1 ;;; mm-bodies.el --- Functions for decoding MIME things
3 ;; Copyright (C) 1998, 1999, 2000, 2001, 2002, 2003, 2004,
4 ;; 2005 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., 51 Franklin Street, Fifth Floor,
23 ;; Boston, MA 02110-1301, USA.
30 (defvar mm-uu-decode-function)
31 (defvar mm-uu-binhex-decode-function))
37 ;; 8bit treatment gets any char except: 0x32 - 0x7f, LF, TAB, BEL,
38 ;; BS, vertical TAB, form feed, and ^_
40 ;; Note that CR is *not* included, as that would allow a non-paired CR
41 ;; in the body contrary to RFC 2822:
43 ;; - CR and LF MUST only occur together as CRLF; they MUST NOT
44 ;; appear independently in the body.
46 (defvar mm-7bit-chars "\x20-\x7f\n\t\x7\x8\xb\xc\x1f")
48 (defcustom mm-body-charset-encoding-alist
49 '((iso-2022-jp . 7bit)
50 (iso-2022-jp-2 . 7bit)
51 ;; We MUST encode UTF-16 because it can contain \0's which is
52 ;; known to break servers.
53 ;; Note: UTF-16 variants are invalid for text parts [RFC 2781],
54 ;; so this can't happen :-/.
55 ;; PPS: Yes, it can happen if the user specifies UTF-16 in the MML
60 "Alist of MIME charsets to encodings.
61 Valid encodings are `7bit', `8bit', `quoted-printable' and `base64'."
62 :type '(repeat (cons (symbol :tag "charset")
63 (choice :tag "encoding"
66 (const quoted-printable)
70 (defun mm-encode-body (&optional charset)
72 Should be called narrowed to the body that is to be encoded.
73 If there is more than one non-ASCII MULE charset in the body, then the
74 list of MULE charsets found is returned.
75 If CHARSET is non-nil, it is used as the MIME charset to encode the body.
76 If successful, the MIME charset is returned.
77 If no encoding was done, nil is returned."
78 (if (not (mm-multibyte-p))
79 ;; In the non-Mule case, we search for non-ASCII chars and
80 ;; return the value of `mail-parse-charset' if any are found.
83 (goto-char (point-min))
84 (if (re-search-forward "[^\x0-\x7f]" nil t)
85 (or mail-parse-charset
86 (message-options-get 'mm-encody-body-charset)
88 'mm-encody-body-charset
89 (mm-read-coding-system "Charset used in the article: ")))
90 ;; The logic in `mml-generate-mime-1' confirms that it's OK
91 ;; to return nil here.
96 (mm-encode-coding-region (point-min) (point-max)
97 (mm-charset-to-coding-system charset))
99 (goto-char (point-min))
100 (let ((charsets (mm-find-mime-charset-region (point-min) (point-max)
106 ;; Too many charsets.
107 ((> (length charsets) 1)
112 (setq charset (car charsets))
113 (mm-encode-coding-region (point-min) (point-max)
114 (mm-charset-to-coding-system charset))))
117 (defun mm-long-lines-p (length)
118 "Say whether any of the lines in the buffer is longer than LENGTH."
120 (goto-char (point-min))
122 (while (and (not (eobp))
123 (not (> (current-column) length)))
126 (and (> (current-column) length)
129 (defvar message-posting-charset)
131 (defun mm-body-encoding (charset &optional encoding)
132 "Do Content-Transfer-Encoding and return the encoding of the current buffer."
133 (when (stringp encoding)
134 (setq encoding (intern (downcase encoding))))
135 (let ((bits (mm-body-7-or-8))
136 (longp (mm-long-lines-p 1000)))
140 (not (and mm-use-ultra-safe-encoding
141 (or (save-excursion (re-search-forward " $" nil t))
142 (save-excursion (re-search-forward "^From " nil t)))))
145 ((and (not mm-use-ultra-safe-encoding)
147 (not (cdr (assq charset mm-body-charset-encoding-alist)))
148 (or (eq t (cdr message-posting-charset))
149 (memq charset (cdr message-posting-charset))
150 (eq charset mail-parse-charset)))
153 (let ((encoding (or encoding
154 (cdr (assq charset mm-body-charset-encoding-alist))
156 (when mm-use-ultra-safe-encoding
157 (setq encoding (mm-safer-encoding encoding)))
158 (mm-encode-content-transfer-encoding encoding "text/plain")
161 (defun mm-body-7-or-8 ()
162 "Say whether the body is 7bit or 8bit."
164 (goto-char (point-min))
165 (skip-chars-forward mm-7bit-chars)
171 ;;; Functions for decoding
174 (eval-when-compile (defvar mm-uu-yenc-decode-function))
176 (defun mm-decode-content-transfer-encoding (encoding &optional type)
177 "Decodes buffer encoded with ENCODING, returning success status.
178 If TYPE is `text/plain' CRLF->LF translation may occur."
180 (condition-case error
182 ((eq encoding 'quoted-printable)
183 (quoted-printable-decode-region (point-min) (point-max))
185 ((eq encoding 'base64)
186 (base64-decode-region
188 ;; Some mailers insert whitespace
189 ;; junk at the end which
190 ;; base64-decode-region dislikes.
191 ;; Also remove possible junk which could
192 ;; have been added by mailing list software.
194 (goto-char (point-min))
195 (while (re-search-forward "^[\t ]*\r?\n" nil t)
196 (delete-region (match-beginning 0) (match-end 0)))
197 (goto-char (point-max))
198 (when (re-search-backward "^[A-Za-z0-9+/]+=*[\t ]*$" nil t)
201 ((memq encoding '(7bit 8bit binary))
207 ((memq encoding '(x-uuencode x-uue))
209 (funcall mm-uu-decode-function (point-min) (point-max))
211 ((eq encoding 'x-binhex)
213 (funcall mm-uu-binhex-decode-function (point-min) (point-max))
215 ((eq encoding 'x-yenc)
217 (funcall mm-uu-yenc-decode-function (point-min) (point-max))
219 ((functionp encoding)
220 (funcall encoding (point-min) (point-max))
223 (message "Unknown encoding %s; defaulting to 8bit" encoding)))
225 (message "Error while decoding: %s" error)
228 (memq encoding '(base64 x-uuencode x-uue x-binhex x-yenc))
229 (string-match "\\`text/" type))
230 (goto-char (point-min))
231 (while (search-forward "\r\n" nil t)
232 (replace-match "\n" t t)))))
234 (defun mm-decode-body (charset &optional encoding type)
235 "Decode the current article that has been encoded with ENCODING to CHARSET.
236 ENCODING is a MIME content transfer encoding.
237 CHARSET is the MIME charset with which to decode the data after transfer
238 decoding. If it is nil, default to `mail-parse-charset'."
239 (when (stringp charset)
240 (setq charset (intern (downcase charset))))
241 (when (or (not charset)
242 (eq 'gnus-all mail-parse-ignored-charsets)
243 (memq 'gnus-all mail-parse-ignored-charsets)
244 (memq charset mail-parse-ignored-charsets))
245 (setq charset mail-parse-charset))
248 (mm-decode-content-transfer-encoding encoding type))
249 (when (featurep 'mule) ; Fixme: Wrong test for unibyte session.
250 (let ((coding-system (mm-charset-to-coding-system charset)))
251 (if (and (not coding-system)
252 (listp mail-parse-ignored-charsets)
253 (memq 'gnus-unknown mail-parse-ignored-charsets))
255 (mm-charset-to-coding-system mail-parse-charset)))
256 (when (and charset coding-system
257 ;; buffer-file-coding-system
258 ;;Article buffer is nil coding system
261 (or (not (eq coding-system 'ascii))
262 (setq coding-system mail-parse-charset))
263 (not (eq coding-system 'gnus-decoded)))
264 (mm-decode-coding-region (point-min) (point-max)
266 (setq buffer-file-coding-system
267 (if (boundp 'last-coding-system-used)
268 (symbol-value 'last-coding-system-used)
271 (defun mm-decode-string (string charset)
272 "Decode STRING with CHARSET."
273 (when (stringp charset)
274 (setq charset (intern (downcase charset))))
275 (when (or (not charset)
276 (eq 'gnus-all mail-parse-ignored-charsets)
277 (memq 'gnus-all mail-parse-ignored-charsets)
278 (memq charset mail-parse-ignored-charsets))
279 (setq charset mail-parse-charset))
281 (when (featurep 'mule)
282 (let ((coding-system (mm-charset-to-coding-system charset)))
283 (if (and (not coding-system)
284 (listp mail-parse-ignored-charsets)
285 (memq 'gnus-unknown mail-parse-ignored-charsets))
287 (mm-charset-to-coding-system mail-parse-charset)))
288 (when (and charset coding-system
290 (or (not (eq coding-system 'ascii))
291 (setq coding-system mail-parse-charset)))
292 (mm-decode-coding-string string coding-system))))
297 ;;; mm-bodies.el ends here