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 (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) charset)
98 (goto-char (point-min))
99 (let ((charsets (mm-find-mime-charset-region (point-min) (point-max)
105 ;; Too many charsets.
106 ((> (length charsets) 1)
111 (setq charset (car charsets))
112 (mm-encode-coding-region (point-min) (point-max)
113 (mm-charset-to-coding-system charset))))
116 (defun mm-long-lines-p (length)
117 "Say whether any of the lines in the buffer is longer than LENGTH."
119 (goto-char (point-min))
121 (while (and (not (eobp))
122 (not (> (current-column) length)))
125 (and (> (current-column) length)
128 (defvar message-posting-charset)
130 (defun mm-body-encoding (charset &optional encoding)
131 "Do Content-Transfer-Encoding and return the encoding of the current buffer."
132 (when (stringp encoding)
133 (setq encoding (intern (downcase encoding))))
134 (let ((bits (mm-body-7-or-8))
135 (longp (mm-long-lines-p 1000)))
139 (not (and mm-use-ultra-safe-encoding
140 (save-excursion (re-search-forward "^From " nil t))))
143 ((and (not mm-use-ultra-safe-encoding)
145 (not (cdr (assq charset mm-body-charset-encoding-alist)))
146 (or (eq t (cdr message-posting-charset))
147 (memq charset (cdr message-posting-charset))
148 (eq charset mail-parse-charset)))
151 (let ((encoding (or encoding
152 (cdr (assq charset mm-body-charset-encoding-alist))
154 (when mm-use-ultra-safe-encoding
155 (setq encoding (mm-safer-encoding encoding)))
156 (mm-encode-content-transfer-encoding encoding "text/plain")
159 (defun mm-body-7-or-8 ()
160 "Say whether the body is 7bit or 8bit."
162 (goto-char (point-min))
163 (skip-chars-forward mm-7bit-chars)
169 ;;; Functions for decoding
172 (eval-when-compile (defvar mm-uu-yenc-decode-function))
174 (defun mm-decode-content-transfer-encoding (encoding &optional type)
175 "Decodes buffer encoded with ENCODING, returning success status.
176 If TYPE is `text/plain' CRLF->LF translation may occur."
178 (condition-case error
180 ((eq encoding 'quoted-printable)
181 (quoted-printable-decode-region (point-min) (point-max))
183 ((eq encoding 'base64)
184 (base64-decode-region
186 ;; Some mailers insert whitespace
187 ;; junk at the end which
188 ;; base64-decode-region dislikes.
189 ;; Also remove possible junk which could
190 ;; have been added by mailing list software.
192 (goto-char (point-min))
193 (while (re-search-forward "^[\t ]*\r?\n" nil t)
194 (delete-region (match-beginning 0) (match-end 0)))
195 (goto-char (point-max))
196 (when (re-search-backward "^[A-Za-z0-9+/]+=*[\t ]*$" nil t)
199 ((memq encoding '(7bit 8bit binary))
205 ((memq encoding '(x-uuencode x-uue))
207 (funcall mm-uu-decode-function (point-min) (point-max))
209 ((eq encoding 'x-binhex)
211 (funcall mm-uu-binhex-decode-function (point-min) (point-max))
213 ((eq encoding 'x-yenc)
215 (funcall mm-uu-yenc-decode-function (point-min) (point-max))
217 ((functionp encoding)
218 (funcall encoding (point-min) (point-max))
221 (message "Unknown encoding %s; defaulting to 8bit" encoding)))
223 (message "Error while decoding: %s" error)
226 (memq encoding '(base64 x-uuencode x-uue x-binhex x-yenc))
227 (equal type "text/plain"))
228 (goto-char (point-min))
229 (while (search-forward "\r\n" nil t)
230 (replace-match "\n" t t)))))
232 (defun mm-decode-body (charset &optional encoding type)
233 "Decode the current article that has been encoded with ENCODING to CHARSET.
234 ENCODING is a MIME content transfer encoding.
235 CHARSET is the MIME charset with which to decode the data after transfer
236 decoding. If it is nil, default to `mail-parse-charset'."
237 (when (stringp charset)
238 (setq charset (intern (downcase charset))))
239 (when (or (not charset)
240 (eq 'gnus-all mail-parse-ignored-charsets)
241 (memq 'gnus-all mail-parse-ignored-charsets)
242 (memq charset mail-parse-ignored-charsets))
243 (setq charset mail-parse-charset))
246 (mm-decode-content-transfer-encoding encoding type))
247 (when (featurep 'mule) ; Fixme: Wrong test for unibyte session.
248 (let ((coding-system (mm-charset-to-coding-system charset)))
249 (if (and (not coding-system)
250 (listp mail-parse-ignored-charsets)
251 (memq 'gnus-unknown mail-parse-ignored-charsets))
253 (mm-charset-to-coding-system mail-parse-charset)))
254 (when (and charset coding-system
255 ;; buffer-file-coding-system
256 ;;Article buffer is nil coding system
259 (or (not (eq coding-system 'ascii))
260 (setq coding-system mail-parse-charset))
261 (not (eq coding-system 'gnus-decoded)))
262 (mm-decode-coding-region (point-min) (point-max)
264 (setq buffer-file-coding-system
265 (if (boundp 'last-coding-system-used)
266 (symbol-value 'last-coding-system-used)
269 (defun mm-decode-string (string charset)
270 "Decode STRING with CHARSET."
271 (when (stringp charset)
272 (setq charset (intern (downcase charset))))
273 (when (or (not charset)
274 (eq 'gnus-all mail-parse-ignored-charsets)
275 (memq 'gnus-all mail-parse-ignored-charsets)
276 (memq charset mail-parse-ignored-charsets))
277 (setq charset mail-parse-charset))
279 (when (featurep 'mule)
280 (let ((coding-system (mm-charset-to-coding-system charset)))
281 (if (and (not coding-system)
282 (listp mail-parse-ignored-charsets)
283 (memq 'gnus-unknown mail-parse-ignored-charsets))
285 (mm-charset-to-coding-system mail-parse-charset)))
286 (when (and charset coding-system
288 (or (not (eq coding-system 'ascii))
289 (setq coding-system mail-parse-charset)))
290 (mm-decode-coding-string string coding-system))))
295 ;;; mm-bodies.el ends here