Re: enhanced select-safe-coding-system

["Stefan Monnier" <monnier+gnu/emacs@RUM.cs.yale.edu>]

> "Stefan Monnier" <monnier+gnu/emacs@RUM.cs.yale.edu> writes:
> 
> > I have recently posted a fairly simple patch that does that by slightly
> > modifying the C code, so it's fast.
> 
> How is that?  I think the Lisp is actually fast enough in that
> application on a P100.  I included the warning in case anyone used it
> without checking.

You might be right that the elisp code is fast enough, but my
patch (attached) makes fewer changes and avoids re-implementing
the same functionality in elisp.


	Stefan


Index: coding.c
===================================================================
RCS file: /cvsroot/emacs/emacs/src/coding.c,v
retrieving revision 1.241
diff -u -r1.241 coding.c
--- coding.c	13 Apr 2002 17:49:00 -0000	1.241
+++ coding.c	5 May 2002 23:23:51 -0000
@@ -6366,8 +6361,6 @@
 	continue;
       if (SINGLE_BYTE_CHAR_P (c))
 	*single_byte_char_found = 1;
-      if (NILP (safe_codings))
-	continue;
       /* Check the safe coding systems for C.  */
       val = char_table_ref_and_index (work_table, c, &idx);
       if (EQ (val, Qt))
@@ -6382,6 +6375,8 @@
       if (!EQ (safe_codings, Qt) && !NILP (val))
 	val = intersection (safe_codings, val);
       safe_codings = val;
+      if (NILP (safe_codings))
+	return make_number (pend - p);
     }
   return safe_codings;
 }
@@ -6393,20 +6388,24 @@
 
 DEFUN ("find-coding-systems-region-internal",
        Ffind_coding_systems_region_internal,
-       Sfind_coding_systems_region_internal, 2, 2, 0,
+       Sfind_coding_systems_region_internal, 2, 3, 0,
        doc: /* Internal use only.  */)
-     (start, end)
-     Lisp_Object start, end;
+     (start, end, safe_codings)
+     Lisp_Object start, end, safe_codings;
 {
-  Lisp_Object work_table, safe_codings;
+  Lisp_Object work_table;
   int non_ascii_p = 0;
   int single_byte_char_found = 0;
   unsigned char *p1, *p1end, *p2, *p2end, *p;
+  int from, to, stop;
+
+  if (NILP (safe_codings))
+    safe_codings = Qt;
 
   if (STRINGP (start))
     {
       if (!STRING_MULTIBYTE (start))
-	return Qt;
+	return safe_codings;
       p1 = XSTRING (start)->data, p1end = p1 + STRING_BYTES (XSTRING (start));
       p2 = p2end = p1end;
       if (XSTRING (start)->size != STRING_BYTES (XSTRING (start)))
@@ -6414,14 +6413,12 @@
     }
   else
     {
-      int from, to, stop;
-
       CHECK_NUMBER_COERCE_MARKER (start);
       CHECK_NUMBER_COERCE_MARKER (end);
       if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end))
 	args_out_of_range (start, end);
       if (NILP (current_buffer->enable_multibyte_characters))
-	return Qt;
+	return safe_codings;
       from = CHAR_TO_BYTE (XINT (start));
       to = CHAR_TO_BYTE (XINT (end));
       stop = from < GPT_BYTE && GPT_BYTE < to ? GPT_BYTE : to;
@@ -6444,17 +6441,27 @@
 	{
 	  for (p = p2; p < p2end && ASCII_BYTE_P (*p); p++);
 	  if (p == p2end)
-	    return Qt;
+	    return safe_codings;
 	}
     }
 
   /* The text contains non-ASCII characters.  */
   work_table = Fcopy_sequence (Vchar_coding_system_table);
-  safe_codings = find_safe_codings (p1, p1end, Qt, work_table,
+  safe_codings = find_safe_codings (p1, p1end, safe_codings, work_table,
 				    &single_byte_char_found);
+  if (INTEGERP (safe_codings))
+    {
+      int byte = p1end - p1 - XINT (safe_codings);
+      return (STRINGP (start)
+	      ? string_byte_to_char (start, byte)
+	      : bytepos_to_charpos (byte + from)) - 1;
+    }
   if (p2 < p2end)
     safe_codings = find_safe_codings (p2, p2end, safe_codings, work_table,
 				      &single_byte_char_found);
+  if (INTEGERP (safe_codings))
+    return bytepos_to_charpos (p2end - p2 - XINT (safe_codings) + stop) - 1;
+
 
   if (EQ (safe_codings, Qt))
     ; /* Nothing to be done.  */