;;; emu-x20.el --- emu API implementation for XEmacs with mule
-;; Copyright (C) 1994,1995,1996,1997 MORIOKA Tomohiko
+;; Copyright (C) 1994,1995,1996,1997,1998 MORIOKA Tomohiko
;; Author: MORIOKA Tomohiko <morioka@jaist.ac.jp>
-;; Version: $Id: emu-x20.el,v 7.69 1998/01/10 18:00:57 morioka Exp $
;; Keywords: emulation, compatibility, Mule, XEmacs
-;; This file is part of XEmacs.
+;; This file is part of emu.
-;; XEmacs is free software; you can redistribute it and/or modify it
-;; under the terms of the GNU General Public License as published by
-;; the Free Software Foundation; either version 2, or (at your option)
-;; any later version.
+;; 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 the Free Software Foundation; either version 2, or (at
+;; your option) any later version.
-;; XEmacs is distributed in the hope that it will be useful, but
+;; This program is distributed in the hope that it will be useful, but
;; WITHOUT ANY WARRANTY; without even the implied warranty of
;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
;; General Public License for more details.
;; You should have received a copy of the GNU General Public License
-;; along with XEmacs; see the file COPYING. If not, write to the Free
-;; Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
-;; 02111-1307, USA.
+;; 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.
;;; Commentary:
;;; Code:
-(require 'emu-xemacs)
(require 'emu-20)
+;;; @ fix coding-system definition
+;;;
+
+;; It seems not bug, but I can not permit it...
(and (coding-system-property 'iso-2022-jp 'input-charset-conversion)
(copy-coding-system 'iso-2022-7bit 'iso-2022-jp))
+;; Redefine if -{dos|mac|unix} is not found.
+(or (find-coding-system 'raw-text-dos)
+ (copy-coding-system 'no-conversion-dos 'raw-text-dos))
+(or (find-coding-system 'raw-text-mac)
+ (copy-coding-system 'no-conversion-mac 'raw-text-mac))
+(or (find-coding-system 'raw-text-unix)
+ (copy-coding-system 'no-conversion-unix 'raw-text-unix))
+
+(or (find-coding-system 'ctext-dos)
+ (make-coding-system
+ 'ctext 'iso2022
+ "Coding-system used in X as Compound Text Encoding."
+ '(charset-g0 ascii charset-g1 latin-iso8859-1
+ eol-type nil
+ mnemonic "CText")))
+
+(or (find-coding-system 'iso-2022-jp-2-dos)
+ (make-coding-system
+ 'iso-2022-jp-2 'iso2022
+ "ISO-2022 coding system using SS2 for 96-charset in 7-bit code."
+ '(charset-g0 ascii
+ charset-g2 t ;; unspecified but can be used later.
+ seven t
+ short t
+ mnemonic "ISO7/SS2"
+ eol-type nil)))
+
+(or (find-coding-system 'euc-kr-dos)
+ (make-coding-system
+ 'euc-kr 'iso2022
+ "Coding-system of Korean EUC (Extended Unix Code)."
+ '(charset-g0 ascii charset-g1 korean-ksc5601
+ mnemonic "ko/EUC"
+ eol-type nil)))
+
+
+;;; @ CCL
+;;;
+
+(defun make-ccl-coding-system (name mnemonic doc-string decoder encoder)
+ (make-coding-system
+ name 'ccl doc-string
+ (list 'mnemonic (char-to-string mnemonic)
+ 'decode (symbol-value decoder)
+ 'encode (symbol-value encoder))))
+
+
+;;; @ without code-conversion
+;;;
+
+(define-obsolete-function-alias 'insert-binary-file-contents
+ 'insert-file-contents-as-binary)
+
+(defun insert-binary-file-contents-literally (filename
+ &optional visit beg end replace)
+ "Like `insert-file-contents-literally', q.v., but don't code conversion.
+A buffer may be modified in several ways after reading into the buffer due
+to advanced Emacs features, such as file-name-handlers, format decoding,
+find-file-hooks, etc.
+ This function ensures that none of these modifications will take place."
+ (let ((coding-system-for-read 'binary))
+ ;; Returns list absolute file name and length of data inserted.
+ (insert-file-contents-literally filename visit beg end replace)))
+
;;; @ MIME charset
;;;
-(defsubst encode-mime-charset-region (start end charset)
+(defun encode-mime-charset-region (start end charset)
"Encode the text between START and END as MIME CHARSET."
(let ((cs (mime-charset-to-coding-system charset)))
(if cs
(encode-coding-region start end cs)
)))
-(defsubst decode-mime-charset-region (start end charset)
- "Decode the text between START and END as MIME CHARSET."
- (let ((cs (mime-charset-to-coding-system charset)))
+(defcustom mime-charset-decoder-alist
+ '((iso-2022-jp . decode-mime-charset-region-with-iso646-unification)
+ (iso-2022-jp-2 . decode-mime-charset-region-with-iso646-unification)
+ (x-ctext . decode-mime-charset-region-with-iso646-unification)
+ (hz-gb-2312 . decode-mime-charset-region-for-hz)
+ (t . decode-mime-charset-region-default))
+ "Alist MIME-charset vs. decoder function."
+ :group 'i18n
+ :type '(repeat (cons mime-charset function)))
+
+(defsubst decode-mime-charset-region-default (start end charset lbt)
+ (let ((cs (mime-charset-to-coding-system charset lbt)))
(if cs
(decode-coding-region start end cs)
)))
+(defcustom mime-iso646-character-unification-alist
+ `,(let (dest
+ (i 33))
+ (while (< i 92)
+ (setq dest
+ (cons (cons (char-to-string (make-char 'latin-jisx0201 i))
+ (format "%c" i))
+ dest))
+ (setq i (1+ i)))
+ (setq i 93)
+ (while (< i 126)
+ (setq dest
+ (cons (cons (char-to-string (make-char 'latin-jisx0201 i))
+ (format "%c" i))
+ dest))
+ (setq i (1+ i)))
+ (nreverse dest))
+ "Alist unified string vs. canonical string."
+ :group 'i18n
+ :type '(repeat (cons string string)))
+
+(defcustom mime-unified-character-face nil
+ "*Face of unified character."
+ :group 'i18n
+ :type 'face)
+
+(defcustom mime-character-unification-limit-size 2048
+ "*Limit size to unify characters."
+ :group 'i18n
+ :type 'integer)
+
+(defun decode-mime-charset-region-with-iso646-unification (start end charset
+ lbt)
+ (decode-mime-charset-region-default start end charset lbt)
+ (if (<= (- end start) mime-character-unification-limit-size)
+ (save-excursion
+ (let ((rest mime-iso646-character-unification-alist))
+ (while rest
+ (let ((pair (car rest)))
+ (goto-char (point-min))
+ (while (search-forward (car pair) nil t)
+ (let ((str (cdr pair)))
+ (put-text-property 0 (length str)
+ 'face mime-unified-character-face str)
+ (replace-match str 'fixed-case 'literal)
+ )
+ ))
+ (setq rest (cdr rest)))))
+ ))
+
+(defun decode-mime-charset-region-for-hz (start end charset lbt)
+ (if lbt
+ (save-restriction
+ (narrow-to-region start end)
+ (decode-coding-region (point-min)(point-max)
+ (mime-charset-to-coding-system 'raw-text lbt))
+ (decode-hz-region (point-min)(point-max)))
+ (decode-hz-region start end)))
+
+(defun decode-mime-charset-region (start end charset &optional lbt)
+ "Decode the text between START and END as MIME CHARSET."
+ (if (stringp charset)
+ (setq charset (intern (downcase charset)))
+ )
+ (let ((func (cdr (or (assq charset mime-charset-decoder-alist)
+ (assq t mime-charset-decoder-alist)))))
+ (funcall func start end charset lbt)))
+
(defsubst encode-mime-charset-string (string charset)
"Encode the STRING as MIME CHARSET."
(let ((cs (mime-charset-to-coding-system charset)))
(encode-coding-string string cs)
string)))
-(defsubst decode-mime-charset-string (string charset)
+;; (defsubst decode-mime-charset-string (string charset)
+;; "Decode the STRING as MIME CHARSET."
+;; (let ((cs (mime-charset-to-coding-system charset)))
+;; (if cs
+;; (decode-coding-string string cs)
+;; string)))
+(defun decode-mime-charset-string (string charset &optional lbt)
"Decode the STRING as MIME CHARSET."
- (let ((cs (mime-charset-to-coding-system charset)))
- (if cs
- (decode-coding-string string cs)
- string)))
+ (with-temp-buffer
+ (insert string)
+ (decode-mime-charset-region (point-min)(point-max) charset lbt)
+ (buffer-string)))
(defvar charsets-mime-charset-alist
((ascii latin-iso8859-9) . iso-8859-9)
((ascii latin-jisx0201
japanese-jisx0208-1978 japanese-jisx0208) . iso-2022-jp)
+ ((ascii latin-jisx0201
+ katakana-jisx0201 japanese-jisx0208) . shift_jis)
((ascii korean-ksc5601) . euc-kr)
((ascii chinese-gb2312) . cn-gb-2312)
((ascii chinese-big5-1 chinese-big5-2) . cn-big5)
chinese-cns11643-7) . iso-2022-int-1)
))
-(defun detect-mime-charset-region (start end)
- "Return MIME charset for region between START and END."
- (charsets-to-mime-charset (charsets-in-region start end)))
+
+;;; @ buffer representation
+;;;
+
+(defsubst-maybe set-buffer-multibyte (flag)
+ "Set the multibyte flag of the current buffer to FLAG.
+If FLAG is t, this makes the buffer a multibyte buffer.
+If FLAG is nil, this makes the buffer a single-byte buffer.
+The buffer contents remain unchanged as a sequence of bytes
+but the contents viewed as characters do change.
+\[Emacs 20.3 emulating function]"
+ flag)
;;; @ character
;;;
+;; avoid bug of XEmacs
+(or (integerp (cdr (split-char ?a)))
+ (defun split-char (char)
+ "Return list of charset and one or two position-codes of CHAR."
+ (let ((charset (char-charset char)))
+ (if (eq charset 'ascii)
+ (list charset (char-int char))
+ (let ((i 0)
+ (len (charset-dimension charset))
+ (code (if (integerp char)
+ char
+ (char-int char)))
+ dest)
+ (while (< i len)
+ (setq dest (cons (logand code 127) dest)
+ code (lsh code -7)
+ i (1+ i)))
+ (cons charset dest)))))
+ )
+
+(defmacro char-next-index (char index)
+ "Return index of character succeeding CHAR whose index is INDEX."
+ `(1+ ,index))
+
;;; @@ Mule emulating aliases
;;;
;;; You should not use them.
-(defalias 'char-leading-char 'char-charset)
+;;(defalias 'char-leading-char 'char-charset)
(defun char-category (character)
"Return string of category mnemonics for CHAR in TABLE.
CHAR can be any multilingual character
TABLE defaults to the current buffer's category table."
(mapconcat (lambda (chr)
- (char-to-string (int-char chr))
- )
+ (char-to-string (int-char chr)))
(char-category-list character)
""))
;;;
(defun string-to-int-list (str)
- (mapcar #'char-int str)
- )
+ (mapcar #'char-int str))
+
+(defalias 'looking-at-as-unibyte 'looking-at)
;;; @ end