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
This commit is contained in:
Joseph Myers 2009-05-03 12:59:26 +01:00 committed by Joseph Myers
parent aea88c05c9
commit 9e322bc1a5
4 changed files with 27 additions and 1 deletions

View file

@ -169,7 +169,7 @@ static inline int
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;