summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorElliott Hughes <enh@google.com>2018-01-10 21:09:26 +0000
committerGerrit Code Review <noreply-gerritcodereview@google.com>2018-01-10 21:09:26 +0000
commit9204094d45b6274f1673472427bdfb6c18538a09 (patch)
treefb58289c35cdba836713f2edeb4898305ae680ab
parentad171f1861bcb2192d4f2dbc2ccff9a8ae32fb59 (diff)
parent7247294fbc43cb0b4fb2ea03d952b81077db7c27 (diff)
Merge "Upgrade to expat 2.2.5."
-rw-r--r--AUTHORS10
-rw-r--r--Android.bp3
-rw-r--r--CMake.README42
-rw-r--r--CMakeLists.txt184
-rw-r--r--COPYING21
-rw-r--r--Changes295
-rw-r--r--ConfigureChecks.cmake68
-rw-r--r--Makefile.am153
l---------[-rw-r--r--]NOTICE22
-rw-r--r--README.android7
-rw-r--r--README.md126
-rw-r--r--README.version8
-rwxr-xr-xbuildconf.sh2
-rwxr-xr-xclean_coverage.sh3
-rw-r--r--configure.ac256
-rw-r--r--conftools/.gitignore10
-rwxr-xr-xconftools/PrintPath116
-rw-r--r--conftools/ac_c_bigendian_cross.m481
-rw-r--r--conftools/expat.m443
-rwxr-xr-xconftools/get-version.sh35
-rwxr-xr-xcoverage.sh237
-rw-r--r--doc/.gitignore2
-rw-r--r--doc/Makefile.am55
-rw-r--r--doc/reference.html16
-rw-r--r--doc/xmlwf.xml18
-rw-r--r--examples/.gitignore8
-rw-r--r--examples/Makefile.am39
-rw-r--r--examples/elements.c58
-rw-r--r--examples/elements.vcxproj140
-rw-r--r--examples/elements.vcxproj.filters22
-rw-r--r--examples/outline.c85
-rw-r--r--examples/outline.vcxproj151
-rw-r--r--examples/outline.vcxproj.filters22
-rw-r--r--expat.pc.in11
-rw-r--r--expat.sln73
-rw-r--r--expat.spec131
-rw-r--r--expat_config.h46
-rw-r--r--expat_config.h.cmake106
-rwxr-xr-xgennmtab/.gitignore3
-rw-r--r--gennmtab/gennmtab.c457
-rwxr-xr-ximport_expat.sh53
-rw-r--r--lib/.gitignore18
-rw-r--r--lib/Makefile.am77
-rw-r--r--lib/ascii.h32
-rw-r--r--lib/asciitab.h32
-rw-r--r--lib/expat.h55
-rw-r--r--lib/expat.vcxproj179
-rw-r--r--lib/expat.vcxproj.filters83
-rw-r--r--lib/expat_external.h89
-rw-r--r--lib/expat_static.vcxproj149
-rw-r--r--lib/expat_static.vcxproj.filters74
-rw-r--r--lib/expatw.vcxproj179
-rw-r--r--lib/expatw.vcxproj.filters83
-rw-r--r--lib/expatw_static.vcxproj149
-rw-r--r--lib/expatw_static.vcxproj.filters74
-rw-r--r--lib/iasciitab.h32
-rw-r--r--lib/internal.h31
-rw-r--r--lib/latin1tab.h32
-rw-r--r--lib/libexpat.def78
-rw-r--r--lib/libexpatw.def78
-rw-r--r--lib/loadlibrary.c143
-rw-r--r--lib/nametab.h32
-rw-r--r--lib/siphash.h374
-rw-r--r--lib/utf8tab.h33
-rw-r--r--lib/winconfig.h63
-rw-r--r--lib/xmlparse.c3558
-rw-r--r--lib/xmlrole.c72
-rw-r--r--lib/xmlrole.h32
-rw-r--r--lib/xmltok.c123
-rw-r--r--lib/xmltok.h37
-rw-r--r--lib/xmltok_impl.c127
-rw-r--r--lib/xmltok_impl.h31
-rw-r--r--lib/xmltok_ns.c33
-rw-r--r--memory-sanitizer-blacklist.txt6
-rwxr-xr-xqa.sh130
-rw-r--r--run.sh.in12
-rwxr-xr-xtest-driver-wrapper.sh43
-rw-r--r--tests/.gitignore9
-rw-r--r--tests/Makefile.am66
-rw-r--r--tests/benchmark/.gitignore1
-rw-r--r--tests/benchmark/Makefile.am40
-rw-r--r--tests/benchmark/benchmark.c47
-rw-r--r--tests/benchmark/benchmark.sln25
-rw-r--r--tests/benchmark/benchmark.vcxproj143
-rw-r--r--tests/chardata.c84
-rw-r--r--tests/chardata.h39
-rw-r--r--tests/memcheck.c198
-rw-r--r--tests/memcheck.h57
-rw-r--r--tests/minicheck.c83
-rw-r--r--tests/minicheck.h48
-rw-r--r--tests/runtests.c11092
-rw-r--r--tests/runtests.sln24
-rw-r--r--tests/runtests.vcxproj142
-rw-r--r--tests/runtests.vcxproj.filters48
-rw-r--r--tests/runtestspp.cpp40
-rw-r--r--tests/structdata.c162
-rw-r--r--tests/structdata.h76
-rwxr-xr-xtests/udiffer.py62
-rw-r--r--tests/xmltest.log.expected10
-rwxr-xr-xtests/xmltest.sh11
-rw-r--r--win32/.gitignore10
-rw-r--r--win32/MANIFEST.txt25
-rw-r--r--win32/README.txt75
-rw-r--r--win32/expat.iss75
-rwxr-xr-xxmlwf/.gitignore6
-rw-r--r--xmlwf/Makefile.am61
-rw-r--r--xmlwf/codepage.c97
-rw-r--r--xmlwf/codepage.h34
-rw-r--r--xmlwf/ct.c179
-rw-r--r--xmlwf/filemap.h57
-rw-r--r--xmlwf/readfilemap.c138
-rw-r--r--xmlwf/unixfilemap.c104
-rw-r--r--xmlwf/win32filemap.c125
-rw-r--r--xmlwf/xmlfile.c290
-rw-r--r--xmlwf/xmlfile.h48
-rw-r--r--xmlwf/xmlmime.c195
-rw-r--r--xmlwf/xmlmime.h51
-rw-r--r--xmlwf/xmltchar.h74
-rw-r--r--xmlwf/xmlurl.h45
-rw-r--r--xmlwf/xmlwf.c1138
-rw-r--r--xmlwf/xmlwf.vcxproj164
-rw-r--r--xmlwf/xmlwf.vcxproj.filters48
-rw-r--r--xmlwf/xmlwin32url.cxx427
123 files changed, 23475 insertions, 2089 deletions
diff --git a/AUTHORS b/AUTHORS
new file mode 100644
index 0000000..99475bb
--- /dev/null
+++ b/AUTHORS
@@ -0,0 +1,10 @@
+Expat is brought to you by:
+
+Clark Cooper
+Fred L. Drake, Jr.
+Greg Stein
+James Clark
+Karl Waclawek
+Rhodri James
+Sebastian Pipping
+Steven Solie
diff --git a/Android.bp b/Android.bp
index 320025c..b3bef06 100644
--- a/Android.bp
+++ b/Android.bp
@@ -12,6 +12,7 @@ cc_library {
sdk_version: "9",
srcs: [
+ "lib/loadlibrary.c",
"lib/xmlparse.c",
"lib/xmlrole.c",
"lib/xmltok.c",
@@ -21,10 +22,12 @@ cc_library {
"-Werror",
"-Wmissing-prototypes",
"-Wstrict-prototypes",
+ "-Wno-unused-function",
"-Wno-unused-parameter",
"-Wno-missing-field-initializers",
"-fexceptions",
"-DHAVE_EXPAT_CONFIG_H",
+ "-UWIN32_LEAN_AND_MEAN",
],
target: {
diff --git a/CMake.README b/CMake.README
new file mode 100644
index 0000000..6ec025b
--- /dev/null
+++ b/CMake.README
@@ -0,0 +1,42 @@
+== How to build expat with cmake (experimental) ==
+
+The cmake based buildsystem for expat works on Windows (cygwin, mingw, Visual
+Studio) and should work on all other platform cmake supports.
+
+Assuming ~/expat-2.2.5 is the source directory of expat, add a subdirectory
+build and change into that directory:
+~/expat-2.2.5$ mkdir build && cd build
+~/expat-2.2.5/build$
+
+From that directory, call cmake first, then call make, make test and
+make install in the usual way:
+~/expat-2.2.5/build$ cmake ..
+-- The C compiler identification is GNU
+-- The CXX compiler identification is GNU
+....
+-- Configuring done
+-- Generating done
+-- Build files have been written to: /home/patrick/expat-2.2.5/build
+
+If you want to specify the install location for your files, append
+-DCMAKE_INSTALL_PREFIX=/your/install/path to the cmake call.
+
+~/expat-2.2.5/build$ make && make test && make install
+Scanning dependencies of target expat
+[ 5%] Building C object CMakeFiles/expat.dir/lib/xmlparse.c.o
+[ 11%] Building C object CMakeFiles/expat.dir/lib/xmlrole.c.o
+....
+-- Installing: /usr/local/lib/pkgconfig/expat.pc
+-- Installing: /usr/local/bin/xmlwf
+-- Installing: /usr/local/share/man/man1/xmlwf.1
+
+For Windows builds, you must make sure to call cmake from an environment where
+your compiler is reachable, that means either you call it from the
+Visual Studio Command Prompt or when using mingw, you must open a cmd.exe and
+make sure that gcc can be called. On Windows, you also might want to specify a
+special Generator for CMake:
+for Visual Studio builds do:
+cmake .. -G "Visual Studio 10" && vcexpress expat.sln
+for mingw builds do:
+cmake .. -G "MinGW Makefiles" -DCMAKE_INSTALL_PREFIX=D:\expat-install
+ && gmake && gmake install
diff --git a/CMakeLists.txt b/CMakeLists.txt
new file mode 100644
index 0000000..504d087
--- /dev/null
+++ b/CMakeLists.txt
@@ -0,0 +1,184 @@
+# This file is copyrighted under the BSD-license for buildsystem files of KDE
+# copyright 2010, Patrick Spendrin <ps_ml@gmx.de>
+
+project(expat)
+
+cmake_minimum_required(VERSION 2.6)
+set(PACKAGE_BUGREPORT "expat-bugs@libexpat.org")
+set(PACKAGE_NAME "expat")
+set(PACKAGE_VERSION "2.2.5")
+set(PACKAGE_STRING "${PACKAGE_NAME} ${PACKAGE_VERSION}")
+set(PACKAGE_TARNAME "${PACKAGE_NAME}")
+
+if(WINCE)
+ set(BUILD_tools_default OFF)
+else()
+ set(BUILD_tools_default ON)
+endif()
+if(MSVC OR NOT BUILD_tools_default)
+ set(BUILD_doc_default OFF)
+else()
+ find_program(DOCBOOK_TO_MAN NAMES docbook2x-man docbook2man docbook-to-man)
+ if(DOCBOOK_TO_MAN)
+ set(BUILD_doc_default ON)
+ else()
+ set(BUILD_doc_default OFF)
+ endif()
+endif()
+
+option(BUILD_tools "build the xmlwf tool for expat library" ${BUILD_tools_default})
+option(BUILD_examples "build the examples for expat library" ON)
+option(BUILD_tests "build the tests for expat library" ON)
+option(BUILD_shared "build a shared expat library" ON)
+option(BUILD_doc "build man page for xmlwf" ${BUILD_doc_default})
+option(USE_libbsd "utilize libbsd (for arc4random_buf)" OFF)
+option(INSTALL "install expat files in cmake install target" ON)
+
+if(USE_libbsd)
+ find_library(LIB_BSD NAMES bsd)
+ if(NOT LIB_BSD)
+ message(FATAL_ERROR "USE_libbsd option is enabled, but libbsd was not found")
+ else()
+ set(HAVE_LIBBSD TRUE)
+ endif()
+endif()
+
+# configuration options
+set(XML_CONTEXT_BYTES 1024 CACHE STRING "Define to specify how much context to retain around the current parse point")
+option(XML_DTD "Define to make parameter entity parsing functionality available" ON)
+option(XML_NS "Define to make XML Namespaces functionality available" ON)
+if(NOT WIN32)
+ option(XML_DEV_URANDOM "Define to include code reading entropy from `/dev/urandom'." ON)
+ if(XML_DEV_URANDOM)
+ add_definitions(-DXML_DEV_URANDOM)
+ endif()
+endif()
+
+if(XML_DTD)
+ set(XML_DTD 1)
+else(XML_DTD)
+ set(XML_DTD 0)
+endif(XML_DTD)
+if(XML_NS)
+ set(XML_NS 1)
+else(XML_NS)
+ set(XML_NS 0)
+endif(XML_NS)
+
+if(BUILD_tests)
+ enable_testing()
+endif(BUILD_tests)
+
+include(${CMAKE_CURRENT_LIST_DIR}/ConfigureChecks.cmake)
+
+set(EXTRA_COMPILE_FLAGS)
+if(FLAG_NO_STRICT_ALIASING)
+ set(EXTRA_COMPILE_FLAGS "${EXTRA_COMPILE_FLAGS} -fno-strict-aliasing")
+endif()
+set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${EXTRA_COMPILE_FLAGS}")
+set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${EXTRA_COMPILE_FLAGS}")
+
+include_directories(${CMAKE_CURRENT_BINARY_DIR} ${CMAKE_CURRENT_SOURCE_DIR}/lib)
+if(MSVC)
+ add_definitions(-D_CRT_SECURE_NO_WARNINGS -wd4996)
+endif(MSVC)
+if(WIN32)
+ set(CMAKE_DEBUG_POSTFIX "d" CACHE STRING "Add a suffix, usually d on Windows")
+endif(WIN32)
+
+set(expat_SRCS
+ lib/loadlibrary.c
+ lib/xmlparse.c
+ lib/xmlrole.c
+ lib/xmltok.c
+ lib/xmltok_impl.c
+ lib/xmltok_ns.c
+)
+
+if(BUILD_shared)
+ set(_SHARED SHARED)
+ if(WIN32)
+ set(expat_SRCS ${expat_SRCS} lib/libexpat.def)
+ endif(WIN32)
+else(BUILD_shared)
+ set(_SHARED STATIC)
+ if(WIN32)
+ add_definitions(-DXML_STATIC)
+ endif(WIN32)
+endif(BUILD_shared)
+
+add_library(expat ${_SHARED} ${expat_SRCS})
+if(USE_libbsd)
+ target_link_libraries(expat ${LIB_BSD})
+endif()
+
+set(LIBCURRENT 7) # sync
+set(LIBREVISION 7) # with
+set(LIBAGE 6) # configure.ac!
+math(EXPR LIBCURRENT_MINUS_AGE "${LIBCURRENT} - ${LIBAGE}")
+
+if(NOT WIN32)
+ set_property(TARGET expat PROPERTY VERSION ${LIBCURRENT_MINUS_AGE}.${LIBAGE}.${LIBREVISION})
+ set_property(TARGET expat PROPERTY SOVERSION ${LIBCURRENT_MINUS_AGE})
+ set_property(TARGET expat PROPERTY NO_SONAME ${NO_SONAME})
+endif(NOT WIN32)
+
+macro(expat_install)
+ if(INSTALL)
+ install(${ARGN})
+ endif()
+endmacro()
+
+expat_install(TARGETS expat RUNTIME DESTINATION bin
+ LIBRARY DESTINATION lib
+ ARCHIVE DESTINATION lib)
+
+set(prefix ${CMAKE_INSTALL_PREFIX})
+set(exec_prefix "\${prefix}/bin")
+set(libdir "\${prefix}/lib")
+set(includedir "\${prefix}/include")
+configure_file(expat.pc.in ${CMAKE_CURRENT_BINARY_DIR}/expat.pc)
+
+expat_install(FILES lib/expat.h lib/expat_external.h DESTINATION include)
+expat_install(FILES ${CMAKE_CURRENT_BINARY_DIR}/expat.pc DESTINATION lib/pkgconfig)
+
+if(BUILD_tools)
+ set(xmlwf_SRCS
+ xmlwf/xmlwf.c
+ xmlwf/xmlfile.c
+ xmlwf/codepage.c
+ xmlwf/readfilemap.c
+ )
+
+ add_executable(xmlwf ${xmlwf_SRCS})
+ set_property(TARGET xmlwf PROPERTY RUNTIME_OUTPUT_DIRECTORY xmlwf)
+ target_link_libraries(xmlwf expat)
+ expat_install(TARGETS xmlwf DESTINATION bin)
+ if(BUILD_doc)
+ add_custom_command(TARGET expat PRE_BUILD COMMAND "${DOCBOOK_TO_MAN}" "${PROJECT_SOURCE_DIR}/doc/xmlwf.xml" && mv "XMLWF.1" "${PROJECT_SOURCE_DIR}/doc/xmlwf.1")
+ expat_install(FILES "${PROJECT_SOURCE_DIR}/doc/xmlwf.1" DESTINATION share/man/man1)
+ endif()
+endif()
+
+if(BUILD_examples)
+ add_executable(elements examples/elements.c)
+ set_property(TARGET elements PROPERTY RUNTIME_OUTPUT_DIRECTORY examples)
+ target_link_libraries(elements expat)
+
+ add_executable(outline examples/outline.c)
+ set_property(TARGET outline PROPERTY RUNTIME_OUTPUT_DIRECTORY examples)
+ target_link_libraries(outline expat)
+endif(BUILD_examples)
+
+if(BUILD_tests)
+ ## these are unittests that can be run on any platform
+ add_executable(runtests tests/runtests.c tests/chardata.c tests/structdata.c tests/minicheck.c tests/memcheck.c)
+ set_property(TARGET runtests PROPERTY RUNTIME_OUTPUT_DIRECTORY tests)
+ target_link_libraries(runtests expat)
+ add_test(runtests tests/runtests)
+
+ add_executable(runtestspp tests/runtestspp.cpp tests/chardata.c tests/structdata.c tests/minicheck.c tests/memcheck.c)
+ set_property(TARGET runtestspp PROPERTY RUNTIME_OUTPUT_DIRECTORY tests)
+ target_link_libraries(runtestspp expat)
+ add_test(runtestspp tests/runtestspp)
+endif(BUILD_tests)
diff --git a/COPYING b/COPYING
new file mode 100644
index 0000000..8d288f0
--- /dev/null
+++ b/COPYING
@@ -0,0 +1,21 @@
+Copyright (c) 1998-2000 Thai Open Source Software Center Ltd and Clark Cooper
+Copyright (c) 2001-2017 Expat maintainers
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be included
+in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
diff --git a/Changes b/Changes
index 583c868..8044982 100644
--- a/Changes
+++ b/Changes
@@ -1,3 +1,285 @@
+NOTE: We are looking for help with a few things:
+ https://github.com/libexpat/libexpat/labels/help%20wanted
+ If you can help, please get in touch. Thanks!
+
+Release 2.2.5 Tue October 31 2017
+ Bug fixes:
+ #8 If the parser runs out of memory, make sure its internal
+ state reflects the memory it actually has, not the memory
+ it wanted to have.
+ #11 The default handler wasn't being called when it should for
+ a SYSTEM or PUBLIC doctype if an entity declaration handler
+ was registered.
+ #137 #138 Fix a case of mistakenly reported parsing success where
+ XML_StopParser was called from an element handler
+ #162 Function XML_ErrorString was returning NULL rather than
+ a message for code XML_ERROR_INVALID_ARGUMENT
+ introduced with release 2.2.1
+
+ Other changes:
+ #106 xmlwf: Add argument -N adding notation declarations
+ #75 #106 Test suite: Resolve expected failure cases where xmlwf
+ output was incomplete
+ #127 Windows: Fix test suite compilation
+ #126 #127 Windows: Fix compilation for Visual Studio 2012
+ #33 #132 tests: Mass-fix compilation for XML_UNICODE_WCHAR_T
+ #129 examples: Fix compilation for XML_UNICODE_WCHAR_T
+ #130 benchmark: Fix compilation for XML_UNICODE_WCHAR_T
+ #144 xmlwf: Fix compilation for XML_UNICODE_WCHAR_T; still needs
+ Windows or MinGW for 2-byte wchar_t
+ #9 Address two Clang Static Analyzer false positives
+ #59 Resolve troublesome macros hiding parser struct membership
+ and dereferencing that pointer
+ #6 Resolve superfluous internal malloc/realloc switch
+ #153 #155 Improve docbook2x-man detection
+ #160 Undefine NDEBUG in the test suite (rather than rejecting it)
+ #161 Address compiler warnings
+ Version info bumped from 7:6:6 to 7:7:6
+
+ Special thanks to:
+ Benbuck Nason
+ Hans Wennborg
+ José Gutiérrez de la Concha
+ Pedro Monreal Gonzalez
+ Rhodri James
+ Rolf Ade
+ Stephen Groat
+ and
+ Core Infrastructure Initiative
+
+Release 2.2.4 Sat August 19 2017
+ Bug fixes:
+ #115 Fix copying of partial characters for UTF-8 input
+
+ Other changes:
+ #109 Fix "make check" for non-x86 architectures that default
+ to unsigned type char (-128..127 rather than 0..255)
+ #109 coverage.sh: Cover -funsigned-char
+ Autotools: Introduce --without-xmlwf argument
+ #65 Autotools: Replace handwritten Makefile with GNU Automake
+ #43 CMake: Auto-detect high quality entropy extractors, add new
+ option USE_libbsd=ON to use arc4random_buf of libbsd
+ #74 CMake: Add -fno-strict-aliasing only where supported
+ #114 CMake: Always honor manually set BUILD_* options
+ #114 CMake: Compile man page if docbook2x-man is available, only
+ #117 Include file tests/xmltest.log.expected in source tarball
+ (required for "make run-xmltest")
+ #117 Include (existing) Visual Studio 2013 files in source tarball
+ Improve test suite error output
+ #111 Fix some typos in documentation
+ Version info bumped from 7:5:6 to 7:6:6
+
+ Special thanks to:
+ Jakub Wilk
+ Joe Orton
+ Lin Tian
+ Rolf Eike Beer
+
+Release 2.2.3 Wed August 2 2017
+ Security fixes:
+ #82 CVE-2017-11742 -- Windows: Fix DLL hijacking vulnerability
+ using Steve Holme's LoadLibrary wrapper for/of cURL
+
+ Bug fixes:
+ #85 Fix a dangling pointer issue related to realloc
+
+ Other changes:
+ Increase code coverage
+ #91 Linux: Allow getrandom to fail if nonblocking pool has not
+ yet been initialized and read /dev/urandom then, instead.
+ This is in line with what recent Python does.
+ #81 Pre-10.7/Lion macOS: Support entropy from arc4random
+ #86 Check that a UTF-16 encoding in an XML declaration has the
+ right endianness
+ #4 #5 #7 Recover correctly when some reallocations fail
+ Repair "./configure && make" for systems without any
+ provider of high quality entropy
+ and try reading /dev/urandom on those
+ Ensure that user-defined character encodings have converter
+ functions when they are needed
+ Fix mis-leading description of argument -c in xmlwf.1
+ Rely on macro HAVE_ARC4RANDOM_BUF (rather than __CloudABI__)
+ for CloudABI
+ #100 Fix use of SIPHASH_MAIN in siphash.h
+ #23 Test suite: Fix memory leaks
+ Version info bumped from 7:4:6 to 7:5:6
+
+ Special thanks to:
+ Chanho Park
+ Joe Orton
+ Pascal Cuoq
+ Rhodri James
+ Simon McVittie
+ Vadim Zeitlin
+ Viktor Szakats
+ and
+ Core Infrastructure Initiative
+
+Release 2.2.2 Wed July 12 2017
+ Security fixes:
+ #43 Protect against compilation without any source of high
+ quality entropy enabled, e.g. with CMake build system;
+ commit ff0207e6076e9828e536b8d9cd45c9c92069b895
+ #60 Windows with _UNICODE:
+ Unintended use of LoadLibraryW with a non-wide string
+ resulted in failure to load advapi32.dll and degradation
+ in quality of used entropy when compiled with _UNICODE for
+ Windows; you can launch existing binaries with
+ EXPAT_ENTROPY_DEBUG=1 in the environment to inspect the
+ quality of entropy used during runtime; commits
+ * 95b95032f907ef1cd17ee7a9a1768010a825d61d
+ * 73a5a2e9c081f49f2d775cf7ced864158b68dc80
+ [MOX-006] Fix non-NULL parser parameter validation in XML_Parse;
+ resulted in NULL dereference, previously;
+ commit ac256dafdffc9622ab0dc2c62fcecb0dfcfa71fe
+
+ Bug fixes:
+ #69 Fix improper use of unsigned long long integer literals
+
+ Other changes:
+ #73 Start requiring a C99 compiler
+ #49 Fix "==" Bashism in configure script
+ #50 Fix too eager getrandom detection for Debian GNU/kFreeBSD
+ #52 and macOS
+ #51 Address lack of stdint.h in Visual Studio 2003 to 2008
+ #58 Address compile warnings
+ #68 Fix "./buildconf.sh && ./configure" for some versions
+ of Dash for /bin/sh
+ #72 CMake: Ease use of Expat in context of a parent project
+ with multiple CMakeLists.txt files
+ #72 CMake: Resolve mistaken executable permissions
+ #76 Address compile warning with -DNDEBUG (not recommended!)
+ #77 Address compile warning about macro redefinition
+
+ Special thanks to:
+ Alexander Bluhm
+ Ben Boeckel
+ Cătălin Răceanu
+ Kerin Millar
+ László Böszörményi
+ S. P. Zeidler
+ Segev Finer
+ Václav Slavík
+ Victor Stinner
+ Viktor Szakats
+ and
+ Radically Open Security
+
+Release 2.2.1 Sat June 17 2017
+ Security fixes:
+ CVE-2017-9233 -- External entity infinite loop DoS
+ Details: https://libexpat.github.io/doc/cve-2017-9233/
+ Commit c4bf96bb51dd2a1b0e185374362ee136fe2c9d7f
+ [MOX-002] CVE-2016-9063 -- Detect integer overflow; commit
+ d4f735b88d9932bd5039df2335eefdd0723dbe20
+ (Fixed version of existing downstream patches!)
+ (SF.net) #539 Fix regression from fix to CVE-2016-0718 cutting off
+ longer tag names; commits
+ * 896b6c1fd3b842f377d1b62135dccf0a579cf65d
+ * af507cef2c93cb8d40062a0abe43a4f4e9158fb2
+ #16 * 0dbbf43fdb20f593ddf4fa1ff67288000dd4a7fd
+ #25 More integer overflow detection (function poolGrow); commits
+ * 810b74e4703dcfdd8f404e3cb177d44684775143
+ * 44178553f3539ce69d34abee77a05e879a7982ac
+ [MOX-002] Detect overflow from len=INT_MAX call to XML_Parse; commits
+ * 4be2cb5afcc018d996f34bbbce6374b7befad47f
+ * 7e5b71b748491b6e459e5c9a1d090820f94544d8
+ [MOX-005] #30 Use high quality entropy for hash initialization:
+ * arc4random_buf on BSD, systems with libbsd
+ (when configured with --with-libbsd), CloudABI
+ * RtlGenRandom on Windows XP / Server 2003 and later
+ * getrandom on Linux 3.17+
+ In a way, that's still part of CVE-2016-5300.
+ https://github.com/libexpat/libexpat/pull/30/commits
+ [MOX-005] For the low quality entropy extraction fallback code,
+ the parser instance address can no longer leak, commit
+ 04ad658bd3079dd15cb60fc67087900f0ff4b083
+ [MOX-003] Prevent use of uninitialised variable; commit
+ [MOX-004] a4dc944f37b664a3ca7199c624a98ee37babdb4b
+ Add missing parameter validation to public API functions
+ and dedicated error code XML_ERROR_INVALID_ARGUMENT:
+ [MOX-006] * NULL checks; commits
+ * d37f74b2b7149a3a95a680c4c4cd2a451a51d60a (merge/many)
+ * 9ed727064b675b7180c98cb3d4f75efba6966681
+ * 6a747c837c50114dfa413994e07c0ba477be4534
+ * Negative length (XML_Parse); commit
+ [MOX-002] 70db8d2538a10f4c022655d6895e4c3e78692e7f
+ [MOX-001] #35 Change hash algorithm to William Ahern's version of SipHash
+ to go further with fixing CVE-2012-0876.
+ https://github.com/libexpat/libexpat/pull/39/commits
+
+ Bug fixes:
+ #32 Fix sharing of hash salt across parsers;
+ relevant where XML_ExternalEntityParserCreate is called
+ prior to XML_Parse, in particular (e.g. FBReader)
+ #28 xmlwf: Auto-disable use of memory-mapping (and parsing
+ as a single chunk) for files larger than ~1 GB (2^30 bytes)
+ rather than failing with error "out of memory"
+ #3 Fix double free after malloc failure in DTD code; commit
+ 7ae9c3d3af433cd4defe95234eae7dc8ed15637f
+ #17 Fix memory leak on parser error for unbound XML attribute
+ prefix with new namespaces defined in the same tag;
+ found by Google's OSS-Fuzz; commits
+ * 16f87daae5a16132e479e4f71862128c7a915c73
+ * b47dbc9745932c160893d433220e462bd605f8cd
+ xmlwf on Windows: Add missing calls to CloseHandle
+
+ New features:
+ #30 Introduced environment switch EXPAT_ENTROPY_DEBUG=1
+ for runtime debugging of entropy extraction
+
+ Other changes:
+ Increase code coverage
+ #33 Reject use of XML_UNICODE_WCHAR_T with sizeof(wchar_t) != 2;
+ XML_UNICODE_WCHAR_T was never meant to be used outside
+ of Windows; 4-byte wchar_t is common on Linux
+ (SF.net) #538 Start using -fno-strict-aliasing
+ (SF.net) #540 Support compilation against cloudlibc of CloudABI
+ Allow MinGW cross-compilation
+ (SF.net) #534 CMake: Introduce option "BUILD_doc" (enabled by default)
+ to bypass compilation of the xmlwf.1 man page
+ (SF.net) pr2 CMake: Introduce option "INSTALL" (enabled by default)
+ to bypass installation of expat files
+ CMake: Fix ninja support
+ Autotools: Add parameters --enable-xml-context [COUNT]
+ and --disable-xml-context; default of context of 1024
+ bytes enabled unchanged
+ #14 Drop AmigaOS 4.x code and includes
+ #14 Drop ancient build systems:
+ * Borland C++ Builder
+ * OpenVMS
+ * Open Watcom
+ * Visual Studio 6.0
+ * Pre-X Mac OS (MPW Makefile)
+ If you happen to rely on some of these, please get in
+ touch for joining with maintenance.
+ #10 Move from WIN32 to _WIN32
+ #13 Fix "make run-xmltest" order instability
+ Address compile warnings
+ Bump version info from 7:2:6 to 7:3:6
+ Add AUTHORS file
+
+ Infrastructure:
+ #1 Migrate from SourceForge to GitHub (except downloads):
+ https://github.com/libexpat/
+ #1 Re-create http://libexpat.org/ project website
+ Start utilizing Travis CI
+
+ Special thanks to:
+ Andy Wang
+ Don Lewis
+ Ed Schouten
+ Karl Waclawek
+ Pascal Cuoq
+ Rhodri James
+ Sergei Nikulov
+ Tobias Taschner
+ Viktor Szakats
+ and
+ Core Infrastructure Initiative
+ Mozilla Foundation (MOSS Track 3: Secure Open Source)
+ Radically Open Security
+
Release 2.2.0 Tue June 21 2016
Security fixes:
#537 CVE-2016-0718 -- Fix crash on malformed input
@@ -63,24 +345,25 @@ Release 2.1.1 Sat March 12 2016
libtool now invoked with --verbose
Release 2.1.0 Sat March 24 2012
+ - Security fixes:
+ #2958794: CVE-2012-1148 - Memory leak in poolGrow.
+ #2895533: CVE-2012-1147 - Resource leak in readfilemap.c.
+ #3496608: CVE-2012-0876 - Hash DOS attack.
+ #2894085: CVE-2009-3560 - Buffer over-read and crash in big2_toUtf8().
+ #1990430: CVE-2009-3720 - Parser crash with special UTF-8 sequences.
- Bug Fixes:
#1742315: Harmful XML_ParserCreateNS suggestion.
- #2895533: CVE-2012-1147 - Resource leak in readfilemap.c.
#1785430: Expat build fails on linux-amd64 with gcc version>=4.1 -O3.
#1983953, 2517952, 2517962, 2649838:
Build modifications using autoreconf instead of buildconf.sh.
#2815947, #2884086: OBJEXT and EXEEXT support while building.
- #1990430: CVE-2009-3720 - Parser crash with special UTF-8 sequences.
#2517938: xmlwf should return non-zero exit status if not well-formed.
#2517946: Wrong statement about XMLDecl in xmlwf.1 and xmlwf.sgml.
#2855609: Dangling positionPtr after error.
- #2894085: CVE-2009-3560 - Buffer over-read and crash in big2_toUtf8().
- #2958794: CVE-2012-1148 - Memory leak in poolGrow.
#2990652: CMake support.
#3010819: UNEXPECTED_STATE with a trailing "%" in entity value.
- #3206497: Unitialized memory returned from XML_Parse.
+ #3206497: Uninitialized memory returned from XML_Parse.
#3287849: make check fails on mingw-w64.
- #3496608: CVE-2012-0876 - Hash DOS attack.
- Patches:
#1749198: pkg-config support.
#3010222: Fix for bug #3010819.
diff --git a/ConfigureChecks.cmake b/ConfigureChecks.cmake
new file mode 100644
index 0000000..d97b397
--- /dev/null
+++ b/ConfigureChecks.cmake
@@ -0,0 +1,68 @@
+include(CheckCCompilerFlag)
+include(CheckCSourceCompiles)
+include(CheckIncludeFile)
+include(CheckIncludeFiles)
+include(CheckFunctionExists)
+include(CheckSymbolExists)
+include(TestBigEndian)
+
+check_include_file("dlfcn.h" HAVE_DLFCN_H)
+check_include_file("fcntl.h" HAVE_FCNTL_H)
+check_include_file("inttypes.h" HAVE_INTTYPES_H)
+check_include_file("memory.h" HAVE_MEMORY_H)
+check_include_file("stdint.h" HAVE_STDINT_H)
+check_include_file("stdlib.h" HAVE_STDLIB_H)
+check_include_file("strings.h" HAVE_STRINGS_H)
+check_include_file("string.h" HAVE_STRING_H)
+check_include_file("sys/stat.h" HAVE_SYS_STAT_H)
+check_include_file("sys/types.h" HAVE_SYS_TYPES_H)
+check_include_file("unistd.h" HAVE_UNISTD_H)
+
+check_function_exists("getpagesize" HAVE_GETPAGESIZE)
+check_function_exists("bcopy" HAVE_BCOPY)
+check_symbol_exists("memmove" "string.h" HAVE_MEMMOVE)
+check_function_exists("mmap" HAVE_MMAP)
+check_function_exists("getrandom" HAVE_GETRANDOM)
+
+if(USE_libbsd)
+ set(CMAKE_REQUIRED_LIBRARIES "${LIB_BSD}")
+endif()
+check_function_exists("arc4random_buf" HAVE_ARC4RANDOM_BUF)
+if(NOT HAVE_ARC4RANDOM_BUF)
+ check_function_exists("arc4random" HAVE_ARC4RANDOM)
+endif()
+set(CMAKE_REQUIRED_LIBRARIES)
+
+#/* Define to 1 if you have the ANSI C header files. */
+check_include_files("stdlib.h;stdarg.h;string.h;float.h" STDC_HEADERS)
+
+test_big_endian(WORDS_BIGENDIAN)
+#/* 1234 = LIL_ENDIAN, 4321 = BIGENDIAN */
+if(WORDS_BIGENDIAN)
+ set(BYTEORDER 4321)
+else(WORDS_BIGENDIAN)
+ set(BYTEORDER 1234)
+endif(WORDS_BIGENDIAN)
+
+if(HAVE_SYS_TYPES_H)
+ check_symbol_exists("off_t" "sys/types.h" OFF_T)
+ check_symbol_exists("size_t" "sys/types.h" SIZE_T)
+else(HAVE_SYS_TYPES_H)
+ set(OFF_T "long")
+ set(SIZE_T "unsigned")
+endif(HAVE_SYS_TYPES_H)
+
+check_c_source_compiles("
+ #include <stdlib.h> /* for NULL */
+ #include <unistd.h> /* for syscall */
+ #include <sys/syscall.h> /* for SYS_getrandom */
+ int main() {
+ syscall(SYS_getrandom, NULL, 0, 0);
+ return 0;
+ }"
+ HAVE_SYSCALL_GETRANDOM)
+
+configure_file(expat_config.h.cmake "${CMAKE_CURRENT_BINARY_DIR}/expat_config.h")
+add_definitions(-DHAVE_EXPAT_CONFIG_H)
+
+check_c_compiler_flag("-fno-strict-aliasing" FLAG_NO_STRICT_ALIASING)
diff --git a/Makefile.am b/Makefile.am
new file mode 100644
index 0000000..5ed9ac4
--- /dev/null
+++ b/Makefile.am
@@ -0,0 +1,153 @@
+#
+# __ __ _
+# ___\ \/ /_ __ __ _| |_
+# / _ \\ /| '_ \ / _` | __|
+# | __// \| |_) | (_| | |_
+# \___/_/\_\ .__/ \__,_|\__|
+# |_| XML parser
+#
+# Copyright (c) 2017 Expat development team
+# Licensed under the MIT license:
+#
+# Permission is hereby granted, free of charge, to any person obtaining
+# a copy of this software and associated documentation files (the
+# "Software"), to deal in the Software without restriction, including
+# without limitation the rights to use, copy, modify, merge, publish,
+# distribute, sublicense, and/or sell copies of the Software, and to permit
+# persons to whom the Software is furnished to do so, subject to the
+# following conditions:
+#
+# The above copyright notice and this permission notice shall be included
+# in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+# NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+# DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+# OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+# USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+AUTOMAKE_OPTIONS = \
+ dist-bzip2 \
+ foreign \
+ no-dist-gzip \
+ subdir-objects
+
+ACLOCAL_AMFLAGS = -I m4
+LIBTOOLFLAGS = --verbose
+
+SUBDIRS = lib examples tests # lib goes first to build first
+if WITH_XMLWF
+SUBDIRS += xmlwf doc
+endif
+
+pkgconfig_DATA = expat.pc
+pkgconfigdir = $(libdir)/pkgconfig
+
+
+_EXTRA_DIST_CMAKE = \
+ CMakeLists.txt \
+ CMake.README \
+ ConfigureChecks.cmake \
+ expat_config.h.cmake
+
+_EXTRA_DIST_WINDOWS = \
+ examples/elements.vcxproj \
+ examples/elements.vcxproj.filters \
+ examples/outline.vcxproj \
+ examples/outline.vcxproj.filters \
+ \
+ lib/expat_static.vcxproj \
+ lib/expat_static.vcxproj.filters \
+ lib/expat.vcxproj \
+ lib/expat.vcxproj.filters \
+ lib/expatw_static.vcxproj \
+ lib/expatw_static.vcxproj.filters \
+ lib/expatw.vcxproj \
+ lib/expatw.vcxproj.filters \
+ \
+ tests/benchmark/benchmark.sln \
+ tests/benchmark/benchmark.vcxproj \
+ \
+ tests/runtests.sln \
+ tests/runtests.vcxproj \
+ tests/runtests.vcxproj.filters \
+ \
+ win32/expat.iss \
+ win32/MANIFEST.txt \
+ win32/README.txt \
+ \
+ xmlwf/xmlwf.vcxproj \
+ xmlwf/xmlwf.vcxproj.filters \
+ \
+ expat.sln
+
+EXTRA_DIST = \
+ $(_EXTRA_DIST_CMAKE) \
+ $(_EXTRA_DIST_WINDOWS) \
+ \
+ conftools/expat.m4 \
+ conftools/get-version.sh \
+ conftools/PrintPath \
+ \
+ Changes \
+ README.md \
+ test-driver-wrapper.sh
+
+
+.PHONY: buildlib
+buildlib:
+ @echo 'ERROR: Running "make buildlib LIBRARY=libexpatw.la"' >&2
+ @echo 'ERROR: is no longer supported. INSTEAD please:' >&2
+ @echo 'ERROR:' >&2
+ @echo 'ERROR: * Mass-patch Makefile.am, e.g.' >&2
+ @echo 'ERROR: # find -name Makefile.am -exec sed \' >&2
+ @echo 'ERROR: -e "s,libexpat\.la,libexpatw.la," \' >&2
+ @echo 'ERROR: -e "s,libexpat_la,libexpatw_la," \' >&2
+ @echo 'ERROR: -i {} +' >&2
+ @echo 'ERROR:' >&2
+ @echo 'ERROR: * Run automake to re-generate Makefile.in files' >&2
+ @echo 'ERROR:' >&2
+ @echo 'ERROR: * Use "./configure --without-xmlwf" and/or' >&2
+ @echo 'ERROR: "make -C lib all install" to bypass compilation' >&2
+ @echo 'ERROR: of xmlwf (e.g. with -DXML_UNICODE)' >&2
+ @echo 'ERROR:' >&2
+ @false
+
+
+.PHONY: run-benchmark
+run-benchmark:
+ $(MAKE) -C tests/benchmark
+ ./run.sh tests/benchmark/benchmark@EXEEXT@ -n $(top_srcdir)/../testdata/largefiles/recset.xml 65535 3
+
+tests/xmlts.zip:
+ if test "$(XMLTS_ZIP)" = ""; then \
+ wget --output-document=tests/xmlts.zip \
+ https://www.w3.org/XML/Test/xmlts20080827.zip; \
+ else \
+ cp $(XMLTS_ZIP) tests/xmlts.zip; \
+ fi
+
+tests/xmlconf: tests/xmlts.zip
+ cd tests && unzip -q xmlts.zip
+
+.PHONY: run-xmltest
+run-xmltest: tests/xmlconf
+if WITH_XMLWF
+ $(MAKE) -C xmlwf
+ tests/xmltest.sh "$(PWD)/run.sh $(PWD)/xmlwf/xmlwf@EXEEXT@" 2>&1 | tee tests/xmltest.log
+ dos2unix tests/xmltest.log
+ diff -u tests/xmltest.log.expected tests/xmltest.log
+else
+ @echo 'ERROR: xmlwf is needed for "make run-xmltest".' >&2
+ @echo 'ERROR: Please re-configure without --without-xmlwf.' >&2
+ @false
+endif
+
+.PHONY: qa
+qa:
+ ./qa.sh address
+ ./qa.sh memory
+ ./qa.sh undefined
+ ./qa.sh coverage
diff --git a/NOTICE b/NOTICE
index 092c83b..7a694c9 100644..120000
--- a/NOTICE
+++ b/NOTICE
@@ -1,21 +1 @@
-Copyright (c) 1998-2000 Thai Open Source Software Center Ltd and Clark Cooper
-Copyright (c) 2001-2016 Expat maintainers
-
-Permission is hereby granted, free of charge, to any person obtaining
-a copy of this software and associated documentation files (the
-"Software"), to deal in the Software without restriction, including
-without limitation the rights to use, copy, modify, merge, publish,
-distribute, sublicense, and/or sell copies of the Software, and to
-permit persons to whom the Software is furnished to do so, subject to
-the following conditions:
-
-The above copyright notice and this permission notice shall be included
-in all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
-IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
-CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
-TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
-SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+LICENSE \ No newline at end of file
diff --git a/README.android b/README.android
deleted file mode 100644
index 4f8abcb..0000000
--- a/README.android
+++ /dev/null
@@ -1,7 +0,0 @@
-Please use ./import_expat.sh to update. For example to import from a tar and rebuild:
-
- (croot && cd external/expat && ./import_expat.sh ~/Downloads/expat-2.1.1.tar.bz2 && mma -j32 -B)
-
-When updating to new versions, please remove any unnecessary build
-files to make the diff of what we are using clearer. It is reasonable
-to keep new docs, examples, and tests for reference.
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..984e927
--- /dev/null
+++ b/README.md
@@ -0,0 +1,126 @@
+[![Travis CI Build Status](https://travis-ci.org/libexpat/libexpat.svg?branch=master)](https://travis-ci.org/libexpat/libexpat)
+[![AppVeyor Build Status](https://ci.appveyor.com/api/projects/status/github/libexpat/libexpat?svg=true)](https://ci.appveyor.com/project/libexpat/libexpat)
+
+
+# Expat, Release 2.2.5
+
+This is Expat, a C library for parsing XML, started by
+[James Clark](https://en.wikipedia.org/wiki/James_Clark_(programmer)) in 1997.
+Expat is a stream-oriented XML parser. This means that you register
+handlers with the parser before starting the parse. These handlers
+are called when the parser discovers the associated structures in the
+document being parsed. A start tag is an example of the kind of
+structures for which you may register handlers.
+
+Windows users should use the
+[`expat_win32` package](https://sourceforge.net/projects/expat/files/expat_win32/),
+which includes both precompiled libraries and executables, and source code for
+developers.
+
+Expat is [free software](https://www.gnu.org/philosophy/free-sw.en.html).
+You may copy, distribute, and modify it under the terms of the License
+contained in the file
+[`COPYING`](https://github.com/libexpat/libexpat/blob/master/expat/COPYING)
+distributed with this package.
+This license is the same as the MIT/X Consortium license.
+
+If you are building Expat from a check-out from the
+[Git repository](https://github.com/libexpat/libexpat/),
+you need to run a script that generates the configure script using the
+GNU autoconf and libtool tools. To do this, you need to have
+autoconf 2.58 or newer. Run the script like this:
+
+```console
+./buildconf.sh
+```
+
+Once this has been done, follow the same instructions as for building
+from a source distribution.
+
+To build Expat from a source distribution, you first run the
+configuration shell script in the top level distribution directory:
+
+```console
+./configure
+```
+
+There are many options which you may provide to configure (which you
+can discover by running configure with the `--help` option). But the
+one of most interest is the one that sets the installation directory.
+By default, the configure script will set things up to install
+libexpat into `/usr/local/lib`, `expat.h` into `/usr/local/include`, and
+`xmlwf` into `/usr/local/bin`. If, for example, you'd prefer to install
+into `/home/me/mystuff/lib`, `/home/me/mystuff/include`, and
+`/home/me/mystuff/bin`, you can tell `configure` about that with:
+
+```console
+./configure --prefix=/home/me/mystuff
+```
+
+Another interesting option is to enable 64-bit integer support for
+line and column numbers and the over-all byte index:
+
+```console
+./configure CPPFLAGS=-DXML_LARGE_SIZE
+```
+
+However, such a modification would be a breaking change to the ABI
+and is therefore not recommended for general use &mdash; e.g. as part of
+a Linux distribution &mdash; but rather for builds with special requirements.
+
+After running the configure script, the `make` command will build
+things and `make install` will install things into their proper
+location. Have a look at the `Makefile` to learn about additional
+`make` options. Note that you need to have write permission into
+the directories into which things will be installed.
+
+If you are interested in building Expat to provide document
+information in UTF-16 encoding rather than the default UTF-8, follow
+these instructions (after having run `make distclean`).
+Please note that we configure with `--without-xmlwf` as xmlwf does not
+support this mode of compilation (yet):
+
+1. Mass-patch `Makefile.am` files to use `libexpatw.la` for a library name:
+ <br/>
+ `find -name Makefile.am -exec sed
+ -e 's,libexpat\.la,libexpatw.la,'
+ -e 's,libexpat_la,libexpatw_la,'
+ -i {} +`
+
+1. Run `automake` to re-write `Makefile.in` files:<br/>
+ `automake`
+
+1. For UTF-16 output as unsigned short (and version/error strings as char),
+ run:<br/>
+ `./configure CPPFLAGS=-DXML_UNICODE --without-xmlwf`<br/>
+ For UTF-16 output as `wchar_t` (incl. version/error strings), run:<br/>
+ `./configure CFLAGS="-g -O2 -fshort-wchar" CPPFLAGS=-DXML_UNICODE_WCHAR_T
+ --without-xmlwf`
+ <br/>Note: The latter requires libc compiled with `-fshort-wchar`, as well.
+
+1. Run `make` (which excludes xmlwf).
+
+1. Run `make install` (again, excludes xmlwf).
+
+Using `DESTDIR` is supported. It works as follows:
+
+```console
+make install DESTDIR=/path/to/image
+```
+
+overrides the in-makefile set `DESTDIR`, because variable-setting priority is
+
+1. commandline
+1. in-makefile
+1. environment
+
+Note: This only applies to the Expat library itself, building UTF-16 versions
+of xmlwf and the tests is currently not supported.
+
+When using Expat with a project using autoconf for configuration, you
+can use the probing macro in `conftools/expat.m4` to determine how to
+include Expat. See the comments at the top of that file for more
+information.
+
+A reference manual is available in the file `doc/reference.html` in this
+distribution.
diff --git a/README.version b/README.version
index 7b85695..a1ff897 100644
--- a/README.version
+++ b/README.version
@@ -1,7 +1,3 @@
-URL: https://sourceforge.net/projects/expat/files/expat/2.2.0/expat-2.2.0.tar.bz2/download
-Version: 2.2.0
+URL: https://github.com/libexpat/libexpat/archive/R_2_2_5.tar.gz
+Version: 2.2.5
BugComponent: 24949
-
-Local Changes:
- Reverted change to switch from COMPILED_FROM_DSP to WIN32. This was needed in order to get it to compile as winconfig.h is not available.
- Fix cast from pointer to integer of different size
diff --git a/buildconf.sh b/buildconf.sh
new file mode 100755
index 0000000..27c01e1
--- /dev/null
+++ b/buildconf.sh
@@ -0,0 +1,2 @@
+#! /bin/sh
+exec autoreconf -i -f
diff --git a/clean_coverage.sh b/clean_coverage.sh
new file mode 100755
index 0000000..bf02fbf
--- /dev/null
+++ b/clean_coverage.sh
@@ -0,0 +1,3 @@
+rm -r build__*
+rm -r coverage__*
+rm -r source__*
diff --git a/configure.ac b/configure.ac
new file mode 100644
index 0000000..c24f518
--- /dev/null
+++ b/configure.ac
@@ -0,0 +1,256 @@
+dnl configuration script for expat
+dnl Process this file with autoconf to produce a configure script.
+dnl
+dnl Copyright 2000 Clark Cooper
+dnl
+dnl This file is part of EXPAT.
+dnl
+dnl EXPAT is free software; you can redistribute it and/or modify it
+dnl under the terms of the License (based on the MIT/X license) contained
+dnl in the file COPYING that comes with this distribution.
+dnl
+
+dnl Ensure that Expat is configured with autoconf 2.58 or newer
+AC_PREREQ(2.58)
+
+dnl Get the version number of Expat, using m4's esyscmd() command to run
+dnl the command at m4-generation time. This allows us to create an m4
+dnl symbol holding the correct version number. AC_INIT() requires the
+dnl version number at m4-time, rather than when ./configure is run, so
+dnl all this must happen as part of m4, not as part of the shell code
+dnl contained in ./configure.
+dnl
+dnl NOTE: esyscmd() is a GNU M4 extension. Thus, we wrap it in an appropriate
+dnl test. I believe this test will work, but I don't have a place with non-
+dnl GNU M4 to test it right now.
+define([expat_version], ifdef([__gnu__],
+ [esyscmd(conftools/get-version.sh lib/expat.h)],
+ [2.2.x]))
+AC_INIT(expat, expat_version, expat-bugs@libexpat.org)
+undefine([expat_version])
+
+AC_CONFIG_SRCDIR(Makefile.in)
+AC_CONFIG_AUX_DIR(conftools)
+AM_INIT_AUTOMAKE
+AC_CONFIG_MACRO_DIR([m4])
+
+
+dnl
+dnl Increment LIBREVISION if source code has changed at all
+dnl
+dnl If the API has changed, increment LIBCURRENT and set LIBREVISION to 0
+dnl
+dnl If the API changes compatibly (i.e. simply adding a new function
+dnl without changing or removing earlier interfaces), then increment LIBAGE.
+dnl
+dnl If the API changes incompatibly set LIBAGE back to 0
+dnl
+
+LIBCURRENT=7 # sync
+LIBREVISION=7 # with
+LIBAGE=6 # CMakeLists.txt!
+
+CPPFLAGS="${CPPFLAGS} -DHAVE_EXPAT_CONFIG_H"
+AC_CONFIG_HEADER(expat_config.h)
+
+sinclude(conftools/ac_c_bigendian_cross.m4)
+
+AC_LIBTOOL_WIN32_DLL
+AC_PROG_LIBTOOL
+
+AC_SUBST(LIBCURRENT)
+AC_SUBST(LIBREVISION)
+AC_SUBST(LIBAGE)
+
+dnl Checks for programs.
+AC_PROG_CC_C99
+AC_PROG_CXX
+AC_PROG_INSTALL
+
+if test "$GCC" = yes ; then
+ dnl
+ dnl Be careful about adding the -fexceptions option; some versions of
+ dnl GCC don't support it and it causes extra warnings that are only
+ dnl distracting; avoid.
+ dnl
+ OLDCFLAGS="$CFLAGS -Wall -Wmissing-prototypes -Wstrict-prototypes"
+ CFLAGS="$OLDCFLAGS -fexceptions"
+ AC_MSG_CHECKING(whether $CC accepts -fexceptions)
+ AC_TRY_LINK( , ,
+ AC_MSG_RESULT(yes),
+ AC_MSG_RESULT(no); CFLAGS="$OLDCFLAGS")
+ if test "x$CXXFLAGS" = x ; then
+ CXXFLAGS=`echo "$CFLAGS" | sed 's/ -Wmissing-prototypes -Wstrict-prototypes//'`
+ fi
+
+ CFLAGS="${CFLAGS} -fno-strict-aliasing"
+ CXXFLAGS="${CXXFLAGS} -fno-strict-aliasing"
+ LDFLAGS="${LDFLAGS} -fno-strict-aliasing"
+fi
+
+dnl Checks for header files.
+AC_HEADER_STDC
+
+dnl Checks for typedefs, structures, and compiler characteristics.
+
+dnl Note: Avoid using AC_C_BIGENDIAN because it does not
+dnl work in a cross compile.
+AC_C_BIGENDIAN_CROSS
+
+AC_C_CONST
+AC_TYPE_SIZE_T
+AC_CHECK_FUNCS(memmove bcopy)
+
+
+AC_ARG_WITH([xmlwf], [
+AS_HELP_STRING([--without-xmlwf], [do not build xmlwf])], [], [with_xmlwf=yes])
+AM_CONDITIONAL([WITH_XMLWF], [test x${with_xmlwf} = xyes])
+
+AM_CONDITIONAL([MINGW], [echo -- "${host}" | fgrep -q mingw])
+AM_CONDITIONAL([UNICODE], [echo -- "${CPPFLAGS}${CFLAGS}" | fgrep -q XML_UNICODE])
+
+
+AC_ARG_WITH([libbsd], [
+AS_HELP_STRING([--with-libbsd], [utilize libbsd (for arc4random_buf)])
+], [], [with_libbsd=no])
+AS_IF([test "x${with_libbsd}" != xno], [
+ AC_CHECK_LIB([bsd], [arc4random_buf], [], [
+ AS_IF([test "x${with_libbsd}" = xyes], [
+ AC_MSG_ERROR([Enforced use of libbsd cannot be satisfied.])
+ ])
+ ])
+])
+AC_MSG_CHECKING([for arc4random_buf (BSD or libbsd)])
+AC_LINK_IFELSE([AC_LANG_SOURCE([
+ #include <stdlib.h> /* for arc4random_buf on BSD, for NULL */
+ #if defined(HAVE_LIBBSD)
+ # include <bsd/stdlib.h>
+ #endif
+ int main() {
+ arc4random_buf(NULL, 0U);
+ return 0;
+ }
+])], [
+ AC_DEFINE([HAVE_ARC4RANDOM_BUF], [1],
+ [Define to 1 if you have the `arc4random_buf' function.])
+ AC_MSG_RESULT([yes])
+], [
+ AC_MSG_RESULT([no])
+
+ AC_MSG_CHECKING([for arc4random (BSD, macOS or libbsd)])
+ AC_LINK_IFELSE([AC_LANG_SOURCE([
+ #if defined(HAVE_LIBBSD)
+ # include <bsd/stdlib.h>
+ #else
+ # include <stdlib.h>
+ #endif
+ int main() {
+ arc4random();
+ return 0;
+ }
+ ])], [
+ AC_DEFINE([HAVE_ARC4RANDOM], [1],
+ [Define to 1 if you have the `arc4random' function.])
+ AC_MSG_RESULT([yes])
+ ], [
+ AC_MSG_RESULT([no])
+ ])
+])
+
+
+AC_MSG_CHECKING([for getrandom (Linux 3.17+, glibc 2.25+)])
+AC_LINK_IFELSE([AC_LANG_SOURCE([
+ #include <stdlib.h> /* for NULL */
+ #include <sys/random.h>
+ int main() {
+ return getrandom(NULL, 0U, 0U);
+ }
+])], [
+ AC_DEFINE([HAVE_GETRANDOM], [1],
+ [Define to 1 if you have the `getrandom' function.])
+ AC_MSG_RESULT([yes])
+], [
+ AC_MSG_RESULT([no])
+
+ AC_MSG_CHECKING([for syscall SYS_getrandom (Linux 3.17+)])
+ AC_LINK_IFELSE([AC_LANG_SOURCE([
+ #include <stdlib.h> /* for NULL */
+ #include <unistd.h> /* for syscall */
+ #include <sys/syscall.h> /* for SYS_getrandom */
+ int main() {
+ syscall(SYS_getrandom, NULL, 0, 0);
+ return 0;
+ }
+ ])], [
+ AC_DEFINE([HAVE_SYSCALL_GETRANDOM], [1],
+ [Define to 1 if you have `syscall' and `SYS_getrandom'.])
+ AC_MSG_RESULT([yes])
+ ], [
+ AC_MSG_RESULT([no])
+ ])
+])
+
+
+dnl Only needed for xmlwf:
+AC_CHECK_HEADERS(fcntl.h unistd.h)
+AC_TYPE_OFF_T
+AC_FUNC_MMAP
+
+if test "$ac_cv_func_mmap_fixed_mapped" = "yes"; then
+ FILEMAP=unixfilemap
+else
+ FILEMAP=readfilemap
+fi
+AC_SUBST(FILEMAP)
+
+
+dnl Some basic configuration:
+AC_DEFINE([XML_NS], 1,
+ [Define to make XML Namespaces functionality available.])
+AC_DEFINE([XML_DTD], 1,
+ [Define to make parameter entity parsing functionality available.])
+AC_DEFINE([XML_DEV_URANDOM], 1,
+ [Define to include code reading entropy from `/dev/urandom'.])
+
+AC_ARG_ENABLE([xml-context],
+ AS_HELP_STRING([--enable-xml-context @<:@COUNT@:>@],
+ [Retain context around the current parse point;
+ default is enabled and a size of 1024 bytes])
+AS_HELP_STRING([--disable-xml-context],
+ [Do not retain context around the current parse point]),
+ [enable_xml_context=${enableval}])
+AS_IF([test "x${enable_xml_context}" != "xno"], [
+ AS_IF([test "x${enable_xml_context}" = "xyes" \
+ -o "x${enable_xml_context}" = "x"], [
+ enable_xml_context=1024
+ ])
+ AC_DEFINE_UNQUOTED([XML_CONTEXT_BYTES], [${enable_xml_context}],
+ [Define to specify how much context to retain around the current parse point.])
+])
+
+AC_ARG_WITH([docbook], [AS_HELP_STRING([--with-docbook],
+ [enforce XML to man page compilation @<:@default=check@:>@])
+AS_HELP_STRING([--without-docbook],
+ [skip XML to man page compilation @<:@default=check@:>@])],
+ [],
+ [with_docbook=check])
+
+AC_ARG_VAR([DOCBOOK_TO_MAN], [docbook2x-man command])
+AS_IF([test "x$with_docbook" != xno],
+ [AC_CHECK_PROGS([DOCBOOK_TO_MAN], [docbook2x-man docbook2man docbook-to-man],
+ [if test "x$with_docbook" != xcheck; then
+ AC_MSG_ERROR([Required program 'docbook2x-man' not found.])])])
+
+AM_CONDITIONAL(WITH_DOCBOOK, [test x${DOCBOOK_TO_MAN} != x])
+
+AC_CONFIG_FILES([Makefile expat.pc])
+AC_CONFIG_FILES([
+ doc/Makefile
+ examples/Makefile
+ lib/Makefile
+ tests/Makefile
+ tests/benchmark/Makefile
+ xmlwf/Makefile
+])
+AC_CONFIG_FILES([run.sh], [chmod +x run.sh])
+AC_OUTPUT
diff --git a/conftools/.gitignore b/conftools/.gitignore
new file mode 100644
index 0000000..ff15588
--- /dev/null
+++ b/conftools/.gitignore
@@ -0,0 +1,10 @@
+compile
+config.guess
+config.sub
+depcomp
+install-sh
+libtool.m4
+ltconfig
+ltmain.sh
+missing
+test-driver
diff --git a/conftools/PrintPath b/conftools/PrintPath
new file mode 100755
index 0000000..e8559a3
--- /dev/null
+++ b/conftools/PrintPath
@@ -0,0 +1,116 @@
+#!/bin/sh
+# Look for program[s] somewhere in $PATH.
+#
+# Options:
+# -s
+# Do not print out full pathname. (silent)
+# -pPATHNAME
+# Look in PATHNAME instead of $PATH
+#
+# Usage:
+# PrintPath [-s] [-pPATHNAME] program [program ...]
+#
+# Initially written by Jim Jagielski for the Apache configuration mechanism
+# (with kudos to Kernighan/Pike)
+#
+# This script falls under the Apache License.
+# See http://www.apache.org/licenses/LICENSE
+
+##
+# Some "constants"
+##
+pathname=$PATH
+echo="yes"
+
+##
+# Find out what OS we are running for later on
+##
+os=`(uname) 2>/dev/null`
+
+##
+# Parse command line
+##
+for args in $*
+do
+ case $args in
+ -s ) echo="no" ;;
+ -p* ) pathname="`echo $args | sed 's/^..//'`" ;;
+ * ) programs="$programs $args" ;;
+ esac
+done
+
+##
+# Now we make the adjustments required for OS/2 and everyone
+# else :)
+#
+# First of all, all OS/2 programs have the '.exe' extension.
+# Next, we adjust PATH (or what was given to us as PATH) to
+# be whitespace separated directories.
+# Finally, we try to determine the best flag to use for
+# test/[] to look for an executable file. OS/2 just has '-r'
+# but with other OSs, we do some funny stuff to check to see
+# if test/[] knows about -x, which is the preferred flag.
+##
+
+if [ "x$os" = "xOS/2" ]
+then
+ ext=".exe"
+ pathname=`echo -E $pathname |
+ sed 's/^;/.;/
+ s/;;/;.;/g
+ s/;$/;./
+ s/;/ /g
+ s/\\\\/\\//g' `
+ test_exec_flag="-r"
+else
+ ext="" # No default extensions
+ pathname=`echo $pathname |
+ sed 's/^:/.:/
+ s/::/:.:/g
+ s/:$/:./
+ s/:/ /g' `
+ # Here is how we test to see if test/[] can handle -x
+ testfile="pp.t.$$"
+
+ cat > $testfile <<ENDTEST
+#!/bin/sh
+if [ -x / ] || [ -x /bin ] || [ -x /bin/ls ]; then
+ exit 0
+fi
+exit 1
+ENDTEST
+
+ if `/bin/sh $testfile 2>/dev/null`; then
+ test_exec_flag="-x"
+ else
+ test_exec_flag="-r"
+ fi
+ rm -f $testfile
+fi
+
+for program in $programs
+do
+ for path in $pathname
+ do
+ if [ $test_exec_flag $path/${program}${ext} ] && \
+ [ ! -d $path/${program}${ext} ]; then
+ if [ "x$echo" = "xyes" ]; then
+ echo $path/${program}${ext}
+ fi
+ exit 0
+ fi
+
+# Next try without extension (if one was used above)
+ if [ "x$ext" != "x" ]; then
+ if [ $test_exec_flag $path/${program} ] && \
+ [ ! -d $path/${program} ]; then
+ if [ "x$echo" = "xyes" ]; then
+ echo $path/${program}
+ fi
+ exit 0
+ fi
+ fi
+ done
+done
+exit 1
+
diff --git a/conftools/ac_c_bigendian_cross.m4 b/conftools/ac_c_bigendian_cross.m4
new file mode 100644
index 0000000..e95ffb6
--- /dev/null
+++ b/conftools/ac_c_bigendian_cross.m4
@@ -0,0 +1,81 @@
+dnl @synopsis AC_C_BIGENDIAN_CROSS
+dnl
+dnl Check endianess even when crosscompiling
+dnl (partially based on the original AC_C_BIGENDIAN).
+dnl
+dnl The implementation will create a binary, and instead of running
+dnl the binary it will be grep'ed for some symbols that will look
+dnl different for different endianess of the binary.
+dnl
+dnl @version $Id: ac_c_bigendian_cross.m4,v 1.1 2001/07/24 19:51:35 fdrake Exp $
+dnl @author Guido Draheim <guidod@gmx.de>
+dnl
+AC_DEFUN([AC_C_BIGENDIAN_CROSS],
+[AC_CACHE_CHECK(whether byte ordering is bigendian, ac_cv_c_bigendian,
+[ac_cv_c_bigendian=unknown
+# See if sys/param.h defines the BYTE_ORDER macro.
+AC_TRY_COMPILE([#include <sys/types.h>
+#include <sys/param.h>], [
+#if !BYTE_ORDER || !BIG_ENDIAN || !LITTLE_ENDIAN
+ bogus endian macros
+#endif], [# It does; now see whether it defined to BIG_ENDIAN or not.
+AC_TRY_COMPILE([#include <sys/types.h>
+#include <sys/param.h>], [
+#if BYTE_ORDER != BIG_ENDIAN
+ not big endian
+#endif], ac_cv_c_bigendian=yes, ac_cv_c_bigendian=no)])
+if test $ac_cv_c_bigendian = unknown; then
+AC_TRY_RUN([main () {
+ /* Are we little or big endian? From Harbison&Steele. */
+ union
+ {
+ long l;
+ char c[sizeof (long)];
+ } u;
+ u.l = 1;
+ exit (u.c[sizeof (long) - 1] == 1);
+}], ac_cv_c_bigendian=no, ac_cv_c_bigendian=yes,
+[ echo $ac_n "cross-compiling... " 2>&AC_FD_MSG ])
+fi])
+if test $ac_cv_c_bigendian = unknown; then
+AC_MSG_CHECKING(to probe for byte ordering)
+[
+cat >conftest.c <<EOF
+short ascii_mm[] = { 0x4249, 0x4765, 0x6E44, 0x6961, 0x6E53, 0x7953, 0 };
+short ascii_ii[] = { 0x694C, 0x5454, 0x656C, 0x6E45, 0x6944, 0x6E61, 0 };
+void _ascii() { char* s = (char*) ascii_mm; s = (char*) ascii_ii; }
+short ebcdic_ii[] = { 0x89D3, 0xE3E3, 0x8593, 0x95C5, 0x89C4, 0x9581, 0 };
+short ebcdic_mm[] = { 0xC2C9, 0xC785, 0x95C4, 0x8981, 0x95E2, 0xA8E2, 0 };
+void _ebcdic() { char* s = (char*) ebcdic_mm; s = (char*) ebcdic_ii; }
+int main() { _ascii (); _ebcdic (); return 0; }
+EOF
+] if test -f conftest.c ; then
+ if ${CC-cc} -c conftest.c -o conftest.o && test -f conftest.o ; then
+ if test `grep -l BIGenDianSyS conftest.o` ; then
+ echo $ac_n ' big endian probe OK, ' 1>&AC_FD_MSG
+ ac_cv_c_bigendian=yes
+ fi
+ if test `grep -l LiTTleEnDian conftest.o` ; then
+ echo $ac_n ' little endian probe OK, ' 1>&AC_FD_MSG
+ if test $ac_cv_c_bigendian = yes ; then
+ ac_cv_c_bigendian=unknown;
+ else
+ ac_cv_c_bigendian=no
+ fi
+ fi
+ echo $ac_n 'guessing bigendian ... ' >&AC_FD_MSG
+ fi
+ fi
+AC_MSG_RESULT($ac_cv_c_bigendian)
+fi
+if test $ac_cv_c_bigendian = yes; then
+ AC_DEFINE(WORDS_BIGENDIAN, 1, [whether byteorder is bigendian])
+ BYTEORDER=4321
+else
+ BYTEORDER=1234
+fi
+AC_DEFINE_UNQUOTED(BYTEORDER, $BYTEORDER, [1234 = LIL_ENDIAN, 4321 = BIGENDIAN])
+if test $ac_cv_c_bigendian = unknown; then
+ AC_MSG_ERROR(unknown endianess - sorry, please pre-set ac_cv_c_bigendian)
+fi
+])
diff --git a/conftools/expat.m4 b/conftools/expat.m4
new file mode 100644
index 0000000..57e579b
--- /dev/null
+++ b/conftools/expat.m4
@@ -0,0 +1,43 @@
+dnl Check if --with-expat[=PREFIX] is specified and
+dnl Expat >= 1.95.0 is installed in the system.
+dnl If yes, substitute EXPAT_CFLAGS, EXPAT_LIBS with regard to
+dnl the specified PREFIX and set with_expat to PREFIX, or 'yes' if PREFIX
+dnl has not been specified. Also HAVE_LIBEXPAT, HAVE_EXPAT_H are defined.
+dnl If --with-expat has not been specified, set with_expat to 'no'.
+dnl In addition, an Automake conditional EXPAT_INSTALLED is set accordingly.
+dnl This is necessary to adapt a whole lot of packages that have expat
+dnl bundled as a static library.
+AC_DEFUN([AM_WITH_EXPAT],
+[ AC_ARG_WITH(expat,
+ [ --with-expat=PREFIX Use system Expat library],
+ , with_expat=no)
+
+ AM_CONDITIONAL(EXPAT_INSTALLED, test $with_expat != no)
+
+ EXPAT_CFLAGS=
+ EXPAT_LIBS=
+ if test $with_expat != no; then
+ if test $with_expat != yes; then
+ EXPAT_CFLAGS="-I$with_expat/include"
+ EXPAT_LIBS="-L$with_expat/lib"
+ fi
+ AC_CHECK_LIB(expat, XML_ParserCreate,
+ [ EXPAT_LIBS="$EXPAT_LIBS -lexpat"
+ expat_found=yes ],
+ [ expat_found=no ],
+ "$EXPAT_LIBS")
+ if test $expat_found = no; then
+ AC_MSG_ERROR([Could not find the Expat library])
+ fi
+ expat_save_CFLAGS="$CFLAGS"
+ CFLAGS="$CFLAGS $EXPAT_CFLAGS"
+ AC_CHECK_HEADERS(expat.h, , expat_found=no)
+ if test $expat_found = no; then
+ AC_MSG_ERROR([Could not find expat.h])
+ fi
+ CFLAGS="$expat_save_CFLAGS"
+ fi
+
+ AC_SUBST(EXPAT_CFLAGS)
+ AC_SUBST(EXPAT_LIBS)
+])
diff --git a/conftools/get-version.sh b/conftools/get-version.sh
new file mode 100755
index 0000000..2592f10
--- /dev/null
+++ b/conftools/get-version.sh
@@ -0,0 +1,35 @@
+#!/bin/sh
+#
+# USAGE: get-version.sh path/to/expat.h
+#
+# This script will print Expat's version number on stdout. For example:
+#
+# $ ./conftools/get-version.sh ./lib/expat.h
+# 1.95.3
+# $
+#
+
+if test $# = 0; then
+ echo "ERROR: pathname for expat.h was not provided."
+ echo ""
+ echo "USAGE: $0 path/to/expat.h"
+ exit 1
+fi
+if test $# != 1; then
+ echo "ERROR: too many arguments were provided."
+ echo ""
+ echo "USAGE: $0 path/to/expat.h"
+ exit 1
+fi
+
+hdr="$1"
+if test ! -r "$hdr"; then
+ echo "ERROR: '$hdr' does not exist, or is not readable."
+ exit 1
+fi
+
+MAJOR_VERSION=$(sed -n -e '/MAJOR_VERSION/s/[^0-9]*//gp' "$hdr")
+MINOR_VERSION=$(sed -n -e '/MINOR_VERSION/s/[^0-9]*//gp' "$hdr")
+MICRO_VERSION=$(sed -n -e '/MICRO_VERSION/s/[^0-9]*//gp' "$hdr")
+
+printf '%s.%s.%s' "$MAJOR_VERSION" "$MINOR_VERSION" "$MICRO_VERSION"
diff --git a/coverage.sh b/coverage.sh
new file mode 100755
index 0000000..20dc9e3
--- /dev/null
+++ b/coverage.sh
@@ -0,0 +1,237 @@
+#! /bin/bash
+# Copyright (C) Sebastian Pipping <sebastian@pipping.org>
+# Licensed under the MIT license
+
+export PS4='# '
+
+
+_get_source_dir() {
+ echo "source__${version}"
+}
+
+
+_get_build_dir() {
+ local libbsd_part=
+ if ${with_libbsd}; then
+ libbsd_part=__libbsd
+ fi
+
+ local mingw_part=
+ if ${with_mingw}; then
+ mingw_part=__windows
+ fi
+
+ local char_part=
+ if ${with_unsigned_char}; then
+ char_part=__unsigned_char
+ fi
+
+ echo "build__${version}__unicode_${unicode_enabled}__xml_context_${xml_context}${libbsd_part}${mingw_part}${char_part}"
+}
+
+
+_get_coverage_dir() {
+ echo "coverage__${version}"
+}
+
+
+_configure() {
+ local configure_args=()
+
+ ${unicode_enabled} \
+ && configure_args+=( CPPFLAGS='-DXML_UNICODE -DXML_UNICODE_WCHAR_T' )
+
+ if [[ ${xml_context} -eq 0 ]]; then
+ configure_args+=( --disable-xml-context )
+ else
+ configure_args+=( --enable-xml-context=${xml_context} )
+ fi
+
+ ${with_libbsd} && configure_args+=( --with-libbsd )
+ ${with_mingw} && configure_args+=( --host=i686-w64-mingw32 )
+
+ (
+ set -x
+ ./buildconf.sh &> configure.log
+ ./configure "${configure_args[@]}" "$@" &>> configure.log
+ )
+}
+
+
+_copy_to() {
+ local target_dir="$1"
+ [[ -d "${target_dir}" ]] && return 0
+
+ mkdir "${target_dir}"
+ git archive --format=tar "${version}" | ( cd "${target_dir}" && tar x )
+}
+
+
+_copy_missing_mingw_libaries() {
+ # These extra files are copied because
+ # * coverage GCC flags make them needed
+ # * With WINEDLLPATH Wine looks for .dll.so in these folders, not .dll
+ local target="$1"
+ local mingw_gcc_dll_dir="$(dirname "$(ls -1 /usr/lib*/gcc/i686-w64-mingw32/*/libgcc_s_sjlj-1.dll | head -n1)")"
+ for dll in libgcc_s_sjlj-1.dll libstdc++-6.dll; do
+ (
+ set -x
+ ln -s "${mingw_gcc_dll_dir}"/${dll} "${target}"/${dll}
+ )
+ done
+
+ local mingw_pthread_dll_dir="$(dirname "$(ls -1 /usr/i686-w64-mingw32/lib*/libwinpthread-1.dll | head -n1)")"
+ for dll in libwinpthread-1.dll; do
+ source="${mingw_pthread_dll_dir}"/${dll}
+ [[ -e "${source}" ]] || continue
+ (
+ set -x
+ ln -s "${source}" "${target}"/${dll}
+ )
+ done
+}
+
+
+_run() {
+ local source_dir="$1"
+ local build_dir="$2"
+ local capture_dir=lib
+
+ local BASE_FLAGS='-pipe -Wall -Wextra -pedantic -Wno-overlength-strings'
+ BASE_FLAGS+=' --coverage --no-inline'
+
+ ${with_unsigned_char} && BASE_FLAGS="${BASE_FLAGS} -funsigned-char"
+
+ local CFLAGS="-std=c99 ${BASE_FLAGS}"
+ local CXXFLAGS="-std=c++98 ${BASE_FLAGS}"
+
+ (
+ set -e
+ cd "${build_dir}"
+
+ _configure \
+ CFLAGS="${BASE_FLAGS}" \
+ CXXFLAGS="${BASE_FLAGS}"
+
+ (
+ set -x
+ make -C lib &> build.log
+
+ lcov -c -d "${capture_dir}" -i -o "${coverage_info}-zero" &> run.log
+ )
+
+ if ${with_mingw}; then
+ for d in {tests,xmlwf}/.libs ; do
+ mkdir -p "${d}"
+ _copy_missing_mingw_libaries "${d}"
+ done
+ fi
+
+ set -x
+ make all check run-xmltest
+
+ lcov -c -d "${capture_dir}" -o "${coverage_info}-test" &>> run.log
+ lcov \
+ -a "${coverage_info}-zero" \
+ -a "${coverage_info}-test" \
+ -o "${coverage_info}-all" \
+ &>> run.log
+
+ # Make sure that files overlap in report despite different build folders
+ sed "/SF:/ s,${build_dir}/,${source_dir}/," "${coverage_info}-all" > "${coverage_info}"
+ ) |& sed 's,^, ,'
+ res=${PIPESTATUS[0]}
+
+ if [[ ${res} -eq 0 ]]; then
+ echo PASSED
+ else
+ echo FAILED >&2
+ return 1
+ fi
+}
+
+
+_merge_coverage_info() {
+ local coverage_dir="$1"
+ shift
+ local build_dirs=( "$@" )
+
+ mkdir -p "${coverage_dir}"
+ (
+ local lcov_merge_args=()
+ for build_dir in "${build_dirs[@]}"; do
+ lcov_merge_args+=( -a "${build_dir}/${coverage_info}" )
+ done
+ lcov_merge_args+=( -o "${coverage_dir}/${coverage_info}" )
+
+ set -x
+ lcov "${lcov_merge_args[@]}"
+ ) &> "${coverage_dir}/merge.log"
+}
+
+
+_render_html_report() {
+ local coverage_dir="$1"
+ genhtml -o "${coverage_dir}" "${coverage_dir}/${coverage_info}" &> "${coverage_dir}/render.log"
+}
+
+
+_show_summary() {
+ local coverage_dir="$1"
+ lcov -q -l "${coverage_dir}/${coverage_info}" | grep -v '^\['
+}
+
+
+_main() {
+ version="$(git describe --tags)"
+ coverage_info=coverage.info
+
+ local build_dirs=()
+ local source_dir="$(_get_source_dir)"
+ local coverage_dir="$(_get_coverage_dir)"
+
+ _copy_to "${source_dir}"
+
+ _build_case() {
+ local build_dir="$(_get_build_dir)"
+
+ echo "[${build_dir}]"
+ _copy_to "${build_dir}"
+ _run "${source_dir}" "${build_dir}"
+
+ build_dirs+=( "${build_dir}" )
+ }
+
+ # All combinations:
+ with_unsigned_char=false
+ with_libbsd=false
+ for with_mingw in true false ; do
+ for unicode_enabled in true false ; do
+ if ${unicode_enabled} && ! ${with_mingw} ; then
+ continue
+ fi
+
+ for xml_context in 0 1024 ; do
+ _build_case
+ done
+ done
+ done
+
+ # Single cases:
+ with_libbsd=true _build_case
+ with_unsigned_char=true _build_case
+
+ echo
+ echo 'Merging coverage files...'
+ _merge_coverage_info "${coverage_dir}" "${build_dirs[@]}"
+
+ echo 'Rendering HTML report...'
+ _render_html_report "${coverage_dir}"
+ echo "--> ${coverage_dir}/index.html"
+
+ echo
+ _show_summary "${coverage_dir}"
+}
+
+
+_main
diff --git a/doc/.gitignore b/doc/.gitignore
new file mode 100644
index 0000000..65c1472
--- /dev/null
+++ b/doc/.gitignore
@@ -0,0 +1,2 @@
+/XMLWF.1
+/xmlwf.1
diff --git a/doc/Makefile.am b/doc/Makefile.am
new file mode 100644
index 0000000..7c79aa4
--- /dev/null
+++ b/doc/Makefile.am
@@ -0,0 +1,55 @@
+#
+# __ __ _
+# ___\ \/ /_ __ __ _| |_
+# / _ \\ /| '_ \ / _` | __|
+# | __// \| |_) | (_| | |_
+# \___/_/\_\ .__/ \__,_|\__|
+# |_| XML parser
+#
+# Copyright (c) 2017 Expat development team
+# Licensed under the MIT license:
+#
+# Permission is hereby granted, free of charge, to any person obtaining
+# a copy of this software and associated documentation files (the
+# "Software"), to deal in the Software without restriction, including
+# without limitation the rights to use, copy, modify, merge, publish,
+# distribute, sublicense, and/or sell copies of the Software, and to permit
+# persons to whom the Software is furnished to do so, subject to the
+# following conditions:
+#
+# The above copyright notice and this permission notice shall be included
+# in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+# NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+# DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+# OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+# USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+dist_man_MANS = xmlwf.1
+
+xmlwf.1: xmlwf.xml
+if WITH_DOCBOOK
+ $(DOCBOOK_TO_MAN) $<
+ mv XMLWF.1 $@
+else
+ @echo 'ERROR: Configure with --with-docbook for "make dist".' 1>&2
+ @false
+endif
+
+# https://www.gnu.org/software/automake/manual/automake.html#What-Gets-Cleaned
+.PHONY: clean-local
+clean-local: clean-local-check
+
+.PHONY: clean-local-check
+clean-local-check:
+ $(RM) xmlwf.1
+
+EXTRA_DIST = \
+ expat.png \
+ reference.html \
+ style.css \
+ valid-xhtml10.png \
+ xmlwf.xml
diff --git a/doc/reference.html b/doc/reference.html
index a4ab405..efc19f4 100644
--- a/doc/reference.html
+++ b/doc/reference.html
@@ -31,7 +31,7 @@ the underlying XML parser for the open source Mozilla project, Perl's
other open-source XML parsers.</p>
<p>This library is the creation of James Clark, who's also given us
-groff (an nroff look-alike), Jade (an implemention of ISO's DSSSL
+groff (an nroff look-alike), Jade (an implementation of ISO's DSSSL
stylesheet language for SGML), XP (a Java XML parser package), XT (a
Java XSL engine). James was also the technical lead on the XML
Working Group at W3C that produced the XML specification.</p>
@@ -277,7 +277,7 @@ directions or Unix directions below.</p>
<p>If you're using the GNU compiler under cygwin, follow the Unix
directions in the next section. Otherwise if you have Microsoft's
Developer Studio installed, then from Windows Explorer double-click on
-"expat.dsp" in the lib directory and build and install in the usual
+"expat.vcxproj" in the lib directory and build and install in the usual
manner.</p>
<p>Alternatively, you may download the Win32 binary package that
@@ -360,7 +360,7 @@ off by default.</dd>
<dd>The number of input bytes of markup context which the parser will
ensure are available for reporting via <code><a href=
"#XML_GetInputContext" >XML_GetInputContext</a></code>. This is
-normally set to 1024, and must be set to a positive interger. If this
+normally set to 1024, and must be set to a positive integer. If this
is not defined, the input context will not be available and <code><a
href= "#XML_GetInputContext" >XML_GetInputContext</a></code> will
always report NULL. Without this, Expat has a smaller memory
@@ -373,7 +373,7 @@ the right MSVC magic annotations correct. This is ignored on other
platforms.</dd>
<dt>XML_ATTR_INFO</dt>
-<dd>If defined, makes the the additional function <code><a href=
+<dd>If defined, makes the additional function <code><a href=
"#XML_GetAttributeInfo" >XML_GetAttributeInfo</a></code> available
for reporting attribute byte offsets.</dd>
</dl>
@@ -739,7 +739,7 @@ arguments:</p>
<dt><code>XML_PARAM_ENTITY_PARSING_NEVER</code></dt>
<dd>Don't parse parameter entities or the external subset</dd>
<dt><code>XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE</code></dt>
-<dd>Parse parameter entites and the external subset unless
+<dd>Parse parameter entities and the external subset unless
<code>standalone</code> was set to "yes" in the XML declaration.</dd>
<dt><code>XML_PARAM_ENTITY_PARSING_ALWAYS</code></dt>
<dd>Always parse parameter entities and the external subset</dd>
@@ -767,7 +767,7 @@ include</p>
<li>Stopping parsing completely (simply free or reset the parser
instead of resuming in the outer parsing loop). This can be useful
- if a application-domain error is found in the XML being parsed or if
+ if an application-domain error is found in the XML being parsed or if
the result of the parse is determined not to be useful after
all.</li>
</ul>
@@ -1564,7 +1564,7 @@ at most once per parsed (external) entity. The optional application
data pointer <code>encodingHandlerData</code> will be passed back to
the handler.</p>
-<p>The map array contains information for every possible possible leading
+<p>The map array contains information for every possible leading
byte in a byte sequence. If the corresponding value is &gt;= 0, then it's
a single byte sequence and the byte encodes that Unicode value. If the
value is -1, then that byte is invalid as the initial byte in a sequence.
@@ -1999,7 +1999,7 @@ return NULL.</p>
<h3><a name="miscellaneous">Miscellaneous functions</a></h3>
<p>The functions in this section either obtain state information from
-the parser or can be used to dynamicly set parser options.</p>
+the parser or can be used to dynamically set parser options.</p>
<pre class="fcndec" id="XML_SetUserData">
void XMLCALL
diff --git a/doc/xmlwf.xml b/doc/xmlwf.xml
index 92ea8b5..5e2a4ae 100644
--- a/doc/xmlwf.xml
+++ b/doc/xmlwf.xml
@@ -58,6 +58,7 @@
<arg><option>-r</option></arg>
<arg><option>-t</option></arg>
+ <arg><option>-N</option></arg>
<arg><option>-v</option></arg>
@@ -146,7 +147,7 @@ supports both.
doesn't encounter any errors, the input file is simply copied to
the output directory unchanged.
This implies no namespaces (turns off <option>-n</option>) and
- requires <option>-d</option> to specify an output file.
+ requires <option>-d</option> to specify an output directory.
</para>
</listitem>
</varlistentry>
@@ -159,8 +160,8 @@ supports both.
representations of the input files.
By default, <option>-d</option> outputs a canonical representation
(described below).
- You can select different output formats using <option>-c</option>
- and <option>-m</option>.
+ You can select different output formats using <option>-c</option>,
+ <option>-m</option> and <option>-N</option>.
</para>
<para>
The output filenames will
@@ -220,6 +221,17 @@ supports both.
</varlistentry>
<varlistentry>
+ <term><option>-N</option></term>
+ <listitem>
+ <para>
+ Adds a doctype and notation declarations to canonical XML output.
+ This matches the example output used by the formal XML test cases.
+ Requires <option>-d</option> to specify an output file.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
<term><option>-p</option></term>
<listitem>
<para>
diff --git a/examples/.gitignore b/examples/.gitignore
new file mode 100644
index 0000000..88a4696
--- /dev/null
+++ b/examples/.gitignore
@@ -0,0 +1,8 @@
+Makefile
+elements
+elements.plg
+outline
+outline.plg
+Debug
+Release
+.libs
diff --git a/examples/Makefile.am b/examples/Makefile.am
new file mode 100644
index 0000000..99edf21
--- /dev/null
+++ b/examples/Makefile.am
@@ -0,0 +1,39 @@
+#
+# __ __ _
+# ___\ \/ /_ __ __ _| |_
+# / _ \\ /| '_ \ / _` | __|
+# | __// \| |_) | (_| | |_
+# \___/_/\_\ .__/ \__,_|\__|
+# |_| XML parser
+#
+# Copyright (c) 2017 Expat development team
+# Licensed under the MIT license:
+#
+# Permission is hereby granted, free of charge, to any person obtaining
+# a copy of this software and associated documentation files (the
+# "Software"), to deal in the Software without restriction, including
+# without limitation the rights to use, copy, modify, merge, publish,
+# distribute, sublicense, and/or sell copies of the Software, and to permit
+# persons to whom the Software is furnished to do so, subject to the
+# following conditions:
+#
+# The above copyright notice and this permission notice shall be included
+# in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+# NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+# DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+# OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+# USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+AM_CPPFLAGS = -I$(srcdir)/../lib
+
+noinst_PROGRAMS = elements outline
+
+elements_SOURCES = elements.c
+elements_LDADD = ../lib/libexpat.la
+
+outline_SOURCES = outline.c
+outline_LDADD = ../lib/libexpat.la
diff --git a/examples/elements.c b/examples/elements.c
index 0ca1abd..2f253f7 100644
--- a/examples/elements.c
+++ b/examples/elements.c
@@ -3,27 +3,59 @@
the name of each element to standard output indenting child
elements by one tab stop more than their parent element.
It must be used with Expat compiled for UTF-8 output.
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
#include <stdio.h>
-#include "expat.h"
-
-#if defined(__amigaos__) && defined(__USE_INLINE__)
-#include <proto/expat.h>
-#endif
+#include <expat.h>
#ifdef XML_LARGE_SIZE
-#if defined(XML_USE_MSC_EXTENSIONS) && _MSC_VER < 1400
-#define XML_FMT_INT_MOD "I64"
+# if defined(XML_USE_MSC_EXTENSIONS) && _MSC_VER < 1400
+# define XML_FMT_INT_MOD "I64"
+# else
+# define XML_FMT_INT_MOD "ll"
+# endif
#else
-#define XML_FMT_INT_MOD "ll"
+# define XML_FMT_INT_MOD "l"
#endif
+
+#ifdef XML_UNICODE_WCHAR_T
+# include <wchar.h>
+# define XML_FMT_STR "ls"
#else
-#define XML_FMT_INT_MOD "l"
+# define XML_FMT_STR "s"
#endif
static void XMLCALL
-startElement(void *userData, const char *name, const char **atts)
+startElement(void *userData, const XML_Char *name, const XML_Char **atts)
{
int i;
int *depthPtr = (int *)userData;
@@ -31,12 +63,12 @@ startElement(void *userData, const char *name, const char **atts)
for (i = 0; i < *depthPtr; i++)
putchar('\t');
- puts(name);
+ printf("%" XML_FMT_STR "\n", name);
*depthPtr += 1;
}
static void XMLCALL
-endElement(void *userData, const char *name)
+endElement(void *userData, const XML_Char *name)
{
int *depthPtr = (int *)userData;
(void)name;
@@ -61,7 +93,7 @@ main(int argc, char *argv[])
done = len < sizeof(buf);
if (XML_Parse(parser, buf, len, done) == XML_STATUS_ERROR) {
fprintf(stderr,
- "%s at line %" XML_FMT_INT_MOD "u\n",
+ "%" XML_FMT_STR " at line %" XML_FMT_INT_MOD "u\n",
XML_ErrorString(XML_GetErrorCode(parser)),
XML_GetCurrentLineNumber(parser));
return 1;
diff --git a/examples/elements.vcxproj b/examples/elements.vcxproj
new file mode 100644
index 0000000..dd3b948
--- /dev/null
+++ b/examples/elements.vcxproj
@@ -0,0 +1,140 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project DefaultTargets="Build" ToolsVersion="15.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+ <ItemGroup Label="ProjectConfigurations">
+ <ProjectConfiguration Include="Debug|Win32">
+ <Configuration>Debug</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Release|Win32">
+ <Configuration>Release</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ </ItemGroup>
+ <PropertyGroup Label="Globals">
+ <SccProjectName />
+ <SccLocalPath />
+ <ProjectGuid>{35262250-C85F-463A-9F6D-670088BFA17E}</ProjectGuid>
+ <WindowsTargetPlatformVersion>10.0.16299.0</WindowsTargetPlatformVersion>
+ </PropertyGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
+ <ConfigurationType>Application</ConfigurationType>
+ <PlatformToolset>v141</PlatformToolset>
+ <UseOfMfc>false</UseOfMfc>
+ <CharacterSet>MultiByte</CharacterSet>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
+ <ConfigurationType>Application</ConfigurationType>
+ <PlatformToolset>v141</PlatformToolset>
+ <UseOfMfc>false</UseOfMfc>
+ <CharacterSet>MultiByte</CharacterSet>
+ </PropertyGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
+ <ImportGroup Label="ExtensionSettings">
+ </ImportGroup>
+ <ImportGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="PropertySheets">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ <Import Project="$(VCTargetsPath)Microsoft.Cpp.UpgradeFromVC60.props" />
+ </ImportGroup>
+ <ImportGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="PropertySheets">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ <Import Project="$(VCTargetsPath)Microsoft.Cpp.UpgradeFromVC60.props" />
+ </ImportGroup>
+ <PropertyGroup Label="UserMacros" />
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+ <OutDir>.\..\win32\bin\Release\</OutDir>
+ <IntDir>.\..\win32\tmp\Release-elements\</IntDir>
+ <LinkIncremental>false</LinkIncremental>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ <OutDir>.\..\win32\bin\Debug\</OutDir>
+ <IntDir>.\..\win32\tmp\Debug-elements\</IntDir>
+ <LinkIncremental>true</LinkIncremental>
+ </PropertyGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+ <ClCompile>
+ <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
+ <InlineFunctionExpansion>Default</InlineFunctionExpansion>
+ <StringPooling>true</StringPooling>
+ <FunctionLevelLinking>true</FunctionLevelLinking>
+ <Optimization>MaxSpeed</Optimization>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <WarningLevel>Level3</WarningLevel>
+ <IgnoreStandardIncludePath>false</IgnoreStandardIncludePath>
+ <AdditionalIncludeDirectories>..\lib;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
+ <PreprocessorDefinitions>NDEBUG;_CONSOLE;XML_STATIC;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <AssemblerListingLocation>.\..\win32\tmp\Release-elements\</AssemblerListingLocation>
+ <PrecompiledHeaderOutputFile>.\..\win32\tmp\Release-elements\elements.pch</PrecompiledHeaderOutputFile>
+ <ObjectFileName>.\..\win32\tmp\Release-elements\</ObjectFileName>
+ <ProgramDataBaseFileName>.\..\win32\tmp\Release-elements\</ProgramDataBaseFileName>
+ </ClCompile>
+ <Midl>
+ <TypeLibraryName>.\..\win32\bin\Release\elements.tlb</TypeLibraryName>
+ </Midl>
+ <ResourceCompile>
+ <Culture>0x0409</Culture>
+ <PreprocessorDefinitions>NDEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ </ResourceCompile>
+ <Bscmake>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <OutputFile>.\..\win32\bin\Release\elements.bsc</OutputFile>
+ </Bscmake>
+ <Link>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <SubSystem>Console</SubSystem>
+ <OutputFile>..\win32\bin\Release\elements.exe</OutputFile>
+ <AdditionalLibraryDirectories>..\win32\bin\Release;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
+ <AdditionalDependencies>libexpatMT.lib;%(AdditionalDependencies)</AdditionalDependencies>
+ </Link>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ <ClCompile>
+ <RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
+ <InlineFunctionExpansion>Default</InlineFunctionExpansion>
+ <FunctionLevelLinking>true</FunctionLevelLinking>
+ <Optimization>Disabled</Optimization>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <WarningLevel>Level3</WarningLevel>
+ <DebugInformationFormat>EditAndContinue</DebugInformationFormat>
+ <AdditionalIncludeDirectories>..\lib;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
+ <PreprocessorDefinitions>_DEBUG;_CONSOLE;XML_STATIC;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <AssemblerListingLocation>.\..\win32\tmp\Debug-elements\</AssemblerListingLocation>
+ <BrowseInformation>true</BrowseInformation>
+ <PrecompiledHeaderOutputFile>.\..\win32\tmp\Debug-elements\elements.pch</PrecompiledHeaderOutputFile>
+ <ObjectFileName>.\..\win32\tmp\Debug-elements\</ObjectFileName>
+ <ProgramDataBaseFileName>.\..\win32\tmp\Debug-elements\</ProgramDataBaseFileName>
+ <BasicRuntimeChecks>EnableFastChecks</BasicRuntimeChecks>
+ </ClCompile>
+ <Midl>
+ <TypeLibraryName>.\..\win32\bin\Debug\elements.tlb</TypeLibraryName>
+ </Midl>
+ <ResourceCompile>
+ <Culture>0x0409</Culture>
+ <PreprocessorDefinitions>_DEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ </ResourceCompile>
+ <Bscmake>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <OutputFile>.\..\win32\bin\Debug\elements.bsc</OutputFile>
+ </Bscmake>
+ <Link>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <GenerateDebugInformation>true</GenerateDebugInformation>
+ <SubSystem>Console</SubSystem>
+ <OutputFile>..\win32\bin\Debug\elements.exe</OutputFile>
+ <AdditionalLibraryDirectories>..\win32\bin\Debug;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
+ <AdditionalDependencies>libexpatMT.lib;%(AdditionalDependencies)</AdditionalDependencies>
+ </Link>
+ </ItemDefinitionGroup>
+ <ItemGroup>
+ <ClCompile Include="elements.c" />
+ </ItemGroup>
+ <ItemGroup>
+ <ProjectReference Include="..\lib\expat_static.vcxproj">
+ <Project>{58a821bc-e4af-4df4-9a54-2baa22b92615}</Project>
+ <ReferenceOutputAssembly>false</ReferenceOutputAssembly>
+ </ProjectReference>
+ </ItemGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
+ <ImportGroup Label="ExtensionTargets">
+ </ImportGroup>
+</Project> \ No newline at end of file
diff --git a/examples/elements.vcxproj.filters b/examples/elements.vcxproj.filters
new file mode 100644
index 0000000..ab374c1
--- /dev/null
+++ b/examples/elements.vcxproj.filters
@@ -0,0 +1,22 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+ <ItemGroup>
+ <Filter Include="Source Files">
+ <UniqueIdentifier>{95d10a62-f554-4b10-a08b-cc74ba9fe102}</UniqueIdentifier>
+ <Extensions>cpp;c;cxx;rc;def;r;odl;idl;hpj;bat</Extensions>
+ </Filter>
+ <Filter Include="Header Files">
+ <UniqueIdentifier>{21ef9308-545b-4d8d-8bde-012f925efa3a}</UniqueIdentifier>
+ <Extensions>h;hpp;hxx;hm;inl</Extensions>
+ </Filter>
+ <Filter Include="Resource Files">
+ <UniqueIdentifier>{ddac4f51-12d6-4e8f-817c-12c85eb1ffd2}</UniqueIdentifier>
+ <Extensions>ico;cur;bmp;dlg;rc2;rct;bin;rgs;gif;jpg;jpeg;jpe</Extensions>
+ </Filter>
+ </ItemGroup>
+ <ItemGroup>
+ <ClCompile Include="elements.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ </ItemGroup>
+</Project> \ No newline at end of file
diff --git a/examples/outline.c b/examples/outline.c
index d9b0917..3e0bbaa 100644
--- a/examples/outline.c
+++ b/examples/outline.c
@@ -1,42 +1,54 @@
-/*****************************************************************
- * outline.c
- *
- * Copyright 1999, Clark Cooper
- * All rights reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the license contained in the
- * COPYING file that comes with the expat distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
- * IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
- * CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
- * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
- * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
- *
- * Read an XML document from standard input and print an element
- * outline on standard output.
- * Must be used with Expat compiled for UTF-8 output.
- */
-
+/* Read an XML document from standard input and print an element
+ outline on standard output.
+ Must be used with Expat compiled for UTF-8 output.
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
#include <stdio.h>
#include <expat.h>
-#if defined(__amigaos__) && defined(__USE_INLINE__)
-#include <proto/expat.h>
-#endif
-
#ifdef XML_LARGE_SIZE
-#if defined(XML_USE_MSC_EXTENSIONS) && _MSC_VER < 1400
-#define XML_FMT_INT_MOD "I64"
+# if defined(XML_USE_MSC_EXTENSIONS) && _MSC_VER < 1400
+# define XML_FMT_INT_MOD "I64"
+# else
+# define XML_FMT_INT_MOD "ll"
+# endif
#else
-#define XML_FMT_INT_MOD "ll"
+# define XML_FMT_INT_MOD "l"
#endif
+
+#ifdef XML_UNICODE_WCHAR_T
+# define XML_FMT_STR "ls"
#else
-#define XML_FMT_INT_MOD "l"
+# define XML_FMT_STR "s"
#endif
#define BUFFSIZE 8192
@@ -46,7 +58,7 @@ char Buff[BUFFSIZE];
int Depth;
static void XMLCALL
-start(void *data, const char *el, const char **attr)
+start(void *data, const XML_Char *el, const XML_Char **attr)
{
int i;
(void)data;
@@ -54,10 +66,10 @@ start(void *data, const char *el, const char **attr)
for (i = 0; i < Depth; i++)
printf(" ");
- printf("%s", el);
+ printf("%" XML_FMT_STR, el);
for (i = 0; attr[i]; i += 2) {
- printf(" %s='%s'", attr[i], attr[i + 1]);
+ printf(" %" XML_FMT_STR "='%" XML_FMT_STR "'", attr[i], attr[i + 1]);
}
printf("\n");
@@ -65,7 +77,7 @@ start(void *data, const char *el, const char **attr)
}
static void XMLCALL
-end(void *data, const char *el)
+end(void *data, const XML_Char *el)
{
(void)data;
(void)el;
@@ -99,7 +111,8 @@ main(int argc, char *argv[])
done = feof(stdin);
if (XML_Parse(p, Buff, len, done) == XML_STATUS_ERROR) {
- fprintf(stderr, "Parse error at line %" XML_FMT_INT_MOD "u:\n%s\n",
+ fprintf(stderr,
+ "Parse error at line %" XML_FMT_INT_MOD "u:\n%" XML_FMT_STR "\n",
XML_GetCurrentLineNumber(p),
XML_ErrorString(XML_GetErrorCode(p)));
exit(-1);
diff --git a/examples/outline.vcxproj b/examples/outline.vcxproj
new file mode 100644
index 0000000..31d6ef1
--- /dev/null
+++ b/examples/outline.vcxproj
@@ -0,0 +1,151 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project DefaultTargets="Build" ToolsVersion="15.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+ <ItemGroup Label="ProjectConfigurations">
+ <ProjectConfiguration Include="Debug|Win32">
+ <Configuration>Debug</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Release|Win32">
+ <Configuration>Release</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Template|Win32">
+ <Configuration>Template</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ </ItemGroup>
+ <PropertyGroup Label="Globals">
+ <SccProjectName />
+ <SccLocalPath />
+ <ProjectGuid>{DE74E6FD-E107-4326-B1B0-A0CFEEB64F25}</ProjectGuid>
+ <WindowsTargetPlatformVersion>10.0.16299.0</WindowsTargetPlatformVersion>
+ </PropertyGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Template|Win32'" Label="Configuration">
+ <ConfigurationType>Application</ConfigurationType>
+ <PlatformToolset>v141</PlatformToolset>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
+ <ConfigurationType>Application</ConfigurationType>
+ <PlatformToolset>v141</PlatformToolset>
+ <UseOfMfc>false</UseOfMfc>
+ <CharacterSet>MultiByte</CharacterSet>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
+ <ConfigurationType>Application</ConfigurationType>
+ <PlatformToolset>v141</PlatformToolset>
+ <UseOfMfc>false</UseOfMfc>
+ <CharacterSet>MultiByte</CharacterSet>
+ </PropertyGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
+ <ImportGroup Label="ExtensionSettings">
+ </ImportGroup>
+ <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Template|Win32'">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ </ImportGroup>
+ <ImportGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="PropertySheets">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ <Import Project="$(VCTargetsPath)Microsoft.Cpp.UpgradeFromVC60.props" />
+ </ImportGroup>
+ <ImportGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="PropertySheets">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ <Import Project="$(VCTargetsPath)Microsoft.Cpp.UpgradeFromVC60.props" />
+ </ImportGroup>
+ <PropertyGroup Label="UserMacros" />
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ <OutDir>.\..\win32\bin\Debug\</OutDir>
+ <IntDir>.\..\win32\tmp\Debug-outline\</IntDir>
+ <LinkIncremental>true</LinkIncremental>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+ <OutDir>.\..\win32\bin\Release\</OutDir>
+ <IntDir>.\..\win32\tmp\Release-outline\</IntDir>
+ <LinkIncremental>false</LinkIncremental>
+ </PropertyGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ <ClCompile>
+ <RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
+ <InlineFunctionExpansion>Default</InlineFunctionExpansion>
+ <FunctionLevelLinking>true</FunctionLevelLinking>
+ <Optimization>Disabled</Optimization>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <WarningLevel>Level3</WarningLevel>
+ <MinimalRebuild>true</MinimalRebuild>
+ <DebugInformationFormat>EditAndContinue</DebugInformationFormat>
+ <AdditionalIncludeDirectories>..\lib;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
+ <PreprocessorDefinitions>_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <AssemblerListingLocation>.\..\win32\tmp\Debug-outline\</AssemblerListingLocation>
+ <PrecompiledHeaderOutputFile>.\..\win32\tmp\Debug-outline\outline.pch</PrecompiledHeaderOutputFile>
+ <ObjectFileName>.\..\win32\tmp\Debug-outline\</ObjectFileName>
+ <ProgramDataBaseFileName>.\..\win32\tmp\Debug-outline\</ProgramDataBaseFileName>
+ <BasicRuntimeChecks>EnableFastChecks</BasicRuntimeChecks>
+ </ClCompile>
+ <Midl>
+ <TypeLibraryName>.\..\win32\bin\Debug\outline.tlb</TypeLibraryName>
+ </Midl>
+ <ResourceCompile>
+ <Culture>0x0409</Culture>
+ <PreprocessorDefinitions>_DEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ </ResourceCompile>
+ <Bscmake>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <OutputFile>.\..\win32\bin\Debug\outline.bsc</OutputFile>
+ </Bscmake>
+ <Link>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <GenerateDebugInformation>true</GenerateDebugInformation>
+ <SubSystem>Console</SubSystem>
+ <OutputFile>..\win32\bin\Debug\outline.exe</OutputFile>
+ <AdditionalLibraryDirectories>..\win32\bin\Debug;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
+ <AdditionalDependencies>libexpat.lib;%(AdditionalDependencies)</AdditionalDependencies>
+ </Link>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+ <ClCompile>
+ <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
+ <InlineFunctionExpansion>Default</InlineFunctionExpansion>
+ <StringPooling>true</StringPooling>
+ <FunctionLevelLinking>true</FunctionLevelLinking>
+ <Optimization>MaxSpeed</Optimization>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <WarningLevel>Level3</WarningLevel>
+ <IgnoreStandardIncludePath>false</IgnoreStandardIncludePath>
+ <AdditionalIncludeDirectories>..\lib;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
+ <PreprocessorDefinitions>NDEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <AssemblerListingLocation>.\..\win32\tmp\Release-outline\</AssemblerListingLocation>
+ <PrecompiledHeaderOutputFile>.\..\win32\tmp\Release-outline\outline.pch</PrecompiledHeaderOutputFile>
+ <ObjectFileName>.\..\win32\tmp\Release-outline\</ObjectFileName>
+ <ProgramDataBaseFileName>.\..\win32\tmp\Release-outline\</ProgramDataBaseFileName>
+ </ClCompile>
+ <Midl>
+ <TypeLibraryName>.\..\win32\bin\Release\outline.tlb</TypeLibraryName>
+ </Midl>
+ <ResourceCompile>
+ <Culture>0x0409</Culture>
+ <PreprocessorDefinitions>NDEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ </ResourceCompile>
+ <Bscmake>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <OutputFile>.\..\win32\bin\Release\outline.bsc</OutputFile>
+ </Bscmake>
+ <Link>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <SubSystem>Console</SubSystem>
+ <OutputFile>..\win32\bin\Release\outline.exe</OutputFile>
+ <AdditionalLibraryDirectories>..\win32\bin\Release;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
+ <AdditionalDependencies>libexpat.lib;%(AdditionalDependencies)</AdditionalDependencies>
+ </Link>
+ </ItemDefinitionGroup>
+ <ItemGroup>
+ <ClCompile Include="outline.c" />
+ </ItemGroup>
+ <ItemGroup>
+ <ProjectReference Include="..\lib\expat.vcxproj">
+ <Project>{45a5074d-66e8-44a4-a03f-018027b528d6}</Project>
+ <ReferenceOutputAssembly>false</ReferenceOutputAssembly>
+ </ProjectReference>
+ </ItemGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
+ <ImportGroup Label="ExtensionTargets">
+ </ImportGroup>
+</Project> \ No newline at end of file
diff --git a/examples/outline.vcxproj.filters b/examples/outline.vcxproj.filters
new file mode 100644
index 0000000..0c23f35
--- /dev/null
+++ b/examples/outline.vcxproj.filters
@@ -0,0 +1,22 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+ <ItemGroup>
+ <Filter Include="Source Files">
+ <UniqueIdentifier>{48092a1f-486d-4bd8-a9ea-d087423ab371}</UniqueIdentifier>
+ <Extensions>cpp;c;cxx;rc;def;r;odl;idl;hpj;bat</Extensions>
+ </Filter>
+ <Filter Include="Header Files">
+ <UniqueIdentifier>{d9494f7e-987c-467b-a3e0-ea577aea229d}</UniqueIdentifier>
+ <Extensions>h;hpp;hxx;hm;inl</Extensions>
+ </Filter>
+ <Filter Include="Resource Files">
+ <UniqueIdentifier>{7e3cfca9-158f-4e78-be6c-02d599fd9254}</UniqueIdentifier>
+ <Extensions>ico;cur;bmp;dlg;rc2;rct;bin;rgs;gif;jpg;jpeg;jpe</Extensions>
+ </Filter>
+ </ItemGroup>
+ <ItemGroup>
+ <ClCompile Include="outline.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ </ItemGroup>
+</Project> \ No newline at end of file
diff --git a/expat.pc.in b/expat.pc.in
new file mode 100644
index 0000000..5207e3e
--- /dev/null
+++ b/expat.pc.in
@@ -0,0 +1,11 @@
+prefix=@prefix@
+exec_prefix=@exec_prefix@
+libdir=@libdir@
+includedir=@includedir@
+
+Name: expat
+Version: @PACKAGE_VERSION@
+Description: expat XML parser
+URL: http://www.libexpat.org
+Libs: -L${libdir} -lexpat
+Cflags: -I${includedir}
diff --git a/expat.sln b/expat.sln
new file mode 100644
index 0000000..d1c4efc
--- /dev/null
+++ b/expat.sln
@@ -0,0 +1,73 @@
+
+Microsoft Visual Studio Solution File, Format Version 12.00
+# Visual Studio 2013
+VisualStudioVersion = 12.0.40629.0
+MinimumVisualStudioVersion = 10.0.40219.1
+Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "elements", "examples\elements.vcxproj", "{35262250-C85F-463A-9F6D-670088BFA17E}"
+EndProject
+Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "expat", "lib\expat.vcxproj", "{45A5074D-66E8-44A4-A03F-018027B528D6}"
+EndProject
+Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "expat_static", "lib\expat_static.vcxproj", "{58A821BC-E4AF-4DF4-9A54-2BAA22B92615}"
+EndProject
+Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "expatw", "lib\expatw.vcxproj", "{C04F1C11-7079-48AD-A90B-6F59B7A55BEF}"
+EndProject
+Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "expatw_static", "lib\expatw_static.vcxproj", "{9220B0F2-C895-4CB2-91D1-1C16C4ECB759}"
+EndProject
+Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "outline", "examples\outline.vcxproj", "{DE74E6FD-E107-4326-B1B0-A0CFEEB64F25}"
+EndProject
+Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "xmlwf", "xmlwf\xmlwf.vcxproj", "{E3C5991F-5238-4168-A179-275D1AC98D7E}"
+EndProject
+Global
+ GlobalSection(SolutionConfigurationPlatforms) = preSolution
+ Debug|Win32 = Debug|Win32
+ Release|Win32 = Release|Win32
+ Template|Win32 = Template|Win32
+ EndGlobalSection
+ GlobalSection(ProjectConfigurationPlatforms) = postSolution
+ {35262250-C85F-463A-9F6D-670088BFA17E}.Debug|Win32.ActiveCfg = Debug|Win32
+ {35262250-C85F-463A-9F6D-670088BFA17E}.Debug|Win32.Build.0 = Debug|Win32
+ {35262250-C85F-463A-9F6D-670088BFA17E}.Release|Win32.ActiveCfg = Release|Win32
+ {35262250-C85F-463A-9F6D-670088BFA17E}.Release|Win32.Build.0 = Release|Win32
+ {35262250-C85F-463A-9F6D-670088BFA17E}.Template|Win32.ActiveCfg = Release|Win32
+ {35262250-C85F-463A-9F6D-670088BFA17E}.Template|Win32.Build.0 = Release|Win32
+ {45A5074D-66E8-44A4-A03F-018027B528D6}.Debug|Win32.ActiveCfg = Debug|Win32
+ {45A5074D-66E8-44A4-A03F-018027B528D6}.Debug|Win32.Build.0 = Debug|Win32
+ {45A5074D-66E8-44A4-A03F-018027B528D6}.Release|Win32.ActiveCfg = Release|Win32
+ {45A5074D-66E8-44A4-A03F-018027B528D6}.Release|Win32.Build.0 = Release|Win32
+ {45A5074D-66E8-44A4-A03F-018027B528D6}.Template|Win32.ActiveCfg = Template|Win32
+ {45A5074D-66E8-44A4-A03F-018027B528D6}.Template|Win32.Build.0 = Template|Win32
+ {58A821BC-E4AF-4DF4-9A54-2BAA22B92615}.Debug|Win32.ActiveCfg = Debug|Win32
+ {58A821BC-E4AF-4DF4-9A54-2BAA22B92615}.Debug|Win32.Build.0 = Debug|Win32
+ {58A821BC-E4AF-4DF4-9A54-2BAA22B92615}.Release|Win32.ActiveCfg = Release|Win32
+ {58A821BC-E4AF-4DF4-9A54-2BAA22B92615}.Release|Win32.Build.0 = Release|Win32
+ {58A821BC-E4AF-4DF4-9A54-2BAA22B92615}.Template|Win32.ActiveCfg = Template|Win32
+ {58A821BC-E4AF-4DF4-9A54-2BAA22B92615}.Template|Win32.Build.0 = Template|Win32
+ {C04F1C11-7079-48AD-A90B-6F59B7A55BEF}.Debug|Win32.ActiveCfg = Debug|Win32
+ {C04F1C11-7079-48AD-A90B-6F59B7A55BEF}.Debug|Win32.Build.0 = Debug|Win32
+ {C04F1C11-7079-48AD-A90B-6F59B7A55BEF}.Release|Win32.ActiveCfg = Release|Win32
+ {C04F1C11-7079-48AD-A90B-6F59B7A55BEF}.Release|Win32.Build.0 = Release|Win32
+ {C04F1C11-7079-48AD-A90B-6F59B7A55BEF}.Template|Win32.ActiveCfg = Template|Win32
+ {C04F1C11-7079-48AD-A90B-6F59B7A55BEF}.Template|Win32.Build.0 = Template|Win32
+ {9220B0F2-C895-4CB2-91D1-1C16C4ECB759}.Debug|Win32.ActiveCfg = Debug|Win32
+ {9220B0F2-C895-4CB2-91D1-1C16C4ECB759}.Debug|Win32.Build.0 = Debug|Win32
+ {9220B0F2-C895-4CB2-91D1-1C16C4ECB759}.Release|Win32.ActiveCfg = Release|Win32
+ {9220B0F2-C895-4CB2-91D1-1C16C4ECB759}.Release|Win32.Build.0 = Release|Win32
+ {9220B0F2-C895-4CB2-91D1-1C16C4ECB759}.Template|Win32.ActiveCfg = Template|Win32
+ {9220B0F2-C895-4CB2-91D1-1C16C4ECB759}.Template|Win32.Build.0 = Template|Win32
+ {DE74E6FD-E107-4326-B1B0-A0CFEEB64F25}.Debug|Win32.ActiveCfg = Debug|Win32
+ {DE74E6FD-E107-4326-B1B0-A0CFEEB64F25}.Debug|Win32.Build.0 = Debug|Win32
+ {DE74E6FD-E107-4326-B1B0-A0CFEEB64F25}.Release|Win32.ActiveCfg = Release|Win32
+ {DE74E6FD-E107-4326-B1B0-A0CFEEB64F25}.Release|Win32.Build.0 = Release|Win32
+ {DE74E6FD-E107-4326-B1B0-A0CFEEB64F25}.Template|Win32.ActiveCfg = Template|Win32
+ {DE74E6FD-E107-4326-B1B0-A0CFEEB64F25}.Template|Win32.Build.0 = Template|Win32
+ {E3C5991F-5238-4168-A179-275D1AC98D7E}.Debug|Win32.ActiveCfg = Debug|Win32
+ {E3C5991F-5238-4168-A179-275D1AC98D7E}.Debug|Win32.Build.0 = Debug|Win32
+ {E3C5991F-5238-4168-A179-275D1AC98D7E}.Release|Win32.ActiveCfg = Release|Win32
+ {E3C5991F-5238-4168-A179-275D1AC98D7E}.Release|Win32.Build.0 = Release|Win32
+ {E3C5991F-5238-4168-A179-275D1AC98D7E}.Template|Win32.ActiveCfg = Template|Win32
+ {E3C5991F-5238-4168-A179-275D1AC98D7E}.Template|Win32.Build.0 = Template|Win32
+ EndGlobalSection
+ GlobalSection(SolutionProperties) = preSolution
+ HideSolutionNode = FALSE
+ EndGlobalSection
+EndGlobal
diff --git a/expat.spec b/expat.spec
new file mode 100644
index 0000000..cd4f4dc
--- /dev/null
+++ b/expat.spec
@@ -0,0 +1,131 @@
+%define version 2.2.5
+%define release 1
+
+Summary: Expat is an XML 1.0 parser written in C.
+Name: expat
+Version: %{version}
+Release: %{release}
+License: MIT/X
+Group: Utilities/parsers
+URL: http://www.libexpat.org/
+Source: https://downloads.sourceforge.net/project/expat/expat/%{version}/expat-%{version}.tar.bz2
+BuildRoot: /var/tmp/%{name}-buildroot
+
+%description
+Expat is an XML 1.0 parser written in C by James Clark. It aims to be
+fully conforming. It is not a validating XML parser.
+
+%prep
+%setup
+
+%build
+./configure
+make lib xmlwf
+
+%install
+rm -rf $RPM_BUILD_ROOT
+mkdir -p $RPM_BUILD_ROOT/usr/bin
+mkdir -p $RPM_BUILD_ROOT/usr/lib
+mkdir -p $RPM_BUILD_ROOT/usr/include
+make install DESTDIR=$RPM_BUILD_ROOT prefix=/usr
+install -D xmlwf/xmlwf $RPM_BUILD_ROOT/usr/bin/xmlwf
+
+%files
+%doc COPYING README.md doc/reference.html doc/style.css doc/*.png
+/usr/bin/xmlwf
+/usr/lib
+/usr/include/expat.h
+/usr/include/expat_config.h
+/usr/include/expat_external.h
+/usr/share/doc/expat/AUTHORS
+/usr/share/doc/expat/changelog
+/usr/share/man/man1/xmlwf.1.gz
+
+%changelog
+* Tue Oct 31 2017 Sebastian Pipping <sebastian@pipping.org>
+[Release 2.2.5-1]
+- Update for the 2.2.5 release.
+
+* Sat Aug 19 2017 Sebastian Pipping <sebastian@pipping.org>
+[Release 2.2.4-1]
+- Update for the 2.2.4 release.
+
+* Wed Aug 2 2017 Sebastian Pipping <sebastian@pipping.org>
+[Release 2.2.3-1]
+- Update for the 2.2.3 release.
+
+* Wed Jul 12 2017 Sebastian Pipping <sebastian@pipping.org>
+[Release 2.2.2-1]
+- Update for the 2.2.2 release.
+
+* Sat Jun 17 2017 Sebastian Pipping <sebastian@pipping.org>
+[Release 2.2.1-1]
+- Update for the 2.2.1 release.
+
+* Tue Jun 21 2016 Sebastian Pipping <sebastian@pipping.org>
+[Release 2.2.0-1]
+- Update for the 2.2.0 release.
+
+* Wed Mar 2 2016 Sebastian Pipping <sebastian@pipping.org>
+[Release 2.1.1-1]
+- Update for the 2.1.1 release.
+
+* Sat Mar 3 2012 Karl Waclawek <karl@waclawek.net>
+[Release 2.1.0-1]
+- Update for the 2.1.0 release.
+
+* Sun Nov 26 2006 Karl Waclawek <karl@waclawek.net>
+[Release 2.0.1-1]
+- Update for the 2.0.1 release.
+
+* Fri Jul 16 2004 Fred L. Drake, Jr. <fdrake@acm.org>
+[Release 1.95.8-1]
+- Update for the 1.95.8 release.
+- Add the expat_external.h header to the installed files.
+
+* Tue Oct 21 2003 Fred L. Drake, Jr. <fdrake@acm.org>
+- Update list of documentation files; we missed a .png file in the
+ previous release.
+
+* Mon Oct 20 2003 Fred L. Drake, Jr. <fdrake@acm.org>
+[Release 1.95.7-1]
+- Updated for the 1.95.7 release.
+
+* Sat Jan 25 2003 Fred L. Drake, Jr. <fdrake@acm.org>
+[Release 1.95.6-1]
+- Updated for the 1.95.6 release.
+
+* Wed Sep 4 2002 Fred L. Drake, Jr. <fdrake@acm.org>
+[Release 1.95.5-1]
+- Updated for the 1.95.5 release.
+- Updated URL for Expat home page to point to www.libexpat.org.
+- Added "Valid XHTML 1.0" icon to the installed documentation.
+
+* Sat Jun 29 2002 Fred L. Drake, Jr. <fdrake@acm.org>
+[Release 1.95.4-1]
+- Updated for the 1.95.4 release.
+
+* Fri May 17 2002 Fred L. Drake, Jr. <fdrake@acm.org>
+[Release 1.95.3-1]
+- Updated for the 1.95.3 release.
+- Added xmlwf man page to the list of files.
+
+* Wed Jul 25 2001 Fred L. Drake, Jr. <fdrake@acm.org>
+[Release 1.95.2-1]
+- Updated for the 1.95.2 release.
+
+* Sun Feb 18 2001 Sean Reifschneider <jafo-rpms@tummy.com>
+[Release 1.95.1-1tummy]
+- Updated to 1.95.1 release.
+- Removed the "/usr/include/expat" directory for headers, as it now uses
+ "expat.h" instead of "xmlparser.h".
+
+* Thu Jan 25 2001 Sean Reifschneider <jafo-rpms@tummy.com>
+[Release 1.1-3tummy]
+- Moved xmlparse.h into "/usr/include/expat" directory to prevent conflict
+ with w3c-libwww-devel package.
+
+* Wed Sep 6 2000 Sean Reifschneider <jafo-rpms@tummy.com>
+- Modified to install into /usr.
+- Modified to use RPM_BUILD_ROOT instead of writing directly to install
+ location.
diff --git a/expat_config.h b/expat_config.h
index 724f47f..aa2ea98 100644
--- a/expat_config.h
+++ b/expat_config.h
@@ -1,9 +1,19 @@
/* expat_config.h. Generated from expat_config.h.in by configure. */
-/* expat_config.h.in. Generated from configure.in by autoheader. */
+/* expat_config.h.in. Generated from configure.ac by autoheader. */
/* 1234 = LIL_ENDIAN, 4321 = BIGENDIAN */
#define BYTEORDER 1234
+/* Define to 1 if you have the `arc4random' function. */
+#if defined(__APPLE__) || defined(__BIONIC__)
+#define HAVE_ARC4RANDOM 1
+#endif
+
+/* Define to 1 if you have the `arc4random_buf' function. */
+#if defined(__APPLE__) || defined(__BIONIC__)
+#define HAVE_ARC4RANDOM_BUF 1
+#endif
+
/* Define to 1 if you have the `bcopy' function. */
#define HAVE_BCOPY 1
@@ -16,9 +26,17 @@
/* Define to 1 if you have the `getpagesize' function. */
#define HAVE_GETPAGESIZE 1
+/* Define to 1 if you have the `getrandom' function. */
+#if defined(__BIONIC__)
+#define HAVE_GETRANDOM 1
+#endif
+
/* Define to 1 if you have the <inttypes.h> header file. */
#define HAVE_INTTYPES_H 1
+/* Define to 1 if you have the `bsd' library (-lbsd). */
+/* #undef HAVE_LIBBSD */
+
/* Define to 1 if you have the `memmove' function. */
#define HAVE_MEMMOVE 1
@@ -40,6 +58,11 @@
/* Define to 1 if you have the <string.h> header file. */
#define HAVE_STRING_H 1
+/* Define to 1 if you have `syscall' and `SYS_getrandom'. */
+#if defined(__BIONIC__)
+#define HAVE_SYSCALL_GETRANDOM 1
+#endif
+
/* Define to 1 if you have the <sys/param.h> header file. */
#define HAVE_SYS_PARAM_H 1
@@ -52,10 +75,12 @@
/* Define to 1 if you have the <unistd.h> header file. */
#define HAVE_UNISTD_H 1
-/* Define to the sub-directory in which libtool stores uninstalled libraries.
- */
+/* Define to the sub-directory where libtool stores uninstalled libraries. */
#define LT_OBJDIR ".libs/"
+/* Name of package */
+#define PACKAGE "expat"
+
/* Define to the address where bug reports for this package should be sent. */
#define PACKAGE_BUGREPORT "expat-bugs@libexpat.org"
@@ -63,7 +88,7 @@
#define PACKAGE_NAME "expat"
/* Define to the full name and version of this package. */
-#define PACKAGE_STRING "expat 2.1.0"
+#define PACKAGE_STRING "expat 2.2.5"
/* Define to the one symbol short name of this package. */
#define PACKAGE_TARNAME "expat"
@@ -72,11 +97,14 @@
#define PACKAGE_URL ""
/* Define to the version of this package. */
-#define PACKAGE_VERSION "2.1.0"
+#define PACKAGE_VERSION "2.2.5"
/* Define to 1 if you have the ANSI C header files. */
#define STDC_HEADERS 1
+/* Version number of package */
+#define VERSION "2.2.5"
+
/* whether byteorder is bigendian */
/* #undef WORDS_BIGENDIAN */
@@ -84,15 +112,17 @@
point. */
#define XML_CONTEXT_BYTES 1024
+/* Define to include code reading entropy from `/dev/urandom'. */
+#if defined(__GLIBC__)
+#define XML_DEV_URANDOM 1
+#endif
+
/* Define to make parameter entity parsing functionality available. */
#define XML_DTD 1
/* Define to make XML Namespaces functionality available. */
#define XML_NS 1
-/* Define to __FUNCTION__ or "" if `__func__' does not conform to ANSI C. */
-/* #undef __func__ */
-
/* Define to empty if `const' does not conform to ANSI C. */
/* #undef const */
diff --git a/expat_config.h.cmake b/expat_config.h.cmake
new file mode 100644
index 0000000..a93c971
--- /dev/null
+++ b/expat_config.h.cmake
@@ -0,0 +1,106 @@
+/* expat_config.h.cmake. Based upon generated expat_config.h.in. */
+
+/* 1234 = LIL_ENDIAN, 4321 = BIGENDIAN */
+#cmakedefine BYTEORDER @BYTEORDER@
+
+/* Define to 1 if you have the `arc4random' function. */
+#cmakedefine HAVE_ARC4RANDOM
+
+/* Define to 1 if you have the `arc4random_buf' function. */
+#cmakedefine HAVE_ARC4RANDOM_BUF
+
+/* Define to 1 if you have the `bcopy' function. */
+#cmakedefine HAVE_BCOPY
+
+/* Define to 1 if you have the <dlfcn.h> header file. */
+#cmakedefine HAVE_DLFCN_H
+
+/* Define to 1 if you have the <fcntl.h> header file. */
+#cmakedefine HAVE_FCNTL_H
+
+/* Define to 1 if you have the `getpagesize' function. */
+#cmakedefine HAVE_GETPAGESIZE
+
+/* Define to 1 if you have the `getrandom' function. */
+#cmakedefine HAVE_GETRANDOM
+
+/* Define to 1 if you have the <inttypes.h> header file. */
+#cmakedefine HAVE_INTTYPES_H
+
+/* Define to 1 if you have the `bsd' library (-lbsd). */
+#cmakedefine HAVE_LIBBSD
+
+/* Define to 1 if you have the `memmove' function. */
+#cmakedefine HAVE_MEMMOVE
+
+/* Define to 1 if you have the <memory.h> header file. */
+#cmakedefine HAVE_MEMORY_H
+
+/* Define to 1 if you have a working `mmap' system call. */
+#cmakedefine HAVE_MMAP
+
+/* Define to 1 if you have the <stdint.h> header file. */
+#cmakedefine HAVE_STDINT_H
+
+/* Define to 1 if you have the <stdlib.h> header file. */
+#cmakedefine HAVE_STDLIB_H
+
+/* Define to 1 if you have the <strings.h> header file. */
+#cmakedefine HAVE_STRINGS_H
+
+/* Define to 1 if you have the <string.h> header file. */
+#cmakedefine HAVE_STRING_H
+
+/* Define to 1 if you have `syscall' and `SYS_getrandom'. */
+#cmakedefine HAVE_SYSCALL_GETRANDOM
+
+/* Define to 1 if you have the <sys/stat.h> header file. */
+#cmakedefine HAVE_SYS_STAT_H
+
+/* Define to 1 if you have the <sys/types.h> header file. */
+#cmakedefine HAVE_SYS_TYPES_H
+
+/* Define to 1 if you have the <unistd.h> header file. */
+#cmakedefine HAVE_UNISTD_H
+
+/* Define to the address where bug reports for this package should be sent. */
+#cmakedefine PACKAGE_BUGREPORT
+
+/* Define to the full name of this package. */
+#cmakedefine PACKAGE_NAME
+
+/* Define to the full name and version of this package. */
+#cmakedefine PACKAGE_STRING
+
+/* Define to the one symbol short name of this package. */
+#cmakedefine PACKAGE_TARNAME
+
+/* Define to the version of this package. */
+#cmakedefine PACKAGE_VERSION
+
+/* Define to 1 if you have the ANSI C header files. */
+#cmakedefine STDC_HEADERS
+
+/* whether byteorder is bigendian */
+#cmakedefine WORDS_BIGENDIAN
+
+/* Define to specify how much context to retain around the current parse
+ point. */
+#cmakedefine XML_CONTEXT_BYTES @XML_CONTEXT_BYTES@
+
+/* Define to make parameter entity parsing functionality available. */
+#cmakedefine XML_DTD
+
+/* Define to make XML Namespaces functionality available. */
+#cmakedefine XML_NS
+
+/* Define to __FUNCTION__ or "" if `__func__' does not conform to ANSI C. */
+#ifdef _MSC_VER
+# define __func__ __FUNCTION__
+#endif
+
+/* Define to `long' if <sys/types.h> does not define. */
+#cmakedefine off_t @OFF_T@
+
+/* Define to `unsigned' if <sys/types.h> does not define. */
+#cmakedefine size_t @SIZE_T@
diff --git a/gennmtab/.gitignore b/gennmtab/.gitignore
new file mode 100755
index 0000000..f966c45
--- /dev/null
+++ b/gennmtab/.gitignore
@@ -0,0 +1,3 @@
+Debug
+Release
+gennmtab.plg
diff --git a/gennmtab/gennmtab.c b/gennmtab/gennmtab.c
new file mode 100644
index 0000000..771f05f
--- /dev/null
+++ b/gennmtab/gennmtab.c
@@ -0,0 +1,457 @@
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+#include <string.h>
+#include <stdio.h>
+#include <stddef.h>
+
+struct range {
+ int start;
+ int end;
+};
+
+struct range nmstrt[] = {
+ { '_' },
+ { ':' },
+ /* BaseChar */
+ { 0x0041, 0x005a },
+ { 0x0061, 0x007a },
+ { 0x00c0, 0x00d6 },
+ { 0x00d8, 0x00f6 },
+ { 0x00f8, 0x00ff },
+ { 0x0100, 0x0131 },
+ { 0x0134, 0x013e },
+ { 0x0141, 0x0148 },
+ { 0x014a, 0x017e },
+ { 0x0180, 0x01c3 },
+ { 0x01cd, 0x01f0 },
+ { 0x01f4, 0x01f5 },
+ { 0x01fa, 0x0217 },
+ { 0x0250, 0x02a8 },
+ { 0x02bb, 0x02c1 },
+ { 0x0386 },
+ { 0x0388, 0x038a },
+ { 0x038c },
+ { 0x038e, 0x03a1 },
+ { 0x03a3, 0x03ce },
+ { 0x03d0, 0x03d6 },
+ { 0x03da },
+ { 0x03dc },
+ { 0x03de },
+ { 0x03e0 },
+ { 0x03e2, 0x03f3 },
+ { 0x0401, 0x040c },
+ { 0x040e, 0x044f },
+ { 0x0451, 0x045c },
+ { 0x045e, 0x0481 },
+ { 0x0490, 0x04c4 },
+ { 0x04c7, 0x04c8 },
+ { 0x04cb, 0x04cc },
+ { 0x04d0, 0x04eb },
+ { 0x04ee, 0x04f5 },
+ { 0x04f8, 0x04f9 },
+ { 0x0531, 0x0556 },
+ { 0x0559 },
+ { 0x0561, 0x0586 },
+ { 0x05d0, 0x05ea },
+ { 0x05f0, 0x05f2 },
+ { 0x0621, 0x063a },
+ { 0x0641, 0x064a },
+ { 0x0671, 0x06b7 },
+ { 0x06ba, 0x06be },
+ { 0x06c0, 0x06ce },
+ { 0x06d0, 0x06d3 },
+ { 0x06d5 },
+ { 0x06e5, 0x06e6 },
+ { 0x0905, 0x0939 },
+ { 0x093d },
+ { 0x0958, 0x0961 },
+ { 0x0985, 0x098c },
+ { 0x098f, 0x0990 },
+ { 0x0993, 0x09a8 },
+ { 0x09aa, 0x09b0 },
+ { 0x09b2 },
+ { 0x09b6, 0x09b9 },
+ { 0x09dc, 0x09dd },
+ { 0x09df, 0x09e1 },
+ { 0x09f0, 0x09f1 },
+ { 0x0a05, 0x0a0a },
+ { 0x0a0f, 0x0a10 },
+ { 0x0a13, 0x0a28 },
+ { 0x0a2a, 0x0a30 },
+ { 0x0a32, 0x0a33 },
+ { 0x0a35, 0x0a36 },
+ { 0x0a38, 0x0a39 },
+ { 0x0a59, 0x0a5c },
+ { 0x0a5e },
+ { 0x0a72, 0x0a74 },
+ { 0x0a85, 0x0a8b },
+ { 0x0a8d },
+ { 0x0a8f, 0x0a91 },
+ { 0x0a93, 0x0aa8 },
+ { 0x0aaa, 0x0ab0 },
+ { 0x0ab2, 0x0ab3 },
+ { 0x0ab5, 0x0ab9 },
+ { 0x0abd },
+ { 0x0ae0 },
+ { 0x0b05, 0x0b0c },
+ { 0x0b0f, 0x0b10 },
+ { 0x0b13, 0x0b28 },
+ { 0x0b2a, 0x0b30 },
+ { 0x0b32, 0x0b33 },
+ { 0x0b36, 0x0b39 },
+ { 0x0b3d },
+ { 0x0b5c, 0x0b5d },
+ { 0x0b5f, 0x0b61 },
+ { 0x0b85, 0x0b8a },
+ { 0x0b8e, 0x0b90 },
+ { 0x0b92, 0x0b95 },
+ { 0x0b99, 0x0b9a },
+ { 0x0b9c },
+ { 0x0b9e, 0x0b9f },
+ { 0x0ba3, 0x0ba4 },
+ { 0x0ba8, 0x0baa },
+ { 0x0bae, 0x0bb5 },
+ { 0x0bb7, 0x0bb9 },
+ { 0x0c05, 0x0c0c },
+ { 0x0c0e, 0x0c10 },
+ { 0x0c12, 0x0c28 },
+ { 0x0c2a, 0x0c33 },
+ { 0x0c35, 0x0c39 },
+ { 0x0c60, 0x0c61 },
+ { 0x0c85, 0x0c8c },
+ { 0x0c8e, 0x0c90 },
+ { 0x0c92, 0x0ca8 },
+ { 0x0caa, 0x0cb3 },
+ { 0x0cb5, 0x0cb9 },
+ { 0x0cde },
+ { 0x0ce0, 0x0ce1 },
+ { 0x0d05, 0x0d0c },
+ { 0x0d0e, 0x0d10 },
+ { 0x0d12, 0x0d28 },
+ { 0x0d2a, 0x0d39 },
+ { 0x0d60, 0x0d61 },
+ { 0x0e01, 0x0e2e },
+ { 0x0e30 },
+ { 0x0e32, 0x0e33 },
+ { 0x0e40, 0x0e45 },
+ { 0x0e81, 0x0e82 },
+ { 0x0e84 },
+ { 0x0e87, 0x0e88 },
+ { 0x0e8a },
+ { 0x0e8d },
+ { 0x0e94, 0x0e97 },
+ { 0x0e99, 0x0e9f },
+ { 0x0ea1, 0x0ea3 },
+ { 0x0ea5 },
+ { 0x0ea7 },
+ { 0x0eaa, 0x0eab },
+ { 0x0ead, 0x0eae },
+ { 0x0eb0 },
+ { 0x0eb2, 0x0eb3 },
+ { 0x0ebd },
+ { 0x0ec0, 0x0ec4 },
+ { 0x0f40, 0x0f47 },
+ { 0x0f49, 0x0f69 },
+ { 0x10a0, 0x10c5 },
+ { 0x10d0, 0x10f6 },
+ { 0x1100 },
+ { 0x1102, 0x1103 },
+ { 0x1105, 0x1107 },
+ { 0x1109 },
+ { 0x110b, 0x110c },
+ { 0x110e, 0x1112 },
+ { 0x113c },
+ { 0x113e },
+ { 0x1140 },
+ { 0x114c },
+ { 0x114e },
+ { 0x1150 },
+ { 0x1154, 0x1155 },
+ { 0x1159 },
+ { 0x115f, 0x1161 },
+ { 0x1163 },
+ { 0x1165 },
+ { 0x1167 },
+ { 0x1169 },
+ { 0x116d, 0x116e },
+ { 0x1172, 0x1173 },
+ { 0x1175 },
+ { 0x119e },
+ { 0x11a8 },
+ { 0x11ab },
+ { 0x11ae, 0x11af },
+ { 0x11b7, 0x11b8 },
+ { 0x11ba },
+ { 0x11bc, 0x11c2 },
+ { 0x11eb },
+ { 0x11f0 },
+ { 0x11f9 },
+ { 0x1e00, 0x1e9b },
+ { 0x1ea0, 0x1ef9 },
+ { 0x1f00, 0x1f15 },
+ { 0x1f18, 0x1f1d },
+ { 0x1f20, 0x1f45 },
+ { 0x1f48, 0x1f4d },
+ { 0x1f50, 0x1f57 },
+ { 0x1f59 },
+ { 0x1f5b },
+ { 0x1f5d },
+ { 0x1f5f, 0x1f7d },
+ { 0x1f80, 0x1fb4 },
+ { 0x1fb6, 0x1fbc },
+ { 0x1fbe },
+ { 0x1fc2, 0x1fc4 },
+ { 0x1fc6, 0x1fcc },
+ { 0x1fd0, 0x1fd3 },
+ { 0x1fd6, 0x1fdb },
+ { 0x1fe0, 0x1fec },
+ { 0x1ff2, 0x1ff4 },
+ { 0x1ff6, 0x1ffc },
+ { 0x2126 },
+ { 0x212a, 0x212b },
+ { 0x212e },
+ { 0x2180, 0x2182 },
+ { 0x3041, 0x3094 },
+ { 0x30a1, 0x30fa },
+ { 0x3105, 0x312c },
+ { 0xac00, 0xd7a3 },
+ /* Ideographic */
+ { 0x4e00, 0x9fa5 },
+ { 0x3007 },
+ { 0x3021, 0x3029 },
+};
+
+/* name chars that are not name start chars */
+struct range name[] = {
+ { '.' },
+ { '-' },
+ /* CombiningChar */
+ { 0x0300, 0x0345 },
+ { 0x0360, 0x0361 },
+ { 0x0483, 0x0486 },
+ { 0x0591, 0x05a1 },
+ { 0x05a3, 0x05b9 },
+ { 0x05bb, 0x05bd },
+ { 0x05bf },
+ { 0x05c1, 0x05c2 },
+ { 0x05c4 },
+ { 0x064b, 0x0652 },
+ { 0x0670 },
+ { 0x06d6, 0x06dc },
+ { 0x06dd, 0x06df },
+ { 0x06e0, 0x06e4 },
+ { 0x06e7, 0x06e8 },
+ { 0x06ea, 0x06ed },
+ { 0x0901, 0x0903 },
+ { 0x093c },
+ { 0x093e, 0x094c },
+ { 0x094d },
+ { 0x0951, 0x0954 },
+ { 0x0962, 0x0963 },
+ { 0x0981, 0x0983 },
+ { 0x09bc },
+ { 0x09be },
+ { 0x09bf },
+ { 0x09c0, 0x09c4 },
+ { 0x09c7, 0x09c8 },
+ { 0x09cb, 0x09cd },
+ { 0x09d7 },
+ { 0x09e2, 0x09e3 },
+ { 0x0a02 },
+ { 0x0a3c },
+ { 0x0a3e },
+ { 0x0a3f },
+ { 0x0a40, 0x0a42 },
+ { 0x0a47, 0x0a48 },
+ { 0x0a4b, 0x0a4d },
+ { 0x0a70, 0x0a71 },
+ { 0x0a81, 0x0a83 },
+ { 0x0abc },
+ { 0x0abe, 0x0ac5 },
+ { 0x0ac7, 0x0ac9 },
+ { 0x0acb, 0x0acd },
+ { 0x0b01, 0x0b03 },
+ { 0x0b3c },
+ { 0x0b3e, 0x0b43 },
+ { 0x0b47, 0x0b48 },
+ { 0x0b4b, 0x0b4d },
+ { 0x0b56, 0x0b57 },
+ { 0x0b82, 0x0b83 },
+ { 0x0bbe, 0x0bc2 },
+ { 0x0bc6, 0x0bc8 },
+ { 0x0bca, 0x0bcd },
+ { 0x0bd7 },
+ { 0x0c01, 0x0c03 },
+ { 0x0c3e, 0x0c44 },
+ { 0x0c46, 0x0c48 },
+ { 0x0c4a, 0x0c4d },
+ { 0x0c55, 0x0c56 },
+ { 0x0c82, 0x0c83 },
+ { 0x0cbe, 0x0cc4 },
+ { 0x0cc6, 0x0cc8 },
+ { 0x0cca, 0x0ccd },
+ { 0x0cd5, 0x0cd6 },
+ { 0x0d02, 0x0d03 },
+ { 0x0d3e, 0x0d43 },
+ { 0x0d46, 0x0d48 },
+ { 0x0d4a, 0x0d4d },
+ { 0x0d57 },
+ { 0x0e31 },
+ { 0x0e34, 0x0e3a },
+ { 0x0e47, 0x0e4e },
+ { 0x0eb1 },
+ { 0x0eb4, 0x0eb9 },
+ { 0x0ebb, 0x0ebc },
+ { 0x0ec8, 0x0ecd },
+ { 0x0f18, 0x0f19 },
+ { 0x0f35 },
+ { 0x0f37 },
+ { 0x0f39 },
+ { 0x0f3e },
+ { 0x0f3f },
+ { 0x0f71, 0x0f84 },
+ { 0x0f86, 0x0f8b },
+ { 0x0f90, 0x0f95 },
+ { 0x0f97 },
+ { 0x0f99, 0x0fad },
+ { 0x0fb1, 0x0fb7 },
+ { 0x0fb9 },
+ { 0x20d0, 0x20dc },
+ { 0x20e1 },
+ { 0x302a, 0x302f },
+ { 0x3099 },
+ { 0x309a },
+ /* Digit */
+ { 0x0030, 0x0039 },
+ { 0x0660, 0x0669 },
+ { 0x06f0, 0x06f9 },
+ { 0x0966, 0x096f },
+ { 0x09e6, 0x09ef },
+ { 0x0a66, 0x0a6f },
+ { 0x0ae6, 0x0aef },
+ { 0x0b66, 0x0b6f },
+ { 0x0be7, 0x0bef },
+ { 0x0c66, 0x0c6f },
+ { 0x0ce6, 0x0cef },
+ { 0x0d66, 0x0d6f },
+ { 0x0e50, 0x0e59 },
+ { 0x0ed0, 0x0ed9 },
+ { 0x0f20, 0x0f29 },
+ /* Extender */
+ { 0xb7 },
+ { 0x02d0 },
+ { 0x02d1 },
+ { 0x0387 },
+ { 0x0640 },
+ { 0x0e46 },
+ { 0x0ec6 },
+ { 0x3005 },
+ { 0x3031, 0x3035 },
+ { 0x309d, 0x309e },
+ { 0x30fc, 0x30fe },
+};
+
+static void
+setTab(char *tab, struct range *ranges, size_t nRanges)
+{
+ size_t i;
+ int j;
+ for (i = 0; i < nRanges; i++) {
+ if (ranges[i].end) {
+ for (j = ranges[i].start; j <= ranges[i].end; j++)
+ tab[j] = 1;
+ }
+ else
+ tab[ranges[i].start] = 1;
+ }
+}
+
+static void
+printTabs(char *tab)
+{
+ int nBitmaps = 2;
+ int i, j, k;
+ unsigned char pageIndex[512];
+
+ printf(
+"static const unsigned namingBitmap[] = {\n\
+0x00000000, 0x00000000, 0x00000000, 0x00000000,\n\
+0x00000000, 0x00000000, 0x00000000, 0x00000000,\n\
+0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF,\n\
+0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF,\n");
+ for (i = 0; i < 512; i++) {
+ int kind = tab[i*256];
+ for (j = 1; j < 256; j++)
+ if (tab[i*256 +j] != kind) {
+ kind = -1;
+ break;
+ }
+ if (i >= 256 && memcmp(tab + (i - 256)*256, tab + i*256, 256) == 0)
+ pageIndex[i] = pageIndex[i - 256];
+ else if (kind == -1) {
+ pageIndex[i] = nBitmaps++;
+ for (j = 0; j < 8; j++) {
+ unsigned val = 0;
+ for (k = 0; k < 32; k++) {
+ if (tab[i*256 + j*32 +k])
+ val |= (1 << k);
+ }
+ printf("0x%08X,", val);
+ putchar((((j + 1) & 3) == 0) ? '\n' : ' ');
+ }
+ }
+ else
+ pageIndex[i] = kind;
+ }
+ printf("};\n");
+ printf("static const unsigned char nmstrtPages[] = {\n");
+ for (i = 0; i < 512; i++) {
+ if (i == 256)
+ printf("};\nstatic const unsigned char namePages[] = {\n");
+ printf("0x%02X,", pageIndex[i]);
+ putchar((((i + 1) & 7) == 0) ? '\n' : ' ');
+ }
+ printf("};\n");
+}
+
+int
+main()
+{
+ char tab[2*65536];
+ memset(tab, 0, 65536);
+ setTab(tab, nmstrt, sizeof(nmstrt)/sizeof(nmstrt[0]));
+ memcpy(tab + 65536, tab, 65536);
+ setTab(tab + 65536, name, sizeof(name)/sizeof(name[0]));
+ printTabs(tab);
+ return 0;
+}
diff --git a/import_expat.sh b/import_expat.sh
deleted file mode 100755
index 17eaf9e..0000000
--- a/import_expat.sh
+++ /dev/null
@@ -1,53 +0,0 @@
-#!/bin/sh
-
-set -e
-
-if [ "$1" = "" ]; then
- echo "usage: $0 expat.tar.bz2"
- exit 1
-fi
-
-echo "Extracting $1"
-tar --extract --bzip2 --strip-components=1 --file $1
-
-echo "Saving COPYING to NOTICE"
-touch MODULE_LICENSE_BSD_LIKE
-mv COPYING NOTICE
-
-echo "Removing unnecessary files"
-rm CMake.README
-rm CMakeLists.txt
-rm ConfigureChecks.cmake
-rm MANIFEST
-rm Makefile.in
-rm aclocal.m4
-rm configure
-rm configure.ac
-rm examples/elements.dsp
-rm examples/outline.dsp
-rm expat.dsw
-rm expat.pc.in
-rm expat_config.h.cmake
-rm expat_config.h.in
-rm lib/Makefile.MPW
-rm lib/amigaconfig.h
-rm lib/expat.dsp
-rm lib/expat_static.dsp
-rm lib/expatw.dsp
-rm lib/expatw_static.dsp
-rm lib/libexpat.def
-rm lib/libexpatw.def
-rm lib/macconfig.h
-rm lib/winconfig.h
-rm tests/benchmark/benchmark.dsp
-rm tests/benchmark/benchmark.dsw
-
-rm -rf amiga
-rm -rf bcb5
-rm -rf conftools
-rm -rf m4
-rm -rf vms
-rm -rf win32
-rm -rf xmlwf
-
-echo "Import complete"
diff --git a/lib/.gitignore b/lib/.gitignore
new file mode 100644
index 0000000..9c9cf88
--- /dev/null
+++ b/lib/.gitignore
@@ -0,0 +1,18 @@
+Makefile
+.libs
+*.lo
+expat.h
+Debug
+Debug-w
+Release
+Release-w
+expat.ncb
+expat.opt
+expat.plg
+Debug_static
+Debug-w_static
+Release_static
+Release-w_static
+expat_static.plg
+expatw.plg
+expatw_static.plg
diff --git a/lib/Makefile.am b/lib/Makefile.am
new file mode 100644
index 0000000..d655a29
--- /dev/null
+++ b/lib/Makefile.am
@@ -0,0 +1,77 @@
+#
+# __ __ _
+# ___\ \/ /_ __ __ _| |_
+# / _ \\ /| '_ \ / _` | __|
+# | __// \| |_) | (_| | |_
+# \___/_/\_\ .__/ \__,_|\__|
+# |_| XML parser
+#
+# Copyright (c) 2017 Expat development team
+# Licensed under the MIT license:
+#
+# Permission is hereby granted, free of charge, to any person obtaining
+# a copy of this software and associated documentation files (the
+# "Software"), to deal in the Software without restriction, including
+# without limitation the rights to use, copy, modify, merge, publish,
+# distribute, sublicense, and/or sell copies of the Software, and to permit
+# persons to whom the Software is furnished to do so, subject to the
+# following conditions:
+#
+# The above copyright notice and this permission notice shall be included
+# in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+# NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+# DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+# OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+# USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+include_HEADERS = \
+ ../expat_config.h \
+ expat.h \
+ expat_external.h
+
+lib_LTLIBRARIES = libexpat.la
+
+libexpat_la_LDFLAGS = \
+ -no-undefined \
+ -version-info @LIBCURRENT@:@LIBREVISION@:@LIBAGE@ \
+ -rpath $(libdir)
+
+libexpat_la_SOURCES = \
+ loadlibrary.c \
+ xmlparse.c \
+ xmltok.c \
+ xmlrole.c
+
+doc_DATA = \
+ ../AUTHORS \
+ ../Changes
+
+install-data-hook:
+ cd "$(DESTDIR)$(docdir)" && $(am__mv) Changes changelog
+
+uninstall-local:
+ $(RM) "$(DESTDIR)$(docdir)/changelog"
+
+EXTRA_DIST = \
+ ascii.h \
+ asciitab.h \
+ expat_external.h \
+ expat.h \
+ iasciitab.h \
+ internal.h \
+ latin1tab.h \
+ libexpat.def \
+ libexpatw.def \
+ nametab.h \
+ siphash.h \
+ utf8tab.h \
+ winconfig.h \
+ xmlrole.h \
+ xmltok.h \
+ xmltok_impl.c \
+ xmltok_impl.h \
+ xmltok_ns.c
diff --git a/lib/ascii.h b/lib/ascii.h
index d10530b..c3587e5 100644
--- a/lib/ascii.h
+++ b/lib/ascii.h
@@ -1,5 +1,33 @@
-/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
- See the file COPYING for copying permission.
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
#define ASCII_A 0x41
diff --git a/lib/asciitab.h b/lib/asciitab.h
index 79a15c2..2f59fd9 100644
--- a/lib/asciitab.h
+++ b/lib/asciitab.h
@@ -1,5 +1,33 @@
-/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
- See the file COPYING for copying permission.
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
/* 0x00 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
diff --git a/lib/expat.h b/lib/expat.h
index 086e24b..1f608c0 100644
--- a/lib/expat.h
+++ b/lib/expat.h
@@ -1,5 +1,33 @@
-/* Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd
- See the file COPYING for copying permission.
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
#ifndef Expat_INCLUDED
@@ -24,7 +52,6 @@ extern "C" {
struct XML_ParserStruct;
typedef struct XML_ParserStruct *XML_Parser;
-/* Should this be defined using stdbool.h when C99 is available? */
typedef unsigned char XML_Bool;
#define XML_TRUE ((XML_Bool) 1)
#define XML_FALSE ((XML_Bool) 0)
@@ -95,7 +122,9 @@ enum XML_Error {
/* Added in 2.0. */
XML_ERROR_RESERVED_PREFIX_XML,
XML_ERROR_RESERVED_PREFIX_XMLNS,
- XML_ERROR_RESERVED_NAMESPACE_URI
+ XML_ERROR_RESERVED_NAMESPACE_URI,
+ /* Added in 2.2.1. */
+ XML_ERROR_INVALID_ARGUMENT
};
enum XML_Content_Type {
@@ -706,6 +735,7 @@ XML_UseParserAsHandlerArg(XML_Parser parser);
be called, despite an external subset being parsed.
Note: If XML_DTD is not defined when Expat is compiled, returns
XML_ERROR_FEATURE_REQUIRES_XML_DTD.
+ Note: If parser == NULL, returns XML_ERROR_INVALID_ARGUMENT.
*/
XMLPARSEAPI(enum XML_Error)
XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD);
@@ -729,15 +759,16 @@ XML_GetBase(XML_Parser parser);
to the XML_StartElementHandler that were specified in the start-tag
rather than defaulted. Each attribute/value pair counts as 2; thus
this correspondds to an index into the atts array passed to the
- XML_StartElementHandler.
+ XML_StartElementHandler. Returns -1 if parser == NULL.
*/
XMLPARSEAPI(int)
XML_GetSpecifiedAttributeCount(XML_Parser parser);
/* Returns the index of the ID attribute passed in the last call to
- XML_StartElementHandler, or -1 if there is no ID attribute. Each
- attribute/value pair counts as 2; thus this correspondds to an
- index into the atts array passed to the XML_StartElementHandler.
+ XML_StartElementHandler, or -1 if there is no ID attribute or
+ parser == NULL. Each attribute/value pair counts as 2; thus this
+ correspondds to an index into the atts array passed to the
+ XML_StartElementHandler.
*/
XMLPARSEAPI(int)
XML_GetIdAttributeIndex(XML_Parser parser);
@@ -901,6 +932,7 @@ enum XML_ParamEntityParsing {
entities is requested; otherwise it will return non-zero.
Note: If XML_SetParamEntityParsing is called after XML_Parse or
XML_ParseBuffer, then it has no effect and will always return 0.
+ Note: If parser == NULL, the function will do nothing and return 0.
*/
XMLPARSEAPI(int)
XML_SetParamEntityParsing(XML_Parser parser,
@@ -910,6 +942,7 @@ XML_SetParamEntityParsing(XML_Parser parser,
Helps in preventing DoS attacks based on predicting hash
function behavior. This must be called before parsing is started.
Returns 1 if successful, 0 when called after parsing has started.
+ Note: If parser == NULL, the function will do nothing and return 0.
*/
XMLPARSEAPI(int)
XML_SetHashSalt(XML_Parser parser,
@@ -936,6 +969,10 @@ XML_GetErrorCode(XML_Parser parser);
the location is the location of the character at which the error
was detected; otherwise the location is the location of the last
parse event, as described above.
+
+ Note: XML_GetCurrentLineNumber and XML_GetCurrentColumnNumber
+ return 0 to indicate an error.
+ Note: XML_GetCurrentByteIndex returns -1 to indicate an error.
*/
XMLPARSEAPI(XML_Size) XML_GetCurrentLineNumber(XML_Parser parser);
XMLPARSEAPI(XML_Size) XML_GetCurrentColumnNumber(XML_Parser parser);
@@ -1039,7 +1076,7 @@ XML_GetFeatureList(void);
*/
#define XML_MAJOR_VERSION 2
#define XML_MINOR_VERSION 2
-#define XML_MICRO_VERSION 0
+#define XML_MICRO_VERSION 5
#ifdef __cplusplus
}
diff --git a/lib/expat.vcxproj b/lib/expat.vcxproj
new file mode 100644
index 0000000..66d646e
--- /dev/null
+++ b/lib/expat.vcxproj
@@ -0,0 +1,179 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project DefaultTargets="Build" ToolsVersion="15.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+ <ItemGroup Label="ProjectConfigurations">
+ <ProjectConfiguration Include="Debug|Win32">
+ <Configuration>Debug</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Release|Win32">
+ <Configuration>Release</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Template|Win32">
+ <Configuration>Template</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ </ItemGroup>
+ <PropertyGroup Label="Globals">
+ <SccProjectName />
+ <SccLocalPath />
+ <ProjectGuid>{45A5074D-66E8-44A4-A03F-018027B528D6}</ProjectGuid>
+ <WindowsTargetPlatformVersion>10.0.16299.0</WindowsTargetPlatformVersion>
+ </PropertyGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Template|Win32'" Label="Configuration">
+ <ConfigurationType>Application</ConfigurationType>
+ <PlatformToolset>v141</PlatformToolset>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
+ <ConfigurationType>DynamicLibrary</ConfigurationType>
+ <PlatformToolset>v141</PlatformToolset>
+ <UseOfMfc>false</UseOfMfc>
+ <CharacterSet>MultiByte</CharacterSet>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
+ <ConfigurationType>DynamicLibrary</ConfigurationType>
+ <PlatformToolset>v141</PlatformToolset>
+ <UseOfMfc>false</UseOfMfc>
+ <CharacterSet>MultiByte</CharacterSet>
+ </PropertyGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
+ <ImportGroup Label="ExtensionSettings">
+ </ImportGroup>
+ <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Template|Win32'">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ </ImportGroup>
+ <ImportGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="PropertySheets">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ <Import Project="$(VCTargetsPath)Microsoft.Cpp.UpgradeFromVC60.props" />
+ </ImportGroup>
+ <ImportGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="PropertySheets">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ <Import Project="$(VCTargetsPath)Microsoft.Cpp.UpgradeFromVC60.props" />
+ </ImportGroup>
+ <PropertyGroup Label="UserMacros" />
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ <OutDir>.\..\win32\bin\Debug\</OutDir>
+ <IntDir>.\..\win32\tmp\Debug\</IntDir>
+ <LinkIncremental>true</LinkIncremental>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+ <OutDir>.\..\win32\bin\Release\</OutDir>
+ <IntDir>.\..\win32\tmp\Release\</IntDir>
+ <LinkIncremental>false</LinkIncremental>
+ </PropertyGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ <ClCompile>
+ <RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
+ <InlineFunctionExpansion>Default</InlineFunctionExpansion>
+ <FunctionLevelLinking>true</FunctionLevelLinking>
+ <Optimization>Disabled</Optimization>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <WarningLevel>Level3</WarningLevel>
+ <DebugInformationFormat>EditAndContinue</DebugInformationFormat>
+ <PreprocessorDefinitions>_DEBUG;_WINDOWS;_USRDLL;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <AssemblerListingLocation>.\..\win32\tmp\Debug\</AssemblerListingLocation>
+ <BrowseInformation>true</BrowseInformation>
+ <PrecompiledHeaderOutputFile>.\..\win32\tmp\Debug\expat.pch</PrecompiledHeaderOutputFile>
+ <ObjectFileName>.\..\win32\tmp\Debug\</ObjectFileName>
+ <ProgramDataBaseFileName>.\..\win32\tmp\Debug\</ProgramDataBaseFileName>
+ <BasicRuntimeChecks>EnableFastChecks</BasicRuntimeChecks>
+ </ClCompile>
+ <Midl>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <PreprocessorDefinitions>_DEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <TypeLibraryName>.\..\win32\bin\Debug\expat.tlb</TypeLibraryName>
+ <MkTypLibCompatible>true</MkTypLibCompatible>
+ <TargetEnvironment>Win32</TargetEnvironment>
+ </Midl>
+ <ResourceCompile>
+ <Culture>0x0409</Culture>
+ <PreprocessorDefinitions>_DEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ </ResourceCompile>
+ <Bscmake>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <OutputFile>.\..\win32\bin\Debug\expat.bsc</OutputFile>
+ </Bscmake>
+ <Link>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <LinkDLL>true</LinkDLL>
+ <GenerateDebugInformation>true</GenerateDebugInformation>
+ <SubSystem>Console</SubSystem>
+ <OutputFile>..\win32\bin\Debug\libexpat.dll</OutputFile>
+ <ImportLibrary>.\..\win32\bin\Debug\libexpat.lib</ImportLibrary>
+ <ModuleDefinitionFile>.\libexpat.def</ModuleDefinitionFile>
+ </Link>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+ <ClCompile>
+ <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
+ <InlineFunctionExpansion>Default</InlineFunctionExpansion>
+ <StringPooling>true</StringPooling>
+ <FunctionLevelLinking>true</FunctionLevelLinking>
+ <Optimization>MaxSpeed</Optimization>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <WarningLevel>Level3</WarningLevel>
+ <PreprocessorDefinitions>NDEBUG;_WINDOWS;_USRDLL;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <AssemblerListingLocation>.\..\win32\tmp\Release\</AssemblerListingLocation>
+ <PrecompiledHeaderOutputFile>.\..\win32\tmp\Release\expat.pch</PrecompiledHeaderOutputFile>
+ <PrecompiledHeader />
+ <ObjectFileName>.\..\win32\tmp\Release\</ObjectFileName>
+ <ProgramDataBaseFileName>.\..\win32\tmp\Release\</ProgramDataBaseFileName>
+ </ClCompile>
+ <Midl>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <PreprocessorDefinitions>NDEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <TypeLibraryName>.\..\win32\bin\Release\expat.tlb</TypeLibraryName>
+ <MkTypLibCompatible>true</MkTypLibCompatible>
+ <TargetEnvironment>Win32</TargetEnvironment>
+ </Midl>
+ <ResourceCompile>
+ <Culture>0x0409</Culture>
+ <PreprocessorDefinitions>NDEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ </ResourceCompile>
+ <Bscmake>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <OutputFile>.\..\win32\bin\Release\expat.bsc</OutputFile>
+ </Bscmake>
+ <Link>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <LinkDLL>true</LinkDLL>
+ <SubSystem>Console</SubSystem>
+ <OutputFile>..\win32\bin\Release\libexpat.dll</OutputFile>
+ <ImportLibrary>.\..\win32\bin\Release\libexpat.lib</ImportLibrary>
+ <ModuleDefinitionFile>.\libexpat.def</ModuleDefinitionFile>
+ </Link>
+ </ItemDefinitionGroup>
+ <ItemGroup>
+ <CustomBuild Include="libexpat.def" />
+ </ItemGroup>
+ <ItemGroup>
+ <ClCompile Include="loadlibrary.c" />
+ <ClCompile Include="xmlparse.c">
+ <ExceptionHandling Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ </ExceptionHandling>
+ </ClCompile>
+ <ClCompile Include="xmlrole.c" />
+ <ClCompile Include="xmltok.c" />
+ <ClCompile Include="xmltok_impl.c" />
+ <ClCompile Include="xmltok_ns.c" />
+ </ItemGroup>
+ <ItemGroup>
+ <ClInclude Include="ascii.h" />
+ <ClInclude Include="asciitab.h" />
+ <ClInclude Include="expat.h" />
+ <ClInclude Include="expat_external.h" />
+ <ClInclude Include="iasciitab.h" />
+ <ClInclude Include="internal.h" />
+ <ClInclude Include="latin1tab.h" />
+ <ClInclude Include="nametab.h" />
+ <ClInclude Include="siphash.h" />
+ <ClInclude Include="utf8tab.h" />
+ <ClInclude Include="xmlrole.h" />
+ <ClInclude Include="xmltok.h" />
+ <ClInclude Include="xmltok_impl.h" />
+ </ItemGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
+ <ImportGroup Label="ExtensionTargets">
+ </ImportGroup>
+</Project> \ No newline at end of file
diff --git a/lib/expat.vcxproj.filters b/lib/expat.vcxproj.filters
new file mode 100644
index 0000000..61c52b5
--- /dev/null
+++ b/lib/expat.vcxproj.filters
@@ -0,0 +1,83 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+ <ItemGroup>
+ <Filter Include="Source Files">
+ <UniqueIdentifier>{f01bb743-0ef8-4601-bc44-378fc0abe768}</UniqueIdentifier>
+ <Extensions>cpp;c;cxx;rc;def;r;odl;idl;hpj;bat</Extensions>
+ </Filter>
+ <Filter Include="Header Files">
+ <UniqueIdentifier>{c22177dc-5748-4bb1-816e-df311093bf72}</UniqueIdentifier>
+ <Extensions>h;hpp;hxx;hm;inl</Extensions>
+ </Filter>
+ <Filter Include="Resource Files">
+ <UniqueIdentifier>{41146e15-3129-4e5e-bb0f-6b78bb4701b9}</UniqueIdentifier>
+ <Extensions>ico;cur;bmp;dlg;rc2;rct;bin;rgs;gif;jpg;jpeg;jpe</Extensions>
+ </Filter>
+ </ItemGroup>
+ <ItemGroup>
+ <ClCompile Include="loadlibrary.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="xmlparse.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="xmlrole.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="xmltok.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="xmltok_impl.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="xmltok_ns.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ </ItemGroup>
+ <ItemGroup>
+ <ClInclude Include="ascii.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="asciitab.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="expat.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="expat_external.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="iasciitab.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="internal.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="latin1tab.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="nametab.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="siphash.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="utf8tab.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="xmlrole.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="xmltok.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="xmltok_impl.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ </ItemGroup>
+ <ItemGroup>
+ <CustomBuild Include="libexpat.def">
+ <Filter>Source Files</Filter>
+ </CustomBuild>
+ </ItemGroup>
+</Project> \ No newline at end of file
diff --git a/lib/expat_external.h b/lib/expat_external.h
index aa08a2f..629483a 100644
--- a/lib/expat_external.h
+++ b/lib/expat_external.h
@@ -1,5 +1,33 @@
-/* Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd
- See the file COPYING for copying permission.
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
#ifndef Expat_External_INCLUDED
@@ -8,7 +36,7 @@
/* External API definitions */
#if defined(_MSC_EXTENSIONS) && !defined(__BEOS__) && !defined(__CYGWIN__)
-#define XML_USE_MSC_EXTENSIONS 1
+# define XML_USE_MSC_EXTENSIONS 1
#endif
/* Expat tries very hard to make the API boundary very specifically
@@ -34,11 +62,11 @@
system headers may assume the cdecl convention.
*/
#ifndef XMLCALL
-#if defined(_MSC_VER)
-#define XMLCALL __cdecl
-#elif defined(__GNUC__) && defined(__i386) && !defined(__INTEL_COMPILER)
-#define XMLCALL __attribute__((cdecl))
-#else
+# if defined(_MSC_VER)
+# define XMLCALL __cdecl
+# elif defined(__GNUC__) && defined(__i386) && !defined(__INTEL_COMPILER)
+# define XMLCALL __attribute__((cdecl))
+# else
/* For any platform which uses this definition and supports more than
one calling convention, we need to extend this definition to
declare the convention used on that platform, if it's possible to
@@ -49,41 +77,41 @@
pre-processor and how to specify the same calling convention as the
platform's malloc() implementation.
*/
-#define XMLCALL
-#endif
+# define XMLCALL
+# endif
#endif /* not defined XMLCALL */
#if !defined(XML_STATIC) && !defined(XMLIMPORT)
-#ifndef XML_BUILDING_EXPAT
+# ifndef XML_BUILDING_EXPAT
/* using Expat from an application */
-#ifdef XML_USE_MSC_EXTENSIONS
-#define XMLIMPORT __declspec(dllimport)
-#endif
+# ifdef XML_USE_MSC_EXTENSIONS
+# define XMLIMPORT __declspec(dllimport)
+# endif
-#endif
+# endif
#endif /* not defined XML_STATIC */
#if !defined(XMLIMPORT) && defined(__GNUC__) && (__GNUC__ >= 4)
-#define XMLIMPORT __attribute__ ((visibility ("default")))
+# define XMLIMPORT __attribute__ ((visibility ("default")))
#endif
/* If we didn't define it above, define it away: */
#ifndef XMLIMPORT
-#define XMLIMPORT
+# define XMLIMPORT
#endif
#if defined(__GNUC__) && (__GNUC__ > 2 || (__GNUC__ == 2 && __GNUC_MINOR__ >= 96))
-#define XML_ATTR_MALLOC __attribute__((__malloc__))
+# define XML_ATTR_MALLOC __attribute__((__malloc__))
#else
-#define XML_ATTR_MALLOC
+# define XML_ATTR_MALLOC
#endif
#if defined(__GNUC__) && ((__GNUC__ > 4) || (__GNUC__ == 4 && __GNUC_MINOR__ >= 3))
-#define XML_ATTR_ALLOC_SIZE(x) __attribute__((__alloc_size__(x)))
+# define XML_ATTR_ALLOC_SIZE(x) __attribute__((__alloc_size__(x)))
#else
-#define XML_ATTR_ALLOC_SIZE(x)
+# define XML_ATTR_ALLOC_SIZE(x)
#endif
#define XMLPARSEAPI(type) XMLIMPORT type XMLCALL
@@ -93,30 +121,35 @@ extern "C" {
#endif
#ifdef XML_UNICODE_WCHAR_T
-#define XML_UNICODE
+# ifndef XML_UNICODE
+# define XML_UNICODE
+# endif
+# if defined(__SIZEOF_WCHAR_T__) && (__SIZEOF_WCHAR_T__ != 2)
+# error "sizeof(wchar_t) != 2; Need -fshort-wchar for both Expat and libc"
+# endif
#endif
#ifdef XML_UNICODE /* Information is UTF-16 encoded. */
-#ifdef XML_UNICODE_WCHAR_T
+# ifdef XML_UNICODE_WCHAR_T
typedef wchar_t XML_Char;
typedef wchar_t XML_LChar;
-#else
+# else
typedef unsigned short XML_Char;
typedef char XML_LChar;
-#endif /* XML_UNICODE_WCHAR_T */
+# endif /* XML_UNICODE_WCHAR_T */
#else /* Information is UTF-8 encoded. */
typedef char XML_Char;
typedef char XML_LChar;
#endif /* XML_UNICODE */
#ifdef XML_LARGE_SIZE /* Use large integers for file/stream positions. */
-#if defined(XML_USE_MSC_EXTENSIONS) && _MSC_VER < 1400
+# if defined(XML_USE_MSC_EXTENSIONS) && _MSC_VER < 1400
typedef __int64 XML_Index;
typedef unsigned __int64 XML_Size;
-#else
+# else
typedef long long XML_Index;
typedef unsigned long long XML_Size;
-#endif
+# endif
#else
typedef long XML_Index;
typedef unsigned long XML_Size;
diff --git a/lib/expat_static.vcxproj b/lib/expat_static.vcxproj
new file mode 100644
index 0000000..b4265e0
--- /dev/null
+++ b/lib/expat_static.vcxproj
@@ -0,0 +1,149 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project DefaultTargets="Build" ToolsVersion="15.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+ <ItemGroup Label="ProjectConfigurations">
+ <ProjectConfiguration Include="Debug|Win32">
+ <Configuration>Debug</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Release|Win32">
+ <Configuration>Release</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Template|Win32">
+ <Configuration>Template</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ </ItemGroup>
+ <PropertyGroup Label="Globals">
+ <SccProjectName />
+ <SccLocalPath />
+ <ProjectGuid>{58A821BC-E4AF-4DF4-9A54-2BAA22B92615}</ProjectGuid>
+ <WindowsTargetPlatformVersion>10.0.16299.0</WindowsTargetPlatformVersion>
+ </PropertyGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Template|Win32'" Label="Configuration">
+ <ConfigurationType>Application</ConfigurationType>
+ <PlatformToolset>v141</PlatformToolset>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
+ <ConfigurationType>StaticLibrary</ConfigurationType>
+ <PlatformToolset>v141</PlatformToolset>
+ <UseOfMfc>false</UseOfMfc>
+ <CharacterSet>MultiByte</CharacterSet>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
+ <ConfigurationType>StaticLibrary</ConfigurationType>
+ <PlatformToolset>v141</PlatformToolset>
+ <UseOfMfc>false</UseOfMfc>
+ <CharacterSet>MultiByte</CharacterSet>
+ </PropertyGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
+ <ImportGroup Label="ExtensionSettings">
+ </ImportGroup>
+ <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Template|Win32'">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ </ImportGroup>
+ <ImportGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="PropertySheets">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ <Import Project="$(VCTargetsPath)Microsoft.Cpp.UpgradeFromVC60.props" />
+ </ImportGroup>
+ <ImportGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="PropertySheets">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ <Import Project="$(VCTargetsPath)Microsoft.Cpp.UpgradeFromVC60.props" />
+ </ImportGroup>
+ <PropertyGroup Label="UserMacros" />
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+ <OutDir>.\..\win32\bin\Release\</OutDir>
+ <IntDir>.\..\win32\tmp\Release_static\</IntDir>
+ <LinkIncremental>false</LinkIncremental>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ <OutDir>.\..\win32\bin\Debug\</OutDir>
+ <IntDir>.\..\win32\tmp\Debug_static\</IntDir>
+ <LinkIncremental>true</LinkIncremental>
+ </PropertyGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+ <ClCompile>
+ <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
+ <InlineFunctionExpansion>Default</InlineFunctionExpansion>
+ <StringPooling>true</StringPooling>
+ <FunctionLevelLinking>true</FunctionLevelLinking>
+ <Optimization>MaxSpeed</Optimization>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <WarningLevel>Level3</WarningLevel>
+ <PreprocessorDefinitions>_WINDOWS;NDEBUG;_LIB;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <AssemblerListingLocation>.\..\win32\tmp\Release_static\</AssemblerListingLocation>
+ <PrecompiledHeaderOutputFile>.\..\win32\tmp\Release_static\expat_static.pch</PrecompiledHeaderOutputFile>
+ <ObjectFileName>.\..\win32\tmp\Release_static\</ObjectFileName>
+ <ProgramDataBaseFileName>.\..\win32\tmp\Release_static\</ProgramDataBaseFileName>
+ </ClCompile>
+ <ResourceCompile>
+ <Culture>0x0409</Culture>
+ <PreprocessorDefinitions>NDEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ </ResourceCompile>
+ <Bscmake>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <OutputFile>.\..\win32\bin\Release\expat_static.bsc</OutputFile>
+ </Bscmake>
+ <Lib>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <OutputFile>..\win32\bin\Release\libexpatMT.lib</OutputFile>
+ </Lib>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ <ClCompile>
+ <RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
+ <InlineFunctionExpansion>Default</InlineFunctionExpansion>
+ <FunctionLevelLinking>true</FunctionLevelLinking>
+ <Optimization>Disabled</Optimization>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <WarningLevel>Level3</WarningLevel>
+ <DebugInformationFormat>EditAndContinue</DebugInformationFormat>
+ <PreprocessorDefinitions>_DEBUG;_WINDOWS;_LIB;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <AssemblerListingLocation>.\..\win32\tmp\Debug_static\</AssemblerListingLocation>
+ <BrowseInformation>true</BrowseInformation>
+ <PrecompiledHeaderOutputFile>.\..\win32\tmp\Debug_static\expat_static.pch</PrecompiledHeaderOutputFile>
+ <ObjectFileName>.\..\win32\tmp\Debug_static\</ObjectFileName>
+ <ProgramDataBaseFileName>.\..\win32\tmp\Debug_static\</ProgramDataBaseFileName>
+ <BasicRuntimeChecks>EnableFastChecks</BasicRuntimeChecks>
+ </ClCompile>
+ <ResourceCompile>
+ <Culture>0x0409</Culture>
+ <PreprocessorDefinitions>_DEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ </ResourceCompile>
+ <Bscmake>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <OutputFile>.\..\win32\bin\Debug\expat_static.bsc</OutputFile>
+ </Bscmake>
+ <Lib>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <OutputFile>..\win32\bin\Debug\libexpatMT.lib</OutputFile>
+ </Lib>
+ </ItemDefinitionGroup>
+ <ItemGroup>
+ <ClCompile Include="loadlibrary.c" />
+ <ClCompile Include="xmlparse.c" />
+ <ClCompile Include="xmlrole.c" />
+ <ClCompile Include="xmltok.c" />
+ <ClCompile Include="xmltok_impl.c" />
+ <ClCompile Include="xmltok_ns.c" />
+ </ItemGroup>
+ <ItemGroup>
+ <ClInclude Include="ascii.h" />
+ <ClInclude Include="asciitab.h" />
+ <ClInclude Include="expat.h" />
+ <ClInclude Include="expat_external.h" />
+ <ClInclude Include="iasciitab.h" />
+ <ClInclude Include="internal.h" />
+ <ClInclude Include="latin1tab.h" />
+ <ClInclude Include="nametab.h" />
+ <ClInclude Include="siphash.h" />
+ <ClInclude Include="utf8tab.h" />
+ <ClInclude Include="xmlrole.h" />
+ <ClInclude Include="xmltok.h" />
+ <ClInclude Include="xmltok_impl.h" />
+ </ItemGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
+ <ImportGroup Label="ExtensionTargets">
+ </ImportGroup>
+</Project> \ No newline at end of file
diff --git a/lib/expat_static.vcxproj.filters b/lib/expat_static.vcxproj.filters
new file mode 100644
index 0000000..a2fe03e
--- /dev/null
+++ b/lib/expat_static.vcxproj.filters
@@ -0,0 +1,74 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+ <ItemGroup>
+ <Filter Include="Source Files">
+ <UniqueIdentifier>{ef375f25-3490-4376-8deb-a8a8bebc0194}</UniqueIdentifier>
+ <Extensions>cpp;c;cxx;rc;def;r;odl;idl;hpj;bat</Extensions>
+ </Filter>
+ <Filter Include="Header Files">
+ <UniqueIdentifier>{f1cd6f85-7111-4c1b-abad-37c79851ca34}</UniqueIdentifier>
+ <Extensions>h;hpp;hxx;hm;inl</Extensions>
+ </Filter>
+ </ItemGroup>
+ <ItemGroup>
+ <ClCompile Include="loadlibrary.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="xmlparse.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="xmlrole.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="xmltok.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="xmltok_impl.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="xmltok_ns.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ </ItemGroup>
+ <ItemGroup>
+ <ClInclude Include="ascii.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="asciitab.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="expat.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="expat_external.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="iasciitab.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="internal.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="latin1tab.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="nametab.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="siphash.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="utf8tab.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="xmlrole.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="xmltok.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="xmltok_impl.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ </ItemGroup>
+</Project> \ No newline at end of file
diff --git a/lib/expatw.vcxproj b/lib/expatw.vcxproj
new file mode 100644
index 0000000..c708309
--- /dev/null
+++ b/lib/expatw.vcxproj
@@ -0,0 +1,179 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project DefaultTargets="Build" ToolsVersion="15.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+ <ItemGroup Label="ProjectConfigurations">
+ <ProjectConfiguration Include="Debug|Win32">
+ <Configuration>Debug</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Release|Win32">
+ <Configuration>Release</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Template|Win32">
+ <Configuration>Template</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ </ItemGroup>
+ <PropertyGroup Label="Globals">
+ <SccProjectName />
+ <SccLocalPath />
+ <ProjectGuid>{C04F1C11-7079-48AD-A90B-6F59B7A55BEF}</ProjectGuid>
+ <WindowsTargetPlatformVersion>10.0.16299.0</WindowsTargetPlatformVersion>
+ </PropertyGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Template|Win32'" Label="Configuration">
+ <ConfigurationType>Application</ConfigurationType>
+ <PlatformToolset>v141</PlatformToolset>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
+ <ConfigurationType>DynamicLibrary</ConfigurationType>
+ <PlatformToolset>v141</PlatformToolset>
+ <UseOfMfc>false</UseOfMfc>
+ <CharacterSet>MultiByte</CharacterSet>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
+ <ConfigurationType>DynamicLibrary</ConfigurationType>
+ <PlatformToolset>v141</PlatformToolset>
+ <UseOfMfc>false</UseOfMfc>
+ <CharacterSet>MultiByte</CharacterSet>
+ </PropertyGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
+ <ImportGroup Label="ExtensionSettings">
+ </ImportGroup>
+ <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Template|Win32'">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ </ImportGroup>
+ <ImportGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="PropertySheets">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ <Import Project="$(VCTargetsPath)Microsoft.Cpp.UpgradeFromVC60.props" />
+ </ImportGroup>
+ <ImportGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="PropertySheets">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ <Import Project="$(VCTargetsPath)Microsoft.Cpp.UpgradeFromVC60.props" />
+ </ImportGroup>
+ <PropertyGroup Label="UserMacros" />
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+ <OutDir>.\..\win32\bin\Release\</OutDir>
+ <IntDir>.\..\win32\tmp\Release-w\</IntDir>
+ <LinkIncremental>false</LinkIncremental>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ <OutDir>.\..\win32\bin\Debug\</OutDir>
+ <IntDir>.\..\win32\tmp\Debug-w\</IntDir>
+ <LinkIncremental>true</LinkIncremental>
+ </PropertyGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+ <ClCompile>
+ <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
+ <InlineFunctionExpansion>Default</InlineFunctionExpansion>
+ <StringPooling>true</StringPooling>
+ <FunctionLevelLinking>true</FunctionLevelLinking>
+ <Optimization>MaxSpeed</Optimization>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <WarningLevel>Level3</WarningLevel>
+ <PreprocessorDefinitions>NDEBUG;_WINDOWS;_USRDLL;XML_UNICODE_WCHAR_T;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <AssemblerListingLocation>.\..\win32\tmp\Release-w\</AssemblerListingLocation>
+ <PrecompiledHeaderOutputFile>.\..\win32\tmp\Release-w\expatw.pch</PrecompiledHeaderOutputFile>
+ <PrecompiledHeader />
+ <ObjectFileName>.\..\win32\tmp\Release-w\</ObjectFileName>
+ <ProgramDataBaseFileName>.\..\win32\tmp\Release-w\</ProgramDataBaseFileName>
+ </ClCompile>
+ <Midl>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <PreprocessorDefinitions>NDEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <TypeLibraryName>.\..\win32\bin\Release\expatw.tlb</TypeLibraryName>
+ <MkTypLibCompatible>true</MkTypLibCompatible>
+ <TargetEnvironment>Win32</TargetEnvironment>
+ </Midl>
+ <ResourceCompile>
+ <Culture>0x0409</Culture>
+ <PreprocessorDefinitions>NDEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ </ResourceCompile>
+ <Bscmake>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <OutputFile>.\..\win32\bin\Release\expatw.bsc</OutputFile>
+ </Bscmake>
+ <Link>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <LinkDLL>true</LinkDLL>
+ <SubSystem>Console</SubSystem>
+ <OutputFile>..\win32\bin\Release\libexpatw.dll</OutputFile>
+ <ImportLibrary>.\..\win32\bin\Release\libexpatw.lib</ImportLibrary>
+ <ModuleDefinitionFile>.\libexpatw.def</ModuleDefinitionFile>
+ </Link>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ <ClCompile>
+ <RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
+ <InlineFunctionExpansion>Default</InlineFunctionExpansion>
+ <FunctionLevelLinking>true</FunctionLevelLinking>
+ <Optimization>Disabled</Optimization>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <WarningLevel>Level3</WarningLevel>
+ <DebugInformationFormat>EditAndContinue</DebugInformationFormat>
+ <PreprocessorDefinitions>_DEBUG;_WINDOWS;_USRDLL;XML_UNICODE_WCHAR_T;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <AssemblerListingLocation>.\..\win32\tmp\Debug-w\</AssemblerListingLocation>
+ <BrowseInformation>true</BrowseInformation>
+ <PrecompiledHeaderOutputFile>.\..\win32\tmp\Debug-w\expatw.pch</PrecompiledHeaderOutputFile>
+ <ObjectFileName>.\..\win32\tmp\Debug-w\</ObjectFileName>
+ <ProgramDataBaseFileName>.\..\win32\tmp\Debug-w\</ProgramDataBaseFileName>
+ <BasicRuntimeChecks>EnableFastChecks</BasicRuntimeChecks>
+ </ClCompile>
+ <Midl>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <PreprocessorDefinitions>_DEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <TypeLibraryName>.\..\win32\bin\Debug\expatw.tlb</TypeLibraryName>
+ <MkTypLibCompatible>true</MkTypLibCompatible>
+ <TargetEnvironment>Win32</TargetEnvironment>
+ </Midl>
+ <ResourceCompile>
+ <Culture>0x0409</Culture>
+ <PreprocessorDefinitions>_DEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ </ResourceCompile>
+ <Bscmake>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <OutputFile>.\..\win32\bin\Debug\expatw.bsc</OutputFile>
+ </Bscmake>
+ <Link>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <LinkDLL>true</LinkDLL>
+ <GenerateDebugInformation>true</GenerateDebugInformation>
+ <SubSystem>Console</SubSystem>
+ <OutputFile>..\win32\bin\Debug\libexpatw.dll</OutputFile>
+ <ImportLibrary>.\..\win32\bin\Debug\libexpatw.lib</ImportLibrary>
+ <ModuleDefinitionFile>.\libexpatw.def</ModuleDefinitionFile>
+ </Link>
+ </ItemDefinitionGroup>
+ <ItemGroup>
+ <CustomBuild Include="libexpatw.def" />
+ </ItemGroup>
+ <ItemGroup>
+ <ClCompile Include="loadlibrary.c" />
+ <ClCompile Include="xmlparse.c">
+ <ExceptionHandling Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ </ExceptionHandling>
+ </ClCompile>
+ <ClCompile Include="xmlrole.c" />
+ <ClCompile Include="xmltok.c" />
+ <ClCompile Include="xmltok_impl.c" />
+ <ClCompile Include="xmltok_ns.c" />
+ </ItemGroup>
+ <ItemGroup>
+ <ClInclude Include="ascii.h" />
+ <ClInclude Include="asciitab.h" />
+ <ClInclude Include="expat.h" />
+ <ClInclude Include="expat_external.h" />
+ <ClInclude Include="iasciitab.h" />
+ <ClInclude Include="internal.h" />
+ <ClInclude Include="latin1tab.h" />
+ <ClInclude Include="nametab.h" />
+ <ClInclude Include="siphash.h" />
+ <ClInclude Include="utf8tab.h" />
+ <ClInclude Include="xmlrole.h" />
+ <ClInclude Include="xmltok.h" />
+ <ClInclude Include="xmltok_impl.h" />
+ </ItemGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
+ <ImportGroup Label="ExtensionTargets">
+ </ImportGroup>
+</Project> \ No newline at end of file
diff --git a/lib/expatw.vcxproj.filters b/lib/expatw.vcxproj.filters
new file mode 100644
index 0000000..fb3909c
--- /dev/null
+++ b/lib/expatw.vcxproj.filters
@@ -0,0 +1,83 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+ <ItemGroup>
+ <Filter Include="Source Files">
+ <UniqueIdentifier>{fea8fd20-7d6d-4664-a821-1ab5a29dadbd}</UniqueIdentifier>
+ <Extensions>cpp;c;cxx;rc;def;r;odl;idl;hpj;bat</Extensions>
+ </Filter>
+ <Filter Include="Header Files">
+ <UniqueIdentifier>{0ceb9aa0-672d-4a6b-bff9-345c51aab04c}</UniqueIdentifier>
+ <Extensions>h;hpp;hxx;hm;inl</Extensions>
+ </Filter>
+ <Filter Include="Resource Files">
+ <UniqueIdentifier>{d62ff6fc-7f74-443d-a048-31ef02a6f99f}</UniqueIdentifier>
+ <Extensions>ico;cur;bmp;dlg;rc2;rct;bin;rgs;gif;jpg;jpeg;jpe</Extensions>
+ </Filter>
+ </ItemGroup>
+ <ItemGroup>
+ <ClCompile Include="loadlibrary.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="xmlparse.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="xmlrole.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="xmltok.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="xmltok_impl.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="xmltok_ns.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ </ItemGroup>
+ <ItemGroup>
+ <ClInclude Include="ascii.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="asciitab.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="expat.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="expat_external.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="iasciitab.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="internal.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="latin1tab.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="nametab.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="siphash.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="utf8tab.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="xmlrole.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="xmltok.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="xmltok_impl.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ </ItemGroup>
+ <ItemGroup>
+ <CustomBuild Include="libexpatw.def">
+ <Filter>Source Files</Filter>
+ </CustomBuild>
+ </ItemGroup>
+</Project> \ No newline at end of file
diff --git a/lib/expatw_static.vcxproj b/lib/expatw_static.vcxproj
new file mode 100644
index 0000000..a917b48
--- /dev/null
+++ b/lib/expatw_static.vcxproj
@@ -0,0 +1,149 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project DefaultTargets="Build" ToolsVersion="15.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+ <ItemGroup Label="ProjectConfigurations">
+ <ProjectConfiguration Include="Debug|Win32">
+ <Configuration>Debug</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Release|Win32">
+ <Configuration>Release</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Template|Win32">
+ <Configuration>Template</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ </ItemGroup>
+ <PropertyGroup Label="Globals">
+ <SccProjectName />
+ <SccLocalPath />
+ <ProjectGuid>{9220B0F2-C895-4CB2-91D1-1C16C4ECB759}</ProjectGuid>
+ <WindowsTargetPlatformVersion>10.0.16299.0</WindowsTargetPlatformVersion>
+ </PropertyGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Template|Win32'" Label="Configuration">
+ <ConfigurationType>Application</ConfigurationType>
+ <PlatformToolset>v141</PlatformToolset>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
+ <ConfigurationType>StaticLibrary</ConfigurationType>
+ <PlatformToolset>v141</PlatformToolset>
+ <UseOfMfc>false</UseOfMfc>
+ <CharacterSet>MultiByte</CharacterSet>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
+ <ConfigurationType>StaticLibrary</ConfigurationType>
+ <PlatformToolset>v141</PlatformToolset>
+ <UseOfMfc>false</UseOfMfc>
+ <CharacterSet>MultiByte</CharacterSet>
+ </PropertyGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
+ <ImportGroup Label="ExtensionSettings">
+ </ImportGroup>
+ <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Template|Win32'">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ </ImportGroup>
+ <ImportGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="PropertySheets">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ <Import Project="$(VCTargetsPath)Microsoft.Cpp.UpgradeFromVC60.props" />
+ </ImportGroup>
+ <ImportGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="PropertySheets">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ <Import Project="$(VCTargetsPath)Microsoft.Cpp.UpgradeFromVC60.props" />
+ </ImportGroup>
+ <PropertyGroup Label="UserMacros" />
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ <OutDir>.\..\win32\bin\Debug\</OutDir>
+ <IntDir>.\..\win32\tmp\Debug-w_static\</IntDir>
+ <LinkIncremental>true</LinkIncremental>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+ <OutDir>.\..\win32\bin\Release\</OutDir>
+ <IntDir>.\..\win32\tmp\Release-w_static\</IntDir>
+ <LinkIncremental>false</LinkIncremental>
+ </PropertyGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ <ClCompile>
+ <RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
+ <InlineFunctionExpansion>Default</InlineFunctionExpansion>
+ <FunctionLevelLinking>true</FunctionLevelLinking>
+ <Optimization>Disabled</Optimization>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <WarningLevel>Level3</WarningLevel>
+ <DebugInformationFormat>EditAndContinue</DebugInformationFormat>
+ <PreprocessorDefinitions>_DEBUG;_WINDOWS;_LIB;XML_UNICODE_WCHAR_T;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <AssemblerListingLocation>.\..\win32\tmp\Debug-w_static\</AssemblerListingLocation>
+ <BrowseInformation>true</BrowseInformation>
+ <PrecompiledHeaderOutputFile>.\..\win32\tmp\Debug-w_static\expatw_static.pch</PrecompiledHeaderOutputFile>
+ <ObjectFileName>.\..\win32\tmp\Debug-w_static\</ObjectFileName>
+ <ProgramDataBaseFileName>.\..\win32\tmp\Debug-w_static\</ProgramDataBaseFileName>
+ <BasicRuntimeChecks>EnableFastChecks</BasicRuntimeChecks>
+ </ClCompile>
+ <ResourceCompile>
+ <Culture>0x0409</Culture>
+ <PreprocessorDefinitions>_DEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ </ResourceCompile>
+ <Bscmake>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <OutputFile>.\..\win32\bin\Debug\expatw_static.bsc</OutputFile>
+ </Bscmake>
+ <Lib>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <OutputFile>..\win32\bin\Debug\libexpatwMT.lib</OutputFile>
+ </Lib>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+ <ClCompile>
+ <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
+ <InlineFunctionExpansion>Default</InlineFunctionExpansion>
+ <StringPooling>true</StringPooling>
+ <FunctionLevelLinking>true</FunctionLevelLinking>
+ <Optimization>MaxSpeed</Optimization>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <WarningLevel>Level3</WarningLevel>
+ <PreprocessorDefinitions>_WINDOWS;NDEBUG;_LIB;XML_UNICODE_WCHAR_T;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <AssemblerListingLocation>.\..\win32\tmp\Release-w_static\</AssemblerListingLocation>
+ <PrecompiledHeaderOutputFile>.\..\win32\tmp\Release-w_static\expatw_static.pch</PrecompiledHeaderOutputFile>
+ <ObjectFileName>.\..\win32\tmp\Release-w_static\</ObjectFileName>
+ <ProgramDataBaseFileName>.\..\win32\tmp\Release-w_static\</ProgramDataBaseFileName>
+ </ClCompile>
+ <ResourceCompile>
+ <Culture>0x0409</Culture>
+ <PreprocessorDefinitions>NDEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ </ResourceCompile>
+ <Bscmake>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <OutputFile>.\..\win32\bin\Release\expatw_static.bsc</OutputFile>
+ </Bscmake>
+ <Lib>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <OutputFile>..\win32\bin\Release\libexpatwMT.lib</OutputFile>
+ </Lib>
+ </ItemDefinitionGroup>
+ <ItemGroup>
+ <ClCompile Include="loadlibrary.c" />
+ <ClCompile Include="xmlparse.c" />
+ <ClCompile Include="xmlrole.c" />
+ <ClCompile Include="xmltok.c" />
+ <ClCompile Include="xmltok_impl.c" />
+ <ClCompile Include="xmltok_ns.c" />
+ </ItemGroup>
+ <ItemGroup>
+ <ClInclude Include="ascii.h" />
+ <ClInclude Include="asciitab.h" />
+ <ClInclude Include="expat.h" />
+ <ClInclude Include="expat_external.h" />
+ <ClInclude Include="iasciitab.h" />
+ <ClInclude Include="internal.h" />
+ <ClInclude Include="latin1tab.h" />
+ <ClInclude Include="nametab.h" />
+ <ClInclude Include="siphash.h" />
+ <ClInclude Include="utf8tab.h" />
+ <ClInclude Include="xmlrole.h" />
+ <ClInclude Include="xmltok.h" />
+ <ClInclude Include="xmltok_impl.h" />
+ </ItemGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
+ <ImportGroup Label="ExtensionTargets">
+ </ImportGroup>
+</Project> \ No newline at end of file
diff --git a/lib/expatw_static.vcxproj.filters b/lib/expatw_static.vcxproj.filters
new file mode 100644
index 0000000..724d9f8
--- /dev/null
+++ b/lib/expatw_static.vcxproj.filters
@@ -0,0 +1,74 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+ <ItemGroup>
+ <Filter Include="Source Files">
+ <UniqueIdentifier>{c0226397-04be-42b5-ba75-257ac91ef7fa}</UniqueIdentifier>
+ <Extensions>cpp;c;cxx;rc;def;r;odl;idl;hpj;bat</Extensions>
+ </Filter>
+ <Filter Include="Header Files">
+ <UniqueIdentifier>{3d74dc56-3aec-4ee9-b700-7203f44e015d}</UniqueIdentifier>
+ <Extensions>h;hpp;hxx;hm;inl</Extensions>
+ </Filter>
+ </ItemGroup>
+ <ItemGroup>
+ <ClCompile Include="loadlibrary.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="xmlparse.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="xmlrole.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="xmltok.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="xmltok_impl.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="xmltok_ns.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ </ItemGroup>
+ <ItemGroup>
+ <ClInclude Include="ascii.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="asciitab.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="expat.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="expat_external.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="iasciitab.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="internal.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="latin1tab.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="nametab.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="siphash.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="utf8tab.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="xmlrole.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="xmltok.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="xmltok_impl.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ </ItemGroup>
+</Project> \ No newline at end of file
diff --git a/lib/iasciitab.h b/lib/iasciitab.h
index 24a1d5c..ce4a4bf 100644
--- a/lib/iasciitab.h
+++ b/lib/iasciitab.h
@@ -1,5 +1,33 @@
-/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
- See the file COPYING for copying permission.
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
/* Like asciitab.h, except that 0xD has code BT_S rather than BT_CR */
diff --git a/lib/internal.h b/lib/internal.h
index 94cb98e..e33fdcb 100644
--- a/lib/internal.h
+++ b/lib/internal.h
@@ -18,6 +18,35 @@
Note: Use of these macros is based on judgement, not hard rules,
and therefore subject to change.
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
#if defined(__GNUC__) && defined(__i386__) && !defined(__MINGW32__)
@@ -87,7 +116,7 @@ extern "C" {
void
-align_limit_to_full_utf8_characters(const char * from, const char ** fromLimRef);
+_INTERNAL_trim_to_complete_utf8_characters(const char * from, const char ** fromLimRef);
#ifdef __cplusplus
diff --git a/lib/latin1tab.h b/lib/latin1tab.h
index 53c25d7..95dfa52 100644
--- a/lib/latin1tab.h
+++ b/lib/latin1tab.h
@@ -1,5 +1,33 @@
-/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
- See the file COPYING for copying permission.
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
/* 0x80 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
diff --git a/lib/libexpat.def b/lib/libexpat.def
new file mode 100644
index 0000000..d08f5b7
--- /dev/null
+++ b/lib/libexpat.def
@@ -0,0 +1,78 @@
+; DEF file for MS VC++
+
+LIBRARY
+EXPORTS
+ XML_DefaultCurrent @1
+ XML_ErrorString @2
+ XML_ExpatVersion @3
+ XML_ExpatVersionInfo @4
+ XML_ExternalEntityParserCreate @5
+ XML_GetBase @6
+ XML_GetBuffer @7
+ XML_GetCurrentByteCount @8
+ XML_GetCurrentByteIndex @9
+ XML_GetCurrentColumnNumber @10
+ XML_GetCurrentLineNumber @11
+ XML_GetErrorCode @12
+ XML_GetIdAttributeIndex @13
+ XML_GetInputContext @14
+ XML_GetSpecifiedAttributeCount @15
+ XML_Parse @16
+ XML_ParseBuffer @17
+ XML_ParserCreate @18
+ XML_ParserCreateNS @19
+ XML_ParserCreate_MM @20
+ XML_ParserFree @21
+ XML_SetAttlistDeclHandler @22
+ XML_SetBase @23
+ XML_SetCdataSectionHandler @24
+ XML_SetCharacterDataHandler @25
+ XML_SetCommentHandler @26
+ XML_SetDefaultHandler @27
+ XML_SetDefaultHandlerExpand @28
+ XML_SetDoctypeDeclHandler @29
+ XML_SetElementDeclHandler @30
+ XML_SetElementHandler @31
+ XML_SetEncoding @32
+ XML_SetEndCdataSectionHandler @33
+ XML_SetEndDoctypeDeclHandler @34
+ XML_SetEndElementHandler @35
+ XML_SetEndNamespaceDeclHandler @36
+ XML_SetEntityDeclHandler @37
+ XML_SetExternalEntityRefHandler @38
+ XML_SetExternalEntityRefHandlerArg @39
+ XML_SetNamespaceDeclHandler @40
+ XML_SetNotStandaloneHandler @41
+ XML_SetNotationDeclHandler @42
+ XML_SetParamEntityParsing @43
+ XML_SetProcessingInstructionHandler @44
+ XML_SetReturnNSTriplet @45
+ XML_SetStartCdataSectionHandler @46
+ XML_SetStartDoctypeDeclHandler @47
+ XML_SetStartElementHandler @48
+ XML_SetStartNamespaceDeclHandler @49
+ XML_SetUnknownEncodingHandler @50
+ XML_SetUnparsedEntityDeclHandler @51
+ XML_SetUserData @52
+ XML_SetXmlDeclHandler @53
+ XML_UseParserAsHandlerArg @54
+; added with version 1.95.3
+ XML_ParserReset @55
+ XML_SetSkippedEntityHandler @56
+; added with version 1.95.5
+ XML_GetFeatureList @57
+ XML_UseForeignDTD @58
+; added with version 1.95.6
+ XML_FreeContentModel @59
+ XML_MemMalloc @60
+ XML_MemRealloc @61
+ XML_MemFree @62
+; added with version 1.95.8
+ XML_StopParser @63
+ XML_ResumeParser @64
+ XML_GetParsingStatus @65
+; added with version 2.1.1
+; XML_GetAttributeInfo @66
+ XML_SetHashSalt @67@
+; added with version 2.2.5
+ _INTERNAL_trim_to_complete_utf8_characters @68@ \ No newline at end of file
diff --git a/lib/libexpatw.def b/lib/libexpatw.def
new file mode 100644
index 0000000..928e01b
--- /dev/null
+++ b/lib/libexpatw.def
@@ -0,0 +1,78 @@
+; DEF file for MS VC++
+
+LIBRARY
+EXPORTS
+ XML_DefaultCurrent @1
+ XML_ErrorString @2
+ XML_ExpatVersion @3
+ XML_ExpatVersionInfo @4
+ XML_ExternalEntityParserCreate @5
+ XML_GetBase @6
+ XML_GetBuffer @7
+ XML_GetCurrentByteCount @8
+ XML_GetCurrentByteIndex @9
+ XML_GetCurrentColumnNumber @10
+ XML_GetCurrentLineNumber @11
+ XML_GetErrorCode @12
+ XML_GetIdAttributeIndex @13
+ XML_GetInputContext @14
+ XML_GetSpecifiedAttributeCount @15
+ XML_Parse @16
+ XML_ParseBuffer @17
+ XML_ParserCreate @18
+ XML_ParserCreateNS @19
+ XML_ParserCreate_MM @20
+ XML_ParserFree @21
+ XML_SetAttlistDeclHandler @22
+ XML_SetBase @23
+ XML_SetCdataSectionHandler @24
+ XML_SetCharacterDataHandler @25
+ XML_SetCommentHandler @26
+ XML_SetDefaultHandler @27
+ XML_SetDefaultHandlerExpand @28
+ XML_SetDoctypeDeclHandler @29
+ XML_SetElementDeclHandler @30
+ XML_SetElementHandler @31
+ XML_SetEncoding @32
+ XML_SetEndCdataSectionHandler @33
+ XML_SetEndDoctypeDeclHandler @34
+ XML_SetEndElementHandler @35
+ XML_SetEndNamespaceDeclHandler @36
+ XML_SetEntityDeclHandler @37
+ XML_SetExternalEntityRefHandler @38
+ XML_SetExternalEntityRefHandlerArg @39
+ XML_SetNamespaceDeclHandler @40
+ XML_SetNotStandaloneHandler @41
+ XML_SetNotationDeclHandler @42
+ XML_SetParamEntityParsing @43
+ XML_SetProcessingInstructionHandler @44
+ XML_SetReturnNSTriplet @45
+ XML_SetStartCdataSectionHandler @46
+ XML_SetStartDoctypeDeclHandler @47
+ XML_SetStartElementHandler @48
+ XML_SetStartNamespaceDeclHandler @49
+ XML_SetUnknownEncodingHandler @50
+ XML_SetUnparsedEntityDeclHandler @51
+ XML_SetUserData @52
+ XML_SetXmlDeclHandler @53
+ XML_UseParserAsHandlerArg @54
+; added with version 1.95.3
+ XML_ParserReset @55
+ XML_SetSkippedEntityHandler @56
+; added with version 1.95.5
+ XML_GetFeatureList @57
+ XML_UseForeignDTD @58
+; added with version 1.95.6
+ XML_FreeContentModel @59
+ XML_MemMalloc @60
+ XML_MemRealloc @61
+ XML_MemFree @62
+; added with version 1.95.8
+ XML_StopParser @63
+ XML_ResumeParser @64
+ XML_GetParsingStatus @65
+; added with version 2.1.1
+; XML_GetAttributeInfo @66
+ XML_SetHashSalt @67@
+; added with version 2.2.5
+ _INTERNAL_trim_to_complete_utf8_characters @68@
diff --git a/lib/loadlibrary.c b/lib/loadlibrary.c
new file mode 100644
index 0000000..35fdf98
--- /dev/null
+++ b/lib/loadlibrary.c
@@ -0,0 +1,143 @@
+/***************************************************************************
+ * _ _ ____ _
+ * Project ___| | | | _ \| |
+ * / __| | | | |_) | |
+ * | (__| |_| | _ <| |___
+ * \___|\___/|_| \_\_____|
+ *
+ * Copyright (C) 2016 - 2017, Steve Holme, <steve_holme@hotmail.com>.
+ * Copyright (C) 2017, Expat development team
+ *
+ * All rights reserved.
+ * Licensed under the MIT license:
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF
+ * THIRD PARTY RIGHTS. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+ * LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF
+ * CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH
+ * THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Except as contained in this notice, the name of a copyright holder shall
+ * not be used in advertising or otherwise to promote the sale, use or other
+ * dealings in this Software without prior written authorization of the
+ * copyright holder.
+ *
+ ***************************************************************************/
+
+#if defined(_WIN32)
+
+#include <windows.h>
+#include <tchar.h>
+
+
+HMODULE _Expat_LoadLibrary(LPCTSTR filename);
+
+
+#if !defined(LOAD_WITH_ALTERED_SEARCH_PATH)
+#define LOAD_WITH_ALTERED_SEARCH_PATH 0x00000008
+#endif
+
+#if !defined(LOAD_LIBRARY_SEARCH_SYSTEM32)
+#define LOAD_LIBRARY_SEARCH_SYSTEM32 0x00000800
+#endif
+
+/* We use our own typedef here since some headers might lack these */
+typedef HMODULE (APIENTRY *LOADLIBRARYEX_FN)(LPCTSTR, HANDLE, DWORD);
+
+/* See function definitions in winbase.h */
+#ifdef UNICODE
+# ifdef _WIN32_WCE
+# define LOADLIBARYEX L"LoadLibraryExW"
+# else
+# define LOADLIBARYEX "LoadLibraryExW"
+# endif
+#else
+# define LOADLIBARYEX "LoadLibraryExA"
+#endif
+
+
+/*
+ * _Expat_LoadLibrary()
+ *
+ * This is used to dynamically load DLLs using the most secure method available
+ * for the version of Windows that we are running on.
+ *
+ * Parameters:
+ *
+ * filename [in] - The filename or full path of the DLL to load. If only the
+ * filename is passed then the DLL will be loaded from the
+ * Windows system directory.
+ *
+ * Returns the handle of the module on success; otherwise NULL.
+ */
+HMODULE _Expat_LoadLibrary(LPCTSTR filename)
+{
+ HMODULE hModule = NULL;
+ LOADLIBRARYEX_FN pLoadLibraryEx = NULL;
+
+ /* Get a handle to kernel32 so we can access it's functions at runtime */
+ HMODULE hKernel32 = GetModuleHandle(TEXT("kernel32"));
+ if(!hKernel32)
+ return NULL; /* LCOV_EXCL_LINE */
+
+ /* Attempt to find LoadLibraryEx() which is only available on Windows 2000
+ and above */
+ pLoadLibraryEx = (LOADLIBRARYEX_FN) GetProcAddress(hKernel32, LOADLIBARYEX);
+
+ /* Detect if there's already a path in the filename and load the library if
+ there is. Note: Both back slashes and forward slashes have been supported
+ since the earlier days of DOS at an API level although they are not
+ supported by command prompt */
+ if(_tcspbrk(filename, TEXT("\\/"))) {
+ /** !checksrc! disable BANNEDFUNC 1 **/
+ hModule = pLoadLibraryEx ?
+ pLoadLibraryEx(filename, NULL, LOAD_WITH_ALTERED_SEARCH_PATH) :
+ LoadLibrary(filename);
+ }
+ /* Detect if KB2533623 is installed, as LOAD_LIBARY_SEARCH_SYSTEM32 is only
+ supported on Windows Vista, Windows Server 2008, Windows 7 and Windows
+ Server 2008 R2 with this patch or natively on Windows 8 and above */
+ else if(pLoadLibraryEx && GetProcAddress(hKernel32, "AddDllDirectory")) {
+ /* Load the DLL from the Windows system directory */
+ hModule = pLoadLibraryEx(filename, NULL, LOAD_LIBRARY_SEARCH_SYSTEM32);
+ }
+ else {
+ /* Attempt to get the Windows system path */
+ UINT systemdirlen = GetSystemDirectory(NULL, 0);
+ if(systemdirlen) {
+ /* Allocate space for the full DLL path (Room for the null terminator
+ is included in systemdirlen) */
+ size_t filenamelen = _tcslen(filename);
+ TCHAR *path = malloc(sizeof(TCHAR) * (systemdirlen + 1 + filenamelen));
+ if(path && GetSystemDirectory(path, systemdirlen)) {
+ /* Calculate the full DLL path */
+ _tcscpy(path + _tcslen(path), TEXT("\\"));
+ _tcscpy(path + _tcslen(path), filename);
+
+ /* Load the DLL from the Windows system directory */
+ /** !checksrc! disable BANNEDFUNC 1 **/
+ hModule = pLoadLibraryEx ?
+ pLoadLibraryEx(path, NULL, LOAD_WITH_ALTERED_SEARCH_PATH) :
+ LoadLibrary(path);
+
+ }
+ free(path);
+ }
+ }
+
+ return hModule;
+}
+
+#else /* defined(_WIN32) */
+
+/* ISO C requires a translation unit to contain at least one declaration
+ [-Wempty-translation-unit] */
+typedef int _TRANSLATION_UNIT_LOAD_LIBRARY_C_NOT_EMTPY;
+
+#endif /* defined(_WIN32) */
diff --git a/lib/nametab.h b/lib/nametab.h
index b05e62c..bfa2bd3 100644
--- a/lib/nametab.h
+++ b/lib/nametab.h
@@ -1,3 +1,35 @@
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
static const unsigned namingBitmap[] = {
0x00000000, 0x00000000, 0x00000000, 0x00000000,
0x00000000, 0x00000000, 0x00000000, 0x00000000,
diff --git a/lib/siphash.h b/lib/siphash.h
new file mode 100644
index 0000000..581872d
--- /dev/null
+++ b/lib/siphash.h
@@ -0,0 +1,374 @@
+/* ==========================================================================
+ * siphash.h - SipHash-2-4 in a single header file
+ * --------------------------------------------------------------------------
+ * Derived by William Ahern from the reference implementation[1] published[2]
+ * by Jean-Philippe Aumasson and Daniel J. Berstein.
+ * Minimal changes by Sebastian Pipping and Victor Stinner on top, see below.
+ * Licensed under the CC0 Public Domain Dedication license.
+ *
+ * 1. https://www.131002.net/siphash/siphash24.c
+ * 2. https://www.131002.net/siphash/
+ * --------------------------------------------------------------------------
+ * HISTORY:
+ *
+ * 2017-07-25 (Vadim Zeitlin)
+ * - Fix use of SIPHASH_MAIN macro
+ *
+ * 2017-07-05 (Sebastian Pipping)
+ * - Use _SIP_ULL macro to not require a C++11 compiler if compiled as C++
+ * - Add const qualifiers at two places
+ * - Ensure <=80 characters line length (assuming tab width 4)
+ *
+ * 2017-06-23 (Victor Stinner)
+ * - Address Win64 compile warnings
+ *
+ * 2017-06-18 (Sebastian Pipping)
+ * - Clarify license note in the header
+ * - Address C89 issues:
+ * - Stop using inline keyword (and let compiler decide)
+ * - Replace _Bool by int
+ * - Turn macro siphash24 into a function
+ * - Address invalid conversion (void pointer) by explicit cast
+ * - Address lack of stdint.h for Visual Studio 2003 to 2008
+ * - Always expose sip24_valid (for self-tests)
+ *
+ * 2012-11-04 - Born. (William Ahern)
+ * --------------------------------------------------------------------------
+ * USAGE:
+ *
+ * SipHash-2-4 takes as input two 64-bit words as the key, some number of
+ * message bytes, and outputs a 64-bit word as the message digest. This
+ * implementation employs two data structures: a struct sipkey for
+ * representing the key, and a struct siphash for representing the hash
+ * state.
+ *
+ * For converting a 16-byte unsigned char array to a key, use either the
+ * macro sip_keyof or the routine sip_tokey. The former instantiates a
+ * compound literal key, while the latter requires a key object as a
+ * parameter.
+ *
+ * unsigned char secret[16];
+ * arc4random_buf(secret, sizeof secret);
+ * struct sipkey *key = sip_keyof(secret);
+ *
+ * For hashing a message, use either the convenience macro siphash24 or the
+ * routines sip24_init, sip24_update, and sip24_final.
+ *
+ * struct siphash state;
+ * void *msg;
+ * size_t len;
+ * uint64_t hash;
+ *
+ * sip24_init(&state, key);
+ * sip24_update(&state, msg, len);
+ * hash = sip24_final(&state);
+ *
+ * or
+ *
+ * hash = siphash24(msg, len, key);
+ *
+ * To convert the 64-bit hash value to a canonical 8-byte little-endian
+ * binary representation, use either the macro sip_binof or the routine
+ * sip_tobin. The former instantiates and returns a compound literal array,
+ * while the latter requires an array object as a parameter.
+ * --------------------------------------------------------------------------
+ * NOTES:
+ *
+ * o Neither sip_keyof, sip_binof, nor siphash24 will work with compilers
+ * lacking compound literal support. Instead, you must use the lower-level
+ * interfaces which take as parameters the temporary state objects.
+ *
+ * o Uppercase macros may evaluate parameters more than once. Lowercase
+ * macros should not exhibit any such side effects.
+ * ==========================================================================
+ */
+#ifndef SIPHASH_H
+#define SIPHASH_H
+
+#include <stddef.h> /* size_t */
+
+#if defined(_WIN32) && defined(_MSC_VER) && (_MSC_VER < 1600)
+ /* For vs2003/7.1 up to vs2008/9.0; _MSC_VER 1600 is vs2010/10.0 */
+ typedef unsigned __int8 uint8_t;
+ typedef unsigned __int32 uint32_t;
+ typedef unsigned __int64 uint64_t;
+#else
+ #include <stdint.h> /* uint64_t uint32_t uint8_t */
+#endif
+
+
+/*
+ * Workaround to not require a C++11 compiler for using ULL suffix
+ * if this code is included and compiled as C++; related GCC warning is:
+ * warning: use of C++11 long long integer constant [-Wlong-long]
+ */
+#define _SIP_ULL(high, low) (((uint64_t)high << 32) | low)
+
+
+#define SIP_ROTL(x, b) (uint64_t)(((x) << (b)) | ( (x) >> (64 - (b))))
+
+#define SIP_U32TO8_LE(p, v) \
+ (p)[0] = (uint8_t)((v) >> 0); (p)[1] = (uint8_t)((v) >> 8); \
+ (p)[2] = (uint8_t)((v) >> 16); (p)[3] = (uint8_t)((v) >> 24);
+
+#define SIP_U64TO8_LE(p, v) \
+ SIP_U32TO8_LE((p) + 0, (uint32_t)((v) >> 0)); \
+ SIP_U32TO8_LE((p) + 4, (uint32_t)((v) >> 32));
+
+#define SIP_U8TO64_LE(p) \
+ (((uint64_t)((p)[0]) << 0) | \
+ ((uint64_t)((p)[1]) << 8) | \
+ ((uint64_t)((p)[2]) << 16) | \
+ ((uint64_t)((p)[3]) << 24) | \
+ ((uint64_t)((p)[4]) << 32) | \
+ ((uint64_t)((p)[5]) << 40) | \
+ ((uint64_t)((p)[6]) << 48) | \
+ ((uint64_t)((p)[7]) << 56))
+
+
+#define SIPHASH_INITIALIZER { 0, 0, 0, 0, { 0 }, 0, 0 }
+
+struct siphash {
+ uint64_t v0, v1, v2, v3;
+
+ unsigned char buf[8], *p;
+ uint64_t c;
+}; /* struct siphash */
+
+
+#define SIP_KEYLEN 16
+
+struct sipkey {
+ uint64_t k[2];
+}; /* struct sipkey */
+
+#define sip_keyof(k) sip_tokey(&(struct sipkey){ { 0 } }, (k))
+
+static struct sipkey *sip_tokey(struct sipkey *key, const void *src) {
+ key->k[0] = SIP_U8TO64_LE((const unsigned char *)src);
+ key->k[1] = SIP_U8TO64_LE((const unsigned char *)src + 8);
+ return key;
+} /* sip_tokey() */
+
+
+#define sip_binof(v) sip_tobin((unsigned char[8]){ 0 }, (v))
+
+static void *sip_tobin(void *dst, uint64_t u64) {
+ SIP_U64TO8_LE((unsigned char *)dst, u64);
+ return dst;
+} /* sip_tobin() */
+
+
+static void sip_round(struct siphash *H, const int rounds) {
+ int i;
+
+ for (i = 0; i < rounds; i++) {
+ H->v0 += H->v1;
+ H->v1 = SIP_ROTL(H->v1, 13);
+ H->v1 ^= H->v0;
+ H->v0 = SIP_ROTL(H->v0, 32);
+
+ H->v2 += H->v3;
+ H->v3 = SIP_ROTL(H->v3, 16);
+ H->v3 ^= H->v2;
+
+ H->v0 += H->v3;
+ H->v3 = SIP_ROTL(H->v3, 21);
+ H->v3 ^= H->v0;
+
+ H->v2 += H->v1;
+ H->v1 = SIP_ROTL(H->v1, 17);
+ H->v1 ^= H->v2;
+ H->v2 = SIP_ROTL(H->v2, 32);
+ }
+} /* sip_round() */
+
+
+static struct siphash *sip24_init(struct siphash *H,
+ const struct sipkey *key) {
+ H->v0 = _SIP_ULL(0x736f6d65U, 0x70736575U) ^ key->k[0];
+ H->v1 = _SIP_ULL(0x646f7261U, 0x6e646f6dU) ^ key->k[1];
+ H->v2 = _SIP_ULL(0x6c796765U, 0x6e657261U) ^ key->k[0];
+ H->v3 = _SIP_ULL(0x74656462U, 0x79746573U) ^ key->k[1];
+
+ H->p = H->buf;
+ H->c = 0;
+
+ return H;
+} /* sip24_init() */
+
+
+#define sip_endof(a) (&(a)[sizeof (a) / sizeof *(a)])
+
+static struct siphash *sip24_update(struct siphash *H, const void *src,
+ size_t len) {
+ const unsigned char *p = (const unsigned char *)src, *pe = p + len;
+ uint64_t m;
+
+ do {
+ while (p < pe && H->p < sip_endof(H->buf))
+ *H->p++ = *p++;
+
+ if (H->p < sip_endof(H->buf))
+ break;
+
+ m = SIP_U8TO64_LE(H->buf);
+ H->v3 ^= m;
+ sip_round(H, 2);
+ H->v0 ^= m;
+
+ H->p = H->buf;
+ H->c += 8;
+ } while (p < pe);
+
+ return H;
+} /* sip24_update() */
+
+
+static uint64_t sip24_final(struct siphash *H) {
+ const char left = (char)(H->p - H->buf);
+ uint64_t b = (H->c + left) << 56;
+
+ switch (left) {
+ case 7: b |= (uint64_t)H->buf[6] << 48;
+ case 6: b |= (uint64_t)H->buf[5] << 40;
+ case 5: b |= (uint64_t)H->buf[4] << 32;
+ case 4: b |= (uint64_t)H->buf[3] << 24;
+ case 3: b |= (uint64_t)H->buf[2] << 16;
+ case 2: b |= (uint64_t)H->buf[1] << 8;
+ case 1: b |= (uint64_t)H->buf[0] << 0;
+ case 0: break;
+ }
+
+ H->v3 ^= b;
+ sip_round(H, 2);
+ H->v0 ^= b;
+ H->v2 ^= 0xff;
+ sip_round(H, 4);
+
+ return H->v0 ^ H->v1 ^ H->v2 ^ H->v3;
+} /* sip24_final() */
+
+
+static uint64_t siphash24(const void *src, size_t len,
+ const struct sipkey *key) {
+ struct siphash state = SIPHASH_INITIALIZER;
+ return sip24_final(sip24_update(sip24_init(&state, key), src, len));
+} /* siphash24() */
+
+
+/*
+ * SipHash-2-4 output with
+ * k = 00 01 02 ...
+ * and
+ * in = (empty string)
+ * in = 00 (1 byte)
+ * in = 00 01 (2 bytes)
+ * in = 00 01 02 (3 bytes)
+ * ...
+ * in = 00 01 02 ... 3e (63 bytes)
+ */
+static int sip24_valid(void) {
+ static const unsigned char vectors[64][8] = {
+ { 0x31, 0x0e, 0x0e, 0xdd, 0x47, 0xdb, 0x6f, 0x72, },
+ { 0xfd, 0x67, 0xdc, 0x93, 0xc5, 0x39, 0xf8, 0x74, },
+ { 0x5a, 0x4f, 0xa9, 0xd9, 0x09, 0x80, 0x6c, 0x0d, },
+ { 0x2d, 0x7e, 0xfb, 0xd7, 0x96, 0x66, 0x67, 0x85, },
+ { 0xb7, 0x87, 0x71, 0x27, 0xe0, 0x94, 0x27, 0xcf, },
+ { 0x8d, 0xa6, 0x99, 0xcd, 0x64, 0x55, 0x76, 0x18, },
+ { 0xce, 0xe3, 0xfe, 0x58, 0x6e, 0x46, 0xc9, 0xcb, },
+ { 0x37, 0xd1, 0x01, 0x8b, 0xf5, 0x00, 0x02, 0xab, },
+ { 0x62, 0x24, 0x93, 0x9a, 0x79, 0xf5, 0xf5, 0x93, },
+ { 0xb0, 0xe4, 0xa9, 0x0b, 0xdf, 0x82, 0x00, 0x9e, },
+ { 0xf3, 0xb9, 0xdd, 0x94, 0xc5, 0xbb, 0x5d, 0x7a, },
+ { 0xa7, 0xad, 0x6b, 0x22, 0x46, 0x2f, 0xb3, 0xf4, },
+ { 0xfb, 0xe5, 0x0e, 0x86, 0xbc, 0x8f, 0x1e, 0x75, },
+ { 0x90, 0x3d, 0x84, 0xc0, 0x27, 0x56, 0xea, 0x14, },
+ { 0xee, 0xf2, 0x7a, 0x8e, 0x90, 0xca, 0x23, 0xf7, },
+ { 0xe5, 0x45, 0xbe, 0x49, 0x61, 0xca, 0x29, 0xa1, },
+ { 0xdb, 0x9b, 0xc2, 0x57, 0x7f, 0xcc, 0x2a, 0x3f, },
+ { 0x94, 0x47, 0xbe, 0x2c, 0xf5, 0xe9, 0x9a, 0x69, },
+ { 0x9c, 0xd3, 0x8d, 0x96, 0xf0, 0xb3, 0xc1, 0x4b, },
+ { 0xbd, 0x61, 0x79, 0xa7, 0x1d, 0xc9, 0x6d, 0xbb, },
+ { 0x98, 0xee, 0xa2, 0x1a, 0xf2, 0x5c, 0xd6, 0xbe, },
+ { 0xc7, 0x67, 0x3b, 0x2e, 0xb0, 0xcb, 0xf2, 0xd0, },
+ { 0x88, 0x3e, 0xa3, 0xe3, 0x95, 0x67, 0x53, 0x93, },
+ { 0xc8, 0xce, 0x5c, 0xcd, 0x8c, 0x03, 0x0c, 0xa8, },
+ { 0x94, 0xaf, 0x49, 0xf6, 0xc6, 0x50, 0xad, 0xb8, },
+ { 0xea, 0xb8, 0x85, 0x8a, 0xde, 0x92, 0xe1, 0xbc, },
+ { 0xf3, 0x15, 0xbb, 0x5b, 0xb8, 0x35, 0xd8, 0x17, },
+ { 0xad, 0xcf, 0x6b, 0x07, 0x63, 0x61, 0x2e, 0x2f, },
+ { 0xa5, 0xc9, 0x1d, 0xa7, 0xac, 0xaa, 0x4d, 0xde, },
+ { 0x71, 0x65, 0x95, 0x87, 0x66, 0x50, 0xa2, 0xa6, },
+ { 0x28, 0xef, 0x49, 0x5c, 0x53, 0xa3, 0x87, 0xad, },
+ { 0x42, 0xc3, 0x41, 0xd8, 0xfa, 0x92, 0xd8, 0x32, },
+ { 0xce, 0x7c, 0xf2, 0x72, 0x2f, 0x51, 0x27, 0x71, },
+ { 0xe3, 0x78, 0x59, 0xf9, 0x46, 0x23, 0xf3, 0xa7, },
+ { 0x38, 0x12, 0x05, 0xbb, 0x1a, 0xb0, 0xe0, 0x12, },
+ { 0xae, 0x97, 0xa1, 0x0f, 0xd4, 0x34, 0xe0, 0x15, },
+ { 0xb4, 0xa3, 0x15, 0x08, 0xbe, 0xff, 0x4d, 0x31, },
+ { 0x81, 0x39, 0x62, 0x29, 0xf0, 0x90, 0x79, 0x02, },
+ { 0x4d, 0x0c, 0xf4, 0x9e, 0xe5, 0xd4, 0xdc, 0xca, },
+ { 0x5c, 0x73, 0x33, 0x6a, 0x76, 0xd8, 0xbf, 0x9a, },
+ { 0xd0, 0xa7, 0x04, 0x53, 0x6b, 0xa9, 0x3e, 0x0e, },
+ { 0x92, 0x59, 0x58, 0xfc, 0xd6, 0x42, 0x0c, 0xad, },
+ { 0xa9, 0x15, 0xc2, 0x9b, 0xc8, 0x06, 0x73, 0x18, },
+ { 0x95, 0x2b, 0x79, 0xf3, 0xbc, 0x0a, 0xa6, 0xd4, },
+ { 0xf2, 0x1d, 0xf2, 0xe4, 0x1d, 0x45, 0x35, 0xf9, },
+ { 0x87, 0x57, 0x75, 0x19, 0x04, 0x8f, 0x53, 0xa9, },
+ { 0x10, 0xa5, 0x6c, 0xf5, 0xdf, 0xcd, 0x9a, 0xdb, },
+ { 0xeb, 0x75, 0x09, 0x5c, 0xcd, 0x98, 0x6c, 0xd0, },
+ { 0x51, 0xa9, 0xcb, 0x9e, 0xcb, 0xa3, 0x12, 0xe6, },
+ { 0x96, 0xaf, 0xad, 0xfc, 0x2c, 0xe6, 0x66, 0xc7, },
+ { 0x72, 0xfe, 0x52, 0x97, 0x5a, 0x43, 0x64, 0xee, },
+ { 0x5a, 0x16, 0x45, 0xb2, 0x76, 0xd5, 0x92, 0xa1, },
+ { 0xb2, 0x74, 0xcb, 0x8e, 0xbf, 0x87, 0x87, 0x0a, },
+ { 0x6f, 0x9b, 0xb4, 0x20, 0x3d, 0xe7, 0xb3, 0x81, },
+ { 0xea, 0xec, 0xb2, 0xa3, 0x0b, 0x22, 0xa8, 0x7f, },
+ { 0x99, 0x24, 0xa4, 0x3c, 0xc1, 0x31, 0x57, 0x24, },
+ { 0xbd, 0x83, 0x8d, 0x3a, 0xaf, 0xbf, 0x8d, 0xb7, },
+ { 0x0b, 0x1a, 0x2a, 0x32, 0x65, 0xd5, 0x1a, 0xea, },
+ { 0x13, 0x50, 0x79, 0xa3, 0x23, 0x1c, 0xe6, 0x60, },
+ { 0x93, 0x2b, 0x28, 0x46, 0xe4, 0xd7, 0x06, 0x66, },
+ { 0xe1, 0x91, 0x5f, 0x5c, 0xb1, 0xec, 0xa4, 0x6c, },
+ { 0xf3, 0x25, 0x96, 0x5c, 0xa1, 0x6d, 0x62, 0x9f, },
+ { 0x57, 0x5f, 0xf2, 0x8e, 0x60, 0x38, 0x1b, 0xe5, },
+ { 0x72, 0x45, 0x06, 0xeb, 0x4c, 0x32, 0x8a, 0x95, }
+ };
+ unsigned char in[64];
+ struct sipkey k;
+ size_t i;
+
+ sip_tokey(&k, "\000\001\002\003\004\005\006\007\010\011"
+ "\012\013\014\015\016\017");
+
+ for (i = 0; i < sizeof in; ++i) {
+ in[i] = (unsigned char)i;
+
+ if (siphash24(in, i, &k) != SIP_U8TO64_LE(vectors[i]))
+ return 0;
+ }
+
+ return 1;
+} /* sip24_valid() */
+
+
+#ifdef SIPHASH_MAIN
+
+#include <stdio.h>
+
+int main(void) {
+ const int ok = sip24_valid();
+
+ if (ok)
+ puts("OK");
+ else
+ puts("FAIL");
+
+ return !ok;
+} /* main() */
+
+#endif /* SIPHASH_MAIN */
+
+
+#endif /* SIPHASH_H */
diff --git a/lib/utf8tab.h b/lib/utf8tab.h
index 7bb3e77..fa0bed6 100644
--- a/lib/utf8tab.h
+++ b/lib/utf8tab.h
@@ -1,7 +1,34 @@
-/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
- See the file COPYING for copying permission.
-*/
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
/* 0x80 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
/* 0x84 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL,
diff --git a/lib/winconfig.h b/lib/winconfig.h
new file mode 100644
index 0000000..17fea46
--- /dev/null
+++ b/lib/winconfig.h
@@ -0,0 +1,63 @@
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+#ifndef WINCONFIG_H
+#define WINCONFIG_H
+
+#define WIN32_LEAN_AND_MEAN
+#include <windows.h>
+#undef WIN32_LEAN_AND_MEAN
+
+#include <memory.h>
+#include <string.h>
+
+
+#if defined(HAVE_EXPAT_CONFIG_H) /* e.g. MinGW */
+# include <expat_config.h>
+#else /* !defined(HAVE_EXPAT_CONFIG_H) */
+
+
+#define XML_NS 1
+#define XML_DTD 1
+#define XML_CONTEXT_BYTES 1024
+
+/* we will assume all Windows platforms are little endian */
+#define BYTEORDER 1234
+
+/* Windows has memmove() available. */
+#define HAVE_MEMMOVE
+
+
+#endif /* !defined(HAVE_EXPAT_CONFIG_H) */
+
+
+#endif /* ndef WINCONFIG_H */
diff --git a/lib/xmlparse.c b/lib/xmlparse.c
index 2f4e725..90a237f 100644
--- a/lib/xmlparse.c
+++ b/lib/xmlparse.c
@@ -1,37 +1,115 @@
-/* Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd
- See the file COPYING for copying permission.
+/* 4b74aa710b4ed5ce464b0ce544852cb47bf905c85a49c7bae2749f5885cb966d (2.2.5+)
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
+#if !defined(_GNU_SOURCE)
+# define _GNU_SOURCE 1 /* syscall prototype */
+#endif
+
#include <stddef.h>
-#include <stdint.h>
#include <string.h> /* memset(), memcpy() */
#include <assert.h>
#include <limits.h> /* UINT_MAX */
+#include <stdio.h> /* fprintf */
+#include <stdlib.h> /* getenv */
-#ifdef COMPILED_FROM_DSP
+#ifdef _WIN32
#define getpid GetCurrentProcessId
#else
#include <sys/time.h> /* gettimeofday() */
#include <sys/types.h> /* getpid() */
#include <unistd.h> /* getpid() */
+#include <fcntl.h> /* O_RDONLY */
+#include <errno.h>
#endif
#define XML_BUILDING_EXPAT 1
-#ifdef COMPILED_FROM_DSP
+#ifdef _WIN32
#include "winconfig.h"
-#elif defined(MACOS_CLASSIC)
-#include "macconfig.h"
-#elif defined(__amigaos__)
-#include "amigaconfig.h"
-#elif defined(__WATCOMC__)
-#include "watcomconfig.h"
#elif defined(HAVE_EXPAT_CONFIG_H)
#include <expat_config.h>
-#endif /* ndef COMPILED_FROM_DSP */
+#endif /* ndef _WIN32 */
#include "ascii.h"
#include "expat.h"
+#include "siphash.h"
+
+#if defined(HAVE_GETRANDOM) || defined(HAVE_SYSCALL_GETRANDOM)
+# if defined(HAVE_GETRANDOM)
+# include <sys/random.h> /* getrandom */
+# else
+# include <unistd.h> /* syscall */
+# include <sys/syscall.h> /* SYS_getrandom */
+# endif
+# if ! defined(GRND_NONBLOCK)
+# define GRND_NONBLOCK 0x0001
+# endif /* defined(GRND_NONBLOCK) */
+#endif /* defined(HAVE_GETRANDOM) || defined(HAVE_SYSCALL_GETRANDOM) */
+
+#if defined(HAVE_LIBBSD) \
+ && (defined(HAVE_ARC4RANDOM_BUF) || defined(HAVE_ARC4RANDOM))
+# include <bsd/stdlib.h>
+#endif
+
+#if defined(_WIN32) && !defined(LOAD_LIBRARY_SEARCH_SYSTEM32)
+# define LOAD_LIBRARY_SEARCH_SYSTEM32 0x00000800
+#endif
+
+#if !defined(HAVE_GETRANDOM) && !defined(HAVE_SYSCALL_GETRANDOM) \
+ && !defined(HAVE_ARC4RANDOM_BUF) && !defined(HAVE_ARC4RANDOM) \
+ && !defined(XML_DEV_URANDOM) \
+ && !defined(_WIN32) \
+ && !defined(XML_POOR_ENTROPY)
+# error \
+ You do not have support for any sources of high quality entropy \
+ enabled. For end user security, that is probably not what you want. \
+ \
+ Your options include: \
+ * Linux + glibc >=2.25 (getrandom): HAVE_GETRANDOM, \
+ * Linux + glibc <2.25 (syscall SYS_getrandom): HAVE_SYSCALL_GETRANDOM, \
+ * BSD / macOS >=10.7 (arc4random_buf): HAVE_ARC4RANDOM_BUF, \
+ * BSD / macOS <10.7 (arc4random): HAVE_ARC4RANDOM, \
+ * libbsd (arc4random_buf): HAVE_ARC4RANDOM_BUF + HAVE_LIBBSD, \
+ * libbsd (arc4random): HAVE_ARC4RANDOM + HAVE_LIBBSD, \
+ * Linux / BSD / macOS (/dev/urandom): XML_DEV_URANDOM \
+ * Windows (RtlGenRandom): _WIN32. \
+ \
+ If insist on not using any of these, bypass this error by defining \
+ XML_POOR_ENTROPY; you have been warned. \
+ \
+ If you have reasons to patch this detection code away or need changes \
+ to the build system, please open a bug. Thank you!
+#endif
+
#ifdef XML_UNICODE
#define XML_ENCODE_MAX XML_UTF16_ENCODE_MAX
@@ -110,17 +188,11 @@ typedef struct {
const XML_Memory_Handling_Suite *mem;
} HASH_TABLE;
-/* Basic character hash algorithm, taken from Python's string hash:
- h = h * 1000003 ^ character, the constant being a prime number.
+static size_t
+keylen(KEY s);
-*/
-#ifdef XML_UNICODE
-#define CHAR_HASH(h, c) \
- (((h) * 0xF4243) ^ (unsigned short)(c))
-#else
-#define CHAR_HASH(h, c) \
- (((h) * 0xF4243) ^ (unsigned char)(c))
-#endif
+static void
+copy_salt_to_sipkey(XML_Parser parser, struct sipkey * key);
/* For probing (after a collision) we need a step size relative prime
to the hash table size, which is a power of 2. We use double-hashing,
@@ -356,6 +428,8 @@ doIgnoreSection(XML_Parser parser, const ENCODING *, const char **startPtr,
const char *end, const char **nextPtr, XML_Bool haveMore);
#endif /* XML_DTD */
+static void
+freeBindings(XML_Parser parser, BINDING *bindings);
static enum XML_Error
storeAtts(XML_Parser parser, const ENCODING *, const char *s,
TAG_NAME *tagNamePtr, BINDING **bindingsPtr);
@@ -396,7 +470,7 @@ setContext(XML_Parser parser, const XML_Char *context);
static void FASTCALL normalizePublicId(XML_Char *s);
static DTD * dtdCreate(const XML_Memory_Handling_Suite *ms);
-/* do not call if parentParser != NULL */
+/* do not call if m_parentParser != NULL */
static void dtdReset(DTD *p, const XML_Memory_Handling_Suite *ms);
static void
dtdDestroy(DTD *p, XML_Bool isDocEntity, const XML_Memory_Handling_Suite *ms);
@@ -440,6 +514,9 @@ static ELEMENT_TYPE *
getElementType(XML_Parser parser, const ENCODING *enc,
const char *ptr, const char *end);
+static XML_Char *copyString(const XML_Char *s,
+ const XML_Memory_Handling_Suite *memsuite);
+
static unsigned long generate_hash_secret_salt(XML_Parser parser);
static XML_Bool startParsing(XML_Parser parser);
@@ -465,7 +542,7 @@ parserInit(XML_Parser parser, const XML_Char *encodingName);
: ((*((pool)->ptr)++ = c), 1))
struct XML_ParserStruct {
- /* The first member must be userData so that the XML_GetUserData
+ /* The first member must be m_userData so that the XML_GetUserData
macro works. */
void *m_userData;
void *m_handlerArg;
@@ -475,7 +552,7 @@ struct XML_ParserStruct {
const char *m_bufferPtr;
/* past last character to be parsed */
char *m_bufferEnd;
- /* allocated end of buffer */
+ /* allocated end of m_buffer */
const char *m_bufferLim;
XML_Index m_parseEndByteIndex;
const char *m_parseEndPtr;
@@ -567,113 +644,10 @@ struct XML_ParserStruct {
unsigned long m_hash_secret_salt;
};
-#define MALLOC(s) (parser->m_mem.malloc_fcn((s)))
-#define REALLOC(p,s) (parser->m_mem.realloc_fcn((p),(s)))
-#define FREE(p) (parser->m_mem.free_fcn((p)))
-
-#define userData (parser->m_userData)
-#define handlerArg (parser->m_handlerArg)
-#define startElementHandler (parser->m_startElementHandler)
-#define endElementHandler (parser->m_endElementHandler)
-#define characterDataHandler (parser->m_characterDataHandler)
-#define processingInstructionHandler \
- (parser->m_processingInstructionHandler)
-#define commentHandler (parser->m_commentHandler)
-#define startCdataSectionHandler \
- (parser->m_startCdataSectionHandler)
-#define endCdataSectionHandler (parser->m_endCdataSectionHandler)
-#define defaultHandler (parser->m_defaultHandler)
-#define startDoctypeDeclHandler (parser->m_startDoctypeDeclHandler)
-#define endDoctypeDeclHandler (parser->m_endDoctypeDeclHandler)
-#define unparsedEntityDeclHandler \
- (parser->m_unparsedEntityDeclHandler)
-#define notationDeclHandler (parser->m_notationDeclHandler)
-#define startNamespaceDeclHandler \
- (parser->m_startNamespaceDeclHandler)
-#define endNamespaceDeclHandler (parser->m_endNamespaceDeclHandler)
-#define notStandaloneHandler (parser->m_notStandaloneHandler)
-#define externalEntityRefHandler \
- (parser->m_externalEntityRefHandler)
-#define externalEntityRefHandlerArg \
- (parser->m_externalEntityRefHandlerArg)
-#define internalEntityRefHandler \
- (parser->m_internalEntityRefHandler)
-#define skippedEntityHandler (parser->m_skippedEntityHandler)
-#define unknownEncodingHandler (parser->m_unknownEncodingHandler)
-#define elementDeclHandler (parser->m_elementDeclHandler)
-#define attlistDeclHandler (parser->m_attlistDeclHandler)
-#define entityDeclHandler (parser->m_entityDeclHandler)
-#define xmlDeclHandler (parser->m_xmlDeclHandler)
-#define encoding (parser->m_encoding)
-#define initEncoding (parser->m_initEncoding)
-#define internalEncoding (parser->m_internalEncoding)
-#define unknownEncodingMem (parser->m_unknownEncodingMem)
-#define unknownEncodingData (parser->m_unknownEncodingData)
-#define unknownEncodingHandlerData \
- (parser->m_unknownEncodingHandlerData)
-#define unknownEncodingRelease (parser->m_unknownEncodingRelease)
-#define protocolEncodingName (parser->m_protocolEncodingName)
-#define ns (parser->m_ns)
-#define ns_triplets (parser->m_ns_triplets)
-#define prologState (parser->m_prologState)
-#define processor (parser->m_processor)
-#define errorCode (parser->m_errorCode)
-#define eventPtr (parser->m_eventPtr)
-#define eventEndPtr (parser->m_eventEndPtr)
-#define positionPtr (parser->m_positionPtr)
-#define position (parser->m_position)
-#define openInternalEntities (parser->m_openInternalEntities)
-#define freeInternalEntities (parser->m_freeInternalEntities)
-#define defaultExpandInternalEntities \
- (parser->m_defaultExpandInternalEntities)
-#define tagLevel (parser->m_tagLevel)
-#define buffer (parser->m_buffer)
-#define bufferPtr (parser->m_bufferPtr)
-#define bufferEnd (parser->m_bufferEnd)
-#define parseEndByteIndex (parser->m_parseEndByteIndex)
-#define parseEndPtr (parser->m_parseEndPtr)
-#define bufferLim (parser->m_bufferLim)
-#define dataBuf (parser->m_dataBuf)
-#define dataBufEnd (parser->m_dataBufEnd)
-#define _dtd (parser->m_dtd)
-#define curBase (parser->m_curBase)
-#define declEntity (parser->m_declEntity)
-#define doctypeName (parser->m_doctypeName)
-#define doctypeSysid (parser->m_doctypeSysid)
-#define doctypePubid (parser->m_doctypePubid)
-#define declAttributeType (parser->m_declAttributeType)
-#define declNotationName (parser->m_declNotationName)
-#define declNotationPublicId (parser->m_declNotationPublicId)
-#define declElementType (parser->m_declElementType)
-#define declAttributeId (parser->m_declAttributeId)
-#define declAttributeIsCdata (parser->m_declAttributeIsCdata)
-#define declAttributeIsId (parser->m_declAttributeIsId)
-#define freeTagList (parser->m_freeTagList)
-#define freeBindingList (parser->m_freeBindingList)
-#define inheritedBindings (parser->m_inheritedBindings)
-#define tagStack (parser->m_tagStack)
-#define atts (parser->m_atts)
-#define attsSize (parser->m_attsSize)
-#define nSpecifiedAtts (parser->m_nSpecifiedAtts)
-#define idAttIndex (parser->m_idAttIndex)
-#define nsAtts (parser->m_nsAtts)
-#define nsAttsVersion (parser->m_nsAttsVersion)
-#define nsAttsPower (parser->m_nsAttsPower)
-#define attInfo (parser->m_attInfo)
-#define tempPool (parser->m_tempPool)
-#define temp2Pool (parser->m_temp2Pool)
-#define groupConnector (parser->m_groupConnector)
-#define groupSize (parser->m_groupSize)
-#define namespaceSeparator (parser->m_namespaceSeparator)
-#define parentParser (parser->m_parentParser)
-#define ps_parsing (parser->m_parsingStatus.parsing)
-#define ps_finalBuffer (parser->m_parsingStatus.finalBuffer)
-#ifdef XML_DTD
-#define isParamEntity (parser->m_isParamEntity)
-#define useForeignDTD (parser->m_useForeignDTD)
-#define paramEntityParsing (parser->m_paramEntityParsing)
-#endif /* XML_DTD */
-#define hash_secret_salt (parser->m_hash_secret_salt)
+#define MALLOC(parser, s) (parser->m_mem.malloc_fcn((s)))
+#define REALLOC(parser, p, s) (parser->m_mem.realloc_fcn((p),(s)))
+#define FREE(parser, p) (parser->m_mem.free_fcn((p)))
+
XML_Parser XMLCALL
XML_ParserCreate(const XML_Char *encodingName)
@@ -698,10 +672,138 @@ static const XML_Char implicitContext[] = {
ASCII_s, ASCII_p, ASCII_a, ASCII_c, ASCII_e, '\0'
};
+
+/* To avoid warnings about unused functions: */
+#if ! defined(HAVE_ARC4RANDOM_BUF) && ! defined(HAVE_ARC4RANDOM)
+
+#if defined(HAVE_GETRANDOM) || defined(HAVE_SYSCALL_GETRANDOM)
+
+/* Obtain entropy on Linux 3.17+ */
+static int
+writeRandomBytes_getrandom_nonblock(void * target, size_t count) {
+ int success = 0; /* full count bytes written? */
+ size_t bytesWrittenTotal = 0;
+ const unsigned int getrandomFlags = GRND_NONBLOCK;
+
+ do {
+ void * const currentTarget = (void*)((char*)target + bytesWrittenTotal);
+ const size_t bytesToWrite = count - bytesWrittenTotal;
+
+ const int bytesWrittenMore =
+#if defined(HAVE_GETRANDOM)
+ getrandom(currentTarget, bytesToWrite, getrandomFlags);
+#else
+ syscall(SYS_getrandom, currentTarget, bytesToWrite, getrandomFlags);
+#endif
+
+ if (bytesWrittenMore > 0) {
+ bytesWrittenTotal += bytesWrittenMore;
+ if (bytesWrittenTotal >= count)
+ success = 1;
+ }
+ } while (! success && (errno == EINTR));
+
+ return success;
+}
+
+#endif /* defined(HAVE_GETRANDOM) || defined(HAVE_SYSCALL_GETRANDOM) */
+
+
+#if ! defined(_WIN32) && defined(XML_DEV_URANDOM)
+
+/* Extract entropy from /dev/urandom */
+static int
+writeRandomBytes_dev_urandom(void * target, size_t count) {
+ int success = 0; /* full count bytes written? */
+ size_t bytesWrittenTotal = 0;
+
+ const int fd = open("/dev/urandom", O_RDONLY);
+ if (fd < 0) {
+ return 0;
+ }
+
+ do {
+ void * const currentTarget = (void*)((char*)target + bytesWrittenTotal);
+ const size_t bytesToWrite = count - bytesWrittenTotal;
+
+ const ssize_t bytesWrittenMore = read(fd, currentTarget, bytesToWrite);
+
+ if (bytesWrittenMore > 0) {
+ bytesWrittenTotal += bytesWrittenMore;
+ if (bytesWrittenTotal >= count)
+ success = 1;
+ }
+ } while (! success && (errno == EINTR));
+
+ close(fd);
+ return success;
+}
+
+#endif /* ! defined(_WIN32) && defined(XML_DEV_URANDOM) */
+
+#endif /* ! defined(HAVE_ARC4RANDOM_BUF) && ! defined(HAVE_ARC4RANDOM) */
+
+
+#if defined(HAVE_ARC4RANDOM)
+
+static void
+writeRandomBytes_arc4random(void * target, size_t count) {
+ size_t bytesWrittenTotal = 0;
+
+ while (bytesWrittenTotal < count) {
+ const uint32_t random32 = arc4random();
+ size_t i = 0;
+
+ for (; (i < sizeof(random32)) && (bytesWrittenTotal < count);
+ i++, bytesWrittenTotal++) {
+ const uint8_t random8 = (uint8_t)(random32 >> (i * 8));
+ ((uint8_t *)target)[bytesWrittenTotal] = random8;
+ }
+ }
+}
+
+#endif /* defined(HAVE_ARC4RANDOM) */
+
+
+#ifdef _WIN32
+
+typedef BOOLEAN (APIENTRY *RTLGENRANDOM_FUNC)(PVOID, ULONG);
+HMODULE _Expat_LoadLibrary(LPCTSTR filename); /* see loadlibrary.c */
+
+/* Obtain entropy on Windows XP / Windows Server 2003 and later.
+ * Hint on RtlGenRandom and the following article from libsodium.
+ *
+ * Michael Howard: Cryptographically Secure Random number on Windows without using CryptoAPI
+ * https://blogs.msdn.microsoft.com/michael_howard/2005/01/14/cryptographically-secure-random-number-on-windows-without-using-cryptoapi/
+ */
+static int
+writeRandomBytes_RtlGenRandom(void * target, size_t count) {
+ int success = 0; /* full count bytes written? */
+ const HMODULE advapi32 = _Expat_LoadLibrary(TEXT("ADVAPI32.DLL"));
+
+ if (advapi32) {
+ const RTLGENRANDOM_FUNC RtlGenRandom
+ = (RTLGENRANDOM_FUNC)GetProcAddress(advapi32, "SystemFunction036");
+ if (RtlGenRandom) {
+ if (RtlGenRandom((PVOID)target, (ULONG)count) == TRUE) {
+ success = 1;
+ }
+ }
+ FreeLibrary(advapi32);
+ }
+
+ return success;
+}
+
+#endif /* _WIN32 */
+
+
+#if ! defined(HAVE_ARC4RANDOM_BUF) && ! defined(HAVE_ARC4RANDOM)
+
static unsigned long
gather_time_entropy(void)
{
-#ifdef COMPILED_FROM_DSP
+#ifdef _WIN32
FILETIME ft;
GetSystemTimeAsFileTime(&ft); /* never fails */
return ft.dwHighDateTime ^ ft.dwLowDateTime;
@@ -710,36 +812,91 @@ gather_time_entropy(void)
int gettimeofday_res;
gettimeofday_res = gettimeofday(&tv, NULL);
+
+#if defined(NDEBUG)
+ (void)gettimeofday_res;
+#else
assert (gettimeofday_res == 0);
+#endif /* defined(NDEBUG) */
/* Microseconds time is <20 bits entropy */
return tv.tv_usec;
#endif
}
+#endif /* ! defined(HAVE_ARC4RANDOM_BUF) && ! defined(HAVE_ARC4RANDOM) */
+
+
+static unsigned long
+ENTROPY_DEBUG(const char * label, unsigned long entropy) {
+ const char * const EXPAT_ENTROPY_DEBUG = getenv("EXPAT_ENTROPY_DEBUG");
+ if (EXPAT_ENTROPY_DEBUG && ! strcmp(EXPAT_ENTROPY_DEBUG, "1")) {
+ fprintf(stderr, "Entropy: %s --> 0x%0*lx (%lu bytes)\n",
+ label,
+ (int)sizeof(entropy) * 2, entropy,
+ (unsigned long)sizeof(entropy));
+ }
+ return entropy;
+}
+
static unsigned long
generate_hash_secret_salt(XML_Parser parser)
{
- /* Process ID is 0 bits entropy if attacker has local access
- * XML_Parser address is few bits of entropy if attacker has local access */
- const unsigned long entropy =
- gather_time_entropy() ^ getpid() ^ (uintptr_t)parser;
+ unsigned long entropy;
+ (void)parser;
+
+ /* "Failproof" high quality providers: */
+#if defined(HAVE_ARC4RANDOM_BUF)
+ arc4random_buf(&entropy, sizeof(entropy));
+ return ENTROPY_DEBUG("arc4random_buf", entropy);
+#elif defined(HAVE_ARC4RANDOM)
+ writeRandomBytes_arc4random((void *)&entropy, sizeof(entropy));
+ return ENTROPY_DEBUG("arc4random", entropy);
+#else
+ /* Try high quality providers first .. */
+#ifdef _WIN32
+ if (writeRandomBytes_RtlGenRandom((void *)&entropy, sizeof(entropy))) {
+ return ENTROPY_DEBUG("RtlGenRandom", entropy);
+ }
+#elif defined(HAVE_GETRANDOM) || defined(HAVE_SYSCALL_GETRANDOM)
+ if (writeRandomBytes_getrandom_nonblock((void *)&entropy, sizeof(entropy))) {
+ return ENTROPY_DEBUG("getrandom", entropy);
+ }
+#endif
+#if ! defined(_WIN32) && defined(XML_DEV_URANDOM)
+ if (writeRandomBytes_dev_urandom((void *)&entropy, sizeof(entropy))) {
+ return ENTROPY_DEBUG("/dev/urandom", entropy);
+ }
+#endif /* ! defined(_WIN32) && defined(XML_DEV_URANDOM) */
+ /* .. and self-made low quality for backup: */
+
+ /* Process ID is 0 bits entropy if attacker has local access */
+ entropy = gather_time_entropy() ^ getpid();
/* Factors are 2^31-1 and 2^61-1 (Mersenne primes M31 and M61) */
if (sizeof(unsigned long) == 4) {
- return entropy * 2147483647;
+ return ENTROPY_DEBUG("fallback(4)", entropy * 2147483647);
} else {
- return entropy * (unsigned long)2305843009213693951;
+ return ENTROPY_DEBUG("fallback(8)",
+ entropy * (unsigned long)2305843009213693951ULL);
}
+#endif
+}
+
+static unsigned long
+get_hash_secret_salt(XML_Parser parser) {
+ if (parser->m_parentParser != NULL)
+ return get_hash_secret_salt(parser->m_parentParser);
+ return parser->m_hash_secret_salt;
}
static XML_Bool /* only valid for root parser */
startParsing(XML_Parser parser)
{
/* hash functions must be initialized before setContext() is called */
- if (hash_secret_salt == 0)
- hash_secret_salt = generate_hash_secret_salt(parser);
- if (ns) {
+ if (parser->m_hash_secret_salt == 0)
+ parser->m_hash_secret_salt = generate_hash_secret_salt(parser);
+ if (parser->m_ns) {
/* implicit context only set for root parser, since child
parsers (i.e. external entity parsers) will inherit it
*/
@@ -789,83 +946,85 @@ parserCreate(const XML_Char *encodingName,
if (!parser)
return parser;
- buffer = NULL;
- bufferLim = NULL;
+ parser->m_buffer = NULL;
+ parser->m_bufferLim = NULL;
- attsSize = INIT_ATTS_SIZE;
- atts = (ATTRIBUTE *)MALLOC(attsSize * sizeof(ATTRIBUTE));
- if (atts == NULL) {
- FREE(parser);
+ parser->m_attsSize = INIT_ATTS_SIZE;
+ parser->m_atts = (ATTRIBUTE *)MALLOC(parser, parser->m_attsSize * sizeof(ATTRIBUTE));
+ if (parser->m_atts == NULL) {
+ FREE(parser, parser);
return NULL;
}
#ifdef XML_ATTR_INFO
- attInfo = (XML_AttrInfo*)MALLOC(attsSize * sizeof(XML_AttrInfo));
- if (attInfo == NULL) {
- FREE(atts);
- FREE(parser);
+ parser->m_attInfo = (XML_AttrInfo*)MALLOC(parser, parser->m_attsSize * sizeof(XML_AttrInfo));
+ if (parser->m_attInfo == NULL) {
+ FREE(parser, parser->m_atts);
+ FREE(parser, parser);
return NULL;
}
#endif
- dataBuf = (XML_Char *)MALLOC(INIT_DATA_BUF_SIZE * sizeof(XML_Char));
- if (dataBuf == NULL) {
- FREE(atts);
+ parser->m_dataBuf = (XML_Char *)MALLOC(parser, INIT_DATA_BUF_SIZE * sizeof(XML_Char));
+ if (parser->m_dataBuf == NULL) {
+ FREE(parser, parser->m_atts);
#ifdef XML_ATTR_INFO
- FREE(attInfo);
+ FREE(parser, parser->m_attInfo);
#endif
- FREE(parser);
+ FREE(parser, parser);
return NULL;
}
- dataBufEnd = dataBuf + INIT_DATA_BUF_SIZE;
+ parser->m_dataBufEnd = parser->m_dataBuf + INIT_DATA_BUF_SIZE;
if (dtd)
- _dtd = dtd;
+ parser->m_dtd = dtd;
else {
- _dtd = dtdCreate(&parser->m_mem);
- if (_dtd == NULL) {
- FREE(dataBuf);
- FREE(atts);
+ parser->m_dtd = dtdCreate(&parser->m_mem);
+ if (parser->m_dtd == NULL) {
+ FREE(parser, parser->m_dataBuf);
+ FREE(parser, parser->m_atts);
#ifdef XML_ATTR_INFO
- FREE(attInfo);
+ FREE(parser, parser->m_attInfo);
#endif
- FREE(parser);
+ FREE(parser, parser);
return NULL;
}
}
- freeBindingList = NULL;
- freeTagList = NULL;
- freeInternalEntities = NULL;
+ parser->m_freeBindingList = NULL;
+ parser->m_freeTagList = NULL;
+ parser->m_freeInternalEntities = NULL;
- groupSize = 0;
- groupConnector = NULL;
+ parser->m_groupSize = 0;
+ parser->m_groupConnector = NULL;
- unknownEncodingHandler = NULL;
- unknownEncodingHandlerData = NULL;
+ parser->m_unknownEncodingHandler = NULL;
+ parser->m_unknownEncodingHandlerData = NULL;
- namespaceSeparator = ASCII_EXCL;
- ns = XML_FALSE;
- ns_triplets = XML_FALSE;
+ parser->m_namespaceSeparator = ASCII_EXCL;
+ parser->m_ns = XML_FALSE;
+ parser->m_ns_triplets = XML_FALSE;
- nsAtts = NULL;
- nsAttsVersion = 0;
- nsAttsPower = 0;
+ parser->m_nsAtts = NULL;
+ parser->m_nsAttsVersion = 0;
+ parser->m_nsAttsPower = 0;
- poolInit(&tempPool, &(parser->m_mem));
- poolInit(&temp2Pool, &(parser->m_mem));
+ parser->m_protocolEncodingName = NULL;
+
+ poolInit(&parser->m_tempPool, &(parser->m_mem));
+ poolInit(&parser->m_temp2Pool, &(parser->m_mem));
parserInit(parser, encodingName);
- if (encodingName && !protocolEncodingName) {
+ if (encodingName && !parser->m_protocolEncodingName) {
XML_ParserFree(parser);
return NULL;
}
if (nameSep) {
- ns = XML_TRUE;
- internalEncoding = XmlGetInternalEncodingNS();
- namespaceSeparator = *nameSep;
+ parser->m_ns = XML_TRUE;
+ parser->m_internalEncoding = XmlGetInternalEncodingNS();
+ parser->m_namespaceSeparator = *nameSep;
}
else {
- internalEncoding = XmlGetInternalEncoding();
+ parser->m_internalEncoding = XmlGetInternalEncoding();
}
return parser;
@@ -874,85 +1033,85 @@ parserCreate(const XML_Char *encodingName,
static void
parserInit(XML_Parser parser, const XML_Char *encodingName)
{
- processor = prologInitProcessor;
- XmlPrologStateInit(&prologState);
- protocolEncodingName = (encodingName != NULL
- ? poolCopyString(&tempPool, encodingName)
- : NULL);
- curBase = NULL;
- XmlInitEncoding(&initEncoding, &encoding, 0);
- userData = NULL;
- handlerArg = NULL;
- startElementHandler = NULL;
- endElementHandler = NULL;
- characterDataHandler = NULL;
- processingInstructionHandler = NULL;
- commentHandler = NULL;
- startCdataSectionHandler = NULL;
- endCdataSectionHandler = NULL;
- defaultHandler = NULL;
- startDoctypeDeclHandler = NULL;
- endDoctypeDeclHandler = NULL;
- unparsedEntityDeclHandler = NULL;
- notationDeclHandler = NULL;
- startNamespaceDeclHandler = NULL;
- endNamespaceDeclHandler = NULL;
- notStandaloneHandler = NULL;
- externalEntityRefHandler = NULL;
- externalEntityRefHandlerArg = parser;
- skippedEntityHandler = NULL;
- elementDeclHandler = NULL;
- attlistDeclHandler = NULL;
- entityDeclHandler = NULL;
- xmlDeclHandler = NULL;
- bufferPtr = buffer;
- bufferEnd = buffer;
- parseEndByteIndex = 0;
- parseEndPtr = NULL;
- declElementType = NULL;
- declAttributeId = NULL;
- declEntity = NULL;
- doctypeName = NULL;
- doctypeSysid = NULL;
- doctypePubid = NULL;
- declAttributeType = NULL;
- declNotationName = NULL;
- declNotationPublicId = NULL;
- declAttributeIsCdata = XML_FALSE;
- declAttributeIsId = XML_FALSE;
- memset(&position, 0, sizeof(POSITION));
- errorCode = XML_ERROR_NONE;
- eventPtr = NULL;
- eventEndPtr = NULL;
- positionPtr = NULL;
- openInternalEntities = NULL;
- defaultExpandInternalEntities = XML_TRUE;
- tagLevel = 0;
- tagStack = NULL;
- inheritedBindings = NULL;
- nSpecifiedAtts = 0;
- unknownEncodingMem = NULL;
- unknownEncodingRelease = NULL;
- unknownEncodingData = NULL;
- parentParser = NULL;
- ps_parsing = XML_INITIALIZED;
+ parser->m_processor = prologInitProcessor;
+ XmlPrologStateInit(&parser->m_prologState);
+ if (encodingName != NULL) {
+ parser->m_protocolEncodingName = copyString(encodingName, &(parser->m_mem));
+ }
+ parser->m_curBase = NULL;
+ XmlInitEncoding(&parser->m_initEncoding, &parser->m_encoding, 0);
+ parser->m_userData = NULL;
+ parser->m_handlerArg = NULL;
+ parser->m_startElementHandler = NULL;
+ parser->m_endElementHandler = NULL;
+ parser->m_characterDataHandler = NULL;
+ parser->m_processingInstructionHandler = NULL;
+ parser->m_commentHandler = NULL;
+ parser->m_startCdataSectionHandler = NULL;
+ parser->m_endCdataSectionHandler = NULL;
+ parser->m_defaultHandler = NULL;
+ parser->m_startDoctypeDeclHandler = NULL;
+ parser->m_endDoctypeDeclHandler = NULL;
+ parser->m_unparsedEntityDeclHandler = NULL;
+ parser->m_notationDeclHandler = NULL;
+ parser->m_startNamespaceDeclHandler = NULL;
+ parser->m_endNamespaceDeclHandler = NULL;
+ parser->m_notStandaloneHandler = NULL;
+ parser->m_externalEntityRefHandler = NULL;
+ parser->m_externalEntityRefHandlerArg = parser;
+ parser->m_skippedEntityHandler = NULL;
+ parser->m_elementDeclHandler = NULL;
+ parser->m_attlistDeclHandler = NULL;
+ parser->m_entityDeclHandler = NULL;
+ parser->m_xmlDeclHandler = NULL;
+ parser->m_bufferPtr = parser->m_buffer;
+ parser->m_bufferEnd = parser->m_buffer;
+ parser->m_parseEndByteIndex = 0;
+ parser->m_parseEndPtr = NULL;
+ parser->m_declElementType = NULL;
+ parser->m_declAttributeId = NULL;
+ parser->m_declEntity = NULL;
+ parser->m_doctypeName = NULL;
+ parser->m_doctypeSysid = NULL;
+ parser->m_doctypePubid = NULL;
+ parser->m_declAttributeType = NULL;
+ parser->m_declNotationName = NULL;
+ parser->m_declNotationPublicId = NULL;
+ parser->m_declAttributeIsCdata = XML_FALSE;
+ parser->m_declAttributeIsId = XML_FALSE;
+ memset(&parser->m_position, 0, sizeof(POSITION));
+ parser->m_errorCode = XML_ERROR_NONE;
+ parser->m_eventPtr = NULL;
+ parser->m_eventEndPtr = NULL;
+ parser->m_positionPtr = NULL;
+ parser->m_openInternalEntities = NULL;
+ parser->m_defaultExpandInternalEntities = XML_TRUE;
+ parser->m_tagLevel = 0;
+ parser->m_tagStack = NULL;
+ parser->m_inheritedBindings = NULL;
+ parser->m_nSpecifiedAtts = 0;
+ parser->m_unknownEncodingMem = NULL;
+ parser->m_unknownEncodingRelease = NULL;
+ parser->m_unknownEncodingData = NULL;
+ parser->m_parentParser = NULL;
+ parser->m_parsingStatus.parsing = XML_INITIALIZED;
#ifdef XML_DTD
- isParamEntity = XML_FALSE;
- useForeignDTD = XML_FALSE;
- paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER;
+ parser->m_isParamEntity = XML_FALSE;
+ parser->m_useForeignDTD = XML_FALSE;
+ parser->m_paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER;
#endif
- hash_secret_salt = 0;
+ parser->m_hash_secret_salt = 0;
}
-/* moves list of bindings to freeBindingList */
+/* moves list of bindings to m_freeBindingList */
static void FASTCALL
moveToFreeBindingList(XML_Parser parser, BINDING *bindings)
{
while (bindings) {
BINDING *b = bindings;
bindings = bindings->nextTagBinding;
- b->nextTagBinding = freeBindingList;
- freeBindingList = b;
+ b->nextTagBinding = parser->m_freeBindingList;
+ parser->m_freeBindingList = b;
}
}
@@ -961,51 +1120,65 @@ XML_ParserReset(XML_Parser parser, const XML_Char *encodingName)
{
TAG *tStk;
OPEN_INTERNAL_ENTITY *openEntityList;
- if (parentParser)
+
+ if (parser == NULL)
+ return XML_FALSE;
+
+ if (parser->m_parentParser)
return XML_FALSE;
- /* move tagStack to freeTagList */
- tStk = tagStack;
+ /* move m_tagStack to m_freeTagList */
+ tStk = parser->m_tagStack;
while (tStk) {
TAG *tag = tStk;
tStk = tStk->parent;
- tag->parent = freeTagList;
+ tag->parent = parser->m_freeTagList;
moveToFreeBindingList(parser, tag->bindings);
tag->bindings = NULL;
- freeTagList = tag;
+ parser->m_freeTagList = tag;
}
- /* move openInternalEntities to freeInternalEntities */
- openEntityList = openInternalEntities;
+ /* move m_openInternalEntities to m_freeInternalEntities */
+ openEntityList = parser->m_openInternalEntities;
while (openEntityList) {
OPEN_INTERNAL_ENTITY *openEntity = openEntityList;
openEntityList = openEntity->next;
- openEntity->next = freeInternalEntities;
- freeInternalEntities = openEntity;
- }
- moveToFreeBindingList(parser, inheritedBindings);
- FREE(unknownEncodingMem);
- if (unknownEncodingRelease)
- unknownEncodingRelease(unknownEncodingData);
- poolClear(&tempPool);
- poolClear(&temp2Pool);
+ openEntity->next = parser->m_freeInternalEntities;
+ parser->m_freeInternalEntities = openEntity;
+ }
+ moveToFreeBindingList(parser, parser->m_inheritedBindings);
+ FREE(parser, parser->m_unknownEncodingMem);
+ if (parser->m_unknownEncodingRelease)
+ parser->m_unknownEncodingRelease(parser->m_unknownEncodingData);
+ poolClear(&parser->m_tempPool);
+ poolClear(&parser->m_temp2Pool);
+ FREE(parser, (void *)parser->m_protocolEncodingName);
+ parser->m_protocolEncodingName = NULL;
parserInit(parser, encodingName);
- dtdReset(_dtd, &parser->m_mem);
+ dtdReset(parser->m_dtd, &parser->m_mem);
return XML_TRUE;
}
enum XML_Status XMLCALL
XML_SetEncoding(XML_Parser parser, const XML_Char *encodingName)
{
+ if (parser == NULL)
+ return XML_STATUS_ERROR;
/* Block after XML_Parse()/XML_ParseBuffer() has been called.
XXX There's no way for the caller to determine which of the
XXX possible error cases caused the XML_STATUS_ERROR return.
*/
- if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED)
+ if (parser->m_parsingStatus.parsing == XML_PARSING || parser->m_parsingStatus.parsing == XML_SUSPENDED)
return XML_STATUS_ERROR;
+
+ /* Get rid of any previous encoding name */
+ FREE(parser, (void *)parser->m_protocolEncodingName);
+
if (encodingName == NULL)
- protocolEncodingName = NULL;
+ /* No new encoding name */
+ parser->m_protocolEncodingName = NULL;
else {
- protocolEncodingName = poolCopyString(&tempPool, encodingName);
- if (!protocolEncodingName)
+ /* Copy the new encoding name into allocated memory */
+ parser->m_protocolEncodingName = copyString(encodingName, &(parser->m_mem));
+ if (!parser->m_protocolEncodingName)
return XML_STATUS_ERROR;
}
return XML_STATUS_OK;
@@ -1018,52 +1191,88 @@ XML_ExternalEntityParserCreate(XML_Parser oldParser,
{
XML_Parser parser = oldParser;
DTD *newDtd = NULL;
- DTD *oldDtd = _dtd;
- XML_StartElementHandler oldStartElementHandler = startElementHandler;
- XML_EndElementHandler oldEndElementHandler = endElementHandler;
- XML_CharacterDataHandler oldCharacterDataHandler = characterDataHandler;
- XML_ProcessingInstructionHandler oldProcessingInstructionHandler
- = processingInstructionHandler;
- XML_CommentHandler oldCommentHandler = commentHandler;
- XML_StartCdataSectionHandler oldStartCdataSectionHandler
- = startCdataSectionHandler;
- XML_EndCdataSectionHandler oldEndCdataSectionHandler
- = endCdataSectionHandler;
- XML_DefaultHandler oldDefaultHandler = defaultHandler;
- XML_UnparsedEntityDeclHandler oldUnparsedEntityDeclHandler
- = unparsedEntityDeclHandler;
- XML_NotationDeclHandler oldNotationDeclHandler = notationDeclHandler;
- XML_StartNamespaceDeclHandler oldStartNamespaceDeclHandler
- = startNamespaceDeclHandler;
- XML_EndNamespaceDeclHandler oldEndNamespaceDeclHandler
- = endNamespaceDeclHandler;
- XML_NotStandaloneHandler oldNotStandaloneHandler = notStandaloneHandler;
- XML_ExternalEntityRefHandler oldExternalEntityRefHandler
- = externalEntityRefHandler;
- XML_SkippedEntityHandler oldSkippedEntityHandler = skippedEntityHandler;
- XML_UnknownEncodingHandler oldUnknownEncodingHandler
- = unknownEncodingHandler;
- XML_ElementDeclHandler oldElementDeclHandler = elementDeclHandler;
- XML_AttlistDeclHandler oldAttlistDeclHandler = attlistDeclHandler;
- XML_EntityDeclHandler oldEntityDeclHandler = entityDeclHandler;
- XML_XmlDeclHandler oldXmlDeclHandler = xmlDeclHandler;
- ELEMENT_TYPE * oldDeclElementType = declElementType;
-
- void *oldUserData = userData;
- void *oldHandlerArg = handlerArg;
- XML_Bool oldDefaultExpandInternalEntities = defaultExpandInternalEntities;
- XML_Parser oldExternalEntityRefHandlerArg = externalEntityRefHandlerArg;
+ DTD *oldDtd;
+ XML_StartElementHandler oldStartElementHandler;
+ XML_EndElementHandler oldEndElementHandler;
+ XML_CharacterDataHandler oldCharacterDataHandler;
+ XML_ProcessingInstructionHandler oldProcessingInstructionHandler;
+ XML_CommentHandler oldCommentHandler;
+ XML_StartCdataSectionHandler oldStartCdataSectionHandler;
+ XML_EndCdataSectionHandler oldEndCdataSectionHandler;
+ XML_DefaultHandler oldDefaultHandler;
+ XML_UnparsedEntityDeclHandler oldUnparsedEntityDeclHandler;
+ XML_NotationDeclHandler oldNotationDeclHandler;
+ XML_StartNamespaceDeclHandler oldStartNamespaceDeclHandler;
+ XML_EndNamespaceDeclHandler oldEndNamespaceDeclHandler;
+ XML_NotStandaloneHandler oldNotStandaloneHandler;
+ XML_ExternalEntityRefHandler oldExternalEntityRefHandler;
+ XML_SkippedEntityHandler oldSkippedEntityHandler;
+ XML_UnknownEncodingHandler oldUnknownEncodingHandler;
+ XML_ElementDeclHandler oldElementDeclHandler;
+ XML_AttlistDeclHandler oldAttlistDeclHandler;
+ XML_EntityDeclHandler oldEntityDeclHandler;
+ XML_XmlDeclHandler oldXmlDeclHandler;
+ ELEMENT_TYPE * oldDeclElementType;
+
+ void *oldUserData;
+ void *oldHandlerArg;
+ XML_Bool oldDefaultExpandInternalEntities;
+ XML_Parser oldExternalEntityRefHandlerArg;
+#ifdef XML_DTD
+ enum XML_ParamEntityParsing oldParamEntityParsing;
+ int oldInEntityValue;
+#endif
+ XML_Bool oldns_triplets;
+ /* Note that the new parser shares the same hash secret as the old
+ parser, so that dtdCopy and copyEntityTable can lookup values
+ from hash tables associated with either parser without us having
+ to worry which hash secrets each table has.
+ */
+ unsigned long oldhash_secret_salt;
+
+ /* Validate the oldParser parameter before we pull everything out of it */
+ if (oldParser == NULL)
+ return NULL;
+
+ /* Stash the original parser contents on the stack */
+ oldDtd = parser->m_dtd;
+ oldStartElementHandler = parser->m_startElementHandler;
+ oldEndElementHandler = parser->m_endElementHandler;
+ oldCharacterDataHandler = parser->m_characterDataHandler;
+ oldProcessingInstructionHandler = parser->m_processingInstructionHandler;
+ oldCommentHandler = parser->m_commentHandler;
+ oldStartCdataSectionHandler = parser->m_startCdataSectionHandler;
+ oldEndCdataSectionHandler = parser->m_endCdataSectionHandler;
+ oldDefaultHandler = parser->m_defaultHandler;
+ oldUnparsedEntityDeclHandler = parser->m_unparsedEntityDeclHandler;
+ oldNotationDeclHandler = parser->m_notationDeclHandler;
+ oldStartNamespaceDeclHandler = parser->m_startNamespaceDeclHandler;
+ oldEndNamespaceDeclHandler = parser->m_endNamespaceDeclHandler;
+ oldNotStandaloneHandler = parser->m_notStandaloneHandler;
+ oldExternalEntityRefHandler = parser->m_externalEntityRefHandler;
+ oldSkippedEntityHandler = parser->m_skippedEntityHandler;
+ oldUnknownEncodingHandler = parser->m_unknownEncodingHandler;
+ oldElementDeclHandler = parser->m_elementDeclHandler;
+ oldAttlistDeclHandler = parser->m_attlistDeclHandler;
+ oldEntityDeclHandler = parser->m_entityDeclHandler;
+ oldXmlDeclHandler = parser->m_xmlDeclHandler;
+ oldDeclElementType = parser->m_declElementType;
+
+ oldUserData = parser->m_userData;
+ oldHandlerArg = parser->m_handlerArg;
+ oldDefaultExpandInternalEntities = parser->m_defaultExpandInternalEntities;
+ oldExternalEntityRefHandlerArg = parser->m_externalEntityRefHandlerArg;
#ifdef XML_DTD
- enum XML_ParamEntityParsing oldParamEntityParsing = paramEntityParsing;
- int oldInEntityValue = prologState.inEntityValue;
+ oldParamEntityParsing = parser->m_paramEntityParsing;
+ oldInEntityValue = parser->m_prologState.inEntityValue;
#endif
- XML_Bool oldns_triplets = ns_triplets;
+ oldns_triplets = parser->m_ns_triplets;
/* Note that the new parser shares the same hash secret as the old
parser, so that dtdCopy and copyEntityTable can lookup values
from hash tables associated with either parser without us having
to worry which hash secrets each table has.
*/
- unsigned long oldhash_secret_salt = hash_secret_salt;
+ oldhash_secret_salt = parser->m_hash_secret_salt;
#ifdef XML_DTD
if (!context)
@@ -1075,9 +1284,9 @@ XML_ExternalEntityParserCreate(XML_Parser oldParser,
here. This makes this function more painful to follow than it
would be otherwise.
*/
- if (ns) {
+ if (parser->m_ns) {
XML_Char tmp[2];
- *tmp = namespaceSeparator;
+ *tmp = parser->m_namespaceSeparator;
parser = parserCreate(encodingName, &parser->m_mem, tmp, newDtd);
}
else {
@@ -1087,62 +1296,62 @@ XML_ExternalEntityParserCreate(XML_Parser oldParser,
if (!parser)
return NULL;
- startElementHandler = oldStartElementHandler;
- endElementHandler = oldEndElementHandler;
- characterDataHandler = oldCharacterDataHandler;
- processingInstructionHandler = oldProcessingInstructionHandler;
- commentHandler = oldCommentHandler;
- startCdataSectionHandler = oldStartCdataSectionHandler;
- endCdataSectionHandler = oldEndCdataSectionHandler;
- defaultHandler = oldDefaultHandler;
- unparsedEntityDeclHandler = oldUnparsedEntityDeclHandler;
- notationDeclHandler = oldNotationDeclHandler;
- startNamespaceDeclHandler = oldStartNamespaceDeclHandler;
- endNamespaceDeclHandler = oldEndNamespaceDeclHandler;
- notStandaloneHandler = oldNotStandaloneHandler;
- externalEntityRefHandler = oldExternalEntityRefHandler;
- skippedEntityHandler = oldSkippedEntityHandler;
- unknownEncodingHandler = oldUnknownEncodingHandler;
- elementDeclHandler = oldElementDeclHandler;
- attlistDeclHandler = oldAttlistDeclHandler;
- entityDeclHandler = oldEntityDeclHandler;
- xmlDeclHandler = oldXmlDeclHandler;
- declElementType = oldDeclElementType;
- userData = oldUserData;
+ parser->m_startElementHandler = oldStartElementHandler;
+ parser->m_endElementHandler = oldEndElementHandler;
+ parser->m_characterDataHandler = oldCharacterDataHandler;
+ parser->m_processingInstructionHandler = oldProcessingInstructionHandler;
+ parser->m_commentHandler = oldCommentHandler;
+ parser->m_startCdataSectionHandler = oldStartCdataSectionHandler;
+ parser->m_endCdataSectionHandler = oldEndCdataSectionHandler;
+ parser->m_defaultHandler = oldDefaultHandler;
+ parser->m_unparsedEntityDeclHandler = oldUnparsedEntityDeclHandler;
+ parser->m_notationDeclHandler = oldNotationDeclHandler;
+ parser->m_startNamespaceDeclHandler = oldStartNamespaceDeclHandler;
+ parser->m_endNamespaceDeclHandler = oldEndNamespaceDeclHandler;
+ parser->m_notStandaloneHandler = oldNotStandaloneHandler;
+ parser->m_externalEntityRefHandler = oldExternalEntityRefHandler;
+ parser->m_skippedEntityHandler = oldSkippedEntityHandler;
+ parser->m_unknownEncodingHandler = oldUnknownEncodingHandler;
+ parser->m_elementDeclHandler = oldElementDeclHandler;
+ parser->m_attlistDeclHandler = oldAttlistDeclHandler;
+ parser->m_entityDeclHandler = oldEntityDeclHandler;
+ parser->m_xmlDeclHandler = oldXmlDeclHandler;
+ parser->m_declElementType = oldDeclElementType;
+ parser->m_userData = oldUserData;
if (oldUserData == oldHandlerArg)
- handlerArg = userData;
+ parser->m_handlerArg = parser->m_userData;
else
- handlerArg = parser;
+ parser->m_handlerArg = parser;
if (oldExternalEntityRefHandlerArg != oldParser)
- externalEntityRefHandlerArg = oldExternalEntityRefHandlerArg;
- defaultExpandInternalEntities = oldDefaultExpandInternalEntities;
- ns_triplets = oldns_triplets;
- hash_secret_salt = oldhash_secret_salt;
- parentParser = oldParser;
+ parser->m_externalEntityRefHandlerArg = oldExternalEntityRefHandlerArg;
+ parser->m_defaultExpandInternalEntities = oldDefaultExpandInternalEntities;
+ parser->m_ns_triplets = oldns_triplets;
+ parser->m_hash_secret_salt = oldhash_secret_salt;
+ parser->m_parentParser = oldParser;
#ifdef XML_DTD
- paramEntityParsing = oldParamEntityParsing;
- prologState.inEntityValue = oldInEntityValue;
+ parser->m_paramEntityParsing = oldParamEntityParsing;
+ parser->m_prologState.inEntityValue = oldInEntityValue;
if (context) {
#endif /* XML_DTD */
- if (!dtdCopy(oldParser, _dtd, oldDtd, &parser->m_mem)
+ if (!dtdCopy(oldParser, parser->m_dtd, oldDtd, &parser->m_mem)
|| !setContext(parser, context)) {
XML_ParserFree(parser);
return NULL;
}
- processor = externalEntityInitProcessor;
+ parser->m_processor = externalEntityInitProcessor;
#ifdef XML_DTD
}
else {
- /* The DTD instance referenced by _dtd is shared between the document's
+ /* The DTD instance referenced by parser->m_dtd is shared between the document's
root parser and external PE parsers, therefore one does not need to
call setContext. In addition, one also *must* not call setContext,
because this would overwrite existing prefix->binding pointers in
- _dtd with ones that get destroyed with the external PE parser.
+ parser->m_dtd with ones that get destroyed with the external PE parser.
This would leave those prefixes with dangling pointers.
*/
- isParamEntity = XML_TRUE;
- XmlPrologStateInitExternalEntity(&prologState);
- processor = externalParEntInitProcessor;
+ parser->m_isParamEntity = XML_TRUE;
+ XmlPrologStateInitExternalEntity(&parser->m_prologState);
+ parser->m_processor = externalParEntInitProcessor;
}
#endif /* XML_DTD */
return parser;
@@ -1156,8 +1365,8 @@ destroyBindings(BINDING *bindings, XML_Parser parser)
if (!b)
break;
bindings = b->nextTagBinding;
- FREE(b->uri);
- FREE(b);
+ FREE(parser, b->uri);
+ FREE(parser, b);
}
}
@@ -1168,78 +1377,82 @@ XML_ParserFree(XML_Parser parser)
OPEN_INTERNAL_ENTITY *entityList;
if (parser == NULL)
return;
- /* free tagStack and freeTagList */
- tagList = tagStack;
+ /* free m_tagStack and m_freeTagList */
+ tagList = parser->m_tagStack;
for (;;) {
TAG *p;
if (tagList == NULL) {
- if (freeTagList == NULL)
+ if (parser->m_freeTagList == NULL)
break;
- tagList = freeTagList;
- freeTagList = NULL;
+ tagList = parser->m_freeTagList;
+ parser->m_freeTagList = NULL;
}
p = tagList;
tagList = tagList->parent;
- FREE(p->buf);
+ FREE(parser, p->buf);
destroyBindings(p->bindings, parser);
- FREE(p);
+ FREE(parser, p);
}
- /* free openInternalEntities and freeInternalEntities */
- entityList = openInternalEntities;
+ /* free m_openInternalEntities and m_freeInternalEntities */
+ entityList = parser->m_openInternalEntities;
for (;;) {
OPEN_INTERNAL_ENTITY *openEntity;
if (entityList == NULL) {
- if (freeInternalEntities == NULL)
+ if (parser->m_freeInternalEntities == NULL)
break;
- entityList = freeInternalEntities;
- freeInternalEntities = NULL;
+ entityList = parser->m_freeInternalEntities;
+ parser->m_freeInternalEntities = NULL;
}
openEntity = entityList;
entityList = entityList->next;
- FREE(openEntity);
+ FREE(parser, openEntity);
}
- destroyBindings(freeBindingList, parser);
- destroyBindings(inheritedBindings, parser);
- poolDestroy(&tempPool);
- poolDestroy(&temp2Pool);
+ destroyBindings(parser->m_freeBindingList, parser);
+ destroyBindings(parser->m_inheritedBindings, parser);
+ poolDestroy(&parser->m_tempPool);
+ poolDestroy(&parser->m_temp2Pool);
+ FREE(parser, (void *)parser->m_protocolEncodingName);
#ifdef XML_DTD
/* external parameter entity parsers share the DTD structure
parser->m_dtd with the root parser, so we must not destroy it
*/
- if (!isParamEntity && _dtd)
+ if (!parser->m_isParamEntity && parser->m_dtd)
#else
- if (_dtd)
+ if (parser->m_dtd)
#endif /* XML_DTD */
- dtdDestroy(_dtd, (XML_Bool)!parentParser, &parser->m_mem);
- FREE((void *)atts);
+ dtdDestroy(parser->m_dtd, (XML_Bool)!parser->m_parentParser, &parser->m_mem);
+ FREE(parser, (void *)parser->m_atts);
#ifdef XML_ATTR_INFO
- FREE((void *)attInfo);
+ FREE(parser, (void *)parser->m_attInfo);
#endif
- FREE(groupConnector);
- FREE(buffer);
- FREE(dataBuf);
- FREE(nsAtts);
- FREE(unknownEncodingMem);
- if (unknownEncodingRelease)
- unknownEncodingRelease(unknownEncodingData);
- FREE(parser);
+ FREE(parser, parser->m_groupConnector);
+ FREE(parser, parser->m_buffer);
+ FREE(parser, parser->m_dataBuf);
+ FREE(parser, parser->m_nsAtts);
+ FREE(parser, parser->m_unknownEncodingMem);
+ if (parser->m_unknownEncodingRelease)
+ parser->m_unknownEncodingRelease(parser->m_unknownEncodingData);
+ FREE(parser, parser);
}
void XMLCALL
XML_UseParserAsHandlerArg(XML_Parser parser)
{
- handlerArg = parser;
+ if (parser != NULL)
+ parser->m_handlerArg = parser;
}
enum XML_Error XMLCALL
XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD)
{
+ if (parser == NULL)
+ return XML_ERROR_INVALID_ARGUMENT;
#ifdef XML_DTD
/* block after XML_Parse()/XML_ParseBuffer() has been called */
- if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED)
+ if (parser->m_parsingStatus.parsing == XML_PARSING || parser->m_parsingStatus.parsing == XML_SUSPENDED)
return XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING;
- useForeignDTD = useDTD;
+ parser->m_useForeignDTD = useDTD;
return XML_ERROR_NONE;
#else
return XML_ERROR_FEATURE_REQUIRES_XML_DTD;
@@ -1249,58 +1462,72 @@ XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD)
void XMLCALL
XML_SetReturnNSTriplet(XML_Parser parser, int do_nst)
{
+ if (parser == NULL)
+ return;
/* block after XML_Parse()/XML_ParseBuffer() has been called */
- if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED)
+ if (parser->m_parsingStatus.parsing == XML_PARSING || parser->m_parsingStatus.parsing == XML_SUSPENDED)
return;
- ns_triplets = do_nst ? XML_TRUE : XML_FALSE;
+ parser->m_ns_triplets = do_nst ? XML_TRUE : XML_FALSE;
}
void XMLCALL
XML_SetUserData(XML_Parser parser, void *p)
{
- if (handlerArg == userData)
- handlerArg = userData = p;
+ if (parser == NULL)
+ return;
+ if (parser->m_handlerArg == parser->m_userData)
+ parser->m_handlerArg = parser->m_userData = p;
else
- userData = p;
+ parser->m_userData = p;
}
enum XML_Status XMLCALL
XML_SetBase(XML_Parser parser, const XML_Char *p)
{
+ if (parser == NULL)
+ return XML_STATUS_ERROR;
if (p) {
- p = poolCopyString(&_dtd->pool, p);
+ p = poolCopyString(&parser->m_dtd->pool, p);
if (!p)
return XML_STATUS_ERROR;
- curBase = p;
+ parser->m_curBase = p;
}
else
- curBase = NULL;
+ parser->m_curBase = NULL;
return XML_STATUS_OK;
}
const XML_Char * XMLCALL
XML_GetBase(XML_Parser parser)
{
- return curBase;
+ if (parser == NULL)
+ return NULL;
+ return parser->m_curBase;
}
int XMLCALL
XML_GetSpecifiedAttributeCount(XML_Parser parser)
{
- return nSpecifiedAtts;
+ if (parser == NULL)
+ return -1;
+ return parser->m_nSpecifiedAtts;
}
int XMLCALL
XML_GetIdAttributeIndex(XML_Parser parser)
{
- return idAttIndex;
+ if (parser == NULL)
+ return -1;
+ return parser->m_idAttIndex;
}
#ifdef XML_ATTR_INFO
const XML_AttrInfo * XMLCALL
XML_GetAttributeInfo(XML_Parser parser)
{
- return attInfo;
+ if (parser == NULL)
+ return NULL;
+ return parser->m_attInfo;
}
#endif
@@ -1309,41 +1536,48 @@ XML_SetElementHandler(XML_Parser parser,
XML_StartElementHandler start,
XML_EndElementHandler end)
{
- startElementHandler = start;
- endElementHandler = end;
+ if (parser == NULL)
+ return;
+ parser->m_startElementHandler = start;
+ parser->m_endElementHandler = end;
}
void XMLCALL
XML_SetStartElementHandler(XML_Parser parser,
XML_StartElementHandler start) {
- startElementHandler = start;
+ if (parser != NULL)
+ parser->m_startElementHandler = start;
}
void XMLCALL
XML_SetEndElementHandler(XML_Parser parser,
XML_EndElementHandler end) {
- endElementHandler = end;
+ if (parser != NULL)
+ parser->m_endElementHandler = end;
}
void XMLCALL
XML_SetCharacterDataHandler(XML_Parser parser,
XML_CharacterDataHandler handler)
{
- characterDataHandler = handler;
+ if (parser != NULL)
+ parser->m_characterDataHandler = handler;
}
void XMLCALL
XML_SetProcessingInstructionHandler(XML_Parser parser,
XML_ProcessingInstructionHandler handler)
{
- processingInstructionHandler = handler;
+ if (parser != NULL)
+ parser->m_processingInstructionHandler = handler;
}
void XMLCALL
XML_SetCommentHandler(XML_Parser parser,
XML_CommentHandler handler)
{
- commentHandler = handler;
+ if (parser != NULL)
+ parser->m_commentHandler = handler;
}
void XMLCALL
@@ -1351,36 +1585,44 @@ XML_SetCdataSectionHandler(XML_Parser parser,
XML_StartCdataSectionHandler start,
XML_EndCdataSectionHandler end)
{
- startCdataSectionHandler = start;
- endCdataSectionHandler = end;
+ if (parser == NULL)
+ return;
+ parser->m_startCdataSectionHandler = start;
+ parser->m_endCdataSectionHandler = end;
}
void XMLCALL
XML_SetStartCdataSectionHandler(XML_Parser parser,
XML_StartCdataSectionHandler start) {
- startCdataSectionHandler = start;
+ if (parser != NULL)
+ parser->m_startCdataSectionHandler = start;
}
void XMLCALL
XML_SetEndCdataSectionHandler(XML_Parser parser,
XML_EndCdataSectionHandler end) {
- endCdataSectionHandler = end;
+ if (parser != NULL)
+ parser->m_endCdataSectionHandler = end;
}
void XMLCALL
XML_SetDefaultHandler(XML_Parser parser,
XML_DefaultHandler handler)
{
- defaultHandler = handler;
- defaultExpandInternalEntities = XML_FALSE;
+ if (parser == NULL)
+ return;
+ parser->m_defaultHandler = handler;
+ parser->m_defaultExpandInternalEntities = XML_FALSE;
}
void XMLCALL
XML_SetDefaultHandlerExpand(XML_Parser parser,
XML_DefaultHandler handler)
{
- defaultHandler = handler;
- defaultExpandInternalEntities = XML_TRUE;
+ if (parser == NULL)
+ return;
+ parser->m_defaultHandler = handler;
+ parser->m_defaultExpandInternalEntities = XML_TRUE;
}
void XMLCALL
@@ -1388,34 +1630,40 @@ XML_SetDoctypeDeclHandler(XML_Parser parser,
XML_StartDoctypeDeclHandler start,
XML_EndDoctypeDeclHandler end)
{
- startDoctypeDeclHandler = start;
- endDoctypeDeclHandler = end;
+ if (parser == NULL)
+ return;
+ parser->m_startDoctypeDeclHandler = start;
+ parser->m_endDoctypeDeclHandler = end;
}
void XMLCALL
XML_SetStartDoctypeDeclHandler(XML_Parser parser,
XML_StartDoctypeDeclHandler start) {
- startDoctypeDeclHandler = start;
+ if (parser != NULL)
+ parser->m_startDoctypeDeclHandler = start;
}
void XMLCALL
XML_SetEndDoctypeDeclHandler(XML_Parser parser,
XML_EndDoctypeDeclHandler end) {
- endDoctypeDeclHandler = end;
+ if (parser != NULL)
+ parser->m_endDoctypeDeclHandler = end;
}
void XMLCALL
XML_SetUnparsedEntityDeclHandler(XML_Parser parser,
XML_UnparsedEntityDeclHandler handler)
{
- unparsedEntityDeclHandler = handler;
+ if (parser != NULL)
+ parser->m_unparsedEntityDeclHandler = handler;
}
void XMLCALL
XML_SetNotationDeclHandler(XML_Parser parser,
XML_NotationDeclHandler handler)
{
- notationDeclHandler = handler;
+ if (parser != NULL)
+ parser->m_notationDeclHandler = handler;
}
void XMLCALL
@@ -1423,50 +1671,59 @@ XML_SetNamespaceDeclHandler(XML_Parser parser,
XML_StartNamespaceDeclHandler start,
XML_EndNamespaceDeclHandler end)
{
- startNamespaceDeclHandler = start;
- endNamespaceDeclHandler = end;
+ if (parser == NULL)
+ return;
+ parser->m_startNamespaceDeclHandler = start;
+ parser->m_endNamespaceDeclHandler = end;
}
void XMLCALL
XML_SetStartNamespaceDeclHandler(XML_Parser parser,
XML_StartNamespaceDeclHandler start) {
- startNamespaceDeclHandler = start;
+ if (parser != NULL)
+ parser->m_startNamespaceDeclHandler = start;
}
void XMLCALL
XML_SetEndNamespaceDeclHandler(XML_Parser parser,
XML_EndNamespaceDeclHandler end) {
- endNamespaceDeclHandler = end;
+ if (parser != NULL)
+ parser->m_endNamespaceDeclHandler = end;
}
void XMLCALL
XML_SetNotStandaloneHandler(XML_Parser parser,
XML_NotStandaloneHandler handler)
{
- notStandaloneHandler = handler;
+ if (parser != NULL)
+ parser->m_notStandaloneHandler = handler;
}
void XMLCALL
XML_SetExternalEntityRefHandler(XML_Parser parser,
XML_ExternalEntityRefHandler handler)
{
- externalEntityRefHandler = handler;
+ if (parser != NULL)
+ parser->m_externalEntityRefHandler = handler;
}
void XMLCALL
XML_SetExternalEntityRefHandlerArg(XML_Parser parser, void *arg)
{
+ if (parser == NULL)
+ return;
if (arg)
- externalEntityRefHandlerArg = (XML_Parser)arg;
+ parser->m_externalEntityRefHandlerArg = (XML_Parser)arg;
else
- externalEntityRefHandlerArg = parser;
+ parser->m_externalEntityRefHandlerArg = parser;
}
void XMLCALL
XML_SetSkippedEntityHandler(XML_Parser parser,
XML_SkippedEntityHandler handler)
{
- skippedEntityHandler = handler;
+ if (parser != NULL)
+ parser->m_skippedEntityHandler = handler;
}
void XMLCALL
@@ -1474,46 +1731,54 @@ XML_SetUnknownEncodingHandler(XML_Parser parser,
XML_UnknownEncodingHandler handler,
void *data)
{
- unknownEncodingHandler = handler;
- unknownEncodingHandlerData = data;
+ if (parser == NULL)
+ return;
+ parser->m_unknownEncodingHandler = handler;
+ parser->m_unknownEncodingHandlerData = data;
}
void XMLCALL
XML_SetElementDeclHandler(XML_Parser parser,
XML_ElementDeclHandler eldecl)
{
- elementDeclHandler = eldecl;
+ if (parser != NULL)
+ parser->m_elementDeclHandler = eldecl;
}
void XMLCALL
XML_SetAttlistDeclHandler(XML_Parser parser,
XML_AttlistDeclHandler attdecl)
{
- attlistDeclHandler = attdecl;
+ if (parser != NULL)
+ parser->m_attlistDeclHandler = attdecl;
}
void XMLCALL
XML_SetEntityDeclHandler(XML_Parser parser,
XML_EntityDeclHandler handler)
{
- entityDeclHandler = handler;
+ if (parser != NULL)
+ parser->m_entityDeclHandler = handler;
}
void XMLCALL
XML_SetXmlDeclHandler(XML_Parser parser,
XML_XmlDeclHandler handler) {
- xmlDeclHandler = handler;
+ if (parser != NULL)
+ parser->m_xmlDeclHandler = handler;
}
int XMLCALL
XML_SetParamEntityParsing(XML_Parser parser,
enum XML_ParamEntityParsing peParsing)
{
+ if (parser == NULL)
+ return 0;
/* block after XML_Parse()/XML_ParseBuffer() has been called */
- if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED)
+ if (parser->m_parsingStatus.parsing == XML_PARSING || parser->m_parsingStatus.parsing == XML_SUSPENDED)
return 0;
#ifdef XML_DTD
- paramEntityParsing = peParsing;
+ parser->m_paramEntityParsing = peParsing;
return 1;
#else
return peParsing == XML_PARAM_ENTITY_PARSING_NEVER;
@@ -1524,88 +1789,117 @@ int XMLCALL
XML_SetHashSalt(XML_Parser parser,
unsigned long hash_salt)
{
+ if (parser == NULL)
+ return 0;
+ if (parser->m_parentParser)
+ return XML_SetHashSalt(parser->m_parentParser, hash_salt);
/* block after XML_Parse()/XML_ParseBuffer() has been called */
- if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED)
+ if (parser->m_parsingStatus.parsing == XML_PARSING || parser->m_parsingStatus.parsing == XML_SUSPENDED)
return 0;
- hash_secret_salt = hash_salt;
+ parser->m_hash_secret_salt = hash_salt;
return 1;
}
enum XML_Status XMLCALL
XML_Parse(XML_Parser parser, const char *s, int len, int isFinal)
{
- switch (ps_parsing) {
+ if ((parser == NULL) || (len < 0) || ((s == NULL) && (len != 0))) {
+ if (parser != NULL)
+ parser->m_errorCode = XML_ERROR_INVALID_ARGUMENT;
+ return XML_STATUS_ERROR;
+ }
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
- errorCode = XML_ERROR_SUSPENDED;
+ parser->m_errorCode = XML_ERROR_SUSPENDED;
return XML_STATUS_ERROR;
case XML_FINISHED:
- errorCode = XML_ERROR_FINISHED;
+ parser->m_errorCode = XML_ERROR_FINISHED;
return XML_STATUS_ERROR;
case XML_INITIALIZED:
- if (parentParser == NULL && !startParsing(parser)) {
- errorCode = XML_ERROR_NO_MEMORY;
+ if (parser->m_parentParser == NULL && !startParsing(parser)) {
+ parser->m_errorCode = XML_ERROR_NO_MEMORY;
return XML_STATUS_ERROR;
}
default:
- ps_parsing = XML_PARSING;
+ parser->m_parsingStatus.parsing = XML_PARSING;
}
if (len == 0) {
- ps_finalBuffer = (XML_Bool)isFinal;
+ parser->m_parsingStatus.finalBuffer = (XML_Bool)isFinal;
if (!isFinal)
return XML_STATUS_OK;
- positionPtr = bufferPtr;
- parseEndPtr = bufferEnd;
+ parser->m_positionPtr = parser->m_bufferPtr;
+ parser->m_parseEndPtr = parser->m_bufferEnd;
/* If data are left over from last buffer, and we now know that these
data are the final chunk of input, then we have to check them again
to detect errors based on that fact.
*/
- errorCode = processor(parser, bufferPtr, parseEndPtr, &bufferPtr);
+ parser->m_errorCode = parser->m_processor(parser, parser->m_bufferPtr, parser->m_parseEndPtr, &parser->m_bufferPtr);
- if (errorCode == XML_ERROR_NONE) {
- switch (ps_parsing) {
+ if (parser->m_errorCode == XML_ERROR_NONE) {
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
- XmlUpdatePosition(encoding, positionPtr, bufferPtr, &position);
- positionPtr = bufferPtr;
+ /* It is hard to be certain, but it seems that this case
+ * cannot occur. This code is cleaning up a previous parse
+ * with no new data (since len == 0). Changing the parsing
+ * state requires getting to execute a handler function, and
+ * there doesn't seem to be an opportunity for that while in
+ * this circumstance.
+ *
+ * Given the uncertainty, we retain the code but exclude it
+ * from coverage tests.
+ *
+ * LCOV_EXCL_START
+ */
+ XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, parser->m_bufferPtr, &parser->m_position);
+ parser->m_positionPtr = parser->m_bufferPtr;
return XML_STATUS_SUSPENDED;
+ /* LCOV_EXCL_STOP */
case XML_INITIALIZED:
case XML_PARSING:
- ps_parsing = XML_FINISHED;
+ parser->m_parsingStatus.parsing = XML_FINISHED;
/* fall through */
default:
return XML_STATUS_OK;
}
}
- eventEndPtr = eventPtr;
- processor = errorProcessor;
+ parser->m_eventEndPtr = parser->m_eventPtr;
+ parser->m_processor = errorProcessor;
return XML_STATUS_ERROR;
}
#ifndef XML_CONTEXT_BYTES
- else if (bufferPtr == bufferEnd) {
+ else if (parser->m_bufferPtr == parser->m_bufferEnd) {
const char *end;
int nLeftOver;
enum XML_Status result;
- parseEndByteIndex += len;
- positionPtr = s;
- ps_finalBuffer = (XML_Bool)isFinal;
+ /* Detect overflow (a+b > MAX <==> b > MAX-a) */
+ if (len > ((XML_Size)-1) / 2 - parser->m_parseEndByteIndex) {
+ parser->m_errorCode = XML_ERROR_NO_MEMORY;
+ parser->m_eventPtr = parser->m_eventEndPtr = NULL;
+ parser->m_processor = errorProcessor;
+ return XML_STATUS_ERROR;
+ }
+ parser->m_parseEndByteIndex += len;
+ parser->m_positionPtr = s;
+ parser->m_parsingStatus.finalBuffer = (XML_Bool)isFinal;
- errorCode = processor(parser, s, parseEndPtr = s + len, &end);
+ parser->m_errorCode = parser->m_processor(parser, s, parser->m_parseEndPtr = s + len, &end);
- if (errorCode != XML_ERROR_NONE) {
- eventEndPtr = eventPtr;
- processor = errorProcessor;
+ if (parser->m_errorCode != XML_ERROR_NONE) {
+ parser->m_eventEndPtr = parser->m_eventPtr;
+ parser->m_processor = errorProcessor;
return XML_STATUS_ERROR;
}
else {
- switch (ps_parsing) {
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
result = XML_STATUS_SUSPENDED;
break;
case XML_INITIALIZED:
case XML_PARSING:
if (isFinal) {
- ps_parsing = XML_FINISHED;
+ parser->m_parsingStatus.parsing = XML_FINISHED;
return XML_STATUS_OK;
}
/* fall through */
@@ -1614,32 +1908,33 @@ XML_Parse(XML_Parser parser, const char *s, int len, int isFinal)
}
}
- XmlUpdatePosition(encoding, positionPtr, end, &position);
+ XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, end, &parser->m_position);
nLeftOver = s + len - end;
if (nLeftOver) {
- if (buffer == NULL || nLeftOver > bufferLim - buffer) {
- /* FIXME avoid integer overflow */
- char *temp;
- temp = (buffer == NULL
- ? (char *)MALLOC(len * 2)
- : (char *)REALLOC(buffer, len * 2));
+ if (parser->m_buffer == NULL || nLeftOver > parser->m_bufferLim - parser->m_buffer) {
+ /* avoid _signed_ integer overflow */
+ char *temp = NULL;
+ const int bytesToAllocate = (int)((unsigned)len * 2U);
+ if (bytesToAllocate > 0) {
+ temp = (char *)REALLOC(parser, parser->m_buffer, bytesToAllocate);
+ }
if (temp == NULL) {
- errorCode = XML_ERROR_NO_MEMORY;
- eventPtr = eventEndPtr = NULL;
- processor = errorProcessor;
+ parser->m_errorCode = XML_ERROR_NO_MEMORY;
+ parser->m_eventPtr = parser->m_eventEndPtr = NULL;
+ parser->m_processor = errorProcessor;
return XML_STATUS_ERROR;
}
- buffer = temp;
- bufferLim = buffer + len * 2;
+ parser->m_buffer = temp;
+ parser->m_bufferLim = parser->m_buffer + bytesToAllocate;
}
- memcpy(buffer, end, nLeftOver);
+ memcpy(parser->m_buffer, end, nLeftOver);
}
- bufferPtr = buffer;
- bufferEnd = buffer + nLeftOver;
- positionPtr = bufferPtr;
- parseEndPtr = bufferEnd;
- eventPtr = bufferPtr;
- eventEndPtr = bufferPtr;
+ parser->m_bufferPtr = parser->m_buffer;
+ parser->m_bufferEnd = parser->m_buffer + nLeftOver;
+ parser->m_positionPtr = parser->m_bufferPtr;
+ parser->m_parseEndPtr = parser->m_bufferEnd;
+ parser->m_eventPtr = parser->m_bufferPtr;
+ parser->m_eventEndPtr = parser->m_bufferPtr;
return result;
}
#endif /* not defined XML_CONTEXT_BYTES */
@@ -1660,106 +1955,110 @@ XML_ParseBuffer(XML_Parser parser, int len, int isFinal)
const char *start;
enum XML_Status result = XML_STATUS_OK;
- switch (ps_parsing) {
+ if (parser == NULL)
+ return XML_STATUS_ERROR;
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
- errorCode = XML_ERROR_SUSPENDED;
+ parser->m_errorCode = XML_ERROR_SUSPENDED;
return XML_STATUS_ERROR;
case XML_FINISHED:
- errorCode = XML_ERROR_FINISHED;
+ parser->m_errorCode = XML_ERROR_FINISHED;
return XML_STATUS_ERROR;
case XML_INITIALIZED:
- if (parentParser == NULL && !startParsing(parser)) {
- errorCode = XML_ERROR_NO_MEMORY;
+ if (parser->m_parentParser == NULL && !startParsing(parser)) {
+ parser->m_errorCode = XML_ERROR_NO_MEMORY;
return XML_STATUS_ERROR;
}
default:
- ps_parsing = XML_PARSING;
+ parser->m_parsingStatus.parsing = XML_PARSING;
}
- start = bufferPtr;
- positionPtr = start;
- bufferEnd += len;
- parseEndPtr = bufferEnd;
- parseEndByteIndex += len;
- ps_finalBuffer = (XML_Bool)isFinal;
+ start = parser->m_bufferPtr;
+ parser->m_positionPtr = start;
+ parser->m_bufferEnd += len;
+ parser->m_parseEndPtr = parser->m_bufferEnd;
+ parser->m_parseEndByteIndex += len;
+ parser->m_parsingStatus.finalBuffer = (XML_Bool)isFinal;
- errorCode = processor(parser, start, parseEndPtr, &bufferPtr);
+ parser->m_errorCode = parser->m_processor(parser, start, parser->m_parseEndPtr, &parser->m_bufferPtr);
- if (errorCode != XML_ERROR_NONE) {
- eventEndPtr = eventPtr;
- processor = errorProcessor;
+ if (parser->m_errorCode != XML_ERROR_NONE) {
+ parser->m_eventEndPtr = parser->m_eventPtr;
+ parser->m_processor = errorProcessor;
return XML_STATUS_ERROR;
}
else {
- switch (ps_parsing) {
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
result = XML_STATUS_SUSPENDED;
break;
case XML_INITIALIZED:
case XML_PARSING:
if (isFinal) {
- ps_parsing = XML_FINISHED;
+ parser->m_parsingStatus.parsing = XML_FINISHED;
return result;
}
default: ; /* should not happen */
}
}
- XmlUpdatePosition(encoding, positionPtr, bufferPtr, &position);
- positionPtr = bufferPtr;
+ XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, parser->m_bufferPtr, &parser->m_position);
+ parser->m_positionPtr = parser->m_bufferPtr;
return result;
}
void * XMLCALL
XML_GetBuffer(XML_Parser parser, int len)
{
+ if (parser == NULL)
+ return NULL;
if (len < 0) {
- errorCode = XML_ERROR_NO_MEMORY;
+ parser->m_errorCode = XML_ERROR_NO_MEMORY;
return NULL;
}
- switch (ps_parsing) {
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
- errorCode = XML_ERROR_SUSPENDED;
+ parser->m_errorCode = XML_ERROR_SUSPENDED;
return NULL;
case XML_FINISHED:
- errorCode = XML_ERROR_FINISHED;
+ parser->m_errorCode = XML_ERROR_FINISHED;
return NULL;
default: ;
}
- if (len > bufferLim - bufferEnd) {
+ if (len > parser->m_bufferLim - parser->m_bufferEnd) {
#ifdef XML_CONTEXT_BYTES
int keep;
#endif /* defined XML_CONTEXT_BYTES */
/* Do not invoke signed arithmetic overflow: */
- int neededSize = (int) ((unsigned)len + (unsigned)(bufferEnd - bufferPtr));
+ int neededSize = (int) ((unsigned)len + (unsigned)(parser->m_bufferEnd - parser->m_bufferPtr));
if (neededSize < 0) {
- errorCode = XML_ERROR_NO_MEMORY;
+ parser->m_errorCode = XML_ERROR_NO_MEMORY;
return NULL;
}
#ifdef XML_CONTEXT_BYTES
- keep = (int)(bufferPtr - buffer);
+ keep = (int)(parser->m_bufferPtr - parser->m_buffer);
if (keep > XML_CONTEXT_BYTES)
keep = XML_CONTEXT_BYTES;
neededSize += keep;
#endif /* defined XML_CONTEXT_BYTES */
- if (neededSize <= bufferLim - buffer) {
+ if (neededSize <= parser->m_bufferLim - parser->m_buffer) {
#ifdef XML_CONTEXT_BYTES
- if (keep < bufferPtr - buffer) {
- int offset = (int)(bufferPtr - buffer) - keep;
- memmove(buffer, &buffer[offset], bufferEnd - bufferPtr + keep);
- bufferEnd -= offset;
- bufferPtr -= offset;
+ if (keep < parser->m_bufferPtr - parser->m_buffer) {
+ int offset = (int)(parser->m_bufferPtr - parser->m_buffer) - keep;
+ memmove(parser->m_buffer, &parser->m_buffer[offset], parser->m_bufferEnd - parser->m_bufferPtr + keep);
+ parser->m_bufferEnd -= offset;
+ parser->m_bufferPtr -= offset;
}
#else
- memmove(buffer, bufferPtr, bufferEnd - bufferPtr);
- bufferEnd = buffer + (bufferEnd - bufferPtr);
- bufferPtr = buffer;
+ memmove(parser->m_buffer, parser->m_bufferPtr, parser->m_bufferEnd - parser->m_bufferPtr);
+ parser->m_bufferEnd = parser->m_buffer + (parser->m_bufferEnd - parser->m_bufferPtr);
+ parser->m_bufferPtr = parser->m_buffer;
#endif /* not defined XML_CONTEXT_BYTES */
}
else {
char *newBuf;
- int bufferSize = (int)(bufferLim - bufferPtr);
+ int bufferSize = (int)(parser->m_bufferLim - parser->m_bufferPtr);
if (bufferSize == 0)
bufferSize = INIT_BUFFER_SIZE;
do {
@@ -1767,71 +2066,73 @@ XML_GetBuffer(XML_Parser parser, int len)
bufferSize = (int) (2U * (unsigned) bufferSize);
} while (bufferSize < neededSize && bufferSize > 0);
if (bufferSize <= 0) {
- errorCode = XML_ERROR_NO_MEMORY;
+ parser->m_errorCode = XML_ERROR_NO_MEMORY;
return NULL;
}
- newBuf = (char *)MALLOC(bufferSize);
+ newBuf = (char *)MALLOC(parser, bufferSize);
if (newBuf == 0) {
- errorCode = XML_ERROR_NO_MEMORY;
+ parser->m_errorCode = XML_ERROR_NO_MEMORY;
return NULL;
}
- bufferLim = newBuf + bufferSize;
+ parser->m_bufferLim = newBuf + bufferSize;
#ifdef XML_CONTEXT_BYTES
- if (bufferPtr) {
- int keep = (int)(bufferPtr - buffer);
+ if (parser->m_bufferPtr) {
+ int keep = (int)(parser->m_bufferPtr - parser->m_buffer);
if (keep > XML_CONTEXT_BYTES)
keep = XML_CONTEXT_BYTES;
- memcpy(newBuf, &bufferPtr[-keep], bufferEnd - bufferPtr + keep);
- FREE(buffer);
- buffer = newBuf;
- bufferEnd = buffer + (bufferEnd - bufferPtr) + keep;
- bufferPtr = buffer + keep;
+ memcpy(newBuf, &parser->m_bufferPtr[-keep], parser->m_bufferEnd - parser->m_bufferPtr + keep);
+ FREE(parser, parser->m_buffer);
+ parser->m_buffer = newBuf;
+ parser->m_bufferEnd = parser->m_buffer + (parser->m_bufferEnd - parser->m_bufferPtr) + keep;
+ parser->m_bufferPtr = parser->m_buffer + keep;
}
else {
- bufferEnd = newBuf + (bufferEnd - bufferPtr);
- bufferPtr = buffer = newBuf;
+ parser->m_bufferEnd = newBuf + (parser->m_bufferEnd - parser->m_bufferPtr);
+ parser->m_bufferPtr = parser->m_buffer = newBuf;
}
#else
- if (bufferPtr) {
- memcpy(newBuf, bufferPtr, bufferEnd - bufferPtr);
- FREE(buffer);
+ if (parser->m_bufferPtr) {
+ memcpy(newBuf, parser->m_bufferPtr, parser->m_bufferEnd - parser->m_bufferPtr);
+ FREE(parser, parser->m_buffer);
}
- bufferEnd = newBuf + (bufferEnd - bufferPtr);
- bufferPtr = buffer = newBuf;
+ parser->m_bufferEnd = newBuf + (parser->m_bufferEnd - parser->m_bufferPtr);
+ parser->m_bufferPtr = parser->m_buffer = newBuf;
#endif /* not defined XML_CONTEXT_BYTES */
}
- eventPtr = eventEndPtr = NULL;
- positionPtr = NULL;
+ parser->m_eventPtr = parser->m_eventEndPtr = NULL;
+ parser->m_positionPtr = NULL;
}
- return bufferEnd;
+ return parser->m_bufferEnd;
}
enum XML_Status XMLCALL
XML_StopParser(XML_Parser parser, XML_Bool resumable)
{
- switch (ps_parsing) {
+ if (parser == NULL)
+ return XML_STATUS_ERROR;
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
if (resumable) {
- errorCode = XML_ERROR_SUSPENDED;
+ parser->m_errorCode = XML_ERROR_SUSPENDED;
return XML_STATUS_ERROR;
}
- ps_parsing = XML_FINISHED;
+ parser->m_parsingStatus.parsing = XML_FINISHED;
break;
case XML_FINISHED:
- errorCode = XML_ERROR_FINISHED;
+ parser->m_errorCode = XML_ERROR_FINISHED;
return XML_STATUS_ERROR;
default:
if (resumable) {
#ifdef XML_DTD
- if (isParamEntity) {
- errorCode = XML_ERROR_SUSPEND_PE;
+ if (parser->m_isParamEntity) {
+ parser->m_errorCode = XML_ERROR_SUSPEND_PE;
return XML_STATUS_ERROR;
}
#endif
- ps_parsing = XML_SUSPENDED;
+ parser->m_parsingStatus.parsing = XML_SUSPENDED;
}
else
- ps_parsing = XML_FINISHED;
+ parser->m_parsingStatus.parsing = XML_FINISHED;
}
return XML_STATUS_OK;
}
@@ -1841,42 +2142,46 @@ XML_ResumeParser(XML_Parser parser)
{
enum XML_Status result = XML_STATUS_OK;
- if (ps_parsing != XML_SUSPENDED) {
- errorCode = XML_ERROR_NOT_SUSPENDED;
+ if (parser == NULL)
+ return XML_STATUS_ERROR;
+ if (parser->m_parsingStatus.parsing != XML_SUSPENDED) {
+ parser->m_errorCode = XML_ERROR_NOT_SUSPENDED;
return XML_STATUS_ERROR;
}
- ps_parsing = XML_PARSING;
+ parser->m_parsingStatus.parsing = XML_PARSING;
- errorCode = processor(parser, bufferPtr, parseEndPtr, &bufferPtr);
+ parser->m_errorCode = parser->m_processor(parser, parser->m_bufferPtr, parser->m_parseEndPtr, &parser->m_bufferPtr);
- if (errorCode != XML_ERROR_NONE) {
- eventEndPtr = eventPtr;
- processor = errorProcessor;
+ if (parser->m_errorCode != XML_ERROR_NONE) {
+ parser->m_eventEndPtr = parser->m_eventPtr;
+ parser->m_processor = errorProcessor;
return XML_STATUS_ERROR;
}
else {
- switch (ps_parsing) {
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
result = XML_STATUS_SUSPENDED;
break;
case XML_INITIALIZED:
case XML_PARSING:
- if (ps_finalBuffer) {
- ps_parsing = XML_FINISHED;
+ if (parser->m_parsingStatus.finalBuffer) {
+ parser->m_parsingStatus.parsing = XML_FINISHED;
return result;
}
default: ;
}
}
- XmlUpdatePosition(encoding, positionPtr, bufferPtr, &position);
- positionPtr = bufferPtr;
+ XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, parser->m_bufferPtr, &parser->m_position);
+ parser->m_positionPtr = parser->m_bufferPtr;
return result;
}
void XMLCALL
XML_GetParsingStatus(XML_Parser parser, XML_ParsingStatus *status)
{
+ if (parser == NULL)
+ return;
assert(status != NULL);
*status = parser->m_parsingStatus;
}
@@ -1884,22 +2189,28 @@ XML_GetParsingStatus(XML_Parser parser, XML_ParsingStatus *status)
enum XML_Error XMLCALL
XML_GetErrorCode(XML_Parser parser)
{
- return errorCode;
+ if (parser == NULL)
+ return XML_ERROR_INVALID_ARGUMENT;
+ return parser->m_errorCode;
}
XML_Index XMLCALL
XML_GetCurrentByteIndex(XML_Parser parser)
{
- if (eventPtr)
- return (XML_Index)(parseEndByteIndex - (parseEndPtr - eventPtr));
+ if (parser == NULL)
+ return -1;
+ if (parser->m_eventPtr)
+ return (XML_Index)(parser->m_parseEndByteIndex - (parser->m_parseEndPtr - parser->m_eventPtr));
return -1;
}
int XMLCALL
XML_GetCurrentByteCount(XML_Parser parser)
{
- if (eventEndPtr && eventPtr)
- return (int)(eventEndPtr - eventPtr);
+ if (parser == NULL)
+ return 0;
+ if (parser->m_eventEndPtr && parser->m_eventPtr)
+ return (int)(parser->m_eventEndPtr - parser->m_eventPtr);
return 0;
}
@@ -1907,11 +2218,19 @@ const char * XMLCALL
XML_GetInputContext(XML_Parser parser, int *offset, int *size)
{
#ifdef XML_CONTEXT_BYTES
- if (eventPtr && buffer) {
- *offset = (int)(eventPtr - buffer);
- *size = (int)(bufferEnd - buffer);
- return buffer;
+ if (parser == NULL)
+ return NULL;
+ if (parser->m_eventPtr && parser->m_buffer) {
+ if (offset != NULL)
+ *offset = (int)(parser->m_eventPtr - parser->m_buffer);
+ if (size != NULL)
+ *size = (int)(parser->m_bufferEnd - parser->m_buffer);
+ return parser->m_buffer;
}
+#else
+ (void)parser;
+ (void)offset;
+ (void)size;
#endif /* defined XML_CONTEXT_BYTES */
return (char *) 0;
}
@@ -1919,109 +2238,166 @@ XML_GetInputContext(XML_Parser parser, int *offset, int *size)
XML_Size XMLCALL
XML_GetCurrentLineNumber(XML_Parser parser)
{
- if (eventPtr && eventPtr >= positionPtr) {
- XmlUpdatePosition(encoding, positionPtr, eventPtr, &position);
- positionPtr = eventPtr;
+ if (parser == NULL)
+ return 0;
+ if (parser->m_eventPtr && parser->m_eventPtr >= parser->m_positionPtr) {
+ XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, parser->m_eventPtr, &parser->m_position);
+ parser->m_positionPtr = parser->m_eventPtr;
}
- return position.lineNumber + 1;
+ return parser->m_position.lineNumber + 1;
}
XML_Size XMLCALL
XML_GetCurrentColumnNumber(XML_Parser parser)
{
- if (eventPtr && eventPtr >= positionPtr) {
- XmlUpdatePosition(encoding, positionPtr, eventPtr, &position);
- positionPtr = eventPtr;
+ if (parser == NULL)
+ return 0;
+ if (parser->m_eventPtr && parser->m_eventPtr >= parser->m_positionPtr) {
+ XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, parser->m_eventPtr, &parser->m_position);
+ parser->m_positionPtr = parser->m_eventPtr;
}
- return position.columnNumber;
+ return parser->m_position.columnNumber;
}
void XMLCALL
XML_FreeContentModel(XML_Parser parser, XML_Content *model)
{
- FREE(model);
+ if (parser != NULL)
+ FREE(parser, model);
}
void * XMLCALL
XML_MemMalloc(XML_Parser parser, size_t size)
{
- return MALLOC(size);
+ if (parser == NULL)
+ return NULL;
+ return MALLOC(parser, size);
}
void * XMLCALL
XML_MemRealloc(XML_Parser parser, void *ptr, size_t size)
{
- return REALLOC(ptr, size);
+ if (parser == NULL)
+ return NULL;
+ return REALLOC(parser, ptr, size);
}
void XMLCALL
XML_MemFree(XML_Parser parser, void *ptr)
{
- FREE(ptr);
+ if (parser != NULL)
+ FREE(parser, ptr);
}
void XMLCALL
XML_DefaultCurrent(XML_Parser parser)
{
- if (defaultHandler) {
- if (openInternalEntities)
+ if (parser == NULL)
+ return;
+ if (parser->m_defaultHandler) {
+ if (parser->m_openInternalEntities)
reportDefault(parser,
- internalEncoding,
- openInternalEntities->internalEventPtr,
- openInternalEntities->internalEventEndPtr);
+ parser->m_internalEncoding,
+ parser->m_openInternalEntities->internalEventPtr,
+ parser->m_openInternalEntities->internalEventEndPtr);
else
- reportDefault(parser, encoding, eventPtr, eventEndPtr);
+ reportDefault(parser, parser->m_encoding, parser->m_eventPtr, parser->m_eventEndPtr);
}
}
const XML_LChar * XMLCALL
XML_ErrorString(enum XML_Error code)
{
- static const XML_LChar* const message[] = {
- 0,
- XML_L("out of memory"),
- XML_L("syntax error"),
- XML_L("no element found"),
- XML_L("not well-formed (invalid token)"),
- XML_L("unclosed token"),
- XML_L("partial character"),
- XML_L("mismatched tag"),
- XML_L("duplicate attribute"),
- XML_L("junk after document element"),
- XML_L("illegal parameter entity reference"),
- XML_L("undefined entity"),
- XML_L("recursive entity reference"),
- XML_L("asynchronous entity"),
- XML_L("reference to invalid character number"),
- XML_L("reference to binary entity"),
- XML_L("reference to external entity in attribute"),
- XML_L("XML or text declaration not at start of entity"),
- XML_L("unknown encoding"),
- XML_L("encoding specified in XML declaration is incorrect"),
- XML_L("unclosed CDATA section"),
- XML_L("error in processing external entity reference"),
- XML_L("document is not standalone"),
- XML_L("unexpected parser state - please send a bug report"),
- XML_L("entity declared in parameter entity"),
- XML_L("requested feature requires XML_DTD support in Expat"),
- XML_L("cannot change setting once parsing has begun"),
- XML_L("unbound prefix"),
- XML_L("must not undeclare prefix"),
- XML_L("incomplete markup in parameter entity"),
- XML_L("XML declaration not well-formed"),
- XML_L("text declaration not well-formed"),
- XML_L("illegal character(s) in public id"),
- XML_L("parser suspended"),
- XML_L("parser not suspended"),
- XML_L("parsing aborted"),
- XML_L("parsing finished"),
- XML_L("cannot suspend in external parameter entity"),
- XML_L("reserved prefix (xml) must not be undeclared or bound to another namespace name"),
- XML_L("reserved prefix (xmlns) must not be declared or undeclared"),
- XML_L("prefix must not be bound to one of the reserved namespace names")
- };
- if (code > 0 && code < sizeof(message)/sizeof(message[0]))
- return message[code];
+ switch (code) {
+ case XML_ERROR_NONE:
+ return NULL;
+ case XML_ERROR_NO_MEMORY:
+ return XML_L("out of memory");
+ case XML_ERROR_SYNTAX:
+ return XML_L("syntax error");
+ case XML_ERROR_NO_ELEMENTS:
+ return XML_L("no element found");
+ case XML_ERROR_INVALID_TOKEN:
+ return XML_L("not well-formed (invalid token)");
+ case XML_ERROR_UNCLOSED_TOKEN:
+ return XML_L("unclosed token");
+ case XML_ERROR_PARTIAL_CHAR:
+ return XML_L("partial character");
+ case XML_ERROR_TAG_MISMATCH:
+ return XML_L("mismatched tag");
+ case XML_ERROR_DUPLICATE_ATTRIBUTE:
+ return XML_L("duplicate attribute");
+ case XML_ERROR_JUNK_AFTER_DOC_ELEMENT:
+ return XML_L("junk after document element");
+ case XML_ERROR_PARAM_ENTITY_REF:
+ return XML_L("illegal parameter entity reference");
+ case XML_ERROR_UNDEFINED_ENTITY:
+ return XML_L("undefined entity");
+ case XML_ERROR_RECURSIVE_ENTITY_REF:
+ return XML_L("recursive entity reference");
+ case XML_ERROR_ASYNC_ENTITY:
+ return XML_L("asynchronous entity");
+ case XML_ERROR_BAD_CHAR_REF:
+ return XML_L("reference to invalid character number");
+ case XML_ERROR_BINARY_ENTITY_REF:
+ return XML_L("reference to binary entity");
+ case XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF:
+ return XML_L("reference to external entity in attribute");
+ case XML_ERROR_MISPLACED_XML_PI:
+ return XML_L("XML or text declaration not at start of entity");
+ case XML_ERROR_UNKNOWN_ENCODING:
+ return XML_L("unknown encoding");
+ case XML_ERROR_INCORRECT_ENCODING:
+ return XML_L("encoding specified in XML declaration is incorrect");
+ case XML_ERROR_UNCLOSED_CDATA_SECTION:
+ return XML_L("unclosed CDATA section");
+ case XML_ERROR_EXTERNAL_ENTITY_HANDLING:
+ return XML_L("error in processing external entity reference");
+ case XML_ERROR_NOT_STANDALONE:
+ return XML_L("document is not standalone");
+ case XML_ERROR_UNEXPECTED_STATE:
+ return XML_L("unexpected parser state - please send a bug report");
+ case XML_ERROR_ENTITY_DECLARED_IN_PE:
+ return XML_L("entity declared in parameter entity");
+ case XML_ERROR_FEATURE_REQUIRES_XML_DTD:
+ return XML_L("requested feature requires XML_DTD support in Expat");
+ case XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING:
+ return XML_L("cannot change setting once parsing has begun");
+ /* Added in 1.95.7. */
+ case XML_ERROR_UNBOUND_PREFIX:
+ return XML_L("unbound prefix");
+ /* Added in 1.95.8. */
+ case XML_ERROR_UNDECLARING_PREFIX:
+ return XML_L("must not undeclare prefix");
+ case XML_ERROR_INCOMPLETE_PE:
+ return XML_L("incomplete markup in parameter entity");
+ case XML_ERROR_XML_DECL:
+ return XML_L("XML declaration not well-formed");
+ case XML_ERROR_TEXT_DECL:
+ return XML_L("text declaration not well-formed");
+ case XML_ERROR_PUBLICID:
+ return XML_L("illegal character(s) in public id");
+ case XML_ERROR_SUSPENDED:
+ return XML_L("parser suspended");
+ case XML_ERROR_NOT_SUSPENDED:
+ return XML_L("parser not suspended");
+ case XML_ERROR_ABORTED:
+ return XML_L("parsing aborted");
+ case XML_ERROR_FINISHED:
+ return XML_L("parsing finished");
+ case XML_ERROR_SUSPEND_PE:
+ return XML_L("cannot suspend in external parameter entity");
+ /* Added in 2.0.0. */
+ case XML_ERROR_RESERVED_PREFIX_XML:
+ return XML_L("reserved prefix (xml) must not be undeclared or bound to another namespace name");
+ case XML_ERROR_RESERVED_PREFIX_XMLNS:
+ return XML_L("reserved prefix (xmlns) must not be declared or undeclared");
+ case XML_ERROR_RESERVED_NAMESPACE_URI:
+ return XML_L("prefix must not be bound to one of the reserved namespace names");
+ /* Added in 2.2.5. */
+ case XML_ERROR_INVALID_ARGUMENT: /* Constant added in 2.2.1, already */
+ return XML_L("invalid argument");
+ }
return NULL;
}
@@ -2104,12 +2480,12 @@ XML_GetFeatureList(void)
static XML_Bool
storeRawNames(XML_Parser parser)
{
- TAG *tag = tagStack;
+ TAG *tag = parser->m_tagStack;
while (tag) {
int bufSize;
int nameLen = sizeof(XML_Char) * (tag->name.strLen + 1);
char *rawNameBuf = tag->buf + nameLen;
- /* Stop if already stored. Since tagStack is a stack, we can stop
+ /* Stop if already stored. Since m_tagStack is a stack, we can stop
at the first entry that has already been copied; everything
below it in the stack is already been accounted for in a
previous call to this function.
@@ -2121,7 +2497,7 @@ storeRawNames(XML_Parser parser)
*/
bufSize = nameLen + ROUND_UP(tag->rawNameLength, sizeof(XML_Char));
if (bufSize > tag->bufEnd - tag->buf) {
- char *temp = (char *)REALLOC(tag->buf, bufSize);
+ char *temp = (char *)REALLOC(parser, tag->buf, bufSize);
if (temp == NULL)
return XML_FALSE;
/* if tag->name.str points to tag->buf (only when namespace
@@ -2152,8 +2528,8 @@ contentProcessor(XML_Parser parser,
const char *end,
const char **endPtr)
{
- enum XML_Error result = doContent(parser, 0, encoding, start, end,
- endPtr, (XML_Bool)!ps_finalBuffer);
+ enum XML_Error result = doContent(parser, 0, parser->m_encoding, start, end,
+ endPtr, (XML_Bool)!parser->m_parsingStatus.finalBuffer);
if (result == XML_ERROR_NONE) {
if (!storeRawNames(parser))
return XML_ERROR_NO_MEMORY;
@@ -2170,7 +2546,7 @@ externalEntityInitProcessor(XML_Parser parser,
enum XML_Error result = initializeEncoding(parser);
if (result != XML_ERROR_NONE)
return result;
- processor = externalEntityInitProcessor2;
+ parser->m_processor = externalEntityInitProcessor2;
return externalEntityInitProcessor2(parser, start, end, endPtr);
}
@@ -2181,7 +2557,7 @@ externalEntityInitProcessor2(XML_Parser parser,
const char **endPtr)
{
const char *next = start; /* XmlContentTok doesn't always set the last arg */
- int tok = XmlContentTok(encoding, start, end, &next);
+ int tok = XmlContentTok(parser->m_encoding, start, end, &next);
switch (tok) {
case XML_TOK_BOM:
/* If we are at the end of the buffer, this would cause the next stage,
@@ -2189,28 +2565,28 @@ externalEntityInitProcessor2(XML_Parser parser,
doContent (by detecting XML_TOK_NONE) without processing any xml text
declaration - causing the error XML_ERROR_MISPLACED_XML_PI in doContent.
*/
- if (next == end && !ps_finalBuffer) {
+ if (next == end && !parser->m_parsingStatus.finalBuffer) {
*endPtr = next;
return XML_ERROR_NONE;
}
start = next;
break;
case XML_TOK_PARTIAL:
- if (!ps_finalBuffer) {
+ if (!parser->m_parsingStatus.finalBuffer) {
*endPtr = start;
return XML_ERROR_NONE;
}
- eventPtr = start;
+ parser->m_eventPtr = start;
return XML_ERROR_UNCLOSED_TOKEN;
case XML_TOK_PARTIAL_CHAR:
- if (!ps_finalBuffer) {
+ if (!parser->m_parsingStatus.finalBuffer) {
*endPtr = start;
return XML_ERROR_NONE;
}
- eventPtr = start;
+ parser->m_eventPtr = start;
return XML_ERROR_PARTIAL_CHAR;
}
- processor = externalEntityInitProcessor3;
+ parser->m_processor = externalEntityInitProcessor3;
return externalEntityInitProcessor3(parser, start, end, endPtr);
}
@@ -2222,9 +2598,9 @@ externalEntityInitProcessor3(XML_Parser parser,
{
int tok;
const char *next = start; /* XmlContentTok doesn't always set the last arg */
- eventPtr = start;
- tok = XmlContentTok(encoding, start, end, &next);
- eventEndPtr = next;
+ parser->m_eventPtr = start;
+ tok = XmlContentTok(parser->m_encoding, start, end, &next);
+ parser->m_eventEndPtr = next;
switch (tok) {
case XML_TOK_XML_DECL:
@@ -2233,7 +2609,7 @@ externalEntityInitProcessor3(XML_Parser parser,
result = processXmlDecl(parser, 1, start, next);
if (result != XML_ERROR_NONE)
return result;
- switch (ps_parsing) {
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
*endPtr = next;
return XML_ERROR_NONE;
@@ -2245,20 +2621,20 @@ externalEntityInitProcessor3(XML_Parser parser,
}
break;
case XML_TOK_PARTIAL:
- if (!ps_finalBuffer) {
+ if (!parser->m_parsingStatus.finalBuffer) {
*endPtr = start;
return XML_ERROR_NONE;
}
return XML_ERROR_UNCLOSED_TOKEN;
case XML_TOK_PARTIAL_CHAR:
- if (!ps_finalBuffer) {
+ if (!parser->m_parsingStatus.finalBuffer) {
*endPtr = start;
return XML_ERROR_NONE;
}
return XML_ERROR_PARTIAL_CHAR;
}
- processor = externalEntityContentProcessor;
- tagLevel = 1;
+ parser->m_processor = externalEntityContentProcessor;
+ parser->m_tagLevel = 1;
return externalEntityContentProcessor(parser, start, end, endPtr);
}
@@ -2268,8 +2644,8 @@ externalEntityContentProcessor(XML_Parser parser,
const char *end,
const char **endPtr)
{
- enum XML_Error result = doContent(parser, 1, encoding, start, end,
- endPtr, (XML_Bool)!ps_finalBuffer);
+ enum XML_Error result = doContent(parser, 1, parser->m_encoding, start, end,
+ endPtr, (XML_Bool)!parser->m_parsingStatus.finalBuffer);
if (result == XML_ERROR_NONE) {
if (!storeRawNames(parser))
return XML_ERROR_NO_MEMORY;
@@ -2287,17 +2663,17 @@ doContent(XML_Parser parser,
XML_Bool haveMore)
{
/* save one level of indirection */
- DTD * const dtd = _dtd;
+ DTD * const dtd = parser->m_dtd;
const char **eventPP;
const char **eventEndPP;
- if (enc == encoding) {
- eventPP = &eventPtr;
- eventEndPP = &eventEndPtr;
+ if (enc == parser->m_encoding) {
+ eventPP = &parser->m_eventPtr;
+ eventEndPP = &parser->m_eventEndPtr;
}
else {
- eventPP = &(openInternalEntities->internalEventPtr);
- eventEndPP = &(openInternalEntities->internalEventEndPtr);
+ eventPP = &(parser->m_openInternalEntities->internalEventPtr);
+ eventEndPP = &(parser->m_openInternalEntities->internalEventEndPtr);
}
*eventPP = s;
@@ -2312,18 +2688,18 @@ doContent(XML_Parser parser,
return XML_ERROR_NONE;
}
*eventEndPP = end;
- if (characterDataHandler) {
+ if (parser->m_characterDataHandler) {
XML_Char c = 0xA;
- characterDataHandler(handlerArg, &c, 1);
+ parser->m_characterDataHandler(parser->m_handlerArg, &c, 1);
}
- else if (defaultHandler)
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, end);
/* We are at the end of the final buffer, should we check for
XML_SUSPENDED, XML_FINISHED?
*/
if (startTagLevel == 0)
return XML_ERROR_NO_ELEMENTS;
- if (tagLevel != startTagLevel)
+ if (parser->m_tagLevel != startTagLevel)
return XML_ERROR_ASYNC_ENTITY;
*nextPtr = end;
return XML_ERROR_NONE;
@@ -2333,7 +2709,7 @@ doContent(XML_Parser parser,
return XML_ERROR_NONE;
}
if (startTagLevel > 0) {
- if (tagLevel != startTagLevel)
+ if (parser->m_tagLevel != startTagLevel)
return XML_ERROR_ASYNC_ENTITY;
*nextPtr = s;
return XML_ERROR_NONE;
@@ -2362,9 +2738,9 @@ doContent(XML_Parser parser,
s + enc->minBytesPerChar,
next - enc->minBytesPerChar);
if (ch) {
- if (characterDataHandler)
- characterDataHandler(handlerArg, &ch, 1);
- else if (defaultHandler)
+ if (parser->m_characterDataHandler)
+ parser->m_characterDataHandler(parser->m_handlerArg, &ch, 1);
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
break;
}
@@ -2386,9 +2762,9 @@ doContent(XML_Parser parser,
return XML_ERROR_ENTITY_DECLARED_IN_PE;
}
else if (!entity) {
- if (skippedEntityHandler)
- skippedEntityHandler(handlerArg, name, 0);
- else if (defaultHandler)
+ if (parser->m_skippedEntityHandler)
+ parser->m_skippedEntityHandler(parser->m_handlerArg, name, 0);
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
break;
}
@@ -2398,10 +2774,10 @@ doContent(XML_Parser parser,
return XML_ERROR_BINARY_ENTITY_REF;
if (entity->textPtr) {
enum XML_Error result;
- if (!defaultExpandInternalEntities) {
- if (skippedEntityHandler)
- skippedEntityHandler(handlerArg, entity->name, 0);
- else if (defaultHandler)
+ if (!parser->m_defaultExpandInternalEntities) {
+ if (parser->m_skippedEntityHandler)
+ parser->m_skippedEntityHandler(parser->m_handlerArg, entity->name, 0);
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
break;
}
@@ -2409,22 +2785,22 @@ doContent(XML_Parser parser,
if (result != XML_ERROR_NONE)
return result;
}
- else if (externalEntityRefHandler) {
+ else if (parser->m_externalEntityRefHandler) {
const XML_Char *context;
entity->open = XML_TRUE;
context = getContext(parser);
entity->open = XML_FALSE;
if (!context)
return XML_ERROR_NO_MEMORY;
- if (!externalEntityRefHandler(externalEntityRefHandlerArg,
+ if (!parser->m_externalEntityRefHandler(parser->m_externalEntityRefHandlerArg,
context,
entity->base,
entity->systemId,
entity->publicId))
return XML_ERROR_EXTERNAL_ENTITY_HANDLING;
- poolDiscard(&tempPool);
+ poolDiscard(&parser->m_tempPool);
}
- else if (defaultHandler)
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
break;
}
@@ -2435,29 +2811,29 @@ doContent(XML_Parser parser,
TAG *tag;
enum XML_Error result;
XML_Char *toPtr;
- if (freeTagList) {
- tag = freeTagList;
- freeTagList = freeTagList->parent;
+ if (parser->m_freeTagList) {
+ tag = parser->m_freeTagList;
+ parser->m_freeTagList = parser->m_freeTagList->parent;
}
else {
- tag = (TAG *)MALLOC(sizeof(TAG));
+ tag = (TAG *)MALLOC(parser, sizeof(TAG));
if (!tag)
return XML_ERROR_NO_MEMORY;
- tag->buf = (char *)MALLOC(INIT_TAG_BUF_SIZE);
+ tag->buf = (char *)MALLOC(parser, INIT_TAG_BUF_SIZE);
if (!tag->buf) {
- FREE(tag);
+ FREE(parser, tag);
return XML_ERROR_NO_MEMORY;
}
tag->bufEnd = tag->buf + INIT_TAG_BUF_SIZE;
}
tag->bindings = NULL;
- tag->parent = tagStack;
- tagStack = tag;
+ tag->parent = parser->m_tagStack;
+ parser->m_tagStack = tag;
tag->name.localPart = NULL;
tag->name.prefix = NULL;
tag->rawName = s + enc->minBytesPerChar;
tag->rawNameLength = XmlNameLength(enc, tag->rawName);
- ++tagLevel;
+ ++parser->m_tagLevel;
{
const char *rawNameEnd = tag->rawName + tag->rawNameLength;
const char *fromPtr = tag->rawName;
@@ -2469,13 +2845,13 @@ doContent(XML_Parser parser,
&fromPtr, rawNameEnd,
(ICHAR **)&toPtr, (ICHAR *)tag->bufEnd - 1);
convLen = (int)(toPtr - (XML_Char *)tag->buf);
- if ((convert_res == XML_CONVERT_COMPLETED) || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) {
+ if ((fromPtr >= rawNameEnd) || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) {
tag->name.strLen = convLen;
break;
}
bufSize = (int)(tag->bufEnd - tag->buf) << 1;
{
- char *temp = (char *)REALLOC(tag->buf, bufSize);
+ char *temp = (char *)REALLOC(parser, tag->buf, bufSize);
if (temp == NULL)
return XML_ERROR_NO_MEMORY;
tag->buf = temp;
@@ -2489,12 +2865,12 @@ doContent(XML_Parser parser,
result = storeAtts(parser, enc, s, &(tag->name), &(tag->bindings));
if (result)
return result;
- if (startElementHandler)
- startElementHandler(handlerArg, tag->name.str,
- (const XML_Char **)atts);
- else if (defaultHandler)
+ if (parser->m_startElementHandler)
+ parser->m_startElementHandler(parser->m_handlerArg, tag->name.str,
+ (const XML_Char **)parser->m_atts);
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
- poolClear(&tempPool);
+ poolClear(&parser->m_tempPool);
break;
}
case XML_TOK_EMPTY_ELEMENT_NO_ATTS:
@@ -2506,51 +2882,47 @@ doContent(XML_Parser parser,
BINDING *bindings = NULL;
XML_Bool noElmHandlers = XML_TRUE;
TAG_NAME name;
- name.str = poolStoreString(&tempPool, enc, rawName,
+ name.str = poolStoreString(&parser->m_tempPool, enc, rawName,
rawName + XmlNameLength(enc, rawName));
if (!name.str)
return XML_ERROR_NO_MEMORY;
- poolFinish(&tempPool);
+ poolFinish(&parser->m_tempPool);
result = storeAtts(parser, enc, s, &name, &bindings);
- if (result)
+ if (result != XML_ERROR_NONE) {
+ freeBindings(parser, bindings);
return result;
- poolFinish(&tempPool);
- if (startElementHandler) {
- startElementHandler(handlerArg, name.str, (const XML_Char **)atts);
+ }
+ poolFinish(&parser->m_tempPool);
+ if (parser->m_startElementHandler) {
+ parser->m_startElementHandler(parser->m_handlerArg, name.str, (const XML_Char **)parser->m_atts);
noElmHandlers = XML_FALSE;
}
- if (endElementHandler) {
- if (startElementHandler)
+ if (parser->m_endElementHandler) {
+ if (parser->m_startElementHandler)
*eventPP = *eventEndPP;
- endElementHandler(handlerArg, name.str);
+ parser->m_endElementHandler(parser->m_handlerArg, name.str);
noElmHandlers = XML_FALSE;
}
- if (noElmHandlers && defaultHandler)
+ if (noElmHandlers && parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
- poolClear(&tempPool);
- while (bindings) {
- BINDING *b = bindings;
- if (endNamespaceDeclHandler)
- endNamespaceDeclHandler(handlerArg, b->prefix->name);
- bindings = bindings->nextTagBinding;
- b->nextTagBinding = freeBindingList;
- freeBindingList = b;
- b->prefix->binding = b->prevPrefixBinding;
- }
+ poolClear(&parser->m_tempPool);
+ freeBindings(parser, bindings);
}
- if (tagLevel == 0)
+ if ((parser->m_tagLevel == 0) &&
+ !((parser->m_parsingStatus.parsing == XML_FINISHED) || (parser->m_parsingStatus.parsing == XML_SUSPENDED))) {
return epilogProcessor(parser, next, end, nextPtr);
+ }
break;
case XML_TOK_END_TAG:
- if (tagLevel == startTagLevel)
+ if (parser->m_tagLevel == startTagLevel)
return XML_ERROR_ASYNC_ENTITY;
else {
int len;
const char *rawName;
- TAG *tag = tagStack;
- tagStack = tag->parent;
- tag->parent = freeTagList;
- freeTagList = tag;
+ TAG *tag = parser->m_tagStack;
+ parser->m_tagStack = tag->parent;
+ tag->parent = parser->m_freeTagList;
+ parser->m_freeTagList = tag;
rawName = s + enc->minBytesPerChar*2;
len = XmlNameLength(enc, rawName);
if (len != tag->rawNameLength
@@ -2558,13 +2930,13 @@ doContent(XML_Parser parser,
*eventPP = rawName;
return XML_ERROR_TAG_MISMATCH;
}
- --tagLevel;
- if (endElementHandler) {
+ --parser->m_tagLevel;
+ if (parser->m_endElementHandler) {
const XML_Char *localPart;
const XML_Char *prefix;
XML_Char *uri;
localPart = tag->name.localPart;
- if (ns && localPart) {
+ if (parser->m_ns && localPart) {
/* localPart and prefix may have been overwritten in
tag->name.str, since this points to the binding->uri
buffer which gets re-used; so we have to add them again
@@ -2573,26 +2945,26 @@ doContent(XML_Parser parser,
/* don't need to check for space - already done in storeAtts() */
while (*localPart) *uri++ = *localPart++;
prefix = (XML_Char *)tag->name.prefix;
- if (ns_triplets && prefix) {
- *uri++ = namespaceSeparator;
+ if (parser->m_ns_triplets && prefix) {
+ *uri++ = parser->m_namespaceSeparator;
while (*prefix) *uri++ = *prefix++;
}
*uri = XML_T('\0');
}
- endElementHandler(handlerArg, tag->name.str);
+ parser->m_endElementHandler(parser->m_handlerArg, tag->name.str);
}
- else if (defaultHandler)
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
while (tag->bindings) {
BINDING *b = tag->bindings;
- if (endNamespaceDeclHandler)
- endNamespaceDeclHandler(handlerArg, b->prefix->name);
+ if (parser->m_endNamespaceDeclHandler)
+ parser->m_endNamespaceDeclHandler(parser->m_handlerArg, b->prefix->name);
tag->bindings = tag->bindings->nextTagBinding;
- b->nextTagBinding = freeBindingList;
- freeBindingList = b;
+ b->nextTagBinding = parser->m_freeBindingList;
+ parser->m_freeBindingList = b;
b->prefix->binding = b->prevPrefixBinding;
}
- if (tagLevel == 0)
+ if (parser->m_tagLevel == 0)
return epilogProcessor(parser, next, end, nextPtr);
}
break;
@@ -2601,29 +2973,29 @@ doContent(XML_Parser parser,
int n = XmlCharRefNumber(enc, s);
if (n < 0)
return XML_ERROR_BAD_CHAR_REF;
- if (characterDataHandler) {
+ if (parser->m_characterDataHandler) {
XML_Char buf[XML_ENCODE_MAX];
- characterDataHandler(handlerArg, buf, XmlEncode(n, (ICHAR *)buf));
+ parser->m_characterDataHandler(parser->m_handlerArg, buf, XmlEncode(n, (ICHAR *)buf));
}
- else if (defaultHandler)
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
}
break;
case XML_TOK_XML_DECL:
return XML_ERROR_MISPLACED_XML_PI;
case XML_TOK_DATA_NEWLINE:
- if (characterDataHandler) {
+ if (parser->m_characterDataHandler) {
XML_Char c = 0xA;
- characterDataHandler(handlerArg, &c, 1);
+ parser->m_characterDataHandler(parser->m_handlerArg, &c, 1);
}
- else if (defaultHandler)
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
break;
case XML_TOK_CDATA_SECT_OPEN:
{
enum XML_Error result;
- if (startCdataSectionHandler)
- startCdataSectionHandler(handlerArg);
+ if (parser->m_startCdataSectionHandler)
+ parser->m_startCdataSectionHandler(parser->m_handlerArg);
#if 0
/* Suppose you doing a transformation on a document that involves
changing only the character data. You set up a defaultHandler
@@ -2637,16 +3009,16 @@ doContent(XML_Parser parser,
However, now we have a start/endCdataSectionHandler, so it seems
easier to let the user deal with this.
*/
- else if (characterDataHandler)
- characterDataHandler(handlerArg, dataBuf, 0);
+ else if (parser->m_characterDataHandler)
+ parser->m_characterDataHandler(parser->m_handlerArg, parser->m_dataBuf, 0);
#endif
- else if (defaultHandler)
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
result = doCdataSection(parser, enc, &next, end, nextPtr, haveMore);
if (result != XML_ERROR_NONE)
return result;
else if (!next) {
- processor = cdataSectionProcessor;
+ parser->m_processor = cdataSectionProcessor;
return result;
}
}
@@ -2656,19 +3028,19 @@ doContent(XML_Parser parser,
*nextPtr = s;
return XML_ERROR_NONE;
}
- if (characterDataHandler) {
+ if (parser->m_characterDataHandler) {
if (MUST_CONVERT(enc, s)) {
- ICHAR *dataPtr = (ICHAR *)dataBuf;
- XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)dataBufEnd);
- characterDataHandler(handlerArg, dataBuf,
- (int)(dataPtr - (ICHAR *)dataBuf));
+ ICHAR *dataPtr = (ICHAR *)parser->m_dataBuf;
+ XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)parser->m_dataBufEnd);
+ parser->m_characterDataHandler(parser->m_handlerArg, parser->m_dataBuf,
+ (int)(dataPtr - (ICHAR *)parser->m_dataBuf));
}
else
- characterDataHandler(handlerArg,
+ parser->m_characterDataHandler(parser->m_handlerArg,
(XML_Char *)s,
(int)((XML_Char *)end - (XML_Char *)s));
}
- else if (defaultHandler)
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, end);
/* We are at the end of the final buffer, should we check for
XML_SUSPENDED, XML_FINISHED?
@@ -2677,7 +3049,7 @@ doContent(XML_Parser parser,
*eventPP = end;
return XML_ERROR_NO_ELEMENTS;
}
- if (tagLevel != startTagLevel) {
+ if (parser->m_tagLevel != startTagLevel) {
*eventPP = end;
return XML_ERROR_ASYNC_ENTITY;
}
@@ -2685,26 +3057,26 @@ doContent(XML_Parser parser,
return XML_ERROR_NONE;
case XML_TOK_DATA_CHARS:
{
- XML_CharacterDataHandler charDataHandler = characterDataHandler;
+ XML_CharacterDataHandler charDataHandler = parser->m_characterDataHandler;
if (charDataHandler) {
if (MUST_CONVERT(enc, s)) {
for (;;) {
- ICHAR *dataPtr = (ICHAR *)dataBuf;
- const enum XML_Convert_Result convert_res = XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)dataBufEnd);
+ ICHAR *dataPtr = (ICHAR *)parser->m_dataBuf;
+ const enum XML_Convert_Result convert_res = XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)parser->m_dataBufEnd);
*eventEndPP = s;
- charDataHandler(handlerArg, dataBuf,
- (int)(dataPtr - (ICHAR *)dataBuf));
+ charDataHandler(parser->m_handlerArg, parser->m_dataBuf,
+ (int)(dataPtr - (ICHAR *)parser->m_dataBuf));
if ((convert_res == XML_CONVERT_COMPLETED) || (convert_res == XML_CONVERT_INPUT_INCOMPLETE))
break;
*eventPP = s;
}
}
else
- charDataHandler(handlerArg,
+ charDataHandler(parser->m_handlerArg,
(XML_Char *)s,
(int)((XML_Char *)next - (XML_Char *)s));
}
- else if (defaultHandler)
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
}
break;
@@ -2717,12 +3089,20 @@ doContent(XML_Parser parser,
return XML_ERROR_NO_MEMORY;
break;
default:
- if (defaultHandler)
+ /* All of the tokens produced by XmlContentTok() have their own
+ * explicit cases, so this default is not strictly necessary.
+ * However it is a useful safety net, so we retain the code and
+ * simply exclude it from the coverage tests.
+ *
+ * LCOV_EXCL_START
+ */
+ if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
break;
+ /* LCOV_EXCL_STOP */
}
*eventPP = s = next;
- switch (ps_parsing) {
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
*nextPtr = next;
return XML_ERROR_NONE;
@@ -2734,6 +3114,29 @@ doContent(XML_Parser parser,
/* not reached */
}
+/* This function does not call free() on the allocated memory, merely
+ * moving it to the parser's m_freeBindingList where it can be freed or
+ * reused as appropriate.
+ */
+static void
+freeBindings(XML_Parser parser, BINDING *bindings)
+{
+ while (bindings) {
+ BINDING *b = bindings;
+
+ /* m_startNamespaceDeclHandler will have been called for this
+ * binding in addBindings(), so call the end handler now.
+ */
+ if (parser->m_endNamespaceDeclHandler)
+ parser->m_endNamespaceDeclHandler(parser->m_handlerArg, b->prefix->name);
+
+ bindings = bindings->nextTagBinding;
+ b->nextTagBinding = parser->m_freeBindingList;
+ parser->m_freeBindingList = b;
+ b->prefix->binding = b->prevPrefixBinding;
+ }
+}
+
/* Precondition: all arguments must be non-NULL;
Purpose:
- normalize attributes
@@ -2749,7 +3152,7 @@ storeAtts(XML_Parser parser, const ENCODING *enc,
const char *attStr, TAG_NAME *tagNamePtr,
BINDING **bindingsPtr)
{
- DTD * const dtd = _dtd; /* save one level of indirection */
+ DTD * const dtd = parser->m_dtd; /* save one level of indirection */
ELEMENT_TYPE *elementType;
int nDefaultAtts;
const XML_Char **appAtts; /* the attribute list for the application */
@@ -2772,39 +3175,43 @@ storeAtts(XML_Parser parser, const ENCODING *enc,
sizeof(ELEMENT_TYPE));
if (!elementType)
return XML_ERROR_NO_MEMORY;
- if (ns && !setElementTypePrefix(parser, elementType))
+ if (parser->m_ns && !setElementTypePrefix(parser, elementType))
return XML_ERROR_NO_MEMORY;
}
nDefaultAtts = elementType->nDefaultAtts;
/* get the attributes from the tokenizer */
- n = XmlGetAttributes(enc, attStr, attsSize, atts);
- if (n + nDefaultAtts > attsSize) {
- int oldAttsSize = attsSize;
+ n = XmlGetAttributes(enc, attStr, parser->m_attsSize, parser->m_atts);
+ if (n + nDefaultAtts > parser->m_attsSize) {
+ int oldAttsSize = parser->m_attsSize;
ATTRIBUTE *temp;
#ifdef XML_ATTR_INFO
XML_AttrInfo *temp2;
#endif
- attsSize = n + nDefaultAtts + INIT_ATTS_SIZE;
- temp = (ATTRIBUTE *)REALLOC((void *)atts, attsSize * sizeof(ATTRIBUTE));
- if (temp == NULL)
+ parser->m_attsSize = n + nDefaultAtts + INIT_ATTS_SIZE;
+ temp = (ATTRIBUTE *)REALLOC(parser, (void *)parser->m_atts, parser->m_attsSize * sizeof(ATTRIBUTE));
+ if (temp == NULL) {
+ parser->m_attsSize = oldAttsSize;
return XML_ERROR_NO_MEMORY;
- atts = temp;
+ }
+ parser->m_atts = temp;
#ifdef XML_ATTR_INFO
- temp2 = (XML_AttrInfo *)REALLOC((void *)attInfo, attsSize * sizeof(XML_AttrInfo));
- if (temp2 == NULL)
+ temp2 = (XML_AttrInfo *)REALLOC(parser, (void *)parser->m_attInfo, parser->m_attsSize * sizeof(XML_AttrInfo));
+ if (temp2 == NULL) {
+ parser->m_attsSize = oldAttsSize;
return XML_ERROR_NO_MEMORY;
- attInfo = temp2;
+ }
+ parser->m_attInfo = temp2;
#endif
if (n > oldAttsSize)
- XmlGetAttributes(enc, attStr, n, atts);
+ XmlGetAttributes(enc, attStr, n, parser->m_atts);
}
- appAtts = (const XML_Char **)atts;
+ appAtts = (const XML_Char **)parser->m_atts;
for (i = 0; i < n; i++) {
- ATTRIBUTE *currAtt = &atts[i];
+ ATTRIBUTE *currAtt = &parser->m_atts[i];
#ifdef XML_ATTR_INFO
- XML_AttrInfo *currAttInfo = &attInfo[i];
+ XML_AttrInfo *currAttInfo = &parser->m_attInfo[i];
#endif
/* add the name and value to the attribute list */
ATTRIBUTE_ID *attId = getAttributeId(parser, enc, currAtt->name,
@@ -2813,25 +3220,25 @@ storeAtts(XML_Parser parser, const ENCODING *enc,
if (!attId)
return XML_ERROR_NO_MEMORY;
#ifdef XML_ATTR_INFO
- currAttInfo->nameStart = parseEndByteIndex - (parseEndPtr - currAtt->name);
+ currAttInfo->nameStart = parser->m_parseEndByteIndex - (parser->m_parseEndPtr - currAtt->name);
currAttInfo->nameEnd = currAttInfo->nameStart +
XmlNameLength(enc, currAtt->name);
- currAttInfo->valueStart = parseEndByteIndex -
- (parseEndPtr - currAtt->valuePtr);
- currAttInfo->valueEnd = parseEndByteIndex - (parseEndPtr - currAtt->valueEnd);
+ currAttInfo->valueStart = parser->m_parseEndByteIndex -
+ (parser->m_parseEndPtr - currAtt->valuePtr);
+ currAttInfo->valueEnd = parser->m_parseEndByteIndex - (parser->m_parseEndPtr - currAtt->valueEnd);
#endif
/* Detect duplicate attributes by their QNames. This does not work when
namespace processing is turned on and different prefixes for the same
namespace are used. For this case we have a check further down.
*/
if ((attId->name)[-1]) {
- if (enc == encoding)
- eventPtr = atts[i].name;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = parser->m_atts[i].name;
return XML_ERROR_DUPLICATE_ATTRIBUTE;
}
(attId->name)[-1] = 1;
appAtts[attIndex++] = attId->name;
- if (!atts[i].normalized) {
+ if (!parser->m_atts[i].normalized) {
enum XML_Error result;
XML_Bool isCdata = XML_TRUE;
@@ -2848,20 +3255,20 @@ storeAtts(XML_Parser parser, const ENCODING *enc,
/* normalize the attribute value */
result = storeAttributeValue(parser, enc, isCdata,
- atts[i].valuePtr, atts[i].valueEnd,
- &tempPool);
+ parser->m_atts[i].valuePtr, parser->m_atts[i].valueEnd,
+ &parser->m_tempPool);
if (result)
return result;
- appAtts[attIndex] = poolStart(&tempPool);
- poolFinish(&tempPool);
+ appAtts[attIndex] = poolStart(&parser->m_tempPool);
+ poolFinish(&parser->m_tempPool);
}
else {
/* the value did not need normalizing */
- appAtts[attIndex] = poolStoreString(&tempPool, enc, atts[i].valuePtr,
- atts[i].valueEnd);
+ appAtts[attIndex] = poolStoreString(&parser->m_tempPool, enc, parser->m_atts[i].valuePtr,
+ parser->m_atts[i].valueEnd);
if (appAtts[attIndex] == 0)
return XML_ERROR_NO_MEMORY;
- poolFinish(&tempPool);
+ poolFinish(&parser->m_tempPool);
}
/* handle prefixed attribute names */
if (attId->prefix) {
@@ -2885,16 +3292,16 @@ storeAtts(XML_Parser parser, const ENCODING *enc,
}
/* set-up for XML_GetSpecifiedAttributeCount and XML_GetIdAttributeIndex */
- nSpecifiedAtts = attIndex;
+ parser->m_nSpecifiedAtts = attIndex;
if (elementType->idAtt && (elementType->idAtt->name)[-1]) {
for (i = 0; i < attIndex; i += 2)
if (appAtts[i] == elementType->idAtt->name) {
- idAttIndex = i;
+ parser->m_idAttIndex = i;
break;
}
}
else
- idAttIndex = -1;
+ parser->m_idAttIndex = -1;
/* do attribute defaulting */
for (i = 0; i < nDefaultAtts; i++) {
@@ -2928,29 +3335,33 @@ storeAtts(XML_Parser parser, const ENCODING *enc,
i = 0;
if (nPrefixes) {
int j; /* hash table index */
- unsigned long version = nsAttsVersion;
- int nsAttsSize = (int)1 << nsAttsPower;
+ unsigned long version = parser->m_nsAttsVersion;
+ int nsAttsSize = (int)1 << parser->m_nsAttsPower;
+ unsigned char oldNsAttsPower = parser->m_nsAttsPower;
/* size of hash table must be at least 2 * (# of prefixed attributes) */
- if ((nPrefixes << 1) >> nsAttsPower) { /* true for nsAttsPower = 0 */
+ if ((nPrefixes << 1) >> parser->m_nsAttsPower) { /* true for m_nsAttsPower = 0 */
NS_ATT *temp;
/* hash table size must also be a power of 2 and >= 8 */
- while (nPrefixes >> nsAttsPower++);
- if (nsAttsPower < 3)
- nsAttsPower = 3;
- nsAttsSize = (int)1 << nsAttsPower;
- temp = (NS_ATT *)REALLOC(nsAtts, nsAttsSize * sizeof(NS_ATT));
- if (!temp)
+ while (nPrefixes >> parser->m_nsAttsPower++);
+ if (parser->m_nsAttsPower < 3)
+ parser->m_nsAttsPower = 3;
+ nsAttsSize = (int)1 << parser->m_nsAttsPower;
+ temp = (NS_ATT *)REALLOC(parser, parser->m_nsAtts, nsAttsSize * sizeof(NS_ATT));
+ if (!temp) {
+ /* Restore actual size of memory in m_nsAtts */
+ parser->m_nsAttsPower = oldNsAttsPower;
return XML_ERROR_NO_MEMORY;
- nsAtts = temp;
- version = 0; /* force re-initialization of nsAtts hash table */
+ }
+ parser->m_nsAtts = temp;
+ version = 0; /* force re-initialization of m_nsAtts hash table */
}
- /* using a version flag saves us from initializing nsAtts every time */
+ /* using a version flag saves us from initializing m_nsAtts every time */
if (!version) { /* initialize version flags when version wraps around */
version = INIT_ATTS_VERSION;
for (j = nsAttsSize; j != 0; )
- nsAtts[--j].version = version;
+ parser->m_nsAtts[--j].version = version;
}
- nsAttsVersion = --version;
+ parser->m_nsAttsVersion = --version;
/* expand prefixed names and check for duplicates */
for (; i < attIndex; i += 2) {
@@ -2958,71 +3369,96 @@ storeAtts(XML_Parser parser, const ENCODING *enc,
if (s[-1] == 2) { /* prefixed */
ATTRIBUTE_ID *id;
const BINDING *b;
- unsigned long uriHash = hash_secret_salt;
+ unsigned long uriHash;
+ struct siphash sip_state;
+ struct sipkey sip_key;
+
+ copy_salt_to_sipkey(parser, &sip_key);
+ sip24_init(&sip_state, &sip_key);
+
((XML_Char *)s)[-1] = 0; /* clear flag */
id = (ATTRIBUTE_ID *)lookup(parser, &dtd->attributeIds, s, 0);
- if (!id || !id->prefix)
- return XML_ERROR_NO_MEMORY;
+ if (!id || !id->prefix) {
+ /* This code is walking through the appAtts array, dealing
+ * with (in this case) a prefixed attribute name. To be in
+ * the array, the attribute must have already been bound, so
+ * has to have passed through the hash table lookup once
+ * already. That implies that an entry for it already
+ * exists, so the lookup above will return a pointer to
+ * already allocated memory. There is no opportunaity for
+ * the allocator to fail, so the condition above cannot be
+ * fulfilled.
+ *
+ * Since it is difficult to be certain that the above
+ * analysis is complete, we retain the test and merely
+ * remove the code from coverage tests.
+ */
+ return XML_ERROR_NO_MEMORY; /* LCOV_EXCL_LINE */
+ }
b = id->prefix->binding;
if (!b)
return XML_ERROR_UNBOUND_PREFIX;
- /* as we expand the name we also calculate its hash value */
for (j = 0; j < b->uriLen; j++) {
const XML_Char c = b->uri[j];
- if (!poolAppendChar(&tempPool, c))
+ if (!poolAppendChar(&parser->m_tempPool, c))
return XML_ERROR_NO_MEMORY;
- uriHash = CHAR_HASH(uriHash, c);
}
+
+ sip24_update(&sip_state, b->uri, b->uriLen * sizeof(XML_Char));
+
while (*s++ != XML_T(ASCII_COLON))
;
+
+ sip24_update(&sip_state, s, keylen(s) * sizeof(XML_Char));
+
do { /* copies null terminator */
- const XML_Char c = *s;
- if (!poolAppendChar(&tempPool, *s))
+ if (!poolAppendChar(&parser->m_tempPool, *s))
return XML_ERROR_NO_MEMORY;
- uriHash = CHAR_HASH(uriHash, c);
} while (*s++);
+ uriHash = (unsigned long)sip24_final(&sip_state);
+
{ /* Check hash table for duplicate of expanded name (uriName).
Derived from code in lookup(parser, HASH_TABLE *table, ...).
*/
unsigned char step = 0;
unsigned long mask = nsAttsSize - 1;
j = uriHash & mask; /* index into hash table */
- while (nsAtts[j].version == version) {
+ while (parser->m_nsAtts[j].version == version) {
/* for speed we compare stored hash values first */
- if (uriHash == nsAtts[j].hash) {
- const XML_Char *s1 = poolStart(&tempPool);
- const XML_Char *s2 = nsAtts[j].uriName;
+ if (uriHash == parser->m_nsAtts[j].hash) {
+ const XML_Char *s1 = poolStart(&parser->m_tempPool);
+ const XML_Char *s2 = parser->m_nsAtts[j].uriName;
/* s1 is null terminated, but not s2 */
for (; *s1 == *s2 && *s1 != 0; s1++, s2++);
if (*s1 == 0)
return XML_ERROR_DUPLICATE_ATTRIBUTE;
}
if (!step)
- step = PROBE_STEP(uriHash, mask, nsAttsPower);
+ step = PROBE_STEP(uriHash, mask, parser->m_nsAttsPower);
j < step ? (j += nsAttsSize - step) : (j -= step);
}
}
- if (ns_triplets) { /* append namespace separator and prefix */
- tempPool.ptr[-1] = namespaceSeparator;
+ if (parser->m_ns_triplets) { /* append namespace separator and prefix */
+ parser->m_tempPool.ptr[-1] = parser->m_namespaceSeparator;
s = b->prefix->name;
do {
- if (!poolAppendChar(&tempPool, *s))
+ if (!poolAppendChar(&parser->m_tempPool, *s))
return XML_ERROR_NO_MEMORY;
} while (*s++);
}
/* store expanded name in attribute list */
- s = poolStart(&tempPool);
- poolFinish(&tempPool);
+ s = poolStart(&parser->m_tempPool);
+ poolFinish(&parser->m_tempPool);
appAtts[i] = s;
/* fill empty slot with new version, uriName and hash value */
- nsAtts[j].version = version;
- nsAtts[j].hash = uriHash;
- nsAtts[j].uriName = s;
+ parser->m_nsAtts[j].version = version;
+ parser->m_nsAtts[j].hash = uriHash;
+ parser->m_nsAtts[j].uriName = s;
if (!--nPrefixes) {
i += 2;
@@ -3039,7 +3475,7 @@ storeAtts(XML_Parser parser, const ENCODING *enc,
for (binding = *bindingsPtr; binding; binding = binding->nextTagBinding)
binding->attId->name[-1] = 0;
- if (!ns)
+ if (!parser->m_ns)
return XML_ERROR_NONE;
/* expand the element type name */
@@ -3058,7 +3494,7 @@ storeAtts(XML_Parser parser, const ENCODING *enc,
else
return XML_ERROR_NONE;
prefixLen = 0;
- if (ns_triplets && binding->prefix->name) {
+ if (parser->m_ns_triplets && binding->prefix->name) {
for (; binding->prefix->name[prefixLen++];)
; /* prefixLen includes null terminator */
}
@@ -3071,24 +3507,24 @@ storeAtts(XML_Parser parser, const ENCODING *enc,
n = i + binding->uriLen + prefixLen;
if (n > binding->uriAlloc) {
TAG *p;
- uri = (XML_Char *)MALLOC((n + EXPAND_SPARE) * sizeof(XML_Char));
+ uri = (XML_Char *)MALLOC(parser, (n + EXPAND_SPARE) * sizeof(XML_Char));
if (!uri)
return XML_ERROR_NO_MEMORY;
binding->uriAlloc = n + EXPAND_SPARE;
memcpy(uri, binding->uri, binding->uriLen * sizeof(XML_Char));
- for (p = tagStack; p; p = p->parent)
+ for (p = parser->m_tagStack; p; p = p->parent)
if (p->name.str == binding->uri)
p->name.str = uri;
- FREE(binding->uri);
+ FREE(parser, binding->uri);
binding->uri = uri;
}
- /* if namespaceSeparator != '\0' then uri includes it already */
+ /* if m_namespaceSeparator != '\0' then uri includes it already */
uri = binding->uri + binding->uriLen;
memcpy(uri, localPart, i * sizeof(XML_Char));
/* we always have a namespace separator between localPart and prefix */
if (prefixLen) {
uri += i - 1;
- *uri = namespaceSeparator; /* replace null terminator */
+ *uri = parser->m_namespaceSeparator; /* replace null terminator */
memcpy(uri + 1, binding->prefix->name, prefixLen * sizeof(XML_Char));
}
tagNamePtr->str = binding->uri;
@@ -3166,48 +3602,48 @@ addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId,
if (isXMLNS)
return XML_ERROR_RESERVED_NAMESPACE_URI;
- if (namespaceSeparator)
+ if (parser->m_namespaceSeparator)
len++;
- if (freeBindingList) {
- b = freeBindingList;
+ if (parser->m_freeBindingList) {
+ b = parser->m_freeBindingList;
if (len > b->uriAlloc) {
- XML_Char *temp = (XML_Char *)REALLOC(b->uri,
+ XML_Char *temp = (XML_Char *)REALLOC(parser, b->uri,
sizeof(XML_Char) * (len + EXPAND_SPARE));
if (temp == NULL)
return XML_ERROR_NO_MEMORY;
b->uri = temp;
b->uriAlloc = len + EXPAND_SPARE;
}
- freeBindingList = b->nextTagBinding;
+ parser->m_freeBindingList = b->nextTagBinding;
}
else {
- b = (BINDING *)MALLOC(sizeof(BINDING));
+ b = (BINDING *)MALLOC(parser, sizeof(BINDING));
if (!b)
return XML_ERROR_NO_MEMORY;
- b->uri = (XML_Char *)MALLOC(sizeof(XML_Char) * (len + EXPAND_SPARE));
+ b->uri = (XML_Char *)MALLOC(parser, sizeof(XML_Char) * (len + EXPAND_SPARE));
if (!b->uri) {
- FREE(b);
+ FREE(parser, b);
return XML_ERROR_NO_MEMORY;
}
b->uriAlloc = len + EXPAND_SPARE;
}
b->uriLen = len;
memcpy(b->uri, uri, len * sizeof(XML_Char));
- if (namespaceSeparator)
- b->uri[len - 1] = namespaceSeparator;
+ if (parser->m_namespaceSeparator)
+ b->uri[len - 1] = parser->m_namespaceSeparator;
b->prefix = prefix;
b->attId = attId;
b->prevPrefixBinding = prefix->binding;
/* NULL binding when default namespace undeclared */
- if (*uri == XML_T('\0') && prefix == &_dtd->defaultPrefix)
+ if (*uri == XML_T('\0') && prefix == &parser->m_dtd->defaultPrefix)
prefix->binding = NULL;
else
prefix->binding = b;
b->nextTagBinding = *bindingsPtr;
*bindingsPtr = b;
/* if attId == NULL then we are not starting a namespace scope */
- if (attId && startNamespaceDeclHandler)
- startNamespaceDeclHandler(handlerArg, prefix->name,
+ if (attId && parser->m_startNamespaceDeclHandler)
+ parser->m_startNamespaceDeclHandler(parser->m_handlerArg, prefix->name,
prefix->binding ? uri : 0);
return XML_ERROR_NONE;
}
@@ -3221,17 +3657,17 @@ cdataSectionProcessor(XML_Parser parser,
const char *end,
const char **endPtr)
{
- enum XML_Error result = doCdataSection(parser, encoding, &start, end,
- endPtr, (XML_Bool)!ps_finalBuffer);
+ enum XML_Error result = doCdataSection(parser, parser->m_encoding, &start, end,
+ endPtr, (XML_Bool)!parser->m_parsingStatus.finalBuffer);
if (result != XML_ERROR_NONE)
return result;
if (start) {
- if (parentParser) { /* we are parsing an external entity */
- processor = externalEntityContentProcessor;
+ if (parser->m_parentParser) { /* we are parsing an external entity */
+ parser->m_processor = externalEntityContentProcessor;
return externalEntityContentProcessor(parser, start, end, endPtr);
}
else {
- processor = contentProcessor;
+ parser->m_processor = contentProcessor;
return contentProcessor(parser, start, end, endPtr);
}
}
@@ -3252,14 +3688,14 @@ doCdataSection(XML_Parser parser,
const char *s = *startPtr;
const char **eventPP;
const char **eventEndPP;
- if (enc == encoding) {
- eventPP = &eventPtr;
+ if (enc == parser->m_encoding) {
+ eventPP = &parser->m_eventPtr;
*eventPP = s;
- eventEndPP = &eventEndPtr;
+ eventEndPP = &parser->m_eventEndPtr;
}
else {
- eventPP = &(openInternalEntities->internalEventPtr);
- eventEndPP = &(openInternalEntities->internalEventEndPtr);
+ eventPP = &(parser->m_openInternalEntities->internalEventPtr);
+ eventEndPP = &(parser->m_openInternalEntities->internalEventEndPtr);
}
*eventPP = s;
*startPtr = NULL;
@@ -3270,51 +3706,51 @@ doCdataSection(XML_Parser parser,
*eventEndPP = next;
switch (tok) {
case XML_TOK_CDATA_SECT_CLOSE:
- if (endCdataSectionHandler)
- endCdataSectionHandler(handlerArg);
+ if (parser->m_endCdataSectionHandler)
+ parser->m_endCdataSectionHandler(parser->m_handlerArg);
#if 0
/* see comment under XML_TOK_CDATA_SECT_OPEN */
- else if (characterDataHandler)
- characterDataHandler(handlerArg, dataBuf, 0);
+ else if (parser->m_characterDataHandler)
+ parser->m_characterDataHandler(parser->m_handlerArg, parser->m_dataBuf, 0);
#endif
- else if (defaultHandler)
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
*startPtr = next;
*nextPtr = next;
- if (ps_parsing == XML_FINISHED)
+ if (parser->m_parsingStatus.parsing == XML_FINISHED)
return XML_ERROR_ABORTED;
else
return XML_ERROR_NONE;
case XML_TOK_DATA_NEWLINE:
- if (characterDataHandler) {
+ if (parser->m_characterDataHandler) {
XML_Char c = 0xA;
- characterDataHandler(handlerArg, &c, 1);
+ parser->m_characterDataHandler(parser->m_handlerArg, &c, 1);
}
- else if (defaultHandler)
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
break;
case XML_TOK_DATA_CHARS:
{
- XML_CharacterDataHandler charDataHandler = characterDataHandler;
+ XML_CharacterDataHandler charDataHandler = parser->m_characterDataHandler;
if (charDataHandler) {
if (MUST_CONVERT(enc, s)) {
for (;;) {
- ICHAR *dataPtr = (ICHAR *)dataBuf;
- const enum XML_Convert_Result convert_res = XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)dataBufEnd);
+ ICHAR *dataPtr = (ICHAR *)parser->m_dataBuf;
+ const enum XML_Convert_Result convert_res = XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)parser->m_dataBufEnd);
*eventEndPP = next;
- charDataHandler(handlerArg, dataBuf,
- (int)(dataPtr - (ICHAR *)dataBuf));
+ charDataHandler(parser->m_handlerArg, parser->m_dataBuf,
+ (int)(dataPtr - (ICHAR *)parser->m_dataBuf));
if ((convert_res == XML_CONVERT_COMPLETED) || (convert_res == XML_CONVERT_INPUT_INCOMPLETE))
break;
*eventPP = s;
}
}
else
- charDataHandler(handlerArg,
+ charDataHandler(parser->m_handlerArg,
(XML_Char *)s,
(int)((XML_Char *)next - (XML_Char *)s));
}
- else if (defaultHandler)
+ else if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
}
break;
@@ -3335,12 +3771,20 @@ doCdataSection(XML_Parser parser,
}
return XML_ERROR_UNCLOSED_CDATA_SECTION;
default:
+ /* Every token returned by XmlCdataSectionTok() has its own
+ * explicit case, so this default case will never be executed.
+ * We retain it as a safety net and exclude it from the coverage
+ * statistics.
+ *
+ * LCOV_EXCL_START
+ */
*eventPP = next;
return XML_ERROR_UNEXPECTED_STATE;
+ /* LCOV_EXCL_STOP */
}
*eventPP = s = next;
- switch (ps_parsing) {
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
*nextPtr = next;
return XML_ERROR_NONE;
@@ -3363,12 +3807,12 @@ ignoreSectionProcessor(XML_Parser parser,
const char *end,
const char **endPtr)
{
- enum XML_Error result = doIgnoreSection(parser, encoding, &start, end,
- endPtr, (XML_Bool)!ps_finalBuffer);
+ enum XML_Error result = doIgnoreSection(parser, parser->m_encoding, &start, end,
+ endPtr, (XML_Bool)!parser->m_parsingStatus.finalBuffer);
if (result != XML_ERROR_NONE)
return result;
if (start) {
- processor = prologProcessor;
+ parser->m_processor = prologProcessor;
return prologProcessor(parser, start, end, endPtr);
}
return result;
@@ -3390,14 +3834,26 @@ doIgnoreSection(XML_Parser parser,
const char *s = *startPtr;
const char **eventPP;
const char **eventEndPP;
- if (enc == encoding) {
- eventPP = &eventPtr;
+ if (enc == parser->m_encoding) {
+ eventPP = &parser->m_eventPtr;
*eventPP = s;
- eventEndPP = &eventEndPtr;
+ eventEndPP = &parser->m_eventEndPtr;
}
else {
- eventPP = &(openInternalEntities->internalEventPtr);
- eventEndPP = &(openInternalEntities->internalEventEndPtr);
+ /* It's not entirely clear, but it seems the following two lines
+ * of code cannot be executed. The only occasions on which 'enc'
+ * is not 'encoding' are when this function is called
+ * from the internal entity processing, and IGNORE sections are an
+ * error in internal entities.
+ *
+ * Since it really isn't clear that this is true, we keep the code
+ * and just remove it from our coverage tests.
+ *
+ * LCOV_EXCL_START
+ */
+ eventPP = &(parser->m_openInternalEntities->internalEventPtr);
+ eventEndPP = &(parser->m_openInternalEntities->internalEventEndPtr);
+ /* LCOV_EXCL_STOP */
}
*eventPP = s;
*startPtr = NULL;
@@ -3405,11 +3861,11 @@ doIgnoreSection(XML_Parser parser,
*eventEndPP = next;
switch (tok) {
case XML_TOK_IGNORE_SECT:
- if (defaultHandler)
+ if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
*startPtr = next;
*nextPtr = next;
- if (ps_parsing == XML_FINISHED)
+ if (parser->m_parsingStatus.parsing == XML_FINISHED)
return XML_ERROR_ABORTED;
else
return XML_ERROR_NONE;
@@ -3430,8 +3886,16 @@ doIgnoreSection(XML_Parser parser,
}
return XML_ERROR_SYNTAX; /* XML_ERROR_UNCLOSED_IGNORE_SECTION */
default:
+ /* All of the tokens that XmlIgnoreSectionTok() returns have
+ * explicit cases to handle them, so this default case is never
+ * executed. We keep it as a safety net anyway, and remove it
+ * from our test coverage statistics.
+ *
+ * LCOV_EXCL_START
+ */
*eventPP = next;
return XML_ERROR_UNEXPECTED_STATE;
+ /* LCOV_EXCL_STOP */
}
/* not reached */
}
@@ -3444,27 +3908,28 @@ initializeEncoding(XML_Parser parser)
const char *s;
#ifdef XML_UNICODE
char encodingBuf[128];
- if (!protocolEncodingName)
+ /* See comments abount `protoclEncodingName` in parserInit() */
+ if (!parser->m_protocolEncodingName)
s = NULL;
else {
int i;
- for (i = 0; protocolEncodingName[i]; i++) {
+ for (i = 0; parser->m_protocolEncodingName[i]; i++) {
if (i == sizeof(encodingBuf) - 1
- || (protocolEncodingName[i] & ~0x7f) != 0) {
+ || (parser->m_protocolEncodingName[i] & ~0x7f) != 0) {
encodingBuf[0] = '\0';
break;
}
- encodingBuf[i] = (char)protocolEncodingName[i];
+ encodingBuf[i] = (char)parser->m_protocolEncodingName[i];
}
encodingBuf[i] = '\0';
s = encodingBuf;
}
#else
- s = protocolEncodingName;
+ s = parser->m_protocolEncodingName;
#endif
- if ((ns ? XmlInitEncodingNS : XmlInitEncoding)(&initEncoding, &encoding, s))
+ if ((parser->m_ns ? XmlInitEncodingNS : XmlInitEncoding)(&parser->m_initEncoding, &parser->m_encoding, s))
return XML_ERROR_NONE;
- return handleUnknownEncoding(parser, protocolEncodingName);
+ return handleUnknownEncoding(parser, parser->m_protocolEncodingName);
}
static enum XML_Error
@@ -3478,13 +3943,13 @@ processXmlDecl(XML_Parser parser, int isGeneralTextEntity,
const char *versionend;
const XML_Char *storedversion = NULL;
int standalone = -1;
- if (!(ns
+ if (!(parser->m_ns
? XmlParseXmlDeclNS
: XmlParseXmlDecl)(isGeneralTextEntity,
- encoding,
+ parser->m_encoding,
s,
next,
- &eventPtr,
+ &parser->m_eventPtr,
&version,
&versionend,
&encodingName,
@@ -3496,62 +3961,69 @@ processXmlDecl(XML_Parser parser, int isGeneralTextEntity,
return XML_ERROR_XML_DECL;
}
if (!isGeneralTextEntity && standalone == 1) {
- _dtd->standalone = XML_TRUE;
+ parser->m_dtd->standalone = XML_TRUE;
#ifdef XML_DTD
- if (paramEntityParsing == XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE)
- paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER;
+ if (parser->m_paramEntityParsing == XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE)
+ parser->m_paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER;
#endif /* XML_DTD */
}
- if (xmlDeclHandler) {
+ if (parser->m_xmlDeclHandler) {
if (encodingName != NULL) {
- storedEncName = poolStoreString(&temp2Pool,
- encoding,
+ storedEncName = poolStoreString(&parser->m_temp2Pool,
+ parser->m_encoding,
encodingName,
encodingName
- + XmlNameLength(encoding, encodingName));
+ + XmlNameLength(parser->m_encoding, encodingName));
if (!storedEncName)
return XML_ERROR_NO_MEMORY;
- poolFinish(&temp2Pool);
+ poolFinish(&parser->m_temp2Pool);
}
if (version) {
- storedversion = poolStoreString(&temp2Pool,
- encoding,
+ storedversion = poolStoreString(&parser->m_temp2Pool,
+ parser->m_encoding,
version,
- versionend - encoding->minBytesPerChar);
+ versionend - parser->m_encoding->minBytesPerChar);
if (!storedversion)
return XML_ERROR_NO_MEMORY;
}
- xmlDeclHandler(handlerArg, storedversion, storedEncName, standalone);
+ parser->m_xmlDeclHandler(parser->m_handlerArg, storedversion, storedEncName, standalone);
}
- else if (defaultHandler)
- reportDefault(parser, encoding, s, next);
- if (protocolEncodingName == NULL) {
+ else if (parser->m_defaultHandler)
+ reportDefault(parser, parser->m_encoding, s, next);
+ if (parser->m_protocolEncodingName == NULL) {
if (newEncoding) {
- if (newEncoding->minBytesPerChar != encoding->minBytesPerChar) {
- eventPtr = encodingName;
+ /* Check that the specified encoding does not conflict with what
+ * the parser has already deduced. Do we have the same number
+ * of bytes in the smallest representation of a character? If
+ * this is UTF-16, is it the same endianness?
+ */
+ if (newEncoding->minBytesPerChar != parser->m_encoding->minBytesPerChar
+ || (newEncoding->minBytesPerChar == 2 &&
+ newEncoding != parser->m_encoding)) {
+ parser->m_eventPtr = encodingName;
return XML_ERROR_INCORRECT_ENCODING;
}
- encoding = newEncoding;
+ parser->m_encoding = newEncoding;
}
else if (encodingName) {
enum XML_Error result;
if (!storedEncName) {
storedEncName = poolStoreString(
- &temp2Pool, encoding, encodingName,
- encodingName + XmlNameLength(encoding, encodingName));
+ &parser->m_temp2Pool, parser->m_encoding, encodingName,
+ encodingName + XmlNameLength(parser->m_encoding, encodingName));
if (!storedEncName)
return XML_ERROR_NO_MEMORY;
}
result = handleUnknownEncoding(parser, storedEncName);
- poolClear(&temp2Pool);
+ poolClear(&parser->m_temp2Pool);
if (result == XML_ERROR_UNKNOWN_ENCODING)
- eventPtr = encodingName;
+ parser->m_eventPtr = encodingName;
return result;
}
}
if (storedEncName || storedversion)
- poolClear(&temp2Pool);
+ poolClear(&parser->m_temp2Pool);
return XML_ERROR_NONE;
}
@@ -3559,7 +4031,7 @@ processXmlDecl(XML_Parser parser, int isGeneralTextEntity,
static enum XML_Error
handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName)
{
- if (unknownEncodingHandler) {
+ if (parser->m_unknownEncodingHandler) {
XML_Encoding info;
int i;
for (i = 0; i < 256; i++)
@@ -3567,25 +4039,25 @@ handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName)
info.convert = NULL;
info.data = NULL;
info.release = NULL;
- if (unknownEncodingHandler(unknownEncodingHandlerData, encodingName,
+ if (parser->m_unknownEncodingHandler(parser->m_unknownEncodingHandlerData, encodingName,
&info)) {
ENCODING *enc;
- unknownEncodingMem = MALLOC(XmlSizeOfUnknownEncoding());
- if (!unknownEncodingMem) {
+ parser->m_unknownEncodingMem = MALLOC(parser, XmlSizeOfUnknownEncoding());
+ if (!parser->m_unknownEncodingMem) {
if (info.release)
info.release(info.data);
return XML_ERROR_NO_MEMORY;
}
- enc = (ns
+ enc = (parser->m_ns
? XmlInitUnknownEncodingNS
- : XmlInitUnknownEncoding)(unknownEncodingMem,
+ : XmlInitUnknownEncoding)(parser->m_unknownEncodingMem,
info.map,
info.convert,
info.data);
if (enc) {
- unknownEncodingData = info.data;
- unknownEncodingRelease = info.release;
- encoding = enc;
+ parser->m_unknownEncodingData = info.data;
+ parser->m_unknownEncodingRelease = info.release;
+ parser->m_encoding = enc;
return XML_ERROR_NONE;
}
}
@@ -3604,7 +4076,7 @@ prologInitProcessor(XML_Parser parser,
enum XML_Error result = initializeEncoding(parser);
if (result != XML_ERROR_NONE)
return result;
- processor = prologProcessor;
+ parser->m_processor = prologProcessor;
return prologProcessor(parser, s, end, nextPtr);
}
@@ -3622,14 +4094,14 @@ externalParEntInitProcessor(XML_Parser parser,
/* we know now that XML_Parse(Buffer) has been called,
so we consider the external parameter entity read */
- _dtd->paramEntityRead = XML_TRUE;
+ parser->m_dtd->paramEntityRead = XML_TRUE;
- if (prologState.inEntityValue) {
- processor = entityValueInitProcessor;
+ if (parser->m_prologState.inEntityValue) {
+ parser->m_processor = entityValueInitProcessor;
return entityValueInitProcessor(parser, s, end, nextPtr);
}
else {
- processor = externalParEntProcessor;
+ parser->m_processor = externalParEntProcessor;
return externalParEntProcessor(parser, s, end, nextPtr);
}
}
@@ -3643,13 +4115,13 @@ entityValueInitProcessor(XML_Parser parser,
int tok;
const char *start = s;
const char *next = start;
- eventPtr = start;
+ parser->m_eventPtr = start;
for (;;) {
- tok = XmlPrologTok(encoding, start, end, &next);
- eventEndPtr = next;
+ tok = XmlPrologTok(parser->m_encoding, start, end, &next);
+ parser->m_eventEndPtr = next;
if (tok <= 0) {
- if (!ps_finalBuffer && tok != XML_TOK_INVALID) {
+ if (!parser->m_parsingStatus.finalBuffer && tok != XML_TOK_INVALID) {
*nextPtr = s;
return XML_ERROR_NONE;
}
@@ -3665,24 +4137,23 @@ entityValueInitProcessor(XML_Parser parser,
break;
}
/* found end of entity value - can store it now */
- return storeEntityValue(parser, encoding, s, end);
+ return storeEntityValue(parser, parser->m_encoding, s, end);
}
else if (tok == XML_TOK_XML_DECL) {
enum XML_Error result;
result = processXmlDecl(parser, 0, start, next);
if (result != XML_ERROR_NONE)
return result;
- switch (ps_parsing) {
- case XML_SUSPENDED:
- *nextPtr = next;
- return XML_ERROR_NONE;
- case XML_FINISHED:
+ /* At this point, m_parsingStatus.parsing cannot be XML_SUSPENDED. For that
+ * to happen, a parameter entity parsing handler must have
+ * attempted to suspend the parser, which fails and raises an
+ * error. The parser can be aborted, but can't be suspended.
+ */
+ if (parser->m_parsingStatus.parsing == XML_FINISHED)
return XML_ERROR_ABORTED;
- default:
- *nextPtr = next;
- }
+ *nextPtr = next;
/* stop scanning for text declaration - we found one */
- processor = entityValueProcessor;
+ parser->m_processor = entityValueProcessor;
return entityValueProcessor(parser, next, end, nextPtr);
}
/* If we are at the end of the buffer, this would cause XmlPrologTok to
@@ -3692,12 +4163,20 @@ entityValueInitProcessor(XML_Parser parser,
then, when this routine is entered the next time, XmlPrologTok will
return XML_TOK_INVALID, since the BOM is still in the buffer
*/
- else if (tok == XML_TOK_BOM && next == end && !ps_finalBuffer) {
+ else if (tok == XML_TOK_BOM && next == end && !parser->m_parsingStatus.finalBuffer) {
*nextPtr = next;
return XML_ERROR_NONE;
}
+ /* If we get this token, we have the start of what might be a
+ normal tag, but not a declaration (i.e. it doesn't begin with
+ "<!"). In a DTD context, that isn't legal.
+ */
+ else if (tok == XML_TOK_INSTANCE_START) {
+ *nextPtr = next;
+ return XML_ERROR_SYNTAX;
+ }
start = next;
- eventPtr = start;
+ parser->m_eventPtr = start;
}
}
@@ -3710,9 +4189,9 @@ externalParEntProcessor(XML_Parser parser,
const char *next = s;
int tok;
- tok = XmlPrologTok(encoding, s, end, &next);
+ tok = XmlPrologTok(parser->m_encoding, s, end, &next);
if (tok <= 0) {
- if (!ps_finalBuffer && tok != XML_TOK_INVALID) {
+ if (!parser->m_parsingStatus.finalBuffer && tok != XML_TOK_INVALID) {
*nextPtr = s;
return XML_ERROR_NONE;
}
@@ -3734,12 +4213,12 @@ externalParEntProcessor(XML_Parser parser,
*/
else if (tok == XML_TOK_BOM) {
s = next;
- tok = XmlPrologTok(encoding, s, end, &next);
+ tok = XmlPrologTok(parser->m_encoding, s, end, &next);
}
- processor = prologProcessor;
- return doProlog(parser, encoding, s, end, tok, next,
- nextPtr, (XML_Bool)!ps_finalBuffer);
+ parser->m_processor = prologProcessor;
+ return doProlog(parser, parser->m_encoding, s, end, tok, next,
+ nextPtr, (XML_Bool)!parser->m_parsingStatus.finalBuffer);
}
static enum XML_Error PTRCALL
@@ -3750,13 +4229,13 @@ entityValueProcessor(XML_Parser parser,
{
const char *start = s;
const char *next = s;
- const ENCODING *enc = encoding;
+ const ENCODING *enc = parser->m_encoding;
int tok;
for (;;) {
tok = XmlPrologTok(enc, start, end, &next);
if (tok <= 0) {
- if (!ps_finalBuffer && tok != XML_TOK_INVALID) {
+ if (!parser->m_parsingStatus.finalBuffer && tok != XML_TOK_INVALID) {
*nextPtr = s;
return XML_ERROR_NONE;
}
@@ -3787,9 +4266,9 @@ prologProcessor(XML_Parser parser,
const char **nextPtr)
{
const char *next = s;
- int tok = XmlPrologTok(encoding, s, end, &next);
- return doProlog(parser, encoding, s, end, tok, next,
- nextPtr, (XML_Bool)!ps_finalBuffer);
+ int tok = XmlPrologTok(parser->m_encoding, s, end, &next);
+ return doProlog(parser, parser->m_encoding, s, end, tok, next,
+ nextPtr, (XML_Bool)!parser->m_parsingStatus.finalBuffer);
}
static enum XML_Error
@@ -3826,19 +4305,19 @@ doProlog(XML_Parser parser,
static const XML_Char enumValueStart[] = { ASCII_LPAREN, '\0' };
/* save one level of indirection */
- DTD * const dtd = _dtd;
+ DTD * const dtd = parser->m_dtd;
const char **eventPP;
const char **eventEndPP;
enum XML_Content_Quant quant;
- if (enc == encoding) {
- eventPP = &eventPtr;
- eventEndPP = &eventEndPtr;
+ if (enc == parser->m_encoding) {
+ eventPP = &parser->m_eventPtr;
+ eventEndPP = &parser->m_eventEndPtr;
}
else {
- eventPP = &(openInternalEntities->internalEventPtr);
- eventEndPP = &(openInternalEntities->internalEventEndPtr);
+ eventPP = &(parser->m_openInternalEntities->internalEventPtr);
+ eventEndPP = &(parser->m_openInternalEntities->internalEventEndPtr);
}
for (;;) {
@@ -3865,7 +4344,7 @@ doProlog(XML_Parser parser,
case XML_TOK_NONE:
#ifdef XML_DTD
/* for internal PE NOT referenced between declarations */
- if (enc != encoding && !openInternalEntities->betweenDecl) {
+ if (enc != parser->m_encoding && !parser->m_openInternalEntities->betweenDecl) {
*nextPtr = s;
return XML_ERROR_NONE;
}
@@ -3873,8 +4352,8 @@ doProlog(XML_Parser parser,
complete markup, not only for external PEs, but also for
internal PEs if the reference occurs between declarations.
*/
- if (isParamEntity || enc != encoding) {
- if (XmlTokenRole(&prologState, XML_TOK_NONE, end, end, enc)
+ if (parser->m_isParamEntity || enc != parser->m_encoding) {
+ if (XmlTokenRole(&parser->m_prologState, XML_TOK_NONE, end, end, enc)
== XML_ROLE_ERROR)
return XML_ERROR_INCOMPLETE_PE;
*nextPtr = s;
@@ -3888,34 +4367,34 @@ doProlog(XML_Parser parser,
break;
}
}
- role = XmlTokenRole(&prologState, tok, s, next, enc);
+ role = XmlTokenRole(&parser->m_prologState, tok, s, next, enc);
switch (role) {
case XML_ROLE_XML_DECL:
{
enum XML_Error result = processXmlDecl(parser, 0, s, next);
if (result != XML_ERROR_NONE)
return result;
- enc = encoding;
+ enc = parser->m_encoding;
handleDefault = XML_FALSE;
}
break;
case XML_ROLE_DOCTYPE_NAME:
- if (startDoctypeDeclHandler) {
- doctypeName = poolStoreString(&tempPool, enc, s, next);
- if (!doctypeName)
+ if (parser->m_startDoctypeDeclHandler) {
+ parser->m_doctypeName = poolStoreString(&parser->m_tempPool, enc, s, next);
+ if (!parser->m_doctypeName)
return XML_ERROR_NO_MEMORY;
- poolFinish(&tempPool);
- doctypePubid = NULL;
+ poolFinish(&parser->m_tempPool);
+ parser->m_doctypePubid = NULL;
handleDefault = XML_FALSE;
}
- doctypeSysid = NULL; /* always initialize to NULL */
+ parser->m_doctypeSysid = NULL; /* always initialize to NULL */
break;
case XML_ROLE_DOCTYPE_INTERNAL_SUBSET:
- if (startDoctypeDeclHandler) {
- startDoctypeDeclHandler(handlerArg, doctypeName, doctypeSysid,
- doctypePubid, 1);
- doctypeName = NULL;
- poolClear(&tempPool);
+ if (parser->m_startDoctypeDeclHandler) {
+ parser->m_startDoctypeDeclHandler(parser->m_handlerArg, parser->m_doctypeName, parser->m_doctypeSysid,
+ parser->m_doctypePubid, 1);
+ parser->m_doctypeName = NULL;
+ poolClear(&parser->m_tempPool);
handleDefault = XML_FALSE;
}
break;
@@ -3925,34 +4404,34 @@ doProlog(XML_Parser parser,
enum XML_Error result = processXmlDecl(parser, 1, s, next);
if (result != XML_ERROR_NONE)
return result;
- enc = encoding;
+ enc = parser->m_encoding;
handleDefault = XML_FALSE;
}
break;
#endif /* XML_DTD */
case XML_ROLE_DOCTYPE_PUBLIC_ID:
#ifdef XML_DTD
- useForeignDTD = XML_FALSE;
- declEntity = (ENTITY *)lookup(parser,
+ parser->m_useForeignDTD = XML_FALSE;
+ parser->m_declEntity = (ENTITY *)lookup(parser,
&dtd->paramEntities,
externalSubsetName,
sizeof(ENTITY));
- if (!declEntity)
+ if (!parser->m_declEntity)
return XML_ERROR_NO_MEMORY;
#endif /* XML_DTD */
dtd->hasParamEntityRefs = XML_TRUE;
- if (startDoctypeDeclHandler) {
+ if (parser->m_startDoctypeDeclHandler) {
XML_Char *pubId;
if (!XmlIsPublicId(enc, s, next, eventPP))
return XML_ERROR_PUBLICID;
- pubId = poolStoreString(&tempPool, enc,
+ pubId = poolStoreString(&parser->m_tempPool, enc,
s + enc->minBytesPerChar,
next - enc->minBytesPerChar);
if (!pubId)
return XML_ERROR_NO_MEMORY;
normalizePublicId(pubId);
- poolFinish(&tempPool);
- doctypePubid = pubId;
+ poolFinish(&parser->m_tempPool);
+ parser->m_doctypePubid = pubId;
handleDefault = XML_FALSE;
goto alreadyChecked;
}
@@ -3961,7 +4440,7 @@ doProlog(XML_Parser parser,
if (!XmlIsPublicId(enc, s, next, eventPP))
return XML_ERROR_PUBLICID;
alreadyChecked:
- if (dtd->keepProcessing && declEntity) {
+ if (dtd->keepProcessing && parser->m_declEntity) {
XML_Char *tem = poolStoreString(&dtd->pool,
enc,
s + enc->minBytesPerChar,
@@ -3969,38 +4448,47 @@ doProlog(XML_Parser parser,
if (!tem)
return XML_ERROR_NO_MEMORY;
normalizePublicId(tem);
- declEntity->publicId = tem;
+ parser->m_declEntity->publicId = tem;
poolFinish(&dtd->pool);
- if (entityDeclHandler)
+ /* Don't suppress the default handler if we fell through from
+ * the XML_ROLE_DOCTYPE_PUBLIC_ID case.
+ */
+ if (parser->m_entityDeclHandler && role == XML_ROLE_ENTITY_PUBLIC_ID)
handleDefault = XML_FALSE;
}
break;
case XML_ROLE_DOCTYPE_CLOSE:
- if (doctypeName) {
- startDoctypeDeclHandler(handlerArg, doctypeName,
- doctypeSysid, doctypePubid, 0);
- poolClear(&tempPool);
+ if (parser->m_doctypeName) {
+ parser->m_startDoctypeDeclHandler(parser->m_handlerArg, parser->m_doctypeName,
+ parser->m_doctypeSysid, parser->m_doctypePubid, 0);
+ poolClear(&parser->m_tempPool);
handleDefault = XML_FALSE;
}
- /* doctypeSysid will be non-NULL in the case of a previous
- XML_ROLE_DOCTYPE_SYSTEM_ID, even if startDoctypeDeclHandler
+ /* parser->m_doctypeSysid will be non-NULL in the case of a previous
+ XML_ROLE_DOCTYPE_SYSTEM_ID, even if parser->m_startDoctypeDeclHandler
was not set, indicating an external subset
*/
#ifdef XML_DTD
- if (doctypeSysid || useForeignDTD) {
+ if (parser->m_doctypeSysid || parser->m_useForeignDTD) {
XML_Bool hadParamEntityRefs = dtd->hasParamEntityRefs;
dtd->hasParamEntityRefs = XML_TRUE;
- if (paramEntityParsing && externalEntityRefHandler) {
+ if (parser->m_paramEntityParsing && parser->m_externalEntityRefHandler) {
ENTITY *entity = (ENTITY *)lookup(parser,
&dtd->paramEntities,
externalSubsetName,
sizeof(ENTITY));
- if (!entity)
- return XML_ERROR_NO_MEMORY;
- if (useForeignDTD)
- entity->base = curBase;
+ if (!entity) {
+ /* The external subset name "#" will have already been
+ * inserted into the hash table at the start of the
+ * external entity parsing, so no allocation will happen
+ * and lookup() cannot fail.
+ */
+ return XML_ERROR_NO_MEMORY; /* LCOV_EXCL_LINE */
+ }
+ if (parser->m_useForeignDTD)
+ entity->base = parser->m_curBase;
dtd->paramEntityRead = XML_FALSE;
- if (!externalEntityRefHandler(externalEntityRefHandlerArg,
+ if (!parser->m_externalEntityRefHandler(parser->m_externalEntityRefHandlerArg,
0,
entity->base,
entity->systemId,
@@ -4008,22 +4496,22 @@ doProlog(XML_Parser parser,
return XML_ERROR_EXTERNAL_ENTITY_HANDLING;
if (dtd->paramEntityRead) {
if (!dtd->standalone &&
- notStandaloneHandler &&
- !notStandaloneHandler(handlerArg))
+ parser->m_notStandaloneHandler &&
+ !parser->m_notStandaloneHandler(parser->m_handlerArg))
return XML_ERROR_NOT_STANDALONE;
}
/* if we didn't read the foreign DTD then this means that there
is no external subset and we must reset dtd->hasParamEntityRefs
*/
- else if (!doctypeSysid)
+ else if (!parser->m_doctypeSysid)
dtd->hasParamEntityRefs = hadParamEntityRefs;
/* end of DTD - no need to update dtd->keepProcessing */
}
- useForeignDTD = XML_FALSE;
+ parser->m_useForeignDTD = XML_FALSE;
}
#endif /* XML_DTD */
- if (endDoctypeDeclHandler) {
- endDoctypeDeclHandler(handlerArg);
+ if (parser->m_endDoctypeDeclHandler) {
+ parser->m_endDoctypeDeclHandler(parser->m_handlerArg);
handleDefault = XML_FALSE;
}
break;
@@ -4032,18 +4520,18 @@ doProlog(XML_Parser parser,
/* if there is no DOCTYPE declaration then now is the
last chance to read the foreign DTD
*/
- if (useForeignDTD) {
+ if (parser->m_useForeignDTD) {
XML_Bool hadParamEntityRefs = dtd->hasParamEntityRefs;
dtd->hasParamEntityRefs = XML_TRUE;
- if (paramEntityParsing && externalEntityRefHandler) {
+ if (parser->m_paramEntityParsing && parser->m_externalEntityRefHandler) {
ENTITY *entity = (ENTITY *)lookup(parser, &dtd->paramEntities,
externalSubsetName,
sizeof(ENTITY));
if (!entity)
return XML_ERROR_NO_MEMORY;
- entity->base = curBase;
+ entity->base = parser->m_curBase;
dtd->paramEntityRead = XML_FALSE;
- if (!externalEntityRefHandler(externalEntityRefHandlerArg,
+ if (!parser->m_externalEntityRefHandler(parser->m_externalEntityRefHandlerArg,
0,
entity->base,
entity->systemId,
@@ -4051,8 +4539,8 @@ doProlog(XML_Parser parser,
return XML_ERROR_EXTERNAL_ENTITY_HANDLING;
if (dtd->paramEntityRead) {
if (!dtd->standalone &&
- notStandaloneHandler &&
- !notStandaloneHandler(handlerArg))
+ parser->m_notStandaloneHandler &&
+ !parser->m_notStandaloneHandler(parser->m_handlerArg))
return XML_ERROR_NOT_STANDALONE;
}
/* if we didn't read the foreign DTD then this means that there
@@ -4064,55 +4552,55 @@ doProlog(XML_Parser parser,
}
}
#endif /* XML_DTD */
- processor = contentProcessor;
+ parser->m_processor = contentProcessor;
return contentProcessor(parser, s, end, nextPtr);
case XML_ROLE_ATTLIST_ELEMENT_NAME:
- declElementType = getElementType(parser, enc, s, next);
- if (!declElementType)
+ parser->m_declElementType = getElementType(parser, enc, s, next);
+ if (!parser->m_declElementType)
return XML_ERROR_NO_MEMORY;
goto checkAttListDeclHandler;
case XML_ROLE_ATTRIBUTE_NAME:
- declAttributeId = getAttributeId(parser, enc, s, next);
- if (!declAttributeId)
+ parser->m_declAttributeId = getAttributeId(parser, enc, s, next);
+ if (!parser->m_declAttributeId)
return XML_ERROR_NO_MEMORY;
- declAttributeIsCdata = XML_FALSE;
- declAttributeType = NULL;
- declAttributeIsId = XML_FALSE;
+ parser->m_declAttributeIsCdata = XML_FALSE;
+ parser->m_declAttributeType = NULL;
+ parser->m_declAttributeIsId = XML_FALSE;
goto checkAttListDeclHandler;
case XML_ROLE_ATTRIBUTE_TYPE_CDATA:
- declAttributeIsCdata = XML_TRUE;
- declAttributeType = atypeCDATA;
+ parser->m_declAttributeIsCdata = XML_TRUE;
+ parser->m_declAttributeType = atypeCDATA;
goto checkAttListDeclHandler;
case XML_ROLE_ATTRIBUTE_TYPE_ID:
- declAttributeIsId = XML_TRUE;
- declAttributeType = atypeID;
+ parser->m_declAttributeIsId = XML_TRUE;
+ parser->m_declAttributeType = atypeID;
goto checkAttListDeclHandler;
case XML_ROLE_ATTRIBUTE_TYPE_IDREF:
- declAttributeType = atypeIDREF;
+ parser->m_declAttributeType = atypeIDREF;
goto checkAttListDeclHandler;
case XML_ROLE_ATTRIBUTE_TYPE_IDREFS:
- declAttributeType = atypeIDREFS;
+ parser->m_declAttributeType = atypeIDREFS;
goto checkAttListDeclHandler;
case XML_ROLE_ATTRIBUTE_TYPE_ENTITY:
- declAttributeType = atypeENTITY;
+ parser->m_declAttributeType = atypeENTITY;
goto checkAttListDeclHandler;
case XML_ROLE_ATTRIBUTE_TYPE_ENTITIES:
- declAttributeType = atypeENTITIES;
+ parser->m_declAttributeType = atypeENTITIES;
goto checkAttListDeclHandler;
case XML_ROLE_ATTRIBUTE_TYPE_NMTOKEN:
- declAttributeType = atypeNMTOKEN;
+ parser->m_declAttributeType = atypeNMTOKEN;
goto checkAttListDeclHandler;
case XML_ROLE_ATTRIBUTE_TYPE_NMTOKENS:
- declAttributeType = atypeNMTOKENS;
+ parser->m_declAttributeType = atypeNMTOKENS;
checkAttListDeclHandler:
- if (dtd->keepProcessing && attlistDeclHandler)
+ if (dtd->keepProcessing && parser->m_attlistDeclHandler)
handleDefault = XML_FALSE;
break;
case XML_ROLE_ATTRIBUTE_ENUM_VALUE:
case XML_ROLE_ATTRIBUTE_NOTATION_VALUE:
- if (dtd->keepProcessing && attlistDeclHandler) {
+ if (dtd->keepProcessing && parser->m_attlistDeclHandler) {
const XML_Char *prefix;
- if (declAttributeType) {
+ if (parser->m_declAttributeType) {
prefix = enumValueSep;
}
else {
@@ -4120,37 +4608,37 @@ doProlog(XML_Parser parser,
? notationPrefix
: enumValueStart);
}
- if (!poolAppendString(&tempPool, prefix))
+ if (!poolAppendString(&parser->m_tempPool, prefix))
return XML_ERROR_NO_MEMORY;
- if (!poolAppend(&tempPool, enc, s, next))
+ if (!poolAppend(&parser->m_tempPool, enc, s, next))
return XML_ERROR_NO_MEMORY;
- declAttributeType = tempPool.start;
+ parser->m_declAttributeType = parser->m_tempPool.start;
handleDefault = XML_FALSE;
}
break;
case XML_ROLE_IMPLIED_ATTRIBUTE_VALUE:
case XML_ROLE_REQUIRED_ATTRIBUTE_VALUE:
if (dtd->keepProcessing) {
- if (!defineAttribute(declElementType, declAttributeId,
- declAttributeIsCdata, declAttributeIsId,
+ if (!defineAttribute(parser->m_declElementType, parser->m_declAttributeId,
+ parser->m_declAttributeIsCdata, parser->m_declAttributeIsId,
0, parser))
return XML_ERROR_NO_MEMORY;
- if (attlistDeclHandler && declAttributeType) {
- if (*declAttributeType == XML_T(ASCII_LPAREN)
- || (*declAttributeType == XML_T(ASCII_N)
- && declAttributeType[1] == XML_T(ASCII_O))) {
+ if (parser->m_attlistDeclHandler && parser->m_declAttributeType) {
+ if (*parser->m_declAttributeType == XML_T(ASCII_LPAREN)
+ || (*parser->m_declAttributeType == XML_T(ASCII_N)
+ && parser->m_declAttributeType[1] == XML_T(ASCII_O))) {
/* Enumerated or Notation type */
- if (!poolAppendChar(&tempPool, XML_T(ASCII_RPAREN))
- || !poolAppendChar(&tempPool, XML_T('\0')))
+ if (!poolAppendChar(&parser->m_tempPool, XML_T(ASCII_RPAREN))
+ || !poolAppendChar(&parser->m_tempPool, XML_T('\0')))
return XML_ERROR_NO_MEMORY;
- declAttributeType = tempPool.start;
- poolFinish(&tempPool);
+ parser->m_declAttributeType = parser->m_tempPool.start;
+ poolFinish(&parser->m_tempPool);
}
*eventEndPP = s;
- attlistDeclHandler(handlerArg, declElementType->name,
- declAttributeId->name, declAttributeType,
+ parser->m_attlistDeclHandler(parser->m_handlerArg, parser->m_declElementType->name,
+ parser->m_declAttributeId->name, parser->m_declAttributeType,
0, role == XML_ROLE_REQUIRED_ATTRIBUTE_VALUE);
- poolClear(&tempPool);
+ poolClear(&parser->m_tempPool);
handleDefault = XML_FALSE;
}
}
@@ -4160,7 +4648,7 @@ doProlog(XML_Parser parser,
if (dtd->keepProcessing) {
const XML_Char *attVal;
enum XML_Error result =
- storeAttributeValue(parser, enc, declAttributeIsCdata,
+ storeAttributeValue(parser, enc, parser->m_declAttributeIsCdata,
s + enc->minBytesPerChar,
next - enc->minBytesPerChar,
&dtd->pool);
@@ -4169,26 +4657,26 @@ doProlog(XML_Parser parser,
attVal = poolStart(&dtd->pool);
poolFinish(&dtd->pool);
/* ID attributes aren't allowed to have a default */
- if (!defineAttribute(declElementType, declAttributeId,
- declAttributeIsCdata, XML_FALSE, attVal, parser))
+ if (!defineAttribute(parser->m_declElementType, parser->m_declAttributeId,
+ parser->m_declAttributeIsCdata, XML_FALSE, attVal, parser))
return XML_ERROR_NO_MEMORY;
- if (attlistDeclHandler && declAttributeType) {
- if (*declAttributeType == XML_T(ASCII_LPAREN)
- || (*declAttributeType == XML_T(ASCII_N)
- && declAttributeType[1] == XML_T(ASCII_O))) {
+ if (parser->m_attlistDeclHandler && parser->m_declAttributeType) {
+ if (*parser->m_declAttributeType == XML_T(ASCII_LPAREN)
+ || (*parser->m_declAttributeType == XML_T(ASCII_N)
+ && parser->m_declAttributeType[1] == XML_T(ASCII_O))) {
/* Enumerated or Notation type */
- if (!poolAppendChar(&tempPool, XML_T(ASCII_RPAREN))
- || !poolAppendChar(&tempPool, XML_T('\0')))
+ if (!poolAppendChar(&parser->m_tempPool, XML_T(ASCII_RPAREN))
+ || !poolAppendChar(&parser->m_tempPool, XML_T('\0')))
return XML_ERROR_NO_MEMORY;
- declAttributeType = tempPool.start;
- poolFinish(&tempPool);
+ parser->m_declAttributeType = parser->m_tempPool.start;
+ poolFinish(&parser->m_tempPool);
}
*eventEndPP = s;
- attlistDeclHandler(handlerArg, declElementType->name,
- declAttributeId->name, declAttributeType,
+ parser->m_attlistDeclHandler(parser->m_handlerArg, parser->m_declElementType->name,
+ parser->m_declAttributeId->name, parser->m_declAttributeType,
attVal,
role == XML_ROLE_FIXED_ATTRIBUTE_VALUE);
- poolClear(&tempPool);
+ poolClear(&parser->m_tempPool);
handleDefault = XML_FALSE;
}
}
@@ -4198,18 +4686,18 @@ doProlog(XML_Parser parser,
enum XML_Error result = storeEntityValue(parser, enc,
s + enc->minBytesPerChar,
next - enc->minBytesPerChar);
- if (declEntity) {
- declEntity->textPtr = poolStart(&dtd->entityValuePool);
- declEntity->textLen = (int)(poolLength(&dtd->entityValuePool));
+ if (parser->m_declEntity) {
+ parser->m_declEntity->textPtr = poolStart(&dtd->entityValuePool);
+ parser->m_declEntity->textLen = (int)(poolLength(&dtd->entityValuePool));
poolFinish(&dtd->entityValuePool);
- if (entityDeclHandler) {
+ if (parser->m_entityDeclHandler) {
*eventEndPP = s;
- entityDeclHandler(handlerArg,
- declEntity->name,
- declEntity->is_param,
- declEntity->textPtr,
- declEntity->textLen,
- curBase, 0, 0, 0);
+ parser->m_entityDeclHandler(parser->m_handlerArg,
+ parser->m_declEntity->name,
+ parser->m_declEntity->is_param,
+ parser->m_declEntity->textPtr,
+ parser->m_declEntity->textLen,
+ parser->m_curBase, 0, 0, 0);
handleDefault = XML_FALSE;
}
}
@@ -4221,97 +4709,100 @@ doProlog(XML_Parser parser,
break;
case XML_ROLE_DOCTYPE_SYSTEM_ID:
#ifdef XML_DTD
- useForeignDTD = XML_FALSE;
+ parser->m_useForeignDTD = XML_FALSE;
#endif /* XML_DTD */
dtd->hasParamEntityRefs = XML_TRUE;
- if (startDoctypeDeclHandler) {
- doctypeSysid = poolStoreString(&tempPool, enc,
+ if (parser->m_startDoctypeDeclHandler) {
+ parser->m_doctypeSysid = poolStoreString(&parser->m_tempPool, enc,
s + enc->minBytesPerChar,
next - enc->minBytesPerChar);
- if (doctypeSysid == NULL)
+ if (parser->m_doctypeSysid == NULL)
return XML_ERROR_NO_MEMORY;
- poolFinish(&tempPool);
+ poolFinish(&parser->m_tempPool);
handleDefault = XML_FALSE;
}
#ifdef XML_DTD
else
- /* use externalSubsetName to make doctypeSysid non-NULL
- for the case where no startDoctypeDeclHandler is set */
- doctypeSysid = externalSubsetName;
+ /* use externalSubsetName to make parser->m_doctypeSysid non-NULL
+ for the case where no parser->m_startDoctypeDeclHandler is set */
+ parser->m_doctypeSysid = externalSubsetName;
#endif /* XML_DTD */
if (!dtd->standalone
#ifdef XML_DTD
- && !paramEntityParsing
+ && !parser->m_paramEntityParsing
#endif /* XML_DTD */
- && notStandaloneHandler
- && !notStandaloneHandler(handlerArg))
+ && parser->m_notStandaloneHandler
+ && !parser->m_notStandaloneHandler(parser->m_handlerArg))
return XML_ERROR_NOT_STANDALONE;
#ifndef XML_DTD
break;
#else /* XML_DTD */
- if (!declEntity) {
- declEntity = (ENTITY *)lookup(parser,
+ if (!parser->m_declEntity) {
+ parser->m_declEntity = (ENTITY *)lookup(parser,
&dtd->paramEntities,
externalSubsetName,
sizeof(ENTITY));
- if (!declEntity)
+ if (!parser->m_declEntity)
return XML_ERROR_NO_MEMORY;
- declEntity->publicId = NULL;
+ parser->m_declEntity->publicId = NULL;
}
/* fall through */
#endif /* XML_DTD */
case XML_ROLE_ENTITY_SYSTEM_ID:
- if (dtd->keepProcessing && declEntity) {
- declEntity->systemId = poolStoreString(&dtd->pool, enc,
+ if (dtd->keepProcessing && parser->m_declEntity) {
+ parser->m_declEntity->systemId = poolStoreString(&dtd->pool, enc,
s + enc->minBytesPerChar,
next - enc->minBytesPerChar);
- if (!declEntity->systemId)
+ if (!parser->m_declEntity->systemId)
return XML_ERROR_NO_MEMORY;
- declEntity->base = curBase;
+ parser->m_declEntity->base = parser->m_curBase;
poolFinish(&dtd->pool);
- if (entityDeclHandler)
+ /* Don't suppress the default handler if we fell through from
+ * the XML_ROLE_DOCTYPE_SYSTEM_ID case.
+ */
+ if (parser->m_entityDeclHandler && role == XML_ROLE_ENTITY_SYSTEM_ID)
handleDefault = XML_FALSE;
}
break;
case XML_ROLE_ENTITY_COMPLETE:
- if (dtd->keepProcessing && declEntity && entityDeclHandler) {
+ if (dtd->keepProcessing && parser->m_declEntity && parser->m_entityDeclHandler) {
*eventEndPP = s;
- entityDeclHandler(handlerArg,
- declEntity->name,
- declEntity->is_param,
+ parser->m_entityDeclHandler(parser->m_handlerArg,
+ parser->m_declEntity->name,
+ parser->m_declEntity->is_param,
0,0,
- declEntity->base,
- declEntity->systemId,
- declEntity->publicId,
+ parser->m_declEntity->base,
+ parser->m_declEntity->systemId,
+ parser->m_declEntity->publicId,
0);
handleDefault = XML_FALSE;
}
break;
case XML_ROLE_ENTITY_NOTATION_NAME:
- if (dtd->keepProcessing && declEntity) {
- declEntity->notation = poolStoreString(&dtd->pool, enc, s, next);
- if (!declEntity->notation)
+ if (dtd->keepProcessing && parser->m_declEntity) {
+ parser->m_declEntity->notation = poolStoreString(&dtd->pool, enc, s, next);
+ if (!parser->m_declEntity->notation)
return XML_ERROR_NO_MEMORY;
poolFinish(&dtd->pool);
- if (unparsedEntityDeclHandler) {
+ if (parser->m_unparsedEntityDeclHandler) {
*eventEndPP = s;
- unparsedEntityDeclHandler(handlerArg,
- declEntity->name,
- declEntity->base,
- declEntity->systemId,
- declEntity->publicId,
- declEntity->notation);
+ parser->m_unparsedEntityDeclHandler(parser->m_handlerArg,
+ parser->m_declEntity->name,
+ parser->m_declEntity->base,
+ parser->m_declEntity->systemId,
+ parser->m_declEntity->publicId,
+ parser->m_declEntity->notation);
handleDefault = XML_FALSE;
}
- else if (entityDeclHandler) {
+ else if (parser->m_entityDeclHandler) {
*eventEndPP = s;
- entityDeclHandler(handlerArg,
- declEntity->name,
+ parser->m_entityDeclHandler(parser->m_handlerArg,
+ parser->m_declEntity->name,
0,0,0,
- declEntity->base,
- declEntity->systemId,
- declEntity->publicId,
- declEntity->notation);
+ parser->m_declEntity->base,
+ parser->m_declEntity->systemId,
+ parser->m_declEntity->publicId,
+ parser->m_declEntity->notation);
handleDefault = XML_FALSE;
}
}
@@ -4319,36 +4810,36 @@ doProlog(XML_Parser parser,
case XML_ROLE_GENERAL_ENTITY_NAME:
{
if (XmlPredefinedEntityName(enc, s, next)) {
- declEntity = NULL;
+ parser->m_declEntity = NULL;
break;
}
if (dtd->keepProcessing) {
const XML_Char *name = poolStoreString(&dtd->pool, enc, s, next);
if (!name)
return XML_ERROR_NO_MEMORY;
- declEntity = (ENTITY *)lookup(parser, &dtd->generalEntities, name,
+ parser->m_declEntity = (ENTITY *)lookup(parser, &dtd->generalEntities, name,
sizeof(ENTITY));
- if (!declEntity)
+ if (!parser->m_declEntity)
return XML_ERROR_NO_MEMORY;
- if (declEntity->name != name) {
+ if (parser->m_declEntity->name != name) {
poolDiscard(&dtd->pool);
- declEntity = NULL;
+ parser->m_declEntity = NULL;
}
else {
poolFinish(&dtd->pool);
- declEntity->publicId = NULL;
- declEntity->is_param = XML_FALSE;
+ parser->m_declEntity->publicId = NULL;
+ parser->m_declEntity->is_param = XML_FALSE;
/* if we have a parent parser or are reading an internal parameter
entity, then the entity declaration is not considered "internal"
*/
- declEntity->is_internal = !(parentParser || openInternalEntities);
- if (entityDeclHandler)
+ parser->m_declEntity->is_internal = !(parser->m_parentParser || parser->m_openInternalEntities);
+ if (parser->m_entityDeclHandler)
handleDefault = XML_FALSE;
}
}
else {
poolDiscard(&dtd->pool);
- declEntity = NULL;
+ parser->m_declEntity = NULL;
}
}
break;
@@ -4358,90 +4849,90 @@ doProlog(XML_Parser parser,
const XML_Char *name = poolStoreString(&dtd->pool, enc, s, next);
if (!name)
return XML_ERROR_NO_MEMORY;
- declEntity = (ENTITY *)lookup(parser, &dtd->paramEntities,
+ parser->m_declEntity = (ENTITY *)lookup(parser, &dtd->paramEntities,
name, sizeof(ENTITY));
- if (!declEntity)
+ if (!parser->m_declEntity)
return XML_ERROR_NO_MEMORY;
- if (declEntity->name != name) {
+ if (parser->m_declEntity->name != name) {
poolDiscard(&dtd->pool);
- declEntity = NULL;
+ parser->m_declEntity = NULL;
}
else {
poolFinish(&dtd->pool);
- declEntity->publicId = NULL;
- declEntity->is_param = XML_TRUE;
+ parser->m_declEntity->publicId = NULL;
+ parser->m_declEntity->is_param = XML_TRUE;
/* if we have a parent parser or are reading an internal parameter
entity, then the entity declaration is not considered "internal"
*/
- declEntity->is_internal = !(parentParser || openInternalEntities);
- if (entityDeclHandler)
+ parser->m_declEntity->is_internal = !(parser->m_parentParser || parser->m_openInternalEntities);
+ if (parser->m_entityDeclHandler)
handleDefault = XML_FALSE;
}
}
else {
poolDiscard(&dtd->pool);
- declEntity = NULL;
+ parser->m_declEntity = NULL;
}
#else /* not XML_DTD */
- declEntity = NULL;
+ parser->m_declEntity = NULL;
#endif /* XML_DTD */
break;
case XML_ROLE_NOTATION_NAME:
- declNotationPublicId = NULL;
- declNotationName = NULL;
- if (notationDeclHandler) {
- declNotationName = poolStoreString(&tempPool, enc, s, next);
- if (!declNotationName)
+ parser->m_declNotationPublicId = NULL;
+ parser->m_declNotationName = NULL;
+ if (parser->m_notationDeclHandler) {
+ parser->m_declNotationName = poolStoreString(&parser->m_tempPool, enc, s, next);
+ if (!parser->m_declNotationName)
return XML_ERROR_NO_MEMORY;
- poolFinish(&tempPool);
+ poolFinish(&parser->m_tempPool);
handleDefault = XML_FALSE;
}
break;
case XML_ROLE_NOTATION_PUBLIC_ID:
if (!XmlIsPublicId(enc, s, next, eventPP))
return XML_ERROR_PUBLICID;
- if (declNotationName) { /* means notationDeclHandler != NULL */
- XML_Char *tem = poolStoreString(&tempPool,
+ if (parser->m_declNotationName) { /* means m_notationDeclHandler != NULL */
+ XML_Char *tem = poolStoreString(&parser->m_tempPool,
enc,
s + enc->minBytesPerChar,
next - enc->minBytesPerChar);
if (!tem)
return XML_ERROR_NO_MEMORY;
normalizePublicId(tem);
- declNotationPublicId = tem;
- poolFinish(&tempPool);
+ parser->m_declNotationPublicId = tem;
+ poolFinish(&parser->m_tempPool);
handleDefault = XML_FALSE;
}
break;
case XML_ROLE_NOTATION_SYSTEM_ID:
- if (declNotationName && notationDeclHandler) {
+ if (parser->m_declNotationName && parser->m_notationDeclHandler) {
const XML_Char *systemId
- = poolStoreString(&tempPool, enc,
+ = poolStoreString(&parser->m_tempPool, enc,
s + enc->minBytesPerChar,
next - enc->minBytesPerChar);
if (!systemId)
return XML_ERROR_NO_MEMORY;
*eventEndPP = s;
- notationDeclHandler(handlerArg,
- declNotationName,
- curBase,
+ parser->m_notationDeclHandler(parser->m_handlerArg,
+ parser->m_declNotationName,
+ parser->m_curBase,
systemId,
- declNotationPublicId);
+ parser->m_declNotationPublicId);
handleDefault = XML_FALSE;
}
- poolClear(&tempPool);
+ poolClear(&parser->m_tempPool);
break;
case XML_ROLE_NOTATION_NO_SYSTEM_ID:
- if (declNotationPublicId && notationDeclHandler) {
+ if (parser->m_declNotationPublicId && parser->m_notationDeclHandler) {
*eventEndPP = s;
- notationDeclHandler(handlerArg,
- declNotationName,
- curBase,
+ parser->m_notationDeclHandler(parser->m_handlerArg,
+ parser->m_declNotationName,
+ parser->m_curBase,
0,
- declNotationPublicId);
+ parser->m_declNotationPublicId);
handleDefault = XML_FALSE;
}
- poolClear(&tempPool);
+ poolClear(&parser->m_tempPool);
break;
case XML_ROLE_ERROR:
switch (tok) {
@@ -4458,41 +4949,45 @@ doProlog(XML_Parser parser,
case XML_ROLE_IGNORE_SECT:
{
enum XML_Error result;
- if (defaultHandler)
+ if (parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
handleDefault = XML_FALSE;
result = doIgnoreSection(parser, enc, &next, end, nextPtr, haveMore);
if (result != XML_ERROR_NONE)
return result;
else if (!next) {
- processor = ignoreSectionProcessor;
+ parser->m_processor = ignoreSectionProcessor;
return result;
}
}
break;
#endif /* XML_DTD */
case XML_ROLE_GROUP_OPEN:
- if (prologState.level >= groupSize) {
- if (groupSize) {
- char *temp = (char *)REALLOC(groupConnector, groupSize *= 2);
- if (temp == NULL)
+ if (parser->m_prologState.level >= parser->m_groupSize) {
+ if (parser->m_groupSize) {
+ char *temp = (char *)REALLOC(parser, parser->m_groupConnector, parser->m_groupSize *= 2);
+ if (temp == NULL) {
+ parser->m_groupSize /= 2;
return XML_ERROR_NO_MEMORY;
- groupConnector = temp;
+ }
+ parser->m_groupConnector = temp;
if (dtd->scaffIndex) {
- int *temp = (int *)REALLOC(dtd->scaffIndex,
- groupSize * sizeof(int));
+ int *temp = (int *)REALLOC(parser, dtd->scaffIndex,
+ parser->m_groupSize * sizeof(int));
if (temp == NULL)
return XML_ERROR_NO_MEMORY;
dtd->scaffIndex = temp;
}
}
else {
- groupConnector = (char *)MALLOC(groupSize = 32);
- if (!groupConnector)
+ parser->m_groupConnector = (char *)MALLOC(parser, parser->m_groupSize = 32);
+ if (!parser->m_groupConnector) {
+ parser->m_groupSize = 0;
return XML_ERROR_NO_MEMORY;
+ }
}
}
- groupConnector[prologState.level] = 0;
+ parser->m_groupConnector[parser->m_prologState.level] = 0;
if (dtd->in_eldecl) {
int myindex = nextScaffoldPart(parser);
if (myindex < 0)
@@ -4500,37 +4995,37 @@ doProlog(XML_Parser parser,
dtd->scaffIndex[dtd->scaffLevel] = myindex;
dtd->scaffLevel++;
dtd->scaffold[myindex].type = XML_CTYPE_SEQ;
- if (elementDeclHandler)
+ if (parser->m_elementDeclHandler)
handleDefault = XML_FALSE;
}
break;
case XML_ROLE_GROUP_SEQUENCE:
- if (groupConnector[prologState.level] == ASCII_PIPE)
+ if (parser->m_groupConnector[parser->m_prologState.level] == ASCII_PIPE)
return XML_ERROR_SYNTAX;
- groupConnector[prologState.level] = ASCII_COMMA;
- if (dtd->in_eldecl && elementDeclHandler)
+ parser->m_groupConnector[parser->m_prologState.level] = ASCII_COMMA;
+ if (dtd->in_eldecl && parser->m_elementDeclHandler)
handleDefault = XML_FALSE;
break;
case XML_ROLE_GROUP_CHOICE:
- if (groupConnector[prologState.level] == ASCII_COMMA)
+ if (parser->m_groupConnector[parser->m_prologState.level] == ASCII_COMMA)
return XML_ERROR_SYNTAX;
if (dtd->in_eldecl
- && !groupConnector[prologState.level]
+ && !parser->m_groupConnector[parser->m_prologState.level]
&& (dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]].type
!= XML_CTYPE_MIXED)
) {
dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]].type
= XML_CTYPE_CHOICE;
- if (elementDeclHandler)
+ if (parser->m_elementDeclHandler)
handleDefault = XML_FALSE;
}
- groupConnector[prologState.level] = ASCII_PIPE;
+ parser->m_groupConnector[parser->m_prologState.level] = ASCII_PIPE;
break;
case XML_ROLE_PARAM_ENTITY_REF:
#ifdef XML_DTD
case XML_ROLE_INNER_PARAM_ENTITY_REF:
dtd->hasParamEntityRefs = XML_TRUE;
- if (!paramEntityParsing)
+ if (!parser->m_paramEntityParsing)
dtd->keepProcessing = dtd->standalone;
else {
const XML_Char *name;
@@ -4546,20 +5041,41 @@ doProlog(XML_Parser parser,
if yes, check that the entity exists, and that it is internal,
otherwise call the skipped entity handler
*/
- if (prologState.documentEntity &&
+ if (parser->m_prologState.documentEntity &&
(dtd->standalone
- ? !openInternalEntities
+ ? !parser->m_openInternalEntities
: !dtd->hasParamEntityRefs)) {
if (!entity)
return XML_ERROR_UNDEFINED_ENTITY;
- else if (!entity->is_internal)
- return XML_ERROR_ENTITY_DECLARED_IN_PE;
+ else if (!entity->is_internal) {
+ /* It's hard to exhaustively search the code to be sure,
+ * but there doesn't seem to be a way of executing the
+ * following line. There are two cases:
+ *
+ * If 'standalone' is false, the DTD must have no
+ * parameter entities or we wouldn't have passed the outer
+ * 'if' statement. That measn the only entity in the hash
+ * table is the external subset name "#" which cannot be
+ * given as a parameter entity name in XML syntax, so the
+ * lookup must have returned NULL and we don't even reach
+ * the test for an internal entity.
+ *
+ * If 'standalone' is true, it does not seem to be
+ * possible to create entities taking this code path that
+ * are not internal entities, so fail the test above.
+ *
+ * Because this analysis is very uncertain, the code is
+ * being left in place and merely removed from the
+ * coverage test statistics.
+ */
+ return XML_ERROR_ENTITY_DECLARED_IN_PE; /* LCOV_EXCL_LINE */
+ }
}
else if (!entity) {
dtd->keepProcessing = dtd->standalone;
/* cannot report skipped entities in declarations */
- if ((role == XML_ROLE_PARAM_ENTITY_REF) && skippedEntityHandler) {
- skippedEntityHandler(handlerArg, name, 1);
+ if ((role == XML_ROLE_PARAM_ENTITY_REF) && parser->m_skippedEntityHandler) {
+ parser->m_skippedEntityHandler(parser->m_handlerArg, name, 1);
handleDefault = XML_FALSE;
}
break;
@@ -4576,10 +5092,10 @@ doProlog(XML_Parser parser,
handleDefault = XML_FALSE;
break;
}
- if (externalEntityRefHandler) {
+ if (parser->m_externalEntityRefHandler) {
dtd->paramEntityRead = XML_FALSE;
entity->open = XML_TRUE;
- if (!externalEntityRefHandler(externalEntityRefHandlerArg,
+ if (!parser->m_externalEntityRefHandler(parser->m_externalEntityRefHandlerArg,
0,
entity->base,
entity->systemId,
@@ -4601,17 +5117,17 @@ doProlog(XML_Parser parser,
}
#endif /* XML_DTD */
if (!dtd->standalone &&
- notStandaloneHandler &&
- !notStandaloneHandler(handlerArg))
+ parser->m_notStandaloneHandler &&
+ !parser->m_notStandaloneHandler(parser->m_handlerArg))
return XML_ERROR_NOT_STANDALONE;
break;
/* Element declaration stuff */
case XML_ROLE_ELEMENT_NAME:
- if (elementDeclHandler) {
- declElementType = getElementType(parser, enc, s, next);
- if (!declElementType)
+ if (parser->m_elementDeclHandler) {
+ parser->m_declElementType = getElementType(parser, enc, s, next);
+ if (!parser->m_declElementType)
return XML_ERROR_NO_MEMORY;
dtd->scaffLevel = 0;
dtd->scaffCount = 0;
@@ -4623,8 +5139,8 @@ doProlog(XML_Parser parser,
case XML_ROLE_CONTENT_ANY:
case XML_ROLE_CONTENT_EMPTY:
if (dtd->in_eldecl) {
- if (elementDeclHandler) {
- XML_Content * content = (XML_Content *) MALLOC(sizeof(XML_Content));
+ if (parser->m_elementDeclHandler) {
+ XML_Content * content = (XML_Content *) MALLOC(parser, sizeof(XML_Content));
if (!content)
return XML_ERROR_NO_MEMORY;
content->quant = XML_CQUANT_NONE;
@@ -4635,7 +5151,7 @@ doProlog(XML_Parser parser,
XML_CTYPE_ANY :
XML_CTYPE_EMPTY);
*eventEndPP = s;
- elementDeclHandler(handlerArg, declElementType->name, content);
+ parser->m_elementDeclHandler(parser->m_handlerArg, parser->m_declElementType->name, content);
handleDefault = XML_FALSE;
}
dtd->in_eldecl = XML_FALSE;
@@ -4646,7 +5162,7 @@ doProlog(XML_Parser parser,
if (dtd->in_eldecl) {
dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]].type
= XML_CTYPE_MIXED;
- if (elementDeclHandler)
+ if (parser->m_elementDeclHandler)
handleDefault = XML_FALSE;
}
break;
@@ -4683,7 +5199,7 @@ doProlog(XML_Parser parser,
nameLen = 0;
for (; name[nameLen++]; );
dtd->contentStringLen += nameLen;
- if (elementDeclHandler)
+ if (parser->m_elementDeclHandler)
handleDefault = XML_FALSE;
}
break;
@@ -4701,7 +5217,7 @@ doProlog(XML_Parser parser,
quant = XML_CQUANT_PLUS;
closeGroup:
if (dtd->in_eldecl) {
- if (elementDeclHandler)
+ if (parser->m_elementDeclHandler)
handleDefault = XML_FALSE;
dtd->scaffLevel--;
dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel]].quant = quant;
@@ -4711,7 +5227,7 @@ doProlog(XML_Parser parser,
if (!model)
return XML_ERROR_NO_MEMORY;
*eventEndPP = s;
- elementDeclHandler(handlerArg, declElementType->name, model);
+ parser->m_elementDeclHandler(parser->m_handlerArg, parser->m_declElementType->name, model);
}
dtd->in_eldecl = XML_FALSE;
dtd->contentStringLen = 0;
@@ -4738,31 +5254,31 @@ doProlog(XML_Parser parser,
}
break;
case XML_ROLE_DOCTYPE_NONE:
- if (startDoctypeDeclHandler)
+ if (parser->m_startDoctypeDeclHandler)
handleDefault = XML_FALSE;
break;
case XML_ROLE_ENTITY_NONE:
- if (dtd->keepProcessing && entityDeclHandler)
+ if (dtd->keepProcessing && parser->m_entityDeclHandler)
handleDefault = XML_FALSE;
break;
case XML_ROLE_NOTATION_NONE:
- if (notationDeclHandler)
+ if (parser->m_notationDeclHandler)
handleDefault = XML_FALSE;
break;
case XML_ROLE_ATTLIST_NONE:
- if (dtd->keepProcessing && attlistDeclHandler)
+ if (dtd->keepProcessing && parser->m_attlistDeclHandler)
handleDefault = XML_FALSE;
break;
case XML_ROLE_ELEMENT_NONE:
- if (elementDeclHandler)
+ if (parser->m_elementDeclHandler)
handleDefault = XML_FALSE;
break;
} /* end of big switch */
- if (handleDefault && defaultHandler)
+ if (handleDefault && parser->m_defaultHandler)
reportDefault(parser, enc, s, next);
- switch (ps_parsing) {
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
*nextPtr = next;
return XML_ERROR_NONE;
@@ -4782,18 +5298,18 @@ epilogProcessor(XML_Parser parser,
const char *end,
const char **nextPtr)
{
- processor = epilogProcessor;
- eventPtr = s;
+ parser->m_processor = epilogProcessor;
+ parser->m_eventPtr = s;
for (;;) {
const char *next = NULL;
- int tok = XmlPrologTok(encoding, s, end, &next);
- eventEndPtr = next;
+ int tok = XmlPrologTok(parser->m_encoding, s, end, &next);
+ parser->m_eventEndPtr = next;
switch (tok) {
/* report partial linebreak - it might be the last token */
case -XML_TOK_PROLOG_S:
- if (defaultHandler) {
- reportDefault(parser, encoding, s, next);
- if (ps_parsing == XML_FINISHED)
+ if (parser->m_defaultHandler) {
+ reportDefault(parser, parser->m_encoding, s, next);
+ if (parser->m_parsingStatus.parsing == XML_FINISHED)
return XML_ERROR_ABORTED;
}
*nextPtr = next;
@@ -4802,28 +5318,28 @@ epilogProcessor(XML_Parser parser,
*nextPtr = s;
return XML_ERROR_NONE;
case XML_TOK_PROLOG_S:
- if (defaultHandler)
- reportDefault(parser, encoding, s, next);
+ if (parser->m_defaultHandler)
+ reportDefault(parser, parser->m_encoding, s, next);
break;
case XML_TOK_PI:
- if (!reportProcessingInstruction(parser, encoding, s, next))
+ if (!reportProcessingInstruction(parser, parser->m_encoding, s, next))
return XML_ERROR_NO_MEMORY;
break;
case XML_TOK_COMMENT:
- if (!reportComment(parser, encoding, s, next))
+ if (!reportComment(parser, parser->m_encoding, s, next))
return XML_ERROR_NO_MEMORY;
break;
case XML_TOK_INVALID:
- eventPtr = next;
+ parser->m_eventPtr = next;
return XML_ERROR_INVALID_TOKEN;
case XML_TOK_PARTIAL:
- if (!ps_finalBuffer) {
+ if (!parser->m_parsingStatus.finalBuffer) {
*nextPtr = s;
return XML_ERROR_NONE;
}
return XML_ERROR_UNCLOSED_TOKEN;
case XML_TOK_PARTIAL_CHAR:
- if (!ps_finalBuffer) {
+ if (!parser->m_parsingStatus.finalBuffer) {
*nextPtr = s;
return XML_ERROR_NONE;
}
@@ -4831,8 +5347,8 @@ epilogProcessor(XML_Parser parser,
default:
return XML_ERROR_JUNK_AFTER_DOC_ELEMENT;
}
- eventPtr = s = next;
- switch (ps_parsing) {
+ parser->m_eventPtr = s = next;
+ switch (parser->m_parsingStatus.parsing) {
case XML_SUSPENDED:
*nextPtr = next;
return XML_ERROR_NONE;
@@ -4852,49 +5368,51 @@ processInternalEntity(XML_Parser parser, ENTITY *entity,
enum XML_Error result;
OPEN_INTERNAL_ENTITY *openEntity;
- if (freeInternalEntities) {
- openEntity = freeInternalEntities;
- freeInternalEntities = openEntity->next;
+ if (parser->m_freeInternalEntities) {
+ openEntity = parser->m_freeInternalEntities;
+ parser->m_freeInternalEntities = openEntity->next;
}
else {
- openEntity = (OPEN_INTERNAL_ENTITY *)MALLOC(sizeof(OPEN_INTERNAL_ENTITY));
+ openEntity = (OPEN_INTERNAL_ENTITY *)MALLOC(parser, sizeof(OPEN_INTERNAL_ENTITY));
if (!openEntity)
return XML_ERROR_NO_MEMORY;
}
entity->open = XML_TRUE;
entity->processed = 0;
- openEntity->next = openInternalEntities;
- openInternalEntities = openEntity;
+ openEntity->next = parser->m_openInternalEntities;
+ parser->m_openInternalEntities = openEntity;
openEntity->entity = entity;
- openEntity->startTagLevel = tagLevel;
+ openEntity->startTagLevel = parser->m_tagLevel;
openEntity->betweenDecl = betweenDecl;
openEntity->internalEventPtr = NULL;
openEntity->internalEventEndPtr = NULL;
textStart = (char *)entity->textPtr;
textEnd = (char *)(entity->textPtr + entity->textLen);
+ /* Set a safe default value in case 'next' does not get set */
+ next = textStart;
#ifdef XML_DTD
if (entity->is_param) {
- int tok = XmlPrologTok(internalEncoding, textStart, textEnd, &next);
- result = doProlog(parser, internalEncoding, textStart, textEnd, tok,
+ int tok = XmlPrologTok(parser->m_internalEncoding, textStart, textEnd, &next);
+ result = doProlog(parser, parser->m_internalEncoding, textStart, textEnd, tok,
next, &next, XML_FALSE);
}
else
#endif /* XML_DTD */
- result = doContent(parser, tagLevel, internalEncoding, textStart,
+ result = doContent(parser, parser->m_tagLevel, parser->m_internalEncoding, textStart,
textEnd, &next, XML_FALSE);
if (result == XML_ERROR_NONE) {
- if (textEnd != next && ps_parsing == XML_SUSPENDED) {
+ if (textEnd != next && parser->m_parsingStatus.parsing == XML_SUSPENDED) {
entity->processed = (int)(next - textStart);
- processor = internalEntityProcessor;
+ parser->m_processor = internalEntityProcessor;
}
else {
entity->open = XML_FALSE;
- openInternalEntities = openEntity->next;
+ parser->m_openInternalEntities = openEntity->next;
/* put openEntity back in list of free instances */
- openEntity->next = freeInternalEntities;
- freeInternalEntities = openEntity;
+ openEntity->next = parser->m_freeInternalEntities;
+ parser->m_freeInternalEntities = openEntity;
}
}
return result;
@@ -4910,54 +5428,56 @@ internalEntityProcessor(XML_Parser parser,
const char *textStart, *textEnd;
const char *next;
enum XML_Error result;
- OPEN_INTERNAL_ENTITY *openEntity = openInternalEntities;
+ OPEN_INTERNAL_ENTITY *openEntity = parser->m_openInternalEntities;
if (!openEntity)
return XML_ERROR_UNEXPECTED_STATE;
entity = openEntity->entity;
textStart = ((char *)entity->textPtr) + entity->processed;
textEnd = (char *)(entity->textPtr + entity->textLen);
+ /* Set a safe default value in case 'next' does not get set */
+ next = textStart;
#ifdef XML_DTD
if (entity->is_param) {
- int tok = XmlPrologTok(internalEncoding, textStart, textEnd, &next);
- result = doProlog(parser, internalEncoding, textStart, textEnd, tok,
+ int tok = XmlPrologTok(parser->m_internalEncoding, textStart, textEnd, &next);
+ result = doProlog(parser, parser->m_internalEncoding, textStart, textEnd, tok,
next, &next, XML_FALSE);
}
else
#endif /* XML_DTD */
- result = doContent(parser, openEntity->startTagLevel, internalEncoding,
+ result = doContent(parser, openEntity->startTagLevel, parser->m_internalEncoding,
textStart, textEnd, &next, XML_FALSE);
if (result != XML_ERROR_NONE)
return result;
- else if (textEnd != next && ps_parsing == XML_SUSPENDED) {
+ else if (textEnd != next && parser->m_parsingStatus.parsing == XML_SUSPENDED) {
entity->processed = (int)(next - (char *)entity->textPtr);
return result;
}
else {
entity->open = XML_FALSE;
- openInternalEntities = openEntity->next;
+ parser->m_openInternalEntities = openEntity->next;
/* put openEntity back in list of free instances */
- openEntity->next = freeInternalEntities;
- freeInternalEntities = openEntity;
+ openEntity->next = parser->m_freeInternalEntities;
+ parser->m_freeInternalEntities = openEntity;
}
#ifdef XML_DTD
if (entity->is_param) {
int tok;
- processor = prologProcessor;
- tok = XmlPrologTok(encoding, s, end, &next);
- return doProlog(parser, encoding, s, end, tok, next, nextPtr,
- (XML_Bool)!ps_finalBuffer);
+ parser->m_processor = prologProcessor;
+ tok = XmlPrologTok(parser->m_encoding, s, end, &next);
+ return doProlog(parser, parser->m_encoding, s, end, tok, next, nextPtr,
+ (XML_Bool)!parser->m_parsingStatus.finalBuffer);
}
else
#endif /* XML_DTD */
{
- processor = contentProcessor;
+ parser->m_processor = contentProcessor;
/* see externalEntityContentProcessor vs contentProcessor */
- return doContent(parser, parentParser ? 1 : 0, encoding, s, end,
- nextPtr, (XML_Bool)!ps_finalBuffer);
+ return doContent(parser, parser->m_parentParser ? 1 : 0, parser->m_encoding, s, end,
+ nextPtr, (XML_Bool)!parser->m_parsingStatus.finalBuffer);
}
}
@@ -4967,7 +5487,7 @@ errorProcessor(XML_Parser parser,
const char *UNUSED_P(end),
const char **UNUSED_P(nextPtr))
{
- return errorCode;
+ return parser->m_errorCode;
}
static enum XML_Error
@@ -4991,7 +5511,7 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata,
const char *ptr, const char *end,
STRING_POOL *pool)
{
- DTD * const dtd = _dtd; /* save one level of indirection */
+ DTD * const dtd = parser->m_dtd; /* save one level of indirection */
for (;;) {
const char *next;
int tok = XmlAttributeValueTok(enc, ptr, end, &next);
@@ -4999,12 +5519,12 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata,
case XML_TOK_NONE:
return XML_ERROR_NONE;
case XML_TOK_INVALID:
- if (enc == encoding)
- eventPtr = next;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = next;
return XML_ERROR_INVALID_TOKEN;
case XML_TOK_PARTIAL:
- if (enc == encoding)
- eventPtr = ptr;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = ptr;
return XML_ERROR_INVALID_TOKEN;
case XML_TOK_CHAR_REF:
{
@@ -5012,8 +5532,8 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata,
int i;
int n = XmlCharRefNumber(enc, ptr);
if (n < 0) {
- if (enc == encoding)
- eventPtr = ptr;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = ptr;
return XML_ERROR_BAD_CHAR_REF;
}
if (!isCdata
@@ -5021,11 +5541,15 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata,
&& (poolLength(pool) == 0 || poolLastChar(pool) == 0x20))
break;
n = XmlEncode(n, (ICHAR *)buf);
- if (!n) {
- if (enc == encoding)
- eventPtr = ptr;
- return XML_ERROR_BAD_CHAR_REF;
- }
+ /* The XmlEncode() functions can never return 0 here. That
+ * error return happens if the code point passed in is either
+ * negative or greater than or equal to 0x110000. The
+ * XmlCharRefNumber() functions will all return a number
+ * strictly less than 0x110000 or a negative value if an error
+ * occurred. The negative value is intercepted above, so
+ * XmlEncode() is never passed a value it might return an
+ * error for.
+ */
for (i = 0; i < n; i++) {
if (!poolAppendChar(pool, buf[i]))
return XML_ERROR_NO_MEMORY;
@@ -5059,25 +5583,25 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata,
return XML_ERROR_NO_MEMORY;
break;
}
- name = poolStoreString(&temp2Pool, enc,
+ name = poolStoreString(&parser->m_temp2Pool, enc,
ptr + enc->minBytesPerChar,
next - enc->minBytesPerChar);
if (!name)
return XML_ERROR_NO_MEMORY;
entity = (ENTITY *)lookup(parser, &dtd->generalEntities, name, 0);
- poolDiscard(&temp2Pool);
+ poolDiscard(&parser->m_temp2Pool);
/* First, determine if a check for an existing declaration is needed;
if yes, check that the entity exists, and that it is internal.
*/
if (pool == &dtd->pool) /* are we called from prolog? */
checkEntityDecl =
#ifdef XML_DTD
- prologState.documentEntity &&
+ parser->m_prologState.documentEntity &&
#endif /* XML_DTD */
(dtd->standalone
- ? !openInternalEntities
+ ? !parser->m_openInternalEntities
: !dtd->hasParamEntityRefs);
- else /* if (pool == &tempPool): we are called from content */
+ else /* if (pool == &parser->m_tempPool): we are called from content */
checkEntityDecl = !dtd->hasParamEntityRefs || dtd->standalone;
if (checkEntityDecl) {
if (!entity)
@@ -5087,37 +5611,55 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata,
}
else if (!entity) {
/* Cannot report skipped entity here - see comments on
- skippedEntityHandler.
- if (skippedEntityHandler)
- skippedEntityHandler(handlerArg, name, 0);
+ parser->m_skippedEntityHandler.
+ if (parser->m_skippedEntityHandler)
+ parser->m_skippedEntityHandler(parser->m_handlerArg, name, 0);
*/
/* Cannot call the default handler because this would be
out of sync with the call to the startElementHandler.
- if ((pool == &tempPool) && defaultHandler)
+ if ((pool == &parser->m_tempPool) && parser->m_defaultHandler)
reportDefault(parser, enc, ptr, next);
*/
break;
}
if (entity->open) {
- if (enc == encoding)
- eventPtr = ptr;
+ if (enc == parser->m_encoding) {
+ /* It does not appear that this line can be executed.
+ *
+ * The "if (entity->open)" check catches recursive entity
+ * definitions. In order to be called with an open
+ * entity, it must have gone through this code before and
+ * been through the recursive call to
+ * appendAttributeValue() some lines below. That call
+ * sets the local encoding ("enc") to the parser's
+ * internal encoding (internal_utf8 or internal_utf16),
+ * which can never be the same as the principle encoding.
+ * It doesn't appear there is another code path that gets
+ * here with entity->open being TRUE.
+ *
+ * Since it is not certain that this logic is watertight,
+ * we keep the line and merely exclude it from coverage
+ * tests.
+ */
+ parser->m_eventPtr = ptr; /* LCOV_EXCL_LINE */
+ }
return XML_ERROR_RECURSIVE_ENTITY_REF;
}
if (entity->notation) {
- if (enc == encoding)
- eventPtr = ptr;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = ptr;
return XML_ERROR_BINARY_ENTITY_REF;
}
if (!entity->textPtr) {
- if (enc == encoding)
- eventPtr = ptr;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = ptr;
return XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF;
}
else {
enum XML_Error result;
const XML_Char *textEnd = entity->textPtr + entity->textLen;
entity->open = XML_TRUE;
- result = appendAttributeValue(parser, internalEncoding, isCdata,
+ result = appendAttributeValue(parser, parser->m_internalEncoding, isCdata,
(char *)entity->textPtr,
(char *)textEnd, pool);
entity->open = XML_FALSE;
@@ -5127,9 +5669,21 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata,
}
break;
default:
- if (enc == encoding)
- eventPtr = ptr;
+ /* The only token returned by XmlAttributeValueTok() that does
+ * not have an explicit case here is XML_TOK_PARTIAL_CHAR.
+ * Getting that would require an entity name to contain an
+ * incomplete XML character (e.g. \xE2\x82); however previous
+ * tokenisers will have already recognised and rejected such
+ * names before XmlAttributeValueTok() gets a look-in. This
+ * default case should be retained as a safety net, but the code
+ * excluded from coverage tests.
+ *
+ * LCOV_EXCL_START
+ */
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = ptr;
return XML_ERROR_UNEXPECTED_STATE;
+ /* LCOV_EXCL_STOP */
}
ptr = next;
}
@@ -5142,12 +5696,12 @@ storeEntityValue(XML_Parser parser,
const char *entityTextPtr,
const char *entityTextEnd)
{
- DTD * const dtd = _dtd; /* save one level of indirection */
+ DTD * const dtd = parser->m_dtd; /* save one level of indirection */
STRING_POOL *pool = &(dtd->entityValuePool);
enum XML_Error result = XML_ERROR_NONE;
#ifdef XML_DTD
- int oldInEntityValue = prologState.inEntityValue;
- prologState.inEntityValue = 1;
+ int oldInEntityValue = parser->m_prologState.inEntityValue;
+ parser->m_prologState.inEntityValue = 1;
#endif /* XML_DTD */
/* never return Null for the value argument in EntityDeclHandler,
since this would indicate an external entity; therefore we
@@ -5163,10 +5717,10 @@ storeEntityValue(XML_Parser parser,
switch (tok) {
case XML_TOK_PARAM_ENTITY_REF:
#ifdef XML_DTD
- if (isParamEntity || enc != encoding) {
+ if (parser->m_isParamEntity || enc != parser->m_encoding) {
const XML_Char *name;
ENTITY *entity;
- name = poolStoreString(&tempPool, enc,
+ name = poolStoreString(&parser->m_tempPool, enc,
entityTextPtr + enc->minBytesPerChar,
next - enc->minBytesPerChar);
if (!name) {
@@ -5174,28 +5728,28 @@ storeEntityValue(XML_Parser parser,
goto endEntityValue;
}
entity = (ENTITY *)lookup(parser, &dtd->paramEntities, name, 0);
- poolDiscard(&tempPool);
+ poolDiscard(&parser->m_tempPool);
if (!entity) {
/* not a well-formedness error - see XML 1.0: WFC Entity Declared */
/* cannot report skipped entity here - see comments on
- skippedEntityHandler
- if (skippedEntityHandler)
- skippedEntityHandler(handlerArg, name, 0);
+ parser->m_skippedEntityHandler
+ if (parser->m_skippedEntityHandler)
+ parser->m_skippedEntityHandler(parser->m_handlerArg, name, 0);
*/
dtd->keepProcessing = dtd->standalone;
goto endEntityValue;
}
if (entity->open) {
- if (enc == encoding)
- eventPtr = entityTextPtr;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = entityTextPtr;
result = XML_ERROR_RECURSIVE_ENTITY_REF;
goto endEntityValue;
}
if (entity->systemId) {
- if (externalEntityRefHandler) {
+ if (parser->m_externalEntityRefHandler) {
dtd->paramEntityRead = XML_FALSE;
entity->open = XML_TRUE;
- if (!externalEntityRefHandler(externalEntityRefHandlerArg,
+ if (!parser->m_externalEntityRefHandler(parser->m_externalEntityRefHandlerArg,
0,
entity->base,
entity->systemId,
@@ -5214,7 +5768,7 @@ storeEntityValue(XML_Parser parser,
else {
entity->open = XML_TRUE;
result = storeEntityValue(parser,
- internalEncoding,
+ parser->m_internalEncoding,
(char *)entity->textPtr,
(char *)(entity->textPtr
+ entity->textLen));
@@ -5227,7 +5781,7 @@ storeEntityValue(XML_Parser parser,
#endif /* XML_DTD */
/* In the internal subset, PE references are not legal
within markup declarations, e.g entity values in this case. */
- eventPtr = entityTextPtr;
+ parser->m_eventPtr = entityTextPtr;
result = XML_ERROR_PARAM_ENTITY_REF;
goto endEntityValue;
case XML_TOK_NONE:
@@ -5256,18 +5810,21 @@ storeEntityValue(XML_Parser parser,
int i;
int n = XmlCharRefNumber(enc, entityTextPtr);
if (n < 0) {
- if (enc == encoding)
- eventPtr = entityTextPtr;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = entityTextPtr;
result = XML_ERROR_BAD_CHAR_REF;
goto endEntityValue;
}
n = XmlEncode(n, (ICHAR *)buf);
- if (!n) {
- if (enc == encoding)
- eventPtr = entityTextPtr;
- result = XML_ERROR_BAD_CHAR_REF;
- goto endEntityValue;
- }
+ /* The XmlEncode() functions can never return 0 here. That
+ * error return happens if the code point passed in is either
+ * negative or greater than or equal to 0x110000. The
+ * XmlCharRefNumber() functions will all return a number
+ * strictly less than 0x110000 or a negative value if an error
+ * occurred. The negative value is intercepted above, so
+ * XmlEncode() is never passed a value it might return an
+ * error for.
+ */
for (i = 0; i < n; i++) {
if (pool->end == pool->ptr && !poolGrow(pool)) {
result = XML_ERROR_NO_MEMORY;
@@ -5278,26 +5835,34 @@ storeEntityValue(XML_Parser parser,
}
break;
case XML_TOK_PARTIAL:
- if (enc == encoding)
- eventPtr = entityTextPtr;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = entityTextPtr;
result = XML_ERROR_INVALID_TOKEN;
goto endEntityValue;
case XML_TOK_INVALID:
- if (enc == encoding)
- eventPtr = next;
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = next;
result = XML_ERROR_INVALID_TOKEN;
goto endEntityValue;
default:
- if (enc == encoding)
- eventPtr = entityTextPtr;
+ /* This default case should be unnecessary -- all the tokens
+ * that XmlEntityValueTok() can return have their own explicit
+ * cases -- but should be retained for safety. We do however
+ * exclude it from the coverage statistics.
+ *
+ * LCOV_EXCL_START
+ */
+ if (enc == parser->m_encoding)
+ parser->m_eventPtr = entityTextPtr;
result = XML_ERROR_UNEXPECTED_STATE;
goto endEntityValue;
+ /* LCOV_EXCL_STOP */
}
entityTextPtr = next;
}
endEntityValue:
#ifdef XML_DTD
- prologState.inEntityValue = oldInEntityValue;
+ parser->m_prologState.inEntityValue = oldInEntityValue;
#endif /* XML_DTD */
return result;
}
@@ -5332,25 +5897,25 @@ reportProcessingInstruction(XML_Parser parser, const ENCODING *enc,
const XML_Char *target;
XML_Char *data;
const char *tem;
- if (!processingInstructionHandler) {
- if (defaultHandler)
+ if (!parser->m_processingInstructionHandler) {
+ if (parser->m_defaultHandler)
reportDefault(parser, enc, start, end);
return 1;
}
start += enc->minBytesPerChar * 2;
tem = start + XmlNameLength(enc, start);
- target = poolStoreString(&tempPool, enc, start, tem);
+ target = poolStoreString(&parser->m_tempPool, enc, start, tem);
if (!target)
return 0;
- poolFinish(&tempPool);
- data = poolStoreString(&tempPool, enc,
+ poolFinish(&parser->m_tempPool);
+ data = poolStoreString(&parser->m_tempPool, enc,
XmlSkipS(enc, tem),
end - enc->minBytesPerChar*2);
if (!data)
return 0;
normalizeLines(data);
- processingInstructionHandler(handlerArg, target, data);
- poolClear(&tempPool);
+ parser->m_processingInstructionHandler(parser->m_handlerArg, target, data);
+ poolClear(&parser->m_tempPool);
return 1;
}
@@ -5359,20 +5924,20 @@ reportComment(XML_Parser parser, const ENCODING *enc,
const char *start, const char *end)
{
XML_Char *data;
- if (!commentHandler) {
- if (defaultHandler)
+ if (!parser->m_commentHandler) {
+ if (parser->m_defaultHandler)
reportDefault(parser, enc, start, end);
return 1;
}
- data = poolStoreString(&tempPool,
+ data = poolStoreString(&parser->m_tempPool,
enc,
start + enc->minBytesPerChar * 4,
end - enc->minBytesPerChar * 3);
if (!data)
return 0;
normalizeLines(data);
- commentHandler(handlerArg, data);
- poolClear(&tempPool);
+ parser->m_commentHandler(parser->m_handlerArg, data);
+ poolClear(&parser->m_tempPool);
return 1;
}
@@ -5384,24 +5949,41 @@ reportDefault(XML_Parser parser, const ENCODING *enc,
enum XML_Convert_Result convert_res;
const char **eventPP;
const char **eventEndPP;
- if (enc == encoding) {
- eventPP = &eventPtr;
- eventEndPP = &eventEndPtr;
+ if (enc == parser->m_encoding) {
+ eventPP = &parser->m_eventPtr;
+ eventEndPP = &parser->m_eventEndPtr;
}
else {
- eventPP = &(openInternalEntities->internalEventPtr);
- eventEndPP = &(openInternalEntities->internalEventEndPtr);
+ /* To get here, two things must be true; the parser must be
+ * using a character encoding that is not the same as the
+ * encoding passed in, and the encoding passed in must need
+ * conversion to the internal format (UTF-8 unless XML_UNICODE
+ * is defined). The only occasions on which the encoding passed
+ * in is not the same as the parser's encoding are when it is
+ * the internal encoding (e.g. a previously defined parameter
+ * entity, already converted to internal format). This by
+ * definition doesn't need conversion, so the whole branch never
+ * gets executed.
+ *
+ * For safety's sake we don't delete these lines and merely
+ * exclude them from coverage statistics.
+ *
+ * LCOV_EXCL_START
+ */
+ eventPP = &(parser->m_openInternalEntities->internalEventPtr);
+ eventEndPP = &(parser->m_openInternalEntities->internalEventEndPtr);
+ /* LCOV_EXCL_STOP */
}
do {
- ICHAR *dataPtr = (ICHAR *)dataBuf;
- convert_res = XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)dataBufEnd);
+ ICHAR *dataPtr = (ICHAR *)parser->m_dataBuf;
+ convert_res = XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)parser->m_dataBufEnd);
*eventEndPP = s;
- defaultHandler(handlerArg, dataBuf, (int)(dataPtr - (ICHAR *)dataBuf));
+ parser->m_defaultHandler(parser->m_handlerArg, parser->m_dataBuf, (int)(dataPtr - (ICHAR *)parser->m_dataBuf));
*eventPP = s;
} while ((convert_res != XML_CONVERT_COMPLETED) && (convert_res != XML_CONVERT_INPUT_INCOMPLETE));
}
else
- defaultHandler(handlerArg, (XML_Char *)s, (int)((XML_Char *)end - (XML_Char *)s));
+ parser->m_defaultHandler(parser->m_handlerArg, (XML_Char *)s, (int)((XML_Char *)end - (XML_Char *)s));
}
@@ -5423,16 +6005,18 @@ defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *attId, XML_Bool isCdata,
if (type->nDefaultAtts == type->allocDefaultAtts) {
if (type->allocDefaultAtts == 0) {
type->allocDefaultAtts = 8;
- type->defaultAtts = (DEFAULT_ATTRIBUTE *)MALLOC(type->allocDefaultAtts
+ type->defaultAtts = (DEFAULT_ATTRIBUTE *)MALLOC(parser, type->allocDefaultAtts
* sizeof(DEFAULT_ATTRIBUTE));
- if (!type->defaultAtts)
+ if (!type->defaultAtts) {
+ type->allocDefaultAtts = 0;
return 0;
+ }
}
else {
DEFAULT_ATTRIBUTE *temp;
int count = type->allocDefaultAtts * 2;
temp = (DEFAULT_ATTRIBUTE *)
- REALLOC(type->defaultAtts, (count * sizeof(DEFAULT_ATTRIBUTE)));
+ REALLOC(parser, type->defaultAtts, (count * sizeof(DEFAULT_ATTRIBUTE)));
if (temp == NULL)
return 0;
type->allocDefaultAtts = count;
@@ -5452,7 +6036,7 @@ defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *attId, XML_Bool isCdata,
static int
setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *elementType)
{
- DTD * const dtd = _dtd; /* save one level of indirection */
+ DTD * const dtd = parser->m_dtd; /* save one level of indirection */
const XML_Char *name;
for (name = elementType->name; *name; name++) {
if (*name == XML_T(ASCII_COLON)) {
@@ -5483,7 +6067,7 @@ static ATTRIBUTE_ID *
getAttributeId(XML_Parser parser, const ENCODING *enc,
const char *start, const char *end)
{
- DTD * const dtd = _dtd; /* save one level of indirection */
+ DTD * const dtd = parser->m_dtd; /* save one level of indirection */
ATTRIBUTE_ID *id;
const XML_Char *name;
if (!poolAppendChar(&dtd->pool, XML_T('\0')))
@@ -5500,7 +6084,7 @@ getAttributeId(XML_Parser parser, const ENCODING *enc,
poolDiscard(&dtd->pool);
else {
poolFinish(&dtd->pool);
- if (!ns)
+ if (!parser->m_ns)
;
else if (name[0] == XML_T(ASCII_x)
&& name[1] == XML_T(ASCII_m)
@@ -5547,21 +6131,42 @@ getAttributeId(XML_Parser parser, const ENCODING *enc,
static const XML_Char *
getContext(XML_Parser parser)
{
- DTD * const dtd = _dtd; /* save one level of indirection */
+ DTD * const dtd = parser->m_dtd; /* save one level of indirection */
HASH_TABLE_ITER iter;
XML_Bool needSep = XML_FALSE;
if (dtd->defaultPrefix.binding) {
int i;
int len;
- if (!poolAppendChar(&tempPool, XML_T(ASCII_EQUALS)))
+ if (!poolAppendChar(&parser->m_tempPool, XML_T(ASCII_EQUALS)))
return NULL;
len = dtd->defaultPrefix.binding->uriLen;
- if (namespaceSeparator)
+ if (parser->m_namespaceSeparator)
len--;
- for (i = 0; i < len; i++)
- if (!poolAppendChar(&tempPool, dtd->defaultPrefix.binding->uri[i]))
- return NULL;
+ for (i = 0; i < len; i++) {
+ if (!poolAppendChar(&parser->m_tempPool, dtd->defaultPrefix.binding->uri[i])) {
+ /* Because of memory caching, I don't believe this line can be
+ * executed.
+ *
+ * This is part of a loop copying the default prefix binding
+ * URI into the parser's temporary string pool. Previously,
+ * that URI was copied into the same string pool, with a
+ * terminating NUL character, as part of setContext(). When
+ * the pool was cleared, that leaves a block definitely big
+ * enough to hold the URI on the free block list of the pool.
+ * The URI copy in getContext() therefore cannot run out of
+ * memory.
+ *
+ * If the pool is used between the setContext() and
+ * getContext() calls, the worst it can do is leave a bigger
+ * block on the front of the free list. Given that this is
+ * all somewhat inobvious and program logic can be changed, we
+ * don't delete the line but we do exclude it from the test
+ * coverage statistics.
+ */
+ return NULL; /* LCOV_EXCL_LINE */
+ }
+ }
needSep = XML_TRUE;
}
@@ -5573,20 +6178,27 @@ getContext(XML_Parser parser)
PREFIX *prefix = (PREFIX *)hashTableIterNext(&iter);
if (!prefix)
break;
- if (!prefix->binding)
- continue;
- if (needSep && !poolAppendChar(&tempPool, CONTEXT_SEP))
+ if (!prefix->binding) {
+ /* This test appears to be (justifiable) paranoia. There does
+ * not seem to be a way of injecting a prefix without a binding
+ * that doesn't get errored long before this function is called.
+ * The test should remain for safety's sake, so we instead
+ * exclude the following line from the coverage statistics.
+ */
+ continue; /* LCOV_EXCL_LINE */
+ }
+ if (needSep && !poolAppendChar(&parser->m_tempPool, CONTEXT_SEP))
return NULL;
for (s = prefix->name; *s; s++)
- if (!poolAppendChar(&tempPool, *s))
+ if (!poolAppendChar(&parser->m_tempPool, *s))
return NULL;
- if (!poolAppendChar(&tempPool, XML_T(ASCII_EQUALS)))
+ if (!poolAppendChar(&parser->m_tempPool, XML_T(ASCII_EQUALS)))
return NULL;
len = prefix->binding->uriLen;
- if (namespaceSeparator)
+ if (parser->m_namespaceSeparator)
len--;
for (i = 0; i < len; i++)
- if (!poolAppendChar(&tempPool, prefix->binding->uri[i]))
+ if (!poolAppendChar(&parser->m_tempPool, prefix->binding->uri[i]))
return NULL;
needSep = XML_TRUE;
}
@@ -5600,73 +6212,73 @@ getContext(XML_Parser parser)
break;
if (!e->open)
continue;
- if (needSep && !poolAppendChar(&tempPool, CONTEXT_SEP))
+ if (needSep && !poolAppendChar(&parser->m_tempPool, CONTEXT_SEP))
return NULL;
for (s = e->name; *s; s++)
- if (!poolAppendChar(&tempPool, *s))
+ if (!poolAppendChar(&parser->m_tempPool, *s))
return 0;
needSep = XML_TRUE;
}
- if (!poolAppendChar(&tempPool, XML_T('\0')))
+ if (!poolAppendChar(&parser->m_tempPool, XML_T('\0')))
return NULL;
- return tempPool.start;
+ return parser->m_tempPool.start;
}
static XML_Bool
setContext(XML_Parser parser, const XML_Char *context)
{
- DTD * const dtd = _dtd; /* save one level of indirection */
+ DTD * const dtd = parser->m_dtd; /* save one level of indirection */
const XML_Char *s = context;
while (*context != XML_T('\0')) {
if (*s == CONTEXT_SEP || *s == XML_T('\0')) {
ENTITY *e;
- if (!poolAppendChar(&tempPool, XML_T('\0')))
+ if (!poolAppendChar(&parser->m_tempPool, XML_T('\0')))
return XML_FALSE;
- e = (ENTITY *)lookup(parser, &dtd->generalEntities, poolStart(&tempPool), 0);
+ e = (ENTITY *)lookup(parser, &dtd->generalEntities, poolStart(&parser->m_tempPool), 0);
if (e)
e->open = XML_TRUE;
if (*s != XML_T('\0'))
s++;
context = s;
- poolDiscard(&tempPool);
+ poolDiscard(&parser->m_tempPool);
}
else if (*s == XML_T(ASCII_EQUALS)) {
PREFIX *prefix;
- if (poolLength(&tempPool) == 0)
+ if (poolLength(&parser->m_tempPool) == 0)
prefix = &dtd->defaultPrefix;
else {
- if (!poolAppendChar(&tempPool, XML_T('\0')))
+ if (!poolAppendChar(&parser->m_tempPool, XML_T('\0')))
return XML_FALSE;
- prefix = (PREFIX *)lookup(parser, &dtd->prefixes, poolStart(&tempPool),
+ prefix = (PREFIX *)lookup(parser, &dtd->prefixes, poolStart(&parser->m_tempPool),
sizeof(PREFIX));
if (!prefix)
return XML_FALSE;
- if (prefix->name == poolStart(&tempPool)) {
+ if (prefix->name == poolStart(&parser->m_tempPool)) {
prefix->name = poolCopyString(&dtd->pool, prefix->name);
if (!prefix->name)
return XML_FALSE;
}
- poolDiscard(&tempPool);
+ poolDiscard(&parser->m_tempPool);
}
for (context = s + 1;
*context != CONTEXT_SEP && *context != XML_T('\0');
context++)
- if (!poolAppendChar(&tempPool, *context))
+ if (!poolAppendChar(&parser->m_tempPool, *context))
return XML_FALSE;
- if (!poolAppendChar(&tempPool, XML_T('\0')))
+ if (!poolAppendChar(&parser->m_tempPool, XML_T('\0')))
return XML_FALSE;
- if (addBinding(parser, prefix, NULL, poolStart(&tempPool),
- &inheritedBindings) != XML_ERROR_NONE)
+ if (addBinding(parser, prefix, NULL, poolStart(&parser->m_tempPool),
+ &parser->m_inheritedBindings) != XML_ERROR_NONE)
return XML_FALSE;
- poolDiscard(&tempPool);
+ poolDiscard(&parser->m_tempPool);
if (*context != XML_T('\0'))
++context;
s = context;
}
else {
- if (!poolAppendChar(&tempPool, *s))
+ if (!poolAppendChar(&parser->m_tempPool, *s))
return XML_FALSE;
s++;
}
@@ -5877,7 +6489,6 @@ dtdCopy(XML_Parser oldParser, DTD *newDtd, const DTD *oldDtd, const XML_Memory_H
newE->defaultAtts = (DEFAULT_ATTRIBUTE *)
ms->malloc_fcn(oldE->nDefaultAtts * sizeof(DEFAULT_ATTRIBUTE));
if (!newE->defaultAtts) {
- ms->free_fcn(newE);
return 0;
}
}
@@ -6012,13 +6623,32 @@ keyeq(KEY s1, KEY s2)
return XML_FALSE;
}
+static size_t
+keylen(KEY s)
+{
+ size_t len = 0;
+ for (; *s; s++, len++);
+ return len;
+}
+
+static void
+copy_salt_to_sipkey(XML_Parser parser, struct sipkey * key)
+{
+ key->k[0] = 0;
+ key->k[1] = get_hash_secret_salt(parser);
+}
+
static unsigned long FASTCALL
hash(XML_Parser parser, KEY s)
{
- unsigned long h = hash_secret_salt;
- while (*s)
- h = CHAR_HASH(h, *s++);
- return h;
+ struct siphash state;
+ struct sipkey key;
+ (void)sip_tobin;
+ (void)sip24_valid;
+ copy_salt_to_sipkey(parser, &key);
+ sip24_init(&state, &key);
+ sip24_update(&state, s, keylen(s) * sizeof(XML_Char));
+ return (unsigned long)sip24_final(&state);
}
static NAMED *
@@ -6227,8 +6857,20 @@ poolCopyString(STRING_POOL *pool, const XML_Char *s)
static const XML_Char *
poolCopyStringN(STRING_POOL *pool, const XML_Char *s, int n)
{
- if (!pool->ptr && !poolGrow(pool))
- return NULL;
+ if (!pool->ptr && !poolGrow(pool)) {
+ /* The following line is unreachable given the current usage of
+ * poolCopyStringN(). Currently it is called from exactly one
+ * place to copy the text of a simple general entity. By that
+ * point, the name of the entity is already stored in the pool, so
+ * pool->ptr cannot be NULL.
+ *
+ * If poolCopyStringN() is used elsewhere as it well might be,
+ * this line may well become executable again. Regardless, this
+ * sort of check shouldn't be removed lightly, so we just exclude
+ * it from the coverage statistics.
+ */
+ return NULL; /* LCOV_EXCL_LINE */
+ }
for (; n > 0; --n, s++) {
if (!poolAppendChar(pool, *s))
return NULL;
@@ -6261,6 +6903,35 @@ poolStoreString(STRING_POOL *pool, const ENCODING *enc,
return pool->start;
}
+static size_t
+poolBytesToAllocateFor(int blockSize)
+{
+ /* Unprotected math would be:
+ ** return offsetof(BLOCK, s) + blockSize * sizeof(XML_Char);
+ **
+ ** Detect overflow, avoiding _signed_ overflow undefined behavior
+ ** For a + b * c we check b * c in isolation first, so that addition of a
+ ** on top has no chance of making us accept a small non-negative number
+ */
+ const size_t stretch = sizeof(XML_Char); /* can be 4 bytes */
+
+ if (blockSize <= 0)
+ return 0;
+
+ if (blockSize > (int)(INT_MAX / stretch))
+ return 0;
+
+ {
+ const int stretchedBlockSize = blockSize * (int)stretch;
+ const int bytesToAllocate = (int)(
+ offsetof(BLOCK, s) + (unsigned)stretchedBlockSize);
+ if (bytesToAllocate < 0)
+ return 0;
+
+ return (size_t)bytesToAllocate;
+ }
+}
+
static XML_Bool FASTCALL
poolGrow(STRING_POOL *pool)
{
@@ -6290,35 +6961,69 @@ poolGrow(STRING_POOL *pool)
if (pool->blocks && pool->start == pool->blocks->s) {
BLOCK *temp;
int blockSize = (int)((unsigned)(pool->end - pool->start)*2U);
+ size_t bytesToAllocate;
+
+ /* NOTE: Needs to be calculated prior to calling `realloc`
+ to avoid dangling pointers: */
+ const ptrdiff_t offsetInsideBlock = pool->ptr - pool->start;
+
+ if (blockSize < 0) {
+ /* This condition traps a situation where either more than
+ * INT_MAX/2 bytes have already been allocated. This isn't
+ * readily testable, since it is unlikely that an average
+ * machine will have that much memory, so we exclude it from the
+ * coverage statistics.
+ */
+ return XML_FALSE; /* LCOV_EXCL_LINE */
+ }
- if (blockSize < 0)
+ bytesToAllocate = poolBytesToAllocateFor(blockSize);
+ if (bytesToAllocate == 0)
return XML_FALSE;
temp = (BLOCK *)
- pool->mem->realloc_fcn(pool->blocks,
- (offsetof(BLOCK, s)
- + blockSize * sizeof(XML_Char)));
+ pool->mem->realloc_fcn(pool->blocks, (unsigned)bytesToAllocate);
if (temp == NULL)
return XML_FALSE;
pool->blocks = temp;
pool->blocks->size = blockSize;
- pool->ptr = pool->blocks->s + (pool->ptr - pool->start);
+ pool->ptr = pool->blocks->s + offsetInsideBlock;
pool->start = pool->blocks->s;
pool->end = pool->start + blockSize;
}
else {
BLOCK *tem;
int blockSize = (int)(pool->end - pool->start);
-
- if (blockSize < 0)
- return XML_FALSE;
+ size_t bytesToAllocate;
+
+ if (blockSize < 0) {
+ /* This condition traps a situation where either more than
+ * INT_MAX bytes have already been allocated (which is prevented
+ * by various pieces of program logic, not least this one, never
+ * mind the unlikelihood of actually having that much memory) or
+ * the pool control fields have been corrupted (which could
+ * conceivably happen in an extremely buggy user handler
+ * function). Either way it isn't readily testable, so we
+ * exclude it from the coverage statistics.
+ */
+ return XML_FALSE; /* LCOV_EXCL_LINE */
+ }
if (blockSize < INIT_BLOCK_SIZE)
blockSize = INIT_BLOCK_SIZE;
- else
+ else {
+ /* Detect overflow, avoiding _signed_ overflow undefined behavior */
+ if ((int)((unsigned)blockSize * 2U) < 0) {
+ return XML_FALSE;
+ }
blockSize *= 2;
- tem = (BLOCK *)pool->mem->malloc_fcn(offsetof(BLOCK, s)
- + blockSize * sizeof(XML_Char));
+ }
+
+ bytesToAllocate = poolBytesToAllocateFor(blockSize);
+ if (bytesToAllocate == 0)
+ return XML_FALSE;
+
+ tem = (BLOCK *)pool->mem->malloc_fcn(bytesToAllocate);
if (!tem)
return XML_FALSE;
tem->size = blockSize;
@@ -6337,12 +7042,12 @@ poolGrow(STRING_POOL *pool)
static int FASTCALL
nextScaffoldPart(XML_Parser parser)
{
- DTD * const dtd = _dtd; /* save one level of indirection */
+ DTD * const dtd = parser->m_dtd; /* save one level of indirection */
CONTENT_SCAFFOLD * me;
int next;
if (!dtd->scaffIndex) {
- dtd->scaffIndex = (int *)MALLOC(groupSize * sizeof(int));
+ dtd->scaffIndex = (int *)MALLOC(parser, parser->m_groupSize * sizeof(int));
if (!dtd->scaffIndex)
return -1;
dtd->scaffIndex[0] = 0;
@@ -6352,13 +7057,13 @@ nextScaffoldPart(XML_Parser parser)
CONTENT_SCAFFOLD *temp;
if (dtd->scaffold) {
temp = (CONTENT_SCAFFOLD *)
- REALLOC(dtd->scaffold, dtd->scaffSize * 2 * sizeof(CONTENT_SCAFFOLD));
+ REALLOC(parser, dtd->scaffold, dtd->scaffSize * 2 * sizeof(CONTENT_SCAFFOLD));
if (temp == NULL)
return -1;
dtd->scaffSize *= 2;
}
else {
- temp = (CONTENT_SCAFFOLD *)MALLOC(INIT_SCAFFOLD_ELEMENTS
+ temp = (CONTENT_SCAFFOLD *)MALLOC(parser, INIT_SCAFFOLD_ELEMENTS
* sizeof(CONTENT_SCAFFOLD));
if (temp == NULL)
return -1;
@@ -6389,7 +7094,7 @@ build_node(XML_Parser parser,
XML_Content **contpos,
XML_Char **strpos)
{
- DTD * const dtd = _dtd; /* save one level of indirection */
+ DTD * const dtd = parser->m_dtd; /* save one level of indirection */
dest->type = dtd->scaffold[src_node].type;
dest->quant = dtd->scaffold[src_node].quant;
if (dest->type == XML_CTYPE_NAME) {
@@ -6423,14 +7128,14 @@ build_node(XML_Parser parser,
static XML_Content *
build_model (XML_Parser parser)
{
- DTD * const dtd = _dtd; /* save one level of indirection */
+ DTD * const dtd = parser->m_dtd; /* save one level of indirection */
XML_Content *ret;
XML_Content *cpos;
XML_Char * str;
int allocsize = (dtd->scaffCount * sizeof(XML_Content)
+ (dtd->contentStringLen * sizeof(XML_Char)));
- ret = (XML_Content *)MALLOC(allocsize);
+ ret = (XML_Content *)MALLOC(parser, allocsize);
if (!ret)
return NULL;
@@ -6447,7 +7152,7 @@ getElementType(XML_Parser parser,
const char *ptr,
const char *end)
{
- DTD * const dtd = _dtd; /* save one level of indirection */
+ DTD * const dtd = parser->m_dtd; /* save one level of indirection */
const XML_Char *name = poolStoreString(&dtd->pool, enc, ptr, end);
ELEMENT_TYPE *ret;
@@ -6465,3 +7170,26 @@ getElementType(XML_Parser parser,
}
return ret;
}
+
+static XML_Char *
+copyString(const XML_Char *s,
+ const XML_Memory_Handling_Suite *memsuite)
+{
+ int charsRequired = 0;
+ XML_Char *result;
+
+ /* First determine how long the string is */
+ while (s[charsRequired] != 0) {
+ charsRequired++;
+ }
+ /* Include the terminator */
+ charsRequired++;
+
+ /* Now allocate space for the copy */
+ result = memsuite->malloc_fcn(charsRequired * sizeof(XML_Char));
+ if (result == NULL)
+ return NULL;
+ /* Copy the original into place */
+ memcpy(result, s, charsRequired * sizeof(XML_Char));
+ return result;
+}
diff --git a/lib/xmlrole.c b/lib/xmlrole.c
index 8a68e20..708507d 100644
--- a/lib/xmlrole.c
+++ b/lib/xmlrole.c
@@ -1,22 +1,44 @@
-/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
- See the file COPYING for copying permission.
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
#include <stddef.h>
-#ifdef COMPILED_FROM_DSP
+#ifdef _WIN32
#include "winconfig.h"
-#elif defined(MACOS_CLASSIC)
-#include "macconfig.h"
-#elif defined(__amigaos__)
-#include "amigaconfig.h"
-#elif defined(__WATCOMC__)
-#include "watcomconfig.h"
#else
#ifdef HAVE_EXPAT_CONFIG_H
#include <expat_config.h>
#endif
-#endif /* ndef COMPILED_FROM_DSP */
+#endif /* ndef _WIN32 */
#include "expat_external.h"
#include "internal.h"
@@ -176,7 +198,14 @@ prolog1(PROLOG_STATE *state,
case XML_TOK_COMMENT:
return XML_ROLE_COMMENT;
case XML_TOK_BOM:
- return XML_ROLE_NONE;
+ /* This case can never arise. To reach this role function, the
+ * parse must have passed through prolog0 and therefore have had
+ * some form of input, even if only a space. At that point, a
+ * byte order mark is no longer a valid character (though
+ * technically it should be interpreted as a non-breaking space),
+ * so will be rejected by the tokenizing stages.
+ */
+ return XML_ROLE_NONE; /* LCOV_EXCL_LINE */
case XML_TOK_DECL_OPEN:
if (!XmlNameMatchesAscii(enc,
ptr + 2 * MIN_BYTES_PER_CHAR(enc),
@@ -1291,6 +1320,26 @@ declClose(PROLOG_STATE *state,
return common(state, tok);
}
+/* This function will only be invoked if the internal logic of the
+ * parser has broken down. It is used in two cases:
+ *
+ * 1: When the XML prolog has been finished. At this point the
+ * processor (the parser level above these role handlers) should
+ * switch from prologProcessor to contentProcessor and reinitialise
+ * the handler function.
+ *
+ * 2: When an error has been detected (via common() below). At this
+ * point again the processor should be switched to errorProcessor,
+ * which will never call a handler.
+ *
+ * The result of this is that error() can only be called if the
+ * processor switch failed to happen, which is an internal error and
+ * therefore we shouldn't be able to provoke it simply by using the
+ * library. It is a necessary backstop, however, so we merely exclude
+ * it from the coverage statistics.
+ *
+ * LCOV_EXCL_START
+ */
static int PTRCALL
error(PROLOG_STATE *UNUSED_P(state),
int UNUSED_P(tok),
@@ -1300,6 +1349,7 @@ error(PROLOG_STATE *UNUSED_P(state),
{
return XML_ROLE_NONE;
}
+/* LCOV_EXCL_STOP */
static int FASTCALL
common(PROLOG_STATE *state, int tok)
diff --git a/lib/xmlrole.h b/lib/xmlrole.h
index 4dd9f06..e5f048e 100644
--- a/lib/xmlrole.h
+++ b/lib/xmlrole.h
@@ -1,5 +1,33 @@
-/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
- See the file COPYING for copying permission.
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
#ifndef XmlRole_INCLUDED
diff --git a/lib/xmltok.c b/lib/xmltok.c
index daa3565..6b415d8 100644
--- a/lib/xmltok.c
+++ b/lib/xmltok.c
@@ -1,22 +1,55 @@
-/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
- See the file COPYING for copying permission.
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
#include <stddef.h>
+#include <string.h> /* memcpy */
-#ifdef COMPILED_FROM_DSP
+#if defined(_MSC_VER) && (_MSC_VER <= 1700)
+ /* for vs2012/11.0/1700 and earlier Visual Studio compilers */
+# define bool int
+# define false 0
+# define true 1
+#else
+# include <stdbool.h>
+#endif
+
+
+#ifdef _WIN32
#include "winconfig.h"
-#elif defined(MACOS_CLASSIC)
-#include "macconfig.h"
-#elif defined(__amigaos__)
-#include "amigaconfig.h"
-#elif defined(__WATCOMC__)
-#include "watcomconfig.h"
#else
#ifdef HAVE_EXPAT_CONFIG_H
#include <expat_config.h>
#endif
-#endif /* ndef COMPILED_FROM_DSP */
+#endif /* ndef _WIN32 */
#include "expat_external.h"
#include "internal.h"
@@ -33,7 +66,6 @@
{ PREFIX(prologTok), PREFIX(contentTok), \
PREFIX(cdataSectionTok) IGNORE_SECTION_TOK_VTABLE }, \
{ PREFIX(attributeValueTok), PREFIX(entityValueTok) }, \
- PREFIX(sameName), \
PREFIX(nameMatchesAscii), \
PREFIX(nameLength), \
PREFIX(skipS), \
@@ -330,7 +362,7 @@ enum { /* UTF8_cvalN is value of masked first byte of N byte sequence */
};
void
-align_limit_to_full_utf8_characters(const char * from, const char ** fromLimRef)
+_INTERNAL_trim_to_complete_utf8_characters(const char * from, const char ** fromLimRef)
{
const char * fromLim = *fromLimRef;
size_t walked = 0;
@@ -369,24 +401,39 @@ utf8_toUtf8(const ENCODING *UNUSED_P(enc),
const char **fromP, const char *fromLim,
char **toP, const char *toLim)
{
- enum XML_Convert_Result res = XML_CONVERT_COMPLETED;
- char *to;
- const char *from;
- if (fromLim - *fromP > toLim - *toP) {
- /* Avoid copying partial characters. */
- res = XML_CONVERT_OUTPUT_EXHAUSTED;
- fromLim = *fromP + (toLim - *toP);
- align_limit_to_full_utf8_characters(*fromP, &fromLim);
+ bool input_incomplete = false;
+ bool output_exhausted = false;
+
+ /* Avoid copying partial characters (due to limited space). */
+ const ptrdiff_t bytesAvailable = fromLim - *fromP;
+ const ptrdiff_t bytesStorable = toLim - *toP;
+ if (bytesAvailable > bytesStorable) {
+ fromLim = *fromP + bytesStorable;
+ output_exhausted = true;
+ }
+
+ /* Avoid copying partial characters (from incomplete input). */
+ {
+ const char * const fromLimBefore = fromLim;
+ _INTERNAL_trim_to_complete_utf8_characters(*fromP, &fromLim);
+ if (fromLim < fromLimBefore) {
+ input_incomplete = true;
+ }
+ }
+
+ {
+ const ptrdiff_t bytesToCopy = fromLim - *fromP;
+ memcpy(*toP, *fromP, bytesToCopy);
+ *fromP += bytesToCopy;
+ *toP += bytesToCopy;
}
- for (to = *toP, from = *fromP; (from < fromLim) && (to < toLim); from++, to++)
- *to = *from;
- *fromP = from;
- *toP = to;
- if ((to == toLim) && (from < fromLim))
+ if (output_exhausted) /* needs to go first */
return XML_CONVERT_OUTPUT_EXHAUSTED;
+ else if (input_incomplete)
+ return XML_CONVERT_INPUT_INCOMPLETE;
else
- return res;
+ return XML_CONVERT_COMPLETED;
}
static enum XML_Convert_Result PTRCALL
@@ -402,7 +449,7 @@ utf8_toUtf16(const ENCODING *enc,
case BT_LEAD2:
if (fromLim - from < 2) {
res = XML_CONVERT_INPUT_INCOMPLETE;
- break;
+ goto after;
}
*to++ = (unsigned short)(((from[0] & 0x1f) << 6) | (from[1] & 0x3f));
from += 2;
@@ -410,7 +457,7 @@ utf8_toUtf16(const ENCODING *enc,
case BT_LEAD3:
if (fromLim - from < 3) {
res = XML_CONVERT_INPUT_INCOMPLETE;
- break;
+ goto after;
}
*to++ = (unsigned short)(((from[0] & 0xf) << 12)
| ((from[1] & 0x3f) << 6) | (from[2] & 0x3f));
@@ -441,6 +488,8 @@ utf8_toUtf16(const ENCODING *enc,
break;
}
}
+ if (from < fromLim)
+ res = XML_CONVERT_OUTPUT_EXHAUSTED;
after:
*fromP = from;
*toP = to;
@@ -1023,7 +1072,11 @@ streqci(const char *s1, const char *s2)
if (ASCII_a <= c1 && c1 <= ASCII_z)
c1 += ASCII_A - ASCII_a;
if (ASCII_a <= c2 && c2 <= ASCII_z)
- c2 += ASCII_A - ASCII_a;
+ /* The following line will never get executed. streqci() is
+ * only called from two places, both of which guarantee to put
+ * upper-case strings into s2.
+ */
+ c2 += ASCII_A - ASCII_a; /* LCOV_EXCL_LINE */
if (c1 != c2)
return 0;
if (!c1)
@@ -1295,7 +1348,7 @@ XmlUtf8Encode(int c, char *buf)
};
if (c < 0)
- return 0;
+ return 0; /* LCOV_EXCL_LINE: this case is always eliminated beforehand */
if (c < min2) {
buf[0] = (char)(c | UTF8_cval1);
return 1;
@@ -1318,7 +1371,7 @@ XmlUtf8Encode(int c, char *buf)
buf[3] = (char)((c & 0x3f) | 0x80);
return 4;
}
- return 0;
+ return 0; /* LCOV_EXCL_LINE: this case too is eliminated before calling */
}
int FASTCALL
@@ -1411,9 +1464,8 @@ unknown_toUtf8(const ENCODING *enc,
return XML_CONVERT_OUTPUT_EXHAUSTED;
(*fromP)++;
}
- do {
- *(*toP)++ = *utf8++;
- } while (--n != 0);
+ memcpy(*toP, utf8, n);
+ *toP += n;
}
}
@@ -1469,6 +1521,9 @@ XmlInitUnknownEncoding(void *mem,
else if (c < 0) {
if (c < -4)
return 0;
+ /* Multi-byte sequences need a converter function */
+ if (!convert)
+ return 0;
e->normal.type[i] = (unsigned char)(BT_LEAD2 - (c + 2));
e->utf8[i][0] = 0;
e->utf16[i] = 0;
diff --git a/lib/xmltok.h b/lib/xmltok.h
index 752007e..50926f3 100644
--- a/lib/xmltok.h
+++ b/lib/xmltok.h
@@ -1,5 +1,33 @@
-/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
- See the file COPYING for copying permission.
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
#ifndef XmlTok_INCLUDED
@@ -139,9 +167,6 @@ enum XML_Convert_Result {
struct encoding {
SCANNER scanners[XML_N_STATES];
SCANNER literalScanners[XML_N_LITERAL_TYPES];
- int (PTRCALL *sameName)(const ENCODING *,
- const char *,
- const char *);
int (PTRCALL *nameMatchesAscii)(const ENCODING *,
const char *,
const char *,
@@ -232,8 +257,6 @@ struct encoding {
#define XmlEntityValueTok(enc, ptr, end, nextTokPtr) \
XmlLiteralTok(enc, XML_ENTITY_VALUE_LITERAL, ptr, end, nextTokPtr)
-#define XmlSameName(enc, ptr1, ptr2) (((enc)->sameName)(enc, ptr1, ptr2))
-
#define XmlNameMatchesAscii(enc, ptr1, end1, ptr2) \
(((enc)->nameMatchesAscii)(enc, ptr1, end1, ptr2))
diff --git a/lib/xmltok_impl.c b/lib/xmltok_impl.c
index 5f779c0..0403dd3 100644
--- a/lib/xmltok_impl.c
+++ b/lib/xmltok_impl.c
@@ -1,8 +1,35 @@
-/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
- See the file COPYING for copying permission.
+/* This file is included!
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
-/* This file is included! */
#ifdef XML_TOK_IMPL_C
#ifndef IS_INVALID_CHAR
@@ -1198,8 +1225,14 @@ PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr,
const char *start;
if (ptr >= end)
return XML_TOK_NONE;
- else if (! HAS_CHAR(enc, ptr, end))
- return XML_TOK_PARTIAL;
+ else if (! HAS_CHAR(enc, ptr, end)) {
+ /* This line cannot be executed. The incoming data has already
+ * been tokenized once, so incomplete characters like this have
+ * already been eliminated from the input. Retaining the paranoia
+ * check is still valuable, however.
+ */
+ return XML_TOK_PARTIAL; /* LCOV_EXCL_LINE */
+ }
start = ptr;
while (HAS_CHAR(enc, ptr, end)) {
switch (BYTE_TYPE(enc, ptr)) {
@@ -1258,8 +1291,14 @@ PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr,
const char *start;
if (ptr >= end)
return XML_TOK_NONE;
- else if (! HAS_CHAR(enc, ptr, end))
- return XML_TOK_PARTIAL;
+ else if (! HAS_CHAR(enc, ptr, end)) {
+ /* This line cannot be executed. The incoming data has already
+ * been tokenized once, so incomplete characters like this have
+ * already been eliminated from the input. Retaining the paranoia
+ * check is still valuable, however.
+ */
+ return XML_TOK_PARTIAL; /* LCOV_EXCL_LINE */
+ }
start = ptr;
while (HAS_CHAR(enc, ptr, end)) {
switch (BYTE_TYPE(enc, ptr)) {
@@ -1615,76 +1654,18 @@ PREFIX(predefinedEntityName)(const ENCODING *UNUSED_P(enc), const char *ptr,
}
static int PTRCALL
-PREFIX(sameName)(const ENCODING *enc, const char *ptr1, const char *ptr2)
-{
- for (;;) {
- switch (BYTE_TYPE(enc, ptr1)) {
-#define LEAD_CASE(n) \
- case BT_LEAD ## n: \
- if (*ptr1++ != *ptr2++) \
- return 0;
- LEAD_CASE(4) LEAD_CASE(3) LEAD_CASE(2)
-#undef LEAD_CASE
- /* fall through */
- if (*ptr1++ != *ptr2++)
- return 0;
- break;
- case BT_NONASCII:
- case BT_NMSTRT:
-#ifdef XML_NS
- case BT_COLON:
-#endif
- case BT_HEX:
- case BT_DIGIT:
- case BT_NAME:
- case BT_MINUS:
- if (*ptr2++ != *ptr1++)
- return 0;
- if (MINBPC(enc) > 1) {
- if (*ptr2++ != *ptr1++)
- return 0;
- if (MINBPC(enc) > 2) {
- if (*ptr2++ != *ptr1++)
- return 0;
- if (MINBPC(enc) > 3) {
- if (*ptr2++ != *ptr1++)
- return 0;
- }
- }
- }
- break;
- default:
- if (MINBPC(enc) == 1 && *ptr1 == *ptr2)
- return 1;
- switch (BYTE_TYPE(enc, ptr2)) {
- case BT_LEAD2:
- case BT_LEAD3:
- case BT_LEAD4:
- case BT_NONASCII:
- case BT_NMSTRT:
-#ifdef XML_NS
- case BT_COLON:
-#endif
- case BT_HEX:
- case BT_DIGIT:
- case BT_NAME:
- case BT_MINUS:
- return 0;
- default:
- return 1;
- }
- }
- }
- /* not reached */
-}
-
-static int PTRCALL
PREFIX(nameMatchesAscii)(const ENCODING *UNUSED_P(enc), const char *ptr1,
const char *end1, const char *ptr2)
{
for (; *ptr2; ptr1 += MINBPC(enc), ptr2++) {
- if (end1 - ptr1 < MINBPC(enc))
- return 0;
+ if (end1 - ptr1 < MINBPC(enc)) {
+ /* This line cannot be executed. THe incoming data has already
+ * been tokenized once, so imcomplete characters like this have
+ * already been eliminated from the input. Retaining the
+ * paranoia check is still valuable, however.
+ */
+ return 0; /* LCOV_EXCL_LINE */
+ }
if (!CHAR_MATCHES(enc, ptr1, *ptr2))
return 0;
}
diff --git a/lib/xmltok_impl.h b/lib/xmltok_impl.h
index da0ea60..a6420f4 100644
--- a/lib/xmltok_impl.h
+++ b/lib/xmltok_impl.h
@@ -1,6 +1,33 @@
/*
-Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
-See the file COPYING for copying permission.
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
enum {
diff --git a/lib/xmltok_ns.c b/lib/xmltok_ns.c
index c3b88fd..23d31e8 100644
--- a/lib/xmltok_ns.c
+++ b/lib/xmltok_ns.c
@@ -1,8 +1,35 @@
-/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd
- See the file COPYING for copying permission.
+/* This file is included!
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
-/* This file is included! */
#ifdef XML_TOK_NS_C
const ENCODING *
diff --git a/memory-sanitizer-blacklist.txt b/memory-sanitizer-blacklist.txt
new file mode 100644
index 0000000..166e6a1
--- /dev/null
+++ b/memory-sanitizer-blacklist.txt
@@ -0,0 +1,6 @@
+# Line "hash_secret_salt = generate_hash_secret_salt(parser);"
+# is mis-reported as use-of-uninitialized-value because
+# its call to writeRandomBytes_getrandom uses syscall
+# SYS_getrandom and MemorySanitizer does not seem to understand that
+# as writing bytes to that memory (which it does).
+fun:startParsing
diff --git a/qa.sh b/qa.sh
new file mode 100755
index 0000000..2a77f2c
--- /dev/null
+++ b/qa.sh
@@ -0,0 +1,130 @@
+#! /bin/bash
+# Copyright (C) 2016 Sebastian Pipping <sebastian@pipping.org>
+# Licensed under MIT license
+
+set -o nounset
+
+: ${GCC_CC:=gcc}
+: ${GCC_CXX:=g++}
+: ${CLANG_CC:=clang}
+: ${CLANG_CXX:=clang++}
+
+: ${AR:=ar}
+: ${CC:="${CLANG_CC}"}
+: ${CXX:="${CLANG_CXX}"}
+: ${LD:=ld}
+: ${MAKE:=make}
+
+: ${BASE_COMPILE_FLAGS:="-pipe -Wall -Wextra -pedantic -Wno-overlength-strings -Wno-long-long"}
+
+ANNOUNCE() {
+ local open='\e[1m'
+ local close='\e[0m'
+
+ echo -e -n "${open}"
+ echo -n "# $*"
+ echo -e "${close}"
+}
+
+RUN() {
+ ANNOUNCE "$@"
+ env "$@"
+}
+
+main() {
+ local mode="${1:-}"
+ shift
+
+ local RUNENV
+ local BASE_COMPILE_FLAGS="${BASE_COMPILE_FLAGS}"
+
+ case "${mode}" in
+ address)
+ # http://clang.llvm.org/docs/AddressSanitizer.html
+ local CC="${CLANG_CC}"
+ local CXX="${CLANG_CXX}"
+ BASE_COMPILE_FLAGS+=" -g -fsanitize=address -fno-omit-frame-pointer"
+ ;;
+ coverage | lib-coverage | app-coverage)
+ local CC="${GCC_CC}"
+ local CXX="${GCC_CXX}"
+ BASE_COMPILE_FLAGS+=" --coverage --no-inline"
+ ;;
+ egypt)
+ BASE_COMPILE_FLAGS+=" -fdump-rtl-expand"
+ ;;
+ memory)
+ # http://clang.llvm.org/docs/MemorySanitizer.html
+ BASE_COMPILE_FLAGS+=" -fsanitize=memory -fno-omit-frame-pointer -g -O2 -fsanitize-memory-track-origins -fsanitize-blacklist=$PWD/memory-sanitizer-blacklist.txt"
+ ;;
+ ncc)
+ # http://students.ceid.upatras.gr/~sxanth/ncc/
+ local CC="ncc -ncgcc -ncld -ncfabs"
+ local AR=nccar
+ local LD=nccld
+ BASE_COMPILE_FLAGS+=" -fPIC"
+ ;;
+ undefined)
+ # http://clang.llvm.org/docs/UndefinedBehaviorSanitizer.html
+ BASE_COMPILE_FLAGS+=" -fsanitize=undefined"
+ export UBSAN_OPTIONS=print_stacktrace=1
+ ;;
+ *)
+ echo "Usage:" 1>&2
+ echo " ${0##*/} (address|coverage|lib-coverage|app-coverage|egypt|memory|ncc|undefined)" 1>&2
+ exit 1
+ ;;
+ esac
+
+ local CFLAGS="-std=c89 ${BASE_COMPILE_FLAGS} ${CFLAGS:-}"
+ local CXXFLAGS="-std=c++98 ${BASE_COMPILE_FLAGS} ${CXXFLAGS:-}"
+
+ (
+ set -e
+
+ RUN CC="${CC}" CFLAGS="${CFLAGS}" \
+ CXX="${CXX}" CXXFLAGS="${CXXFLAGS}" \
+ AR="${AR}" \
+ LD="${LD}" \
+ ./configure "$@"
+
+ RUN "${MAKE}" clean all
+
+ case "${mode}" in
+ egypt|ncc)
+ ;;
+ *)
+ RUN "${MAKE}" check run-xmltest
+ ;;
+ esac
+ )
+ [[ $? -ne 0 ]] && exit 1
+
+ case "${mode}" in
+ coverage)
+ find -name '*.gcda' | sort | xargs gcov
+ ;;
+ lib-coverage)
+ find lib -name '*.gcda' | sort | xargs gcov
+ ;;
+ app-coverage)
+ find lib xmlwf -name '*.gcda' | sort | xargs gcov
+ ;;
+ egypt)
+ local DOT_FORMAT="${DOT_FORMAT:-svg}"
+ local o="callgraph.${DOT_FORMAT}"
+ ANNOUNCE "egypt ...... | dot ...... > ${o}"
+ find -name '*.expand' \
+ | sort \
+ | xargs -r egypt \
+ | unflatten -c 20 \
+ | dot -T${DOT_FORMAT} -Grankdir=LR \
+ > "${o}"
+ ;;
+ ncc)
+ RUN nccnav ./.libs/libexpat.a.nccout
+ ;;
+ esac
+}
+
+main "$@"
diff --git a/run.sh.in b/run.sh.in
new file mode 100644
index 0000000..ff3fb36
--- /dev/null
+++ b/run.sh.in
@@ -0,0 +1,12 @@
+#! /usr/bin/env bash
+# Copyright (C) 2017 Expat development team
+# Licensed under the MIT license
+
+case "@host@" in
+*-mingw*)
+ exec wine "$@"
+ ;;
+*)
+ exec "$@"
+ ;;
+esac
diff --git a/test-driver-wrapper.sh b/test-driver-wrapper.sh
new file mode 100755
index 0000000..30b34d5
--- /dev/null
+++ b/test-driver-wrapper.sh
@@ -0,0 +1,43 @@
+#! /bin/bash
+# __ __ _
+# ___\ \/ /_ __ __ _| |_
+# / _ \\ /| '_ \ / _` | __|
+# | __// \| |_) | (_| | |_
+# \___/_/\_\ .__/ \__,_|\__|
+# |_| XML parser
+#
+# Copyright (c) 2017 Expat development team
+# Licensed under the MIT license:
+#
+# Permission is hereby granted, free of charge, to any person obtaining
+# a copy of this software and associated documentation files (the
+# "Software"), to deal in the Software without restriction, including
+# without limitation the rights to use, copy, modify, merge, publish,
+# distribute, sublicense, and/or sell copies of the Software, and to permit
+# persons to whom the Software is furnished to do so, subject to the
+# following conditions:
+#
+# The above copyright notice and this permission notice shall be included
+# in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+# NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+# DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+# OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+# USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+set -e
+top_srcdir="$(dirname "$(type -p "$0")")"
+top_builddir=..
+
+# Suck up all dash-dash test-driver arguments
+test_driver_args=()
+while [[ ${1} != '--' ]]; do
+ test_driver_args=( "${test_driver_args[@]}" "${1}" )
+ shift
+done
+shift # drop "--"
+
+exec "${top_srcdir}"/conftools/test-driver "${test_driver_args[@]}" "${top_builddir}"/run.sh "$@"
diff --git a/tests/.gitignore b/tests/.gitignore
new file mode 100644
index 0000000..410d083
--- /dev/null
+++ b/tests/.gitignore
@@ -0,0 +1,9 @@
+/out
+/xmlconf
+/xmltest.log
+Makefile
+runtests
+runtestspp
+xmlts.zip
+XML-Test-Suite
+.libs
diff --git a/tests/Makefile.am b/tests/Makefile.am
new file mode 100644
index 0000000..742ed43
--- /dev/null
+++ b/tests/Makefile.am
@@ -0,0 +1,66 @@
+#
+# __ __ _
+# ___\ \/ /_ __ __ _| |_
+# / _ \\ /| '_ \ / _` | __|
+# | __// \| |_) | (_| | |_
+# \___/_/\_\ .__/ \__,_|\__|
+# |_| XML parser
+#
+# Copyright (c) 2017 Expat development team
+# Licensed under the MIT license:
+#
+# Permission is hereby granted, free of charge, to any person obtaining
+# a copy of this software and associated documentation files (the
+# "Software"), to deal in the Software without restriction, including
+# without limitation the rights to use, copy, modify, merge, publish,
+# distribute, sublicense, and/or sell copies of the Software, and to permit
+# persons to whom the Software is furnished to do so, subject to the
+# following conditions:
+#
+# The above copyright notice and this permission notice shall be included
+# in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+# NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+# DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+# OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+# USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+SUBDIRS = . benchmark
+
+AM_CPPFLAGS = -I$(srcdir)/../lib
+
+noinst_LIBRARIES = libruntests.a
+
+check_PROGRAMS = runtests runtestspp
+TESTS = runtests runtestspp
+
+# To support MinGW and Non-MinGW at the same time:
+LOG_DRIVER = $(srcdir)/../test-driver-wrapper.sh
+
+libruntests_a_SOURCES = \
+ chardata.c \
+ structdata.c \
+ memcheck.c \
+ minicheck.c
+
+runtests_SOURCES = \
+ runtests.c
+
+runtestspp_SOURCES = \
+ runtestspp.cpp
+
+runtests_LDADD = libruntests.a ../lib/libexpat.la
+runtestspp_LDADD = libruntests.a ../lib/libexpat.la
+
+EXTRA_DIST = \
+ chardata.h \
+ structdata.h \
+ minicheck.h \
+ memcheck.h \
+ README.txt \
+ udiffer.py \
+ xmltest.log.expected \
+ xmltest.sh
diff --git a/tests/benchmark/.gitignore b/tests/benchmark/.gitignore
new file mode 100644
index 0000000..f9c8c38
--- /dev/null
+++ b/tests/benchmark/.gitignore
@@ -0,0 +1 @@
+/benchmark
diff --git a/tests/benchmark/Makefile.am b/tests/benchmark/Makefile.am
new file mode 100644
index 0000000..f4d7a8e
--- /dev/null
+++ b/tests/benchmark/Makefile.am
@@ -0,0 +1,40 @@
+#
+# __ __ _
+# ___\ \/ /_ __ __ _| |_
+# / _ \\ /| '_ \ / _` | __|
+# | __// \| |_) | (_| | |_
+# \___/_/\_\ .__/ \__,_|\__|
+# |_| XML parser
+#
+# Copyright (c) 2017 Expat development team
+# Licensed under the MIT license:
+#
+# Permission is hereby granted, free of charge, to any person obtaining
+# a copy of this software and associated documentation files (the
+# "Software"), to deal in the Software without restriction, including
+# without limitation the rights to use, copy, modify, merge, publish,
+# distribute, sublicense, and/or sell copies of the Software, and to permit
+# persons to whom the Software is furnished to do so, subject to the
+# following conditions:
+#
+# The above copyright notice and this permission notice shall be included
+# in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+# NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+# DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+# OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+# USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+AM_CPPFLAGS = -I$(srcdir)/../../lib
+
+noinst_PROGRAMS = benchmark
+
+benchmark_SOURCES = benchmark.c
+
+benchmark_LDADD = ../../lib/libexpat.la
+
+EXTRA_DIST = \
+ README.txt
diff --git a/tests/benchmark/benchmark.c b/tests/benchmark/benchmark.c
index 0f0fd18..0c91554 100644
--- a/tests/benchmark/benchmark.c
+++ b/tests/benchmark/benchmark.c
@@ -1,17 +1,51 @@
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
#include <sys/stat.h>
#include <stdlib.h>
#include <stdio.h>
#include <time.h>
#include "expat.h"
-#if defined(__amigaos__) && defined(__USE_INLINE__)
-#include <proto/expat.h>
+#ifdef XML_LARGE_SIZE
+# define XML_FMT_INT_MOD "ll"
+#else
+# define XML_FMT_INT_MOD "l"
#endif
-#ifdef XML_LARGE_SIZE
-#define XML_FMT_INT_MOD "ll"
+#ifdef XML_UNICODE_WCHAR_T
+# define XML_FMT_STR "ls"
#else
-#define XML_FMT_INT_MOD "l"
+# define XML_FMT_STR "s"
#endif
static void
@@ -88,7 +122,8 @@ int main (int argc, char *argv[])
else
parseBufferSize = bufferSize;
if (!XML_Parse (parser, XMLBufPtr, parseBufferSize, isFinal)) {
- fprintf (stderr, "error '%s' at line %" XML_FMT_INT_MOD \
+ fprintf (stderr,
+ "error '%" XML_FMT_STR "' at line %" XML_FMT_INT_MOD \
"u character %" XML_FMT_INT_MOD "u\n",
XML_ErrorString (XML_GetErrorCode (parser)),
XML_GetCurrentLineNumber (parser),
diff --git a/tests/benchmark/benchmark.sln b/tests/benchmark/benchmark.sln
new file mode 100644
index 0000000..bc790bc
--- /dev/null
+++ b/tests/benchmark/benchmark.sln
@@ -0,0 +1,25 @@
+
+Microsoft Visual Studio Solution File, Format Version 12.00
+# Visual Studio 2013
+VisualStudioVersion = 12.0.40629.0
+MinimumVisualStudioVersion = 10.0.40219.1
+Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "benchmark", "benchmark.vcxproj", "{FF89BA66-62C4-49EC-9189-1E7B603A1FD6}"
+EndProject
+Global
+ GlobalSection(SolutionConfigurationPlatforms) = preSolution
+ Debug|Win32 = Debug|Win32
+ Release|Win32 = Release|Win32
+ Template|Win32 = Template|Win32
+ EndGlobalSection
+ GlobalSection(ProjectConfigurationPlatforms) = postSolution
+ {FF89BA66-62C4-49EC-9189-1E7B603A1FD6}.Debug|Win32.ActiveCfg = Debug|Win32
+ {FF89BA66-62C4-49EC-9189-1E7B603A1FD6}.Debug|Win32.Build.0 = Debug|Win32
+ {FF89BA66-62C4-49EC-9189-1E7B603A1FD6}.Release|Win32.ActiveCfg = Release|Win32
+ {FF89BA66-62C4-49EC-9189-1E7B603A1FD6}.Release|Win32.Build.0 = Release|Win32
+ {FF89BA66-62C4-49EC-9189-1E7B603A1FD6}.Template|Win32.ActiveCfg = Template|Win32
+ {FF89BA66-62C4-49EC-9189-1E7B603A1FD6}.Template|Win32.Build.0 = Template|Win32
+ EndGlobalSection
+ GlobalSection(SolutionProperties) = preSolution
+ HideSolutionNode = FALSE
+ EndGlobalSection
+EndGlobal
diff --git a/tests/benchmark/benchmark.vcxproj b/tests/benchmark/benchmark.vcxproj
new file mode 100644
index 0000000..0f46e88
--- /dev/null
+++ b/tests/benchmark/benchmark.vcxproj
@@ -0,0 +1,143 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project DefaultTargets="Build" ToolsVersion="12.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+ <ItemGroup Label="ProjectConfigurations">
+ <ProjectConfiguration Include="Debug|Win32">
+ <Configuration>Debug</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Release|Win32">
+ <Configuration>Release</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Template|Win32">
+ <Configuration>Template</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ </ItemGroup>
+ <PropertyGroup Label="Globals">
+ <SccProjectName />
+ <SccLocalPath />
+ <ProjectGuid>{FF89BA66-62C4-49EC-9189-1E7B603A1FD6}</ProjectGuid>
+ </PropertyGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Template|Win32'" Label="Configuration">
+ <ConfigurationType>Application</ConfigurationType>
+ <PlatformToolset>v120</PlatformToolset>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
+ <ConfigurationType>Application</ConfigurationType>
+ <PlatformToolset>v120</PlatformToolset>
+ <UseOfMfc>false</UseOfMfc>
+ <CharacterSet>MultiByte</CharacterSet>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
+ <ConfigurationType>Application</ConfigurationType>
+ <PlatformToolset>v120</PlatformToolset>
+ <UseOfMfc>false</UseOfMfc>
+ <CharacterSet>MultiByte</CharacterSet>
+ </PropertyGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
+ <ImportGroup Label="ExtensionSettings">
+ </ImportGroup>
+ <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Template|Win32'">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ </ImportGroup>
+ <ImportGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="PropertySheets">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ <Import Project="$(VCTargetsPath)Microsoft.Cpp.UpgradeFromVC60.props" />
+ </ImportGroup>
+ <ImportGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="PropertySheets">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ <Import Project="$(VCTargetsPath)Microsoft.Cpp.UpgradeFromVC60.props" />
+ </ImportGroup>
+ <PropertyGroup Label="UserMacros" />
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+ <OutDir>.\Release\</OutDir>
+ <IntDir>.\Release\</IntDir>
+ <LinkIncremental>false</LinkIncremental>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ <OutDir>.\Debug\</OutDir>
+ <IntDir>.\Debug\</IntDir>
+ <LinkIncremental>true</LinkIncremental>
+ </PropertyGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+ <ClCompile>
+ <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
+ <InlineFunctionExpansion>Default</InlineFunctionExpansion>
+ <StringPooling>true</StringPooling>
+ <FunctionLevelLinking>true</FunctionLevelLinking>
+ <Optimization>MaxSpeed</Optimization>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <WarningLevel>Level3</WarningLevel>
+ <AdditionalIncludeDirectories>..\..\lib;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
+ <PreprocessorDefinitions>NDEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <AssemblerListingLocation>.\Release\</AssemblerListingLocation>
+ <PrecompiledHeaderOutputFile>.\Release\benchmark.pch</PrecompiledHeaderOutputFile>
+ <ObjectFileName>.\Release\</ObjectFileName>
+ <ProgramDataBaseFileName>.\Release\</ProgramDataBaseFileName>
+ </ClCompile>
+ <Midl>
+ <TypeLibraryName>.\Release\benchmark.tlb</TypeLibraryName>
+ </Midl>
+ <ResourceCompile>
+ <Culture>0x1009</Culture>
+ <PreprocessorDefinitions>NDEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ </ResourceCompile>
+ <Bscmake>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <OutputFile>.\Release\benchmark.bsc</OutputFile>
+ </Bscmake>
+ <Link>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <SubSystem>Console</SubSystem>
+ <OutputFile>.\Release\benchmark.exe</OutputFile>
+ <AdditionalLibraryDirectories>..\..\win32\bin\Release;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
+ <AdditionalDependencies>libexpat.lib;%(AdditionalDependencies)</AdditionalDependencies>
+ </Link>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ <ClCompile>
+ <RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
+ <InlineFunctionExpansion>Default</InlineFunctionExpansion>
+ <FunctionLevelLinking>true</FunctionLevelLinking>
+ <Optimization>Disabled</Optimization>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <WarningLevel>Level3</WarningLevel>
+ <MinimalRebuild>true</MinimalRebuild>
+ <DebugInformationFormat>EditAndContinue</DebugInformationFormat>
+ <AdditionalIncludeDirectories>..\..\lib;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
+ <PreprocessorDefinitions>_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <AssemblerListingLocation>.\Debug\</AssemblerListingLocation>
+ <PrecompiledHeaderOutputFile>.\Debug\benchmark.pch</PrecompiledHeaderOutputFile>
+ <ObjectFileName>.\Debug\</ObjectFileName>
+ <ProgramDataBaseFileName>.\Debug\</ProgramDataBaseFileName>
+ <BasicRuntimeChecks>EnableFastChecks</BasicRuntimeChecks>
+ </ClCompile>
+ <Midl>
+ <TypeLibraryName>.\Debug\benchmark.tlb</TypeLibraryName>
+ </Midl>
+ <ResourceCompile>
+ <Culture>0x1009</Culture>
+ <PreprocessorDefinitions>_DEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ </ResourceCompile>
+ <Bscmake>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <OutputFile>.\Debug\benchmark.bsc</OutputFile>
+ </Bscmake>
+ <Link>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <GenerateDebugInformation>true</GenerateDebugInformation>
+ <SubSystem>Console</SubSystem>
+ <OutputFile>.\Debug\benchmark.exe</OutputFile>
+ <AdditionalLibraryDirectories>..\..\win32\bin\Debug;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
+ <AdditionalDependencies>libexpat.lib;%(AdditionalDependencies)</AdditionalDependencies>
+ </Link>
+ </ItemDefinitionGroup>
+ <ItemGroup>
+ <ClCompile Include="benchmark.c" />
+ </ItemGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
+ <ImportGroup Label="ExtensionTargets">
+ </ImportGroup>
+</Project> \ No newline at end of file
diff --git a/tests/chardata.c b/tests/chardata.c
index 012499b..53e7333 100644
--- a/tests/chardata.c
+++ b/tests/chardata.c
@@ -1,11 +1,37 @@
-/* Copyright (c) 1998-2003 Thai Open Source Software Center Ltd
- See the file COPYING for copying permission.
-
- chardata.c
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
#ifdef HAVE_EXPAT_CONFIG_H
-#include <expat_config.h>
+# include <expat_config.h>
#endif
#include "minicheck.h"
@@ -35,25 +61,6 @@ CharData_Init(CharData *storage)
}
void
-CharData_AppendString(CharData *storage, const char *s)
-{
- int maxchars = sizeof(storage->data) / sizeof(storage->data[0]);
- int len;
-
- assert(s != NULL);
- len = strlen(s);
- if (storage->count < 0)
- storage->count = 0;
- if ((len + storage->count) > maxchars) {
- len = (maxchars - storage->count);
- }
- if (len + storage->count < (int)sizeof(storage->data)) {
- memcpy(storage->data + storage->count, s, len);
- storage->count += len;
- }
-}
-
-void
CharData_AppendXMLChars(CharData *storage, const XML_Char *s, int len)
{
int maxchars;
@@ -76,35 +83,6 @@ CharData_AppendXMLChars(CharData *storage, const XML_Char *s, int len)
}
int
-CharData_CheckString(CharData *storage, const char *expected)
-{
- char buffer[1280];
- int len;
- int count;
-
- assert(storage != NULL);
- assert(expected != NULL);
- count = (storage->count < 0) ? 0 : storage->count;
- len = strlen(expected);
- if (len != count) {
- if (sizeof(XML_Char) == 1)
- sprintf(buffer, "wrong number of data characters:"
- " got %d, expected %d:\n%s", count, len, storage->data);
- else
- sprintf(buffer,
- "wrong number of data characters: got %d, expected %d",
- count, len);
- fail(buffer);
- return 0;
- }
- if (memcmp(expected, storage->data, len) != 0) {
- fail("got bad data bytes");
- return 0;
- }
- return 1;
-}
-
-int
CharData_CheckXMLChars(CharData *storage, const XML_Char *expected)
{
char buffer[1024];
diff --git a/tests/chardata.h b/tests/chardata.h
index e8dc4ce..d3ad869 100644
--- a/tests/chardata.h
+++ b/tests/chardata.h
@@ -1,7 +1,34 @@
-/* chardata.h
-
- Interface to some helper routines used to accumulate and check text
+/* Interface to some helper routines used to accumulate and check text
and attribute content.
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
#ifdef __cplusplus
@@ -18,18 +45,14 @@ extern "C" {
typedef struct {
int count; /* # of chars, < 0 if not set */
- XML_Char data[1024];
+ XML_Char data[2048];
} CharData;
void CharData_Init(CharData *storage);
-void CharData_AppendString(CharData *storage, const char *s);
-
void CharData_AppendXMLChars(CharData *storage, const XML_Char *s, int len);
-int CharData_CheckString(CharData *storage, const char *s);
-
int CharData_CheckXMLChars(CharData *storage, const XML_Char *s);
diff --git a/tests/memcheck.c b/tests/memcheck.c
new file mode 100644
index 0000000..23e9fdf
--- /dev/null
+++ b/tests/memcheck.c
@@ -0,0 +1,198 @@
+/* Debug allocators for the Expat test suite
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+#include <stdio.h>
+#include <stdlib.h>
+#include "memcheck.h"
+
+
+/* Structures to keep track of what has been allocated. Speed isn't a
+ * big issue for the tests this is required for, so we will use a
+ * doubly-linked list to make deletion easier.
+ */
+
+typedef struct allocation_entry {
+ struct allocation_entry * next;
+ struct allocation_entry * prev;
+ void * allocation;
+ size_t num_bytes;
+} AllocationEntry;
+
+static AllocationEntry *alloc_head = NULL;
+static AllocationEntry *alloc_tail = NULL;
+
+static AllocationEntry *find_allocation(void *ptr);
+
+
+/* Allocate some memory and keep track of it. */
+void *
+tracking_malloc(size_t size)
+{
+ AllocationEntry *entry = malloc(sizeof(AllocationEntry));
+
+ if (entry == NULL) {
+ printf("Allocator failure\n");
+ return NULL;
+ }
+ entry->num_bytes = size;
+ entry->allocation = malloc(size);
+ if (entry->allocation == NULL) {
+ free(entry);
+ return NULL;
+ }
+ entry->next = NULL;
+
+ /* Add to the list of allocations */
+ if (alloc_head == NULL) {
+ entry->prev = NULL;
+ alloc_head = alloc_tail = entry;
+ } else {
+ entry->prev = alloc_tail;
+ alloc_tail->next = entry;
+ alloc_tail = entry;
+ }
+
+ return entry->allocation;
+}
+
+static AllocationEntry *
+find_allocation(void *ptr)
+{
+ AllocationEntry *entry;
+
+ for (entry = alloc_head; entry != NULL; entry = entry->next) {
+ if (entry->allocation == ptr) {
+ return entry;
+ }
+ }
+ return NULL;
+}
+
+/* Free some memory and remove the tracking for it */
+void
+tracking_free(void *ptr)
+{
+ AllocationEntry *entry;
+
+ if (ptr == NULL) {
+ /* There won't be an entry for this */
+ return;
+ }
+
+ entry = find_allocation(ptr);
+ if (entry != NULL) {
+ /* This is the relevant allocation. Unlink it */
+ if (entry->prev != NULL)
+ entry->prev->next = entry->next;
+ else
+ alloc_head = entry->next;
+ if (entry->next != NULL)
+ entry->next->prev = entry->prev;
+ else
+ alloc_tail = entry->next;
+ free(entry);
+ } else {
+ printf("Attempting to free unallocated memory at %p\n", ptr);
+ }
+ free(ptr);
+}
+
+/* Reallocate some memory and keep track of it */
+void *
+tracking_realloc(void *ptr, size_t size)
+{
+ AllocationEntry *entry;
+
+ if (ptr == NULL) {
+ /* By definition, this is equivalent to malloc(size) */
+ return tracking_malloc(size);
+ }
+ if (size == 0) {
+ /* By definition, this is equivalent to free(ptr) */
+ tracking_free(ptr);
+ return NULL;
+ }
+
+ /* Find the allocation entry for this memory */
+ entry = find_allocation(ptr);
+ if (entry == NULL) {
+ printf("Attempting to realloc unallocated memory at %p\n", ptr);
+ entry = malloc(sizeof(AllocationEntry));
+ if (entry == NULL) {
+ printf("Reallocator failure\n");
+ return NULL;
+ }
+ entry->allocation = realloc(ptr, size);
+ if (entry->allocation == NULL) {
+ free(entry);
+ return NULL;
+ }
+
+ /* Add to the list of allocations */
+ entry->next = NULL;
+ if (alloc_head == NULL) {
+ entry->prev = NULL;
+ alloc_head = alloc_tail = entry;
+ } else {
+ entry->prev = alloc_tail;
+ alloc_tail->next = entry;
+ alloc_tail = entry;
+ }
+ } else {
+ entry->allocation = realloc(ptr, size);
+ if (entry->allocation == NULL) {
+ /* Realloc semantics say the original is still allocated */
+ entry->allocation = ptr;
+ return NULL;
+ }
+ }
+
+ entry->num_bytes = size;
+ return entry->allocation;
+}
+
+int
+tracking_report(void)
+{
+ AllocationEntry *entry;
+
+ if (alloc_head == NULL)
+ return 1;
+
+ /* Otherwise we have allocations that haven't been freed */
+ for (entry = alloc_head; entry != NULL; entry = entry->next)
+ {
+ printf("Allocated %lu bytes at %p\n",
+ (long unsigned)entry->num_bytes, entry->allocation);
+ }
+ return 0;
+}
diff --git a/tests/memcheck.h b/tests/memcheck.h
new file mode 100644
index 0000000..1cc4848
--- /dev/null
+++ b/tests/memcheck.h
@@ -0,0 +1,57 @@
+/* Interface to allocation functions that will track what has or has
+ not been freed.
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifndef XML_MEMCHECK_H
+#define XML_MEMCHECK_H 1
+
+/* Allocation declarations */
+
+void *tracking_malloc(size_t size);
+void tracking_free(void *ptr);
+void *tracking_realloc(void *ptr, size_t size);
+
+/* End-of-test check to see if unfreed allocations remain. Returns
+ * TRUE (1) if there is nothing, otherwise prints a report of the
+ * remaining allocations and returns FALSE (0).
+ */
+int tracking_report(void);
+
+#endif /* XML_MEMCHECK_H */
+
+#ifdef __cplusplus
+}
+#endif
diff --git a/tests/minicheck.c b/tests/minicheck.c
index 5a1f5ed..be1e37e 100644
--- a/tests/minicheck.c
+++ b/tests/minicheck.c
@@ -1,14 +1,44 @@
/* Miniature re-implementation of the "check" library.
- *
- * This is intended to support just enough of check to run the Expat
- * tests. This interface is based entirely on the portion of the
- * check library being used.
- */
+
+ This is intended to support just enough of check to run the Expat
+ tests. This interface is based entirely on the portion of the
+ check library being used.
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
#include <stdio.h>
#include <stdlib.h>
#include <setjmp.h>
#include <assert.h>
+#include <string.h>
#include "internal.h" /* for UNUSED_P only */
#include "minicheck.h"
@@ -63,16 +93,39 @@ tcase_add_test(TCase *tc, tcase_test_function test)
size_t new_size = sizeof(tcase_test_function) * nalloc;
tcase_test_function *new_tests = realloc(tc->tests, new_size);
assert(new_tests != NULL);
- if (new_tests != tc->tests) {
- free(tc->tests);
- tc->tests = new_tests;
- }
+ tc->tests = new_tests;
tc->allocated = nalloc;
}
tc->tests[tc->ntests] = test;
tc->ntests++;
}
+static void
+tcase_free(TCase *tc)
+{
+ if (! tc) {
+ return;
+ }
+
+ free(tc->tests);
+ free(tc);
+}
+
+static void
+suite_free(Suite *suite)
+{
+ if (! suite) {
+ return;
+ }
+
+ while (suite->tests != NULL) {
+ TCase *next = suite->tests->next_tcase;
+ tcase_free(suite->tests);
+ suite->tests = next;
+ }
+ free(suite);
+}
+
SRunner *
srunner_create(Suite *suite)
{
@@ -163,8 +216,10 @@ _fail_unless(int UNUSED_P(condition), const char *UNUSED_P(file), int UNUSED_P(l
we have a failure, so there's no reason to be quiet about what
it is.
*/
- if (msg != NULL)
- printf("%s", msg);
+ if (msg != NULL) {
+ const int has_newline = (msg[strlen(msg) - 1] == '\n');
+ fprintf(stderr, "ERROR: %s%s", msg, has_newline ? "" : "\n");
+ }
longjmp(env, 1);
}
@@ -178,6 +233,10 @@ srunner_ntests_failed(SRunner *runner)
void
srunner_free(SRunner *runner)
{
- free(runner->suite);
+ if (! runner) {
+ return;
+ }
+
+ suite_free(runner->suite);
free(runner);
}
diff --git a/tests/minicheck.h b/tests/minicheck.h
index 9b06f51..a2f57dd 100644
--- a/tests/minicheck.h
+++ b/tests/minicheck.h
@@ -1,11 +1,40 @@
/* Miniature re-implementation of the "check" library.
- *
- * This is intended to support just enough of check to run the Expat
- * tests. This interface is based entirely on the portion of the
- * check library being used.
- *
- * This is *source* compatible, but not necessary *link* compatible.
- */
+
+ This is intended to support just enough of check to run the Expat
+ tests. This interface is based entirely on the portion of the
+ check library being used.
+
+ This is *source* compatible, but not necessary *link* compatible.
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
#ifdef __cplusplus
extern "C" {
@@ -26,11 +55,6 @@ extern "C" {
#define __func__ __FUNCTION__
#endif
-/* ISO C90 does not support '__func__' predefined identifier */
-#if defined(__STDC_VERSION__) && (__STDC_VERSION__ < 199901)
-# define __func__ "(unknown)"
-#endif
-
#define START_TEST(testname) static void testname(void) { \
_check_set_test_info(__func__, __FILE__, __LINE__); \
{
diff --git a/tests/runtests.c b/tests/runtests.c
index c0cdea9..463bb38 100644
--- a/tests/runtests.c
+++ b/tests/runtests.c
@@ -1,11 +1,41 @@
-/* Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd
- See the file COPYING for copying permission.
-
- runtest.c : run the Expat test suite
+/* Run the Expat test suite
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
+#if defined(NDEBUG)
+# undef NDEBUG /* because test suite relies on assert(...) at the moment */
+#endif
+
#ifdef HAVE_EXPAT_CONFIG_H
-#include <expat_config.h>
+# include <expat_config.h>
#endif
#include <assert.h>
@@ -14,26 +44,60 @@
#include <string.h>
#include <stdint.h>
#include <stddef.h> /* ptrdiff_t */
-#ifndef __cplusplus
-# include <stdbool.h>
+#include <ctype.h>
+#include <limits.h>
+
+#if ! defined(__cplusplus)
+# if defined(_MSC_VER) && (_MSC_VER <= 1700)
+ /* for vs2012/11.0/1700 and earlier Visual Studio compilers */
+# define bool int
+# define false 0
+# define true 1
+# else
+# include <stdbool.h>
+# endif
#endif
+
#include "expat.h"
#include "chardata.h"
+#include "structdata.h"
#include "internal.h" /* for UNUSED_P only */
#include "minicheck.h"
-
-#if defined(__amigaos__) && defined(__USE_INLINE__)
-#include <proto/expat.h>
-#endif
+#include "memcheck.h"
+#include "siphash.h"
+#include "ascii.h" /* for ASCII_xxx */
#ifdef XML_LARGE_SIZE
-#define XML_FMT_INT_MOD "ll"
+# define XML_FMT_INT_MOD "ll"
#else
-#define XML_FMT_INT_MOD "l"
+# define XML_FMT_INT_MOD "l"
#endif
-static XML_Parser parser;
+#ifdef XML_UNICODE_WCHAR_T
+# define XML_FMT_CHAR "lc"
+# define XML_FMT_STR "ls"
+# include <wchar.h>
+# define xcstrlen(s) wcslen(s)
+# define xcstrcmp(s, t) wcscmp((s), (t))
+# define xcstrncmp(s, t, n) wcsncmp((s), (t), (n))
+# define XCS(s) _XCS(s)
+# define _XCS(s) L ## s
+#else
+# ifdef XML_UNICODE
+# error "No support for UTF-16 character without wchar_t in tests"
+# else
+# define XML_FMT_CHAR "c"
+# define XML_FMT_STR "s"
+# define xcstrlen(s) strlen(s)
+# define xcstrcmp(s, t) strcmp((s), (t))
+# define xcstrncmp(s, t, n) strncmp((s), (t), (n))
+# define XCS(s) s
+# endif /* XML_UNICODE */
+#endif /* XML_UNICODE_WCHAR_T */
+
+
+static XML_Parser parser = NULL;
static void
@@ -47,8 +111,10 @@ basic_setup(void)
static void
basic_teardown(void)
{
- if (parser != NULL)
+ if (parser != NULL) {
XML_ParserFree(parser);
+ parser = NULL;
+ }
}
/* Generate a failure using the parser state to create an error message;
@@ -61,7 +127,8 @@ _xml_failure(XML_Parser parser, const char *file, int line)
char buffer[1024];
enum XML_Error err = XML_GetErrorCode(parser);
sprintf(buffer,
- " %d: %s (line %" XML_FMT_INT_MOD "u, offset %"\
+ " %d: %" XML_FMT_STR " (line %"
+ XML_FMT_INT_MOD "u, offset %"
XML_FMT_INT_MOD "u)\n reported from %s, line %d\n",
err,
XML_ErrorString(err),
@@ -113,6 +180,34 @@ _expect_failure(const char *text, enum XML_Error errorCode, const char *errorMes
/* Dummy handlers for when we need to set a handler to tickle a bug,
but it doesn't need to do anything.
*/
+static unsigned long dummy_handler_flags = 0;
+
+#define DUMMY_START_DOCTYPE_HANDLER_FLAG (1UL << 0)
+#define DUMMY_END_DOCTYPE_HANDLER_FLAG (1UL << 1)
+#define DUMMY_ENTITY_DECL_HANDLER_FLAG (1UL << 2)
+#define DUMMY_NOTATION_DECL_HANDLER_FLAG (1UL << 3)
+#define DUMMY_ELEMENT_DECL_HANDLER_FLAG (1UL << 4)
+#define DUMMY_ATTLIST_DECL_HANDLER_FLAG (1UL << 5)
+#define DUMMY_COMMENT_HANDLER_FLAG (1UL << 6)
+#define DUMMY_PI_HANDLER_FLAG (1UL << 7)
+#define DUMMY_START_ELEMENT_HANDLER_FLAG (1UL << 8)
+#define DUMMY_START_CDATA_HANDLER_FLAG (1UL << 9)
+#define DUMMY_END_CDATA_HANDLER_FLAG (1UL << 10)
+#define DUMMY_UNPARSED_ENTITY_DECL_HANDLER_FLAG (1UL << 11)
+#define DUMMY_START_NS_DECL_HANDLER_FLAG (1UL << 12)
+#define DUMMY_END_NS_DECL_HANDLER_FLAG (1UL << 13)
+#define DUMMY_START_DOCTYPE_DECL_HANDLER_FLAG (1UL << 14)
+#define DUMMY_END_DOCTYPE_DECL_HANDLER_FLAG (1UL << 15)
+#define DUMMY_SKIP_HANDLER_FLAG (1UL << 16)
+#define DUMMY_DEFAULT_HANDLER_FLAG (1UL << 17)
+
+
+static void XMLCALL
+dummy_xdecl_handler(void *UNUSED_P(userData),
+ const XML_Char *UNUSED_P(version),
+ const XML_Char *UNUSED_P(encoding),
+ int UNUSED_P(standalone))
+{}
static void XMLCALL
dummy_start_doctype_handler(void *UNUSED_P(userData),
@@ -120,11 +215,15 @@ dummy_start_doctype_handler(void *UNUSED_P(userData),
const XML_Char *UNUSED_P(sysid),
const XML_Char *UNUSED_P(pubid),
int UNUSED_P(has_internal_subset))
-{}
+{
+ dummy_handler_flags |= DUMMY_START_DOCTYPE_HANDLER_FLAG;
+}
static void XMLCALL
dummy_end_doctype_handler(void *UNUSED_P(userData))
-{}
+{
+ dummy_handler_flags |= DUMMY_END_DOCTYPE_HANDLER_FLAG;
+}
static void XMLCALL
dummy_entity_decl_handler(void *UNUSED_P(userData),
@@ -136,7 +235,9 @@ dummy_entity_decl_handler(void *UNUSED_P(userData),
const XML_Char *UNUSED_P(systemId),
const XML_Char *UNUSED_P(publicId),
const XML_Char *UNUSED_P(notationName))
-{}
+{
+ dummy_handler_flags |= DUMMY_ENTITY_DECL_HANDLER_FLAG;
+}
static void XMLCALL
dummy_notation_decl_handler(void *UNUSED_P(userData),
@@ -144,13 +245,22 @@ dummy_notation_decl_handler(void *UNUSED_P(userData),
const XML_Char *UNUSED_P(base),
const XML_Char *UNUSED_P(systemId),
const XML_Char *UNUSED_P(publicId))
-{}
+{
+ dummy_handler_flags |= DUMMY_NOTATION_DECL_HANDLER_FLAG;
+}
static void XMLCALL
dummy_element_decl_handler(void *UNUSED_P(userData),
const XML_Char *UNUSED_P(name),
- XML_Content *UNUSED_P(model))
-{}
+ XML_Content *model)
+{
+ /* The content model must be freed by the handler. Unfortunately
+ * we cannot pass the parser as the userData because this is used
+ * with other handlers that require other userData.
+ */
+ XML_FreeContentModel(parser, model);
+ dummy_handler_flags |= DUMMY_ELEMENT_DECL_HANDLER_FLAG;
+}
static void XMLCALL
dummy_attlist_decl_handler(void *UNUSED_P(userData),
@@ -159,21 +269,185 @@ dummy_attlist_decl_handler(void *UNUSED_P(userData),
const XML_Char *UNUSED_P(att_type),
const XML_Char *UNUSED_P(dflt),
int UNUSED_P(isrequired))
-{}
+{
+ dummy_handler_flags |= DUMMY_ATTLIST_DECL_HANDLER_FLAG;
+}
static void XMLCALL
dummy_comment_handler(void *UNUSED_P(userData), const XML_Char *UNUSED_P(data))
-{}
+{
+ dummy_handler_flags |= DUMMY_COMMENT_HANDLER_FLAG;
+}
static void XMLCALL
dummy_pi_handler(void *UNUSED_P(userData), const XML_Char *UNUSED_P(target), const XML_Char *UNUSED_P(data))
-{}
+{
+ dummy_handler_flags |= DUMMY_PI_HANDLER_FLAG;
+}
static void XMLCALL
dummy_start_element(void *UNUSED_P(userData),
const XML_Char *UNUSED_P(name), const XML_Char **UNUSED_P(atts))
+{
+ dummy_handler_flags |= DUMMY_START_ELEMENT_HANDLER_FLAG;
+}
+
+static void XMLCALL
+dummy_end_element(void *UNUSED_P(userData), const XML_Char *UNUSED_P(name))
+{}
+
+static void XMLCALL
+dummy_start_cdata_handler(void *UNUSED_P(userData))
+{
+ dummy_handler_flags |= DUMMY_START_CDATA_HANDLER_FLAG;
+}
+
+static void XMLCALL
+dummy_end_cdata_handler(void *UNUSED_P(userData))
+{
+ dummy_handler_flags |= DUMMY_END_CDATA_HANDLER_FLAG;
+}
+
+static void XMLCALL
+dummy_cdata_handler(void *UNUSED_P(userData),
+ const XML_Char *UNUSED_P(s),
+ int UNUSED_P(len))
{}
+static void XMLCALL
+dummy_start_namespace_decl_handler(void *UNUSED_P(userData),
+ const XML_Char *UNUSED_P(prefix),
+ const XML_Char *UNUSED_P(uri))
+{
+ dummy_handler_flags |= DUMMY_START_NS_DECL_HANDLER_FLAG;
+}
+
+static void XMLCALL
+dummy_end_namespace_decl_handler(void *UNUSED_P(userData),
+ const XML_Char *UNUSED_P(prefix))
+{
+ dummy_handler_flags |= DUMMY_END_NS_DECL_HANDLER_FLAG;
+}
+
+/* This handler is obsolete, but while the code exists we should
+ * ensure that dealing with the handler is covered by tests.
+ */
+static void XMLCALL
+dummy_unparsed_entity_decl_handler(void *UNUSED_P(userData),
+ const XML_Char *UNUSED_P(entityName),
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId),
+ const XML_Char *UNUSED_P(notationName))
+{
+ dummy_handler_flags |= DUMMY_UNPARSED_ENTITY_DECL_HANDLER_FLAG;
+}
+
+static void XMLCALL
+dummy_default_handler(void *UNUSED_P(userData),
+ const XML_Char *UNUSED_P(s),
+ int UNUSED_P(len))
+{}
+
+static void XMLCALL
+dummy_start_doctype_decl_handler(void *UNUSED_P(userData),
+ const XML_Char *UNUSED_P(doctypeName),
+ const XML_Char *UNUSED_P(sysid),
+ const XML_Char *UNUSED_P(pubid),
+ int UNUSED_P(has_internal_subset))
+{
+ dummy_handler_flags |= DUMMY_START_DOCTYPE_DECL_HANDLER_FLAG;
+}
+
+static void XMLCALL
+dummy_end_doctype_decl_handler(void *UNUSED_P(userData))
+{
+ dummy_handler_flags |= DUMMY_END_DOCTYPE_DECL_HANDLER_FLAG;
+}
+
+static void XMLCALL
+dummy_skip_handler(void *UNUSED_P(userData),
+ const XML_Char *UNUSED_P(entityName),
+ int UNUSED_P(is_parameter_entity))
+{
+ dummy_handler_flags |= DUMMY_SKIP_HANDLER_FLAG;
+}
+
+/* Useful external entity handler */
+typedef struct ExtOption {
+ const XML_Char *system_id;
+ const char *parse_text;
+} ExtOption;
+
+static int XMLCALL
+external_entity_optioner(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *systemId,
+ const XML_Char *UNUSED_P(publicId))
+{
+ ExtOption *options = (ExtOption *)XML_GetUserData(parser);
+ XML_Parser ext_parser;
+
+ while (options->parse_text != NULL) {
+ if (!xcstrcmp(systemId, options->system_id)) {
+ enum XML_Status rc;
+ ext_parser =
+ XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ return XML_STATUS_ERROR;
+ rc = _XML_Parse_SINGLE_BYTES(ext_parser, options->parse_text,
+ strlen(options->parse_text),
+ XML_TRUE);
+ XML_ParserFree(ext_parser);
+ return rc;
+ }
+ options++;
+ }
+ fail("No suitable option found");
+ return XML_STATUS_ERROR;
+}
+
+/*
+ * Parameter entity evaluation support.
+ */
+#define ENTITY_MATCH_FAIL (-1)
+#define ENTITY_MATCH_NOT_FOUND (0)
+#define ENTITY_MATCH_SUCCESS (1)
+static const XML_Char *entity_name_to_match = NULL;
+static const XML_Char *entity_value_to_match = NULL;
+static int entity_match_flag = ENTITY_MATCH_NOT_FOUND;
+
+static void XMLCALL
+param_entity_match_handler(void *UNUSED_P(userData),
+ const XML_Char *entityName,
+ int is_parameter_entity,
+ const XML_Char *value,
+ int value_length,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId),
+ const XML_Char *UNUSED_P(notationName))
+{
+ if (!is_parameter_entity ||
+ entity_name_to_match == NULL ||
+ entity_value_to_match == NULL) {
+ return;
+ }
+ if (!xcstrcmp(entityName, entity_name_to_match)) {
+ /* The cast here is safe because we control the horizontal and
+ * the vertical, and we therefore know our strings are never
+ * going to overflow an int.
+ */
+ if (value_length != (int)xcstrlen(entity_value_to_match) ||
+ xcstrncmp(value, entity_value_to_match, value_length)) {
+ entity_match_flag = ENTITY_MATCH_FAIL;
+ } else {
+ entity_match_flag = ENTITY_MATCH_SUCCESS;
+ }
+ }
+ /* Else leave the match flag alone */
+}
/*
* Character & encoding tests.
@@ -201,6 +475,45 @@ START_TEST(test_u0000_char)
}
END_TEST
+START_TEST(test_siphash_self)
+{
+ if (! sip24_valid())
+ fail("SipHash self-test failed");
+}
+END_TEST
+
+START_TEST(test_siphash_spec)
+{
+ /* https://131002.net/siphash/siphash.pdf (page 19, "Test values") */
+ const char message[] = "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09"
+ "\x0a\x0b\x0c\x0d\x0e";
+ const size_t len = sizeof(message) - 1;
+ const uint64_t expected = _SIP_ULL(0xa129ca61U, 0x49be45e5U);
+ struct siphash state;
+ struct sipkey key;
+ (void)sip_tobin;
+
+ sip_tokey(&key,
+ "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09"
+ "\x0a\x0b\x0c\x0d\x0e\x0f");
+ sip24_init(&state, &key);
+
+ /* Cover spread across calls */
+ sip24_update(&state, message, 4);
+ sip24_update(&state, message + 4, len - 4);
+
+ /* Cover null length */
+ sip24_update(&state, message, 0);
+
+ if (sip24_final(&state) != expected)
+ fail("sip24_final failed spec test\n");
+
+ /* Cover wrapper */
+ if (siphash24(message, len, &key) != expected)
+ fail("siphash24 failed spec test\n");
+}
+END_TEST
+
START_TEST(test_bom_utf8)
{
/* This test is really just making sure we don't core on a UTF-8 BOM. */
@@ -229,6 +542,16 @@ START_TEST(test_bom_utf16_le)
}
END_TEST
+/* Parse whole buffer at once to exercise a different code path */
+START_TEST(test_nobom_utf16_le)
+{
+ char text[] = " \0<\0e\0/\0>\0";
+
+ if (XML_Parse(parser, text, sizeof(text)-1, XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
static void XMLCALL
accumulate_characters(void *userData, const XML_Char *s, int len)
{
@@ -240,15 +563,21 @@ accumulate_attribute(void *userData, const XML_Char *UNUSED_P(name),
const XML_Char **atts)
{
CharData *storage = (CharData *)userData;
- if (storage->count < 0 && atts != NULL && atts[0] != NULL) {
+
+ /* Check there are attributes to deal with */
+ if (atts == NULL)
+ return;
+
+ while (storage->count < 0 && atts[0] != NULL) {
/* "accumulate" the value of the first attribute we see */
CharData_AppendXMLChars(storage, atts[1], -1);
+ atts += 2;
}
}
static void
-_run_character_check(const XML_Char *text, const XML_Char *expected,
+_run_character_check(const char *text, const XML_Char *expected,
const char *file, int line)
{
CharData storage;
@@ -265,7 +594,7 @@ _run_character_check(const XML_Char *text, const XML_Char *expected,
_run_character_check(text, expected, __FILE__, __LINE__)
static void
-_run_attribute_check(const XML_Char *text, const XML_Char *expected,
+_run_attribute_check(const char *text, const XML_Char *expected,
const char *file, int line)
{
CharData storage;
@@ -281,14 +610,54 @@ _run_attribute_check(const XML_Char *text, const XML_Char *expected,
#define run_attribute_check(text, expected) \
_run_attribute_check(text, expected, __FILE__, __LINE__)
+typedef struct ExtTest {
+ const char *parse_text;
+ const XML_Char *encoding;
+ CharData *storage;
+} ExtTest;
+
+static void XMLCALL
+ext_accumulate_characters(void *userData, const XML_Char *s, int len)
+{
+ ExtTest *test_data = (ExtTest *)userData;
+ accumulate_characters(test_data->storage, s, len);
+}
+
+static void
+_run_ext_character_check(const char *text,
+ ExtTest *test_data,
+ const XML_Char *expected,
+ const char *file, int line)
+{
+ CharData storage;
+
+ CharData_Init(&storage);
+ test_data->storage = &storage;
+ XML_SetUserData(parser, test_data);
+ XML_SetCharacterDataHandler(parser, ext_accumulate_characters);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ _xml_failure(parser, file, line);
+ CharData_CheckXMLChars(&storage, expected);
+}
+
+#define run_ext_character_check(text, test_data, expected) \
+ _run_ext_character_check(text, test_data, expected, __FILE__, __LINE__)
+
/* Regression test for SF bug #491986. */
START_TEST(test_danish_latin1)
{
const char *text =
"<?xml version='1.0' encoding='iso-8859-1'?>\n"
"<e>J\xF8rgen \xE6\xF8\xE5\xC6\xD8\xC5</e>";
- run_character_check(text,
- "J\xC3\xB8rgen \xC3\xA6\xC3\xB8\xC3\xA5\xC3\x86\xC3\x98\xC3\x85");
+#ifdef XML_UNICODE
+ const XML_Char *expected =
+ XCS("J\x00f8rgen \x00e6\x00f8\x00e5\x00c6\x00d8\x00c5");
+#else
+ const XML_Char *expected =
+ XCS("J\xC3\xB8rgen \xC3\xA6\xC3\xB8\xC3\xA5\xC3\x86\xC3\x98\xC3\x85");
+#endif
+ run_character_check(text, expected);
}
END_TEST
@@ -299,8 +668,14 @@ START_TEST(test_french_charref_hexidecimal)
const char *text =
"<?xml version='1.0' encoding='iso-8859-1'?>\n"
"<doc>&#xE9;&#xE8;&#xE0;&#xE7;&#xEA;&#xC8;</doc>";
- run_character_check(text,
- "\xC3\xA9\xC3\xA8\xC3\xA0\xC3\xA7\xC3\xAA\xC3\x88");
+#ifdef XML_UNICODE
+ const XML_Char *expected =
+ XCS("\x00e9\x00e8\x00e0\x00e7\x00ea\x00c8");
+#else
+ const XML_Char *expected =
+ XCS("\xC3\xA9\xC3\xA8\xC3\xA0\xC3\xA7\xC3\xAA\xC3\x88");
+#endif
+ run_character_check(text, expected);
}
END_TEST
@@ -309,8 +684,14 @@ START_TEST(test_french_charref_decimal)
const char *text =
"<?xml version='1.0' encoding='iso-8859-1'?>\n"
"<doc>&#233;&#232;&#224;&#231;&#234;&#200;</doc>";
- run_character_check(text,
- "\xC3\xA9\xC3\xA8\xC3\xA0\xC3\xA7\xC3\xAA\xC3\x88");
+#ifdef XML_UNICODE
+ const XML_Char *expected =
+ XCS("\x00e9\x00e8\x00e0\x00e7\x00ea\x00c8");
+#else
+ const XML_Char *expected =
+ XCS("\xC3\xA9\xC3\xA8\xC3\xA0\xC3\xA7\xC3\xAA\xC3\x88");
+#endif
+ run_character_check(text, expected);
}
END_TEST
@@ -319,8 +700,14 @@ START_TEST(test_french_latin1)
const char *text =
"<?xml version='1.0' encoding='iso-8859-1'?>\n"
"<doc>\xE9\xE8\xE0\xE7\xEa\xC8</doc>";
- run_character_check(text,
- "\xC3\xA9\xC3\xA8\xC3\xA0\xC3\xA7\xC3\xAA\xC3\x88");
+#ifdef XML_UNICODE
+ const XML_Char *expected =
+ XCS("\x00e9\x00e8\x00e0\x00e7\x00ea\x00c8");
+#else
+ const XML_Char *expected =
+ XCS("\xC3\xA9\xC3\xA8\xC3\xA0\xC3\xA7\xC3\xAA\xC3\x88");
+#endif
+ run_character_check(text, expected);
}
END_TEST
@@ -329,7 +716,12 @@ START_TEST(test_french_utf8)
const char *text =
"<?xml version='1.0' encoding='utf-8'?>\n"
"<doc>\xC3\xA9</doc>";
- run_character_check(text, "\xC3\xA9");
+#ifdef XML_UNICODE
+ const XML_Char *expected = XCS("\x00e9");
+#else
+ const XML_Char *expected = XCS("\xC3\xA9");
+#endif
+ run_character_check(text, expected);
}
END_TEST
@@ -341,7 +733,12 @@ END_TEST
START_TEST(test_utf8_false_rejection)
{
const char *text = "<doc>\xEF\xBA\xBF</doc>";
- run_character_check(text, "\xEF\xBA\xBF");
+#ifdef XML_UNICODE
+ const XML_Char *expected = XCS("\xfebf");
+#else
+ const XML_Char *expected = XCS("\xEF\xBA\xBF");
+#endif
+ run_character_check(text, expected);
}
END_TEST
@@ -411,15 +808,17 @@ START_TEST(test_utf8_auto_align)
const char * const fromLimInitially = fromLim;
ptrdiff_t actualMovementInChars;
- align_limit_to_full_utf8_characters(cases[i].input, &fromLim);
+ _INTERNAL_trim_to_complete_utf8_characters(cases[i].input, &fromLim);
actualMovementInChars = (fromLim - fromLimInitially);
if (actualMovementInChars != cases[i].expectedMovementInChars) {
size_t j = 0;
success = false;
- printf("[-] UTF-8 case %2lu: Expected movement by %2ld chars"
- ", actually moved by %2ld chars: \"",
- i + 1, cases[i].expectedMovementInChars, actualMovementInChars);
+ printf("[-] UTF-8 case %2u: Expected movement by %2d chars"
+ ", actually moved by %2d chars: \"",
+ (unsigned)(i + 1),
+ (int)cases[i].expectedMovementInChars,
+ (int)actualMovementInChars);
for (; j < strlen(cases[i].input); j++) {
printf("\\x%02x", (unsigned char)cases[i].input[j]);
}
@@ -436,18 +835,31 @@ END_TEST
START_TEST(test_utf16)
{
/* <?xml version="1.0" encoding="UTF-16"?>
- <doc a='123'>some text</doc>
- */
+ * <doc a='123'>some {A} text</doc>
+ *
+ * where {A} is U+FF21, FULLWIDTH LATIN CAPITAL LETTER A
+ */
char text[] =
"\000<\000?\000x\000m\000\154\000 \000v\000e\000r\000s\000i\000o"
"\000n\000=\000'\0001\000.\000\060\000'\000 \000e\000n\000c\000o"
"\000d\000i\000n\000g\000=\000'\000U\000T\000F\000-\0001\000\066"
"\000'\000?\000>\000\n"
- "\000<\000d\000o\000c\000 \000a\000=\000'\0001\0002\0003\000'"
- "\000>\000s\000o\000m\000e\000 \000t\000e\000x\000t\000<\000/"
- "\000d\000o\000c\000>";
+ "\000<\000d\000o\000c\000 \000a\000=\000'\0001\0002\0003\000'\000>"
+ "\000s\000o\000m\000e\000 \xff\x21\000 \000t\000e\000x\000t\000"
+ "<\000/\000d\000o\000c\000>";
+#ifdef XML_UNICODE
+ const XML_Char *expected = XCS("some \xff21 text");
+#else
+ const XML_Char *expected = XCS("some \357\274\241 text");
+#endif
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetUserData(parser, &storage);
+ XML_SetCharacterDataHandler(parser, accumulate_characters);
if (_XML_Parse_SINGLE_BYTES(parser, text, sizeof(text)-1, XML_TRUE) == XML_STATUS_ERROR)
xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
}
END_TEST
@@ -474,6 +886,34 @@ START_TEST(test_utf16_le_epilog_newline)
}
END_TEST
+/* Test that an outright lie in the encoding is faulted */
+START_TEST(test_not_utf16)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='utf-16'?>"
+ "<doc>Hi</doc>";
+
+ /* Use a handler to provoke the appropriate code paths */
+ XML_SetXmlDeclHandler(parser, dummy_xdecl_handler);
+ expect_failure(text,
+ XML_ERROR_INCORRECT_ENCODING,
+ "UTF-16 declared in UTF-8 not faulted");
+}
+END_TEST
+
+/* Test that an unknown encoding is rejected */
+START_TEST(test_bad_encoding)
+{
+ const char *text = "<doc>Hi</doc>";
+
+ if (!XML_SetEncoding(parser, XCS("unknown-encoding")))
+ fail("XML_SetEncoding failed");
+ expect_failure(text,
+ XML_ERROR_UNKNOWN_ENCODING,
+ "Unknown encoding not faulted");
+}
+END_TEST
+
/* Regression test for SF bug #481609, #774028. */
START_TEST(test_latin1_umlauts)
{
@@ -481,13 +921,167 @@ START_TEST(test_latin1_umlauts)
"<?xml version='1.0' encoding='iso-8859-1'?>\n"
"<e a='\xE4 \xF6 \xFC &#228; &#246; &#252; &#x00E4; &#x0F6; &#xFC; >'\n"
" >\xE4 \xF6 \xFC &#228; &#246; &#252; &#x00E4; &#x0F6; &#xFC; ></e>";
- const char *utf8 =
- "\xC3\xA4 \xC3\xB6 \xC3\xBC "
- "\xC3\xA4 \xC3\xB6 \xC3\xBC "
- "\xC3\xA4 \xC3\xB6 \xC3\xBC >";
- run_character_check(text, utf8);
+#ifdef XML_UNICODE
+ /* Expected results in UTF-16 */
+ const XML_Char *expected =
+ XCS("\x00e4 \x00f6 \x00fc ")
+ XCS("\x00e4 \x00f6 \x00fc ")
+ XCS("\x00e4 \x00f6 \x00fc >");
+#else
+ /* Expected results in UTF-8 */
+ const XML_Char *expected =
+ XCS("\xC3\xA4 \xC3\xB6 \xC3\xBC ")
+ XCS("\xC3\xA4 \xC3\xB6 \xC3\xBC ")
+ XCS("\xC3\xA4 \xC3\xB6 \xC3\xBC >");
+#endif
+
+ run_character_check(text, expected);
XML_ParserReset(parser, NULL);
- run_attribute_check(text, utf8);
+ run_attribute_check(text, expected);
+ /* Repeat with a default handler */
+ XML_ParserReset(parser, NULL);
+ XML_SetDefaultHandler(parser, dummy_default_handler);
+ run_character_check(text, expected);
+ XML_ParserReset(parser, NULL);
+ XML_SetDefaultHandler(parser, dummy_default_handler);
+ run_attribute_check(text, expected);
+}
+END_TEST
+
+/* Test that an element name with a 4-byte UTF-8 character is rejected */
+START_TEST(test_long_utf8_character)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='utf-8'?>\n"
+ /* 0xf0 0x90 0x80 0x80 = U+10000, the first Linear B character */
+ "<do\xf0\x90\x80\x80/>";
+ expect_failure(text,
+ XML_ERROR_INVALID_TOKEN,
+ "4-byte UTF-8 character in element name not faulted");
+}
+END_TEST
+
+/* Test that a long latin-1 attribute (too long to convert in one go)
+ * is correctly converted
+ */
+START_TEST(test_long_latin1_attribute)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='iso-8859-1'?>\n"
+ "<doc att='"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ /* Last character splits across a buffer boundary */
+ "\xe4'>\n</doc>";
+#ifdef XML_UNICODE
+ const XML_Char *expected =
+ /* 64 characters per line */
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO")
+ XCS("\x00e4");
+#else
+ const XML_Char *expected =
+ /* 64 characters per line */
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO")
+ XCS("\xc3\xa4");
+#endif
+
+ run_attribute_check(text, expected);
+}
+END_TEST
+
+
+/* Test that a long ASCII attribute (too long to convert in one go)
+ * is correctly converted
+ */
+START_TEST(test_long_ascii_attribute)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='us-ascii'?>\n"
+ "<doc att='"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "01234'>\n</doc>";
+ const XML_Char *expected =
+ /* 64 characters per line */
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("01234");
+
+ run_attribute_check(text, expected);
}
END_TEST
@@ -530,33 +1124,27 @@ START_TEST(test_column_number_after_parse)
}
END_TEST
+#define STRUCT_START_TAG 0
+#define STRUCT_END_TAG 1
static void XMLCALL
start_element_event_handler2(void *userData, const XML_Char *name,
const XML_Char **UNUSED_P(attr))
{
- CharData *storage = (CharData *) userData;
- char buffer[100];
-
- sprintf(buffer,
- "<%s> at col:%" XML_FMT_INT_MOD "u line:%"\
- XML_FMT_INT_MOD "u\n", name,
- XML_GetCurrentColumnNumber(parser),
- XML_GetCurrentLineNumber(parser));
- CharData_AppendString(storage, buffer);
+ StructData *storage = (StructData *) userData;
+ StructData_AddItem(storage, name,
+ XML_GetCurrentColumnNumber(parser),
+ XML_GetCurrentLineNumber(parser),
+ STRUCT_START_TAG);
}
static void XMLCALL
end_element_event_handler2(void *userData, const XML_Char *name)
{
- CharData *storage = (CharData *) userData;
- char buffer[100];
-
- sprintf(buffer,
- "</%s> at col:%" XML_FMT_INT_MOD "u line:%"\
- XML_FMT_INT_MOD "u\n", name,
- XML_GetCurrentColumnNumber(parser),
- XML_GetCurrentLineNumber(parser));
- CharData_AppendString(storage, buffer);
+ StructData *storage = (StructData *) userData;
+ StructData_AddItem(storage, name,
+ XML_GetCurrentColumnNumber(parser),
+ XML_GetCurrentLineNumber(parser),
+ STRUCT_END_TAG);
}
/* Regression test #3 for SF bug #653180. */
@@ -571,27 +1159,30 @@ START_TEST(test_line_and_column_numbers_inside_handlers)
" <f/>\n"
" </d>\n"
"</a>";
- const char *expected =
- "<a> at col:0 line:1\n"
- "<b> at col:2 line:2\n"
- "<c> at col:4 line:3\n"
- "</c> at col:8 line:3\n"
- "</b> at col:2 line:4\n"
- "<d> at col:2 line:5\n"
- "<f> at col:4 line:6\n"
- "</f> at col:8 line:6\n"
- "</d> at col:2 line:7\n"
- "</a> at col:0 line:8\n";
- CharData storage;
+ const StructDataEntry expected[] = {
+ { XCS("a"), 0, 1, STRUCT_START_TAG },
+ { XCS("b"), 2, 2, STRUCT_START_TAG },
+ { XCS("c"), 4, 3, STRUCT_START_TAG },
+ { XCS("c"), 8, 3, STRUCT_END_TAG },
+ { XCS("b"), 2, 4, STRUCT_END_TAG },
+ { XCS("d"), 2, 5, STRUCT_START_TAG },
+ { XCS("f"), 4, 6, STRUCT_START_TAG },
+ { XCS("f"), 8, 6, STRUCT_END_TAG },
+ { XCS("d"), 2, 7, STRUCT_END_TAG },
+ { XCS("a"), 0, 8, STRUCT_END_TAG }
+ };
+ const int expected_count = sizeof(expected) / sizeof(StructDataEntry);
+ StructData storage;
- CharData_Init(&storage);
+ StructData_Init(&storage);
XML_SetUserData(parser, &storage);
XML_SetStartElementHandler(parser, start_element_event_handler2);
XML_SetEndElementHandler(parser, end_element_event_handler2);
if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR)
xml_failure(parser);
- CharData_CheckString(&storage, expected);
+ StructData_CheckItems(&storage, expected, expected_count);
+ StructData_Dispose(&storage);
}
END_TEST
@@ -671,23 +1262,75 @@ START_TEST(test_really_long_lines)
}
END_TEST
+/* Test cdata processing across a buffer boundary */
+START_TEST(test_really_long_encoded_lines)
+{
+ /* As above, except that we want to provoke an output buffer
+ * overflow with a non-trivial encoding. For this we need to pass
+ * the whole cdata in one go, not byte-by-byte.
+ */
+ void *buffer;
+ const char *text =
+ "<?xml version='1.0' encoding='iso-8859-1'?>"
+ "<e>"
+ /* 64 chars */
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
+ /* until we have at least 1024 characters on the line: */
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+"
+ "</e>";
+ int parse_len = strlen(text);
+
+ /* Need a cdata handler to provoke the code path we want to test */
+ XML_SetCharacterDataHandler(parser, dummy_cdata_handler);
+ buffer = XML_GetBuffer(parser, parse_len);
+ if (buffer == NULL)
+ fail("Could not allocate parse buffer");
+ memcpy(buffer, text, parse_len);
+ if (XML_ParseBuffer(parser, parse_len, XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
/*
* Element event tests.
*/
static void XMLCALL
+start_element_event_handler(void *userData,
+ const XML_Char *name,
+ const XML_Char **UNUSED_P(atts))
+{
+ CharData_AppendXMLChars((CharData *)userData, name, -1);
+}
+
+static void XMLCALL
end_element_event_handler(void *userData, const XML_Char *name)
{
CharData *storage = (CharData *) userData;
- CharData_AppendString(storage, "/");
+ CharData_AppendXMLChars(storage, XCS("/"), 1);
CharData_AppendXMLChars(storage, name, -1);
}
START_TEST(test_end_element_events)
{
const char *text = "<a><b><c/></b><d><f/></d></a>";
- const char *expected = "/c/b/f/d/a";
+ const XML_Char *expected = XCS("/c/b/f/d/a");
CharData storage;
CharData_Init(&storage);
@@ -695,7 +1338,7 @@ START_TEST(test_end_element_events)
XML_SetEndElementHandler(parser, end_element_event_handler);
if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR)
xml_failure(parser);
- CharData_CheckString(&storage, expected);
+ CharData_CheckXMLChars(&storage, expected);
}
END_TEST
@@ -719,9 +1362,9 @@ is_whitespace_normalized(const XML_Char *s, int is_cdata)
int blanks = 0;
int at_start = 1;
while (*s) {
- if (*s == ' ')
+ if (*s == XCS(' '))
++blanks;
- else if (*s == '\t' || *s == '\n' || *s == '\r')
+ else if (*s == XCS('\t') || *s == XCS('\n') || *s == XCS('\r'))
return 0;
else {
if (at_start) {
@@ -745,25 +1388,25 @@ is_whitespace_normalized(const XML_Char *s, int is_cdata)
static void
testhelper_is_whitespace_normalized(void)
{
- assert(is_whitespace_normalized("abc", 0));
- assert(is_whitespace_normalized("abc", 1));
- assert(is_whitespace_normalized("abc def ghi", 0));
- assert(is_whitespace_normalized("abc def ghi", 1));
- assert(!is_whitespace_normalized(" abc def ghi", 0));
- assert(is_whitespace_normalized(" abc def ghi", 1));
- assert(!is_whitespace_normalized("abc def ghi", 0));
- assert(is_whitespace_normalized("abc def ghi", 1));
- assert(!is_whitespace_normalized("abc def ghi ", 0));
- assert(is_whitespace_normalized("abc def ghi ", 1));
- assert(!is_whitespace_normalized(" ", 0));
- assert(is_whitespace_normalized(" ", 1));
- assert(!is_whitespace_normalized("\t", 0));
- assert(!is_whitespace_normalized("\t", 1));
- assert(!is_whitespace_normalized("\n", 0));
- assert(!is_whitespace_normalized("\n", 1));
- assert(!is_whitespace_normalized("\r", 0));
- assert(!is_whitespace_normalized("\r", 1));
- assert(!is_whitespace_normalized("abc\t def", 1));
+ assert(is_whitespace_normalized(XCS("abc"), 0));
+ assert(is_whitespace_normalized(XCS("abc"), 1));
+ assert(is_whitespace_normalized(XCS("abc def ghi"), 0));
+ assert(is_whitespace_normalized(XCS("abc def ghi"), 1));
+ assert(!is_whitespace_normalized(XCS(" abc def ghi"), 0));
+ assert(is_whitespace_normalized(XCS(" abc def ghi"), 1));
+ assert(!is_whitespace_normalized(XCS("abc def ghi"), 0));
+ assert(is_whitespace_normalized(XCS("abc def ghi"), 1));
+ assert(!is_whitespace_normalized(XCS("abc def ghi "), 0));
+ assert(is_whitespace_normalized(XCS("abc def ghi "), 1));
+ assert(!is_whitespace_normalized(XCS(" "), 0));
+ assert(is_whitespace_normalized(XCS(" "), 1));
+ assert(!is_whitespace_normalized(XCS("\t"), 0));
+ assert(!is_whitespace_normalized(XCS("\t"), 1));
+ assert(!is_whitespace_normalized(XCS("\n"), 0));
+ assert(!is_whitespace_normalized(XCS("\n"), 1));
+ assert(!is_whitespace_normalized(XCS("\r"), 0));
+ assert(!is_whitespace_normalized(XCS("\r"), 1));
+ assert(!is_whitespace_normalized(XCS("abc\t def"), 1));
}
static void XMLCALL
@@ -775,12 +1418,13 @@ check_attr_contains_normalized_whitespace(void *UNUSED_P(userData),
for (i = 0; atts[i] != NULL; i += 2) {
const XML_Char *attrname = atts[i];
const XML_Char *value = atts[i + 1];
- if (strcmp("attr", attrname) == 0
- || strcmp("ents", attrname) == 0
- || strcmp("refs", attrname) == 0) {
+ if (xcstrcmp(XCS("attr"), attrname) == 0
+ || xcstrcmp(XCS("ents"), attrname) == 0
+ || xcstrcmp(XCS("refs"), attrname) == 0) {
if (!is_whitespace_normalized(value, 0)) {
char buffer[256];
- sprintf(buffer, "attribute value not normalized: %s='%s'",
+ sprintf(buffer, "attribute value not normalized: %"
+ XML_FMT_STR "='%" XML_FMT_STR "'",
attrname, value);
fail(buffer);
}
@@ -826,11 +1470,36 @@ START_TEST(test_xmldecl_misplaced)
}
END_TEST
+START_TEST(test_xmldecl_invalid)
+{
+ expect_failure("<?xml version='1.0' \xc3\xa7?>\n<doc/>",
+ XML_ERROR_XML_DECL,
+ "Failed to report invalid XML declaration");
+}
+END_TEST
+
+START_TEST(test_xmldecl_missing_attr)
+{
+ expect_failure("<?xml ='1.0'?>\n<doc/>\n",
+ XML_ERROR_XML_DECL,
+ "Failed to report missing XML declaration attribute");
+}
+END_TEST
+
+START_TEST(test_xmldecl_missing_value)
+{
+ expect_failure("<?xml version='1.0' encoding='us-ascii' standalone?>\n"
+ "<doc/>",
+ XML_ERROR_XML_DECL,
+ "Failed to report missing attribute value");
+}
+END_TEST
+
/* Regression test for SF bug #584832. */
static int XMLCALL
UnknownEncodingHandler(void *UNUSED_P(data),const XML_Char *encoding,XML_Encoding *info)
{
- if (strcmp(encoding,"unsupported-encoding") == 0) {
+ if (xcstrcmp(encoding, XCS("unsupported-encoding")) == 0) {
int i;
for (i = 0; i < 256; ++i)
info->map[i] = i;
@@ -855,46 +1524,213 @@ START_TEST(test_unknown_encoding_internal_entity)
}
END_TEST
-/* Regression test for SF bug #620106. */
+/* Test unrecognised encoding handler */
+static void dummy_release(void *UNUSED_P(data))
+{
+}
+
static int XMLCALL
-external_entity_loader_set_encoding(XML_Parser parser,
- const XML_Char *context,
- const XML_Char *UNUSED_P(base),
- const XML_Char *UNUSED_P(systemId),
- const XML_Char *UNUSED_P(publicId))
-{
- /* This text says it's an unsupported encoding, but it's really
- UTF-8, which we tell Expat using XML_SetEncoding().
- */
+UnrecognisedEncodingHandler(void *UNUSED_P(data),
+ const XML_Char *UNUSED_P(encoding),
+ XML_Encoding *info)
+{
+ info->data = NULL;
+ info->convert = NULL;
+ info->release = dummy_release;
+ return XML_STATUS_ERROR;
+}
+
+START_TEST(test_unrecognised_encoding_internal_entity)
+{
const char *text =
- "<?xml encoding='iso-8859-3'?>"
- "\xC3\xA9";
+ "<?xml version='1.0' encoding='unsupported-encoding'?>\n"
+ "<!DOCTYPE test [<!ENTITY foo 'bar'>]>\n"
+ "<test a='&foo;'/>";
+
+ XML_SetUnknownEncodingHandler(parser,
+ UnrecognisedEncodingHandler,
+ NULL);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text), XML_TRUE) != XML_STATUS_ERROR)
+ fail("Unrecognised encoding not rejected");
+}
+END_TEST
+
+/* Regression test for SF bug #620106. */
+static int XMLCALL
+external_entity_loader(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ ExtTest *test_data = (ExtTest *)XML_GetUserData(parser);
XML_Parser extparser;
extparser = XML_ExternalEntityParserCreate(parser, context, NULL);
if (extparser == NULL)
fail("Could not create external entity parser.");
- if (!XML_SetEncoding(extparser, "utf-8"))
- fail("XML_SetEncoding() ignored for external entity");
- if ( _XML_Parse_SINGLE_BYTES(extparser, text, strlen(text), XML_TRUE)
+ if (test_data->encoding != NULL) {
+ if (!XML_SetEncoding(extparser, test_data->encoding))
+ fail("XML_SetEncoding() ignored for external entity");
+ }
+ if ( _XML_Parse_SINGLE_BYTES(extparser,
+ test_data->parse_text,
+ strlen(test_data->parse_text),
+ XML_TRUE)
== XML_STATUS_ERROR) {
- xml_failure(parser);
- return 0;
+ xml_failure(extparser);
+ return XML_STATUS_ERROR;
}
- return 1;
+ XML_ParserFree(extparser);
+ return XML_STATUS_OK;
}
START_TEST(test_ext_entity_set_encoding)
{
const char *text =
"<!DOCTYPE doc [\n"
- " <!ENTITY en SYSTEM 'http://xml.libexpat.org/dummy.ent'>\n"
+ " <!ENTITY en SYSTEM 'http://example.org/dummy.ent'>\n"
"]>\n"
"<doc>&en;</doc>";
+ ExtTest test_data = {
+ /* This text says it's an unsupported encoding, but it's really
+ UTF-8, which we tell Expat using XML_SetEncoding().
+ */
+ "<?xml encoding='iso-8859-3'?>\xC3\xA9",
+ XCS("utf-8"),
+ NULL
+ };
+#ifdef XML_UNICODE
+ const XML_Char *expected = XCS("\x00e9");
+#else
+ const XML_Char *expected = XCS("\xc3\xa9");
+#endif
- XML_SetExternalEntityRefHandler(parser,
- external_entity_loader_set_encoding);
- run_character_check(text, "\xC3\xA9");
+ XML_SetExternalEntityRefHandler(parser, external_entity_loader);
+ run_ext_character_check(text, &test_data, expected);
+}
+END_TEST
+
+/* Test external entities with no handler */
+START_TEST(test_ext_entity_no_handler)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY en SYSTEM 'http://example.org/dummy.ent'>\n"
+ "]>\n"
+ "<doc>&en;</doc>";
+
+ XML_SetDefaultHandler(parser, dummy_default_handler);
+ run_character_check(text, XCS(""));
+}
+END_TEST
+
+/* Test UTF-8 BOM is accepted */
+START_TEST(test_ext_entity_set_bom)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY en SYSTEM 'http://example.org/dummy.ent'>\n"
+ "]>\n"
+ "<doc>&en;</doc>";
+ ExtTest test_data = {
+ "\xEF\xBB\xBF" /* BOM */
+ "<?xml encoding='iso-8859-3'?>"
+ "\xC3\xA9",
+ XCS("utf-8"),
+ NULL
+ };
+#ifdef XML_UNICODE
+ const XML_Char *expected = XCS("\x00e9");
+#else
+ const XML_Char *expected = XCS("\xc3\xa9");
+#endif
+
+ XML_SetExternalEntityRefHandler(parser, external_entity_loader);
+ run_ext_character_check(text, &test_data, expected);
+}
+END_TEST
+
+
+/* Test that bad encodings are faulted */
+typedef struct ext_faults
+{
+ const char *parse_text;
+ const char *fail_text;
+ const XML_Char *encoding;
+ enum XML_Error error;
+} ExtFaults;
+
+static int XMLCALL
+external_entity_faulter(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ XML_Parser ext_parser;
+ ExtFaults *fault = (ExtFaults *)XML_GetUserData(parser);
+
+ ext_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ fail("Could not create external entity parser");
+ if (fault->encoding != NULL) {
+ if (!XML_SetEncoding(ext_parser, fault->encoding))
+ fail("XML_SetEncoding failed");
+ }
+ if (_XML_Parse_SINGLE_BYTES(ext_parser,
+ fault->parse_text,
+ strlen(fault->parse_text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ fail(fault->fail_text);
+ if (XML_GetErrorCode(ext_parser) != fault->error)
+ xml_failure(ext_parser);
+
+ XML_ParserFree(ext_parser);
+ return XML_STATUS_ERROR;
+}
+
+START_TEST(test_ext_entity_bad_encoding)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY en SYSTEM 'http://example.org/dummy.ent'>\n"
+ "]>\n"
+ "<doc>&en;</doc>";
+ ExtFaults fault = {
+ "<?xml encoding='iso-8859-3'?>u",
+ "Unsupported encoding not faulted",
+ XCS("unknown"),
+ XML_ERROR_UNKNOWN_ENCODING
+ };
+
+ XML_SetExternalEntityRefHandler(parser, external_entity_faulter);
+ XML_SetUserData(parser, &fault);
+ expect_failure(text,
+ XML_ERROR_EXTERNAL_ENTITY_HANDLING,
+ "Bad encoding should not have been accepted");
+}
+END_TEST
+
+/* Try handing an invalid encoding to an external entity parser */
+START_TEST(test_ext_entity_bad_encoding_2)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='us-ascii'?>\n"
+ "<!DOCTYPE doc SYSTEM 'foo'>\n"
+ "<doc>&entity;</doc>";
+ ExtFaults fault = {
+ "<!ELEMENT doc (#PCDATA)*>",
+ "Unknown encoding not faulted",
+ XCS("unknown-encoding"),
+ XML_ERROR_UNKNOWN_ENCODING
+ };
+
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_faulter);
+ XML_SetUserData(parser, &fault);
+ expect_failure(text, XML_ERROR_EXTERNAL_ENTITY_HANDLING,
+ "Bad encoding not faulted in external entity handler");
}
END_TEST
@@ -936,27 +1772,6 @@ START_TEST(test_wfc_undeclared_entity_standalone) {
}
END_TEST
-static int XMLCALL
-external_entity_loader(XML_Parser parser,
- const XML_Char *context,
- const XML_Char *UNUSED_P(base),
- const XML_Char *UNUSED_P(systemId),
- const XML_Char *UNUSED_P(publicId))
-{
- char *text = (char *)XML_GetUserData(parser);
- XML_Parser extparser;
-
- extparser = XML_ExternalEntityParserCreate(parser, context, NULL);
- if (extparser == NULL)
- fail("Could not create external entity parser.");
- if ( _XML_Parse_SINGLE_BYTES(extparser, text, strlen(text), XML_TRUE)
- == XML_STATUS_ERROR) {
- xml_failure(parser);
- return XML_STATUS_ERROR;
- }
- return XML_STATUS_OK;
-}
-
/* Test that an error is reported for unknown entities if we have read
an external subset, and standalone is true.
*/
@@ -965,11 +1780,14 @@ START_TEST(test_wfc_undeclared_entity_with_external_subset_standalone) {
"<?xml version='1.0' encoding='us-ascii' standalone='yes'?>\n"
"<!DOCTYPE doc SYSTEM 'foo'>\n"
"<doc>&entity;</doc>";
- char foo_text[] =
- "<!ELEMENT doc (#PCDATA)*>";
+ ExtTest test_data = {
+ "<!ELEMENT doc (#PCDATA)*>",
+ NULL,
+ NULL
+ };
XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
- XML_SetUserData(parser, foo_text);
+ XML_SetUserData(parser, &test_data);
XML_SetExternalEntityRefHandler(parser, external_entity_loader);
expect_failure(text,
XML_ERROR_UNDEFINED_ENTITY,
@@ -977,6 +1795,26 @@ START_TEST(test_wfc_undeclared_entity_with_external_subset_standalone) {
}
END_TEST
+/* Test that external entity handling is not done if the parsing flag
+ * is set to UNLESS_STANDALONE
+ */
+START_TEST(test_entity_with_external_subset_unless_standalone) {
+ const char *text =
+ "<?xml version='1.0' encoding='us-ascii' standalone='yes'?>\n"
+ "<!DOCTYPE doc SYSTEM 'foo'>\n"
+ "<doc>&entity;</doc>";
+ ExtTest test_data = { "<!ENTITY entity 'bar'>", NULL, NULL };
+
+ XML_SetParamEntityParsing(parser,
+ XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE);
+ XML_SetUserData(parser, &test_data);
+ XML_SetExternalEntityRefHandler(parser, external_entity_loader);
+ expect_failure(text,
+ XML_ERROR_UNDEFINED_ENTITY,
+ "Parser did not report undefined entity");
+}
+END_TEST
+
/* Test that no error is reported for unknown entities if we have read
an external subset, and standalone is false.
*/
@@ -985,14 +1823,80 @@ START_TEST(test_wfc_undeclared_entity_with_external_subset) {
"<?xml version='1.0' encoding='us-ascii'?>\n"
"<!DOCTYPE doc SYSTEM 'foo'>\n"
"<doc>&entity;</doc>";
- char foo_text[] =
- "<!ELEMENT doc (#PCDATA)*>";
+ ExtTest test_data = {
+ "<!ELEMENT doc (#PCDATA)*>",
+ NULL,
+ NULL
+ };
XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
- XML_SetUserData(parser, foo_text);
XML_SetExternalEntityRefHandler(parser, external_entity_loader);
- if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR)
- xml_failure(parser);
+ run_ext_character_check(text, &test_data, XCS(""));
+}
+END_TEST
+
+/* Test that an error is reported if our NotStandalone handler fails */
+static int XMLCALL
+reject_not_standalone_handler(void *UNUSED_P(userData))
+{
+ return XML_STATUS_ERROR;
+}
+
+START_TEST(test_not_standalone_handler_reject)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='us-ascii'?>\n"
+ "<!DOCTYPE doc SYSTEM 'foo'>\n"
+ "<doc>&entity;</doc>";
+ ExtTest test_data = {
+ "<!ELEMENT doc (#PCDATA)*>",
+ NULL,
+ NULL
+ };
+
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetUserData(parser, &test_data);
+ XML_SetExternalEntityRefHandler(parser, external_entity_loader);
+ XML_SetNotStandaloneHandler(parser, reject_not_standalone_handler);
+ expect_failure(text, XML_ERROR_NOT_STANDALONE,
+ "NotStandalone handler failed to reject");
+
+ /* Try again but without external entity handling */
+ XML_ParserReset(parser, NULL);
+ XML_SetNotStandaloneHandler(parser, reject_not_standalone_handler);
+ expect_failure(text, XML_ERROR_NOT_STANDALONE,
+ "NotStandalone handler failed to reject");
+}
+END_TEST
+
+/* Test that no error is reported if our NotStandalone handler succeeds */
+static int XMLCALL
+accept_not_standalone_handler(void *UNUSED_P(userData))
+{
+ return XML_STATUS_OK;
+}
+
+START_TEST(test_not_standalone_handler_accept)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='us-ascii'?>\n"
+ "<!DOCTYPE doc SYSTEM 'foo'>\n"
+ "<doc>&entity;</doc>";
+ ExtTest test_data = {
+ "<!ELEMENT doc (#PCDATA)*>",
+ NULL,
+ NULL
+ };
+
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_loader);
+ XML_SetNotStandaloneHandler(parser, accept_not_standalone_handler);
+ run_ext_character_check(text, &test_data, XCS(""));
+
+ /* Repeat wtihout the external entity handler */
+ XML_ParserReset(parser, NULL);
+ XML_SetNotStandaloneHandler(parser, accept_not_standalone_handler);
+ run_character_check(text, XCS(""));
}
END_TEST
@@ -1010,13 +1914,57 @@ START_TEST(test_wfc_no_recursive_entity_refs)
}
END_TEST
+/* Test incomplete external entities are faulted */
+START_TEST(test_ext_entity_invalid_parse)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY en SYSTEM 'http://example.org/dummy.ent'>\n"
+ "]>\n"
+ "<doc>&en;</doc>";
+ const ExtFaults faults[] = {
+ {
+ "<",
+ "Incomplete element declaration not faulted",
+ NULL,
+ XML_ERROR_UNCLOSED_TOKEN
+ },
+ {
+ "<\xe2\x82", /* First two bytes of a three-byte char */
+ "Incomplete character not faulted",
+ NULL,
+ XML_ERROR_PARTIAL_CHAR
+ },
+ {
+ "<tag>\xe2\x82",
+ "Incomplete character in CDATA not faulted",
+ NULL,
+ XML_ERROR_PARTIAL_CHAR
+ },
+ { NULL, NULL, NULL, XML_ERROR_NONE }
+ };
+ const ExtFaults *fault = faults;
+
+ for (; fault->parse_text != NULL; fault++) {
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_faulter);
+ XML_SetUserData(parser, (void *)fault);
+ expect_failure(text,
+ XML_ERROR_EXTERNAL_ENTITY_HANDLING,
+ "Parser did not report external entity error");
+ XML_ParserReset(parser, NULL);
+ }
+}
+END_TEST
+
+
/* Regression test for SF bug #483514. */
START_TEST(test_dtd_default_handling)
{
const char *text =
"<!DOCTYPE doc [\n"
- "<!ENTITY e SYSTEM 'http://xml.libexpat.org/e'>\n"
- "<!NOTATION n SYSTEM 'http://xml.libexpat.org/n'>\n"
+ "<!ENTITY e SYSTEM 'http://example.org/e'>\n"
+ "<!NOTATION n SYSTEM 'http://example.org/n'>\n"
"<!ELEMENT doc EMPTY>\n"
"<!ATTLIST doc a CDATA #IMPLIED>\n"
"<?pi in dtd?>\n"
@@ -1024,16 +1972,122 @@ START_TEST(test_dtd_default_handling)
"]><doc/>";
XML_SetDefaultHandler(parser, accumulate_characters);
- XML_SetDoctypeDeclHandler(parser,
- dummy_start_doctype_handler,
- dummy_end_doctype_handler);
+ XML_SetStartDoctypeDeclHandler(parser, dummy_start_doctype_handler);
+ XML_SetEndDoctypeDeclHandler(parser, dummy_end_doctype_handler);
XML_SetEntityDeclHandler(parser, dummy_entity_decl_handler);
XML_SetNotationDeclHandler(parser, dummy_notation_decl_handler);
XML_SetElementDeclHandler(parser, dummy_element_decl_handler);
XML_SetAttlistDeclHandler(parser, dummy_attlist_decl_handler);
XML_SetProcessingInstructionHandler(parser, dummy_pi_handler);
XML_SetCommentHandler(parser, dummy_comment_handler);
- run_character_check(text, "\n\n\n\n\n\n\n<doc/>");
+ XML_SetStartCdataSectionHandler(parser, dummy_start_cdata_handler);
+ XML_SetEndCdataSectionHandler(parser, dummy_end_cdata_handler);
+ run_character_check(text, XCS("\n\n\n\n\n\n\n<doc/>"));
+}
+END_TEST
+
+/* Test handling of attribute declarations */
+typedef struct AttTest {
+ const char *definition;
+ const XML_Char *element_name;
+ const XML_Char *attr_name;
+ const XML_Char *attr_type;
+ const XML_Char *default_value;
+ int is_required;
+} AttTest;
+
+static void XMLCALL
+verify_attlist_decl_handler(void *userData,
+ const XML_Char *element_name,
+ const XML_Char *attr_name,
+ const XML_Char *attr_type,
+ const XML_Char *default_value,
+ int is_required)
+{
+ AttTest *at = (AttTest *)userData;
+
+ if (xcstrcmp(element_name, at->element_name))
+ fail("Unexpected element name in attribute declaration");
+ if (xcstrcmp(attr_name, at->attr_name))
+ fail("Unexpected attribute name in attribute declaration");
+ if (xcstrcmp(attr_type, at->attr_type))
+ fail("Unexpected attribute type in attribute declaration");
+ if ((default_value == NULL && at->default_value != NULL) ||
+ (default_value != NULL && at->default_value == NULL) ||
+ (default_value != NULL && xcstrcmp(default_value, at->default_value)))
+ fail("Unexpected default value in attribute declaration");
+ if (is_required != at->is_required)
+ fail("Requirement mismatch in attribute declaration");
+}
+
+START_TEST(test_dtd_attr_handling)
+{
+ const char *prolog =
+ "<!DOCTYPE doc [\n"
+ "<!ELEMENT doc EMPTY>\n";
+ AttTest attr_data[] = {
+ {
+ "<!ATTLIST doc a ( one | two | three ) #REQUIRED>\n"
+ "]>"
+ "<doc a='two'/>",
+ XCS("doc"),
+ XCS("a"),
+ XCS("(one|two|three)"), /* Extraneous spaces will be removed */
+ NULL,
+ XML_TRUE
+ },
+ {
+ "<!NOTATION foo SYSTEM 'http://example.org/foo'>\n"
+ "<!ATTLIST doc a NOTATION (foo) #IMPLIED>\n"
+ "]>"
+ "<doc/>",
+ XCS("doc"),
+ XCS("a"),
+ XCS("NOTATION(foo)"),
+ NULL,
+ XML_FALSE
+ },
+ {
+ "<!ATTLIST doc a NOTATION (foo) 'bar'>\n"
+ "]>"
+ "<doc/>",
+ XCS("doc"),
+ XCS("a"),
+ XCS("NOTATION(foo)"),
+ XCS("bar"),
+ XML_FALSE
+ },
+ {
+ "<!ATTLIST doc a CDATA '\xdb\xb2'>\n"
+ "]>"
+ "<doc/>",
+ XCS("doc"),
+ XCS("a"),
+ XCS("CDATA"),
+#ifdef XML_UNICODE
+ XCS("\x06f2"),
+#else
+ XCS("\xdb\xb2"),
+#endif
+ XML_FALSE
+ },
+ { NULL, NULL, NULL, NULL, NULL, XML_FALSE }
+ };
+ AttTest *test;
+
+ for (test = attr_data; test->definition != NULL; test++) {
+ XML_SetAttlistDeclHandler(parser, verify_attlist_decl_handler);
+ XML_SetUserData(parser, test);
+ if (_XML_Parse_SINGLE_BYTES(parser, prolog, strlen(prolog),
+ XML_FALSE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ if (_XML_Parse_SINGLE_BYTES(parser,
+ test->definition,
+ strlen(test->definition),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ XML_ParserReset(parser, NULL);
+ }
}
END_TEST
@@ -1046,7 +2100,7 @@ END_TEST
START_TEST(test_empty_ns_without_namespaces)
{
const char *text =
- "<doc xmlns:prefix='http://www.example.com/'>\n"
+ "<doc xmlns:prefix='http://example.org/'>\n"
" <e xmlns:prefix=''/>\n"
"</doc>";
@@ -1064,7 +2118,7 @@ START_TEST(test_ns_in_attribute_default_without_namespaces)
const char *text =
"<!DOCTYPE e:element [\n"
" <!ATTLIST e:element\n"
- " xmlns:e CDATA 'http://example.com/'>\n"
+ " xmlns:e CDATA 'http://example.org/'>\n"
" ]>\n"
"<e:element/>";
@@ -1146,18 +2200,97 @@ START_TEST(test_suspend_parser_between_char_data_calls)
xml_failure(parser);
if (XML_GetErrorCode(parser) != XML_ERROR_NONE)
xml_failure(parser);
+ /* Try parsing directly */
+ if (XML_Parse(parser, text, strlen(text), XML_TRUE) != XML_STATUS_ERROR)
+ fail("Attempt to continue parse while suspended not faulted");
+ if (XML_GetErrorCode(parser) != XML_ERROR_SUSPENDED)
+ fail("Suspended parse not faulted with correct error");
}
END_TEST
+
+static XML_Bool abortable = XML_FALSE;
+
+static void
+parser_stop_character_handler(void *UNUSED_P(userData),
+ const XML_Char *UNUSED_P(s),
+ int UNUSED_P(len))
+{
+ XML_StopParser(parser, resumable);
+ XML_SetCharacterDataHandler(parser, NULL);
+ if (!resumable) {
+ /* Check that aborting an aborted parser is faulted */
+ if (XML_StopParser(parser, XML_FALSE) != XML_STATUS_ERROR)
+ fail("Aborting aborted parser not faulted");
+ if (XML_GetErrorCode(parser) != XML_ERROR_FINISHED)
+ xml_failure(parser);
+ } else if (abortable) {
+ /* Check that aborting a suspended parser works */
+ if (XML_StopParser(parser, XML_FALSE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ } else {
+ /* Check that suspending a suspended parser works */
+ if (XML_StopParser(parser, XML_TRUE) != XML_STATUS_ERROR)
+ fail("Suspending suspended parser not faulted");
+ if (XML_GetErrorCode(parser) != XML_ERROR_SUSPENDED)
+ xml_failure(parser);
+ }
+}
+
+/* Test repeated calls to XML_StopParser are handled correctly */
+START_TEST(test_repeated_stop_parser_between_char_data_calls)
+{
+ const char *text = long_character_data_text;
+
+ XML_SetCharacterDataHandler(parser, parser_stop_character_handler);
+ resumable = XML_FALSE;
+ abortable = XML_FALSE;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ fail("Failed to double-stop parser");
+
+ XML_ParserReset(parser, NULL);
+ XML_SetCharacterDataHandler(parser, parser_stop_character_handler);
+ resumable = XML_TRUE;
+ abortable = XML_FALSE;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_SUSPENDED)
+ fail("Failed to double-suspend parser");
+
+ XML_ParserReset(parser, NULL);
+ XML_SetCharacterDataHandler(parser, parser_stop_character_handler);
+ resumable = XML_TRUE;
+ abortable = XML_TRUE;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ fail("Failed to suspend-abort parser");
+}
+END_TEST
+
+
START_TEST(test_good_cdata_ascii)
{
const char *text = "<a><![CDATA[<greeting>Hello, world!</greeting>]]></a>";
- const char *expected = "<greeting>Hello, world!</greeting>";
+ const XML_Char *expected = XCS("<greeting>Hello, world!</greeting>");
CharData storage;
CharData_Init(&storage);
XML_SetUserData(parser, &storage);
XML_SetCharacterDataHandler(parser, accumulate_characters);
+ /* Add start and end handlers for coverage */
+ XML_SetStartCdataSectionHandler(parser, dummy_start_cdata_handler);
+ XML_SetEndCdataSectionHandler(parser, dummy_end_cdata_handler);
+
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+
+ /* Try again, this time with a default handler */
+ XML_ParserReset(parser, NULL);
+ CharData_Init(&storage);
+ XML_SetUserData(parser, &storage);
+ XML_SetCharacterDataHandler(parser, accumulate_characters);
+ XML_SetDefaultHandler(parser, dummy_default_handler);
if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR)
xml_failure(parser);
@@ -1177,9 +2310,146 @@ START_TEST(test_good_cdata_utf16)
" \0e\0n\0c\0o\0d\0i\0n\0g\0=\0'\0u\0t\0f\0-\0""1\0""6\0'"
"\0?\0>\0\n"
"\0<\0a\0>\0<\0!\0[\0C\0D\0A\0T\0A\0[\0h\0e\0l\0l\0o\0]\0]\0>\0<\0/\0a\0>";
- const char *expected = "hello";
+ const XML_Char *expected = XCS("hello");
+
+ CharData storage;
+ CharData_Init(&storage);
+ XML_SetUserData(parser, &storage);
+ XML_SetCharacterDataHandler(parser, accumulate_characters);
+
+ if (_XML_Parse_SINGLE_BYTES(parser, text, sizeof(text) - 1, XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+START_TEST(test_good_cdata_utf16_le)
+{
+ /* Test data is:
+ * <?xml version='1.0' encoding='utf-16'?>
+ * <a><![CDATA[hello]]></a>
+ */
+ const char text[] =
+ "<\0?\0x\0m\0l\0"
+ " \0v\0e\0r\0s\0i\0o\0n\0=\0'\0\x31\0.\0\x30\0'\0"
+ " \0e\0n\0c\0o\0d\0i\0n\0g\0=\0'\0u\0t\0f\0-\0""1\0""6\0'"
+ "\0?\0>\0\n"
+ "\0<\0a\0>\0<\0!\0[\0C\0D\0A\0T\0A\0[\0h\0e\0l\0l\0o\0]\0]\0>\0<\0/\0a\0>\0";
+ const XML_Char *expected = XCS("hello");
+
+ CharData storage;
+ CharData_Init(&storage);
+ XML_SetUserData(parser, &storage);
+ XML_SetCharacterDataHandler(parser, accumulate_characters);
+
+ if (_XML_Parse_SINGLE_BYTES(parser, text, sizeof(text) - 1, XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+/* Test UTF16 conversion of a long cdata string */
+
+/* 16 characters: handy macro to reduce visual clutter */
+#define A_TO_P_IN_UTF16 "\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P"
+
+START_TEST(test_long_cdata_utf16)
+{
+ /* Test data is:
+ * <?xlm version='1.0' encoding='utf-16'?>
+ * <a><![CDATA[
+ * ABCDEFGHIJKLMNOP
+ * ]]></a>
+ */
+ const char text[] =
+ "\0<\0?\0x\0m\0l\0 "
+ "\0v\0e\0r\0s\0i\0o\0n\0=\0'\0\x31\0.\0\x30\0'\0 "
+ "\0e\0n\0c\0o\0d\0i\0n\0g\0=\0'\0u\0t\0f\0-\0\x31\0\x36\0'\0?\0>"
+ "\0<\0a\0>\0<\0!\0[\0C\0D\0A\0T\0A\0["
+ /* 64 characters per line */
+ A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16
+ A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16
+ A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16
+ A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16
+ A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16
+ A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16
+ A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16
+ A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16
+ A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16
+ A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16
+ A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16
+ A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16
+ A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16
+ A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16
+ A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16
+ A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16 A_TO_P_IN_UTF16
+ A_TO_P_IN_UTF16
+ "\0]\0]\0>\0<\0/\0a\0>";
+ const XML_Char *expected =
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP")
+ XCS("ABCDEFGHIJKLMNOP";)
+ CharData storage;
+ void *buffer;
+
+ CharData_Init(&storage);
+ XML_SetUserData(parser, &storage);
+ XML_SetCharacterDataHandler(parser, accumulate_characters);
+ buffer = XML_GetBuffer(parser, sizeof(text) - 1);
+ if (buffer == NULL)
+ fail("Could not allocate parse buffer");
+ memcpy(buffer, text, sizeof(text) - 1);
+ if (XML_ParseBuffer(parser,
+ sizeof(text) - 1,
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+/* Test handling of multiple unit UTF-16 characters */
+START_TEST(test_multichar_cdata_utf16)
+{
+ /* Test data is:
+ * <?xml version='1.0' encoding='utf-16'?>
+ * <a><![CDATA[{MINIM}{CROTCHET}]]></a>
+ *
+ * where {MINIM} is U+1d15e (a minim or half-note)
+ * UTF-16: 0xd834 0xdd5e
+ * UTF-8: 0xf0 0x9d 0x85 0x9e
+ * and {CROTCHET} is U+1d15f (a crotchet or quarter-note)
+ * UTF-16: 0xd834 0xdd5f
+ * UTF-8: 0xf0 0x9d 0x85 0x9f
+ */
+ const char text[] =
+ "\0<\0?\0x\0m\0l\0"
+ " \0v\0e\0r\0s\0i\0o\0n\0=\0'\0\x31\0.\0\x30\0'\0"
+ " \0e\0n\0c\0o\0d\0i\0n\0g\0=\0'\0u\0t\0f\0-\0""1\0""6\0'"
+ "\0?\0>\0\n"
+ "\0<\0a\0>\0<\0!\0[\0C\0D\0A\0T\0A\0["
+ "\xd8\x34\xdd\x5e\xd8\x34\xdd\x5f"
+ "\0]\0]\0>\0<\0/\0a\0>";
+#ifdef XML_UNICODE
+ const XML_Char *expected = XCS("\xd834\xdd5e\xd834\xdd5f");
+#else
+ const XML_Char *expected = XCS("\xf0\x9d\x85\x9e\xf0\x9d\x85\x9f");
+#endif
CharData storage;
+
CharData_Init(&storage);
XML_SetUserData(parser, &storage);
XML_SetCharacterDataHandler(parser, accumulate_characters);
@@ -1190,6 +2460,35 @@ START_TEST(test_good_cdata_utf16)
}
END_TEST
+/* Test that an element name with a UTF-16 surrogate pair is rejected */
+START_TEST(test_utf16_bad_surrogate_pair)
+{
+ /* Test data is:
+ * <?xml version='1.0' encoding='utf-16'?>
+ * <a><![CDATA[{BADLINB}]]></a>
+ *
+ * where {BADLINB} is U+10000 (the first Linear B character)
+ * with the UTF-16 surrogate pair in the wrong order, i.e.
+ * 0xdc00 0xd800
+ */
+ const char text[] =
+ "\0<\0?\0x\0m\0l\0"
+ " \0v\0e\0r\0s\0i\0o\0n\0=\0'\0\x31\0.\0\x30\0'\0"
+ " \0e\0n\0c\0o\0d\0i\0n\0g\0=\0'\0u\0t\0f\0-\0""1\0""6\0'"
+ "\0?\0>\0\n"
+ "\0<\0a\0>\0<\0!\0[\0C\0D\0A\0T\0A\0["
+ "\xdc\x00\xd8\x00"
+ "\0]\0]\0>\0<\0/\0a\0>";
+
+ if (_XML_Parse_SINGLE_BYTES(parser, text, sizeof(text) - 1,
+ XML_TRUE) != XML_STATUS_ERROR)
+ fail("Reversed UTF-16 surrogate pair not faulted");
+ if (XML_GetErrorCode(parser) != XML_ERROR_INVALID_TOKEN)
+ xml_failure(parser);
+}
+END_TEST
+
+
START_TEST(test_bad_cdata)
{
struct CaseData {
@@ -1244,6 +2543,4533 @@ START_TEST(test_bad_cdata)
}
END_TEST
+/* Test failures in UTF-16 CDATA */
+START_TEST(test_bad_cdata_utf16)
+{
+ struct CaseData {
+ size_t text_bytes;
+ const char *text;
+ enum XML_Error expected_error;
+ };
+
+ const char prolog[] =
+ "\0<\0?\0x\0m\0l\0"
+ " \0v\0e\0r\0s\0i\0o\0n\0=\0'\0\x31\0.\0\x30\0'\0"
+ " \0e\0n\0c\0o\0d\0i\0n\0g\0=\0'\0u\0t\0f\0-\0""1\0""6\0'"
+ "\0?\0>\0\n"
+ "\0<\0a\0>";
+ struct CaseData cases[] = {
+ {1, "\0", XML_ERROR_UNCLOSED_TOKEN},
+ {2, "\0<", XML_ERROR_UNCLOSED_TOKEN},
+ {3, "\0<\0", XML_ERROR_UNCLOSED_TOKEN},
+ {4, "\0<\0!", XML_ERROR_UNCLOSED_TOKEN},
+ {5, "\0<\0!\0", XML_ERROR_UNCLOSED_TOKEN},
+ {6, "\0<\0!\0[", XML_ERROR_UNCLOSED_TOKEN},
+ {7, "\0<\0!\0[\0", XML_ERROR_UNCLOSED_TOKEN},
+ {8, "\0<\0!\0[\0C", XML_ERROR_UNCLOSED_TOKEN},
+ {9, "\0<\0!\0[\0C\0", XML_ERROR_UNCLOSED_TOKEN},
+ {10, "\0<\0!\0[\0C\0D", XML_ERROR_UNCLOSED_TOKEN},
+ {11, "\0<\0!\0[\0C\0D\0", XML_ERROR_UNCLOSED_TOKEN},
+ {12, "\0<\0!\0[\0C\0D\0A", XML_ERROR_UNCLOSED_TOKEN},
+ {13, "\0<\0!\0[\0C\0D\0A\0", XML_ERROR_UNCLOSED_TOKEN},
+ {14, "\0<\0!\0[\0C\0D\0A\0T", XML_ERROR_UNCLOSED_TOKEN},
+ {15, "\0<\0!\0[\0C\0D\0A\0T\0", XML_ERROR_UNCLOSED_TOKEN},
+ {16, "\0<\0!\0[\0C\0D\0A\0T\0A", XML_ERROR_UNCLOSED_TOKEN},
+ {17, "\0<\0!\0[\0C\0D\0A\0T\0A\0", XML_ERROR_UNCLOSED_TOKEN},
+ {18, "\0<\0!\0[\0C\0D\0A\0T\0A\0[",
+ XML_ERROR_UNCLOSED_CDATA_SECTION},
+ {19, "\0<\0!\0[\0C\0D\0A\0T\0A\0[\0",
+ XML_ERROR_UNCLOSED_CDATA_SECTION},
+ {20, "\0<\0!\0[\0C\0D\0A\0T\0A\0[\0Z",
+ XML_ERROR_UNCLOSED_CDATA_SECTION},
+ /* Now add a four-byte UTF-16 character */
+ {21, "\0<\0!\0[\0C\0D\0A\0T\0A\0[\0Z\xd8",
+ XML_ERROR_UNCLOSED_CDATA_SECTION},
+ {22, "\0<\0!\0[\0C\0D\0A\0T\0A\0[\0Z\xd8\x34",
+ XML_ERROR_PARTIAL_CHAR},
+ {23, "\0<\0!\0[\0C\0D\0A\0T\0A\0[\0Z\xd8\x34\xdd",
+ XML_ERROR_PARTIAL_CHAR},
+ {24, "\0<\0!\0[\0C\0D\0A\0T\0A\0[\0Z\xd8\x34\xdd\x5e",
+ XML_ERROR_UNCLOSED_CDATA_SECTION}
+ };
+ size_t i;
+
+ for (i = 0; i < sizeof(cases)/sizeof(struct CaseData); i++) {
+ enum XML_Status actual_status;
+ enum XML_Error actual_error;
+
+ if (_XML_Parse_SINGLE_BYTES(parser, prolog, sizeof(prolog)-1,
+ XML_FALSE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ actual_status = _XML_Parse_SINGLE_BYTES(parser,
+ cases[i].text,
+ cases[i].text_bytes,
+ XML_TRUE);
+ assert(actual_status == XML_STATUS_ERROR);
+ actual_error = XML_GetErrorCode(parser);
+ if (actual_error != cases[i].expected_error) {
+ char message[1024];
+
+ sprintf(message,
+ "Expected error %d (%" XML_FMT_STR
+ "), got %d (%" XML_FMT_STR ") for case %lu\n",
+ cases[i].expected_error,
+ XML_ErrorString(cases[i].expected_error),
+ actual_error,
+ XML_ErrorString(actual_error),
+ (long unsigned)(i+1));
+ fail(message);
+ }
+ XML_ParserReset(parser, NULL);
+ }
+}
+END_TEST
+
+static const char *long_cdata_text =
+ "<s><![CDATA["
+ "012345678901234567890123456789012345678901234567890123456789"
+ "012345678901234567890123456789012345678901234567890123456789"
+ "012345678901234567890123456789012345678901234567890123456789"
+ "012345678901234567890123456789012345678901234567890123456789"
+ "012345678901234567890123456789012345678901234567890123456789"
+ "012345678901234567890123456789012345678901234567890123456789"
+ "012345678901234567890123456789012345678901234567890123456789"
+ "012345678901234567890123456789012345678901234567890123456789"
+ "012345678901234567890123456789012345678901234567890123456789"
+ "012345678901234567890123456789012345678901234567890123456789"
+ "012345678901234567890123456789012345678901234567890123456789"
+ "012345678901234567890123456789012345678901234567890123456789"
+ "012345678901234567890123456789012345678901234567890123456789"
+ "012345678901234567890123456789012345678901234567890123456789"
+ "012345678901234567890123456789012345678901234567890123456789"
+ "012345678901234567890123456789012345678901234567890123456789"
+ "012345678901234567890123456789012345678901234567890123456789"
+ "012345678901234567890123456789012345678901234567890123456789"
+ "012345678901234567890123456789012345678901234567890123456789"
+ "012345678901234567890123456789012345678901234567890123456789"
+ "]]></s>";
+
+/* Test stopping the parser in cdata handler */
+START_TEST(test_stop_parser_between_cdata_calls)
+{
+ const char *text = long_cdata_text;
+
+ XML_SetCharacterDataHandler(parser,
+ clearing_aborting_character_handler);
+ resumable = XML_FALSE;
+ expect_failure(text, XML_ERROR_ABORTED,
+ "Parse not aborted in CDATA handler");
+}
+END_TEST
+
+/* Test suspending the parser in cdata handler */
+START_TEST(test_suspend_parser_between_cdata_calls)
+{
+ const char *text = long_cdata_text;
+ enum XML_Status result;
+
+ XML_SetCharacterDataHandler(parser,
+ clearing_aborting_character_handler);
+ resumable = XML_TRUE;
+ result = _XML_Parse_SINGLE_BYTES(parser, text, strlen(text), XML_TRUE);
+ if (result != XML_STATUS_SUSPENDED) {
+ if (result == XML_STATUS_ERROR)
+ xml_failure(parser);
+ fail("Parse not suspended in CDATA handler");
+ }
+ if (XML_GetErrorCode(parser) != XML_ERROR_NONE)
+ xml_failure(parser);
+}
+END_TEST
+
+/* Test memory allocation functions */
+START_TEST(test_memory_allocation)
+{
+ char *buffer = (char *)XML_MemMalloc(parser, 256);
+ char *p;
+
+ if (buffer == NULL) {
+ fail("Allocation failed");
+ } else {
+ /* Try writing to memory; some OSes try to cheat! */
+ buffer[0] = 'T';
+ buffer[1] = 'E';
+ buffer[2] = 'S';
+ buffer[3] = 'T';
+ buffer[4] = '\0';
+ if (strcmp(buffer, "TEST") != 0) {
+ fail("Memory not writable");
+ } else {
+ p = (char *)XML_MemRealloc(parser, buffer, 512);
+ if (p == NULL) {
+ fail("Reallocation failed");
+ } else {
+ /* Write again, just to be sure */
+ buffer = p;
+ buffer[0] = 'V';
+ if (strcmp(buffer, "VEST") != 0) {
+ fail("Reallocated memory not writable");
+ }
+ }
+ }
+ XML_MemFree(parser, buffer);
+ }
+}
+END_TEST
+
+static void XMLCALL
+record_default_handler(void *userData,
+ const XML_Char *UNUSED_P(s),
+ int UNUSED_P(len))
+{
+ CharData_AppendXMLChars((CharData *)userData, XCS("D"), 1);
+}
+
+static void XMLCALL
+record_cdata_handler(void *userData,
+ const XML_Char *UNUSED_P(s),
+ int UNUSED_P(len))
+{
+ CharData_AppendXMLChars((CharData *)userData, XCS("C"), 1);
+ XML_DefaultCurrent(parser);
+}
+
+static void XMLCALL
+record_cdata_nodefault_handler(void *userData,
+ const XML_Char *UNUSED_P(s),
+ int UNUSED_P(len))
+{
+ CharData_AppendXMLChars((CharData *)userData, XCS("c"), 1);
+}
+
+static void XMLCALL
+record_skip_handler(void *userData,
+ const XML_Char *UNUSED_P(entityName),
+ int is_parameter_entity)
+{
+ CharData_AppendXMLChars((CharData *)userData,
+ is_parameter_entity ? XCS("E") : XCS("e"), 1);
+}
+
+/* Test XML_DefaultCurrent() passes handling on correctly */
+START_TEST(test_default_current)
+{
+ const char *text = "<doc>hell]</doc>";
+ const char *entity_text =
+ "<!DOCTYPE doc [\n"
+ "<!ENTITY entity '&#37;'>\n"
+ "]>\n"
+ "<doc>&entity;</doc>";
+ CharData storage;
+
+ XML_SetDefaultHandler(parser, record_default_handler);
+ XML_SetCharacterDataHandler(parser, record_cdata_handler);
+ CharData_Init(&storage);
+ XML_SetUserData(parser, &storage);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, XCS("DCDCDCDCDCDD"));
+
+ /* Again, without the defaulting */
+ XML_ParserReset(parser, NULL);
+ XML_SetDefaultHandler(parser, record_default_handler);
+ XML_SetCharacterDataHandler(parser, record_cdata_nodefault_handler);
+ CharData_Init(&storage);
+ XML_SetUserData(parser, &storage);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, XCS("DcccccD"));
+
+ /* Now with an internal entity to complicate matters */
+ XML_ParserReset(parser, NULL);
+ XML_SetDefaultHandler(parser, record_default_handler);
+ XML_SetCharacterDataHandler(parser, record_cdata_handler);
+ CharData_Init(&storage);
+ XML_SetUserData(parser, &storage);
+ if (_XML_Parse_SINGLE_BYTES(parser, entity_text, strlen(entity_text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ /* The default handler suppresses the entity */
+ CharData_CheckXMLChars(&storage, XCS("DDDDDDDDDDDDDDDDDDD"));
+
+ /* Again, with a skip handler */
+ XML_ParserReset(parser, NULL);
+ XML_SetDefaultHandler(parser, record_default_handler);
+ XML_SetCharacterDataHandler(parser, record_cdata_handler);
+ XML_SetSkippedEntityHandler(parser, record_skip_handler);
+ CharData_Init(&storage);
+ XML_SetUserData(parser, &storage);
+ if (_XML_Parse_SINGLE_BYTES(parser, entity_text, strlen(entity_text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ /* The default handler suppresses the entity */
+ CharData_CheckXMLChars(&storage, XCS("DDDDDDDDDDDDDDDDDeD"));
+
+ /* This time, allow the entity through */
+ XML_ParserReset(parser, NULL);
+ XML_SetDefaultHandlerExpand(parser, record_default_handler);
+ XML_SetCharacterDataHandler(parser, record_cdata_handler);
+ CharData_Init(&storage);
+ XML_SetUserData(parser, &storage);
+ if (_XML_Parse_SINGLE_BYTES(parser, entity_text, strlen(entity_text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, XCS("DDDDDDDDDDDDDDDDDCDD"));
+
+ /* Finally, without passing the cdata to the default handler */
+ XML_ParserReset(parser, NULL);
+ XML_SetDefaultHandlerExpand(parser, record_default_handler);
+ XML_SetCharacterDataHandler(parser, record_cdata_nodefault_handler);
+ CharData_Init(&storage);
+ XML_SetUserData(parser, &storage);
+ if (_XML_Parse_SINGLE_BYTES(parser, entity_text, strlen(entity_text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, XCS("DDDDDDDDDDDDDDDDDcD"));
+}
+END_TEST
+
+/* Test DTD element parsing code paths */
+START_TEST(test_dtd_elements)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ "<!ELEMENT doc (chapter)>\n"
+ "<!ELEMENT chapter (#PCDATA)>\n"
+ "]>\n"
+ "<doc><chapter>Wombats are go</chapter></doc>";
+
+ XML_SetElementDeclHandler(parser, dummy_element_decl_handler);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
+/* Test foreign DTD handling */
+START_TEST(test_set_foreign_dtd)
+{
+ const char *text1 =
+ "<?xml version='1.0' encoding='us-ascii'?>\n";
+ const char *text2 =
+ "<doc>&entity;</doc>";
+ ExtTest test_data = {
+ "<!ELEMENT doc (#PCDATA)*>",
+ NULL,
+ NULL
+ };
+
+ /* Check hash salt is passed through too */
+ XML_SetHashSalt(parser, 0x12345678);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetUserData(parser, &test_data);
+ XML_SetExternalEntityRefHandler(parser, external_entity_loader);
+ /* Add a default handler to exercise more code paths */
+ XML_SetDefaultHandler(parser, dummy_default_handler);
+ if (XML_UseForeignDTD(parser, XML_TRUE) != XML_ERROR_NONE)
+ fail("Could not set foreign DTD");
+ if (_XML_Parse_SINGLE_BYTES(parser, text1, strlen(text1),
+ XML_FALSE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+
+ /* Ensure that trying to set the DTD after parsing has started
+ * is faulted, even if it's the same setting.
+ */
+ if (XML_UseForeignDTD(parser, XML_TRUE) !=
+ XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING)
+ fail("Failed to reject late foreign DTD setting");
+ /* Ditto for the hash salt */
+ if (XML_SetHashSalt(parser, 0x23456789))
+ fail("Failed to reject late hash salt change");
+
+ /* Now finish the parse */
+ if (_XML_Parse_SINGLE_BYTES(parser, text2, strlen(text2),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
+/* Test foreign DTD handling with a failing NotStandalone handler */
+START_TEST(test_foreign_dtd_not_standalone)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='us-ascii'?>\n"
+ "<doc>&entity;</doc>";
+ ExtTest test_data = {
+ "<!ELEMENT doc (#PCDATA)*>",
+ NULL,
+ NULL
+ };
+
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetUserData(parser, &test_data);
+ XML_SetExternalEntityRefHandler(parser, external_entity_loader);
+ XML_SetNotStandaloneHandler(parser, reject_not_standalone_handler);
+ if (XML_UseForeignDTD(parser, XML_TRUE) != XML_ERROR_NONE)
+ fail("Could not set foreign DTD");
+ expect_failure(text, XML_ERROR_NOT_STANDALONE,
+ "NotStandalonehandler failed to reject");
+}
+END_TEST
+
+/* Test invalid character in a foreign DTD is faulted */
+START_TEST(test_invalid_foreign_dtd)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='us-ascii'?>\n"
+ "<doc>&entity;</doc>";
+ ExtFaults test_data = {
+ "$",
+ "Dollar not faulted",
+ NULL,
+ XML_ERROR_INVALID_TOKEN
+ };
+
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetUserData(parser, &test_data);
+ XML_SetExternalEntityRefHandler(parser, external_entity_faulter);
+ XML_UseForeignDTD(parser, XML_TRUE);
+ expect_failure(text,
+ XML_ERROR_EXTERNAL_ENTITY_HANDLING,
+ "Bad DTD should not have been accepted");
+}
+END_TEST
+
+/* Test foreign DTD use with a doctype */
+START_TEST(test_foreign_dtd_with_doctype)
+{
+ const char *text1 =
+ "<?xml version='1.0' encoding='us-ascii'?>\n"
+ "<!DOCTYPE doc [<!ENTITY entity 'hello world'>]>\n";
+ const char *text2 =
+ "<doc>&entity;</doc>";
+ ExtTest test_data = {
+ "<!ELEMENT doc (#PCDATA)*>",
+ NULL,
+ NULL
+ };
+
+ /* Check hash salt is passed through too */
+ XML_SetHashSalt(parser, 0x12345678);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetUserData(parser, &test_data);
+ XML_SetExternalEntityRefHandler(parser, external_entity_loader);
+ /* Add a default handler to exercise more code paths */
+ XML_SetDefaultHandler(parser, dummy_default_handler);
+ if (XML_UseForeignDTD(parser, XML_TRUE) != XML_ERROR_NONE)
+ fail("Could not set foreign DTD");
+ if (_XML_Parse_SINGLE_BYTES(parser, text1, strlen(text1),
+ XML_FALSE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+
+ /* Ensure that trying to set the DTD after parsing has started
+ * is faulted, even if it's the same setting.
+ */
+ if (XML_UseForeignDTD(parser, XML_TRUE) !=
+ XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING)
+ fail("Failed to reject late foreign DTD setting");
+ /* Ditto for the hash salt */
+ if (XML_SetHashSalt(parser, 0x23456789))
+ fail("Failed to reject late hash salt change");
+
+ /* Now finish the parse */
+ if (_XML_Parse_SINGLE_BYTES(parser, text2, strlen(text2),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
+/* Test XML_UseForeignDTD with no external subset present */
+static int XMLCALL
+external_entity_null_loader(XML_Parser UNUSED_P(parser),
+ const XML_Char *UNUSED_P(context),
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ return XML_STATUS_OK;
+}
+
+START_TEST(test_foreign_dtd_without_external_subset)
+{
+ const char *text =
+ "<!DOCTYPE doc [<!ENTITY foo 'bar'>]>\n"
+ "<doc>&foo;</doc>";
+
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetUserData(parser, NULL);
+ XML_SetExternalEntityRefHandler(parser, external_entity_null_loader);
+ XML_UseForeignDTD(parser, XML_TRUE);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
+START_TEST(test_empty_foreign_dtd)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='us-ascii'?>\n"
+ "<doc>&entity;</doc>";
+
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_null_loader);
+ XML_UseForeignDTD(parser, XML_TRUE);
+ expect_failure(text, XML_ERROR_UNDEFINED_ENTITY,
+ "Undefined entity not faulted");
+}
+END_TEST
+
+/* Test XML Base is set and unset appropriately */
+START_TEST(test_set_base)
+{
+ const XML_Char *old_base;
+ const XML_Char *new_base = XCS("/local/file/name.xml");
+
+ old_base = XML_GetBase(parser);
+ if (XML_SetBase(parser, new_base) != XML_STATUS_OK)
+ fail("Unable to set base");
+ if (xcstrcmp(XML_GetBase(parser), new_base) != 0)
+ fail("Base setting not correct");
+ if (XML_SetBase(parser, NULL) != XML_STATUS_OK)
+ fail("Unable to NULL base");
+ if (XML_GetBase(parser) != NULL)
+ fail("Base setting not nulled");
+ XML_SetBase(parser, old_base);
+}
+END_TEST
+
+/* Test attribute counts, indexing, etc */
+typedef struct attrInfo {
+ const XML_Char *name;
+ const XML_Char *value;
+} AttrInfo;
+
+typedef struct elementInfo {
+ const XML_Char *name;
+ int attr_count;
+ const XML_Char *id_name;
+ AttrInfo *attributes;
+} ElementInfo;
+
+static void XMLCALL
+counting_start_element_handler(void *userData,
+ const XML_Char *name,
+ const XML_Char **atts)
+{
+ ElementInfo *info = (ElementInfo *)userData;
+ AttrInfo *attr;
+ int count, id, i;
+
+ while (info->name != NULL) {
+ if (!xcstrcmp(name, info->name))
+ break;
+ info++;
+ }
+ if (info->name == NULL)
+ fail("Element not recognised");
+ /* The attribute count is twice what you might expect. It is a
+ * count of items in atts, an array which contains alternating
+ * attribute names and attribute values. For the naive user this
+ * is possibly a little unexpected, but it is what the
+ * documentation in expat.h tells us to expect.
+ */
+ count = XML_GetSpecifiedAttributeCount(parser);
+ if (info->attr_count * 2 != count) {
+ fail("Not got expected attribute count");
+ return;
+ }
+ id = XML_GetIdAttributeIndex(parser);
+ if (id == -1 && info->id_name != NULL) {
+ fail("ID not present");
+ return;
+ }
+ if (id != -1 && xcstrcmp(atts[id], info->id_name)) {
+ fail("ID does not have the correct name");
+ return;
+ }
+ for (i = 0; i < info->attr_count; i++) {
+ attr = info->attributes;
+ while (attr->name != NULL) {
+ if (!xcstrcmp(atts[0], attr->name))
+ break;
+ attr++;
+ }
+ if (attr->name == NULL) {
+ fail("Attribute not recognised");
+ return;
+ }
+ if (xcstrcmp(atts[1], attr->value)) {
+ fail("Attribute has wrong value");
+ return;
+ }
+ /* Remember, two entries in atts per attribute (see above) */
+ atts += 2;
+ }
+}
+
+START_TEST(test_attributes)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ "<!ELEMENT doc (tag)>\n"
+ "<!ATTLIST doc id ID #REQUIRED>\n"
+ "]>"
+ "<doc a='1' id='one' b='2'>"
+ "<tag c='3'/>"
+ "</doc>";
+ AttrInfo doc_info[] = {
+ { XCS("a"), XCS("1") },
+ { XCS("b"), XCS("2") },
+ { XCS("id"), XCS("one") },
+ { NULL, NULL }
+ };
+ AttrInfo tag_info[] = {
+ { XCS("c"), XCS("3") },
+ { NULL, NULL }
+ };
+ ElementInfo info[] = {
+ { XCS("doc"), 3, XCS("id"), NULL },
+ { XCS("tag"), 1, NULL, NULL },
+ { NULL, 0, NULL, NULL }
+ };
+ info[0].attributes = doc_info;
+ info[1].attributes = tag_info;
+
+ XML_SetStartElementHandler(parser, counting_start_element_handler);
+ XML_SetUserData(parser, info);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
+/* Test reset works correctly in the middle of processing an internal
+ * entity. Exercises some obscure code in XML_ParserReset().
+ */
+START_TEST(test_reset_in_entity)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ "<!ENTITY wombat 'wom'>\n"
+ "<!ENTITY entity 'hi &wom; there'>\n"
+ "]>\n"
+ "<doc>&entity;</doc>";
+ XML_ParsingStatus status;
+
+ resumable = XML_TRUE;
+ XML_SetCharacterDataHandler(parser, clearing_aborting_character_handler);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text), XML_FALSE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ XML_GetParsingStatus(parser, &status);
+ if (status.parsing != XML_SUSPENDED)
+ fail("Parsing status not SUSPENDED");
+ XML_ParserReset(parser, NULL);
+ XML_GetParsingStatus(parser, &status);
+ if (status.parsing != XML_INITIALIZED)
+ fail("Parsing status doesn't reset to INITIALIZED");
+}
+END_TEST
+
+/* Test that resume correctly passes through parse errors */
+START_TEST(test_resume_invalid_parse)
+{
+ const char *text = "<doc>Hello</doc"; /* Missing closing wedge */
+
+ resumable = XML_TRUE;
+ XML_SetCharacterDataHandler(parser,
+ clearing_aborting_character_handler);
+ if (XML_Parse(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ if (XML_ResumeParser(parser) == XML_STATUS_OK)
+ fail("Resumed invalid parse not faulted");
+ if (XML_GetErrorCode(parser) != XML_ERROR_UNCLOSED_TOKEN)
+ fail("Invalid parse not correctly faulted");
+}
+END_TEST
+
+/* Test that re-suspended parses are correctly passed through */
+START_TEST(test_resume_resuspended)
+{
+ const char *text = "<doc>Hello<meep/>world</doc>";
+
+ resumable = XML_TRUE;
+ XML_SetCharacterDataHandler(parser,
+ clearing_aborting_character_handler);
+ if (XML_Parse(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ resumable = XML_TRUE;
+ XML_SetCharacterDataHandler(parser,
+ clearing_aborting_character_handler);
+ if (XML_ResumeParser(parser) != XML_STATUS_SUSPENDED)
+ fail("Resumption not suspended");
+ /* This one should succeed and finish up */
+ if (XML_ResumeParser(parser) != XML_STATUS_OK)
+ xml_failure(parser);
+}
+END_TEST
+
+/* Test that CDATA shows up correctly through a default handler */
+START_TEST(test_cdata_default)
+{
+ const char *text = "<doc><![CDATA[Hello\nworld]]></doc>";
+ const XML_Char *expected = XCS("<doc><![CDATA[Hello\nworld]]></doc>");
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetUserData(parser, &storage);
+ XML_SetDefaultHandler(parser, accumulate_characters);
+
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+/* Test resetting a subordinate parser does exactly nothing */
+static int XMLCALL
+external_entity_resetter(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ const char *text = "<!ELEMENT doc (#PCDATA)*>";
+ XML_Parser ext_parser;
+ XML_ParsingStatus status;
+
+ ext_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ fail("Could not create external entity parser");
+ XML_GetParsingStatus(ext_parser, &status);
+ if (status.parsing != XML_INITIALIZED) {
+ fail("Parsing status is not INITIALIZED");
+ return XML_STATUS_ERROR;
+ }
+ if (_XML_Parse_SINGLE_BYTES(ext_parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR) {
+ xml_failure(parser);
+ return XML_STATUS_ERROR;
+ }
+ XML_GetParsingStatus(ext_parser, &status);
+ if (status.parsing != XML_FINISHED) {
+ fail("Parsing status is not FINISHED");
+ return XML_STATUS_ERROR;
+ }
+ /* Check we can't parse here */
+ if (XML_Parse(ext_parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ fail("Parsing when finished not faulted");
+ if (XML_GetErrorCode(ext_parser) != XML_ERROR_FINISHED)
+ fail("Parsing when finished faulted with wrong code");
+ XML_ParserReset(ext_parser, NULL);
+ XML_GetParsingStatus(ext_parser, &status);
+ if (status.parsing != XML_FINISHED) {
+ fail("Parsing status not still FINISHED");
+ return XML_STATUS_ERROR;
+ }
+ XML_ParserFree(ext_parser);
+ return XML_STATUS_OK;
+}
+
+START_TEST(test_subordinate_reset)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='us-ascii'?>\n"
+ "<!DOCTYPE doc SYSTEM 'foo'>\n"
+ "<doc>&entity;</doc>";
+
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_resetter);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
+
+/* Test suspending a subordinate parser */
+
+static void XMLCALL
+entity_suspending_decl_handler(void *userData,
+ const XML_Char *UNUSED_P(name),
+ XML_Content *model)
+{
+ XML_Parser ext_parser = (XML_Parser)userData;
+
+ if (XML_StopParser(ext_parser, XML_TRUE) != XML_STATUS_ERROR)
+ fail("Attempting to suspend a subordinate parser not faulted");
+ if (XML_GetErrorCode(ext_parser) != XML_ERROR_SUSPEND_PE)
+ fail("Suspending subordinate parser get wrong code");
+ XML_SetElementDeclHandler(ext_parser, NULL);
+ XML_FreeContentModel(parser, model);
+}
+
+static int XMLCALL
+external_entity_suspender(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ const char *text = "<!ELEMENT doc (#PCDATA)*>";
+ XML_Parser ext_parser;
+
+ ext_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ fail("Could not create external entity parser");
+ XML_SetElementDeclHandler(ext_parser, entity_suspending_decl_handler);
+ XML_SetUserData(ext_parser, ext_parser);
+ if (_XML_Parse_SINGLE_BYTES(ext_parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR) {
+ xml_failure(ext_parser);
+ return XML_STATUS_ERROR;
+ }
+ XML_ParserFree(ext_parser);
+ return XML_STATUS_OK;
+}
+
+START_TEST(test_subordinate_suspend)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='us-ascii'?>\n"
+ "<!DOCTYPE doc SYSTEM 'foo'>\n"
+ "<doc>&entity;</doc>";
+
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_suspender);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
+/* Test suspending a subordinate parser from an XML declaration */
+/* Increases code coverage of the tests */
+static void XMLCALL
+entity_suspending_xdecl_handler(void *userData,
+ const XML_Char *UNUSED_P(version),
+ const XML_Char *UNUSED_P(encoding),
+ int UNUSED_P(standalone))
+{
+ XML_Parser ext_parser = (XML_Parser)userData;
+
+ XML_StopParser(ext_parser, resumable);
+ XML_SetXmlDeclHandler(ext_parser, NULL);
+}
+
+static int XMLCALL
+external_entity_suspend_xmldecl(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ const char *text = "<?xml version='1.0' encoding='us-ascii'?>";
+ XML_Parser ext_parser;
+ XML_ParsingStatus status;
+ enum XML_Status rc;
+
+ ext_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ fail("Could not create external entity parser");
+ XML_SetXmlDeclHandler(ext_parser, entity_suspending_xdecl_handler);
+ XML_SetUserData(ext_parser, ext_parser);
+ rc = _XML_Parse_SINGLE_BYTES(ext_parser, text, strlen(text), XML_TRUE);
+ XML_GetParsingStatus(ext_parser, &status);
+ if (resumable) {
+ if (rc == XML_STATUS_ERROR)
+ xml_failure(ext_parser);
+ if (status.parsing != XML_SUSPENDED)
+ fail("Ext Parsing status not SUSPENDED");
+ } else {
+ if (rc != XML_STATUS_ERROR)
+ fail("Ext parsing not aborted");
+ if (XML_GetErrorCode(ext_parser) != XML_ERROR_ABORTED)
+ xml_failure(ext_parser);
+ if (status.parsing != XML_FINISHED)
+ fail("Ext Parsing status not FINISHED");
+ }
+
+ XML_ParserFree(ext_parser);
+ return XML_STATUS_OK;
+}
+
+START_TEST(test_subordinate_xdecl_suspend)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY entity SYSTEM 'http://example.org/dummy.ent'>\n"
+ "]>\n"
+ "<doc>&entity;</doc>";
+
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser,
+ external_entity_suspend_xmldecl);
+ resumable = XML_TRUE;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
+START_TEST(test_subordinate_xdecl_abort)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY entity SYSTEM 'http://example.org/dummy.ent'>\n"
+ "]>\n"
+ "<doc>&entity;</doc>";
+
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser,
+ external_entity_suspend_xmldecl);
+ resumable = XML_FALSE;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
+/* Test external entity fault handling with suspension */
+static int XMLCALL
+external_entity_suspending_faulter(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ XML_Parser ext_parser;
+ ExtFaults *fault = (ExtFaults *)XML_GetUserData(parser);
+ void *buffer;
+ int parse_len = strlen(fault->parse_text);
+
+ ext_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ fail("Could not create external entity parser");
+ XML_SetXmlDeclHandler(ext_parser, entity_suspending_xdecl_handler);
+ XML_SetUserData(ext_parser, ext_parser);
+ resumable = XML_TRUE;
+ buffer = XML_GetBuffer(ext_parser, parse_len);
+ if (buffer == NULL)
+ fail("Could not allocate parse buffer");
+ memcpy(buffer, fault->parse_text, parse_len);
+ if (XML_ParseBuffer(ext_parser, parse_len,
+ XML_FALSE) != XML_STATUS_SUSPENDED)
+ fail("XML declaration did not suspend");
+ if (XML_ResumeParser(ext_parser) != XML_STATUS_OK)
+ xml_failure(ext_parser);
+ if (XML_ParseBuffer(ext_parser, 0, XML_TRUE) != XML_STATUS_ERROR)
+ fail(fault->fail_text);
+ if (XML_GetErrorCode(ext_parser) != fault->error)
+ xml_failure(ext_parser);
+
+ XML_ParserFree(ext_parser);
+ return XML_STATUS_ERROR;
+}
+
+START_TEST(test_ext_entity_invalid_suspended_parse)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY en SYSTEM 'http://example.org/dummy.ent'>\n"
+ "]>\n"
+ "<doc>&en;</doc>";
+ ExtFaults faults[] = {
+ {
+ "<?xml version='1.0' encoding='us-ascii'?><",
+ "Incomplete element declaration not faulted",
+ NULL,
+ XML_ERROR_UNCLOSED_TOKEN
+ },
+ {
+ /* First two bytes of a three-byte char */
+ "<?xml version='1.0' encoding='utf-8'?>\xe2\x82",
+ "Incomplete character not faulted",
+ NULL,
+ XML_ERROR_PARTIAL_CHAR
+ },
+ { NULL, NULL, NULL, XML_ERROR_NONE }
+ };
+ ExtFaults *fault;
+
+ for (fault = &faults[0]; fault->parse_text != NULL; fault++) {
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser,
+ external_entity_suspending_faulter);
+ XML_SetUserData(parser, fault);
+ expect_failure(text,
+ XML_ERROR_EXTERNAL_ENTITY_HANDLING,
+ "Parser did not report external entity error");
+ XML_ParserReset(parser, NULL);
+ }
+}
+END_TEST
+
+
+
+/* Test setting an explicit encoding */
+START_TEST(test_explicit_encoding)
+{
+ const char *text1 = "<doc>Hello ";
+ const char *text2 = " World</doc>";
+
+ /* Just check that we can set the encoding to NULL before starting */
+ if (XML_SetEncoding(parser, NULL) != XML_STATUS_OK)
+ fail("Failed to initialise encoding to NULL");
+ /* Say we are UTF-8 */
+ if (XML_SetEncoding(parser, XCS("utf-8")) != XML_STATUS_OK)
+ fail("Failed to set explicit encoding");
+ if (_XML_Parse_SINGLE_BYTES(parser, text1, strlen(text1),
+ XML_FALSE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ /* Try to switch encodings mid-parse */
+ if (XML_SetEncoding(parser, XCS("us-ascii")) != XML_STATUS_ERROR)
+ fail("Allowed encoding change");
+ if (_XML_Parse_SINGLE_BYTES(parser, text2, strlen(text2),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ /* Try now the parse is over */
+ if (XML_SetEncoding(parser, NULL) != XML_STATUS_OK)
+ fail("Failed to unset encoding");
+}
+END_TEST
+
+
+/* Test handling of trailing CR (rather than newline) */
+static void XMLCALL
+cr_cdata_handler(void *userData, const XML_Char *s, int len)
+{
+ int *pfound = (int *)userData;
+
+ /* Internal processing turns the CR into a newline for the
+ * character data handler, but not for the default handler
+ */
+ if (len == 1 && (*s == XCS('\n') || *s == XCS('\r')))
+ *pfound = 1;
+}
+
+START_TEST(test_trailing_cr)
+{
+ const char *text = "<doc>\r";
+ int found_cr;
+
+ /* Try with a character handler, for code coverage */
+ XML_SetCharacterDataHandler(parser, cr_cdata_handler);
+ XML_SetUserData(parser, &found_cr);
+ found_cr = 0;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_OK)
+ fail("Failed to fault unclosed doc");
+ if (found_cr == 0)
+ fail("Did not catch the carriage return");
+ XML_ParserReset(parser, NULL);
+
+ /* Now with a default handler instead */
+ XML_SetDefaultHandler(parser, cr_cdata_handler);
+ XML_SetUserData(parser, &found_cr);
+ found_cr = 0;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_OK)
+ fail("Failed to fault unclosed doc");
+ if (found_cr == 0)
+ fail("Did not catch default carriage return");
+}
+END_TEST
+
+/* Test trailing CR in an external entity parse */
+static int XMLCALL
+external_entity_cr_catcher(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ const char *text = "\r";
+ XML_Parser ext_parser;
+
+ ext_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ fail("Could not create external entity parser");
+ XML_SetCharacterDataHandler(ext_parser, cr_cdata_handler);
+ if (_XML_Parse_SINGLE_BYTES(ext_parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(ext_parser);
+ XML_ParserFree(ext_parser);
+ return XML_STATUS_OK;
+}
+
+static int XMLCALL
+external_entity_bad_cr_catcher(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ const char *text = "<tag>\r";
+ XML_Parser ext_parser;
+
+ ext_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ fail("Could not create external entity parser");
+ XML_SetCharacterDataHandler(ext_parser, cr_cdata_handler);
+ if (_XML_Parse_SINGLE_BYTES(ext_parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_OK)
+ fail("Async entity error not caught");
+ if (XML_GetErrorCode(ext_parser) != XML_ERROR_ASYNC_ENTITY)
+ xml_failure(ext_parser);
+ XML_ParserFree(ext_parser);
+ return XML_STATUS_OK;
+}
+
+START_TEST(test_ext_entity_trailing_cr)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY en SYSTEM 'http://example.org/dummy.ent'>\n"
+ "]>\n"
+ "<doc>&en;</doc>";
+ int found_cr;
+
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_cr_catcher);
+ XML_SetUserData(parser, &found_cr);
+ found_cr = 0;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_OK)
+ xml_failure(parser);
+ if (found_cr == 0)
+ fail("No carriage return found");
+ XML_ParserReset(parser, NULL);
+
+ /* Try again with a different trailing CR */
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_bad_cr_catcher);
+ XML_SetUserData(parser, &found_cr);
+ found_cr = 0;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_OK)
+ xml_failure(parser);
+ if (found_cr == 0)
+ fail("No carriage return found");
+}
+END_TEST
+
+/* Test handling of trailing square bracket */
+static void XMLCALL
+rsqb_handler(void *userData, const XML_Char *s, int len)
+{
+ int *pfound = (int *)userData;
+
+ if (len == 1 && *s == XCS(']'))
+ *pfound = 1;
+}
+
+START_TEST(test_trailing_rsqb)
+{
+ const char *text8 = "<doc>]";
+ const char text16[] = "\xFF\xFE<\000d\000o\000c\000>\000]\000";
+ int found_rsqb;
+ int text8_len = strlen(text8);
+
+ XML_SetCharacterDataHandler(parser, rsqb_handler);
+ XML_SetUserData(parser, &found_rsqb);
+ found_rsqb = 0;
+ if (_XML_Parse_SINGLE_BYTES(parser, text8, text8_len,
+ XML_TRUE) == XML_STATUS_OK)
+ fail("Failed to fault unclosed doc");
+ if (found_rsqb == 0)
+ fail("Did not catch the right square bracket");
+
+ /* Try again with a different encoding */
+ XML_ParserReset(parser, NULL);
+ XML_SetCharacterDataHandler(parser, rsqb_handler);
+ XML_SetUserData(parser, &found_rsqb);
+ found_rsqb = 0;
+ if (_XML_Parse_SINGLE_BYTES(parser, text16, sizeof(text16)-1,
+ XML_TRUE) == XML_STATUS_OK)
+ fail("Failed to fault unclosed doc");
+ if (found_rsqb == 0)
+ fail("Did not catch the right square bracket");
+
+ /* And finally with a default handler */
+ XML_ParserReset(parser, NULL);
+ XML_SetDefaultHandler(parser, rsqb_handler);
+ XML_SetUserData(parser, &found_rsqb);
+ found_rsqb = 0;
+ if (_XML_Parse_SINGLE_BYTES(parser, text16, sizeof(text16)-1,
+ XML_TRUE) == XML_STATUS_OK)
+ fail("Failed to fault unclosed doc");
+ if (found_rsqb == 0)
+ fail("Did not catch the right square bracket");
+}
+END_TEST
+
+/* Test trailing right square bracket in an external entity parse */
+static int XMLCALL
+external_entity_rsqb_catcher(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ const char *text = "<tag>]";
+ XML_Parser ext_parser;
+
+ ext_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ fail("Could not create external entity parser");
+ XML_SetCharacterDataHandler(ext_parser, rsqb_handler);
+ if (_XML_Parse_SINGLE_BYTES(ext_parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ fail("Async entity error not caught");
+ if (XML_GetErrorCode(ext_parser) != XML_ERROR_ASYNC_ENTITY)
+ xml_failure(ext_parser);
+ XML_ParserFree(ext_parser);
+ return XML_STATUS_OK;
+}
+
+START_TEST(test_ext_entity_trailing_rsqb)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY en SYSTEM 'http://example.org/dummy.ent'>\n"
+ "]>\n"
+ "<doc>&en;</doc>";
+ int found_rsqb;
+
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_rsqb_catcher);
+ XML_SetUserData(parser, &found_rsqb);
+ found_rsqb = 0;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_OK)
+ xml_failure(parser);
+ if (found_rsqb == 0)
+ fail("No right square bracket found");
+}
+END_TEST
+
+/* Test CDATA handling in an external entity */
+static int XMLCALL
+external_entity_good_cdata_ascii(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ const char *text =
+ "<a><![CDATA[<greeting>Hello, world!</greeting>]]></a>";
+ const XML_Char *expected = XCS("<greeting>Hello, world!</greeting>");
+ CharData storage;
+ XML_Parser ext_parser;
+
+ CharData_Init(&storage);
+ ext_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ fail("Could not create external entity parser");
+ XML_SetUserData(ext_parser, &storage);
+ XML_SetCharacterDataHandler(ext_parser, accumulate_characters);
+
+ if (_XML_Parse_SINGLE_BYTES(ext_parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(ext_parser);
+ CharData_CheckXMLChars(&storage, expected);
+
+ XML_ParserFree(ext_parser);
+ return XML_STATUS_OK;
+}
+
+START_TEST(test_ext_entity_good_cdata)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY en SYSTEM 'http://example.org/dummy.ent'>\n"
+ "]>\n"
+ "<doc>&en;</doc>";
+
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser,
+ external_entity_good_cdata_ascii);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_OK)
+ xml_failure(parser);
+}
+END_TEST
+
+/* Test user parameter settings */
+/* Variable holding the expected handler userData */
+static void *handler_data = NULL;
+/* Count of the number of times the comment handler has been invoked */
+static int comment_count = 0;
+/* Count of the number of skipped entities */
+static int skip_count = 0;
+/* Count of the number of times the XML declaration handler is invoked */
+static int xdecl_count = 0;
+
+static void XMLCALL
+xml_decl_handler(void *userData,
+ const XML_Char *UNUSED_P(version),
+ const XML_Char *UNUSED_P(encoding),
+ int standalone)
+{
+ if (userData != handler_data)
+ fail("User data (xml decl) not correctly set");
+ if (standalone != -1)
+ fail("Standalone not flagged as not present in XML decl");
+ xdecl_count++;
+}
+
+static void XMLCALL
+param_check_skip_handler(void *userData,
+ const XML_Char *UNUSED_P(entityName),
+ int UNUSED_P(is_parameter_entity))
+{
+ if (userData != handler_data)
+ fail("User data (skip) not correctly set");
+ skip_count++;
+}
+
+static void XMLCALL
+data_check_comment_handler(void *userData, const XML_Char *UNUSED_P(data))
+{
+ /* Check that the userData passed through is what we expect */
+ if (userData != handler_data)
+ fail("User data (parser) not correctly set");
+ /* Check that the user data in the parser is appropriate */
+ if (XML_GetUserData(userData) != (void *)1)
+ fail("User data in parser not correctly set");
+ comment_count++;
+}
+
+static int XMLCALL
+external_entity_param_checker(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ const char *text =
+ "<!-- Subordinate parser -->\n"
+ "<!ELEMENT doc (#PCDATA)*>";
+ XML_Parser ext_parser;
+
+ ext_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ fail("Could not create external entity parser");
+ handler_data = ext_parser;
+ if (_XML_Parse_SINGLE_BYTES(ext_parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR) {
+ xml_failure(parser);
+ return XML_STATUS_ERROR;
+ }
+ handler_data = parser;
+ XML_ParserFree(ext_parser);
+ return XML_STATUS_OK;
+}
+
+START_TEST(test_user_parameters)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='us-ascii'?>\n"
+ "<!-- Primary parse -->\n"
+ "<!DOCTYPE doc SYSTEM 'foo'>\n"
+ "<doc>&entity;";
+ const char *epilog =
+ "<!-- Back to primary parser -->\n"
+ "</doc>";
+
+ comment_count = 0;
+ skip_count = 0;
+ xdecl_count = 0;
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetXmlDeclHandler(parser, xml_decl_handler);
+ XML_SetExternalEntityRefHandler(parser, external_entity_param_checker);
+ XML_SetCommentHandler(parser, data_check_comment_handler);
+ XML_SetSkippedEntityHandler(parser, param_check_skip_handler);
+ XML_UseParserAsHandlerArg(parser);
+ XML_SetUserData(parser, (void *)1);
+ handler_data = parser;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_FALSE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ if (comment_count != 2)
+ fail("Comment handler not invoked enough times");
+ /* Ensure we can't change policy mid-parse */
+ if (XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_NEVER))
+ fail("Changed param entity parsing policy while parsing");
+ if (_XML_Parse_SINGLE_BYTES(parser, epilog, strlen(epilog),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ if (comment_count != 3)
+ fail("Comment handler not invoked enough times");
+ if (skip_count != 1)
+ fail("Skip handler not invoked enough times");
+ if (xdecl_count != 1)
+ fail("XML declaration handler not invoked");
+}
+END_TEST
+
+/* Test that an explicit external entity handler argument replaces
+ * the parser as the first argument.
+ *
+ * We do not call the first parameter to the external entity handler
+ * 'parser' for once, since the first time the handler is called it
+ * will actually be a text string. We need to be able to access the
+ * global 'parser' variable to create our external entity parser from,
+ * since there are code paths we need to ensure get executed.
+ */
+static int XMLCALL
+external_entity_ref_param_checker(XML_Parser parameter,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ const char *text = "<!ELEMENT doc (#PCDATA)*>";
+ XML_Parser ext_parser;
+
+ if ((void *)parameter != handler_data)
+ fail("External entity ref handler parameter not correct");
+
+ /* Here we use the global 'parser' variable */
+ ext_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ fail("Could not create external entity parser");
+ if (_XML_Parse_SINGLE_BYTES(ext_parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(ext_parser);
+
+ XML_ParserFree(ext_parser);
+ return XML_STATUS_OK;
+}
+
+START_TEST(test_ext_entity_ref_parameter)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='us-ascii'?>\n"
+ "<!DOCTYPE doc SYSTEM 'foo'>\n"
+ "<doc>&entity;</doc>";
+
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser,
+ external_entity_ref_param_checker);
+ /* Set a handler arg that is not NULL and not parser (which is
+ * what NULL would cause to be passed.
+ */
+ XML_SetExternalEntityRefHandlerArg(parser, (void *)text);
+ handler_data = (void *)text;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+
+ /* Now try again with unset args */
+ XML_ParserReset(parser, NULL);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser,
+ external_entity_ref_param_checker);
+ XML_SetExternalEntityRefHandlerArg(parser, NULL);
+ handler_data = (void *)parser;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
+/* Test the parsing of an empty string */
+START_TEST(test_empty_parse)
+{
+ const char *text = "<doc></doc>";
+ const char *partial = "<doc>";
+
+ if (XML_Parse(parser, NULL, 0, XML_FALSE) == XML_STATUS_ERROR)
+ fail("Parsing empty string faulted");
+ if (XML_Parse(parser, NULL, 0, XML_TRUE) != XML_STATUS_ERROR)
+ fail("Parsing final empty string not faulted");
+ if (XML_GetErrorCode(parser) != XML_ERROR_NO_ELEMENTS)
+ fail("Parsing final empty string faulted for wrong reason");
+
+ /* Now try with valid text before the empty end */
+ XML_ParserReset(parser, NULL);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_FALSE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ if (XML_Parse(parser, NULL, 0, XML_TRUE) == XML_STATUS_ERROR)
+ fail("Parsing final empty string faulted");
+
+ /* Now try with invalid text before the empty end */
+ XML_ParserReset(parser, NULL);
+ if (_XML_Parse_SINGLE_BYTES(parser, partial, strlen(partial),
+ XML_FALSE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ if (XML_Parse(parser, NULL, 0, XML_TRUE) != XML_STATUS_ERROR)
+ fail("Parsing final incomplete empty string not faulted");
+}
+END_TEST
+
+/* Test odd corners of the XML_GetBuffer interface */
+static enum XML_Status
+get_feature(enum XML_FeatureEnum feature_id, long *presult)
+{
+ const XML_Feature *feature = XML_GetFeatureList();
+
+ if (feature == NULL)
+ return XML_STATUS_ERROR;
+ for (; feature->feature != XML_FEATURE_END; feature++) {
+ if (feature->feature == feature_id) {
+ *presult = feature->value;
+ return XML_STATUS_OK;
+ }
+ }
+ return XML_STATUS_ERROR;
+}
+
+/* Having an element name longer than 1024 characters exercises some
+ * of the pool allocation code in the parser that otherwise does not
+ * get executed. The count at the end of the line is the number of
+ * characters (bytes) in the element name by that point.x
+ */
+static const char *get_buffer_test_text =
+ "<documentwitharidiculouslylongelementnametotease" /* 0x030 */
+ "aparticularcorneroftheallocationinXML_GetBuffers" /* 0x060 */
+ "othatwecanimprovethecoverageyetagain012345678901" /* 0x090 */
+ "123456789abcdef0123456789abcdef0123456789abcdef0" /* 0x0c0 */
+ "123456789abcdef0123456789abcdef0123456789abcdef0" /* 0x0f0 */
+ "123456789abcdef0123456789abcdef0123456789abcdef0" /* 0x120 */
+ "123456789abcdef0123456789abcdef0123456789abcdef0" /* 0x150 */
+ "123456789abcdef0123456789abcdef0123456789abcdef0" /* 0x180 */
+ "123456789abcdef0123456789abcdef0123456789abcdef0" /* 0x1b0 */
+ "123456789abcdef0123456789abcdef0123456789abcdef0" /* 0x1e0 */
+ "123456789abcdef0123456789abcdef0123456789abcdef0" /* 0x210 */
+ "123456789abcdef0123456789abcdef0123456789abcdef0" /* 0x240 */
+ "123456789abcdef0123456789abcdef0123456789abcdef0" /* 0x270 */
+ "123456789abcdef0123456789abcdef0123456789abcdef0" /* 0x2a0 */
+ "123456789abcdef0123456789abcdef0123456789abcdef0" /* 0x2d0 */
+ "123456789abcdef0123456789abcdef0123456789abcdef0" /* 0x300 */
+ "123456789abcdef0123456789abcdef0123456789abcdef0" /* 0x330 */
+ "123456789abcdef0123456789abcdef0123456789abcdef0" /* 0x360 */
+ "123456789abcdef0123456789abcdef0123456789abcdef0" /* 0x390 */
+ "123456789abcdef0123456789abcdef0123456789abcdef0" /* 0x3c0 */
+ "123456789abcdef0123456789abcdef0123456789abcdef0" /* 0x3f0 */
+ "123456789abcdef0123456789abcdef0123456789>\n<ef0"; /* 0x420 */
+
+/* Test odd corners of the XML_GetBuffer interface */
+START_TEST(test_get_buffer_1)
+{
+ const char *text = get_buffer_test_text;
+ void *buffer;
+ long context_bytes;
+
+ /* Attempt to allocate a negative length buffer */
+ if (XML_GetBuffer(parser, -12) != NULL)
+ fail("Negative length buffer not failed");
+
+ /* Now get a small buffer and extend it past valid length */
+ buffer = XML_GetBuffer(parser, 1536);
+ if (buffer == NULL)
+ fail("1.5K buffer failed");
+ memcpy(buffer, text, strlen(text));
+ if (XML_ParseBuffer(parser, strlen(text), XML_FALSE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ if (XML_GetBuffer(parser, INT_MAX) != NULL)
+ fail("INT_MAX buffer not failed");
+
+ /* Now try extending it a more reasonable but still too large
+ * amount. The allocator in XML_GetBuffer() doubles the buffer
+ * size until it exceeds the requested amount or INT_MAX. If it
+ * exceeds INT_MAX, it rejects the request, so we want a request
+ * between INT_MAX and INT_MAX/2. A gap of 1K seems comfortable,
+ * with an extra byte just to ensure that the request is off any
+ * boundary. The request will be inflated internally by
+ * XML_CONTEXT_BYTES (if defined), so we subtract that from our
+ * request.
+ */
+ if (get_feature(XML_FEATURE_CONTEXT_BYTES,
+ &context_bytes) != XML_STATUS_OK)
+ context_bytes = 0;
+ if (XML_GetBuffer(parser, INT_MAX - (context_bytes + 1025)) != NULL)
+ fail("INT_MAX- buffer not failed");
+
+ /* Now try extending it a carefully crafted amount */
+ if (XML_GetBuffer(parser, 1000) == NULL)
+ fail("1000 buffer failed");
+}
+END_TEST
+
+/* Test more corners of the XML_GetBuffer interface */
+START_TEST(test_get_buffer_2)
+{
+ const char *text = get_buffer_test_text;
+ void *buffer;
+
+ /* Now get a decent buffer */
+ buffer = XML_GetBuffer(parser, 1536);
+ if (buffer == NULL)
+ fail("1.5K buffer failed");
+ memcpy(buffer, text, strlen(text));
+ if (XML_ParseBuffer(parser, strlen(text), XML_FALSE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+
+ /* Extend it, to catch a different code path */
+ if (XML_GetBuffer(parser, 1024) == NULL)
+ fail("1024 buffer failed");
+}
+END_TEST
+
+/* Test position information macros */
+START_TEST(test_byte_info_at_end)
+{
+ const char *text = "<doc></doc>";
+
+ if (XML_GetCurrentByteIndex(parser) != -1 ||
+ XML_GetCurrentByteCount(parser) != 0)
+ fail("Byte index/count incorrect at start of parse");
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ /* At end, the count will be zero and the index the end of string */
+ if (XML_GetCurrentByteCount(parser) != 0)
+ fail("Terminal byte count incorrect");
+ if (XML_GetCurrentByteIndex(parser) != (XML_Index)strlen(text))
+ fail("Terminal byte index incorrect");
+}
+END_TEST
+
+/* Test position information from errors */
+#define PRE_ERROR_STR "<doc></"
+#define POST_ERROR_STR "wombat></doc>"
+START_TEST(test_byte_info_at_error)
+{
+ const char *text = PRE_ERROR_STR POST_ERROR_STR;
+
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_OK)
+ fail("Syntax error not faulted");
+ if (XML_GetCurrentByteCount(parser) != 0)
+ fail("Error byte count incorrect");
+ if (XML_GetCurrentByteIndex(parser) != strlen(PRE_ERROR_STR))
+ fail("Error byte index incorrect");
+}
+END_TEST
+#undef PRE_ERROR_STR
+#undef POST_ERROR_STR
+
+/* Test position information in handler */
+typedef struct ByteTestData {
+ int start_element_len;
+ int cdata_len;
+ int total_string_len;
+} ByteTestData;
+
+static void
+byte_character_handler(void *userData,
+ const XML_Char *UNUSED_P(s),
+ int len)
+{
+#ifdef XML_CONTEXT_BYTES
+ int offset, size;
+ const char *buffer;
+ ByteTestData *data = (ByteTestData *)userData;
+
+ buffer = XML_GetInputContext(parser, &offset, &size);
+ if (buffer == NULL)
+ fail("Failed to get context buffer");
+ if (offset != data->start_element_len)
+ fail("Context offset in unexpected position");
+ if (len != data->cdata_len)
+ fail("CDATA length reported incorrectly");
+ if (size != data->total_string_len)
+ fail("Context size is not full buffer");
+ if (XML_GetCurrentByteIndex(parser) != offset)
+ fail("Character byte index incorrect");
+ if (XML_GetCurrentByteCount(parser) != len)
+ fail("Character byte count incorrect");
+#else
+ (void)userData;
+ (void)len;
+#endif
+}
+
+#define START_ELEMENT "<e>"
+#define CDATA_TEXT "Hello"
+#define END_ELEMENT "</e>"
+START_TEST(test_byte_info_at_cdata)
+{
+ const char *text = START_ELEMENT CDATA_TEXT END_ELEMENT;
+ int offset, size;
+ ByteTestData data;
+
+ /* Check initial context is empty */
+ if (XML_GetInputContext(parser, &offset, &size) != NULL)
+ fail("Unexpected context at start of parse");
+
+ data.start_element_len = strlen(START_ELEMENT);
+ data.cdata_len = strlen(CDATA_TEXT);
+ data.total_string_len = strlen(text);
+ XML_SetCharacterDataHandler(parser, byte_character_handler);
+ XML_SetUserData(parser, &data);
+ if (XML_Parse(parser, text, strlen(text), XML_TRUE) != XML_STATUS_OK)
+ xml_failure(parser);
+}
+END_TEST
+#undef START_ELEMENT
+#undef CDATA_TEXT
+#undef END_ELEMENT
+
+/* Test predefined entities are correctly recognised */
+START_TEST(test_predefined_entities)
+{
+ const char *text = "<doc>&lt;&gt;&amp;&quot;&apos;</doc>";
+ const XML_Char *expected = XCS("<doc>&lt;&gt;&amp;&quot;&apos;</doc>");
+ const XML_Char *result = XCS("<>&\"'");
+ CharData storage;
+
+ XML_SetDefaultHandler(parser, accumulate_characters);
+ /* run_character_check uses XML_SetCharacterDataHandler(), which
+ * unfortunately heads off a code path that we need to exercise.
+ */
+ CharData_Init(&storage);
+ XML_SetUserData(parser, &storage);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ /* The default handler doesn't translate the entities */
+ CharData_CheckXMLChars(&storage, expected);
+
+ /* Now try again and check the translation */
+ XML_ParserReset(parser, NULL);
+ run_character_check(text, result);
+}
+END_TEST
+
+/* Regression test that an invalid tag in an external parameter
+ * reference in an external DTD is correctly faulted.
+ *
+ * Only a few specific tags are legal in DTDs ignoring comments and
+ * processing instructions, all of which begin with an exclamation
+ * mark. "<el/>" is not one of them, so the parser should raise an
+ * error on encountering it.
+ */
+static int XMLCALL
+external_entity_param(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *systemId,
+ const XML_Char *UNUSED_P(publicId))
+{
+ const char *text1 =
+ "<!ELEMENT doc EMPTY>\n"
+ "<!ENTITY % e1 SYSTEM '004-2.ent'>\n"
+ "<!ENTITY % e2 '%e1;'>\n"
+ "%e1;\n";
+ const char *text2 =
+ "<!ELEMENT el EMPTY>\n"
+ "<el/>\n";
+ XML_Parser ext_parser;
+
+ if (systemId == NULL)
+ return XML_STATUS_OK;
+
+ ext_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ fail("Could not create external entity parser");
+
+ if (!xcstrcmp(systemId, XCS("004-1.ent"))) {
+ if (_XML_Parse_SINGLE_BYTES(ext_parser, text1, strlen(text1),
+ XML_TRUE) != XML_STATUS_ERROR)
+ fail("Inner DTD with invalid tag not rejected");
+ if (XML_GetErrorCode(ext_parser) != XML_ERROR_EXTERNAL_ENTITY_HANDLING)
+ xml_failure(ext_parser);
+ }
+ else if (!xcstrcmp(systemId, XCS("004-2.ent"))) {
+ if (_XML_Parse_SINGLE_BYTES(ext_parser, text2, strlen(text2),
+ XML_TRUE) != XML_STATUS_ERROR)
+ fail("Invalid tag in external param not rejected");
+ if (XML_GetErrorCode(ext_parser) != XML_ERROR_SYNTAX)
+ xml_failure(ext_parser);
+ } else {
+ fail("Unknown system ID");
+ }
+
+ XML_ParserFree(ext_parser);
+ return XML_STATUS_ERROR;
+}
+
+START_TEST(test_invalid_tag_in_dtd)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM '004-1.ent'>\n"
+ "<doc></doc>\n";
+
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_param);
+ expect_failure(text, XML_ERROR_EXTERNAL_ENTITY_HANDLING,
+ "Invalid tag IN DTD external param not rejected");
+}
+END_TEST
+
+/* Test entities not quite the predefined ones are not mis-recognised */
+START_TEST(test_not_predefined_entities)
+{
+ const char *text[] = {
+ "<doc>&pt;</doc>",
+ "<doc>&amo;</doc>",
+ "<doc>&quid;</doc>",
+ "<doc>&apod;</doc>",
+ NULL
+ };
+ int i = 0;
+
+ while (text[i] != NULL) {
+ expect_failure(text[i], XML_ERROR_UNDEFINED_ENTITY,
+ "Undefined entity not rejected");
+ XML_ParserReset(parser, NULL);
+ i++;
+ }
+}
+END_TEST
+
+/* Test conditional inclusion (IGNORE) */
+static int XMLCALL
+external_entity_load_ignore(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ const char *text = "<![IGNORE[<!ELEMENT e (#PCDATA)*>]]>";
+ XML_Parser ext_parser;
+
+ ext_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ fail("Could not create external entity parser");
+ if (_XML_Parse_SINGLE_BYTES(ext_parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+
+ XML_ParserFree(ext_parser);
+ return XML_STATUS_OK;
+}
+
+START_TEST(test_ignore_section)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM 'foo'>\n"
+ "<doc><e>&entity;</e></doc>";
+ const XML_Char *expected =
+ XCS("<![IGNORE[<!ELEMENT e (#PCDATA)*>]]>\n&entity;");
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetUserData(parser, &storage);
+ XML_SetExternalEntityRefHandler(parser, external_entity_load_ignore);
+ XML_SetDefaultHandler(parser, accumulate_characters);
+ XML_SetStartDoctypeDeclHandler(parser, dummy_start_doctype_handler);
+ XML_SetEndDoctypeDeclHandler(parser, dummy_end_doctype_handler);
+ XML_SetElementDeclHandler(parser, dummy_element_decl_handler);
+ XML_SetStartElementHandler(parser, dummy_start_element);
+ XML_SetEndElementHandler(parser, dummy_end_element);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+static int XMLCALL
+external_entity_load_ignore_utf16(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ const char text[] =
+ /* <![IGNORE[<!ELEMENT e (#PCDATA)*>]]> */
+ "<\0!\0[\0I\0G\0N\0O\0R\0E\0[\0"
+ "<\0!\0E\0L\0E\0M\0E\0N\0T\0 \0e\0 \0"
+ "(\0#\0P\0C\0D\0A\0T\0A\0)\0*\0>\0]\0]\0>\0";
+ XML_Parser ext_parser;
+
+ ext_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ fail("Could not create external entity parser");
+ if (_XML_Parse_SINGLE_BYTES(ext_parser, text, sizeof(text)-1,
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+
+ XML_ParserFree(ext_parser);
+ return XML_STATUS_OK;
+}
+
+START_TEST(test_ignore_section_utf16)
+{
+ const char text[] =
+ /* <!DOCTYPE d SYSTEM 's'> */
+ "<\0!\0D\0O\0C\0T\0Y\0P\0E\0 \0d\0 "
+ "\0S\0Y\0S\0T\0E\0M\0 \0'\0s\0'\0>\0\n\0"
+ /* <d><e>&en;</e></d> */
+ "<\0d\0>\0<\0e\0>\0&\0e\0n\0;\0<\0/\0e\0>\0<\0/\0d\0>\0";
+ const XML_Char *expected =
+ XCS("<![IGNORE[<!ELEMENT e (#PCDATA)*>]]>\n&en;");
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetUserData(parser, &storage);
+ XML_SetExternalEntityRefHandler(parser,
+ external_entity_load_ignore_utf16);
+ XML_SetDefaultHandler(parser, accumulate_characters);
+ XML_SetStartDoctypeDeclHandler(parser, dummy_start_doctype_handler);
+ XML_SetEndDoctypeDeclHandler(parser, dummy_end_doctype_handler);
+ XML_SetElementDeclHandler(parser, dummy_element_decl_handler);
+ XML_SetStartElementHandler(parser, dummy_start_element);
+ XML_SetEndElementHandler(parser, dummy_end_element);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, sizeof(text)-1,
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+static int XMLCALL
+external_entity_load_ignore_utf16_be(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ const char text[] =
+ /* <![IGNORE[<!ELEMENT e (#PCDATA)*>]]> */
+ "\0<\0!\0[\0I\0G\0N\0O\0R\0E\0["
+ "\0<\0!\0E\0L\0E\0M\0E\0N\0T\0 \0e\0 "
+ "\0(\0#\0P\0C\0D\0A\0T\0A\0)\0*\0>\0]\0]\0>";
+ XML_Parser ext_parser;
+
+ ext_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ fail("Could not create external entity parser");
+ if (_XML_Parse_SINGLE_BYTES(ext_parser, text, sizeof(text)-1,
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+
+ XML_ParserFree(ext_parser);
+ return XML_STATUS_OK;
+}
+
+START_TEST(test_ignore_section_utf16_be)
+{
+ const char text[] =
+ /* <!DOCTYPE d SYSTEM 's'> */
+ "\0<\0!\0D\0O\0C\0T\0Y\0P\0E\0 \0d\0 "
+ "\0S\0Y\0S\0T\0E\0M\0 \0'\0s\0'\0>\0\n"
+ /* <d><e>&en;</e></d> */
+ "\0<\0d\0>\0<\0e\0>\0&\0e\0n\0;\0<\0/\0e\0>\0<\0/\0d\0>";
+ const XML_Char *expected =
+ XCS("<![IGNORE[<!ELEMENT e (#PCDATA)*>]]>\n&en;");
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetUserData(parser, &storage);
+ XML_SetExternalEntityRefHandler(parser,
+ external_entity_load_ignore_utf16_be);
+ XML_SetDefaultHandler(parser, accumulate_characters);
+ XML_SetStartDoctypeDeclHandler(parser, dummy_start_doctype_handler);
+ XML_SetEndDoctypeDeclHandler(parser, dummy_end_doctype_handler);
+ XML_SetElementDeclHandler(parser, dummy_element_decl_handler);
+ XML_SetStartElementHandler(parser, dummy_start_element);
+ XML_SetEndElementHandler(parser, dummy_end_element);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, sizeof(text)-1,
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+/* Test mis-formatted conditional exclusion */
+START_TEST(test_bad_ignore_section)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM 'foo'>\n"
+ "<doc><e>&entity;</e></doc>";
+ ExtFaults faults[] = {
+ {
+ "<![IGNORE[<!ELEM",
+ "Broken-off declaration not faulted",
+ NULL,
+ XML_ERROR_SYNTAX
+ },
+ {
+ "<![IGNORE[\x01]]>",
+ "Invalid XML character not faulted",
+ NULL,
+ XML_ERROR_INVALID_TOKEN
+ },
+ {
+ /* FIrst two bytes of a three-byte char */
+ "<![IGNORE[\xe2\x82",
+ "Partial XML character not faulted",
+ NULL,
+ XML_ERROR_PARTIAL_CHAR
+ },
+ { NULL, NULL, NULL, XML_ERROR_NONE }
+ };
+ ExtFaults *fault;
+
+ for (fault = &faults[0]; fault->parse_text != NULL; fault++) {
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_faulter);
+ XML_SetUserData(parser, fault);
+ expect_failure(text, XML_ERROR_EXTERNAL_ENTITY_HANDLING,
+ "Incomplete IGNORE section not failed");
+ XML_ParserReset(parser, NULL);
+ }
+}
+END_TEST
+
+/* Test recursive parsing */
+static int XMLCALL
+external_entity_valuer(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *systemId,
+ const XML_Char *UNUSED_P(publicId))
+{
+ const char *text1 =
+ "<!ELEMENT doc EMPTY>\n"
+ "<!ENTITY % e1 SYSTEM '004-2.ent'>\n"
+ "<!ENTITY % e2 '%e1;'>\n"
+ "%e1;\n";
+ XML_Parser ext_parser;
+
+ if (systemId == NULL)
+ return XML_STATUS_OK;
+ ext_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ fail("Could not create external entity parser");
+ if (!xcstrcmp(systemId, XCS("004-1.ent"))) {
+ if (_XML_Parse_SINGLE_BYTES(ext_parser, text1, strlen(text1),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(ext_parser);
+ }
+ else if (!xcstrcmp(systemId, XCS("004-2.ent"))) {
+ ExtFaults *fault = (ExtFaults *)XML_GetUserData(parser);
+ enum XML_Status status;
+ enum XML_Error error;
+
+ status = _XML_Parse_SINGLE_BYTES(ext_parser,
+ fault->parse_text,
+ strlen(fault->parse_text),
+ XML_TRUE);
+ if (fault->error == XML_ERROR_NONE) {
+ if (status == XML_STATUS_ERROR)
+ xml_failure(ext_parser);
+ } else {
+ if (status != XML_STATUS_ERROR)
+ fail(fault->fail_text);
+ error = XML_GetErrorCode(ext_parser);
+ if (error != fault->error &&
+ (fault->error != XML_ERROR_XML_DECL ||
+ error != XML_ERROR_TEXT_DECL))
+ xml_failure(ext_parser);
+ }
+ }
+
+ XML_ParserFree(ext_parser);
+ return XML_STATUS_OK;
+}
+
+START_TEST(test_external_entity_values)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM '004-1.ent'>\n"
+ "<doc></doc>\n";
+ ExtFaults data_004_2[] = {
+ {
+ "<!ATTLIST doc a1 CDATA 'value'>",
+ NULL,
+ NULL,
+ XML_ERROR_NONE
+ },
+ {
+ "<!ATTLIST $doc a1 CDATA 'value'>",
+ "Invalid token not faulted",
+ NULL,
+ XML_ERROR_INVALID_TOKEN
+ },
+ {
+ "'wombat",
+ "Unterminated string not faulted",
+ NULL,
+ XML_ERROR_UNCLOSED_TOKEN
+ },
+ {
+ "\xe2\x82",
+ "Partial UTF-8 character not faulted",
+ NULL,
+ XML_ERROR_PARTIAL_CHAR
+ },
+ {
+ "<?xml version='1.0' encoding='utf-8'?>\n",
+ NULL,
+ NULL,
+ XML_ERROR_NONE
+ },
+ {
+ "<?xml?>",
+ "Malformed XML declaration not faulted",
+ NULL,
+ XML_ERROR_XML_DECL
+ },
+ {
+ /* UTF-8 BOM */
+ "\xEF\xBB\xBF<!ATTLIST doc a1 CDATA 'value'>",
+ NULL,
+ NULL,
+ XML_ERROR_NONE
+ },
+ {
+ "<?xml version='1.0' encoding='utf-8'?>\n$",
+ "Invalid token after text declaration not faulted",
+ NULL,
+ XML_ERROR_INVALID_TOKEN
+ },
+ {
+ "<?xml version='1.0' encoding='utf-8'?>\n'wombat",
+ "Unterminated string after text decl not faulted",
+ NULL,
+ XML_ERROR_UNCLOSED_TOKEN
+ },
+ {
+ "<?xml version='1.0' encoding='utf-8'?>\n\xe2\x82",
+ "Partial UTF-8 character after text decl not faulted",
+ NULL,
+ XML_ERROR_PARTIAL_CHAR
+ },
+ {
+ "%e1;",
+ "Recursive parameter entity not faulted",
+ NULL,
+ XML_ERROR_RECURSIVE_ENTITY_REF
+ },
+ { NULL, NULL, NULL, XML_ERROR_NONE }
+ };
+ int i;
+
+ for (i = 0; data_004_2[i].parse_text != NULL; i++) {
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_valuer);
+ XML_SetUserData(parser, &data_004_2[i]);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ XML_ParserReset(parser, NULL);
+ }
+}
+END_TEST
+
+/* Test the recursive parse interacts with a not standalone handler */
+static int XMLCALL
+external_entity_not_standalone(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *systemId,
+ const XML_Char *UNUSED_P(publicId))
+{
+ const char *text1 =
+ "<!ELEMENT doc EMPTY>\n"
+ "<!ENTITY % e1 SYSTEM 'bar'>\n"
+ "%e1;\n";
+ const char *text2 = "<!ATTLIST doc a1 CDATA 'value'>";
+ XML_Parser ext_parser;
+
+ if (systemId == NULL)
+ return XML_STATUS_OK;
+ ext_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ fail("Could not create external entity parser");
+ if (!xcstrcmp(systemId, XCS("foo"))) {
+ XML_SetNotStandaloneHandler(ext_parser,
+ reject_not_standalone_handler);
+ if (_XML_Parse_SINGLE_BYTES(ext_parser, text1, strlen(text1),
+ XML_TRUE) != XML_STATUS_ERROR)
+ fail("Expected not standalone rejection");
+ if (XML_GetErrorCode(ext_parser) != XML_ERROR_NOT_STANDALONE)
+ xml_failure(ext_parser);
+ XML_SetNotStandaloneHandler(ext_parser, NULL);
+ XML_ParserFree(ext_parser);
+ return XML_STATUS_ERROR;
+ }
+ else if (!xcstrcmp(systemId, XCS("bar"))) {
+ if (_XML_Parse_SINGLE_BYTES(ext_parser, text2, strlen(text2),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(ext_parser);
+ }
+
+ XML_ParserFree(ext_parser);
+ return XML_STATUS_OK;
+}
+
+START_TEST(test_ext_entity_not_standalone)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM 'foo'>\n"
+ "<doc></doc>";
+
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_not_standalone);
+ expect_failure(text, XML_ERROR_EXTERNAL_ENTITY_HANDLING,
+ "Standalone rejection not caught");
+}
+END_TEST
+
+static int XMLCALL
+external_entity_value_aborter(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *systemId,
+ const XML_Char *UNUSED_P(publicId))
+{
+ const char *text1 =
+ "<!ELEMENT doc EMPTY>\n"
+ "<!ENTITY % e1 SYSTEM '004-2.ent'>\n"
+ "<!ENTITY % e2 '%e1;'>\n"
+ "%e1;\n";
+ const char *text2 =
+ "<?xml version='1.0' encoding='utf-8'?>";
+ XML_Parser ext_parser;
+
+ if (systemId == NULL)
+ return XML_STATUS_OK;
+ ext_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ fail("Could not create external entity parser");
+ if (!xcstrcmp(systemId, XCS("004-1.ent"))) {
+ if (_XML_Parse_SINGLE_BYTES(ext_parser, text1, strlen(text1),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(ext_parser);
+ }
+ if (!xcstrcmp(systemId, XCS("004-2.ent"))) {
+ XML_SetXmlDeclHandler(ext_parser, entity_suspending_xdecl_handler);
+ XML_SetUserData(ext_parser, ext_parser);
+ if (_XML_Parse_SINGLE_BYTES(ext_parser, text2, strlen(text2),
+ XML_TRUE) != XML_STATUS_ERROR)
+ fail("Aborted parse not faulted");
+ if (XML_GetErrorCode(ext_parser) != XML_ERROR_ABORTED)
+ xml_failure(ext_parser);
+ }
+
+ XML_ParserFree(ext_parser);
+ return XML_STATUS_OK;
+}
+
+START_TEST(test_ext_entity_value_abort)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM '004-1.ent'>\n"
+ "<doc></doc>\n";
+
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser,
+ external_entity_value_aborter);
+ resumable = XML_FALSE;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
+START_TEST(test_bad_public_doctype)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='utf-8'?>\n"
+ "<!DOCTYPE doc PUBLIC '{BadName}' 'test'>\n"
+ "<doc></doc>";
+
+ /* Setting a handler provokes a particular code path */
+ XML_SetDoctypeDeclHandler(parser,
+ dummy_start_doctype_handler,
+ dummy_end_doctype_handler);
+ expect_failure(text, XML_ERROR_PUBLICID, "Bad Public ID not failed");
+}
+END_TEST
+
+/* Test based on ibm/valid/P32/ibm32v04.xml */
+START_TEST(test_attribute_enum_value)
+{
+ const char *text =
+ "<?xml version='1.0' standalone='no'?>\n"
+ "<!DOCTYPE animal SYSTEM 'test.dtd'>\n"
+ "<animal>This is a \n <a/> \n\nyellow tiger</animal>";
+ ExtTest dtd_data = {
+ "<!ELEMENT animal (#PCDATA|a)*>\n"
+ "<!ELEMENT a EMPTY>\n"
+ "<!ATTLIST animal xml:space (default|preserve) 'preserve'>",
+ NULL,
+ NULL
+ };
+ const XML_Char *expected = XCS("This is a \n \n\nyellow tiger");
+
+ XML_SetExternalEntityRefHandler(parser, external_entity_loader);
+ XML_SetUserData(parser, &dtd_data);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ /* An attribute list handler provokes a different code path */
+ XML_SetAttlistDeclHandler(parser, dummy_attlist_decl_handler);
+ run_ext_character_check(text, &dtd_data, expected);
+}
+END_TEST
+
+/* Slightly bizarrely, the library seems to silently ignore entity
+ * definitions for predefined entities, even when they are wrong. The
+ * language of the XML 1.0 spec is somewhat unhelpful as to what ought
+ * to happen, so this is currently treated as acceptable.
+ */
+START_TEST(test_predefined_entity_redefinition)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ "<!ENTITY apos 'foo'>\n"
+ "]>\n"
+ "<doc>&apos;</doc>";
+ run_character_check(text, XCS("'"));
+}
+END_TEST
+
+/* Test that the parser stops processing the DTD after an unresolved
+ * parameter entity is encountered.
+ */
+START_TEST(test_dtd_stop_processing)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ "%foo;\n"
+ "<!ENTITY bar 'bas'>\n"
+ "]><doc/>";
+
+ XML_SetEntityDeclHandler(parser, dummy_entity_decl_handler);
+ dummy_handler_flags = 0;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ if (dummy_handler_flags != 0)
+ fail("DTD processing still going after undefined PE");
+}
+END_TEST
+
+/* Test public notations with no system ID */
+START_TEST(test_public_notation_no_sysid)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ "<!NOTATION note PUBLIC 'foo'>\n"
+ "<!ELEMENT doc EMPTY>\n"
+ "]>\n<doc/>";
+
+ dummy_handler_flags = 0;
+ XML_SetNotationDeclHandler(parser, dummy_notation_decl_handler);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ if (dummy_handler_flags != DUMMY_NOTATION_DECL_HANDLER_FLAG)
+ fail("Notation declaration handler not called");
+}
+END_TEST
+
+static void XMLCALL
+record_element_start_handler(void *userData,
+ const XML_Char *name,
+ const XML_Char **UNUSED_P(atts))
+{
+ CharData_AppendXMLChars((CharData *)userData, name, xcstrlen(name));
+}
+
+START_TEST(test_nested_groups)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ "<!ELEMENT doc "
+ /* Sixteen elements per line */
+ "(e,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,"
+ "(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?"
+ "))))))))))))))))))))))))))))))))>\n"
+ "<!ELEMENT e EMPTY>"
+ "]>\n"
+ "<doc><e/></doc>";
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetElementDeclHandler(parser, dummy_element_decl_handler);
+ XML_SetStartElementHandler(parser, record_element_start_handler);
+ XML_SetUserData(parser, &storage);
+ dummy_handler_flags = 0;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, XCS("doce"));
+ if (dummy_handler_flags != DUMMY_ELEMENT_DECL_HANDLER_FLAG)
+ fail("Element handler not fired");
+}
+END_TEST
+
+START_TEST(test_group_choice)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ "<!ELEMENT doc (a|b|c)+>\n"
+ "<!ELEMENT a EMPTY>\n"
+ "<!ELEMENT b (#PCDATA)>\n"
+ "<!ELEMENT c ANY>\n"
+ "]>\n"
+ "<doc>\n"
+ "<a/>\n"
+ "<b attr='foo'>This is a foo</b>\n"
+ "<c></c>\n"
+ "</doc>\n";
+
+ XML_SetElementDeclHandler(parser, dummy_element_decl_handler);
+ dummy_handler_flags = 0;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ if (dummy_handler_flags != DUMMY_ELEMENT_DECL_HANDLER_FLAG)
+ fail("Element handler flag not raised");
+}
+END_TEST
+
+static int XMLCALL
+external_entity_public(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *systemId,
+ const XML_Char *publicId)
+{
+ const char *text1 = (const char *)XML_GetUserData(parser);
+ const char *text2 = "<!ATTLIST doc a CDATA 'value'>";
+ const char *text = NULL;
+ XML_Parser ext_parser;
+ int parse_res;
+
+ ext_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ return XML_STATUS_ERROR;
+ if (systemId != NULL && !xcstrcmp(systemId, XCS("http://example.org/"))) {
+ text = text1;
+ }
+ else if (publicId != NULL && !xcstrcmp(publicId, XCS("foo"))) {
+ text = text2;
+ }
+ else
+ fail("Unexpected parameters to external entity parser");
+ parse_res = _XML_Parse_SINGLE_BYTES(ext_parser, text, strlen(text),
+ XML_TRUE);
+ XML_ParserFree(ext_parser);
+ return parse_res;
+}
+
+START_TEST(test_standalone_parameter_entity)
+{
+ const char *text =
+ "<?xml version='1.0' standalone='yes'?>\n"
+ "<!DOCTYPE doc SYSTEM 'http://example.org/' [\n"
+ "<!ENTITY % entity '<!ELEMENT doc (#PCDATA)>'>\n"
+ "%entity;\n"
+ "]>\n"
+ "<doc></doc>";
+ char dtd_data[] =
+ "<!ENTITY % e1 'foo'>\n";
+
+ XML_SetUserData(parser, dtd_data);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_public);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
+/* Test skipping of parameter entity in an external DTD */
+/* Derived from ibm/invalid/P69/ibm69i01.xml */
+START_TEST(test_skipped_parameter_entity)
+{
+ const char *text =
+ "<?xml version='1.0'?>\n"
+ "<!DOCTYPE root SYSTEM 'http://example.org/dtd.ent' [\n"
+ "<!ELEMENT root (#PCDATA|a)* >\n"
+ "]>\n"
+ "<root></root>";
+ ExtTest dtd_data = { "%pe2;", NULL, NULL };
+
+ XML_SetExternalEntityRefHandler(parser, external_entity_loader);
+ XML_SetUserData(parser, &dtd_data);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetSkippedEntityHandler(parser, dummy_skip_handler);
+ dummy_handler_flags = 0;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ if (dummy_handler_flags != DUMMY_SKIP_HANDLER_FLAG)
+ fail("Skip handler not executed");
+}
+END_TEST
+
+/* Test recursive parameter entity definition rejected in external DTD */
+START_TEST(test_recursive_external_parameter_entity)
+{
+ const char *text =
+ "<?xml version='1.0'?>\n"
+ "<!DOCTYPE root SYSTEM 'http://example.org/dtd.ent' [\n"
+ "<!ELEMENT root (#PCDATA|a)* >\n"
+ "]>\n"
+ "<root></root>";
+ ExtFaults dtd_data = {
+ "<!ENTITY % pe2 '&#37;pe2;'>\n%pe2;",
+ "Recursive external parameter entity not faulted",
+ NULL,
+ XML_ERROR_RECURSIVE_ENTITY_REF
+ };
+
+ XML_SetExternalEntityRefHandler(parser, external_entity_faulter);
+ XML_SetUserData(parser, &dtd_data);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ expect_failure(text,
+ XML_ERROR_EXTERNAL_ENTITY_HANDLING,
+ "Recursive external parameter not spotted");
+}
+END_TEST
+
+/* Test undefined parameter entity in external entity handler */
+static int XMLCALL
+external_entity_devaluer(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *systemId,
+ const XML_Char *UNUSED_P(publicId))
+{
+ const char *text =
+ "<!ELEMENT doc EMPTY>\n"
+ "<!ENTITY % e1 SYSTEM 'bar'>\n"
+ "%e1;\n";
+ XML_Parser ext_parser;
+ int clear_handler = (intptr_t)XML_GetUserData(parser);
+
+ if (systemId == NULL || !xcstrcmp(systemId, XCS("bar")))
+ return XML_STATUS_OK;
+ if (xcstrcmp(systemId, XCS("foo")))
+ fail("Unexpected system ID");
+ ext_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ fail("Could note create external entity parser");
+ if (clear_handler)
+ XML_SetExternalEntityRefHandler(ext_parser, NULL);
+ if (_XML_Parse_SINGLE_BYTES(ext_parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(ext_parser);
+
+ XML_ParserFree(ext_parser);
+ return XML_STATUS_OK;
+}
+
+START_TEST(test_undefined_ext_entity_in_external_dtd)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM 'foo'>\n"
+ "<doc></doc>\n";
+
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_devaluer);
+ XML_SetUserData(parser, (void *)(intptr_t)XML_FALSE);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+
+ /* Now repeat without the external entity ref handler invoking
+ * another copy of itself.
+ */
+ XML_ParserReset(parser, NULL);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_devaluer);
+ XML_SetUserData(parser, (void *)(intptr_t)XML_TRUE);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
+
+static void XMLCALL
+aborting_xdecl_handler(void *UNUSED_P(userData),
+ const XML_Char *UNUSED_P(version),
+ const XML_Char *UNUSED_P(encoding),
+ int UNUSED_P(standalone))
+{
+ XML_StopParser(parser, resumable);
+ XML_SetXmlDeclHandler(parser, NULL);
+}
+
+/* Test suspending the parse on receiving an XML declaration works */
+START_TEST(test_suspend_xdecl)
+{
+ const char *text = long_character_data_text;
+
+ XML_SetXmlDeclHandler(parser, aborting_xdecl_handler);
+ resumable = XML_TRUE;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_SUSPENDED)
+ xml_failure(parser);
+ if (XML_GetErrorCode(parser) != XML_ERROR_NONE)
+ xml_failure(parser);
+ /* Attempt to start a new parse while suspended */
+ if (XML_Parse(parser, text, strlen(text), XML_TRUE) != XML_STATUS_ERROR)
+ fail("Attempt to parse while suspended not faulted");
+ if (XML_GetErrorCode(parser) != XML_ERROR_SUSPENDED)
+ fail("Suspended parse not faulted with correct error");
+}
+END_TEST
+
+/* Test aborting the parse in an epilog works */
+static void XMLCALL
+selective_aborting_default_handler(void *userData,
+ const XML_Char *s,
+ int len)
+{
+ const XML_Char *match = (const XML_Char *)userData;
+
+ if (match == NULL ||
+ (xcstrlen(match) == (unsigned)len &&
+ !xcstrncmp(match, s, len))) {
+ XML_StopParser(parser, resumable);
+ XML_SetDefaultHandler(parser, NULL);
+ }
+}
+
+START_TEST(test_abort_epilog)
+{
+ const char *text = "<doc></doc>\n\r\n";
+ XML_Char match[] = XCS("\r");
+
+ XML_SetDefaultHandler(parser, selective_aborting_default_handler);
+ XML_SetUserData(parser, match);
+ resumable = XML_FALSE;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ fail("Abort not triggered");
+ if (XML_GetErrorCode(parser) != XML_ERROR_ABORTED)
+ xml_failure(parser);
+}
+END_TEST
+
+/* Test a different code path for abort in the epilog */
+START_TEST(test_abort_epilog_2)
+{
+ const char *text = "<doc></doc>\n";
+ XML_Char match[] = XCS("\n");
+
+ XML_SetDefaultHandler(parser, selective_aborting_default_handler);
+ XML_SetUserData(parser, match);
+ resumable = XML_FALSE;
+ expect_failure(text, XML_ERROR_ABORTED, "Abort not triggered");
+}
+END_TEST
+
+/* Test suspension from the epilog */
+START_TEST(test_suspend_epilog)
+{
+ const char *text = "<doc></doc>\n";
+ XML_Char match[] = XCS("\n");
+
+ XML_SetDefaultHandler(parser, selective_aborting_default_handler);
+ XML_SetUserData(parser, match);
+ resumable = XML_TRUE;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_SUSPENDED)
+ xml_failure(parser);
+}
+END_TEST
+
+START_TEST(test_unfinished_epilog)
+{
+ const char *text = "<doc></doc><";
+
+ expect_failure(text, XML_ERROR_UNCLOSED_TOKEN,
+ "Incomplete epilog entry not faulted");
+}
+END_TEST
+
+START_TEST(test_partial_char_in_epilog)
+{
+ const char *text = "<doc></doc>\xe2\x82";
+
+ /* First check that no fault is raised if the parse is not finished */
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_FALSE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ /* Now check that it is faulted once we finish */
+ if (XML_ParseBuffer(parser, 0, XML_TRUE) != XML_STATUS_ERROR)
+ fail("Partial character in epilog not faulted");
+ if (XML_GetErrorCode(parser) != XML_ERROR_PARTIAL_CHAR)
+ xml_failure(parser);
+}
+END_TEST
+
+START_TEST(test_hash_collision)
+{
+ /* For full coverage of the lookup routine, we need to ensure a
+ * hash collision even though we can only tell that we have one
+ * through breakpoint debugging or coverage statistics. The
+ * following will cause a hash collision on machines with a 64-bit
+ * long type; others will have to experiment. The full coverage
+ * tests invoked from qa.sh usually provide a hash collision, but
+ * not always. This is an attempt to provide insurance.
+ */
+#define COLLIDING_HASH_SALT (unsigned long)_SIP_ULL(0xffffffffU, 0xff99fc90U)
+ const char * text =
+ "<doc>\n"
+ "<a1/><a2/><a3/><a4/><a5/><a6/><a7/><a8/>\n"
+ "<b1></b1><b2 attr='foo'>This is a foo</b2><b3></b3><b4></b4>\n"
+ "<b5></b5><b6></b6><b7></b7><b8></b8>\n"
+ "<c1/><c2/><c3/><c4/><c5/><c6/><c7/><c8/>\n"
+ "<d1/><d2/><d3/><d4/><d5/><d6/><d7/>\n"
+ "<d8>This triggers the table growth and collides with b2</d8>\n"
+ "</doc>\n";
+
+ XML_SetHashSalt(parser, COLLIDING_HASH_SALT);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+#undef COLLIDING_HASH_SALT
+
+/* Test resuming a parse suspended in entity substitution */
+static void XMLCALL
+start_element_suspender(void *UNUSED_P(userData),
+ const XML_Char *name,
+ const XML_Char **UNUSED_P(atts))
+{
+ if (!xcstrcmp(name, XCS("suspend")))
+ XML_StopParser(parser, XML_TRUE);
+ if (!xcstrcmp(name, XCS("abort")))
+ XML_StopParser(parser, XML_FALSE);
+}
+
+START_TEST(test_suspend_resume_internal_entity)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ "<!ENTITY foo '<suspend>Hi<suspend>Ho</suspend></suspend>'>\n"
+ "]>\n"
+ "<doc>&foo;</doc>\n";
+ const XML_Char *expected1 = XCS("Hi");
+ const XML_Char *expected2 = XCS("HiHo");
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetStartElementHandler(parser, start_element_suspender);
+ XML_SetCharacterDataHandler(parser, accumulate_characters);
+ XML_SetUserData(parser, &storage);
+ if (XML_Parse(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_SUSPENDED)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, XCS(""));
+ if (XML_ResumeParser(parser) != XML_STATUS_SUSPENDED)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected1);
+ if (XML_ResumeParser(parser) != XML_STATUS_OK)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected2);
+}
+END_TEST
+
+/* Test syntax error is caught at parse resumption */
+START_TEST(test_resume_entity_with_syntax_error)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ "<!ENTITY foo '<suspend>Hi</wombat>'>\n"
+ "]>\n"
+ "<doc>&foo;</doc>\n";
+
+ XML_SetStartElementHandler(parser, start_element_suspender);
+ if (XML_Parse(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_SUSPENDED)
+ xml_failure(parser);
+ if (XML_ResumeParser(parser) != XML_STATUS_ERROR)
+ fail("Syntax error in entity not faulted");
+ if (XML_GetErrorCode(parser) != XML_ERROR_TAG_MISMATCH)
+ xml_failure(parser);
+}
+END_TEST
+
+/* Test suspending and resuming in a parameter entity substitution */
+static void XMLCALL
+element_decl_suspender(void *UNUSED_P(userData),
+ const XML_Char *UNUSED_P(name),
+ XML_Content *model)
+{
+ XML_StopParser(parser, XML_TRUE);
+ XML_FreeContentModel(parser, model);
+}
+
+START_TEST(test_suspend_resume_parameter_entity)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ "<!ENTITY % foo '<!ELEMENT doc (#PCDATA)*>'>\n"
+ "%foo;\n"
+ "]>\n"
+ "<doc>Hello, world</doc>";
+ const XML_Char *expected = XCS("Hello, world");
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetElementDeclHandler(parser, element_decl_suspender);
+ XML_SetCharacterDataHandler(parser, accumulate_characters);
+ XML_SetUserData(parser, &storage);
+ if (XML_Parse(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_SUSPENDED)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, XCS(""));
+ if (XML_ResumeParser(parser) != XML_STATUS_OK)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+/* Test attempting to use parser after an error is faulted */
+START_TEST(test_restart_on_error)
+{
+ const char *text = "<$doc><doc></doc>";
+
+ if (XML_Parse(parser, text, strlen(text), XML_TRUE) != XML_STATUS_ERROR)
+ fail("Invalid tag name not faulted");
+ if (XML_GetErrorCode(parser) != XML_ERROR_INVALID_TOKEN)
+ xml_failure(parser);
+ if (XML_Parse(parser, NULL, 0, XML_TRUE) != XML_STATUS_ERROR)
+ fail("Restarting invalid parse not faulted");
+ if (XML_GetErrorCode(parser) != XML_ERROR_INVALID_TOKEN)
+ xml_failure(parser);
+}
+END_TEST
+
+/* Test that angle brackets in an attribute default value are faulted */
+START_TEST(test_reject_lt_in_attribute_value)
+{
+ const char *text =
+ "<!DOCTYPE doc [<!ATTLIST doc a CDATA '<bar>'>]>\n"
+ "<doc></doc>";
+
+ expect_failure(text, XML_ERROR_INVALID_TOKEN,
+ "Bad attribute default not faulted");
+}
+END_TEST
+
+START_TEST(test_reject_unfinished_param_in_att_value)
+{
+ const char *text =
+ "<!DOCTYPE doc [<!ATTLIST doc a CDATA '&foo'>]>\n"
+ "<doc></doc>";
+
+ expect_failure(text, XML_ERROR_INVALID_TOKEN,
+ "Bad attribute default not faulted");
+}
+END_TEST
+
+START_TEST(test_trailing_cr_in_att_value)
+{
+ const char *text = "<doc a='value\r'/>";
+
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
+/* Try parsing a general entity within a parameter entity in a
+ * standalone internal DTD. Covers a corner case in the parser.
+ */
+START_TEST(test_standalone_internal_entity)
+{
+ const char *text =
+ "<?xml version='1.0' standalone='yes' ?>\n"
+ "<!DOCTYPE doc [\n"
+ " <!ELEMENT doc (#PCDATA)>\n"
+ " <!ENTITY % pe '<!ATTLIST doc att2 CDATA \"&ge;\">'>\n"
+ " <!ENTITY ge 'AttDefaultValue'>\n"
+ " %pe;\n"
+ "]>\n"
+ "<doc att2='any'/>";
+
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
+/* Test that a reference to an unknown external entity is skipped */
+START_TEST(test_skipped_external_entity)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM 'http://example.org/'>\n"
+ "<doc></doc>\n";
+ ExtTest test_data = {
+ "<!ELEMENT doc EMPTY>\n"
+ "<!ENTITY % e2 '%e1;'>\n",
+ NULL,
+ NULL
+ };
+
+ XML_SetUserData(parser, &test_data);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_loader);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
+/* Test a different form of unknown external entity */
+typedef struct ext_hdlr_data {
+ const char *parse_text;
+ XML_ExternalEntityRefHandler handler;
+} ExtHdlrData;
+
+static int XMLCALL
+external_entity_oneshot_loader(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ ExtHdlrData *test_data = (ExtHdlrData *)XML_GetUserData(parser);
+ XML_Parser ext_parser;
+
+ ext_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ fail("Could not create external entity parser.");
+ /* Use the requested entity parser for further externals */
+ XML_SetExternalEntityRefHandler(ext_parser, test_data->handler);
+ if ( _XML_Parse_SINGLE_BYTES(ext_parser,
+ test_data->parse_text,
+ strlen(test_data->parse_text),
+ XML_TRUE) == XML_STATUS_ERROR) {
+ xml_failure(ext_parser);
+ }
+
+ XML_ParserFree(ext_parser);
+ return XML_STATUS_OK;
+}
+
+START_TEST(test_skipped_null_loaded_ext_entity)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM 'http://example.org/one.ent'>\n"
+ "<doc />";
+ ExtHdlrData test_data = {
+ "<!ENTITY % pe1 SYSTEM 'http://example.org/two.ent'>\n"
+ "<!ENTITY % pe2 '%pe1;'>\n"
+ "%pe2;\n",
+ external_entity_null_loader
+ };
+
+ XML_SetUserData(parser, &test_data);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_oneshot_loader);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
+START_TEST(test_skipped_unloaded_ext_entity)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM 'http://example.org/one.ent'>\n"
+ "<doc />";
+ ExtHdlrData test_data = {
+ "<!ENTITY % pe1 SYSTEM 'http://example.org/two.ent'>\n"
+ "<!ENTITY % pe2 '%pe1;'>\n"
+ "%pe2;\n",
+ NULL
+ };
+
+ XML_SetUserData(parser, &test_data);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_oneshot_loader);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
+/* Test that a parameter entity value ending with a carriage return
+ * has it translated internally into a newline.
+ */
+START_TEST(test_param_entity_with_trailing_cr)
+{
+#define PARAM_ENTITY_NAME "pe"
+#define PARAM_ENTITY_CORE_VALUE "<!ATTLIST doc att CDATA \"default\">"
+ const char *text =
+ "<!DOCTYPE doc SYSTEM 'http://example.org/'>\n"
+ "<doc/>";
+ ExtTest test_data = {
+ "<!ENTITY % " PARAM_ENTITY_NAME
+ " '" PARAM_ENTITY_CORE_VALUE "\r'>\n"
+ "%" PARAM_ENTITY_NAME ";\n",
+ NULL,
+ NULL
+ };
+
+ XML_SetUserData(parser, &test_data);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_loader);
+ XML_SetEntityDeclHandler(parser, param_entity_match_handler);
+ entity_name_to_match = XCS(PARAM_ENTITY_NAME);
+ entity_value_to_match = XCS(PARAM_ENTITY_CORE_VALUE) XCS("\n");
+ entity_match_flag = ENTITY_MATCH_NOT_FOUND;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ if (entity_match_flag == ENTITY_MATCH_FAIL)
+ fail("Parameter entity CR->NEWLINE conversion failed");
+ else if (entity_match_flag == ENTITY_MATCH_NOT_FOUND)
+ fail("Parameter entity not parsed");
+}
+#undef PARAM_ENTITY_NAME
+#undef PARAM_ENTITY_CORE_VALUE
+END_TEST
+
+START_TEST(test_invalid_character_entity)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY entity '&#x110000;'>\n"
+ "]>\n"
+ "<doc>&entity;</doc>";
+
+ expect_failure(text, XML_ERROR_BAD_CHAR_REF,
+ "Out of range character reference not faulted");
+}
+END_TEST
+
+START_TEST(test_invalid_character_entity_2)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY entity '&#xg0;'>\n"
+ "]>\n"
+ "<doc>&entity;</doc>";
+
+ expect_failure(text, XML_ERROR_INVALID_TOKEN,
+ "Out of range character reference not faulted");
+}
+END_TEST
+
+START_TEST(test_invalid_character_entity_3)
+{
+ const char text[] =
+ /* <!DOCTYPE doc [\n */
+ "\0<\0!\0D\0O\0C\0T\0Y\0P\0E\0 \0d\0o\0c\0 \0[\0\n"
+ /* U+0E04 = KHO KHWAI
+ * U+0E08 = CHO CHAN */
+ /* <!ENTITY entity '&\u0e04\u0e08;'>\n */
+ "\0<\0!\0E\0N\0T\0I\0T\0Y\0 \0e\0n\0t\0i\0t\0y\0 "
+ "\0'\0&\x0e\x04\x0e\x08\0;\0'\0>\0\n"
+ /* ]>\n */
+ "\0]\0>\0\n"
+ /* <doc>&entity;</doc> */
+ "\0<\0d\0o\0c\0>\0&\0e\0n\0t\0i\0t\0y\0;\0<\0/\0d\0o\0c\0>";
+
+ if (_XML_Parse_SINGLE_BYTES(parser, text, sizeof(text)-1,
+ XML_TRUE) != XML_STATUS_ERROR)
+ fail("Invalid start of entity name not faulted");
+ if (XML_GetErrorCode(parser) != XML_ERROR_UNDEFINED_ENTITY)
+ xml_failure(parser);
+}
+END_TEST
+
+START_TEST(test_invalid_character_entity_4)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY entity '&#1114112;'>\n" /* = &#x110000 */
+ "]>\n"
+ "<doc>&entity;</doc>";
+
+ expect_failure(text, XML_ERROR_BAD_CHAR_REF,
+ "Out of range character reference not faulted");
+}
+END_TEST
+
+
+/* Test that processing instructions are picked up by a default handler */
+START_TEST(test_pi_handled_in_default)
+{
+ const char *text = "<?test processing instruction?>\n<doc/>";
+ const XML_Char *expected = XCS("<?test processing instruction?>\n<doc/>");
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetDefaultHandler(parser, accumulate_characters);
+ XML_SetUserData(parser, &storage);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE)== XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+
+/* Test that comments are picked up by a default handler */
+START_TEST(test_comment_handled_in_default)
+{
+ const char *text = "<!-- This is a comment -->\n<doc/>";
+ const XML_Char *expected = XCS("<!-- This is a comment -->\n<doc/>");
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetDefaultHandler(parser, accumulate_characters);
+ XML_SetUserData(parser, &storage);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+/* Test PIs that look almost but not quite like XML declarations */
+static void XMLCALL
+accumulate_pi_characters(void *userData,
+ const XML_Char *target,
+ const XML_Char *data)
+{
+ CharData *storage = (CharData *)userData;
+
+ CharData_AppendXMLChars(storage, target, -1);
+ CharData_AppendXMLChars(storage, XCS(": "), 2);
+ CharData_AppendXMLChars(storage, data, -1);
+ CharData_AppendXMLChars(storage, XCS("\n"), 1);
+}
+
+START_TEST(test_pi_yml)
+{
+ const char *text = "<?yml something like data?><doc/>";
+ const XML_Char *expected = XCS("yml: something like data\n");
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetProcessingInstructionHandler(parser, accumulate_pi_characters);
+ XML_SetUserData(parser, &storage);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+START_TEST(test_pi_xnl)
+{
+ const char *text = "<?xnl nothing like data?><doc/>";
+ const XML_Char *expected = XCS("xnl: nothing like data\n");
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetProcessingInstructionHandler(parser, accumulate_pi_characters);
+ XML_SetUserData(parser, &storage);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+START_TEST(test_pi_xmm)
+{
+ const char *text = "<?xmm everything like data?><doc/>";
+ const XML_Char *expected = XCS("xmm: everything like data\n");
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetProcessingInstructionHandler(parser, accumulate_pi_characters);
+ XML_SetUserData(parser, &storage);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+START_TEST(test_utf16_pi)
+{
+ const char text[] =
+ /* <?{KHO KHWAI}{CHO CHAN}?>
+ * where {KHO KHWAI} = U+0E04
+ * and {CHO CHAN} = U+0E08
+ */
+ "<\0?\0\x04\x0e\x08\x0e?\0>\0"
+ /* <q/> */
+ "<\0q\0/\0>\0";
+#ifdef XML_UNICODE
+ const XML_Char *expected = XCS("\x0e04\x0e08: \n");
+#else
+ const XML_Char *expected = XCS("\xe0\xb8\x84\xe0\xb8\x88: \n");
+#endif
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetProcessingInstructionHandler(parser, accumulate_pi_characters);
+ XML_SetUserData(parser, &storage);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, sizeof(text)-1,
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+START_TEST(test_utf16_be_pi)
+{
+ const char text[] =
+ /* <?{KHO KHWAI}{CHO CHAN}?>
+ * where {KHO KHWAI} = U+0E04
+ * and {CHO CHAN} = U+0E08
+ */
+ "\0<\0?\x0e\x04\x0e\x08\0?\0>"
+ /* <q/> */
+ "\0<\0q\0/\0>";
+#ifdef XML_UNICODE
+ const XML_Char *expected = XCS("\x0e04\x0e08: \n");
+#else
+ const XML_Char *expected = XCS("\xe0\xb8\x84\xe0\xb8\x88: \n");
+#endif
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetProcessingInstructionHandler(parser, accumulate_pi_characters);
+ XML_SetUserData(parser, &storage);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, sizeof(text)-1,
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+/* Test that comments can be picked up and translated */
+static void XMLCALL
+accumulate_comment(void *userData,
+ const XML_Char *data)
+{
+ CharData *storage = (CharData *)userData;
+
+ CharData_AppendXMLChars(storage, data, -1);
+}
+
+START_TEST(test_utf16_be_comment)
+{
+ const char text[] =
+ /* <!-- Comment A --> */
+ "\0<\0!\0-\0-\0 \0C\0o\0m\0m\0e\0n\0t\0 \0A\0 \0-\0-\0>\0\n"
+ /* <doc/> */
+ "\0<\0d\0o\0c\0/\0>";
+ const XML_Char *expected = XCS(" Comment A ");
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetCommentHandler(parser, accumulate_comment);
+ XML_SetUserData(parser, &storage);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, sizeof(text)-1,
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+START_TEST(test_utf16_le_comment)
+{
+ const char text[] =
+ /* <!-- Comment B --> */
+ "<\0!\0-\0-\0 \0C\0o\0m\0m\0e\0n\0t\0 \0B\0 \0-\0-\0>\0\n\0"
+ /* <doc/> */
+ "<\0d\0o\0c\0/\0>\0";
+ const XML_Char *expected = XCS(" Comment B ");
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetCommentHandler(parser, accumulate_comment);
+ XML_SetUserData(parser, &storage);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, sizeof(text)-1,
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+/* Test that the unknown encoding handler with map entries that expect
+ * conversion but no conversion function is faulted
+ */
+static int XMLCALL
+failing_converter(void *UNUSED_P(data), const char *UNUSED_P(s))
+{
+ /* Always claim to have failed */
+ return -1;
+}
+
+static int XMLCALL
+prefix_converter(void *UNUSED_P(data), const char *s)
+{
+ /* If the first byte is 0xff, raise an error */
+ if (s[0] == (char)-1)
+ return -1;
+ /* Just add the low bits of the first byte to the second */
+ return (s[1] + (s[0] & 0x7f)) & 0x01ff;
+}
+
+static int XMLCALL
+MiscEncodingHandler(void *data,
+ const XML_Char *encoding,
+ XML_Encoding *info)
+{
+ int i;
+ int high_map = -2; /* Assume a 2-byte sequence */
+
+ if (!xcstrcmp(encoding, XCS("invalid-9")) ||
+ !xcstrcmp(encoding, XCS("ascii-like")) ||
+ !xcstrcmp(encoding, XCS("invalid-len")) ||
+ !xcstrcmp(encoding, XCS("invalid-a")) ||
+ !xcstrcmp(encoding, XCS("invalid-surrogate")) ||
+ !xcstrcmp(encoding, XCS("invalid-high")))
+ high_map = -1;
+
+ for (i = 0; i < 128; ++i)
+ info->map[i] = i;
+ for (; i < 256; ++i)
+ info->map[i] = high_map;
+
+ /* If required, put an invalid value in the ASCII entries */
+ if (!xcstrcmp(encoding, XCS("invalid-9")))
+ info->map[9] = 5;
+ /* If required, have a top-bit set character starts a 5-byte sequence */
+ if (!xcstrcmp(encoding, XCS("invalid-len")))
+ info->map[0x81] = -5;
+ /* If required, make a top-bit set character a valid ASCII character */
+ if (!xcstrcmp(encoding, XCS("invalid-a")))
+ info->map[0x82] = 'a';
+ /* If required, give a top-bit set character a forbidden value,
+ * what would otherwise be the first of a surrogate pair.
+ */
+ if (!xcstrcmp(encoding, XCS("invalid-surrogate")))
+ info->map[0x83] = 0xd801;
+ /* If required, give a top-bit set character too high a value */
+ if (!xcstrcmp(encoding, XCS("invalid-high")))
+ info->map[0x84] = 0x010101;
+
+ info->data = data;
+ info->release = NULL;
+ if (!xcstrcmp(encoding, XCS("failing-conv")))
+ info->convert = failing_converter;
+ else if (!xcstrcmp(encoding, XCS("prefix-conv")))
+ info->convert = prefix_converter;
+ else
+ info->convert = NULL;
+ return XML_STATUS_OK;
+}
+
+START_TEST(test_missing_encoding_conversion_fn)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='no-conv'?>\n"
+ "<doc>\x81</doc>";
+
+ XML_SetUnknownEncodingHandler(parser, MiscEncodingHandler, NULL);
+ /* MiscEncodingHandler sets up an encoding with every top-bit-set
+ * character introducing a two-byte sequence. For this, it
+ * requires a convert function. The above function call doesn't
+ * pass one through, so when BadEncodingHandler actually gets
+ * called it should supply an invalid encoding.
+ */
+ expect_failure(text, XML_ERROR_UNKNOWN_ENCODING,
+ "Encoding with missing convert() not faulted");
+}
+END_TEST
+
+START_TEST(test_failing_encoding_conversion_fn)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='failing-conv'?>\n"
+ "<doc>\x81</doc>";
+
+ XML_SetUnknownEncodingHandler(parser, MiscEncodingHandler, NULL);
+ /* BadEncodingHandler sets up an encoding with every top-bit-set
+ * character introducing a two-byte sequence. For this, it
+ * requires a convert function. The above function call passes
+ * one that insists all possible sequences are invalid anyway.
+ */
+ expect_failure(text, XML_ERROR_INVALID_TOKEN,
+ "Encoding with failing convert() not faulted");
+}
+END_TEST
+
+/* Test unknown encoding conversions */
+START_TEST(test_unknown_encoding_success)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='prefix-conv'?>\n"
+ /* Equivalent to <eoc>Hello, world</eoc> */
+ "<\x81\x64\x80oc>Hello, world</\x81\x64\x80oc>";
+
+ XML_SetUnknownEncodingHandler(parser, MiscEncodingHandler, NULL);
+ run_character_check(text, XCS("Hello, world"));
+}
+END_TEST
+
+/* Test bad name character in unknown encoding */
+START_TEST(test_unknown_encoding_bad_name)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='prefix-conv'?>\n"
+ "<\xff\x64oc>Hello, world</\xff\x64oc>";
+
+ XML_SetUnknownEncodingHandler(parser, MiscEncodingHandler, NULL);
+ expect_failure(text, XML_ERROR_INVALID_TOKEN,
+ "Bad name start in unknown encoding not faulted");
+}
+END_TEST
+
+/* Test bad mid-name character in unknown encoding */
+START_TEST(test_unknown_encoding_bad_name_2)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='prefix-conv'?>\n"
+ "<d\xffoc>Hello, world</d\xffoc>";
+
+ XML_SetUnknownEncodingHandler(parser, MiscEncodingHandler, NULL);
+ expect_failure(text, XML_ERROR_INVALID_TOKEN,
+ "Bad name in unknown encoding not faulted");
+}
+END_TEST
+
+/* Test element name that is long enough to fill the conversion buffer
+ * in an unknown encoding, finishing with an encoded character.
+ */
+START_TEST(test_unknown_encoding_long_name_1)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='prefix-conv'?>\n"
+ "<abcdefghabcdefghabcdefghijkl\x80m\x80n\x80o\x80p>"
+ "Hi"
+ "</abcdefghabcdefghabcdefghijkl\x80m\x80n\x80o\x80p>";
+ const XML_Char *expected = XCS("abcdefghabcdefghabcdefghijklmnop");
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetUnknownEncodingHandler(parser, MiscEncodingHandler, NULL);
+ XML_SetStartElementHandler(parser, record_element_start_handler);
+ XML_SetUserData(parser, &storage);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+/* Test element name that is long enough to fill the conversion buffer
+ * in an unknown encoding, finishing with an simple character.
+ */
+START_TEST(test_unknown_encoding_long_name_2)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='prefix-conv'?>\n"
+ "<abcdefghabcdefghabcdefghijklmnop>"
+ "Hi"
+ "</abcdefghabcdefghabcdefghijklmnop>";
+ const XML_Char *expected = XCS("abcdefghabcdefghabcdefghijklmnop");
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetUnknownEncodingHandler(parser, MiscEncodingHandler, NULL);
+ XML_SetStartElementHandler(parser, record_element_start_handler);
+ XML_SetUserData(parser, &storage);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+START_TEST(test_invalid_unknown_encoding)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='invalid-9'?>\n"
+ "<doc>Hello world</doc>";
+
+ XML_SetUnknownEncodingHandler(parser, MiscEncodingHandler, NULL);
+ expect_failure(text, XML_ERROR_UNKNOWN_ENCODING,
+ "Invalid unknown encoding not faulted");
+}
+END_TEST
+
+START_TEST(test_unknown_ascii_encoding_ok)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='ascii-like'?>\n"
+ "<doc>Hello, world</doc>";
+
+ XML_SetUnknownEncodingHandler(parser, MiscEncodingHandler, NULL);
+ run_character_check(text, XCS("Hello, world"));
+}
+END_TEST
+
+START_TEST(test_unknown_ascii_encoding_fail)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='ascii-like'?>\n"
+ "<doc>Hello, \x80 world</doc>";
+
+ XML_SetUnknownEncodingHandler(parser, MiscEncodingHandler, NULL);
+ expect_failure(text, XML_ERROR_INVALID_TOKEN,
+ "Invalid character not faulted");
+}
+END_TEST
+
+START_TEST(test_unknown_encoding_invalid_length)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='invalid-len'?>\n"
+ "<doc>Hello, world</doc>";
+
+ XML_SetUnknownEncodingHandler(parser, MiscEncodingHandler, NULL);
+ expect_failure(text, XML_ERROR_UNKNOWN_ENCODING,
+ "Invalid unknown encoding not faulted");
+}
+END_TEST
+
+START_TEST(test_unknown_encoding_invalid_topbit)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='invalid-a'?>\n"
+ "<doc>Hello, world</doc>";
+
+ XML_SetUnknownEncodingHandler(parser, MiscEncodingHandler, NULL);
+ expect_failure(text, XML_ERROR_UNKNOWN_ENCODING,
+ "Invalid unknown encoding not faulted");
+}
+END_TEST
+
+START_TEST(test_unknown_encoding_invalid_surrogate)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='invalid-surrogate'?>\n"
+ "<doc>Hello, \x82 world</doc>";
+
+ XML_SetUnknownEncodingHandler(parser, MiscEncodingHandler, NULL);
+ expect_failure(text, XML_ERROR_INVALID_TOKEN,
+ "Invalid unknown encoding not faulted");
+}
+END_TEST
+
+START_TEST(test_unknown_encoding_invalid_high)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='invalid-high'?>\n"
+ "<doc>Hello, world</doc>";
+
+ XML_SetUnknownEncodingHandler(parser, MiscEncodingHandler, NULL);
+ expect_failure(text, XML_ERROR_UNKNOWN_ENCODING,
+ "Invalid unknown encoding not faulted");
+}
+END_TEST
+
+START_TEST(test_unknown_encoding_invalid_attr_value)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='prefix-conv'?>\n"
+ "<doc attr='\xff\x30'/>";
+
+ XML_SetUnknownEncodingHandler(parser, MiscEncodingHandler, NULL);
+ expect_failure(text, XML_ERROR_INVALID_TOKEN,
+ "Invalid attribute valid not faulted");
+}
+END_TEST
+
+/* Test an external entity parser set to use latin-1 detects UTF-16
+ * BOMs correctly.
+ */
+enum ee_parse_flags {
+ EE_PARSE_NONE = 0x00,
+ EE_PARSE_FULL_BUFFER = 0x01
+};
+
+typedef struct ExtTest2 {
+ const char *parse_text;
+ int parse_len;
+ const XML_Char *encoding;
+ CharData *storage;
+ enum ee_parse_flags flags;
+} ExtTest2;
+
+static int XMLCALL
+external_entity_loader2(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ ExtTest2 *test_data = (ExtTest2 *)XML_GetUserData(parser);
+ XML_Parser extparser;
+
+ extparser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (extparser == NULL)
+ fail("Coulr not create external entity parser");
+ if (test_data->encoding != NULL) {
+ if (!XML_SetEncoding(extparser, test_data->encoding))
+ fail("XML_SetEncoding() ignored for external entity");
+ }
+ if (test_data->flags & EE_PARSE_FULL_BUFFER) {
+ if (XML_Parse(extparser,
+ test_data->parse_text,
+ test_data->parse_len,
+ XML_TRUE) == XML_STATUS_ERROR) {
+ xml_failure(extparser);
+ }
+ }
+ else if (_XML_Parse_SINGLE_BYTES(extparser,
+ test_data->parse_text,
+ test_data->parse_len,
+ XML_TRUE) == XML_STATUS_ERROR) {
+ xml_failure(extparser);
+ }
+
+ XML_ParserFree(extparser);
+ return XML_STATUS_OK;
+}
+
+/* Test that UTF-16 BOM does not select UTF-16 given explicit encoding */
+static void XMLCALL
+ext2_accumulate_characters(void *userData, const XML_Char *s, int len)
+{
+ ExtTest2 *test_data = (ExtTest2 *)userData;
+ accumulate_characters(test_data->storage, s, len);
+}
+
+START_TEST(test_ext_entity_latin1_utf16le_bom)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY en SYSTEM 'http://example.org/dummy.ent'>\n"
+ "]>\n"
+ "<doc>&en;</doc>";
+ ExtTest2 test_data = {
+ /* If UTF-16, 0xfeff is the BOM and 0x204c is black left bullet */
+ /* If Latin-1, 0xff = Y-diaeresis, 0xfe = lowercase thorn,
+ * 0x4c = L and 0x20 is a space
+ */
+ "\xff\xfe\x4c\x20",
+ 4,
+ XCS("iso-8859-1"),
+ NULL,
+ EE_PARSE_NONE
+ };
+#ifdef XML_UNICODE
+ const XML_Char *expected = XCS("\x00ff\x00feL ");
+#else
+ /* In UTF-8, y-diaeresis is 0xc3 0xbf, lowercase thorn is 0xc3 0xbe */
+ const XML_Char *expected = XCS("\xc3\xbf\xc3\xbeL ");
+#endif
+ CharData storage;
+
+
+ CharData_Init(&storage);
+ test_data.storage = &storage;
+ XML_SetExternalEntityRefHandler(parser, external_entity_loader2);
+ XML_SetUserData(parser, &test_data);
+ XML_SetCharacterDataHandler(parser, ext2_accumulate_characters);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+START_TEST(test_ext_entity_latin1_utf16be_bom)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY en SYSTEM 'http://example.org/dummy.ent'>\n"
+ "]>\n"
+ "<doc>&en;</doc>";
+ ExtTest2 test_data = {
+ /* If UTF-16, 0xfeff is the BOM and 0x204c is black left bullet */
+ /* If Latin-1, 0xff = Y-diaeresis, 0xfe = lowercase thorn,
+ * 0x4c = L and 0x20 is a space
+ */
+ "\xfe\xff\x20\x4c",
+ 4,
+ XCS("iso-8859-1"),
+ NULL,
+ EE_PARSE_NONE
+ };
+#ifdef XML_UNICODE
+ const XML_Char *expected = XCS("\x00fe\x00ff L");
+#else
+ /* In UTF-8, y-diaeresis is 0xc3 0xbf, lowercase thorn is 0xc3 0xbe */
+ const XML_Char *expected = XCS("\xc3\xbe\xc3\xbf L");
+#endif
+ CharData storage;
+
+
+ CharData_Init(&storage);
+ test_data.storage = &storage;
+ XML_SetExternalEntityRefHandler(parser, external_entity_loader2);
+ XML_SetUserData(parser, &test_data);
+ XML_SetCharacterDataHandler(parser, ext2_accumulate_characters);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+
+/* Parsing the full buffer rather than a byte at a time makes a
+ * difference to the encoding scanning code, so repeat the above tests
+ * without breaking them down by byte.
+ */
+START_TEST(test_ext_entity_latin1_utf16le_bom2)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY en SYSTEM 'http://example.org/dummy.ent'>\n"
+ "]>\n"
+ "<doc>&en;</doc>";
+ ExtTest2 test_data = {
+ /* If UTF-16, 0xfeff is the BOM and 0x204c is black left bullet */
+ /* If Latin-1, 0xff = Y-diaeresis, 0xfe = lowercase thorn,
+ * 0x4c = L and 0x20 is a space
+ */
+ "\xff\xfe\x4c\x20",
+ 4,
+ XCS("iso-8859-1"),
+ NULL,
+ EE_PARSE_FULL_BUFFER
+ };
+#ifdef XML_UNICODE
+ const XML_Char *expected = XCS("\x00ff\x00feL ");
+#else
+ /* In UTF-8, y-diaeresis is 0xc3 0xbf, lowercase thorn is 0xc3 0xbe */
+ const XML_Char *expected = XCS("\xc3\xbf\xc3\xbeL ");
+#endif
+ CharData storage;
+
+
+ CharData_Init(&storage);
+ test_data.storage = &storage;
+ XML_SetExternalEntityRefHandler(parser, external_entity_loader2);
+ XML_SetUserData(parser, &test_data);
+ XML_SetCharacterDataHandler(parser, ext2_accumulate_characters);
+ if (XML_Parse(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+START_TEST(test_ext_entity_latin1_utf16be_bom2)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY en SYSTEM 'http://example.org/dummy.ent'>\n"
+ "]>\n"
+ "<doc>&en;</doc>";
+ ExtTest2 test_data = {
+ /* If UTF-16, 0xfeff is the BOM and 0x204c is black left bullet */
+ /* If Latin-1, 0xff = Y-diaeresis, 0xfe = lowercase thorn,
+ * 0x4c = L and 0x20 is a space
+ */
+ "\xfe\xff\x20\x4c",
+ 4,
+ XCS("iso-8859-1"),
+ NULL,
+ EE_PARSE_FULL_BUFFER
+ };
+#ifdef XML_UNICODE
+ const XML_Char *expected = XCS("\x00fe\x00ff L");
+#else
+ /* In UTF-8, y-diaeresis is 0xc3 0xbf, lowercase thorn is 0xc3 0xbe */
+ const XML_Char *expected = "\xc3\xbe\xc3\xbf L";
+#endif
+ CharData storage;
+
+
+ CharData_Init(&storage);
+ test_data.storage = &storage;
+ XML_SetExternalEntityRefHandler(parser, external_entity_loader2);
+ XML_SetUserData(parser, &test_data);
+ XML_SetCharacterDataHandler(parser, ext2_accumulate_characters);
+ if (XML_Parse(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+/* Test little-endian UTF-16 given an explicit big-endian encoding */
+START_TEST(test_ext_entity_utf16_be)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY en SYSTEM 'http://example.org/dummy.ent'>\n"
+ "]>\n"
+ "<doc>&en;</doc>";
+ ExtTest2 test_data = {
+ "<\0e\0/\0>\0",
+ 8,
+ XCS("utf-16be"),
+ NULL,
+ EE_PARSE_NONE
+ };
+#ifdef XML_UNICODE
+ const XML_Char *expected = XCS("\x3c00\x6500\x2f00\x3e00");
+#else
+ const XML_Char *expected =
+ XCS("\xe3\xb0\x80" /* U+3C00 */
+ "\xe6\x94\x80" /* U+6500 */
+ "\xe2\xbc\x80" /* U+2F00 */
+ "\xe3\xb8\x80"); /* U+3E00 */
+#endif
+ CharData storage;
+
+ CharData_Init(&storage);
+ test_data.storage = &storage;
+ XML_SetExternalEntityRefHandler(parser, external_entity_loader2);
+ XML_SetUserData(parser, &test_data);
+ XML_SetCharacterDataHandler(parser, ext2_accumulate_characters);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+/* Test big-endian UTF-16 given an explicit little-endian encoding */
+START_TEST(test_ext_entity_utf16_le)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY en SYSTEM 'http://example.org/dummy.ent'>\n"
+ "]>\n"
+ "<doc>&en;</doc>";
+ ExtTest2 test_data = {
+ "\0<\0e\0/\0>",
+ 8,
+ XCS("utf-16le"),
+ NULL,
+ EE_PARSE_NONE
+ };
+#ifdef XML_UNICODE
+ const XML_Char *expected = XCS("\x3c00\x6500\x2f00\x3e00");
+#else
+ const XML_Char *expected =
+ XCS("\xe3\xb0\x80" /* U+3C00 */
+ "\xe6\x94\x80" /* U+6500 */
+ "\xe2\xbc\x80" /* U+2F00 */
+ "\xe3\xb8\x80"); /* U+3E00 */
+#endif
+ CharData storage;
+
+ CharData_Init(&storage);
+ test_data.storage = &storage;
+ XML_SetExternalEntityRefHandler(parser, external_entity_loader2);
+ XML_SetUserData(parser, &test_data);
+ XML_SetCharacterDataHandler(parser, ext2_accumulate_characters);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+/* Test little-endian UTF-16 given no explicit encoding.
+ * The existing default encoding (UTF-8) is assumed to hold without a
+ * BOM to contradict it, so the entity value will in fact provoke an
+ * error because 0x00 is not a valid XML character. We parse the
+ * whole buffer in one go rather than feeding it in byte by byte to
+ * exercise different code paths in the initial scanning routines.
+ */
+typedef struct ExtFaults2 {
+ const char *parse_text;
+ int parse_len;
+ const char *fail_text;
+ const XML_Char *encoding;
+ enum XML_Error error;
+} ExtFaults2;
+
+static int XMLCALL
+external_entity_faulter2(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ ExtFaults2 *test_data = (ExtFaults2 *)XML_GetUserData(parser);
+ XML_Parser extparser;
+
+ extparser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (extparser == NULL)
+ fail("Could not create external entity parser");
+ if (test_data->encoding != NULL) {
+ if (!XML_SetEncoding(extparser, test_data->encoding))
+ fail("XML_SetEncoding() ignored for external entity");
+ }
+ if (XML_Parse(extparser,
+ test_data->parse_text,
+ test_data->parse_len,
+ XML_TRUE) != XML_STATUS_ERROR)
+ fail(test_data->fail_text);
+ if (XML_GetErrorCode(extparser) != test_data->error)
+ xml_failure(extparser);
+
+ XML_ParserFree(extparser);
+ return XML_STATUS_ERROR;
+}
+
+START_TEST(test_ext_entity_utf16_unknown)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY en SYSTEM 'http://example.org/dummy.ent'>\n"
+ "]>\n"
+ "<doc>&en;</doc>";
+ ExtFaults2 test_data = {
+ "a\0b\0c\0",
+ 6,
+ "Invalid character in entity not faulted",
+ NULL,
+ XML_ERROR_INVALID_TOKEN
+ };
+
+ XML_SetExternalEntityRefHandler(parser, external_entity_faulter2);
+ XML_SetUserData(parser, &test_data);
+ expect_failure(text, XML_ERROR_EXTERNAL_ENTITY_HANDLING,
+ "Invalid character should not have been accepted");
+}
+END_TEST
+
+/* Test not-quite-UTF-8 BOM (0xEF 0xBB 0xBF) */
+START_TEST(test_ext_entity_utf8_non_bom)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY en SYSTEM 'http://example.org/dummy.ent'>\n"
+ "]>\n"
+ "<doc>&en;</doc>";
+ ExtTest2 test_data = {
+ "\xef\xbb\x80", /* Arabic letter DAD medial form, U+FEC0 */
+ 3,
+ NULL,
+ NULL,
+ EE_PARSE_NONE
+ };
+#ifdef XML_UNICODE
+ const XML_Char *expected = XCS("\xfec0");
+#else
+ const XML_Char *expected = XCS("\xef\xbb\x80");
+#endif
+ CharData storage;
+
+ CharData_Init(&storage);
+ test_data.storage = &storage;
+ XML_SetExternalEntityRefHandler(parser, external_entity_loader2);
+ XML_SetUserData(parser, &test_data);
+ XML_SetCharacterDataHandler(parser, ext2_accumulate_characters);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+/* Test that UTF-8 in a CDATA section is correctly passed through */
+START_TEST(test_utf8_in_cdata_section)
+{
+ const char *text = "<doc><![CDATA[one \xc3\xa9 two]]></doc>";
+#ifdef XML_UNICODE
+ const XML_Char *expected = XCS("one \x00e9 two");
+#else
+ const XML_Char *expected = XCS("one \xc3\xa9 two");
+#endif
+
+ run_character_check(text, expected);
+}
+END_TEST
+
+/* Test that little-endian UTF-16 in a CDATA section is handled */
+START_TEST(test_utf8_in_cdata_section_2)
+{
+ const char *text = "<doc><![CDATA[\xc3\xa9]\xc3\xa9two]]></doc>";
+#ifdef XML_UNICODE
+ const XML_Char *expected = XCS("\x00e9]\x00e9two");
+#else
+ const XML_Char *expected = XCS("\xc3\xa9]\xc3\xa9two");
+#endif
+
+ run_character_check(text, expected);
+}
+END_TEST
+
+/* Test trailing spaces in elements are accepted */
+static void XMLCALL
+record_element_end_handler(void *userData,
+ const XML_Char *name)
+{
+ CharData *storage = (CharData *)userData;
+
+ CharData_AppendXMLChars(storage, XCS("/"), 1);
+ CharData_AppendXMLChars(storage, name, -1);
+}
+
+START_TEST(test_trailing_spaces_in_elements)
+{
+ const char *text = "<doc >Hi</doc >";
+ const XML_Char *expected = XCS("doc/doc");
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetElementHandler(parser, record_element_start_handler,
+ record_element_end_handler);
+ XML_SetUserData(parser, &storage);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+START_TEST(test_utf16_attribute)
+{
+ const char text[] =
+ /* <d {KHO KHWAI}{CHO CHAN}='a'/>
+ * where {KHO KHWAI} = U+0E04 = 0xe0 0xb8 0x84 in UTF-8
+ * and {CHO CHAN} = U+0E08 = 0xe0 0xb8 0x88 in UTF-8
+ */
+ "<\0d\0 \0\x04\x0e\x08\x0e=\0'\0a\0'\0/\0>\0";
+ const XML_Char *expected = XCS("a");
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetStartElementHandler(parser, accumulate_attribute);
+ XML_SetUserData(parser, &storage);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, sizeof(text)-1,
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+START_TEST(test_utf16_second_attr)
+{
+ /* <d a='1' {KHO KHWAI}{CHO CHAN}='2'/>
+ * where {KHO KHWAI} = U+0E04 = 0xe0 0xb8 0x84 in UTF-8
+ * and {CHO CHAN} = U+0E08 = 0xe0 0xb8 0x88 in UTF-8
+ */
+ const char text[] =
+ "<\0d\0 \0a\0=\0'\0\x31\0'\0 \0"
+ "\x04\x0e\x08\x0e=\0'\0\x32\0'\0/\0>\0";
+ const XML_Char *expected = XCS("1");
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetStartElementHandler(parser, accumulate_attribute);
+ XML_SetUserData(parser, &storage);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, sizeof(text)-1,
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+START_TEST(test_attr_after_solidus)
+{
+ const char *text = "<doc attr1='a' / attr2='b'>";
+
+ expect_failure(text, XML_ERROR_INVALID_TOKEN,
+ "Misplaced / not faulted");
+}
+END_TEST
+
+static void XMLCALL
+accumulate_entity_decl(void *userData,
+ const XML_Char *entityName,
+ int UNUSED_P(is_parameter_entity),
+ const XML_Char *value,
+ int value_length,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId),
+ const XML_Char *UNUSED_P(notationName))
+{
+ CharData *storage = (CharData *)userData;
+
+ CharData_AppendXMLChars(storage, entityName, -1);
+ CharData_AppendXMLChars(storage, XCS("="), 1);
+ CharData_AppendXMLChars(storage, value, value_length);
+ CharData_AppendXMLChars(storage, XCS("\n"), 1);
+}
+
+
+START_TEST(test_utf16_pe)
+{
+ /* <!DOCTYPE doc [
+ * <!ENTITY % {KHO KHWAI}{CHO CHAN} '<!ELEMENT doc (#PCDATA)>'>
+ * %{KHO KHWAI}{CHO CHAN};
+ * ]>
+ * <doc></doc>
+ *
+ * where {KHO KHWAI} = U+0E04 = 0xe0 0xb8 0x84 in UTF-8
+ * and {CHO CHAN} = U+0E08 = 0xe0 0xb8 0x88 in UTF-8
+ */
+ const char text[] =
+ "\0<\0!\0D\0O\0C\0T\0Y\0P\0E\0 \0d\0o\0c\0 \0[\0\n"
+ "\0<\0!\0E\0N\0T\0I\0T\0Y\0 \0%\0 \x0e\x04\x0e\x08\0 "
+ "\0'\0<\0!\0E\0L\0E\0M\0E\0N\0T\0 "
+ "\0d\0o\0c\0 \0(\0#\0P\0C\0D\0A\0T\0A\0)\0>\0'\0>\0\n"
+ "\0%\x0e\x04\x0e\x08\0;\0\n"
+ "\0]\0>\0\n"
+ "\0<\0d\0o\0c\0>\0<\0/\0d\0o\0c\0>";
+#ifdef XML_UNICODE
+ const XML_Char *expected =
+ XCS("\x0e04\x0e08=<!ELEMENT doc (#PCDATA)>\n");
+#else
+ const XML_Char *expected =
+ XCS("\xe0\xb8\x84\xe0\xb8\x88=<!ELEMENT doc (#PCDATA)>\n");
+#endif
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetUserData(parser, &storage);
+ XML_SetEntityDeclHandler(parser, accumulate_entity_decl);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, sizeof(text)-1,
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+/* Test that duff attribute description keywords are rejected */
+START_TEST(test_bad_attr_desc_keyword)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ATTLIST doc attr CDATA #!IMPLIED>\n"
+ "]>\n"
+ "<doc />";
+
+ expect_failure(text, XML_ERROR_INVALID_TOKEN,
+ "Bad keyword !IMPLIED not faulted");
+}
+END_TEST
+
+/* Test that an invalid attribute description keyword consisting of
+ * UTF-16 characters with their top bytes non-zero are correctly
+ * faulted
+ */
+START_TEST(test_bad_attr_desc_keyword_utf16)
+{
+ /* <!DOCTYPE d [
+ * <!ATTLIST d a CDATA #{KHO KHWAI}{CHO CHAN}>
+ * ]><d/>
+ *
+ * where {KHO KHWAI} = U+0E04 = 0xe0 0xb8 0x84 in UTF-8
+ * and {CHO CHAN} = U+0E08 = 0xe0 0xb8 0x88 in UTF-8
+ */
+ const char text[] =
+ "\0<\0!\0D\0O\0C\0T\0Y\0P\0E\0 \0d\0 \0[\0\n"
+ "\0<\0!\0A\0T\0T\0L\0I\0S\0T\0 \0d\0 \0a\0 \0C\0D\0A\0T\0A\0 "
+ "\0#\x0e\x04\x0e\x08\0>\0\n"
+ "\0]\0>\0<\0d\0/\0>";
+
+ if (_XML_Parse_SINGLE_BYTES(parser, text, sizeof(text)-1,
+ XML_TRUE) != XML_STATUS_ERROR)
+ fail("Invalid UTF16 attribute keyword not faulted");
+ if (XML_GetErrorCode(parser) != XML_ERROR_SYNTAX)
+ xml_failure(parser);
+}
+END_TEST
+
+/* Test that invalid syntax in a <!DOCTYPE> is rejected. Do this
+ * using prefix-encoding (see above) to trigger specific code paths
+ */
+START_TEST(test_bad_doctype)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='prefix-conv'?>\n"
+ "<!DOCTYPE doc [ \x80\x44 ]><doc/>";
+
+ XML_SetUnknownEncodingHandler(parser, MiscEncodingHandler, NULL);
+ expect_failure(text, XML_ERROR_SYNTAX,
+ "Invalid bytes in DOCTYPE not faulted");
+}
+END_TEST
+
+START_TEST(test_bad_doctype_utf16)
+{
+ const char text[] =
+ /* <!DOCTYPE doc [ \x06f2 ]><doc/>
+ *
+ * U+06F2 = EXTENDED ARABIC-INDIC DIGIT TWO, a valid number
+ * (name character) but not a valid letter (name start character)
+ */
+ "\0<\0!\0D\0O\0C\0T\0Y\0P\0E\0 \0d\0o\0c\0 \0[\0 "
+ "\x06\xf2"
+ "\0 \0]\0>\0<\0d\0o\0c\0/\0>";
+
+ if (_XML_Parse_SINGLE_BYTES(parser, text, sizeof(text)-1,
+ XML_TRUE) != XML_STATUS_ERROR)
+ fail("Invalid bytes in DOCTYPE not faulted");
+ if (XML_GetErrorCode(parser) != XML_ERROR_SYNTAX)
+ xml_failure(parser);
+}
+END_TEST
+
+START_TEST(test_bad_doctype_plus)
+{
+ const char *text =
+ "<!DOCTYPE 1+ [ <!ENTITY foo 'bar'> ]>\n"
+ "<1+>&foo;</1+>";
+
+ expect_failure(text, XML_ERROR_INVALID_TOKEN,
+ "'+' in document name not faulted");
+}
+END_TEST
+
+START_TEST(test_bad_doctype_star)
+{
+ const char *text =
+ "<!DOCTYPE 1* [ <!ENTITY foo 'bar'> ]>\n"
+ "<1*>&foo;</1*>";
+
+ expect_failure(text, XML_ERROR_INVALID_TOKEN,
+ "'*' in document name not faulted");
+}
+END_TEST
+
+START_TEST(test_bad_doctype_query)
+{
+ const char *text =
+ "<!DOCTYPE 1? [ <!ENTITY foo 'bar'> ]>\n"
+ "<1?>&foo;</1?>";
+
+ expect_failure(text, XML_ERROR_INVALID_TOKEN,
+ "'?' in document name not faulted");
+}
+END_TEST
+
+START_TEST(test_unknown_encoding_bad_ignore)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='prefix-conv'?>"
+ "<!DOCTYPE doc SYSTEM 'foo'>"
+ "<doc><e>&entity;</e></doc>";
+ ExtFaults fault = {
+ "<![IGNORE[<!ELEMENT \xffG (#PCDATA)*>]]>",
+ "Invalid character not faulted",
+ XCS("prefix-conv"),
+ XML_ERROR_INVALID_TOKEN
+ };
+
+ XML_SetUnknownEncodingHandler(parser, MiscEncodingHandler, NULL);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_faulter);
+ XML_SetUserData(parser, &fault);
+ expect_failure(text, XML_ERROR_EXTERNAL_ENTITY_HANDLING,
+ "Bad IGNORE section with unknown encoding not failed");
+}
+END_TEST
+
+START_TEST(test_entity_in_utf16_be_attr)
+{
+ const char text[] =
+ /* <e a='&#228; &#x00E4;'></e> */
+ "\0<\0e\0 \0a\0=\0'\0&\0#\0\x32\0\x32\0\x38\0;\0 "
+ "\0&\0#\0x\0\x30\0\x30\0E\0\x34\0;\0'\0>\0<\0/\0e\0>";
+#ifdef XML_UNICODE
+ const XML_Char *expected = XCS("\x00e4 \x00e4");
+#else
+ const XML_Char *expected = XCS("\xc3\xa4 \xc3\xa4");
+#endif
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetUserData(parser, &storage);
+ XML_SetStartElementHandler(parser, accumulate_attribute);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, sizeof(text)-1,
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+START_TEST(test_entity_in_utf16_le_attr)
+{
+ const char text[] =
+ /* <e a='&#228; &#x00E4;'></e> */
+ "<\0e\0 \0a\0=\0'\0&\0#\0\x32\0\x32\0\x38\0;\0 \0"
+ "&\0#\0x\0\x30\0\x30\0E\0\x34\0;\0'\0>\0<\0/\0e\0>\0";
+#ifdef XML_UNICODE
+ const XML_Char *expected = XCS("\x00e4 \x00e4");
+#else
+ const XML_Char *expected = XCS("\xc3\xa4 \xc3\xa4");
+#endif
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetUserData(parser, &storage);
+ XML_SetStartElementHandler(parser, accumulate_attribute);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, sizeof(text)-1,
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+START_TEST(test_entity_public_utf16_be)
+{
+ const char text[] =
+ /* <!DOCTYPE d [ */
+ "\0<\0!\0D\0O\0C\0T\0Y\0P\0E\0 \0d\0 \0[\0\n"
+ /* <!ENTITY % e PUBLIC 'foo' 'bar.ent'> */
+ "\0<\0!\0E\0N\0T\0I\0T\0Y\0 \0%\0 \0e\0 \0P\0U\0B\0L\0I\0C\0 "
+ "\0'\0f\0o\0o\0'\0 \0'\0b\0a\0r\0.\0e\0n\0t\0'\0>\0\n"
+ /* %e; */
+ "\0%\0e\0;\0\n"
+ /* ]> */
+ "\0]\0>\0\n"
+ /* <d>&j;</d> */
+ "\0<\0d\0>\0&\0j\0;\0<\0/\0d\0>";
+ ExtTest2 test_data = {
+ /* <!ENTITY j 'baz'> */
+ "\0<\0!\0E\0N\0T\0I\0T\0Y\0 \0j\0 \0'\0b\0a\0z\0'\0>",
+ 34,
+ NULL,
+ NULL,
+ EE_PARSE_NONE
+ };
+ const XML_Char *expected = XCS("baz");
+ CharData storage;
+
+ CharData_Init(&storage);
+ test_data.storage = &storage;
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_loader2);
+ XML_SetUserData(parser, &test_data);
+ XML_SetCharacterDataHandler(parser, ext2_accumulate_characters);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, sizeof(text)-1,
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+START_TEST(test_entity_public_utf16_le)
+{
+ const char text[] =
+ /* <!DOCTYPE d [ */
+ "<\0!\0D\0O\0C\0T\0Y\0P\0E\0 \0d\0 \0[\0\n\0"
+ /* <!ENTITY % e PUBLIC 'foo' 'bar.ent'> */
+ "<\0!\0E\0N\0T\0I\0T\0Y\0 \0%\0 \0e\0 \0P\0U\0B\0L\0I\0C\0 \0"
+ "'\0f\0o\0o\0'\0 \0'\0b\0a\0r\0.\0e\0n\0t\0'\0>\0\n\0"
+ /* %e; */
+ "%\0e\0;\0\n\0"
+ /* ]> */
+ "]\0>\0\n\0"
+ /* <d>&j;</d> */
+ "<\0d\0>\0&\0j\0;\0<\0/\0d\0>\0";
+ ExtTest2 test_data = {
+ /* <!ENTITY j 'baz'> */
+ "<\0!\0E\0N\0T\0I\0T\0Y\0 \0j\0 \0'\0b\0a\0z\0'\0>\0",
+ 34,
+ NULL,
+ NULL,
+ EE_PARSE_NONE
+ };
+ const XML_Char *expected = XCS("baz");
+ CharData storage;
+
+ CharData_Init(&storage);
+ test_data.storage = &storage;
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_loader2);
+ XML_SetUserData(parser, &test_data);
+ XML_SetCharacterDataHandler(parser, ext2_accumulate_characters);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, sizeof(text)-1,
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+/* Test that a doctype with neither an internal nor external subset is
+ * faulted
+ */
+START_TEST(test_short_doctype)
+{
+ const char *text = "<!DOCTYPE doc></doc>";
+ expect_failure(text, XML_ERROR_INVALID_TOKEN,
+ "DOCTYPE without subset not rejected");
+}
+END_TEST
+
+START_TEST(test_short_doctype_2)
+{
+ const char *text = "<!DOCTYPE doc PUBLIC></doc>";
+ expect_failure(text, XML_ERROR_SYNTAX,
+ "DOCTYPE without Public ID not rejected");
+}
+END_TEST
+
+START_TEST(test_short_doctype_3)
+{
+ const char *text = "<!DOCTYPE doc SYSTEM></doc>";
+ expect_failure(text, XML_ERROR_SYNTAX,
+ "DOCTYPE without System ID not rejected");
+}
+END_TEST
+
+START_TEST(test_long_doctype)
+{
+ const char *text = "<!DOCTYPE doc PUBLIC 'foo' 'bar' 'baz'></doc>";
+ expect_failure(text, XML_ERROR_SYNTAX,
+ "DOCTYPE with extra ID not rejected");
+}
+END_TEST
+
+START_TEST(test_bad_entity)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY foo PUBLIC>\n"
+ "]>\n"
+ "<doc/>";
+ expect_failure(text, XML_ERROR_SYNTAX,
+ "ENTITY without Public ID is not rejected");
+}
+END_TEST
+
+/* Test unquoted value is faulted */
+START_TEST(test_bad_entity_2)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY % foo bar>\n"
+ "]>\n"
+ "<doc/>";
+ expect_failure(text, XML_ERROR_SYNTAX,
+ "ENTITY without Public ID is not rejected");
+}
+END_TEST
+
+START_TEST(test_bad_entity_3)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY % foo PUBLIC>\n"
+ "]>\n"
+ "<doc/>";
+ expect_failure(text, XML_ERROR_SYNTAX,
+ "Parameter ENTITY without Public ID is not rejected");
+}
+END_TEST
+
+START_TEST(test_bad_entity_4)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY % foo SYSTEM>\n"
+ "]>\n"
+ "<doc/>";
+ expect_failure(text, XML_ERROR_SYNTAX,
+ "Parameter ENTITY without Public ID is not rejected");
+}
+END_TEST
+
+START_TEST(test_bad_notation)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!NOTATION n SYSTEM>\n"
+ "]>\n"
+ "<doc/>";
+ expect_failure(text, XML_ERROR_SYNTAX,
+ "Notation without System ID is not rejected");
+}
+END_TEST
+
+/* Test for issue #11, wrongly suppressed default handler */
+typedef struct default_check {
+ const XML_Char *expected;
+ const int expectedLen;
+ XML_Bool seen;
+} DefaultCheck;
+
+static void XMLCALL
+checking_default_handler(void *userData,
+ const XML_Char *s,
+ int len)
+{
+ DefaultCheck *data = (DefaultCheck *)userData;
+ int i;
+
+ for (i = 0; data[i].expected != NULL; i++) {
+ if (data[i].expectedLen == len &&
+ !memcmp(data[i].expected, s, len * sizeof(XML_Char))) {
+ data[i].seen = XML_TRUE;
+ break;
+ }
+ }
+}
+
+START_TEST(test_default_doctype_handler)
+{
+ const char *text =
+ "<!DOCTYPE doc PUBLIC 'pubname' 'test.dtd' [\n"
+ " <!ENTITY foo 'bar'>\n"
+ "]>\n"
+ "<doc>&foo;</doc>";
+ DefaultCheck test_data[] = {
+ {
+ XCS("'pubname'"),
+ 9,
+ XML_FALSE
+ },
+ {
+ XCS("'test.dtd'"),
+ 10,
+ XML_FALSE
+ },
+ { NULL, 0, XML_FALSE }
+ };
+ int i;
+
+ XML_SetUserData(parser, &test_data);
+ XML_SetDefaultHandler(parser, checking_default_handler);
+ XML_SetEntityDeclHandler(parser, dummy_entity_decl_handler);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ for (i = 0; test_data[i].expected != NULL; i++)
+ if (!test_data[i].seen)
+ fail("Default handler not run for public !DOCTYPE");
+}
+END_TEST
+
+START_TEST(test_empty_element_abort)
+{
+ const char *text = "<abort/>";
+
+ XML_SetStartElementHandler(parser, start_element_suspender);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ fail("Expected to error on abort");
+}
+END_TEST
/*
* Namespaces tests.
@@ -1252,7 +7078,7 @@ END_TEST
static void
namespace_setup(void)
{
- parser = XML_ParserCreateNS(NULL, ' ');
+ parser = XML_ParserCreateNS(NULL, XCS(' '));
if (parser == NULL)
fail("Parser not created.");
}
@@ -1268,20 +7094,25 @@ namespace_teardown(void)
provided as the userData argument; the first is the expected
element name, and the second is the expected attribute name.
*/
+static int triplet_start_flag = XML_FALSE;
+static int triplet_end_flag = XML_FALSE;
+
static void XMLCALL
triplet_start_checker(void *userData, const XML_Char *name,
const XML_Char **atts)
{
- char **elemstr = (char **)userData;
+ XML_Char **elemstr = (XML_Char **)userData;
char buffer[1024];
- if (strcmp(elemstr[0], name) != 0) {
- sprintf(buffer, "unexpected start string: '%s'", name);
+ if (xcstrcmp(elemstr[0], name) != 0) {
+ sprintf(buffer, "unexpected start string: '%" XML_FMT_STR "'", name);
fail(buffer);
}
- if (strcmp(elemstr[1], atts[0]) != 0) {
- sprintf(buffer, "unexpected attribute string: '%s'", atts[0]);
+ if (xcstrcmp(elemstr[1], atts[0]) != 0) {
+ sprintf(buffer, "unexpected attribute string: '%" XML_FMT_STR "'",
+ atts[0]);
fail(buffer);
}
+ triplet_start_flag = XML_TRUE;
}
/* Check that the element name passed to the end-element handler matches
@@ -1291,28 +7122,50 @@ triplet_start_checker(void *userData, const XML_Char *name,
static void XMLCALL
triplet_end_checker(void *userData, const XML_Char *name)
{
- char **elemstr = (char **)userData;
- if (strcmp(elemstr[0], name) != 0) {
+ XML_Char **elemstr = (XML_Char **)userData;
+ if (xcstrcmp(elemstr[0], name) != 0) {
char buffer[1024];
- sprintf(buffer, "unexpected end string: '%s'", name);
+ sprintf(buffer, "unexpected end string: '%" XML_FMT_STR "'", name);
fail(buffer);
}
+ triplet_end_flag = XML_TRUE;
}
START_TEST(test_return_ns_triplet)
{
const char *text =
- "<foo:e xmlns:foo='http://expat.sf.net/' bar:a='12'\n"
- " xmlns:bar='http://expat.sf.net/'></foo:e>";
- const char *elemstr[] = {
- "http://expat.sf.net/ e foo",
- "http://expat.sf.net/ a bar"
+ "<foo:e xmlns:foo='http://example.org/' bar:a='12'\n"
+ " xmlns:bar='http://example.org/'>";
+ const char *epilog = "</foo:e>";
+ const XML_Char *elemstr[] = {
+ XCS("http://example.org/ e foo"),
+ XCS("http://example.org/ a bar")
};
XML_SetReturnNSTriplet(parser, XML_TRUE);
XML_SetUserData(parser, elemstr);
- XML_SetElementHandler(parser, triplet_start_checker, triplet_end_checker);
- if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR)
+ XML_SetElementHandler(parser, triplet_start_checker,
+ triplet_end_checker);
+ XML_SetNamespaceDeclHandler(parser,
+ dummy_start_namespace_decl_handler,
+ dummy_end_namespace_decl_handler);
+ triplet_start_flag = XML_FALSE;
+ triplet_end_flag = XML_FALSE;
+ dummy_handler_flags = 0;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_FALSE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ if (!triplet_start_flag)
+ fail("triplet_start_checker not invoked");
+ /* Check that unsetting "return triplets" fails while still parsing */
+ XML_SetReturnNSTriplet(parser, XML_FALSE);
+ if (_XML_Parse_SINGLE_BYTES(parser, epilog, strlen(epilog),
+ XML_TRUE) == XML_STATUS_ERROR)
xml_failure(parser);
+ if (!triplet_end_flag)
+ fail("triplet_end_checker not invoked");
+ if (dummy_handler_flags != (DUMMY_START_NS_DECL_HANDLER_FLAG |
+ DUMMY_END_NS_DECL_HANDLER_FLAG))
+ fail("Namespace handlers not called");
}
END_TEST
@@ -1321,27 +7174,27 @@ overwrite_start_checker(void *userData, const XML_Char *name,
const XML_Char **atts)
{
CharData *storage = (CharData *) userData;
- CharData_AppendString(storage, "start ");
+ CharData_AppendXMLChars(storage, XCS("start "), 6);
CharData_AppendXMLChars(storage, name, -1);
while (*atts != NULL) {
- CharData_AppendString(storage, "\nattribute ");
+ CharData_AppendXMLChars(storage, XCS("\nattribute "), 11);
CharData_AppendXMLChars(storage, *atts, -1);
atts += 2;
}
- CharData_AppendString(storage, "\n");
+ CharData_AppendXMLChars(storage, XCS("\n"), 1);
}
static void XMLCALL
overwrite_end_checker(void *userData, const XML_Char *name)
{
CharData *storage = (CharData *) userData;
- CharData_AppendString(storage, "end ");
+ CharData_AppendXMLChars(storage, XCS("end "), 4);
CharData_AppendXMLChars(storage, name, -1);
- CharData_AppendString(storage, "\n");
+ CharData_AppendXMLChars(storage, XCS("\n"), 1);
}
static void
-run_ns_tagname_overwrite_test(const char *text, const char *result)
+run_ns_tagname_overwrite_test(const char *text, const XML_Char *result)
{
CharData storage;
CharData_Init(&storage);
@@ -1350,26 +7203,26 @@ run_ns_tagname_overwrite_test(const char *text, const char *result)
overwrite_start_checker, overwrite_end_checker);
if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR)
xml_failure(parser);
- CharData_CheckString(&storage, result);
+ CharData_CheckXMLChars(&storage, result);
}
/* Regression test for SF bug #566334. */
START_TEST(test_ns_tagname_overwrite)
{
const char *text =
- "<n:e xmlns:n='http://xml.libexpat.org/'>\n"
+ "<n:e xmlns:n='http://example.org/'>\n"
" <n:f n:attr='foo'/>\n"
" <n:g n:attr2='bar'/>\n"
"</n:e>";
- const char *result =
- "start http://xml.libexpat.org/ e\n"
- "start http://xml.libexpat.org/ f\n"
- "attribute http://xml.libexpat.org/ attr\n"
- "end http://xml.libexpat.org/ f\n"
- "start http://xml.libexpat.org/ g\n"
- "attribute http://xml.libexpat.org/ attr2\n"
- "end http://xml.libexpat.org/ g\n"
- "end http://xml.libexpat.org/ e\n";
+ const XML_Char *result =
+ XCS("start http://example.org/ e\n")
+ XCS("start http://example.org/ f\n")
+ XCS("attribute http://example.org/ attr\n")
+ XCS("end http://example.org/ f\n")
+ XCS("start http://example.org/ g\n")
+ XCS("attribute http://example.org/ attr2\n")
+ XCS("end http://example.org/ g\n")
+ XCS("end http://example.org/ e\n");
run_ns_tagname_overwrite_test(text, result);
}
END_TEST
@@ -1378,19 +7231,19 @@ END_TEST
START_TEST(test_ns_tagname_overwrite_triplet)
{
const char *text =
- "<n:e xmlns:n='http://xml.libexpat.org/'>\n"
+ "<n:e xmlns:n='http://example.org/'>\n"
" <n:f n:attr='foo'/>\n"
" <n:g n:attr2='bar'/>\n"
"</n:e>";
- const char *result =
- "start http://xml.libexpat.org/ e n\n"
- "start http://xml.libexpat.org/ f n\n"
- "attribute http://xml.libexpat.org/ attr n\n"
- "end http://xml.libexpat.org/ f n\n"
- "start http://xml.libexpat.org/ g n\n"
- "attribute http://xml.libexpat.org/ attr2 n\n"
- "end http://xml.libexpat.org/ g n\n"
- "end http://xml.libexpat.org/ e n\n";
+ const XML_Char *result =
+ XCS("start http://example.org/ e n\n")
+ XCS("start http://example.org/ f n\n")
+ XCS("attribute http://example.org/ attr n\n")
+ XCS("end http://example.org/ f n\n")
+ XCS("start http://example.org/ g n\n")
+ XCS("attribute http://example.org/ attr2 n\n")
+ XCS("end http://example.org/ g n\n")
+ XCS("end http://example.org/ e n\n");
XML_SetReturnNSTriplet(parser, XML_TRUE);
run_ns_tagname_overwrite_test(text, result);
}
@@ -1420,10 +7273,11 @@ START_TEST(test_start_ns_clears_start_element)
syntax doesn't cause the problematic path through Expat to be
taken.
*/
- const char *text = "<e xmlns='http://xml.libexpat.org/'></e>";
+ const char *text = "<e xmlns='http://example.org/'></e>";
XML_SetStartElementHandler(parser, start_element_fail);
XML_SetStartNamespaceDeclHandler(parser, start_ns_clearing_start_element);
+ XML_SetEndNamespaceDeclHandler(parser, dummy_end_namespace_decl_handler);
XML_UseParserAsHandlerArg(parser);
if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR)
xml_failure(parser);
@@ -1454,20 +7308,20 @@ external_entity_handler(XML_Parser parser,
p2 = XML_ExternalEntityParserCreate(parser, context, NULL);
if (_XML_Parse_SINGLE_BYTES(p2, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR) {
xml_failure(p2);
- return 0;
+ return XML_STATUS_ERROR;
}
XML_ParserFree(p2);
- return 1;
+ return XML_STATUS_OK;
}
START_TEST(test_default_ns_from_ext_subset_and_ext_ge)
{
const char *text =
"<?xml version='1.0'?>\n"
- "<!DOCTYPE doc SYSTEM 'http://xml.libexpat.org/doc.dtd' [\n"
- " <!ENTITY en SYSTEM 'http://xml.libexpat.org/entity.ent'>\n"
+ "<!DOCTYPE doc SYSTEM 'http://example.org/doc.dtd' [\n"
+ " <!ENTITY en SYSTEM 'http://example.org/entity.ent'>\n"
"]>\n"
- "<doc xmlns='http://xml.libexpat.org/ns1'>\n"
+ "<doc xmlns='http://example.org/ns1'>\n"
"&en;\n"
"</doc>";
@@ -1485,7 +7339,7 @@ END_TEST
START_TEST(test_ns_prefix_with_empty_uri_1)
{
const char *text =
- "<doc xmlns:prefix='http://xml.libexpat.org/'>\n"
+ "<doc xmlns:prefix='http://example.org/'>\n"
" <e xmlns:prefix=''/>\n"
"</doc>";
@@ -1533,14 +7387,14 @@ START_TEST(test_ns_prefix_with_empty_uri_4)
"<!DOCTYPE doc [\n"
" <!ELEMENT prefix:doc EMPTY>\n"
" <!ATTLIST prefix:doc\n"
- " xmlns:prefix CDATA 'http://xml.libexpat.org/'>\n"
+ " xmlns:prefix CDATA 'http://example.org/'>\n"
"]>\n"
"<prefix:doc/>";
/* Packaged info expected by the end element handler;
the weird structuring lets us re-use the triplet_end_checker()
function also used for another test. */
- const char *elemstr[] = {
- "http://xml.libexpat.org/ doc prefix"
+ const XML_Char *elemstr[] = {
+ XCS("http://example.org/ doc prefix")
};
XML_SetReturnNSTriplet(parser, XML_TRUE);
XML_SetUserData(parser, elemstr);
@@ -1550,12 +7404,36 @@ START_TEST(test_ns_prefix_with_empty_uri_4)
}
END_TEST
+/* Test with non-xmlns prefix */
+START_TEST(test_ns_unbound_prefix)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ELEMENT prefix:doc EMPTY>\n"
+ " <!ATTLIST prefix:doc\n"
+ " notxmlns:prefix CDATA 'http://example.org/'>\n"
+ "]>\n"
+ "<prefix:doc/>";
+
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ fail("Unbound prefix incorrectly passed");
+ if (XML_GetErrorCode(parser) != XML_ERROR_UNBOUND_PREFIX)
+ xml_failure(parser);
+}
+END_TEST
+
START_TEST(test_ns_default_with_empty_uri)
{
const char *text =
- "<doc xmlns='http://xml.libexpat.org/'>\n"
+ "<doc xmlns='http://example.org/'>\n"
" <e xmlns=''/>\n"
"</doc>";
+ /* Add some handlers to exercise extra code paths */
+ XML_SetStartNamespaceDeclHandler(parser,
+ dummy_start_namespace_decl_handler);
+ XML_SetEndNamespaceDeclHandler(parser,
+ dummy_end_namespace_decl_handler);
if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR)
xml_failure(parser);
}
@@ -1565,8 +7443,8 @@ END_TEST
START_TEST(test_ns_duplicate_attrs_diff_prefixes)
{
const char *text =
- "<doc xmlns:a='http://xml.libexpat.org/a'\n"
- " xmlns:b='http://xml.libexpat.org/a'\n"
+ "<doc xmlns:a='http://example.org/a'\n"
+ " xmlns:b='http://example.org/a'\n"
" a:a='v' b:a='v' />";
expect_failure(text,
XML_ERROR_DUPLICATE_ATTRIBUTE,
@@ -1574,6 +7452,33 @@ START_TEST(test_ns_duplicate_attrs_diff_prefixes)
}
END_TEST
+START_TEST(test_ns_duplicate_hashes)
+{
+ /* The hash of an attribute is calculated as the hash of its URI
+ * concatenated with a space followed by its name (after the
+ * colon). We wish to generate attributes with the same hash
+ * value modulo the attribute table size so that we can check that
+ * the attribute hash table works correctly. The attribute hash
+ * table size will be the smallest power of two greater than the
+ * number of attributes, but at least eight. There is
+ * unfortunately no programmatic way of getting the hash or the
+ * table size at user level, but the test code coverage percentage
+ * will drop if the hashes cease to point to the same row.
+ *
+ * The cunning plan is to have few enough attributes to have a
+ * reliable table size of 8, and have the single letter attribute
+ * names be 8 characters apart, producing a hash which will be the
+ * same modulo 8.
+ */
+ const char *text =
+ "<doc xmlns:a='http://example.org/a'\n"
+ " a:a='v' a:i='w' />";
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
/* Regression test for SF bug #695401: unbound prefix. */
START_TEST(test_ns_unbound_prefix_on_attribute)
{
@@ -1594,25 +7499,4472 @@ START_TEST(test_ns_unbound_prefix_on_element)
}
END_TEST
+/* Test that the parsing status is correctly reset by XML_ParserReset().
+ * We usE test_return_ns_triplet() for our example parse to improve
+ * coverage of tidying up code executed.
+ */
+START_TEST(test_ns_parser_reset)
+{
+ XML_ParsingStatus status;
+
+ XML_GetParsingStatus(parser, &status);
+ if (status.parsing != XML_INITIALIZED)
+ fail("parsing status doesn't start INITIALIZED");
+ test_return_ns_triplet();
+ XML_GetParsingStatus(parser, &status);
+ if (status.parsing != XML_FINISHED)
+ fail("parsing status doesn't end FINISHED");
+ XML_ParserReset(parser, NULL);
+ XML_GetParsingStatus(parser, &status);
+ if (status.parsing != XML_INITIALIZED)
+ fail("parsing status doesn't reset to INITIALIZED");
+}
+END_TEST
+
+/* Test that long element names with namespaces are handled correctly */
+START_TEST(test_ns_long_element)
+{
+ const char *text =
+ "<foo:thisisalongenoughelementnametotriggerareallocation\n"
+ " xmlns:foo='http://example.org/' bar:a='12'\n"
+ " xmlns:bar='http://example.org/'>"
+ "</foo:thisisalongenoughelementnametotriggerareallocation>";
+ const XML_Char *elemstr[] = {
+ XCS("http://example.org/")
+ XCS(" thisisalongenoughelementnametotriggerareallocation foo"),
+ XCS("http://example.org/ a bar")
+ };
+
+ XML_SetReturnNSTriplet(parser, XML_TRUE);
+ XML_SetUserData(parser, elemstr);
+ XML_SetElementHandler(parser,
+ triplet_start_checker,
+ triplet_end_checker);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
+/* Test mixed population of prefixed and unprefixed attributes */
+START_TEST(test_ns_mixed_prefix_atts)
+{
+ const char *text =
+ "<e a='12' bar:b='13'\n"
+ " xmlns:bar='http://example.org/'>"
+ "</e>";
+
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
+/* Test having a long namespaced element name inside a short one.
+ * This exercises some internal buffer reallocation that is shared
+ * across elements with the same namespace URI.
+ */
+START_TEST(test_ns_extend_uri_buffer)
+{
+ const char *text =
+ "<foo:e xmlns:foo='http://example.org/'>"
+ " <foo:thisisalongenoughnametotriggerallocationaction"
+ " foo:a='12' />"
+ "</foo:e>";
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
+/* Test that xmlns is correctly rejected as an attribute in the xmlns
+ * namespace, but not in other namespaces
+ */
+START_TEST(test_ns_reserved_attributes)
+{
+ const char *text1 =
+ "<foo:e xmlns:foo='http://example.org/' xmlns:xmlns='12' />";
+ const char *text2 =
+ "<foo:e xmlns:foo='http://example.org/' foo:xmlns='12' />";
+ expect_failure(text1, XML_ERROR_RESERVED_PREFIX_XMLNS,
+ "xmlns not rejected as an attribute");
+ XML_ParserReset(parser, NULL);
+ if (_XML_Parse_SINGLE_BYTES(parser, text2, strlen(text2),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
+/* Test more reserved attributes */
+START_TEST(test_ns_reserved_attributes_2)
+{
+ const char *text1 =
+ "<foo:e xmlns:foo='http://example.org/'"
+ " xmlns:xml='http://example.org/' />";
+ const char *text2 =
+ "<foo:e xmlns:foo='http://www.w3.org/XML/1998/namespace' />";
+ const char *text3 =
+ "<foo:e xmlns:foo='http://www.w3.org/2000/xmlns/' />";
+
+ expect_failure(text1, XML_ERROR_RESERVED_PREFIX_XML,
+ "xml not rejected as an attribute");
+ XML_ParserReset(parser, NULL);
+ expect_failure(text2, XML_ERROR_RESERVED_NAMESPACE_URI,
+ "Use of w3.org URL not faulted");
+ XML_ParserReset(parser, NULL);
+ expect_failure(text3, XML_ERROR_RESERVED_NAMESPACE_URI,
+ "Use of w3.org xmlns URL not faulted");
+}
+END_TEST
+
+/* Test string pool handling of namespace names of 2048 characters */
+/* Exercises a particular string pool growth path */
+START_TEST(test_ns_extremely_long_prefix)
+{
+ /* C99 compilers are only required to support 4095-character
+ * strings, so the following needs to be split in two to be safe
+ * for all compilers.
+ */
+ const char *text1 =
+ "<doc "
+ /* 64 character on each line */
+ /* ...gives a total length of 2048 */
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ ":a='12'";
+ const char *text2 =
+ " xmlns:"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "='foo'\n>"
+ "</doc>";
+
+ if (_XML_Parse_SINGLE_BYTES(parser, text1, strlen(text1),
+ XML_FALSE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ if (_XML_Parse_SINGLE_BYTES(parser, text2, strlen(text2),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
+/* Test unknown encoding handlers in namespace setup */
+START_TEST(test_ns_unknown_encoding_success)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='prefix-conv'?>\n"
+ "<foo:e xmlns:foo='http://example.org/'>Hi</foo:e>";
+
+ XML_SetUnknownEncodingHandler(parser, MiscEncodingHandler, NULL);
+ run_character_check(text, XCS("Hi"));
+}
+END_TEST
+
+/* Test that too many colons are rejected */
+START_TEST(test_ns_double_colon)
+{
+ const char *text =
+ "<foo:e xmlns:foo='http://example.org/' foo:a:b='bar' />";
+
+ expect_failure(text, XML_ERROR_INVALID_TOKEN,
+ "Double colon in attribute name not faulted");
+}
+END_TEST
+
+START_TEST(test_ns_double_colon_element)
+{
+ const char *text =
+ "<foo:bar:e xmlns:foo='http://example.org/' />";
+
+ expect_failure(text, XML_ERROR_INVALID_TOKEN,
+ "Double colon in element name not faulted");
+}
+END_TEST
+
+/* Test that non-name characters after a colon are rejected */
+START_TEST(test_ns_bad_attr_leafname)
+{
+ const char *text =
+ "<foo:e xmlns:foo='http://example.org/' foo:?ar='baz' />";
+
+ expect_failure(text, XML_ERROR_INVALID_TOKEN,
+ "Invalid character in leafname not faulted");
+}
+END_TEST
+
+START_TEST(test_ns_bad_element_leafname)
+{
+ const char *text =
+ "<foo:?oc xmlns:foo='http://example.org/' />";
+
+ expect_failure(text, XML_ERROR_INVALID_TOKEN,
+ "Invalid character in element leafname not faulted");
+}
+END_TEST
+
+/* Test high-byte-set UTF-16 characters are valid in a leafname */
+START_TEST(test_ns_utf16_leafname)
+{
+ const char text[] =
+ /* <n:e xmlns:n='URI' n:{KHO KHWAI}='a' />
+ * where {KHO KHWAI} = U+0E04 = 0xe0 0xb8 0x84 in UTF-8
+ */
+ "<\0n\0:\0e\0 \0x\0m\0l\0n\0s\0:\0n\0=\0'\0U\0R\0I\0'\0 \0"
+ "n\0:\0\x04\x0e=\0'\0a\0'\0 \0/\0>\0";
+ const XML_Char *expected = XCS("a");
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetStartElementHandler(parser, accumulate_attribute);
+ XML_SetUserData(parser, &storage);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, sizeof(text)-1,
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+START_TEST(test_ns_utf16_element_leafname)
+{
+ const char text[] =
+ /* <n:{KHO KHWAI} xmlns:n='URI'/>
+ * where {KHO KHWAI} = U+0E04 = 0xe0 0xb8 0x84 in UTF-8
+ */
+ "\0<\0n\0:\x0e\x04\0 \0x\0m\0l\0n\0s\0:\0n\0=\0'\0U\0R\0I\0'\0/\0>";
+#ifdef XML_UNICODE
+ const XML_Char *expected = XCS("URI \x0e04");
+#else
+ const XML_Char *expected = XCS("URI \xe0\xb8\x84");
+#endif
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetStartElementHandler(parser, start_element_event_handler);
+ XML_SetUserData(parser, &storage);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, sizeof(text)-1,
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+START_TEST(test_ns_utf16_doctype)
+{
+ const char text[] =
+ /* <!DOCTYPE foo:{KHO KHWAI} [ <!ENTITY bar 'baz'> ]>\n
+ * where {KHO KHWAI} = U+0E04 = 0xe0 0xb8 0x84 in UTF-8
+ */
+ "\0<\0!\0D\0O\0C\0T\0Y\0P\0E\0 \0f\0o\0o\0:\x0e\x04\0 "
+ "\0[\0 \0<\0!\0E\0N\0T\0I\0T\0Y\0 \0b\0a\0r\0 \0'\0b\0a\0z\0'\0>\0 "
+ "\0]\0>\0\n"
+ /* <foo:{KHO KHWAI} xmlns:foo='URI'>&bar;</foo:{KHO KHWAI}> */
+ "\0<\0f\0o\0o\0:\x0e\x04\0 "
+ "\0x\0m\0l\0n\0s\0:\0f\0o\0o\0=\0'\0U\0R\0I\0'\0>"
+ "\0&\0b\0a\0r\0;"
+ "\0<\0/\0f\0o\0o\0:\x0e\x04\0>";
+#ifdef XML_UNICODE
+ const XML_Char *expected = XCS("URI \x0e04");
+#else
+ const XML_Char *expected = XCS("URI \xe0\xb8\x84");
+#endif
+ CharData storage;
+
+ CharData_Init(&storage);
+ XML_SetUserData(parser, &storage);
+ XML_SetStartElementHandler(parser, start_element_event_handler);
+ XML_SetUnknownEncodingHandler(parser, MiscEncodingHandler, NULL);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, sizeof(text)-1,
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+START_TEST(test_ns_invalid_doctype)
+{
+ const char *text =
+ "<!DOCTYPE foo:!bad [ <!ENTITY bar 'baz' ]>\n"
+ "<foo:!bad>&bar;</foo:!bad>";
+
+ expect_failure(text, XML_ERROR_INVALID_TOKEN,
+ "Invalid character in document local name not faulted");
+}
+END_TEST
+
+START_TEST(test_ns_double_colon_doctype)
+{
+ const char *text =
+ "<!DOCTYPE foo:a:doc [ <!ENTITY bar 'baz' ]>\n"
+ "<foo:a:doc>&bar;</foo:a:doc>";
+
+ expect_failure(text, XML_ERROR_SYNTAX,
+ "Double colon in document name not faulted");
+}
+END_TEST
+
+/* Control variable; the number of times duff_allocator() will successfully allocate */
+#define ALLOC_ALWAYS_SUCCEED (-1)
+#define REALLOC_ALWAYS_SUCCEED (-1)
+
+static int allocation_count = ALLOC_ALWAYS_SUCCEED;
+static int reallocation_count = REALLOC_ALWAYS_SUCCEED;
+
+/* Crocked allocator for allocation failure tests */
+static void *duff_allocator(size_t size)
+{
+ if (allocation_count == 0)
+ return NULL;
+ if (allocation_count != ALLOC_ALWAYS_SUCCEED)
+ allocation_count--;
+ return malloc(size);
+}
+
+/* Crocked reallocator for allocation failure tests */
+static void *duff_reallocator(void *ptr, size_t size)
+{
+ if (reallocation_count == 0)
+ return NULL;
+ if (reallocation_count != REALLOC_ALWAYS_SUCCEED)
+ reallocation_count--;
+ return realloc(ptr, size);
+}
+
+/* Test that a failure to allocate the parser structure fails gracefully */
+START_TEST(test_misc_alloc_create_parser)
+{
+ XML_Memory_Handling_Suite memsuite = { duff_allocator, realloc, free };
+ unsigned int i;
+ const unsigned int max_alloc_count = 10;
+
+ /* Something this simple shouldn't need more than 10 allocations */
+ for (i = 0; i < max_alloc_count; i++)
+ {
+ allocation_count = i;
+ parser = XML_ParserCreate_MM(NULL, &memsuite, NULL);
+ if (parser != NULL)
+ break;
+ }
+ if (i == 0)
+ fail("Parser unexpectedly ignored failing allocator");
+ else if (i == max_alloc_count)
+ fail("Parser not created with max allocation count");
+}
+END_TEST
+
+/* Test memory allocation failures for a parser with an encoding */
+START_TEST(test_misc_alloc_create_parser_with_encoding)
+{
+ XML_Memory_Handling_Suite memsuite = { duff_allocator, realloc, free };
+ unsigned int i;
+ const unsigned int max_alloc_count = 10;
+
+ /* Try several levels of allocation */
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ parser = XML_ParserCreate_MM(XCS("us-ascii"), &memsuite, NULL);
+ if (parser != NULL)
+ break;
+ }
+ if (i == 0)
+ fail("Parser ignored failing allocator");
+ else if (i == max_alloc_count)
+ fail("Parser not created with max allocation count");
+}
+END_TEST
+
+/* Test that freeing a NULL parser doesn't cause an explosion.
+ * (Not actually tested anywhere else)
+ */
+START_TEST(test_misc_null_parser)
+{
+ XML_ParserFree(NULL);
+}
+END_TEST
+
+/* Test that XML_ErrorString rejects out-of-range codes */
+START_TEST(test_misc_error_string)
+{
+ if (XML_ErrorString((enum XML_Error)-1) != NULL)
+ fail("Negative error code not rejected");
+ if (XML_ErrorString((enum XML_Error)100) != NULL)
+ fail("Large error code not rejected");
+}
+END_TEST
+
+/* Test the version information is consistent */
+
+/* Since we are working in XML_LChars (potentially 16-bits), we
+ * can't use the standard C library functions for character
+ * manipulation and have to roll our own.
+ */
+static int
+parse_version(const XML_LChar *version_text,
+ XML_Expat_Version *version_struct)
+{
+ while (*version_text != 0x00) {
+ if (*version_text >= ASCII_0 && *version_text <= ASCII_9)
+ break;
+ version_text++;
+ }
+ if (*version_text == 0x00)
+ return XML_FALSE;
+
+ /* version_struct->major = strtoul(version_text, 10, &version_text) */
+ version_struct->major = 0;
+ while (*version_text >= ASCII_0 && *version_text <= ASCII_9) {
+ version_struct->major =
+ 10 * version_struct->major + (*version_text++ - ASCII_0);
+ }
+ if (*version_text++ != ASCII_PERIOD)
+ return XML_FALSE;
+
+ /* Now for the minor version number */
+ version_struct->minor = 0;
+ while (*version_text >= ASCII_0 && *version_text <= ASCII_9) {
+ version_struct->minor =
+ 10 * version_struct->minor + (*version_text++ - ASCII_0);
+ }
+ if (*version_text++ != ASCII_PERIOD)
+ return XML_FALSE;
+
+ /* Finally the micro version number */
+ version_struct->micro = 0;
+ while (*version_text >= ASCII_0 && *version_text <= ASCII_9) {
+ version_struct->micro =
+ 10 * version_struct->micro + (*version_text++ - ASCII_0);
+ }
+ if (*version_text != 0x00)
+ return XML_FALSE;
+ return XML_TRUE;
+}
+
+static int
+versions_equal(const XML_Expat_Version *first,
+ const XML_Expat_Version *second)
+{
+ return (first->major == second->major &&
+ first->minor == second->minor &&
+ first->micro == second->micro);
+}
+
+START_TEST(test_misc_version)
+{
+ XML_Expat_Version read_version = XML_ExpatVersionInfo();
+ /* Silence compiler warning with the following assignment */
+ XML_Expat_Version parsed_version = { 0, 0, 0 };
+ const XML_LChar *version_text = XML_ExpatVersion();
+
+ if (version_text == NULL)
+ fail("Could not obtain version text");
+ if (!parse_version(version_text, &parsed_version))
+ fail("Unable to parse version text");
+ if (!versions_equal(&read_version, &parsed_version))
+ fail("Version mismatch");
+
+#if ! defined(XML_UNICODE) || defined(XML_UNICODE_WCHAR_T)
+ if (xcstrcmp(version_text, XCS("expat_2.2.5"))) /* needs bump on releases */
+ fail("XML_*_VERSION in expat.h out of sync?\n");
+#else
+ /* If we have XML_UNICODE defined but not XML_UNICODE_WCHAR_T
+ * then XML_LChar is defined as char, for some reason.
+ */
+ if (strcmp(version_text, "expat_2.2.5")) /* needs bump on releases */
+ fail("XML_*_VERSION in expat.h out of sync?\n");
+#endif /* ! defined(XML_UNICODE) || defined(XML_UNICODE_WCHAR_T) */
+}
+END_TEST
+
+/* Test feature information */
+START_TEST(test_misc_features)
+{
+ const XML_Feature *features = XML_GetFeatureList();
+
+ /* Prevent problems with double-freeing parsers */
+ parser = NULL;
+ if (features == NULL)
+ fail("Failed to get feature information");
+ /* Loop through the features checking what we can */
+ while (features->feature != XML_FEATURE_END) {
+ switch(features->feature) {
+ case XML_FEATURE_SIZEOF_XML_CHAR:
+ if (features->value != sizeof(XML_Char))
+ fail("Incorrect size of XML_Char");
+ break;
+ case XML_FEATURE_SIZEOF_XML_LCHAR:
+ if (features->value != sizeof(XML_LChar))
+ fail("Incorrect size of XML_LChar");
+ break;
+ default:
+ break;
+ }
+ features++;
+ }
+}
+END_TEST
+
+/* Regression test for GitHub Issue #17: memory leak parsing attribute
+ * values with mixed bound and unbound namespaces.
+ */
+START_TEST(test_misc_attribute_leak)
+{
+ const char *text = "<D xmlns:L=\"D\" l:a='' L:a=''/>";
+ XML_Memory_Handling_Suite memsuite = {
+ tracking_malloc,
+ tracking_realloc,
+ tracking_free
+ };
+
+ parser = XML_ParserCreate_MM(XCS("UTF-8"), &memsuite, XCS("\n"));
+ expect_failure(text, XML_ERROR_UNBOUND_PREFIX,
+ "Unbound prefixes not found");
+ XML_ParserFree(parser);
+ /* Prevent the teardown trying to double free */
+ parser = NULL;
+
+ if (!tracking_report())
+ fail("Memory leak found");
+}
+END_TEST
+
+/* Test parser created for UTF-16LE is successful */
+START_TEST(test_misc_utf16le)
+{
+ const char text[] =
+ /* <?xml version='1.0'?><q>Hi</q> */
+ "<\0?\0x\0m\0l\0 \0"
+ "v\0e\0r\0s\0i\0o\0n\0=\0'\0\x31\0.\0\x30\0'\0?\0>\0"
+ "<\0q\0>\0H\0i\0<\0/\0q\0>\0";
+ const XML_Char *expected = XCS("Hi");
+ CharData storage;
+
+ parser = XML_ParserCreate(XCS("UTF-16LE"));
+ if (parser == NULL)
+ fail("Parser not created");
+
+ CharData_Init(&storage);
+ XML_SetUserData(parser, &storage);
+ XML_SetCharacterDataHandler(parser, accumulate_characters);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, sizeof(text)-1,
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+ CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
+
+static void
+alloc_setup(void)
+{
+ XML_Memory_Handling_Suite memsuite = {
+ duff_allocator,
+ duff_reallocator,
+ free
+ };
+
+ /* Ensure the parser creation will go through */
+ allocation_count = ALLOC_ALWAYS_SUCCEED;
+ reallocation_count = REALLOC_ALWAYS_SUCCEED;
+ parser = XML_ParserCreate_MM(NULL, &memsuite, NULL);
+ if (parser == NULL)
+ fail("Parser not created");
+}
+
+static void
+alloc_teardown(void)
+{
+ basic_teardown();
+}
+
+
+/* Test the effects of allocation failures on xml declaration processing */
+START_TEST(test_alloc_parse_xdecl)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='utf-8'?>\n"
+ "<doc>Hello, world</doc>";
+ int i;
+ const int max_alloc_count = 15;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ XML_SetXmlDeclHandler(parser, dummy_xdecl_handler);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* Resetting the parser is insufficient, because some memory
+ * allocations are cached within the parser. Instead we use
+ * the teardown and setup routines to ensure that we have the
+ * right sort of parser back in our hands.
+ */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite failing allocator");
+ if (i == max_alloc_count)
+ fail("Parse failed with max allocations");
+}
+END_TEST
+
+/* As above, but with an encoding big enough to cause storing the
+ * version information to expand the string pool being used.
+ */
+static int XMLCALL
+long_encoding_handler(void *UNUSED_P(userData),
+ const XML_Char *UNUSED_P(encoding),
+ XML_Encoding *info)
+{
+ int i;
+
+ for (i = 0; i < 256; i++)
+ info->map[i] = i;
+ info->data = NULL;
+ info->convert = NULL;
+ info->release = NULL;
+ return XML_STATUS_OK;
+}
+
+START_TEST(test_alloc_parse_xdecl_2)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='"
+ /* Each line is 64 characters */
+ "ThisIsAStupidlyLongEncodingNameIntendedToTriggerPoolGrowth123456"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMN"
+ "'?>"
+ "<doc>Hello, world</doc>";
+ int i;
+ const int max_alloc_count = 20;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ XML_SetXmlDeclHandler(parser, dummy_xdecl_handler);
+ XML_SetUnknownEncodingHandler(parser, long_encoding_handler, NULL);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite failing allocator");
+ if (i == max_alloc_count)
+ fail("Parse failed with max allocations");
+}
+END_TEST
+
+/* Test the effects of allocation failures on a straightforward parse */
+START_TEST(test_alloc_parse_pi)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='utf-8'?>\n"
+ "<?pi unknown?>\n"
+ "<doc>"
+ "Hello, world"
+ "</doc>";
+ int i;
+ const int max_alloc_count = 15;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ XML_SetProcessingInstructionHandler(parser, dummy_pi_handler);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite failing allocator");
+ if (i == max_alloc_count)
+ fail("Parse failed with max allocations");
+}
+END_TEST
+
+START_TEST(test_alloc_parse_pi_2)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='utf-8'?>\n"
+ "<doc>"
+ "Hello, world"
+ "<?pi unknown?>\n"
+ "</doc>";
+ int i;
+ const int max_alloc_count = 15;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ XML_SetProcessingInstructionHandler(parser, dummy_pi_handler);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite failing allocator");
+ if (i == max_alloc_count)
+ fail("Parse failed with max allocations");
+}
+END_TEST
+
+START_TEST(test_alloc_parse_pi_3)
+{
+ const char *text =
+ "<?"
+ /* 64 characters per line */
+ "This processing instruction should be long enough to ensure that"
+ "it triggers the growth of an internal string pool when the "
+ "allocator fails at a cruicial moment FGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "Q?><doc/>";
+ int i;
+ const int max_alloc_count = 20;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ XML_SetProcessingInstructionHandler(parser, dummy_pi_handler);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite failing allocator");
+ if (i == max_alloc_count)
+ fail("Parse failed with max allocations");
+}
+END_TEST
+
+START_TEST(test_alloc_parse_comment)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='utf-8'?>\n"
+ "<!-- Test parsing this comment -->"
+ "<doc>Hi</doc>";
+ int i;
+ const int max_alloc_count = 15;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ XML_SetCommentHandler(parser, dummy_comment_handler);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite failing allocator");
+ if (i == max_alloc_count)
+ fail("Parse failed with max allocations");
+}
+END_TEST
+
+START_TEST(test_alloc_parse_comment_2)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='utf-8'?>\n"
+ "<doc>"
+ "Hello, world"
+ "<!-- Parse this comment too -->"
+ "</doc>";
+ int i;
+ const int max_alloc_count = 15;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ XML_SetCommentHandler(parser, dummy_comment_handler);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite failing allocator");
+ if (i == max_alloc_count)
+ fail("Parse failed with max allocations");
+}
+END_TEST
+
+static int XMLCALL
+external_entity_duff_loader(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ XML_Parser new_parser;
+ unsigned int i;
+ const unsigned int max_alloc_count = 10;
+
+ /* Try a few different allocation levels */
+ for (i = 0; i < max_alloc_count; i++)
+ {
+ allocation_count = i;
+ new_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (new_parser != NULL)
+ {
+ XML_ParserFree(new_parser);
+ break;
+ }
+ }
+ if (i == 0)
+ fail("External parser creation ignored failing allocator");
+ else if (i == max_alloc_count)
+ fail("Extern parser not created with max allocation count");
+
+ /* Make sure other random allocation doesn't now fail */
+ allocation_count = ALLOC_ALWAYS_SUCCEED;
+
+ /* Make sure the failure code path is executed too */
+ return XML_STATUS_ERROR;
+}
+
+/* Test that external parser creation running out of memory is
+ * correctly reported. Based on the external entity test cases.
+ */
+START_TEST(test_alloc_create_external_parser)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='us-ascii'?>\n"
+ "<!DOCTYPE doc SYSTEM 'foo'>\n"
+ "<doc>&entity;</doc>";
+ char foo_text[] =
+ "<!ELEMENT doc (#PCDATA)*>";
+
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetUserData(parser, foo_text);
+ XML_SetExternalEntityRefHandler(parser,
+ external_entity_duff_loader);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text), XML_TRUE) != XML_STATUS_ERROR) {
+ fail("External parser allocator returned success incorrectly");
+ }
+}
+END_TEST
+
+/* More external parser memory allocation testing */
+START_TEST(test_alloc_run_external_parser)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='us-ascii'?>\n"
+ "<!DOCTYPE doc SYSTEM 'foo'>\n"
+ "<doc>&entity;</doc>";
+ char foo_text[] =
+ "<!ELEMENT doc (#PCDATA)*>";
+ unsigned int i;
+ const unsigned int max_alloc_count = 15;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ XML_SetParamEntityParsing(parser,
+ XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetUserData(parser, foo_text);
+ XML_SetExternalEntityRefHandler(parser,
+ external_entity_null_loader);
+ allocation_count = i;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text), XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing ignored failing allocator");
+ else if (i == max_alloc_count)
+ fail("Parsing failed with allocation count 10");
+}
+END_TEST
+
+
+static int XMLCALL
+external_entity_dbl_handler(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ intptr_t callno = (intptr_t)XML_GetUserData(parser);
+ const char *text;
+ XML_Parser new_parser;
+ int i;
+ const int max_alloc_count = 20;
+
+ if (callno == 0) {
+ /* First time through, check how many calls to malloc occur */
+ text = ("<!ELEMENT doc (e+)>\n"
+ "<!ATTLIST doc xmlns CDATA #IMPLIED>\n"
+ "<!ELEMENT e EMPTY>\n");
+ allocation_count = 10000;
+ new_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (new_parser == NULL) {
+ fail("Unable to allocate first external parser");
+ return XML_STATUS_ERROR;
+ }
+ /* Stash the number of calls in the user data */
+ XML_SetUserData(parser, (void *)(intptr_t)(10000 - allocation_count));
+ } else {
+ text = ("<?xml version='1.0' encoding='us-ascii'?>"
+ "<e/>");
+ /* Try at varying levels to exercise more code paths */
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = callno + i;
+ new_parser = XML_ExternalEntityParserCreate(parser,
+ context,
+ NULL);
+ if (new_parser != NULL)
+ break;
+ }
+ if (i == 0) {
+ fail("Second external parser unexpectedly created");
+ XML_ParserFree(new_parser);
+ return XML_STATUS_ERROR;
+ }
+ else if (i == max_alloc_count) {
+ fail("Second external parser not created");
+ return XML_STATUS_ERROR;
+ }
+ }
+
+ allocation_count = ALLOC_ALWAYS_SUCCEED;
+ if (_XML_Parse_SINGLE_BYTES(new_parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR) {
+ xml_failure(new_parser);
+ return XML_STATUS_ERROR;
+ }
+ XML_ParserFree(new_parser);
+ return XML_STATUS_OK;
+}
+
+/* Test that running out of memory in dtdCopy is correctly reported.
+ * Based on test_default_ns_from_ext_subset_and_ext_ge()
+ */
+START_TEST(test_alloc_dtd_copy_default_atts)
+{
+ const char *text =
+ "<?xml version='1.0'?>\n"
+ "<!DOCTYPE doc SYSTEM 'http://example.org/doc.dtd' [\n"
+ " <!ENTITY en SYSTEM 'http://example.org/entity.ent'>\n"
+ "]>\n"
+ "<doc xmlns='http://example.org/ns1'>\n"
+ "&en;\n"
+ "</doc>";
+
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser,
+ external_entity_dbl_handler);
+ XML_SetUserData(parser, NULL);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+}
+END_TEST
+
+
+static int XMLCALL
+external_entity_dbl_handler_2(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ intptr_t callno = (intptr_t)XML_GetUserData(parser);
+ const char *text;
+ XML_Parser new_parser;
+ enum XML_Status rv;
+
+ if (callno == 0) {
+ /* Try different allocation levels for whole exercise */
+ text = ("<!ELEMENT doc (e+)>\n"
+ "<!ATTLIST doc xmlns CDATA #IMPLIED>\n"
+ "<!ELEMENT e EMPTY>\n");
+ XML_SetUserData(parser, (void *)(intptr_t)1);
+ new_parser = XML_ExternalEntityParserCreate(parser,
+ context,
+ NULL);
+ if (new_parser == NULL)
+ return XML_STATUS_ERROR;
+ rv = _XML_Parse_SINGLE_BYTES(new_parser, text, strlen(text),
+ XML_TRUE);
+ } else {
+ /* Just run through once */
+ text = ("<?xml version='1.0' encoding='us-ascii'?>"
+ "<e/>");
+ new_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (new_parser == NULL)
+ return XML_STATUS_ERROR;
+ rv =_XML_Parse_SINGLE_BYTES(new_parser, text, strlen(text),
+ XML_TRUE);
+ }
+ XML_ParserFree(new_parser);
+ if (rv == XML_STATUS_ERROR)
+ return XML_STATUS_ERROR;
+ return XML_STATUS_OK;
+}
+
+/* Test more external entity allocation failure paths */
+START_TEST(test_alloc_external_entity)
+{
+ const char *text =
+ "<?xml version='1.0'?>\n"
+ "<!DOCTYPE doc SYSTEM 'http://example.org/doc.dtd' [\n"
+ " <!ENTITY en SYSTEM 'http://example.org/entity.ent'>\n"
+ "]>\n"
+ "<doc xmlns='http://example.org/ns1'>\n"
+ "&en;\n"
+ "</doc>";
+ int i;
+ const int alloc_test_max_repeats = 50;
+
+ for (i = 0; i < alloc_test_max_repeats; i++) {
+ allocation_count = -1;
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser,
+ external_entity_dbl_handler_2);
+ XML_SetUserData(parser, NULL);
+ allocation_count = i;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_OK)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ allocation_count = -1;
+ if (i == 0)
+ fail("External entity parsed despite duff allocator");
+ if (i == alloc_test_max_repeats)
+ fail("External entity not parsed at max allocation count");
+}
+END_TEST
+
+/* Test more allocation failure paths */
+static int XMLCALL
+external_entity_alloc_set_encoding(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ /* As for external_entity_loader() */
+ const char *text =
+ "<?xml encoding='iso-8859-3'?>"
+ "\xC3\xA9";
+ XML_Parser ext_parser;
+ enum XML_Status status;
+
+ ext_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ return XML_STATUS_ERROR;
+ if (!XML_SetEncoding(ext_parser, XCS("utf-8"))) {
+ XML_ParserFree(ext_parser);
+ return XML_STATUS_ERROR;
+ }
+ status = _XML_Parse_SINGLE_BYTES(ext_parser, text, strlen(text),
+ XML_TRUE);
+ XML_ParserFree(ext_parser);
+ if (status == XML_STATUS_ERROR)
+ return XML_STATUS_ERROR;
+ return XML_STATUS_OK;
+}
+
+START_TEST(test_alloc_ext_entity_set_encoding)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY en SYSTEM 'http://example.org/dummy.ent'>\n"
+ "]>\n"
+ "<doc>&en;</doc>";
+ int i;
+ const int max_allocation_count = 30;
+
+ for (i = 0; i < max_allocation_count; i++) {
+ XML_SetExternalEntityRefHandler(parser,
+ external_entity_alloc_set_encoding);
+ allocation_count = i;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_OK)
+ break;
+ allocation_count = -1;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Encoding check succeeded despite failing allocator");
+ if (i == max_allocation_count)
+ fail("Encoding failed at max allocation count");
+}
+END_TEST
+
+static int XMLCALL
+unknown_released_encoding_handler(void *UNUSED_P(data),
+ const XML_Char *encoding,
+ XML_Encoding *info)
+{
+ if (!xcstrcmp(encoding, XCS("unsupported-encoding"))) {
+ int i;
+
+ for (i = 0; i < 256; i++)
+ info->map[i] = i;
+ info->data = NULL;
+ info->convert = NULL;
+ info->release = dummy_release;
+ return XML_STATUS_OK;
+ }
+ return XML_STATUS_ERROR;
+}
+
+/* Test the effects of allocation failure in internal entities.
+ * Based on test_unknown_encoding_internal_entity
+ */
+START_TEST(test_alloc_internal_entity)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='unsupported-encoding'?>\n"
+ "<!DOCTYPE test [<!ENTITY foo 'bar'>]>\n"
+ "<test a='&foo;'/>";
+ unsigned int i;
+ const unsigned int max_alloc_count = 20;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ XML_SetUnknownEncodingHandler(parser,
+ unknown_released_encoding_handler,
+ NULL);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text), XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Internal entity worked despite failing allocations");
+ else if (i == max_alloc_count)
+ fail("Internal entity failed at max allocation count");
+}
+END_TEST
+
+
+/* Test the robustness against allocation failure of element handling
+ * Based on test_dtd_default_handling().
+ */
+START_TEST(test_alloc_dtd_default_handling)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ "<!ENTITY e SYSTEM 'http://example.org/e'>\n"
+ "<!NOTATION n SYSTEM 'http://example.org/n'>\n"
+ "<!ENTITY e1 SYSTEM 'http://example.org/e' NDATA n>\n"
+ "<!ELEMENT doc (#PCDATA)>\n"
+ "<!ATTLIST doc a CDATA #IMPLIED>\n"
+ "<?pi in dtd?>\n"
+ "<!--comment in dtd-->\n"
+ "]>\n"
+ "<doc><![CDATA[text in doc]]></doc>";
+ const XML_Char *expected = XCS("\n\n\n\n\n\n\n\n\n<doc>text in doc</doc>");
+ CharData storage;
+ int i;
+ const int max_alloc_count = 25;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ dummy_handler_flags = 0;
+ XML_SetDefaultHandler(parser, accumulate_characters);
+ XML_SetDoctypeDeclHandler(parser,
+ dummy_start_doctype_handler,
+ dummy_end_doctype_handler);
+ XML_SetEntityDeclHandler(parser, dummy_entity_decl_handler);
+ XML_SetNotationDeclHandler(parser, dummy_notation_decl_handler);
+ XML_SetElementDeclHandler(parser, dummy_element_decl_handler);
+ XML_SetAttlistDeclHandler(parser, dummy_attlist_decl_handler);
+ XML_SetProcessingInstructionHandler(parser, dummy_pi_handler);
+ XML_SetCommentHandler(parser, dummy_comment_handler);
+ XML_SetCdataSectionHandler(parser,
+ dummy_start_cdata_handler,
+ dummy_end_cdata_handler);
+ XML_SetUnparsedEntityDeclHandler(
+ parser,
+ dummy_unparsed_entity_decl_handler);
+ CharData_Init(&storage);
+ XML_SetUserData(parser, &storage);
+ XML_SetCharacterDataHandler(parser, accumulate_characters);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Default DTD parsed despite allocation failures");
+ if (i == max_alloc_count)
+ fail("Default DTD not parsed with maximum alloc count");
+ CharData_CheckXMLChars(&storage, expected);
+ if (dummy_handler_flags != (DUMMY_START_DOCTYPE_HANDLER_FLAG |
+ DUMMY_END_DOCTYPE_HANDLER_FLAG |
+ DUMMY_ENTITY_DECL_HANDLER_FLAG |
+ DUMMY_NOTATION_DECL_HANDLER_FLAG |
+ DUMMY_ELEMENT_DECL_HANDLER_FLAG |
+ DUMMY_ATTLIST_DECL_HANDLER_FLAG |
+ DUMMY_COMMENT_HANDLER_FLAG |
+ DUMMY_PI_HANDLER_FLAG |
+ DUMMY_START_CDATA_HANDLER_FLAG |
+ DUMMY_END_CDATA_HANDLER_FLAG |
+ DUMMY_UNPARSED_ENTITY_DECL_HANDLER_FLAG))
+ fail("Not all handlers were called");
+}
+END_TEST
+
+/* Test robustness of XML_SetEncoding() with a failing allocator */
+START_TEST(test_alloc_explicit_encoding)
+{
+ int i;
+ const int max_alloc_count = 5;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ if (XML_SetEncoding(parser, XCS("us-ascii")) == XML_STATUS_OK)
+ break;
+ }
+ if (i == 0)
+ fail("Encoding set despite failing allocator");
+ else if (i == max_alloc_count)
+ fail("Encoding not set at max allocation count");
+}
+END_TEST
+
+/* Test robustness of XML_SetBase against a failing allocator */
+START_TEST(test_alloc_set_base)
+{
+ const XML_Char *new_base = XCS("/local/file/name.xml");
+ int i;
+ const int max_alloc_count = 5;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ if (XML_SetBase(parser, new_base) == XML_STATUS_OK)
+ break;
+ }
+ if (i == 0)
+ fail("Base set despite failing allocator");
+ else if (i == max_alloc_count)
+ fail("Base not set with max allocation count");
+}
+END_TEST
+
+/* Test buffer extension in the face of a duff reallocator */
+START_TEST(test_alloc_realloc_buffer)
+{
+ const char *text = get_buffer_test_text;
+ void *buffer;
+ int i;
+ const int max_realloc_count = 10;
+
+ /* Get a smallish buffer */
+ for (i = 0; i < max_realloc_count; i++) {
+ reallocation_count = i;
+ buffer = XML_GetBuffer(parser, 1536);
+ if (buffer == NULL)
+ fail("1.5K buffer reallocation failed");
+ memcpy(buffer, text, strlen(text));
+ if (XML_ParseBuffer(parser, strlen(text),
+ XML_FALSE) == XML_STATUS_OK)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ reallocation_count = -1;
+ if (i == 0)
+ fail("Parse succeeded with no reallocation");
+ else if (i == max_realloc_count)
+ fail("Parse failed with max reallocation count");
+}
+END_TEST
+
+/* Same test for external entity parsers */
+static int XMLCALL
+external_entity_reallocator(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ const char *text = get_buffer_test_text;
+ XML_Parser ext_parser;
+ void *buffer;
+ enum XML_Status status;
+
+ ext_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ fail("Could not create external entity parser");
+
+ reallocation_count = (intptr_t)XML_GetUserData(parser);
+ buffer = XML_GetBuffer(ext_parser, 1536);
+ if (buffer == NULL)
+ fail("Buffer allocation failed");
+ memcpy(buffer, text, strlen(text));
+ status = XML_ParseBuffer(ext_parser, strlen(text), XML_FALSE);
+ reallocation_count = -1;
+ XML_ParserFree(ext_parser);
+ return (status == XML_STATUS_OK) ? XML_STATUS_OK : XML_STATUS_ERROR;
+}
+
+START_TEST(test_alloc_ext_entity_realloc_buffer)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY en SYSTEM 'http://example.org/dummy.ent'>\n"
+ "]>\n"
+ "<doc>&en;</doc>";
+ int i;
+ const int max_realloc_count = 10;
+
+ for (i = 0; i < max_realloc_count; i++) {
+ XML_SetExternalEntityRefHandler(parser,
+ external_entity_reallocator);
+ XML_SetUserData(parser, (void *)(intptr_t)i);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) == XML_STATUS_OK)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Succeeded with no reallocations");
+ if (i == max_realloc_count)
+ fail("Failed with max reallocations");
+}
+END_TEST
+
+/* Test elements with many attributes are handled correctly */
+START_TEST(test_alloc_realloc_many_attributes)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ "<!ATTLIST doc za CDATA 'default'>\n"
+ "<!ATTLIST doc zb CDATA 'def2'>\n"
+ "<!ATTLIST doc zc CDATA 'def3'>\n"
+ "]>\n"
+ "<doc a='1'"
+ " b='2'"
+ " c='3'"
+ " d='4'"
+ " e='5'"
+ " f='6'"
+ " g='7'"
+ " h='8'"
+ " i='9'"
+ " j='10'"
+ " k='11'"
+ " l='12'"
+ " m='13'"
+ " n='14'"
+ " p='15'"
+ " q='16'"
+ " r='17'"
+ " s='18'>"
+ "</doc>";
+ int i;
+ const int max_realloc_count = 10;
+
+ for (i = 0; i < max_realloc_count; i++) {
+ reallocation_count = i;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite no reallocations");
+ if (i == max_realloc_count)
+ fail("Parse failed at max reallocations");
+}
+END_TEST
+
+/* Test handling of a public entity with failing allocator */
+START_TEST(test_alloc_public_entity_value)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM 'http://example.org/'>\n"
+ "<doc></doc>\n";
+ char dtd_text[] =
+ "<!ELEMENT doc EMPTY>\n"
+ "<!ENTITY % e1 PUBLIC 'foo' 'bar.ent'>\n"
+ "<!ENTITY % "
+ /* Each line is 64 characters */
+ "ThisIsAStupidlyLongParameterNameIntendedToTriggerPoolGrowth12345"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ " '%e1;'>\n"
+ "%e1;\n";
+ int i;
+ const int max_alloc_count = 50;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ dummy_handler_flags = 0;
+ XML_SetUserData(parser, dtd_text);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_public);
+ /* Provoke a particular code path */
+ XML_SetEntityDeclHandler(parser, dummy_entity_decl_handler);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing allocation");
+ if (i == max_alloc_count)
+ fail("Parsing failed at max allocation count");
+ if (dummy_handler_flags != DUMMY_ENTITY_DECL_HANDLER_FLAG)
+ fail("Entity declaration handler not called");
+}
+END_TEST
+
+START_TEST(test_alloc_realloc_subst_public_entity_value)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM 'http://example.org/'>\n"
+ "<doc></doc>\n";
+ char dtd_text[] =
+ "<!ELEMENT doc EMPTY>\n"
+ "<!ENTITY % "
+ /* Each line is 64 characters */
+ "ThisIsAStupidlyLongParameterNameIntendedToTriggerPoolGrowth12345"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ " PUBLIC 'foo' 'bar.ent'>\n"
+ "%ThisIsAStupidlyLongParameterNameIntendedToTriggerPoolGrowth12345"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP;";
+ int i;
+ const int max_realloc_count = 10;
+
+ for (i = 0; i < max_realloc_count; i++) {
+ reallocation_count = i;
+ XML_SetUserData(parser, dtd_text);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_public);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing reallocation");
+ if (i == max_realloc_count)
+ fail("Parsing failed at max reallocation count");
+}
+END_TEST
+
+START_TEST(test_alloc_parse_public_doctype)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='utf-8'?>\n"
+ "<!DOCTYPE doc PUBLIC '"
+ /* 64 characters per line */
+ "http://example.com/a/long/enough/name/to/trigger/pool/growth/zz/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "' 'test'>\n"
+ "<doc></doc>";
+ int i;
+ const int max_alloc_count = 25;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ dummy_handler_flags = 0;
+ XML_SetDoctypeDeclHandler(parser,
+ dummy_start_doctype_decl_handler,
+ dummy_end_doctype_decl_handler);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite failing allocator");
+ if (i == max_alloc_count)
+ fail("Parse failed at maximum allocation count");
+ if (dummy_handler_flags != (DUMMY_START_DOCTYPE_DECL_HANDLER_FLAG |
+ DUMMY_END_DOCTYPE_DECL_HANDLER_FLAG))
+ fail("Doctype handler functions not called");
+}
+END_TEST
+
+START_TEST(test_alloc_parse_public_doctype_long_name)
+{
+ const char *text =
+ "<?xml version='1.0' encoding='utf-8'?>\n"
+ "<!DOCTYPE doc PUBLIC 'http://example.com/foo' '"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNOP"
+ "'>\n"
+ "<doc></doc>";
+ int i;
+ const int max_alloc_count = 25;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ XML_SetDoctypeDeclHandler(parser,
+ dummy_start_doctype_decl_handler,
+ dummy_end_doctype_decl_handler);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite failing allocator");
+ if (i == max_alloc_count)
+ fail("Parse failed at maximum allocation count");
+}
+END_TEST
+
+static int XMLCALL
+external_entity_alloc(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *UNUSED_P(systemId),
+ const XML_Char *UNUSED_P(publicId))
+{
+ const char *text = (const char *)XML_GetUserData(parser);
+ XML_Parser ext_parser;
+ int parse_res;
+
+ ext_parser = XML_ExternalEntityParserCreate(parser, context, NULL);
+ if (ext_parser == NULL)
+ return XML_STATUS_ERROR;
+ parse_res = _XML_Parse_SINGLE_BYTES(ext_parser, text, strlen(text),
+ XML_TRUE);
+ XML_ParserFree(ext_parser);
+ return parse_res;
+}
+
+/* Test foreign DTD handling */
+START_TEST(test_alloc_set_foreign_dtd)
+{
+ const char *text1 =
+ "<?xml version='1.0' encoding='us-ascii'?>\n"
+ "<doc>&entity;</doc>";
+ char text2[] = "<!ELEMENT doc (#PCDATA)*>";
+ int i;
+ const int max_alloc_count = 25;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetUserData(parser, &text2);
+ XML_SetExternalEntityRefHandler(parser, external_entity_alloc);
+ if (XML_UseForeignDTD(parser, XML_TRUE) != XML_ERROR_NONE)
+ fail("Could not set foreign DTD");
+ if (_XML_Parse_SINGLE_BYTES(parser, text1, strlen(text1),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite failing allocator");
+ if (i == max_alloc_count)
+ fail("Parse failed at maximum allocation count");
+}
+END_TEST
+
+/* Test based on ibm/valid/P32/ibm32v04.xml */
+START_TEST(test_alloc_attribute_enum_value)
+{
+ const char *text =
+ "<?xml version='1.0' standalone='no'?>\n"
+ "<!DOCTYPE animal SYSTEM 'test.dtd'>\n"
+ "<animal>This is a \n <a/> \n\nyellow tiger</animal>";
+ char dtd_text[] =
+ "<!ELEMENT animal (#PCDATA|a)*>\n"
+ "<!ELEMENT a EMPTY>\n"
+ "<!ATTLIST animal xml:space (default|preserve) 'preserve'>";
+ int i;
+ const int max_alloc_count = 30;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ XML_SetExternalEntityRefHandler(parser, external_entity_alloc);
+ XML_SetUserData(parser, dtd_text);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ /* An attribute list handler provokes a different code path */
+ XML_SetAttlistDeclHandler(parser, dummy_attlist_decl_handler);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite failing allocator");
+ if (i == max_alloc_count)
+ fail("Parse failed at maximum allocation count");
+}
+END_TEST
+
+/* Test attribute enums sufficient to overflow the string pool */
+START_TEST(test_alloc_realloc_attribute_enum_value)
+{
+ const char *text =
+ "<?xml version='1.0' standalone='no'?>\n"
+ "<!DOCTYPE animal SYSTEM 'test.dtd'>\n"
+ "<animal>This is a yellow tiger</animal>";
+ /* We wish to define a collection of attribute enums that will
+ * cause the string pool storing them to have to expand. This
+ * means more than 1024 bytes, including the parentheses and
+ * separator bars.
+ */
+ char dtd_text[] =
+ "<!ELEMENT animal (#PCDATA)*>\n"
+ "<!ATTLIST animal thing "
+ "(default"
+ /* Each line is 64 characters */
+ "|ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|BBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|CBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|DBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|EBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|FBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|GBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|HBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|IBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|JBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|KBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|LBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|MBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|NBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|OBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|PBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO)"
+ " 'default'>";
+ int i;
+ const int max_realloc_count = 10;
+
+ for (i = 0; i < max_realloc_count; i++) {
+ reallocation_count = i;
+ XML_SetExternalEntityRefHandler(parser, external_entity_alloc);
+ XML_SetUserData(parser, dtd_text);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ /* An attribute list handler provokes a different code path */
+ XML_SetAttlistDeclHandler(parser, dummy_attlist_decl_handler);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite failing reallocator");
+ if (i == max_realloc_count)
+ fail("Parse failed at maximum reallocation count");
+}
+END_TEST
+
+/* Test attribute enums in a #IMPLIED attribute forcing pool growth */
+START_TEST(test_alloc_realloc_implied_attribute)
+{
+ /* Forcing this particular code path is a balancing act. The
+ * addition of the closing parenthesis and terminal NUL must be
+ * what pushes the string of enums over the 1024-byte limit,
+ * otherwise a different code path will pick up the realloc.
+ */
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ "<!ELEMENT doc EMPTY>\n"
+ "<!ATTLIST doc a "
+ /* Each line is 64 characters */
+ "(ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|BBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|CBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|DBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|EBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|FBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|GBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|HBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|IBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|JBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|KBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|LBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|MBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|NBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|OBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|PBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMN)"
+ " #IMPLIED>\n"
+ "]><doc/>";
+ int i;
+ const int max_realloc_count = 10;
+
+ for (i = 0; i < max_realloc_count; i++) {
+ reallocation_count = i;
+ XML_SetAttlistDeclHandler(parser, dummy_attlist_decl_handler);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite failing reallocator");
+ if (i == max_realloc_count)
+ fail("Parse failed at maximum reallocation count");
+}
+END_TEST
+
+/* Test attribute enums in a defaulted attribute forcing pool growth */
+START_TEST(test_alloc_realloc_default_attribute)
+{
+ /* Forcing this particular code path is a balancing act. The
+ * addition of the closing parenthesis and terminal NUL must be
+ * what pushes the string of enums over the 1024-byte limit,
+ * otherwise a different code path will pick up the realloc.
+ */
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ "<!ELEMENT doc EMPTY>\n"
+ "<!ATTLIST doc a "
+ /* Each line is 64 characters */
+ "(ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|BBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|CBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|DBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|EBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|FBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|GBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|HBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|IBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|JBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|KBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|LBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|MBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|NBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|OBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO"
+ "|PBCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMN)"
+ " 'ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNO'"
+ ">\n]><doc/>";
+ int i;
+ const int max_realloc_count = 10;
+
+ for (i = 0; i < max_realloc_count; i++) {
+ reallocation_count = i;
+ XML_SetAttlistDeclHandler(parser, dummy_attlist_decl_handler);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite failing reallocator");
+ if (i == max_realloc_count)
+ fail("Parse failed at maximum reallocation count");
+}
+END_TEST
+
+/* Test long notation name with dodgy allocator */
+START_TEST(test_alloc_notation)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ "<!NOTATION "
+ /* Each line is 64 characters */
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ " SYSTEM 'http://example.org/n'>\n"
+ "<!ENTITY e SYSTEM 'http://example.org/e' NDATA "
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ ">\n"
+ "<!ELEMENT doc EMPTY>\n"
+ "]>\n<doc/>";
+ int i;
+ const int max_alloc_count = 20;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ dummy_handler_flags = 0;
+ XML_SetNotationDeclHandler(parser, dummy_notation_decl_handler);
+ XML_SetEntityDeclHandler(parser, dummy_entity_decl_handler);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite allocation failures");
+ if (i == max_alloc_count)
+ fail("Parse failed at maximum allocation count");
+ if (dummy_handler_flags != (DUMMY_ENTITY_DECL_HANDLER_FLAG |
+ DUMMY_NOTATION_DECL_HANDLER_FLAG))
+ fail("Entity declaration handler not called");
+}
+END_TEST
+
+/* Test public notation with dodgy allocator */
+START_TEST(test_alloc_public_notation)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ "<!NOTATION note PUBLIC '"
+ /* 64 characters per line */
+ "http://example.com/a/long/enough/name/to/trigger/pool/growth/zz/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "' 'foo'>\n"
+ "<!ENTITY e SYSTEM 'http://example.com/e' NDATA note>\n"
+ "<!ELEMENT doc EMPTY>\n"
+ "]>\n<doc/>";
+ int i;
+ const int max_alloc_count = 20;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ dummy_handler_flags = 0;
+ XML_SetNotationDeclHandler(parser, dummy_notation_decl_handler);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite allocation failures");
+ if (i == max_alloc_count)
+ fail("Parse failed at maximum allocation count");
+ if (dummy_handler_flags != DUMMY_NOTATION_DECL_HANDLER_FLAG)
+ fail("Notation handler not called");
+}
+END_TEST
+
+/* Test public notation with dodgy allocator */
+START_TEST(test_alloc_system_notation)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ "<!NOTATION note SYSTEM '"
+ /* 64 characters per line */
+ "http://example.com/a/long/enough/name/to/trigger/pool/growth/zz/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "'>\n"
+ "<!ENTITY e SYSTEM 'http://example.com/e' NDATA note>\n"
+ "<!ELEMENT doc EMPTY>\n"
+ "]>\n<doc/>";
+ int i;
+ const int max_alloc_count = 20;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ dummy_handler_flags = 0;
+ XML_SetNotationDeclHandler(parser, dummy_notation_decl_handler);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite allocation failures");
+ if (i == max_alloc_count)
+ fail("Parse failed at maximum allocation count");
+ if (dummy_handler_flags != DUMMY_NOTATION_DECL_HANDLER_FLAG)
+ fail("Notation handler not called");
+}
+END_TEST
+
+START_TEST(test_alloc_nested_groups)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ "<!ELEMENT doc "
+ /* Sixteen elements per line */
+ "(e,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,"
+ "(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?"
+ "))))))))))))))))))))))))))))))))>\n"
+ "<!ELEMENT e EMPTY>"
+ "]>\n"
+ "<doc><e/></doc>";
+ CharData storage;
+ int i;
+ const int max_alloc_count = 20;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ CharData_Init(&storage);
+ XML_SetElementDeclHandler(parser, dummy_element_decl_handler);
+ XML_SetStartElementHandler(parser, record_element_start_handler);
+ XML_SetUserData(parser, &storage);
+ dummy_handler_flags = 0;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+
+ if (i == 0)
+ fail("Parse succeeded despite failing reallocator");
+ if (i == max_alloc_count)
+ fail("Parse failed at maximum reallocation count");
+ CharData_CheckXMLChars(&storage, XCS("doce"));
+ if (dummy_handler_flags != DUMMY_ELEMENT_DECL_HANDLER_FLAG)
+ fail("Element handler not fired");
+}
+END_TEST
+
+START_TEST(test_alloc_realloc_nested_groups)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ "<!ELEMENT doc "
+ /* Sixteen elements per line */
+ "(e,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,"
+ "(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?,(e?"
+ "))))))))))))))))))))))))))))))))>\n"
+ "<!ELEMENT e EMPTY>"
+ "]>\n"
+ "<doc><e/></doc>";
+ CharData storage;
+ int i;
+ const int max_realloc_count = 10;
+
+ for (i = 0; i < max_realloc_count; i++) {
+ reallocation_count = i;
+ CharData_Init(&storage);
+ XML_SetElementDeclHandler(parser, dummy_element_decl_handler);
+ XML_SetStartElementHandler(parser, record_element_start_handler);
+ XML_SetUserData(parser, &storage);
+ dummy_handler_flags = 0;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+
+ if (i == 0)
+ fail("Parse succeeded despite failing reallocator");
+ if (i == max_realloc_count)
+ fail("Parse failed at maximum reallocation count");
+ CharData_CheckXMLChars(&storage, XCS("doce"));
+ if (dummy_handler_flags != DUMMY_ELEMENT_DECL_HANDLER_FLAG)
+ fail("Element handler not fired");
+}
+END_TEST
+
+START_TEST(test_alloc_large_group)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ "<!ELEMENT doc ("
+ "a1|a2|a3|a4|a5|a6|a7|a8|"
+ "b1|b2|b3|b4|b5|b6|b7|b8|"
+ "c1|c2|c3|c4|c5|c6|c7|c8|"
+ "d1|d2|d3|d4|d5|d6|d7|d8|"
+ "e1"
+ ")+>\n"
+ "]>\n"
+ "<doc>\n"
+ "<a1/>\n"
+ "</doc>\n";
+ int i;
+ const int max_alloc_count = 50;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ XML_SetElementDeclHandler(parser, dummy_element_decl_handler);
+ dummy_handler_flags = 0;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite failing allocator");
+ if (i == max_alloc_count)
+ fail("Parse failed at maximum allocation count");
+ if (dummy_handler_flags != DUMMY_ELEMENT_DECL_HANDLER_FLAG)
+ fail("Element handler flag not raised");
+}
+END_TEST
+
+START_TEST(test_alloc_realloc_group_choice)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ "<!ELEMENT doc ("
+ "a1|a2|a3|a4|a5|a6|a7|a8|"
+ "b1|b2|b3|b4|b5|b6|b7|b8|"
+ "c1|c2|c3|c4|c5|c6|c7|c8|"
+ "d1|d2|d3|d4|d5|d6|d7|d8|"
+ "e1"
+ ")+>\n"
+ "]>\n"
+ "<doc>\n"
+ "<a1/>\n"
+ "<b2 attr='foo'>This is a foo</b2>\n"
+ "<c3></c3>\n"
+ "</doc>\n";
+ int i;
+ const int max_realloc_count = 10;
+
+ for (i = 0; i < max_realloc_count; i++) {
+ reallocation_count = i;
+ XML_SetElementDeclHandler(parser, dummy_element_decl_handler);
+ dummy_handler_flags = 0;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite failing reallocator");
+ if (i == max_realloc_count)
+ fail("Parse failed at maximum reallocation count");
+ if (dummy_handler_flags != DUMMY_ELEMENT_DECL_HANDLER_FLAG)
+ fail("Element handler flag not raised");
+}
+END_TEST
+
+START_TEST(test_alloc_pi_in_epilog)
+{
+ const char *text =
+ "<doc></doc>\n"
+ "<?pi in epilog?>";
+ int i;
+ const int max_alloc_count = 15;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ XML_SetProcessingInstructionHandler(parser, dummy_pi_handler);
+ dummy_handler_flags = 0;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse completed despite failing allocator");
+ if (i == max_alloc_count)
+ fail("Parse failed at maximum allocation count");
+ if (dummy_handler_flags != DUMMY_PI_HANDLER_FLAG)
+ fail("Processing instruction handler not invoked");
+}
+END_TEST
+
+START_TEST(test_alloc_comment_in_epilog)
+{
+ const char *text =
+ "<doc></doc>\n"
+ "<!-- comment in epilog -->";
+ int i;
+ const int max_alloc_count = 15;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ XML_SetCommentHandler(parser, dummy_comment_handler);
+ dummy_handler_flags = 0;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse completed despite failing allocator");
+ if (i == max_alloc_count)
+ fail("Parse failed at maximum allocation count");
+ if (dummy_handler_flags != DUMMY_COMMENT_HANDLER_FLAG)
+ fail("Processing instruction handler not invoked");
+}
+END_TEST
+
+START_TEST(test_alloc_realloc_long_attribute_value)
+{
+ const char *text =
+ "<!DOCTYPE doc [<!ENTITY foo '"
+ /* Each line is 64 characters */
+ "This entity will be substituted as an attribute value, and is "
+ "calculated to be exactly long enough that the terminating NUL "
+ "that the library adds internally will trigger the string pool to"
+ "grow. GHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "'>]>\n"
+ "<doc a='&foo;'></doc>";
+ int i;
+ const int max_realloc_count = 10;
+
+ for (i = 0; i < max_realloc_count; i++) {
+ reallocation_count = i;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite failing reallocator");
+ if (i == max_realloc_count)
+ fail("Parse failed at maximum reallocation count");
+}
+END_TEST
+
+START_TEST(test_alloc_attribute_whitespace)
+{
+ const char *text = "<doc a=' '></doc>";
+ int i;
+ const int max_alloc_count = 15;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite failing allocator");
+ if (i == max_alloc_count)
+ fail("Parse failed at maximum allocation count");
+}
+END_TEST
+
+START_TEST(test_alloc_attribute_predefined_entity)
+{
+ const char *text = "<doc a='&amp;'></doc>";
+ int i;
+ const int max_alloc_count = 15;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite failing allocator");
+ if (i == max_alloc_count)
+ fail("Parse failed at maximum allocation count");
+}
+END_TEST
+
+/* Test that a character reference at the end of a suitably long
+ * default value for an attribute can trigger pool growth, and recovers
+ * if the allocator fails on it.
+ */
+START_TEST(test_alloc_long_attr_default_with_char_ref)
+{
+ const char *text =
+ "<!DOCTYPE doc [<!ATTLIST doc a CDATA '"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHI"
+ "&#x31;'>]>\n"
+ "<doc/>";
+ int i;
+ const int max_alloc_count = 20;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite failing allocator");
+ if (i == max_alloc_count)
+ fail("Parse failed at maximum allocation count");
+}
+END_TEST
+
+/* Test that a long character reference substitution triggers a pool
+ * expansion correctly for an attribute value.
+ */
+START_TEST(test_alloc_long_attr_value)
+{
+ const char *text =
+ "<!DOCTYPE test [<!ENTITY foo '\n"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "'>]>\n"
+ "<test a='&foo;'/>";
+ int i;
+ const int max_alloc_count = 25;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite failing allocator");
+ if (i == max_alloc_count)
+ fail("Parse failed at maximum allocation count");
+}
+END_TEST
+
+/* Test that an error in a nested parameter entity substitution is
+ * handled correctly. It seems unlikely that the code path being
+ * exercised can be reached purely by carefully crafted XML, but an
+ * allocation error in the right place will definitely do it.
+ */
+START_TEST(test_alloc_nested_entities)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM 'http://example.org/one.ent'>\n"
+ "<doc />";
+ ExtFaults test_data = {
+ "<!ENTITY % pe1 '"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "'>\n"
+ "<!ENTITY % pe2 '%pe1;'>\n"
+ "%pe2;",
+ "Memory Fail not faulted",
+ NULL,
+ XML_ERROR_NO_MEMORY
+ };
+
+ /* Causes an allocation error in a nested storeEntityValue() */
+ allocation_count = 12;
+ XML_SetUserData(parser, &test_data);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_faulter);
+ expect_failure(text, XML_ERROR_EXTERNAL_ENTITY_HANDLING,
+ "Entity allocation failure not noted");
+}
+END_TEST
+
+START_TEST(test_alloc_realloc_param_entity_newline)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM 'http://example.org/'>\n"
+ "<doc/>";
+ char dtd_text[] =
+ "<!ENTITY % pe '<!ATTLIST doc att CDATA \""
+ /* 64 characters per line */
+ "This default value is carefully crafted so that the carriage "
+ "return right at the end of the entity string causes an internal "
+ "string pool to have to grow. This allows us to test the alloc "
+ "failure path from that point. OPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDE"
+ "\">\n'>"
+ "%pe;\n";
+ int i;
+ const int max_realloc_count = 5;
+
+ for (i = 0; i < max_realloc_count; i++) {
+ reallocation_count = i;
+ XML_SetUserData(parser, dtd_text);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_alloc);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite failing reallocator");
+ if (i == max_realloc_count)
+ fail("Parse failed at maximum reallocation count");
+}
+END_TEST
+
+START_TEST(test_alloc_realloc_ce_extends_pe)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM 'http://example.org/'>\n"
+ "<doc/>";
+ char dtd_text[] =
+ "<!ENTITY % pe '<!ATTLIST doc att CDATA \""
+ /* 64 characters per line */
+ "This default value is carefully crafted so that the character "
+ "entity at the end causes an internal string pool to have to "
+ "grow. This allows us to test the allocation failure path from "
+ "that point onwards. EFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFG&#x51;"
+ "\">\n'>"
+ "%pe;\n";
+ int i;
+ const int max_realloc_count = 5;
+
+ for (i = 0; i < max_realloc_count; i++) {
+ reallocation_count = i;
+ XML_SetUserData(parser, dtd_text);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_alloc);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parse succeeded despite failing reallocator");
+ if (i == max_realloc_count)
+ fail("Parse failed at maximum reallocation count");
+}
+END_TEST
+
+START_TEST(test_alloc_realloc_attributes)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ATTLIST doc\n"
+ " a1 (a|b|c) 'a'\n"
+ " a2 (foo|bar) #IMPLIED\n"
+ " a3 NMTOKEN #IMPLIED\n"
+ " a4 NMTOKENS #IMPLIED\n"
+ " a5 ID #IMPLIED\n"
+ " a6 IDREF #IMPLIED\n"
+ " a7 IDREFS #IMPLIED\n"
+ " a8 ENTITY #IMPLIED\n"
+ " a9 ENTITIES #IMPLIED\n"
+ " a10 CDATA #IMPLIED\n"
+ " >]>\n"
+ "<doc>wombat</doc>\n";
+ int i;
+ const int max_realloc_count = 5;
+
+ for (i = 0; i < max_realloc_count; i++) {
+ reallocation_count = i;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+
+ if (i == 0)
+ fail("Parse succeeded despite failing reallocator");
+ if (i == max_realloc_count)
+ fail("Parse failed at maximum reallocation count");
+}
+END_TEST
+
+START_TEST(test_alloc_long_doc_name)
+{
+ const char *text =
+ /* 64 characters per line */
+ "<LongRootElementNameThatWillCauseTheNextAllocationToExpandTheStr"
+ "ingPoolForTheDTDQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ " a='1'/>";
+ int i;
+ const int max_alloc_count = 20;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing reallocations");
+ else if (i == max_alloc_count)
+ fail("Parsing failed even at max reallocation count");
+}
+END_TEST
+
+START_TEST(test_alloc_long_base)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY e SYSTEM 'foo'>\n"
+ "]>\n"
+ "<doc>&e;</doc>";
+ char entity_text[] = "Hello world";
+ const XML_Char *base =
+ /* 64 characters per line */
+ XCS("LongBaseURI/that/will/overflow/an/internal/buffer/and/cause/it/t")
+ XCS("o/have/to/grow/PQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/");
+ int i;
+ const int max_alloc_count = 25;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ XML_SetUserData(parser, entity_text);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_alloc);
+ if (XML_SetBase(parser, base) == XML_STATUS_ERROR) {
+ XML_ParserReset(parser, NULL);
+ continue;
+ }
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing allocations");
+ else if (i == max_alloc_count)
+ fail("Parsing failed even at max allocation count");
+}
+END_TEST
+
+START_TEST(test_alloc_long_public_id)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY e PUBLIC '"
+ /* 64 characters per line */
+ "LongPublicIDThatShouldResultInAnInternalStringPoolGrowingAtASpec"
+ "ificMomentKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "' 'bar'>\n"
+ "]>\n"
+ "<doc>&e;</doc>";
+ char entity_text[] = "Hello world";
+ int i;
+ const int max_alloc_count = 40;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ XML_SetUserData(parser, entity_text);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_alloc);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing allocations");
+ else if (i == max_alloc_count)
+ fail("Parsing failed even at max allocation count");
+}
+END_TEST
+
+START_TEST(test_alloc_long_entity_value)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ENTITY e1 '"
+ /* 64 characters per line */
+ "Long entity value that should provoke a string pool to grow whil"
+ "e setting up to parse the external entity below. xyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "'>\n"
+ " <!ENTITY e2 SYSTEM 'bar'>\n"
+ "]>\n"
+ "<doc>&e2;</doc>";
+ char entity_text[] = "Hello world";
+ int i;
+ const int max_alloc_count = 40;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ XML_SetUserData(parser, entity_text);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_alloc);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing allocations");
+ else if (i == max_alloc_count)
+ fail("Parsing failed even at max allocation count");
+}
+END_TEST
+
+START_TEST(test_alloc_long_notation)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!NOTATION note SYSTEM '"
+ /* 64 characters per line */
+ "ALongNotationNameThatShouldProvokeStringPoolGrowthWhileCallingAn"
+ "ExternalEntityParserUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "'>\n"
+ " <!ENTITY e1 SYSTEM 'foo' NDATA "
+ /* 64 characters per line */
+ "ALongNotationNameThatShouldProvokeStringPoolGrowthWhileCallingAn"
+ "ExternalEntityParserUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AB"
+ ">\n"
+ " <!ENTITY e2 SYSTEM 'bar'>\n"
+ "]>\n"
+ "<doc>&e2;</doc>";
+ ExtOption options[] = {
+ { XCS("foo"), "Entity Foo" },
+ { XCS("bar"), "Entity Bar" },
+ { NULL, NULL }
+ };
+ int i;
+ const int max_alloc_count = 40;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ XML_SetUserData(parser, options);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_optioner);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+
+ /* See comment in test_alloc_parse_xdecl() */
+ alloc_teardown();
+ alloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing allocations");
+ else if (i == max_alloc_count)
+ fail("Parsing failed even at max allocation count");
+}
+END_TEST
+
+
+static void
+nsalloc_setup(void)
+{
+ XML_Memory_Handling_Suite memsuite = {
+ duff_allocator,
+ duff_reallocator,
+ free
+ };
+ XML_Char ns_sep[2] = { ' ', '\0' };
+
+ /* Ensure the parser creation will go through */
+ allocation_count = ALLOC_ALWAYS_SUCCEED;
+ reallocation_count = REALLOC_ALWAYS_SUCCEED;
+ parser = XML_ParserCreate_MM(NULL, &memsuite, ns_sep);
+ if (parser == NULL)
+ fail("Parser not created");
+}
+
+static void
+nsalloc_teardown(void)
+{
+ basic_teardown();
+}
+
+
+/* Test the effects of allocation failure in simple namespace parsing.
+ * Based on test_ns_default_with_empty_uri()
+ */
+START_TEST(test_nsalloc_xmlns)
+{
+ const char *text =
+ "<doc xmlns='http://example.org/'>\n"
+ " <e xmlns=''/>\n"
+ "</doc>";
+ unsigned int i;
+ const unsigned int max_alloc_count = 30;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ /* Exercise more code paths with a default handler */
+ XML_SetDefaultHandler(parser, dummy_default_handler);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* Resetting the parser is insufficient, because some memory
+ * allocations are cached within the parser. Instead we use
+ * the teardown and setup routines to ensure that we have the
+ * right sort of parser back in our hands.
+ */
+ nsalloc_teardown();
+ nsalloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing allocations");
+ else if (i == max_alloc_count)
+ fail("Parsing failed even at maximum allocation count");
+}
+END_TEST
+
+/* Test XML_ParseBuffer interface with namespace and a dicky allocator */
+START_TEST(test_nsalloc_parse_buffer)
+{
+ const char *text = "<doc>Hello</doc>";
+ void *buffer;
+
+ /* Try a parse before the start of the world */
+ /* (Exercises new code path) */
+ allocation_count = 0;
+ if (XML_ParseBuffer(parser, 0, XML_FALSE) != XML_STATUS_ERROR)
+ fail("Pre-init XML_ParseBuffer not faulted");
+ if (XML_GetErrorCode(parser) != XML_ERROR_NO_MEMORY)
+ fail("Pre-init XML_ParseBuffer faulted for wrong reason");
+
+ /* Now with actual memory allocation */
+ allocation_count = ALLOC_ALWAYS_SUCCEED;
+ if (XML_ParseBuffer(parser, 0, XML_FALSE) != XML_STATUS_OK)
+ xml_failure(parser);
+
+ /* Check that resuming an unsuspended parser is faulted */
+ if (XML_ResumeParser(parser) != XML_STATUS_ERROR)
+ fail("Resuming unsuspended parser not faulted");
+ if (XML_GetErrorCode(parser) != XML_ERROR_NOT_SUSPENDED)
+ xml_failure(parser);
+
+ /* Get the parser into suspended state */
+ XML_SetCharacterDataHandler(parser, clearing_aborting_character_handler);
+ resumable = XML_TRUE;
+ buffer = XML_GetBuffer(parser, strlen(text));
+ if (buffer == NULL)
+ fail("Could not acquire parse buffer");
+ memcpy(buffer, text, strlen(text));
+ if (XML_ParseBuffer(parser, strlen(text),
+ XML_TRUE) != XML_STATUS_SUSPENDED)
+ xml_failure(parser);
+ if (XML_GetErrorCode(parser) != XML_ERROR_NONE)
+ xml_failure(parser);
+ if (XML_ParseBuffer(parser, strlen(text), XML_TRUE) != XML_STATUS_ERROR)
+ fail("Suspended XML_ParseBuffer not faulted");
+ if (XML_GetErrorCode(parser) != XML_ERROR_SUSPENDED)
+ xml_failure(parser);
+ if (XML_GetBuffer(parser, strlen(text)) != NULL)
+ fail("Suspended XML_GetBuffer not faulted");
+
+ /* Get it going again and complete the world */
+ XML_SetCharacterDataHandler(parser, NULL);
+ if (XML_ResumeParser(parser) != XML_STATUS_OK)
+ xml_failure(parser);
+ if (XML_ParseBuffer(parser, strlen(text), XML_TRUE) != XML_STATUS_ERROR)
+ fail("Post-finishing XML_ParseBuffer not faulted");
+ if (XML_GetErrorCode(parser) != XML_ERROR_FINISHED)
+ xml_failure(parser);
+ if (XML_GetBuffer(parser, strlen(text)) != NULL)
+ fail("Post-finishing XML_GetBuffer not faulted");
+}
+END_TEST
+
+/* Check handling of long prefix names (pool growth) */
+START_TEST(test_nsalloc_long_prefix)
+{
+ const char *text =
+ "<"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ ":foo xmlns:"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "='http://example.org/'>"
+ "</"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ ":foo>";
+ int i;
+ const int max_alloc_count = 40;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_nsalloc_xmlns() */
+ nsalloc_teardown();
+ nsalloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing allocations");
+ else if (i == max_alloc_count)
+ fail("Parsing failed even at max allocation count");
+}
+END_TEST
+
+/* Check handling of long uri names (pool growth) */
+START_TEST(test_nsalloc_long_uri)
+{
+ const char *text =
+ "<foo:e xmlns:foo='http://example.org/"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "' bar:a='12'\n"
+ "xmlns:bar='http://example.org/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789A/"
+ "'>"
+ "</foo:e>";
+ int i;
+ const int max_alloc_count = 40;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_nsalloc_xmlns() */
+ nsalloc_teardown();
+ nsalloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing allocations");
+ else if (i == max_alloc_count)
+ fail("Parsing failed even at max allocation count");
+}
+END_TEST
+
+/* Test handling of long attribute names with prefixes */
+START_TEST(test_nsalloc_long_attr)
+{
+ const char *text =
+ "<foo:e xmlns:foo='http://example.org/' bar:"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "='12'\n"
+ "xmlns:bar='http://example.org/'>"
+ "</foo:e>";
+ int i;
+ const int max_alloc_count = 40;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_nsalloc_xmlns() */
+ nsalloc_teardown();
+ nsalloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing allocations");
+ else if (i == max_alloc_count)
+ fail("Parsing failed even at max allocation count");
+}
+END_TEST
+
+/* Test handling of an attribute name with a long namespace prefix */
+START_TEST(test_nsalloc_long_attr_prefix)
+{
+ const char *text =
+ "<foo:e xmlns:foo='http://example.org/' "
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ ":a='12'\n"
+ "xmlns:"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "='http://example.org/'>"
+ "</foo:e>";
+ const XML_Char *elemstr[] = {
+ XCS("http://example.org/ e foo"),
+ XCS("http://example.org/ a ")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ")
+ XCS("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ")
+ };
+ int i;
+ const int max_alloc_count = 40;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ XML_SetReturnNSTriplet(parser, XML_TRUE);
+ XML_SetUserData(parser, elemstr);
+ XML_SetElementHandler(parser,
+ triplet_start_checker,
+ triplet_end_checker);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_nsalloc_xmlns() */
+ nsalloc_teardown();
+ nsalloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing allocations");
+ else if (i == max_alloc_count)
+ fail("Parsing failed even at max allocation count");
+}
+END_TEST
+
+/* Test attribute handling in the face of a dodgy reallocator */
+START_TEST(test_nsalloc_realloc_attributes)
+{
+ const char *text =
+ "<foo:e xmlns:foo='http://example.org/' bar:a='12'\n"
+ " xmlns:bar='http://example.org/'>"
+ "</foo:e>";
+ int i;
+ const int max_realloc_count = 10;
+
+ for (i = 0; i < max_realloc_count; i++) {
+ reallocation_count = i;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_nsalloc_xmlns() */
+ nsalloc_teardown();
+ nsalloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing reallocations");
+ else if (i == max_realloc_count)
+ fail("Parsing failed at max reallocation count");
+}
+END_TEST
+
+/* Test long element names with namespaces under a failing allocator */
+START_TEST(test_nsalloc_long_element)
+{
+ const char *text =
+ "<foo:thisisalongenoughelementnametotriggerareallocation\n"
+ " xmlns:foo='http://example.org/' bar:a='12'\n"
+ " xmlns:bar='http://example.org/'>"
+ "</foo:thisisalongenoughelementnametotriggerareallocation>";
+ const XML_Char *elemstr[] = {
+ XCS("http://example.org/")
+ XCS(" thisisalongenoughelementnametotriggerareallocation foo"),
+ XCS("http://example.org/ a bar")
+ };
+ int i;
+ const int max_alloc_count = 30;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ XML_SetReturnNSTriplet(parser, XML_TRUE);
+ XML_SetUserData(parser, elemstr);
+ XML_SetElementHandler(parser,
+ triplet_start_checker,
+ triplet_end_checker);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_nsalloc_xmlns() */
+ nsalloc_teardown();
+ nsalloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing reallocations");
+ else if (i == max_alloc_count)
+ fail("Parsing failed at max reallocation count");
+}
+END_TEST
+
+/* Test the effects of reallocation failure when reassigning a
+ * binding.
+ *
+ * XML_ParserReset does not free the BINDING structures used by a
+ * parser, but instead adds them to an internal free list to be reused
+ * as necessary. Likewise the URI buffers allocated for the binding
+ * aren't freed, but kept attached to their existing binding. If the
+ * new binding has a longer URI, it will need reallocation. This test
+ * provokes that reallocation, and tests the control path if it fails.
+ */
+START_TEST(test_nsalloc_realloc_binding_uri)
+{
+ const char *first =
+ "<doc xmlns='http://example.org/'>\n"
+ " <e xmlns='' />\n"
+ "</doc>";
+ const char *second =
+ "<doc xmlns='http://example.org/long/enough/URI/to/reallocate/'>\n"
+ " <e xmlns='' />\n"
+ "</doc>";
+ unsigned i;
+ const unsigned max_realloc_count = 10;
+
+ /* First, do a full parse that will leave bindings around */
+ if (_XML_Parse_SINGLE_BYTES(parser, first, strlen(first),
+ XML_TRUE) == XML_STATUS_ERROR)
+ xml_failure(parser);
+
+ /* Now repeat with a longer URI and a duff reallocator */
+ for (i = 0; i < max_realloc_count; i++) {
+ XML_ParserReset(parser, NULL);
+ reallocation_count = i;
+ if (_XML_Parse_SINGLE_BYTES(parser, second, strlen(second),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing reallocation");
+ else if (i == max_realloc_count)
+ fail("Parsing failed at max reallocation count");
+}
+END_TEST
+
+/* Check handling of long prefix names (pool growth) */
+START_TEST(test_nsalloc_realloc_long_prefix)
+{
+ const char *text =
+ "<"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ ":foo xmlns:"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "='http://example.org/'>"
+ "</"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ ":foo>";
+ int i;
+ const int max_realloc_count = 12;
+
+ for (i = 0; i < max_realloc_count; i++) {
+ reallocation_count = i;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_nsalloc_xmlns() */
+ nsalloc_teardown();
+ nsalloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing reallocations");
+ else if (i == max_realloc_count)
+ fail("Parsing failed even at max reallocation count");
+}
+END_TEST
+
+/* Check handling of even long prefix names (different code path) */
+START_TEST(test_nsalloc_realloc_longer_prefix)
+{
+ const char *text =
+ "<"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "Q:foo xmlns:"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "Q='http://example.org/'>"
+ "</"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "Q:foo>";
+ int i;
+ const int max_realloc_count = 12;
+
+ for (i = 0; i < max_realloc_count; i++) {
+ reallocation_count = i;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_nsalloc_xmlns() */
+ nsalloc_teardown();
+ nsalloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing reallocations");
+ else if (i == max_realloc_count)
+ fail("Parsing failed even at max reallocation count");
+}
+END_TEST
+
+START_TEST(test_nsalloc_long_namespace)
+{
+ const char *text1 =
+ "<"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ ":e xmlns:"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "='http://example.org/'>\n";
+ const char *text2 =
+ "<"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ ":f "
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ ":attr='foo'/>\n"
+ "</"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ ":e>";
+ int i;
+ const int max_alloc_count = 40;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ if (_XML_Parse_SINGLE_BYTES(parser, text1, strlen(text1),
+ XML_FALSE) != XML_STATUS_ERROR &&
+ _XML_Parse_SINGLE_BYTES(parser, text2, strlen(text2),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_nsalloc_xmlns() */
+ nsalloc_teardown();
+ nsalloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing allocations");
+ else if (i == max_alloc_count)
+ fail("Parsing failed even at max allocation count");
+}
+END_TEST
+
+/* Using a slightly shorter namespace name provokes allocations in
+ * slightly different places in the code.
+ */
+START_TEST(test_nsalloc_less_long_namespace)
+{
+ const char *text =
+ "<"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz012345678"
+ ":e xmlns:"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz012345678"
+ "='http://example.org/'>\n"
+ "<"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz012345678"
+ ":f "
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz012345678"
+ ":att='foo'/>\n"
+ "</"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789AZ"
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz012345678"
+ ":e>";
+ int i;
+ const int max_alloc_count = 40;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_nsalloc_xmlns() */
+ nsalloc_teardown();
+ nsalloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing allocations");
+ else if (i == max_alloc_count)
+ fail("Parsing failed even at max allocation count");
+}
+END_TEST
+
+START_TEST(test_nsalloc_long_context)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM 'foo' [\n"
+ " <!ATTLIST doc baz ID #REQUIRED>\n"
+ " <!ENTITY en SYSTEM 'bar'>\n"
+ "]>\n"
+ "<doc xmlns='http://example.org/"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKL"
+ "' baz='2'>\n"
+ "&en;"
+ "</doc>";
+ ExtOption options[] = {
+ { XCS("foo"), "<!ELEMENT e EMPTY>"},
+ { XCS("bar"), "<e/>" },
+ { NULL, NULL }
+ };
+ int i;
+ const int max_alloc_count = 70;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ XML_SetUserData(parser, options);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_optioner);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+
+ /* See comment in test_nsalloc_xmlns() */
+ nsalloc_teardown();
+ nsalloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing allocations");
+ else if (i == max_alloc_count)
+ fail("Parsing failed even at max allocation count");
+}
+END_TEST
+
+/* This function is void; it will throw a fail() on error, so if it
+ * returns normally it must have succeeded.
+ */
+static void
+context_realloc_test(const char *text)
+{
+ ExtOption options[] = {
+ { XCS("foo"), "<!ELEMENT e EMPTY>"},
+ { XCS("bar"), "<e/>" },
+ { NULL, NULL }
+ };
+ int i;
+ const int max_realloc_count = 6;
+
+ for (i = 0; i < max_realloc_count; i++) {
+ reallocation_count = i;
+ XML_SetUserData(parser, options);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_optioner);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_nsalloc_xmlns() */
+ nsalloc_teardown();
+ nsalloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing reallocations");
+ else if (i == max_realloc_count)
+ fail("Parsing failed even at max reallocation count");
+}
+
+START_TEST(test_nsalloc_realloc_long_context)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM 'foo' [\n"
+ " <!ENTITY en SYSTEM 'bar'>\n"
+ "]>\n"
+ "<doc xmlns='http://example.org/"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKL"
+ "'>\n"
+ "&en;"
+ "</doc>";
+
+ context_realloc_test(text);
+}
+END_TEST
+
+START_TEST(test_nsalloc_realloc_long_context_2)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM 'foo' [\n"
+ " <!ENTITY en SYSTEM 'bar'>\n"
+ "]>\n"
+ "<doc xmlns='http://example.org/"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJK"
+ "'>\n"
+ "&en;"
+ "</doc>";
+
+ context_realloc_test(text);
+}
+END_TEST
+
+START_TEST(test_nsalloc_realloc_long_context_3)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM 'foo' [\n"
+ " <!ENTITY en SYSTEM 'bar'>\n"
+ "]>\n"
+ "<doc xmlns='http://example.org/"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGH"
+ "'>\n"
+ "&en;"
+ "</doc>";
+
+ context_realloc_test(text);
+}
+END_TEST
+
+START_TEST(test_nsalloc_realloc_long_context_4)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM 'foo' [\n"
+ " <!ENTITY en SYSTEM 'bar'>\n"
+ "]>\n"
+ "<doc xmlns='http://example.org/"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO"
+ "'>\n"
+ "&en;"
+ "</doc>";
+
+ context_realloc_test(text);
+}
+END_TEST
+
+START_TEST(test_nsalloc_realloc_long_context_5)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM 'foo' [\n"
+ " <!ENTITY en SYSTEM 'bar'>\n"
+ "]>\n"
+ "<doc xmlns='http://example.org/"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABC"
+ "'>\n"
+ "&en;"
+ "</doc>";
+
+ context_realloc_test(text);
+}
+END_TEST
+
+START_TEST(test_nsalloc_realloc_long_context_6)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM 'foo' [\n"
+ " <!ENTITY en SYSTEM 'bar'>\n"
+ "]>\n"
+ "<doc xmlns='http://example.org/"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNOP"
+ "'>\n"
+ "&en;"
+ "</doc>";
+
+ context_realloc_test(text);
+}
+END_TEST
+
+START_TEST(test_nsalloc_realloc_long_context_7)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM 'foo' [\n"
+ " <!ENTITY en SYSTEM 'bar'>\n"
+ "]>\n"
+ "<doc xmlns='http://example.org/"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLM"
+ "'>\n"
+ "&en;"
+ "</doc>";
+
+ context_realloc_test(text);
+}
+END_TEST
+
+START_TEST(test_nsalloc_realloc_long_ge_name)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM 'foo' [\n"
+ " <!ENTITY "
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ " SYSTEM 'bar'>\n"
+ "]>\n"
+ "<doc xmlns='http://example.org/baz'>\n"
+ "&"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ ";"
+ "</doc>";
+ ExtOption options[] = {
+ { XCS("foo"), "<!ELEMENT el EMPTY>" },
+ { XCS("bar"), "<el/>" },
+ { NULL, NULL }
+ };
+ int i;
+ const int max_realloc_count = 10;
+
+ for (i = 0; i < max_realloc_count; i++) {
+ reallocation_count = i;
+ XML_SetUserData(parser, options);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_optioner);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_nsalloc_xmlns() */
+ nsalloc_teardown();
+ nsalloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing reallocations");
+ else if (i == max_realloc_count)
+ fail("Parsing failed even at max reallocation count");
+}
+END_TEST
+
+/* Test that when a namespace is passed through the context mechanism
+ * to an external entity parser, the parsers handle reallocation
+ * failures correctly. The prefix is exactly the right length to
+ * provoke particular uncommon code paths.
+ */
+START_TEST(test_nsalloc_realloc_long_context_in_dtd)
+{
+ const char *text1 =
+ "<!DOCTYPE "
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ ":doc [\n"
+ " <!ENTITY First SYSTEM 'foo/First'>\n"
+ "]>\n"
+ "<"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ ":doc xmlns:"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "='foo/Second'>&First;";
+ const char *text2 = "</"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ ":doc>";
+ ExtOption options[] = {
+ { XCS("foo/First"), "Hello world" },
+ { NULL, NULL }
+ };
+ int i;
+ const int max_realloc_count = 20;
+
+ for (i = 0; i < max_realloc_count; i++) {
+ reallocation_count = i;
+ XML_SetUserData(parser, options);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_optioner);
+ if (_XML_Parse_SINGLE_BYTES(parser, text1, strlen(text1),
+ XML_FALSE) != XML_STATUS_ERROR &&
+ _XML_Parse_SINGLE_BYTES(parser, text2, strlen(text2),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+ /* See comment in test_nsalloc_xmlns() */
+ nsalloc_teardown();
+ nsalloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing reallocations");
+ else if (i == max_realloc_count)
+ fail("Parsing failed even at max reallocation count");
+}
+END_TEST
+
+START_TEST(test_nsalloc_long_default_in_ext)
+{
+ const char *text =
+ "<!DOCTYPE doc [\n"
+ " <!ATTLIST e a1 CDATA '"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+ "'>\n"
+ " <!ENTITY x SYSTEM 'foo'>\n"
+ "]>\n"
+ "<doc>&x;</doc>";
+ ExtOption options[] = {
+ { XCS("foo"), "<e/>"},
+ { NULL, NULL }
+ };
+ int i;
+ const int max_alloc_count = 50;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ XML_SetUserData(parser, options);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_optioner);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+
+ /* See comment in test_nsalloc_xmlns() */
+ nsalloc_teardown();
+ nsalloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing allocations");
+ else if (i == max_alloc_count)
+ fail("Parsing failed even at max allocation count");
+}
+END_TEST
+
+START_TEST(test_nsalloc_long_systemid_in_ext)
+{
+ const char *text =
+ "<!DOCTYPE doc SYSTEM 'foo' [\n"
+ " <!ENTITY en SYSTEM '"
+ /* 64 characters per line */
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"
+ "'>\n"
+ "]>\n"
+ "<doc>&en;</doc>";
+ ExtOption options[] = {
+ { XCS("foo"), "<!ELEMENT e EMPTY>" },
+ {
+ XCS("ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/")
+ XCS("ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/")
+ XCS("ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/")
+ XCS("ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/")
+ XCS("ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/")
+ XCS("ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/")
+ XCS("ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/")
+ XCS("ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/")
+ XCS("ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/")
+ XCS("ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/")
+ XCS("ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/")
+ XCS("ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/")
+ XCS("ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/")
+ XCS("ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/")
+ XCS("ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/")
+ XCS("ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/ABCDEFGHIJKLMNO/"),
+ "<e/>"
+ },
+ { NULL, NULL }
+ };
+ int i;
+ const int max_alloc_count = 55;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ XML_SetUserData(parser, options);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_optioner);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+
+ /* See comment in test_nsalloc_xmlns() */
+ nsalloc_teardown();
+ nsalloc_setup();
+ }
+ if (i == 0)
+ fail("Parsing worked despite failing allocations");
+ else if (i == max_alloc_count)
+ fail("Parsing failed even at max allocation count");
+}
+END_TEST
+
+/* Test the effects of allocation failure on parsing an element in a
+ * namespace. Based on test_nsalloc_long_context.
+ */
+START_TEST(test_nsalloc_prefixed_element)
+{
+ const char *text =
+ "<!DOCTYPE pfx:element SYSTEM 'foo' [\n"
+ " <!ATTLIST pfx:element baz ID #REQUIRED>\n"
+ " <!ENTITY en SYSTEM 'bar'>\n"
+ "]>\n"
+ "<pfx:element xmlns:pfx='http://example.org/' baz='2'>\n"
+ "&en;"
+ "</pfx:element>";
+ ExtOption options[] = {
+ { XCS("foo"), "<!ELEMENT e EMPTY>" },
+ { XCS("bar"), "<e/>" },
+ { NULL, NULL }
+ };
+ int i;
+ const int max_alloc_count = 70;
+
+ for (i = 0; i < max_alloc_count; i++) {
+ allocation_count = i;
+ XML_SetUserData(parser, options);
+ XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS);
+ XML_SetExternalEntityRefHandler(parser, external_entity_optioner);
+ if (_XML_Parse_SINGLE_BYTES(parser, text, strlen(text),
+ XML_TRUE) != XML_STATUS_ERROR)
+ break;
+
+ /* See comment in test_nsalloc_xmlns() */
+ nsalloc_teardown();
+ nsalloc_setup();
+ }
+ if (i == 0)
+ fail("Success despite failing allocator");
+ else if (i == max_alloc_count)
+ fail("Failed even at full allocation count");
+}
+END_TEST
+
static Suite *
make_suite(void)
{
Suite *s = suite_create("basic");
TCase *tc_basic = tcase_create("basic tests");
TCase *tc_namespace = tcase_create("XML namespaces");
+ TCase *tc_misc = tcase_create("miscellaneous tests");
+ TCase *tc_alloc = tcase_create("allocation tests");
+ TCase *tc_nsalloc = tcase_create("namespace allocation tests");
suite_add_tcase(s, tc_basic);
tcase_add_checked_fixture(tc_basic, basic_setup, basic_teardown);
tcase_add_test(tc_basic, test_nul_byte);
tcase_add_test(tc_basic, test_u0000_char);
+ tcase_add_test(tc_basic, test_siphash_self);
+ tcase_add_test(tc_basic, test_siphash_spec);
tcase_add_test(tc_basic, test_bom_utf8);
tcase_add_test(tc_basic, test_bom_utf16_be);
tcase_add_test(tc_basic, test_bom_utf16_le);
+ tcase_add_test(tc_basic, test_nobom_utf16_le);
tcase_add_test(tc_basic, test_illegal_utf8);
tcase_add_test(tc_basic, test_utf8_auto_align);
tcase_add_test(tc_basic, test_utf16);
tcase_add_test(tc_basic, test_utf16_le_epilog_newline);
+ tcase_add_test(tc_basic, test_not_utf16);
+ tcase_add_test(tc_basic, test_bad_encoding);
tcase_add_test(tc_basic, test_latin1_umlauts);
+ tcase_add_test(tc_basic, test_long_utf8_character);
+ tcase_add_test(tc_basic, test_long_latin1_attribute);
+ tcase_add_test(tc_basic, test_long_ascii_attribute);
/* Regression test for SF bug #491986. */
tcase_add_test(tc_basic, test_danish_latin1);
/* Regression test for SF bug #514281. */
@@ -1627,27 +11979,190 @@ make_suite(void)
tcase_add_test(tc_basic, test_line_number_after_error);
tcase_add_test(tc_basic, test_column_number_after_error);
tcase_add_test(tc_basic, test_really_long_lines);
+ tcase_add_test(tc_basic, test_really_long_encoded_lines);
tcase_add_test(tc_basic, test_end_element_events);
tcase_add_test(tc_basic, test_attr_whitespace_normalization);
tcase_add_test(tc_basic, test_xmldecl_misplaced);
+ tcase_add_test(tc_basic, test_xmldecl_invalid);
+ tcase_add_test(tc_basic, test_xmldecl_missing_attr);
+ tcase_add_test(tc_basic, test_xmldecl_missing_value);
tcase_add_test(tc_basic, test_unknown_encoding_internal_entity);
+ tcase_add_test(tc_basic, test_unrecognised_encoding_internal_entity);
tcase_add_test(tc_basic,
test_wfc_undeclared_entity_unread_external_subset);
tcase_add_test(tc_basic, test_wfc_undeclared_entity_no_external_subset);
tcase_add_test(tc_basic, test_wfc_undeclared_entity_standalone);
tcase_add_test(tc_basic, test_wfc_undeclared_entity_with_external_subset);
+ tcase_add_test(tc_basic, test_not_standalone_handler_reject);
+ tcase_add_test(tc_basic, test_not_standalone_handler_accept);
tcase_add_test(tc_basic,
test_wfc_undeclared_entity_with_external_subset_standalone);
+ tcase_add_test(tc_basic,
+ test_entity_with_external_subset_unless_standalone);
tcase_add_test(tc_basic, test_wfc_no_recursive_entity_refs);
tcase_add_test(tc_basic, test_ext_entity_set_encoding);
+ tcase_add_test(tc_basic, test_ext_entity_no_handler);
+ tcase_add_test(tc_basic, test_ext_entity_set_bom);
+ tcase_add_test(tc_basic, test_ext_entity_bad_encoding);
+ tcase_add_test(tc_basic, test_ext_entity_bad_encoding_2);
+ tcase_add_test(tc_basic, test_ext_entity_invalid_parse);
+ tcase_add_test(tc_basic, test_ext_entity_invalid_suspended_parse);
tcase_add_test(tc_basic, test_dtd_default_handling);
+ tcase_add_test(tc_basic, test_dtd_attr_handling);
tcase_add_test(tc_basic, test_empty_ns_without_namespaces);
tcase_add_test(tc_basic, test_ns_in_attribute_default_without_namespaces);
tcase_add_test(tc_basic, test_stop_parser_between_char_data_calls);
tcase_add_test(tc_basic, test_suspend_parser_between_char_data_calls);
+ tcase_add_test(tc_basic, test_repeated_stop_parser_between_char_data_calls);
tcase_add_test(tc_basic, test_good_cdata_ascii);
tcase_add_test(tc_basic, test_good_cdata_utf16);
+ tcase_add_test(tc_basic, test_good_cdata_utf16_le);
+ tcase_add_test(tc_basic, test_long_cdata_utf16);
+ tcase_add_test(tc_basic, test_multichar_cdata_utf16);
+ tcase_add_test(tc_basic, test_utf16_bad_surrogate_pair);
tcase_add_test(tc_basic, test_bad_cdata);
+ tcase_add_test(tc_basic, test_bad_cdata_utf16);
+ tcase_add_test(tc_basic, test_stop_parser_between_cdata_calls);
+ tcase_add_test(tc_basic, test_suspend_parser_between_cdata_calls);
+ tcase_add_test(tc_basic, test_memory_allocation);
+ tcase_add_test(tc_basic, test_default_current);
+ tcase_add_test(tc_basic, test_dtd_elements);
+ tcase_add_test(tc_basic, test_set_foreign_dtd);
+ tcase_add_test(tc_basic, test_foreign_dtd_not_standalone);
+ tcase_add_test(tc_basic, test_invalid_foreign_dtd);
+ tcase_add_test(tc_basic, test_foreign_dtd_with_doctype);
+ tcase_add_test(tc_basic, test_foreign_dtd_without_external_subset);
+ tcase_add_test(tc_basic, test_empty_foreign_dtd);
+ tcase_add_test(tc_basic, test_set_base);
+ tcase_add_test(tc_basic, test_attributes);
+ tcase_add_test(tc_basic, test_reset_in_entity);
+ tcase_add_test(tc_basic, test_resume_invalid_parse);
+ tcase_add_test(tc_basic, test_resume_resuspended);
+ tcase_add_test(tc_basic, test_cdata_default);
+ tcase_add_test(tc_basic, test_subordinate_reset);
+ tcase_add_test(tc_basic, test_subordinate_suspend);
+ tcase_add_test(tc_basic, test_subordinate_xdecl_suspend);
+ tcase_add_test(tc_basic, test_subordinate_xdecl_abort);
+ tcase_add_test(tc_basic, test_explicit_encoding);
+ tcase_add_test(tc_basic, test_trailing_cr);
+ tcase_add_test(tc_basic, test_ext_entity_trailing_cr);
+ tcase_add_test(tc_basic, test_trailing_rsqb);
+ tcase_add_test(tc_basic, test_ext_entity_trailing_rsqb);
+ tcase_add_test(tc_basic, test_ext_entity_good_cdata);
+ tcase_add_test(tc_basic, test_user_parameters);
+ tcase_add_test(tc_basic, test_ext_entity_ref_parameter);
+ tcase_add_test(tc_basic, test_empty_parse);
+ tcase_add_test(tc_basic, test_get_buffer_1);
+ tcase_add_test(tc_basic, test_get_buffer_2);
+ tcase_add_test(tc_basic, test_byte_info_at_end);
+ tcase_add_test(tc_basic, test_byte_info_at_error);
+ tcase_add_test(tc_basic, test_byte_info_at_cdata);
+ tcase_add_test(tc_basic, test_predefined_entities);
+ tcase_add_test(tc_basic, test_invalid_tag_in_dtd);
+ tcase_add_test(tc_basic, test_not_predefined_entities);
+ tcase_add_test(tc_basic, test_ignore_section);
+ tcase_add_test(tc_basic, test_ignore_section_utf16);
+ tcase_add_test(tc_basic, test_ignore_section_utf16_be);
+ tcase_add_test(tc_basic, test_bad_ignore_section);
+ tcase_add_test(tc_basic, test_external_entity_values);
+ tcase_add_test(tc_basic, test_ext_entity_not_standalone);
+ tcase_add_test(tc_basic, test_ext_entity_value_abort);
+ tcase_add_test(tc_basic, test_bad_public_doctype);
+ tcase_add_test(tc_basic, test_attribute_enum_value);
+ tcase_add_test(tc_basic, test_predefined_entity_redefinition);
+ tcase_add_test(tc_basic, test_dtd_stop_processing);
+ tcase_add_test(tc_basic, test_public_notation_no_sysid);
+ tcase_add_test(tc_basic, test_nested_groups);
+ tcase_add_test(tc_basic, test_group_choice);
+ tcase_add_test(tc_basic, test_standalone_parameter_entity);
+ tcase_add_test(tc_basic, test_skipped_parameter_entity);
+ tcase_add_test(tc_basic, test_recursive_external_parameter_entity);
+ tcase_add_test(tc_basic, test_undefined_ext_entity_in_external_dtd);
+ tcase_add_test(tc_basic, test_suspend_xdecl);
+ tcase_add_test(tc_basic, test_abort_epilog);
+ tcase_add_test(tc_basic, test_abort_epilog_2);
+ tcase_add_test(tc_basic, test_suspend_epilog);
+ tcase_add_test(tc_basic, test_unfinished_epilog);
+ tcase_add_test(tc_basic, test_partial_char_in_epilog);
+ tcase_add_test(tc_basic, test_hash_collision);
+ tcase_add_test(tc_basic, test_suspend_resume_internal_entity);
+ tcase_add_test(tc_basic, test_resume_entity_with_syntax_error);
+ tcase_add_test(tc_basic, test_suspend_resume_parameter_entity);
+ tcase_add_test(tc_basic, test_restart_on_error);
+ tcase_add_test(tc_basic, test_reject_lt_in_attribute_value);
+ tcase_add_test(tc_basic, test_reject_unfinished_param_in_att_value);
+ tcase_add_test(tc_basic, test_trailing_cr_in_att_value);
+ tcase_add_test(tc_basic, test_standalone_internal_entity);
+ tcase_add_test(tc_basic, test_skipped_external_entity);
+ tcase_add_test(tc_basic, test_skipped_null_loaded_ext_entity);
+ tcase_add_test(tc_basic, test_skipped_unloaded_ext_entity);
+ tcase_add_test(tc_basic, test_param_entity_with_trailing_cr);
+ tcase_add_test(tc_basic, test_invalid_character_entity);
+ tcase_add_test(tc_basic, test_invalid_character_entity_2);
+ tcase_add_test(tc_basic, test_invalid_character_entity_3);
+ tcase_add_test(tc_basic, test_invalid_character_entity_4);
+ tcase_add_test(tc_basic, test_pi_handled_in_default);
+ tcase_add_test(tc_basic, test_comment_handled_in_default);
+ tcase_add_test(tc_basic, test_pi_yml);
+ tcase_add_test(tc_basic, test_pi_xnl);
+ tcase_add_test(tc_basic, test_pi_xmm);
+ tcase_add_test(tc_basic, test_utf16_pi);
+ tcase_add_test(tc_basic, test_utf16_be_pi);
+ tcase_add_test(tc_basic, test_utf16_be_comment);
+ tcase_add_test(tc_basic, test_utf16_le_comment);
+ tcase_add_test(tc_basic, test_missing_encoding_conversion_fn);
+ tcase_add_test(tc_basic, test_failing_encoding_conversion_fn);
+ tcase_add_test(tc_basic, test_unknown_encoding_success);
+ tcase_add_test(tc_basic, test_unknown_encoding_bad_name);
+ tcase_add_test(tc_basic, test_unknown_encoding_bad_name_2);
+ tcase_add_test(tc_basic, test_unknown_encoding_long_name_1);
+ tcase_add_test(tc_basic, test_unknown_encoding_long_name_2);
+ tcase_add_test(tc_basic, test_invalid_unknown_encoding);
+ tcase_add_test(tc_basic, test_unknown_ascii_encoding_ok);
+ tcase_add_test(tc_basic, test_unknown_ascii_encoding_fail);
+ tcase_add_test(tc_basic, test_unknown_encoding_invalid_length);
+ tcase_add_test(tc_basic, test_unknown_encoding_invalid_topbit);
+ tcase_add_test(tc_basic, test_unknown_encoding_invalid_surrogate);
+ tcase_add_test(tc_basic, test_unknown_encoding_invalid_high);
+ tcase_add_test(tc_basic, test_unknown_encoding_invalid_attr_value);
+ tcase_add_test(tc_basic, test_ext_entity_latin1_utf16le_bom);
+ tcase_add_test(tc_basic, test_ext_entity_latin1_utf16be_bom);
+ tcase_add_test(tc_basic, test_ext_entity_latin1_utf16le_bom2);
+ tcase_add_test(tc_basic, test_ext_entity_latin1_utf16be_bom2);
+ tcase_add_test(tc_basic, test_ext_entity_utf16_be);
+ tcase_add_test(tc_basic, test_ext_entity_utf16_le);
+ tcase_add_test(tc_basic, test_ext_entity_utf16_unknown);
+ tcase_add_test(tc_basic, test_ext_entity_utf8_non_bom);
+ tcase_add_test(tc_basic, test_utf8_in_cdata_section);
+ tcase_add_test(tc_basic, test_utf8_in_cdata_section_2);
+ tcase_add_test(tc_basic, test_trailing_spaces_in_elements);
+ tcase_add_test(tc_basic, test_utf16_attribute);
+ tcase_add_test(tc_basic, test_utf16_second_attr);
+ tcase_add_test(tc_basic, test_attr_after_solidus);
+ tcase_add_test(tc_basic, test_utf16_pe);
+ tcase_add_test(tc_basic, test_bad_attr_desc_keyword);
+ tcase_add_test(tc_basic, test_bad_attr_desc_keyword_utf16);
+ tcase_add_test(tc_basic, test_bad_doctype);
+ tcase_add_test(tc_basic, test_bad_doctype_utf16);
+ tcase_add_test(tc_basic, test_bad_doctype_plus);
+ tcase_add_test(tc_basic, test_bad_doctype_star);
+ tcase_add_test(tc_basic, test_bad_doctype_query);
+ tcase_add_test(tc_basic, test_unknown_encoding_bad_ignore);
+ tcase_add_test(tc_basic, test_entity_in_utf16_be_attr);
+ tcase_add_test(tc_basic, test_entity_in_utf16_le_attr);
+ tcase_add_test(tc_basic, test_entity_public_utf16_be);
+ tcase_add_test(tc_basic, test_entity_public_utf16_le);
+ tcase_add_test(tc_basic, test_short_doctype);
+ tcase_add_test(tc_basic, test_short_doctype_2);
+ tcase_add_test(tc_basic, test_short_doctype_3);
+ tcase_add_test(tc_basic, test_long_doctype);
+ tcase_add_test(tc_basic, test_bad_entity);
+ tcase_add_test(tc_basic, test_bad_entity_2);
+ tcase_add_test(tc_basic, test_bad_entity_3);
+ tcase_add_test(tc_basic, test_bad_entity_4);
+ tcase_add_test(tc_basic, test_bad_notation);
+ tcase_add_test(tc_basic, test_default_doctype_handler);
+ tcase_add_test(tc_basic, test_empty_element_abort);
suite_add_tcase(s, tc_namespace);
tcase_add_checked_fixture(tc_namespace,
@@ -1661,10 +12176,123 @@ make_suite(void)
tcase_add_test(tc_namespace, test_ns_prefix_with_empty_uri_2);
tcase_add_test(tc_namespace, test_ns_prefix_with_empty_uri_3);
tcase_add_test(tc_namespace, test_ns_prefix_with_empty_uri_4);
+ tcase_add_test(tc_namespace, test_ns_unbound_prefix);
tcase_add_test(tc_namespace, test_ns_default_with_empty_uri);
tcase_add_test(tc_namespace, test_ns_duplicate_attrs_diff_prefixes);
+ tcase_add_test(tc_namespace, test_ns_duplicate_hashes);
tcase_add_test(tc_namespace, test_ns_unbound_prefix_on_attribute);
tcase_add_test(tc_namespace, test_ns_unbound_prefix_on_element);
+ tcase_add_test(tc_namespace, test_ns_parser_reset);
+ tcase_add_test(tc_namespace, test_ns_long_element);
+ tcase_add_test(tc_namespace, test_ns_mixed_prefix_atts);
+ tcase_add_test(tc_namespace, test_ns_extend_uri_buffer);
+ tcase_add_test(tc_namespace, test_ns_reserved_attributes);
+ tcase_add_test(tc_namespace, test_ns_reserved_attributes_2);
+ tcase_add_test(tc_namespace, test_ns_extremely_long_prefix);
+ tcase_add_test(tc_namespace, test_ns_unknown_encoding_success);
+ tcase_add_test(tc_namespace, test_ns_double_colon);
+ tcase_add_test(tc_namespace, test_ns_double_colon_element);
+ tcase_add_test(tc_namespace, test_ns_bad_attr_leafname);
+ tcase_add_test(tc_namespace, test_ns_bad_element_leafname);
+ tcase_add_test(tc_namespace, test_ns_utf16_leafname);
+ tcase_add_test(tc_namespace, test_ns_utf16_element_leafname);
+ tcase_add_test(tc_namespace, test_ns_utf16_doctype);
+ tcase_add_test(tc_namespace, test_ns_invalid_doctype);
+ tcase_add_test(tc_namespace, test_ns_double_colon_doctype);
+
+ suite_add_tcase(s, tc_misc);
+ tcase_add_checked_fixture(tc_misc, NULL, basic_teardown);
+ tcase_add_test(tc_misc, test_misc_alloc_create_parser);
+ tcase_add_test(tc_misc, test_misc_alloc_create_parser_with_encoding);
+ tcase_add_test(tc_misc, test_misc_null_parser);
+ tcase_add_test(tc_misc, test_misc_error_string);
+ tcase_add_test(tc_misc, test_misc_version);
+ tcase_add_test(tc_misc, test_misc_features);
+ tcase_add_test(tc_misc, test_misc_attribute_leak);
+ tcase_add_test(tc_misc, test_misc_utf16le);
+
+ suite_add_tcase(s, tc_alloc);
+ tcase_add_checked_fixture(tc_alloc, alloc_setup, alloc_teardown);
+ tcase_add_test(tc_alloc, test_alloc_parse_xdecl);
+ tcase_add_test(tc_alloc, test_alloc_parse_xdecl_2);
+ tcase_add_test(tc_alloc, test_alloc_parse_pi);
+ tcase_add_test(tc_alloc, test_alloc_parse_pi_2);
+ tcase_add_test(tc_alloc, test_alloc_parse_pi_3);
+ tcase_add_test(tc_alloc, test_alloc_parse_comment);
+ tcase_add_test(tc_alloc, test_alloc_parse_comment_2);
+ tcase_add_test(tc_alloc, test_alloc_create_external_parser);
+ tcase_add_test(tc_alloc, test_alloc_run_external_parser);
+ tcase_add_test(tc_alloc, test_alloc_dtd_copy_default_atts);
+ tcase_add_test(tc_alloc, test_alloc_external_entity);
+ tcase_add_test(tc_alloc, test_alloc_ext_entity_set_encoding);
+ tcase_add_test(tc_alloc, test_alloc_internal_entity);
+ tcase_add_test(tc_alloc, test_alloc_dtd_default_handling);
+ tcase_add_test(tc_alloc, test_alloc_explicit_encoding);
+ tcase_add_test(tc_alloc, test_alloc_set_base);
+ tcase_add_test(tc_alloc, test_alloc_realloc_buffer);
+ tcase_add_test(tc_alloc, test_alloc_ext_entity_realloc_buffer);
+ tcase_add_test(tc_alloc, test_alloc_realloc_many_attributes);
+ tcase_add_test(tc_alloc, test_alloc_public_entity_value);
+ tcase_add_test(tc_alloc, test_alloc_realloc_subst_public_entity_value);
+ tcase_add_test(tc_alloc, test_alloc_parse_public_doctype);
+ tcase_add_test(tc_alloc, test_alloc_parse_public_doctype_long_name);
+ tcase_add_test(tc_alloc, test_alloc_set_foreign_dtd);
+ tcase_add_test(tc_alloc, test_alloc_attribute_enum_value);
+ tcase_add_test(tc_alloc, test_alloc_realloc_attribute_enum_value);
+ tcase_add_test(tc_alloc, test_alloc_realloc_implied_attribute);
+ tcase_add_test(tc_alloc, test_alloc_realloc_default_attribute);
+ tcase_add_test(tc_alloc, test_alloc_notation);
+ tcase_add_test(tc_alloc, test_alloc_public_notation);
+ tcase_add_test(tc_alloc, test_alloc_system_notation);
+ tcase_add_test(tc_alloc, test_alloc_nested_groups);
+ tcase_add_test(tc_alloc, test_alloc_realloc_nested_groups);
+ tcase_add_test(tc_alloc, test_alloc_large_group);
+ tcase_add_test(tc_alloc, test_alloc_realloc_group_choice);
+ tcase_add_test(tc_alloc, test_alloc_pi_in_epilog);
+ tcase_add_test(tc_alloc, test_alloc_comment_in_epilog);
+ tcase_add_test(tc_alloc, test_alloc_realloc_long_attribute_value);
+ tcase_add_test(tc_alloc, test_alloc_attribute_whitespace);
+ tcase_add_test(tc_alloc, test_alloc_attribute_predefined_entity);
+ tcase_add_test(tc_alloc, test_alloc_long_attr_default_with_char_ref);
+ tcase_add_test(tc_alloc, test_alloc_long_attr_value);
+ tcase_add_test(tc_alloc, test_alloc_nested_entities);
+ tcase_add_test(tc_alloc, test_alloc_realloc_param_entity_newline);
+ tcase_add_test(tc_alloc, test_alloc_realloc_ce_extends_pe);
+ tcase_add_test(tc_alloc, test_alloc_realloc_attributes);
+ tcase_add_test(tc_alloc, test_alloc_long_doc_name);
+ tcase_add_test(tc_alloc, test_alloc_long_base);
+ tcase_add_test(tc_alloc, test_alloc_long_public_id);
+ tcase_add_test(tc_alloc, test_alloc_long_entity_value);
+ tcase_add_test(tc_alloc, test_alloc_long_notation);
+
+ suite_add_tcase(s, tc_nsalloc);
+ tcase_add_checked_fixture(tc_nsalloc, nsalloc_setup, nsalloc_teardown);
+ tcase_add_test(tc_nsalloc, test_nsalloc_xmlns);
+ tcase_add_test(tc_nsalloc, test_nsalloc_parse_buffer);
+ tcase_add_test(tc_nsalloc, test_nsalloc_long_prefix);
+ tcase_add_test(tc_nsalloc, test_nsalloc_long_uri);
+ tcase_add_test(tc_nsalloc, test_nsalloc_long_attr);
+ tcase_add_test(tc_nsalloc, test_nsalloc_long_attr_prefix);
+ tcase_add_test(tc_nsalloc, test_nsalloc_realloc_attributes);
+ tcase_add_test(tc_nsalloc, test_nsalloc_long_element);
+ tcase_add_test(tc_nsalloc, test_nsalloc_realloc_binding_uri);
+ tcase_add_test(tc_nsalloc, test_nsalloc_realloc_long_prefix);
+ tcase_add_test(tc_nsalloc, test_nsalloc_realloc_longer_prefix);
+ tcase_add_test(tc_nsalloc, test_nsalloc_long_namespace);
+ tcase_add_test(tc_nsalloc, test_nsalloc_less_long_namespace);
+ tcase_add_test(tc_nsalloc, test_nsalloc_long_context);
+ tcase_add_test(tc_nsalloc, test_nsalloc_realloc_long_context);
+ tcase_add_test(tc_nsalloc, test_nsalloc_realloc_long_context_2);
+ tcase_add_test(tc_nsalloc, test_nsalloc_realloc_long_context_3);
+ tcase_add_test(tc_nsalloc, test_nsalloc_realloc_long_context_4);
+ tcase_add_test(tc_nsalloc, test_nsalloc_realloc_long_context_5);
+ tcase_add_test(tc_nsalloc, test_nsalloc_realloc_long_context_6);
+ tcase_add_test(tc_nsalloc, test_nsalloc_realloc_long_context_7);
+ tcase_add_test(tc_nsalloc, test_nsalloc_realloc_long_ge_name);
+ tcase_add_test(tc_nsalloc, test_nsalloc_realloc_long_context_in_dtd);
+ tcase_add_test(tc_nsalloc, test_nsalloc_long_default_in_ext);
+ tcase_add_test(tc_nsalloc, test_nsalloc_long_systemid_in_ext);
+ tcase_add_test(tc_nsalloc, test_nsalloc_prefixed_element);
return s;
}
@@ -1693,7 +12321,7 @@ main(int argc, char *argv[])
}
}
if (verbosity != CK_SILENT)
- printf("Expat version: %s\n", XML_ExpatVersion());
+ printf("Expat version: %" XML_FMT_STR "\n", XML_ExpatVersion());
srunner_run_all(sr, verbosity);
nf = srunner_ntests_failed(sr);
srunner_free(sr);
diff --git a/tests/runtests.sln b/tests/runtests.sln
new file mode 100644
index 0000000..6e07293
--- /dev/null
+++ b/tests/runtests.sln
@@ -0,0 +1,24 @@
+
+Microsoft Visual Studio Solution File, Format Version 12.00
+# Visual Studio 2013
+VisualStudioVersion = 12.0.40629.0
+MinimumVisualStudioVersion = 10.0.40219.1
+Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "runtests", "runtests.vcxproj", "{63D6D820-B526-4A5F-9605-9B8551FAC591}"
+EndProject
+Global
+ GlobalSection(SolutionConfigurationPlatforms) = preSolution
+ Debug|Win32 = Debug|Win32
+ Release|Win32 = Release|Win32
+ Template|Win32 = Template|Win32
+ EndGlobalSection
+ GlobalSection(ProjectConfigurationPlatforms) = postSolution
+ {63D6D820-B526-4A5F-9605-9B8551FAC591}.Debug|Win32.ActiveCfg = Debug|Win32
+ {63D6D820-B526-4A5F-9605-9B8551FAC591}.Debug|Win32.Build.0 = Debug|Win32
+ {63D6D820-B526-4A5F-9605-9B8551FAC591}.Release|Win32.ActiveCfg = Release|Win32
+ {63D6D820-B526-4A5F-9605-9B8551FAC591}.Release|Win32.Build.0 = Release|Win32
+ {63D6D820-B526-4A5F-9605-9B8551FAC591}.Template|Win32.ActiveCfg = Release|Win32
+ EndGlobalSection
+ GlobalSection(SolutionProperties) = preSolution
+ HideSolutionNode = FALSE
+ EndGlobalSection
+EndGlobal
diff --git a/tests/runtests.vcxproj b/tests/runtests.vcxproj
new file mode 100644
index 0000000..fc77e51
--- /dev/null
+++ b/tests/runtests.vcxproj
@@ -0,0 +1,142 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project DefaultTargets="Build" ToolsVersion="12.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+ <ItemGroup Label="ProjectConfigurations">
+ <ProjectConfiguration Include="Debug|Win32">
+ <Configuration>Debug</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Release|Win32">
+ <Configuration>Release</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ </ItemGroup>
+ <PropertyGroup Label="Globals">
+ <SccProjectName />
+ <SccLocalPath />
+ <ProjectGuid>{63D6D820-B526-4A5F-9605-9B8551FAC591}</ProjectGuid>
+ </PropertyGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
+ <ConfigurationType>Application</ConfigurationType>
+ <PlatformToolset>v120</PlatformToolset>
+ <UseOfMfc>false</UseOfMfc>
+ <CharacterSet>MultiByte</CharacterSet>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
+ <ConfigurationType>Application</ConfigurationType>
+ <PlatformToolset>v120</PlatformToolset>
+ <UseOfMfc>false</UseOfMfc>
+ <CharacterSet>MultiByte</CharacterSet>
+ </PropertyGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
+ <ImportGroup Label="ExtensionSettings">
+ </ImportGroup>
+ <ImportGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="PropertySheets">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ <Import Project="$(VCTargetsPath)Microsoft.Cpp.UpgradeFromVC60.props" />
+ </ImportGroup>
+ <ImportGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="PropertySheets">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ <Import Project="$(VCTargetsPath)Microsoft.Cpp.UpgradeFromVC60.props" />
+ </ImportGroup>
+ <PropertyGroup Label="UserMacros" />
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+ <OutDir>.\Release\</OutDir>
+ <IntDir>.\Release\</IntDir>
+ <LinkIncremental>false</LinkIncremental>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ <OutDir>.\Debug\</OutDir>
+ <IntDir>.\Debug\</IntDir>
+ <LinkIncremental>true</LinkIncremental>
+ </PropertyGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+ <ClCompile>
+ <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
+ <InlineFunctionExpansion>Default</InlineFunctionExpansion>
+ <StringPooling>true</StringPooling>
+ <FunctionLevelLinking>true</FunctionLevelLinking>
+ <Optimization>MaxSpeed</Optimization>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <WarningLevel>Level3</WarningLevel>
+ <AdditionalIncludeDirectories>..\lib;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
+ <PreprocessorDefinitions>NDEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <AssemblerListingLocation>.\Release\</AssemblerListingLocation>
+ <PrecompiledHeaderOutputFile>.\Release\runtests.pch</PrecompiledHeaderOutputFile>
+ <ObjectFileName>.\Release\</ObjectFileName>
+ <ProgramDataBaseFileName>.\Release\</ProgramDataBaseFileName>
+ </ClCompile>
+ <Midl>
+ <TypeLibraryName>.\Release\runtests.tlb</TypeLibraryName>
+ </Midl>
+ <ResourceCompile>
+ <Culture>0x1009</Culture>
+ <PreprocessorDefinitions>NDEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ </ResourceCompile>
+ <Bscmake>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <OutputFile>.\Release\runtests.bsc</OutputFile>
+ </Bscmake>
+ <Link>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <SubSystem>Console</SubSystem>
+ <OutputFile>.\Release\runtests.exe</OutputFile>
+ <AdditionalLibraryDirectories>..\win32\bin\Release;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
+ <AdditionalDependencies>libexpatMT.lib;libexpat.exp;%(AdditionalDependencies)</AdditionalDependencies>
+ </Link>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ <ClCompile>
+ <RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
+ <InlineFunctionExpansion>Default</InlineFunctionExpansion>
+ <FunctionLevelLinking>true</FunctionLevelLinking>
+ <Optimization>Disabled</Optimization>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <WarningLevel>Level3</WarningLevel>
+ <MinimalRebuild>true</MinimalRebuild>
+ <DebugInformationFormat>EditAndContinue</DebugInformationFormat>
+ <AdditionalIncludeDirectories>..\lib;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
+ <PreprocessorDefinitions>_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <AssemblerListingLocation>.\Debug\</AssemblerListingLocation>
+ <PrecompiledHeaderOutputFile>.\Debug\runtests.pch</PrecompiledHeaderOutputFile>
+ <ObjectFileName>.\Debug\</ObjectFileName>
+ <ProgramDataBaseFileName>.\Debug\</ProgramDataBaseFileName>
+ <BasicRuntimeChecks>EnableFastChecks</BasicRuntimeChecks>
+ </ClCompile>
+ <Midl>
+ <TypeLibraryName>.\Debug\runtests.tlb</TypeLibraryName>
+ </Midl>
+ <ResourceCompile>
+ <Culture>0x1009</Culture>
+ <PreprocessorDefinitions>_DEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ </ResourceCompile>
+ <Bscmake>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <OutputFile>.\Debug\runtests.bsc</OutputFile>
+ </Bscmake>
+ <Link>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <GenerateDebugInformation>true</GenerateDebugInformation>
+ <SubSystem>Console</SubSystem>
+ <OutputFile>.\Debug\runtests.exe</OutputFile>
+ <AdditionalLibraryDirectories>..\win32\bin\Debug;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
+ <AdditionalDependencies>libexpatMT.lib;libexpat.exp;%(AdditionalDependencies)</AdditionalDependencies>
+ </Link>
+ </ItemDefinitionGroup>
+ <ItemGroup>
+ <ClCompile Include="chardata.c" />
+ <ClCompile Include="minicheck.c" />
+ <ClCompile Include="memcheck.c" />
+ <ClCompile Include="runtests.c" />
+ <ClCompile Include="structdata.c" />
+ </ItemGroup>
+ <ItemGroup>
+ <ClInclude Include="chardata.h" />
+ <ClInclude Include="minicheck.h" />
+ <ClInclude Include="memcheck.h" />
+ <ClInclude Include="structdata.h" />
+ </ItemGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
+ <ImportGroup Label="ExtensionTargets">
+ </ImportGroup>
+</Project> \ No newline at end of file
diff --git a/tests/runtests.vcxproj.filters b/tests/runtests.vcxproj.filters
new file mode 100644
index 0000000..c058c12
--- /dev/null
+++ b/tests/runtests.vcxproj.filters
@@ -0,0 +1,48 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+ <ItemGroup>
+ <Filter Include="Source Files">
+ <UniqueIdentifier>{a3e83144-e1b8-4d37-853a-793ce2b17b31}</UniqueIdentifier>
+ <Extensions>cpp;c;cxx;rc;def;r;odl;idl;hpj;bat</Extensions>
+ </Filter>
+ <Filter Include="Header Files">
+ <UniqueIdentifier>{6a1287d5-359d-4ecb-a1a8-79aec14ad46d}</UniqueIdentifier>
+ <Extensions>h;hpp;hxx;hm;inl</Extensions>
+ </Filter>
+ <Filter Include="Resource Files">
+ <UniqueIdentifier>{75f72e18-16a8-453e-84bc-fe9301b8d5b2}</UniqueIdentifier>
+ <Extensions>ico;cur;bmp;dlg;rc2;rct;bin;rgs;gif;jpg;jpeg;jpe</Extensions>
+ </Filter>
+ </ItemGroup>
+ <ItemGroup>
+ <ClCompile Include="chardata.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="minicheck.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="memcheck.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="runtests.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="structdata.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ </ItemGroup>
+ <ItemGroup>
+ <ClInclude Include="chardata.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="minicheck.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="memcheck.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="structdata.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ </ItemGroup>
+</Project> \ No newline at end of file
diff --git a/tests/runtestspp.cpp b/tests/runtestspp.cpp
index c35dc58..fd3ceaa 100644
--- a/tests/runtestspp.cpp
+++ b/tests/runtestspp.cpp
@@ -1,6 +1,36 @@
-// C++ compilation harness for the test suite.
-//
-// This is used to ensure the Expat headers can be included from C++
-// and have everything work as expected.
-//
+/* C++ compilation harness for the test suite.
+
+ This is used to ensure the Expat headers can be included from C++
+ and have everything work as expected.
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
#include "runtests.c"
diff --git a/tests/structdata.c b/tests/structdata.c
new file mode 100644
index 0000000..22cb0eb
--- /dev/null
+++ b/tests/structdata.c
@@ -0,0 +1,162 @@
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+#ifdef HAVE_EXPAT_CONFIG_H
+# include "expat_config.h"
+#endif
+
+
+#include <assert.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+
+#include "structdata.h"
+#include "minicheck.h"
+
+#define STRUCT_EXTENSION_COUNT 8
+
+#ifdef XML_UNICODE_WCHAR_T
+# include <wchar.h>
+# define XML_FMT_STR "ls"
+# define xcstrlen(s) wcslen(s)
+# define xcstrcmp(s, t) wcscmp((s), (t))
+#else
+# define XML_FMT_STR "s"
+# define xcstrlen(s) strlen(s)
+# define xcstrcmp(s, t) strcmp((s), (t))
+#endif
+
+
+static XML_Char *
+xmlstrdup(const XML_Char *s)
+{
+ int byte_count = (xcstrlen(s) + 1) * sizeof(XML_Char);
+ XML_Char *dup = malloc(byte_count);
+
+ assert(dup != NULL);
+ memcpy(dup, s, byte_count);
+ return dup;
+}
+
+
+void
+StructData_Init(StructData *storage)
+{
+ assert(storage != NULL);
+ storage->count = 0;
+ storage->max_count = 0;
+ storage->entries = NULL;
+}
+
+void
+StructData_AddItem(StructData *storage,
+ const XML_Char *s,
+ int data0,
+ int data1,
+ int data2)
+{
+ StructDataEntry *entry;
+
+ assert(storage != NULL);
+ assert(s != NULL);
+ if (storage->count == storage->max_count) {
+ StructDataEntry *new;
+
+ storage->max_count += STRUCT_EXTENSION_COUNT;
+ new = realloc(storage->entries,
+ storage->max_count * sizeof(StructDataEntry));
+ assert(new != NULL);
+ storage->entries = new;
+ }
+
+ entry = &storage->entries[storage->count];
+ entry->str = xmlstrdup(s);
+ entry->data0 = data0;
+ entry->data1 = data1;
+ entry->data2 = data2;
+ storage->count++;
+}
+
+/* 'fail()' aborts the function via a longjmp, so there is no point
+ * in returning a value from this function.
+ */
+void
+StructData_CheckItems(StructData *storage,
+ const StructDataEntry *expected,
+ int count)
+{
+ char buffer[1024];
+ int i;
+
+ assert(storage != NULL);
+ assert(expected != NULL);
+ if (count != storage->count) {
+ sprintf(buffer, "wrong number of entries: got %d, expected %d",
+ storage->count, count);
+ StructData_Dispose(storage);
+ fail(buffer);
+ }
+ for (i = 0; i < count; i++)
+ {
+ const StructDataEntry *got = &storage->entries[i];
+ const StructDataEntry *want = &expected[i];
+
+ if (xcstrcmp(got->str, want->str) != 0) {
+ StructData_Dispose(storage);
+ fail("structure got bad string");
+ }
+ if (got->data0 != want->data0 ||
+ got->data1 != want->data1 ||
+ got->data2 != want->data2) {
+ sprintf(buffer,
+ "struct '%" XML_FMT_STR
+ "' expected (%d,%d,%d), got (%d,%d,%d)",
+ got->str,
+ want->data0, want->data1, want->data2,
+ got->data0, got->data1, got->data2);
+ StructData_Dispose(storage);
+ fail(buffer);
+ }
+ }
+}
+
+void
+StructData_Dispose(StructData *storage)
+{
+ int i;
+
+ assert(storage != NULL);
+ for (i = 0; i < storage->count; i++)
+ free((void *)storage->entries[i].str);
+ free(storage->entries);
+}
diff --git a/tests/structdata.h b/tests/structdata.h
new file mode 100644
index 0000000..19016a9
--- /dev/null
+++ b/tests/structdata.h
@@ -0,0 +1,76 @@
+/* Interface to some helper routines used to accumulate and check
+ structured content.
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifndef XML_STRUCTDATA_H
+#define XML_STRUCTDATA_H 1
+
+#include "expat.h"
+
+typedef struct {
+ const XML_Char *str;
+ int data0;
+ int data1;
+ int data2;
+} StructDataEntry;
+
+typedef struct {
+ int count; /* Number of entries used */
+ int max_count; /* Number of StructDataEntry items in `entries` */
+ StructDataEntry *entries;
+} StructData;
+
+
+void StructData_Init(StructData *storage);
+
+void StructData_AddItem(StructData *storage,
+ const XML_Char *s,
+ int data0,
+ int data1,
+ int data2);
+
+void StructData_CheckItems(StructData *storage,
+ const StructDataEntry *expected,
+ int count);
+
+void StructData_Dispose(StructData *storage);
+
+
+#endif /* XML_STRUCTDATA_H */
+
+#ifdef __cplusplus
+}
+#endif
diff --git a/tests/udiffer.py b/tests/udiffer.py
new file mode 100755
index 0000000..6fb91be
--- /dev/null
+++ b/tests/udiffer.py
@@ -0,0 +1,62 @@
+#! /usr/bin/env python3
+# __ __ _
+# ___\ \/ /_ __ __ _| |_
+# / _ \\ /| '_ \ / _` | __|
+# | __// \| |_) | (_| | |_
+# \___/_/\_\ .__/ \__,_|\__|
+# |_| XML parser
+#
+# Copyright (c) 2017 Expat development team
+# Licensed under the MIT license:
+#
+# Permission is hereby granted, free of charge, to any person obtaining
+# a copy of this software and associated documentation files (the
+# "Software"), to deal in the Software without restriction, including
+# without limitation the rights to use, copy, modify, merge, publish,
+# distribute, sublicense, and/or sell copies of the Software, and to permit
+# persons to whom the Software is furnished to do so, subject to the
+# following conditions:
+#
+# The above copyright notice and this permission notice shall be included
+# in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+# NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+# DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+# OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+# USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+import argparse
+import difflib
+import sys
+
+
+def _read_lines(filename):
+ try:
+ with open(filename) as f:
+ return f.readlines()
+ except UnicodeDecodeError:
+ with open(filename, encoding='utf_16') as f:
+ return f.readlines()
+
+
+def main():
+ parser = argparse.ArgumentParser()
+ parser.add_argument('first', metavar='FILE')
+ parser.add_argument('second', metavar='FILE')
+ config = parser.parse_args()
+
+ first = _read_lines(config.first)
+ second = _read_lines(config.second)
+
+ diffs = list(difflib.unified_diff(first, second, fromfile=config.first,
+ tofile=config.second))
+ if diffs:
+ sys.stdout.writelines(diffs)
+ sys.exit(1)
+
+
+if __name__ == '__main__':
+ main()
diff --git a/tests/xmltest.log.expected b/tests/xmltest.log.expected
new file mode 100644
index 0000000..032f546
--- /dev/null
+++ b/tests/xmltest.log.expected
@@ -0,0 +1,10 @@
+Output differs: ibm/valid/P02/ibm02v01.xml
+ibm49i02.dtd: No such file or directory
+Expected not well-formed: ibm/not-wf/misc/432gewf.xml
+Expected not well-formed: xmltest/not-wf/not-sa/005.xml
+Expected not well-formed: sun/not-wf/uri01.xml
+Expected not well-formed: oasis/p06fail1.xml
+Expected not well-formed: oasis/p08fail1.xml
+Expected not well-formed: oasis/p08fail2.xml
+Passed: 1801
+Failed: 8
diff --git a/tests/xmltest.sh b/tests/xmltest.sh
index 64a17ee..2b8cb19 100755
--- a/tests/xmltest.sh
+++ b/tests/xmltest.sh
@@ -25,12 +25,14 @@ shopt -s nullglob
MYDIR="`dirname \"$0\"`"
cd "$MYDIR"
MYDIR="`pwd`"
-XMLWF="`dirname \"$MYDIR\"`/xmlwf/xmlwf"
+XMLWF="${1:-`dirname \"$MYDIR\"`/xmlwf/xmlwf}"
# XMLWF=/usr/local/bin/xmlwf
TS="$MYDIR"
# OUTPUT must terminate with the directory separator.
OUTPUT="$TS/out/"
# OUTPUT=/home/tmp/xml-testsuite-out/
+# Unicode-aware diff utility
+DIFF="$TS/udiffer.py"
# RunXmlwfNotWF file reldir
@@ -53,11 +55,11 @@ RunXmlwfNotWF() {
RunXmlwfWF() {
file="$1"
reldir="$2"
- $XMLWF -p -d "$OUTPUT$reldir" "$file" > outfile || return $?
+ $XMLWF -p -N -d "$OUTPUT$reldir" "$file" > outfile || return $?
read outdata < outfile
if test "$outdata" = "" ; then
if [ -f "out/$file" ] ; then
- diff -u "$OUTPUT$reldir$file" "out/$file" > outfile
+ $DIFF "$OUTPUT$reldir$file" "out/$file" > outfile
if [ -s outfile ] ; then
cp outfile "$OUTPUT$reldir$file.diff"
echo "Output differs: $reldir$file"
@@ -98,7 +100,8 @@ for xmldir in ibm/valid/P* \
sun/invalid ; do
cd "$TS/xmlconf/$xmldir"
mkdir -p "$OUTPUT$xmldir"
- for xmlfile in *.xml ; do
+ for xmlfile in $(ls -1 *.xml | sort -d) ; do
+ [[ -f "$xmlfile" ]] || continue
RunXmlwfWF "$xmlfile" "$xmldir/"
UpdateStatus $?
done
diff --git a/win32/.gitignore b/win32/.gitignore
new file mode 100644
index 0000000..e754677
--- /dev/null
+++ b/win32/.gitignore
@@ -0,0 +1,10 @@
+expat.IAB
+expat.IAD
+expat.IMB
+expat.IMD
+expat.PFI
+expat.PO
+expat.PR
+expat.PRI
+expat.PS
+expat.WK3
diff --git a/win32/MANIFEST.txt b/win32/MANIFEST.txt
new file mode 100644
index 0000000..22b61d1
--- /dev/null
+++ b/win32/MANIFEST.txt
@@ -0,0 +1,25 @@
+ Overview of the Expat distribution
+
+The Expat distribution creates several subdirectories on your system.
+Some of these directories contain components of interest to all Expat
+users, and some contain material of interest to developers who wish to
+use Expat in their applications. In the list below, <top> is the
+directory you specified to the installer.
+
+ Directory Contents
+ ---------------------------------------------------------------------
+ <top>\ Some general information files.
+
+ <top>\Doc\ API documentation for developers.
+
+ <top>\Bin\ Pre-compiled dynamic libraries for developers.
+ Pre-compiled static libraries for developers (*MT.lib).
+ The XML well-formedness checker xmlwf.
+
+ <top>\Source\ Source code, which may interest some developers,
+ including a workspace for Microsft Visual C++.
+ The source code includes the parser, the well-
+ formedness checker, and a couple of small sample
+ applications.
+
+
diff --git a/win32/README.txt b/win32/README.txt
new file mode 100644
index 0000000..462c49b
--- /dev/null
+++ b/win32/README.txt
@@ -0,0 +1,75 @@
+
+Expat can be built on Windows in two ways:
+ using MS Visual Studio .NET or Cygwin.
+
+* Cygwin:
+ This follows the Unix build procedures.
+
+* MS Visual Studio 2013, 2015 and 2017:
+ A solution file for Visual Studio 2013 is provided: expat.sln.
+ The associated project files (*.vcxproj) reside in the appropriate
+ project directories. This solution file can be opened in VS 2015 or VS 2017
+ and should be upgraded automatically if VS 2013 is not also installed.
+ Note: Tests have their own solution files.
+
+* All MS C/C++ compilers:
+ The output for all projects will be generated in the win32\bin
+ directory, intermediate files will be located in project-specific
+ subdirectories of win32\tmp.
+
+* Creating MinGW dynamic libraries from MS VC++ DLLs:
+
+ On the command line, execute these steps:
+ pexports libexpat.dll > expat.def
+ pexports libexpatw.dll > expatw.def
+ dlltool -d expat.def -l libexpat.a
+ dlltool -d expatw.def -l libexpatw.a
+
+ The *.a files are mingw libraries.
+
+* Special note about MS VC++ and runtime libraries:
+
+ There are three possible configurations: using the
+ single threaded or multithreaded run-time library,
+ or using the multi-threaded run-time Dll. That is,
+ one can build three different Expat libraries depending
+ on the needs of the application.
+
+ Dynamic Linking:
+
+ By default the Expat Dlls are built to link statically
+ with the multi-threaded run-time library.
+ The libraries are named
+ - libexpat(w).dll
+ - libexpat(w).lib (import library)
+ The "w" indicates the UTF-16 version of the library.
+
+ One rarely uses other versions of the Dll, but they can
+ be built easily by specifying a different RTL linkage in
+ the IDE on the C/C++ tab under the category Code Generation.
+
+ Static Linking:
+
+ The libraries should be named like this:
+ Single-theaded: libexpat(w)ML.lib
+ Multi-threaded: libexpat(w)MT.lib
+ Multi-threaded Dll: libexpat(w)MD.lib
+ The suffixes conform to the compiler switch settings
+ /ML, /MT and /MD for MS VC++.
+
+ Note: In Visual Studio 2005 (Visual C++ 8.0) and later, the
+ single-threaded runtime library is not supported anymore.
+
+ By default, the expat-static and expatw-static projects are set up
+ to link statically against the multithreaded run-time library,
+ so they will build libexpatMT.lib or libexpatwMT.lib files.
+
+ To build the other versions of the static library,
+ go to Project - Settings:
+ - specify a different RTL linkage on the C/C++ tab
+ under the category Code Generation.
+ - then, on the Library tab, change the output file name
+ accordingly, as described above
+
+ An application linking to the static libraries must
+ have the global macro XML_STATIC defined.
diff --git a/win32/expat.iss b/win32/expat.iss
new file mode 100644
index 0000000..6168cf7
--- /dev/null
+++ b/win32/expat.iss
@@ -0,0 +1,75 @@
+; Basic setup script for the Inno Setup installer builder. For more
+; information on the free installer builder, see www.jrsoftware.org.
+;
+; This script was contributed by Tim Peters.
+; It was designed for Inno Setup 2.0.19 but works with later versions as well.
+
+#define expatVer "2.2.5"
+
+[Setup]
+AppName=Expat
+AppId=expat
+AppVersion={#expatVer}
+AppVerName=Expat {#expatVer}
+AppCopyright=Copyright © 1998-2017 Thai Open Source Software Center, Clark Cooper, and the Expat maintainers
+AppPublisher=The Expat Developers
+AppPublisherURL=http://www.libexpat.org/
+AppSupportURL=http://www.libexpat.org/
+AppUpdatesURL=http://www.libexpat.org/
+UninstallDisplayName=Expat XML Parser {#expatVer}
+VersionInfoVersion={#expatVer}
+OutputBaseFilename=expat-win32bin-{#expatVer}
+
+DefaultDirName={pf}\Expat {#expatVer}
+UninstallFilesDir={app}\Uninstall
+
+Compression=lzma
+SolidCompression=yes
+SourceDir=..
+OutputDir=win32
+DisableStartupPrompt=yes
+AllowNoIcons=yes
+DisableProgramGroupPage=yes
+DisableReadyPage=yes
+
+[Files]
+Flags: ignoreversion; Source: win32\bin\Release\xmlwf.exe; DestDir: "{app}\Bin"
+Flags: ignoreversion; Source: win32\MANIFEST.txt; DestDir: "{app}"
+Flags: ignoreversion; Source: AUTHORS; DestDir: "{app}"; DestName: AUTHORS.txt
+Flags: ignoreversion; Source: Changes; DestDir: "{app}"; DestName: Changes.txt
+Flags: ignoreversion; Source: COPYING; DestDir: "{app}"; DestName: COPYING.txt
+Flags: ignoreversion; Source: README.md; DestDir: "{app}"; DestName: README.txt
+Flags: ignoreversion; Source: doc\*.html; DestDir: "{app}\Doc"
+Flags: ignoreversion; Source: doc\*.css; DestDir: "{app}\Doc"
+Flags: ignoreversion; Source: doc\*.png; DestDir: "{app}\Doc"
+Flags: ignoreversion; Source: win32\bin\Release\*.dll; DestDir: "{app}\Bin"
+Flags: ignoreversion; Source: win32\bin\Release\*.lib; DestDir: "{app}\Bin"
+Flags: ignoreversion; Source: expat.sln; DestDir: "{app}\Source"
+Flags: ignoreversion; Source: win32\README.txt; DestDir: "{app}\Source"
+Flags: ignoreversion; Source: lib\*.c; DestDir: "{app}\Source\lib"
+Flags: ignoreversion; Source: lib\*.h; DestDir: "{app}\Source\lib"
+Flags: ignoreversion; Source: lib\*.def; DestDir: "{app}\Source\lib"
+Flags: ignoreversion; Source: lib\*.vcxproj; DestDir: "{app}\Source\lib"
+Flags: ignoreversion; Source: lib\*.vcxproj.filters; DestDir: "{app}\Source\lib"
+Flags: ignoreversion; Source: examples\*.c; DestDir: "{app}\Source\examples"
+Flags: ignoreversion; Source: examples\*.vcxproj; DestDir: "{app}\Source\examples"
+Flags: ignoreversion; Source: examples\*.vcxproj.filters; DestDir: "{app}\Source\examples"
+Flags: ignoreversion; Source: tests\*.c; DestDir: "{app}\Source\tests"
+Flags: ignoreversion; Source: tests\*.cpp; DestDir: "{app}\Source\tests"
+Flags: ignoreversion; Source: tests\*.h; DestDir: "{app}\Source\tests"
+Flags: ignoreversion; Source: tests\*.sln; DestDir: "{app}\Source\tests"
+Flags: ignoreversion; Source: tests\*.vcxproj; DestDir: "{app}\Source\tests"
+Flags: ignoreversion; Source: tests\*.vcxproj.filters; DestDir: "{app}\Source\tests"
+Flags: ignoreversion; Source: tests\README.txt; DestDir: "{app}\Source\tests"
+Flags: ignoreversion; Source: tests\benchmark\*.c; DestDir: "{app}\Source\tests\benchmark"
+Flags: ignoreversion; Source: tests\benchmark\*.sln; DestDir: "{app}\Source\tests\benchmark"
+Flags: ignoreversion; Source: tests\benchmark\*.vcxproj; DestDir: "{app}\Source\tests\benchmark"
+Flags: ignoreversion; Source: tests\benchmark\README.txt; DestDir: "{app}\Source\tests\benchmark"
+Flags: ignoreversion; Source: xmlwf\*.c*; DestDir: "{app}\Source\xmlwf"
+Flags: ignoreversion; Source: xmlwf\*.h; DestDir: "{app}\Source\xmlwf"
+Flags: ignoreversion; Source: xmlwf\*.vcxproj; DestDir: "{app}\Source\xmlwf"
+Flags: ignoreversion; Source: xmlwf\*.vcxproj.filters; DestDir: "{app}\Source\xmlwf"
+
+[Messages]
+WelcomeLabel1=Welcome to the Expat XML Parser Setup Wizard
+WelcomeLabel2=This will install [name/ver] on your computer.%n%nExpat is an XML parser with a C-language API, and is primarily made available to allow developers to build applications which use XML using a portable API and fast implementation.%n%nIt is strongly recommended that you close all other applications you have running before continuing. This will help prevent any conflicts during the installation process.
diff --git a/xmlwf/.gitignore b/xmlwf/.gitignore
new file mode 100755
index 0000000..90464b4
--- /dev/null
+++ b/xmlwf/.gitignore
@@ -0,0 +1,6 @@
+Debug
+Release
+xmlwf.plg
+Makefile
+xmlwf
+.libs
diff --git a/xmlwf/Makefile.am b/xmlwf/Makefile.am
new file mode 100644
index 0000000..ff46090
--- /dev/null
+++ b/xmlwf/Makefile.am
@@ -0,0 +1,61 @@
+#
+# __ __ _
+# ___\ \/ /_ __ __ _| |_
+# / _ \\ /| '_ \ / _` | __|
+# | __// \| |_) | (_| | |_
+# \___/_/\_\ .__/ \__,_|\__|
+# |_| XML parser
+#
+# Copyright (c) 2017 Expat development team
+# Licensed under the MIT license:
+#
+# Permission is hereby granted, free of charge, to any person obtaining
+# a copy of this software and associated documentation files (the
+# "Software"), to deal in the Software without restriction, including
+# without limitation the rights to use, copy, modify, merge, publish,
+# distribute, sublicense, and/or sell copies of the Software, and to permit
+# persons to whom the Software is furnished to do so, subject to the
+# following conditions:
+#
+# The above copyright notice and this permission notice shall be included
+# in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+# NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+# DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+# OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+# USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+bin_PROGRAMS = xmlwf
+
+xmlwf_LDADD = ../lib/libexpat.la
+xmlwf_SOURCES = \
+ xmlwf.c \
+ xmlfile.c \
+ codepage.c \
+ @FILEMAP@.c
+
+xmlwf_CPPFLAGS = -I$(srcdir)/../lib
+
+if MINGW
+if UNICODE
+xmlwf_CPPFLAGS += -mwindows
+xmlwf_LDFLAGS = -municode
+endif
+endif
+
+EXTRA_DIST = \
+ codepage.h \
+ ct.c \
+ filemap.h \
+ readfilemap.c \
+ unixfilemap.c \
+ win32filemap.c \
+ xmlfile.h \
+ xmlmime.c \
+ xmlmime.h \
+ xmltchar.h \
+ xmlurl.h \
+ xmlwin32url.cxx
diff --git a/xmlwf/codepage.c b/xmlwf/codepage.c
new file mode 100644
index 0000000..1a0487f
--- /dev/null
+++ b/xmlwf/codepage.c
@@ -0,0 +1,97 @@
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+#include "codepage.h"
+#include "internal.h" /* for UNUSED_P only */
+
+#if defined(_WIN32)
+#define STRICT 1
+#define WIN32_LEAN_AND_MEAN 1
+
+#include <windows.h>
+
+int
+codepageMap(int cp, int *map)
+{
+ int i;
+ CPINFO info;
+ if (!GetCPInfo(cp, &info) || info.MaxCharSize > 2)
+ return 0;
+ for (i = 0; i < 256; i++)
+ map[i] = -1;
+ if (info.MaxCharSize > 1) {
+ for (i = 0; i < MAX_LEADBYTES; i+=2) {
+ int j, lim;
+ if (info.LeadByte[i] == 0 && info.LeadByte[i + 1] == 0)
+ break;
+ lim = info.LeadByte[i + 1];
+ for (j = info.LeadByte[i]; j <= lim; j++)
+ map[j] = -2;
+ }
+ }
+ for (i = 0; i < 256; i++) {
+ if (map[i] == -1) {
+ char c = (char)i;
+ unsigned short n;
+ if (MultiByteToWideChar(cp, MB_PRECOMPOSED|MB_ERR_INVALID_CHARS,
+ &c, 1, &n, 1) == 1)
+ map[i] = n;
+ }
+ }
+ return 1;
+}
+
+int
+codepageConvert(int cp, const char *p)
+{
+ unsigned short c;
+ if (MultiByteToWideChar(cp, MB_PRECOMPOSED|MB_ERR_INVALID_CHARS,
+ p, 2, &c, 1) == 1)
+ return c;
+ return -1;
+}
+
+#else /* not _WIN32 */
+
+int
+codepageMap(int UNUSED_P(cp), int *UNUSED_P(map))
+{
+ return 0;
+}
+
+int
+codepageConvert(int UNUSED_P(cp), const char *UNUSED_P(p))
+{
+ return -1;
+}
+
+#endif /* not _WIN32 */
diff --git a/xmlwf/codepage.h b/xmlwf/codepage.h
new file mode 100644
index 0000000..1b75d58
--- /dev/null
+++ b/xmlwf/codepage.h
@@ -0,0 +1,34 @@
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+int codepageMap(int cp, int *map);
+int codepageConvert(int cp, const char *p);
diff --git a/xmlwf/ct.c b/xmlwf/ct.c
new file mode 100644
index 0000000..dd42f5e
--- /dev/null
+++ b/xmlwf/ct.c
@@ -0,0 +1,179 @@
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+#define CHARSET_MAX 41
+
+static const char *
+getTok(const char **pp)
+{
+ enum { inAtom, inString, init, inComment };
+ int state = init;
+ const char *tokStart = 0;
+ for (;;) {
+ switch (**pp) {
+ case '\0':
+ return 0;
+ case ' ':
+ case '\r':
+ case '\t':
+ case '\n':
+ if (state == inAtom)
+ return tokStart;
+ break;
+ case '(':
+ if (state == inAtom)
+ return tokStart;
+ if (state != inString)
+ state++;
+ break;
+ case ')':
+ if (state > init)
+ --state;
+ else if (state != inString)
+ return 0;
+ break;
+ case ';':
+ case '/':
+ case '=':
+ if (state == inAtom)
+ return tokStart;
+ if (state == init)
+ return (*pp)++;
+ break;
+ case '\\':
+ ++*pp;
+ if (**pp == '\0')
+ return 0;
+ break;
+ case '"':
+ switch (state) {
+ case inString:
+ ++*pp;
+ return tokStart;
+ case inAtom:
+ return tokStart;
+ case init:
+ tokStart = *pp;
+ state = inString;
+ break;
+ }
+ break;
+ default:
+ if (state == init) {
+ tokStart = *pp;
+ state = inAtom;
+ }
+ break;
+ }
+ ++*pp;
+ }
+ /* not reached */
+}
+
+/* key must be lowercase ASCII */
+
+static int
+matchkey(const char *start, const char *end, const char *key)
+{
+ if (!start)
+ return 0;
+ for (; start != end; start++, key++)
+ if (*start != *key && *start != 'A' + (*key - 'a'))
+ return 0;
+ return *key == '\0';
+}
+
+void
+getXMLCharset(const char *buf, char *charset)
+{
+ const char *next, *p;
+
+ charset[0] = '\0';
+ next = buf;
+ p = getTok(&next);
+ if (matchkey(p, next, "text"))
+ strcpy(charset, "us-ascii");
+ else if (!matchkey(p, next, "application"))
+ return;
+ p = getTok(&next);
+ if (!p || *p != '/')
+ return;
+ p = getTok(&next);
+ if (matchkey(p, next, "xml"))
+ isXml = 1;
+ p = getTok(&next);
+ while (p) {
+ if (*p == ';') {
+ p = getTok(&next);
+ if (matchkey(p, next, "charset")) {
+ p = getTok(&next);
+ if (p && *p == '=') {
+ p = getTok(&next);
+ if (p) {
+ char *s = charset;
+ if (*p == '"') {
+ while (++p != next - 1) {
+ if (*p == '\\')
+ ++p;
+ if (s == charset + CHARSET_MAX - 1) {
+ charset[0] = '\0';
+ break;
+ }
+ *s++ = *p;
+ }
+ *s++ = '\0';
+ }
+ else {
+ if (next - p > CHARSET_MAX - 1)
+ break;
+ while (p != next)
+ *s++ = *p++;
+ *s = 0;
+ break;
+ }
+ }
+ }
+ }
+ }
+ else
+ p = getTok(&next);
+ }
+}
+
+int
+main(int argc, char **argv)
+{
+ char buf[CHARSET_MAX];
+ getXMLCharset(argv[1], buf);
+ printf("charset = \"%s\"\n", buf);
+ return 0;
+}
diff --git a/xmlwf/filemap.h b/xmlwf/filemap.h
new file mode 100644
index 0000000..5487a4e
--- /dev/null
+++ b/xmlwf/filemap.h
@@ -0,0 +1,57 @@
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+#include <limits.h> /* INT_MAX */
+#include <stddef.h>
+
+
+/* The following limit (for XML_Parse's int len) derives from
+ * this loop in xmparse.c:
+ *
+ * do {
+ * bufferSize = (int) (2U * (unsigned) bufferSize);
+ * } while (bufferSize < neededSize && bufferSize > 0);
+ */
+#define XML_MAX_CHUNK_LEN (INT_MAX / 2 + 1)
+
+
+#ifdef XML_UNICODE
+int filemap(const wchar_t *name,
+ void (*processor)(const void *, size_t,
+ const wchar_t *, void *arg),
+ void *arg);
+#else
+int filemap(const char *name,
+ void (*processor)(const void *, size_t,
+ const char *, void *arg),
+ void *arg);
+#endif
diff --git a/xmlwf/readfilemap.c b/xmlwf/readfilemap.c
new file mode 100644
index 0000000..3cc4f76
--- /dev/null
+++ b/xmlwf/readfilemap.c
@@ -0,0 +1,138 @@
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <stdlib.h>
+#include <stdio.h>
+
+/* Functions close(2) and read(2) */
+#if !defined(_WIN32) && !defined(_WIN64)
+# include <unistd.h>
+#endif
+
+/* Function "read": */
+#if defined(_MSC_VER)
+ /* https://msdn.microsoft.com/en-us/library/wyssk1bs(v=vs.100).aspx */
+# define _EXPAT_read _read
+# define _EXPAT_read_count_t int
+#else /* POSIX */
+ /* http://pubs.opengroup.org/onlinepubs/009695399/functions/read.html */
+# define _EXPAT_read read
+# define _EXPAT_read_count_t ssize_t
+#endif
+
+#ifndef S_ISREG
+# ifndef S_IFREG
+# define S_IFREG _S_IFREG
+# endif
+# ifndef S_IFMT
+# define S_IFMT _S_IFMT
+# endif
+# define S_ISREG(m) (((m) & S_IFMT) == S_IFREG)
+#endif /* not S_ISREG */
+
+#ifndef O_BINARY
+# ifdef _O_BINARY
+# define O_BINARY _O_BINARY
+# else
+# define O_BINARY 0
+# endif
+#endif
+
+#include "xmltchar.h"
+#include "filemap.h"
+
+int
+filemap(const tchar *name,
+ void (*processor)(const void *, size_t, const tchar *, void *arg),
+ void *arg)
+{
+ size_t nbytes;
+ int fd;
+ _EXPAT_read_count_t n;
+ struct stat sb;
+ void *p;
+
+ fd = topen(name, O_RDONLY|O_BINARY);
+ if (fd < 0) {
+ tperror(name);
+ return 0;
+ }
+ if (fstat(fd, &sb) < 0) {
+ tperror(name);
+ close(fd);
+ return 0;
+ }
+ if (!S_ISREG(sb.st_mode)) {
+ ftprintf(stderr, T("%s: not a regular file\n"), name);
+ close(fd);
+ return 0;
+ }
+ if (sb.st_size > XML_MAX_CHUNK_LEN) {
+ close(fd);
+ return 2; /* Cannot be passed to XML_Parse in one go */
+ }
+
+ nbytes = sb.st_size;
+ /* malloc will return NULL with nbytes == 0, handle files with size 0 */
+ if (nbytes == 0) {
+ static const char c = '\0';
+ processor(&c, 0, name, arg);
+ close(fd);
+ return 1;
+ }
+ p = malloc(nbytes);
+ if (!p) {
+ ftprintf(stderr, T("%s: out of memory\n"), name);
+ close(fd);
+ return 0;
+ }
+ n = _EXPAT_read(fd, p, nbytes);
+ if (n < 0) {
+ tperror(name);
+ free(p);
+ close(fd);
+ return 0;
+ }
+ if (n != (_EXPAT_read_count_t)nbytes) {
+ ftprintf(stderr, T("%s: read unexpected number of bytes\n"), name);
+ free(p);
+ close(fd);
+ return 0;
+ }
+ processor(p, nbytes, name, arg);
+ free(p);
+ close(fd);
+ return 1;
+}
diff --git a/xmlwf/unixfilemap.c b/xmlwf/unixfilemap.c
new file mode 100644
index 0000000..4ab757c
--- /dev/null
+++ b/xmlwf/unixfilemap.c
@@ -0,0 +1,104 @@
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+#include <sys/types.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <string.h>
+#include <stdio.h>
+#include <unistd.h>
+
+#ifndef MAP_FILE
+#define MAP_FILE 0
+#endif
+
+#include "xmltchar.h"
+#include "filemap.h"
+
+#ifdef XML_UNICODE_WCHAR_T
+# define XML_FMT_STR "ls"
+#else
+# define XML_FMT_STR "s"
+#endif
+
+int
+filemap(const tchar *name,
+ void (*processor)(const void *, size_t, const tchar *, void *arg),
+ void *arg)
+{
+ int fd;
+ size_t nbytes;
+ struct stat sb;
+ void *p;
+
+ fd = topen(name, O_RDONLY);
+ if (fd < 0) {
+ tperror(name);
+ return 0;
+ }
+ if (fstat(fd, &sb) < 0) {
+ tperror(name);
+ close(fd);
+ return 0;
+ }
+ if (!S_ISREG(sb.st_mode)) {
+ close(fd);
+ fprintf(stderr, "%" XML_FMT_STR ": not a regular file\n", name);
+ return 0;
+ }
+ if (sb.st_size > XML_MAX_CHUNK_LEN) {
+ close(fd);
+ return 2; /* Cannot be passed to XML_Parse in one go */
+ }
+
+ nbytes = sb.st_size;
+ /* mmap fails for zero length files */
+ if (nbytes == 0) {
+ static const char c = '\0';
+ processor(&c, 0, name, arg);
+ close(fd);
+ return 1;
+ }
+ p = (void *)mmap((void *)0, (size_t)nbytes, PROT_READ,
+ MAP_FILE|MAP_PRIVATE, fd, (off_t)0);
+ if (p == (void *)-1) {
+ tperror(name);
+ close(fd);
+ return 0;
+ }
+ processor(p, nbytes, name, arg);
+ munmap((void *)p, nbytes);
+ close(fd);
+ return 1;
+}
diff --git a/xmlwf/win32filemap.c b/xmlwf/win32filemap.c
new file mode 100644
index 0000000..a040a09
--- /dev/null
+++ b/xmlwf/win32filemap.c
@@ -0,0 +1,125 @@
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+#define STRICT 1
+#define WIN32_LEAN_AND_MEAN 1
+
+#ifdef XML_UNICODE_WCHAR_T
+# ifndef XML_UNICODE
+# define XML_UNICODE
+# endif
+#endif
+
+#ifdef XML_UNICODE
+# define UNICODE
+# define _UNICODE
+#endif /* XML_UNICODE */
+#include <windows.h>
+#include <stdio.h>
+#include <tchar.h>
+#include "filemap.h"
+
+static void win32perror(const TCHAR *);
+
+int
+filemap(const TCHAR *name,
+ void (*processor)(const void *, size_t, const TCHAR *, void *arg),
+ void *arg)
+{
+ HANDLE f;
+ HANDLE m;
+ DWORD size;
+ DWORD sizeHi;
+ void *p;
+
+ f = CreateFile(name, GENERIC_READ, FILE_SHARE_READ, NULL, OPEN_EXISTING,
+ FILE_FLAG_SEQUENTIAL_SCAN, NULL);
+ if (f == INVALID_HANDLE_VALUE) {
+ win32perror(name);
+ return 0;
+ }
+ size = GetFileSize(f, &sizeHi);
+ if (size == (DWORD)-1) {
+ win32perror(name);
+ CloseHandle(f);
+ return 0;
+ }
+ if (sizeHi || (size > XML_MAX_CHUNK_LEN)) {
+ CloseHandle(f);
+ return 2; /* Cannot be passed to XML_Parse in one go */
+ }
+ /* CreateFileMapping barfs on zero length files */
+ if (size == 0) {
+ static const char c = '\0';
+ processor(&c, 0, name, arg);
+ CloseHandle(f);
+ return 1;
+ }
+ m = CreateFileMapping(f, NULL, PAGE_READONLY, 0, 0, NULL);
+ if (m == NULL) {
+ win32perror(name);
+ CloseHandle(f);
+ return 0;
+ }
+ p = MapViewOfFile(m, FILE_MAP_READ, 0, 0, 0);
+ if (p == NULL) {
+ win32perror(name);
+ CloseHandle(m);
+ CloseHandle(f);
+ return 0;
+ }
+ processor(p, size, name, arg);
+ UnmapViewOfFile(p);
+ CloseHandle(m);
+ CloseHandle(f);
+ return 1;
+}
+
+static void
+win32perror(const TCHAR *s)
+{
+ LPVOID buf;
+ if (FormatMessage(FORMAT_MESSAGE_ALLOCATE_BUFFER
+ | FORMAT_MESSAGE_FROM_SYSTEM,
+ NULL,
+ GetLastError(),
+ MAKELANGID(LANG_NEUTRAL, SUBLANG_DEFAULT),
+ (LPTSTR) &buf,
+ 0,
+ NULL)) {
+ _ftprintf(stderr, _T("%s: %s"), s, buf);
+ fflush(stderr);
+ LocalFree(buf);
+ }
+ else
+ _ftprintf(stderr, _T("%s: unknown Windows error\n"), s);
+}
diff --git a/xmlwf/xmlfile.c b/xmlwf/xmlfile.c
new file mode 100644
index 0000000..4075f57
--- /dev/null
+++ b/xmlwf/xmlfile.c
@@ -0,0 +1,290 @@
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stddef.h>
+#include <string.h>
+#include <fcntl.h>
+
+#ifdef _WIN32
+#include "winconfig.h"
+#elif defined(HAVE_EXPAT_CONFIG_H)
+#include <expat_config.h>
+#endif /* ndef _WIN32 */
+
+#include "expat.h"
+#include "internal.h" /* for UNUSED_P only */
+#include "xmlfile.h"
+#include "xmltchar.h"
+#include "filemap.h"
+
+#if defined(_MSC_VER)
+#include <io.h>
+#endif
+
+#ifdef HAVE_UNISTD_H
+#include <unistd.h>
+#endif
+
+#ifndef O_BINARY
+#ifdef _O_BINARY
+#define O_BINARY _O_BINARY
+#else
+#define O_BINARY 0
+#endif
+#endif
+
+#ifdef _DEBUG
+#define READ_SIZE 16
+#else
+#define READ_SIZE (1024*8)
+#endif
+
+
+typedef struct {
+ XML_Parser parser;
+ int *retPtr;
+} PROCESS_ARGS;
+
+static int
+processStream(const XML_Char *filename, XML_Parser parser);
+
+static void
+reportError(XML_Parser parser, const XML_Char *filename)
+{
+ enum XML_Error code = XML_GetErrorCode(parser);
+ const XML_Char *message = XML_ErrorString(code);
+ if (message)
+ ftprintf(stdout,
+ T("%s")
+ T(":%") T(XML_FMT_INT_MOD) T("u")
+ T(":%") T(XML_FMT_INT_MOD) T("u")
+ T(": %s\n"),
+ filename,
+ XML_GetErrorLineNumber(parser),
+ XML_GetErrorColumnNumber(parser),
+ message);
+ else
+ ftprintf(stderr, T("%s: (unknown message %d)\n"), filename, code);
+}
+
+/* This implementation will give problems on files larger than INT_MAX. */
+static void
+processFile(const void *data, size_t size,
+ const XML_Char *filename, void *args)
+{
+ XML_Parser parser = ((PROCESS_ARGS *)args)->parser;
+ int *retPtr = ((PROCESS_ARGS *)args)->retPtr;
+ if (XML_Parse(parser, (const char *)data, (int)size, 1) == XML_STATUS_ERROR) {
+ reportError(parser, filename);
+ *retPtr = 0;
+ }
+ else
+ *retPtr = 1;
+}
+
+#if defined(_WIN32)
+
+static int
+isAsciiLetter(XML_Char c)
+{
+ return (T('a') <= c && c <= T('z')) || (T('A') <= c && c <= T('Z'));
+}
+
+#endif /* _WIN32 */
+
+static const XML_Char *
+resolveSystemId(const XML_Char *base, const XML_Char *systemId,
+ XML_Char **toFree)
+{
+ XML_Char *s;
+ *toFree = 0;
+ if (!base
+ || *systemId == T('/')
+#if defined(_WIN32)
+ || *systemId == T('\\')
+ || (isAsciiLetter(systemId[0]) && systemId[1] == T(':'))
+#endif
+ )
+ return systemId;
+ *toFree = (XML_Char *)malloc((tcslen(base) + tcslen(systemId) + 2)
+ * sizeof(XML_Char));
+ if (!*toFree)
+ return systemId;
+ tcscpy(*toFree, base);
+ s = *toFree;
+ if (tcsrchr(s, T('/')))
+ s = tcsrchr(s, T('/')) + 1;
+#if defined(_WIN32)
+ if (tcsrchr(s, T('\\')))
+ s = tcsrchr(s, T('\\')) + 1;
+#endif
+ tcscpy(s, systemId);
+ return *toFree;
+}
+
+static int
+externalEntityRefFilemap(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *base,
+ const XML_Char *systemId,
+ const XML_Char *UNUSED_P(publicId))
+{
+ int result;
+ XML_Char *s;
+ const XML_Char *filename;
+ XML_Parser entParser = XML_ExternalEntityParserCreate(parser, context, 0);
+ int filemapRes;
+ PROCESS_ARGS args;
+ args.retPtr = &result;
+ args.parser = entParser;
+ filename = resolveSystemId(base, systemId, &s);
+ XML_SetBase(entParser, filename);
+ filemapRes = filemap(filename, processFile, &args);
+ switch (filemapRes) {
+ case 0:
+ result = 0;
+ break;
+ case 2:
+ ftprintf(stderr, T("%s: file too large for memory-mapping")
+ T(", switching to streaming\n"), filename);
+ result = processStream(filename, entParser);
+ break;
+ }
+ free(s);
+ XML_ParserFree(entParser);
+ return result;
+}
+
+static int
+processStream(const XML_Char *filename, XML_Parser parser)
+{
+ /* passing NULL for filename means read intput from stdin */
+ int fd = 0; /* 0 is the fileno for stdin */
+
+ if (filename != NULL) {
+ fd = topen(filename, O_BINARY|O_RDONLY);
+ if (fd < 0) {
+ tperror(filename);
+ return 0;
+ }
+ }
+ for (;;) {
+ int nread;
+ char *buf = (char *)XML_GetBuffer(parser, READ_SIZE);
+ if (!buf) {
+ if (filename != NULL)
+ close(fd);
+ ftprintf(stderr, T("%s: out of memory\n"),
+ filename != NULL ? filename : T("xmlwf"));
+ return 0;
+ }
+ nread = read(fd, buf, READ_SIZE);
+ if (nread < 0) {
+ tperror(filename != NULL ? filename : T("STDIN"));
+ if (filename != NULL)
+ close(fd);
+ return 0;
+ }
+ if (XML_ParseBuffer(parser, nread, nread == 0) == XML_STATUS_ERROR) {
+ reportError(parser, filename != NULL ? filename : T("STDIN"));
+ if (filename != NULL)
+ close(fd);
+ return 0;
+ }
+ if (nread == 0) {
+ if (filename != NULL)
+ close(fd);
+ break;;
+ }
+ }
+ return 1;
+}
+
+static int
+externalEntityRefStream(XML_Parser parser,
+ const XML_Char *context,
+ const XML_Char *base,
+ const XML_Char *systemId,
+ const XML_Char *UNUSED_P(publicId))
+{
+ XML_Char *s;
+ const XML_Char *filename;
+ int ret;
+ XML_Parser entParser = XML_ExternalEntityParserCreate(parser, context, 0);
+ filename = resolveSystemId(base, systemId, &s);
+ XML_SetBase(entParser, filename);
+ ret = processStream(filename, entParser);
+ free(s);
+ XML_ParserFree(entParser);
+ return ret;
+}
+
+int
+XML_ProcessFile(XML_Parser parser,
+ const XML_Char *filename,
+ unsigned flags)
+{
+ int result;
+
+ if (!XML_SetBase(parser, filename)) {
+ ftprintf(stderr, T("%s: out of memory"), filename);
+ exit(1);
+ }
+
+ if (flags & XML_EXTERNAL_ENTITIES)
+ XML_SetExternalEntityRefHandler(parser,
+ (flags & XML_MAP_FILE)
+ ? externalEntityRefFilemap
+ : externalEntityRefStream);
+ if (flags & XML_MAP_FILE) {
+ int filemapRes;
+ PROCESS_ARGS args;
+ args.retPtr = &result;
+ args.parser = parser;
+ filemapRes = filemap(filename, processFile, &args);
+ switch (filemapRes) {
+ case 0:
+ result = 0;
+ break;
+ case 2:
+ ftprintf(stderr, T("%s: file too large for memory-mapping")
+ T(", switching to streaming\n"), filename);
+ result = processStream(filename, parser);
+ break;
+ }
+ }
+ else
+ result = processStream(filename, parser);
+ return result;
+}
diff --git a/xmlwf/xmlfile.h b/xmlwf/xmlfile.h
new file mode 100644
index 0000000..c47ea2c
--- /dev/null
+++ b/xmlwf/xmlfile.h
@@ -0,0 +1,48 @@
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+#define XML_MAP_FILE 01
+#define XML_EXTERNAL_ENTITIES 02
+
+#ifdef XML_LARGE_SIZE
+#if defined(XML_USE_MSC_EXTENSIONS) && _MSC_VER < 1400
+#define XML_FMT_INT_MOD "I64"
+#else
+#define XML_FMT_INT_MOD "ll"
+#endif
+#else
+#define XML_FMT_INT_MOD "l"
+#endif
+
+extern int XML_ProcessFile(XML_Parser parser,
+ const XML_Char *filename,
+ unsigned flags);
diff --git a/xmlwf/xmlmime.c b/xmlwf/xmlmime.c
new file mode 100644
index 0000000..c530979
--- /dev/null
+++ b/xmlwf/xmlmime.c
@@ -0,0 +1,195 @@
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+#include <string.h>
+#include "xmlmime.h"
+
+static const char *
+getTok(const char **pp)
+{
+ /* inComment means one level of nesting; inComment+1 means two levels etc */
+ enum { inAtom, inString, init, inComment };
+ int state = init;
+ const char *tokStart = 0;
+ for (;;) {
+ switch (**pp) {
+ case '\0':
+ if (state == inAtom)
+ return tokStart;
+ return 0;
+ case ' ':
+ case '\r':
+ case '\t':
+ case '\n':
+ if (state == inAtom)
+ return tokStart;
+ break;
+ case '(':
+ if (state == inAtom)
+ return tokStart;
+ if (state != inString)
+ state++;
+ break;
+ case ')':
+ if (state > init)
+ --state;
+ else if (state != inString)
+ return 0;
+ break;
+ case ';':
+ case '/':
+ case '=':
+ if (state == inAtom)
+ return tokStart;
+ if (state == init)
+ return (*pp)++;
+ break;
+ case '\\':
+ ++*pp;
+ if (**pp == '\0')
+ return 0;
+ break;
+ case '"':
+ switch (state) {
+ case inString:
+ ++*pp;
+ return tokStart;
+ case inAtom:
+ return tokStart;
+ case init:
+ tokStart = *pp;
+ state = inString;
+ break;
+ }
+ break;
+ default:
+ if (state == init) {
+ tokStart = *pp;
+ state = inAtom;
+ }
+ break;
+ }
+ ++*pp;
+ }
+ /* not reached */
+}
+
+/* key must be lowercase ASCII */
+
+static int
+matchkey(const char *start, const char *end, const char *key)
+{
+ if (!start)
+ return 0;
+ for (; start != end; start++, key++)
+ if (*start != *key && *start != 'A' + (*key - 'a'))
+ return 0;
+ return *key == '\0';
+}
+
+void
+getXMLCharset(const char *buf, char *charset)
+{
+ const char *next, *p;
+
+ charset[0] = '\0';
+ next = buf;
+ p = getTok(&next);
+ if (matchkey(p, next, "text"))
+ strcpy(charset, "us-ascii");
+ else if (!matchkey(p, next, "application"))
+ return;
+ p = getTok(&next);
+ if (!p || *p != '/')
+ return;
+ p = getTok(&next);
+#if 0
+ if (!matchkey(p, next, "xml") && charset[0] == '\0')
+ return;
+#endif
+ p = getTok(&next);
+ while (p) {
+ if (*p == ';') {
+ p = getTok(&next);
+ if (matchkey(p, next, "charset")) {
+ p = getTok(&next);
+ if (p && *p == '=') {
+ p = getTok(&next);
+ if (p) {
+ char *s = charset;
+ if (*p == '"') {
+ while (++p != next - 1) {
+ if (*p == '\\')
+ ++p;
+ if (s == charset + CHARSET_MAX - 1) {
+ charset[0] = '\0';
+ break;
+ }
+ *s++ = *p;
+ }
+ *s++ = '\0';
+ }
+ else {
+ if (next - p > CHARSET_MAX - 1)
+ break;
+ while (p != next)
+ *s++ = *p++;
+ *s = 0;
+ break;
+ }
+ }
+ }
+ break;
+ }
+ }
+ else
+ p = getTok(&next);
+ }
+}
+
+#ifdef TEST
+
+#include <stdio.h>
+
+int
+main(int argc, char *argv[])
+{
+ char buf[CHARSET_MAX];
+ if (argc <= 1)
+ return 1;
+ printf("%s\n", argv[1]);
+ getXMLCharset(argv[1], buf);
+ printf("charset=\"%s\"\n", buf);
+ return 0;
+}
+
+#endif /* TEST */
diff --git a/xmlwf/xmlmime.h b/xmlwf/xmlmime.h
new file mode 100644
index 0000000..0471286
--- /dev/null
+++ b/xmlwf/xmlmime.h
@@ -0,0 +1,51 @@
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Registered charset names are at most 40 characters long. */
+
+#define CHARSET_MAX 41
+
+/* Figure out the charset to use from the ContentType.
+ buf contains the body of the header field (the part after "Content-Type:").
+ charset gets the charset to use. It must be at least CHARSET_MAX chars
+ long. charset will be empty if the default charset should be used.
+*/
+
+void getXMLCharset(const char *buf, char *charset);
+
+#ifdef __cplusplus
+}
+#endif
diff --git a/xmlwf/xmltchar.h b/xmlwf/xmltchar.h
new file mode 100644
index 0000000..cdfaea7
--- /dev/null
+++ b/xmlwf/xmltchar.h
@@ -0,0 +1,74 @@
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+/* Ensures compile-time constants are consistent */
+#include "expat_external.h"
+
+#ifdef XML_UNICODE
+# ifndef XML_UNICODE_WCHAR_T
+# error xmlwf requires a 16-bit Unicode-compatible wchar_t
+# endif
+# define _PREPEND_BIG_L(x) L ## x
+# define T(x) _PREPEND_BIG_L(x)
+# define ftprintf fwprintf
+# define tfopen _wfopen
+# define fputts fputws
+# define puttc putwc
+# define tcscmp wcscmp
+# define tcscpy wcscpy
+# define tcscat wcscat
+# define tcschr wcschr
+# define tcsrchr wcsrchr
+# define tcslen wcslen
+# define tperror _wperror
+# define topen _wopen
+# define tmain wmain
+# define tremove _wremove
+# define tchar wchar_t
+#else /* not XML_UNICODE */
+# define T(x) x
+# define ftprintf fprintf
+# define tfopen fopen
+# define fputts fputs
+# define puttc putc
+# define tcscmp strcmp
+# define tcscpy strcpy
+# define tcscat strcat
+# define tcschr strchr
+# define tcsrchr strrchr
+# define tcslen strlen
+# define tperror perror
+# define topen open
+# define tmain main
+# define tremove remove
+# define tchar char
+#endif /* not XML_UNICODE */
diff --git a/xmlwf/xmlurl.h b/xmlwf/xmlurl.h
new file mode 100644
index 0000000..f2cff09
--- /dev/null
+++ b/xmlwf/xmlurl.h
@@ -0,0 +1,45 @@
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+int XML_URLInit();
+void XML_URLUninit();
+int XML_ProcessURL(XML_Parser parser,
+ const XML_Char *url,
+ unsigned flags);
+
+#ifdef __cplusplus
+}
+#endif
diff --git a/xmlwf/xmlwf.c b/xmlwf/xmlwf.c
new file mode 100644
index 0000000..82d028e
--- /dev/null
+++ b/xmlwf/xmlwf.c
@@ -0,0 +1,1138 @@
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+#include <assert.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stddef.h>
+#include <string.h>
+
+#include "expat.h"
+#include "codepage.h"
+#include "internal.h" /* for UNUSED_P only */
+#include "xmlfile.h"
+#include "xmltchar.h"
+
+#ifdef _MSC_VER
+# include <crtdbg.h>
+#endif
+
+#ifdef XML_UNICODE
+# include <wchar.h>
+#endif
+
+/* Structures for handler user data */
+typedef struct NotationList {
+ struct NotationList *next;
+ const XML_Char *notationName;
+ const XML_Char *systemId;
+ const XML_Char *publicId;
+} NotationList;
+
+typedef struct xmlwfUserData {
+ FILE *fp;
+ NotationList *notationListHead;
+ const XML_Char *currentDoctypeName;
+} XmlwfUserData;
+
+
+/* This ensures proper sorting. */
+
+#define NSSEP T('\001')
+
+static void XMLCALL
+characterData(void *userData, const XML_Char *s, int len)
+{
+ FILE *fp = ((XmlwfUserData *)userData)->fp;
+ for (; len > 0; --len, ++s) {
+ switch (*s) {
+ case T('&'):
+ fputts(T("&amp;"), fp);
+ break;
+ case T('<'):
+ fputts(T("&lt;"), fp);
+ break;
+ case T('>'):
+ fputts(T("&gt;"), fp);
+ break;
+#ifdef W3C14N
+ case 13:
+ fputts(T("&#xD;"), fp);
+ break;
+#else
+ case T('"'):
+ fputts(T("&quot;"), fp);
+ break;
+ case 9:
+ case 10:
+ case 13:
+ ftprintf(fp, T("&#%d;"), *s);
+ break;
+#endif
+ default:
+ puttc(*s, fp);
+ break;
+ }
+ }
+}
+
+static void
+attributeValue(FILE *fp, const XML_Char *s)
+{
+ puttc(T('='), fp);
+ puttc(T('"'), fp);
+ assert(s);
+ for (;;) {
+ switch (*s) {
+ case 0:
+ case NSSEP:
+ puttc(T('"'), fp);
+ return;
+ case T('&'):
+ fputts(T("&amp;"), fp);
+ break;
+ case T('<'):
+ fputts(T("&lt;"), fp);
+ break;
+ case T('"'):
+ fputts(T("&quot;"), fp);
+ break;
+#ifdef W3C14N
+ case 9:
+ fputts(T("&#x9;"), fp);
+ break;
+ case 10:
+ fputts(T("&#xA;"), fp);
+ break;
+ case 13:
+ fputts(T("&#xD;"), fp);
+ break;
+#else
+ case T('>'):
+ fputts(T("&gt;"), fp);
+ break;
+ case 9:
+ case 10:
+ case 13:
+ ftprintf(fp, T("&#%d;"), *s);
+ break;
+#endif
+ default:
+ puttc(*s, fp);
+ break;
+ }
+ s++;
+ }
+}
+
+/* Lexicographically comparing UTF-8 encoded attribute values,
+is equivalent to lexicographically comparing based on the character number. */
+
+static int
+attcmp(const void *att1, const void *att2)
+{
+ return tcscmp(*(const XML_Char **)att1, *(const XML_Char **)att2);
+}
+
+static void XMLCALL
+startElement(void *userData, const XML_Char *name, const XML_Char **atts)
+{
+ int nAtts;
+ const XML_Char **p;
+ FILE *fp = ((XmlwfUserData *)userData)->fp;
+ puttc(T('<'), fp);
+ fputts(name, fp);
+
+ p = atts;
+ while (*p)
+ ++p;
+ nAtts = (int)((p - atts) >> 1);
+ if (nAtts > 1)
+ qsort((void *)atts, nAtts, sizeof(XML_Char *) * 2, attcmp);
+ while (*atts) {
+ puttc(T(' '), fp);
+ fputts(*atts++, fp);
+ attributeValue(fp, *atts);
+ atts++;
+ }
+ puttc(T('>'), fp);
+}
+
+static void XMLCALL
+endElement(void *userData, const XML_Char *name)
+{
+ FILE *fp = ((XmlwfUserData *)userData)->fp;
+ puttc(T('<'), fp);
+ puttc(T('/'), fp);
+ fputts(name, fp);
+ puttc(T('>'), fp);
+}
+
+static int
+nsattcmp(const void *p1, const void *p2)
+{
+ const XML_Char *att1 = *(const XML_Char **)p1;
+ const XML_Char *att2 = *(const XML_Char **)p2;
+ int sep1 = (tcsrchr(att1, NSSEP) != 0);
+ int sep2 = (tcsrchr(att1, NSSEP) != 0);
+ if (sep1 != sep2)
+ return sep1 - sep2;
+ return tcscmp(att1, att2);
+}
+
+static void XMLCALL
+startElementNS(void *userData, const XML_Char *name, const XML_Char **atts)
+{
+ int nAtts;
+ int nsi;
+ const XML_Char **p;
+ FILE *fp = ((XmlwfUserData *)userData)->fp;
+ const XML_Char *sep;
+ puttc(T('<'), fp);
+
+ sep = tcsrchr(name, NSSEP);
+ if (sep) {
+ fputts(T("n1:"), fp);
+ fputts(sep + 1, fp);
+ fputts(T(" xmlns:n1"), fp);
+ attributeValue(fp, name);
+ nsi = 2;
+ }
+ else {
+ fputts(name, fp);
+ nsi = 1;
+ }
+
+ p = atts;
+ while (*p)
+ ++p;
+ nAtts = (int)((p - atts) >> 1);
+ if (nAtts > 1)
+ qsort((void *)atts, nAtts, sizeof(XML_Char *) * 2, nsattcmp);
+ while (*atts) {
+ name = *atts++;
+ sep = tcsrchr(name, NSSEP);
+ puttc(T(' '), fp);
+ if (sep) {
+ ftprintf(fp, T("n%d:"), nsi);
+ fputts(sep + 1, fp);
+ }
+ else
+ fputts(name, fp);
+ attributeValue(fp, *atts);
+ if (sep) {
+ ftprintf(fp, T(" xmlns:n%d"), nsi++);
+ attributeValue(fp, name);
+ }
+ atts++;
+ }
+ puttc(T('>'), fp);
+}
+
+static void XMLCALL
+endElementNS(void *userData, const XML_Char *name)
+{
+ FILE *fp = ((XmlwfUserData *)userData)->fp;
+ const XML_Char *sep;
+ puttc(T('<'), fp);
+ puttc(T('/'), fp);
+ sep = tcsrchr(name, NSSEP);
+ if (sep) {
+ fputts(T("n1:"), fp);
+ fputts(sep + 1, fp);
+ }
+ else
+ fputts(name, fp);
+ puttc(T('>'), fp);
+}
+
+#ifndef W3C14N
+
+static void XMLCALL
+processingInstruction(void *userData, const XML_Char *target,
+ const XML_Char *data)
+{
+ FILE *fp = ((XmlwfUserData *)userData)->fp;
+ puttc(T('<'), fp);
+ puttc(T('?'), fp);
+ fputts(target, fp);
+ puttc(T(' '), fp);
+ fputts(data, fp);
+ puttc(T('?'), fp);
+ puttc(T('>'), fp);
+}
+
+
+static XML_Char *xcsdup(const XML_Char *s)
+{
+ XML_Char *result;
+ int count = 0;
+ int numBytes;
+
+ /* Get the length of the string, including terminator */
+ while (s[count++] != 0) {
+ /* Do nothing */
+ }
+ numBytes = count * sizeof(XML_Char);
+ result = malloc(numBytes);
+ if (result == NULL)
+ return NULL;
+ memcpy(result, s, numBytes);
+ return result;
+}
+
+static void XMLCALL
+startDoctypeDecl(void *userData,
+ const XML_Char *doctypeName,
+ const XML_Char *UNUSED_P(sysid),
+ const XML_Char *UNUSED_P(publid),
+ int UNUSED_P(has_internal_subset))
+{
+ XmlwfUserData *data = (XmlwfUserData *)userData;
+ data->currentDoctypeName = xcsdup(doctypeName);
+}
+
+static void
+freeNotations(XmlwfUserData *data)
+{
+ NotationList *notationListHead = data->notationListHead;
+
+ while (notationListHead != NULL) {
+ NotationList *next = notationListHead->next;
+ free((void *)notationListHead->notationName);
+ free((void *)notationListHead->systemId);
+ free((void *)notationListHead->publicId);
+ free(notationListHead);
+ notationListHead = next;
+ }
+ data->notationListHead = NULL;
+}
+
+static int xcscmp(const XML_Char *xs, const XML_Char *xt)
+{
+ while (*xs != 0 && *xt != 0) {
+ if (*xs < *xt)
+ return -1;
+ if (*xs > *xt)
+ return 1;
+ xs++;
+ xt++;
+ }
+ if (*xs < *xt)
+ return -1;
+ if (*xs > *xt)
+ return 1;
+ return 0;
+}
+
+static int
+notationCmp(const void *a, const void *b)
+{
+ const NotationList * const n1 = *(NotationList **)a;
+ const NotationList * const n2 = *(NotationList **)b;
+
+ return xcscmp(n1->notationName, n2->notationName);
+}
+
+static void XMLCALL
+endDoctypeDecl(void *userData)
+{
+ XmlwfUserData *data = (XmlwfUserData *)userData;
+ NotationList **notations;
+ int notationCount = 0;
+ NotationList *p;
+ int i;
+
+ /* How many notations do we have? */
+ for (p = data->notationListHead; p != NULL; p = p->next)
+ notationCount++;
+ if (notationCount == 0) {
+ /* Nothing to report */
+ free((void *)data->currentDoctypeName);
+ data->currentDoctypeName = NULL;
+ return;
+ }
+
+ notations = malloc(notationCount * sizeof(NotationList *));
+ if (notations == NULL) {
+ fprintf(stderr, "Unable to sort notations");
+ freeNotations(data);
+ return;
+ }
+
+ for (p = data->notationListHead, i = 0;
+ i < notationCount;
+ p = p->next, i++) {
+ notations[i] = p;
+ }
+ qsort(notations, notationCount, sizeof(NotationList *), notationCmp);
+
+ /* Output the DOCTYPE header */
+ fputts(T("<!DOCTYPE "), data->fp);
+ fputts(data->currentDoctypeName, data->fp);
+ fputts(T(" [\n"), data->fp);
+
+ /* Now the NOTATIONs */
+ for (i = 0; i < notationCount; i++) {
+ fputts(T("<!NOTATION "), data->fp);
+ fputts(notations[i]->notationName, data->fp);
+ if (notations[i]->publicId != NULL) {
+ fputts(T(" PUBLIC '"), data->fp);
+ fputts(notations[i]->publicId, data->fp);
+ puttc(T('\''), data->fp);
+ if (notations[i]->systemId != NULL) {
+ puttc(T(' '), data->fp);
+ puttc(T('\''), data->fp);
+ fputts(notations[i]->systemId, data->fp);
+ puttc(T('\''), data->fp);
+ }
+ }
+ else if (notations[i]->systemId != NULL) {
+ fputts(T(" SYSTEM '"), data->fp);
+ fputts(notations[i]->systemId, data->fp);
+ puttc(T('\''), data->fp);
+ }
+ puttc(T('>'), data->fp);
+ puttc(T('\n'), data->fp);
+ }
+
+ /* Finally end the DOCTYPE */
+ fputts(T("]>\n"), data->fp);
+
+ free(notations);
+ freeNotations(data);
+ free((void *)data->currentDoctypeName);
+ data->currentDoctypeName = NULL;
+}
+
+static void XMLCALL
+notationDecl(void *userData,
+ const XML_Char *notationName,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *systemId,
+ const XML_Char *publicId)
+{
+ XmlwfUserData *data = (XmlwfUserData *)userData;
+ NotationList *entry = malloc(sizeof(NotationList));
+ const char *errorMessage = "Unable to store NOTATION for output\n";
+
+ if (entry == NULL) {
+ fputs(errorMessage, stderr);
+ return; /* Nothing we can really do about this */
+ }
+ entry->notationName = xcsdup(notationName);
+ if (entry->notationName == NULL) {
+ fputs(errorMessage, stderr);
+ free(entry);
+ return;
+ }
+ if (systemId != NULL) {
+ entry->systemId = xcsdup(systemId);
+ if (entry->systemId == NULL) {
+ fputs(errorMessage, stderr);
+ free((void *)entry->notationName);
+ free(entry);
+ return;
+ }
+ }
+ else {
+ entry->systemId = NULL;
+ }
+ if (publicId != NULL) {
+ entry->publicId = xcsdup(publicId);
+ if (entry->publicId == NULL) {
+ fputs(errorMessage, stderr);
+ free((void *)entry->systemId); /* Safe if it's NULL */
+ free((void *)entry->notationName);
+ free(entry);
+ return;
+ }
+ }
+ else {
+ entry->publicId = NULL;
+ }
+
+ entry->next = data->notationListHead;
+ data->notationListHead = entry;
+}
+
+#endif /* not W3C14N */
+
+static void XMLCALL
+defaultCharacterData(void *userData, const XML_Char *UNUSED_P(s), int UNUSED_P(len))
+{
+ XML_DefaultCurrent((XML_Parser) userData);
+}
+
+static void XMLCALL
+defaultStartElement(void *userData, const XML_Char *UNUSED_P(name),
+ const XML_Char **UNUSED_P(atts))
+{
+ XML_DefaultCurrent((XML_Parser) userData);
+}
+
+static void XMLCALL
+defaultEndElement(void *userData, const XML_Char *UNUSED_P(name))
+{
+ XML_DefaultCurrent((XML_Parser) userData);
+}
+
+static void XMLCALL
+defaultProcessingInstruction(void *userData, const XML_Char *UNUSED_P(target),
+ const XML_Char *UNUSED_P(data))
+{
+ XML_DefaultCurrent((XML_Parser) userData);
+}
+
+static void XMLCALL
+nopCharacterData(void *UNUSED_P(userData), const XML_Char *UNUSED_P(s), int UNUSED_P(len))
+{
+}
+
+static void XMLCALL
+nopStartElement(void *UNUSED_P(userData), const XML_Char *UNUSED_P(name), const XML_Char **UNUSED_P(atts))
+{
+}
+
+static void XMLCALL
+nopEndElement(void *UNUSED_P(userData), const XML_Char *UNUSED_P(name))
+{
+}
+
+static void XMLCALL
+nopProcessingInstruction(void *UNUSED_P(userData), const XML_Char *UNUSED_P(target),
+ const XML_Char *UNUSED_P(data))
+{
+}
+
+static void XMLCALL
+markup(void *userData, const XML_Char *s, int len)
+{
+ FILE *fp = ((XmlwfUserData *)XML_GetUserData((XML_Parser) userData))->fp;
+ for (; len > 0; --len, ++s)
+ puttc(*s, fp);
+}
+
+static void
+metaLocation(XML_Parser parser)
+{
+ const XML_Char *uri = XML_GetBase(parser);
+ FILE *fp = ((XmlwfUserData *)XML_GetUserData(parser))->fp;
+ if (uri)
+ ftprintf(fp, T(" uri=\"%s\""), uri);
+ ftprintf(fp,
+ T(" byte=\"%") T(XML_FMT_INT_MOD) T("d\"")
+ T(" nbytes=\"%d\"")
+ T(" line=\"%") T(XML_FMT_INT_MOD) T("u\"")
+ T(" col=\"%") T(XML_FMT_INT_MOD) T("u\""),
+ XML_GetCurrentByteIndex(parser),
+ XML_GetCurrentByteCount(parser),
+ XML_GetCurrentLineNumber(parser),
+ XML_GetCurrentColumnNumber(parser));
+}
+
+static void
+metaStartDocument(void *userData)
+{
+ fputts(T("<document>\n"),
+ ((XmlwfUserData *)XML_GetUserData((XML_Parser) userData))->fp);
+}
+
+static void
+metaEndDocument(void *userData)
+{
+ fputts(T("</document>\n"),
+ ((XmlwfUserData *)XML_GetUserData((XML_Parser) userData))->fp);
+}
+
+static void XMLCALL
+metaStartElement(void *userData, const XML_Char *name,
+ const XML_Char **atts)
+{
+ XML_Parser parser = (XML_Parser) userData;
+ XmlwfUserData *data = (XmlwfUserData *)XML_GetUserData(parser);
+ FILE *fp = data->fp;
+ const XML_Char **specifiedAttsEnd
+ = atts + XML_GetSpecifiedAttributeCount(parser);
+ const XML_Char **idAttPtr;
+ int idAttIndex = XML_GetIdAttributeIndex(parser);
+ if (idAttIndex < 0)
+ idAttPtr = 0;
+ else
+ idAttPtr = atts + idAttIndex;
+
+ ftprintf(fp, T("<starttag name=\"%s\""), name);
+ metaLocation(parser);
+ if (*atts) {
+ fputts(T(">\n"), fp);
+ do {
+ ftprintf(fp, T("<attribute name=\"%s\" value=\""), atts[0]);
+ characterData(data, atts[1], (int)tcslen(atts[1]));
+ if (atts >= specifiedAttsEnd)
+ fputts(T("\" defaulted=\"yes\"/>\n"), fp);
+ else if (atts == idAttPtr)
+ fputts(T("\" id=\"yes\"/>\n"), fp);
+ else
+ fputts(T("\"/>\n"), fp);
+ } while (*(atts += 2));
+ fputts(T("</starttag>\n"), fp);
+ }
+ else
+ fputts(T("/>\n"), fp);
+}
+
+static void XMLCALL
+metaEndElement(void *userData, const XML_Char *name)
+{
+ XML_Parser parser = (XML_Parser) userData;
+ XmlwfUserData *data = (XmlwfUserData *)XML_GetUserData(parser);
+ FILE *fp = data->fp;
+ ftprintf(fp, T("<endtag name=\"%s\""), name);
+ metaLocation(parser);
+ fputts(T("/>\n"), fp);
+}
+
+static void XMLCALL
+metaProcessingInstruction(void *userData, const XML_Char *target,
+ const XML_Char *data)
+{
+ XML_Parser parser = (XML_Parser) userData;
+ XmlwfUserData *usrData = (XmlwfUserData *)XML_GetUserData(parser);
+ FILE *fp = usrData->fp;
+ ftprintf(fp, T("<pi target=\"%s\" data=\""), target);
+ characterData(usrData, data, (int)tcslen(data));
+ puttc(T('"'), fp);
+ metaLocation(parser);
+ fputts(T("/>\n"), fp);
+}
+
+static void XMLCALL
+metaComment(void *userData, const XML_Char *data)
+{
+ XML_Parser parser = (XML_Parser) userData;
+ XmlwfUserData *usrData = (XmlwfUserData *)XML_GetUserData(parser);
+ FILE *fp = usrData->fp;
+ fputts(T("<comment data=\""), fp);
+ characterData(usrData, data, (int)tcslen(data));
+ puttc(T('"'), fp);
+ metaLocation(parser);
+ fputts(T("/>\n"), fp);
+}
+
+static void XMLCALL
+metaStartCdataSection(void *userData)
+{
+ XML_Parser parser = (XML_Parser) userData;
+ XmlwfUserData *data = (XmlwfUserData *)XML_GetUserData(parser);
+ FILE *fp = data->fp;
+ fputts(T("<startcdata"), fp);
+ metaLocation(parser);
+ fputts(T("/>\n"), fp);
+}
+
+static void XMLCALL
+metaEndCdataSection(void *userData)
+{
+ XML_Parser parser = (XML_Parser) userData;
+ XmlwfUserData *data = (XmlwfUserData *)XML_GetUserData(parser);
+ FILE *fp = data->fp;
+ fputts(T("<endcdata"), fp);
+ metaLocation(parser);
+ fputts(T("/>\n"), fp);
+}
+
+static void XMLCALL
+metaCharacterData(void *userData, const XML_Char *s, int len)
+{
+ XML_Parser parser = (XML_Parser) userData;
+ XmlwfUserData *data = (XmlwfUserData *)XML_GetUserData(parser);
+ FILE *fp = data->fp;
+ fputts(T("<chars str=\""), fp);
+ characterData(data, s, len);
+ puttc(T('"'), fp);
+ metaLocation(parser);
+ fputts(T("/>\n"), fp);
+}
+
+static void XMLCALL
+metaStartDoctypeDecl(void *userData,
+ const XML_Char *doctypeName,
+ const XML_Char *UNUSED_P(sysid),
+ const XML_Char *UNUSED_P(pubid),
+ int UNUSED_P(has_internal_subset))
+{
+ XML_Parser parser = (XML_Parser) userData;
+ XmlwfUserData *data = (XmlwfUserData *)XML_GetUserData(parser);
+ FILE *fp = data->fp;
+ ftprintf(fp, T("<startdoctype name=\"%s\""), doctypeName);
+ metaLocation(parser);
+ fputts(T("/>\n"), fp);
+}
+
+static void XMLCALL
+metaEndDoctypeDecl(void *userData)
+{
+ XML_Parser parser = (XML_Parser) userData;
+ XmlwfUserData *data = (XmlwfUserData *)XML_GetUserData(parser);
+ FILE *fp = data->fp;
+ fputts(T("<enddoctype"), fp);
+ metaLocation(parser);
+ fputts(T("/>\n"), fp);
+}
+
+static void XMLCALL
+metaNotationDecl(void *userData,
+ const XML_Char *notationName,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *systemId,
+ const XML_Char *publicId)
+{
+ XML_Parser parser = (XML_Parser) userData;
+ XmlwfUserData *data = (XmlwfUserData *)XML_GetUserData(parser);
+ FILE *fp = data->fp;
+ ftprintf(fp, T("<notation name=\"%s\""), notationName);
+ if (publicId)
+ ftprintf(fp, T(" public=\"%s\""), publicId);
+ if (systemId) {
+ fputts(T(" system=\""), fp);
+ characterData(data, systemId, (int)tcslen(systemId));
+ puttc(T('"'), fp);
+ }
+ metaLocation(parser);
+ fputts(T("/>\n"), fp);
+}
+
+
+static void XMLCALL
+metaEntityDecl(void *userData,
+ const XML_Char *entityName,
+ int UNUSED_P(is_param),
+ const XML_Char *value,
+ int value_length,
+ const XML_Char *UNUSED_P(base),
+ const XML_Char *systemId,
+ const XML_Char *publicId,
+ const XML_Char *notationName)
+{
+ XML_Parser parser = (XML_Parser) userData;
+ XmlwfUserData *data = (XmlwfUserData *)XML_GetUserData(parser);
+ FILE *fp = data->fp;
+
+ if (value) {
+ ftprintf(fp, T("<entity name=\"%s\""), entityName);
+ metaLocation(parser);
+ puttc(T('>'), fp);
+ characterData(data, value, value_length);
+ fputts(T("</entity/>\n"), fp);
+ }
+ else if (notationName) {
+ ftprintf(fp, T("<entity name=\"%s\""), entityName);
+ if (publicId)
+ ftprintf(fp, T(" public=\"%s\""), publicId);
+ fputts(T(" system=\""), fp);
+ characterData(data, systemId, (int)tcslen(systemId));
+ puttc(T('"'), fp);
+ ftprintf(fp, T(" notation=\"%s\""), notationName);
+ metaLocation(parser);
+ fputts(T("/>\n"), fp);
+ }
+ else {
+ ftprintf(fp, T("<entity name=\"%s\""), entityName);
+ if (publicId)
+ ftprintf(fp, T(" public=\"%s\""), publicId);
+ fputts(T(" system=\""), fp);
+ characterData(data, systemId, (int)tcslen(systemId));
+ puttc(T('"'), fp);
+ metaLocation(parser);
+ fputts(T("/>\n"), fp);
+ }
+}
+
+static void XMLCALL
+metaStartNamespaceDecl(void *userData,
+ const XML_Char *prefix,
+ const XML_Char *uri)
+{
+ XML_Parser parser = (XML_Parser) userData;
+ XmlwfUserData *data = (XmlwfUserData *)XML_GetUserData(parser);
+ FILE *fp = data->fp;
+ fputts(T("<startns"), fp);
+ if (prefix)
+ ftprintf(fp, T(" prefix=\"%s\""), prefix);
+ if (uri) {
+ fputts(T(" ns=\""), fp);
+ characterData(data, uri, (int)tcslen(uri));
+ fputts(T("\"/>\n"), fp);
+ }
+ else
+ fputts(T("/>\n"), fp);
+}
+
+static void XMLCALL
+metaEndNamespaceDecl(void *userData, const XML_Char *prefix)
+{
+ XML_Parser parser = (XML_Parser) userData;
+ XmlwfUserData *data = (XmlwfUserData *)XML_GetUserData(parser);
+ FILE *fp = data->fp;
+ if (!prefix)
+ fputts(T("<endns/>\n"), fp);
+ else
+ ftprintf(fp, T("<endns prefix=\"%s\"/>\n"), prefix);
+}
+
+static int XMLCALL
+unknownEncodingConvert(void *data, const char *p)
+{
+ return codepageConvert(*(int *)data, p);
+}
+
+static int XMLCALL
+unknownEncoding(void *UNUSED_P(userData), const XML_Char *name, XML_Encoding *info)
+{
+ int cp;
+ static const XML_Char prefixL[] = T("windows-");
+ static const XML_Char prefixU[] = T("WINDOWS-");
+ int i;
+
+ for (i = 0; prefixU[i]; i++)
+ if (name[i] != prefixU[i] && name[i] != prefixL[i])
+ return 0;
+
+ cp = 0;
+ for (; name[i]; i++) {
+ static const XML_Char digits[] = T("0123456789");
+ const XML_Char *s = tcschr(digits, name[i]);
+ if (!s)
+ return 0;
+ cp *= 10;
+ cp += (int)(s - digits);
+ if (cp >= 0x10000)
+ return 0;
+ }
+ if (!codepageMap(cp, info->map))
+ return 0;
+ info->convert = unknownEncodingConvert;
+ /* We could just cast the code page integer to a void *,
+ and avoid the use of release. */
+ info->release = free;
+ info->data = malloc(sizeof(int));
+ if (!info->data)
+ return 0;
+ *(int *)info->data = cp;
+ return 1;
+}
+
+static int XMLCALL
+notStandalone(void *UNUSED_P(userData))
+{
+ return 0;
+}
+
+static void
+showVersion(XML_Char *prog)
+{
+ XML_Char *s = prog;
+ XML_Char ch;
+ const XML_Feature *features = XML_GetFeatureList();
+ while ((ch = *s) != 0) {
+ if (ch == '/'
+#if defined(_WIN32)
+ || ch == '\\'
+#endif
+ )
+ prog = s + 1;
+ ++s;
+ }
+ ftprintf(stdout, T("%s using %s\n"), prog, XML_ExpatVersion());
+ if (features != NULL && features[0].feature != XML_FEATURE_END) {
+ int i = 1;
+ ftprintf(stdout, T("%s"), features[0].name);
+ if (features[0].value)
+ ftprintf(stdout, T("=%ld"), features[0].value);
+ while (features[i].feature != XML_FEATURE_END) {
+ ftprintf(stdout, T(", %s"), features[i].name);
+ if (features[i].value)
+ ftprintf(stdout, T("=%ld"), features[i].value);
+ ++i;
+ }
+ ftprintf(stdout, T("\n"));
+ }
+}
+
+static void
+usage(const XML_Char *prog, int rc)
+{
+ ftprintf(stderr,
+ T("usage: %s [-s] [-n] [-p] [-x] [-e encoding] [-w] [-d output-dir] [-c] [-m] [-r] [-t] [-N] [file ...]\n"), prog);
+ exit(rc);
+}
+
+#if defined(__MINGW32__) && defined(XML_UNICODE)
+/* Silence warning about missing prototype */
+int wmain(int argc, XML_Char **argv);
+#endif
+
+int
+tmain(int argc, XML_Char **argv)
+{
+ int i, j;
+ const XML_Char *outputDir = NULL;
+ const XML_Char *encoding = NULL;
+ unsigned processFlags = XML_MAP_FILE;
+ int windowsCodePages = 0;
+ int outputType = 0;
+ int useNamespaces = 0;
+ int requireStandalone = 0;
+ int requiresNotations = 0;
+ enum XML_ParamEntityParsing paramEntityParsing =
+ XML_PARAM_ENTITY_PARSING_NEVER;
+ int useStdin = 0;
+ XmlwfUserData userData = { NULL, NULL, NULL };
+
+#ifdef _MSC_VER
+ _CrtSetDbgFlag(_CRTDBG_ALLOC_MEM_DF|_CRTDBG_LEAK_CHECK_DF);
+#endif
+
+ i = 1;
+ j = 0;
+ while (i < argc) {
+ if (j == 0) {
+ if (argv[i][0] != T('-'))
+ break;
+ if (argv[i][1] == T('-') && argv[i][2] == T('\0')) {
+ i++;
+ break;
+ }
+ j++;
+ }
+ switch (argv[i][j]) {
+ case T('r'):
+ processFlags &= ~XML_MAP_FILE;
+ j++;
+ break;
+ case T('s'):
+ requireStandalone = 1;
+ j++;
+ break;
+ case T('n'):
+ useNamespaces = 1;
+ j++;
+ break;
+ case T('p'):
+ paramEntityParsing = XML_PARAM_ENTITY_PARSING_ALWAYS;
+ /* fall through */
+ case T('x'):
+ processFlags |= XML_EXTERNAL_ENTITIES;
+ j++;
+ break;
+ case T('w'):
+ windowsCodePages = 1;
+ j++;
+ break;
+ case T('m'):
+ outputType = 'm';
+ j++;
+ break;
+ case T('c'):
+ outputType = 'c';
+ useNamespaces = 0;
+ j++;
+ break;
+ case T('t'):
+ outputType = 't';
+ j++;
+ break;
+ case T('N'):
+ requiresNotations = 1;
+ j++;
+ break;
+ case T('d'):
+ if (argv[i][j + 1] == T('\0')) {
+ if (++i == argc)
+ usage(argv[0], 2);
+ outputDir = argv[i];
+ }
+ else
+ outputDir = argv[i] + j + 1;
+ i++;
+ j = 0;
+ break;
+ case T('e'):
+ if (argv[i][j + 1] == T('\0')) {
+ if (++i == argc)
+ usage(argv[0], 2);
+ encoding = argv[i];
+ }
+ else
+ encoding = argv[i] + j + 1;
+ i++;
+ j = 0;
+ break;
+ case T('h'):
+ usage(argv[0], 0);
+ return 0;
+ case T('v'):
+ showVersion(argv[0]);
+ return 0;
+ case T('\0'):
+ if (j > 1) {
+ i++;
+ j = 0;
+ break;
+ }
+ /* fall through */
+ default:
+ usage(argv[0], 2);
+ }
+ }
+ if (i == argc) {
+ useStdin = 1;
+ processFlags &= ~XML_MAP_FILE;
+ i--;
+ }
+ for (; i < argc; i++) {
+ XML_Char *outName = 0;
+ int result;
+ XML_Parser parser;
+ if (useNamespaces)
+ parser = XML_ParserCreateNS(encoding, NSSEP);
+ else
+ parser = XML_ParserCreate(encoding);
+
+ if (! parser) {
+ tperror(T("Could not instantiate parser"));
+ exit(1);
+ }
+
+ if (requireStandalone)
+ XML_SetNotStandaloneHandler(parser, notStandalone);
+ XML_SetParamEntityParsing(parser, paramEntityParsing);
+ if (outputType == 't') {
+ /* This is for doing timings; this gives a more realistic estimate of
+ the parsing time. */
+ outputDir = 0;
+ XML_SetElementHandler(parser, nopStartElement, nopEndElement);
+ XML_SetCharacterDataHandler(parser, nopCharacterData);
+ XML_SetProcessingInstructionHandler(parser, nopProcessingInstruction);
+ }
+ else if (outputDir) {
+ const XML_Char * delim = T("/");
+ const XML_Char *file = useStdin ? T("STDIN") : argv[i];
+ if (!useStdin) {
+ /* Jump after last (back)slash */
+ const XML_Char * lastDelim = tcsrchr(file, delim[0]);
+ if (lastDelim)
+ file = lastDelim + 1;
+#if defined(_WIN32)
+ else {
+ const XML_Char * winDelim = T("\\");
+ lastDelim = tcsrchr(file, winDelim[0]);
+ if (lastDelim) {
+ file = lastDelim + 1;
+ delim = winDelim;
+ }
+ }
+#endif
+ }
+ outName = (XML_Char *)malloc((tcslen(outputDir) + tcslen(file) + 2)
+ * sizeof(XML_Char));
+ tcscpy(outName, outputDir);
+ tcscat(outName, delim);
+ tcscat(outName, file);
+ userData.fp = tfopen(outName, T("wb"));
+ if (!userData.fp) {
+ tperror(outName);
+ exit(1);
+ }
+ setvbuf(userData.fp, NULL, _IOFBF, 16384);
+#ifdef XML_UNICODE
+ puttc(0xFEFF, userData.fp);
+#endif
+ XML_SetUserData(parser, &userData);
+ switch (outputType) {
+ case 'm':
+ XML_UseParserAsHandlerArg(parser);
+ XML_SetElementHandler(parser, metaStartElement, metaEndElement);
+ XML_SetProcessingInstructionHandler(parser, metaProcessingInstruction);
+ XML_SetCommentHandler(parser, metaComment);
+ XML_SetCdataSectionHandler(parser, metaStartCdataSection,
+ metaEndCdataSection);
+ XML_SetCharacterDataHandler(parser, metaCharacterData);
+ XML_SetDoctypeDeclHandler(parser, metaStartDoctypeDecl,
+ metaEndDoctypeDecl);
+ XML_SetEntityDeclHandler(parser, metaEntityDecl);
+ XML_SetNotationDeclHandler(parser, metaNotationDecl);
+ XML_SetNamespaceDeclHandler(parser, metaStartNamespaceDecl,
+ metaEndNamespaceDecl);
+ metaStartDocument(parser);
+ break;
+ case 'c':
+ XML_UseParserAsHandlerArg(parser);
+ XML_SetDefaultHandler(parser, markup);
+ XML_SetElementHandler(parser, defaultStartElement, defaultEndElement);
+ XML_SetCharacterDataHandler(parser, defaultCharacterData);
+ XML_SetProcessingInstructionHandler(parser,
+ defaultProcessingInstruction);
+ break;
+ default:
+ if (useNamespaces)
+ XML_SetElementHandler(parser, startElementNS, endElementNS);
+ else
+ XML_SetElementHandler(parser, startElement, endElement);
+ XML_SetCharacterDataHandler(parser, characterData);
+#ifndef W3C14N
+ XML_SetProcessingInstructionHandler(parser, processingInstruction);
+ if (requiresNotations) {
+ XML_SetDoctypeDeclHandler(parser, startDoctypeDecl, endDoctypeDecl);
+ XML_SetNotationDeclHandler(parser, notationDecl);
+ }
+#endif /* not W3C14N */
+ break;
+ }
+ }
+ if (windowsCodePages)
+ XML_SetUnknownEncodingHandler(parser, unknownEncoding, 0);
+ result = XML_ProcessFile(parser, useStdin ? NULL : argv[i], processFlags);
+ if (outputDir) {
+ if (outputType == 'm')
+ metaEndDocument(parser);
+ fclose(userData.fp);
+ if (!result) {
+ tremove(outName);
+ exit(2);
+ }
+ free(outName);
+ }
+ XML_ParserFree(parser);
+ }
+ return 0;
+}
diff --git a/xmlwf/xmlwf.vcxproj b/xmlwf/xmlwf.vcxproj
new file mode 100644
index 0000000..ed9c50f
--- /dev/null
+++ b/xmlwf/xmlwf.vcxproj
@@ -0,0 +1,164 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project DefaultTargets="Build" ToolsVersion="15.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+ <ItemGroup Label="ProjectConfigurations">
+ <ProjectConfiguration Include="Debug|Win32">
+ <Configuration>Debug</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Release|Win32">
+ <Configuration>Release</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Template|Win32">
+ <Configuration>Template</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ </ItemGroup>
+ <PropertyGroup Label="Globals">
+ <SccProjectName />
+ <SccLocalPath />
+ <ProjectGuid>{E3C5991F-5238-4168-A179-275D1AC98D7E}</ProjectGuid>
+ <WindowsTargetPlatformVersion>10.0.16299.0</WindowsTargetPlatformVersion>
+ </PropertyGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Template|Win32'" Label="Configuration">
+ <ConfigurationType>Application</ConfigurationType>
+ <PlatformToolset>v141</PlatformToolset>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
+ <ConfigurationType>Application</ConfigurationType>
+ <PlatformToolset>v141</PlatformToolset>
+ <UseOfMfc>false</UseOfMfc>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
+ <ConfigurationType>Application</ConfigurationType>
+ <PlatformToolset>v141</PlatformToolset>
+ <UseOfMfc>false</UseOfMfc>
+ </PropertyGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
+ <ImportGroup Label="ExtensionSettings">
+ </ImportGroup>
+ <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Template|Win32'">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ </ImportGroup>
+ <ImportGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="PropertySheets">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ <Import Project="$(VCTargetsPath)Microsoft.Cpp.UpgradeFromVC60.props" />
+ </ImportGroup>
+ <ImportGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="PropertySheets">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ <Import Project="$(VCTargetsPath)Microsoft.Cpp.UpgradeFromVC60.props" />
+ </ImportGroup>
+ <PropertyGroup Label="UserMacros" />
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+ <OutDir>.\..\win32\bin\Release\</OutDir>
+ <IntDir>.\..\win32\tmp\Release-xmlwf\</IntDir>
+ <LinkIncremental>false</LinkIncremental>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ <OutDir>.\..\win32\bin\Debug\</OutDir>
+ <IntDir>.\..\win32\tmp\Debug-xmlwf\</IntDir>
+ <LinkIncremental>true</LinkIncremental>
+ </PropertyGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+ <ClCompile>
+ <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
+ <InlineFunctionExpansion>Default</InlineFunctionExpansion>
+ <StringPooling>true</StringPooling>
+ <FunctionLevelLinking>true</FunctionLevelLinking>
+ <Optimization>MaxSpeed</Optimization>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <WarningLevel>Level3</WarningLevel>
+ <AdditionalIncludeDirectories>..\lib;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
+ <PreprocessorDefinitions>NDEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <AssemblerListingLocation>.\..\win32\tmp\Release-xmlwf\</AssemblerListingLocation>
+ <PrecompiledHeaderOutputFile>.\..\win32\tmp\Release-xmlwf\xmlwf.pch</PrecompiledHeaderOutputFile>
+ <PrecompiledHeader />
+ <ObjectFileName>.\..\win32\tmp\Release-xmlwf\</ObjectFileName>
+ <ProgramDataBaseFileName>.\..\win32\tmp\Release-xmlwf\</ProgramDataBaseFileName>
+ </ClCompile>
+ <Midl>
+ <TypeLibraryName>.\..\win32\bin\Release\xmlwf.tlb</TypeLibraryName>
+ </Midl>
+ <ResourceCompile>
+ <Culture>0x0409</Culture>
+ <PreprocessorDefinitions>NDEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ </ResourceCompile>
+ <Bscmake>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <OutputFile>.\..\win32\bin\Release\xmlwf.bsc</OutputFile>
+ </Bscmake>
+ <Link>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <SubSystem>Console</SubSystem>
+ <IgnoreAllDefaultLibraries>false</IgnoreAllDefaultLibraries>
+ <OutputFile>..\win32\bin\Release\xmlwf.exe</OutputFile>
+ <AdditionalLibraryDirectories>..\win32\bin\Release;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
+ <AdditionalDependencies>libexpat.lib;setargv.obj;%(AdditionalDependencies)</AdditionalDependencies>
+ </Link>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ <ClCompile>
+ <RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
+ <InlineFunctionExpansion>Default</InlineFunctionExpansion>
+ <FunctionLevelLinking>true</FunctionLevelLinking>
+ <Optimization>Disabled</Optimization>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <WarningLevel>Level3</WarningLevel>
+ <DebugInformationFormat>EditAndContinue</DebugInformationFormat>
+ <AdditionalIncludeDirectories>..\lib;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
+ <PreprocessorDefinitions>_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ <AssemblerListingLocation>.\..\win32\tmp\Debug-xmlwf\</AssemblerListingLocation>
+ <PrecompiledHeaderOutputFile>.\..\win32\tmp\Debug-xmlwf\xmlwf.pch</PrecompiledHeaderOutputFile>
+ <ObjectFileName>.\..\win32\tmp\Debug-xmlwf\</ObjectFileName>
+ <ProgramDataBaseFileName>.\..\win32\tmp\Debug-xmlwf\</ProgramDataBaseFileName>
+ </ClCompile>
+ <Midl>
+ <TypeLibraryName>.\..\win32\bin\Debug\xmlwf.tlb</TypeLibraryName>
+ </Midl>
+ <ResourceCompile>
+ <Culture>0x0409</Culture>
+ <PreprocessorDefinitions>_DEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+ </ResourceCompile>
+ <Bscmake>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <OutputFile>.\..\win32\bin\Debug\xmlwf.bsc</OutputFile>
+ </Bscmake>
+ <Link>
+ <SuppressStartupBanner>true</SuppressStartupBanner>
+ <GenerateDebugInformation>true</GenerateDebugInformation>
+ <SubSystem>Console</SubSystem>
+ <OutputFile>..\win32\bin\Debug\xmlwf.exe</OutputFile>
+ <AdditionalLibraryDirectories>..\win32\bin\Debug;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
+ <AdditionalDependencies>libexpat.lib;setargv.obj;%(AdditionalDependencies)</AdditionalDependencies>
+ </Link>
+ </ItemDefinitionGroup>
+ <ItemGroup>
+ <ClCompile Include="codepage.c" />
+ <ClCompile Include="readfilemap.c">
+ <ExcludedFromBuild Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">true</ExcludedFromBuild>
+ <ExcludedFromBuild Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">true</ExcludedFromBuild>
+ </ClCompile>
+ <ClCompile Include="unixfilemap.c">
+ <ExcludedFromBuild Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">true</ExcludedFromBuild>
+ <ExcludedFromBuild Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">true</ExcludedFromBuild>
+ </ClCompile>
+ <ClCompile Include="win32filemap.c" />
+ <ClCompile Include="xmlfile.c" />
+ <ClCompile Include="xmlwf.c" />
+ </ItemGroup>
+ <ItemGroup>
+ <ClInclude Include="codepage.h" />
+ <ClInclude Include="xmlfile.h" />
+ <ClInclude Include="xmltchar.h" />
+ </ItemGroup>
+ <ItemGroup>
+ <ProjectReference Include="..\lib\expat.vcxproj">
+ <Project>{45a5074d-66e8-44a4-a03f-018027b528d6}</Project>
+ <ReferenceOutputAssembly>false</ReferenceOutputAssembly>
+ </ProjectReference>
+ </ItemGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
+ <ImportGroup Label="ExtensionTargets">
+ </ImportGroup>
+</Project> \ No newline at end of file
diff --git a/xmlwf/xmlwf.vcxproj.filters b/xmlwf/xmlwf.vcxproj.filters
new file mode 100644
index 0000000..890b9ef
--- /dev/null
+++ b/xmlwf/xmlwf.vcxproj.filters
@@ -0,0 +1,48 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+ <ItemGroup>
+ <Filter Include="Source Files">
+ <UniqueIdentifier>{843deb01-ec59-4070-9fb7-4de851940fbd}</UniqueIdentifier>
+ <Extensions>cpp;c;cxx;rc;def;r;odl;idl;hpj;bat;for;f90</Extensions>
+ </Filter>
+ <Filter Include="Header Files">
+ <UniqueIdentifier>{41225059-d26f-42fd-9d1b-fda760b7e45d}</UniqueIdentifier>
+ <Extensions>h;hpp;hxx;hm;inl;fi;fd</Extensions>
+ </Filter>
+ <Filter Include="Resource Files">
+ <UniqueIdentifier>{a722469e-558e-4d77-b8ea-88c9f136e29a}</UniqueIdentifier>
+ <Extensions>ico;cur;bmp;dlg;rc2;rct;bin;cnt;rtf;gif;jpg;jpeg;jpe</Extensions>
+ </Filter>
+ </ItemGroup>
+ <ItemGroup>
+ <ClCompile Include="codepage.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="readfilemap.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="unixfilemap.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="win32filemap.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="xmlfile.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ <ClCompile Include="xmlwf.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ </ItemGroup>
+ <ItemGroup>
+ <ClInclude Include="codepage.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="xmlfile.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ <ClInclude Include="xmltchar.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ </ItemGroup>
+</Project> \ No newline at end of file
diff --git a/xmlwf/xmlwin32url.cxx b/xmlwf/xmlwin32url.cxx
new file mode 100644
index 0000000..ef2a137
--- /dev/null
+++ b/xmlwf/xmlwin32url.cxx
@@ -0,0 +1,427 @@
+/*
+ __ __ _
+ ___\ \/ /_ __ __ _| |_
+ / _ \\ /| '_ \ / _` | __|
+ | __// \| |_) | (_| | |_
+ \___/_/\_\ .__/ \__,_|\__|
+ |_| XML parser
+
+ Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+ Copyright (c) 2000-2017 Expat development team
+ Licensed under the MIT license:
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to permit
+ persons to whom the Software is furnished to do so, subject to the
+ following conditions:
+
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+ NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+#include "expat.h"
+#ifdef XML_UNICODE
+#define UNICODE
+#endif
+#include <windows.h>
+#include <urlmon.h>
+#include <wininet.h>
+#include <stdio.h>
+#include <tchar.h>
+#include "xmlurl.h"
+#include "xmlmime.h"
+
+static int
+processURL(XML_Parser parser, IMoniker *baseMoniker, const XML_Char *url);
+
+typedef void (*StopHandler)(void *, HRESULT);
+
+class Callback : public IBindStatusCallback {
+public:
+ // IUnknown methods
+ STDMETHODIMP QueryInterface(REFIID,void **);
+ STDMETHODIMP_(ULONG) AddRef();
+ STDMETHODIMP_(ULONG) Release();
+ // IBindStatusCallback methods
+ STDMETHODIMP OnStartBinding(DWORD, IBinding *);
+ STDMETHODIMP GetPriority(LONG *);
+ STDMETHODIMP OnLowResource(DWORD);
+ STDMETHODIMP OnProgress(ULONG, ULONG, ULONG, LPCWSTR);
+ STDMETHODIMP OnStopBinding(HRESULT, LPCWSTR);
+ STDMETHODIMP GetBindInfo(DWORD *, BINDINFO *);
+ STDMETHODIMP OnDataAvailable(DWORD, DWORD, FORMATETC *, STGMEDIUM *);
+ STDMETHODIMP OnObjectAvailable(REFIID, IUnknown *);
+ Callback(XML_Parser, IMoniker *, StopHandler, void *);
+ ~Callback();
+ int externalEntityRef(const XML_Char *context,
+ const XML_Char *systemId, const XML_Char *publicId);
+private:
+ XML_Parser parser_;
+ IMoniker *baseMoniker_;
+ DWORD totalRead_;
+ ULONG ref_;
+ IBinding *pBinding_;
+ StopHandler stopHandler_;
+ void *stopArg_;
+};
+
+STDMETHODIMP_(ULONG)
+Callback::AddRef()
+{
+ return ref_++;
+}
+
+STDMETHODIMP_(ULONG)
+Callback::Release()
+{
+ if (--ref_ == 0) {
+ delete this;
+ return 0;
+ }
+ return ref_;
+}
+
+STDMETHODIMP
+Callback::QueryInterface(REFIID riid, void** ppv)
+{
+ if (IsEqualGUID(riid, IID_IUnknown))
+ *ppv = (IUnknown *)this;
+ else if (IsEqualGUID(riid, IID_IBindStatusCallback))
+ *ppv = (IBindStatusCallback *)this;
+ else
+ return E_NOINTERFACE;
+ ((LPUNKNOWN)*ppv)->AddRef();
+ return S_OK;
+}
+
+STDMETHODIMP
+Callback::OnStartBinding(DWORD, IBinding* pBinding)
+{
+ pBinding_ = pBinding;
+ pBinding->AddRef();
+ return S_OK;
+}
+
+STDMETHODIMP
+Callback::GetPriority(LONG *)
+{
+ return E_NOTIMPL;
+}
+
+STDMETHODIMP
+Callback::OnLowResource(DWORD)
+{
+ return E_NOTIMPL;
+}
+
+STDMETHODIMP
+Callback::OnProgress(ULONG, ULONG, ULONG, LPCWSTR)
+{
+ return S_OK;
+}
+
+STDMETHODIMP
+Callback::OnStopBinding(HRESULT hr, LPCWSTR szError)
+{
+ if (pBinding_) {
+ pBinding_->Release();
+ pBinding_ = 0;
+ }
+ if (baseMoniker_) {
+ baseMoniker_->Release();
+ baseMoniker_ = 0;
+ }
+ stopHandler_(stopArg_, hr);
+ return S_OK;
+}
+
+STDMETHODIMP
+Callback::GetBindInfo(DWORD* pgrfBINDF, BINDINFO* pbindinfo)
+{
+ *pgrfBINDF = BINDF_ASYNCHRONOUS;
+ return S_OK;
+}
+
+static void
+reportError(XML_Parser parser)
+{
+ int code = XML_GetErrorCode(parser);
+ const XML_Char *message = XML_ErrorString(code);
+ if (message)
+ _ftprintf(stderr, _T("%s:%d:%ld: %s\n"),
+ XML_GetBase(parser),
+ XML_GetErrorLineNumber(parser),
+ XML_GetErrorColumnNumber(parser),
+ message);
+ else
+ _ftprintf(stderr, _T("%s: (unknown message %d)\n"),
+ XML_GetBase(parser), code);
+}
+
+STDMETHODIMP
+Callback::OnDataAvailable(DWORD grfBSCF,
+ DWORD dwSize,
+ FORMATETC *pfmtetc,
+ STGMEDIUM* pstgmed)
+{
+ if (grfBSCF & BSCF_FIRSTDATANOTIFICATION) {
+ IWinInetHttpInfo *hp;
+ HRESULT hr = pBinding_->QueryInterface(IID_IWinInetHttpInfo,
+ (void **)&hp);
+ if (SUCCEEDED(hr)) {
+ char contentType[1024];
+ DWORD bufSize = sizeof(contentType);
+ DWORD flags = 0;
+ contentType[0] = 0;
+ hr = hp->QueryInfo(HTTP_QUERY_CONTENT_TYPE, contentType,
+ &bufSize, 0, NULL);
+ if (SUCCEEDED(hr)) {
+ char charset[CHARSET_MAX];
+ getXMLCharset(contentType, charset);
+ if (charset[0]) {
+#ifdef XML_UNICODE
+ XML_Char wcharset[CHARSET_MAX];
+ XML_Char *p1 = wcharset;
+ const char *p2 = charset;
+ while ((*p1++ = (unsigned char)*p2++) != 0)
+ ;
+ XML_SetEncoding(parser_, wcharset);
+#else
+ XML_SetEncoding(parser_, charset);
+#endif
+ }
+ }
+ hp->Release();
+ }
+ }
+ if (!parser_)
+ return E_ABORT;
+ if (pstgmed->tymed == TYMED_ISTREAM) {
+ while (totalRead_ < dwSize) {
+#define READ_MAX (64*1024)
+ DWORD nToRead = dwSize - totalRead_;
+ if (nToRead > READ_MAX)
+ nToRead = READ_MAX;
+ void *buf = XML_GetBuffer(parser_, nToRead);
+ if (!buf) {
+ _ftprintf(stderr, _T("out of memory\n"));
+ return E_ABORT;
+ }
+ DWORD nRead;
+ HRESULT hr = pstgmed->pstm->Read(buf, nToRead, &nRead);
+ if (SUCCEEDED(hr)) {
+ totalRead_ += nRead;
+ if (!XML_ParseBuffer(parser_,
+ nRead,
+ (grfBSCF & BSCF_LASTDATANOTIFICATION) != 0
+ && totalRead_ == dwSize)) {
+ reportError(parser_);
+ return E_ABORT;
+ }
+ }
+ }
+ }
+ return S_OK;
+}
+
+STDMETHODIMP
+Callback::OnObjectAvailable(REFIID, IUnknown *)
+{
+ return S_OK;
+}
+
+int
+Callback::externalEntityRef(const XML_Char *context,
+ const XML_Char *systemId,
+ const XML_Char *publicId)
+{
+ XML_Parser entParser = XML_ExternalEntityParserCreate(parser_, context, 0);
+ XML_SetBase(entParser, systemId);
+ int ret = processURL(entParser, baseMoniker_, systemId);
+ XML_ParserFree(entParser);
+ return ret;
+}
+
+Callback::Callback(XML_Parser parser, IMoniker *baseMoniker,
+ StopHandler stopHandler, void *stopArg)
+: parser_(parser),
+ baseMoniker_(baseMoniker),
+ ref_(0),
+ pBinding_(0),
+ totalRead_(0),
+ stopHandler_(stopHandler),
+ stopArg_(stopArg)
+{
+ if (baseMoniker_)
+ baseMoniker_->AddRef();
+}
+
+Callback::~Callback()
+{
+ if (pBinding_)
+ pBinding_->Release();
+ if (baseMoniker_)
+ baseMoniker_->Release();
+}
+
+static int
+externalEntityRef(void *arg,
+ const XML_Char *context,
+ const XML_Char *base,
+ const XML_Char *systemId,
+ const XML_Char *publicId)
+{
+ return ((Callback *)arg)->externalEntityRef(context, systemId, publicId);
+}
+
+
+static HRESULT
+openStream(XML_Parser parser,
+ IMoniker *baseMoniker,
+ const XML_Char *uri,
+ StopHandler stopHandler, void *stopArg)
+{
+ if (!XML_SetBase(parser, uri))
+ return E_OUTOFMEMORY;
+ HRESULT hr;
+ IMoniker *m;
+#ifdef XML_UNICODE
+ hr = CreateURLMoniker(0, uri, &m);
+#else
+ LPWSTR uriw = new wchar_t[strlen(uri) + 1];
+ for (int i = 0;; i++) {
+ uriw[i] = uri[i];
+ if (uriw[i] == 0)
+ break;
+ }
+ hr = CreateURLMoniker(baseMoniker, uriw, &m);
+ delete [] uriw;
+#endif
+ if (FAILED(hr))
+ return hr;
+ IBindStatusCallback *cb = new Callback(parser, m, stopHandler, stopArg);
+ XML_SetExternalEntityRefHandler(parser, externalEntityRef);
+ XML_SetExternalEntityRefHandlerArg(parser, cb);
+ cb->AddRef();
+ IBindCtx *b;
+ if (FAILED(hr = CreateAsyncBindCtx(0, cb, 0, &b))) {
+ cb->Release();
+ m->Release();
+ return hr;
+ }
+ cb->Release();
+ IStream *pStream;
+ hr = m->BindToStorage(b, 0, IID_IStream, (void **)&pStream);
+ if (SUCCEEDED(hr)) {
+ if (pStream)
+ pStream->Release();
+ }
+ if (hr == MK_S_ASYNCHRONOUS)
+ hr = S_OK;
+ m->Release();
+ b->Release();
+ return hr;
+}
+
+struct QuitInfo {
+ const XML_Char *url;
+ HRESULT hr;
+ int stop;
+};
+
+static void
+winPerror(const XML_Char *url, HRESULT hr)
+{
+ LPVOID buf;
+ if (FormatMessage(FORMAT_MESSAGE_ALLOCATE_BUFFER
+ | FORMAT_MESSAGE_FROM_HMODULE,
+ GetModuleHandleA("urlmon.dll"),
+ hr,
+ MAKELANGID(LANG_NEUTRAL, SUBLANG_DEFAULT),
+ (LPTSTR) &buf,
+ 0,
+ NULL)
+ || FormatMessage(FORMAT_MESSAGE_ALLOCATE_BUFFER
+ | FORMAT_MESSAGE_FROM_SYSTEM,
+ 0,
+ hr,
+ MAKELANGID(LANG_NEUTRAL, SUBLANG_DEFAULT),
+ (LPTSTR) &buf,
+ 0,
+ NULL)) {
+ /* The system error messages seem to end with a newline. */
+ _ftprintf(stderr, _T("%s: %s"), url, buf);
+ fflush(stderr);
+ LocalFree(buf);
+ }
+ else
+ _ftprintf(stderr, _T("%s: error %x\n"), url, hr);
+}
+
+static void
+threadQuit(void *p, HRESULT hr)
+{
+ QuitInfo *qi = (QuitInfo *)p;
+ qi->hr = hr;
+ qi->stop = 1;
+}
+
+extern "C"
+int
+XML_URLInit(void)
+{
+ return SUCCEEDED(CoInitialize(0));
+}
+
+extern "C"
+void
+XML_URLUninit(void)
+{
+ CoUninitialize();
+}
+
+static int
+processURL(XML_Parser parser, IMoniker *baseMoniker,
+ const XML_Char *url)
+{
+ QuitInfo qi;
+ qi.stop = 0;
+ qi.url = url;
+
+ XML_SetBase(parser, url);
+ HRESULT hr = openStream(parser, baseMoniker, url, threadQuit, &qi);
+ if (FAILED(hr)) {
+ winPerror(url, hr);
+ return 0;
+ }
+ else if (FAILED(qi.hr)) {
+ winPerror(url, qi.hr);
+ return 0;
+ }
+ MSG msg;
+ while (!qi.stop && GetMessage (&msg, NULL, 0, 0)) {
+ TranslateMessage (&msg);
+ DispatchMessage (&msg);
+ }
+ return 1;
+}
+
+extern "C"
+int
+XML_ProcessURL(XML_Parser parser,
+ const XML_Char *url,
+ unsigned flags)
+{
+ return processURL(parser, 0, url);
+}