X-Git-Url: http://erislabs.net/gitweb/?a=blobdiff_plain;f=m4%2Fregex.m4;h=08bd46a96d98c59c4a25b27b73b86f82a8c681ad;hb=1276a2c5f24c0c932426aca9c899fa524d2443f2;hp=3c35934e277ce74a9d904b4b4508982300f48102;hpb=e57b0bd6cce7d468a30356c0a2cdab8a0af58eca;p=gnulib.git diff --git a/m4/regex.m4 b/m4/regex.m4 index 3c35934e2..08bd46a96 100644 --- a/m4/regex.m4 +++ b/m4/regex.m4 @@ -1,118 +1,291 @@ -#serial 15 +# serial 65 + +# Copyright (C) 1996-2001, 2003-2014 Free Software Foundation, Inc. +# +# This file is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# 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], [ - jm_INCLUDED_REGEX([lib/regex.c]) -]) - -dnl Usage: jm_INCLUDED_REGEX([lib/regex.c]) -dnl -AC_DEFUN([jm_INCLUDED_REGEX], - [ - dnl Even packages that don't use regex.c can use this macro. - dnl Of course, for them it doesn't do anything. + 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).])]) - # Assume we'll default to using the included regex.c. - ac_use_included_regex=yes - - # However, if the system regex support is good enough that it passes the - # the following run test, then default to *not* using the included regex.c. + 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. The first failing regular expression is from `Spencer ere - # test #75' in grep-2.3. + # regex.c. + AC_CHECK_DECLS_ONCE([alarm]) + AC_CHECK_HEADERS_ONCE([malloc.h]) AC_CACHE_CHECK([for working re_compile_pattern], - jm_cv_func_working_re_compile_pattern, - AC_TRY_RUN( -[#include -#include -#include - int - main () - { - static struct re_pattern_buffer regex; - const char *s; - struct re_registers regs; - re_set_syntax (RE_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 doesn't 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 + [gl_cv_func_re_compile_pattern_working], + [AC_RUN_IFELSE( + [AC_LANG_PROGRAM( + [[#include + + #include + #include + #include + + #if defined M_CHECK_ACTION || HAVE_DECL_ALARM + # include + # include + #endif + + #if HAVE_MALLOC_H + # include + #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")) + { + { + /* 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. */ + 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; + } + + { + /* This test is from glibc bug 15078. + The test case is from Andreas Schwab in + . + */ + static char const pat[] = "[^x]x"; + static char const data[] = + /* */ + "\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 (®ex, 0, sizeof regex); + s = re_compile_pattern (pat, sizeof pat - 1, ®ex); + if (s) + result |= 1; + else + { + i = re_search (®ex, data, sizeof data - 1, + 0, sizeof data - 1, 0); + if (i != 0 && i != 21) + 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 . */ - memset (®ex, 0, sizeof (regex)); - s = re_compile_pattern ("[[anù]]*n", 7, ®ex); - if (s) - exit (1); - - /* This should match, but doesn't 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 didn't - work with a negative RANGE argument. */ - if (re_search (®ex, "wxy", 3, 2, -2, ®s) != 1) - exit (1); - - exit (0); - } - ], - jm_cv_func_working_re_compile_pattern=yes, - jm_cv_func_working_re_compile_pattern=no, - dnl When crosscompiling, assume it's broken. - jm_cv_func_working_re_compile_pattern=no)) - if test $jm_cv_func_working_re_compile_pattern = yes; then - ac_use_included_regex=no - fi - - test -n "$1" || AC_MSG_ERROR([missing argument]) - m4_syscmd([test -f $1]) - ifelse(m4_sysval, 0, - [ - AC_ARG_WITH(included-regex, - [ --without-included-regex don't compile regex; this is the default on - systems with version 2 of the GNU C library - (use with caution on other system)], - jm_with_regex=$withval, - jm_with_regex=$ac_use_included_regex) - if test "$jm_with_regex" = yes; then - AC_LIBOBJ(regex) - jm_PREREQ_REGEX - fi - ], - ) - ] -) - -# Prerequisites of lib/regex.c. -AC_DEFUN([jm_PREREQ_REGEX], + 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_INCLUDE_LIMITS_H], [1], + [Define if you want to include , so that it + consistently overrides '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], [ - dnl FIXME: Maybe provide a btowc replacement someday: Solaris 2.5.1 lacks it. - dnl FIXME: Check for wctype and iswctype, and and add -lw if necessary - dnl to get them. - - dnl Persuade glibc to declare mempcpy(). - AC_REQUIRE([AC_GNU_SOURCE]) - - AC_REQUIRE([AC_FUNC_ALLOCA]) - AC_REQUIRE([AC_HEADER_STDC]) - AC_CHECK_HEADERS_ONCE(limits.h string.h wchar.h wctype.h) - AC_CHECK_FUNCS_ONCE(isascii mempcpy) - AC_CHECK_FUNCS(btowc) + 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_REQUIRE([gl_GLIBC21]) + AC_CHECK_HEADERS([libintl.h]) + AC_CHECK_FUNCS_ONCE([isblank iswctype]) + AC_CHECK_DECLS([isblank], [], [], [[#include ]]) ])