lib/glibc
1
0
Fork 0
mirror of https://sourceware.org/git/glibc.git synced 2025-07-29 11:41:21 +03:00
Code Activity

Fix ranges with multibyte characters as endpoints.

Browse Source 
This is another bug in computing the fastmap.  It was reported by a user
of sed because it usually does not happen with !_LIBC.  However, it is
there in that case too.

The bug is that whenever we have a range at the beginning of the regex,
the regex must be tested on any possible multibyte character.  The reason
why _LIBC masks it, is that in general there is a collation symbol for
each possible multibyte-character lead byte, so all the lead bytes are
in general already part of the fastmap.

The tests use cyrillic characters as an example.  With _LIBC, they pass
without the patch too, but you can make them fail by removing collation
symbols handling.
This commit is contained in:
Paolo Bonzini
2009-11-17 16:23:24 -08:00
committed by Ulrich Drepper
parent 7443244740
commit 815d8147a3
4 changed files with 114 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

103
posix/bug-regex30.c Normal file
View File

@ -0,0 +1,103 @@
/* Russian regular expression tests.
Copyright (C) 2009 Free Software Foundation, Inc.
This file is part of the GNU C Library.
Contributed by Paolo Bonzini <pbonzini@redhat.com>, 2009.
The GNU C Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
The GNU C Library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with the GNU C Library; if not, write to the Free
Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
02111-1307 USA. */
#include <sys/types.h>
#include <mcheck.h>
#include <regex.h>
#include <stdio.h>
#include <stdlib.h>
#include <locale.h>
/* Tests supposed to match. */
struct
{
const char *pattern;
const char *string;
int flags, nmatch;
regmatch_t rm[5];
} tests[] = {
/* U+0413 \xd0\x93 CYRILLIC CAPITAL LETTER GHE
U+0420 \xd0\xa0 CYRILLIC CAPITAL LETTER ER
U+0430 \xd0\xb0 CYRILLIC SMALL LETTER A
U+0433 \xd0\xb3 CYRILLIC SMALL LETTER GHE
U+0440 \xd1\x80 CYRILLIC SMALL LETTER ER
U+044F \xd1\x8f CYRILLIC SMALL LETTER YA */
{ "[\xd0\xb0-\xd1\x8f]", "\xd0\xb3", 0, 1,
{ { 0, 2 } } },
{ "[\xd0\xb0-\xd1\x8f]", "\xd0\x93", REG_ICASE, 1,
{ { 0, 2 } } },
{ "[\xd1\x80-\xd1\x8f]", "\xd0\xa0", REG_ICASE, 1,
{ { 0, 2 } } },
};
static int
do_test (void)
{
if (setlocale (LC_ALL, "de_DE.UTF-8") == NULL)
{
puts ("setlocale failed");
return 1;
}
int ret = 0;
for (size_t i = 0; i < sizeof (tests) / sizeof (tests[0]); ++i)
{
regex_t re;
regmatch_t rm[5];
int n = regcomp (&re, tests[i].pattern, tests[i].flags);
if (n != 0)
{
char buf[500];
regerror (n, &re, buf, sizeof (buf));
printf ("regcomp %zd failed: %s\n", i, buf);
ret = 1;
continue;
}
if (regexec (&re, tests[i].string, tests[i].nmatch, rm, 0))
{
printf ("regexec %zd failed\n", i);
ret = 1;
regfree (&re);
continue;
}
for (n = 0; n < tests[i].nmatch; ++n)
if (rm[n].rm_so != tests[i].rm[n].rm_so
|| rm[n].rm_eo != tests[i].rm[n].rm_eo)
{
if (tests[i].rm[n].rm_so == -1 && tests[i].rm[n].rm_eo == -1)
break;
printf ("regexec match failure rm[%d] %d..%d\n",
n, rm[n].rm_so, rm[n].rm_eo);
ret = 1;
break;
}
regfree (&re);
}
return ret;
}
#define TEST_FUNCTION do_test ()
#include "../test-skeleton.c"