git
/
gcc
mirror of git://gcc.gnu.org/git/gcc.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

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
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
gcc/testsuite/ChangeLog
View File

@ -1,3 +1,7 @@
2009-05-03 Joseph Myers <joseph@codesourcery.com>
* gcc.dg/cpp/utf8-5byte-1.c: New test.
2009-05-02 Joseph Myers <joseph@codesourcery.com> 2009-05-02 Joseph Myers <joseph@codesourcery.com>
* gcc.dg/ucnid-6.c: Fix typo in dg-do directive. * gcc.dg/ucnid-6.c: Fix typo in dg-do directive.

17
gcc/testsuite/gcc.dg/cpp/utf8-5byte-1.c Normal file
View File

@ -0,0 +1,17 @@
/* Test for bug in conversions from 5-byte UTF-8 sequences in
cpplib. */
/* { dg-do run { target { 4byte_wchar_t } } } */
/* { dg-options "-std=gnu99" } */
extern void abort (void);
extern void exit (int);
__WCHAR_TYPE__ ws[] = L"û¿¿¿¿";
int
main (void)
{
if (ws[0] != L'\U03FFFFFF' || ws[1] != 0)
abort ();
exit (0);
}

5
libcpp/ChangeLog
View File

@ -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> 2009-04-25 Joseph Myers <joseph@codesourcery.com>
PR preprocessor/39559 PR preprocessor/39559

2
libcpp/charset.c
View File

@ -169,7 +169,7 @@ static inline int
one_utf8_to_cppchar (const uchar **inbufp, size_t *inbytesleftp, one_utf8_to_cppchar (const uchar **inbufp, size_t *inbytesleftp,
cppchar_t *cp) 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 }; static const uchar patns[6] = { 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC };
cppchar_t c; cppchar_t c;