-#serial 30
+# serial 59
-# Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2003, 2004, 2005 Free
-# Software Foundation, Inc.
+# Copyright (C) 1996-2001, 2003-2011 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
AC_DEFUN([gl_REGEX],
[
- AC_REQUIRE([AC_SYS_LARGEFILE]) dnl for a sufficently-wide off_t
- AC_DEFINE([_REGEX_LARGE_OFFSETS], 1,
- [Define if you want regoff_t to be at least as wide POSIX requires.])
-
- AC_LIBSOURCES(
- [regcomp.c, regex.c, regex.h,
- regex_internal.c, regex_internal.h, regexec.c])
-
AC_ARG_WITH([included-regex],
- [AC_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)])])
+ [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
+ 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 the
+ # 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. The first failing regular expression is from `Spencer ere
- # test #75' in grep-2.3.
+ # regex.c.
AC_CACHE_CHECK([for working re_compile_pattern],
- [gl_cv_func_re_compile_pattern_broken],
+ [gl_cv_func_re_compile_pattern_working],
[AC_RUN_IFELSE(
- [AC_LANG_PROGRAM(
- [AC_INCLUDES_DEFAULT
- #include <regex.h>],
- [[static struct re_pattern_buffer regex;
- const char *s;
- struct re_registers regs;
- /* Use the POSIX-compliant spelling with leading REG_,
- rather than the traditional GNU spelling with leading RE_,
- so that we reject older libc implementations. */
- re_set_syntax (REG_SYNTAX_POSIX_EGREP);
- memset (®ex, 0, sizeof (regex));
- s = re_compile_pattern ("a[:@:>@:]b\n", 9, ®ex);
- /* This should fail with _Invalid character class name_ error. */
- if (!s)
- exit (1);
-
- /* This should succeed, but does not for e.g. glibc-2.1.3. */
- memset (®ex, 0, sizeof (regex));
- s = re_compile_pattern ("{1", 2, ®ex);
-
- if (s)
- exit (1);
-
- /* The following example is derived from a problem report
- against gawk from Jorge Stolfi <stolfi@ic.unicamp.br>. */
- memset (®ex, 0, sizeof (regex));
- s = re_compile_pattern ("[an\371]*n", 7, ®ex);
- if (s)
- exit (1);
-
- /* This should match, but does not for e.g. glibc-2.2.1. */
- if (re_match (®ex, "an", 2, 0, ®s) != 2)
- exit (1);
-
- memset (®ex, 0, sizeof (regex));
- s = re_compile_pattern ("x", 1, ®ex);
- if (s)
- exit (1);
-
- /* The version of regex.c in e.g. GNU libc-2.2.93 did not
- work with a negative RANGE argument. */
- if (re_search (®ex, "wxy", 3, 2, -2, ®s) != 1)
- exit (1);
-
- /* The version of regex.c in older versions of gnulib
- ignored REG_IGNORE_CASE (which was then called RE_ICASE).
- Detect that problem too. */
- memset (®ex, 0, sizeof (regex));
- re_set_syntax (REG_SYNTAX_EMACS | REG_IGNORE_CASE);
- s = re_compile_pattern ("x", 1, ®ex);
- if (s)
- exit (1);
-
- if (re_search (®ex, "WXY", 3, 0, 3, ®s) < 0)
- exit (1);
-
- /* REG_STARTEND was added to glibc on 2004-01-15.
- Reject older versions. */
- if (! REG_STARTEND)
- exit (1);
-
- /* Reject hosts whose regoff_t values are too narrow.
- These include glibc 2.3.5 on hosts with 64-bit off_t
- and 32-bit int, and Solaris 10 on hosts with 32-bit int
- and _FILE_OFFSET_BITS=64. */
- if (sizeof (regoff_t) < sizeof (off_t))
- exit (1);
-
- exit (0);]])],
- [gl_cv_func_re_compile_pattern_broken=no],
- [gl_cv_func_re_compile_pattern_broken=yes],
- dnl When crosscompiling, assume it is broken.
- [gl_cv_func_re_compile_pattern_broken=yes])])
- ac_use_included_regex=$gl_cv_func_re_compile_pattern_broken
+ [AC_LANG_PROGRAM(
+ [AC_INCLUDES_DEFAULT[
+ #include <locale.h>
+ #include <limits.h>
+ #include <regex.h>
+ ]],
+ [[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;
+
+ /* http://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. */
+ if (setlocale (LC_ALL, "en_US.UTF-8"))
+ {
+ 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 (®ex, 0, sizeof regex);
+ s = re_compile_pattern (pat, sizeof pat - 1, ®ex);
+ if (s)
+ result |= 1;
+ else if (re_search (®ex, data, sizeof data - 1,
+ 0, sizeof data - 1, ®s)
+ != -1)
+ result |= 1;
+ 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 (®ex, 0, sizeof regex);
+ s = re_compile_pattern ("a[^x]b", 6, ®ex);
+ if (s)
+ result |= 2;
+ /* This should fail, but succeeds for glibc-2.5. */
+ else if (re_search (®ex, "a\nb", 3, 0, 3, ®s) != -1)
+ result |= 2;
+
+ /* This regular expression is from Spencer ere test number 75
+ in grep-2.3. */
+ re_set_syntax (RE_SYNTAX_POSIX_EGREP);
+ memset (®ex, 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, ®ex);
+ /* This should fail with _Invalid character class name_ error. */
+ if (!s)
+ result |= 4;
+
+ /* 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 (®ex, 0, sizeof regex);
+ s = re_compile_pattern ("a[b-a]", 6, ®ex);
+ if (s == 0)
+ result |= 8;
+
+ /* This should succeed, but does not for glibc-2.1.3. */
+ memset (®ex, 0, sizeof regex);
+ s = re_compile_pattern ("{1", 2, ®ex);
+ if (s)
+ result |= 8;
+
+ /* The following example is derived from a problem report
+ against gawk from Jorge Stolfi <stolfi@ic.unicamp.br>. */
+ memset (®ex, 0, sizeof regex);
+ s = re_compile_pattern ("[an\371]*n", 7, ®ex);
+ if (s)
+ result |= 8;
+ /* This should match, but does not for glibc-2.2.1. */
+ else if (re_match (®ex, "an", 2, 0, ®s) != 2)
+ result |= 8;
+
+ memset (®ex, 0, sizeof regex);
+ s = re_compile_pattern ("x", 1, ®ex);
+ if (s)
+ result |= 8;
+ /* glibc-2.2.93 does not work with a negative RANGE argument. */
+ else if (re_search (®ex, "wxy", 3, 2, -2, ®s) != 1)
+ result |= 8;
+
+ /* 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 (®ex, 0, sizeof regex);
+ s = re_compile_pattern ("x", 1, ®ex);
+ if (s)
+ result |= 16;
+ else if (re_search (®ex, "WXY", 3, 0, 3, ®s) < 0)
+ result |= 16;
+
+ /* Catch a bug reported by Vin Shelton in
+ http://lists.gnu.org/archive/html/bug-coreutils/2007-06/msg00089.html
+ */
+ re_set_syntax (RE_SYNTAX_POSIX_BASIC
+ & ~RE_CONTEXT_INVALID_DUP
+ & ~RE_NO_EMPTY_RANGES);
+ memset (®ex, 0, sizeof regex);
+ s = re_compile_pattern ("[[:alnum:]_-]\\\\+$", 16, ®ex);
+ if (s)
+ result |= 32;
+
+ /* REG_STARTEND was added to glibc on 2004-01-15.
+ Reject older versions. */
+ if (! REG_STARTEND)
+ result |= 64;
+
+#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],
+ dnl When crosscompiling, assume it is not working.
+ [gl_cv_func_re_compile_pattern_working=no])])
+ 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_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_regerror if the replacement should be used.])
AC_DEFINE([regfree], [rpl_regfree],
[Define to rpl_regfree if the replacement should be used.])
- AC_LIBOBJ([regex])
- gl_PREREQ_REGEX
fi
])
# Prerequisites of lib/regex.c and lib/regex_internal.c.
AC_DEFUN([gl_PREREQ_REGEX],
[
- AC_REQUIRE([AC_GNU_SOURCE])
- AC_REQUIRE([gl_C_RESTRICT])
- AC_REQUIRE([AM_LANGINFO_CODESET])
- AC_CHECK_HEADERS_ONCE([locale.h wchar.h wctype.h])
- AC_CHECK_FUNCS_ONCE([isblank mbrtowc mempcpy wcrtomb wcscoll])
+ AC_REQUIRE([AC_USE_SYSTEM_EXTENSIONS])
+ AC_REQUIRE([AC_C_INLINE])
+ AC_REQUIRE([AC_C_RESTRICT])
+ AC_REQUIRE([AC_TYPE_MBSTATE_T])
+ AC_CHECK_HEADERS([libintl.h])
+ AC_CHECK_FUNCS_ONCE([isblank iswctype wcscoll])
+ AC_CHECK_DECLS([isblank], [], [], [#include <ctype.h>])
])