. The default behavior is that the file name does not depend on the + key. + + @param key + the key of the output data + @param name + the leaf file name + @return generated file name]]> + </doc> + </method> + <method name="generateActualKey" return="K extends org.apache.hadoop.io.WritableComparable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="key" type="K extends org.apache.hadoop.io.WritableComparable"/> + <param name="value" type="V extends org.apache.hadoop.io.Writable"/> + <doc> + <![CDATA[Generate the actual key from the given key/value. The default behavior is that + the actual key is equal to the given key + + @param key + the key of the output data + @param value + the value of the output data + @return the actual key derived from the given key/value]]> + </doc> + </method> + <method name="generateActualValue" return="V extends org.apache.hadoop.io.Writable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="key" type="K extends org.apache.hadoop.io.WritableComparable"/> + <param name="value" type="V extends org.apache.hadoop.io.Writable"/> + <doc> + <![CDATA[Generate the actual value from the given key and value. The default behavior is that + the actual value is equal to the given value + + @param key + the key of the output data + @param value + the value of the output data + @return the actual value derived from the given key/value]]> + </doc> + </method> + <method name="getInputFileBasedOutputFileName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="name" type="java.lang.String"/> + <doc> + <![CDATA[Generate the outfile name based on a given anme and the input file name. If + the map input file does not exists (i.e. this is not for a map only job), + the given name is returned unchanged. If the config value for + "num.of.trailing.legs.to.use" is not set, or set 0 or negative, the given + name is returned unchanged. Otherwise, return a file name consisting of the + N trailing legs of the input file name where N is the config value for + "num.of.trailing.legs.to.use". + + @param job + the job config + @param name + the output file name + @return the outfile name based on a given anme and the input file name.]]> + </doc> + </method> + <method name="getBaseRecordWriter" return="org.apache.hadoop.mapred.RecordWriter<K, V>" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="name" type="java.lang.String"/> + <param name="arg3" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[@param fs + the file system to use + @param job + a job conf object + @param name + the name of the file over which a record writer object will be + constructed + @param arg3 + a progressable object + @return A RecordWriter object over the given file + @throws IOException]]> + </doc> + </method> + <doc> + <![CDATA[This abstract class extends the OutputFormatBase, allowing to write the + output data to different output files. There are three basic use cases for + this class. + + Case one: This class is used for a map reduce job with at least one reducer. + The reducer wants to write data to different files depending on the actual + keys. It is assumed that a key (or value) enocodes the actual key (value) + and the desired location for the actual key (value). + + Case two: Tis class is used for a map only job. The job wants to use an + output file name that is either a part of the input file name of the input + data, or some derivation of it. + + Case three: This class is used for a map only job. The job wants to use an + output file name that depends on both the keys and the input file name,]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.MultipleOutputFormat --> + <!-- start class org.apache.hadoop.mapred.lib.MultipleSequenceFileOutputFormat --> + <class name="MultipleSequenceFileOutputFormat" extends="org.apache.hadoop.mapred.lib.MultipleOutputFormat<org.apache.hadoop.io.WritableComparable, org.apache.hadoop.io.Writable>" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="MultipleSequenceFileOutputFormat" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getBaseRecordWriter" return="org.apache.hadoop.mapred.RecordWriter<org.apache.hadoop.io.WritableComparable, org.apache.hadoop.io.Writable>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="name" type="java.lang.String"/> + <param name="arg3" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[This class extends the MultipleOutputFormat, allowing to write the output data + to different output files in sequence file output format.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.MultipleSequenceFileOutputFormat --> + <!-- start class org.apache.hadoop.mapred.lib.MultipleTextOutputFormat --> + <class name="MultipleTextOutputFormat" extends="org.apache.hadoop.mapred.lib.MultipleOutputFormat<K, V>" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="MultipleTextOutputFormat" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getBaseRecordWriter" return="org.apache.hadoop.mapred.RecordWriter<K, V>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="fs" type="org.apache.hadoop.fs.FileSystem"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="name" type="java.lang.String"/> + <param name="arg3" type="org.apache.hadoop.util.Progressable"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[This class extends the MultipleOutputFormat, allowing to write the output + data to different output files in Text output format.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.MultipleTextOutputFormat --> + <!-- start class org.apache.hadoop.mapred.lib.MultithreadedMapRunner --> + <class name="MultithreadedMapRunner" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.MapRunnable<K1, V1, K2, V2>"/> + <constructor name="MultithreadedMapRunner" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="configure" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobConf" type="org.apache.hadoop.mapred.JobConf"/> + </method> + <method name="run" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="input" type="org.apache.hadoop.mapred.RecordReader<K1, V1>"/> + <param name="output" type="org.apache.hadoop.mapred.OutputCollector<K2, V2>"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[Multithreaded implementation for @link org.apache.hadoop.mapred.MapRunnable. + <p> + It can be used instead of the default implementation, + @link org.apache.hadoop.mapred.MapRunner, when the Map operation is not CPU + bound in order to improve throughput. + <p> + Map implementations using this MapRunnable must be thread-safe. + <p> + The Map-Reduce job has to be configured to use this MapRunnable class (using + the JobConf.setMapRunnerClass method) and + the number of thread the thread-pool can use with the + <code>mapred.map.multithreadedrunner.threads</code> property, its default + value is 10 threads. + <p>]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.MultithreadedMapRunner --> + <!-- start class org.apache.hadoop.mapred.lib.NullOutputFormat --> + <class name="NullOutputFormat" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.OutputFormat<K, V>"/> + <constructor name="NullOutputFormat" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getRecordWriter" return="org.apache.hadoop.mapred.RecordWriter<K, V>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="name" type="java.lang.String"/> + <param name="progress" type="org.apache.hadoop.util.Progressable"/> + </method> + <method name="checkOutputSpecs" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + </method> + <doc> + <![CDATA[Consume all outputs and put them in /dev/null.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.NullOutputFormat --> + <!-- start class org.apache.hadoop.mapred.lib.RegexMapper --> + <class name="RegexMapper" extends="org.apache.hadoop.mapred.MapReduceBase" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.Mapper<K, org.apache.hadoop.io.Text, org.apache.hadoop.io.Text, org.apache.hadoop.io.LongWritable>"/> + <constructor name="RegexMapper" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="configure" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + </method> + <method name="map" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K"/> + <param name="value" type="org.apache.hadoop.io.Text"/> + <param name="output" type="org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.Text, org.apache.hadoop.io.LongWritable>"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[A {@link Mapper} that extracts text matching a regular expression.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.RegexMapper --> + <!-- start class org.apache.hadoop.mapred.lib.TokenCountMapper --> + <class name="TokenCountMapper" extends="org.apache.hadoop.mapred.MapReduceBase" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.Mapper<K, org.apache.hadoop.io.Text, org.apache.hadoop.io.Text, org.apache.hadoop.io.LongWritable>"/> + <constructor name="TokenCountMapper" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="map" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K"/> + <param name="value" type="org.apache.hadoop.io.Text"/> + <param name="output" type="org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.Text, org.apache.hadoop.io.LongWritable>"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[A {@link Mapper} that maps text values into <token,freq> pairs. Uses + {@link StringTokenizer} to break text into tokens.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.TokenCountMapper --> + <doc> + <![CDATA[<p>Library of generally useful mappers, reducers, and partitioners.</p>]]> + </doc> +</package> +<package name="org.apache.hadoop.mapred.lib.aggregate"> + <!-- start class org.apache.hadoop.mapred.lib.aggregate.DoubleValueSum --> + <class name="DoubleValueSum" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.lib.aggregate.ValueAggregator"/> + <constructor name="DoubleValueSum" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The default constructor]]> + </doc> + </constructor> + <method name="addNextValue" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="java.lang.Object"/> + <doc> + <![CDATA[add a value to the aggregator + + @param val + an object whose string representation represents a double value.]]> + </doc> + </method> + <method name="addNextValue" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="double"/> + <doc> + <![CDATA[add a value to the aggregator + + @param val + a double value.]]> + </doc> + </method> + <method name="getReport" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the string representation of the aggregated value]]> + </doc> + </method> + <method name="getSum" return="double" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the aggregated value]]> + </doc> + </method> + <method name="reset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[reset the aggregator]]> + </doc> + </method> + <method name="getCombinerOutput" return="java.util.ArrayList<java.lang.String>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return return an array of one element. The element is a string + representation of the aggregated value. The return value is + expected to be used by the a combiner.]]> + </doc> + </method> + <doc> + <![CDATA[This class implements a value aggregator that sums up a sequence of double + values.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.aggregate.DoubleValueSum --> + <!-- start class org.apache.hadoop.mapred.lib.aggregate.LongValueMax --> + <class name="LongValueMax" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.lib.aggregate.ValueAggregator"/> + <constructor name="LongValueMax" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[the default constructor]]> + </doc> + </constructor> + <method name="addNextValue" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="java.lang.Object"/> + <doc> + <![CDATA[add a value to the aggregator + + @param val + an object whose string representation represents a long value.]]> + </doc> + </method> + <method name="addNextValue" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="newVal" type="long"/> + <doc> + <![CDATA[add a value to the aggregator + + @param newVal + a long value.]]> + </doc> + </method> + <method name="getVal" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the aggregated value]]> + </doc> + </method> + <method name="getReport" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the string representation of the aggregated value]]> + </doc> + </method> + <method name="reset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[reset the aggregator]]> + </doc> + </method> + <method name="getCombinerOutput" return="java.util.ArrayList<java.lang.String>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return return an array of one element. The element is a string + representation of the aggregated value. The return value is + expected to be used by the a combiner.]]> + </doc> + </method> + <doc> + <![CDATA[This class implements a value aggregator that maintain the maximum of + a sequence of long values.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.aggregate.LongValueMax --> + <!-- start class org.apache.hadoop.mapred.lib.aggregate.LongValueMin --> + <class name="LongValueMin" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.lib.aggregate.ValueAggregator"/> + <constructor name="LongValueMin" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[the default constructor]]> + </doc> + </constructor> + <method name="addNextValue" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="java.lang.Object"/> + <doc> + <![CDATA[add a value to the aggregator + + @param val + an object whose string representation represents a long value.]]> + </doc> + </method> + <method name="addNextValue" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="newVal" type="long"/> + <doc> + <![CDATA[add a value to the aggregator + + @param newVal + a long value.]]> + </doc> + </method> + <method name="getVal" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the aggregated value]]> + </doc> + </method> + <method name="getReport" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the string representation of the aggregated value]]> + </doc> + </method> + <method name="reset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[reset the aggregator]]> + </doc> + </method> + <method name="getCombinerOutput" return="java.util.ArrayList<java.lang.String>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return return an array of one element. The element is a string + representation of the aggregated value. The return value is + expected to be used by the a combiner.]]> + </doc> + </method> + <doc> + <![CDATA[This class implements a value aggregator that maintain the minimum of + a sequence of long values.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.aggregate.LongValueMin --> + <!-- start class org.apache.hadoop.mapred.lib.aggregate.LongValueSum --> + <class name="LongValueSum" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.lib.aggregate.ValueAggregator"/> + <constructor name="LongValueSum" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[the default constructor]]> + </doc> + </constructor> + <method name="addNextValue" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="java.lang.Object"/> + <doc> + <![CDATA[add a value to the aggregator + + @param val + an object whose string representation represents a long value.]]> + </doc> + </method> + <method name="addNextValue" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="long"/> + <doc> + <![CDATA[add a value to the aggregator + + @param val + a long value.]]> + </doc> + </method> + <method name="getSum" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the aggregated value]]> + </doc> + </method> + <method name="getReport" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the string representation of the aggregated value]]> + </doc> + </method> + <method name="reset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[reset the aggregator]]> + </doc> + </method> + <method name="getCombinerOutput" return="java.util.ArrayList<java.lang.String>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return return an array of one element. The element is a string + representation of the aggregated value. The return value is + expected to be used by the a combiner.]]> + </doc> + </method> + <doc> + <![CDATA[This class implements a value aggregator that sums up + a sequence of long values.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.aggregate.LongValueSum --> + <!-- start class org.apache.hadoop.mapred.lib.aggregate.StringValueMax --> + <class name="StringValueMax" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.lib.aggregate.ValueAggregator"/> + <constructor name="StringValueMax" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[the default constructor]]> + </doc> + </constructor> + <method name="addNextValue" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="java.lang.Object"/> + <doc> + <![CDATA[add a value to the aggregator + + @param val + a string.]]> + </doc> + </method> + <method name="getVal" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the aggregated value]]> + </doc> + </method> + <method name="getReport" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the string representation of the aggregated value]]> + </doc> + </method> + <method name="reset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[reset the aggregator]]> + </doc> + </method> + <method name="getCombinerOutput" return="java.util.ArrayList<java.lang.String>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return return an array of one element. The element is a string + representation of the aggregated value. The return value is + expected to be used by the a combiner.]]> + </doc> + </method> + <doc> + <![CDATA[This class implements a value aggregator that maintain the biggest of + a sequence of strings.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.aggregate.StringValueMax --> + <!-- start class org.apache.hadoop.mapred.lib.aggregate.StringValueMin --> + <class name="StringValueMin" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.lib.aggregate.ValueAggregator"/> + <constructor name="StringValueMin" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[the default constructor]]> + </doc> + </constructor> + <method name="addNextValue" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="java.lang.Object"/> + <doc> + <![CDATA[add a value to the aggregator + + @param val + a string.]]> + </doc> + </method> + <method name="getVal" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the aggregated value]]> + </doc> + </method> + <method name="getReport" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the string representation of the aggregated value]]> + </doc> + </method> + <method name="reset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[reset the aggregator]]> + </doc> + </method> + <method name="getCombinerOutput" return="java.util.ArrayList<java.lang.String>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return return an array of one element. The element is a string + representation of the aggregated value. The return value is + expected to be used by the a combiner.]]> + </doc> + </method> + <doc> + <![CDATA[This class implements a value aggregator that maintain the smallest of + a sequence of strings.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.aggregate.StringValueMin --> + <!-- start class org.apache.hadoop.mapred.lib.aggregate.UniqValueCount --> + <class name="UniqValueCount" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.lib.aggregate.ValueAggregator"/> + <constructor name="UniqValueCount" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[the default constructor]]> + </doc> + </constructor> + <constructor name="UniqValueCount" type="long" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[constructor + @param maxNum the limit in the number of unique values to keep.]]> + </doc> + </constructor> + <method name="setMaxItems" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="n" type="long"/> + <doc> + <![CDATA[Set the limit on the number of unique values + @param n the desired limit on the number of unique values + @return the new limit on the number of unique values]]> + </doc> + </method> + <method name="addNextValue" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="java.lang.Object"/> + <doc> + <![CDATA[add a value to the aggregator + + @param val + an object.]]> + </doc> + </method> + <method name="getReport" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return return the number of unique objects aggregated]]> + </doc> + </method> + <method name="getUniqueItems" return="java.util.Set" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the set of the unique objects]]> + </doc> + </method> + <method name="reset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[reset the aggregator]]> + </doc> + </method> + <method name="getCombinerOutput" return="java.util.ArrayList" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return return an array of the unique objects. The return value is + expected to be used by the a combiner.]]> + </doc> + </method> + <doc> + <![CDATA[This class implements a value aggregator that dedupes a sequence of objects.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.aggregate.UniqValueCount --> + <!-- start class org.apache.hadoop.mapred.lib.aggregate.UserDefinedValueAggregatorDescriptor --> + <class name="UserDefinedValueAggregatorDescriptor" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorDescriptor"/> + <constructor name="UserDefinedValueAggregatorDescriptor" type="java.lang.String, org.apache.hadoop.mapred.JobConf" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@param className the class name of the user defined descriptor class + @param job a configure object used for decriptor configuration]]> + </doc> + </constructor> + <method name="createInstance" return="java.lang.Object" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="className" type="java.lang.String"/> + <doc> + <![CDATA[Create an instance of the given class + @param className the name of the class + @return a dynamically created instance of the given class]]> + </doc> + </method> + <method name="generateKeyValPairs" return="java.util.ArrayList<java.util.Map.Entry<org.apache.hadoop.io.Text, org.apache.hadoop.io.Text>>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="java.lang.Object"/> + <param name="val" type="java.lang.Object"/> + <doc> + <![CDATA[Generate a list of aggregation-id/value pairs for the given key/value pairs + by delegating the invocation to the real object. + + @param key + input key + @param val + input value + @return a list of aggregation id/value pairs. An aggregation id encodes an + aggregation type which is used to guide the way to aggregate the + value in the reduce/combiner phrase of an Aggregate based job.]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the string representation of this object.]]> + </doc> + </method> + <method name="configure" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <doc> + <![CDATA[Do nothing.]]> + </doc> + </method> + <doc> + <![CDATA[This class implements a wrapper for a user defined value aggregator descriptor. + It servs two functions: One is to create an object of ValueAggregatorDescriptor from the + name of a user defined class that may be dynamically loaded. The other is to + deligate inviokations of generateKeyValPairs function to the created object.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.aggregate.UserDefinedValueAggregatorDescriptor --> + <!-- start interface org.apache.hadoop.mapred.lib.aggregate.ValueAggregator --> + <interface name="ValueAggregator" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="addNextValue" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="java.lang.Object"/> + <doc> + <![CDATA[add a value to the aggregator + + @param val the value to be added]]> + </doc> + </method> + <method name="reset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[reset the aggregator]]> + </doc> + </method> + <method name="getReport" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the string representation of the agregator]]> + </doc> + </method> + <method name="getCombinerOutput" return="java.util.ArrayList" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return an array of values as the outputs of the combiner.]]> + </doc> + </method> + <doc> + <![CDATA[This interface defines the minimal protocol for value aggregators.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.mapred.lib.aggregate.ValueAggregator --> + <!-- start class org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorBaseDescriptor --> + <class name="ValueAggregatorBaseDescriptor" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorDescriptor"/> + <constructor name="ValueAggregatorBaseDescriptor" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="generateEntry" return="java.util.Map.Entry<org.apache.hadoop.io.Text, org.apache.hadoop.io.Text>" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="type" type="java.lang.String"/> + <param name="id" type="java.lang.String"/> + <param name="val" type="org.apache.hadoop.io.Text"/> + <doc> + <![CDATA[@param type the aggregation type + @param id the aggregation id + @param val the val associated with the id to be aggregated + @return an Entry whose key is the aggregation id prefixed with + the aggregation type.]]> + </doc> + </method> + <method name="generateValueAggregator" return="org.apache.hadoop.mapred.lib.aggregate.ValueAggregator" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="type" type="java.lang.String"/> + <doc> + <![CDATA[@param type the aggregation type + @return a value aggregator of the given type.]]> + </doc> + </method> + <method name="generateKeyValPairs" return="java.util.ArrayList<java.util.Map.Entry<org.apache.hadoop.io.Text, org.apache.hadoop.io.Text>>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="java.lang.Object"/> + <param name="val" type="java.lang.Object"/> + <doc> + <![CDATA[Generate 1 or 2 aggregation-id/value pairs for the given key/value pair. + The first id will be of type LONG_VALUE_SUM, with "record_count" as + its aggregation id. If the input is a file split, + the second id of the same type will be generated too, with the file name + as its aggregation id. This achieves the behavior of counting the total number + of records in the input data, and the number of records in each input file. + + @param key + input key + @param val + input value + @return a list of aggregation id/value pairs. An aggregation id encodes an + aggregation type which is used to guide the way to aggregate the + value in the reduce/combiner phrase of an Aggregate based job.]]> + </doc> + </method> + <method name="configure" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <doc> + <![CDATA[get the input file name. + + @param job a job configuration object]]> + </doc> + </method> + <field name="UNIQ_VALUE_COUNT" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="LONG_VALUE_SUM" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="DOUBLE_VALUE_SUM" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="VALUE_HISTOGRAM" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="LONG_VALUE_MAX" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="LONG_VALUE_MIN" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="STRING_VALUE_MAX" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="STRING_VALUE_MIN" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="inputFile" type="java.lang.String" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[This class implements the common functionalities of + the subclasses of ValueAggregatorDescriptor class.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorBaseDescriptor --> + <!-- start class org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorCombiner --> + <class name="ValueAggregatorCombiner" extends="org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorJobBase<K1, V1>" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="ValueAggregatorCombiner" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="configure" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <doc> + <![CDATA[Combiner does not need to configure.]]> + </doc> + </method> + <method name="reduce" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.Text"/> + <param name="values" type="java.util.Iterator<org.apache.hadoop.io.Text>"/> + <param name="output" type="org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.Text, org.apache.hadoop.io.Text>"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Combines values for a given key. + @param key the key is expected to be a Text object, whose prefix indicates + the type of aggregation to aggregate the values. + @param values the values to combine + @param output to collect combined values]]> + </doc> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Do nothing.]]> + </doc> + </method> + <method name="map" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="arg0" type="K1 extends org.apache.hadoop.io.WritableComparable"/> + <param name="arg1" type="V1 extends org.apache.hadoop.io.Writable"/> + <param name="arg2" type="org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.Text, org.apache.hadoop.io.Text>"/> + <param name="arg3" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Do nothing. Should not be called.]]> + </doc> + </method> + <doc> + <![CDATA[This class implements the generic combiner of Aggregate.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorCombiner --> + <!-- start interface org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorDescriptor --> + <interface name="ValueAggregatorDescriptor" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="generateKeyValPairs" return="java.util.ArrayList<java.util.Map.Entry<org.apache.hadoop.io.Text, org.apache.hadoop.io.Text>>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="java.lang.Object"/> + <param name="val" type="java.lang.Object"/> + <doc> + <![CDATA[Generate a list of aggregation-id/value pairs for the given key/value pair. + This function is usually called by the mapper of an Aggregate based job. + + @param key + input key + @param val + input value + @return a list of aggregation id/value pairs. An aggregation id encodes an + aggregation type which is used to guide the way to aggregate the + value in the reduce/combiner phrase of an Aggregate based job.]]> + </doc> + </method> + <method name="configure" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <doc> + <![CDATA[Configure the object + + @param job + a JobConf object that may contain the information that can be used + to configure the object.]]> + </doc> + </method> + <field name="TYPE_SEPARATOR" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="ONE" type="org.apache.hadoop.io.Text" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[This interface defines the contract a value aggregator descriptor must + support. Such a descriptor can be configured with a JobConf object. Its main + function is to generate a list of aggregation-id/value pairs. An aggregation + id encodes an aggregation type which is used to guide the way to aggregate + the value in the reduce/combiner phrase of an Aggregate based job.The mapper in + an Aggregate based map/reduce job may create one or more of + ValueAggregatorDescriptor objects at configuration time. For each input + key/value pair, the mapper will use those objects to create aggregation + id/value pairs.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorDescriptor --> + <!-- start class org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorJob --> + <class name="ValueAggregatorJob" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="ValueAggregatorJob" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="createValueAggregatorJobs" return="org.apache.hadoop.mapred.jobcontrol.JobControl" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <param name="descriptors" type="java.lang.Class[]"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="createValueAggregatorJobs" return="org.apache.hadoop.mapred.jobcontrol.JobControl" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="createValueAggregatorJob" return="org.apache.hadoop.mapred.JobConf" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create an Aggregate based map/reduce job. + + @param args the arguments used for job creation. Generic hadoop + arguments are accepted. + @return a JobConf object ready for submission. + + @throws IOException + @see GenericOptionsParser]]> + </doc> + </method> + <method name="createValueAggregatorJob" return="org.apache.hadoop.mapred.JobConf" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <param name="descriptors" type="java.lang.Class[]"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="setAggregatorDescriptors" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <param name="descriptors" type="java.lang.Class[]"/> + </method> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[create and run an Aggregate based map/reduce job. + + @param args the arguments used for job creation + @throws IOException]]> + </doc> + </method> + <doc> + <![CDATA[This is the main class for creating a map/reduce job using Aggregate + framework. The Aggregate is a specialization of map/reduce framework, + specilizing for performing various simple aggregations. + + Generally speaking, in order to implement an application using Map/Reduce + model, the developer is to implement Map and Reduce functions (and possibly + combine function). However, a lot of applications related to counting and + statistics computing have very similar characteristics. Aggregate abstracts + out the general patterns of these functions and implementing those patterns. + In particular, the package provides generic mapper/redducer/combiner classes, + and a set of built-in value aggregators, and a generic utility class that + helps user create map/reduce jobs using the generic class. The built-in + aggregators include: + + sum over numeric values count the number of distinct values compute the + histogram of values compute the minimum, maximum, media,average, standard + deviation of numeric values + + The developer using Aggregate will need only to provide a plugin class + conforming to the following interface: + + public interface ValueAggregatorDescriptor { public ArrayList<Entry> + generateKeyValPairs(Object key, Object value); public void + configure(JobConfjob); } + + The package also provides a base class, ValueAggregatorBaseDescriptor, + implementing the above interface. The user can extend the base class and + implement generateKeyValPairs accordingly. + + The primary work of generateKeyValPairs is to emit one or more key/value + pairs based on the input key/value pair. The key in an output key/value pair + encode two pieces of information: aggregation type and aggregation id. The + value will be aggregated onto the aggregation id according the aggregation + type. + + This class offers a function to generate a map/reduce job using Aggregate + framework. The function takes the following parameters: input directory spec + input format (text or sequence file) output directory a file specifying the + user plugin class]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorJob --> + <!-- start class org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorJobBase --> + <class name="ValueAggregatorJobBase" extends="java.lang.Object" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.Mapper<K1, V1, org.apache.hadoop.io.Text, org.apache.hadoop.io.Text>"/> + <implements name="org.apache.hadoop.mapred.Reducer<org.apache.hadoop.io.Text, org.apache.hadoop.io.Text, org.apache.hadoop.io.Text, org.apache.hadoop.io.Text>"/> + <constructor name="ValueAggregatorJobBase" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="configure" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + </method> + <method name="logSpec" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <field name="aggregatorDescriptorList" type="java.util.ArrayList<org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorDescriptor>" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[This abstract class implements some common functionalities of the + the generic mapper, reducer and combiner classes of Aggregate.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorJobBase --> + <!-- start class org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorMapper --> + <class name="ValueAggregatorMapper" extends="org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorJobBase<K1, V1>" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="ValueAggregatorMapper" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="map" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K1 extends org.apache.hadoop.io.WritableComparable"/> + <param name="value" type="V1 extends org.apache.hadoop.io.Writable"/> + <param name="output" type="org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.Text, org.apache.hadoop.io.Text>"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[the map function. It iterates through the value aggregator descriptor + list to generate aggregation id/value pairs and emit them.]]> + </doc> + </method> + <method name="reduce" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="arg0" type="org.apache.hadoop.io.Text"/> + <param name="arg1" type="java.util.Iterator<org.apache.hadoop.io.Text>"/> + <param name="arg2" type="org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.Text, org.apache.hadoop.io.Text>"/> + <param name="arg3" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Do nothing. Should not be called.]]> + </doc> + </method> + <doc> + <![CDATA[This class implements the generic mapper of Aggregate.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorMapper --> + <!-- start class org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorReducer --> + <class name="ValueAggregatorReducer" extends="org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorJobBase<K1, V1>" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="ValueAggregatorReducer" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="reduce" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="org.apache.hadoop.io.Text"/> + <param name="values" type="java.util.Iterator<org.apache.hadoop.io.Text>"/> + <param name="output" type="org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.Text, org.apache.hadoop.io.Text>"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[@param key + the key is expected to be a Text object, whose prefix indicates + the type of aggregation to aggregate the values. In effect, data + driven computing is achieved. It is assumed that each aggregator's + getReport method emits appropriate output for the aggregator. This + may be further customiized. + @value the values to be aggregated]]> + </doc> + </method> + <method name="map" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="arg0" type="K1 extends org.apache.hadoop.io.WritableComparable"/> + <param name="arg1" type="V1 extends org.apache.hadoop.io.Writable"/> + <param name="arg2" type="org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.Text, org.apache.hadoop.io.Text>"/> + <param name="arg3" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Do nothing. Should not be called]]> + </doc> + </method> + <doc> + <![CDATA[This class implements the generic reducer of Aggregate.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorReducer --> + <!-- start class org.apache.hadoop.mapred.lib.aggregate.ValueHistogram --> + <class name="ValueHistogram" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.lib.aggregate.ValueAggregator"/> + <constructor name="ValueHistogram" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="addNextValue" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="java.lang.Object"/> + <doc> + <![CDATA[add the given val to the aggregator. + + @param val the value to be added. It is expected to be a string + in the form of xxxx\tnum, meaning xxxx has num occurrences.]]> + </doc> + </method> + <method name="getReport" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the string representation of this aggregator. + It includes the following basic statistics of the histogram: + the number of unique values + the minimum value + the media value + the maximum value + the average value + the standard deviation]]> + </doc> + </method> + <method name="getReportDetails" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return a string representation of the list of value/frequence pairs of + the histogram]]> + </doc> + </method> + <method name="getCombinerOutput" return="java.util.ArrayList" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return a list value/frequence pairs. + The return value is expected to be used by the reducer.]]> + </doc> + </method> + <method name="getReportItems" return="java.util.TreeMap" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return a TreeMap representation of the histogram]]> + </doc> + </method> + <method name="reset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[reset the aggregator]]> + </doc> + </method> + <doc> + <![CDATA[This class implements a value aggregator that computes the + histogram of a sequence of strings.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.lib.aggregate.ValueHistogram --> + <doc> + <![CDATA[Classes for performing various counting and aggregations. +<p /> +<h2><a name="Aggregate"></a>Aggregate framework </h2> +<p /> +Generally speaking, in order to implement an application using Map/Reduce +model, the developer needs to implement Map and Reduce functions (and possibly +Combine function). However, for a lot of applications related to counting and +statistics computing, these functions have very similar +characteristics. This provides a package implementing +those patterns. In particular, the package provides a generic mapper class, +a reducer class and a combiner class, and a set of built-in value aggregators. +It also provides a generic utility class, ValueAggregatorJob, that offers a static function that +creates map/reduce jobs: +<blockquote> +<pre> +public static JobConf createValueAggregatorJob(String args[]) throws IOException; +</pre> +</blockquote> +To call this function, the user needs to pass in arguments specifying the input directories, the output directory, +the number of reducers, the input data format (textinputformat or sequencefileinputformat), and a file specifying user plugin class(es) to load by the mapper. +A user plugin class is responsible for specifying what +aggregators to use and what values are for which aggregators. +A plugin class must implement the following interface: +<blockquote> +<pre> + public interface ValueAggregatorDescriptor { + public ArrayList<Entry> generateKeyValPairs(Object key, Object value); + public void configure(JobConfjob); +} +</pre> +</blockquote> +Function generateKeyValPairs will generate aggregation key/value pairs for the +input key/value pair. Each aggregation key encodes two pieces of information: the aggregation type and aggregation ID. +The value is the value to be aggregated onto the aggregation ID according to the aggregation type. Here +is a simple example user plugin class for counting the words in the input texts: +<blockquote> +<pre> +public class WordCountAggregatorDescriptor extends ValueAggregatorBaseDescriptor { + public ArrayList<Entry> generateKeyValPairs(Object key, Object val) { + String words [] = val.toString().split(" |\t"); + ArrayList<Entry> retv = new ArrayList<Entry>(); + for (int i = 0; i < words.length; i++) { + retv.add(generateEntry(LONG_VALUE_SUM, words[i], ONE)) + } + return retv; + } + public void configure(JobConf job) {} +} +</pre> +</blockquote> +In the above code, LONG_VALUE_SUM is a string denoting the aggregation type LongValueSum, which sums over long values. +ONE denotes a string "1". Function generateEntry(LONG_VALUE_SUM, words[i], ONE) will inperpret the first argument as an aggregation type, the second as an aggregation ID, and the third argumnent as the value to be aggregated. The output will look like: "LongValueSum:xxxx", where XXXX is the string value of words[i]. The value will be "1". The mapper will call generateKeyValPairs(Object key, Object val) for each input key/value pair to generate the desired aggregation id/value pairs. +The down stream combiner/reducer will interpret these pairs as adding one to the aggregator XXXX. +<p /> +Class ValueAggregatorBaseDescriptor is a base class that user plugin classes can extend. Here is the XML fragment specifying the user plugin class: +<blockquote> +<pre> +<property> + <name>aggregator.descriptor.num</name> + <value>1</value> +</property> +<property> + <name>aggregator.descriptor.0</name> + <value>UserDefined,org.apache.hadoop.mapred.lib.aggregate.examples.WordCountAggregatorDescriptor</value> +</property> +</pre> +</blockquote> +Class ValueAggregatorBaseDescriptor itself provides a default implementation for generateKeyValPairs: +<blockquote> +<pre> +public ArrayList<Entry> generateKeyValPairs(Object key, Object val) { + ArrayList<Entry> retv = new ArrayList<Entry>(); + String countType = LONG_VALUE_SUM; + String id = "record_count"; + retv.add(generateEntry(countType, id, ONE)); + return retv; +} +</pre> +</blockquote> +Thus, if no user plugin class is specified, the default behavior of the map/reduce job is to count the number of records (lines) in the imput files. +<p /> +During runtime, the mapper will invoke the generateKeyValPairs function for each input key/value pair, and emit the generated +key/value pairs: +<blockquote> +<pre> +public void map(WritableComparable key, Writable value, + OutputCollector output, Reporter reporter) throws IOException { + Iterator iter = this.aggregatorDescriptorList.iterator(); + while (iter.hasNext()) { + ValueAggregatorDescriptor ad = (ValueAggregatorDescriptor) iter.next(); + Iterator<Entry> ens = ad.generateKeyValPairs(key, value).iterator(); + while (ens.hasNext()) { + Entry en = ens.next(); + output.collect((WritableComparable)en.getKey(), (Writable)en.getValue()); + } + } +} +</pre> +</blockquote> +The reducer will create an aggregator object for each key/value list pair, and perform the appropriate aggregation. +At the end, it will emit the aggregator's results: +<blockquote> +<pre> +public void reduce(WritableComparable key, Iterator values, + OutputCollector output, Reporter reporter) throws IOException { + String keyStr = key.toString(); + int pos = keyStr.indexOf(ValueAggregatorDescriptor.TYPE_SEPARATOR); + String type = keyStr.substring(0,pos); + keyStr = keyStr.substring(pos+ValueAggregatorDescriptor.TYPE_SEPARATOR.length()); + ValueAggregator aggregator = + ValueAggregatorBaseDescriptor.generateValueAggregator(type); + while (values.hasNext()) { + aggregator.addNextValue(values.next()); + } + String val = aggregator.getReport(); + key = new Text(keyStr); + output.collect(key, new Text(val)); +} +</pre> +</blockquote> +In order to be able to use combiner, all the aggregation type be aggregators must be associative and communitive. +The following are the types supported: <ul> +<li> LongValueSum: sum over long values +</li> <li> DoubleValueSum: sum over float/double values +</li> <li> uniqValueCount: count the number of distinct values +</li> <li> ValueHistogram: compute the histogram of values compute the minimum, maximum, media,average, standard deviation of numeric values +</li></ul> +<p /> +<h2><a name="Create_and_run"></a> Create and run an application </h2> +<p /> +To create an application, the user needs to do the following things: +<p /> +1. Implement a user plugin: +<blockquote> +<pre> +import org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorBaseDescriptor; +import org.apache.hadoop.mapred.JobConf; + +public class WordCountAggregatorDescriptor extends ValueAggregatorBaseDescriptor { + public void map(WritableComparable key, Writable value, + OutputCollector output, Reporter reporter) throws IOException { + } + public void configure(JobConf job) { + + } +} +</pre> +</blockquote> + +2. Create an xml file specifying the user plugin. +<p /> +3. Compile your java class and create a jar file, say wc.jar. + +<p /> +Finally, run the job: +<blockquote> +<pre> + hadoop jar wc.jar org.apache.hadoop.mapred.lib.aggregate..ValueAggregatorJob indirs outdir numofreducers textinputformat|sequencefileinputformat spec_file +</pre> +</blockquote> +<p />]]> + </doc> +</package> +<package name="org.apache.hadoop.mapred.pipes"> + <!-- start class org.apache.hadoop.mapred.pipes.Submitter --> + <class name="Submitter" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="Submitter" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getExecutable" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <doc> + <![CDATA[Get the URI of the application's executable. + @param conf + @return the URI where the application's executable is located]]> + </doc> + </method> + <method name="setExecutable" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <param name="executable" type="java.lang.String"/> + <doc> + <![CDATA[Set the URI for the application's executable. Normally this is a hdfs: + location. + @param conf + @param executable The URI of the application's executable.]]> + </doc> + </method> + <method name="setIsJavaRecordReader" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <param name="value" type="boolean"/> + <doc> + <![CDATA[Set whether the job is using a Java RecordReader. + @param conf the configuration to modify + @param value the new value]]> + </doc> + </method> + <method name="getIsJavaRecordReader" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <doc> + <![CDATA[Check whether the job is using a Java RecordReader + @param conf the configuration to check + @return is it a Java RecordReader?]]> + </doc> + </method> + <method name="setIsJavaMapper" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <param name="value" type="boolean"/> + <doc> + <![CDATA[Set whether the Mapper is written in Java. + @param conf the configuration to modify + @param value the new value]]> + </doc> + </method> + <method name="getIsJavaMapper" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <doc> + <![CDATA[Check whether the job is using a Java Mapper. + @param conf the configuration to check + @return is it a Java Mapper?]]> + </doc> + </method> + <method name="setIsJavaReducer" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <param name="value" type="boolean"/> + <doc> + <![CDATA[Set whether the Reducer is written in Java. + @param conf the configuration to modify + @param value the new value]]> + </doc> + </method> + <method name="getIsJavaReducer" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <doc> + <![CDATA[Check whether the job is using a Java Reducer. + @param conf the configuration to check + @return is it a Java Reducer?]]> + </doc> + </method> + <method name="setIsJavaRecordWriter" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <param name="value" type="boolean"/> + <doc> + <![CDATA[Set whether the job will use a Java RecordWriter. + @param conf the configuration to modify + @param value the new value to set]]> + </doc> + </method> + <method name="getIsJavaRecordWriter" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <doc> + <![CDATA[Will the reduce use a Java RecordWriter? + @param conf the configuration to check + @return true, if the output of the job will be written by Java]]> + </doc> + </method> + <method name="getKeepCommandFile" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <doc> + <![CDATA[Does the user want to keep the command file for debugging? If this is + true, pipes will write a copy of the command data to a file in the + task directory named "downlink.data", which may be used to run the C++ + program under the debugger. You probably also want to set + JobConf.setKeepFailedTaskFiles(true) to keep the entire directory from + being deleted. + To run using the data file, set the environment variable + "hadoop.pipes.command.file" to point to the file. + @param conf the configuration to check + @return will the framework save the command file?]]> + </doc> + </method> + <method name="setKeepCommandFile" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <param name="keep" type="boolean"/> + <doc> + <![CDATA[Set whether to keep the command file for debugging + @param conf the configuration to modify + @param keep the new value]]> + </doc> + </method> + <method name="submitJob" return="org.apache.hadoop.mapred.RunningJob" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.mapred.JobConf"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Submit a job to the map/reduce cluster. All of the necessary modifications + to the job to run under pipes are made to the configuration. + @param conf the job to submit to the cluster (MODIFIED) + @throws IOException]]> + </doc> + </method> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + <doc> + <![CDATA[Submit a pipes job based on the command line arguments. + @param args]]> + </doc> + </method> + <doc> + <![CDATA[The main entry point and job submitter. It may either be used as a command + line-based or API-based method to launch Pipes jobs.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.mapred.pipes.Submitter --> + <doc> + <![CDATA[Hadoop Pipes allows C++ code to use Hadoop DFS and map/reduce. The +primary approach is to split the C++ code into a separate process that +does the application specific code. In many ways, the approach will be +similar to Hadoop streaming, but using Writable serialization to +convert the types into bytes that are sent to the process via a +socket. + +<p> + +The class org.apache.hadoop.mapred.pipes.Submitter has a public static +method to submit a job as a JobConf and a main method that takes an +application and optional configuration file, input directories, and +output directory. The cli for the main looks like: + +<pre> +bin/hadoop pipes \ + [-conf <i>path</i>] \ + [-input <i>inputDir</i>] \ + [-output <i>outputDir</i>] \ + [-jar <i>applicationJarFile</i>] \ + [-inputformat <i>class</i>] \ + [-map <i>class</i>] \ + [-partitioner <i>class</i>] \ + [-reduce <i>class</i>] \ + [-writer <i>class</i>] \ + [-program <i>program url</i>] +</pre> + +<p> + +The application programs link against a thin C++ wrapper library that +handles the communication with the rest of the Hadoop system. The C++ +interface is "swigable" so that interfaces can be generated for python +and other scripting languages. All of the C++ functions and classes +are in the HadoopPipes namespace. The job may consist of any +combination of Java and C++ RecordReaders, Mappers, Paritioner, +Combiner, Reducer, and RecordWriter. + +<p> + +Hadoop Pipes has a generic Java class for handling the mapper and +reducer (PipesMapRunner and PipesReducer). They fork off the +application program and communicate with it over a socket. The +communication is handled by the C++ wrapper library and the +PipesMapRunner and PipesReducer. + +<p> + +The application program passes in a factory object that can create +the various objects needed by the framework to the runTask +function. The framework creates the Mapper or Reducer as +appropriate and calls the map or reduce method to invoke the +application's code. The JobConf is available to the application. + +<p> + +The Mapper and Reducer objects get all of their inputs, outputs, and +context via context objects. The advantage of using the context +objects is that their interface can be extended with additional +methods without breaking clients. Although this interface is different +from the current Java interface, the plan is to migrate the Java +interface in this direction. + +<p> + +Although the Java implementation is typed, the C++ interfaces of keys +and values is just a byte buffer. Since STL strings provide precisely +the right functionality and are standard, they will be used. The +decision to not use stronger types was to simplify the interface. + +<p> + +The application can also define combiner functions. The combiner will +be run locally by the framework in the application process to avoid +the round trip to the Java process and back. Because the compare +function is not available in C++, the combiner will use memcmp to +sort the inputs to the combiner. This is not as general as the Java +equivalent, which uses the user's comparator, but should cover the +majority of the use cases. As the map function outputs key/value +pairs, they will be buffered. When the buffer is full, it will be +sorted and passed to the combiner. The output of the combiner will be +sent to the Java process. + +<p> + +The application can also set a partition function to control which key +is given to a particular reduce. If a partition function is not +defined, the Java one will be used. The partition function will be +called by the C++ framework before the key/value pair is sent back to +Java.]]> + </doc> +</package> +<package name="org.apache.hadoop.metrics"> + <!-- start class org.apache.hadoop.metrics.ContextFactory --> + <class name="ContextFactory" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="ContextFactory" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of ContextFactory]]> + </doc> + </constructor> + <method name="getAttribute" return="java.lang.Object" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="attributeName" type="java.lang.String"/> + <doc> + <![CDATA[Returns the value of the named attribute, or null if there is no + attribute of that name. + + @param attributeName the attribute name + @return the attribute value]]> + </doc> + </method> + <method name="getAttributeNames" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the names of all the factory's attributes. + + @return the attribute names]]> + </doc> + </method> + <method name="setAttribute" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="attributeName" type="java.lang.String"/> + <param name="value" type="java.lang.Object"/> + <doc> + <![CDATA[Sets the named factory attribute to the specified value, creating it + if it did not already exist. If the value is null, this is the same as + calling removeAttribute. + + @param attributeName the attribute name + @param value the new attribute value]]> + </doc> + </method> + <method name="removeAttribute" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="attributeName" type="java.lang.String"/> + <doc> + <![CDATA[Removes the named attribute if it exists. + + @param attributeName the attribute name]]> + </doc> + </method> + <method name="getContext" return="org.apache.hadoop.metrics.MetricsContext" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="contextName" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/> + <exception name="InstantiationException" type="java.lang.InstantiationException"/> + <exception name="IllegalAccessException" type="java.lang.IllegalAccessException"/> + <doc> + <![CDATA[Returns the named MetricsContext instance, constructing it if necessary + using the factory's current configuration attributes. <p/> + + When constructing the instance, if the factory property + <i>contextName</i>.class</code> exists, + its value is taken to be the name of the class to instantiate. Otherwise, + the default is to create an instance of + <code>org.apache.hadoop.metrics.spi.NullContext</code>, which is a + dummy "no-op" context which will cause all metric data to be discarded. + + @param contextName the name of the context + @return the named MetricsContext]]> + </doc> + </method> + <method name="getNullContext" return="org.apache.hadoop.metrics.MetricsContext" + abstract="false" native="false" synchronized="true" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="contextName" type="java.lang.String"/> + <doc> + <![CDATA[Returns a "null" context - one which does nothing.]]> + </doc> + </method> + <method name="getFactory" return="org.apache.hadoop.metrics.ContextFactory" + abstract="false" native="false" synchronized="true" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns the singleton ContextFactory instance, constructing it if + necessary. <p/> + + When the instance is constructed, this method checks if the file + <code>hadoop-metrics.properties</code> exists on the class path. If it + exists, it must be in the format defined by java.util.Properties, and all + the properties in the file are set as attributes on the newly created + ContextFactory instance. + + @return the singleton ContextFactory instance]]> + </doc> + </method> + <doc> + <![CDATA[Factory class for creating MetricsContext objects. To obtain an instance + of this class, use the static <code>getFactory()</code> method.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.metrics.ContextFactory --> + <!-- start interface org.apache.hadoop.metrics.MetricsContext --> + <interface name="MetricsContext" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="getContextName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the context name. + + @return the context name]]> + </doc> + </method> + <method name="startMonitoring" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Starts or restarts monitoring, the emitting of metrics records as they are + updated.]]> + </doc> + </method> + <method name="stopMonitoring" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Stops monitoring. This does not free any data that the implementation + may have buffered for sending at the next timer event. It + is OK to call <code>startMonitoring()</code> again after calling + this. + @see #close()]]> + </doc> + </method> + <method name="isMonitoring" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns true if monitoring is currently in progress.]]> + </doc> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Stops monitoring and also frees any buffered data, returning this + object to its initial state.]]> + </doc> + </method> + <method name="createRecord" return="org.apache.hadoop.metrics.MetricsRecord" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="recordName" type="java.lang.String"/> + <doc> + <![CDATA[Creates a new MetricsRecord instance with the given <code>recordName</code>. + Throws an exception if the metrics implementation is configured with a fixed + set of record names and <code>recordName</code> is not in that set. + + @param recordName the name of the record + @throws MetricsException if recordName conflicts with configuration data]]> + </doc> + </method> + <method name="registerUpdater" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="updater" type="org.apache.hadoop.metrics.Updater"/> + <doc> + <![CDATA[Registers a callback to be called at regular time intervals, as + determined by the implementation-class specific configuration. + + @param updater object to be run periodically; it should updated + some metrics records and then return]]> + </doc> + </method> + <method name="unregisterUpdater" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="updater" type="org.apache.hadoop.metrics.Updater"/> + <doc> + <![CDATA[Removes a callback, if it exists. + + @param updater object to be removed from the callback list]]> + </doc> + </method> + <field name="DEFAULT_PERIOD" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Default period in seconds at which data is sent to the metrics system.]]> + </doc> + </field> + <doc> + <![CDATA[The main interface to the metrics package.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.metrics.MetricsContext --> + <!-- start class org.apache.hadoop.metrics.MetricsException --> + <class name="MetricsException" extends="java.lang.RuntimeException" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="MetricsException" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of MetricsException]]> + </doc> + </constructor> + <constructor name="MetricsException" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of MetricsException + + @param message an error message]]> + </doc> + </constructor> + <doc> + <![CDATA[General-purpose, unchecked metrics exception.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.metrics.MetricsException --> + <!-- start interface org.apache.hadoop.metrics.MetricsRecord --> + <interface name="MetricsRecord" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="getRecordName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the record name. + + @return the record name]]> + </doc> + </method> + <method name="setTag" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tagName" type="java.lang.String"/> + <param name="tagValue" type="java.lang.String"/> + <doc> + <![CDATA[Sets the named tag to the specified value. The tagValue may be null, + which is treated the same as an empty String. + + @param tagName name of the tag + @param tagValue new value of the tag + @throws MetricsException if the tagName conflicts with the configuration]]> + </doc> + </method> + <method name="setTag" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tagName" type="java.lang.String"/> + <param name="tagValue" type="int"/> + <doc> + <![CDATA[Sets the named tag to the specified value. + + @param tagName name of the tag + @param tagValue new value of the tag + @throws MetricsException if the tagName conflicts with the configuration]]> + </doc> + </method> + <method name="setTag" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tagName" type="java.lang.String"/> + <param name="tagValue" type="short"/> + <doc> + <![CDATA[Sets the named tag to the specified value. + + @param tagName name of the tag + @param tagValue new value of the tag + @throws MetricsException if the tagName conflicts with the configuration]]> + </doc> + </method> + <method name="setTag" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tagName" type="java.lang.String"/> + <param name="tagValue" type="byte"/> + <doc> + <![CDATA[Sets the named tag to the specified value. + + @param tagName name of the tag + @param tagValue new value of the tag + @throws MetricsException if the tagName conflicts with the configuration]]> + </doc> + </method> + <method name="removeTag" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tagName" type="java.lang.String"/> + <doc> + <![CDATA[Removes any tag of the specified name. + + @param tagName name of a tag]]> + </doc> + </method> + <method name="setMetric" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="metricName" type="java.lang.String"/> + <param name="metricValue" type="int"/> + <doc> + <![CDATA[Sets the named metric to the specified value. + + @param metricName name of the metric + @param metricValue new value of the metric + @throws MetricsException if the metricName or the type of the metricValue + conflicts with the configuration]]> + </doc> + </method> + <method name="setMetric" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="metricName" type="java.lang.String"/> + <param name="metricValue" type="short"/> + <doc> + <![CDATA[Sets the named metric to the specified value. + + @param metricName name of the metric + @param metricValue new value of the metric + @throws MetricsException if the metricName or the type of the metricValue + conflicts with the configuration]]> + </doc> + </method> + <method name="setMetric" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="metricName" type="java.lang.String"/> + <param name="metricValue" type="byte"/> + <doc> + <![CDATA[Sets the named metric to the specified value. + + @param metricName name of the metric + @param metricValue new value of the metric + @throws MetricsException if the metricName or the type of the metricValue + conflicts with the configuration]]> + </doc> + </method> + <method name="setMetric" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="metricName" type="java.lang.String"/> + <param name="metricValue" type="float"/> + <doc> + <![CDATA[Sets the named metric to the specified value. + + @param metricName name of the metric + @param metricValue new value of the metric + @throws MetricsException if the metricName or the type of the metricValue + conflicts with the configuration]]> + </doc> + </method> + <method name="incrMetric" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="metricName" type="java.lang.String"/> + <param name="metricValue" type="int"/> + <doc> + <![CDATA[Increments the named metric by the specified value. + + @param metricName name of the metric + @param metricValue incremental value + @throws MetricsException if the metricName or the type of the metricValue + conflicts with the configuration]]> + </doc> + </method> + <method name="incrMetric" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="metricName" type="java.lang.String"/> + <param name="metricValue" type="short"/> + <doc> + <![CDATA[Increments the named metric by the specified value. + + @param metricName name of the metric + @param metricValue incremental value + @throws MetricsException if the metricName or the type of the metricValue + conflicts with the configuration]]> + </doc> + </method> + <method name="incrMetric" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="metricName" type="java.lang.String"/> + <param name="metricValue" type="byte"/> + <doc> + <![CDATA[Increments the named metric by the specified value. + + @param metricName name of the metric + @param metricValue incremental value + @throws MetricsException if the metricName or the type of the metricValue + conflicts with the configuration]]> + </doc> + </method> + <method name="incrMetric" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="metricName" type="java.lang.String"/> + <param name="metricValue" type="float"/> + <doc> + <![CDATA[Increments the named metric by the specified value. + + @param metricName name of the metric + @param metricValue incremental value + @throws MetricsException if the metricName or the type of the metricValue + conflicts with the configuration]]> + </doc> + </method> + <method name="update" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Updates the table of buffered data which is to be sent periodically. + If the tag values match an existing row, that row is updated; + otherwise, a new row is added.]]> + </doc> + </method> + <method name="remove" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Removes, from the buffered data table, all rows having tags + that equal the tags that have been set on this record. For example, + if there are no tags on this record, all rows for this record name + would be removed. Or, if there is a single tag on this record, then + just rows containing a tag with the same name and value would be removed.]]> + </doc> + </method> + <doc> + <![CDATA[A named and optionally tagged set of records to be sent to the metrics + system. <p/> + + A record name identifies the kind of data to be reported. For example, a + program reporting statistics relating to the disks on a computer might use + a record name "diskStats".<p/> + + A record has zero or more <i>tags</i>. A tag has a name and a value. To + continue the example, the "diskStats" record might use a tag named + "diskName" to identify a particular disk. Sometimes it is useful to have + more than one tag, so there might also be a "diskType" with value "ide" or + "scsi" or whatever.<p/> + + A record also has zero or more <i>metrics</i>. These are the named + values that are to be reported to the metrics system. In the "diskStats" + example, possible metric names would be "diskPercentFull", "diskPercentBusy", + "kbReadPerSecond", etc.<p/> + + The general procedure for using a MetricsRecord is to fill in its tag and + metric values, and then call <code>update()</code> to pass the record to the + client library. + Metric data is not immediately sent to the metrics system + each time that <code>update()</code> is called. + An internal table is maintained, identified by the record name. This + table has columns + corresponding to the tag and the metric names, and rows + corresponding to each unique set of tag values. An update + either modifies an existing row in the table, or adds a new row with a set of + tag values that are different from all the other rows. Note that if there + are no tags, then there can be at most one row in the table. <p/> + + Once a row is added to the table, its data will be sent to the metrics system + on every timer period, whether or not it has been updated since the previous + timer period. If this is inappropriate, for example if metrics were being + reported by some transient object in an application, the <code>remove()</code> + method can be used to remove the row and thus stop the data from being + sent.<p/> + + Note that the <code>update()</code> method is atomic. This means that it is + safe for different threads to be updating the same metric. More precisely, + it is OK for different threads to call <code>update()</code> on MetricsRecord instances + with the same set of tag names and tag values. Different threads should + <b>not</b> use the same MetricsRecord instance at the same time.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.metrics.MetricsRecord --> + <!-- start class org.apache.hadoop.metrics.MetricsUtil --> + <class name="MetricsUtil" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="getContext" return="org.apache.hadoop.metrics.MetricsContext" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="contextName" type="java.lang.String"/> + <doc> + <![CDATA[Utility method to return the named context. + If the desired context cannot be created for any reason, the exception + is logged, and a null context is returned.]]> + </doc> + </method> + <method name="createRecord" return="org.apache.hadoop.metrics.MetricsRecord" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="context" type="org.apache.hadoop.metrics.MetricsContext"/> + <param name="recordName" type="java.lang.String"/> + <doc> + <![CDATA[Utility method to create and return new metrics record instance within the + given context. This record is tagged with the host name. + + @param context the context + @param recordName name of the record + @return newly created metrics record]]> + </doc> + </method> + <doc> + <![CDATA[Utility class to simplify creation and reporting of hadoop metrics. + + For examples of usage, see {@link org.apache.hadoop.dfs.DataNode}. + @see org.apache.hadoop.metrics.MetricsRecord + @see org.apache.hadoop.metrics.MetricsContext + @see org.apache.hadoop.metrics.ContextFactory]]> + </doc> + </class> + <!-- end class org.apache.hadoop.metrics.MetricsUtil --> + <!-- start interface org.apache.hadoop.metrics.Updater --> + <interface name="Updater" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="doUpdates" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="context" type="org.apache.hadoop.metrics.MetricsContext"/> + <doc> + <![CDATA[Timer-based call-back from the metric library.]]> + </doc> + </method> + <doc> + <![CDATA[Call-back interface. See <code>MetricsContext.registerUpdater()</code>.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.metrics.Updater --> + <doc> + <![CDATA[This package defines an API for reporting performance metric information. +<p/> +The API is abstract so that it can be implemented on top of +a variety of metrics client libraries. The choice of +client library is a configuration option, and different +modules within the same application can use +different metrics implementation libraries. +<p/> +Sub-packages: +<dl> + <dt><code>org.apache.hadoop.metrics.spi</code></dt> + <dd>The abstract Server Provider Interface package. Those wishing to + integrate the metrics API with a particular metrics client library should + extend this package.</dd> + + <dt><code>org.apache.hadoop.metrics.file</code></dt> + <dd>An implementation package which writes the metric data to + a file, or sends it to the standard output stream.</dd> + + <dt> <code>org.apache.hadoop.metrics.ganglia</code></dt> + <dd>An implementation package which sends metric data to + <a href="http://ganglia.sourceforge.net/">Ganglia</a>.</dd> +</dl> + +<h3>Introduction to the Metrics API</h3> + +Here is a simple example of how to use this package to report a single +metric value: +<pre> + private ContextFactory contextFactory = ContextFactory.getFactory(); + + void reportMyMetric(float myMetric) { + MetricsContext myContext = contextFactory.getContext("myContext"); + MetricsRecord myRecord = myContext.getRecord("myRecord"); + myRecord.setMetric("myMetric", myMetric); + myRecord.update(); + } +</pre> + +In this example there are three names: +<dl> + <dt><i>myContext</i></dt> + <dd>The context name will typically identify either the application, or else a + module within an application or library.</dd> + + <dt><i>myRecord</i></dt> + <dd>The record name generally identifies some entity for which a set of + metrics are to be reported. For example, you could have a record named + "cacheStats" for reporting a number of statistics relating to the usage of + some cache in your application.</dd> + + <dt><i>myMetric</i></dt> + <dd>This identifies a particular metric. For example, you might have metrics + named "cache_hits" and "cache_misses". + </dd> +</dl> + +<h3>Tags</h3> + +In some cases it is useful to have multiple records with the same name. For +example, suppose that you want to report statistics about each disk on a computer. +In this case, the record name would be something like "diskStats", but you also +need to identify the disk which is done by adding a <i>tag</i> to the record. +The code could look something like this: +<pre> + private MetricsRecord diskStats = + contextFactory.getContext("myContext").getRecord("diskStats"); + + void reportDiskMetrics(String diskName, float diskBusy, float diskUsed) { + diskStats.setTag("diskName", diskName); + diskStats.setMetric("diskBusy", diskBusy); + diskStats.setMetric("diskUsed", diskUsed); + diskStats.update(); + } +</pre> + +<h3>Buffering and Callbacks</h3> + +Data is not sent immediately to the metrics system when +<code>MetricsRecord.update()</code> is called. Instead it is stored in an +internal table, and the contents of the table are sent periodically. +This can be important for two reasons: +<ol> + <li>It means that a programmer is free to put calls to this API in an + inner loop, since updates can be very frequent without slowing down + the application significantly.</li> + <li>Some implementations can gain efficiency by combining many metrics + into a single UDP message.</li> +</ol> + +The API provides a timer-based callback via the +<code>registerUpdater()</code> method. The benefit of this +versus using <code>java.util.Timer</code> is that the callbacks will be done +immediately before sending the data, making the data as current as possible. + +<h3>Configuration</h3> + +It is possible to programmatically examine and modify configuration data +before creating a context, like this: +<pre> + ContextFactory factory = ContextFactory.getFactory(); + ... examine and/or modify factory attributes ... + MetricsContext context = factory.getContext("myContext"); +</pre> +The factory attributes can be examined and modified using the following +<code>ContextFactory</code>methods: +<ul> + <li><code>Object getAttribute(String attributeName)</code></li> + <li><code>String[] getAttributeNames()</code></li> + <li><code>void setAttribute(String name, Object value)</code></li> + <li><code>void removeAttribute(attributeName)</code></li> +</ul> + +<p/> +<code>ContextFactory.getFactory()</code> initializes the factory attributes by +reading the properties file <code>hadoop-metrics.properties</code> if it exists +on the class path. + +<p/> +A factory attribute named: +<pre> +<i>contextName</i>.class +</pre> +should have as its value the fully qualified name of the class to be +instantiated by a call of the <code>CodeFactory</code> method +<code>getContext(<i>contextName</i>)</code>. If this factory attribute is not +specified, the default is to instantiate +<code>org.apache.hadoop.metrics.file.FileContext</code>. + +<p/> +Other factory attributes are specific to a particular implementation of this +API and are documented elsewhere. For example, configuration attributes for +the file and Ganglia implementations can be found in the javadoc for +their respective packages.]]> + </doc> +</package> +<package name="org.apache.hadoop.metrics.file"> + <!-- start class org.apache.hadoop.metrics.file.FileContext --> + <class name="FileContext" extends="org.apache.hadoop.metrics.spi.AbstractMetricsContext" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="FileContext" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of FileContext]]> + </doc> + </constructor> + <method name="init" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="contextName" type="java.lang.String"/> + <param name="factory" type="org.apache.hadoop.metrics.ContextFactory"/> + </method> + <method name="getFileName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the configured file name, or null.]]> + </doc> + </method> + <method name="startMonitoring" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Starts or restarts monitoring, by opening in append-mode, the + file specified by the <code>fileName</code> attribute, + if specified. Otherwise the data will be written to standard + output.]]> + </doc> + </method> + <method name="stopMonitoring" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Stops monitoring, closing the file. + @see #close()]]> + </doc> + </method> + <method name="emitRecord" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="contextName" type="java.lang.String"/> + <param name="recordName" type="java.lang.String"/> + <param name="outRec" type="org.apache.hadoop.metrics.spi.OutputRecord"/> + <doc> + <![CDATA[Emits a metrics record to a file.]]> + </doc> + </method> + <method name="flush" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Flushes the output writer, forcing updates to disk.]]> + </doc> + </method> + <field name="FILE_NAME_PROPERTY" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="PERIOD_PROPERTY" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="protected" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[Metrics context for writing metrics to a file.<p/> + + This class is configured by setting ContextFactory attributes which in turn + are usually configured through a properties file. All the attributes are + prefixed by the contextName. For example, the properties file might contain: + <pre> + myContextName.fileName=/tmp/metrics.log + myContextName.period=5 + </pre>]]> + </doc> + </class> + <!-- end class org.apache.hadoop.metrics.file.FileContext --> + <doc> + <![CDATA[Implementation of the metrics package that writes the metrics to a file. +Programmers should not normally need to use this package directly. Instead +they should use org.hadoop.metrics. + +<p/> +These are the implementation specific factory attributes +(See ContextFactory.getFactory()): + +<dl> + <dt><i>contextName</i>.fileName</dt> + <dd>The path of the file to which metrics in context <i>contextName</i> + are to be appended. If this attribute is not specified, the metrics + are written to standard output by default.</dd> + + <dt><i>contextName</i>.period</dt> + <dd>The period in seconds on which the metric data is written to the + file.</dd> + +</dl>]]> + </doc> +</package> +<package name="org.apache.hadoop.metrics.ganglia"> + <!-- start class org.apache.hadoop.metrics.ganglia.GangliaContext --> + <class name="GangliaContext" extends="org.apache.hadoop.metrics.spi.AbstractMetricsContext" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="GangliaContext" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of GangliaContext]]> + </doc> + </constructor> + <method name="init" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="contextName" type="java.lang.String"/> + <param name="factory" type="org.apache.hadoop.metrics.ContextFactory"/> + </method> + <method name="emitRecord" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="contextName" type="java.lang.String"/> + <param name="recordName" type="java.lang.String"/> + <param name="outRec" type="org.apache.hadoop.metrics.spi.OutputRecord"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[Context for sending metrics to Ganglia.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.metrics.ganglia.GangliaContext --> + <doc> + <![CDATA[<!-- + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. +--> + +Implementation of the metrics package that sends metric data to +<a href="http://ganglia.sourceforge.net/">Ganglia</a>. +Programmers should not normally need to use this package directly. Instead +they should use org.hadoop.metrics. + +<p/> +These are the implementation specific factory attributes +(See ContextFactory.getFactory()): + +<dl> + <dt><i>contextName</i>.servers</dt> + <dd>Space and/or comma separated sequence of servers to which UDP + messages should be sent.</dd> + + <dt><i>contextName</i>.period</dt> + <dd>The period in seconds on which the metric data is sent to the + server(s).</dd> + + <dt><i>contextName</i>.units.<i>recordName</i>.<i>metricName</i></dt> + <dd>The units for the specified metric in the specified record.</dd> + + <dt><i>contextName</i>.slope.<i>recordName</i>.<i>metricName</i></dt> + <dd>The slope for the specified metric in the specified record.</dd> + + <dt><i>contextName</i>.tmax.<i>recordName</i>.<i>metricName</i></dt> + <dd>The tmax for the specified metric in the specified record.</dd> + + <dt><i>contextName</i>.dmax.<i>recordName</i>.<i>metricName</i></dt> + <dd>The dmax for the specified metric in the specified record.</dd> + +</dl>]]> + </doc> +</package> +<package name="org.apache.hadoop.metrics.jvm"> + <!-- start class org.apache.hadoop.metrics.jvm.EventCounter --> + <class name="EventCounter" extends="org.apache.log4j.AppenderSkeleton" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="EventCounter" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getFatal" return="long" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getError" return="long" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getWarn" return="long" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getInfo" return="long" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="append" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="event" type="org.apache.log4j.spi.LoggingEvent"/> + </method> + <method name="close" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="requiresLayout" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[A log4J Appender that simply counts logging events in three levels: + fatal, error and warn.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.metrics.jvm.EventCounter --> + <!-- start class org.apache.hadoop.metrics.jvm.JvmMetrics --> + <class name="JvmMetrics" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.metrics.Updater"/> + <method name="init" return="org.apache.hadoop.metrics.jvm.JvmMetrics" + abstract="false" native="false" synchronized="true" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="processName" type="java.lang.String"/> + <param name="sessionId" type="java.lang.String"/> + </method> + <method name="doUpdates" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="context" type="org.apache.hadoop.metrics.MetricsContext"/> + <doc> + <![CDATA[This will be called periodically (with the period being configuration + dependent).]]> + </doc> + </method> + <doc> + <![CDATA[Singleton class which eports Java Virtual Machine metrics to the metrics API. + Any application can create an instance of this class in order to emit + Java VM metrics.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.metrics.jvm.JvmMetrics --> +</package> +<package name="org.apache.hadoop.metrics.spi"> + <!-- start class org.apache.hadoop.metrics.spi.AbstractMetricsContext --> + <class name="AbstractMetricsContext" extends="java.lang.Object" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.metrics.MetricsContext"/> + <constructor name="AbstractMetricsContext" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of AbstractMetricsContext]]> + </doc> + </constructor> + <method name="init" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="contextName" type="java.lang.String"/> + <param name="factory" type="org.apache.hadoop.metrics.ContextFactory"/> + <doc> + <![CDATA[Initializes the context.]]> + </doc> + </method> + <method name="getAttribute" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="attributeName" type="java.lang.String"/> + <doc> + <![CDATA[Convenience method for subclasses to access factory attributes.]]> + </doc> + </method> + <method name="getAttributeTable" return="java.util.Map<java.lang.String, java.lang.String>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="tableName" type="java.lang.String"/> + <doc> + <![CDATA[Returns an attribute-value map derived from the factory attributes + by finding all factory attributes that begin with + <i>contextName</i>.<i>tableName</i>. The returned map consists of + those attributes with the contextName and tableName stripped off.]]> + </doc> + </method> + <method name="getContextName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the context name.]]> + </doc> + </method> + <method name="getContextFactory" return="org.apache.hadoop.metrics.ContextFactory" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the factory by which this context was created.]]> + </doc> + </method> + <method name="startMonitoring" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Starts or restarts monitoring, the emitting of metrics records.]]> + </doc> + </method> + <method name="stopMonitoring" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Stops monitoring. This does not free buffered data. + @see #close()]]> + </doc> + </method> + <method name="isMonitoring" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns true if monitoring is currently in progress.]]> + </doc> + </method> + <method name="close" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Stops monitoring and frees buffered data, returning this + object to its initial state.]]> + </doc> + </method> + <method name="createRecord" return="org.apache.hadoop.metrics.MetricsRecord" + abstract="false" native="false" synchronized="true" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <param name="recordName" type="java.lang.String"/> + <doc> + <![CDATA[Creates a new AbstractMetricsRecord instance with the given <code>recordName</code>. + Throws an exception if the metrics implementation is configured with a fixed + set of record names and <code>recordName</code> is not in that set. + + @param recordName the name of the record + @throws MetricsException if recordName conflicts with configuration data]]> + </doc> + </method> + <method name="newRecord" return="org.apache.hadoop.metrics.spi.MetricsRecordImpl" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="recordName" type="java.lang.String"/> + <doc> + <![CDATA[Subclasses should override this if they subclass MetricsRecordImpl. + @param recordName the name of the record + @return newly created instance of MetricsRecordImpl or subclass]]> + </doc> + </method> + <method name="registerUpdater" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="updater" type="org.apache.hadoop.metrics.Updater"/> + <doc> + <![CDATA[Registers a callback to be called at time intervals determined by + the configuration. + + @param updater object to be run periodically; it should update + some metrics records]]> + </doc> + </method> + <method name="unregisterUpdater" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="updater" type="org.apache.hadoop.metrics.Updater"/> + <doc> + <![CDATA[Removes a callback, if it exists. + + @param updater object to be removed from the callback list]]> + </doc> + </method> + <method name="emitRecord" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="contextName" type="java.lang.String"/> + <param name="recordName" type="java.lang.String"/> + <param name="outRec" type="org.apache.hadoop.metrics.spi.OutputRecord"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Sends a record to the metrics system.]]> + </doc> + </method> + <method name="flush" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Called each period after all records have been emitted, this method does nothing. + Subclasses may override it in order to perform some kind of flush.]]> + </doc> + </method> + <method name="update" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="record" type="org.apache.hadoop.metrics.spi.MetricsRecordImpl"/> + <doc> + <![CDATA[Called by MetricsRecordImpl.update(). Creates or updates a row in + the internal table of metric data.]]> + </doc> + </method> + <method name="remove" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="record" type="org.apache.hadoop.metrics.spi.MetricsRecordImpl"/> + <doc> + <![CDATA[Called by MetricsRecordImpl.remove(). Removes all matching rows in + the internal table of metric data. A row matches if it has the same + tag names and values as record, but it may also have additional + tags.]]> + </doc> + </method> + <method name="getPeriod" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the timer period.]]> + </doc> + </method> + <method name="setPeriod" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="period" type="int"/> + <doc> + <![CDATA[Sets the timer period]]> + </doc> + </method> + <doc> + <![CDATA[The main class of the Service Provider Interface. This class should be + extended in order to integrate the Metrics API with a specific metrics + client library. <p/> + + This class implements the internal table of metric data, and the timer + on which data is to be sent to the metrics system. Subclasses must + override the abstract <code>emitRecord</code> method in order to transmit + the data. <p/>]]> + </doc> + </class> + <!-- end class org.apache.hadoop.metrics.spi.AbstractMetricsContext --> + <!-- start class org.apache.hadoop.metrics.spi.MetricsRecordImpl --> + <class name="MetricsRecordImpl" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.metrics.MetricsRecord"/> + <constructor name="MetricsRecordImpl" type="java.lang.String, org.apache.hadoop.metrics.spi.AbstractMetricsContext" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of FileRecord]]> + </doc> + </constructor> + <method name="getRecordName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the record name. + + @return the record name]]> + </doc> + </method> + <method name="setTag" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tagName" type="java.lang.String"/> + <param name="tagValue" type="java.lang.String"/> + <doc> + <![CDATA[Sets the named tag to the specified value. + + @param tagName name of the tag + @param tagValue new value of the tag + @throws MetricsException if the tagName conflicts with the configuration]]> + </doc> + </method> + <method name="setTag" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tagName" type="java.lang.String"/> + <param name="tagValue" type="int"/> + <doc> + <![CDATA[Sets the named tag to the specified value. + + @param tagName name of the tag + @param tagValue new value of the tag + @throws MetricsException if the tagName conflicts with the configuration]]> + </doc> + </method> + <method name="setTag" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tagName" type="java.lang.String"/> + <param name="tagValue" type="short"/> + <doc> + <![CDATA[Sets the named tag to the specified value. + + @param tagName name of the tag + @param tagValue new value of the tag + @throws MetricsException if the tagName conflicts with the configuration]]> + </doc> + </method> + <method name="setTag" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tagName" type="java.lang.String"/> + <param name="tagValue" type="byte"/> + <doc> + <![CDATA[Sets the named tag to the specified value. + + @param tagName name of the tag + @param tagValue new value of the tag + @throws MetricsException if the tagName conflicts with the configuration]]> + </doc> + </method> + <method name="removeTag" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tagName" type="java.lang.String"/> + <doc> + <![CDATA[Removes any tag of the specified name.]]> + </doc> + </method> + <method name="setMetric" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="metricName" type="java.lang.String"/> + <param name="metricValue" type="int"/> + <doc> + <![CDATA[Sets the named metric to the specified value. + + @param metricName name of the metric + @param metricValue new value of the metric + @throws MetricsException if the metricName or the type of the metricValue + conflicts with the configuration]]> + </doc> + </method> + <method name="setMetric" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="metricName" type="java.lang.String"/> + <param name="metricValue" type="short"/> + <doc> + <![CDATA[Sets the named metric to the specified value. + + @param metricName name of the metric + @param metricValue new value of the metric + @throws MetricsException if the metricName or the type of the metricValue + conflicts with the configuration]]> + </doc> + </method> + <method name="setMetric" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="metricName" type="java.lang.String"/> + <param name="metricValue" type="byte"/> + <doc> + <![CDATA[Sets the named metric to the specified value. + + @param metricName name of the metric + @param metricValue new value of the metric + @throws MetricsException if the metricName or the type of the metricValue + conflicts with the configuration]]> + </doc> + </method> + <method name="setMetric" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="metricName" type="java.lang.String"/> + <param name="metricValue" type="float"/> + <doc> + <![CDATA[Sets the named metric to the specified value. + + @param metricName name of the metric + @param metricValue new value of the metric + @throws MetricsException if the metricName or the type of the metricValue + conflicts with the configuration]]> + </doc> + </method> + <method name="incrMetric" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="metricName" type="java.lang.String"/> + <param name="metricValue" type="int"/> + <doc> + <![CDATA[Increments the named metric by the specified value. + + @param metricName name of the metric + @param metricValue incremental value + @throws MetricsException if the metricName or the type of the metricValue + conflicts with the configuration]]> + </doc> + </method> + <method name="incrMetric" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="metricName" type="java.lang.String"/> + <param name="metricValue" type="short"/> + <doc> + <![CDATA[Increments the named metric by the specified value. + + @param metricName name of the metric + @param metricValue incremental value + @throws MetricsException if the metricName or the type of the metricValue + conflicts with the configuration]]> + </doc> + </method> + <method name="incrMetric" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="metricName" type="java.lang.String"/> + <param name="metricValue" type="byte"/> + <doc> + <![CDATA[Increments the named metric by the specified value. + + @param metricName name of the metric + @param metricValue incremental value + @throws MetricsException if the metricName or the type of the metricValue + conflicts with the configuration]]> + </doc> + </method> + <method name="incrMetric" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="metricName" type="java.lang.String"/> + <param name="metricValue" type="float"/> + <doc> + <![CDATA[Increments the named metric by the specified value. + + @param metricName name of the metric + @param metricValue incremental value + @throws MetricsException if the metricName or the type of the metricValue + conflicts with the configuration]]> + </doc> + </method> + <method name="update" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Updates the table of buffered data which is to be sent periodically. + If the tag values match an existing row, that row is updated; + otherwise, a new row is added.]]> + </doc> + </method> + <method name="remove" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Removes the row, if it exists, in the buffered data table having tags + that equal the tags that have been set on this record.]]> + </doc> + </method> + <doc> + <![CDATA[An implementation of MetricsRecord. Keeps a back-pointer to the context + from which it was created, and delegates back to it on <code>update</code> + and <code>remove()</code>.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.metrics.spi.MetricsRecordImpl --> + <!-- start class org.apache.hadoop.metrics.spi.MetricValue --> + <class name="MetricValue" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="MetricValue" type="java.lang.Number, boolean" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of MetricValue]]> + </doc> + </constructor> + <method name="isIncrement" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="isAbsolute" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getNumber" return="java.lang.Number" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <field name="ABSOLUTE" type="boolean" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="INCREMENT" type="boolean" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[A Number that is either an absolute or an incremental amount.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.metrics.spi.MetricValue --> + <!-- start class org.apache.hadoop.metrics.spi.NullContext --> + <class name="NullContext" extends="org.apache.hadoop.metrics.spi.AbstractMetricsContext" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="NullContext" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of NullContext]]> + </doc> + </constructor> + <method name="startMonitoring" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Do-nothing version of startMonitoring]]> + </doc> + </method> + <method name="emitRecord" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="contextName" type="java.lang.String"/> + <param name="recordName" type="java.lang.String"/> + <param name="outRec" type="org.apache.hadoop.metrics.spi.OutputRecord"/> + <doc> + <![CDATA[Do-nothing version of emitRecord]]> + </doc> + </method> + <method name="update" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="record" type="org.apache.hadoop.metrics.spi.MetricsRecordImpl"/> + <doc> + <![CDATA[Do-nothing version of update]]> + </doc> + </method> + <method name="remove" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="record" type="org.apache.hadoop.metrics.spi.MetricsRecordImpl"/> + <doc> + <![CDATA[Do-nothing version of remove]]> + </doc> + </method> + <doc> + <![CDATA[Null metrics context: a metrics context which does nothing. Used as the + default context, so that no performance data is emitted if no configuration + data is found.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.metrics.spi.NullContext --> + <!-- start class org.apache.hadoop.metrics.spi.NullContextWithUpdateThread --> + <class name="NullContextWithUpdateThread" extends="org.apache.hadoop.metrics.spi.AbstractMetricsContext" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="NullContextWithUpdateThread" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of NullContextWithUpdateThread]]> + </doc> + </constructor> + <method name="init" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="contextName" type="java.lang.String"/> + <param name="factory" type="org.apache.hadoop.metrics.ContextFactory"/> + </method> + <method name="emitRecord" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="contextName" type="java.lang.String"/> + <param name="recordName" type="java.lang.String"/> + <param name="outRec" type="org.apache.hadoop.metrics.spi.OutputRecord"/> + <doc> + <![CDATA[Do-nothing version of emitRecord]]> + </doc> + </method> + <method name="update" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="record" type="org.apache.hadoop.metrics.spi.MetricsRecordImpl"/> + <doc> + <![CDATA[Do-nothing version of update]]> + </doc> + </method> + <method name="remove" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="record" type="org.apache.hadoop.metrics.spi.MetricsRecordImpl"/> + <doc> + <![CDATA[Do-nothing version of remove]]> + </doc> + </method> + <doc> + <![CDATA[A null context which has a thread calling + periodically when monitoring is started. This keeps the data sampled + correctly. + In all other respects, this is like the NULL context: No data is emitted. + This is suitable for Monitoring systems like JMX which reads the metrics + when someone reads the data from JMX. + + The default impl of start and stop monitoring: + is the AbstractMetricsContext is good enough.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.metrics.spi.NullContextWithUpdateThread --> + <!-- start class org.apache.hadoop.metrics.spi.OutputRecord --> + <class name="OutputRecord" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="getTagNames" return="java.util.Set<java.lang.String>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the set of tag names]]> + </doc> + </method> + <method name="getTag" return="java.lang.Object" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <doc> + <![CDATA[Returns a tag object which is can be a String, Integer, Short or Byte. + + @return the tag value, or null if there is no such tag]]> + </doc> + </method> + <method name="getMetricNames" return="java.util.Set<java.lang.String>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the set of metric names.]]> + </doc> + </method> + <method name="getMetric" return="java.lang.Number" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <doc> + <![CDATA[Returns the metric object which can be a Float, Integer, Short or Byte.]]> + </doc> + </method> + <doc> + <![CDATA[Represents a record of metric data to be sent to a metrics system.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.metrics.spi.OutputRecord --> + <!-- start class org.apache.hadoop.metrics.spi.Util --> + <class name="Util" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="parse" return="java.util.List<java.net.InetSocketAddress>" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="specs" type="java.lang.String"/> + <param name="defaultPort" type="int"/> + <doc> + <![CDATA[Parses a space and/or comma separated sequence of server specifications + of the form <i>hostname</i> or <i>hostname:port</i>. If + the specs string is null, defaults to localhost:defaultPort. + + @return a list of InetSocketAddress objects.]]> + </doc> + </method> + <doc> + <![CDATA[Static utility methods]]> + </doc> + </class> + <!-- end class org.apache.hadoop.metrics.spi.Util --> + <doc> + <![CDATA[The Service Provider Interface for the Metrics API. This package provides +an interface allowing a variety of metrics reporting implementations to be +plugged in to the Metrics API. Examples of such implementations can be found +in the packages <code>org.apache.hadoop.metrics.file</code> and +<code>org.apache.hadoop.metrics.ganglia</code>.<p/> + +Plugging in an implementation involves writing a concrete subclass of +<code>AbstractMetricsContext</code>. The subclass should get its + configuration information using the <code>getAttribute(<i>attributeName</i>)</code> + method.]]> + </doc> +</package> +<package name="org.apache.hadoop.metrics.util"> + <!-- start class org.apache.hadoop.metrics.util.MBeanUtil --> + <class name="MBeanUtil" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="MBeanUtil" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="registerMBean" return="javax.management.ObjectName" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="serviceName" type="java.lang.String"/> + <param name="nameName" type="java.lang.String"/> + <param name="theMbean" type="java.lang.Object"/> + <doc> + <![CDATA[Register the mbean using out standard MBeanName format + "hadoop.dfs:service=<serviceName>,name=<nameName>" + Where the <serviceName> and <nameName> are the supplied parameters + + @param serviceName + @param nameName + @param theMbean - the MBean to register + @return the named used to register the MBean]]> + </doc> + </method> + <method name="unregisterMBean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="mbeanName" type="javax.management.ObjectName"/> + </method> + <doc> + <![CDATA[This util class provides a method to register an MBean using + our standard naming convention as described in the doc + for {link {@link #registerMBean(String, String, Object)}]]> + </doc> + </class> + <!-- end class org.apache.hadoop.metrics.util.MBeanUtil --> + <!-- start class org.apache.hadoop.metrics.util.MetricsIntValue --> + <class name="MetricsIntValue" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="MetricsIntValue" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Constructor - create a new metric + @param nam the name of the metrics to be used to publish the metric]]> + </doc> + </constructor> + <method name="set" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="newValue" type="int"/> + <doc> + <![CDATA[Set the value + @param newValue]]> + </doc> + </method> + <method name="get" return="int" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get value + @return the value last set]]> + </doc> + </method> + <method name="pushMetric" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="mr" type="org.apache.hadoop.metrics.MetricsRecord"/> + <doc> + <![CDATA[Push the metric to the mr. + The metric is pushed only if it was updated since last push + + Note this does NOT push to JMX + (JMX gets the info via {@link #get()} + + @param mr]]> + </doc> + </method> + <doc> + <![CDATA[The MetricsIntValue class is for a metric that is not time varied + but changes only when it is set. + Each time its value is set, it is published only *once* at the next update + call.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.metrics.util.MetricsIntValue --> + <!-- start class org.apache.hadoop.metrics.util.MetricsTimeVaryingInt --> + <class name="MetricsTimeVaryingInt" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="MetricsTimeVaryingInt" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Constructor - create a new metric + @param nam the name of the metrics to be used to publish the metric]]> + </doc> + </constructor> + <method name="inc" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="incr" type="int"/> + <doc> + <![CDATA[Inc metrics for incr vlaue + @param incr - number of operations]]> + </doc> + </method> + <method name="inc" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Inc metrics by one]]> + </doc> + </method> + <method name="pushMetric" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="mr" type="org.apache.hadoop.metrics.MetricsRecord"/> + <doc> + <![CDATA[Push the delta metrics to the mr. + The delta is since the last push/interval. + + Note this does NOT push to JMX + (JMX gets the info via {@link #previousIntervalValue} + + @param mr]]> + </doc> + </method> + <method name="getPreviousIntervalValue" return="int" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The Value at the Previous interval + @return prev interval value]]> + </doc> + </method> + <doc> + <![CDATA[The MetricsTimeVaryingInt class is for a metric that naturally + varies over time (e.g. number of files created). + The metric is is published at interval heart beat (the interval + is set in the metrics config file). + Note if one wants a time associated with the metric then use + @see org.apache.hadoop.metrics.util.MetricsTimeVaryingRate]]> + </doc> + </class> + <!-- end class org.apache.hadoop.metrics.util.MetricsTimeVaryingInt --> + <!-- start class org.apache.hadoop.metrics.util.MetricsTimeVaryingRate --> + <class name="MetricsTimeVaryingRate" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="MetricsTimeVaryingRate" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Constructor - create a new metric + @param n the name of the metrics to be used to publish the metric]]> + </doc> + </constructor> + <method name="inc" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="numOps" type="int"/> + <param name="time" type="long"/> + <doc> + <![CDATA[Increment the metrics for numOps operations + @param numOps - number of operations + @param time - time for numOps operations]]> + </doc> + </method> + <method name="inc" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="time" type="long"/> + <doc> + <![CDATA[Increment the metrics for one operation + @param time for one operation]]> + </doc> + </method> + <method name="pushMetric" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="mr" type="org.apache.hadoop.metrics.MetricsRecord"/> + <doc> + <![CDATA[Push the delta metrics to the mr. + The delta is since the last push/interval. + + Note this does NOT push to JMX + (JMX gets the info via {@link #getPreviousIntervalAverageTime()} and + {@link #getPreviousIntervalNumOps()} + + @param mr]]> + </doc> + </method> + <method name="getPreviousIntervalNumOps" return="int" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The number of operations in the previous interval + @return - ops in prev interval]]> + </doc> + </method> + <method name="getPreviousIntervalAverageTime" return="long" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The average rate of an operation in the previous interval + @return - the average rate.]]> + </doc> + </method> + <method name="getMinTime" return="long" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The min time for a single operation since the last reset + {@link #resetMinMax()} + @return min time for an operation]]> + </doc> + </method> + <method name="getMaxTime" return="long" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The max time for a single operation since the last reset + {@link #resetMinMax()} + @return max time for an operation]]> + </doc> + </method> + <method name="resetMinMax" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Reset the min max values]]> + </doc> + </method> + <doc> + <![CDATA[The MetricsTimeVaryingRate class is for a rate based metric that + naturally varies over time (e.g. time taken to create a file). + The rate is averaged at each interval heart beat (the interval + is set in the metrics config file). + This class also keeps track of the min and max rates along with + a method to reset the min-max.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.metrics.util.MetricsTimeVaryingRate --> +</package> +<package name="org.apache.hadoop.net"> + <!-- start class org.apache.hadoop.net.DNS --> + <class name="DNS" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="DNS" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="reverseDns" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="hostIp" type="java.net.InetAddress"/> + <param name="ns" type="java.lang.String"/> + <exception name="NamingException" type="javax.naming.NamingException"/> + <doc> + <![CDATA[Returns the hostname associated with the specified IP address by the + provided nameserver. + + @param hostIp + The address to reverse lookup + @param ns + The host name of a reachable DNS server + @return The host name associated with the provided IP + @throws NamingException + If a NamingException is encountered]]> + </doc> + </method> + <method name="getIPs" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="strInterface" type="java.lang.String"/> + <exception name="UnknownHostException" type="java.net.UnknownHostException"/> + <doc> + <![CDATA[Returns all the IPs associated with the provided interface, if any, in + textual form. + + @param strInterface + The name of the network interface to query (e.g. eth0) + @return A string vector of all the IPs associated with the provided + interface + @throws UnknownHostException + If an UnknownHostException is encountered in querying the + default interface]]> + </doc> + </method> + <method name="getDefaultIP" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="strInterface" type="java.lang.String"/> + <exception name="UnknownHostException" type="java.net.UnknownHostException"/> + <doc> + <![CDATA[Returns the first available IP address associated with the provided + network interface + + @param strInterface + The name of the network interface to query (e.g. eth0) + @return The IP address in text form + @throws UnknownHostException + If one is encountered in querying the default interface]]> + </doc> + </method> + <method name="getHosts" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="strInterface" type="java.lang.String"/> + <param name="nameserver" type="java.lang.String"/> + <exception name="UnknownHostException" type="java.net.UnknownHostException"/> + <doc> + <![CDATA[Returns all the host names associated by the provided nameserver with the + address bound to the specified network interface + + @param strInterface + The name of the network interface to query (e.g. eth0) + @param nameserver + The DNS host name + @return A string vector of all host names associated with the IPs tied to + the specified interface + @throws UnknownHostException]]> + </doc> + </method> + <method name="getHosts" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="strInterface" type="java.lang.String"/> + <exception name="UnknownHostException" type="java.net.UnknownHostException"/> + <doc> + <![CDATA[Returns all the host names associated by the default nameserver with the + address bound to the specified network interface + + @param strInterface + The name of the network interface to query (e.g. eth0) + @return The list of host names associated with IPs bound to the network + interface + @throws UnknownHostException + If one is encountered while querying the deault interface]]> + </doc> + </method> + <method name="getDefaultHost" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="strInterface" type="java.lang.String"/> + <param name="nameserver" type="java.lang.String"/> + <exception name="UnknownHostException" type="java.net.UnknownHostException"/> + <doc> + <![CDATA[Returns the default (first) host name associated by the provided + nameserver with the address bound to the specified network interface + + @param strInterface + The name of the network interface to query (e.g. eth0) + @param nameserver + The DNS host name + @return The default host names associated with IPs bound to the network + interface + @throws UnknownHostException + If one is encountered while querying the deault interface]]> + </doc> + </method> + <method name="getDefaultHost" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="strInterface" type="java.lang.String"/> + <exception name="UnknownHostException" type="java.net.UnknownHostException"/> + <doc> + <![CDATA[Returns the default (first) host name associated by the default + nameserver with the address bound to the specified network interface + + @param strInterface + The name of the network interface to query (e.g. eth0) + @return The default host name associated with IPs bound to the network + interface + @throws UnknownHostException + If one is encountered while querying the deault interface]]> + </doc> + </method> + <doc> + <![CDATA[A class that provides direct and reverse lookup functionalities, allowing + the querying of specific network interfaces or nameservers.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.net.DNS --> + <!-- start interface org.apache.hadoop.net.DNSToSwitchMapping --> + <interface name="DNSToSwitchMapping" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="resolve" return="java.util.List<java.lang.String>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="names" type="java.util.List<java.lang.String>"/> + <doc> + <![CDATA[Resolves a list of DNS-names/IP-addresses and returns back a list of + switch information (network paths). One-to-one correspondence must be + maintained between the elements in the lists. + Consider an element in the argument list - x.y.com. The switch information + that is returned must be a network path of the form /foo/rack, + where / is the root, and 'foo' is the switch where 'rack' is connected. + Note the hostname/ip-address is not part of the returned path. + The network topology of the cluster would determine the number of + components in the network path. + @param names + @return list of resolved network paths]]> + </doc> + </method> + <doc> + <![CDATA[An interface that should be implemented to allow pluggable + DNS-name/IP-address to RackID resolvers.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.net.DNSToSwitchMapping --> + <!-- start class org.apache.hadoop.net.NetUtils --> + <class name="NetUtils" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="NetUtils" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getSocketFactory" return="javax.net.SocketFactory" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="clazz" type="java.lang.Class<?>"/> + <doc> + <![CDATA[Get the socket factory for the given class according to its + configuration parameter + <tt>hadoop.rpc.socket.factory.class.<ClassName></tt>. When no + such parameter exists then fall back on the default socket factory as + configured by <tt>hadoop.rpc.socket.factory.class.default</tt>. If + this default socket factory is not configured, then fall back on the JVM + default socket factory. + + @param conf the configuration + @param clazz the class (usually a {@link VersionedProtocol}) + @return a socket factory]]> + </doc> + </method> + <method name="getDefaultSocketFactory" return="javax.net.SocketFactory" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[Get the default socket factory as specified by the configuration + parameter <tt>hadoop.rpc.socket.factory.default</tt> + + @param conf the configuration + @return the default socket factory as specified in the configuration or + the JVM default socket factory if the configuration does not + contain a default socket factory property.]]> + </doc> + </method> + <method name="getSocketFactoryFromProperty" return="javax.net.SocketFactory" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="propValue" type="java.lang.String"/> + <doc> + <![CDATA[Get the socket factory corresponding to the given proxy URI. If the + given proxy URI corresponds to an absence of configuration parameter, + returns null. If the URI is malformed raises an exception. + + @param propValue the property which is the class name of the + SocketFactory to instantiate; assumed non null and non empty. + @return a socket factory as defined in the property value.]]> + </doc> + </method> + <method name="createSocketAddr" return="java.net.InetSocketAddress" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="target" type="java.lang.String"/> + <doc> + <![CDATA[Util method to build socket addr from either: + <host>:<post> + <fs>://<host>:<port>/<path>]]> + </doc> + </method> + <method name="getServerAddress" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="oldBindAddressName" type="java.lang.String"/> + <param name="oldPortName" type="java.lang.String"/> + <param name="newBindAddressName" type="java.lang.String"/> + <doc> + <![CDATA[Handle the transition from pairs of attributes specifying a host and port + to a single colon separated one. + @param conf the configuration to check + @param oldBindAddressName the old address attribute name + @param oldPortName the old port attribute name + @param newBindAddressName the new combined name + @return the complete address from the configuration]]> + </doc> + </method> + <method name="addStaticResolution" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="host" type="java.lang.String"/> + <param name="resolvedName" type="java.lang.String"/> + <doc> + <![CDATA[Adds a static resolution for host. This can be used for setting up + hostnames with names that are fake to point to a well known host. For e.g. + in some testcases we require to have daemons with different hostnames + running on the same machine. In order to create connections to these + daemons, one can set up mappings from those hostnames to "localhost". + {@link NetUtils#getStaticResolution(String)} can be used to query for + the actual hostname. + @param host + @param resolvedName]]> + </doc> + </method> + <method name="getStaticResolution" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="host" type="java.lang.String"/> + <doc> + <![CDATA[Retrieves the resolved name for the passed host. The resolved name must + have been set earlier using + {@link NetUtils#addStaticResolution(String, String)} + @param host + @return the resolution]]> + </doc> + </method> + <method name="getAllStaticResolutions" return="java.util.List<java.lang.String[]>" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[This is used to get all the resolutions that were added using + {@link NetUtils#addStaticResolution(String, String)}. The return + value is a List each element of which contains an array of String + of the form String[0]=hostname, String[1]=resolved-hostname + @return the list of resolutions]]> + </doc> + </method> + <method name="getConnectAddress" return="java.net.InetSocketAddress" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="server" type="org.apache.hadoop.ipc.Server"/> + <doc> + <![CDATA[Returns InetSocketAddress that a client can use to + connect to the server. Server.getListenerAddress() is not correct when + the server binds to "0.0.0.0". This returns "127.0.0.1:port" when + the getListenerAddress() returns "0.0.0.0:port". + + @param server + @return socket address that a client can use to connect to the server.]]> + </doc> + </method> + <method name="getInputStream" return="java.io.InputStream" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="socket" type="java.net.Socket"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Same as getInputStream(socket, socket.getSoTimeout()).<br><br> + + From documentation for {@link #getInputStream(Socket, long)}:<br> + Returns InputStream for the socket. If the socket has an associated + SocketChannel then it returns a + {@link SocketInputStream} with the given timeout. If the socket does not + have a channel, {@link Socket#getInputStream()} is returned. In the later + case, the timeout argument is ignored and the timeout set with + {@link Socket#setSoTimeout(int)} applies for reads.<br><br> + + Any socket created using socket factories returned by {@link #NetUtils}, + must use this interface instead of {@link Socket#getInputStream()}. + + @see #getInputStream(Socket, long) + + @param socket + @return InputStream for reading from the socket. + @throws IOException]]> + </doc> + </method> + <method name="getInputStream" return="java.io.InputStream" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="socket" type="java.net.Socket"/> + <param name="timeout" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns InputStream for the socket. If the socket has an associated + SocketChannel then it returns a + {@link SocketInputStream} with the given timeout. If the socket does not + have a channel, {@link Socket#getInputStream()} is returned. In the later + case, the timeout argument is ignored and the timeout set with + {@link Socket#setSoTimeout(int)} applies for reads.<br><br> + + Any socket created using socket factories returned by {@link #NetUtils}, + must use this interface instead of {@link Socket#getInputStream()}. + + @see Socket#getChannel() + + @param socket + @param timeout timeout in milliseconds. This may not always apply. zero + for waiting as long as necessary. + @return InputStream for reading from the socket. + @throws IOException]]> + </doc> + </method> + <method name="getOutputStream" return="java.io.OutputStream" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="socket" type="java.net.Socket"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Same as getOutputStream(socket, 0). Timeout of zero implies write will + wait until data is available.<br><br> + + From documentation for {@link #getOutputStream(Socket, long)} : <br> + Returns OutputStream for the socket. If the socket has an associated + SocketChannel then it returns a + {@link SocketOutputStream} with the given timeout. If the socket does not + have a channel, {@link Socket#getOutputStream()} is returned. In the later + case, the timeout argument is ignored and the write will wait until + data is available.<br><br> + + Any socket created using socket factories returned by {@link #NetUtils}, + must use this interface instead of {@link Socket#getOutputStream()}. + + @see #getOutputStream(Socket, long) + + @param socket + @return OutputStream for writing to the socket. + @throws IOException]]> + </doc> + </method> + <method name="getOutputStream" return="java.io.OutputStream" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="socket" type="java.net.Socket"/> + <param name="timeout" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Returns OutputStream for the socket. If the socket has an associated + SocketChannel then it returns a + {@link SocketOutputStream} with the given timeout. If the socket does not + have a channel, {@link Socket#getOutputStream()} is returned. In the later + case, the timeout argument is ignored and the write will wait until + data is available.<br><br> + + Any socket created using socket factories returned by {@link #NetUtils}, + must use this interface instead of {@link Socket#getOutputStream()}. + + @see Socket#getChannel() + + @param socket + @param timeout timeout in milliseconds. This may not always apply. zero + for waiting as long as necessary. + @return OutputStream for writing to the socket. + @throws IOException]]> + </doc> + </method> + </class> + <!-- end class org.apache.hadoop.net.NetUtils --> + <!-- start class org.apache.hadoop.net.NetworkTopology --> + <class name="NetworkTopology" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="NetworkTopology" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="add" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="node" type="org.apache.hadoop.net.Node"/> + <doc> + <![CDATA[Add a leaf node + Update node counter & rack counter if neccessary + @param node + node to be added + @exception IllegalArgumentException if add a node to a leave + or node to be added is not a leaf]]> + </doc> + </method> + <method name="remove" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="node" type="org.apache.hadoop.net.Node"/> + <doc> + <![CDATA[Remove a node + Update node counter & rack counter if neccessary + @param node + node to be removed]]> + </doc> + </method> + <method name="contains" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="node" type="org.apache.hadoop.net.Node"/> + <doc> + <![CDATA[Check if the tree contains node <i>node</i> + + @param node + a node + @return true if <i>node</i> is already in the tree; false otherwise]]> + </doc> + </method> + <method name="getNode" return="org.apache.hadoop.net.Node" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="loc" type="java.lang.String"/> + <doc> + <![CDATA[Given a string representation of a node, return its reference + + @param loc + a path-like string representation of a node + @return a reference to the node; null if the node is not in the tree]]> + </doc> + </method> + <method name="getNumOfRacks" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the total number of racks]]> + </doc> + </method> + <method name="getNumOfLeaves" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the total number of nodes]]> + </doc> + </method> + <method name="getDistance" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="node1" type="org.apache.hadoop.net.Node"/> + <param name="node2" type="org.apache.hadoop.net.Node"/> + <doc> + <![CDATA[Return the distance between two nodes + It is assumed that the distance from one node to its parent is 1 + The distance between two nodes is calculated by summing up their distances + to their closest common ancestor. + @param node1 one node + @param node2 another node + @return the distance between node1 and node2 + node1 or node2 do not belong to the cluster]]> + </doc> + </method> + <method name="isOnSameRack" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="node1" type="org.apache.hadoop.net.Node"/> + <param name="node2" type="org.apache.hadoop.net.Node"/> + <doc> + <![CDATA[Check if two nodes are on the same rack + @param node1 one node + @param node2 another node + @return true if node1 and node2 are pm the same rack; false otherwise + @exception IllegalArgumentException when either node1 or node2 is null, or + node1 or node2 do not belong to the cluster]]> + </doc> + </method> + <method name="chooseRandom" return="org.apache.hadoop.net.Node" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="scope" type="java.lang.String"/> + <doc> + <![CDATA[randomly choose one node from <i>scope</i> + if scope starts with ~, choose one from the all nodes except for the + ones in <i>scope</i>; otherwise, choose one from <i>scope</i> + @param scope range of nodes from which a node will be choosen + @return the choosen node]]> + </doc> + </method> + <method name="countNumOfAvailableNodes" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="scope" type="java.lang.String"/> + <param name="excludedNodes" type="java.util.List<org.apache.hadoop.net.Node>"/> + <doc> + <![CDATA[return the number of leaves in <i>scope</i> but not in <i>excludedNodes</i> + if scope starts with ~, return the number of nodes that are not + in <i>scope</i> and <i>excludedNodes</i>; + @param scope a path string that may start with ~ + @param excludedNodes a list of nodes + @return number of available nodes]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[convert a network tree to a string]]> + </doc> + </method> + <method name="pseudoSortByDistance" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="reader" type="org.apache.hadoop.net.Node"/> + <param name="nodes" type="org.apache.hadoop.net.Node[]"/> + <doc> + <![CDATA[Sort nodes array by their distances to <i>reader</i> + It linearly scans the array, if a local node is found, swap it with + the first element of the array. + If a local rack node is found, swap it with the first element following + the local node. + If neither local node or local rack node is found, put a random replica + location at postion 0. + It leaves the rest nodes untouched.]]> + </doc> + </method> + <field name="DEFAULT_RACK" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="UNRESOLVED" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="DEFAULT_HOST_LEVEL" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="LOG" type="org.apache.commons.logging.Log" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[The class represents a cluster of computer with a tree hierarchical + network topology. + For example, a cluster may be consists of many data centers filled + with racks of computers. + In a network topology, leaves represent data nodes (computers) and inner + nodes represent switches/routers that manage traffic in/out of data centers + or racks.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.net.NetworkTopology --> + <!-- start interface org.apache.hadoop.net.Node --> + <interface name="Node" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="getNetworkLocation" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the string representation of this node's network location]]> + </doc> + </method> + <method name="setNetworkLocation" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="location" type="java.lang.String"/> + <doc> + <![CDATA[Set the node's network location]]> + </doc> + </method> + <method name="getName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return this node's name]]> + </doc> + </method> + <method name="getParent" return="org.apache.hadoop.net.Node" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return this node's parent]]> + </doc> + </method> + <method name="setParent" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="parent" type="org.apache.hadoop.net.Node"/> + <doc> + <![CDATA[Set this node's parent]]> + </doc> + </method> + <method name="getLevel" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return this node's level in the tree. + E.g. the root of a tree returns 0 and its children return 1]]> + </doc> + </method> + <method name="setLevel" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="i" type="int"/> + <doc> + <![CDATA[Set this node's level in the tree.]]> + </doc> + </method> + <doc> + <![CDATA[The interface defines a node in a network topology. + A node may be a leave representing a data node or an inner + node representing a datacenter or rack. + Each data has a name and its location in the network is + decided by a string with syntax similar to a file name. + For example, a data node's name is hostname:port# and if it's located at + rack "orange" in datacenter "dog", the string representation of its + network location is /dog/orange]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.net.Node --> + <!-- start class org.apache.hadoop.net.NodeBase --> + <class name="NodeBase" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.net.Node"/> + <constructor name="NodeBase" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Default constructor]]> + </doc> + </constructor> + <constructor name="NodeBase" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct a node from its path + @param path + a concatenation of this node's location, the path seperator, and its name]]> + </doc> + </constructor> + <constructor name="NodeBase" type="java.lang.String, java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct a node from its name and its location + @param name this node's name + @param location this node's location]]> + </doc> + </constructor> + <constructor name="NodeBase" type="java.lang.String, java.lang.String, org.apache.hadoop.net.Node, int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct a node from its name and its location + @param name this node's name + @param location this node's location + @param parent this node's parent node + @param level this node's level in the tree]]> + </doc> + </constructor> + <method name="getName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return this node's name]]> + </doc> + </method> + <method name="getNetworkLocation" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return this node's network location]]> + </doc> + </method> + <method name="setNetworkLocation" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="location" type="java.lang.String"/> + <doc> + <![CDATA[Set this node's network location]]> + </doc> + </method> + <method name="getPath" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="node" type="org.apache.hadoop.net.Node"/> + <doc> + <![CDATA[Return this node's path]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return this node's string representation]]> + </doc> + </method> + <method name="normalize" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="path" type="java.lang.String"/> + <doc> + <![CDATA[Normalize a path]]> + </doc> + </method> + <method name="getParent" return="org.apache.hadoop.net.Node" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return this node's parent]]> + </doc> + </method> + <method name="setParent" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="parent" type="org.apache.hadoop.net.Node"/> + <doc> + <![CDATA[Set this node's parent]]> + </doc> + </method> + <method name="getLevel" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return this node's level in the tree. + E.g. the root of a tree returns 0 and its children return 1]]> + </doc> + </method> + <method name="setLevel" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="level" type="int"/> + <doc> + <![CDATA[Set this node's level in the tree]]> + </doc> + </method> + <field name="PATH_SEPARATOR" type="char" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="PATH_SEPARATOR_STR" type="java.lang.String" + transient="false" volatile="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="ROOT" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="name" type="java.lang.String" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="location" type="java.lang.String" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="level" type="int" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="parent" type="org.apache.hadoop.net.Node" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[A base class that implements interface Node]]> + </doc> + </class> + <!-- end class org.apache.hadoop.net.NodeBase --> + <!-- start class org.apache.hadoop.net.ScriptBasedMapping --> + <class name="ScriptBasedMapping" extends="java.lang.Object" + abstract="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.conf.Configurable"/> + <implements name="org.apache.hadoop.net.DNSToSwitchMapping"/> + <constructor name="ScriptBasedMapping" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="setConf" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + </method> + <method name="getConf" return="org.apache.hadoop.conf.Configuration" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="resolve" return="java.util.List<java.lang.String>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="names" type="java.util.List<java.lang.String>"/> + </method> + <doc> + <![CDATA[This class implements the {@link DNSToSwitchMapping} interface using a + script configured via topology.script.file.name .]]> + </doc> + </class> + <!-- end class org.apache.hadoop.net.ScriptBasedMapping --> + <!-- start class org.apache.hadoop.net.SocketInputStream --> + <class name="SocketInputStream" extends="java.io.InputStream" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="java.nio.channels.ReadableByteChannel"/> + <constructor name="SocketInputStream" type="java.nio.channels.ReadableByteChannel, long" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create a new input stream with the given timeout. If the timeout + is zero, it will be treated as infinite timeout. The socket's + channel will be configured to be non-blocking. + + @param channel + Channel for reading, should also be a {@link SelectableChannel}. + The channel will be configured to be non-blocking. + @param timeout timeout in milliseconds. must not be negative. + @throws IOException]]> + </doc> + </constructor> + <constructor name="SocketInputStream" type="java.net.Socket, long" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Same as SocketInputStream(socket.getChannel(), timeout): <br><br> + + Create a new input stream with the given timeout. If the timeout + is zero, it will be treated as infinite timeout. The socket's + channel will be configured to be non-blocking. + + @see SocketInputStream#SocketInputStream(ReadableByteChannel, long) + + @param socket should have a channel associated with it. + @param timeout timeout timeout in milliseconds. must not be negative. + @throws IOException]]> + </doc> + </constructor> + <constructor name="SocketInputStream" type="java.net.Socket" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Same as SocketInputStream(socket.getChannel(), socket.getSoTimeout()) + :<br><br> + + Create a new input stream with the given timeout. If the timeout + is zero, it will be treated as infinite timeout. The socket's + channel will be configured to be non-blocking. + @see SocketInputStream#SocketInputStream(ReadableByteChannel, long) + + @param socket should have a channel associated with it. + @throws IOException]]> + </doc> + </constructor> + <method name="read" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="read" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="close" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getChannel" return="java.nio.channels.ReadableByteChannel" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns underlying channel used by inputstream. + This is useful in certain cases like channel for + {@link FileChannel#transferFrom(ReadableByteChannel, long, long)}.]]> + </doc> + </method> + <method name="isOpen" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="read" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dst" type="java.nio.ByteBuffer"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[This implements an input stream that can have a timeout while reading. + This sets non-blocking flag on the socket channel. + So after create this object, read() on + {@link Socket#getInputStream()} and write() on + {@link Socket#getOutputStream()} for the associated socket will throw + IllegalBlockingModeException. + Please use {@link SocketOutputStream} for writing.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.net.SocketInputStream --> + <!-- start class org.apache.hadoop.net.SocketOutputStream --> + <class name="SocketOutputStream" extends="java.io.OutputStream" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="java.nio.channels.WritableByteChannel"/> + <constructor name="SocketOutputStream" type="java.nio.channels.WritableByteChannel, long" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Create a new ouput stream with the given timeout. If the timeout + is zero, it will be treated as infinite timeout. The socket's + channel will be configured to be non-blocking. + + @param channel + Channel for writing, should also be a {@link SelectableChannel}. + The channel will be configured to be non-blocking. + @param timeout timeout in milliseconds. must not be negative. + @throws IOException]]> + </doc> + </constructor> + <constructor name="SocketOutputStream" type="java.net.Socket, long" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Same as SocketOutputStream(socket.getChannel(), timeout):<br><br> + + Create a new ouput stream with the given timeout. If the timeout + is zero, it will be treated as infinite timeout. The socket's + channel will be configured to be non-blocking. + + @see SocketOutputStream#SocketOutputStream(WritableByteChannel, long) + + @param socket should have a channel associated with it. + @param timeout timeout timeout in milliseconds. must not be negative. + @throws IOException]]> + </doc> + </constructor> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte[]"/> + <param name="off" type="int"/> + <param name="len" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="close" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getChannel" return="java.nio.channels.WritableByteChannel" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns underlying channel used by this stream. + This is useful in certain cases like channel for + {@link FileChannel#transferTo(long, long, WritableByteChannel)}]]> + </doc> + </method> + <method name="isOpen" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="write" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="java.nio.ByteBuffer"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[This implements an output stream that can have a timeout while writing. + This sets non-blocking flag on the socket channel. + So after creating this object , read() on + {@link Socket#getInputStream()} and write() on + {@link Socket#getOutputStream()} on the associated socket will throw + llegalBlockingModeException. + Please use {@link SocketInputStream} for reading.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.net.SocketOutputStream --> + <!-- start class org.apache.hadoop.net.SocksSocketFactory --> + <class name="SocksSocketFactory" extends="javax.net.SocketFactory" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.conf.Configurable"/> + <constructor name="SocksSocketFactory" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Default empty constructor (for use with the reflection API).]]> + </doc> + </constructor> + <constructor name="SocksSocketFactory" type="java.net.Proxy" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Constructor with a supplied Proxy + + @param proxy the proxy to use to create sockets]]> + </doc> + </constructor> + <method name="createSocket" return="java.net.Socket" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="createSocket" return="java.net.Socket" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="addr" type="java.net.InetAddress"/> + <param name="port" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="createSocket" return="java.net.Socket" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="addr" type="java.net.InetAddress"/> + <param name="port" type="int"/> + <param name="localHostAddr" type="java.net.InetAddress"/> + <param name="localPort" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="createSocket" return="java.net.Socket" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="host" type="java.lang.String"/> + <param name="port" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <exception name="UnknownHostException" type="java.net.UnknownHostException"/> + </method> + <method name="createSocket" return="java.net.Socket" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="host" type="java.lang.String"/> + <param name="port" type="int"/> + <param name="localHostAddr" type="java.net.InetAddress"/> + <param name="localPort" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <exception name="UnknownHostException" type="java.net.UnknownHostException"/> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="obj" type="java.lang.Object"/> + </method> + <method name="getConf" return="org.apache.hadoop.conf.Configuration" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="setConf" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + </method> + <doc> + <![CDATA[Specialized SocketFactory to create sockets with a SOCKS proxy]]> + </doc> + </class> + <!-- end class org.apache.hadoop.net.SocksSocketFactory --> + <!-- start class org.apache.hadoop.net.StandardSocketFactory --> + <class name="StandardSocketFactory" extends="javax.net.SocketFactory" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="StandardSocketFactory" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Default empty constructor (for use with the reflection API).]]> + </doc> + </constructor> + <method name="createSocket" return="java.net.Socket" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="createSocket" return="java.net.Socket" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="addr" type="java.net.InetAddress"/> + <param name="port" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="createSocket" return="java.net.Socket" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="addr" type="java.net.InetAddress"/> + <param name="port" type="int"/> + <param name="localHostAddr" type="java.net.InetAddress"/> + <param name="localPort" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="createSocket" return="java.net.Socket" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="host" type="java.lang.String"/> + <param name="port" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <exception name="UnknownHostException" type="java.net.UnknownHostException"/> + </method> + <method name="createSocket" return="java.net.Socket" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="host" type="java.lang.String"/> + <param name="port" type="int"/> + <param name="localHostAddr" type="java.net.InetAddress"/> + <param name="localPort" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <exception name="UnknownHostException" type="java.net.UnknownHostException"/> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="obj" type="java.lang.Object"/> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[Specialized SocketFactory to create sockets with a SOCKS proxy]]> + </doc> + </class> + <!-- end class org.apache.hadoop.net.StandardSocketFactory --> + <doc> + <![CDATA[Network-related classes.]]> + </doc> +</package> +<package name="org.apache.hadoop.record"> + <!-- start class org.apache.hadoop.record.BinaryRecordInput --> + <class name="BinaryRecordInput" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.record.RecordInput"/> + <constructor name="BinaryRecordInput" type="java.io.InputStream" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of BinaryRecordInput]]> + </doc> + </constructor> + <constructor name="BinaryRecordInput" type="java.io.DataInput" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of BinaryRecordInput]]> + </doc> + </constructor> + <method name="get" return="org.apache.hadoop.record.BinaryRecordInput" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="inp" type="java.io.DataInput"/> + <doc> + <![CDATA[Get a thread-local record input for the supplied DataInput. + @param inp data input stream + @return binary record input corresponding to the supplied DataInput.]]> + </doc> + </method> + <method name="readByte" return="byte" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readBool" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readInt" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readLong" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFloat" return="float" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readDouble" return="double" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readBuffer" return="org.apache.hadoop.record.Buffer" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="startRecord" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="endRecord" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="startVector" return="org.apache.hadoop.record.Index" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="endVector" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="startMap" return="org.apache.hadoop.record.Index" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="endMap" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + </class> + <!-- end class org.apache.hadoop.record.BinaryRecordInput --> + <!-- start class org.apache.hadoop.record.BinaryRecordOutput --> + <class name="BinaryRecordOutput" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.record.RecordOutput"/> + <constructor name="BinaryRecordOutput" type="java.io.OutputStream" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of BinaryRecordOutput]]> + </doc> + </constructor> + <constructor name="BinaryRecordOutput" type="java.io.DataOutput" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of BinaryRecordOutput]]> + </doc> + </constructor> + <method name="get" return="org.apache.hadoop.record.BinaryRecordOutput" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <doc> + <![CDATA[Get a thread-local record output for the supplied DataOutput. + @param out data output stream + @return binary record output corresponding to the supplied DataOutput.]]> + </doc> + </method> + <method name="writeByte" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeBool" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="boolean"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeInt" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="i" type="int"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeLong" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="l" type="long"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeFloat" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="float"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeDouble" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="d" type="double"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeString" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="s" type="java.lang.String"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeBuffer" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="buf" type="org.apache.hadoop.record.Buffer"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="startRecord" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="r" type="org.apache.hadoop.record.Record"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="endRecord" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="r" type="org.apache.hadoop.record.Record"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="startVector" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="v" type="java.util.ArrayList"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="endVector" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="v" type="java.util.ArrayList"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="startMap" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="v" type="java.util.TreeMap"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="endMap" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="v" type="java.util.TreeMap"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + </class> + <!-- end class org.apache.hadoop.record.BinaryRecordOutput --> + <!-- start class org.apache.hadoop.record.Buffer --> + <class name="Buffer" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="java.lang.Comparable"/> + <implements name="java.lang.Cloneable"/> + <constructor name="Buffer" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Create a zero-count sequence.]]> + </doc> + </constructor> + <constructor name="Buffer" type="byte[]" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Create a Buffer using the byte array as the initial value. + + @param bytes This array becomes the backing storage for the object.]]> + </doc> + </constructor> + <constructor name="Buffer" type="byte[], int, int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Create a Buffer using the byte range as the initial value. + + @param bytes Copy of this array becomes the backing storage for the object. + @param offset offset into byte array + @param length length of data]]> + </doc> + </constructor> + <method name="set" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="bytes" type="byte[]"/> + <doc> + <![CDATA[Use the specified bytes array as underlying sequence. + + @param bytes byte sequence]]> + </doc> + </method> + <method name="copy" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <param name="bytes" type="byte[]"/> + <param name="offset" type="int"/> + <param name="length" type="int"/> + <doc> + <![CDATA[Copy the specified byte array to the Buffer. Replaces the current buffer. + + @param bytes byte array to be assigned + @param offset offset into byte array + @param length length of data]]> + </doc> + </method> + <method name="get" return="byte[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the data from the Buffer. + + @return The data is only valid between 0 and getCount() - 1.]]> + </doc> + </method> + <method name="getCount" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the current count of the buffer.]]> + </doc> + </method> + <method name="getCapacity" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the capacity, which is the maximum count that could handled without + resizing the backing storage. + + @return The number of bytes]]> + </doc> + </method> + <method name="setCapacity" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="newCapacity" type="int"/> + <doc> + <![CDATA[Change the capacity of the backing storage. + The data is preserved if newCapacity >= getCount(). + @param newCapacity The new capacity in bytes.]]> + </doc> + </method> + <method name="reset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Reset the buffer to 0 size]]> + </doc> + </method> + <method name="truncate" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Change the capacity of the backing store to be the same as the current + count of buffer.]]> + </doc> + </method> + <method name="append" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="bytes" type="byte[]"/> + <param name="offset" type="int"/> + <param name="length" type="int"/> + <doc> + <![CDATA[Append specified bytes to the buffer. + + @param bytes byte array to be appended + @param offset offset into byte array + @param length length of data]]> + </doc> + </method> + <method name="append" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="bytes" type="byte[]"/> + <doc> + <![CDATA[Append specified bytes to the buffer + + @param bytes byte array to be appended]]> + </doc> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="compareTo" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="other" type="java.lang.Object"/> + <doc> + <![CDATA[Define the sort order of the Buffer. + + @param other The other buffer + @return Positive if this is bigger than other, 0 if they are equal, and + negative if this is smaller than other.]]> + </doc> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="other" type="java.lang.Object"/> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="charsetName" type="java.lang.String"/> + <exception name="UnsupportedEncodingException" type="java.io.UnsupportedEncodingException"/> + <doc> + <![CDATA[Convert the byte buffer to a string an specific character encoding + + @param charsetName Valid Java Character Set Name]]> + </doc> + </method> + <method name="clone" return="java.lang.Object" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="CloneNotSupportedException" type="java.lang.CloneNotSupportedException"/> + </method> + <doc> + <![CDATA[A byte sequence that is used as a Java native type for buffer. + It is resizable and distinguishes between the count of the seqeunce and + the current capacity.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.Buffer --> + <!-- start class org.apache.hadoop.record.CsvRecordInput --> + <class name="CsvRecordInput" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.record.RecordInput"/> + <constructor name="CsvRecordInput" type="java.io.InputStream" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of CsvRecordInput]]> + </doc> + </constructor> + <method name="readByte" return="byte" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readBool" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readInt" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readLong" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFloat" return="float" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readDouble" return="double" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readBuffer" return="org.apache.hadoop.record.Buffer" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="startRecord" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="endRecord" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="startVector" return="org.apache.hadoop.record.Index" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="endVector" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="startMap" return="org.apache.hadoop.record.Index" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="endMap" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + </class> + <!-- end class org.apache.hadoop.record.CsvRecordInput --> + <!-- start class org.apache.hadoop.record.CsvRecordOutput --> + <class name="CsvRecordOutput" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.record.RecordOutput"/> + <constructor name="CsvRecordOutput" type="java.io.OutputStream" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of CsvRecordOutput]]> + </doc> + </constructor> + <method name="writeByte" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeBool" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="boolean"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeInt" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="i" type="int"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeLong" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="l" type="long"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeFloat" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="float"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeDouble" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="d" type="double"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeString" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="s" type="java.lang.String"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeBuffer" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="buf" type="org.apache.hadoop.record.Buffer"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="startRecord" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="r" type="org.apache.hadoop.record.Record"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="endRecord" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="r" type="org.apache.hadoop.record.Record"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="startVector" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="v" type="java.util.ArrayList"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="endVector" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="v" type="java.util.ArrayList"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="startMap" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="v" type="java.util.TreeMap"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="endMap" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="v" type="java.util.TreeMap"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + </class> + <!-- end class org.apache.hadoop.record.CsvRecordOutput --> + <!-- start interface org.apache.hadoop.record.Index --> + <interface name="Index" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="done" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="incr" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[Interface that acts as an iterator for deserializing maps. + The deserializer returns an instance that the record uses to + read vectors and maps. An example of usage is as follows: + + <code> + Index idx = startVector(...); + while (!idx.done()) { + .... // read element of a vector + idx.incr(); + } + </code>]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.record.Index --> + <!-- start class org.apache.hadoop.record.Record --> + <class name="Record" extends="java.lang.Object" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.WritableComparable"/> + <implements name="java.lang.Cloneable"/> + <constructor name="Record" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="serialize" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="rout" type="org.apache.hadoop.record.RecordOutput"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Serialize a record with tag (ususally field name) + @param rout Record output destination + @param tag record tag (Used only in tagged serialization e.g. XML)]]> + </doc> + </method> + <method name="deserialize" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="rin" type="org.apache.hadoop.record.RecordInput"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Deserialize a record with a tag (usually field name) + @param rin Record input source + @param tag Record tag (Used only in tagged serialization e.g. XML)]]> + </doc> + </method> + <method name="compareTo" return="int" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="peer" type="java.lang.Object"/> + <exception name="ClassCastException" type="java.lang.ClassCastException"/> + </method> + <method name="serialize" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="rout" type="org.apache.hadoop.record.RecordOutput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Serialize a record without a tag + @param rout Record output destination]]> + </doc> + </method> + <method name="deserialize" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="rin" type="org.apache.hadoop.record.RecordInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Deserialize a record without a tag + @param rin Record input source]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="din" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[Abstract class that is extended by generated classes.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.Record --> + <!-- start class org.apache.hadoop.record.RecordComparator --> + <class name="RecordComparator" extends="org.apache.hadoop.io.WritableComparator" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="RecordComparator" type="java.lang.Class" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct a raw {@link Record} comparison implementation.]]> + </doc> + </constructor> + <method name="compare" return="int" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b1" type="byte[]"/> + <param name="s1" type="int"/> + <param name="l1" type="int"/> + <param name="b2" type="byte[]"/> + <param name="s2" type="int"/> + <param name="l2" type="int"/> + </method> + <method name="define" + abstract="false" native="false" synchronized="true" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="c" type="java.lang.Class"/> + <param name="comparator" type="org.apache.hadoop.record.RecordComparator"/> + <doc> + <![CDATA[Register an optimized comparator for a {@link Record} implementation. + + @param c record classs for which a raw comparator is provided + @param comparator Raw comparator instance for class c]]> + </doc> + </method> + <doc> + <![CDATA[A raw record comparator base class]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.RecordComparator --> + <!-- start interface org.apache.hadoop.record.RecordInput --> + <interface name="RecordInput" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="readByte" return="byte" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read a byte from serialized record. + @param tag Used by tagged serialization formats (such as XML) + @return value read from serialized record.]]> + </doc> + </method> + <method name="readBool" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read a boolean from serialized record. + @param tag Used by tagged serialization formats (such as XML) + @return value read from serialized record.]]> + </doc> + </method> + <method name="readInt" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read an integer from serialized record. + @param tag Used by tagged serialization formats (such as XML) + @return value read from serialized record.]]> + </doc> + </method> + <method name="readLong" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read a long integer from serialized record. + @param tag Used by tagged serialization formats (such as XML) + @return value read from serialized record.]]> + </doc> + </method> + <method name="readFloat" return="float" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read a single-precision float from serialized record. + @param tag Used by tagged serialization formats (such as XML) + @return value read from serialized record.]]> + </doc> + </method> + <method name="readDouble" return="double" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read a double-precision number from serialized record. + @param tag Used by tagged serialization formats (such as XML) + @return value read from serialized record.]]> + </doc> + </method> + <method name="readString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read a UTF-8 encoded string from serialized record. + @param tag Used by tagged serialization formats (such as XML) + @return value read from serialized record.]]> + </doc> + </method> + <method name="readBuffer" return="org.apache.hadoop.record.Buffer" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read byte array from serialized record. + @param tag Used by tagged serialization formats (such as XML) + @return value read from serialized record.]]> + </doc> + </method> + <method name="startRecord" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Check the mark for start of the serialized record. + @param tag Used by tagged serialization formats (such as XML)]]> + </doc> + </method> + <method name="endRecord" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Check the mark for end of the serialized record. + @param tag Used by tagged serialization formats (such as XML)]]> + </doc> + </method> + <method name="startVector" return="org.apache.hadoop.record.Index" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Check the mark for start of the serialized vector. + @param tag Used by tagged serialization formats (such as XML) + @return Index that is used to count the number of elements.]]> + </doc> + </method> + <method name="endVector" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Check the mark for end of the serialized vector. + @param tag Used by tagged serialization formats (such as XML)]]> + </doc> + </method> + <method name="startMap" return="org.apache.hadoop.record.Index" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Check the mark for start of the serialized map. + @param tag Used by tagged serialization formats (such as XML) + @return Index that is used to count the number of map entries.]]> + </doc> + </method> + <method name="endMap" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Check the mark for end of the serialized map. + @param tag Used by tagged serialization formats (such as XML)]]> + </doc> + </method> + <doc> + <![CDATA[Interface that all the Deserializers have to implement.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.record.RecordInput --> + <!-- start interface org.apache.hadoop.record.RecordOutput --> + <interface name="RecordOutput" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="writeByte" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Write a byte to serialized record. + @param b Byte to be serialized + @param tag Used by tagged serialization formats (such as XML) + @throws IOException Indicates error in serialization]]> + </doc> + </method> + <method name="writeBool" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="boolean"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Write a boolean to serialized record. + @param b Boolean to be serialized + @param tag Used by tagged serialization formats (such as XML) + @throws IOException Indicates error in serialization]]> + </doc> + </method> + <method name="writeInt" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="i" type="int"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Write an integer to serialized record. + @param i Integer to be serialized + @param tag Used by tagged serialization formats (such as XML) + @throws IOException Indicates error in serialization]]> + </doc> + </method> + <method name="writeLong" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="l" type="long"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Write a long integer to serialized record. + @param l Long to be serialized + @param tag Used by tagged serialization formats (such as XML) + @throws IOException Indicates error in serialization]]> + </doc> + </method> + <method name="writeFloat" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="float"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Write a single-precision float to serialized record. + @param f Float to be serialized + @param tag Used by tagged serialization formats (such as XML) + @throws IOException Indicates error in serialization]]> + </doc> + </method> + <method name="writeDouble" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="d" type="double"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Write a double precision floating point number to serialized record. + @param d Double to be serialized + @param tag Used by tagged serialization formats (such as XML) + @throws IOException Indicates error in serialization]]> + </doc> + </method> + <method name="writeString" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="s" type="java.lang.String"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Write a unicode string to serialized record. + @param s String to be serialized + @param tag Used by tagged serialization formats (such as XML) + @throws IOException Indicates error in serialization]]> + </doc> + </method> + <method name="writeBuffer" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="buf" type="org.apache.hadoop.record.Buffer"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Write a buffer to serialized record. + @param buf Buffer to be serialized + @param tag Used by tagged serialization formats (such as XML) + @throws IOException Indicates error in serialization]]> + </doc> + </method> + <method name="startRecord" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="r" type="org.apache.hadoop.record.Record"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Mark the start of a record to be serialized. + @param r Record to be serialized + @param tag Used by tagged serialization formats (such as XML) + @throws IOException Indicates error in serialization]]> + </doc> + </method> + <method name="endRecord" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="r" type="org.apache.hadoop.record.Record"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Mark the end of a serialized record. + @param r Record to be serialized + @param tag Used by tagged serialization formats (such as XML) + @throws IOException Indicates error in serialization]]> + </doc> + </method> + <method name="startVector" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="v" type="java.util.ArrayList"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Mark the start of a vector to be serialized. + @param v Vector to be serialized + @param tag Used by tagged serialization formats (such as XML) + @throws IOException Indicates error in serialization]]> + </doc> + </method> + <method name="endVector" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="v" type="java.util.ArrayList"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Mark the end of a serialized vector. + @param v Vector to be serialized + @param tag Used by tagged serialization formats (such as XML) + @throws IOException Indicates error in serialization]]> + </doc> + </method> + <method name="startMap" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="m" type="java.util.TreeMap"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Mark the start of a map to be serialized. + @param m Map to be serialized + @param tag Used by tagged serialization formats (such as XML) + @throws IOException Indicates error in serialization]]> + </doc> + </method> + <method name="endMap" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="m" type="java.util.TreeMap"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Mark the end of a serialized map. + @param m Map to be serialized + @param tag Used by tagged serialization formats (such as XML) + @throws IOException Indicates error in serialization]]> + </doc> + </method> + <doc> + <![CDATA[Interface that alll the serializers have to implement.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.record.RecordOutput --> + <!-- start class org.apache.hadoop.record.Utils --> + <class name="Utils" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="readFloat" return="float" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="bytes" type="byte[]"/> + <param name="start" type="int"/> + <doc> + <![CDATA[Parse a float from a byte array.]]> + </doc> + </method> + <method name="readDouble" return="double" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="bytes" type="byte[]"/> + <param name="start" type="int"/> + <doc> + <![CDATA[Parse a double from a byte array.]]> + </doc> + </method> + <method name="readVLong" return="long" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="bytes" type="byte[]"/> + <param name="start" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Reads a zero-compressed encoded long from a byte array and returns it. + @param bytes byte array with decode long + @param start starting index + @throws java.io.IOException + @return deserialized long]]> + </doc> + </method> + <method name="readVInt" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="bytes" type="byte[]"/> + <param name="start" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Reads a zero-compressed encoded integer from a byte array and returns it. + @param bytes byte array with the encoded integer + @param start start index + @throws java.io.IOException + @return deserialized integer]]> + </doc> + </method> + <method name="readVLong" return="long" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Reads a zero-compressed encoded long from a stream and return it. + @param in input stream + @throws java.io.IOException + @return deserialized long]]> + </doc> + </method> + <method name="readVInt" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Reads a zero-compressed encoded integer from a stream and returns it. + @param in input stream + @throws java.io.IOException + @return deserialized integer]]> + </doc> + </method> + <method name="getVIntSize" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="i" type="long"/> + <doc> + <![CDATA[Get the encoded length if an integer is stored in a variable-length format + @return the encoded length]]> + </doc> + </method> + <method name="writeVLong" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="stream" type="java.io.DataOutput"/> + <param name="i" type="long"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Serializes a long to a binary stream with zero-compressed encoding. + For -112 <= i <= 127, only one byte is used with the actual value. + For other values of i, the first byte value indicates whether the + long is positive or negative, and the number of bytes that follow. + If the first byte value v is between -113 and -120, the following long + is positive, with number of bytes that follow are -(v+112). + If the first byte value v is between -121 and -128, the following long + is negative, with number of bytes that follow are -(v+120). Bytes are + stored in the high-non-zero-byte-first order. + + @param stream Binary output stream + @param i Long to be serialized + @throws java.io.IOException]]> + </doc> + </method> + <method name="writeVInt" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="stream" type="java.io.DataOutput"/> + <param name="i" type="int"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Serializes an int to a binary stream with zero-compressed encoding. + + @param stream Binary output stream + @param i int to be serialized + @throws java.io.IOException]]> + </doc> + </method> + <method name="compareBytes" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b1" type="byte[]"/> + <param name="s1" type="int"/> + <param name="l1" type="int"/> + <param name="b2" type="byte[]"/> + <param name="s2" type="int"/> + <param name="l2" type="int"/> + <doc> + <![CDATA[Lexicographic order of binary data.]]> + </doc> + </method> + <field name="hexchars" type="char[]" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[Various utility functions for Hadooop record I/O runtime.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.Utils --> + <!-- start class org.apache.hadoop.record.XmlRecordInput --> + <class name="XmlRecordInput" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.record.RecordInput"/> + <constructor name="XmlRecordInput" type="java.io.InputStream" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of XmlRecordInput]]> + </doc> + </constructor> + <method name="readByte" return="byte" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readBool" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readInt" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readLong" return="long" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readFloat" return="float" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readDouble" return="double" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="readBuffer" return="org.apache.hadoop.record.Buffer" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="startRecord" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="endRecord" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="startVector" return="org.apache.hadoop.record.Index" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="endVector" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="startMap" return="org.apache.hadoop.record.Index" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="endMap" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[XML Deserializer.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.XmlRecordInput --> + <!-- start class org.apache.hadoop.record.XmlRecordOutput --> + <class name="XmlRecordOutput" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.record.RecordOutput"/> + <constructor name="XmlRecordOutput" type="java.io.OutputStream" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of XmlRecordOutput]]> + </doc> + </constructor> + <method name="writeByte" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="byte"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeBool" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b" type="boolean"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeInt" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="i" type="int"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeLong" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="l" type="long"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeFloat" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="f" type="float"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeDouble" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="d" type="double"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeString" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="s" type="java.lang.String"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="writeBuffer" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="buf" type="org.apache.hadoop.record.Buffer"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="startRecord" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="r" type="org.apache.hadoop.record.Record"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="endRecord" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="r" type="org.apache.hadoop.record.Record"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="startVector" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="v" type="java.util.ArrayList"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="endVector" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="v" type="java.util.ArrayList"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="startMap" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="v" type="java.util.TreeMap"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="endMap" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="v" type="java.util.TreeMap"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[XML Serializer.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.XmlRecordOutput --> + <doc> + <![CDATA[Hadoop record I/O contains classes and a record description language + translator for simplifying serialization and deserialization of records in a + language-neutral manner. + + <h2>Introduction</h2> + + Software systems of any significant complexity require mechanisms for data +interchange with the outside world. These interchanges typically involve the +marshaling and unmarshaling of logical units of data to and from data streams +(files, network connections, memory buffers etc.). Applications usually have +some code for serializing and deserializing the data types that they manipulate +embedded in them. The work of serialization has several features that make +automatic code generation for it worthwhile. Given a particular output encoding +(binary, XML, etc.), serialization of primitive types and simple compositions +of primitives (structs, vectors etc.) is a very mechanical task. Manually +written serialization code can be susceptible to bugs especially when records +have a large number of fields or a record definition changes between software +versions. Lastly, it can be very useful for applications written in different +programming languages to be able to share and interchange data. This can be +made a lot easier by describing the data records manipulated by these +applications in a language agnostic manner and using the descriptions to derive +implementations of serialization in multiple target languages. + +This document describes Hadoop Record I/O, a mechanism that is aimed +at +<ul> +<li> enabling the specification of simple serializable data types (records) +<li> enabling the generation of code in multiple target languages for +marshaling and unmarshaling such types +<li> providing target language specific support that will enable application +programmers to incorporate generated code into their applications +</ul> + +The goals of Hadoop Record I/O are similar to those of mechanisms such as XDR, +ASN.1, PADS and ICE. While these systems all include a DDL that enables +the specification of most record types, they differ widely in what else they +focus on. The focus in Hadoop Record I/O is on data marshaling and +multi-lingual support. We take a translator-based approach to serialization. +Hadoop users have to describe their data in a simple data description +language. The Hadoop DDL translator rcc generates code that users +can invoke in order to read/write their data from/to simple stream +abstractions. Next we list explicitly some of the goals and non-goals of +Hadoop Record I/O. + + +<h3>Goals</h3> + +<ul> +<li> Support for commonly used primitive types. Hadoop should include as +primitives commonly used builtin types from programming languages we intend to +support. + +<li> Support for common data compositions (including recursive compositions). +Hadoop should support widely used composite types such as structs and +vectors. + +<li> Code generation in multiple target languages. Hadoop should be capable of +generating serialization code in multiple target languages and should be +easily extensible to new target languages. The initial target languages are +C++ and Java. + +<li> Support for generated target languages. Hadooop should include support +in the form of headers, libraries, packages for supported target languages +that enable easy inclusion and use of generated code in applications. + +<li> Support for multiple output encodings. Candidates include +packed binary, comma-separated text, XML etc. + +<li> Support for specifying record types in a backwards/forwards compatible +manner. This will probably be in the form of support for optional fields in +records. This version of the document does not include a description of the +planned mechanism, we intend to include it in the next iteration. + +</ul> + +<h3>Non-Goals</h3> + +<ul> + <li> Serializing existing arbitrary C++ classes. + <li> Serializing complex data structures such as trees, linked lists etc. + <li> Built-in indexing schemes, compression, or check-sums. + <li> Dynamic construction of objects from an XML schema. +</ul> + +The remainder of this document describes the features of Hadoop record I/O +in more detail. Section 2 describes the data types supported by the system. +Section 3 lays out the DDL syntax with some examples of simple records. +Section 4 describes the process of code generation with rcc. Section 5 +describes target language mappings and support for Hadoop types. We include a +fairly complete description of C++ mappings with intent to include Java and +others in upcoming iterations of this document. The last section talks about +supported output encodings. + + +<h2>Data Types and Streams</h2> + +This section describes the primitive and composite types supported by Hadoop. +We aim to support a set of types that can be used to simply and efficiently +express a wide range of record types in different programming languages. + +<h3>Primitive Types</h3> + +For the most part, the primitive types of Hadoop map directly to primitive +types in high level programming languages. Special cases are the +ustring (a Unicode string) and buffer types, which we believe +find wide use and which are usually implemented in library code and not +available as language built-ins. Hadoop also supplies these via library code +when a target language built-in is not present and there is no widely +adopted "standard" implementation. The complete list of primitive types is: + +<ul> + <li> byte: An 8-bit unsigned integer. + <li> boolean: A boolean value. + <li> int: A 32-bit signed integer. + <li> long: A 64-bit signed integer. + <li> float: A single precision floating point number as described by + IEEE-754. + <li> double: A double precision floating point number as described by + IEEE-754. + <li> ustring: A string consisting of Unicode characters. + <li> buffer: An arbitrary sequence of bytes. +</ul> + + +<h3>Composite Types</h3> +Hadoop supports a small set of composite types that enable the description +of simple aggregate types and containers. A composite type is serialized +by sequentially serializing it constituent elements. The supported +composite types are: + +<ul> + + <li> record: An aggregate type like a C-struct. This is a list of +typed fields that are together considered a single unit of data. A record +is serialized by sequentially serializing its constituent fields. In addition +to serialization a record has comparison operations (equality and less-than) +implemented for it, these are defined as memberwise comparisons. + + <li>vector: A sequence of entries of the same data type, primitive +or composite. + + <li> map: An associative container mapping instances of a key type to +instances of a value type. The key and value types may themselves be primitive +or composite types. + +</ul> + +<h3>Streams</h3> + +Hadoop generates code for serializing and deserializing record types to +abstract streams. For each target language Hadoop defines very simple input +and output stream interfaces. Application writers can usually develop +concrete implementations of these by putting a one method wrapper around +an existing stream implementation. + + +<h2>DDL Syntax and Examples</h2> + +We now describe the syntax of the Hadoop data description language. This is +followed by a few examples of DDL usage. + +<h3>Hadoop DDL Syntax</h3> + +<pre><code> +recfile = *include module *record +include = "include" path +path = (relative-path / absolute-path) +module = "module" module-name +module-name = name *("." name) +record := "class" name "{" 1*(field) "}" +field := type name ";" +name := ALPHA (ALPHA / DIGIT / "_" )* +type := (ptype / ctype) +ptype := ("byte" / "boolean" / "int" | + "long" / "float" / "double" + "ustring" / "buffer") +ctype := (("vector" "<" type ">") / + ("map" "<" type "," type ">" ) ) / name) +</code></pre> + +A DDL file describes one or more record types. It begins with zero or +more include declarations, a single mandatory module declaration +followed by zero or more class declarations. The semantics of each of +these declarations are described below: + +<ul> + +<li>include: An include declaration specifies a DDL file to be +referenced when generating code for types in the current DDL file. Record types +in the current compilation unit may refer to types in all included files. +File inclusion is recursive. An include does not trigger code +generation for the referenced file. + +<li> module: Every Hadoop DDL file must have a single module +declaration that follows the list of includes and precedes all record +declarations. A module declaration identifies a scope within which +the names of all types in the current file are visible. Module names are +mapped to C++ namespaces, Java packages etc. in generated code. + +<li> class: Records types are specified through class +declarations. A class declaration is like a Java class declaration. +It specifies a named record type and a list of fields that constitute records +of the type. Usage is illustrated in the following examples. + +</ul> + +<h3>Examples</h3> + +<ul> +<li>A simple DDL file links.jr with just one record declaration. +<pre><code> +module links { + class Link { + ustring URL; + boolean isRelative; + ustring anchorText; + }; +} +</code></pre> + +<li> A DDL file outlinks.jr which includes another +<pre><code> +include "links.jr" + +module outlinks { + class OutLinks { + ustring baseURL; + vector<links.Link> outLinks; + }; +} +</code></pre> +</ul> + +<h2>Code Generation</h2> + +The Hadoop translator is written in Java. Invocation is done by executing a +wrapper shell script named named rcc. It takes a list of +record description files as a mandatory argument and an +optional language argument (the default is Java) --language or +-l. Thus a typical invocation would look like: +<pre><code> +$ rcc -l C++ <filename> ... +</code></pre> + + +<h2>Target Language Mappings and Support</h2> + +For all target languages, the unit of code generation is a record type. +For each record type, Hadoop generates code for serialization and +deserialization, record comparison and access to record members. + +<h3>C++</h3> + +Support for including Hadoop generated C++ code in applications comes in the +form of a header file recordio.hh which needs to be included in source +that uses Hadoop types and a library librecordio.a which applications need +to be linked with. The header declares the Hadoop C++ namespace which defines +appropriate types for the various primitives, the basic interfaces for +records and streams and enumerates the supported serialization encodings. +Declarations of these interfaces and a description of their semantics follow: + +<pre><code> +namespace hadoop { + + enum RecFormat { kBinary, kXML, kCSV }; + + class InStream { + public: + virtual ssize_t read(void *buf, size_t n) = 0; + }; + + class OutStream { + public: + virtual ssize_t write(const void *buf, size_t n) = 0; + }; + + class IOError : public runtime_error { + public: + explicit IOError(const std::string& msg); + }; + + class IArchive; + class OArchive; + + class RecordReader { + public: + RecordReader(InStream& in, RecFormat fmt); + virtual ~RecordReader(void); + + virtual void read(Record& rec); + }; + + class RecordWriter { + public: + RecordWriter(OutStream& out, RecFormat fmt); + virtual ~RecordWriter(void); + + virtual void write(Record& rec); + }; + + + class Record { + public: + virtual std::string type(void) const = 0; + virtual std::string signature(void) const = 0; + protected: + virtual bool validate(void) const = 0; + + virtual void + serialize(OArchive& oa, const std::string& tag) const = 0; + + virtual void + deserialize(IArchive& ia, const std::string& tag) = 0; + }; +} +</code></pre> + +<ul> + +<li> RecFormat: An enumeration of the serialization encodings supported +by this implementation of Hadoop. + +<li> InStream: A simple abstraction for an input stream. This has a +single public read method that reads n bytes from the stream into +the buffer buf. Has the same semantics as a blocking read system +call. Returns the number of bytes read or -1 if an error occurs. + +<li> OutStream: A simple abstraction for an output stream. This has a +single write method that writes n bytes to the stream from the +buffer buf. Has the same semantics as a blocking write system +call. Returns the number of bytes written or -1 if an error occurs. + +<li> RecordReader: A RecordReader reads records one at a time from +an underlying stream in a specified record format. The reader is instantiated +with a stream and a serialization format. It has a read method that +takes an instance of a record and deserializes the record from the stream. + +<li> RecordWriter: A RecordWriter writes records one at a +time to an underlying stream in a specified record format. The writer is +instantiated with a stream and a serialization format. It has a +write method that takes an instance of a record and serializes the +record to the stream. + +<li> Record: The base class for all generated record types. This has two +public methods type and signature that return the typename and the +type signature of the record. + +</ul> + +Two files are generated for each record file (note: not for each record). If a +record file is named "name.jr", the generated files are +"name.jr.cc" and "name.jr.hh" containing serialization +implementations and record type declarations respectively. + +For each record in the DDL file, the generated header file will contain a +class definition corresponding to the record type, method definitions for the +generated type will be present in the '.cc' file. The generated class will +inherit from the abstract class hadoop::Record. The DDL files +module declaration determines the namespace the record belongs to. +Each '.' delimited token in the module declaration results in the +creation of a namespace. For instance, the declaration module docs.links +results in the creation of a docs namespace and a nested +docs::links namespace. In the preceding examples, the Link class +is placed in the links namespace. The header file corresponding to +the links.jr file will contain: + +<pre><code> +namespace links { + class Link : public hadoop::Record { + // .... + }; +}; +</code></pre> + +Each field within the record will cause the generation of a private member +declaration of the appropriate type in the class declaration, and one or more +acccessor methods. The generated class will implement the serialize and +deserialize methods defined in hadoop::Record+. It will also +implement the inspection methods type and signature from +hadoop::Record. A default constructor and virtual destructor will also +be generated. Serialization code will read/write records into streams that +implement the hadoop::InStream and the hadoop::OutStream interfaces. + +For each member of a record an accessor method is generated that returns +either the member or a reference to the member. For members that are returned +by value, a setter method is also generated. This is true for primitive +data members of the types byte, int, long, boolean, float and +double. For example, for a int field called MyField the folowing +code is generated. + +<pre><code> +... +private: + int32_t mMyField; + ... +public: + int32_t getMyField(void) const { + return mMyField; + }; + + void setMyField(int32_t m) { + mMyField = m; + }; + ... +</code></pre> + +For a ustring or buffer or composite field. The generated code +only contains accessors that return a reference to the field. A const +and a non-const accessor are generated. For example: + +<pre><code> +... +private: + std::string mMyBuf; + ... +public: + + std::string& getMyBuf() { + return mMyBuf; + }; + + const std::string& getMyBuf() const { + return mMyBuf; + }; + ... +</code></pre> + +<h4>Examples</h4> + +Suppose the inclrec.jr file contains: +<pre><code> +module inclrec { + class RI { + int I32; + double D; + ustring S; + }; +} +</code></pre> + +and the testrec.jr file contains: + +<pre><code> +include "inclrec.jr" +module testrec { + class R { + vector<float> VF; + RI Rec; + buffer Buf; + }; +} +</code></pre> + +Then the invocation of rcc such as: +<pre><code> +$ rcc -l c++ inclrec.jr testrec.jr +</code></pre> +will result in generation of four files: +inclrec.jr.{cc,hh} and testrec.jr.{cc,hh}. + +The inclrec.jr.hh will contain: + +<pre><code> +#ifndef _INCLREC_JR_HH_ +#define _INCLREC_JR_HH_ + +#include "recordio.hh" + +namespace inclrec { + + class RI : public hadoop::Record { + + private: + + int32_t I32; + double D; + std::string S; + + public: + + RI(void); + virtual ~RI(void); + + virtual bool operator==(const RI& peer) const; + virtual bool operator<(const RI& peer) const; + + virtual int32_t getI32(void) const { return I32; } + virtual void setI32(int32_t v) { I32 = v; } + + virtual double getD(void) const { return D; } + virtual void setD(double v) { D = v; } + + virtual std::string& getS(void) const { return S; } + virtual const std::string& getS(void) const { return S; } + + virtual std::string type(void) const; + virtual std::string signature(void) const; + + protected: + + virtual void serialize(hadoop::OArchive& a) const; + virtual void deserialize(hadoop::IArchive& a); + }; +} // end namespace inclrec + +#endif /* _INCLREC_JR_HH_ */ + +</code></pre> + +The testrec.jr.hh file will contain: + + +<pre><code> + +#ifndef _TESTREC_JR_HH_ +#define _TESTREC_JR_HH_ + +#include "inclrec.jr.hh" + +namespace testrec { + class R : public hadoop::Record { + + private: + + std::vector<float> VF; + inclrec::RI Rec; + std::string Buf; + + public: + + R(void); + virtual ~R(void); + + virtual bool operator==(const R& peer) const; + virtual bool operator<(const R& peer) const; + + virtual std::vector<float>& getVF(void) const; + virtual const std::vector<float>& getVF(void) const; + + virtual std::string& getBuf(void) const ; + virtual const std::string& getBuf(void) const; + + virtual inclrec::RI& getRec(void) const; + virtual const inclrec::RI& getRec(void) const; + + virtual bool serialize(hadoop::OutArchive& a) const; + virtual bool deserialize(hadoop::InArchive& a); + + virtual std::string type(void) const; + virtual std::string signature(void) const; + }; +}; // end namespace testrec +#endif /* _TESTREC_JR_HH_ */ + +</code></pre> + +<h3>Java</h3> + +Code generation for Java is similar to that for C++. A Java class is generated +for each record type with private members corresponding to the fields. Getters +and setters for fields are also generated. Some differences arise in the +way comparison is expressed and in the mapping of modules to packages and +classes to files. For equality testing, an equals method is generated +for each record type. As per Java requirements a hashCode method is also +generated. For comparison a compareTo method is generated for each +record type. This has the semantics as defined by the Java Comparable +interface, that is, the method returns a negative integer, zero, or a positive +integer as the invoked object is less than, equal to, or greater than the +comparison parameter. + +A .java file is generated per record type as opposed to per DDL +file as in C++. The module declaration translates to a Java +package declaration. The module name maps to an identical Java package +name. In addition to this mapping, the DDL compiler creates the appropriate +directory hierarchy for the package and places the generated .java +files in the correct directories. + +<h2>Mapping Summary</h2> + +<pre><code> +DDL Type C++ Type Java Type + +boolean bool boolean +byte int8_t byte +int int32_t int +long int64_t long +float float float +double double double +ustring std::string java.lang.String +buffer std::string org.apache.hadoop.record.Buffer +class type class type class type +vector<type> std::vector<type> java.util.ArrayList<type> +map<type,type> std::map<type,type> java.util.TreeMap<type,type> +</code></pre> + +<h2>Data encodings</h2> + +This section describes the format of the data encodings supported by Hadoop. +Currently, three data encodings are supported, namely binary, CSV and XML. + +<h3>Binary Serialization Format</h3> + +The binary data encoding format is fairly dense. Serialization of composite +types is simply defined as a concatenation of serializations of the constituent +elements (lengths are included in vectors and maps). + +Composite types are serialized as follows: +<ul> +<li> class: Sequence of serialized members. +<li> vector: The number of elements serialized as an int. Followed by a +sequence of serialized elements. +<li> map: The number of key value pairs serialized as an int. Followed +by a sequence of serialized (key,value) pairs. +</ul> + +Serialization of primitives is more interesting, with a zero compression +optimization for integral types and normalization to UTF-8 for strings. +Primitive types are serialized as follows: + +<ul> +<li> byte: Represented by 1 byte, as is. +<li> boolean: Represented by 1-byte (0 or 1) +<li> int/long: Integers and longs are serialized zero compressed. +Represented as 1-byte if -120 <= value < 128. Otherwise, serialized as a +sequence of 2-5 bytes for ints, 2-9 bytes for longs. The first byte represents +the number of trailing bytes, N, as the negative number (-120-N). For example, +the number 1024 (0x400) is represented by the byte sequence 'x86 x04 x00'. +This doesn't help much for 4-byte integers but does a reasonably good job with +longs without bit twiddling. +<li> float/double: Serialized in IEEE 754 single and double precision +format in network byte order. This is the format used by Java. +<li> ustring: Serialized as 4-byte zero compressed length followed by +data encoded as UTF-8. Strings are normalized to UTF-8 regardless of native +language representation. +<li> buffer: Serialized as a 4-byte zero compressed length followed by the +raw bytes in the buffer. +</ul> + + +<h3>CSV Serialization Format</h3> + +The CSV serialization format has a lot more structure than the "standard" +Excel CSV format, but we believe the additional structure is useful because + +<ul> +<li> it makes parsing a lot easier without detracting too much from legibility +<li> the delimiters around composites make it obvious when one is reading a +sequence of Hadoop records +</ul> + +Serialization formats for the various types are detailed in the grammar that +follows. The notable feature of the formats is the use of delimiters for +indicating the certain field types. + +<ul> +<li> A string field begins with a single quote ('). +<li> A buffer field begins with a sharp (#). +<li> A class, vector or map begins with 's{', 'v{' or 'm{' respectively and +ends with '}'. +</ul> + +The CSV format can be described by the following grammar: + +<pre><code> +record = primitive / struct / vector / map +primitive = boolean / int / long / float / double / ustring / buffer + +boolean = "T" / "F" +int = ["-"] 1*DIGIT +long = ";" ["-"] 1*DIGIT +float = ["-"] 1*DIGIT "." 1*DIGIT ["E" / "e" ["-"] 1*DIGIT] +double = ";" ["-"] 1*DIGIT "." 1*DIGIT ["E" / "e" ["-"] 1*DIGIT] + +ustring = "'" *(UTF8 char except NULL, LF, % and , / "%00" / "%0a" / "%25" / "%2c" ) + +buffer = "#" *(BYTE except NULL, LF, % and , / "%00" / "%0a" / "%25" / "%2c" ) + +struct = "s{" record *("," record) "}" +vector = "v{" [record *("," record)] "}" +map = "m{" [*(record "," record)] "}" +</code></pre> + +<h3>XML Serialization Format</h3> + +The XML serialization format is the same used by Apache XML-RPC +(http://ws.apache.org/xmlrpc/types.html). This is an extension of the original +XML-RPC format and adds some additional data types. All record I/O types are +not directly expressible in this format, and access to a DDL is required in +order to convert these to valid types. All types primitive or composite are +represented by <value> elements. The particular XML-RPC type is +indicated by a nested element in the <value> element. The encoding for +records is always UTF-8. Primitive types are serialized as follows: + +<ul> +<li> byte: XML tag <ex:i1>. Values: 1-byte unsigned +integers represented in US-ASCII +<li> boolean: XML tag <boolean>. Values: "0" or "1" +<li> int: XML tags <i4> or <int>. Values: 4-byte +signed integers represented in US-ASCII. +<li> long: XML tag <ex:i8>. Values: 8-byte signed integers +represented in US-ASCII. +<li> float: XML tag <ex:float>. Values: Single precision +floating point numbers represented in US-ASCII. +<li> double: XML tag <double>. Values: Double precision +floating point numbers represented in US-ASCII. +<li> ustring: XML tag <;string>. Values: String values +represented as UTF-8. XML does not permit all Unicode characters in literal +data. In particular, NULLs and control chars are not allowed. Additionally, +XML processors are required to replace carriage returns with line feeds and to +replace CRLF sequences with line feeds. Programming languages that we work +with do not impose these restrictions on string types. To work around these +restrictions, disallowed characters and CRs are percent escaped in strings. +The '%' character is also percent escaped. +<li> buffer: XML tag <string&>. Values: Arbitrary binary +data. Represented as hexBinary, each byte is replaced by its 2-byte +hexadecimal representation. +</ul> + +Composite types are serialized as follows: + +<ul> +<li> class: XML tag <struct>. A struct is a sequence of +<member> elements. Each <member> element has a <name> +element and a <value> element. The <name> is a string that must +match /[a-zA-Z][a-zA-Z0-9_]*/. The value of the member is represented +by a <value> element. + +<li> vector: XML tag <array<. An <array> contains a +single <data> element. The <data> element is a sequence of +<value> elements each of which represents an element of the vector. + +<li> map: XML tag <array>. Same as vector. + +</ul> + +For example: + +<pre><code> +class { + int MY_INT; // value 5 + vector<float> MY_VEC; // values 0.1, -0.89, 2.45e4 + buffer MY_BUF; // value '\00\n\tabc%' +} +</code></pre> + +is serialized as + +<pre><code class="XML"> +<value> + <struct> + <member> + <name>MY_INT</name> + <value><i4>5</i4></value> + </member> + <member> + <name>MY_VEC</name> + <value> + <array> + <data> + <value><ex:float>0.1</ex:float></value> + <value><ex:float>-0.89</ex:float></value> + <value><ex:float>2.45e4</ex:float></value> + </data> + </array> + </value> + </member> + <member> + <name>MY_BUF</name> + <value><string>%00\n\tabc%25</string></value> + </member> + </struct> +</value> +</code></pre>]]> + </doc> +</package> +<package name="org.apache.hadoop.record.compiler"> + <!-- start class org.apache.hadoop.record.compiler.CodeBuffer --> + <class name="CodeBuffer" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[A wrapper around StringBuffer that automatically does indentation]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.compiler.CodeBuffer --> + <!-- start class org.apache.hadoop.record.compiler.Consts --> + <class name="Consts" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <field name="RIO_PREFIX" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="RTI_VAR" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="RTI_FILTER" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="RTI_FILTER_FIELDS" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="RECORD_OUTPUT" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="RECORD_INPUT" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="TAG" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[const definitions for Record I/O compiler]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.compiler.Consts --> + <!-- start class org.apache.hadoop.record.compiler.JBoolean --> + <class name="JBoolean" extends="org.apache.hadoop.record.compiler.JType" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JBoolean" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of JBoolean]]> + </doc> + </constructor> + </class> + <!-- end class org.apache.hadoop.record.compiler.JBoolean --> + <!-- start class org.apache.hadoop.record.compiler.JBuffer --> + <class name="JBuffer" extends="org.apache.hadoop.record.compiler.JCompType" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JBuffer" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of JBuffer]]> + </doc> + </constructor> + <doc> + <![CDATA[Code generator for "buffer" type.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.compiler.JBuffer --> + <!-- start class org.apache.hadoop.record.compiler.JByte --> + <class name="JByte" extends="org.apache.hadoop.record.compiler.JType" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JByte" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <doc> + <![CDATA[Code generator for "byte" type.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.compiler.JByte --> + <!-- start class org.apache.hadoop.record.compiler.JDouble --> + <class name="JDouble" extends="org.apache.hadoop.record.compiler.JType" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JDouble" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of JDouble]]> + </doc> + </constructor> + </class> + <!-- end class org.apache.hadoop.record.compiler.JDouble --> + <!-- start class org.apache.hadoop.record.compiler.JField --> + <class name="JField" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JField" type="java.lang.String, T" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of JField]]> + </doc> + </constructor> + <doc> + <![CDATA[A thin wrappper around record field.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.compiler.JField --> + <!-- start class org.apache.hadoop.record.compiler.JFile --> + <class name="JFile" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JFile" type="java.lang.String, java.util.ArrayList<org.apache.hadoop.record.compiler.JFile>, java.util.ArrayList<org.apache.hadoop.record.compiler.JRecord>" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of JFile + + @param name possibly full pathname to the file + @param inclFiles included files (as JFile) + @param recList List of records defined within this file]]> + </doc> + </constructor> + <method name="genCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="language" type="java.lang.String"/> + <param name="destDir" type="java.lang.String"/> + <param name="options" type="java.util.ArrayList<java.lang.String>"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Generate record code in given language. Language should be all + lowercase.]]> + </doc> + </method> + <doc> + <![CDATA[Container for the Hadoop Record DDL. + The main components of the file are filename, list of included files, + and records defined in that file.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.compiler.JFile --> + <!-- start class org.apache.hadoop.record.compiler.JFloat --> + <class name="JFloat" extends="org.apache.hadoop.record.compiler.JType" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JFloat" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of JFloat]]> + </doc> + </constructor> + </class> + <!-- end class org.apache.hadoop.record.compiler.JFloat --> + <!-- start class org.apache.hadoop.record.compiler.JInt --> + <class name="JInt" extends="org.apache.hadoop.record.compiler.JType" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JInt" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of JInt]]> + </doc> + </constructor> + <doc> + <![CDATA[Code generator for "int" type]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.compiler.JInt --> + <!-- start class org.apache.hadoop.record.compiler.JLong --> + <class name="JLong" extends="org.apache.hadoop.record.compiler.JType" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JLong" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of JLong]]> + </doc> + </constructor> + <doc> + <![CDATA[Code generator for "long" type]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.compiler.JLong --> + <!-- start class org.apache.hadoop.record.compiler.JMap --> + <class name="JMap" extends="org.apache.hadoop.record.compiler.JCompType" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JMap" type="org.apache.hadoop.record.compiler.JType, org.apache.hadoop.record.compiler.JType" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of JMap]]> + </doc> + </constructor> + </class> + <!-- end class org.apache.hadoop.record.compiler.JMap --> + <!-- start class org.apache.hadoop.record.compiler.JRecord --> + <class name="JRecord" extends="org.apache.hadoop.record.compiler.JCompType" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JRecord" type="java.lang.String, java.util.ArrayList<org.apache.hadoop.record.compiler.JField<org.apache.hadoop.record.compiler.JType>>" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of JRecord]]> + </doc> + </constructor> + </class> + <!-- end class org.apache.hadoop.record.compiler.JRecord --> + <!-- start class org.apache.hadoop.record.compiler.JString --> + <class name="JString" extends="org.apache.hadoop.record.compiler.JCompType" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JString" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of JString]]> + </doc> + </constructor> + </class> + <!-- end class org.apache.hadoop.record.compiler.JString --> + <!-- start class org.apache.hadoop.record.compiler.JType --> + <class name="JType" extends="java.lang.Object" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JType" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <doc> + <![CDATA[Abstract Base class for all types supported by Hadoop Record I/O.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.compiler.JType --> + <!-- start class org.apache.hadoop.record.compiler.JVector --> + <class name="JVector" extends="org.apache.hadoop.record.compiler.JCompType" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="JVector" type="org.apache.hadoop.record.compiler.JType" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of JVector]]> + </doc> + </constructor> + </class> + <!-- end class org.apache.hadoop.record.compiler.JVector --> + <doc> + <![CDATA[This package contains classes needed for code generation + from the hadoop record compiler. CppGenerator and JavaGenerator + are the main entry points from the parser. There are classes + corrsponding to every primitive type and compound type + included in Hadoop record I/O syntax.]]> + </doc> +</package> +<package name="org.apache.hadoop.record.compiler.ant"> + <!-- start class org.apache.hadoop.record.compiler.ant.RccTask --> + <class name="RccTask" extends="org.apache.tools.ant.Task" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="RccTask" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new instance of RccTask]]> + </doc> + </constructor> + <method name="setLanguage" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="language" type="java.lang.String"/> + <doc> + <![CDATA[Sets the output language option + @param language "java"/"c++"]]> + </doc> + </method> + <method name="setFile" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="file" type="java.io.File"/> + <doc> + <![CDATA[Sets the record definition file attribute + @param file record definition file]]> + </doc> + </method> + <method name="setFailonerror" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="flag" type="boolean"/> + <doc> + <![CDATA[Given multiple files (via fileset), set the error handling behavior + @param flag true will throw build exception in case of failure (default)]]> + </doc> + </method> + <method name="setDestdir" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dir" type="java.io.File"/> + <doc> + <![CDATA[Sets directory where output files will be generated + @param dir output directory]]> + </doc> + </method> + <method name="addFileset" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="set" type="org.apache.tools.ant.types.FileSet"/> + <doc> + <![CDATA[Adds a fileset that can consist of one or more files + @param set Set of record definition files]]> + </doc> + </method> + <method name="execute" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="BuildException" type="org.apache.tools.ant.BuildException"/> + <doc> + <![CDATA[Invoke the Hadoop record compiler on each record definition file]]> + </doc> + </method> + <doc> + <![CDATA[Hadoop record compiler ant Task +<p> This task takes the given record definition files and compiles them into + java or c++ + files. It is then up to the user to compile the generated files. + + <p> The task requires the <code>file</code> or the nested fileset element to be + specified. Optional attributes are <code>language</code> (set the output + language, default is "java"), + <code>destdir</code> (name of the destination directory for generated java/c++ + code, default is ".") and <code>failonerror</code> (specifies error handling + behavior. default is true). + <p><h4>Usage</h4> + <pre> + <recordcc + destdir="${basedir}/gensrc" + language="java"> + <fileset include="**\/*.jr" /> + </recordcc> + </pre>]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.compiler.ant.RccTask --> +</package> +<package name="org.apache.hadoop.record.compiler.generated"> + <!-- start class org.apache.hadoop.record.compiler.generated.ParseException --> + <class name="ParseException" extends="java.lang.Exception" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="ParseException" type="org.apache.hadoop.record.compiler.generated.Token, int[][], java.lang.String[]" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[This constructor is used by the method "generateParseException" + in the generated parser. Calling this constructor generates + a new object of this type with the fields "currentToken", + "expectedTokenSequences", and "tokenImage" set. The boolean + flag "specialConstructor" is also set to true to indicate that + this constructor was used to create this object. + This constructor calls its super class with the empty string + to force the "toString" method of parent class "Throwable" to + print the error message in the form: + ParseException: <result of getMessage>]]> + </doc> + </constructor> + <constructor name="ParseException" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The following constructors are for use by you for whatever + purpose you can think of. Constructing the exception in this + manner makes the exception behave in the normal way - i.e., as + documented in the class "Throwable". The fields "errorToken", + "expectedTokenSequences", and "tokenImage" do not contain + relevant information. The JavaCC generated code does not use + these constructors.]]> + </doc> + </constructor> + <constructor name="ParseException" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getMessage" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[This method has the standard behavior when this object has been + created using the standard constructors. Otherwise, it uses + "currentToken" and "expectedTokenSequences" to generate a parse + error message and returns it. If this object has been created + due to a parse error, and you do not catch it (it gets thrown + from the parser), then this method is called during the printing + of the final stack trace, and hence the correct error message + gets displayed.]]> + </doc> + </method> + <method name="add_escapes" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="str" type="java.lang.String"/> + <doc> + <![CDATA[Used to convert raw characters to their escaped version + when these raw version cannot be used as part of an ASCII + string literal.]]> + </doc> + </method> + <field name="specialConstructor" type="boolean" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[This variable determines which constructor was used to create + this object and thereby affects the semantics of the + "getMessage" method (see below).]]> + </doc> + </field> + <field name="currentToken" type="org.apache.hadoop.record.compiler.generated.Token" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[This is the last token that has been consumed successfully. If + this object has been created due to a parse error, the token + followng this token will (therefore) be the first error token.]]> + </doc> + </field> + <field name="expectedTokenSequences" type="int[][]" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Each entry in this array is an array of integers. Each array + of integers represents a sequence of tokens (by their ordinal + values) that is expected at this point of the parse.]]> + </doc> + </field> + <field name="tokenImage" type="java.lang.String[]" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[This is a reference to the "tokenImage" array of the generated + parser within which the parse error occurred. This array is + defined in the generated ...Constants interface.]]> + </doc> + </field> + <field name="eol" type="java.lang.String" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[The end of line string for this machine.]]> + </doc> + </field> + <doc> + <![CDATA[This exception is thrown when parse errors are encountered. + You can explicitly create objects of this exception type by + calling the method generateParseException in the generated + parser. + + You can modify this class to customize your error reporting + mechanisms so long as you retain the public fields.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.compiler.generated.ParseException --> + <!-- start class org.apache.hadoop.record.compiler.generated.Rcc --> + <class name="Rcc" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.record.compiler.generated.RccConstants"/> + <constructor name="Rcc" type="java.io.InputStream" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="Rcc" type="java.io.InputStream, java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="Rcc" type="java.io.Reader" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="Rcc" type="org.apache.hadoop.record.compiler.generated.RccTokenManager" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + </method> + <method name="usage" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="driver" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + </method> + <method name="Input" return="org.apache.hadoop.record.compiler.JFile" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <exception name="ParseException" type="org.apache.hadoop.record.compiler.generated.ParseException"/> + </method> + <method name="Include" return="org.apache.hadoop.record.compiler.JFile" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <exception name="ParseException" type="org.apache.hadoop.record.compiler.generated.ParseException"/> + </method> + <method name="Module" return="java.util.ArrayList<org.apache.hadoop.record.compiler.JRecord>" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <exception name="ParseException" type="org.apache.hadoop.record.compiler.generated.ParseException"/> + </method> + <method name="ModuleName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <exception name="ParseException" type="org.apache.hadoop.record.compiler.generated.ParseException"/> + </method> + <method name="RecordList" return="java.util.ArrayList<org.apache.hadoop.record.compiler.JRecord>" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <exception name="ParseException" type="org.apache.hadoop.record.compiler.generated.ParseException"/> + </method> + <method name="Record" return="org.apache.hadoop.record.compiler.JRecord" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <exception name="ParseException" type="org.apache.hadoop.record.compiler.generated.ParseException"/> + </method> + <method name="Field" return="org.apache.hadoop.record.compiler.JField<org.apache.hadoop.record.compiler.JType>" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <exception name="ParseException" type="org.apache.hadoop.record.compiler.generated.ParseException"/> + </method> + <method name="Type" return="org.apache.hadoop.record.compiler.JType" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <exception name="ParseException" type="org.apache.hadoop.record.compiler.generated.ParseException"/> + </method> + <method name="Map" return="org.apache.hadoop.record.compiler.JMap" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <exception name="ParseException" type="org.apache.hadoop.record.compiler.generated.ParseException"/> + </method> + <method name="Vector" return="org.apache.hadoop.record.compiler.JVector" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <exception name="ParseException" type="org.apache.hadoop.record.compiler.generated.ParseException"/> + </method> + <method name="ReInit" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="stream" type="java.io.InputStream"/> + </method> + <method name="ReInit" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="stream" type="java.io.InputStream"/> + <param name="encoding" type="java.lang.String"/> + </method> + <method name="ReInit" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="stream" type="java.io.Reader"/> + </method> + <method name="ReInit" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tm" type="org.apache.hadoop.record.compiler.generated.RccTokenManager"/> + </method> + <method name="getNextToken" return="org.apache.hadoop.record.compiler.generated.Token" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getToken" return="org.apache.hadoop.record.compiler.generated.Token" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <param name="index" type="int"/> + </method> + <method name="generateParseException" return="org.apache.hadoop.record.compiler.generated.ParseException" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="enable_tracing" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + </method> + <method name="disable_tracing" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + </method> + <field name="token_source" type="org.apache.hadoop.record.compiler.generated.RccTokenManager" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="token" type="org.apache.hadoop.record.compiler.generated.Token" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="jj_nt" type="org.apache.hadoop.record.compiler.generated.Token" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + </class> + <!-- end class org.apache.hadoop.record.compiler.generated.Rcc --> + <!-- start interface org.apache.hadoop.record.compiler.generated.RccConstants --> + <interface name="RccConstants" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <field name="EOF" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="MODULE_TKN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="RECORD_TKN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="INCLUDE_TKN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="BYTE_TKN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="BOOLEAN_TKN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="INT_TKN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="LONG_TKN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="FLOAT_TKN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="DOUBLE_TKN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="USTRING_TKN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="BUFFER_TKN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="VECTOR_TKN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="MAP_TKN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="LBRACE_TKN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="RBRACE_TKN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="LT_TKN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="GT_TKN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="SEMICOLON_TKN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="COMMA_TKN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="DOT_TKN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="CSTRING_TKN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="IDENT_TKN" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="DEFAULT" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="WithinOneLineComment" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="WithinMultiLineComment" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="tokenImage" type="java.lang.String[]" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + </interface> + <!-- end interface org.apache.hadoop.record.compiler.generated.RccConstants --> + <!-- start class org.apache.hadoop.record.compiler.generated.RccTokenManager --> + <class name="RccTokenManager" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.record.compiler.generated.RccConstants"/> + <constructor name="RccTokenManager" type="org.apache.hadoop.record.compiler.generated.SimpleCharStream" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="RccTokenManager" type="org.apache.hadoop.record.compiler.generated.SimpleCharStream, int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="setDebugStream" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="ds" type="java.io.PrintStream"/> + </method> + <method name="ReInit" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="stream" type="org.apache.hadoop.record.compiler.generated.SimpleCharStream"/> + </method> + <method name="ReInit" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="stream" type="org.apache.hadoop.record.compiler.generated.SimpleCharStream"/> + <param name="lexState" type="int"/> + </method> + <method name="SwitchTo" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="lexState" type="int"/> + </method> + <method name="jjFillToken" return="org.apache.hadoop.record.compiler.generated.Token" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </method> + <method name="getNextToken" return="org.apache.hadoop.record.compiler.generated.Token" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <field name="debugStream" type="java.io.PrintStream" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="jjstrLiteralImages" type="java.lang.String[]" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="lexStateNames" type="java.lang.String[]" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="jjnewLexState" type="int[]" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="input_stream" type="org.apache.hadoop.record.compiler.generated.SimpleCharStream" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="curChar" type="char" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + </class> + <!-- end class org.apache.hadoop.record.compiler.generated.RccTokenManager --> + <!-- start class org.apache.hadoop.record.compiler.generated.SimpleCharStream --> + <class name="SimpleCharStream" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="SimpleCharStream" type="java.io.Reader, int, int, int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="SimpleCharStream" type="java.io.Reader, int, int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="SimpleCharStream" type="java.io.Reader" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="SimpleCharStream" type="java.io.InputStream, java.lang.String, int, int, int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="UnsupportedEncodingException" type="java.io.UnsupportedEncodingException"/> + </constructor> + <constructor name="SimpleCharStream" type="java.io.InputStream, int, int, int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="SimpleCharStream" type="java.io.InputStream, java.lang.String, int, int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="UnsupportedEncodingException" type="java.io.UnsupportedEncodingException"/> + </constructor> + <constructor name="SimpleCharStream" type="java.io.InputStream, int, int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="SimpleCharStream" type="java.io.InputStream, java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="UnsupportedEncodingException" type="java.io.UnsupportedEncodingException"/> + </constructor> + <constructor name="SimpleCharStream" type="java.io.InputStream" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="setTabSize" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="i" type="int"/> + </method> + <method name="getTabSize" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="i" type="int"/> + </method> + <method name="ExpandBuff" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="wrapAround" type="boolean"/> + </method> + <method name="FillBuff" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="BeginToken" return="char" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="UpdateLineColumn" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="c" type="char"/> + </method> + <method name="readChar" return="char" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getEndColumn" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getEndLine" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getBeginColumn" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getBeginLine" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="backup" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="amount" type="int"/> + </method> + <method name="ReInit" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dstream" type="java.io.Reader"/> + <param name="startline" type="int"/> + <param name="startcolumn" type="int"/> + <param name="buffersize" type="int"/> + </method> + <method name="ReInit" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dstream" type="java.io.Reader"/> + <param name="startline" type="int"/> + <param name="startcolumn" type="int"/> + </method> + <method name="ReInit" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dstream" type="java.io.Reader"/> + </method> + <method name="ReInit" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dstream" type="java.io.InputStream"/> + <param name="encoding" type="java.lang.String"/> + <param name="startline" type="int"/> + <param name="startcolumn" type="int"/> + <param name="buffersize" type="int"/> + <exception name="UnsupportedEncodingException" type="java.io.UnsupportedEncodingException"/> + </method> + <method name="ReInit" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dstream" type="java.io.InputStream"/> + <param name="startline" type="int"/> + <param name="startcolumn" type="int"/> + <param name="buffersize" type="int"/> + </method> + <method name="ReInit" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dstream" type="java.io.InputStream"/> + <param name="encoding" type="java.lang.String"/> + <exception name="UnsupportedEncodingException" type="java.io.UnsupportedEncodingException"/> + </method> + <method name="ReInit" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dstream" type="java.io.InputStream"/> + </method> + <method name="ReInit" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dstream" type="java.io.InputStream"/> + <param name="encoding" type="java.lang.String"/> + <param name="startline" type="int"/> + <param name="startcolumn" type="int"/> + <exception name="UnsupportedEncodingException" type="java.io.UnsupportedEncodingException"/> + </method> + <method name="ReInit" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dstream" type="java.io.InputStream"/> + <param name="startline" type="int"/> + <param name="startcolumn" type="int"/> + </method> + <method name="GetImage" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="GetSuffix" return="char[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="len" type="int"/> + </method> + <method name="Done" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="adjustBeginLineColumn" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="newLine" type="int"/> + <param name="newCol" type="int"/> + <doc> + <![CDATA[Method to adjust line and column numbers for the start of a token.]]> + </doc> + </method> + <field name="staticFlag" type="boolean" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="bufpos" type="int" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </field> + <field name="bufline" type="int[]" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="bufcolumn" type="int[]" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="column" type="int" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="line" type="int" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="prevCharIsCR" type="boolean" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="prevCharIsLF" type="boolean" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="inputStream" type="java.io.Reader" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="buffer" type="char[]" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="maxNextCharInd" type="int" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="inBuf" type="int" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <field name="tabSize" type="int" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[An implementation of interface CharStream, where the stream is assumed to + contain only ASCII characters (without unicode processing).]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.compiler.generated.SimpleCharStream --> + <!-- start class org.apache.hadoop.record.compiler.generated.Token --> + <class name="Token" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="Token" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the image.]]> + </doc> + </method> + <method name="newToken" return="org.apache.hadoop.record.compiler.generated.Token" + abstract="false" native="false" synchronized="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <param name="ofKind" type="int"/> + <doc> + <![CDATA[Returns a new Token object, by default. However, if you want, you + can create and return subclass objects based on the value of ofKind. + Simply add the cases to the switch for all those special cases. + For example, if you have a subclass of Token called IDToken that + you want to create if ofKind is ID, simlpy add something like : + + case MyParserConstants.ID : return new IDToken(); + + to the following switch statement. Then you can cast matchedToken + variable to the appropriate type and use it in your lexical actions.]]> + </doc> + </method> + <field name="kind" type="int" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[An integer that describes the kind of this token. This numbering + system is determined by JavaCCParser, and a table of these numbers is + stored in the file ...Constants.java.]]> + </doc> + </field> + <field name="beginLine" type="int" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[beginLine and beginColumn describe the position of the first character + of this token; endLine and endColumn describe the position of the + last character of this token.]]> + </doc> + </field> + <field name="beginColumn" type="int" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[beginLine and beginColumn describe the position of the first character + of this token; endLine and endColumn describe the position of the + last character of this token.]]> + </doc> + </field> + <field name="endLine" type="int" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[beginLine and beginColumn describe the position of the first character + of this token; endLine and endColumn describe the position of the + last character of this token.]]> + </doc> + </field> + <field name="endColumn" type="int" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[beginLine and beginColumn describe the position of the first character + of this token; endLine and endColumn describe the position of the + last character of this token.]]> + </doc> + </field> + <field name="image" type="java.lang.String" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The string image of the token.]]> + </doc> + </field> + <field name="next" type="org.apache.hadoop.record.compiler.generated.Token" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[A reference to the next regular (non-special) token from the input + stream. If this is the last token from the input stream, or if the + token manager has not read tokens beyond this one, this field is + set to null. This is true only if this token is also a regular + token. Otherwise, see below for a description of the contents of + this field.]]> + </doc> + </field> + <field name="specialToken" type="org.apache.hadoop.record.compiler.generated.Token" + transient="false" volatile="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[This field is used to access special tokens that occur prior to this + token, but after the immediately preceding regular (non-special) token. + If there are no such special tokens, this field is set to null. + When there are more than one such special token, this field refers + to the last of these special tokens, which in turn refers to the next + previous special token through its specialToken field, and so on + until the first special token (whose specialToken field is null). + The next fields of special tokens refer to other special tokens that + immediately follow it (without an intervening regular token). If there + is no such token, this field is null.]]> + </doc> + </field> + <doc> + <![CDATA[Describes the input token stream.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.compiler.generated.Token --> + <!-- start class org.apache.hadoop.record.compiler.generated.TokenMgrError --> + <class name="TokenMgrError" extends="java.lang.Error" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="TokenMgrError" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="TokenMgrError" type="java.lang.String, int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="TokenMgrError" type="boolean, int, int, int, java.lang.String, char, int" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="addEscapes" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="true" visibility="protected" + deprecated="not deprecated"> + <param name="str" type="java.lang.String"/> + <doc> + <![CDATA[Replaces unprintable characters by their espaced (or unicode escaped) + equivalents in the given string]]> + </doc> + </method> + <method name="LexicalError" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="EOFSeen" type="boolean"/> + <param name="lexState" type="int"/> + <param name="errorLine" type="int"/> + <param name="errorColumn" type="int"/> + <param name="errorAfter" type="java.lang.String"/> + <param name="curChar" type="char"/> + <doc> + <![CDATA[Returns a detailed message for the Error when it is thrown by the + token manager to indicate a lexical error. + Parameters : + EOFSeen : indicates if EOF caused the lexicl error + curLexState : lexical state in which this error occured + errorLine : line number when the error occured + errorColumn : column number when the error occured + errorAfter : prefix that was seen before this error occured + curchar : the offending character + Note: You can customize the lexical error message by modifying this method.]]> + </doc> + </method> + <method name="getMessage" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[You can also modify the body of this method to customize your error messages. + For example, cases like LOOP_DETECTED and INVALID_LEXICAL_STATE are not + of end-users concern, so you can return something like : + + "Internal Error : Please file a bug report .... " + + from this method for such cases in the release version of your parser.]]> + </doc> + </method> + </class> + <!-- end class org.apache.hadoop.record.compiler.generated.TokenMgrError --> + <doc> + <![CDATA[This package contains code generated by JavaCC from the + Hadoop record syntax file rcc.jj. For details about the + record file syntax please @see org.apache.hadoop.record.]]> + </doc> +</package> +<package name="org.apache.hadoop.record.meta"> + <!-- start class org.apache.hadoop.record.meta.FieldTypeInfo --> + <class name="FieldTypeInfo" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="getTypeID" return="org.apache.hadoop.record.meta.TypeID" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[get the field's TypeID object]]> + </doc> + </method> + <method name="getFieldID" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[get the field's id (name)]]> + </doc> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + <doc> + <![CDATA[Two FieldTypeInfos are equal if ach of their fields matches]]> + </doc> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[We use a basic hashcode implementation, since this class will likely not + be used as a hashmap key]]> + </doc> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="ti" type="org.apache.hadoop.record.meta.FieldTypeInfo"/> + </method> + <doc> + <![CDATA[Represents a type information for a field, which is made up of its + ID (name) and its type (a TypeID object).]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.meta.FieldTypeInfo --> + <!-- start class org.apache.hadoop.record.meta.MapTypeID --> + <class name="MapTypeID" extends="org.apache.hadoop.record.meta.TypeID" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="MapTypeID" type="org.apache.hadoop.record.meta.TypeID, org.apache.hadoop.record.meta.TypeID" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getKeyTypeID" return="org.apache.hadoop.record.meta.TypeID" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[get the TypeID of the map's key element]]> + </doc> + </method> + <method name="getValueTypeID" return="org.apache.hadoop.record.meta.TypeID" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[get the TypeID of the map's value element]]> + </doc> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + <doc> + <![CDATA[Two map typeIDs are equal if their constituent elements have the + same type]]> + </doc> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[We use a basic hashcode implementation, since this class will likely not + be used as a hashmap key]]> + </doc> + </method> + <doc> + <![CDATA[Represents typeID for a Map]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.meta.MapTypeID --> + <!-- start class org.apache.hadoop.record.meta.RecordTypeInfo --> + <class name="RecordTypeInfo" extends="org.apache.hadoop.record.Record" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="RecordTypeInfo" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Create an empty RecordTypeInfo object.]]> + </doc> + </constructor> + <constructor name="RecordTypeInfo" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Create a RecordTypeInfo object representing a record with the given name + @param name Name of the record]]> + </doc> + </constructor> + <method name="getName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[return the name of the record]]> + </doc> + </method> + <method name="setName" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <doc> + <![CDATA[set the name of the record]]> + </doc> + </method> + <method name="addField" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fieldName" type="java.lang.String"/> + <param name="tid" type="org.apache.hadoop.record.meta.TypeID"/> + <doc> + <![CDATA[Add a field. + @param fieldName Name of the field + @param tid Type ID of the field]]> + </doc> + </method> + <method name="getFieldTypeInfos" return="java.util.Collection<org.apache.hadoop.record.meta.FieldTypeInfo>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return a collection of field type infos]]> + </doc> + </method> + <method name="getNestedStructTypeInfo" return="org.apache.hadoop.record.meta.RecordTypeInfo" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <doc> + <![CDATA[Return the type info of a nested record. We only consider nesting + to one level. + @param name Name of the nested record]]> + </doc> + </method> + <method name="serialize" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="rout" type="org.apache.hadoop.record.RecordOutput"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Serialize the type information for a record]]> + </doc> + </method> + <method name="deserialize" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="rin" type="org.apache.hadoop.record.RecordInput"/> + <param name="tag" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Deserialize the type information for a record]]> + </doc> + </method> + <method name="compareTo" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="peer_" type="java.lang.Object"/> + <exception name="ClassCastException" type="java.lang.ClassCastException"/> + <doc> + <![CDATA[This class doesn't implement Comparable as it's not meant to be used + for anything besides de/serializing. + So we always throw an exception. + Not implemented. Always returns 0 if another RecordTypeInfo is passed in.]]> + </doc> + </method> + <doc> + <![CDATA[A record's Type Information object which can read/write itself. + + Type information for a record comprises metadata about the record, + as well as a collection of type information for each field in the record.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.meta.RecordTypeInfo --> + <!-- start class org.apache.hadoop.record.meta.StructTypeID --> + <class name="StructTypeID" extends="org.apache.hadoop.record.meta.TypeID" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="StructTypeID" type="org.apache.hadoop.record.meta.RecordTypeInfo" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Create a StructTypeID based on the RecordTypeInfo of some record]]> + </doc> + </constructor> + <method name="getFieldTypeInfos" return="java.util.Collection<org.apache.hadoop.record.meta.FieldTypeInfo>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[Represents typeID for a struct]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.meta.StructTypeID --> + <!-- start class org.apache.hadoop.record.meta.TypeID --> + <class name="TypeID" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="getTypeVal" return="byte" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the type value. One of the constants in RIOType.]]> + </doc> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + <doc> + <![CDATA[Two base typeIDs are equal if they refer to the same type]]> + </doc> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[We use a basic hashcode implementation, since this class will likely not + be used as a hashmap key]]> + </doc> + </method> + <field name="BoolTypeID" type="org.apache.hadoop.record.meta.TypeID" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Constant classes for the basic types, so we can share them.]]> + </doc> + </field> + <field name="BufferTypeID" type="org.apache.hadoop.record.meta.TypeID" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="ByteTypeID" type="org.apache.hadoop.record.meta.TypeID" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="DoubleTypeID" type="org.apache.hadoop.record.meta.TypeID" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="FloatTypeID" type="org.apache.hadoop.record.meta.TypeID" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="IntTypeID" type="org.apache.hadoop.record.meta.TypeID" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="LongTypeID" type="org.apache.hadoop.record.meta.TypeID" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="StringTypeID" type="org.apache.hadoop.record.meta.TypeID" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="typeVal" type="byte" + transient="false" volatile="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[Represents typeID for basic types.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.meta.TypeID --> + <!-- start class org.apache.hadoop.record.meta.TypeID.RIOType --> + <class name="TypeID.RIOType" extends="java.lang.Object" + abstract="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <constructor name="TypeID.RIOType" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <field name="BOOL" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="BUFFER" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="BYTE" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="DOUBLE" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="FLOAT" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="INT" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="LONG" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="MAP" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="STRING" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="STRUCT" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="VECTOR" type="byte" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[constants representing the IDL types we support]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.meta.TypeID.RIOType --> + <!-- start class org.apache.hadoop.record.meta.Utils --> + <class name="Utils" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="skip" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="rin" type="org.apache.hadoop.record.RecordInput"/> + <param name="tag" type="java.lang.String"/> + <param name="typeID" type="org.apache.hadoop.record.meta.TypeID"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[read/skip bytes from stream based on a type]]> + </doc> + </method> + <doc> + <![CDATA[Various utility functions for Hadooop record I/O platform.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.meta.Utils --> + <!-- start class org.apache.hadoop.record.meta.VectorTypeID --> + <class name="VectorTypeID" extends="org.apache.hadoop.record.meta.TypeID" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="VectorTypeID" type="org.apache.hadoop.record.meta.TypeID" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getElementTypeID" return="org.apache.hadoop.record.meta.TypeID" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="o" type="java.lang.Object"/> + <doc> + <![CDATA[Two vector typeIDs are equal if their constituent elements have the + same type]]> + </doc> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[We use a basic hashcode implementation, since this class will likely not + be used as a hashmap key]]> + </doc> + </method> + <doc> + <![CDATA[Represents typeID for vector.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.record.meta.VectorTypeID --> +</package> +<package name="org.apache.hadoop.security"> + <!-- start class org.apache.hadoop.security.UnixUserGroupInformation --> + <class name="UnixUserGroupInformation" extends="org.apache.hadoop.security.UserGroupInformation" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="UnixUserGroupInformation" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Default constructor]]> + </doc> + </constructor> + <constructor name="UnixUserGroupInformation" type="java.lang.String, java.lang.String[]" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Constructor with parameters user name and its group names. + The first entry in the groups list is the default group. + + @param userName a user's name + @param groupNames groups list, first of which is the default group + @exception IllegalArgumentException if any argument is null]]> + </doc> + </constructor> + <constructor name="UnixUserGroupInformation" type="java.lang.String[]" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Constructor with parameter user/group names + + @param ugi an array containing user/group names, the first + element of which is the user name, the second of + which is the default group name. + @exception IllegalArgumentException if the array size is less than 2 + or any element is null.]]> + </doc> + </constructor> + <method name="createImmutable" return="org.apache.hadoop.security.UnixUserGroupInformation" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="ugi" type="java.lang.String[]"/> + <doc> + <![CDATA[Create an immutable {@link UnixUserGroupInformation} object.]]> + </doc> + </method> + <method name="getGroupNames" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return an array of group names]]> + </doc> + </method> + <method name="getUserName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return the user's name]]> + </doc> + </method> + <method name="readFields" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="in" type="java.io.DataInput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Deserialize this object + First check if this is a UGI in the string format. + If no, throw an IOException; otherwise + set this object's fields by reading them from the given data input + + @param in input stream + @exception IOException is thrown if encounter any error when reading]]> + </doc> + </method> + <method name="write" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.DataOutput"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Serialize this object + First write a string marking that this is a UGI in the string format, + then write this object's serialized form to the given data output + + @param out output stream + @exception IOException if encounter any error during writing]]> + </doc> + </method> + <method name="saveToConf" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="attr" type="java.lang.String"/> + <param name="ugi" type="org.apache.hadoop.security.UnixUserGroupInformation"/> + <doc> + <![CDATA[Store the given <code>ugi</code> as a comma separated string in + <code>conf</code> as a property <code>attr</code> + + The String starts with the user name followed by the default group names, + and other group names. + + @param conf configuration + @param attr property name + @param ugi a UnixUserGroupInformation]]> + </doc> + </method> + <method name="readFromConf" return="org.apache.hadoop.security.UnixUserGroupInformation" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="attr" type="java.lang.String"/> + <exception name="LoginException" type="javax.security.auth.login.LoginException"/> + <doc> + <![CDATA[Read a UGI from the given <code>conf</code> + + The object is expected to store with the property name <code>attr</code> + as a comma separated string that starts + with the user name followed by group names. + If the property name is not defined, return null. + It's assumed that there is only one UGI per user. If this user already + has a UGI in the ugi map, return the ugi in the map. + Otherwise, construct a UGI from the configuration, store it in the + ugi map and return it. + + @param conf configuration + @param attr property name + @return a UnixUGI + @throws LoginException if the stored string is ill-formatted.]]> + </doc> + </method> + <method name="login" return="org.apache.hadoop.security.UnixUserGroupInformation" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="LoginException" type="javax.security.auth.login.LoginException"/> + <doc> + <![CDATA[Get current user's name and the names of all its groups from Unix. + It's assumed that there is only one UGI per user. If this user already + has a UGI in the ugi map, return the ugi in the map. + Otherwise get the current user's information from Unix, store it + in the map, and return it.]]> + </doc> + </method> + <method name="login" return="org.apache.hadoop.security.UnixUserGroupInformation" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="LoginException" type="javax.security.auth.login.LoginException"/> + <doc> + <![CDATA[Equivalent to login(conf, false).]]> + </doc> + </method> + <method name="login" return="org.apache.hadoop.security.UnixUserGroupInformation" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="save" type="boolean"/> + <exception name="LoginException" type="javax.security.auth.login.LoginException"/> + <doc> + <![CDATA[Get a user's name & its group names from the given configuration; + If it is not defined in the configuration, get the current user's + information from Unix. + If the user has a UGI in the ugi map, return the one in + the UGI map. + + @param conf either a job configuration or client's configuration + @param save saving it to conf? + @return UnixUserGroupInformation a user/group information + @exception LoginException if not able to get the user/group information]]> + </doc> + </method> + <method name="equals" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="other" type="java.lang.Object"/> + <doc> + <![CDATA[Decide if two UGIs are the same + + @param other other object + @return true if they are the same; false otherwise.]]> + </doc> + </method> + <method name="hashCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns a hash code for this UGI. + The hash code for a UGI is the hash code of its user name string. + + @return a hash code value for this UGI.]]> + </doc> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Convert this object to a string + + @return a comma separated string containing the user name and group names]]> + </doc> + </method> + <field name="UGI_PROPERTY_NAME" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[An implementation of UserGroupInformation in the Unix system]]> + </doc> + </class> + <!-- end class org.apache.hadoop.security.UnixUserGroupInformation --> + <!-- start class org.apache.hadoop.security.UserGroupInformation --> + <class name="UserGroupInformation" extends="java.lang.Object" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.io.Writable"/> + <constructor name="UserGroupInformation" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getCurrentUGI" return="org.apache.hadoop.security.UserGroupInformation" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@return the {@link UserGroupInformation} for the current thread]]> + </doc> + </method> + <method name="setCurrentUGI" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="ugi" type="org.apache.hadoop.security.UserGroupInformation"/> + <doc> + <![CDATA[Set the {@link UserGroupInformation} for the current thread]]> + </doc> + </method> + <method name="getUserName" return="java.lang.String" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get username + + @return the user's name]]> + </doc> + </method> + <method name="getGroupNames" return="java.lang.String[]" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the name of the groups that the user belong to + + @return an array of group names]]> + </doc> + </method> + <method name="login" return="org.apache.hadoop.security.UserGroupInformation" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="LoginException" type="javax.security.auth.login.LoginException"/> + <doc> + <![CDATA[Login and return a UserGroupInformation object.]]> + </doc> + </method> + <method name="readFrom" return="org.apache.hadoop.security.UserGroupInformation" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Read a {@link UserGroupInformation} from conf]]> + </doc> + </method> + <field name="LOG" type="org.apache.commons.logging.Log" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[A {@link Writable} abstract class for storing user and groups information.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.security.UserGroupInformation --> +</package> +<package name="org.apache.hadoop.tools"> + <!-- start class org.apache.hadoop.tools.Logalyzer --> + <class name="Logalyzer" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="Logalyzer" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="doArchive" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="logListURI" type="java.lang.String"/> + <param name="archiveDirectory" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[doArchive: Workhorse function to archive log-files. + @param logListURI : The uri which will serve list of log-files to archive. + @param archiveDirectory : The directory to store archived logfiles. + @throws IOException]]> + </doc> + </method> + <method name="doAnalyze" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="inputFilesDirectory" type="java.lang.String"/> + <param name="outputDirectory" type="java.lang.String"/> + <param name="grepPattern" type="java.lang.String"/> + <param name="sortColumns" type="java.lang.String"/> + <param name="columnSeparator" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[doAnalyze: + @param inputFilesDirectory : Directory containing the files to be analyzed. + @param outputDirectory : Directory to store analysis (output). + @param grepPattern : Pattern to *grep* for. + @param sortColumns : Sort specification for output. + @param columnSeparator : Column separator. + @throws IOException]]> + </doc> + </method> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + </method> + <doc> + <![CDATA[Logalyzer: A utility tool for archiving and analyzing hadoop logs. + <p> + This tool supports archiving and anaylzing (sort/grep) of log-files. + It takes as input + a) Input uri which will serve uris of the logs to be archived. + b) Output directory (not mandatory). + b) Directory on dfs to archive the logs. + c) The sort/grep patterns for analyzing the files and separator for boundaries. + Usage: + Logalyzer -archive -archiveDir <directory to archive logs> -analysis <directory> -logs <log-list uri> -grep <pattern> -sort <col1, col2> -separator <separator> + <p>]]> + </doc> + </class> + <!-- end class org.apache.hadoop.tools.Logalyzer --> + <!-- start class org.apache.hadoop.tools.Logalyzer.LogComparator --> + <class name="Logalyzer.LogComparator" extends="org.apache.hadoop.io.Text.Comparator" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.conf.Configurable"/> + <constructor name="Logalyzer.LogComparator" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="setConf" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + </method> + <method name="getConf" return="org.apache.hadoop.conf.Configuration" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="compare" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="b1" type="byte[]"/> + <param name="s1" type="int"/> + <param name="l1" type="int"/> + <param name="b2" type="byte[]"/> + <param name="s2" type="int"/> + <param name="l2" type="int"/> + </method> + <doc> + <![CDATA[A WritableComparator optimized for UTF8 keys of the logs.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.tools.Logalyzer.LogComparator --> + <!-- start class org.apache.hadoop.tools.Logalyzer.LogRegexMapper --> + <class name="Logalyzer.LogRegexMapper" extends="org.apache.hadoop.mapred.MapReduceBase" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.mapred.Mapper<K, org.apache.hadoop.io.Text, org.apache.hadoop.io.Text, org.apache.hadoop.io.LongWritable>"/> + <constructor name="Logalyzer.LogRegexMapper" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="configure" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + </method> + <method name="map" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="key" type="K extends org.apache.hadoop.io.WritableComparable"/> + <param name="value" type="org.apache.hadoop.io.Text"/> + <param name="output" type="org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.Text, org.apache.hadoop.io.LongWritable>"/> + <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <doc> + <![CDATA[A {@link Mapper} that extracts text matching a regular expression.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.tools.Logalyzer.LogRegexMapper --> +</package> +<package name="org.apache.hadoop.util"> + <!-- start class org.apache.hadoop.util.CopyFiles --> + <class name="CopyFiles" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.util.Tool"/> + <constructor name="CopyFiles" type="org.apache.hadoop.conf.Configuration" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="setConf" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + </method> + <method name="getConf" return="org.apache.hadoop.conf.Configuration" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="copy" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="srcPath" type="java.lang.String"/> + <param name="destPath" type="java.lang.String"/> + <param name="logPath" type="org.apache.hadoop.fs.Path"/> + <param name="srcAsList" type="boolean"/> + <param name="ignoreReadFailures" type="boolean"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="run" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + <doc> + <![CDATA[This is the main driver for recursively copying directories + across file systems. It takes at least two cmdline parameters. A source + URL and a destination URL. It then essentially does an "ls -lR" on the + source URL, and writes the output in a round-robin manner to all the map + input files. The mapper actually copies the files allotted to it. The + reduce is empty.]]> + </doc> + </method> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + </method> + <doc> + <![CDATA[A Map-reduce program to recursively copy directories between + different file-systems.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.util.CopyFiles --> + <!-- start class org.apache.hadoop.util.CopyFiles.DuplicationException --> + <class name="CopyFiles.DuplicationException" extends="java.io.IOException" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <field name="ERROR_CODE" type="int" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Error code for this exception]]> + </doc> + </field> + <doc> + <![CDATA[An exception class for duplicated source files.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.util.CopyFiles.DuplicationException --> + <!-- start class org.apache.hadoop.util.Daemon --> + <class name="Daemon" extends="java.lang.Thread" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="Daemon" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct a daemon thread.]]> + </doc> + </constructor> + <constructor name="Daemon" type="java.lang.Runnable" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct a daemon thread.]]> + </doc> + </constructor> + <constructor name="Daemon" type="java.lang.ThreadGroup, java.lang.Runnable" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Construct a daemon thread to be part of a specified thread group.]]> + </doc> + </constructor> + <method name="getRunnable" return="java.lang.Runnable" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[A thread that has called {@link Thread#setDaemon(boolean) } with true.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.util.Daemon --> + <!-- start class org.apache.hadoop.util.DiskChecker --> + <class name="DiskChecker" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="DiskChecker" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="mkdirsWithExistsCheck" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dir" type="java.io.File"/> + <doc> + <![CDATA[The semantics of mkdirsWithExistsCheck method is different from the mkdirs + method provided in the Sun's java.io.File class in the following way: + While creating the non-existent parent directories, this method checks for + the existence of those directories if the mkdir fails at any point (since + that directory might have just been created by some other process). + If both mkdir() and the exists() check fails for any seemingly + non-existent directory, then we signal an error; Sun's mkdir would signal + an error (return false) if a directory it is attempting to create already + exists or the mkdir fails. + @param dir + @return true on success, false on failure]]> + </doc> + </method> + <method name="checkDir" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dir" type="java.io.File"/> + <exception name="DiskChecker.DiskErrorException" type="org.apache.hadoop.util.DiskChecker.DiskErrorException"/> + </method> + <doc> + <![CDATA[Class that provides utility functions for checking disk problem]]> + </doc> + </class> + <!-- end class org.apache.hadoop.util.DiskChecker --> + <!-- start class org.apache.hadoop.util.DiskChecker.DiskErrorException --> + <class name="DiskChecker.DiskErrorException" extends="java.io.IOException" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="DiskChecker.DiskErrorException" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + </class> + <!-- end class org.apache.hadoop.util.DiskChecker.DiskErrorException --> + <!-- start class org.apache.hadoop.util.DiskChecker.DiskOutOfSpaceException --> + <class name="DiskChecker.DiskOutOfSpaceException" extends="java.io.IOException" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="DiskChecker.DiskOutOfSpaceException" type="java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + </class> + <!-- end class org.apache.hadoop.util.DiskChecker.DiskOutOfSpaceException --> + <!-- start class org.apache.hadoop.util.GenericOptionsParser --> + <class name="GenericOptionsParser" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="GenericOptionsParser" type="org.apache.hadoop.conf.Configuration, java.lang.String[]" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Create a <code>GenericOptionsParser<code> to parse only the generic Hadoop + arguments. + + The array of string arguments other than the generic arguments can be + obtained by {@link #getRemainingArgs()}. + + @param conf the <code>Configuration</code> to modify. + @param args command-line arguments.]]> + </doc> + </constructor> + <constructor name="GenericOptionsParser" type="org.apache.hadoop.conf.Configuration, org.apache.commons.cli.Options, java.lang.String[]" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Create a <code>GenericOptionsParser</code> to parse given options as well + as generic Hadoop options. + + The resulting <code>CommandLine</code> object can be obtained by + {@link #getCommandLine()}. + + @param conf the configuration to modify + @param options options built by the caller + @param args User-specified arguments]]> + </doc> + </constructor> + <method name="getRemainingArgs" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns an array of Strings containing only application-specific arguments. + + @return array of <code>String</code>s containing the un-parsed arguments.]]> + </doc> + </method> + <method name="getCommandLine" return="org.apache.commons.cli.CommandLine" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the commons-cli <code>CommandLine</code> object + to process the parsed arguments. + + Note: If the object is created with + {@link #GenericOptionsParser(Configuration, String[])}, then returned + object will only contain parsed generic options. + + @return <code>CommandLine</code> representing list of arguments + parsed against Options descriptor.]]> + </doc> + </method> + <method name="printGenericCommandUsage" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.PrintStream"/> + <doc> + <![CDATA[Print the usage message for generic command-line options supported. + + @param out stream to print the usage message to.]]> + </doc> + </method> + <doc> + <![CDATA[<code>GenericOptionsParser</code> is a utility to parse command line + arguments generic to the Hadoop framework. + + <code>GenericOptionsParser</code> recognizes several standarad command + line arguments, enabling applications to easily specify a namenode, a + jobtracker, additional configuration resources etc. + + <h4 id="GenericOptions">Generic Options</h4> + + <p>The supported generic options are:</p> + <p><blockquote><pre> + -conf <configuration file> specify a configuration file + -D <property=value> use value for given property + -fs <local|namenode:port> specify a namenode + -jt <local|jobtracker:port> specify a job tracker + </pre></blockquote></p> + + <p>The general command line syntax is:</p> + <p><tt><pre> + bin/hadoop command [genericOptions] [commandOptions] + </pre></tt></p> + + <p>Generic command line arguments <strong>might</strong> modify + <code>Configuration </code> objects, given to constructors.</p> + + <p>The functionality is implemented using Commons CLI.</p> + + <p>Examples:</p> + <p><blockquote><pre> + $ bin/hadoop dfs -fs darwin:8020 -ls /data + list /data directory in dfs with namenode darwin:8020 + + $ bin/hadoop dfs -D fs.default.name=darwin:8020 -ls /data + list /data directory in dfs with namenode darwin:8020 + + $ bin/hadoop dfs -conf hadoop-site.xml -ls /data + list /data directory in dfs with conf specified in hadoop-site.xml + + $ bin/hadoop job -D mapred.job.tracker=darwin:50020 -submit job.xml + submit a job to job tracker darwin:50020 + + $ bin/hadoop job -jt darwin:50020 -submit job.xml + submit a job to job tracker darwin:50020 + + $ bin/hadoop job -jt local -submit job.xml + submit a job to local runner + </pre></blockquote></p> + + @see Tool + @see ToolRunner]]> + </doc> + </class> + <!-- end class org.apache.hadoop.util.GenericOptionsParser --> + <!-- start class org.apache.hadoop.util.GenericsUtil --> + <class name="GenericsUtil" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="GenericsUtil" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getClass" return="java.lang.Class<T>" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="t" type="T"/> + <doc> + <![CDATA[Returns the Class object (of type <code>Class<T></code>) of the + argument of type <code>T</code>. + @param <T> The type of the argument + @param t the object to get it class + @return <code>Class<T></code>]]> + </doc> + </method> + <method name="toArray" return="T[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="c" type="java.lang.Class<T>"/> + <param name="list" type="java.util.List<T>"/> + <doc> + <![CDATA[Converts the given <code>List<T></code> to a an array of + <code>T[]</code>. + @param c the Class object of the items in the list + @param list the list to convert]]> + </doc> + </method> + <method name="toArray" return="T[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="list" type="java.util.List<T>"/> + <doc> + <![CDATA[Converts the given <code>List<T></code> to a an array of + <code>T[]</code>. + @param list the list to convert + @throws ArrayIndexOutOfBoundsException if the list is empty. + Use {@link #toArray(Class, List)} if the list may be empty.]]> + </doc> + </method> + <doc> + <![CDATA[Contains utility methods for dealing with Java Generics.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.util.GenericsUtil --> + <!-- start class org.apache.hadoop.util.HostsFileReader --> + <class name="HostsFileReader" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="HostsFileReader" type="java.lang.String, java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </constructor> + <method name="refresh" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getHosts" return="java.util.Set<java.lang.String>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <method name="getExcludedHosts" return="java.util.Set<java.lang.String>" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + </class> + <!-- end class org.apache.hadoop.util.HostsFileReader --> + <!-- start interface org.apache.hadoop.util.IndexedSortable --> + <interface name="IndexedSortable" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="compare" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="i" type="int"/> + <param name="j" type="int"/> + <doc> + <![CDATA[Compare items at the given addresses consistent with the semantics of + {@link java.util.Comparable#compare}.]]> + </doc> + </method> + <method name="swap" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="i" type="int"/> + <param name="j" type="int"/> + <doc> + <![CDATA[Swap items at the given addresses.]]> + </doc> + </method> + <doc> + <![CDATA[Interface for collections capable of being sorted by {@link IndexedSorter} + algorithms.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.util.IndexedSortable --> + <!-- start interface org.apache.hadoop.util.IndexedSorter --> + <interface name="IndexedSorter" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="sort" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="s" type="org.apache.hadoop.util.IndexedSortable"/> + <param name="l" type="int"/> + <param name="r" type="int"/> + <doc> + <![CDATA[Sort the items accessed through the given IndexedSortable over the given + range of logical indices. From the perspective of the sort algorithm, + each index between l (inclusive) and r (exclusive) is an addressable + entry. + @see IndexedSortable#compare + @see IndexedSortable#swap]]> + </doc> + </method> + <doc> + <![CDATA[Interface for sort algorithms accepting {@link IndexedSortable} items. + + A sort algorithm implementing this interface may only + {@link IndexedSortable#compare} and {@link IndexedSortable#swap} items + for a range of indices to effect a sort across that range.]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.util.IndexedSorter --> + <!-- start class org.apache.hadoop.util.MergeSort --> + <class name="MergeSort" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="MergeSort" type="java.util.Comparator<org.apache.hadoop.io.IntWritable>" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="mergeSort" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="src" type="int[]"/> + <param name="dest" type="int[]"/> + <param name="low" type="int"/> + <param name="high" type="int"/> + </method> + <doc> + <![CDATA[An implementation of the core algorithm of MergeSort.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.util.MergeSort --> + <!-- start class org.apache.hadoop.util.NativeCodeLoader --> + <class name="NativeCodeLoader" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="NativeCodeLoader" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="isNativeCodeLoaded" return="boolean" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Check if native-hadoop code is loaded for this platform. + + @return <code>true</code> if native-hadoop is loaded, + else <code>false</code>]]> + </doc> + </method> + <method name="getLoadNativeLibraries" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobConf" type="org.apache.hadoop.mapred.JobConf"/> + <doc> + <![CDATA[Return if native hadoop libraries, if present, can be used for this job. + @param jobConf job configuration + + @return <code>true</code> if native hadoop libraries, if present, can be + used for this job; <code>false</code> otherwise.]]> + </doc> + </method> + <method name="setLoadNativeLibraries" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jobConf" type="org.apache.hadoop.mapred.JobConf"/> + <param name="loadNativeLibraries" type="boolean"/> + <doc> + <![CDATA[Set if native hadoop libraries, if present, can be used for this job. + + @param jobConf job configuration + @param loadNativeLibraries can native hadoop libraries be loaded]]> + </doc> + </method> + <doc> + <![CDATA[A helper to load the native hadoop code i.e. libhadoop.so. + This handles the fallback to either the bundled libhadoop-Linux-i386-32.so + or the default java implementations where appropriate.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.util.NativeCodeLoader --> + <!-- start class org.apache.hadoop.util.PlatformName --> + <class name="PlatformName" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="PlatformName" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getPlatformName" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the complete platform as per the java-vm. + @return returns the complete platform as per the java-vm.]]> + </doc> + </method> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + </method> + <doc> + <![CDATA[A helper class for getting build-info of the java-vm.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.util.PlatformName --> + <!-- start class org.apache.hadoop.util.PrintJarMainClass --> + <class name="PrintJarMainClass" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="PrintJarMainClass" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <doc> + <![CDATA[@param args]]> + </doc> + </method> + <doc> + <![CDATA[A micro-application that prints the main class name out of a jar file.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.util.PrintJarMainClass --> + <!-- start class org.apache.hadoop.util.PriorityQueue --> + <class name="PriorityQueue" extends="java.lang.Object" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="PriorityQueue" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="lessThan" return="boolean" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="a" type="java.lang.Object"/> + <param name="b" type="java.lang.Object"/> + <doc> + <![CDATA[Determines the ordering of objects in this priority queue. Subclasses + must define this one method.]]> + </doc> + </method> + <method name="initialize" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="protected" + deprecated="not deprecated"> + <param name="maxSize" type="int"/> + <doc> + <![CDATA[Subclass constructors must call this.]]> + </doc> + </method> + <method name="put" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <param name="element" type="java.lang.Object"/> + <doc> + <![CDATA[Adds an Object to a PriorityQueue in log(size) time. + If one tries to add more objects than maxSize from initialize + a RuntimeException (ArrayIndexOutOfBound) is thrown.]]> + </doc> + </method> + <method name="insert" return="boolean" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="element" type="java.lang.Object"/> + <doc> + <![CDATA[Adds element to the PriorityQueue in log(size) time if either + the PriorityQueue is not full, or not lessThan(element, top()). + @param element + @return true if element is added, false otherwise.]]> + </doc> + </method> + <method name="top" return="java.lang.Object" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the least element of the PriorityQueue in constant time.]]> + </doc> + </method> + <method name="pop" return="java.lang.Object" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Removes and returns the least element of the PriorityQueue in log(size) + time.]]> + </doc> + </method> + <method name="adjustTop" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Should be called when the Object at top changes values. Still log(n) + worst case, but it's at least twice as fast to <pre> + { pq.top().change(); pq.adjustTop(); } + </pre> instead of <pre> + { o = pq.pop(); o.change(); pq.push(o); } + </pre>]]> + </doc> + </method> + <method name="size" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the number of elements currently stored in the PriorityQueue.]]> + </doc> + </method> + <method name="clear" + abstract="false" native="false" synchronized="false" + static="false" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Removes all entries from the PriorityQueue.]]> + </doc> + </method> + <doc> + <![CDATA[A PriorityQueue maintains a partial ordering of its elements such that the + least element can always be found in constant time. Put()'s and pop()'s + require log(size) time.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.util.PriorityQueue --> + <!-- start class org.apache.hadoop.util.ProgramDriver --> + <class name="ProgramDriver" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="ProgramDriver" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="addClass" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="name" type="java.lang.String"/> + <param name="mainClass" type="java.lang.Class"/> + <param name="description" type="java.lang.String"/> + <exception name="Throwable" type="java.lang.Throwable"/> + <doc> + <![CDATA[This is the method that adds the classed to the repository + @param name The name of the string you want the class instance to be called with + @param mainClass The class that you want to add to the repository + @param description The description of the class + @throws NoSuchMethodException + @throws SecurityException]]> + </doc> + </method> + <method name="driver" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <exception name="Throwable" type="java.lang.Throwable"/> + <doc> + <![CDATA[This is a driver for the example programs. + It looks at the first command line argument and tries to find an + example program with that name. + If it is found, it calls the main method in that class with the rest + of the command line arguments. + @param args The argument from the user. args[0] is the command to run. + @throws NoSuchMethodException + @throws SecurityException + @throws IllegalAccessException + @throws IllegalArgumentException + @throws Throwable Anything thrown by the example program's main]]> + </doc> + </method> + <doc> + <![CDATA[A driver that is used to run programs added to it]]> + </doc> + </class> + <!-- end class org.apache.hadoop.util.ProgramDriver --> + <!-- start class org.apache.hadoop.util.Progress --> + <class name="Progress" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="Progress" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Creates a new root node.]]> + </doc> + </constructor> + <method name="addPhase" return="org.apache.hadoop.util.Progress" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="status" type="java.lang.String"/> + <doc> + <![CDATA[Adds a named node to the tree.]]> + </doc> + </method> + <method name="addPhase" return="org.apache.hadoop.util.Progress" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Adds a node to the tree.]]> + </doc> + </method> + <method name="startNextPhase" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Called during execution to move to the next phase at this level in the + tree.]]> + </doc> + </method> + <method name="phase" return="org.apache.hadoop.util.Progress" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the current sub-node executing.]]> + </doc> + </method> + <method name="complete" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Completes this node, moving the parent node to its next child.]]> + </doc> + </method> + <method name="set" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="progress" type="float"/> + <doc> + <![CDATA[Called during execution on a leaf node to set its progress.]]> + </doc> + </method> + <method name="get" return="float" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Returns the overall progress of the root.]]> + </doc> + </method> + <method name="setStatus" + abstract="false" native="false" synchronized="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="status" type="java.lang.String"/> + </method> + <method name="toString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[Utility to assist with generation of progress reports. Applications build + a hierarchy of {@link Progress} instances, each modelling a phase of + execution. The root is constructed with {@link #Progress()}. Nodes for + sub-phases are created by calling {@link #addPhase()}.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.util.Progress --> + <!-- start interface org.apache.hadoop.util.Progressable --> + <interface name="Progressable" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <method name="progress" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Report progress to the Hadoop framework.]]> + </doc> + </method> + <doc> + <![CDATA[A facility for reporting progress. + + <p>Clients and/or applications can use the provided <code>Progressable</code> + to explicitly report progress to the Hadoop framework. This is especially + important for operations which take an insignificant amount of time since, + in-lieu of the reported progress, the framework has to assume that an error + has occured and time-out the operation.</p>]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.util.Progressable --> + <!-- start class org.apache.hadoop.util.QuickSort --> + <class name="QuickSort" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.util.IndexedSorter"/> + <constructor name="QuickSort" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="sort" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="s" type="org.apache.hadoop.util.IndexedSortable"/> + <param name="p" type="int"/> + <param name="r" type="int"/> + </method> + <method name="sort" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="s" type="org.apache.hadoop.util.IndexedSortable"/> + <param name="p" type="int"/> + <param name="r" type="int"/> + <param name="rep" type="org.apache.hadoop.util.Progressable"/> + <doc> + <![CDATA[Same as {@link #sort}, but indicate that we're making progress after + each partition.]]> + </doc> + </method> + <doc> + <![CDATA[An implementation of the core algorithm of QuickSort. + See "Median-of-Three Partitioning" in Sedgewick book.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.util.QuickSort --> + <!-- start class org.apache.hadoop.util.ReflectionUtils --> + <class name="ReflectionUtils" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="ReflectionUtils" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="setConf" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="theObject" type="java.lang.Object"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[Check and set 'configuration' if necessary. + + @param theObject object for which to set configuration + @param conf Configuration]]> + </doc> + </method> + <method name="newInstance" return="java.lang.Object" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="theClass" type="java.lang.Class<?>"/> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <doc> + <![CDATA[Create an object for the given class and initialize it from conf + + @param theClass class of which an object is created + @param conf Configuration + @return a new object]]> + </doc> + </method> + <method name="setContentionTracing" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="val" type="boolean"/> + </method> + <method name="printThreadInfo" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="stream" type="java.io.PrintWriter"/> + <param name="title" type="java.lang.String"/> + <doc> + <![CDATA[Print all of the thread's information and stack traces. + + @param stream the stream to + @param title a string title for the stack trace]]> + </doc> + </method> + <method name="logThreadInfo" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="log" type="org.apache.commons.logging.Log"/> + <param name="title" type="java.lang.String"/> + <param name="minInterval" type="long"/> + <doc> + <![CDATA[Log the current thread stacks at INFO level. + @param log the logger that logs the stack trace + @param title a descriptive title for the call stacks + @param minInterval the minimum time from the last]]> + </doc> + </method> + <doc> + <![CDATA[General reflection utils]]> + </doc> + </class> + <!-- end class org.apache.hadoop.util.ReflectionUtils --> + <!-- start class org.apache.hadoop.util.RunJar --> + <class name="RunJar" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="RunJar" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="unJar" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="jarFile" type="java.io.File"/> + <param name="toDir" type="java.io.File"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Unpack a jar file into a directory.]]> + </doc> + </method> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <exception name="Throwable" type="java.lang.Throwable"/> + <doc> + <![CDATA[Run a Hadoop job jar. If the main class is not in the jar's manifest, + then it must be provided on the command line.]]> + </doc> + </method> + <doc> + <![CDATA[Run a Hadoop job jar.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.util.RunJar --> + <!-- start class org.apache.hadoop.util.ServletUtil --> + <class name="ServletUtil" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="ServletUtil" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="initHTML" return="java.io.PrintWriter" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="response" type="javax.servlet.ServletResponse"/> + <param name="title" type="java.lang.String"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Initial HTML header]]> + </doc> + </method> + <method name="getParameter" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="request" type="javax.servlet.ServletRequest"/> + <param name="name" type="java.lang.String"/> + <doc> + <![CDATA[Get a parameter from a ServletRequest. + Return null if the parameter contains only white spaces.]]> + </doc> + </method> + <method name="htmlFooter" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[HTML footer to be added in the jsps. + @return the HTML footer.]]> + </doc> + </method> + <field name="HTML_TAIL" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + </class> + <!-- end class org.apache.hadoop.util.ServletUtil --> + <!-- start class org.apache.hadoop.util.Shell --> + <class name="Shell" extends="java.lang.Object" + abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="Shell" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="Shell" type="long" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[@param interval the minimum duration to wait before re-executing the + command.]]> + </doc> + </constructor> + <method name="getGROUPS_COMMAND" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[a Unix command to get the current user's groups list]]> + </doc> + </method> + <method name="getGET_PERMISSION_COMMAND" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return a Unix command to get permission information.]]> + </doc> + </method> + <method name="getUlimitMemoryCommand" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="job" type="org.apache.hadoop.mapred.JobConf"/> + <doc> + <![CDATA[Get the Unix command for setting the maximum virtual memory available + to a given child process. This is only relevant when we are forking a + process from within the {@link org.apache.hadoop.mapred.Mapper} or the + {@link org.apache.hadoop.mapred.Reducer} implementations + e.g. <a href="{@docRoot}/org/apache/hadoop/mapred/pipes/package-summary.html">Hadoop Pipes</a> + or <a href="{@docRoot}/org/apache/hadoop/streaming/package-summary.html">Hadoop Streaming</a>. + + It also checks to ensure that we are running on a *nix platform else + (e.g. in Cygwin/Windows) it returns <code>null</code>. + @param job job configuration + @return a <code>String[]</code> with the ulimit command arguments or + <code>null</code> if we are running on a non *nix platform or + if the limit is unspecified.]]> + </doc> + </method> + <method name="setEnvironment" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="env" type="java.util.Map<java.lang.String, java.lang.String>"/> + <doc> + <![CDATA[set the environment for the command + @param env Mapping of environment variables]]> + </doc> + </method> + <method name="setWorkingDirectory" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="dir" type="java.io.File"/> + <doc> + <![CDATA[set the working directory + @param dir The directory where the command would be executed]]> + </doc> + </method> + <method name="run" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[check to see if a command needs to be executed and execute if needed]]> + </doc> + </method> + <method name="getExecString" return="java.lang.String[]" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <doc> + <![CDATA[return an array containing the command name & its parameters]]> + </doc> + </method> + <method name="parseExecResult" + abstract="true" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="lines" type="java.io.BufferedReader"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Parse the execution result]]> + </doc> + </method> + <method name="getProcess" return="java.lang.Process" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[get the current sub-process executing the given command + @return process executing the command]]> + </doc> + </method> + <method name="getExitCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[get the exit code + @return the exit code of the process]]> + </doc> + </method> + <method name="execCommand" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="cmd" type="java.lang.String[]"/> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Static method to execute a shell command. + Covers most of the simple cases without requiring the user to implement + the <code>Shell</code> interface. + @param cmd shell command to execute. + @return the output of the executed command.]]> + </doc> + </method> + <field name="LOG" type="org.apache.commons.logging.Log" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="USER_NAME_COMMAND" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[a Unix command to get the current user's name]]> + </doc> + </field> + <field name="SET_PERMISSION_COMMAND" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[a Unix command to set permission]]> + </doc> + </field> + <field name="SET_OWNER_COMMAND" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[a Unix command to set owner]]> + </doc> + </field> + <field name="SET_GROUP_COMMAND" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="WINDOWS" type="boolean" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Set to true on Windows platforms]]> + </doc> + </field> + <doc> + <![CDATA[A base class for running a Unix command. + + <code>Shell</code> can be used to run unix commands like <code>du</code> or + <code>df</code>. It also offers facilities to gate commands by + time-intervals.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.util.Shell --> + <!-- start class org.apache.hadoop.util.Shell.ExitCodeException --> + <class name="Shell.ExitCodeException" extends="java.io.IOException" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="Shell.ExitCodeException" type="int, java.lang.String" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getExitCode" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </method> + <doc> + <![CDATA[This is an IOException with exit code added.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.util.Shell.ExitCodeException --> + <!-- start class org.apache.hadoop.util.Shell.ShellCommandExecutor --> + <class name="Shell.ShellCommandExecutor" extends="org.apache.hadoop.util.Shell" + abstract="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="Shell.ShellCommandExecutor" type="java.lang.String[]" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="Shell.ShellCommandExecutor" type="java.lang.String[], java.io.File" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <constructor name="Shell.ShellCommandExecutor" type="java.lang.String[], java.io.File, java.util.Map<java.lang.String, java.lang.String>" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="execute" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <exception name="IOException" type="java.io.IOException"/> + <doc> + <![CDATA[Execute the shell command.]]> + </doc> + </method> + <method name="getExecString" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + </method> + <method name="parseExecResult" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="protected" + deprecated="not deprecated"> + <param name="lines" type="java.io.BufferedReader"/> + <exception name="IOException" type="java.io.IOException"/> + </method> + <method name="getOutput" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the output of the shell command.]]> + </doc> + </method> + <doc> + <![CDATA[A simple shell command executor. + + <code>ShellCommandExecutor</code>should be used in cases where the output + of the command needs no explicit parsing and where the command, working + directory and the environment remains unchanged. The output of the command + is stored as-is and is expected to be small.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.util.Shell.ShellCommandExecutor --> + <!-- start class org.apache.hadoop.util.StringUtils --> + <class name="StringUtils" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="StringUtils" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="stringifyException" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="e" type="java.lang.Throwable"/> + <doc> + <![CDATA[Make a string representation of the exception. + @param e The exception to stringify + @return A string with exception name and call stack.]]> + </doc> + </method> + <method name="simpleHostname" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="fullHostname" type="java.lang.String"/> + <doc> + <![CDATA[Given a full hostname, return the word upto the first dot. + @param fullHostname the full hostname + @return the hostname to the first dot]]> + </doc> + </method> + <method name="humanReadableInt" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="number" type="long"/> + <doc> + <![CDATA[Given an integer, return a string that is in an approximate, but human + readable format. + It uses the bases 'k', 'm', and 'g' for 1024, 1024**2, and 1024**3. + @param number the number to format + @return a human readable form of the integer]]> + </doc> + </method> + <method name="formatPercent" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="done" type="double"/> + <param name="digits" type="int"/> + <doc> + <![CDATA[Format a percentage for presentation to the user. + @param done the percentage to format (0.0 to 1.0) + @param digits the number of digits past the decimal point + @return a string representation of the percentage]]> + </doc> + </method> + <method name="arrayToString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="strs" type="java.lang.String[]"/> + <doc> + <![CDATA[Given an array of strings, return a comma-separated list of its elements. + @param strs Array of strings + @return Empty string if strs.length is 0, comma separated list of strings + otherwise]]> + </doc> + </method> + <method name="byteToHexString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="bytes" type="byte[]"/> + <doc> + <![CDATA[Given an array of bytes it will convert the bytes to a hex string + representation of the bytes + @param bytes + @return hex string representation of the byte array]]> + </doc> + </method> + <method name="hexStringToByte" return="byte[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="hex" type="java.lang.String"/> + <doc> + <![CDATA[Given a hexstring this will return the byte array corresponding to the + string + @param hex the hex String array + @return a byte array that is a hex string representation of the given + string. The size of the byte array is therefore hex.length/2]]> + </doc> + </method> + <method name="uriToString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="uris" type="java.net.URI[]"/> + <doc> + <![CDATA[@param uris]]> + </doc> + </method> + <method name="stringToURI" return="java.net.URI[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="str" type="java.lang.String[]"/> + <doc> + <![CDATA[@param str]]> + </doc> + </method> + <method name="stringToPath" return="org.apache.hadoop.fs.Path[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="str" type="java.lang.String[]"/> + <doc> + <![CDATA[@param str]]> + </doc> + </method> + <method name="formatTimeDiff" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="finishTime" type="long"/> + <param name="startTime" type="long"/> + <doc> + <![CDATA[Given a finish and start time in long milliseconds, returns a + String in the format Xhrs, Ymins, Z sec, for the time difference between two times. + If finish time comes before start time then negative valeus of X, Y and Z wil return. + + @param finishTime finish time + @param startTime start time]]> + </doc> + </method> + <method name="getFormattedTimeWithDiff" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="dateFormat" type="java.text.DateFormat"/> + <param name="finishTime" type="long"/> + <param name="startTime" type="long"/> + <doc> + <![CDATA[Formats time in ms and appends difference (finishTime - startTime) + as returned by formatTimeDiff(). + If finish time is 0, empty string is returned, if start time is 0 + then difference is not appended to return value. + @param dateFormat date format to use + @param finishTime fnish time + @param startTime start time + @return formatted value.]]> + </doc> + </method> + <method name="getStrings" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="str" type="java.lang.String"/> + <doc> + <![CDATA[returns an arraylist of strings + @param str the comma seperated string values + @return the arraylist of the comma seperated string values]]> + </doc> + </method> + <method name="split" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="str" type="java.lang.String"/> + <doc> + <![CDATA[Split a string using the default separator + @param str a string that may have escaped separator + @return an array of strings]]> + </doc> + </method> + <method name="split" return="java.lang.String[]" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="str" type="java.lang.String"/> + <param name="escapeChar" type="char"/> + <param name="separator" type="char"/> + <doc> + <![CDATA[Split a string using the given separator + @param str a string that may have escaped separator + @param escapeChar a char that be used to escape the separator + @param separator a separator char + @return an array of strings]]> + </doc> + </method> + <method name="escapeString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="str" type="java.lang.String"/> + <doc> + <![CDATA[Escape commas in the string using the default escape char + @param str a string + @return an escaped string]]> + </doc> + </method> + <method name="escapeString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="str" type="java.lang.String"/> + <param name="escapeChar" type="char"/> + <param name="charToEscape" type="char"/> + <doc> + <![CDATA[Escape <code>charToEscape</code> in the string + with the escape char <code>escapeChar</code> + + @param str string + @param escapeChar escape char + @param charToEscape the char to be escaped + @return an escaped string]]> + </doc> + </method> + <method name="unEscapeString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="str" type="java.lang.String"/> + <doc> + <![CDATA[Unescape commas in the string using the default escape char + @param str a string + @return an unescaped string]]> + </doc> + </method> + <method name="unEscapeString" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="str" type="java.lang.String"/> + <param name="escapeChar" type="char"/> + <param name="charToEscape" type="char"/> + <doc> + <![CDATA[Unescape <code>charToEscape</code> in the string + with the escape char <code>escapeChar</code> + + @param str string + @param escapeChar escape char + @param charToEscape the escaped char + @return an unescaped string]]> + </doc> + </method> + <method name="getHostname" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Return hostname without throwing exception. + @return hostname]]> + </doc> + </method> + <method name="startupShutdownMessage" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="clazz" type="java.lang.Class"/> + <param name="args" type="java.lang.String[]"/> + <param name="LOG" type="org.apache.commons.logging.Log"/> + <doc> + <![CDATA[Print a log message for starting up and shutting down + @param clazz the class of the server + @param args arguments + @param LOG the target log object]]> + </doc> + </method> + <field name="COMMA" type="char" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="COMMA_STR" type="java.lang.String" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <field name="ESCAPE_CHAR" type="char" + transient="false" volatile="false" + static="true" final="true" visibility="public" + deprecated="not deprecated"> + </field> + <doc> + <![CDATA[General string utils]]> + </doc> + </class> + <!-- end class org.apache.hadoop.util.StringUtils --> + <!-- start interface org.apache.hadoop.util.Tool --> + <interface name="Tool" abstract="true" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <implements name="org.apache.hadoop.conf.Configurable"/> + <method name="run" return="int" + abstract="false" native="false" synchronized="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + <doc> + <![CDATA[Execute the command with the given arguments. + + @param args command specific arguments. + @return exit code. + @throws Exception]]> + </doc> + </method> + <doc> + <![CDATA[A tool interface that supports handling of generic command-line options. + + <p><code>Tool</code>, is the standard for any Map-Reduce tool/application. + The tool/application should delegate the handling of + <a href="{@docRoot}/org/apache/hadoop/util/GenericOptionsParser.html#GenericOptions"> + standard command-line options</a> to {@link ToolRunner#run(Tool, String[])} + and only handle its custom arguments.</p> + + <p>Here is how a typical <code>Tool</code> is implemented:</p> + <p><blockquote><pre> + public class MyApp extends Configured implements Tool { + + public int run(String[] args) throws Exception { + // <code>Configuration</code> processed by <code>ToolRunner</code> + Configuration conf = getConf(); + + // Create a JobConf using the processed <code>conf</code> + JobConf job = new JobConf(conf, MyApp.class); + + // Process custom command-line options + Path in = new Path(args[1]); + Path out = new Path(args[2]); + + // Specify various job-specific parameters + job.setJobName("my-app"); + job.setInputPath(in); + job.setOutputPath(out); + job.setMapperClass(MyApp.MyMapper.class); + job.setReducerClass(MyApp.MyReducer.class); + + // Submit the job, then poll for progress until the job is complete + JobClient.runJob(job); + } + + public static void main(String[] args) throws Exception { + // Let <code>ToolRunner</code> handle generic command-line options + int res = ToolRunner.run(new Configuration(), new Sort(), args); + + System.exit(res); + } + } + </pre></blockquote></p> + + @see GenericOptionsParser + @see ToolRunner]]> + </doc> + </interface> + <!-- end interface org.apache.hadoop.util.Tool --> + <!-- start class org.apache.hadoop.util.ToolRunner --> + <class name="ToolRunner" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="ToolRunner" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="run" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="conf" type="org.apache.hadoop.conf.Configuration"/> + <param name="tool" type="org.apache.hadoop.util.Tool"/> + <param name="args" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + <doc> + <![CDATA[Runs the given <code>Tool</code> by {@link Tool#run(String[])}, after + parsing with the given generic arguments. Uses the given + <code>Configuration</code>, or builds one if null. + + Sets the <code>Tool</code>'s configuration with the possibly modified + version of the <code>conf</code>. + + @param conf <code>Configuration</code> for the <code>Tool</code>. + @param tool <code>Tool</code> to run. + @param args command-line arguments to the tool. + @return exit code of the {@link Tool#run(String[])} method.]]> + </doc> + </method> + <method name="run" return="int" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="tool" type="org.apache.hadoop.util.Tool"/> + <param name="args" type="java.lang.String[]"/> + <exception name="Exception" type="java.lang.Exception"/> + <doc> + <![CDATA[Runs the <code>Tool</code> with its <code>Configuration</code>. + + Equivalent to <code>run(tool.getConf(), tool, args)</code>. + + @param tool <code>Tool</code> to run. + @param args command-line arguments to the tool. + @return exit code of the {@link Tool#run(String[])} method.]]> + </doc> + </method> + <method name="printGenericCommandUsage" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="out" type="java.io.PrintStream"/> + <doc> + <![CDATA[Prints generic command-line argurments and usage information. + + @param out stream to write usage information to.]]> + </doc> + </method> + <doc> + <![CDATA[A utility to help run {@link Tool}s. + + <p><code>ToolRunner</code> can be used to run classes implementing + <code>Tool</code> interface. It works in conjunction with + {@link GenericOptionsParser} to parse the + <a href="{@docRoot}/org/apache/hadoop/util/GenericOptionsParser.html#GenericOptions"> + generic hadoop command line arguments</a> and modifies the + <code>Configuration</code> of the <code>Tool</code>. The + application-specific options are passed along without being modified. + </p> + + @see Tool + @see GenericOptionsParser]]> + </doc> + </class> + <!-- end class org.apache.hadoop.util.ToolRunner --> + <!-- start class org.apache.hadoop.util.VersionInfo --> + <class name="VersionInfo" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="VersionInfo" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="getVersion" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the Hadoop version. + @return the Hadoop version string, eg. "0.6.3-dev"]]> + </doc> + </method> + <method name="getRevision" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the subversion revision number for the root directory + @return the revision number, eg. "451451"]]> + </doc> + </method> + <method name="getDate" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The date that Hadoop was compiled. + @return the compilation date in unix date format]]> + </doc> + </method> + <method name="getUser" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[The user that compiled Hadoop. + @return the username of the user]]> + </doc> + </method> + <method name="getUrl" return="java.lang.String" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <doc> + <![CDATA[Get the subversion URL for the root Hadoop directory.]]> + </doc> + </method> + <method name="main" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="args" type="java.lang.String[]"/> + </method> + <doc> + <![CDATA[This class finds the package info for Hadoop and the HadoopVersionAnnotation + information.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.util.VersionInfo --> + <!-- start class org.apache.hadoop.util.XMLUtils --> + <class name="XMLUtils" extends="java.lang.Object" + abstract="false" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + <constructor name="XMLUtils" + static="false" final="false" visibility="public" + deprecated="not deprecated"> + </constructor> + <method name="transform" + abstract="false" native="false" synchronized="false" + static="true" final="false" visibility="public" + deprecated="not deprecated"> + <param name="styleSheet" type="java.io.InputStream"/> + <param name="xml" type="java.io.InputStream"/> + <param name="out" type="java.io.Writer"/> + <exception name="TransformerConfigurationException" type="javax.xml.transform.TransformerConfigurationException"/> + <exception name="TransformerException" type="javax.xml.transform.TransformerException"/> + <doc> + <![CDATA[Transform input xml given a stylesheet. + + @param styleSheet the style-sheet + @param xml input xml data + @param out output + @throws TransformerConfigurationException + @throws TransformerException]]> + </doc> + </method> + <doc> + <![CDATA[General xml utilities.]]> + </doc> + </class> + <!-- end class org.apache.hadoop.util.XMLUtils --> + <doc> + <![CDATA[Common utilities.]]> + </doc> +</package> + +</api> |