X-Git-Url: http://cgit.sxemacs.org/?p=gnus;a=blobdiff_plain;f=lisp%2Fmm-bodies.el;h=06d5208e5e17041fe1104bb718e773841aa47da7;hp=9a7d7b5ee3a694b15f0a1d500b3c44690c96b353;hb=9ff43b22e07294fa5393fdea5c1e90a86edbe717;hpb=8225be557cc7f4a32b57150d409afdc065e45ba5 diff --git a/lisp/mm-bodies.el b/lisp/mm-bodies.el index 9a7d7b5ee..06d5208e5 100644 --- a/lisp/mm-bodies.el +++ b/lisp/mm-bodies.el @@ -1,52 +1,60 @@ ;;; mm-bodies.el --- Functions for decoding MIME things -;; Copyright (C) 1998, 1999, 2000, 2001, 2003 -;; Free Software Foundation, Inc. +;; Copyright (C) 1998-2013 Free Software Foundation, Inc. ;; Author: Lars Magne Ingebrigtsen ;; MORIOKA Tomohiko ;; 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 . ;;; Commentary: ;;; Code: +;; For Emacs <22.2 and XEmacs. (eval-and-compile - (or (fboundp 'base64-decode-region) - (require 'base64))) - -(eval-when-compile - (defvar mm-uu-decode-function) - (defvar mm-uu-binhex-decode-function)) + (unless (fboundp 'declare-function) (defmacro declare-function (&rest r)))) (require 'mm-util) (require 'rfc2047) (require 'mm-encode) -;; 8bit treatment gets any char except: 0x32 - 0x7f, CR, LF, TAB, BEL, +(defvar mm-uu-yenc-decode-function) +(defvar mm-uu-decode-function) +(defvar mm-uu-binhex-decode-function) + +;; 8bit treatment gets any char except: 0x32 - 0x7f, LF, TAB, BEL, ;; BS, vertical TAB, form feed, and ^_ -(defvar mm-7bit-chars "\x20-\x7f\r\n\t\x7\x8\xb\xc\x1f") +;; +;; Note that CR is *not* included, as that would allow a non-paired CR +;; in the body contrary to RFC 2822: +;; +;; - CR and LF MUST only occur together as CRLF; they MUST NOT +;; appear independently in the body. + +(defvar mm-7bit-chars "\x20-\x7f\n\t\x7\x8\xb\xc\x1f") (defcustom mm-body-charset-encoding-alist '((iso-2022-jp . 7bit) (iso-2022-jp-2 . 7bit) ;; We MUST encode UTF-16 because it can contain \0's which is ;; known to break servers. + ;; Note: UTF-16 variants are invalid for text parts [RFC 2781], + ;; so this can't happen :-/. + ;; PPS: Yes, it can happen if the user specifies UTF-16 in the MML + ;; markup. - jh. (utf-16 . base64) (utf-16be . base64) (utf-16le . base64)) @@ -60,12 +68,15 @@ Valid encodings are `7bit', `8bit', `quoted-printable' and `base64'." (const base64)))) :group 'mime) +(autoload 'message-options-get "message") +(declare-function message-options-set "message" (symbol value)) + (defun mm-encode-body (&optional charset) "Encode a body. Should be called narrowed to the body that is to be encoded. -If there is more than one non-ASCII MULE charset, then list of found -MULE charsets are returned. -If CHARSET is non-nil, it is used. +If there is more than one non-ASCII MULE charset in the body, then the +list of MULE charsets found is returned. +If CHARSET is non-nil, it is used as the MIME charset to encode the body. If successful, the MIME charset is returned. If no encoding was done, nil is returned." (if (not (mm-multibyte-p)) @@ -76,17 +87,18 @@ If no encoding was done, nil is returned." (goto-char (point-min)) (if (re-search-forward "[^\x0-\x7f]" nil t) (or mail-parse-charset - (message-options-get 'mm-encody-body-charset) + (message-options-get 'mm-body-charset-encoding-alist) (message-options-set - 'mm-encody-body-charset - (mm-read-charset "Charset used in the article: "))) + 'mm-body-charset-encoding-alist + (mm-read-coding-system "Charset used in the article: "))) ;; The logic in `mml-generate-mime-1' confirms that it's OK ;; to return nil here. nil))) (save-excursion (if charset (progn - (mm-encode-coding-region (point-min) (point-max) charset) + (mm-encode-coding-region (point-min) (point-max) + (mm-charset-to-coding-system charset)) charset) (goto-char (point-min)) (let ((charsets (mm-find-mime-charset-region (point-min) (point-max) @@ -107,7 +119,7 @@ If no encoding was done, nil is returned." )))))) (defun mm-long-lines-p (length) - "Say whether any of the lines in the buffer is longer than LINES." + "Say whether any of the lines in the buffer is longer than LENGTH." (save-excursion (goto-char (point-min)) (end-of-line) @@ -128,8 +140,10 @@ If no encoding was done, nil is returned." (longp (mm-long-lines-p 1000))) (require 'message) (cond - ((and (not mm-use-ultra-safe-encoding) - (not longp) + ((and (not longp) + (not (and mm-use-ultra-safe-encoding + (or (save-excursion (re-search-forward " $" nil t)) + (save-excursion (re-search-forward "^From " nil t))))) (eq bits '7bit)) bits) ((and (not mm-use-ultra-safe-encoding) @@ -150,27 +164,12 @@ If no encoding was done, nil is returned." (defun mm-body-7-or-8 () "Say whether the body is 7bit or 8bit." - (cond - ((not (featurep 'mule)) - (if (save-excursion - (goto-char (point-min)) - (skip-chars-forward mm-7bit-chars) - (eobp)) - '7bit - '8bit)) - (t - ;; Mule version - (if (and (null (delq 'ascii - (mm-find-charset-region (point-min) (point-max)))) - ;;!!!The following is necessary because the function - ;;!!!above seems to return the wrong result under - ;;!!!Emacs 20.3. Sometimes. - (save-excursion - (goto-char (point-min)) - (skip-chars-forward mm-7bit-chars) - (eobp))) - '7bit - '8bit)))) + (if (save-excursion + (goto-char (point-min)) + (skip-chars-forward mm-7bit-chars) + (eobp)) + '7bit + '8bit)) ;;; ;;; Functions for decoding @@ -198,13 +197,11 @@ If TYPE is `text/plain' CRLF->LF translation may occur." (while (re-search-forward "^[\t ]*\r?\n" nil t) (delete-region (match-beginning 0) (match-end 0))) (goto-char (point-max)) - (when (re-search-backward "^[A-Za-z0-9+/]+=*[\t ]*$" nil t) + (when (re-search-backward "^[\t ]*[A-Za-z0-9+/]+=*[\t ]*$" + nil t) (forward-line)) (point)))) - ((memq encoding '(7bit 8bit binary)) - ;; Do nothing. - t) - ((null encoding) + ((memq encoding '(nil 7bit 8bit binary)) ;; Do nothing. t) ((memq encoding '(x-uuencode x-uue)) @@ -228,78 +225,52 @@ If TYPE is `text/plain' CRLF->LF translation may occur." (message "Error while decoding: %s" error) nil)) (when (and + type (memq encoding '(base64 x-uuencode x-uue x-binhex x-yenc)) - (equal type "text/plain")) + (string-match "\\`text/" type)) (goto-char (point-min)) (while (search-forward "\r\n" nil t) (replace-match "\n" t t))))) -(defun mm-decode-body (charset &optional encoding type force) - "Decode the current article that has been encoded with ENCODING. -The characters in CHARSET should then be decoded. If FORCE is non-nil -use the supplied charset unconditionally." - (let ((charset-supplied charset)) - (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 - charset-supplied nil)) - (save-excursion - (when encoding - (mm-decode-content-transfer-encoding encoding type)) - (when (featurep 'mule) - (let ((coding-system (mm-charset-to-coding-system charset))) - (if (and (not coding-system) - (listp mail-parse-ignored-charsets) - (memq 'gnus-unknown mail-parse-ignored-charsets)) - (setq coding-system - (mm-charset-to-coding-system mail-parse-charset))) - (when (and charset coding-system - ;; buffer-file-coding-system - ;;Article buffer is nil coding system - ;;in XEmacs - (mm-multibyte-p) - (or (not (eq coding-system 'ascii)) - (setq coding-system mail-parse-charset)) - (not (eq coding-system 'gnus-decoded))) - (if (or force - ;; If a charset was supplied and `code-pages' - ;; hasn't been loaded, then use the supplied - ;; charset unconditionally. - (and (not (featurep 'code-pages)) - charset-supplied)) - (mm-decode-coding-region (point-min) (point-max) - coding-system) - ;; Otherwise allow Emacs to auto-detect the charset. - ;; Messages in windows-125x are frequently incorrectly - ;; advertised as iso-8859-x -- if `code-pages' has been - ;; loaded and configured, we're able to deal with them - ;; properly. - (mm-decode-coding-region-safely (point-min) (point-max) - coding-system))) - (setq buffer-file-coding-system - (if (boundp 'last-coding-system-used) - (symbol-value 'last-coding-system-used) - coding-system))))))) - -(defun mm-decode-coding-region-safely (start end coding-system) - "Decode region between START and END with CODING-SYSTEM. -If CODING-SYSTEM is not a valid coding system for the text, let Emacs -decide which coding system to use." - (let* ((orig (buffer-substring start end)) - charsets) - (save-restriction - (narrow-to-region start end) - (mm-decode-coding-region (point-min) (point-max) coding-system) - (setq charsets (find-charset-region (point-min) (point-max))) - (when (or (memq 'eight-bit-control charsets) - (memq 'eight-bit-graphic charsets)) - (delete-region (point-min) (point-max)) - (insert orig) - (mm-decode-coding-region (point-min) (point-max) 'undecided))))) +(defun mm-decode-body (charset &optional encoding type) + "Decode the current article that has been encoded with ENCODING to CHARSET. +ENCODING is a MIME content transfer encoding. +CHARSET is the MIME charset with which to decode the data after transfer +decoding. If it is nil, default to `mail-parse-charset'." + (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)) + (save-excursion + (when encoding + (mm-decode-content-transfer-encoding encoding type)) + (when (and (featurep 'mule) ;; Fixme: Wrong test for unibyte session. + (not (eq charset 'gnus-decoded))) + (let ((coding-system (mm-charset-to-coding-system + ;; Allow overwrite using + ;; `mm-charset-override-alist'. + charset nil t))) + (if (and (not coding-system) + (listp mail-parse-ignored-charsets) + (memq 'gnus-unknown mail-parse-ignored-charsets)) + (setq coding-system + (mm-charset-to-coding-system mail-parse-charset))) + (when (and charset coding-system + ;; buffer-file-coding-system + ;;Article buffer is nil coding system + ;;in XEmacs + (mm-multibyte-p) + (or (not (eq coding-system 'ascii)) + (setq coding-system mail-parse-charset))) + (mm-decode-coding-region (point-min) (point-max) + coding-system)) + (setq buffer-file-coding-system + (if (boundp 'last-coding-system-used) + (symbol-value 'last-coding-system-used) + coding-system)))))) (defun mm-decode-string (string charset) "Decode STRING with CHARSET." @@ -312,7 +283,11 @@ decide which coding system to use." (setq charset mail-parse-charset)) (or (when (featurep 'mule) - (let ((coding-system (mm-charset-to-coding-system charset))) + (let ((coding-system (mm-charset-to-coding-system + charset + ;; Allow overwrite using + ;; `mm-charset-override-alist'. + nil t))) (if (and (not coding-system) (listp mail-parse-ignored-charsets) (memq 'gnus-unknown mail-parse-ignored-charsets))