charset.c (one_utf8_to_cppchar): Correct mask used for 5-byte UTF-8 sequences.
libcpp:
* charset.c (one_utf8_to_cppchar): Correct mask used for 5-byte
UTF-8 sequences.
gcc/testsuite:
* gcc.dg/cpp/utf8-5byte-1.c: New test.
From-SVN: r147073
diff --git a/libcpp/ChangeLog b/libcpp/ChangeLog
index 24f3f8d..a541b69 100644
--- a/libcpp/ChangeLog
+++ b/libcpp/ChangeLog
@@ -1,3 +1,8 @@
+2009-05-03 Joseph Myers <joseph@codesourcery.com>
+
+ * charset.c (one_utf8_to_cppchar): Correct mask used for 5-byte
+ UTF-8 sequences.
+
2009-04-25 Joseph Myers <joseph@codesourcery.com>
PR preprocessor/39559
diff --git a/libcpp/charset.c b/libcpp/charset.c
index e743b1e..f1da426 100644
--- a/libcpp/charset.c
+++ b/libcpp/charset.c
@@ -169,7 +169,7 @@
one_utf8_to_cppchar (const uchar **inbufp, size_t *inbytesleftp,
cppchar_t *cp)
{
- static const uchar masks[6] = { 0x7F, 0x1F, 0x0F, 0x07, 0x02, 0x01 };
+ static const uchar masks[6] = { 0x7F, 0x1F, 0x0F, 0x07, 0x03, 0x01 };
static const uchar patns[6] = { 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC };
cppchar_t c;