;;; rfc2047.el --- functions for encoding and decoding rfc2047 messages
-;; Copyright (C) 1998, 1999, 2000, 2002, 2003 Free Software Foundation, Inc.
+
+;; Copyright (C) 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006,
+;; 2007, 2008, 2009, 2010 Free Software Foundation, Inc.
;; Author: Lars Magne Ingebrigtsen <larsi@gnus.org>
;; MORIOKA Tomohiko <morioka@jaist.ac.jp>
;; This file is part of GNU Emacs.
-;; GNU Emacs is free software; you can redistribute it and/or modify
+;; GNU Emacs is free software: you can redistribute it and/or modify
;; it under the terms of the GNU General Public License as published by
-;; the Free Software Foundation; either version 2, or (at your option)
-;; any later version.
+;; the Free Software Foundation, either version 3 of the License, or
+;; (at your option) any later version.
;; GNU Emacs is distributed in the hope that it will be useful,
;; but WITHOUT ANY WARRANTY; without even the implied warranty of
-;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
;; GNU General Public License for more details.
;; You should have received a copy of the GNU General Public License
-;; along with GNU Emacs; see the file COPYING. If not, write to the
-;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
-;; Boston, MA 02111-1307, USA.
+;; along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>.
;;; Commentary:
;;; Code:
(eval-when-compile
- (require 'cl)
- (defvar message-posting-charset))
+ (require 'cl))
+(defvar message-posting-charset)
-(require 'qp)
(require 'mm-util)
+(require 'ietf-drums)
;; Fixme: Avoid this (used for mail-parse-charset) mm dependence on gnus.
(require 'mail-prsvr)
-(require 'base64)
+(require 'rfc2045) ;; rfc2045-encode-string
(autoload 'mm-body-7-or-8 "mm-bodies")
(defvar rfc2047-header-encoding-alist
'(("Newsgroups" . nil)
("Followup-To" . nil)
("Message-ID" . nil)
- ("\\(Resent-\\)?\\(From\\|Cc\\|To\\|Bcc\\|Reply-To\\|Sender\
+ ("\\(Resent-\\)?\\(From\\|Cc\\|To\\|Bcc\\|\\(In-\\)?Reply-To\\|Sender\
\\|Mail-Followup-To\\|Mail-Copies-To\\|Approved\\)" . address-mime)
(t . mime))
"*Header/encoding method alist.
(iso-2022-jp . B)
(iso-2022-kr . B)
(gb2312 . B)
+ (gbk . B)
+ (gb18030 . B)
(big5 . B)
(cn-big5 . B)
(cn-gb . B)
Valid encodings are nil, `Q' and `B'. These indicate binary (no) encoding,
quoted-printable and base64 respectively.")
-(defvar rfc2047-encoding-function-alist
- '((Q . rfc2047-q-encode-region)
- (B . rfc2047-b-encode-region)
- (nil . ignore))
+(defvar rfc2047-encode-function-alist
+ '((Q . rfc2047-q-encode-string)
+ (B . rfc2047-b-encode-string)
+ (nil . identity))
"Alist of RFC2047 encodings to encoding functions.")
+(defvar rfc2047-encode-encoded-words t
+ "Whether encoded words should be encoded again.")
+
+(defvar rfc2047-allow-irregular-q-encoded-words t
+ "*Whether to decode irregular Q-encoded words.")
+
+(eval-and-compile ;; Necessary to hard code them in `rfc2047-decode-region'.
+ (defconst rfc2047-encoded-word-regexp
+ "=\\?\\([^][\000-\040()<>@,\;:*\\\"/?.=]+\\)\\(?:\\*[^?]+\\)?\\?\
+\\(B\\?[+/0-9A-Za-z]*=*\
+\\|Q\\?[ ->@-~]*\
+\\)\\?="
+ "Regexp that matches encoded word."
+ ;; The patterns for the B encoding and the Q encoding, i.e. the ones
+ ;; beginning with "B" and "Q" respectively, are restricted into only
+ ;; the characters that those encodings may generally use.
+ )
+ (defconst rfc2047-encoded-word-regexp-loose
+ "=\\?\\([^][\000-\040()<>@,\;:*\\\"/?.=]+\\)\\(?:\\*[^?]+\\)?\\?\
+\\(B\\?[+/0-9A-Za-z]*=*\
+\\|Q\\?\\(?:\\?+[ -<>@-~]\\)?\\(?:[ ->@-~]+\\?+[ -<>@-~]\\)*[ ->@-~]*\\?*\
+\\)\\?="
+ "Regexp that matches encoded word allowing loose Q encoding."
+ ;; The pattern for the Q encoding, i.e. the one beginning with "Q",
+ ;; is similar to:
+ ;; "Q\\?\\(\\?+[^\n=?]\\)?\\([^\n?]+\\?+[^\n=?]\\)*[^\n?]*\\?*"
+ ;; <--------1-------><----------2,3----------><--4--><-5->
+ ;; They mean:
+ ;; 1. After "Q?", allow "?"s that follow a character other than "=".
+ ;; 2. Allow "=" after "Q?"; it isn't regarded as the terminator.
+ ;; 3. In the middle of an encoded word, allow "?"s that follow a
+ ;; character other than "=".
+ ;; 4. Allow any characters other than "?" in the middle of an
+ ;; encoded word.
+ ;; 5. At the end, allow "?"s.
+ ))
+
;;;
;;; Functions for encoding RFC2047 messages
;;;
+(defun rfc2047-qp-or-base64 ()
+ "Return the type with which to encode the buffer.
+This is either `base64' or `quoted-printable'."
+ (save-excursion
+ (let ((limit (min (point-max) (+ 2000 (point-min))))
+ (n8bit 0))
+ (goto-char (point-min))
+ (skip-chars-forward "\x20-\x7f\r\n\t" limit)
+ (while (< (point) limit)
+ (incf n8bit)
+ (forward-char 1)
+ (skip-chars-forward "\x20-\x7f\r\n\t" limit))
+ (if (or (< (* 6 n8bit) (- limit (point-min)))
+ ;; Don't base64, say, a short line with a single
+ ;; non-ASCII char when splitting parts by charset.
+ (= n8bit 1))
+ 'quoted-printable
+ 'base64))))
+
(defun rfc2047-narrow-to-field ()
"Narrow the buffer to the header on the current line."
(beginning-of-line)
(save-restriction
(rfc2047-narrow-to-field)
(re-search-forward ":[ \t\n]*" nil t)
- (buffer-substring (point) (point-max)))))
+ (buffer-substring-no-properties (point) (point-max)))))
+
+(defun rfc2047-quote-special-characters-in-quoted-strings (&optional
+ encodable-regexp)
+ "Quote special characters with `\\'s in quoted strings.
+Quoting will not be done in a quoted string if it contains characters
+matching ENCODABLE-REGEXP or it is within parentheses."
+ (goto-char (point-min))
+ (let ((tspecials (concat "[" ietf-drums-tspecials "]"))
+ (start (point))
+ beg end)
+ (with-syntax-table (standard-syntax-table)
+ (while (not (eobp))
+ (if (ignore-errors
+ (forward-list 1)
+ (eq (char-before) ?\)))
+ (forward-list -1)
+ (goto-char (point-max)))
+ (save-restriction
+ (narrow-to-region start (point))
+ (goto-char start)
+ (while (search-forward "\"" nil t)
+ (setq beg (match-beginning 0))
+ (unless (eq (char-before beg) ?\\)
+ (goto-char beg)
+ (setq beg (1+ beg))
+ (condition-case nil
+ (progn
+ (forward-sexp)
+ (setq end (1- (point)))
+ (goto-char beg)
+ (if (and encodable-regexp
+ (re-search-forward encodable-regexp end t))
+ (goto-char (1+ end))
+ (save-restriction
+ (narrow-to-region beg end)
+ (while (re-search-forward tspecials nil 'move)
+ (if (eq (char-before) ?\\)
+ (if (looking-at tspecials) ;; Already quoted.
+ (forward-char)
+ (insert "\\"))
+ (goto-char (match-beginning 0))
+ (insert "\\")
+ (forward-char))))
+ (forward-char)))
+ (error
+ (goto-char beg)))))
+ (goto-char (point-max)))
+ (forward-list 1)
+ (setq start (point))))))
(defvar rfc2047-encoding-type 'address-mime
"The type of encoding done by `rfc2047-encode-region'.
(while (not (eobp))
(save-restriction
(rfc2047-narrow-to-field)
+ (setq method nil
+ alist rfc2047-header-encoding-alist)
+ (while (setq elem (pop alist))
+ (when (or (and (stringp (car elem))
+ (looking-at (car elem)))
+ (eq (car elem) t))
+ (setq alist nil
+ method (cdr elem))))
(if (not (rfc2047-encodable-p))
- (prog1
- (if (and (eq (mm-body-7-or-8) '8bit)
- (mm-multibyte-p)
- (mm-coding-system-p
- (car message-posting-charset)))
- ;; 8 bit must be decoded.
- (mm-encode-coding-region
- (point-min) (point-max)
- (mm-charset-to-coding-system
- (car message-posting-charset))))
+ (prog2
+ (when (eq method 'address-mime)
+ (rfc2047-quote-special-characters-in-quoted-strings))
+ (if (and (eq (mm-body-7-or-8) '8bit)
+ (mm-multibyte-p)
+ (mm-coding-system-p
+ (car message-posting-charset)))
+ ;; 8 bit must be decoded.
+ (mm-encode-coding-region
+ (point-min) (point-max)
+ (mm-charset-to-coding-system
+ (car message-posting-charset))))
;; No encoding necessary, but folding is nice
- (rfc2047-fold-region
- (save-excursion
- (goto-char (point-min))
- (skip-chars-forward "^:")
- (when (looking-at ": ")
- (forward-char 2))
- (point))
- (point-max)))
+ (when nil
+ (rfc2047-fold-region
+ (save-excursion
+ (goto-char (point-min))
+ (skip-chars-forward "^:")
+ (when (looking-at ": ")
+ (forward-char 2))
+ (point))
+ (point-max))))
;; We found something that may perhaps be encoded.
- (setq method nil
- alist rfc2047-header-encoding-alist)
- (while (setq elem (pop alist))
- (when (or (and (stringp (car elem))
- (looking-at (car elem)))
- (eq (car elem) t))
- (setq alist nil
- method (cdr elem))))
- (goto-char (point-min))
(re-search-forward "^[^:]+: *" nil t)
(cond
((eq method 'address-mime)
(rfc2047-encode-region (point) (point-max))))
((eq method 'default)
(if (and (featurep 'mule)
- (if (boundp 'default-enable-multibyte-characters)
- default-enable-multibyte-characters)
+ (if (boundp 'enable-multibyte-characters)
+ (default-value 'enable-multibyte-characters))
mail-parse-charset)
(mm-encode-coding-region (point) (point-max)
mail-parse-charset)))
;; 8-bit names. The group name mail copy just got
;; unconditionally encoded. Previously, it would ask
;; whether to encode, which was quite confusing for the
- ;; user. If the new behaviour is wrong, tell me. I have
+ ;; user. If the new behavior is wrong, tell me. I have
;; left the old code commented out below.
;; -- Per Abrahamsen <abraham@dina.kvl.dk> Date: 2001-10-07.
;; Modified by Dave Love, with the commented-out code changed
;;; (rfc2047-encode-region (point-min) (point-max))
;;; (error "Cannot send unencoded text")))
((mm-coding-system-p method)
- (if (and (featurep 'mule)
- (if (boundp 'default-enable-multibyte-characters)
- default-enable-multibyte-characters))
+ (if (or (and (featurep 'mule)
+ (if (boundp 'enable-multibyte-characters)
+ (default-value 'enable-multibyte-characters)))
+ (featurep 'file-coding))
(mm-encode-coding-region (point) (point-max) method)))
;; Hm.
(t)))
;; Fixme: This, and the require below may not be the Right Thing, but
;; should be safe just before release. -- fx 2001-02-08
-(eval-when-compile (defvar message-posting-charset))
(defun rfc2047-encodable-p ()
"Return non-nil if any characters in current buffer need encoding in headers.
(require 'message) ; for message-posting-charset
(let ((charsets
(mm-find-mime-charset-region (point-min) (point-max))))
- (and charsets
- (not (equal charsets (list (car message-posting-charset)))))))
+ (goto-char (point-min))
+ (or (and rfc2047-encode-encoded-words
+ (prog1
+ (re-search-forward rfc2047-encoded-word-regexp nil t)
+ (goto-char (point-min))))
+ (and charsets
+ (not (equal charsets (list (car message-posting-charset))))))))
;; Use this syntax table when parsing into regions that may need
;; encoding. Double quotes are string delimiters, backslash is
;; (make-char-table 'syntax-table '(2)) only works in Emacs.
(let ((table (make-syntax-table)))
;; The following is done to work for setting all elements of the table
- ;; in Emacs 21 and 22 and XEmacs; it appears to be the cleanest way.
+ ;; in Emacs 21-23 and XEmacs; it appears to be the cleanest way.
;; Play safe and don't assume the form of the word syntax entry --
;; copy it from ?a.
(if (fboundp 'set-char-table-range) ; Emacs
table))))
(modify-syntax-entry ?\\ "\\" table)
(modify-syntax-entry ?\" "\"" table)
- (modify-syntax-entry ?\( "." table)
- (modify-syntax-entry ?\) "." table)
+ (modify-syntax-entry ?\( "(" table)
+ (modify-syntax-entry ?\) ")" table)
(modify-syntax-entry ?\< "." table)
(modify-syntax-entry ?\> "." table)
(modify-syntax-entry ?\[ "." table)
Dynamically bind `rfc2047-encoding-type' to change that."
(save-restriction
(narrow-to-region b e)
- (if (eq 'mime rfc2047-encoding-type)
- ;; Simple case. Treat as single word after any initial ASCII
- ;; part and before any tailing ASCII part. The leading ASCII
- ;; is relevant for instance in Subject headers with `Re:' for
- ;; interoperability with non-MIME clients, and we might as
- ;; well avoid the tail too.
- (progn
- (goto-char (point-min))
- ;; Does it need encoding?
- (skip-chars-forward "\000-\177")
- (unless (eobp)
- (skip-chars-backward "^ \n") ; beginning of space-delimited word
- (rfc2047-encode (point) (progn
- (goto-char e)
- (skip-chars-backward "\000-\177")
- (skip-chars-forward "^ \n")
- ;; end of space-delimited word
- (point)))))
- ;; `address-mime' case -- take care of quoted words, comments.
- (with-syntax-table rfc2047-syntax-table
- (let ((start) ; start of current token
- end ; end of current token
- ;; Whether there's an encoded word before the current
- ;; token, either immediately or separated by space.
- last-encoded)
+ (let ((encodable-regexp (if rfc2047-encode-encoded-words
+ "[^\000-\177]+\\|=\\?"
+ "[^\000-\177]+"))
+ start ; start of current token
+ end begin csyntax
+ ;; Whether there's an encoded word before the current token,
+ ;; either immediately or separated by space.
+ last-encoded
+ (orig-text (buffer-substring-no-properties b e)))
+ (if (eq 'mime rfc2047-encoding-type)
+ ;; Simple case. Continuous words in which all those contain
+ ;; non-ASCII characters are encoded collectively. Encoding
+ ;; ASCII words, including `Re:' used in Subject headers, is
+ ;; avoided for interoperability with non-MIME clients and
+ ;; for making it easy to find keywords.
+ (progn
+ (goto-char (point-min))
+ (while (progn (skip-chars-forward " \t\n")
+ (not (eobp)))
+ (setq start (point))
+ (while (and (looking-at "[ \t\n]*\\([^ \t\n]+\\)")
+ (progn
+ (setq end (match-end 0))
+ (re-search-forward encodable-regexp end t)))
+ (goto-char end))
+ (if (> (point) start)
+ (rfc2047-encode start (point))
+ (goto-char end))))
+ ;; `address-mime' case -- take care of quoted words, comments.
+ (rfc2047-quote-special-characters-in-quoted-strings encodable-regexp)
+ (with-syntax-table rfc2047-syntax-table
(goto-char (point-min))
- (condition-case nil ; in case of unbalanced quotes
+ (condition-case err ; in case of unbalanced quotes
;; Look for rfc2822-style: sequences of atoms, quoted
;; strings, specials, whitespace. (Specials mustn't be
;; encoded.)
(while (not (eobp))
- (setq start (point))
;; Skip whitespace.
- (unless (= 0 (skip-chars-forward " \t\n"))
- (setq start (point)))
+ (skip-chars-forward " \t\n")
+ (setq start (point))
(cond
((not (char-after))) ; eob
;; else token start
- ((eq ?\" (char-syntax (char-after)))
+ ((eq ?\" (setq csyntax (char-syntax (char-after))))
;; Quoted word.
(forward-sexp)
(setq end (point))
;; Does it need encoding?
(goto-char start)
- (skip-chars-forward "\000-\177" end)
- (if (= end (point))
- (setq last-encoded nil)
- ;; It needs encoding. Strip the quotes first,
- ;; since encoded words can't occur in quotes.
- (goto-char end)
- (delete-backward-char 1)
- (goto-char start)
- (delete-char 1)
- (when last-encoded
- ;; There was a preceding quoted word. We need
- ;; to include any separating whitespace in this
- ;; word to avoid it getting lost.
- (skip-chars-backward " \t")
- ;; A space is needed between the encoded words.
- (insert ? )
- (setq start (point)
- end (1+ end)))
- ;; Adjust the end position for the deleted quotes.
- (rfc2047-encode start (- end 2))
- (setq last-encoded t))) ; record that it was encoded
- ((eq ?. (char-syntax (char-after)))
+ (if (re-search-forward encodable-regexp end 'move)
+ ;; It needs encoding. Strip the quotes first,
+ ;; since encoded words can't occur in quotes.
+ (progn
+ (goto-char end)
+ (delete-char -1)
+ (goto-char start)
+ (delete-char 1)
+ (when last-encoded
+ ;; There was a preceding quoted word. We need
+ ;; to include any separating whitespace in this
+ ;; word to avoid it getting lost.
+ (skip-chars-backward " \t")
+ ;; A space is needed between the encoded words.
+ (insert ? )
+ (setq start (point)
+ end (1+ end)))
+ ;; Adjust the end position for the deleted quotes.
+ (rfc2047-encode start (- end 2))
+ (setq last-encoded t)) ; record that it was encoded
+ (setq last-encoded nil)))
+ ((eq ?. csyntax)
;; Skip other delimiters, but record that they've
;; potentially separated quoted words.
(forward-char)
(setq last-encoded nil))
+ ((eq ?\) csyntax)
+ (error "Unbalanced parentheses"))
+ ((eq ?\( csyntax)
+ ;; Look for the end of parentheses.
+ (forward-list)
+ ;; Encode text as an unstructured field.
+ (let ((rfc2047-encoding-type 'mime))
+ (rfc2047-encode-region (1+ start) (1- (point))))
+ (skip-chars-forward ")"))
(t ; normal token/whitespace sequence
;; Find the end.
- (forward-word 1)
- (skip-chars-backward " \t")
+ ;; Skip one ASCII word, or encode continuous words
+ ;; in which all those contain non-ASCII characters.
+ (setq end nil)
+ (while (not (or end (eobp)))
+ (when (looking-at "[\000-\177]+")
+ (setq begin (point)
+ end (match-end 0))
+ (when (progn
+ (while (and (or (re-search-forward
+ "[ \t\n]\\|\\Sw" end 'move)
+ (setq end nil))
+ (eq ?\\ (char-syntax (char-before))))
+ ;; Skip backslash-quoted characters.
+ (forward-char))
+ end)
+ (setq end (match-beginning 0))
+ (if rfc2047-encode-encoded-words
+ (progn
+ (goto-char begin)
+ (when (search-forward "=?" end 'move)
+ (goto-char (match-beginning 0))
+ (setq end nil)))
+ (goto-char end))))
+ ;; Where the value nil of `end' means there may be
+ ;; text to have to be encoded following the point.
+ ;; Otherwise, the point reached to the end of ASCII
+ ;; words separated by whitespace or a special char.
+ (unless end
+ (when (looking-at encodable-regexp)
+ (goto-char (setq begin (match-end 0)))
+ (while (and (looking-at "[ \t\n]+\\([^ \t\n]+\\)")
+ (setq end (match-end 0))
+ (progn
+ (while (re-search-forward
+ encodable-regexp end t))
+ (< begin (point)))
+ (goto-char begin)
+ (or (not (re-search-forward "\\Sw" end t))
+ (progn
+ (goto-char (match-beginning 0))
+ nil)))
+ (goto-char end))
+ (when (looking-at "[^ \t\n]+")
+ (setq end (match-end 0))
+ (if (re-search-forward "\\Sw+" end t)
+ ;; There are special characters better
+ ;; to be encoded so that MTAs may parse
+ ;; them safely.
+ (cond ((= end (point)))
+ ((looking-at (concat "\\sw*\\("
+ encodable-regexp
+ "\\)"))
+ (setq end nil))
+ (t
+ (goto-char (1- (match-end 0)))
+ (unless (= (point) (match-beginning 0))
+ ;; Separate encodable text and
+ ;; delimiter.
+ (insert " "))))
+ (goto-char end)
+ (skip-chars-forward " \t\n")
+ (if (and (looking-at "[^ \t\n]+")
+ (string-match encodable-regexp
+ (match-string 0)))
+ (setq end nil)
+ (goto-char end)))))))
+ (skip-chars-backward " \t\n")
(setq end (point))
- ;; Deal with encoding and leading space as for
- ;; quoted words.
(goto-char start)
- (skip-chars-forward "\000-\177" end)
- (if (= end (point))
- (setq last-encoded nil)
- (when last-encoded
- (goto-char start)
- (skip-chars-backward " \t")
- (insert ? )
- (setq start (point)
- end (1+ end)))
- (rfc2047-encode start end)
- (setq last-encoded t)))))
+ (if (re-search-forward encodable-regexp end 'move)
+ (progn
+ (unless (memq (char-before start) '(nil ?\t ? ))
+ (if (progn
+ (goto-char start)
+ (skip-chars-backward "^ \t\n")
+ (and (looking-at "\\Sw+")
+ (= (match-end 0) start)))
+ ;; Also encode bogus delimiters.
+ (setq start (point))
+ ;; Separate encodable text and delimiter.
+ (goto-char start)
+ (insert " ")
+ (setq start (1+ start)
+ end (1+ end))))
+ (rfc2047-encode start end)
+ (setq last-encoded t))
+ (setq last-encoded nil)))))
(error
- (error "Invalid data for rfc2047 encoding: %s"
- (buffer-substring b e)))))))
- (rfc2047-fold-region b (point))))
+ (if (or debug-on-quit debug-on-error)
+ (signal (car err) (cdr err))
+ (error "Invalid data for rfc2047 encoding: %s"
+ (mm-replace-in-string orig-text "[ \t\n]+" " "))))))))
+ (rfc2047-fold-region b (point))
+ (goto-char (point-max))))
(defun rfc2047-encode-string (string)
"Encode words in STRING.
By default, the string is treated as containing addresses (see
`rfc2047-encoding-type')."
- (with-temp-buffer
+ (mm-with-multibyte-buffer
(insert string)
(rfc2047-encode-region (point-min) (point-max))
(buffer-string)))
+;; From RFC 2047:
+;; 2. Syntax of encoded-words
+;; [...]
+;; While there is no limit to the length of a multiple-line header
+;; field, each line of a header field that contains one or more
+;; 'encoded-word's is limited to 76 characters.
+;;
+;; In `rfc2047-encode-parameter' it is bound to nil, so don't defconst it.
+(defvar rfc2047-encode-max-chars 76
+ "Maximum characters of each header line that contain encoded-words.
+According to RFC 2047, it is 76. If it is nil, encoded-words
+will not be folded. Too small value may cause an error. You
+should not change this value.")
+
+(defun rfc2047-encode-1 (column string cs encoder start crest tail
+ &optional eword)
+ "Subroutine used by `rfc2047-encode'."
+ (cond ((string-equal string "")
+ (or eword ""))
+ ((not rfc2047-encode-max-chars)
+ (concat start
+ (funcall encoder (if cs
+ (mm-encode-coding-string string cs)
+ string))
+ "?="))
+ ((>= column rfc2047-encode-max-chars)
+ (when eword
+ (cond ((string-match "\n[ \t]+\\'" eword)
+ ;; Reomove a superfluous empty line.
+ (setq eword (substring eword 0 (match-beginning 0))))
+ ((string-match "(+\\'" eword)
+ ;; Break the line before the open parenthesis.
+ (setq crest (concat crest (match-string 0 eword))
+ eword (substring eword 0 (match-beginning 0))))))
+ (rfc2047-encode-1 (length crest) string cs encoder start " " tail
+ (concat eword "\n" crest)))
+ (t
+ (let ((index 0)
+ (limit (1- (length string)))
+ (prev "")
+ next len)
+ (while (and prev
+ (<= index limit))
+ (setq next (concat start
+ (funcall encoder
+ (if cs
+ (mm-encode-coding-string
+ (substring string 0 (1+ index))
+ cs)
+ (substring string 0 (1+ index))))
+ "?=")
+ len (+ column (length next)))
+ (if (> len rfc2047-encode-max-chars)
+ (setq next prev
+ prev nil)
+ (if (or (< index limit)
+ (<= (+ len (or (string-match "\n" tail)
+ (length tail)))
+ rfc2047-encode-max-chars))
+ (setq prev next
+ index (1+ index))
+ (if (string-match "\\`)+" tail)
+ ;; Break the line after the close parenthesis.
+ (setq tail (concat (substring tail 0 (match-end 0))
+ "\n "
+ (substring tail (match-end 0)))
+ prev next
+ index (1+ index))
+ (setq next prev
+ prev nil)))))
+ (if (> index limit)
+ (concat eword next tail)
+ (if (= 0 index)
+ (if (and eword
+ (string-match "(+\\'" eword))
+ (setq crest (concat crest (match-string 0 eword))
+ eword (substring eword 0 (match-beginning 0)))
+ (setq eword (concat eword next)))
+ (setq crest " "
+ eword (concat eword next)))
+ (when (string-match "\n[ \t]+\\'" eword)
+ ;; Reomove a superfluous empty line.
+ (setq eword (substring eword 0 (match-beginning 0))))
+ (rfc2047-encode-1 (length crest) (substring string index)
+ cs encoder start " " tail
+ (concat eword "\n" crest)))))))
+
(defun rfc2047-encode (b e)
"Encode the word(s) in the region B to E.
-By default, the region is treated as containing addresses (see
-`rfc2047-encoding-type')."
- (let* ((mime-charset (mm-find-mime-charset-region b e))
- (cs (if (> (length mime-charset) 1)
- ;; Fixme: Instead of this, try to break region into
- ;; parts that can be encoded separately.
- (error "Can't rfc2047-encode `%s'"
- (buffer-substring b e))
- (setq mime-charset (car mime-charset))
- (mm-charset-to-coding-system mime-charset)))
- ;; Fixme: Better, calculate the number of non-ASCII
- ;; characters, at least for 8-bit charsets.
- (encoding (or (cdr (assq mime-charset
+Point moves to the end of the region."
+ (let ((mime-charset (or (mm-find-mime-charset-region b e) (list 'us-ascii)))
+ cs encoding tail crest eword)
+ ;; Use utf-8 as a last resort if determining charset of text fails.
+ (if (memq nil mime-charset)
+ (setq mime-charset (list 'utf-8)))
+ (cond ((> (length mime-charset) 1)
+ (error "Can't rfc2047-encode `%s'"
+ (buffer-substring-no-properties b e)))
+ ((= (length mime-charset) 1)
+ (setq mime-charset (car mime-charset)
+ cs (mm-charset-to-coding-system mime-charset))
+ (unless (and (mm-multibyte-p)
+ (mm-coding-system-p cs))
+ (setq cs nil))
+ (save-restriction
+ (narrow-to-region b e)
+ (setq encoding
+ (or (cdr (assq mime-charset
rfc2047-charset-encoding-alist))
;; For the charsets that don't have a preferred
;; encoding, choose the one that's shorter.
- (save-restriction
- (narrow-to-region b e)
- (if (eq (mm-qp-or-base64) 'base64)
- 'B
- 'Q))))
- (start (concat
- "=?" (downcase (symbol-name mime-charset)) "?"
- (downcase (symbol-name encoding)) "?"))
- (factor (case mime-charset
- ((iso-8859-5 iso-8859-7 iso-8859-8 koi8-r) 1)
- ((big5 gb2312 euc-kr) 2)
- (utf-8 4)
- (t 8)))
- (pre (- b (save-restriction
- (widen)
- (point-at-bol))))
- ;; encoded-words must not be longer than 75 characters,
- ;; including charset, encoding etc. This leaves us with
- ;; 75 - (length start) - 2 - 2 characters. The last 2 is for
- ;; possible base64 padding. In the worst case (iso-2022-*)
- ;; each character expands to 8 bytes which is expanded by a
- ;; factor of 4/3 by base64 encoding.
- (length (floor (- 75 (length start) 4) (* factor (/ 4.0 3.0))))
- ;; Limit line length to 76 characters.
- (length1 (max 1 (floor (- 76 (length start) 4 pre)
- (* factor (/ 4.0 3.0)))))
- (first t))
- (if mime-charset
- (save-restriction
- (narrow-to-region b e)
- (when (eq encoding 'B)
- ;; break into lines before encoding
- (goto-char (point-min))
- (while (not (eobp))
- (if first
- (progn
- (goto-char (min (point-max) (+ length1 (point))))
- (setq first nil))
- (goto-char (min (point-max) (+ length (point)))))
- (unless (eobp)
- (insert ?\n)))
- (setq first t))
- (if (and (mm-multibyte-p)
- (mm-coding-system-p cs))
- (mm-encode-coding-region (point-min) (point-max) cs))
- (funcall (cdr (assq encoding rfc2047-encoding-function-alist))
- (point-min) (point-max))
- (goto-char (point-min))
- (while (not (eobp))
- (unless first
- (insert ? ))
- (setq first nil)
- (insert start)
- (end-of-line)
- (insert "?=")
- (forward-line 1))))))
+ (if (eq (rfc2047-qp-or-base64) 'base64)
+ 'B
+ &nb