;;; mule.el --- basic commands for multilingual environment
;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006,
-;; 2007, 2008, 2009, 2010
+;; 2007, 2008, 2009, 2010, 2011
;; Free Software Foundation, Inc.
;; Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
-;; 2005, 2006, 2007, 2008, 2009, 2010
+;; 2005, 2006, 2007, 2008, 2009, 2010, 2011
;; National Institute of Advanced Industrial Science and Technology (AIST)
;; Registration Number H14PRO021
;; Copyright (C) 2003
(with-current-buffer buffer
;; So that we don't get completely screwed if the
;; file is encoded in some complicated character set,
- ;; read it with real decoding, as a multibyte buffer,
- ;; even if this is a --unibyte Emacs session.
+ ;; read it with real decoding, as a multibyte buffer.
(set-buffer-multibyte t)
;; Don't let deactivate-mark remain set.
(let (deactivate-mark)
(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.
-;; (not (default-value 'enable-multibyte-characters))
- nil t
- ))
+ nil t))
(let (kill-buffer-hook kill-buffer-query-functions)
(kill-buffer buffer)))
(do-after-load-evaluation fullname)
VALUE is the EOL (end-of-line) format of the coding system. It must be
one of `unix', `dos', `mac'. The symbol `unix' means Unix-like EOL
\(i.e. single LF), `dos' means DOS-like EOL \(i.e. sequence of CR LF),
-and `mac' means Mac-like EOL \(i.e. single CR). If omitted, on
-decoding by the coding system, Emacs automatically detects the EOL
-format of the source text.
+and `mac' means Mac-like EOL \(i.e. single CR). If omitted, Emacs
+detects the EOL format automatically when decoding.
`:charset-list'
VALUE must be a function to call after some text is inserted and
decoded by the coding system itself and before any functions in
-`after-insert-functions' are called. The arguments to this function
-are the same as those of a function in `after-insert-file-functions',
-i.e. LENGTH of the text to be decoded with point at the head of it,
-and the function should leave point unchanged.
+`after-insert-functions' are called. This function is passed one
+argument; the number of characters in the text to convert, with
+point at the start of the text. The function should leave point
+the same, and return the new character count.
`:pre-write-conversion'
VALUE must be a function to call after all functions in
-`write-region-annotate-functions' and `buffer-file-format' are called,
-and before the text is encoded by the coding system itself. The
-arguments to this function are the same as those of a function in
-`write-region-annotate-functions'.
+`write-region-annotate-functions' and `buffer-file-format' are
+called, and before the text is encoded by the coding system
+itself. This function should convert the whole text in the
+current buffer. For backward compatibility, this function is
+passed two arguments which can be ignored.
`:default-char'
VALUE non-nil means that visiting a file with the coding system
results in a unibyte buffer.
-`:eol-type'
-
-VALUE must be `unix', `dos', `mac'. The symbol `unix' means Unix-like
-EOL (LF), `dos' means DOS-like EOL (CRLF), and `mac' means Mac-like
-EOL (CR). If omitted, on decoding, the coding system detects EOL
-format automatically, and on encoding, uses Unix-like EOL.
-
`:mime-charset'
VALUE must be a symbol whose name is that of a MIME charset converted
(make-variable-buffer-local 'buffer-file-coding-system-explicit)
(put 'buffer-file-coding-system-explicit 'permanent-local t)
+(defun read-buffer-file-coding-system ()
+ (let* ((bcss (find-coding-systems-region (point-min) (point-max)))
+ (css-table
+ (unless (equal bcss '(undecided))
+ (append '("dos" "unix" "mac")
+ (delq nil (mapcar (lambda (cs)
+ (if (memq (coding-system-base cs) bcss)
+ (symbol-name cs)))
+ coding-system-list)))))
+ (combined-table
+ (if css-table
+ (completion-table-in-turn css-table coding-system-alist)
+ coding-system-alist))
+ (auto-cs
+ (unless find-file-literally
+ (save-excursion
+ (save-restriction
+ (widen)
+ (goto-char (point-min))
+ (funcall set-auto-coding-function
+ (or buffer-file-name "") (buffer-size))))))
+ (preferred
+ (let ((bfcs (default-value 'buffer-file-coding-system)))
+ (cons (and (or (equal bcss '(undecided))
+ (memq (coding-system-base bfcs) bcss))
+ bfcs)
+ (mapcar (lambda (cs)
+ (and (coding-system-p cs)
+ (coding-system-get cs :mime-charset)
+ (or (equal bcss '(undecided))
+ (memq (coding-system-base cs) bcss))
+ cs))
+ (coding-system-priority-list)))))
+ (default
+ (let ((current (coding-system-base buffer-file-coding-system)))
+ ;; Generally use as a default the first preferred coding-system
+ ;; different from the current coding-system, except for
+ ;; the case of auto-cs since choosing anything else is asking
+ ;; for trouble (would lead to using a different coding
+ ;; system than specified in the coding tag).
+ (or auto-cs
+ (car (delq nil
+ (mapcar (lambda (cs)
+ (if (eq current (coding-system-base cs))
+ nil
+ cs))
+ preferred))))))
+ (completion-ignore-case t)
+ (completion-pcm--delim-wild-regex ; Let "u8" complete to "utf-8".
+ (concat completion-pcm--delim-wild-regex
+ "\\|\\([[:alpha:]]\\)[[:digit:]]"))
+ (cs (completing-read
+ (format "Coding system for saving file (default %s): " default)
+ combined-table
+ nil t nil 'coding-system-history
+ (if default (symbol-name default)))))
+ (unless (zerop (length cs)) (intern cs))))
+
(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
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")
+ (interactive
+ (list (read-buffer-file-coding-system)
+ current-prefix-arg))
(check-coding-system coding-system)
(if (and coding-system buffer-file-coding-system (null force))
(setq coding-system
(merge-coding-systems coding-system buffer-file-coding-system)))
+ (when (called-interactively-p 'interactive)
+ ;; Check whether save would succeed, and jump to the offending char(s)
+ ;; if not.
+ (let ((css (find-coding-systems-region (point-min) (point-max))))
+ (unless (or (eq (car css) 'undecided)
+ (memq (coding-system-base coding-system) css))
+ (setq coding-system (select-safe-coding-system-interactively
+ (point-min) (point-max) css
+ (list coding-system))))))
(setq buffer-file-coding-system coding-system)
(if buffer-file-coding-system-explicit
(setcdr buffer-file-coding-system-explicit coding-system)
(setq buffer-file-coding-system-explicit (cons nil coding-system)))
- ;; This is in case of an explicit call. Normally, `normal-mode' and
- ;; `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))
(unless nomodify
(set-buffer-modified-p t))
(force-mode-line-update))
;; self-extracting exe archives.
(mapcar (lambda (arg) (cons (purecopy (car arg)) (cdr arg)))
'(("\\.\\(\
-arc\\|zip\\|lzh\\|lha\\|zoo\\|[jew]ar\\|xpi\\|rar\\|\
-ARC\\|ZIP\\|LZH\\|LHA\\|ZOO\\|[JEW]AR\\|XPI\\|RAR\\)\\'"
+arc\\|zip\\|lzh\\|lha\\|zoo\\|[jew]ar\\|xpi\\|rar\\|7z\\|\
+ARC\\|ZIP\\|LZH\\|LHA\\|ZOO\\|[JEW]AR\\|XPI\\|RAR\\|7Z\\)\\'"
. no-conversion-multibyte)
("\\.\\(exe\\|EXE\\)\\'" . no-conversion)
("\\.\\(sx[dmicw]\\|odt\\|tar\\|tgz\\)\\'" . no-conversion)
- ("\\.\\(gz\\|Z\\|bz\\|bz2\\|gpg\\)\\'" . no-conversion)
+ ("\\.\\(gz\\|Z\\|bz\\|bz2\\|xz\\|gpg\\)\\'" . no-conversion)
("\\.\\(jpe?g\\|png\\|gif\\|tiff?\\|p[bpgn]m\\)\\'" . no-conversion)
("\\.pdf\\'" . no-conversion)
("/#[^/]+#\\'" . emacs-mule)))
The settings in this alist take priority over `coding:' tags
in the file (see the function `set-auto-coding')
and the contents of `file-coding-system-alist'."
+ :version "24.1" ; added xz
:group 'files
:group 'mule
:type '(repeat (cons (regexp :tag "File name regexp")
(defun make-translation-table-from-vector (vec)
"Make translation table from decoding vector VEC.
VEC is an array of 256 elements to map unibyte codes to multibyte
-characters. Elements may be nil for undefined code points.
-See also the variable `nonascii-translation-table'."
+characters. Elements may be nil for undefined code points."
(let ((table (make-char-table 'translation-table))
(rev-table (make-char-table 'translation-table))
ch)
(setq table val)))
(translate-region-internal start end table))
-(put 'with-category-table 'lisp-indent-function 1)
-
(defmacro with-category-table (table &rest body)
"Execute BODY like `progn' with TABLE the current category table.
The category table of the current buffer is saved, BODY is evaluated,
then the saved table is restored, even in case of an abnormal exit.
Value is what BODY returns."
+ (declare (indent 1) (debug t))
(let ((old-table (make-symbol "old-table"))
(old-buffer (make-symbol "old-buffer")))
`(let ((,old-table (category-table))