* posix/regex_internal.c (re_string_skip_chars): If no character has

	been converted at all, set *last_wc to WEOF.  If mbrtowc failed, set wc
	to the byte which couldn't be converted.
	(re_string_reconstruct): Don't clear valid_raw_len before calling
	re_string_skip_chars.  If wc is WEOF after re_string_skip_chars, set
	tip_context using re_string_context_at.
	* posix/Makefile: Add rules to build and run bug-regex25 test.
	* posix/bug-regex25.c: New test.

diff --git a/ChangeLog b/ChangeLog
index c299adc3e3a8242e528a3ec16897f35d4cab8202..6999e7d1e761868b5fb773d8841e4395bb4a3176 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,14 @@
+2006-06-02  Jakub Jelinek  <jakub@redhat.com>
+
+       * posix/regex_internal.c (re_string_skip_chars): If no character has
+       been converted at all, set *last_wc to WEOF.  If mbrtowc failed, set wc
+       to the byte which couldn't be converted.
+       (re_string_reconstruct): Don't clear valid_raw_len before calling
+       re_string_skip_chars.  If wc is WEOF after re_string_skip_chars, set
+       tip_context using re_string_context_at.
+       * posix/Makefile: Add rules to build and run bug-regex25 test.
+       * posix/bug-regex25.c: New test.
+
 2006-06-02  Ryan S. Arnold  <rsa@us.ibm.com>
 
        [BZ #2703]

diff --git a/posix/Makefile b/posix/Makefile
index 418e1cbe5f5222296652cf535434ef0950642ddf..a9d99102ae1fca8ff89cc0e7950a1ad9b8b6111f 100644 (file)
--- a/posix/Makefile
+++ b/posix/Makefile
@@ -81,7 +81,7 @@ tests         := tstgetopt testfnm runtests runptests      \
                   bug-regex13 bug-regex14 bug-regex15 bug-regex16 \
                   bug-regex17 bug-regex18 bug-regex19 bug-regex20 \
                   bug-regex21 bug-regex22 bug-regex23 bug-regex24 \
-                  tst-nice tst-nanosleep tst-regex2 \
+                  bug-regex25 tst-nice tst-nanosleep tst-regex2 \
                   transbug tst-rxspencer tst-pcre tst-boost \
                   bug-ga1 tst-vfork1 tst-vfork2 tst-waitid \
                   tst-getaddrinfo2 bug-glob1 bug-glob2 tst-sysconf \
@@ -188,6 +188,7 @@ bug-regex19-ENV = LOCPATH=$(common-objpfx)localedata
 bug-regex20-ENV = LOCPATH=$(common-objpfx)localedata
 bug-regex22-ENV = LOCPATH=$(common-objpfx)localedata
 bug-regex23-ENV = LOCPATH=$(common-objpfx)localedata
+bug-regex25-ENV = LOCPATH=$(common-objpfx)localedata
 tst-rxspencer-ARGS = --utf8 rxspencer/tests
 tst-rxspencer-ENV = LOCPATH=$(common-objpfx)localedata
 tst-pcre-ARGS = PCRE.tests

diff --git a/posix/bug-regex25.c b/posix/bug-regex25.c
new file mode 100644 (file)
index 0000000..5e56e49
--- /dev/null
+++ b/posix/bug-regex25.c
@@ -0,0 +1,57 @@
+/* Test re_search in multibyte locale other than UTF-8.
+   Copyright (C) 2006 Free Software Foundation, Inc.
+   This file is part of the GNU C Library.
+   Contributed by Jakub Jelinek <jakub@redhat.com>, 2006.
+
+   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 <locale.h>
+#include <regex.h>
+#include <stdio.h>
+#include <string.h>
+
+const char *str1 = "\xa3\xd8\xa3\xc9\xa3\xc9";
+const char *str2 = "\xa3\xd8\xa3\xc9";
+
+int
+main (void)
+{
+  setlocale (LC_ALL, "ja_JP.eucJP");
+
+  re_set_syntax (RE_SYNTAX_SED);
+
+  struct re_pattern_buffer re;
+  memset (&re, 0, sizeof (re));
+
+  struct re_registers regs;
+  memset (&regs, 0, sizeof (regs));
+
+  re_compile_pattern ("$", 1, &re);
+
+  int ret = 0, r = re_search (&re, str1, 4, 0, 4, &regs);
+  if (r != 4)
+    {
+      printf ("First re_search returned %d\n", r);
+      ret = 1;
+    }
+  r = re_search (&re, str2, 4, 0, 4, &regs);
+  if (r != 4)
+    {
+      printf ("Second re_search returned %d\n", r);
+      ret = 1;
+    }
+  return ret;
+}

diff --git a/posix/regex_internal.c b/posix/regex_internal.c
index 855497ebf1479802c43d44756f8df78bce4d3286..ac312db0cdf68ee33f0a370bc9ecfa24853b92fd 100644 (file)
--- a/posix/regex_internal.c
+++ b/posix/regex_internal.c
@@ -482,7 +482,7 @@ re_string_skip_chars (re_string_t *pstr, int new_raw_idx, wint_t *last_wc)
   mbstate_t prev_st;
   int rawbuf_idx;
   size_t mbclen;
-  wchar_t wc = 0;
+  wchar_t wc = WEOF;
 
   /* Skip the characters which are not necessary to check.  */
   for (rawbuf_idx = pstr->raw_mbs_idx + pstr->valid_raw_len;
@@ -495,7 +495,11 @@ re_string_skip_chars (re_string_t *pstr, int new_raw_idx, wint_t *last_wc)
                        remain_len, &pstr->cur_state);
       if (BE (mbclen == (size_t) -2 || mbclen == (size_t) -1 || mbclen == 0, 0))
        {
-         /* We treat these cases as a singlebyte character.  */
+         /* We treat these cases as a single byte character.  */
+         if (mbclen == 0 || remain_len == 0)
+           wc = L'\0';
+         else
+           wc = *(unsigned char *) (pstr->raw_mbs + rawbuf_idx);
          mbclen = 1;
          pstr->cur_state = prev_st;
        }
@@ -618,7 +622,6 @@ re_string_reconstruct (re_string_t *pstr, int idx, int eflags)
            }
 #endif
          pstr->valid_len = 0;
-         pstr->valid_raw_len = 0;
 #ifdef RE_ENABLE_I18N
          if (pstr->mb_cur_max > 1)
            {
@@ -681,6 +684,16 @@ re_string_reconstruct (re_string_t *pstr, int idx, int eflags)
 
              if (wc == WEOF)
                pstr->valid_len = re_string_skip_chars (pstr, idx, &wc) - idx;
+             if (wc == WEOF)
+               pstr->tip_context
+                 = re_string_context_at (pstr, pstr->valid_raw_len - 1, eflags);
+             else
+               pstr->tip_context = ((BE (pstr->word_ops_used != 0, 0)
+                                     && IS_WIDE_WORD_CHAR (wc))
+                                    ? CONTEXT_WORD
+                                    : ((IS_WIDE_NEWLINE (wc)
+                                        && pstr->newline_anchor)
+                                       ? CONTEXT_NEWLINE : 0));
              if (BE (pstr->valid_len, 0))
                {
                  for (wcs_idx = 0; wcs_idx < pstr->valid_len; ++wcs_idx)
@@ -689,17 +702,12 @@ re_string_reconstruct (re_string_t *pstr, int idx, int eflags)
                    memset (pstr->mbs, 255, pstr->valid_len);
                }
              pstr->valid_raw_len = pstr->valid_len;
-             pstr->tip_context = ((BE (pstr->word_ops_used != 0, 0)
-                                   && IS_WIDE_WORD_CHAR (wc))
-                                  ? CONTEXT_WORD
-                                  : ((IS_WIDE_NEWLINE (wc)
-                                      && pstr->newline_anchor)
-                                     ? CONTEXT_NEWLINE : 0));
            }
          else
 #endif /* RE_ENABLE_I18N */
            {
              int c = pstr->raw_mbs[pstr->raw_mbs_idx + offset - 1];
+             pstr->valid_raw_len = 0;
              if (pstr->trans)
                c = pstr->trans[c];
              pstr->tip_context = (bitset_contain (pstr->word_char, c)