1 ;;; tm-ew-d.el --- RFC 2047 based encoded-word decoder for GNU Emacs
3 ;; Copyright (C) 1995,1996,1997 Free Software Foundation, Inc.
5 ;; Author: ENAMI Tsugutomo <enami@sys.ptg.sony.co.jp>
6 ;; MORIOKA Tomohiko <morioka@jaist.ac.jp>
7 ;; Maintainer: MORIOKA Tomohiko <morioka@jaist.ac.jp>
9 ;; Original: 1992/07/20 ENAMI Tsugutomo's `mime.el'.
10 ;; Renamed: 1993/06/03 to tiny-mime.el.
11 ;; Renamed: 1995/10/03 from tiny-mime.el. (split off encoder)
12 ;; Version: $Revision: 7.40 $
13 ;; Keywords: encoded-word, MIME, multilingual, header, mail, news
15 ;; This file is part of tm (Tools for MIME).
17 ;; This program is free software; you can redistribute it and/or
18 ;; modify it under the terms of the GNU General Public License as
19 ;; published by the Free Software Foundation; either version 2, or (at
20 ;; your option) any later version.
22 ;; This program is distributed in the hope that it will be useful, but
23 ;; WITHOUT ANY WARRANTY; without even the implied warranty of
24 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
25 ;; General Public License for more details.
27 ;; You should have received a copy of the GNU General Public License
28 ;; along with GNU Emacs; see the file COPYING. If not, write to the
29 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
30 ;; Boston, MA 02111-1307, USA.
44 (defconst tm-ew-d/RCS-ID
45 "$Id: tm-ew-d.el,v 7.40 1997/03/06 17:53:51 morioka Exp $")
46 (defconst mime/eword-decoder-version (get-version-string tm-ew-d/RCS-ID))
49 ;;; @ MIME encoded-word definition
52 (defconst mime/encoded-text-regexp "[!->@-~]+")
53 (defconst mime/encoded-word-regexp (concat (regexp-quote "=?")
61 mime/encoded-text-regexp
69 (defun mime-eword/decode-string (string &optional must-unfold)
70 "Decode MIME encoded-words in STRING.
72 STRING is unfolded before decoding.
74 If an encoded-word is broken or your emacs implementation can not
75 decode the charset included in it, it is not decoded.
77 If MUST-UNFOLD is non-nil, it unfolds and eliminates line-breaks even
78 if there are in decoded encoded-words (generated by bad manner MUA
79 such as a version of Net$cape). [tm-ew-d.el]"
80 (setq string (std11-unfold-string string))
81 (let ((dest "")(ew nil)
83 (while (and (string-match mime/encoded-word-regexp string)
84 (setq beg (match-beginning 0)
90 (string-match "^[ \t]+$" (substring string 0 beg))
92 (setq dest (concat dest (substring string 0 beg)))
97 (mime/decode-encoded-word
98 (substring string beg end) must-unfold)
100 (setq string (substring string end))
110 (defun mime-eword/decode-region (start end &optional unfolding must-unfold)
111 "Decode MIME encoded-words in region between START and END.
113 If UNFOLDING is not nil, it unfolds before decoding.
115 If MUST-UNFOLD is non-nil, it unfolds and eliminates line-breaks even
116 if there are in decoded encoded-words (generated by bad manner MUA
117 such as a version of Net$cape). [tm-ew-d.el]"
121 (narrow-to-region start end)
125 (goto-char (point-min))
126 (while (re-search-forward (concat "\\(" mime/encoded-word-regexp "\\)"
128 "\\(" mime/encoded-word-regexp "\\)")
130 (replace-match "\\1\\6")
131 (goto-char (point-min))
133 (let (charset encoding text)
134 (while (re-search-forward mime/encoded-word-regexp nil t)
135 (insert (mime/decode-encoded-word
137 (buffer-substring (match-beginning 0) (match-end 0))
138 (delete-region (match-beginning 0) (match-end 0))
144 ;;; @ for message header
147 (defun mime/decode-message-header ()
148 "Decode MIME encoded-words in message header. [tm-ew-d.el]"
152 (narrow-to-region (goto-char (point-min))
153 (progn (re-search-forward "^$" nil t) (point)))
154 (mime-eword/decode-region (point-min) (point-max) t)
157 (defun mime/unfolding ()
158 (goto-char (point-min))
160 (while (re-search-forward std11-field-head-regexp nil t)
161 (setq beg (match-beginning 0)
162 end (std11-field-end))
163 (setq field (buffer-substring beg end))
164 (if (string-match mime/encoded-word-regexp field)
166 (narrow-to-region (goto-char beg) end)
167 (while (re-search-forward "\n\\([ \t]\\)" nil t)
171 (goto-char (point-max))
176 ;;; @ encoded-word decoder
179 (defun mime/decode-encoded-word (word &optional must-unfold)
180 "Decode WORD if it is an encoded-word.
182 If your emacs implementation can not decode the charset of WORD, it
183 returns WORD. Similarly the encoded-word is broken, it returns WORD.
185 If MUST-UNFOLD is non-nil, it unfolds and eliminates line-breaks even
186 if there are in decoded encoded-word (generated by bad manner MUA such
187 as a version of Net$cape). [tm-ew-d.el]"
188 (or (if (string-match mime/encoded-word-regexp word)
190 (substring word (match-beginning 1) (match-end 1))
194 (substring word (match-beginning 2) (match-end 2))
197 (substring word (match-beginning 3) (match-end 3))
200 (mime/decode-encoded-text charset encoding text must-unfold)
202 (and (add-text-properties 0 (length word)
204 (list 'face tm:warning-face))
211 ;;; @ encoded-text decoder
214 (defun mime/decode-encoded-text (charset encoding string &optional must-unfold)
215 "Decode STRING as an encoded-text.
217 If your emacs implementation can not decode CHARSET, it returns nil.
219 If ENCODING is not \"B\" or \"Q\", it occurs error.
220 So you should write error-handling code if you don't want break by errors.
222 If MUST-UNFOLD is non-nil, it unfolds and eliminates line-breaks even
223 if there are in decoded encoded-text (generated by bad manner MUA such
224 as a version of Net$cape). [tm-ew-d.el]"
225 (let ((cs (mime-charset-to-coding-system charset)))
229 ((string-equal "B" encoding)
230 (if (and (string-match mime/B-encoded-text-regexp string)
231 (string-equal string (match-string 0 string)))
232 (base64-decode-string string)
233 (error "Invalid encoded-text %s" string)))
234 ((string-equal "Q" encoding)
235 (if (and (string-match mime/Q-encoded-text-regexp string)
236 (string-equal string (match-string 0 string)))
237 (q-encoding-decode-string string)
238 (error "Invalid encoded-text %s" string)))
240 (error "Invalid encoding %s" encoding)
245 (setq dest (decode-coding-string dest cs))
252 (t (char-to-string chr)))
254 (std11-unfold-string dest)
265 ;;; tm-ew-d.el ends here