1 ;;; mm-util.el --- Utility functions for MIME things
2 ;; Copyright (C) 1998,99 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-mime-mule-charset-alist
29 (iso-8859-1 latin-iso8859-1)
30 (iso-8859-2 latin-iso8859-2)
31 (iso-8859-3 latin-iso8859-3)
32 (iso-8859-4 latin-iso8859-4)
33 (iso-8859-5 cyrillic-iso8859-5)
34 (koi8-r cyrillic-iso8859-5)
35 (iso-8859-6 arabic-iso8859-6)
36 (iso-8859-7 greek-iso8859-7)
37 (iso-8859-8 hebrew-iso8859-8)
38 (iso-8859-9 latin-iso8859-9)
39 (viscii vietnamese-viscii-lower)
40 (iso-2022-jp latin-jisx0201 japanese-jisx0208 japanese-jisx0208-1978)
41 (euc-kr korean-ksc5601)
42 (cn-gb-2312 chinese-gb2312)
43 (cn-big5 chinese-big5-1 chinese-big5-2)
45 (thai-tis620 thai-tis620)
46 (iso-2022-7bit ethiopic arabic-1-column arabic-2-column)
47 (iso-2022-jp-2 latin-iso8859-1 greek-iso8859-7
48 latin-jisx0201 japanese-jisx0208-1978
49 chinese-gb2312 japanese-jisx0208
50 korean-ksc5601 japanese-jisx0212
52 (iso-2022-int-1 latin-iso8859-1 greek-iso8859-7
53 latin-jisx0201 japanese-jisx0208-1978
54 chinese-gb2312 japanese-jisx0208
55 korean-ksc5601 japanese-jisx0212
56 chinese-cns11643-1 chinese-cns11643-2)
57 (iso-2022-int-1 latin-iso8859-1 latin-iso8859-2
58 cyrillic-iso8859-5 greek-iso8859-7
59 latin-jisx0201 japanese-jisx0208-1978
60 chinese-gb2312 japanese-jisx0208
61 korean-ksc5601 japanese-jisx0212
62 chinese-cns11643-1 chinese-cns11643-2
63 chinese-cns11643-3 chinese-cns11643-4
64 chinese-cns11643-5 chinese-cns11643-6
66 "Alist of MIME-charset/MULE-charsets.")
72 (let ((nfunc (intern (format "mm-%s" (car elem)))))
73 (if (fboundp (car elem))
74 (defalias nfunc (car elem))
75 (defalias nfunc (cdr elem)))))
76 '((decode-coding-string . (lambda (s a) s))
77 (encode-coding-string . (lambda (s a) s))
78 (encode-coding-region . ignore)
79 (coding-system-list . ignore)
80 (decode-coding-region . ignore)
82 (device-type . ignore)
83 (coding-system-equal . equal)
84 (annotationp . ignore)
85 (set-buffer-file-coding-system . ignore)
87 . (lambda (charset int)
91 "Prompt the user for a coding system."
93 prompt (mapcar (lambda (s) (list (symbol-name (car s))))
94 mm-mime-mule-charset-alist)))))))
96 (defvar mm-coding-system-list nil)
97 (defun mm-get-coding-system-list ()
98 "Get the coding system list."
99 (or mm-coding-system-list
100 (setq mm-coding-system-list (mm-coding-system-list))))
102 (defvar mm-charset-synonym-alist
104 (gb2312 . cn-gb-2312)
106 "A mapping from invalid charset names to the real charset names.")
108 (defun mm-coding-system-p (sym)
109 "Return non-nil if SYM is a coding system."
110 (or (and (fboundp 'coding-system-p) (coding-system-p sym))
111 (memq sym (mm-get-coding-system-list))))
113 (defvar mm-binary-coding-system
115 ((mm-coding-system-p 'binary) 'binary)
116 ((mm-coding-system-p 'no-conversion) 'no-conversion)
118 "100% binary coding system.")
120 (defvar mm-text-coding-system
121 (or (if (memq system-type '(windows-nt ms-dos ms-windows))
122 (and (mm-coding-system-p 'raw-text-dos) 'raw-text-dos)
123 (and (mm-coding-system-p 'raw-text) 'raw-text))
124 mm-binary-coding-system)
125 "Text-safe coding system (For removing ^M).")
127 (defvar mm-text-coding-system-for-write nil
128 "Text coding system for write.")
130 (defvar mm-auto-save-coding-system
132 ((mm-coding-system-p 'emacs-mule)
133 (if (memq system-type '(windows-nt ms-dos ms-windows))
134 (if (mm-coding-system-p 'emacs-mule-dos)
135 'emacs-mule-dos mm-binary-coding-system)
137 ((mm-coding-system-p 'escape-quoted) 'escape-quoted)
138 (t mm-binary-coding-system))
139 "Coding system of auto save file.")
141 ;;; Internal variables:
145 (defun mm-mule-charset-to-mime-charset (charset)
146 "Return the MIME charset corresponding to MULE CHARSET."
147 (let ((alist mm-mime-mule-charset-alist)
150 (when (memq charset (cdar alist))
151 (setq out (caar alist)
156 (defun mm-charset-to-coding-system (charset &optional lbt)
157 "Return coding-system corresponding to CHARSET.
158 CHARSET is a symbol naming a MIME charset.
159 If optional argument LBT (`unix', `dos' or `mac') is specified, it is
160 used as the line break code type of the coding system."
161 (when (stringp charset)
162 (setq charset (intern (downcase charset))))
164 (or (cdr (assq charset mm-charset-synonym-alist))
167 (setq charset (intern (format "%s-%s" charset lbt))))
169 ;; Running in a non-MULE environment.
170 ((null (mm-get-coding-system-list))
173 ((eq charset 'us-ascii)
175 ;; Check to see whether we can handle this charset.
176 ((memq charset (mm-get-coding-system-list))
182 (defun mm-replace-chars-in-string (string from to)
183 "Replace characters in STRING from FROM to TO."
184 (let ((string (substring string 0)) ;Copy string.
185 (len (length string))
187 ;; Replace all occurrences of FROM with TO.
189 (when (= (aref string idx) from)
190 (aset string idx to))
194 (defsubst mm-enable-multibyte ()
195 "Enable multibyte in the current buffer."
196 (when (and (fboundp 'set-buffer-multibyte)
197 (boundp 'enable-multibyte-characters)
198 (default-value 'enable-multibyte-characters))
199 (set-buffer-multibyte t)))
201 (defsubst mm-disable-multibyte ()
202 "Disable multibyte in the current buffer."
203 (when (fboundp 'set-buffer-multibyte)
204 (set-buffer-multibyte nil)))
206 (defun mm-preferred-coding-system (charset)
207 ;; A typo in some Emacs versions.
208 (or (get-charset-property charset 'prefered-coding-system)
209 (get-charset-property charset 'preferred-coding-system)))
211 (defun mm-mime-charset (charset)
212 "Return the MIME charset corresponding to the MULE CHARSET."
213 (if (fboundp 'coding-system-get)
214 ;; This exists in Emacs 20.
216 (and (mm-preferred-coding-system charset)
218 (mm-preferred-coding-system charset) 'mime-charset))
219 (and (eq charset 'ascii)
221 (mm-preferred-coding-system charset)
222 (mm-mule-charset-to-mime-charset charset))
223 ;; This is for XEmacs.
224 (mm-mule-charset-to-mime-charset charset)))
226 (defun mm-find-mime-charset-region (b e)
227 "Return the MIME charsets needed to encode the region between B and E."
229 (mapcar 'mm-mime-charset
231 (mm-find-charset-region b e)))))
232 (when (memq 'iso-2022-jp-2 charsets)
233 (setq charsets (delq 'iso-2022-jp charsets)))
234 (delete-duplicates charsets)))
236 (defsubst mm-multibyte-p ()
237 "Say whether multibyte is enabled."
238 (or (string-match "XEmacs\\|Lucid" emacs-version)
239 (and (boundp 'enable-multibyte-characters)
240 enable-multibyte-characters)))
242 (defmacro mm-with-unibyte-buffer (&rest forms)
243 "Create a temporary buffer, and evaluate FORMS there like `progn'.
244 See also `with-temp-file' and `with-output-to-string'."
245 (let ((temp-buffer (make-symbol "temp-buffer"))
246 (multibyte (make-symbol "multibyte")))
247 `(if (or (string-match "XEmacs\\|Lucid" emacs-version)
248 (not (boundp 'enable-multibyte-characters)))
249 (with-temp-buffer ,@forms)
250 (let ((,multibyte (default-value 'enable-multibyte-characters))
254 (setq-default enable-multibyte-characters nil)
256 (get-buffer-create (generate-new-buffer-name " *temp*")))
258 (with-current-buffer ,temp-buffer
259 (let ((buffer-file-coding-system mm-binary-coding-system)
260 (coding-system-for-read mm-binary-coding-system)
261 (coding-system-for-write mm-binary-coding-system))
263 (and (buffer-name ,temp-buffer)
264 (kill-buffer ,temp-buffer))))
265 (setq-default enable-multibyte-characters ,multibyte))))))
266 (put 'mm-with-unibyte-buffer 'lisp-indent-function 0)
267 (put 'mm-with-unibyte-buffer 'edebug-form-spec '(body))
269 (defun mm-find-charset-region (b e)
270 "Return a list of charsets in the region."
272 ((and (mm-multibyte-p)
273 (fboundp 'find-charset-region))
274 (find-charset-region b e))
275 ((not (boundp 'current-language-environment))
278 (narrow-to-region b e)
279 (goto-char (point-min))
280 (skip-chars-forward "\0-\177")
283 (delq nil (list 'ascii mail-parse-charset))))))
285 ;; We are in a unibyte buffer, so we futz around a bit.
288 (narrow-to-region b e)
289 (goto-char (point-min))
290 (let ((entry (assoc (capitalize current-language-environment)
291 language-info-alist)))
292 (skip-chars-forward "\0-\177")
295 (list 'ascii (car (last (assq 'charset entry)))))))))))
297 (defun mm-read-charset (prompt)
302 (mapcar (lambda (e) (list (symbol-name (car e))))
303 mm-mime-mule-charset-alist)
306 (defun mm-quote-arg (arg)
307 "Return a version of ARG that is safe to evaluate in a shell."
308 (let ((pos 0) new-pos accum)
309 ;; *** bug: we don't handle newline characters properly
310 (while (setq new-pos (string-match "[]*[;!'`\"$\\& \t{} |()<>]" arg pos))
311 (push (substring arg pos new-pos) accum)
313 (push (list (aref arg new-pos)) accum)
314 (setq pos (1+ new-pos)))
317 (apply 'concat (nconc (nreverse accum) (list (substring arg pos)))))))
319 (defun mm-auto-mode-alist ()
320 "Return an `auto-mode-alist' with only the .gz (etc) thingies."
321 (let ((alist auto-mode-alist)
324 (when (listp (cdar alist))
325 (push (car alist) out))
329 (defvar mm-inhibit-file-name-handlers
331 "A list of handlers doing (un)compression (etc) thingies.")
333 (defun mm-insert-file-contents (filename &optional visit beg end replace
335 "Like `insert-file-contents', q.v., but only reads in the file.
336 A buffer may be modified in several ways after reading into the buffer due
337 to advanced Emacs features, such as file-name-handlers, format decoding,
338 find-file-hooks, etc.
339 If INHIBIT is non-nil, inhibit mm-inhibit-file-name-handlers.
340 This function ensures that none of these modifications will take place."
341 (let ((format-alist nil)
342 (auto-mode-alist (if inhibit nil (mm-auto-mode-alist)))
343 (default-major-mode 'fundamental-mode)
344 (enable-local-variables nil)
345 (after-insert-file-functions nil)
346 (enable-local-eval nil)
347 (find-file-hooks nil)
348 (inhibit-file-name-operation (if inhibit
349 'insert-file-contents
350 inhibit-file-name-operation))
351 (inhibit-file-name-handlers
353 (append mm-inhibit-file-name-handlers
354 inhibit-file-name-handlers)
355 inhibit-file-name-handlers)))
356 (insert-file-contents filename visit beg end replace)))
358 (defun mm-append-to-file (start end filename &optional codesys inhibit)
359 "Append the contents of the region to the end of file FILENAME.
360 When called from a function, expects three arguments,
361 START, END and FILENAME. START and END are buffer positions
362 saying what text to write.
363 Optional fourth argument specifies the coding system to use when
365 If INHIBIT is non-nil, inhibit mm-inhibit-file-name-handlers."
366 (let ((coding-system-for-write
367 (or codesys mm-text-coding-system-for-write
368 mm-text-coding-system))
369 (inhibit-file-name-operation (if inhibit
371 inhibit-file-name-operation))
372 (inhibit-file-name-handlers
374 (append mm-inhibit-file-name-handlers
375 inhibit-file-name-handlers)
376 inhibit-file-name-handlers)))
377 (append-to-file start end filename)))
379 (defun mm-write-region (start end filename &optional append visit lockname
380 coding-system inhibit)
382 "Like `write-region'.
383 If INHIBIT is non-nil, inhibit mm-inhibit-file-name-handlers."
384 (let ((coding-system-for-write
385 (or coding-system mm-text-coding-system-for-write
386 mm-text-coding-system))
387 (inhibit-file-name-operation (if inhibit
389 inhibit-file-name-operation))
390 (inhibit-file-name-handlers
392 (append mm-inhibit-file-name-handlers
393 inhibit-file-name-handlers)
394 inhibit-file-name-handlers)))
395 (write-region start end filename append visit lockname)))
399 ;;; mm-util.el ends here