coreutils-8.25HEADcoreutils-8.25master

1 files changed, 214 insertions, 134 deletions

diff --git a/m4/regex.m4 b/m4/regex.m4
index b8d5b1e..1996c47 100644
--- a/m4/regex.m4
+++ b/m4/regex.m4
@@ -1,7 +1,6 @@
-#serial 46
+# serial 65
 
-# Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2003, 2004, 2005,
-# 2006, 2007 Free Software Foundation, Inc.
+# Copyright (C) 1996-2001, 2003-2016 Free Software Foundation, Inc.
 #
 # This file is free software; the Free Software Foundation
 # gives unlimited permission to copy and/or distribute it,
@@ -14,142 +13,217 @@ AC_PREREQ([2.50])
 
 AC_DEFUN([gl_REGEX],
 [
-  AC_CHECK_HEADERS_ONCE([locale.h])
-
   AC_ARG_WITH([included-regex],
-    [AC_HELP_STRING([--without-included-regex],
-		    [don't compile regex; this is the default on 32-bit
-		     systems with recent-enough versions of the GNU C
-		     Library (use with caution on other systems).
-		     On systems with 64-bit ptrdiff_t and 32-bit int,
-		     --with-included-regex is the default, in case
-		     regex functions operate on very long strings (>2GB)])])
+    [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],
+                   [gl_cv_func_re_compile_pattern_working],
       [AC_RUN_IFELSE(
-	[AC_LANG_PROGRAM(
-	  [AC_INCLUDES_DEFAULT
-	   #if HAVE_LOCALE_H
-	    #include <locale.h>
-	   #endif
-	   #include <limits.h>
-	   #include <regex.h>
-	   ],
-	  [[static struct re_pattern_buffer regex;
-	    unsigned char folded_chars[UCHAR_MAX + 1];
-	    int i;
-	    const char *s;
-	    struct re_registers regs;
-
-	    #if HAVE_LOCALE_H
-	      /* 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 (&regex, 0, sizeof regex);
-		  s = re_compile_pattern (pat, sizeof pat - 1, &regex);
-		  if (s)
-		    return 1;
-		  if (re_search (&regex, data, sizeof data - 1,
-				 0, sizeof data - 1, &regs)
-		      != -1)
-		    return 1;
-		  if (! setlocale (LC_ALL, "C"))
-		    return 1;
-		}
-	    #endif
-
-	    /* 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)
-	      return 1;
-
-	    /* This should fail, but succeeds for glibc-2.5.  */
-	    if (re_search (&regex, "a\nb", 3, 0, 3, &regs) != -1)
-	      return 1;
-
-	    /* 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)
-	      return 1;
-
-	    /* 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)
-	      return 1;
-
-	    /* 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)
-	      return 1;
-
-	    /* This should match, but does not for glibc-2.2.1.  */
-	    if (re_match (&regex, "an", 2, 0, &regs) != 2)
-	      return 1;
-
-	    memset (&regex, 0, sizeof regex);
-	    s = re_compile_pattern ("x", 1, &regex);
-	    if (s)
-	      return 1;
-
-	    /* glibc-2.2.93 does not work with a negative RANGE argument.  */
-	    if (re_search (&regex, "wxy", 3, 2, -2, &regs) != 1)
-	      return 1;
-
-	    /* 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)
-	      return 1;
-
-	    if (re_search (&regex, "WXY", 3, 0, 3, &regs) < 0)
-	      return 1;
-
-	    /* REG_STARTEND was added to glibc on 2004-01-15.
-	       Reject older versions.  */
-	    if (! REG_STARTEND)
-	      return 1;
-
-	    /* Reject hosts whose regoff_t values are too narrow.
-	       These include glibc 2.3.5 on hosts with 64-bit ptrdiff_t
-	       and 32-bit int.  */
-	    if (sizeof (regoff_t) < sizeof (ptrdiff_t)
-		|| sizeof (regoff_t) < sizeof (ssize_t))
-	      return 1;
-
-	    return 0;]])],
+        [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"))
+              {
+                {
+                  /* 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 (&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;
+                }
+
+                {
+                  /* This test is from glibc bug 15078.
+                     The test case is from Andreas Schwab in
+                     <http://www.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;
+                    }
+                }
+
+                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;
+            /* This should fail, but succeeds for glibc-2.5.  */
+            else if (re_search (&regex, "a\nb", 3, 0, 3, &regs) != -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 (&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;
+
+            /* 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;
+
+            /* 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;
+
+            /* 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;
+            /* This should match, but does not for glibc-2.2.1.  */
+            else if (re_match (&regex, "an", 2, 0, &regs) != 2)
+              result |= 8;
+
+            memset (&regex, 0, sizeof regex);
+            s = re_compile_pattern ("x", 1, &regex);
+            if (s)
+              result |= 8;
+            /* glibc-2.2.93 does not work with a negative RANGE argument.  */
+            else if (re_search (&regex, "wxy", 3, 2, -2, &regs) != 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 (&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;
+
+            /* 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 (&regex, 0, sizeof regex);
+            s = re_compile_pattern ("[[:alnum:]_-]\\\\+$", 16, &regex);
+            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.
@@ -164,7 +238,10 @@ AC_DEFUN([gl_REGEX],
   esac
 
   if test $ac_use_included_regex = yes; then
-    AC_DEFINE([_REGEX_LARGE_OFFSETS], 1,
+    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.])
@@ -196,16 +273,19 @@ AC_DEFUN([gl_REGEX],
       [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([AC_USE_SYSTEM_EXTENSIONS])
+  AC_REQUIRE([AC_C_INLINE])
   AC_REQUIRE([AC_C_RESTRICT])
-  AC_CHECK_FUNCS_ONCE([iswctype mbrtowc wcrtomb wcscoll])
-  AC_CHECK_DECLS([isblank], [], [], [#include <ctype.h>])
+  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 <ctype.h>]])
 ])