This is the mail archive of the libc-alpha@sources.redhat.com mailing list for the glibc project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

[PATCH] regex bug fix for gawk


Hi,

Attached patch is a test case and a fix for the bug Arnold told me.
In concretely, the RE "[0\-9]" incorrectly matches "1" when the syntax
contains RE_BACKSLASH_ESCAPE_IN_LISTS.

Would you please try the patch?

2002-10-21  Isamu Hasegawa  <isamu@yamato.ibm.com>

	* posix/Makefile: Add a test case for the bug reported by Aharon
	Robbins <arnold@skeeve.com>.
	* posix/bug-regex13.c: New file.
	* posix/regcomp.c (peek_token_bracket): Skip the byte already read.

-- 
Isamu Hasegawa
IBM Japan, Ltd.

diff -urNp libc-/posix/Makefile libc/posix/Makefile
--- libc-/posix/Makefile	2002-10-21 22:07:21.000000000 +0900
+++ libc/posix/Makefile	2002-10-21 22:08:24.000000000 +0900
@@ -73,7 +73,8 @@ tests		:= tstgetopt testfnm runtests run
 		   tst-truncate64 tst-fork tst-fnmatch tst-regexloc tst-dir \
 		   tst-chmod bug-regex1 bug-regex2 bug-regex3 bug-regex4 \
 		   tst-gnuglob tst-regex bug-regex5 bug-regex6 bug-regex7 \
-		   bug-regex8 bug-regex9 bug-regex10 bug-regex11 bug-regex12
+		   bug-regex8 bug-regex9 bug-regex10 bug-regex11 bug-regex12 \
+		   bug-regex13
 ifeq (yes,$(build-shared))
 test-srcs	:= globtest
 tests           += wordexp-test tst-exec tst-spawn
diff -urNp libc-/posix/bug-regex13.c libc/posix/bug-regex13.c
--- libc-/posix/bug-regex13.c	1970-01-01 09:00:00.000000000 +0900
+++ libc/posix/bug-regex13.c	2002-10-21 22:11:06.000000000 +0900
@@ -0,0 +1,75 @@
+/* Regular expression tests.
+   Copyright (C) 2002 Free Software Foundation, Inc.
+   This file is part of the GNU C Library.
+   Contributed by Isamu Hasegawa <isamu@yamato.ibm.com>, 2002.
+
+   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, write to the Free
+   Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
+   02111-1307 USA.  */
+
+#include <sys/types.h>
+#include <mcheck.h>
+#include <regex.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+struct
+{
+  int syntax;
+  const char *pattern;
+  const char *string;
+  int start;
+} tests[] = {
+  {RE_BACKSLASH_ESCAPE_IN_LISTS, "[0\\-9]", "1", -1}, /* It should not match.  */
+  {RE_BACKSLASH_ESCAPE_IN_LISTS, "[0\\-9]", "-", 0}, /* It should match.  */
+};
+
+int
+main (void)
+{
+  struct re_pattern_buffer regbuf;
+  const char *err;
+  size_t i;
+  int ret = 0;
+
+  mtrace ();
+
+  for (i = 0; i < sizeof (tests) / sizeof (tests[0]); ++i)
+    {
+      int start;
+      re_set_syntax (tests[i].syntax);
+      memset (&regbuf, '\0', sizeof (regbuf));
+      err = re_compile_pattern (tests[i].pattern, strlen (tests[i].pattern),
+                                &regbuf);
+      if (err != NULL)
+	{
+	  printf ("re_compile_pattern failed: %s\n", err);
+	  ret = 1;
+	  continue;
+	}
+
+      start = re_search (&regbuf, tests[i].string, strlen (tests[i].string),
+                         0, strlen (tests[i].string), NULL);
+      if (start != tests[i].start)
+	{
+	  printf ("re_search failed %d\n", start);
+	  ret = 1;
+	  regfree (&regbuf);
+	  continue;
+	}
+      regfree (&regbuf);
+    }
+
+  return ret;
+}
diff -urNp libc-/posix/regcomp.c libc/posix/regcomp.c
--- libc-/posix/regcomp.c	2002-10-21 22:07:15.000000000 +0900
+++ libc/posix/regcomp.c	2002-10-21 22:08:59.000000000 +0900
@@ -1690,7 +1690,8 @@ peek_token_bracket (token, input, syntax
     {
       /* In this case, '\' escape a character.  */
       unsigned char c2;
-      c2 = re_string_peek_byte (input, 1);
+      re_string_skip_bytes (input, 1);
+      c2 = re_string_peek_byte (input, 0);
       token->opr.c = c2;
       token->type = CHARACTER;
       return 1;


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]