X-Git-Url: http://git.chise.org/gitweb/?a=blobdiff_plain;f=src%2Fregex.c;h=6f27ce8b2935f249cf1d6717259d526bac85c2b7;hb=2003d10ed3d849e2e973337bb4adf43fa769e6ae;hp=9dcbc10a0f035652f6a5ba78078cd147b659e85f;hpb=ee38d21b330f5001b47a577cefb5ba7b82a3b7d3;p=chise%2Fxemacs-chise.git.1

diff --git a/src/regex.c b/src/regex.c
index 9dcbc10..6f27ce8 100644
--- a/src/regex.c
+++ b/src/regex.c
@@ -6,6 +6,7 @@
    Copyright (C) 1993, 1994, 1995 Free Software Foundation, Inc.
    Copyright (C) 1995 Sun Microsystems, Inc.
    Copyright (C) 1995 Ben Wing.
+   Copyright (C) 1999,2000,2001 MORIOKA Tomohiko
 
    This program is free software; you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
@@ -1145,7 +1146,7 @@ static const char *re_error_msgid[] =
    when matching.  If this number is exceeded, we allocate more
    space, so it is not a hard limit.  */
 #ifndef INIT_FAILURE_ALLOC
-#define INIT_FAILURE_ALLOC 5
+#define INIT_FAILURE_ALLOC 20
 #endif
 
 /* Roughly the maximum number of failure points on the stack.  Would be
@@ -1155,9 +1156,9 @@ static const char *re_error_msgid[] =
 #if defined (MATCH_MAY_ALLOCATE) || defined (REGEX_MALLOC)
 /* 4400 was enough to cause a crash on Alpha OSF/1,
    whose default stack limit is 2mb.  */
-int re_max_failures = 20000;
+int re_max_failures = 40000;
 #else
-int re_max_failures = 2000;
+int re_max_failures = 4000;
 #endif
 
 union fail_stack_elt
@@ -3426,8 +3427,12 @@ compile_extended_range (re_char **p_ptr, re_char *pend,
      ranges entirely within the first 256 chars. */
 
   if ((range_start >= 0x100 || range_end >= 0x100)
-      && CHAR_LEADING_BYTE (range_start) !=
-      CHAR_LEADING_BYTE (range_end))
+#ifdef UTF2000
+      && CHAR_CHARSET_ID (range_start) != CHAR_CHARSET_ID (range_end)
+#else
+      && CHAR_LEADING_BYTE (range_start) != CHAR_LEADING_BYTE (range_end)
+#endif
+      )
     return REG_ERANGESPAN;
 
   /* As advertised, translations only work over the 0 - 0x7F range.
@@ -3719,19 +3724,30 @@ re_compile_fastmap (struct re_pattern_buffer *bufp)
 #endif
 	  matchsyntax:
 #ifdef MULE
+#ifdef UTF2000
+	  for (j = 0; j < 0x80; j++)
+	    if (SYNTAX_UNSAFE
+		(XCHAR_TABLE
+		 (regex_emacs_buffer->syntax_table), j) ==
+		(enum syntaxcode) k)
+	      fastmap[j] = 1;
+#else
 	  for (j = 0; j < 0x80; j++)
 	    if (SYNTAX_UNSAFE
 		(XCHAR_TABLE
 		 (regex_emacs_buffer->mirror_syntax_table), j) ==
 		(enum syntaxcode) k)
 	      fastmap[j] = 1;
+#endif
 	  for (j = 0x80; j < 0xA0; j++)
 	    {
+#ifndef UTF2000
 	      if (LEADING_BYTE_PREFIX_P(j))
 		/* too complicated to calculate this right */
 		fastmap[j] = 1;
 	      else
 		{
+#endif
 		  int multi_p;
 		  Lisp_Object cset;
 
@@ -3743,7 +3759,9 @@ re_compile_fastmap (struct re_pattern_buffer *bufp)
 			  == Sword || multi_p)
 			fastmap[j] = 1;
 		    }
+#ifndef UTF2000
 		}
+#endif
 	    }
 #else /* not MULE */
 	  for (j = 0; j < (1 << BYTEWIDTH); j++)
@@ -3762,19 +3780,30 @@ re_compile_fastmap (struct re_pattern_buffer *bufp)
 #endif
 	  matchnotsyntax:
 #ifdef MULE
+#ifdef UTF2000
+	  for (j = 0; j < 0x80; j++)
+	    if (SYNTAX_UNSAFE
+		(XCHAR_TABLE
+		 (regex_emacs_buffer->syntax_table), j) !=
+		(enum syntaxcode) k)
+	      fastmap[j] = 1;
+#else
 	  for (j = 0; j < 0x80; j++)
 	    if (SYNTAX_UNSAFE
 		(XCHAR_TABLE
 		 (regex_emacs_buffer->mirror_syntax_table), j) !=
 		(enum syntaxcode) k)
 	      fastmap[j] = 1;
+#endif
 	  for (j = 0x80; j < 0xA0; j++)
 	    {
+#ifndef UTF2000
 	      if (LEADING_BYTE_PREFIX_P(j))
 		/* too complicated to calculate this right */
 		fastmap[j] = 1;
 	      else
 		{
+#endif
 		  int multi_p;
 		  Lisp_Object cset;
 
@@ -3786,7 +3815,9 @@ re_compile_fastmap (struct re_pattern_buffer *bufp)
 			  != Sword || multi_p)
 			fastmap[j] = 1;
 		    }
+#ifndef UTF2000
 		}
+#endif
 	    }
 #else /* not MULE */
 	  for (j = 0; j < (1 << BYTEWIDTH); j++)
@@ -4308,9 +4339,15 @@ re_search_2 (struct re_pattern_buffer *bufp, const char *str1,
 #define POS_AFTER_GAP_UNSAFE(d) ((d) == end1 ? string2 : (d))
 
 /* Test if CH is a word-constituent character. (XEmacs change) */
+#ifdef UTF2000
+#define WORDCHAR_P_UNSAFE(ch)					   \
+  (SYNTAX_UNSAFE (XCHAR_TABLE (regex_emacs_buffer->syntax_table),  \
+                               ch) == Sword)
+#else
 #define WORDCHAR_P_UNSAFE(ch)						   \
   (SYNTAX_UNSAFE (XCHAR_TABLE (regex_emacs_buffer->mirror_syntax_table),   \
                                ch) == Sword)
+#endif
 
 /* Free everything we malloc.  */
 #ifdef MATCH_MAY_ALLOCATE
@@ -5822,8 +5859,13 @@ re_match_2_internal (struct re_pattern_buffer *bufp, re_char *string1,
 #endif
 
 	    emch = charptr_emchar ((const Bufbyte *) d);
+#ifdef UTF2000
+	    matches = (SYNTAX_FROM_CACHE (XCHAR_TABLE (regex_emacs_buffer->syntax_table),
+			emch) == (enum syntaxcode) mcnt);
+#else
 	    matches = (SYNTAX_FROM_CACHE (XCHAR_TABLE (regex_emacs_buffer->mirror_syntax_table),
 			emch) == (enum syntaxcode) mcnt);
+#endif
 	    INC_CHARPTR (d);
 	    if (matches != should_succeed)
 	      goto fail;