;;; mm-util.el --- Utility functions for Mule and low level things
-;; Copyright (C) 1998, 1999, 2000, 2001, 2002, 2003, 2004,
-;; 2005, 2006, 2007, 2008 Free Software Foundation, Inc.
+;; Copyright (C) 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006,
+;; 2007, 2008, 2009 Free Software Foundation, Inc.
;; Author: Lars Magne Ingebrigtsen <larsi@gnus.org>
;; MORIOKA Tomohiko <morioka@jaist.ac.jp>
(defvar mm-mime-mule-charset-alist )
+;; Emulate functions that are not available in every (X)Emacs version.
+;; The name of a function is prefixed with mm-, like `mm-char-int' for
+;; `char-int' that is a native XEmacs function, not available in Emacs.
+;; Gnus programs all should use mm- functions, not the original ones.
(eval-and-compile
(mapc
(lambda (elem)
(if (fboundp (car elem))
(defalias nfunc (car elem))
(defalias nfunc (cdr elem)))))
- '((coding-system-list . ignore)
+ `(;; `coding-system-list' is not available in XEmacs 21.4 built
+ ;; without the `file-coding' feature.
+ (coding-system-list . ignore)
+ ;; `char-int' is an XEmacs function, not available in Emacs.
(char-int . identity)
+ ;; `coding-system-equal' is an Emacs function, not available in XEmacs.
(coding-system-equal . equal)
+ ;; `annotationp' is an XEmacs function, not available in Emacs.
(annotationp . ignore)
+ ;; `set-buffer-file-coding-system' is not available in XEmacs 21.4
+ ;; built without the `file-coding' feature.
(set-buffer-file-coding-system . ignore)
+ ;; `read-charset' is an Emacs function, not available in XEmacs.
(read-charset
- . (lambda (prompt)
- "Return a charset."
- (intern
- (completing-read
- prompt
- (mapcar (lambda (e) (list (symbol-name (car e))))
- mm-mime-mule-charset-alist)
- nil t))))
+ . ,(lambda (prompt)
+ "Return a charset."
+ (intern
+ (completing-read
+ prompt
+ (mapcar (lambda (e) (list (symbol-name (car e))))
+ mm-mime-mule-charset-alist)
+ nil t))))
+ ;; `subst-char-in-string' is not available in XEmacs 21.4.
(subst-char-in-string
- . (lambda (from to string &optional inplace)
- ;; stolen (and renamed) from nnheader.el
- "Replace characters in STRING from FROM to TO.
+ . ,(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.
- (while (< idx len)
- (when (= (aref string idx) from)
- (aset string idx to))
- (setq idx (1+ idx)))
- string)))
+ (let ((string (if inplace string (copy-sequence string)))
+ (len (length string))
+ (idx 0))
+ ;; Replace all occurrences of FROM with TO.
+ (while (< idx len)
+ (when (= (aref string idx) from)
+ (aset string idx to))
+ (setq idx (1+ idx)))
+ string)))
+ ;; `replace-in-string' is an XEmacs function, not available in Emacs.
(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)))
+ . ,(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' is an Emacs function, not available in XEmacs.
(string-as-unibyte . identity)
+ ;; `string-make-unibyte' is an Emacs function, not available in XEmacs.
(string-make-unibyte . identity)
;; string-as-multibyte often doesn't really do what you think it does.
;; Example:
;; (string-as-multibyte s) ~= (decode-coding-string s 'emacs-mule)
;; (string-to-multibyte s) ~= (decode-coding-string s 'binary)
;; (string-make-multibyte s) ~= (decode-coding-string s locale-coding-system)
+ ;; `string-as-multibyte' is an Emacs function, not available in XEmacs.
(string-as-multibyte . identity)
+ ;; `multibyte-string-p' is an Emacs function, not available in XEmacs.
(multibyte-string-p . ignore)
+ ;; `insert-byte' is available only in Emacs 23.1 or greater.
(insert-byte . insert-char)
+ ;; `multibyte-char-to-unibyte' is an Emacs function, not available
+ ;; in XEmacs.
(multibyte-char-to-unibyte . identity)
+ ;; `set-buffer-multibyte' is an Emacs function, not available in XEmacs.
(set-buffer-multibyte . ignore)
+ ;; `special-display-p' is an Emacs function, not available in XEmacs.
(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))))))))))))
-
+ . ,(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)))))))))
+ ;; `substring-no-properties' is available only in Emacs 22.1 or greater.
+ (substring-no-properties
+ . ,(lambda (string &optional from to)
+ "Return a substring of STRING, without text properties.
+It starts at index FROM and ending before TO.
+TO may be nil or omitted; then the substring runs to the end of STRING.
+If FROM is nil or omitted, the substring starts at the beginning of STRING.
+If FROM or TO is negative, it counts from the end.
+
+With one argument, just copy STRING without its properties."
+ (setq string (substring string (or from 0) to))
+ (set-text-properties 0 (length string) nil string)
+ string))
+ ;; `line-number-at-pos' is available only in Emacs 22.1 or greater
+ ;; and XEmacs 21.5.
+ (line-number-at-pos
+ . ,(lambda (&optional pos)
+ "Return (narrowed) buffer line number at position POS.
+If POS is nil, use current buffer location.
+Counting starts at (point-min), so the value refers
+to the contents of the accessible portion of the buffer."
+ (let ((opoint (or pos (point))) start)
+ (save-excursion
+ (goto-char (point-min))
+ (setq start (point))
+ (goto-char opoint)
+ (forward-line 0)
+ (1+ (count-lines start (point))))))))))
+
+;; `decode-coding-string', `encode-coding-string', `decode-coding-region'
+;; and `encode-coding-region' are available in Emacs and XEmacs built with
+;; the `file-coding' feature, but the XEmacs versions treat nil, that is
+;; given as the `coding-system' argument, as the `binary' coding system.
(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
(defalias 'mm-decode-coding-region 'decode-coding-region)
(defalias 'mm-encode-coding-region 'encode-coding-region)))
+;; `string-to-multibyte' is available only in Emacs 22.1 or greater.
(defalias 'mm-string-to-multibyte
(cond
((featurep 'xemacs)
'string-to-multibyte)
(t
(lambda (string)
- "Return a multibyte string with the same individual chars as string."
+ "Return a multibyte string with the same individual chars as STRING."
(mapconcat
(lambda (ch) (mm-string-as-multibyte (char-to-string ch)))
string "")))))
+;; `char-or-char-int-p' is an XEmacs function, not available in Emacs.
(eval-and-compile
(defalias 'mm-char-or-char-int-p
(cond
((fboundp 'char-valid-p) 'char-valid-p)
(t 'identity))))
+;; `ucs-to-char' is a function that Mule-UCS provides.
+(if (featurep 'xemacs)
+ (cond ((and (fboundp 'unicode-to-char) ;; XEmacs 21.5.
+ (subrp (symbol-function 'unicode-to-char)))
+ (if (featurep 'mule)
+ (defalias 'mm-ucs-to-char 'unicode-to-char)
+ (defun mm-ucs-to-char (codepoint)
+ "Convert Unicode codepoint to character."
+ (or (unicode-to-char codepoint) ?#))))
+ ((featurep 'mule)
+ (defun mm-ucs-to-char (codepoint)
+ "Convert Unicode codepoint to character."
+ (if (fboundp 'ucs-to-char) ;; Mule-UCS is loaded.
+ (progn
+ (defalias 'mm-ucs-to-char
+ (lambda (codepoint)
+ "Convert Unicode codepoint to character."
+ (condition-case nil
+ (or (ucs-to-char codepoint) ?#)
+ (error ?#))))
+ (mm-ucs-to-char codepoint))
+ (condition-case nil
+ (or (int-to-char codepoint) ?#)
+ (error ?#)))))
+ (t
+ (defun mm-ucs-to-char (codepoint)
+ "Convert Unicode codepoint to character."
+ (condition-case nil
+ (or (int-to-char codepoint) ?#)
+ (error ?#)))))
+ (if (let ((char (make-char 'japanese-jisx0208 36 34)))
+ (eq char (decode-char 'ucs char)))
+ ;; Emacs 23.
+ (defalias 'mm-ucs-to-char 'identity)
+ (defun mm-ucs-to-char (codepoint)
+ "Convert Unicode codepoint to character."
+ (or (decode-char 'ucs codepoint) ?#))))
+
;; 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
,@(when (and (not (mm-coding-system-p 'gbk))
(mm-coding-system-p 'cp936))
'((gbk . cp936)))
+ ;; UTF8 is a bogus name for UTF-8
+ ,@(when (and (not (mm-coding-system-p 'utf8))
+ (mm-coding-system-p 'utf-8))
+ '((utf8 . utf-8)))
;; ISO8859-1 is a bogus name for ISO-8859-1
,@(when (and (not (mm-coding-system-p 'iso8859-1))
(mm-coding-system-p 'iso-8859-1))
'((iso8859-1 . iso-8859-1)))
+ ;; ISO_8859-1 is a bogus name for ISO-8859-1
+ ,@(when (and (not (mm-coding-system-p 'iso_8859-1))
+ (mm-coding-system-p 'iso-8859-1))
+ '((iso_8859-1 . iso-8859-1)))
)
"A mapping from unknown or invalid charset names to the real charset names.
:group 'mime)
(put 'mm-charset-eval-alist 'risky-local-variable t)
+(defvar mm-charset-override-alist)
+
;; Note: this function has to be defined before `mm-charset-override-alist'
;; since it will use this function in order to determine its default value
;; when loading mm-util.elc.
"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)))))
+ (let ((lang (if (boundp 'current-language-environment)
+ (symbol-value 'current-language-environment))))
+ (cond (;; XEmacs without Mule but with `file-coding'.
+ (not lang) nil)
+ ;; In XEmacs 21.5 it may be the one like "Japanese (UTF-8)".
+ ((string-match "\\`Japanese" lang)
+ ;; 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.
(eval-and-compile
(defvar mm-emacs-mule (and (not (featurep 'xemacs))
- (boundp 'default-enable-multibyte-characters)
- default-enable-multibyte-characters
+ (boundp 'enable-multibyte-characters)
+ (default-value 'enable-multibyte-characters)
(fboundp 'set-buffer-multibyte))
"True in Emacs with Mule.")
"Return non-nil if the session is multibyte.
This affects whether coding conversion should be attempted generally."
(if (featurep 'mule)
- (if (boundp 'default-enable-multibyte-characters)
- default-enable-multibyte-characters
+ (if (boundp 'enable-multibyte-characters)
+ (default-value 'enable-multibyte-characters)
t)))
(defun mm-iso-8859-x-to-15-region (&optional b e)
(defmacro mm-with-unibyte-current-buffer (&rest forms)
"Evaluate FORMS with current buffer temporarily made unibyte.
-Also bind `default-enable-multibyte-characters' to nil.
+Also bind the default-value of `enable-multibyte-characters' to nil.
Equivalent to `progn' in XEmacs
NOTE: Use this macro with caution in multibyte buffers (it is not
(let ((,multibyte enable-multibyte-characters)
(,buffer (current-buffer)))
(unwind-protect
- (let (default-enable-multibyte-characters)
+ (letf (((default-value 'enable-multibyte-characters) nil))
(set-buffer-multibyte nil)
,@forms)
(set-buffer ,buffer)
(set-buffer-multibyte ,multibyte)))
- (let (default-enable-multibyte-characters)
+ (letf (((default-value 'enable-multibyte-characters) nil))
,@forms))))
(put 'mm-with-unibyte-current-buffer 'lisp-indent-function 0)
(put 'mm-with-unibyte-current-buffer 'edebug-form-spec '(body))
`find-file-hooks', etc.
If INHIBIT is non-nil, inhibit `mm-inhibit-file-name-handlers'.
This function ensures that none of these modifications will take place."
- (let* ((format-alist nil)
- (auto-mode-alist (if inhibit nil (mm-auto-mode-alist)))
- (default-major-mode 'fundamental-mode)
- (enable-local-variables nil)
- (after-insert-file-functions nil)
- (enable-local-eval nil)
- (inhibit-file-name-operation (if inhibit
- 'insert-file-contents
- inhibit-file-name-operation))
- (inhibit-file-name-handlers
- (if inhibit
- (append mm-inhibit-file-name-handlers
- inhibit-file-name-handlers)
- inhibit-file-name-handlers))
- (ffh (if (boundp 'find-file-hook)
- 'find-file-hook
- 'find-file-hooks))
- (val (symbol-value ffh)))
+ (letf* ((format-alist nil)
+ (auto-mode-alist (if inhibit nil (mm-auto-mode-alist)))
+ ((default-value 'major-mode) 'fundamental-mode)
+ (enable-local-variables nil)
+ (after-insert-file-functions nil)
+ (enable-local-eval nil)
+ (inhibit-file-name-operation (if inhibit
+ 'insert-file-contents
+ inhibit-file-name-operation))
+ (inhibit-file-name-handlers
+ (if inhibit
+ (append mm-inhibit-file-name-handlers
+ inhibit-file-name-handlers)
+ inhibit-file-name-handlers))
+ (ffh (if (boundp 'find-file-hook)
+ 'find-file-hook
+ 'find-file-hooks))
+ (val (symbol-value ffh)))
(set ffh nil)
(unwind-protect
(insert-file-contents filename visit beg end replace)
filename))
(mm-decompress-buffer filename nil t))))
(when decomp
- (set-buffer (let (default-enable-multibyte-characters)
- (generate-new-buffer " *temp*")))
+ (set-buffer (letf (((default-value 'enable-multibyte-characters) nil))
+ (generate-new-buffer " *temp*")))
(insert decomp)
(setq filename (file-name-sans-extension filename)))
(goto-char (point-min))