1 ;;; rfc2231.el --- Functions for decoding rfc2231 headers
3 ;; Copyright (C) 1998, 1999, 2000, 2002, 2003, 2004
4 ;; Free Software Foundation, Inc.
6 ;; Author: Lars Magne Ingebrigtsen <larsi@gnus.org>
7 ;; This file is part of GNU Emacs.
9 ;; GNU Emacs is free software; you can redistribute it and/or modify
10 ;; it under the terms of the GNU General Public License as published by
11 ;; the Free Software Foundation; either version 2, or (at your option)
14 ;; GNU Emacs is distributed in the hope that it will be useful,
15 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
16 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
17 ;; GNU General Public License for more details.
19 ;; You should have received a copy of the GNU General Public License
20 ;; along with GNU Emacs; see the file COPYING. If not, write to the
21 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
22 ;; Boston, MA 02111-1307, USA.
28 (eval-when-compile (require 'cl))
31 (autoload 'mm-encode-body "mm-bodies")
32 (autoload 'mail-header-remove-whitespace "mail-parse")
33 (autoload 'mail-header-remove-comments "mail-parse")
35 (defun rfc2231-get-value (ct attribute)
36 "Return the value of ATTRIBUTE from CT."
37 (cdr (assq attribute (cdr ct))))
39 (defun rfc2231-parse-qp-string (string)
40 "Parse QP-encoded string using `rfc2231-parse-string'.
41 N.B. This is in violation with RFC2047, but it seem to be in common use."
42 (rfc2231-parse-string (rfc2047-decode-string string)))
44 (defun rfc2231-parse-string (string)
45 "Parse STRING and return a list.
46 The list will be on the form
47 `(name (attribute . value) (attribute . value)...)"
49 (let ((ttoken (ietf-drums-token-to-list ietf-drums-text-token))
50 (stoken (ietf-drums-token-to-list ietf-drums-tspecials))
51 (ntoken (ietf-drums-token-to-list "0-9"))
53 display-name mailbox c display-string parameters
54 attribute value type subtype number encoded
56 (ietf-drums-init (mail-header-remove-whitespace
57 (mail-header-remove-comments string)))
58 (let ((table (copy-syntax-table ietf-drums-syntax-table)))
59 (modify-syntax-entry ?\' "w" table)
60 (modify-syntax-entry ?* " " table)
61 (modify-syntax-entry ?\; " " table)
62 (modify-syntax-entry ?= " " table)
63 ;; The following isn't valid, but one should be liberal
64 ;; in what one receives.
65 (modify-syntax-entry ?\: "w" table)
66 (set-syntax-table table))
68 (when (and (memq c ttoken)
69 (not (memq c stoken)))
70 (setq type (downcase (buffer-substring
71 (point) (progn (forward-sexp 1) (point)))))
76 (error "Invalid header: %s" string))
78 ;; If c in nil, then this is an invalid header, but
79 ;; since elm generates invalid headers on this form,
81 (when (setq c (char-after))
82 (if (and (memq c ttoken)
83 (not (memq c stoken)))
88 (point) (progn (forward-sexp 1) (point))))))
89 (error "Invalid header: %s" string))
95 (if (not (memq c ntoken))
101 (point) (progn (forward-sexp 1) (point)))))
102 (setq c (char-after))
106 (setq c (char-after)))))
107 ;; See if we have any previous continuations.
108 (when (and prev-attribute
109 (not (eq prev-attribute attribute)))
110 (push (cons prev-attribute prev-value) parameters)
111 (setq prev-attribute nil
114 (error "Invalid header: %s" string))
116 (setq c (char-after))
120 (buffer-substring (1+ (point))
121 (progn (forward-sexp 1) (1- (point))))))
122 ((and (or (memq c ttoken)
123 (> c ?\177)) ;; EXTENSION: Support non-ascii chars.
124 (not (memq c stoken)))
125 (setq value (buffer-substring
126 (point) (progn (forward-sexp) (point)))))
128 (error "Invalid header: %s" string)))
130 (setq value (rfc2231-decode-encoded-string value)))
132 (setq prev-attribute attribute
133 prev-value (concat prev-value value))
134 (push (cons attribute value) parameters))))
136 ;; Take care of any final continuations.
138 (push (cons prev-attribute prev-value) parameters))
141 `(,type ,@(nreverse parameters)))))))
143 (defun rfc2231-decode-encoded-string (string)
144 "Decode an RFC2231-encoded string.
145 These look like \"us-ascii'en-us'This%20is%20%2A%2A%2Afun%2A%2A%2A\"."
147 (let ((elems (split-string string "'")))
148 ;; The encoded string may contain zero to two single-quote
149 ;; marks. This should give us the encoded word stripped
150 ;; of any preceding values.
151 (insert (car (last elems)))
152 (goto-char (point-min))
153 (while (search-forward "%" nil t)
156 (string-to-number (buffer-substring (point) (+ (point) 2)) 16)
157 (delete-region (1- (point)) (+ (point) 2)))))
158 ;; Encode using the charset, if any.
159 (when (and (mm-multibyte-p)
161 (not (equal (intern (downcase (car elems))) 'us-ascii)))
162 (mm-decode-coding-region (point-min) (point-max)
163 (intern (downcase (car elems)))))
166 (defun rfc2231-encode-string (param value)
167 "Return and PARAM=VALUE string encoded according to RFC2231."
168 (let ((control (ietf-drums-token-to-list ietf-drums-no-ws-ctl-token))
169 (tspecial (ietf-drums-token-to-list ietf-drums-tspecials))
170 (special (ietf-drums-token-to-list "*'%\n\t"))
171 (ascii (ietf-drums-token-to-list ietf-drums-text-token))
173 spacep encodep charsetp charset broken)
176 (goto-char (point-min))
179 ((or (memq (following-char) control)
180 (memq (following-char) tspecial)
181 (memq (following-char) special))
183 ((eq (following-char) ? )
185 ((not (memq (following-char) ascii))
189 (setq charset (mm-encode-body)))
191 ((or encodep charsetp)
192 (goto-char (point-min))
194 (when (> (current-column) 60)
197 (if (or (not (memq (following-char) ascii))
198 (memq (following-char) control)
199 (memq (following-char) tspecial)
200 (memq (following-char) special)
201 (eq (following-char) ? ))
203 (insert "%" (format "%02x" (following-char)))
206 (goto-char (point-min))
207 (insert (symbol-name (or charset 'us-ascii)) "''")
208 (goto-char (point-min))
212 (insert (if (>= num 0) " " "\n ")
213 param "*" (format "%d" (incf num)) "*=")
216 (goto-char (point-min))
218 (goto-char (point-max))
221 (goto-char (point-min))
227 ;;; rfc2231.el ends here