;;; mm-util.el --- Utility functions for Mule and low level things
;; Copyright (C) 1998, 1999, 2000, 2001, 2002, 2003, 2004,
-;; 2005 Free Software Foundation, Inc.
+;; 2005, 2006, 2007 Free Software Foundation, Inc.
;; Author: Lars Magne Ingebrigtsen <larsi@gnus.org>
;; MORIOKA Tomohiko <morioka@jaist.ac.jp>
;; 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)
+;; the Free Software Foundation; either version 3, or (at your option)
;; any later version.
;; GNU Emacs is distributed in the hope that it will be useful,
(eval-when-compile (require 'cl))
(require 'mail-prsvr)
+(eval-and-compile
+ (if (featurep 'xemacs)
+ (unless (ignore-errors
+ (require 'timer-funcs))
+ (require 'timer))
+ (require 'timer)))
+
(eval-and-compile
(mapcar
(lambda (elem)
(if (fboundp (car elem))
(defalias nfunc (car elem))
(defalias nfunc (cdr elem)))))
- '((decode-coding-string . (lambda (s a) s))
- (encode-coding-string . (lambda (s a) s))
- (encode-coding-region . ignore)
- (coding-system-list . ignore)
- (decode-coding-region . ignore)
+ '((coding-system-list . ignore)
(char-int . identity)
(coding-system-equal . equal)
(annotationp . ignore)
;; (string-to-multibyte s) ~= (decode-coding-string s 'binary)
;; (string-make-multibyte s) ~= (decode-coding-string s locale-coding-system)
(string-as-multibyte . identity)
- (string-to-multibyte
- . (lambda (string)
- "Return a multibyte string with the same individual chars as string."
- (mapconcat
- (lambda (ch) (mm-string-as-multibyte (char-to-string ch)))
- string "")))
(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))))
+ (multibyte-char-to-unibyte . identity)
+ (special-display-p
+ . (lambda (buffer-name)
+ "Returns non-nil if a buffer named BUFFER-NAME gets a special frame."
+ (and special-display-function
+ (or (and (member buffer-name special-display-buffer-names) t)
+ (cdr (assoc buffer-name special-display-buffer-names))
+ (catch 'return
+ (dolist (elem special-display-regexps)
+ (and (stringp elem)
+ (string-match elem buffer-name)
+ (throw 'return t))
+ (and (consp elem)
+ (stringp (car elem))
+ (string-match (car elem) buffer-name)
+ (throw 'return (cdr elem))))))))))))
+
+(eval-and-compile
+ (if (featurep 'xemacs)
+ (if (featurep 'file-coding)
+ ;; Don't modify string if CODING-SYSTEM is nil.
+ (progn
+ (defun mm-decode-coding-string (str coding-system)
+ (if coding-system
+ (decode-coding-string str coding-system)
+ str))
+ (defun mm-encode-coding-string (str coding-system)
+ (if coding-system
+ (encode-coding-string str coding-system)
+ str))
+ (defun mm-decode-coding-region (start end coding-system)
+ (if coding-system
+ (decode-coding-region start end coding-system)))
+ (defun mm-encode-coding-region (start end coding-system)
+ (if coding-system
+ (encode-coding-region start end coding-system))))
+ (defun mm-decode-coding-string (str coding-system) str)
+ (defun mm-encode-coding-string (str coding-system) str)
+ (defalias 'mm-decode-coding-region 'ignore)
+ (defalias 'mm-encode-coding-region 'ignore))
+ (defalias 'mm-decode-coding-string 'decode-coding-string)
+ (defalias 'mm-encode-coding-string 'encode-coding-string)
+ (defalias 'mm-decode-coding-region 'decode-coding-region)
+ (defalias 'mm-encode-coding-region 'encode-coding-region)))
+
+(defalias 'mm-string-to-multibyte
+ (cond
+ ((featurep 'xemacs)
+ 'identity)
+ ((fboundp 'string-to-multibyte)
+ 'string-to-multibyte)
+ (t
+ (lambda (string)
+ "Return a multibyte string with the same individual chars as string."
+ (mapconcat
+ (lambda (ch) (mm-string-as-multibyte (char-to-string ch)))
+ string "")))))
(eval-and-compile
(defalias 'mm-char-or-char-int-p
(if (fboundp 'coding-system-p)
(when (coding-system-p cs)
cs)
- ;; Is this branch ever actually useful?
+ ;; no-MULE XEmacs:
(car (memq cs (mm-get-coding-system-list))))))
(defun mm-codepage-setup (number &optional alias)
(unless (mm-coding-system-p cp)
(codepage-setup number))
(when (and alias
- (mm-coding-system-p alias)
;; Don't add alias if setup of cp failed.
(mm-coding-system-p cp))
(add-to-list 'mm-charset-synonym-alist (cons alias cp)))))
`(
;; Not in XEmacs, but it's not a proper MIME charset anyhow.
,@(unless (mm-coding-system-p 'x-ctext)
- '((x-ctext . ctext)))
- ;; ISO-8859-15 is very similar to ISO-8859-1. But it's _different_!
+ '((x-ctext . ctext)))
+ ;; ISO-8859-15 is very similar to ISO-8859-1. But it's _different_ in 8
+ ;; positions!
,@(unless (mm-coding-system-p 'iso-8859-15)
- '((iso-8859-15 . iso-8859-1)))
+ '((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)
- (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.
- ,@(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)))
+ ,@(when (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))))
+ ;; Windows-31J is Windows Codepage 932.
+ ,@(when (and (not (mm-coding-system-p 'windows-31j))
+ (mm-coding-system-p 'cp932))
+ '((windows-31j . cp932)))
+ ;; ISO8859-1 is ISO-8859-1
+ ,@(when (and (not (mm-coding-system-p 'iso8859-1))
+ (mm-coding-system-p 'iso-8859-1))
+ '((iso8859-1 . iso-8859-1)))
)
- "A mapping from unknown or invalid charset names to the real charset names.")
+ "A mapping from unknown or invalid charset names to the real charset names.
+
+See `mm-codepage-iso-8859-list' and `mm-codepage-ibm-list'.")
+
+(defcustom mm-codepage-iso-8859-list
+ (list 1250 ;; 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
+ ;; (Emacs 21).
+ '(1252 . 1) ;; Windows-1252 is a superset of iso-8859-1 (West
+ ;; Europe). See also `gnus-article-dumbquotes-map'.
+ '(1254 . 9) ;; Windows-1254 is a superset of iso-8859-9 (Turkish).
+ '(1255 . 8));; Windows-1255 is a superset of iso-8859-8 (Hebrew).
+ "A list of Windows codepage numbers and iso-8859 charset numbers.
+
+If an element is a number corresponding to a supported windows
+codepage, appropriate entries to `mm-charset-synonym-alist' are
+added by `mm-setup-codepage-iso-8859'. An element may also be a
+cons cell where the car is a codepage number and the cdr is the
+corresponding number of an iso-8859 charset."
+ :type '(list (set :inline t
+ (const 1250 :tag "Central and East European")
+ (const (1252 . 1) :tag "West European")
+ (const (1254 . 9) :tag "Turkish")
+ (const (1255 . 8) :tag "Hebrew"))
+ (repeat :inline t
+ :tag "Other options"
+ (choice
+ (integer :tag "Windows codepage number")
+ (cons (integer :tag "Windows codepage number")
+ (integer :tag "iso-8859 charset number")))))
+ :version "22.1" ;; Gnus 5.10.9
+ :group 'mime)
+
+(defcustom mm-codepage-ibm-list
+ (list 437 ;; (US etc.)
+ 860 ;; (Portugal)
+ 861 ;; (Iceland)
+ 862 ;; (Israel)
+ 863 ;; (Canadian French)
+ 865 ;; (Nordic)
+ 852 ;;
+ 850 ;; (Latin 1)
+ 855 ;; (Cyrillic)
+ 866 ;; (Cyrillic - Russian)
+ 857 ;; (Turkish)
+ 864 ;; (Arabic)
+ 869 ;; (Greek)
+ 874);; (Thai)
+ ;; In Emacs 23 (unicode), cp... and ibm... are aliases.
+ ;; Cf. http://thread.gmane.org/v9lkng5nwy.fsf@marauder.physik.uni-ulm.de
+ "List of IBM codepage numbers.
+
+The codepage mappings slighly differ between IBM and other vendors.
+See \"ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/IBM/README.TXT\".
+
+If an element is a number corresponding to a supported windows
+codepage, appropriate entries to `mm-charset-synonym-alist' are
+added by `mm-setup-codepage-ibm'."
+ :type '(list (set :inline t
+ (const 437 :tag "US etc.")
+ (const 860 :tag "Portugal")
+ (const 861 :tag "Iceland")
+ (const 862 :tag "Israel")
+ (const 863 :tag "Canadian French")
+ (const 865 :tag "Nordic")
+ (const 852)
+ (const 850 :tag "Latin 1")
+ (const 855 :tag "Cyrillic")
+ (const 866 :tag "Cyrillic - Russian")
+ (const 857 :tag "Turkish")
+ (const 864 :tag "Arabic")
+ (const 869 :tag "Greek")
+ (const 874 :tag "Thai"))
+ (repeat :inline t
+ :tag "Other options"
+ (integer :tag "Codepage number")))
+ :version "22.1" ;; Gnus 5.10.9
+ :group 'mime)
+
+(defun mm-setup-codepage-iso-8859 (&optional list)
+ "Add appropriate entries to `mm-charset-synonym-alist'.
+Unless LIST is given, `mm-codepage-iso-8859-list' is used."
+ (unless list
+ (setq list mm-codepage-iso-8859-list))
+ (dolist (i list)
+ (let (cp windows iso)
+ (if (consp i)
+ (setq cp (intern (format "cp%d" (car i)))
+ windows (intern (format "windows-%d" (car i)))
+ iso (intern (format "iso-8859-%d" (cdr i))))
+ (setq cp (intern (format "cp%d" i))
+ windows (intern (format "windows-%d" i))))
+ (unless (mm-coding-system-p windows)
+ (if (mm-coding-system-p cp)
+ (add-to-list 'mm-charset-synonym-alist (cons windows cp))
+ (add-to-list 'mm-charset-synonym-alist (cons windows iso)))))))
+
+(defun mm-setup-codepage-ibm (&optional list)
+ "Add appropriate entries to `mm-charset-synonym-alist'.
+Unless LIST is given, `mm-codepage-ibm-list' is used."
+ (unless list
+ (setq list mm-codepage-ibm-list))
+ (dolist (number list)
+ (let ((ibm (intern (format "ibm%d" number)))
+ (cp (intern (format "cp%d" number))))
+ (when (and (not (mm-coding-system-p ibm))
+ (mm-coding-system-p cp))
+ (add-to-list 'mm-charset-synonym-alist (cons ibm cp))))))
+
+;; Initialize:
+(mm-setup-codepage-iso-8859)
+(mm-setup-codepage-ibm)
(defcustom mm-charset-override-alist
- `((iso-8859-1 . windows-1252))
+ '((iso-8859-1 . windows-1252)
+ (iso-8859-8 . windows-1255)
+ (iso-8859-9 . windows-1254))
"A mapping from undesired charset names to their replacement.
-You may add pair like (iso-8859-1 . windows-1252) here,
+You may add pairs like (iso-8859-1 . windows-1252) here,
i.e. treat iso-8859-1 as windows-1252. windows-1252 is a
superset of iso-8859-1."
:type '(list (set :inline t
(const (iso-8859-1 . windows-1252))
+ (const (iso-8859-8 . windows-1255))
+ (const (iso-8859-9 . windows-1254))
(const (undecided . windows-1252)))
(repeat :inline t
:tag "Other options"
(cons (symbol :tag "From charset")
(symbol :tag "To charset"))))
- :version "23.0" ;; No Gnus
+ :version "22.1" ;; Gnus 5.10.9
:group 'mime)
(defcustom mm-charset-eval-alist
evaluated. This allows to load additional libraries providing
charsets on demand. If supported by your Emacs version, you
could use `autoload-coding-system' here."
- :version "23.0" ;; No Gnus
+ :version "22.1" ;; Gnus 5.10.9
:type '(list (set :inline t
(const (windows-1250 . (mm-codepage-setup 1250 t)))
(const (windows-1251 . (mm-codepage-setup 1251 t)))
(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)))
- '(utf-8 unicode-a unicode-b unicode-c unicode-d unicode-e)
- ;; If we have utf-8 we're in Mule 5+.
- (append '(utf-8)
- (delete 'ascii
- (coding-system-get 'mule-utf-8 'safe-charsets)))))
+ ,(cond ((fboundp 'unicode-precedence-list)
+ (cons 'utf-8 (delq 'ascii (mapcar 'charset-name
+ (unicode-precedence-list)))))
+ ((or (not (fboundp 'charsetp)) ;; non-Mule case
+ (charsetp 'unicode-a)
+ (not (mm-coding-system-p 'mule-utf-8)))
+ '(utf-8 unicode-a unicode-b unicode-c unicode-d unicode-e))
+ (t ;; If we have utf-8 we're in Mule 5+.
+ (append '(utf-8)
+ (delete 'ascii
+ (coding-system-get 'mule-utf-8 'safe-charsets))))))
"Alist of MIME-charset/MULE-charsets.")
(defun mm-enrich-utf-8-by-mule-ucs ()
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
cs mime mule alist)
(while css
(setq cs (pop css)
- mime (or (coding-system-get cs :mime-charset) ; Emacs 22
+ mime (or (coding-system-get cs :mime-charset) ; Emacs 23 (unicode)
(coding-system-get cs 'mime-charset)))
(when (and mime
(not (eq t (setq mule
(pop alist))
out)))
-(defun mm-charset-to-coding-system (charset &optional lbt)
+(defun mm-charset-to-coding-system (charset &optional lbt
+ allow-override)
"Return coding-system corresponding to CHARSET.
CHARSET is a symbol naming a MIME charset.
If optional argument LBT (`unix', `dos' or `mac') is specified, it is
-used as the line break code type of the coding system."
+used as the line break code type of the coding system.
+
+If ALLOW-OVERRIDE is given, use `mm-charset-override-alist' to
+map undesired charset names to their replacement. This should
+only be used for decoding, not for encoding."
+ ;; OVERRIDE is used (only) in `mm-decode-body' and `mm-decode-string'.
(when (stringp charset)
(setq charset (intern (downcase charset))))
(when lbt
((or (null (mm-get-coding-system-list))
(not (fboundp 'coding-system-get)))
charset)
- ;; Check override list quite early:
- ((let ((cs (cdr (assq charset mm-charset-override-alist))))
- (and cs (mm-coding-system-p cs) cs)))
+ ;; Check override list quite early. Should only used for decoding, not for
+ ;; encoding!
+ ((and allow-override
+ (let ((cs (cdr (assq charset mm-charset-override-alist))))
+ (and cs (mm-coding-system-p cs) cs))))
;; ascii
((eq charset 'us-ascii)
'ascii)
(defmacro mm-with-unibyte-current-buffer (&rest forms)
"Evaluate FORMS with current buffer temporarily made unibyte.
Also bind `default-enable-multibyte-characters' to nil.
-Equivalent to `progn' in XEmacs"
+Equivalent to `progn' in XEmacs
+
+NOTE: Use this macro with caution in multibyte buffers (it is not
+worth using this macro in unibyte buffers of course). Use of
+`(set-buffer-multibyte t)', which is run finally, is generally
+harmful since it is likely to modify existing data in the buffer.
+For instance, it converts \"\\300\\255\" into \"\\255\" in
+Emacs 23 (unicode)."
(let ((multibyte (make-symbol "multibyte"))
(buffer (make-symbol "buffer")))
`(if mm-emacs-mule
- (let ((,multibyte enable-multibyte-characters)
+ (let ((,multibyte enable-multibyte-characters)
(,buffer (current-buffer)))
(unwind-protect
(let (default-enable-multibyte-characters)
(nreverse out)))
(defvar mm-inhibit-file-name-handlers
- '(jka-compr-handler image-file-handler)
+ '(jka-compr-handler image-file-handler epa-file-handler)
"A list of handlers doing (un)compression (etc) thingies.")
(defun mm-insert-file-contents (filename &optional visit beg end replace
inhibit-file-name-handlers)))
(write-region start end filename append visit lockname)))
+;; It is not a MIME function, but some MIME functions use it.
+(if (and (fboundp 'make-temp-file)
+ (ignore-errors
+ (let ((def (symbol-function 'make-temp-file)))
+ (and (byte-code-function-p def)
+ (setq def (if (fboundp 'compiled-function-arglist)
+ ;; XEmacs
+ (eval (list 'compiled-function-arglist def))
+ (aref def 0)))
+ (>= (length def) 4)
+ (eq (nth 3 def) 'suffix)))))
+ (defalias 'mm-make-temp-file 'make-temp-file)
+ ;; Stolen (and modified for XEmacs) from Emacs 22.
+ (defun mm-make-temp-file (prefix &optional dir-flag suffix)
+ "Create a temporary file.
+The returned file name (created by appending some random characters at the end
+of PREFIX, and expanding against `temporary-file-directory' if necessary),
+is guaranteed to point to a newly created empty file.
+You can then use `write-region' to write new data into the file.
+
+If DIR-FLAG is non-nil, create a new empty directory instead of a file.
+
+If SUFFIX is non-nil, add that at the end of the file name."
+ (let ((umask (default-file-modes))
+ file)
+ (unwind-protect
+ (progn
+ ;; Create temp files with strict access rights. It's easy to
+ ;; loosen them later, whereas it's impossible to close the
+ ;; time-window of loose permissions otherwise.
+ (set-default-file-modes 448)
+ (while (condition-case err
+ (progn
+ (setq file
+ (make-temp-name
+ (expand-file-name
+ prefix
+ (if (fboundp 'temp-directory)
+ ;; XEmacs
+ (temp-directory)
+ temporary-file-directory))))
+ (if suffix
+ (setq file (concat file suffix)))
+ (if dir-flag
+ (make-directory file)
+ ;; NOTE: This is unsafe if Emacs 20
+ ;; users and XEmacs users don't use
+ ;; a secure temp directory.
+ (gmm-write-region "" nil file nil 'silent
+ nil 'excl))
+ nil)
+ (file-already-exists t)
+ ;; The XEmacs version of `make-directory' issues
+ ;; `file-error'.
+ (file-error (or (and (featurep 'xemacs)
+ (file-exists-p file))
+ (signal (car err) (cdr err)))))
+ ;; the file was somehow created by someone else between
+ ;; `make-temp-name' and `write-region', let's try again.
+ nil)
+ file)
+ ;; Reset the umask.
+ (set-default-file-modes umask)))))
+
(defun mm-image-load-path (&optional package)
(let (dir result)
(dolist (path load-path (nreverse result))
(coding-system-for-write mm-binary-coding-system)
retval err-msg)
(message "%s" msg)
- (with-temp-buffer
+ (mm-with-unibyte-buffer
(insert-buffer-substring cur)
(condition-case err
(progn