X-Git-Url: http://cgit.sxemacs.org/?a=blobdiff_plain;f=lisp%2Fqp.el;h=149d30ab09183c8714eb00a804df2c3bf7eff755;hb=824e6d2628472a538da898196185889a9c84b2d3;hp=4dccdcf9ae7d9509d38d72689bb4bc29b7adf7db;hpb=59140ecfd09c5ca7f49b75972671443b84f62503;p=gnus diff --git a/lisp/qp.el b/lisp/qp.el index 4dccdcf9a..149d30ab0 100644 --- a/lisp/qp.el +++ b/lisp/qp.el @@ -1,7 +1,10 @@ ;;; qp.el --- Quoted-Printable functions -;; Copyright (C) 1998, 1999, 2000 Free Software Foundation, Inc. + +;; Copyright (C) 1998, 1999, 2000, 2001, 2002, 2003 Free Software Foundation, Inc. ;; Author: Lars Magne Ingebrigtsen +;; Keywords: mail, extensions + ;; This file is part of GNU Emacs. ;; GNU Emacs is free software; you can redistribute it and/or modify @@ -21,131 +24,146 @@ ;;; Commentary: +;; Functions for encoding and decoding quoted-printable text as +;; defined in RFC 2045. + ;;; Code: (require 'mm-util) - -(defvar quoted-printable-encoding-characters - (mapcar 'identity "0123456789ABCDEFabcdef")) - -(defun quoted-printable-decode-region (from to &optional charset) - "Decode quoted-printable in the region between FROM and TO. -If CHARSET is non-nil, decode the region with charset." - (interactive "r") +(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 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 (start) + ;; 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 (not (eobp)) - (cond - ((eq (char-after) ?=) - (delete-char 1) - (unless start - (setq start (point))) - (cond - ;; End of the line. - ((eq (char-after) ?\n) - (delete-char 1)) - ;; Encoded character. - ((and - (memq (char-after) quoted-printable-encoding-characters) - (memq (char-after (1+ (point))) - quoted-printable-encoding-characters)) - (insert - (string-to-number - (buffer-substring (point) (+ 2 (point))) - 16)) - (delete-char 2)) - ;; Quoted equal sign. - ((eq (char-after) ?=) - (forward-char 1)) - ;; End of buffer. - ((eobp)) - ;; Invalid. - (t - (message "Malformed MIME quoted-printable message")))) - ((and charset start (not (eq (mm-charset-after) 'ascii))) - (mm-decode-coding-region start (point) charset) - (setq start nil) - (forward-char 1)) - (t - (forward-char 1)))) - (if (and charset start) - (mm-decode-coding-region start (point) charset)))))) - -(defun quoted-printable-decode-string (string &optional charset) - "Decode the quoted-printable-encoded STRING and return the results. -If CHARSET is non-nil, decode the region with charset." + ;; 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))) + (mm-insert-byte byte 1) + (delete-char 3))) + (t + (error "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 coding-system) + "Decode the quoted-printable encoded STRING and return the result. +If CODING-SYSTEM is non-nil, decode the region with coding-system." (with-temp-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) - "QP-encode the region between FROM and TO. + "Quoted-printable encode the region between FROM and TO per RFC 2045. -If FOLD fold long lines. If CLASS, translate the characters -matched by that regexp. +If FOLD, fold long lines at 76 characters (as required by the RFC). +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 unconditionally and +If `mm-use-ultra-safe-encoding' is set, fold lines unconditionally and encode lines starting with \"From\"." (interactive "r") + (save-excursion + (goto-char from) + (if (fboundp 'string-to-multibyte) ; Emacs 22 + (if (re-search-forward (string-to-multibyte "[^\x0-\x7f\x80-\xff]") + to t) + ;; Fixme: This is somewhat misleading. + (error "Multibyte character in QP encoding region")) + (if (re-search-forward (mm-string-as-multibyte "[^\0-\377]") to t) + (error "Multibyte character in QP encoding region")))) + (unless 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 (save-restriction (narrow-to-region from to) - (mm-with-unibyte-current-buffer-mule4 - ;; (mm-encode-body) - ;; Encode all the non-ascii and control characters. - (goto-char (point-min)) - (while (and (skip-chars-forward - ;; Avoid using 8bit characters. = is \075. - ;; Equivalent to "^\000-\007\013\015-\037\200-\377=" - (or class "\010-\012\014\040-\074\076-\177")) - (not (eobp))) + ;; Encode all the non-ascii and control characters. + (goto-char (point-min)) + (while (and (skip-chars-forward class) + (not (eobp))) + (insert + (prog1 + ;; 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)) + (while (re-search-forward "[ \t]+$" nil t) + (goto-char (match-beginning 0)) + (while (not (eolp)) (insert (prog1 - (upcase (format "=%02x" (char-after))) - (delete-char 1)))) - ;; Encode white space at the end of lines. - (goto-char (point-min)) - (while (re-search-forward "[ \t]+$" nil t) - (goto-char (match-beginning 0)) - (while (not (eolp)) - (insert - (prog1 - (upcase (format "=%02x" (char-after))) - (delete-char 1))))) + (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. + (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. + ;; In ultra-safe mode, encode "From " at the beginning + ;; of a line. (when mm-use-ultra-safe-encoding - (beginning-of-line) (if (looking-at "From ") (replace-match "From=20" nil t) (if (looking-at "-") (replace-match "=2D" nil t)))) (end-of-line) - (while (> (current-column) 76);; tab-width must be 1. + ;; Fold long lines. + (while (> (current-column) 76) ; tab-width must be 1. (beginning-of-line) - (forward-char 75);; 75 chars plus an "=" + (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) - "QP-encode STRING and return the results." - (mm-with-unibyte-buffer - (insert string) - (quoted-printable-encode-region (point-min) (point-max)) - (buffer-string))) + "Encode the STRING as quoted-printable and return the result." + (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) -;; qp.el ends here +;;; qp.el ends here