mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-25 06:20:06 +00:00
466f2be6c0
We add a new C.UTF-8 locale. This locale is not builtin to glibc, but is provided as a distinct locale. The locale provides full support for UTF-8 and this includes full code point sorting via STRCMP-based collation (strcmp or wcscmp). The collation uses a new keyword 'codepoint_collation' which drops all collation rules and generates an empty zero rules collation to enable STRCMP usage in collation. This ensures that we get full code point sorting for C.UTF-8 with a minimal 1406 bytes of overhead (LC_COLLATE structure information and ASCII collating tables). The new locale is added to SUPPORTED. Minimal test data for specific code points (minus those not supported by collate-test) is provided in C.UTF-8.in, and this verifies code point sorting is working reasonably across the range. The locale was tested manually with the full set of code points without failure. The locale is harmonized with locales already shipping in various downstream distributions. A new tst-iconv9 test is added which verifies the C.UTF-8 locale is generally usable. Testing for fnmatch, regexec, and recomp is provided by extending bug-regex1, bugregex19, bug-regex4, bug-regex6, transbug, tst-fnmatch, tst-regcomp-truncated, and tst-regex to use C.UTF-8. Tested on x86_64 or i686 without regression. Reviewed-by: Florian Weimer <fweimer@redhat.com>
75 lines
2.1 KiB
C
75 lines
2.1 KiB
C
/* Test for regexec.
|
|
Copyright (C) 2002-2021 Free Software Foundation, Inc.
|
|
This file is part of the GNU C Library.
|
|
|
|
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, see
|
|
<https://www.gnu.org/licenses/>. */
|
|
|
|
#include <locale.h>
|
|
#include <stdio.h>
|
|
#include <string.h>
|
|
#include <sys/types.h>
|
|
#include <regex.h>
|
|
|
|
|
|
int
|
|
main (int argc, char *argv[])
|
|
{
|
|
regex_t re;
|
|
regmatch_t mat[10];
|
|
int i, j, ret = 0;
|
|
const char *locales[] = { "C", "C.UTF-8", "de_DE.UTF-8" };
|
|
const char *string = "http://www.regex.com/pattern/matching.html#intro";
|
|
regmatch_t expect[10] = {
|
|
{ 0, 48 }, { 0, 5 }, { 0, 4 }, { 5, 20 }, { 7, 20 }, { 20, 42 },
|
|
{ -1, -1 }, { -1, -1 }, { 42, 48 }, { 43, 48 } };
|
|
|
|
for (i = 0; i < sizeof (locales) / sizeof (locales[0]); ++i)
|
|
{
|
|
if (setlocale (LC_ALL, locales[i]) == NULL)
|
|
{
|
|
puts ("cannot set locale");
|
|
ret = 1;
|
|
}
|
|
else if (regcomp (&re,
|
|
"^(([^:/?#]+):)?(//([^/?#]*))?([^?#]*)(\\?([^#]*))?(#(.*))?",
|
|
REG_EXTENDED) != REG_NOERROR)
|
|
{
|
|
puts ("cannot compile the regular expression");
|
|
ret = 1;
|
|
}
|
|
else if (regexec (&re, string, 10, mat, 0) == REG_NOMATCH)
|
|
{
|
|
puts ("no match");
|
|
ret = 1;
|
|
}
|
|
else
|
|
{
|
|
if (! memcmp (mat, expect, sizeof (mat)))
|
|
printf ("matching ok for %s locale\n", locales[i]);
|
|
else
|
|
{
|
|
printf ("matching failed for %s locale:\n", locales[i]);
|
|
ret = 1;
|
|
for (j = 0; j < 9; ++j)
|
|
if (mat[j].rm_so != -1)
|
|
printf ("%d: %.*s\n", j, mat[j].rm_eo - mat[j].rm_so,
|
|
string + mat[j].rm_so);
|
|
}
|
|
}
|
|
}
|
|
|
|
return ret;
|
|
}
|