;;; mm-util.el --- Utility functions for Mule and low level things
-;; Copyright (C) 1998, 1999, 2000, 2001 Free Software Foundation, Inc.
+;; Copyright (C) 1998, 1999, 2000, 2001, 2002, 2003, 2004
+;; Free Software Foundation, Inc.
;; Author: Lars Magne Ingebrigtsen <larsi@gnus.org>
;; MORIOKA Tomohiko <morioka@jaist.ac.jp>
(coding-system-list . ignore)
(decode-coding-region . ignore)
(char-int . identity)
- (device-type . ignore)
(coding-system-equal . equal)
(annotationp . ignore)
(set-buffer-file-coding-system . ignore)
- (make-char
- . (lambda (charset int)
- (int-to-char int)))
(read-charset
. (lambda (prompt)
"Return a charset."
mm-mime-mule-charset-alist)
nil t))))
(subst-char-in-string
- . (lambda (from to string) ;; stolen (and renamed) from nnheader.el
- "Replace characters in STRING from FROM to TO."
- (let ((string (substring string 0)) ;Copy string.
+ . (lambda (from to string &optional inplace) ;; stolen (and renamed) from nnheader.el
+ "Replace characters in STRING from FROM to TO.
+ Unless optional argument INPLACE is non-nil, return a new string."
+ (let ((string (if inplace string (copy-sequence string)))
(len (length string))
(idx 0))
;; Replace all occurrences of FROM with TO.
(aset string idx to))
(setq idx (1+ idx)))
string)))
+ (replace-in-string
+ . (lambda (string regexp rep &optional literal)
+ "See `replace-regexp-in-string', only the order of args differs."
+ (replace-regexp-in-string regexp rep string nil literal)))
(string-as-unibyte . identity)
+ (string-make-unibyte . identity)
(string-as-multibyte . identity)
- (multibyte-string-p . ignore))))
+ (multibyte-string-p . ignore)
+ ;; It is not a MIME function, but some MIME functions use it.
+ (make-temp-file . (lambda (prefix &optional dir-flag)
+ (let ((file (expand-file-name
+ (make-temp-name prefix)
+ (if (fboundp 'temp-directory)
+ (temp-directory)
+ temporary-file-directory))))
+ (if dir-flag
+ (make-directory file))
+ file)))
+ (insert-byte . insert-char)
+ (multibyte-char-to-unibyte . identity))))
(eval-and-compile
(defalias 'mm-char-or-char-int-p
((fboundp 'char-valid-p) 'char-valid-p)
(t 'identity))))
+;; Fixme: This seems always to be used to read a MIME charset, so it
+;; should be re-named and fixed (in Emacs) to offer completion only on
+;; proper charset names (base coding systems which have a
+;; mime-charset defined). XEmacs doesn't believe in mime-charset;
+;; test with
+;; `(or (coding-system-get 'iso-8859-1 'mime-charset)
+;; (coding-system-get 'iso-8859-1 :mime-charset))'
+;; Actually, there should be an `mm-coding-system-mime-charset'.
(eval-and-compile
(defalias 'mm-read-coding-system
(cond
(or mm-coding-system-list
(setq mm-coding-system-list (mm-coding-system-list))))
-(defun mm-coding-system-p (sym)
- "Return non-nil if SYM is a coding system."
- (or (and (fboundp 'coding-system-p) (coding-system-p sym))
- (memq sym (mm-get-coding-system-list))))
+(defun mm-coding-system-p (cs)
+ "Return non-nil if CS is a symbol naming a coding system.
+In XEmacs, also return non-nil if CS is a coding system object.
+If CS is available, return CS itself in Emacs, and return a coding
+system object in XEmacs."
+ (if (fboundp 'find-coding-system)
+ (find-coding-system cs)
+ (if (fboundp 'coding-system-p)
+ (when (coding-system-p cs)
+ cs)
+ ;; Is this branch ever actually useful?
+ (car (memq cs (mm-get-coding-system-list))))))
(defvar mm-charset-synonym-alist
`(
- ;; Perfectly fine? A valid MIME name, anyhow.
- ,(unless (mm-coding-system-p 'big5)
- '(big5 . cn-big5))
;; Not in XEmacs, but it's not a proper MIME charset anyhow.
- ,(unless (mm-coding-system-p 'x-ctext)
- '(x-ctext . ctext))
- ;; Apparently not defined in Emacs 20, but is a valid MIME name.
- ,(unless (mm-coding-system-p 'gb2312)
- '(gb2312 . cn-gb-2312))
+ ,@(unless (mm-coding-system-p 'x-ctext)
+ '((x-ctext . ctext)))
+ ;; ISO-8859-15 is very similar to ISO-8859-1. But it's _different_!
+ ,@(unless (mm-coding-system-p 'iso-8859-15)
+ '((iso-8859-15 . iso-8859-1)))
+ ;; BIG-5HKSCS is similar to, but different than, BIG-5.
+ ,@(unless (mm-coding-system-p 'big5-hkscs)
+ '((big5-hkscs . big5)))
;; Windows-1252 is actually a superset of Latin-1. See also
;; `gnus-article-dumbquotes-map'.
- ;;,(unless (mm-coding-system-p 'windows-1252)
- ; should be defined eventually
- ;; '(windows-1252 . iso-8859-1))
- ;; ISO-8859-15 is very similar to ISO-8859-1.
- ;;,(unless (mm-coding-system-p 'iso-8859-15) ; Emacs 21 defines it.
- ;; '(iso-8859-15 . iso-8859-1))
+ ,@(unless (mm-coding-system-p 'windows-1252)
+ (if (mm-coding-system-p 'cp1252)
+ '((windows-1252 . cp1252))
+ '((windows-1252 . iso-8859-1))))
;; Windows-1250 is a variant of Latin-2 heavily used by Microsoft
;; Outlook users in Czech republic. Use this to allow reading of their
;; e-mails. cp1250 should be defined by M-x codepage-setup.
- ;;,(unless (mm-coding-system-p 'windows-1250)
- ; should be defined eventually
- ;; '(windows-1250 . cp1250))
+ ,@(if (and (not (mm-coding-system-p 'windows-1250))
+ (mm-coding-system-p 'cp1250))
+ '((windows-1250 . cp1250)))
+ ;; A Microsoft misunderstanding.
+ ,@(if (and (not (mm-coding-system-p 'unicode))
+ (mm-coding-system-p 'utf-16-le))
+ '((unicode . utf-16-le)))
+ ;; A Microsoft misunderstanding.
+ ,@(unless (mm-coding-system-p 'ks_c_5601-1987)
+ (if (mm-coding-system-p 'cp949)
+ '((ks_c_5601-1987 . cp949))
+ '((ks_c_5601-1987 . euc-kr))))
)
"A mapping from invalid charset names to the real charset names.")
(defvar mm-auto-save-coding-system
(cond
+ ((mm-coding-system-p 'utf-8-emacs) ; Mule 7
+ (if (memq system-type '(windows-nt ms-dos ms-windows))
+ (if (mm-coding-system-p 'utf-8-emacs-dos)
+ 'utf-8-emacs-dos mm-binary-coding-system)
+ 'utf-8-emacs))
((mm-coding-system-p 'emacs-mule)
(if (memq system-type '(windows-nt ms-dos ms-windows))
(if (mm-coding-system-p 'emacs-mule-dos)
"Coding system of auto save file.")
(defvar mm-universal-coding-system mm-auto-save-coding-system
- "The universal Coding system.")
+ "The universal coding system.")
;; Fixme: some of the cars here aren't valid MIME charsets. That
;; should only matter with XEmacs, though.
(big5 chinese-big5-1 chinese-big5-2)
(tibetan tibetan)
(thai-tis620 thai-tis620)
+ (windows-1251 cyrillic-iso8859-5)
(iso-2022-7bit ethiopic arabic-1-column arabic-2-column)
(iso-2022-jp-2 latin-iso8859-1 greek-iso8859-7
latin-jisx0201 japanese-jisx0208-1978
chinese-gb2312 japanese-jisx0208
- korean-ksc5601 japanese-jisx0212
- katakana-jisx0201)
+ korean-ksc5601 japanese-jisx0212)
(iso-2022-int-1 latin-iso8859-1 greek-iso8859-7
latin-jisx0201 japanese-jisx0208-1978
chinese-gb2312 japanese-jisx0208
chinese-cns11643-3 chinese-cns11643-4
chinese-cns11643-5 chinese-cns11643-6
chinese-cns11643-7)
+ (iso-2022-jp-3 latin-jisx0201 japanese-jisx0208-1978 japanese-jisx0208
+ japanese-jisx0213-1 japanese-jisx0213-2)
+ (shift_jis latin-jisx0201 katakana-jisx0201 japanese-jisx0208)
,(if (or (not (fboundp 'charsetp)) ;; non-Mule case
(charsetp 'unicode-a)
(not (mm-coding-system-p 'mule-utf-8)))
(coding-system-get 'mule-utf-8 'safe-charsets)))))
"Alist of MIME-charset/MULE-charsets.")
-;; Correct by construction, but should be unnecessary:
-;; XEmacs hates it.
-(when (and (not (featurep 'xemacs))
- (fboundp 'coding-system-list)
- (fboundp 'sort-coding-systems))
- (setq mm-mime-mule-charset-alist
- (apply
- 'nconc
- (mapcar
- (lambda (cs)
- (when (and (coding-system-get cs 'mime-charset)
- (not (eq t (coding-system-get cs 'safe-charsets))))
- (list (cons (coding-system-get cs 'mime-charset)
- (delq 'ascii
- (coding-system-get cs 'safe-charsets))))))
- (sort-coding-systems (coding-system-list 'base-only))))))
+(defun mm-enrich-utf-8-by-mule-ucs ()
+ "Make the `utf-8' MIME charset usable by the Mule-UCS package.
+This function will run when the `un-define' module is loaded under
+XEmacs, and fill the `utf-8' entry in `mm-mime-mule-charset-alist'
+with Mule charsets. It is completely useless for Emacs."
+ (unless (cdr (delete '(mm-enrich-utf-8-by-mule-ucs)
+ (assoc "un-define" after-load-alist)))
+ (setq after-load-alist
+ (delete '("un-define") after-load-alist)))
+ (when (boundp 'unicode-basic-translation-charset-order-list)
+ (condition-case nil
+ (let ((val (delq
+ 'ascii
+ (copy-sequence
+ (symbol-value
+ 'unicode-basic-translation-charset-order-list))))
+ (elem (assq 'utf-8 mm-mime-mule-charset-alist)))
+ (if elem
+ (setcdr elem val)
+ (setq mm-mime-mule-charset-alist
+ (nconc mm-mime-mule-charset-alist
+ (list (cons 'utf-8 val))))))
+ (error))))
+
+;; Correct by construction, but should be unnecessary for Emacs:
+(if (featurep 'xemacs)
+ (eval-after-load "un-define" '(mm-enrich-utf-8-by-mule-ucs))
+ (when (and (fboundp 'coding-system-list)
+ (fboundp 'sort-coding-systems))
+ (let ((css (sort-coding-systems (coding-system-list 'base-only)))
+ cs mime mule alist)
+ (while css
+ (setq cs (pop css)
+ mime (or (coding-system-get cs :mime-charset) ; Emacs 22
+ (coding-system-get cs 'mime-charset)))
+ (when (and mime
+ (not (eq t (setq mule
+ (coding-system-get cs 'safe-charsets))))
+ (not (assq mime alist)))
+ (push (cons mime (delq 'ascii mule)) alist)))
+ (setq mm-mime-mule-charset-alist (nreverse alist)))))
+
+(defvar mm-hack-charsets '(iso-8859-15 iso-2022-jp-2)
+ "A list of special charsets.
+Valid elements include:
+`iso-8859-15' convert ISO-8859-1, -9 to ISO-8859-15 if ISO-8859-15 exists.
+`iso-2022-jp-2' convert ISO-2022-jp to ISO-2022-jp-2 if ISO-2022-jp-2 exists."
+)
+
+(defvar mm-iso-8859-15-compatible
+ '((iso-8859-1 "\xA4\xA6\xA8\xB4\xB8\xBC\xBD\xBE")
+ (iso-8859-9 "\xA4\xA6\xA8\xB4\xB8\xBC\xBD\xBE\xD0\xDD\xDE\xF0\xFD\xFE"))
+ "ISO-8859-15 exchangeable coding systems and inconvertible characters.")
+
+(defvar mm-iso-8859-x-to-15-table
+ (and (fboundp 'coding-system-p)
+ (mm-coding-system-p 'iso-8859-15)
+ (mapcar
+ (lambda (cs)
+ (if (mm-coding-system-p (car cs))
+ (let ((c (string-to-char
+ (decode-coding-string "\341" (car cs)))))
+ (cons (char-charset c)
+ (cons
+ (- (string-to-char
+ (decode-coding-string "\341" 'iso-8859-15)) c)
+ (string-to-list (decode-coding-string (car (cdr cs))
+ (car cs))))))
+ '(gnus-charset 0)))
+ mm-iso-8859-15-compatible))
+ "A table of the difference character between ISO-8859-X and ISO-8859-15.")
+
+(defcustom mm-coding-system-priorities
+ (if (boundp 'current-language-environment)
+ (let ((lang (symbol-value 'current-language-environment)))
+ (cond ((string= lang "Japanese")
+ ;; Japanese users prefer iso-2022-jp to euc-japan or
+ ;; shift_jis, however iso-8859-1 should be used when
+ ;; there are only ASCII text and Latin-1 characters.
+ '(iso-8859-1 iso-2022-jp iso-2022-jp-2 shift_jis utf-8)))))
+ "Preferred coding systems for encoding outgoing messages.
+
+More than one suitable coding system may be found for some text.
+By default, the coding system with the highest priority is used
+to encode outgoing messages (see `sort-coding-systems'). If this
+variable is set, it overrides the default priority."
+ :version "21.2"
+ :type '(repeat (symbol :tag "Coding system"))
+ :group 'mime)
+
+;; ??
+(defvar mm-use-find-coding-systems-region
+ (fboundp 'find-coding-systems-region)
+ "Use `find-coding-systems-region' to find proper coding systems.
+
+Setting it to nil is useful on Emacsen supporting Unicode if sending
+mail with multiple parts is preferred to sending a Unicode one.")
;;; Internal variables:
(defun mm-mule-charset-to-mime-charset (charset)
"Return the MIME charset corresponding to the given Mule CHARSET."
- (if (fboundp 'find-coding-systems-for-charsets)
- (let (mime)
- (dolist (cs (find-coding-systems-for-charsets (list charset)))
- (unless mime
- (when cs
- (setq mime (coding-system-get cs 'mime-charset)))))
+ (if (and (fboundp 'find-coding-systems-for-charsets)
+ (fboundp 'sort-coding-systems))
+ (let ((css (sort (sort-coding-systems
+ (find-coding-systems-for-charsets (list charset)))
+ &nb