2001-05-14 09:25:37 +00:00
|
|
|
/* Test for re_search_2.
|
2023-01-06 21:08:04 +00:00
|
|
|
Copyright (C) 2001-2023 Free Software Foundation, Inc.
|
2001-07-06 04:58:11 +00:00
|
|
|
This file is part of the GNU C Library.
|
2001-05-14 09:25:37 +00:00
|
|
|
|
|
|
|
The GNU C Library is free software; you can redistribute it and/or
|
2001-07-06 04:58:11 +00:00
|
|
|
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.
|
2001-05-14 09:25:37 +00:00
|
|
|
|
|
|
|
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
|
2001-07-06 04:58:11 +00:00
|
|
|
Lesser General Public License for more details.
|
2001-05-14 09:25:37 +00:00
|
|
|
|
2001-07-06 04:58:11 +00:00
|
|
|
You should have received a copy of the GNU Lesser General Public
|
2012-02-09 23:18:22 +00:00
|
|
|
License along with the GNU C Library; if not, see
|
Prefer https to http for gnu.org and fsf.org URLs
Also, change sources.redhat.com to sourceware.org.
This patch was automatically generated by running the following shell
script, which uses GNU sed, and which avoids modifying files imported
from upstream:
sed -ri '
s,(http|ftp)(://(.*\.)?(gnu|fsf|sourceware)\.org($|[^.]|\.[^a-z])),https\2,g
s,(http|ftp)(://(.*\.)?)sources\.redhat\.com($|[^.]|\.[^a-z]),https\2sourceware.org\4,g
' \
$(find $(git ls-files) -prune -type f \
! -name '*.po' \
! -name 'ChangeLog*' \
! -path COPYING ! -path COPYING.LIB \
! -path manual/fdl-1.3.texi ! -path manual/lgpl-2.1.texi \
! -path manual/texinfo.tex ! -path scripts/config.guess \
! -path scripts/config.sub ! -path scripts/install-sh \
! -path scripts/mkinstalldirs ! -path scripts/move-if-change \
! -path INSTALL ! -path locale/programs/charmap-kw.h \
! -path po/libc.pot ! -path sysdeps/gnu/errlist.c \
! '(' -name configure \
-execdir test -f configure.ac -o -f configure.in ';' ')' \
! '(' -name preconfigure \
-execdir test -f preconfigure.ac ';' ')' \
-print)
and then by running 'make dist-prepare' to regenerate files built
from the altered files, and then executing the following to cleanup:
chmod a+x sysdeps/unix/sysv/linux/riscv/configure
# Omit irrelevant whitespace and comment-only changes,
# perhaps from a slightly-different Autoconf version.
git checkout -f \
sysdeps/csky/configure \
sysdeps/hppa/configure \
sysdeps/riscv/configure \
sysdeps/unix/sysv/linux/csky/configure
# Omit changes that caused a pre-commit check to fail like this:
# remote: *** error: sysdeps/powerpc/powerpc64/ppc-mcount.S: trailing lines
git checkout -f \
sysdeps/powerpc/powerpc64/ppc-mcount.S \
sysdeps/unix/sysv/linux/s390/s390-64/syscall.S
# Omit change that caused a pre-commit check to fail like this:
# remote: *** error: sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S: last line does not end in newline
git checkout -f sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S
2019-09-07 05:40:42 +00:00
|
|
|
<https://www.gnu.org/licenses/>. */
|
2001-05-14 09:25:37 +00:00
|
|
|
|
|
|
|
#include <locale.h>
|
|
|
|
#include <stdio.h>
|
|
|
|
#include <string.h>
|
|
|
|
#include <regex.h>
|
|
|
|
|
|
|
|
int
|
|
|
|
main (void)
|
|
|
|
{
|
|
|
|
struct re_pattern_buffer regex;
|
|
|
|
const char *s;
|
|
|
|
int match[3];
|
|
|
|
int result = 0;
|
|
|
|
|
|
|
|
memset (®ex, '\0', sizeof (regex));
|
|
|
|
|
Add generic C.UTF-8 locale (Bug 17318)
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>
2021-09-01 19:19:19 +00:00
|
|
|
printf ("INFO: Checking C.\n");
|
2001-05-14 09:25:37 +00:00
|
|
|
setlocale (LC_ALL, "C");
|
|
|
|
|
Add generic C.UTF-8 locale (Bug 17318)
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>
2021-09-01 19:19:19 +00:00
|
|
|
s = re_compile_pattern ("ab[cde]", 7, ®ex);
|
|
|
|
if (s != NULL)
|
|
|
|
{
|
|
|
|
puts ("re_compile_pattern returned non-NULL value");
|
|
|
|
result = 1;
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
match[0] = re_search_2 (®ex, "xyabez", 6, "", 0, 1, 5, NULL, 6);
|
|
|
|
match[1] = re_search_2 (®ex, NULL, 0, "abc", 3, 0, 3, NULL, 3);
|
|
|
|
match[2] = re_search_2 (®ex, "xya", 3, "bd", 2, 2, 3, NULL, 5);
|
|
|
|
if (match[0] != 2 || match[1] != 0 || match[2] != 2)
|
|
|
|
{
|
|
|
|
printf ("re_search_2 returned %d,%d,%d, expected 2,0,2\n",
|
|
|
|
match[0], match[1], match[2]);
|
|
|
|
result = 1;
|
|
|
|
}
|
|
|
|
else
|
|
|
|
puts (" -> OK");
|
|
|
|
}
|
|
|
|
|
|
|
|
printf ("INFO: Checking C.UTF-8.\n");
|
|
|
|
setlocale (LC_ALL, "C.UTF-8");
|
|
|
|
|
2001-05-14 09:25:37 +00:00
|
|
|
s = re_compile_pattern ("ab[cde]", 7, ®ex);
|
|
|
|
if (s != NULL)
|
|
|
|
{
|
2002-07-27 08:28:46 +00:00
|
|
|
puts ("re_compile_pattern returned non-NULL value");
|
2001-05-14 09:25:37 +00:00
|
|
|
result = 1;
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
2003-04-08 01:23:29 +00:00
|
|
|
match[0] = re_search_2 (®ex, "xyabez", 6, "", 0, 1, 5, NULL, 6);
|
2001-05-14 09:25:37 +00:00
|
|
|
match[1] = re_search_2 (®ex, NULL, 0, "abc", 3, 0, 3, NULL, 3);
|
2003-04-08 01:23:29 +00:00
|
|
|
match[2] = re_search_2 (®ex, "xya", 3, "bd", 2, 2, 3, NULL, 5);
|
2001-05-14 09:25:37 +00:00
|
|
|
if (match[0] != 2 || match[1] != 0 || match[2] != 2)
|
|
|
|
{
|
2002-07-27 08:28:46 +00:00
|
|
|
printf ("re_search_2 returned %d,%d,%d, expected 2,0,2\n",
|
2001-05-14 09:25:37 +00:00
|
|
|
match[0], match[1], match[2]);
|
|
|
|
result = 1;
|
|
|
|
}
|
|
|
|
else
|
|
|
|
puts (" -> OK");
|
|
|
|
}
|
|
|
|
|
|
|
|
return result;
|
|
|
|
}
|