summary refs log tree commit diff
path: root/posix/bug-regex19.c
diff options
context:
space:
mode:
authorUlrich Drepper <drepper@redhat.com>2003-11-12 17:47:46 +0000
committerUlrich Drepper <drepper@redhat.com>2003-11-12 17:47:46 +0000
commit3c0fb5745f66c8920ed4cfa8d3ead55216b15ec1 (patch)
treed993d46e33582e130e8324c5bd7fb7817d2a7f54 /posix/bug-regex19.c
parente432c0378ecfa545948d4be68190ab470446554b (diff)
downloadglibc-3c0fb5745f66c8920ed4cfa8d3ead55216b15ec1.tar.gz
glibc-3c0fb5745f66c8920ed4cfa8d3ead55216b15ec1.tar.xz
glibc-3c0fb5745f66c8920ed4cfa8d3ead55216b15ec1.zip
Update.
2003-11-12  Jakub Jelinek  <jakub@redhat.com>

	* io/ftw.c (NFTW_NEW_NAME, NFTW_OLD_NAME): Add prototypes.

2003-11-12  Jakub Jelinek  <jakub@redhat.com>

	* posix/tst-regex.c (umemlen): New variable.
	(test_expr): Add expectedicase argument.  Test case insensitive
	searches as well as backwards searches (case sensitive and
	insensitive) too.
	(run_test): Add icase argument.  Use it to compute regcomp flags.
	(run_test_backwards): New function.
	(main): Cast read to size_t to avoid warning.  Set umemlen.
	Add expectedicase arguments to test_expr.
	* posix/regex_internal.c (re_string_reconstruct): If is_utf8,
	find previous character by walking back instead of converting
	all chars from beginning.

2003-11-12  Jakub Jelinek  <jakub@redhat.com>

	* posix/regex_internal.h (struct re_string_t): Add is_utf8
	and mb_cur_max fields.
	(struct re_dfa_t): Likewise.  Reorder fields to make structure
	smaller on 64-bit arches.
	(re_string_allocate, re_string_construct): Add mb_cur_max and
	is_utf8 arguments.
	(re_string_char_size_at, re_string_wchar_at): Use pstr->mb_cur_max
	instead of MB_CUR_MAX.
	* posix/regcomp.c (re_compile_fastmap_iter): Use dfa->mb_cur_max
	instead of MB_CUR_MAX.
	(re_compile_internal): Pass new arguments to re_string_construct.
	(init_dfa): Initialize mb_cur_max and is_utf8 fields.
	(peek_token, peek_token_bracket): Use input->mb_cur_max instead
	of MB_CUR_MAX.
	(parse_expression, parse_bracket_exp, parse_charclass_op): Use
	dfa->mb_cur_max instead of MB_CUR_MAX.
	* posix/regex_internal.c (re_string_construct_common): Add
	mb_cur_max and is_utf8 arguments.  Initialize fields with them.
	(re_string_allocate, re_string_construct): Add mb_cur_max and
	is_utf8 arguments, pass them to re_string_construct_common.
	Use mb_cur_max instead of MB_CUR_MAX.
	(re_string_realloc_buffers): Use pstr->mb_cur_max instead of
	MB_CUR_MAX.
	(re_string_reconstruct): Likewise.
	(re_string_context_at): Use input->mb_cur_max instead of
	MB_CUR_MAX.
	(create_ci_newstate, create_cd_newstate): Use dfa->mb_cur_max
	instead of MB_CUR_MAX.
	* posix/regexec.c (re_search_internal): Likewise.
	Pass new arguments to re_string_allocate.
	(check_matching, transit_state_sb): Use dfa->mb_cur_max instead of
	MB_CUR_MAX.
	(extend_buffers): Use pstr->mb_cur_max instead of MB_CUR_MAX.

2003-11-12  Jakub Jelinek  <jakub@redhat.com>

	* posix/Makefile (tests): Add bug-regex19.
	(bug-regex19-ENV): Add LOCPATH.
	* posix/bug-regex19.c: New test.
Diffstat (limited to 'posix/bug-regex19.c')
-rw-r--r--posix/bug-regex19.c112
1 files changed, 112 insertions, 0 deletions
diff --git a/posix/bug-regex19.c b/posix/bug-regex19.c
new file mode 100644
index 0000000000..837ab654bc
--- /dev/null
+++ b/posix/bug-regex19.c
@@ -0,0 +1,112 @@
+/* Regular expression tests.
+   Copyright (C) 2003 Free Software Foundation, Inc.
+   This file is part of the GNU C Library.
+   Contributed by Jakub Jelinek <jakub@redhat.com>, 2003.
+
+   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>
+#include <string.h>
+#include <locale.h>
+
+static struct
+{
+  int syntax;
+  const char *pattern;
+  const char *string;
+  int start, res;
+} tests[] = {
+  /* \xc3\x84		LATIN CAPITAL LETTER A WITH DIAERESIS
+     \xc3\x96		LATIN CAPITAL LETTER O WITH DIAERESIS
+     \xe2\x80\x94	EM DASH  */
+  /* Should not match.  */
+  {RE_SYNTAX_POSIX_BASIC, "\\<A", "aOAA", 2, -1},
+  {RE_SYNTAX_POSIX_BASIC, "A\\>", "aAAO", 1, -1},
+  {RE_SYNTAX_POSIX_BASIC, "\\bA", "aOAA", 2, -1},
+  {RE_SYNTAX_POSIX_BASIC, "A\\b", "aAAO", 1, -1},
+  {RE_SYNTAX_POSIX_BASIC, "\\<\xc3\x84", "a\xc3\x96\xc3\x84\xc3\x84", 3, -1},
+  {RE_SYNTAX_POSIX_BASIC, "\xc3\x84\\>", "a\xc3\x84\xc3\x84\xc3\x96", 1, -1},
+#if 0
+  /* XXX Not used since they fail so far.  */
+  {RE_SYNTAX_POSIX_BASIC, "\\b\xc3\x84", "a\xc3\x96\xc3\x84\xc3\x84", 3, -1},
+  {RE_SYNTAX_POSIX_BASIC, "\xc3\x84\\b", "a\xc3\x84\xc3\x84\xc3\x96", 1, -1},
+#endif
+  /* Should match.  */
+  {RE_SYNTAX_POSIX_BASIC, "\\<A", "AA", 0, 0},
+  {RE_SYNTAX_POSIX_BASIC, "\\<A", "a-AA", 2, 2},
+  {RE_SYNTAX_POSIX_BASIC, "A\\>", "aAA-", 1, 2},
+  {RE_SYNTAX_POSIX_BASIC, "A\\>", "aAA", 1, 2},
+  {RE_SYNTAX_POSIX_BASIC, "\\bA", "AA", 0, 0},
+  {RE_SYNTAX_POSIX_BASIC, "\\bA", "a-AA", 2, 2},
+  {RE_SYNTAX_POSIX_BASIC, "A\\b", "aAA-", 1, 2},
+  {RE_SYNTAX_POSIX_BASIC, "A\\b", "aAA", 1, 2},
+#if 0
+  /* XXX Not used since they fail so far.  */
+  {RE_SYNTAX_POSIX_BASIC, "\\<\xc3\x84", "\xc3\x84\xc3\x84", 0, 0},
+  {RE_SYNTAX_POSIX_BASIC, "\\<\xc3\x84", "a\xe2\x80\x94\xc3\x84\xc3\x84", 4, 4},
+  {RE_SYNTAX_POSIX_BASIC, "\xc3\x84\\>", "a\xc3\x84\xc3\x84\xe2\x80\x94", 1, 3},
+  {RE_SYNTAX_POSIX_BASIC, "\xc3\x84\\>", "a\xc3\x84\xc3\x84", 1, 3},
+  {RE_SYNTAX_POSIX_BASIC, "\\b\xc3\x84", "\xc3\x84\xc3\x84", 0, 0},
+  {RE_SYNTAX_POSIX_BASIC, "\\b\xc3\x84", "a\xe2\x80\x94\xc3\x84\xc3\x84", 4, 4},
+  {RE_SYNTAX_POSIX_BASIC, "\xc3\x84\\b", "a\xc3\x84\xc3\x84\xe2\x80\x94", 1, 3},
+  {RE_SYNTAX_POSIX_BASIC, "\xc3\x84\\b", "a\xc3\x84\xc3\x84", 1, 3}
+#endif
+};
+
+int
+main (void)
+{
+  struct re_pattern_buffer regbuf;
+  const char *err;
+  size_t i;
+  int ret = 0;
+
+  mtrace ();
+
+  setlocale (LC_ALL, "de_DE.UTF-8");
+  for (i = 0; i < sizeof (tests) / sizeof (tests[0]); ++i)
+    {
+      int res;
+      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;
+	}
+
+      res = re_search (&regbuf, tests[i].string, strlen (tests[i].string),
+		       tests[i].start,
+		       strlen (tests[i].string) - tests[i].start, NULL);
+      if (res != tests[i].res)
+	{
+	  printf ("re_search %zd failed: %d\n", i, res);
+	  ret = 1;
+	  regfree (&regbuf);
+	  continue;
+	}
+      regfree (&regbuf);
+    }
+
+  return ret;
+}