X-Git-Url: https://code.delx.au/gnu-emacs/blobdiff_plain/3b0bf2617c6dc06345152599963c25260b079e8b..4bc30b74c881c4f602722b79123b1b7203218cef:/lisp/gnus/qp.el diff --git a/lisp/gnus/qp.el b/lisp/gnus/qp.el index 6d2c01d41d..d95508123a 100644 --- a/lisp/gnus/qp.el +++ b/lisp/gnus/qp.el @@ -1,6 +1,7 @@ ;;; qp.el --- Quoted-Printable functions -;; Copyright (C) 1998, 1999, 2000 Free Software Foundation, Inc. +;; Copyright (C) 1998, 1999, 2000, 2001, 2002, 2003, 2005 +;; Free Software Foundation, Inc. ;; Author: Lars Magne Ingebrigtsen ;; Keywords: mail, extensions @@ -19,8 +20,8 @@ ;; 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: @@ -29,74 +30,86 @@ ;;; Code: -(defun quoted-printable-decode-region (from to &optional charset) +(require 'mm-util) +(eval-when-compile (defvar mm-use-ultra-safe-encoding)) + +;;;###autoload +(defun quoted-printable-decode-region (from to &optional coding-system) "Decode quoted-printable in the region between FROM and TO, per RFC 2045. -If CHARSET is non-nil, decode bytes into characters with that charset." - (interactive "r") +If CODING-SYSTEM is non-nil, decode bytes into characters with that +coding-system. + +Interactively, you can supply the CODING-SYSTEM argument +with \\[universal-coding-system-argument]. + +The CODING-SYSTEM argument is a historical hangover and is deprecated. +QP encodes raw bytes and should be decoded into raw bytes. Decoding +them into characters should be done separately." + (interactive + ;; Let the user determine the coding system with "C-x RET c". + (list (region-beginning) (region-end) coding-system-for-read)) + (unless (mm-coding-system-p coding-system) ; e.g. `ascii' from Gnus + (setq coding-system nil)) (save-excursion (save-restriction - (let ((nonascii-insert-offset nonascii-insert-offset) - ;; RFC 2045: An "=" followed by two hexadecimal digits, - ;; one or both of which are lowercase letters in "abcdef", - ;; is formally illegal. A robust implementation might - ;; choose to recognize them as the corresponding uppercase - ;; letters. - (case-fold-search t)) - (if charset - (setq nonascii-insert-offset (- (make-char charset) 128))) + ;; RFC 2045: ``An "=" followed by two hexadecimal digits, one + ;; or both of which are lowercase letters in "abcdef", is + ;; formally illegal. A robust implementation might choose to + ;; recognize them as the corresponding uppercase letters.'' + (let ((case-fold-search t)) (narrow-to-region from to) - (goto-char from) - (while (and (skip-chars-forward "^=" to) + ;; Do this in case we're called from Gnus, say, in a buffer + ;; which already contains non-ASCII characters which would + ;; then get doubly-decoded below. + (if coding-system + (mm-encode-coding-region (point-min) (point-max) coding-system)) + (goto-char (point-min)) + (while (and (skip-chars-forward "^=") (not (eobp))) (cond ((eq (char-after (1+ (point))) ?\n) (delete-char 2)) ((looking-at "=[0-9A-F][0-9A-F]") - (let ((byte (string-to-int (buffer-substring (1+ (point)) - (+ 3 (point))) - 16))) - (if (and charset (fboundp 'unibyte-char-to-multibyte)) - (insert (unibyte-char-to-multibyte byte)) - (insert byte)) - (delete-region (point) (+ 3 (point))) - (unless (eq byte ?=) - (backward-char)))) - ((eq (char-after (1+ (point))) ?=) - (forward-char) - (delete-char 1)) + (let ((byte (string-to-number (buffer-substring (1+ (point)) + (+ 3 (point))) + 16))) + (mm-insert-byte byte 1) + (delete-char 3))) (t - (message "Malformed MIME quoted-printable message") - (forward-char)))))))) + (message "Malformed quoted-printable text") + (forward-char))))) + (if coding-system + (mm-decode-coding-region (point-min) (point-max) coding-system))))) -(defun quoted-printable-decode-string (string &optional charset) +(defun quoted-printable-decode-string (string &optional coding-system) "Decode the quoted-printable encoded STRING and return the result. -If CHARSET is non-nil, decode the region with charset." - (with-temp-buffer +If CODING-SYSTEM is non-nil, decode the region with coding-system. +Use of CODING-SYSTEM is deprecated; this function should deal with +raw bytes, and coding conversion should be done separately." + (mm-with-unibyte-buffer (insert string) - (quoted-printable-decode-region (point-min) (point-max) charset) + (quoted-printable-decode-region (point-min) (point-max) coding-system) (buffer-string))) (defun quoted-printable-encode-region (from to &optional fold class) "Quoted-printable encode the region between FROM and TO per RFC 2045. If FOLD, fold long lines at 76 characters (as required by the RFC). -If CLASS is non-nil, translate the characters matched by that class in -the form expected by `skip-chars-forward'. +If CLASS is non-nil, translate the characters not matched by that +regexp class, which is in the form expected by `skip-chars-forward'. +You should probably avoid non-ASCII characters in this arg. If `mm-use-ultra-safe-encoding' is set, fold lines unconditionally and encode lines starting with \"From\"." (interactive "r") - ;; Fixme: what should this do in XEmacs/Mule? - (if (fboundp 'find-charset-region) ; else XEmacs, non-Mule - (if (delq 'unknown ; Emacs 20 unibyte - (delq 'eight-bit-graphic ; Emacs 21 - (delq 'eight-bit-control - (delq 'ascii (find-charset-region from to))))) - (error "Multibyte character in QP encoding region"))) (unless class - (setq class "^\000-\007\013\015-\037\200-\377=")) - (if (fboundp 'string-as-multibyte) - (setq class (string-as-multibyte class))) + ;; Avoid using 8bit characters. = is \075. + ;; Equivalent to "^\000-\007\013\015-\037\200-\377=" + (setq class "\010-\012\014\040-\074\076-\177")) (save-excursion + (goto-char from) + (if (re-search-forward (mm-string-to-multibyte "[^\x0-\x7f\x80-\xff]") + to t) + (error "Multibyte character in QP encoding region")) (save-restriction (narrow-to-region from to) ;; Encode all the non-ascii and control characters. @@ -105,7 +118,8 @@ encode lines starting with \"From\"." (not (eobp))) (insert (prog1 - (format "=%02x" (upcase (char-after))) + ;; To unibyte in case of Emacs 22 eight-bit. + (format "=%02X" (mm-multibyte-char-to-unibyte (char-after))) (delete-char 1)))) ;; Encode white space at the end of lines. (goto-char (point-min)) @@ -114,39 +128,41 @@ encode lines starting with \"From\"." (while (not (eolp)) (insert (prog1 - (format "=%02x" (upcase (char-after))) + (format "=%02X" (char-after)) (delete-char 1))))) (let ((mm-use-ultra-safe-encoding (and (boundp 'mm-use-ultra-safe-encoding) mm-use-ultra-safe-encoding))) (when (or fold mm-use-ultra-safe-encoding) - ;; Fold long lines. (let ((tab-width 1)) ; HTAB is one character. (goto-char (point-min)) (while (not (eobp)) ;; In ultra-safe mode, encode "From " at the beginning ;; of a line. (when mm-use-ultra-safe-encoding - (beginning-of-line) - (when (looking-at "From ") - (replace-match "From=20" nil t))) + (if (looking-at "From ") + (replace-match "From=20" nil t) + (if (looking-at "-") + (replace-match "=2D" nil t)))) (end-of-line) + ;; Fold long lines. (while (> (current-column) 76) ; tab-width must be 1. (beginning-of-line) (forward-char 75) ; 75 chars plus an "=" (search-backward "=" (- (point) 2) t) (insert "=\n") (end-of-line)) - (unless (eobp) - (forward-line))))))))) + (forward-line)))))))) (defun quoted-printable-encode-string (string) "Encode the STRING as quoted-printable and return the result." - (with-temp-buffer - (insert string) - (quoted-printable-encode-region (point-min) (point-max)) - (buffer-string))) + (let ((default-enable-multibyte-characters (mm-multibyte-string-p string))) + (with-temp-buffer + (insert string) + (quoted-printable-encode-region (point-min) (point-max)) + (buffer-string)))) (provide 'qp) +;;; arch-tag: db89e52a-e4a1-4b69-926f-f434f04216ba ;;; qp.el ends here