X-Git-Url: https://erislabs.net/gitweb/?a=blobdiff_plain;f=lib%2Fregcomp.c;h=6472ff6b2eb0d1b7707ddce159c58bd9da81d3fc;hb=298d8b4a29e66da0b046b64b822f97d1c8fef74b;hp=dc15666503622c57f1821033805f472dec13899e;hpb=1f191226cb1994d17429ac7dd9e9e1979e705efb;p=gnulib.git

diff --git a/lib/regcomp.c b/lib/regcomp.c
index dc1566650..6472ff6b2 100644
--- a/lib/regcomp.c
+++ b/lib/regcomp.c
@@ -1,5 +1,6 @@
 /* Extended regular expression matching and search library.
-   Copyright (C) 2002,2003,2004,2005,2006,2007 Free Software Foundation, Inc.
+   Copyright (C) 2002,2003,2004,2005,2006,2007,2008,2009
+   Free Software Foundation, Inc.
    This file is part of the GNU C Library.
    Contributed by Isamu Hasegawa <isamu@yamato.ibm.com>.
 
@@ -333,8 +334,8 @@ re_compile_fastmap_iter (regex_t *bufp, const re_dfastate_t *init_state,
 		     && dfa->nodes[node].mb_partial)
 		*p++ = dfa->nodes[node].opr.c;
 	      memset (&state, '\0', sizeof (state));
-	      if (mbrtowc (&wc, (const char *) buf, p - buf,
-			   &state) == p - buf
+	      if (__mbrtowc (&wc, (const char *) buf, p - buf,
+			     &state) == p - buf
 		  && (__wcrtomb ((char *) buf, towlower (wc), &state)
 		      != (size_t) -1))
 		re_set_fastmap (fastmap, false, buf[0]);
@@ -356,45 +357,65 @@ re_compile_fastmap_iter (regex_t *bufp, const re_dfastate_t *init_state,
 #ifdef RE_ENABLE_I18N
       else if (type == COMPLEX_BRACKET)
 	{
-	  Idx i;
 	  re_charset_t *cset = dfa->nodes[node].opr.mbcset;
-	  if (cset->non_match || cset->ncoll_syms || cset->nequiv_classes
-	      || cset->nranges || cset->nchar_classes)
-	    {
+	  Idx i;
+
 # ifdef _LIBC
-	      if (_NL_CURRENT_WORD (LC_COLLATE, _NL_COLLATE_NRULES) != 0)
+	  /* See if we have to try all bytes which start multiple collation
+	     elements.
+	     e.g. In da_DK, we want to catch 'a' since "aa" is a valid
+		  collation element, and don't catch 'b' since 'b' is
+		  the only collation element which starts from 'b' (and
+		  it is caught by SIMPLE_BRACKET).  */
+	      if (_NL_CURRENT_WORD (LC_COLLATE, _NL_COLLATE_NRULES) != 0
+		  && (cset->ncoll_syms || cset->nranges))
 		{
-		  /* In this case we want to catch the bytes which are
-		     the first byte of any collation elements.
-		     e.g. In da_DK, we want to catch 'a' since "aa"
-			  is a valid collation element, and don't catch
-			  'b' since 'b' is the only collation element
-			  which starts from 'b'.  */
 		  const int32_t *table = (const int32_t *)
 		    _NL_CURRENT (LC_COLLATE, _NL_COLLATE_TABLEMB);
 		  for (i = 0; i < SBC_MAX; ++i)
 		    if (table[i] < 0)
 		      re_set_fastmap (fastmap, icase, i);
 		}
-# else
-	      if (dfa->mb_cur_max > 1)
-		for (i = 0; i < SBC_MAX; ++i)
-		  if (__btowc (i) == WEOF)
-		    re_set_fastmap (fastmap, icase, i);
-# endif /* not _LIBC */
+# endif /* _LIBC */
+
+	  /* See if we have to start the match at all multibyte characters,
+	     i.e. where we would not find an invalid sequence.  This only
+	     applies to multibyte character sets; for single byte character
+	     sets, the SIMPLE_BRACKET again suffices.  */
+	  if (dfa->mb_cur_max > 1
+	      && (cset->nchar_classes || cset->non_match
+# ifdef _LIBC
+		  || cset->nequiv_classes
+# endif /* _LIBC */
+		 ))
+	    {
+	      unsigned char c = 0;
+	      do
+		{
+		  mbstate_t mbs;
+		  memset (&mbs, 0, sizeof (mbs));
+		  if (__mbrtowc (NULL, (char *) &c, 1, &mbs) == (size_t) -2)
+		    re_set_fastmap (fastmap, false, (int) c);
+		}
+	      while (++c != 0);
 	    }
-	  for (i = 0; i < cset->nmbchars; ++i)
+
+	  else
 	    {
-	      char buf[256];
-	      mbstate_t state;
-	      memset (&state, '\0', sizeof (state));
-	      if (__wcrtomb (buf, cset->mbchars[i], &state) != (size_t) -1)
-		re_set_fastmap (fastmap, icase, *(unsigned char *) buf);
-	      if ((bufp->syntax & RE_ICASE) && dfa->mb_cur_max > 1)
+	      /* ... Else catch all bytes which can start the mbchars.  */
+	      for (i = 0; i < cset->nmbchars; ++i)
 		{
-		  if (__wcrtomb (buf, towlower (cset->mbchars[i]), &state)
-		      != (size_t) -1)
-		    re_set_fastmap (fastmap, false, *(unsigned char *) buf);
+		  char buf[256];
+		  mbstate_t state;
+		  memset (&state, '\0', sizeof (state));
+		  if (__wcrtomb (buf, cset->mbchars[i], &state) != (size_t) -1)
+		    re_set_fastmap (fastmap, icase, *(unsigned char *) buf);
+		  if ((bufp->syntax & RE_ICASE) && dfa->mb_cur_max > 1)
+		    {
+		      if (__wcrtomb (buf, towlower (cset->mbchars[i]), &state)
+			  != (size_t) -1)
+			re_set_fastmap (fastmap, false, *(unsigned char *) buf);
+		    }
 		}
 	    }
 	}
@@ -776,7 +797,7 @@ re_compile_internal (regex_t *preg, const char * pattern, size_t length,
   __libc_lock_init (dfa->lock);
 
   err = re_string_construct (&regexp, pattern, length, preg->translate,
-			     syntax & RE_ICASE, dfa);
+			     (syntax & RE_ICASE) != 0, dfa);
   if (BE (err != REG_NOERROR, 0))
     {
     re_compile_internal_free_return: