1 ;;; mm-util.el --- Utility functions for MIME things
2 ;; Copyright (C) 1998, 1999, 2000 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.
29 (defvar mm-mime-mule-charset-alist
31 (iso-8859-1 latin-iso8859-1)
32 (iso-8859-2 latin-iso8859-2)
33 (iso-8859-3 latin-iso8859-3)
34 (iso-8859-4 latin-iso8859-4)
35 (iso-8859-5 cyrillic-iso8859-5)
36 ;; Non-mule (X)Emacs uses the last mule-charset for 8bit characters.
37 ;; The fake mule-charset, gnus-koi8-r, tells Gnus that the default
38 ;; charset is koi8-r, not iso-8859-5.
39 (koi8-r cyrillic-iso8859-5 gnus-koi8-r)
40 (iso-8859-6 arabic-iso8859-6)
41 (iso-8859-7 greek-iso8859-7)
42 (iso-8859-8 hebrew-iso8859-8)
43 (iso-8859-9 latin-iso8859-9)
44 (viscii vietnamese-viscii-lower)
45 (iso-2022-jp latin-jisx0201 japanese-jisx0208 japanese-jisx0208-1978)
46 (euc-kr korean-ksc5601)
47 (cn-gb-2312 chinese-gb2312)
48 (cn-big5 chinese-big5-1 chinese-big5-2)
50 (thai-tis620 thai-tis620)
51 (iso-2022-7bit ethiopic arabic-1-column arabic-2-column)
52 (iso-2022-jp-2 latin-iso8859-1 greek-iso8859-7
53 latin-jisx0201 japanese-jisx0208-1978
54 chinese-gb2312 japanese-jisx0208
55 korean-ksc5601 japanese-jisx0212
57 (iso-2022-int-1 latin-iso8859-1 greek-iso8859-7
58 latin-jisx0201 japanese-jisx0208-1978
59 chinese-gb2312 japanese-jisx0208
60 korean-ksc5601 japanese-jisx0212
61 chinese-cns11643-1 chinese-cns11643-2)
62 (iso-2022-int-1 latin-iso8859-1 latin-iso8859-2
63 cyrillic-iso8859-5 greek-iso8859-7
64 latin-jisx0201 japanese-jisx0208-1978
65 chinese-gb2312 japanese-jisx0208
66 korean-ksc5601 japanese-jisx0212
67 chinese-cns11643-1 chinese-cns11643-2
68 chinese-cns11643-3 chinese-cns11643-4
69 chinese-cns11643-5 chinese-cns11643-6
71 (utf-8 unicode-a unicode-b unicode-c unicode-d unicode-e))
72 "Alist of MIME-charset/MULE-charsets.")
77 (let ((nfunc (intern (format "mm-%s" (car elem)))))
78 (if (fboundp (car elem))
79 (defalias nfunc (car elem))
80 (defalias nfunc (cdr elem)))))
81 '((decode-coding-string . (lambda (s a) s))
82 (encode-coding-string . (lambda (s a) s))
83 (encode-coding-region . ignore)
84 (coding-system-list . ignore)
85 (decode-coding-region . ignore)
87 (device-type . ignore)
88 (coding-system-equal . equal)
89 (annotationp . ignore)
90 (set-buffer-file-coding-system . ignore)
92 . (lambda (charset int)
96 "Prompt the user for a coding system."
98 prompt (mapcar (lambda (s) (list (symbol-name (car s))))
99 mm-mime-mule-charset-alist)))))))
102 (defalias 'mm-char-or-char-int-p
104 ((fboundp 'char-or-char-int-p) 'char-or-char-int-p)
105 ((fboundp 'char-valid-p) 'char-valid-p)
108 (defvar mm-coding-system-list nil)
109 (defun mm-get-coding-system-list ()
110 "Get the coding system list."
111 (or mm-coding-system-list
112 (setq mm-coding-system-list (mm-coding-system-list))))
114 (defvar mm-charset-synonym-alist
116 (gb2312 . cn-gb-2312)
118 "A mapping from invalid charset names to the real charset names.")
120 (defun mm-coding-system-p (sym)
121 "Return non-nil if SYM is a coding system."
122 (or (and (fboundp 'coding-system-p) (coding-system-p sym))
123 (memq sym (mm-get-coding-system-list))))
125 (defvar mm-binary-coding-system
127 ((mm-coding-system-p 'binary) 'binary)
128 ((mm-coding-system-p 'no-conversion) 'no-conversion)
130 "100% binary coding system.")
132 (defvar mm-text-coding-system
133 (or (if (memq system-type '(windows-nt ms-dos ms-windows))
134 (and (mm-coding-system-p 'raw-text-dos) 'raw-text-dos)
135 (and (mm-coding-system-p 'raw-text) 'raw-text))
136 mm-binary-coding-system)
137 "Text-safe coding system (For removing ^M).")
139 (defvar mm-text-coding-system-for-write nil
140 "Text coding system for write.")
142 (defvar mm-auto-save-coding-system
144 ((mm-coding-system-p 'emacs-mule)
145 (if (memq system-type '(windows-nt ms-dos ms-windows))
146 (if (mm-coding-system-p 'emacs-mule-dos)
147 'emacs-mule-dos mm-binary-coding-system)
149 ((mm-coding-system-p 'escape-quoted) 'escape-quoted)
150 (t mm-binary-coding-system))
151 "Coding system of auto save file.")
153 ;;; Internal variables:
157 (defun mm-mule-charset-to-mime-charset (charset)
158 "Return the MIME charset corresponding to MULE CHARSET."
159 (let ((alist mm-mime-mule-charset-alist)
162 (when (memq charset (cdar alist))
163 (setq out (caar alist)
168 (defun mm-charset-to-coding-system (charset &optional lbt)
169 "Return coding-system corresponding to CHARSET.
170 CHARSET is a symbol naming a MIME charset.
171 If optional argument LBT (`unix', `dos' or `mac') is specified, it is
172 used as the line break code type of the coding system."
173 (when (stringp charset)
174 (setq charset (intern (downcase charset))))
176 (or (cdr (assq charset mm-charset-synonym-alist))
179 (setq charset (intern (format "%s-%s" charset lbt))))
181 ;; Running in a non-MULE environment.
182 ((null (mm-get-coding-system-list))
185 ((eq charset 'us-ascii)
187 ;; Check to see whether we can handle this charset.
188 ((memq charset (mm-get-coding-system-list))
194 (defun mm-replace-chars-in-string (string from to)
195 "Replace characters in STRING from FROM to TO."
196 (let ((string (substring string 0)) ;Copy string.
197 (len (length string))
199 ;; Replace all occurrences of FROM with TO.
201 (when (= (aref string idx) from)
202 (aset string idx to))
206 (defsubst mm-enable-multibyte ()
207 "Enable multibyte in the current buffer."
208 (when (and (fboundp 'set-buffer-multibyte)
209 (boundp 'enable-multibyte-characters)
210 (default-value 'enable-multibyte-characters))
211 (set-buffer-multibyte t)))
213 (defsubst mm-disable-multibyte ()
214 "Disable multibyte in the current buffer."
215 (when (fboundp 'set-buffer-multibyte)
216 (set-buffer-multibyte nil)))
218 (defun mm-preferred-coding-system (charset)
219 ;; A typo in some Emacs versions.
220 (or (get-charset-property charset 'prefered-coding-system)
221 (get-charset-property charset 'preferred-coding-system)))
223 (defun mm-charset-after (&optional pos)
224 "Return charset of a character in current buffer at position POS.
225 If POS is nil, it defauls to the current point.
226 If POS is out of range, the value is nil.
227 If the charset is `composition', return the actual one."
229 ((fboundp 'charset-after)
231 ((fboundp 'char-charset)
232 (char-charset (char-after pos)))
233 ((< (mm-char-int (char-after pos)) 128)
235 (mail-parse-mule-charset ;; cached mule-charset
236 mail-parse-mule-charset)
237 ((boundp 'current-language-environment)
238 (let ((entry (assoc current-language-environment
239 language-info-alist)))
240 (setq mail-parse-mule-charset
241 (or (car (last (assq 'charset entry)))
243 (t ;; figure out the charset
244 (setq mail-parse-mule-charset
245 (or (car (last (assq mail-parse-charset
246 mm-mime-mule-charset-alist)))
247 'latin-iso8859-1))))))
248 (if (eq charset 'composition)
249 (let ((p (or pos (point))))
250 (cadr (find-charset-region p (1+ p))))
253 (defun mm-mime-charset (charset)
254 "Return the MIME charset corresponding to the MULE CHARSET."
255 (if (and (fboundp 'coding-system-get) (fboundp 'get-charset-property))
256 ;; This exists in Emacs 20.
258 (and (mm-preferred-coding-system charset)
260 (mm-preferred-coding-system charset) 'mime-charset))
261 (and (eq charset 'ascii)
263 (mm-preferred-coding-system charset)
264 (mm-mule-charset-to-mime-charset charset))
265 ;; This is for XEmacs.
266 (mm-mule-charset-to-mime-charset charset)))
268 (defun mm-delete-duplicates (list)
269 "Simple substitute for CL `delete-duplicates', testing with `equal'."
272 (setq head (car list))
273 (setq list (delete head list))
274 (setq result (cons head result)))
277 (defun mm-find-mime-charset-region (b e)
278 "Return the MIME charsets needed to encode the region between B and E."
279 (let ((charsets (mapcar 'mm-mime-charset
281 (mm-find-charset-region b e)))))
282 (when (memq 'iso-2022-jp-2 charsets)
283 (setq charsets (delq 'iso-2022-jp charsets)))
284 (setq charsets (mm-delete-duplicates charsets))
285 (if (and (> (length charsets) 1)
286 (fboundp 'find-coding-systems-region)
287 (memq 'utf-8 (find-coding-systems-region b e)))
291 (defsubst mm-multibyte-p ()
292 "Say whether multibyte is enabled."
293 (or (string-match "XEmacs\\|Lucid" emacs-version)
294 (and (boundp 'enable-multibyte-characters)
295 enable-multibyte-characters)))
297 (defmacro mm-with-unibyte-buffer (&rest forms)
298 "Create a temporary buffer, and evaluate FORMS there like `progn'.
299 See also `with-temp-file' and `with-output-to-string'."
300 (let ((temp-buffer (make-symbol "temp-buffer"))
301 (multibyte (make-symbol "multibyte")))
302 `(if (or (string-match "XEmacs\\|Lucid" emacs-version)
303 (not (boundp 'enable-multibyte-characters)))
304 (with-temp-buffer ,@forms)
305 (let ((,multibyte (default-value 'enable-multibyte-characters))
309 (setq-default enable-multibyte-characters nil)
311 (get-buffer-create (generate-new-buffer-name " *temp*")))
313 (with-current-buffer ,temp-buffer
314 (let ((buffer-file-coding-system mm-binary-coding-system)
315 (coding-system-for-read mm-binary-coding-system)
316 (coding-system-for-write mm-binary-coding-system))
318 (and (buffer-name ,temp-buffer)
319 (kill-buffer ,temp-buffer))))
320 (setq-default enable-multibyte-characters ,multibyte))))))
321 (put 'mm-with-unibyte-buffer 'lisp-indent-function 0)
322 (put 'mm-with-unibyte-buffer 'edebug-form-spec '(body))
324 (defmacro mm-with-unibyte-current-buffer (&rest forms)
325 "Evaluate FORMS there like `progn' in current buffer."
326 (let ((multibyte (make-symbol "multibyte")))
327 `(if (or (string-match "XEmacs\\|Lucid" emacs-version)
328 (not (fboundp 'set-buffer-multibyte)))
331 (let ((,multibyte (default-value 'enable-multibyte-characters)))
333 (let ((buffer-file-coding-system mm-binary-coding-system)
334 (coding-system-for-read mm-binary-coding-system)
335 (coding-system-for-write mm-binary-coding-system))
336 (set-buffer-multibyte nil)
338 (set-buffer-multibyte ,multibyte))))))
339 (put 'mm-with-unibyte-current-buffer 'lisp-indent-function 0)
340 (put 'mm-with-unibyte-current-buffer 'edebug-form-spec '(body))
342 (defmacro mm-with-unibyte (&rest forms)
343 "Set default `enable-multibyte-characters' to `nil', eval the FORMS."
344 (let ((multibyte (make-symbol "multibyte")))
345 `(if (or (string-match "XEmacs\\|Lucid" emacs-version)
346 (not (boundp 'enable-multibyte-characters)))
348 (let ((,multibyte (default-value 'enable-multibyte-characters)))
351 (setq-default enable-multibyte-characters nil)
353 (setq-default enable-multibyte-characters ,multibyte))))))
354 (put 'mm-with-unibyte 'lisp-indent-function 0)
355 (put 'mm-with-unibyte 'edebug-form-spec '(body))
357 (defun mm-find-charset-region (b e)
358 "Return a list of charsets in the region."
360 ((and (mm-multibyte-p)
361 (fboundp 'find-charset-region))
362 ;; Remove composition since the base charsets have been included.
363 (delq 'composition (find-charset-region b e)))
364 ((not (boundp 'current-language-environment))
367 (narrow-to-region b e)
368 (goto-char (point-min))
369 (skip-chars-forward "\0-\177")
372 (delq nil (list 'ascii
373 (or (car (last (assq mail-parse-charset
374 mm-mime-mule-charset-alist)))
375 'latin-iso8859-1)))))))
377 ;; We are in a unibyte buffer, so we futz around a bit.
380 (narrow-to-region b e)
381 (goto-char (point-min))
382 (let ((entry (assoc current-language-environment
383 language-info-alist)))
384 (skip-chars-forward "\0-\177")
387 (delq nil (list 'ascii
388 (or (car (last (assq 'charset entry)))
389 'latin-iso8859-1))))))))))
391 (defun mm-read-charset (prompt)
396 (mapcar (lambda (e) (list (symbol-name (car e))))
397 mm-mime-mule-charset-alist)
400 (defun mm-quote-arg (arg)
401 "Return a version of ARG that is safe to evaluate in a shell."
402 (let ((pos 0) new-pos accum)
403 ;; *** bug: we don't handle newline characters properly
404 (while (setq new-pos (string-match "[]*[;!'`\"$\\& \t{} |()<>]" arg pos))
405 (push (substring arg pos new-pos) accum)
407 (push (list (aref arg new-pos)) accum)
408 (setq pos (1+ new-pos)))
411 (apply 'concat (nconc (nreverse accum) (list (substring arg pos)))))))
413 (defun mm-auto-mode-alist ()
414 "Return an `auto-mode-alist' with only the .gz (etc) thingies."
415 (let ((alist auto-mode-alist)
418 (when (listp (cdar alist))
419 (push (car alist) out))
423 (defvar mm-inhibit-file-name-handlers
425 "A list of handlers doing (un)compression (etc) thingies.")
427 (defun mm-insert-file-contents (filename &optional visit beg end replace
429 "Like `insert-file-contents', q.v., but only reads in the file.
430 A buffer may be modified in several ways after reading into the buffer due
431 to advanced Emacs features, such as file-name-handlers, format decoding,
432 find-file-hooks, etc.
433 If INHIBIT is non-nil, inhibit mm-inhibit-file-name-handlers.
434 This function ensures that none of these modifications will take place."
435 (let ((format-alist nil)
436 (auto-mode-alist (if inhibit nil (mm-auto-mode-alist)))
437 (default-major-mode 'fundamental-mode)
438 (enable-local-variables nil)
439 (after-insert-file-functions nil)
440 (enable-local-eval nil)
441 (find-file-hooks nil)
442 (inhibit-file-name-operation (if inhibit
443 'insert-file-contents
444 inhibit-file-name-operation))
445 (inhibit-file-name-handlers
447 (append mm-inhibit-file-name-handlers
448 inhibit-file-name-handlers)
449 inhibit-file-name-handlers)))
450 (insert-file-contents filename visit beg end replace)))
452 (defun mm-append-to-file (start end filename &optional codesys inhibit)
453 "Append the contents of the region to the end of file FILENAME.
454 When called from a function, expects three arguments,
455 START, END and FILENAME. START and END are buffer positions
456 saying what text to write.
457 Optional fourth argument specifies the coding system to use when
459 If INHIBIT is non-nil, inhibit mm-inhibit-file-name-handlers."
460 (let ((coding-system-for-write
461 (or codesys mm-text-coding-system-for-write
462 mm-text-coding-system))
463 (inhibit-file-name-operation (if inhibit
465 inhibit-file-name-operation))
466 (inhibit-file-name-handlers
468 (append mm-inhibit-file-name-handlers
469 inhibit-file-name-handlers)
470 inhibit-file-name-handlers)))
471 (append-to-file start end filename)))
473 (defun mm-write-region (start end filename &optional append visit lockname
474 coding-system inhibit)
476 "Like `write-region'.
477 If INHIBIT is non-nil, inhibit mm-inhibit-file-name-handlers."
478 (let ((coding-system-for-write
479 (or coding-system mm-text-coding-system-for-write
480 mm-text-coding-system))
481 (inhibit-file-name-operation (if inhibit
483 inhibit-file-name-operation))
484 (inhibit-file-name-handlers
486 (append mm-inhibit-file-name-handlers
487 inhibit-file-name-handlers)
488 inhibit-file-name-handlers)))
489 (write-region start end filename append visit lockname)))
493 ;;; mm-util.el ends here