glibc/posix/bug-regex28.c
Adhemerval Zanella 6951b6ac39 posix: Sync gnulib regex implementation
This patch syncs the regex implementation with gnulib (commit 0ee5212).
Only two changes in GLIBC regex testing are required:

  1. posix/bug-regex28.c: as previously discussed [1] the change of
     expected results on the pattern should be safe.

  2. posix/PCRE.tests: the ERE (a)|\1 is malformed (in the sense that
     the \1 doesn't mean anything) and although current GLIBC accepts
     it has undefined behavior.  This patch removes the specific test.

This sync contains some patches from thread 'Regex: Make libc regex
more usable outside GLIBC.' [2] which have been pushed upstream in
gnulib.  This patches also fixes some regex issues (BZ #23233,
BZ #21163, BZ #18986, BZ #13762) and I did not add testcases for
both #23233 and #13762 because I couldn't think a simple way to
trigger the expected failure path to trigger them.

Checked on x86_64-linux-gnu and i686-linux-gnu.

	[BZ #23233]
	[BZ #21163]
	[BZ #18986]
	[BZ #13762]
	* posix/Makefile (tests): Add bug-regex37 and bug-regex38.
	* posix/PCRE.tests: Remove invalid test.
	* posix/bug-regex28.c: Fix expected values for used syntax.
	* posix/bug-regex37.c: New file.
	* posix/bug-regex38.c: Likewise.
	* posix/regcomp.c: Sync with gnulib.
	* posix/regex.c: Likewise.
	* posix/regex.h: Likewise.
	* posix/regex_internal.c: Likewise.
	* posix/regex_internal.h: Likewise.
	* posix/regexec.c: Likewise.

[1] https://sourceware.org/ml/libc-alpha/2017-12/msg00807.html
[2] https://sourceware.org/ml/libc-alpha/2017-12/msg00237.html
2021-08-27 17:26:07 -07:00

79 lines
2.4 KiB
C

/* Test RE_HAT_LISTS_NOT_NEWLINE and RE_DOT_NEWLINE.
Copyright (C) 2007-2018 Free Software Foundation, Inc.
This file is part of the GNU C Library.
Contributed by Jakub Jelinek <jakub@redhat.com>, 2007.
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
<http://www.gnu.org/licenses/>. */
#include <regex.h>
#include <stdio.h>
#include <string.h>
#include <support/test-driver.h>
#include <support/check.h>
struct tests
{
const char *regex;
const char *string;
reg_syntax_t syntax;
int retval;
};
static const struct tests tests[] = {
#define EGREP RE_SYNTAX_EGREP
#define EGREP_NL (RE_SYNTAX_EGREP | RE_DOT_NEWLINE) & ~RE_HAT_LISTS_NOT_NEWLINE
{ "a.b", "a\nb", EGREP, 0 },
{ "a.b", "a\nb", EGREP_NL, 0 },
{ "a[^x]b", "a\nb", EGREP, 0 },
{ "a[^x]b", "a\nb", EGREP_NL, 0 },
/* While \S and \W are internally handled as [^[:space:]] and [^[:alnum:]_],
RE_HAT_LISTS_NOT_NEWLINE did not make any difference, so ensure
it doesn't change. */
{ "a\\Sb", "a\nb", EGREP, -1 },
{ "a\\Sb", "a\nb", EGREP_NL, -1 },
{ "a\\Wb", "a\nb", EGREP, 0 },
{ "a\\Wb", "a\nb", EGREP_NL, 0 }
};
static const size_t tests_size = sizeof (tests) / sizeof (tests[0]);
static int
do_test (void)
{
struct re_pattern_buffer r;
for (size_t i = 0; i < tests_size; i++)
{
re_set_syntax (tests[i].syntax);
memset (&r, 0, sizeof (r));
const char *re = re_compile_pattern (tests[i].regex,
strlen (tests[i].regex), &r);
TEST_VERIFY (re == NULL);
if (re != NULL)
continue;
size_t len = strlen (tests[i].string);
int rv = re_search (&r, tests[i].string, len, 0, len, NULL);
TEST_VERIFY (rv == tests[i].retval);
if (test_verbose > 0)
printf ("info: i=%zu rv=%d expected=%d\n", i, rv, tests[i].retval);
regfree (&r);
}
return 0;
}
#include <support/test-driver.c>