importing regex changes from libc

[Paul Eggert]

I may have found a bug in the gnulib regex code, but the first step
before fixing it is to import recent changes from libc, so I installed
this:

2006-08-10  Paul Eggert  <address@hidden>

        Import the following changes from libc:

        2006-06-02  Jakub Jelinek  <address@hidden>

        * 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.

        2006-05-02  Ulrich Drepper  <address@hidden>

        * posix/regex.h: g++ still cannot handled [restrict].

        2006-04-21  Ulrich Drepper  <address@hidden>

        * posix/regex.h: Remove special handling for VMS.
 
Index: lib/regex.h
===================================================================
RCS file: /cvsroot/gnulib/gnulib/lib/regex.h,v
retrieving revision 1.37
diff -p -u -r1.37 regex.h
--- lib/regex.h 13 Apr 2006 22:14:12 -0000      1.37
+++ lib/regex.h 10 Aug 2006 20:05:48 -0000
@@ -37,12 +37,6 @@ extern "C" {
 # define __USE_GNU_REGEX 1
 #endif
 
-#ifdef __VMS
-/* VMS doesn't have `size_t' in <sys/types.h>, even though POSIX says it
-   should be there.  */
-# include <stddef.h>
-#endif
-
 #ifdef _REGEX_LARGE_OFFSETS
 
 /* Use types and values that are wide enough to represent signed and
@@ -641,9 +635,10 @@ extern int re_exec (const char *);
 #  endif
 # endif
 #endif
-/* gcc 3.1 and up support the [restrict] syntax, but g++ doesn't.  */
+/* gcc 3.1 and up support the [restrict] syntax.  */
 #ifndef __restrict_arr
-# if (__GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 1)) && !defined 
__cplusplus
+# if (__GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 1)) \
+     && !defined __GNUG__
 #  define __restrict_arr __restrict
 # else
 #  define __restrict_arr
Index: lib/regex_internal.c
===================================================================
RCS file: /cvsroot/gnulib/gnulib/lib/regex_internal.c,v
retrieving revision 1.20
diff -p -u -r1.20 regex_internal.c
--- lib/regex_internal.c        10 Apr 2006 06:43:33 -0000      1.20
+++ lib/regex_internal.c        10 Aug 2006 20:05:48 -0000
@@ -488,7 +488,7 @@ re_string_skip_chars (re_string_t *pstr,
   mbstate_t prev_st;
   Idx 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;
@@ -501,7 +501,11 @@ re_string_skip_chars (re_string_t *pstr,
                        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;
        }
@@ -627,7 +631,6 @@ re_string_reconstruct (re_string_t *pstr
            }
 #endif
          pstr->valid_len = 0;
-         pstr->valid_raw_len = 0;
 #ifdef RE_ENABLE_I18N
          if (pstr->mb_cur_max > 1)
            {
@@ -690,6 +693,16 @@ re_string_reconstruct (re_string_t *pstr
 
              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)
@@ -698,17 +711,12 @@ re_string_reconstruct (re_string_t *pstr
                    memset (pstr->mbs, -1, 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)