1 ;;; mm-util.el --- Utility functions for MIME things
2 ;; Copyright (C) 1998 Free Software Foundation, Inc.
4 ;; Author: Lars Magne Ingebrigtsen <larsi@gnus.org>
5 ;; MORIOKA Tomohiko <morioka@jaist.ac.jp>
6 ;; This file is part of GNU Emacs.
8 ;; GNU Emacs is free software; you can redistribute it and/or modify
9 ;; it under the terms of the GNU General Public License as published by
10 ;; the Free Software Foundation; either version 2, or (at your option)
13 ;; GNU Emacs is distributed in the hope that it will be useful,
14 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
15 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
16 ;; GNU General Public License for more details.
18 ;; You should have received a copy of the GNU General Public License
19 ;; along with GNU Emacs; see the file COPYING. If not, write to the
20 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
21 ;; Boston, MA 02111-1307, USA.
27 (defvar mm-binary-coding-system
28 (if (string-match "XEmacs" emacs-version)
29 'binary 'no-conversion)
30 "100% binary coding system.")
32 (defvar mm-default-coding-system nil
33 "The default coding system to use.")
35 (defvar mm-known-charsets '(iso-8859-1)
36 "List of known charsets.")
38 (defvar mm-mime-mule-charset-alist
40 (iso-8859-1 latin-iso8859-1)
41 (iso-8859-2 latin-iso8859-2)
42 (iso-8859-3 latin-iso8859-3)
43 (iso-8859-4 latin-iso8859-4)
44 (iso-8859-5 cyrillic-iso8859-5)
45 (koi8-r cyrillic-iso8859-5)
46 (iso-8859-6 arabic-iso8859-6)
47 (iso-8859-7 greek-iso8859-7)
48 (iso-8859-8 hebrew-iso8859-8)
49 (iso-8859-9 latin-iso8859-9)
50 (iso-2022-jp-2 japanese-jisx0208)
51 (iso-2022-jp latin-jisx0201
52 japanese-jisx0208-1978)
53 (euc-kr korean-ksc5601)
54 (cn-gb-2312 chinese-gb2312)
55 (cn-big5 chinese-big5-1 chinese-big5-2)
56 (iso-2022-jp-2 latin-iso8859-1 greek-iso8859-7
57 latin-jisx0201 japanese-jisx0208-1978
58 chinese-gb2312 japanese-jisx0208
59 korean-ksc5601 japanese-jisx0212)
60 (iso-2022-int-1 latin-iso8859-1 greek-iso8859-7
61 latin-jisx0201 japanese-jisx0208-1978
62 chinese-gb2312 japanese-jisx0208
63 korean-ksc5601 japanese-jisx0212
64 chinese-cns11643-1 chinese-cns11643-2)
65 (iso-2022-int-1 latin-iso8859-1 latin-iso8859-2
66 cyrillic-iso8859-5 greek-iso8859-7
67 latin-jisx0201 japanese-jisx0208-1978
68 chinese-gb2312 japanese-jisx0208
69 korean-ksc5601 japanese-jisx0212
70 chinese-cns11643-1 chinese-cns11643-2
71 chinese-cns11643-3 chinese-cns11643-4
72 chinese-cns11643-5 chinese-cns11643-6
74 "Alist of MIME-charset/MULE-charsets.")
80 (let ((nfunc (intern (format "mm-%s" (car elem)))))
81 (if (fboundp (car elem))
82 (fset nfunc (car elem))
83 (fset nfunc (cdr elem)))))
84 '((decode-coding-string . (lambda (s a) s))
85 (encode-coding-string . (lambda (s a) s))
86 (encode-coding-region . ignore)
87 (coding-system-list . ignore)
88 (decode-coding-region . ignore)
90 (device-type . ignore)
91 (coding-system-equal . equal)
92 (annotationp . ignore)
93 (set-buffer-file-coding-system . ignore)
95 . (lambda (charset int)
99 "Prompt the user for a coding system."
101 prompt (mapcar (lambda (s) (list (symbol-name (car s))))
102 mm-mime-mule-charset-alist)))))))
104 (defvar mm-coding-system-list nil)
105 (defun mm-get-coding-system-list ()
106 "Get the coding system list."
107 (or mm-coding-system-list
108 (setq mm-coding-system-list (mm-coding-system-list))))
110 (defvar mm-charset-coding-system-alist
112 '((gb2312 . cn-gb-2312)
113 (iso-2022-jp-2 . iso-2022-7bit-ss2)
115 (systems (mm-get-coding-system-list))
118 (let ((pair (car rest)))
119 (unless (memq (car pair) systems)
120 (setq dest (cons pair dest))))
121 (setq rest (cdr rest)))
123 "Charset/coding system alist.")
126 (defvar mm-charset-iso-8859-1-forced nil)
128 (defun mm-mule-charset-to-mime-charset (charset)
129 "Return the MIME charset corresponding to MULE CHARSET."
130 (let ((alist mm-mime-mule-charset-alist)
133 (when (memq charset (cdar alist))
134 (setq out (caar alist)
139 (defun mm-charset-to-coding-system (charset &optional lbt)
140 "Return coding-system corresponding to CHARSET.
141 CHARSET is a symbol naming a MIME charset.
142 If optional argument LBT (`unix', `dos' or `mac') is specified, it is
143 used as the line break code type of the coding system."
144 (when (stringp charset)
145 (setq charset (intern (downcase charset))))
146 (if (and mm-charset-iso-8859-1-forced
147 (eq charset 'iso-8859-1))
148 (setq charset mm-charset-iso-8859-1-forced))
150 (or (cdr (assq charset mm-charset-coding-system-alist))
153 (setq charset (intern (format "%s-%s" charset lbt))))
155 ;; Running in a non-MULE environment.
156 ((and (null (mm-get-coding-system-list))
157 (memq charset mm-known-charsets))
160 ((eq charset 'us-ascii)
162 ;; Check to see whether we can handle this charset.
163 ((memq charset (mm-get-coding-system-list))
169 (defun mm-replace-chars-in-string (string from to)
170 "Replace characters in STRING from FROM to TO."
171 (let ((string (substring string 0)) ;Copy string.
172 (len (length string))
174 ;; Replace all occurrences of FROM with TO.
176 (when (= (aref string idx) from)
177 (aset string idx to))
181 (defsubst mm-enable-multibyte ()
182 "Enable multibyte in the current buffer."
183 (when (and (fboundp 'set-buffer-multibyte)
184 (default-value 'enable-multibyte-characters))
185 (set-buffer-multibyte t)))
187 (defsubst mm-disable-multibyte ()
188 "Disable multibyte in the current buffer."
189 (when (fboundp 'set-buffer-multibyte)
190 (set-buffer-multibyte nil)))
192 (defun mm-mime-charset (charset b e)
193 (if (fboundp 'coding-system-get)
196 mm-default-coding-system
197 (let ((safe (coding-system-get mm-default-coding-system
199 (or (eq safe t) (memq charset safe)))
200 (coding-system-get mm-default-coding-system 'mime-charset))
202 (get-charset-property charset 'prefered-coding-system)
204 (car (memq charset (find-coding-systems-region
205 (point-min) (point-max)))))
206 (mm-mule-charset-to-mime-charset charset)))
208 (defsubst mm-multibyte-p ()
209 "Say whether multibyte is enabled."
210 (and (boundp 'enable-multibyte-characters)
211 enable-multibyte-characters))
213 (defmacro mm-with-unibyte-buffer (&rest forms)
214 "Create a temporary buffer, and evaluate FORMS there like `progn'.
215 See also `with-temp-file' and `with-output-to-string'."
216 (let ((temp-buffer (make-symbol "temp-buffer"))
217 (multibyte (make-symbol "multibyte")))
218 `(if (not (boundp 'enable-multibyte-characters))
219 (with-temp-buffer ,@forms)
220 (let ((,multibyte (default-value 'enable-multibyte-characters))
224 (setq-default enable-multibyte-characters nil)
226 (get-buffer-create (generate-new-buffer-name " *temp*")))
228 (with-current-buffer ,temp-buffer
229 (let ((buffer-file-coding-system mm-binary-coding-system)
230 (coding-system-for-read mm-binary-coding-system)
231 (coding-system-for-write mm-binary-coding-system))
233 (and (buffer-name ,temp-buffer)
234 (kill-buffer ,temp-buffer))))
235 (setq-default enable-multibyte-characters ,multibyte))))))
236 (put 'mm-with-unibyte-buffer 'lisp-indent-function 0)
237 (put 'mm-with-unibyte-buffer 'edebug-form-spec '(body))
239 (defun mm-find-charset-region (b e)
240 "Return a list of charsets in the region."
242 ((and (boundp 'enable-multibyte-characters)
243 enable-multibyte-characters)
244 (find-charset-region b e))
245 ((not (boundp 'current-language-environment))
248 (narrow-to-region b e)
249 (goto-char (point-min))
250 (skip-chars-forward "\0-\177")
254 (list 'ascii 'latin-iso8859-1)))))
256 ;; We are in a unibyte buffer, so we futz around a bit.
259 (narrow-to-region b e)
260 (goto-char (point-min))
261 (let ((entry (assoc (capitalize current-language-environment)
262 language-info-alist)))
263 (skip-chars-forward "\0-\177")
266 (list 'ascii (car (last (assq 'charset entry)))))))))))
270 ;;; mm-util.el ends here