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 ;; We MUST encode UTF-16 because it can contain \0's which is
49 ;; known to break servers.
50 ;; Note: UTF-16 variants are invalid for text parts [RFC 2781],
51 ;; so this can't happen :-/.
55 "Alist of MIME charsets to encodings.
56 Valid encodings are `7bit', `8bit', `quoted-printable' and `base64'."
57 :type '(repeat (cons (symbol :tag "charset")
58 (choice :tag "encoding"
61 (const quoted-printable)
65 (defun mm-encode-body (&optional charset)
67 Should be called narrowed to the body that is to be encoded.
68 If there is more than one non-ASCII MULE charset in the body, then the
69 list of MULE charsets found is returned.
70 If CHARSET is non-nil, it is used as the MIME charset to encode the body.
71 If successful, the MIME charset is returned.
72 If no encoding was done, nil is returned."
73 (if (not (mm-multibyte-p))
74 ;; In the non-Mule case, we search for non-ASCII chars and
75 ;; return the value of `mail-parse-charset' if any are found.
78 (goto-char (point-min))
79 (if (re-search-forward "[^\x0-\x7f]" nil t)
80 (or mail-parse-charset
81 (message-options-get 'mm-encody-body-charset)
83 'mm-encody-body-charset
84 (mm-read-coding-system "Charset used in the article: ")))
85 ;; The logic in `mml-generate-mime-1' confirms that it's OK
86 ;; to return nil here.
91 (mm-encode-coding-region (point-min) (point-max) charset)
93 (goto-char (point-min))
94 (let ((charsets (mm-find-mime-charset-region (point-min) (point-max)
100 ;; Too many charsets.
101 ((> (length charsets) 1)
106 (setq charset (car charsets))
107 (mm-encode-coding-region (point-min) (point-max)
108 (mm-charset-to-coding-system charset))))
111 (defun mm-long-lines-p (length)
112 "Say whether any of the lines in the buffer is longer than LINES."
114 (goto-char (point-min))
116 (while (and (not (eobp))
117 (not (> (current-column) length)))
120 (and (> (current-column) length)
123 (defvar message-posting-charset)
125 (defun mm-body-encoding (charset &optional encoding)
126 "Do Content-Transfer-Encoding and return the encoding of the current buffer."
127 (when (stringp encoding)
128 (setq encoding (intern (downcase encoding))))
129 (let ((bits (mm-body-7-or-8))
130 (longp (mm-long-lines-p 1000)))
133 ((and (not mm-use-ultra-safe-encoding)
137 ((and (not mm-use-ultra-safe-encoding)
139 (not (cdr (assq charset mm-body-charset-encoding-alist)))
140 (or (eq t (cdr message-posting-charset))
141 (memq charset (cdr message-posting-charset))
142 (eq charset mail-parse-charset)))
145 (let ((encoding (or encoding
146 (cdr (assq charset mm-body-charset-encoding-alist))
148 (when mm-use-ultra-safe-encoding
149 (setq encoding (mm-safer-encoding encoding)))
150 (mm-encode-content-transfer-encoding encoding "text/plain")
153 (defun mm-body-7-or-8 ()
154 "Say whether the body is 7bit or 8bit."
156 (goto-char (point-min))
157 (skip-chars-forward mm-7bit-chars)
163 ;;; Functions for decoding
166 (eval-when-compile (defvar mm-uu-yenc-decode-function))
168 (defun mm-decode-content-transfer-encoding (encoding &optional type)
169 "Decodes buffer encoded with ENCODING, returning success status.
170 If TYPE is `text/plain' CRLF->LF translation may occur."
172 (condition-case error
174 ((eq encoding 'quoted-printable)
175 (quoted-printable-decode-region (point-min) (point-max))
177 ((eq encoding 'base64)
178 (base64-decode-region
180 ;; Some mailers insert whitespace
181 ;; junk at the end which
182 ;; base64-decode-region dislikes.
183 ;; Also remove possible junk which could
184 ;; have been added by mailing list software.
186 (goto-char (point-min))
187 (while (re-search-forward "^[\t ]*\r?\n" nil t)
188 (delete-region (match-beginning 0) (match-end 0)))
189 (goto-char (point-max))
190 (when (re-search-backward "^[A-Za-z0-9+/]+=*[\t ]*$" nil t)
193 ((memq encoding '(7bit 8bit binary))
199 ((memq encoding '(x-uuencode x-uue))
201 (funcall mm-uu-decode-function (point-min) (point-max))
203 ((eq encoding 'x-binhex)
205 (funcall mm-uu-binhex-decode-function (point-min) (point-max))
207 ((eq encoding 'x-yenc)
209 (funcall mm-uu-yenc-decode-function (point-min) (point-max))
211 ((functionp encoding)
212 (funcall encoding (point-min) (point-max))
215 (message "Unknown encoding %s; defaulting to 8bit" encoding)))
217 (message "Error while decoding: %s" error)
220 (memq encoding '(base64 x-uuencode x-uue x-binhex x-yenc))
221 (equal type "text/plain"))
222 (goto-char (point-min))
223 (while (search-forward "\r\n" nil t)
224 (replace-match "\n" t t)))))
226 (defun mm-decode-body (charset &optional encoding type)
227 "Decode the current article that has been encoded with ENCODING to CHARSET.
228 ENCODING is a MIME content transfer encoding.
229 CHARSET is the MIME charset with which to decode the data after transfer
230 decoding. If it is nil, default to `mail-parse-charset'."
231 (when (stringp charset)
232 (setq charset (intern (downcase charset))))
233 (when (or (not charset)
234 (eq 'gnus-all mail-parse-ignored-charsets)
235 (memq 'gnus-all mail-parse-ignored-charsets)
236 (memq charset mail-parse-ignored-charsets))
237 (setq charset mail-parse-charset))
240 (mm-decode-content-transfer-encoding encoding type))
241 (when (featurep 'mule) ; Fixme: Wrong test for unibyte session.
242 (let ((coding-system (mm-charset-to-coding-system charset)))
243 (if (and (not coding-system)
244 (listp mail-parse-ignored-charsets)
245 (memq 'gnus-unknown mail-parse-ignored-charsets))
247 (mm-charset-to-coding-system mail-parse-charset)))
248 (when (and charset coding-system
249 ;; buffer-file-coding-system
250 ;;Article buffer is nil coding system
253 (or (not (eq coding-system 'ascii))
254 (setq coding-system mail-parse-charset))
255 (not (eq coding-system 'gnus-decoded)))
256 (mm-decode-coding-region (point-min) (point-max)
258 (setq buffer-file-coding-system
259 (if (boundp 'last-coding-system-used)
260 (symbol-value 'last-coding-system-used)
263 (defun mm-decode-string (string charset)
264 "Decode STRING with CHARSET."
265 (when (stringp charset)
266 (setq charset (intern (downcase charset))))
267 (when (or (not charset)
268 (eq 'gnus-all mail-parse-ignored-charsets)
269 (memq 'gnus-all mail-parse-ignored-charsets)
270 (memq charset mail-parse-ignored-charsets))
271 (setq charset mail-parse-charset))
273 (when (featurep 'mule)
274 (let ((coding-system (mm-charset-to-coding-system charset)))
275 (if (and (not coding-system)
276 (listp mail-parse-ignored-charsets)
277 (memq 'gnus-unknown mail-parse-ignored-charsets))
279 (mm-charset-to-coding-system mail-parse-charset)))
280 (when (and charset coding-system
282 (or (not (eq coding-system 'ascii))
283 (setq coding-system mail-parse-charset)))
284 (mm-decode-coding-string string coding-system))))
289 ;;; mm-bodies.el ends here