From: Miles Bader <miles@gnu.org>
Date: Sat, 17 Jun 2006 20:57:37 +0000 (+0000)
Subject: Merge from emacs--devo--0
X-Git-Tag: emacs-pretest-23.0.90~8295^2~878
X-Git-Url: http://git.eshelyaron.com/gitweb/?a=commitdiff_plain;h=10c1758c0b2d29b3e1fb8e3ffe5c5dc262f25217;p=emacs.git

Merge from emacs--devo--0

Patches applied:

 * emacs--devo--0  (patch 300-313)

   - Update from CVS
   - Update from CVS: lispref/display.texi (Forcing Redisplay): Fix typo.
   - Merge from gnus--rel--5.10

 * gnus--rel--5.10  (patch 105-106)

   - Update from CVS

Revision: emacs@sv.gnu.org/emacs--unicode--0--patch-74
---

10c1758c0b2d29b3e1fb8e3ffe5c5dc262f25217
diff --cc lisp/term/mac-win.el
index b5dc01ff9bf,7ab9ac9481f..9843d984e34
--- a/lisp/term/mac-win.el
+++ b/lisp/term/mac-win.el
@@@ -1319,8 -1272,8 +1322,8 @@@ correspoinding TextEncodingBase value.
  	  (if (string-match "[\xa0\xfd-\xff]" str)
  	      (setq str nil)
  	    ;; ASCII-only?
- 	    (unless (string-match "\\`[[:ascii:]]*\\'" str)
+ 	    (unless (mac-code-convert-string data nil mac-text-encoding-ascii)
 -	      (subst-char-in-string ?\x5c ?\(J\(B str t)
 +	      (subst-char-in-string ?\x5c ?\Â¥ str t)
  	      (subst-char-in-string ?\x80 ?\\ str t)))))
      (or str
  	(decode-coding-string data
diff --cc src/lread.c
index d8abde1c458,a0d4ad825dd..6ea92d1aebf
--- a/src/lread.c
+++ b/src/lread.c
@@@ -1915,16 -1717,59 +1915,19 @@@ read0 (readcharfun
  static int read_buffer_size;
  static char *read_buffer;
  
 -/* Read multibyte form and return it as a character.  C is a first
 -   byte of multibyte form, and rest of them are read from
 -   READCHARFUN.  */
 -
 -static int
 -read_multibyte (c, readcharfun)
 -     register int c;
 -     Lisp_Object readcharfun;
 -{
 -  /* We need the actual character code of this multibyte
 -     characters.  */
 -  unsigned char str[MAX_MULTIBYTE_LENGTH];
 -  int len = 0;
 -  int bytes;
 -
 -  if (c < 0)
 -    return c;
 -
 -  str[len++] = c;
 -  while ((c = READCHAR) >= 0xA0
 -	 && len < MAX_MULTIBYTE_LENGTH)
 -    {
 -      str[len++] = c;
 -      readchar_count--;
 -    }
 -  UNREAD (c);
 -  if (UNIBYTE_STR_AS_MULTIBYTE_P (str, len, bytes))
 -    return STRING_CHAR (str, len);
 -  /* The byte sequence is not valid as multibyte.  Unread all bytes
 -     but the first one, and return the first byte.  */
 -  while (--len > 0)
 -    UNREAD (str[len]);
 -  return str[0];
 -}
 -
  /* Read a \-escape sequence, assuming we already read the `\'.
 -   If the escape sequence forces unibyte, store 1 into *BYTEREP.
 -   If the escape sequence forces multibyte, store 2 into *BYTEREP.
 -   Otherwise store 0 into *BYTEREP.  */
 +   If the escape sequence forces unibyte, return eight-bit char.  */
  
  static int
 -read_escape (readcharfun, stringp, byterep)
 +read_escape (readcharfun, stringp)
       Lisp_Object readcharfun;
       int stringp;
 -     int *byterep;
  {
    register int c = READCHAR;
+   /* \u allows up to four hex digits, \U up to eight. Default to the
+      behaviour for \u, and change this value in the case that \U is seen. */
+   int unicode_hex_count = 4;
  
 -  *byterep = 0;
 -
    switch (c)
      {
      case -1:
@@@ -2090,7 -1931,55 +2093,53 @@@
  	return i;
        }
  
+     case 'U':
+       /* Post-Unicode-2.0: Up to eight hex chars.  */
+       unicode_hex_count = 8;
+     case 'u':
+ 
+       /* A Unicode escape. We only permit them in strings and characters,
+ 	 not arbitrarily in the source code, as in some other languages.  */
+       {
+ 	int i = 0;
+ 	int count = 0;
+ 	Lisp_Object lisp_char;
+ 	struct gcpro gcpro1;
+ 
+ 	while (++count <= unicode_hex_count)
+ 	  {
+ 	    c = READCHAR;
+ 	    /* isdigit(), isalpha() may be locale-specific, which we don't
+ 	       want. */
+ 	    if      (c >= '0' && c <= '9')  i = (i << 4) + (c - '0');
+ 	    else if (c >= 'a' && c <= 'f')  i = (i << 4) + (c - 'a') + 10;
+             else if (c >= 'A' && c <= 'F')  i = (i << 4) + (c - 'A') + 10;
+ 	    else
+ 	      {
+ 		error ("Non-hex digit used for Unicode escape");
+ 		break;
+ 	      }
+ 	  }
+ 
+ 	GCPRO1 (readcharfun);
+ 	lisp_char = call2(intern("decode-char"), intern("ucs"),
+ 			  make_number(i));
+ 	UNGCPRO;
+ 
+ 	if (EQ(Qnil, lisp_char))
+ 	  {
+ 	    /* This is ugly and horrible and trashes the user's data.  */
+ 	    XSETFASTINT (i, MAKE_CHAR (charset_katakana_jisx0201,
+ 				       34 + 128, 46 + 128));
+             return i;
+ 	  }
+ 	else
+ 	  {
+ 	    return XFASTINT (lisp_char);
+ 	  }
+       }
+ 
      default:
 -      if (BASE_LEADING_CODE_P (c))
 -	c = read_multibyte (c, readcharfun);
        return c;
      }
  }