mirror/emacs
1
0
Fork 0
mirror of https://git.savannah.gnu.org/git/emacs.git synced 2024-11-25 07:28:20 +00:00
Code Issues Releases Activity
e5b6c39f5d
emacs/m4/regex.m4
Paul Eggert 7ae091d933 Update from Gnulib by running admin/merge-gnulib
2024-05-11 18:46:26 -07:00

396 lines
15 KiB
Plaintext
Raw Blame History

# regex.m4
# serial 75
dnl Copyright (C) 1996-2001, 2003-2024 Free Software Foundation, Inc.
dnl This file is free software; the Free Software Foundation
dnl gives unlimited permission to copy and/or distribute it,
dnl with or without modifications, as long as this notice is preserved.
dnl Initially derived from code in GNU grep.
dnl Mostly written by Jim Meyering.
AC_PREREQ([2.50])
AC_DEFUN([gl_REGEX],
[
AC_REQUIRE([AC_CANONICAL_HOST]) dnl for cross-compiles
AC_ARG_WITH([included-regex],
[AS_HELP_STRING([[--without-included-regex]],
[don't compile regex; this is the default on systems
with recent-enough versions of the GNU C Library
(use with caution on other systems).])])
case $with_included_regex in #(
yes|no) ac_use_included_regex=$with_included_regex
;;
'')
# If the system regex support is good enough that it passes the
# following run test, then default to *not* using the included regex.c.
# If cross compiling, assume the test would fail and use the included
# regex.c.
AC_CHECK_DECLS_ONCE([alarm])
AC_CHECK_HEADERS_ONCE([malloc.h])
AC_CACHE_CHECK([for working re_compile_pattern],
[gl_cv_func_re_compile_pattern_working],
[AC_RUN_IFELSE(
[AC_LANG_PROGRAM(
[[#include <regex.h>
#include <locale.h>
#include <limits.h>
#include <string.h>
#if defined M_CHECK_ACTION || HAVE_DECL_ALARM
# include <signal.h>
# include <unistd.h>
#endif
#if HAVE_MALLOC_H
# include <malloc.h>
#endif
#ifdef M_CHECK_ACTION
/* Exit with distinguishable exit code. */
static void sigabrt_no_core (int sig) { raise (SIGTERM); }
#endif
]],
[[int result = 0;
static struct re_pattern_buffer regex;
unsigned char folded_chars[UCHAR_MAX + 1];
int i;
const char *s;
struct re_registers regs;
/* Some builds of glibc go into an infinite loop on this
test. Use alarm to force death, and mallopt to avoid
malloc recursion in diagnosing the corrupted heap. */
#if HAVE_DECL_ALARM
signal (SIGALRM, SIG_DFL);
alarm (2);
#endif
#ifdef M_CHECK_ACTION
signal (SIGABRT, sigabrt_no_core);
mallopt (M_CHECK_ACTION, 2);
#endif
if (setlocale (LC_ALL, "en_US.UTF-8"))
{
{
/* https://sourceware.org/ml/libc-hacker/2006-09/msg00008.html
This test needs valgrind to catch the bug on Debian
GNU/Linux 3.1 x86, but it might catch the bug better
on other platforms and it shouldn't hurt to try the
test here. */
static char const pat[] = "insert into";
static char const data[] =
"\xFF\0\x12\xA2\xAA\xC4\xB1,K\x12\xC4\xB1*\xACK";
re_set_syntax (RE_SYNTAX_GREP | RE_HAT_LISTS_NOT_NEWLINE
| RE_ICASE);
memset (&regex, 0, sizeof regex);
s = re_compile_pattern (pat, sizeof pat - 1, &regex);
if (s)
result |= 1;
else
{
if (re_search (&regex, data, sizeof data - 1,
0, sizeof data - 1, &regs)
!= -1)
result |= 1;
regfree (&regex);
}
}
{
/* This test is from glibc bug 15078.
The test case is from Andreas Schwab in
<https://sourceware.org/ml/libc-alpha/2013-01/msg00967.html>.
*/
static char const pat[] = "[^x]x";
static char const data[] =
/* <U1000><U103B><U103D><U1014><U103A><U102F><U1015><U103A> */
"\xe1\x80\x80"
"\xe1\x80\xbb"
"\xe1\x80\xbd"
"\xe1\x80\x94"
"\xe1\x80\xba"
"\xe1\x80\xaf"
"\xe1\x80\x95"
"\xe1\x80\xba"
"x";
re_set_syntax (0);
memset (&regex, 0, sizeof regex);
s = re_compile_pattern (pat, sizeof pat - 1, &regex);
if (s)
result |= 1;
else
{
i = re_search (&regex, data, sizeof data - 1,
0, sizeof data - 1, 0);
if (i != 0 && i != 21)
result |= 1;
regfree (&regex);
}
}
if (! setlocale (LC_ALL, "C"))
return 1;
}
/* This test is from glibc bug 3957, reported by Andrew Mackey. */
re_set_syntax (RE_SYNTAX_EGREP | RE_HAT_LISTS_NOT_NEWLINE);
memset (&regex, 0, sizeof regex);
s = re_compile_pattern ("a[^x]b", 6, &regex);
if (s)
result |= 2;
else
{
/* This should fail, but succeeds for glibc-2.5. */
if (re_search (&regex, "a\nb", 3, 0, 3, &regs) != -1)
result |= 2;
regfree (&regex);
}
/* This regular expression is from Spencer ere test number 75
in grep-2.3. */
re_set_syntax (RE_SYNTAX_POSIX_EGREP);
memset (&regex, 0, sizeof regex);
for (i = 0; i <= UCHAR_MAX; i++)
folded_chars[i] = i;
regex.translate = folded_chars;
s = re_compile_pattern ("a[[:@:>@:]]b\n", 11, &regex);
/* This should fail with _Invalid character class name_ error. */
if (!s)
{
result |= 4;
regfree (&regex);
}
/* Ensure that [b-a] is diagnosed as invalid, when
using RE_NO_EMPTY_RANGES. */
re_set_syntax (RE_SYNTAX_POSIX_EGREP | RE_NO_EMPTY_RANGES);
memset (&regex, 0, sizeof regex);
s = re_compile_pattern ("a[b-a]", 6, &regex);
if (s == 0)
{
result |= 8;
regfree (&regex);
}
/* This should succeed, but does not for glibc-2.1.3. */
memset (&regex, 0, sizeof regex);
s = re_compile_pattern ("{1", 2, &regex);
if (s)
result |= 8;
else
regfree (&regex);
/* The following example is derived from a problem report
against gawk from Jorge Stolfi <stolfi@ic.unicamp.br>. */
memset (&regex, 0, sizeof regex);
s = re_compile_pattern ("[an\371]*n", 7, &regex);
if (s)
result |= 8;
else
{
/* This should match, but does not for glibc-2.2.1. */
if (re_match (&regex, "an", 2, 0, &regs) != 2)
result |= 8;
else
{
free (regs.start);
free (regs.end);
}
regfree (&regex);
}
memset (&regex, 0, sizeof regex);
s = re_compile_pattern ("x", 1, &regex);
if (s)
result |= 8;
else
{
/* glibc-2.2.93 does not work with a negative RANGE argument. */
if (re_search (&regex, "wxy", 3, 2, -2, &regs) != 1)
result |= 8;
else
{
free (regs.start);
free (regs.end);
}
regfree (&regex);
}
/* The version of regex.c in older versions of gnulib
ignored RE_ICASE. Detect that problem too. */
re_set_syntax (RE_SYNTAX_EMACS | RE_ICASE);
memset (&regex, 0, sizeof regex);
s = re_compile_pattern ("x", 1, &regex);
if (s)
result |= 16;
else
{
if (re_search (&regex, "WXY", 3, 0, 3, &regs) < 0)
result |= 16;
else
{
free (regs.start);
free (regs.end);
}
regfree (&regex);
}
/* Catch a bug reported by Vin Shelton in
https://lists.gnu.org/r/bug-coreutils/2007-06/msg00089.html
*/
re_set_syntax (RE_SYNTAX_POSIX_BASIC
& ~RE_CONTEXT_INVALID_DUP
& ~RE_NO_EMPTY_RANGES);
memset (&regex, 0, sizeof regex);
s = re_compile_pattern ("[[:alnum:]_-]\\\\+\$", 16, &regex);
if (s)
result |= 32;
else
regfree (&regex);
/* REG_STARTEND was added to glibc on 2004-01-15.
Reject older versions. */
if (! REG_STARTEND)
result |= 64;
/* Matching with the compiled form of this regexp would provoke
an assertion failure prior to glibc-2.28:
regexec.c:1375: pop_fail_stack: Assertion 'num >= 0' failed
With glibc-2.28, compilation fails and reports the invalid
back reference. */
re_set_syntax (RE_SYNTAX_POSIX_EGREP);
memset (&regex, 0, sizeof regex);
s = re_compile_pattern ("0|()0|\\\\1|0", 10, &regex);
if (!s)
{
memset (&regs, 0, sizeof regs);
i = re_search (&regex, "x", 1, 0, 1, &regs);
if (i != -1)
result |= 64;
if (0 <= i)
{
free (regs.start);
free (regs.end);
}
regfree (&regex);
}
else
{
if (strcmp (s, "Invalid back reference"))
result |= 64;
}
/* glibc bug 11053. */
re_set_syntax (RE_SYNTAX_POSIX_BASIC);
memset (&regex, 0, sizeof regex);
static char const pat_sub2[] = "\\\\(a*\\\\)*a*\\\\1";
s = re_compile_pattern (pat_sub2, sizeof pat_sub2 - 1, &regex);
if (s)
result |= 64;
else
{
memset (&regs, 0, sizeof regs);
static char const data[] = "a";
int datalen = sizeof data - 1;
i = re_search (&regex, data, datalen, 0, datalen, &regs);
if (i != 0)
result |= 64;
else if (regs.num_regs < 2)
result |= 64;
else if (! (regs.start[0] == 0 && regs.end[0] == 1))
result |= 64;
else if (! (regs.start[1] == 0 && regs.end[1] == 0))
result |= 64;
regfree (&regex);
free (regs.start);
free (regs.end);
}
#if 0
/* It would be nice to reject hosts whose regoff_t values are too
narrow (including glibc on hosts with 64-bit ptrdiff_t and
32-bit int), but we should wait until glibc implements this
feature. Otherwise, support for equivalence classes and
multibyte collation symbols would always be broken except
when compiling --without-included-regex. */
if (sizeof (regoff_t) < sizeof (ptrdiff_t)
|| sizeof (regoff_t) < sizeof (ssize_t))
result |= 64;
#endif
return result;
]])],
[gl_cv_func_re_compile_pattern_working=yes],
[gl_cv_func_re_compile_pattern_working=no],
[case "$host_os" in
# Guess no on native Windows.
mingw* | windows*) gl_cv_func_re_compile_pattern_working="guessing no" ;;
# Otherwise obey --enable-cross-guesses.
*) gl_cv_func_re_compile_pattern_working="$gl_cross_guess_normal" ;;
esac
])
])
case "$gl_cv_func_re_compile_pattern_working" in #(
*yes) ac_use_included_regex=no;; #(
*no) ac_use_included_regex=yes;;
esac
;;
*) AC_MSG_ERROR([Invalid value for --with-included-regex: $with_included_regex])
;;
esac
if test $ac_use_included_regex = yes; then
AC_DEFINE([_REGEX_INCLUDE_LIMITS_H], [1],
[Define if you want <regex.h> to include <limits.h>, so that it
consistently overrides <limits.h>'s RE_DUP_MAX.])
AC_DEFINE([_REGEX_LARGE_OFFSETS], [1],
[Define if you want regoff_t to be at least as wide POSIX requires.])
AC_DEFINE([re_syntax_options], [rpl_re_syntax_options],
[Define to rpl_re_syntax_options if the replacement should be used.])
AC_DEFINE([re_set_syntax], [rpl_re_set_syntax],
[Define to rpl_re_set_syntax if the replacement should be used.])
AC_DEFINE([re_compile_pattern], [rpl_re_compile_pattern],
[Define to rpl_re_compile_pattern if the replacement should be used.])
AC_DEFINE([re_compile_fastmap], [rpl_re_compile_fastmap],
[Define to rpl_re_compile_fastmap if the replacement should be used.])
AC_DEFINE([re_search], [rpl_re_search],
[Define to rpl_re_search if the replacement should be used.])
AC_DEFINE([re_search_2], [rpl_re_search_2],
[Define to rpl_re_search_2 if the replacement should be used.])
AC_DEFINE([re_match], [rpl_re_match],
[Define to rpl_re_match if the replacement should be used.])
AC_DEFINE([re_match_2], [rpl_re_match_2],
[Define to rpl_re_match_2 if the replacement should be used.])
AC_DEFINE([re_set_registers], [rpl_re_set_registers],
[Define to rpl_re_set_registers if the replacement should be used.])
AC_DEFINE([re_comp], [rpl_re_comp],
[Define to rpl_re_comp if the replacement should be used.])
AC_DEFINE([re_exec], [rpl_re_exec],
[Define to rpl_re_exec if the replacement should be used.])
AC_DEFINE([regcomp], [rpl_regcomp],
[Define to rpl_regcomp if the replacement should be used.])
AC_DEFINE([regexec], [rpl_regexec],
[Define to rpl_regexec if the replacement should be used.])
AC_DEFINE([regerror], [rpl_regerror],
[Define to rpl_regerror if the replacement should be used.])
AC_DEFINE([regfree], [rpl_regfree],
[Define to rpl_regfree if the replacement should be used.])
fi
])
# Prerequisites of lib/regex.c and lib/regex_internal.c.
AC_DEFUN([gl_PREREQ_REGEX],
[
AC_REQUIRE([AC_USE_SYSTEM_EXTENSIONS])
AC_REQUIRE([AC_C_INLINE])
AC_REQUIRE([AC_C_RESTRICT])
AC_REQUIRE([AC_TYPE_MBSTATE_T])
AC_REQUIRE([gl_EEMALLOC])
AC_CHECK_HEADERS([libintl.h])
AC_CHECK_FUNCS_ONCE([isblank iswctype])
AC_CHECK_DECLS([isblank], [], [], [[#include <ctype.h>]])
])
Reference in New Issue View Git Blame Copy Permalink