;;; mule.el --- basic commands for mulitilingual environment
-;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
-;; Licensed to the Free Software Foundation.
-;; Copyright (C) 2001, 2002 Free Software Foundation, Inc.
+;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007
+;; Free Software Foundation, Inc.
+;; Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
+;; 2005, 2006, 2007
+;; National Institute of Advanced Industrial Science and Technology (AIST)
+;; Registration Number H14PRO021
;; Keywords: mule, multilingual, character set, coding system
;; 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.
+;; Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
+;; Boston, MA 02110-1301, USA.
;;; Commentary:
(defun load-with-code-conversion (fullname file &optional noerror nomessage)
"Execute a file of Lisp code named FILE whose absolute name is FULLNAME.
The file contents are decoded before evaluation if necessary.
-If optional second arg NOERROR is non-nil,
+If optional third arg NOERROR is non-nil,
report no error if FILE doesn't exist.
Print messages at start and end of loading unless
- optional third arg NOMESSAGE is non-nil.
+ optional fourth arg NOMESSAGE is non-nil.
Return t if file exists."
(if (null (file-readable-p fullname))
(and (null noerror)
(let ((load-file-name fullname)
(set-auto-coding-for-load t)
(inhibit-file-name-operation nil))
- (save-excursion
- (set-buffer buffer)
- (insert-file-contents fullname)
+ (with-current-buffer buffer
+ ;; Don't let deactivate-mark remain set.
+ (let (deactivate-mark)
+ (insert-file-contents fullname))
;; If the loaded file was inserted with no-conversion or
;; raw-text coding system, make the buffer unibyte.
;; Otherwise, eval-buffer might try to interpret random
;; Make `kill-buffer' quiet.
(set-buffer-modified-p nil))
;; Have the original buffer current while we eval.
- (eval-buffer buffer nil file
+ (eval-buffer buffer nil
+ ;; This is compatible with what `load' does.
+ (if purify-flag file fullname)
;; If this Emacs is running with --unibyte,
;; convert multibyte strings to unibyte
;; after reading them.
))
(let (kill-buffer-hook kill-buffer-query-functions)
(kill-buffer buffer)))
- (let ((hook (assoc file after-load-alist)))
- (when hook
- (mapcar (function eval) (cdr hook))))
+ (unless purify-flag
+ (do-after-load-evaluation fullname))
+
(unless (or nomessage noninteractive)
(if source
(message "Loading %s (source)...done" file)
(< (aref vector 0) 160)))))
(defsubst charsetp (object)
- "T if OBJECT is a charset."
+ "Return t if OBJECT is a charset."
(and (symbolp object) (vectorp (get object 'charset))))
(defsubst charset-info (charset)
CODE1 and CODE2 are optional, but if you don't supply
sufficient position codes, return a generic character which stands for
all characters or group of characters in the character set.
-A generic character can be used to index a char table (e.g. syntax-table).
+A generic character can be used to index a char table (e.g. `syntax-table').
Such character sets as ascii, eight-bit-control, and eight-bit-graphic
don't have corresponding generic characters. If CHARSET is one of
(make-char-internal (charset-id charset) code1 code2))
(put 'make-char 'byte-compile
- (function
- (lambda (form)
- (let ((charset (nth 1 form)))
- (if (charset-quoted-standard-p charset)
- (byte-compile-normal-call
- (cons 'make-char-internal
- (cons (charset-id (nth 1 charset)) (nthcdr 2 form))))
- (byte-compile-normal-call
- (cons 'make-char-internal
- (cons (list 'charset-id charset) (nthcdr 2 form)))))))))
+ (lambda (form)
+ (let ((charset (nth 1 form)))
+ (byte-compile-normal-call
+ (cons 'make-char-internal
+ (cons (if (charset-quoted-standard-p charset)
+ (charset-id (nth 1 charset))
+ (list 'charset-id charset))
+ (nthcdr 2 form)))))))
(defun charset-list ()
"Return list of charsets ever defined.
Currently the only supported coded character set is `ucs' (ISO/IEC
10646: Universal Multi-Octet Coded Character Set), and the result is
translated through the translation-table named
-`utf-translation-table-for-decode' or the translation-hash-table named
-`utf-subst-table-for-decode'.
+`utf-translation-table-for-decode', or through the
+translation-hash-table named `utf-subst-table-for-decode'
+\(if `utf-translate-cjk-mode' is non-nil).
Optional argument RESTRICTION specifies a way to map the pair of CCS
and CODE-POINT to a character. Currently not supported and just ignored."
(cond
((eq ccs 'ucs)
- (or (utf-lookup-subst-table-for-decode code-point)
+ (or (and utf-translate-cjk-mode
+ (utf-lookup-subst-table-for-decode code-point))
(let ((c (cond
((< code-point 160)
code-point)
Currently the only supported coded character set is `ucs' (ISO/IEC
10646: Universal Multi-Octet Coded Character Set), and CHAR is first
translated through the translation-table named
-`utf-translation-table-for-encode' or the translation-hash-table named
-`utf-subst-table-for-encode'.
+`utf-translation-table-for-encode', or through the
+translation-hash-table named `utf-subst-table-for-encode' \(if
+`utf-translate-cjk-mode' is non-nil).
CHAR should be in one of these charsets:
ascii, latin-iso8859-1, mule-unicode-0100-24ff, mule-unicode-2500-33ff,
(charset (car split))
trans)
(cond ((eq ccs 'ucs)
- (or (utf-lookup-subst-table-for-encode char)
+ (or (and utf-translate-cjk-mode
+ (utf-lookup-subst-table-for-encode char))
(let ((table (get 'utf-translation-table-for-encode
'translation-table)))
(setq trans (aref table char))
Any alias nor subsidiary coding systems are not base coding system."
(car (coding-system-get coding-system 'alias-coding-systems)))
-(defalias 'coding-system-parent 'coding-system-base)
-(make-obsolete 'coding-system-parent 'coding-system-base "20.3")
-
;; Coding system also has a property `eol-type'.
;;
;; This property indicates how the coding system handles end-of-line
(and (not (> (downcase c1) (downcase c2)))
(< c1 c2)))))))
+(defun coding-system-equal (coding-system-1 coding-system-2)
+ "Return t if and only if CODING-SYSTEM-1 and CODING-SYSTEM-2 are identical.
+Two coding systems are identical if two symbols are equal
+or one is an alias of the other."
+ (or (eq coding-system-1 coding-system-2)
+ (and (equal (coding-system-spec coding-system-1)
+ (coding-system-spec coding-system-2))
+ (let ((eol-type-1 (coding-system-eol-type coding-system-1))
+ (eol-type-2 (coding-system-eol-type coding-system-2)))
+ (or (eq eol-type-1 eol-type-2)
+ (and (vectorp eol-type-1) (vectorp eol-type-2)))))))
+
(defun add-to-coding-system-list (coding-system)
"Add CODING-SYSTEM to `coding-system-list' while keeping it sorted."
(if (or (null coding-system-list)
(subsidiaries (vector (intern (format "%s-unix" coding-system))
(intern (format "%s-dos" coding-system))
(intern (format "%s-mac" coding-system))))
- (i 0)
- temp)
- (while (< i 3)
- (put (aref subsidiaries i) 'coding-system coding-spec)
- (put (aref subsidiaries i) 'eol-type i)
- (add-to-coding-system-list (aref subsidiaries i))
- (setq coding-system-alist
- (cons (list (symbol-name (aref subsidiaries i)))
- coding-system-alist))
- (setq i (1+ i)))
+ elt)
+ (dotimes (i 3)
+ (setq elt (aref subsidiaries i))
+ (put elt 'coding-system coding-spec)
+ (put elt 'eol-type i)
+ (put elt 'coding-system-define-form nil)
+ (add-to-coding-system-list elt)
+ (or (assoc (symbol-name elt) coding-system-alist)
+ (setq coding-system-alist
+ (cons (list (symbol-name elt)) coding-system-alist))))
subsidiaries))
(defun transform-make-coding-system-args (name type &optional doc-string props)
If the value is non-nil, the coding system preserves composition
information.
+ o ascii-incompatible
+
+ If the value is non-nil, the coding system is not compatible
+ with ASCII, which means it encodes or decodes ASCII character
+ string to the different byte sequence.
+
These properties are set in PLIST, a property list. This function
also sets properties `coding-category' and `alias-coding-systems'
automatically.
(setq coding-category (plist-get plist 'coding-category))
(aset coding-spec coding-spec-plist-idx plist))
(put coding-system 'coding-system coding-spec)
+ (put coding-system 'coding-system-define-form nil)
(put coding-category 'coding-systems
(cons coding-system (get coding-category 'coding-systems))))
;; At last, register CODING-SYSTEM in `coding-system-list' and
;; `coding-system-alist'.
(add-to-coding-system-list coding-system)
- (setq coding-system-alist (cons (list (symbol-name coding-system))
- coding-system-alist))
+ (or (assoc (symbol-name coding-system) coding-system-alist)
+ (setq coding-system-alist (cons (list (symbol-name coding-system))
+ coding-system-alist)))
;; For a coding system of cateogory iso-8-1 and iso-8-2, create
;; XXX-with-esc variants.
(defun define-coding-system-alias (alias coding-system)
"Define ALIAS as an alias for coding system CODING-SYSTEM."
(put alias 'coding-system (coding-system-spec coding-system))
+ (put alias 'coding-system-define-form nil)
(add-to-coding-system-list alias)
- (setq coding-system-alist (cons (list (symbol-name alias))
- coding-system-alist))
+ (or (assoc (symbol-name alias) coding-system-alist)
+ (setq coding-system-alist (cons (list (symbol-name alias))
+ coding-system-alist)))
(let ((eol-type (coding-system-eol-type coding-system)))
(if (vectorp eol-type)
(progn
FROM is a form to evaluate to define the coding-system."
(put symbol 'coding-system-define-form form)
(setq coding-system-alist (cons (list (symbol-name symbol))
- coding-system-alist)))
+ coding-system-alist))
+ (dolist (elt '("-unix" "-dos" "-mac"))
+ (let ((name (concat (symbol-name symbol) elt)))
+ (put (intern name) 'coding-system-define-form form)
+ (setq coding-system-alist (cons (list name) coding-system-alist)))))
-(defun set-buffer-file-coding-system (coding-system &optional force)
+(defun set-buffer-file-coding-system (coding-system &optional force nomodify)
"Set the file coding-system of the current buffer to CODING-SYSTEM.
This means that when you save the buffer, it will be converted
according to CODING-SYSTEM. For a list of possible values of CODING-SYSTEM,
This marks the buffer modified so that the succeeding \\[save-buffer]
surely saves the buffer with CODING-SYSTEM. From a program, if you
-don't want to mark the buffer modified, just set the variable
-`buffer-file-coding-system' directly."
- (interactive "zCoding system for saving file (default, nil): \nP")
+don't want to mark the buffer modified, specify t for NOMODIFY.
+If you know exactly what coding system you want to use,
+just set the variable `buffer-file-coding-system' directly."
+ (interactive "zCoding system for saving file (default nil): \nP")
(check-coding-system coding-system)
(if (and coding-system buffer-file-coding-system (null force))
(setq coding-system
;; `set-buffer-major-mode-hook' take care of setting the table.
(if (fboundp 'ucs-set-table-for-input) ; don't lose when building
(ucs-set-table-for-input))
- (set-buffer-modified-p t)
+ (unless nomodify
+ (set-buffer-modified-p t))
(force-mode-line-update))
(defun revert-buffer-with-coding-system (coding-system &optional force)
buffer's previous `buffer-file-coding-system' value (if it is
specified there). Otherwise, determine it from the file contents as
usual for visiting a file."
- (interactive "zCoding system for visited file (default, nil): \nP")
+ (interactive "zCoding system for visited file (default nil): \nP")
(check-coding-system coding-system)
(if (and coding-system buffer-file-coding-system (null force))
(setq coding-system
"Set coding system for decoding and encoding file names to CODING-SYSTEM.
It actually just set the variable `file-name-coding-system' (which
see) to CODING-SYSTEM."
- (interactive "zCoding system for file names (default, nil): ")
+ (interactive "zCoding system for file names (default nil): ")
(check-coding-system coding-system)
+ (if (and coding-system
+ (coding-system-get coding-system 'ascii-incompatible))
+ (error "%s is not ASCII-compatible" coding-system))
(setq file-name-coding-system coding-system))
(defvar default-terminal-coding-system nil
default-terminal-coding-system)
default-terminal-coding-system)))
(read-coding-system
- (format "Coding system for terminal display (default, %s): "
+ (format "Coding system for terminal display (default %s): "
default)
default))))
(if (and (not coding-system)
default-keyboard-coding-system)
default-keyboard-coding-system)))
(read-coding-system
- (format "Coding system for keyboard input (default, %s): "
+ (format "Coding system for keyboard input (default %s): "
default)
default))))
(if (and (not coding-system)
(setq coding-system default-keyboard-coding-system))
(if coding-system
(setq default-keyboard-coding-system coding-system))
+ (if (and coding-system
+ (coding-system-get coding-system 'ascii-incompatible))
+ (error "%s is not ASCII-compatible" coding-system))
(set-keyboard-coding-system-internal coding-system)
(setq keyboard-coding-system coding-system)
(encoded-kbd-mode (if coding-system 1 0)))
"Specify coding system for keyboard input.
If you set this on a terminal which can't distinguish Meta keys from
8-bit characters, you will have to use ESC to type Meta characters.
-See Info node `Specify Coding' and Info node `Single-Byte Character Support'.
+See Info node `Terminal Coding' and Info node `Unibyte Mode'.
On non-windowing terminals, this is set from the locale by default.
Setting this variable directly does not take effect;
use either \\[customize] or \\[set-keyboard-coding-system]."
:type '(coding-system :tag "Coding system")
- :link '(info-link "(emacs)Specify Coding")
- :link '(info-link "(emacs)Single-Byte Character Support")
+ :link '(info-link "(emacs)Terminal Coding")
+ :link '(info-link "(emacs)Unibyte Mode")
:set (lambda (symbol value)
;; Don't load encoded-kbd-mode unnecessarily.
(if (or value (boundp 'encoded-kbd-mode))
(set-keyboard-coding-system value)
(set-default 'keyboard-coding-system nil))) ; must initialize
- :version "21.4"
+ :version "22.1"
:group 'keyboard
:group 'mule)
(interactive
(list (read-coding-system
(if last-next-selection-coding-system
- (format "Coding system for the next X selection (default, %S): "
+ (format "Coding system for the next X selection (default %S): "
last-next-selection-coding-system)
"Coding system for the next X selection: ")
last-next-selection-coding-system)))
by encode-coding-string, generate a new temp buffer, insert the
text, and convert it in the temporary buffer. Otherwise, convert in-place."
(save-match-data
- ;; Setup a working buffer if necessary.
- (cond ((stringp from)
- (let ((buf (current-buffer)))
- (set-buffer (generate-new-buffer " *temp"))
+ (let ((workbuf (get-buffer-create " *code-conversion-work*")))
+ ;; Setup a working buffer if necessary.
+ (cond ((stringp from)
+ (set-buffer workbuf)
+ (erase-buffer)
(set-buffer-multibyte (multibyte-string-p from))
- (insert from)))
- ((not (string= (buffer-name) " *code-converting-work*"))
- (let ((buf (current-buffer))
- (multibyte enable-multibyte-characters))
- (set-buffer (generate-new-buffer " *temp"))
- (set-buffer-multibyte multibyte)
- (insert-buffer-substring buf from to))))
+ (insert from))
+ ((not (eq (current-buffer) workbuf))
+ (let ((buf (current-buffer))
+ (multibyte enable-multibyte-characters))
+ (set-buffer workbuf)
+ (erase-buffer)
+ (set-buffer-multibyte multibyte)
+ (insert-buffer-substring buf from to)))))
;; Now we can encode the whole buffer.
(let ((encoding-table (ctext-non-standard-encodings-table))
;;; FILE I/O
(defcustom auto-coding-alist
- '(("\\.\\(arc\\|zip\\|lzh\\|zoo\\|jar\\|sx[dmicw]\\|tar\\|tgz\\)\\'" . no-conversion)
+ '(("\\.\\(arc\\|zip\\|lzh\\|lha\\|zoo\\|[jew]ar\\|xpi\\)\\'" . no-conversion)
+ ("\\.\\(ARC\\|ZIP\\|LZH\\|LHA\\|ZOO\\|[JEW]AR\\|XPI\\)\\'" . no-conversion)
+ ("\\.\\(sx[dmicw]\\|odt\\|tar\\|tgz\\)\\'" . no-conversion)
("\\.\\(gz\\|Z\\|bz\\|bz2\\|gpg\\)\\'" . no-conversion)
+ ("\\.\\(jpe?g\\|png\\|gif\\|tiff?\\|p[bpgn]m\\)\\'" . no-conversion)
("/#[^/]+#\\'" . emacs-mule))
"Alist of filename patterns vs corresponding coding systems.
Each element looks like (REGEXP . CODING-SYSTEM).
(symbol :tag "Coding system"))))
(defcustom auto-coding-regexp-alist
- '(("^BABYL OPTIONS:[ \t]*-\\*-[ \t]*rmail[ \t]*-\\*-" . no-conversion))
+ '(("^BABYL OPTIONS:[ \t]*-\\*-[ \t]*rmail[ \t]*-\\*-" . no-conversion)
+ ("\\`\xFE\xFF" . utf-16be-with-signature)
+ ("\\`\xFF\xFE" . utf-16le-with-signature)
+ ("\\`\xEF\xBB\xBF" . utf-8))
"Alist of patterns vs corresponding coding systems.
Each element looks like (REGEXP . CODING-SYSTEM).
A file whose first bytes match REGEXP is decoded by CODING-SYSTEM on reading.
:type '(repeat (cons (regexp :tag "Regexp")
(symbol :tag "Coding system"))))
+(defun auto-coding-regexp-alist-lookup (from to)
+ "Lookup `auto-coding-regexp-alist' for the contents of the current buffer.
+The value is a coding system is specified for the region FROM and TO,
+or nil."
+ (save-excursion
+ (goto-char from)
+ (let ((alist auto-coding-regexp-alist)
+ coding-system)
+ (while (and alist (not coding-system))
+ (let ((regexp (car (car alist))))
+ (if enable-multibyte-characters
+ (setq regexp (string-to-multibyte regexp)))
+ (if (re-search-forward regexp to t)
+ (setq coding-system (cdr (car alist)))
+ (setq alist (cdr alist)))))
+ coding-system)))
+
;; See the bottom of this file for built-in auto coding functions.
(defcustom auto-coding-functions '(sgml-xml-auto-coding-function
sgml-html-meta-auto-coding-function)
(setq alist (cdr alist))))
coding-system))
-(defun set-auto-coding (filename size)
- "Return coding system for a file FILENAME of which SIZE bytes follow point.
+(put 'enable-character-translation 'permanent-local t)
+(put 'enable-character-translation 'safe-local-variable 'booleanp)
+
+(defun find-auto-coding (filename size)
+ "Find a coding system for a file FILENAME of which SIZE bytes follow point.
These bytes should include at least the first 1k of the file
and the last 3k of the file, but the middle may be omitted.
succeed, it checks to see if any function in `auto-coding-functions'
gives a match.
-The return value is the specified coding system, or nil if nothing is
-specified.
-
-The variable `set-auto-coding-function' (which see) is set to this
-function by default."
- (or (auto-coding-alist-lookup filename)
+If a coding system is specifed, the return value is a
+cons (CODING . SOURCE), where CODING is the specified coding
+system and SOURCE is a symbol `auto-coding-alist',
+`auto-coding-regexp-alist', `coding:', or `auto-coding-functions'
+indicating by what CODING is specified. Note that the validity
+of CODING is not checked; it's the caller's responsibility to check it.
+
+If nothing is specified, the return value is nil."
+ (or (let ((coding-system (auto-coding-alist-lookup filename)))
+ (if coding-system
+ (cons coding-system 'auto-coding-alist)))
;; Try using `auto-coding-regexp-alist'.
- (save-excursion
- (let ((alist auto-coding-regexp-alist)
- coding-system)
- (while (and alist (not coding-system))
- (let ((regexp (car (car alist))))
- (when (re-search-forward regexp (+ (point) size) t)
- (setq coding-system (cdr (car alist)))))
- (setq alist (cdr alist)))
- coding-system))
+ (let ((coding-system (auto-coding-regexp-alist-lookup (point)
+ (+ (point) size))))
+ (if coding-system
+ (cons coding-system 'auto-coding-regexp-alist)))
(let* ((case-fold-search t)
(head-start (point))
(head-end (+ head-start (min size 1024)))
(tail-start (+ head-start (max (- size 3072) 0)))
(tail-end (+ head-start size))
- coding-system head-found tail-found pos)
+ coding-system head-found tail-found pos char-trans)
;; Try a short cut by searching for the string "coding:"
;; and for "unibyte:" at the head and tail of SIZE bytes.
(setq head-found (or (search-forward "coding:" head-end t)
- (search-forward "unibyte:" head-end t)))
+ (search-forward "unibyte:" head-end t)
+ (search-forward "enable-character-translation:"
+ head-end t)))
(if (and head-found (> head-found tail-start))
;; Head and tail are overlapped.
(setq tail-found head-found)
(goto-char tail-start)
(setq tail-found (or (search-forward "coding:" tail-end t)
- (search-forward "unibyte:" tail-end t))))
+ (search-forward "unibyte:" tail-end t)
+ (search-forward "enable-character-translation:"
+ tail-end t))))
;; At first check the head.
(when head-found
(re-search-forward
"\\(.*;\\)?[ \t]*coding:[ \t]*\\([^ ;]+\\)"
head-end t))
- (setq coding-system (intern (match-string 2)))
- (or (coding-system-p coding-system)
- (setq coding-system nil)))))
+ (setq coding-system (intern (match-string 2))))
+ (when (re-search-forward
+ "\\(.*;\\)?[ \t]*enable-character-translation:[ \t]*\\([^ ;]+\\)"
+ head-end t)
+ (setq char-trans (match-string 2)))))
;; If no coding: tag in the head, check the tail.
;; Here we must pay attention to the case that the end-of-line
;; is just "\r" and we can't use "^" nor "$" in regexp.
- (when (and tail-found (not coding-system))
+ (when (and tail-found (or (not coding-system) (not char-trans)))
(goto-char tail-start)
- (re-search-forward "[\r\n]\^L" nil t)
+ (re-search-forward "[\r\n]\^L" tail-end t)
(if (re-search-forward
"[\r\n]\\([^[\r\n]*\\)[ \t]*Local Variables:[ \t]*\\([^\r\n]*\\)[\r\n]"
tail-end t)
"[\r\n]" prefix
"[ \t]*unibyte[ \t]*:[ \t]*\\([^ \t\r\n]+\\)[ \t]*"
suffix "[\r\n]"))
+ (re-char-trans
+ (concat
+ "[\r\n]" prefix
+ "[ \t]*enable-character-translation[ \t]*:[ \t]*\\([^ \t\r\n]+\\)[ \t]*"
+ suffix "[\r\n]"))
(re-end
(concat "[\r\n]" prefix "[ \t]*End *:[ \t]*" suffix
"[\r\n]?"))
(setq coding-system 'raw-text))
(when (and (not coding-system)
(re-search-forward re-coding tail-end t))
- (setq coding-system (intern (match-string 1)))
- (or (coding-system-p coding-system)
- (setq coding-system nil))))))
- coding-system)
+ (setq coding-system (intern (match-string 1))))
+ (when (and (not char-trans)
+ (re-search-forward re-char-trans tail-end t))
+ (setq char-trans (match-string 1))))))
+ (if coding-system
+ ;; If the coding-system name ends with "!", remove it and
+ ;; set char-trans to "nil".
+ (let ((name (symbol-name coding-system)))
+ (if (= (aref name (1- (length name))) ?!)
+ (setq coding-system (intern (substring name 0 -1))
+ char-trans "nil"))))
+ (when (and char-trans
+ (not (setq char-trans (intern char-trans))))
+ (make-local-variable 'enable-character-translation)
+ (setq enable-character-translation nil))
+ (if coding-system
+ (cons coding-system :coding)))
;; Finally, try all the `auto-coding-functions'.
(let ((funcs auto-coding-functions)
(coding-system nil))
(goto-char (point-min))
(funcall (pop funcs) size))
(error nil))))
- coding-system)))
+ (if coding-system
+ (cons coding-system 'auto-coding-functions)))))
+
+(defun set-auto-coding (filename size)
+ "Return coding system for a file FILENAME of which SIZE bytes follow point.
+See `find-auto-coding' for how the coding system is found.
+Return nil if an invalid coding system is found.
+
+The variable `set-auto-coding-function' (which see) is set to this
+function by default."
+ (let ((found (find-auto-coding filename size)))
+ (if (and found (coding-system-p (car found)))
+ (car found))))
(setq set-auto-coding-function 'set-auto-coding)
-(defun after-insert-file-set-coding (inserted)
+;; This variable is set in these two cases:
+;; (1) A file is read by a coding system specified explicitly.
+;; after-insert-file-set-coding sets this value to
+;; coding-system-for-read.
+;; (2) A buffer is saved.
+;; After writing, basic-save-buffer-1 sets this value to
+;; last-coding-system-used.
+;; This variable is used for decoding in revert-buffer.
+(defvar buffer-file-coding-system-explicit nil
+ "The file coding system explicitly specified for the current buffer.
+Internal use only.")
+(make-variable-buffer-local 'buffer-file-coding-system-explicit)
+(put 'buffer-file-coding-system-explicit 'permanent-local t)
+
+(defun after-insert-file-set-coding (inserted &optional visit)
"Set `buffer-file-coding-system' of current buffer after text is inserted.
INSERTED is the number of characters that were inserted, as figured
in the situation before this function. Return the number of characters
inserted, as figured in the situation after. The two numbers can be
-different if the buffer has become unibyte."
+different if the buffer has become unibyte.
+The optional second arg VISIT non-nil means that we are visiting a file."
+ (if (and visit
+ coding-system-for-read
+ (not (eq coding-system-for-read 'auto-save-coding)))
+ (setq buffer-file-coding-system-explicit coding-system-for-read))
(if last-coding-system-used
(let ((coding-system
(find-new-buffer-file-coding-system last-coding-system-used))
(modified-p (buffer-modified-p)))
(when coding-system
- (set-buffer-file-coding-system coding-system t)
+ ;; Tell set-buffer-file-coding-system not to mark the file
+ ;; as modified; we just read it, and it's supposed to be unmodified.
+ ;; Marking it modified would try to lock it, which would
+ ;; check the modtime, and we don't want to do that again now.
+ (set-buffer-file-coding-system coding-system t t)
(if (and enable-multibyte-characters
(or (eq coding-system 'no-conversion)
(eq (coding-system-type coding-system) 5))
(= (buffer-size) inserted))
;; For coding systems no-conversion and raw-text...,
;; edit the buffer as unibyte.
- (let ((pos-marker (copy-marker (+ (point) inserted))))
- (set-buffer-multibyte nil)
+ (let ((pos-marker (copy-marker (+ (point) inserted)))
+ ;; Prevent locking.
+ (buffer-file-name nil))
+ (if visit
+ ;; If we're doing this for find-file,
+ ;; don't record undo info; this counts as
+ ;; part of producing the buffer's initial contents.
+ (let ((buffer-undo-list t))
+ (set-buffer-multibyte nil))
+ (set-buffer-multibyte nil))
(setq inserted (- pos-marker (point)))))
- (set-buffer-modified-p modified-p))))
+ (restore-buffer-modified-p modified-p))))
inserted)
;; The coding-spec and eol-type of coding-system returned is decided
(defun decode-coding-inserted-region (from to filename
&optional visit beg end replace)
"Decode the region between FROM and TO as if it is read from file FILENAME.
+The idea is that the text between FROM and TO was just inserted somehow.
Optional arguments VISIT, BEG, END, and REPLACE are the same as those
-of the function `insert-file-contents'."
+of the function `insert-file-contents'.
+Part of the job of this function is setting `buffer-undo-list' appropriately."
(save-excursion
(save-restriction
- (narrow-to-region from to)
- (goto-char (point-min))
- (let ((coding coding-system-for-read))
+ (let ((coding coding-system-for-read)
+ undo-list-saved)
+ (if visit
+ ;; Temporarily turn off undo recording, if we're decoding the
+ ;; text of a visited file.
+ (setq buffer-undo-list t)
+ ;; Otherwise, if we can recognize the undo elt for the insertion,
+ ;; remove it and get ready to replace it later.
+ ;; In the mean time, turn off undo recording.
+ (let ((last (car-safe buffer-undo-list)))
+ (if (and (consp last) (eql (car last) from) (eql (cdr last) to))
+ (setq undo-list-saved (cdr buffer-undo-list)
+ buffer-undo-list t))))
+ (narrow-to-region from to)
+ (goto-char (point-min))
(or coding
(setq coding (funcall set-auto-coding-function
filename (- (point-max) (point-min)))))
(or coding
(setq coding (car (find-operation-coding-system
'insert-file-contents
- filename visit beg end replace))))
+ (cons filename (current-buffer))
+ visit beg end replace))))
(if (coding-system-p coding)
(or enable-multibyte-characters
(setq coding
(setq coding nil))
(if coding
(decode-coding-region (point-min) (point-max) coding)
- (setq last-coding-system-used coding))))))
+ (setq last-coding-system-used coding))
+ ;; If we're decoding the text of a visited file,
+ ;; the undo list should start out empty.
+ (if visit
+ (setq buffer-undo-list nil)
+ ;; If we decided to replace the undo entry for the insertion,
+ ;; do so now.
+ (if undo-list-saved
+ (setq buffer-undo-list
+ (cons (cons from (point-max)) undo-list-saved))))))))
+
+(defun recode-region (start end new-coding coding)
+ "Re-decode the region (previously decoded by CODING) by NEW-CODING."
+ (interactive
+ (list (region-beginning) (region-end)
+ (read-coding-system "Text was really in: ")
+ (let ((coding (or buffer-file-coding-system last-coding-system-used)))
+ (read-coding-system
+ (concat "But was interpreted as"
+ (if coding (format " (default %S): " coding) ": "))
+ coding))))
+ (or (and new-coding coding)
+ (error "Coding system not specified"))
+ ;; Check it before we encode the region.
+ (check-coding-system new-coding)
+ (save-restriction
+ (narrow-to-region start end)
+ (encode-coding-region (point-min) (point-max) coding)
+ (decode-coding-region (point-min) (point-max) new-coding)))
(defun make-translation-table (&rest args)
"Make a translation table from arguments.
(put symbol 'translation-table-id id)
id))
+(defun translate-region (start end table)
+ "From START to END, translate characters according to TABLE.
+TABLE is a string or a char-table.
+If TABLE is a string, the Nth character in it is the mapping
+for the character with code N.
+If TABLE is a char-table, the element for character N is the mapping
+for the character with code N.
+It returns the number of characters changed."
+ (interactive
+ (list (region-beginning)
+ (region-end)
+ (let (table l)
+ (dotimes (i (length translation-table-vector))
+ (if (consp (aref translation-table-vector i))
+ (push (list (symbol-name
+ (car (aref translation-table-vector i)))) l)))
+ (if (not l)
+ (error "No translation table defined"))
+ (while (not table)
+ (setq table (completing-read "Translation table: " l nil t)))
+ (intern table))))
+ (if (symbolp table)
+ (let ((val (get table 'translation-table)))
+ (or (char-table-p val)
+ (error "Invalid translation table name: %s" table))
+ (setq table val)))
+ (translate-region-internal start end table))
+
(put 'with-category-table 'lisp-indent-function 1)
(defmacro with-category-table (table &rest body)
(progn
(set-category-table ,table)
,@body)
- (save-current-buffer
- (set-buffer ,old-buffer)
+ (with-current-buffer ,old-buffer
(set-category-table ,old-table))))))
(defun define-translation-hash-table (symbol table)
(when (re-search-forward "\\`[[:space:]\n]*<\\?xml" size t)
(let ((end (save-excursion
;; This is a hack.
- (re-search-forward "\"\\s-*\\?>" size t))))
+ (re-search-forward "[\"']\\s-*\\?>" size t))))
(when end
- (if (re-search-forward "encoding=\"\\(.+?\\)\"" end t)
+ (if (re-search-forward "encoding=[\"']\\(.+?\\)[\"']" end t)
(let* ((match (match-string 1))
(sym (intern (downcase match))))
(if (coding-system-p sym)
"If the buffer has an HTML meta tag, use it to determine encoding.
This function is intended to be added to `auto-coding-functions'."
(setq size (min (+ (point) size)
- ;; Only search forward 10 lines
(save-excursion
- (forward-line 10)
+ ;; Limit the search by the end of the HTML header.
+ (or (search-forward "</head>" size t)
+ ;; In case of no header, search only 10 lines.
+ (forward-line 10))
(point))))
- (when (and (search-forward "<html>" size t)
- (re-search-forward "<meta\\s-+http-equiv=\"content-type\"\\s-+content=\"text/\\sw+;\\s-*charset=\\(.+?\\)\"" size t))
- (let* ((match (match-string 1))
- (sym (intern (downcase match))))
- (if (coding-system-p sym)
- sym
- (message "Warning: unknown coding system \"%s\"" match)
- nil))))
+ ;; Make sure that the buffer really contains an HTML document, by
+ ;; checking that it starts with a doctype or a <HTML> start tag
+ ;; (allowing for whitespace at bob). Note: 'DOCTYPE NETSCAPE' is
+ ;; useful for Mozilla bookmark files.
+ (when (and (re-search-forward "\\`[[:space:]\n]*\\(<!doctype[[:space:]\n]+\\(html\\|netscape\\)\\|<html\\)" size t)
+ (re-search-forward "<meta\\s-+http-equiv=[\"']?content-type[\"']?\\s-+content=[\"']text/\\sw+;\\s-*charset=\\(.+?\\)[\"']" size t))
+ (let* ((match (match-string 1))
+ (sym (intern (downcase match))))
+ (if (coding-system-p sym)
+ sym
+ (message "Warning: unknown coding system \"%s\"" match)
+ nil))))
;;;
(provide 'mule)
-;;; arch-tag: 9aebaa6e-0e8a-40a9-b857-cb5d04a39e7c
+;; arch-tag: 9aebaa6e-0e8a-40a9-b857-cb5d04a39e7c
;;; mule.el ends here