1 ;;; mm-bodies.el --- Functions for decoding MIME things
3 ;; Copyright (C) 1998, 1999, 2000, 2001, 2003
4 ;; Free Software Foundation, Inc.
6 ;; Author: Lars Magne Ingebrigtsen <larsi@gnus.org>
7 ;; MORIOKA Tomohiko <morioka@jaist.ac.jp>
8 ;; This file is part of GNU Emacs.
10 ;; GNU Emacs is free software; you can redistribute it and/or modify
11 ;; it under the terms of the GNU General Public License as published by
12 ;; the Free Software Foundation; either version 2, or (at your option)
15 ;; GNU Emacs is distributed in the hope that it will be useful,
16 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
17 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
18 ;; GNU General Public License for more details.
20 ;; You should have received a copy of the GNU General Public License
21 ;; along with GNU Emacs; see the file COPYING. If not, write to the
22 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
23 ;; Boston, MA 02111-1307, USA.
30 (or (fboundp 'base64-decode-region)
34 (defvar mm-uu-decode-function)
35 (defvar mm-uu-binhex-decode-function))
41 ;; 8bit treatment gets any char except: 0x32 - 0x7f, CR, LF, TAB, BEL,
42 ;; BS, vertical TAB, form feed, and ^_
43 (defvar mm-7bit-chars "\x20-\x7f\r\n\t\x7\x8\xb\xc\x1f")
45 (defcustom mm-body-charset-encoding-alist
46 '((iso-2022-jp . 7bit)
47 (iso-2022-jp-2 . 7bit))
48 "Alist of MIME charsets to encodings.
49 Valid encodings are `7bit', `8bit', `quoted-printable' and `base64'."
50 :type '(repeat (cons (symbol :tag "charset")
51 (choice :tag "encoding"
54 (const quoted-printable)
58 (defun mm-encode-body (&optional charset)
60 Should be called narrowed to the body that is to be encoded.
61 If there is more than one non-ASCII MULE charset, then list of found
62 MULE charsets are returned.
63 If CHARSET is non-nil, it is used.
64 If successful, the MIME charset is returned.
65 If no encoding was done, nil is returned."
66 (if (not (mm-multibyte-p))
67 ;; In the non-Mule case, we search for non-ASCII chars and
68 ;; return the value of `mail-parse-charset' if any are found.
71 (goto-char (point-min))
72 (if (re-search-forward "[^\x0-\x7f]" nil t)
73 (or mail-parse-charset
74 (message-options-get 'mm-encody-body-charset)
76 'mm-encody-body-charset
77 (mm-read-charset "Charset used in the article: ")))
78 ;; The logic in `mml-generate-mime-1' confirms that it's OK
79 ;; to return nil here.
84 (mm-encode-coding-region (point-min) (point-max) charset)
86 (goto-char (point-min))
87 (let ((charsets (mm-find-mime-charset-region (point-min) (point-max)
95 ((> (length charsets) 1)
99 (setq charset (car charsets))
101 (if (eq (mm-charset-after) 'ascii)
104 (narrow-to-region start (point))
105 (mm-encode-coding-region
106 start (point) (mm-charset-to-coding-system charset))
107 (goto-char (point-max)))
110 (setq start (point))))
113 (mm-encode-coding-region start (point)
114 (mm-charset-to-coding-system charset))
118 (defun mm-long-lines-p (length)
119 "Say whether any of the lines in the buffer is longer than LINES."
121 (goto-char (point-min))
123 (while (and (not (eobp))
124 (not (> (current-column) length)))
127 (and (> (current-column) length)
130 (defvar message-posting-charset)
132 (defun mm-body-encoding (charset &optional encoding)
133 "Do Content-Transfer-Encoding and return the encoding of the current buffer."
134 (when (stringp encoding)
135 (setq encoding (intern (downcase encoding))))
136 (let ((bits (mm-body-7-or-8))
137 (longp (mm-long-lines-p 1000)))
140 ((and (not mm-use-ultra-safe-encoding)
144 ((and (not mm-use-ultra-safe-encoding)
146 (not (eq '7bit (cdr (assq charset mm-body-charset-encoding-alist))))
147 (or (eq t (cdr message-posting-charset))
148 (memq charset (cdr message-posting-charset))
149 (eq charset mail-parse-charset)))
152 (let ((encoding (or encoding
153 (cdr (assq charset mm-body-charset-encoding-alist))
155 (when mm-use-ultra-safe-encoding
156 (setq encoding (mm-safer-encoding encoding)))
157 (mm-encode-content-transfer-encoding encoding "text/plain")
160 (defun mm-body-7-or-8 ()
161 "Say whether the body is 7bit or 8bit."
163 ((not (featurep 'mule))
165 (goto-char (point-min))
166 (skip-chars-forward mm-7bit-chars)
172 (if (and (null (delq 'ascii
173 (mm-find-charset-region (point-min) (point-max))))
174 ;;!!!The following is necessary because the function
175 ;;!!!above seems to return the wrong result under
176 ;;!!!Emacs 20.3. Sometimes.
178 (goto-char (point-min))
179 (skip-chars-forward mm-7bit-chars)
185 ;;; Functions for decoding
188 (defun mm-decode-content-transfer-encoding (encoding &optional type)
189 "Decodes buffer encoded with ENCODING, returning success status.
190 If TYPE is `text/plain' CRLF->LF translation may occur."
192 (condition-case error
194 ((eq encoding 'quoted-printable)
195 (quoted-printable-decode-region (point-min) (point-max))
197 ((eq encoding 'base64)
198 (base64-decode-region
200 ;; Some mailers insert whitespace
201 ;; junk at the end which
202 ;; base64-decode-region dislikes.
203 ;; Also remove possible junk which could
204 ;; have been added by mailing list software.
206 (goto-char (point-min))
207 (while (re-search-forward "^[\t ]*\r?\n" nil t)
208 (delete-region (match-beginning 0) (match-end 0)))
209 (goto-char (point-max))
210 (when (re-search-backward "^[A-Za-z0-9+/]+=*[\t ]*$" nil t)
213 ((memq encoding '(7bit 8bit binary))
219 ((memq encoding '(x-uuencode x-uue))
221 (funcall mm-uu-decode-function (point-min) (point-max))
223 ((eq encoding 'x-binhex)
225 (funcall mm-uu-binhex-decode-function (point-min) (point-max))
227 ((eq encoding 'x-yenc)
229 (funcall mm-uu-yenc-decode-function (point-min) (point-max))
231 ((functionp encoding)
232 (funcall encoding (point-min) (point-max))
235 (message "Unknown encoding %s; defaulting to 8bit" encoding)))
237 (message "Error while decoding: %s" error)
240 (memq encoding '(base64 x-uuencode x-uue x-binhex x-yenc))
241 (equal type "text/plain"))
242 (goto-char (point-min))
243 (while (search-forward "\r\n" nil t)
244 (replace-match "\n" t t)))))
246 (defun mm-decode-body (charset &optional encoding type force)
247 "Decode the current article that has been encoded with ENCODING.
248 The characters in CHARSET should then be decoded. If FORCE is non-nil
249 use the supplied charset unconditionally."
250 (if (stringp charset)
251 (setq charset (intern (downcase charset))))
252 (if (or (not charset)
253 (eq 'gnus-all mail-parse-ignored-charsets)
254 (memq 'gnus-all mail-parse-ignored-charsets)
255 (memq charset mail-parse-ignored-charsets))
256 (setq charset mail-parse-charset))
259 (mm-decode-content-transfer-encoding encoding type))
260 (when (featurep 'mule)
261 (let ((coding-system (mm-charset-to-coding-system charset)))
262 (if (and (not coding-system)
263 (listp mail-parse-ignored-charsets)
264 (memq 'gnus-unknown mail-parse-ignored-charsets))
266 (mm-charset-to-coding-system mail-parse-charset)))
267 (when (and charset coding-system
268 ;; buffer-file-coding-system
269 ;;Article buffer is nil coding system
272 (or (not (eq coding-system 'ascii))
273 (setq coding-system mail-parse-charset))
274 (not (eq coding-system 'gnus-decoded)))
276 (mm-decode-coding-region (point-min) (point-max)
278 (mm-decode-coding-region-safely (point-min) (point-max)
280 (setq buffer-file-coding-system
281 (if (boundp 'last-coding-system-used)
282 last-coding-system-used
285 (defun mm-decode-coding-region-safely (start end coding-system)
286 "Decode region between START and END with CODING-SYSTEM.
287 If CODING-SYSTEM is not a valid coding system for the text, let Emacs
288 decide which coding system to use."
289 (let* ((orig (buffer-substring start end))
292 (narrow-to-region start end)
293 (mm-decode-coding-region (point-min) (point-max) coding-system)
294 (setq charsets (find-charset-region (point-min) (point-max)))
295 (when (or (memq 'eight-bit-control charsets)
296 (memq 'eight-bit-graphic charsets))
297 (delete-region (point-min) (point-max))
299 (mm-decode-coding-region (point-min) (point-max) 'undecided)))))
301 (defun mm-decode-string (string charset)
302 "Decode STRING with CHARSET."
303 (when (stringp charset)
304 (setq charset (intern (downcase charset))))
305 (when (or (not charset)
306 (eq 'gnus-all mail-parse-ignored-charsets)
307 (memq 'gnus-all mail-parse-ignored-charsets)
308 (memq charset mail-parse-ignored-charsets))
309 (setq charset mail-parse-charset))
311 (when (featurep 'mule)
312 (let ((coding-system (mm-charset-to-coding-system charset)))
313 (if (and (not coding-system)
314 (listp mail-parse-ignored-charsets)
315 (memq 'gnus-unknown mail-parse-ignored-charsets))
317 (mm-charset-to-coding-system mail-parse-charset)))
318 (when (and charset coding-system
320 (or (not (eq coding-system 'ascii))
321 (setq coding-system mail-parse-charset)))
322 (mm-decode-coding-string string coding-system))))
327 ;;; mm-bodies.el ends here