- (mapcar
- 'mm-mime-charset
- (mm-find-charset-region (point-min) (point-max))))
- (cs (list 'us-ascii (car message-posting-charset)))
- found)
- (while charsets
- (unless (memq (pop charsets) cs)
- (setq found t)))
- found))
-
-(defun rfc2047-dissect-region (b e &optional word-chars)
- "Dissect the region between B and E into words."
- (unless word-chars
- ;; Anything except most CTLs, WSP
- (setq word-chars "\010\012\014\041-\177"))
- (let (mail-parse-mule-charset
- words point current
- result word)
- (save-restriction
- (narrow-to-region b e)
- (goto-char (point-min))
- (skip-chars-forward "\000-\177")
- (while (not (eobp))
- (setq point (point))
- (skip-chars-backward word-chars b)
- (unless (eq b (point))
- (push (cons (buffer-substring b (point)) nil) words))
- (setq b (point))
- (goto-char point)
- (setq current (mm-charset-after))
- (forward-char 1)
- (skip-chars-forward word-chars)
- (while (and (not (eobp))
- (eq (mm-charset-after) current))
- (forward-char 1)
- (skip-chars-forward word-chars))
- (unless (eq b (point))
- (push (cons (buffer-substring b (point)) current) words))
- (setq b (point))
- (skip-chars-forward "\000-\177"))
- (unless (eq b (point))
- (push (cons (buffer-substring b (point)) nil) words)))
- ;; merge adjacent words
- (setq word (pop words))
- (while word
- (if (and (cdr word)
- (caar words)
- (not (cdar words))
- (not (string-match "[^ \t]" (caar words))))
- (if (eq (cdr (nth 1 words)) (cdr word))
- (progn
- (setq word (cons (concat
- (car (nth 1 words)) (caar words)
- (car word))
- (cdr word)))
- (pop words)
- (pop words))
- (push (cons (concat (caar words) (car word)) (cdr word))
- result)
- (pop words)
- (setq word (pop words)))
- (push word result)
- (setq word (pop words))))
- result))
-
-(defun rfc2047-encode-region (b e &optional word-chars)
- "Encode all encodable words in region B to E."
- (let ((words (rfc2047-dissect-region b e word-chars)) word)
- (save-restriction
- (narrow-to-region b e)
- (delete-region (point-min) (point-max))
- (while (setq word (pop words))
- (if (not (cdr word))
- (insert (car word))
- (rfc2047-fold-region (gnus-point-at-bol) (point))
- (goto-char (point-max))
- (if (> (- (point) (save-restriction
- (widen)
- (gnus-point-at-bol))) 76)
- (insert "\n "))
- ;; Insert blank between encoded words
- (if (eq (char-before) ?=) (insert " "))
- (rfc2047-encode (point)
- (progn (insert (car word)) (point))
- (cdr word))))
- (rfc2047-fold-region (point-min) (point-max)))))
-
-(defun rfc2047-encode-string (string &optional word-chars)
- "Encode words in STRING."
- (with-temp-buffer
+ (mm-find-mime-charset-region (point-min) (point-max))))
+ (goto-char (point-min))
+ (or (and rfc2047-encode-encoded-words
+ (prog1
+ (search-forward "=?" 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
+;; character quoting, and all other RFC 2822 special characters are
+;; treated as punctuation so we can use forward-sexp/forward-word to
+;; skip to the end of regions appropriately. Nb. ietf-drums does
+;; things differently.
+(defconst rfc2047-syntax-table
+ ;; (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.
+ ;; Play safe and don't assume the form of the word syntax entry --
+ ;; copy it from ?a.
+ (if (fboundp 'set-char-table-range) ; Emacs
+ (funcall (intern "set-char-table-range")
+ table t (aref (standard-syntax-table) ?a))
+ (if (fboundp 'put-char-table)
+ (if (fboundp 'get-char-table) ; warning avoidance
+ (put-char-table t (get-char-table ?a (standard-syntax-table))
+ 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)
+ (modify-syntax-entry ?\; "." table)
+ (modify-syntax-entry ?, "." table)
+ (modify-syntax-entry ?@ "." table)
+ table))
+
+(defun rfc2047-encode-region (b e)
+ "Encode words in region B to E that need encoding.
+By default, the region is treated as containing RFC2822 addresses.
+Dynamically bind `rfc2047-encoding-type' to change that."
+ (save-restriction
+ (narrow-to-region b e)
+ (let ((encodable-regexp (if rfc2047-encode-encoded-words
+ "[^\000-\177]+\\|=\\?"
+ "[^\000-\177]+"))
+ start ; start of current token
+ end begin
+ ;; 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.
+ (with-syntax-table rfc2047-syntax-table
+ (goto-char (point-min))
+ (condition-case nil ; in case of unbalanced quotes
+ ;; Look for rfc2822-style: sequences of atoms, quoted
+ ;; strings, specials, whitespace. (Specials mustn't be
+ ;; encoded.)
+ (while (not (eobp))
+ ;; Skip whitespace.
+ (skip-chars-forward " \t\n")
+ (setq start (point))
+ (cond
+ ((not (char-after))) ; eob
+ ;; else token start
+ ((eq ?\" (char-syntax (char-after)))
+ ;; Quoted word.
+ (forward-sexp)
+ (setq end (point))
+ ;; Does it need encoding?
+ (goto-char start)
+ (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-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
+ (setq last-encoded nil)))
+ ((eq ?. (char-syntax (char-after)))
+ ;; Skip other delimiters, but record that they've
+ ;; potentially separated quoted words.
+ (forward-char)
+ (setq last-encoded nil))
+ ((eq ?\) (char-syntax (char-after)))
+ (error "Unbalanced parentheses"))
+ ((eq ?\( (char-syntax (char-after)))
+ ;; 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)))
+ (forward-char)))
+ (t ; normal token/whitespace sequence
+ ;; Find the end.
+ ;; Skip one ASCII word, or encode continuous words
+ ;; in which all those contain non-ASCII characters.
+ (setq end nil)
+ (while (not end)
+ (when (looking-at "[\000-\177]+")
+ (setq begin (point)
+ end (match-end 0))
+ (if (re-search-forward "[ \t\n]\\|\\Sw" end 'move)
+ (progn
+ (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)))
+ (setq end nil)))
+ (unless end
+ (setq end t)
+ (when (looking-at encodable-regexp)
+ (goto-char (match-end 0))
+ (while (and (looking-at "[ \t\n]+\\([^ \t\n]+\\)")
+ (setq end (match-end 0))
+ (string-match encodable-regexp
+ (match-string 1)))
+ (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 encodable-regexp)
+ (setq end nil))
+ (t
+ (goto-char (1- (match-end 0)))
+ (unless (= (point) (match-beginning 0))
+ (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))
+ (goto-char start)
+ (if (re-search-forward encodable-regexp end 'move)
+ (progn
+ (rfc2047-encode start end)
+ (setq last-encoded t))
+ (setq last-encoded nil)))))
+ (error
+ (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')."
+ (mm-with-multibyte-buffer
projects / elisp / gnus.git- / blobdiff