X-Git-Url: http://git.chise.org/gitweb/?a=blobdiff_plain;f=lisp%2Frfc2047.el;h=559c2a867a171f25b7993c5f9b9b8d9a501ed412;hb=779dd81d09cb6fa76e6a0fd64147099b7cf0119d;hp=07818b831ace8df3371c2ae091d76199302f494b;hpb=8bc1d48e1a38b0ae49d3b9d56f417704aed89e95;p=elisp%2Fgnus.git- diff --git a/lisp/rfc2047.el b/lisp/rfc2047.el index 07818b8..559c2a8 100644 --- a/lisp/rfc2047.el +++ b/lisp/rfc2047.el @@ -1,7 +1,7 @@ ;;; rfc2047.el --- functions for encoding and decoding rfc2047 messages -;; Copyright (C) 1998, 1999, 2000, 2002, 2003, 2004 -;; Free Software Foundation, Inc. +;; Copyright (C) 1998, 1999, 2000, 2002, 2003, 2004, +;; 2005 Free Software Foundation, Inc. ;; Author: Lars Magne Ingebrigtsen ;; MORIOKA Tomohiko @@ -19,8 +19,8 @@ ;; 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. +;; Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, +;; Boston, MA 02110-1301, USA. ;;; Commentary: @@ -35,6 +35,7 @@ (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) @@ -44,7 +45,7 @@ '(("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. @@ -369,8 +370,8 @@ Dynamically bind `rfc2047-encoding-type' to change that." (forward-list) ;; Encode text as an unstructured field. (let ((rfc2047-encoding-type 'mime)) - (rfc2047-encode-region (1+ start) (1- (point))) - (forward-char))) + (rfc2047-encode-region (1+ start) (1- (point)))) + (skip-chars-forward ")")) (t ; normal token/whitespace sequence ;; Find the end. ;; Skip one ASCII word, or encode continuous words @@ -422,7 +423,9 @@ Dynamically bind `rfc2047-encoding-type' to change that." ;; to be encoded so that MTAs may parse ;; them safely. (cond ((= end (point))) - ((looking-at encodable-regexp) + ((looking-at (concat "\\sw*\\(" + encodable-regexp + "\\)")) (setq end nil)) (t (goto-char (1- (match-end 0))) @@ -442,12 +445,20 @@ Dynamically bind `rfc2047-encoding-type' to change that." (goto-char start) (if (re-search-forward encodable-regexp end 'move) (progn - (goto-char start) - (unless (memq (char-before) '(nil ?\t ? )) - ;; Separate encodable text and delimiter. - (insert " ") - (setq end (1+ end))) - (rfc2047-encode (point) end) + (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 @@ -607,7 +618,9 @@ Point moves to the end of the region." (insert eword) (set-marker b nil) (set-marker e nil) - (unless (looking-at "[ \t\n)]") + (unless (or (/= 0 (length tail)) + (eobp) + (looking-at "[ \t\n)]")) (insert " ")))) (t (goto-char e))))) @@ -754,8 +767,7 @@ it, put the following line in your ~/.gnus.el file: (let* ((rfc2047-encoding-type 'mime) (rfc2047-encode-max-chars nil) (string (rfc2047-encode-string value))) - (if (string-match "[][()<>@,;:\\\"/?=]" ;; tspecials - string) + (if (string-match (concat "[" ietf-drums-tspecials "]") string) (format "%s=%S" param string) (concat param "=" string)))) @@ -768,6 +780,88 @@ it, put the following line in your ~/.gnus.el file: "=\\?\\([^][\000-\040()<>@,\;:*\\\"/?.=]+\\)\\(?:\\*[^?]+\\)?\ \\?\\(B\\|Q\\)\\?\\([!->@-~ ]*\\)\\?=")) +(defvar rfc2047-quote-decoded-words-containing-tspecials nil + "If non-nil, quote decoded words containing special characters.") + +(defvar rfc2047-allow-incomplete-encoded-text t + "*Non-nil means allow incomplete encoded-text in successive encoded-words. +Dividing of encoded-text in the place other than character boundaries +violates RFC2047 section 5, while we have a capability to decode it. +If it is non-nil, the decoder will decode B- or Q-encoding in each +encoded-word, concatenate them, and decode it by charset. Otherwise, +the decoder will fully decode each encoded-word before concatenating +them.") + +(defun rfc2047-charset-to-coding-system (charset) + "Return coding-system corresponding to MIME CHARSET. +If your Emacs implementation can't decode CHARSET, return nil." + (when (stringp charset) + (setq charset (intern (downcase charset)))) + (when (or (not charset) + (eq 'gnus-all mail-parse-ignored-charsets) + (memq 'gnus-all mail-parse-ignored-charsets) + (memq charset mail-parse-ignored-charsets)) + (setq charset mail-parse-charset)) + (let ((cs (mm-charset-to-coding-system charset))) + (cond ((eq cs 'ascii) + (setq cs (or (mm-charset-to-coding-system mail-parse-charset) + 'raw-text))) + ((setq cs (mm-coding-system-p cs))) + ((and charset + (listp mail-parse-ignored-charsets) + (memq 'gnus-unknown mail-parse-ignored-charsets)) + (setq cs (mm-charset-to-coding-system mail-parse-charset)))) + (if (eq cs 'ascii) + 'raw-text + cs))) + +(defun rfc2047-decode-encoded-words (words) + "Decode successive encoded-words in WORDS and return a decoded string. +Each element of WORDS looks like (CHARSET ENCODING ENCODED-TEXT +ENCODED-WORD)." + (let (word charset cs encoding text rest) + (while words + (setq word (pop words)) + (if (and (or (setq cs (rfc2047-charset-to-coding-system + (setq charset (car word)))) + (progn + (message "Unknown charset: %s" charset) + nil)) + (condition-case code + (cond ((char-equal ?B (nth 1 word)) + (setq text (base64-decode-string + (rfc2047-pad-base64 (nth 2 word))))) + ((char-equal ?Q (nth 1 word)) + (setq text (quoted-printable-decode-string + (mm-subst-char-in-string + ?_ ? (nth 2 word) t))))) + (error + (message "%s" (error-message-string code)) + nil))) + (if (and rfc2047-allow-incomplete-encoded-text + (eq cs (caar rest))) + ;; Concatenate text of which the charset is the same. + (setcdr (car rest) (concat (cdar rest) text)) + (push (cons cs text) rest)) + ;; Don't decode encoded-word. + (push (cons nil (nth 3 word)) rest))) + (while rest + (setq words (concat + (or (and (setq cs (caar rest)) + (condition-case code + (mm-decode-coding-string (cdar rest) cs) + (error + (message "%s" (error-message-string code)) + nil))) + (concat (when (cdr rest) " ") + (cdar rest) + (when (and words + (not (eq (string-to-char words) ? ))) + " "))) + words) + rest (cdr rest))) + words)) + ;; Fixme: This should decode in place, not cons intermediate strings. ;; Also check whether it needs to worry about delimiting fields like ;; encoding. @@ -782,34 +876,86 @@ it, put the following line in your ~/.gnus.el file: "Decode MIME-encoded words in region between START and END." (interactive "r") (let ((case-fold-search t) - b e) + (eword-regexp (eval-when-compile + ;; Ignore whitespace between encoded-words. + (concat "[\n\t ]*\\(" rfc2047-encoded-word-regexp + "\\)"))) + b e match words) (save-excursion (save-restriction (narrow-to-region start end) - (goto-char (point-min)) - ;; Remove whitespace between encoded words. - (while (re-search-forward - (eval-when-compile - (concat "\\(" rfc2047-encoded-word-regexp "\\)" - "\\(\n?[ \t]\\)+" - "\\(" rfc2047-encoded-word-regexp "\\)")) - nil t) - (delete-region (goto-char (match-end 1)) (match-beginning 6))) - ;; Decode the encoded words. - (setq b (goto-char (point-min))) - (while (re-search-forward rfc2047-encoded-word-regexp nil t) - (setq e (match-beginning 0)) - (insert (rfc2047-parse-and-decode - (prog1 - (match-string 0) - (delete-region (match-beginning 0) (match-end 0))))) - ;; Remove newlines between decoded words, though such things - ;; essentially must not be there. + (goto-char (setq b start)) + ;; Look for the encoded-words. + (while (setq match (re-search-forward eword-regexp nil t)) + (setq e (match-beginning 1) + end (match-end 0) + words nil) + (while match + (push (list (match-string 2) ;; charset + (char-after (match-beginning 3)) ;; encoding + (match-string 4) ;; encoded-text + (match-string 1)) ;; encoded-word + words) + ;; Look for the subsequent encoded-words. + (when (setq match (looking-at eword-regexp)) + (goto-char (setq end (match-end 0))))) + ;; Replace the encoded-words with the decoded one. + (delete-region e end) + (insert (rfc2047-decode-encoded-words (nreverse words))) (save-restriction (narrow-to-region e (point)) (goto-char e) + ;; Remove newlines between decoded words, though such + ;; things essentially must not be there. (while (re-search-forward "[\n\r]+" nil t) (replace-match " ")) + ;; Quote decoded words if there are special characters + ;; which might violate RFC2822. + (when (and rfc2047-quote-decoded-words-containing-tspecials + (let ((regexp (car (rassq + 'address-mime + rfc2047-header-encoding-alist)))) + (when regexp + (save-restriction + (widen) + (beginning-of-line) + (while (and (memq (char-after) '(? ?\t)) + (zerop (forward-line -1)))) + (looking-at regexp))))) + (let (quoted) + (goto-char e) + (skip-chars-forward " \t") + (setq start (point)) + (setq quoted (eq (char-after) ?\")) + (goto-char (point-max)) + (skip-chars-backward " \t") + (if (setq quoted (and quoted + (> (point) (1+ start)) + (eq (char-before) ?\"))) + (progn + (backward-char) + (setq start (1+ start) + end (point-marker))) + (setq end (point-marker))) + (goto-char start) + (while (search-forward "\"" end t) + (when (prog2 + (backward-char) + (zerop (% (skip-chars-backward "\\\\") 2)) + (goto-char (match-beginning 0))) + (insert "\\")) + (forward-char)) + (when (and (not quoted) + (progn + (goto-char start) + (re-search-forward + (concat "[" ietf-drums-tspecials "]") + end t))) + (goto-char start) + (insert "\"") + (goto-char end) + (insert "\"")) + (set-marker end nil))) (goto-char (point-max))) (when (and (mm-multibyte-p) mail-parse-charset @@ -861,21 +1007,6 @@ it, put the following line in your ~/.gnus.el file: (mm-decode-coding-string string mail-parse-charset)) (mm-string-as-multibyte string))))) -(defun rfc2047-parse-and-decode (word) - "Decode WORD and return it if it is an encoded word. -Return WORD if it is not not an encoded word or if the charset isn't -decodable." - (if (not (string-match rfc2047-encoded-word-regexp word)) - word - (or - (condition-case nil - (rfc2047-decode - (match-string 1 word) - (string-to-char (match-string 2 word)) - (match-string 3 word)) - (error word)) - word))) ; un-decodable - (defun rfc2047-pad-base64 (string) "Pad STRING to quartets." ;; Be more liberal to accept buggy base64 strings. If @@ -891,36 +1022,6 @@ decodable." (2 (concat string "==")) (3 (concat string "="))))) -(defun rfc2047-decode (charset encoding string) - "Decode STRING from the given MIME CHARSET in the given ENCODING. -Valid ENCODINGs are the characters \"B\" and \"Q\". -If your Emacs implementation can't decode CHARSET, return nil." - (if (stringp charset) - (setq charset (intern (downcase charset)))) - (if (or (not charset) - (eq 'gnus-all mail-parse-ignored-charsets) - (memq 'gnus-all mail-parse-ignored-charsets) - (memq charset mail-parse-ignored-charsets)) - (setq charset mail-parse-charset)) - (let ((cs (mm-charset-to-coding-system charset))) - (if (and (not cs) charset - (listp mail-parse-ignored-charsets) - (memq 'gnus-unknown mail-parse-ignored-charsets)) - (setq cs (mm-charset-to-coding-system mail-parse-charset))) - (when cs - (when (eq cs 'ascii) - (setq cs (or mail-parse-charset 'raw-text))) - (mm-decode-coding-string - (cond - ((char-equal ?B encoding) - (base64-decode-string - (rfc2047-pad-base64 string))) - ((char-equal ?Q encoding) - (quoted-printable-decode-string - (mm-subst-char-in-string ?_ ? string t))) - (t (error "Invalid encoding: %c" encoding))) - cs)))) - (provide 'rfc2047) ;;; rfc2047.el ends here