(Command Loop Info, Adjusting Point): Remove @tindex.

[gnu-emacs] / src / search.c

diff --git a/src/search.c b/src/search.c
index 3c9b70b1581b9461b4943bcfe4dbb24f1d818bce..99db7f184fc22673ea07bc4773dd730d03585ce9 100644 (file)
--- a/src/search.c
+++ b/src/search.c
@@ -1,6 +1,6 @@
 /* String search routines for GNU Emacs.
-   Copyright (C) 1985, 86,87,93,94,97,98, 1999, 2004
-             Free Software Foundation, Inc.
+   Copyright (C) 1985, 1986, 1987, 1993, 1994, 1997, 1998, 1999, 2002, 2003,
+                 2004, 2005, 2006 Free Software Foundation, Inc.
 
 This file is part of GNU Emacs.
 
@@ -16,8 +16,8 @@ GNU General Public License for more details.
 
 You should have received a copy of the GNU General Public License
 along with GNU Emacs; see the file COPYING.  If not, write to
-the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
-Boston, MA 02111-1307, USA.  */
+the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
+Boston, MA 02110-1301, USA.  */
 
 
 #include <config.h>
@@ -90,6 +90,7 @@ static void save_search_regs ();
 static int simple_search ();
 static int boyer_moore ();
 static int search_buffer ();
+static void matcher_overflow () NO_RETURN;
 
 static void
 matcher_overflow ()
@@ -429,7 +430,7 @@ string_match_1 (regexp, string, start, posix)
 
 DEFUN ("string-match", Fstring_match, Sstring_match, 2, 3, 0,
        doc: /* Return index of start of first match for REGEXP in STRING, or nil.
-Case is ignored if `case-fold-search' is non-nil in the current buffer.
+Matching ignores case if `case-fold-search' is non-nil.
 If third arg START is non-nil, start search at that index in STRING.
 For index of first char beyond the match, do (match-end 0).
 `match-end' and `match-beginning' also give indices of substrings
@@ -1174,10 +1175,10 @@ search_buffer (string, pos, pos_byte, lim, lim_byte, n,
       int raw_pattern_size_byte;
       unsigned char *patbuf;
       int multibyte = !NILP (current_buffer->enable_multibyte_characters);
-      unsigned char *base_pat = SDATA (string);
-      /* Set to nozero if we find a non-ASCII char that need
-        translation.  */
-      int charset_base = 0;
+      unsigned char *base_pat;
+      /* Set to positive if we find a non-ASCII char that need
+        translation.  Otherwise set to zero later.  */
+      int charset_base = -1;
       int boyer_moore_ok = 1;
 
       /* MULTIBYTE says whether the text to be searched is multibyte.
@@ -1275,24 +1276,30 @@ search_buffer (string, pos, pos_byte, lim, lim_byte, n,
                         always handle their translation.  */
                      while (1)
                        {
-                         if (! ASCII_BYTE_P (inverse))
+                         if (ASCII_BYTE_P (inverse))
                            {
-                             if (SINGLE_BYTE_CHAR_P (inverse))
-                               {
-                                 /* Boyer-moore search can't handle a
-                                    translation of an eight-bit
-                                    character.  */
-                                 boyer_moore_ok = 0;
-                                 break;
-                               }
-                             else if (charset_base == 0)
-                               charset_base = inverse & ~CHAR_FIELD3_MASK;
-                             else if ((inverse & ~CHAR_FIELD3_MASK)
-                                      != charset_base)
+                             if (charset_base > 0)
                                {
                                  boyer_moore_ok = 0;
                                  break;
                                }
+                             charset_base = 0;
+                           }
+                         else if (SINGLE_BYTE_CHAR_P (inverse))
+                           {
+                             /* Boyer-moore search can't handle a
+                                translation of an eight-bit
+                                character.  */
+                             boyer_moore_ok = 0;
+                             break;
+                           }
+                         else if (charset_base < 0)
+                           charset_base = inverse & ~CHAR_FIELD3_MASK;
+                         else if ((inverse & ~CHAR_FIELD3_MASK)
+                                  != charset_base)
+                           {
+                             boyer_moore_ok = 0;
+                             break;
                            }
                          if (c == inverse)
                            break;
@@ -1300,6 +1307,8 @@ search_buffer (string, pos, pos_byte, lim, lim_byte, n,
                        }
                    }
                }
+             if (charset_base < 0)
+               charset_base = 0;
 
              /* Store this character into the translated pattern.  */
              bcopy (str, pat, charlen);
@@ -1701,7 +1710,7 @@ boyer_moore (n, base_pat, len, len_byte, trt, inverse_trt,
          if (ASCII_BYTE_P (*ptr) || ! multibyte)
            ch = *ptr;
          else if (charset_base
-                  && (pat_end - ptr) == 1 || CHAR_HEAD_P (ptr[1]))
+                  && ((pat_end - ptr) == 1 || CHAR_HEAD_P (ptr[1])))
            {
              unsigned char *charstart = ptr - 1;
 
@@ -1712,7 +1721,7 @@ boyer_moore (n, base_pat, len, len_byte, trt, inverse_trt,
                ch = -1;
            }
 
-         if (ch > 0400)
+         if (ch >= 0400)
            j = ((unsigned char) ch) | 0200;
          else
            j = *ptr;
@@ -1731,7 +1740,7 @@ boyer_moore (n, base_pat, len, len_byte, trt, inverse_trt,
              while (1)
                {
                  TRANSLATE (ch, inverse_trt, ch);
-                 if (ch > 0400)
+                 if (ch >= 0400)
                    j = ((unsigned char) ch) | 0200;
                  else
                    j = (unsigned char) ch;
@@ -2296,7 +2305,7 @@ since only regular expressions have distinguished subexpressions.  */)
                                /* but some C compilers blew it */
 
   if (search_regs.num_regs <= 0)
-    error ("replace-match called before any match found");
+    error ("`replace-match' called before any match found");
 
   if (NILP (subexp))
     sub = 0;
@@ -2368,7 +2377,7 @@ since only regular expressions have distinguished subexpressions.  */)
              else
                some_multiletter_word = 1;
            }
-         else if (!NOCASEP (c))
+         else if (UPPERCASEP (c))
            {
              some_uppercase = 1;
              if (SYNTAX (prevc) != Sword)
@@ -3058,7 +3067,7 @@ DEFUN ("regexp-quote", Fregexp_quote, Sregexp_quote, 1, 1, 0,
 
   for (; in != end; in++)
     {
-      if (*in == '[' || *in == ']'
+      if (*in == '['
          || *in == '*' || *in == '.' || *in == '\\'
          || *in == '?' || *in == '+'
          || *in == '^' || *in == '$')
@@ -3085,6 +3094,7 @@ syms_of_search ()
       searchbufs[i].regexp = Qnil;
       searchbufs[i].whitespace_regexp = Qnil;
       staticpro (&searchbufs[i].regexp);
+      staticpro (&searchbufs[i].whitespace_regexp);
       searchbufs[i].next = (i == REGEXP_CACHE_SIZE-1 ? 0 : &searchbufs[i+1]);
     }
   searchbuf_head = &searchbufs[0];