-;;; mule-cmds.el --- commands for mulitilingual environment
-;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
+;;; mule-cmds.el --- commands for mulitilingual environment -*-coding: iso-2022-7bit -*-
+
+;; Copyright (C) 2000, 2001, 2002, 2003, 2004, 2005 Free Software Foundation, Inc.
+;; Copyright (C) 1995, 2003 Electrotechnical Laboratory, JAPAN.
;; Licensed to the Free Software Foundation.
-;; Copyright (C) 2000, 2001, 2002, 2003 Free Software Foundation, Inc.
;; Keywords: mule, multilingual
(define-key-after mule-menu-keymap [set-language-environment]
(list 'menu-item "Set Language Environment" setup-language-environment-map
:help "Multilingual environment suitable for a specific language"))
-(define-key-after mule-menu-keymap [mouse-set-font]
- '(menu-item "Set Font/Fontset" mouse-set-font
- :visible (fboundp 'generate-fontset-menu)
- :help "Select a font from list of known fonts/fontsets"))
(define-key-after mule-menu-keymap [separator-mule]
'("--")
t)
t)
(define-key-after mule-menu-keymap [set-various-coding-system]
(list 'menu-item "Set Coding Systems" set-coding-system-map
- :enable 'enable-multibyte-characters))
+ :enable 'default-enable-multibyte-characters))
(define-key-after mule-menu-keymap [view-hello-file]
'(menu-item "Show Multi-lingual Text" view-hello-file
:enable (file-readable-p
(not (eq cmd 'universal-argument-other-key)))
(let ((current-prefix-arg prefix-arg)
;; Have to bind `last-command-char' here so that
- ;; `digit-argument', for isntance, can compute the
+ ;; `digit-argument', for instance, can compute the
;; prefix arg.
(last-command-char (aref keyseq 0)))
(call-interactively cmd)))
- ;; This is the final call to `univeral-argument-other-key', which
+ ;; This is the final call to `universal-argument-other-key', which
;; set's the final `prefix-arg.
(let ((current-prefix-arg prefix-arg))
(call-interactively cmd))
o default value for the command `set-keyboard-coding-system'."
(check-coding-system coding-system)
(setq-default buffer-file-coding-system coding-system)
- (if default-enable-multibyte-characters
+ (if (fboundp 'ucs-set-table-for-input)
+ (dolist (buffer (buffer-list))
+ (or (local-variable-p 'buffer-file-coding-system buffer)
+ (ucs-set-table-for-input buffer))))
+
+ (if (and default-enable-multibyte-characters (not (eq system-type 'darwin)))
+ ;; The file-name coding system on Darwin systems is always utf-8.
(setq default-file-name-coding-system coding-system))
;; If coding-system is nil, honor that on MS-DOS as well, so
;; that they could reset the terminal coding system.
non-nil, it is used to sort CODINGS in the different way than above."
(if sort-coding-systems-predicate
(sort codings sort-coding-systems-predicate)
- (let* ((most-preferred (symbol-value (car coding-category-list)))
+ (let* ((from-categories (mapcar #'(lambda (x) (symbol-value x))
+ coding-category-list))
+ (most-preferred (car from-categories))
(lang-preferred (get-language-info current-language-environment
'coding-system))
(func (function
(lambda (x)
(let ((base (coding-system-base x)))
- (+ (if (eq base most-preferred) 64 0)
- (let ((mime (coding-system-get base 'mime-charset)))
+ ;; We calculate the priority number 0..255 by
+ ;; using the 8 bits PMMLCEII as this:
+ ;; P: 1 iff most preferred.
+ ;; MM: greater than 0 iff mime-charset.
+ ;; L: 1 iff one of the current lang. env.'s codings.
+ ;; C: 1 iff one of codings listed in the category list.
+ ;; E: 1 iff not XXX-with-esc
+ ;; II: if iso-2022 based, 0..3, else 1.
+ (logior
+ (lsh (if (eq base most-preferred) 1 0) 7)
+ (lsh
+ (let ((mime (coding-system-get base 'mime-charset)))
;; Prefer coding systems corresponding to a
;; MIME charset.
(if mime
;; Lower utf-16 priority so that we
;; normally prefer utf-8 to it, and put
;; x-ctext below that.
- (cond ((or (eq base 'mule-utf-16-le)
- (eq base 'mule-utf-16-be))
- 16)
+ (cond ((string-match "utf-16"
+ (symbol-name mime))
+ 2)
((string-match "^x-" (symbol-name mime))
- 8)
- (t 32))
+ 1)
+ (t 3))
0))
- (if (memq base lang-preferred) 8 0)
- (if (string-match "-with-esc\\'" (symbol-name base))
- 0 4)
- (if (eq (coding-system-type base) 2)
- ;; For ISO based coding systems, prefer
- ;; one that doesn't use escape sequences.
- (let ((flags (coding-system-flags base)))
- (if (or (consp (aref flags 0))
- (consp (aref flags 1))
- (consp (aref flags 2))
- (consp (aref flags 3)))
- (if (or (aref flags 8) (aref flags 9))
- 0
- 1)
- 2))
- 1)))))))
+ 5)
+ (lsh (if (memq base lang-preferred) 1 0) 4)
+ (lsh (if (memq base from-categories) 1 0) 3)
+ (lsh (if (string-match "-with-esc\\'"
+ (symbol-name base))
+ 0 1) 2)
+ (if (eq (coding-system-type base) 2)
+ ;; For ISO based coding systems, prefer
+ ;; one that doesn't use escape sequences.
+ (let ((flags (coding-system-flags base)))
+ (if (or (consp (aref flags 0))
+ (consp (aref flags 1))
+ (consp (aref flags 2))
+ (consp (aref flags 3)))
+ (if (or (aref flags 8) (aref flags 9))
+ 0
+ 1)
+ 2))
+ 1)))))))
(sort codings (function (lambda (x y)
(> (funcall func x) (funcall func y))))))))
(defun find-coding-systems-for-charsets (charsets)
"Return a list of proper coding systems to encode characters of CHARSETS.
-CHARSETS is a list of character sets."
+CHARSETS is a list of character sets.
+It actually checks at most the first 96 characters of each charset.
+So, if a charset of dimension two is included in CHARSETS, the value may
+contain a coding system that can't encode all characters of the charset."
(cond ((or (null charsets)
(and (= (length charsets) 1)
(eq 'ascii (car charsets))))
'(raw-text emacs-mule))
(t
(let ((codings t)
- charset l ll)
+ charset l str)
(while (and codings charsets)
(setq charset (car charsets) charsets (cdr charsets))
(unless (eq charset 'ascii)
- (setq l (aref char-coding-system-table (make-char charset)))
+ (setq str (make-string 96 32))
+ (if (= (charset-dimension charset) 1)
+ (if (= (charset-chars charset) 96)
+ (dotimes (i 96)
+ (aset str i (make-char charset (+ i 32))))
+ (dotimes (i 94)
+ (aset str i (make-char charset (+ i 33)))))
+ (if (= (charset-chars charset) 96)
+ (dotimes (i 96)
+ (aset str i (make-char charset 32 (+ i 32))))
+ (dotimes (i 94)
+ (aset str i (make-char charset 33 (+ i 33))))))
+ (setq l (find-coding-systems-string str))
(if (eq codings t)
(setq codings l)
(let ((ll nil))
- (while codings
- (if (memq (car codings) l)
- (setq ll (cons (car codings) ll)))
- (setq codings (cdr codings)))
+ (dolist (elt codings)
+ (if (memq elt l)
+ (setq ll (cons elt ll))))
(setq codings ll)))))
- (append codings
- (char-table-extra-slot char-coding-system-table 0))))))
+ codings))))
(defun find-multibyte-characters (from to &optional maxcount excludes)
"Find multibyte characters in the region specified by FROM and TO.
where
CHARSET is a character set,
COUNT is a number of characters,
- CHARs are found characters of the character set.
+ CHARs are the characters found from the character set.
Optional 3rd arg MAXCOUNT limits how many CHARs are put in the above list.
Optional 4th arg EXCLUDE is a list of character sets to be ignored.
function `select-safe-coding-system' (which see). This variable
overrides that argument.")
+(defun select-safe-coding-system-interactively (from to codings unsafe
+ &optional rejected default)
+ "Select interactively a coding system for the region FROM ... TO.
+FROM can be a string, as in `write-region'.
+CODINGS is the list of base coding systems known to be safe for this region,
+ typically obtained with `find-coding-systems-region'.
+UNSAFE is a list of coding systems known to be unsafe for this region.
+REJECTED is a list of coding systems which were safe but for some reason
+ were not recommended in the particular context.
+DEFAULT is the coding system to use by default in the query."
+ ;; At first, if some defaults are unsafe, record at most 11
+ ;; problematic characters and their positions for them by turning
+ ;; (CODING ...)
+ ;; into
+ ;; ((CODING (POS . CHAR) (POS . CHAR) ...) ...)
+ (if unsafe
+ (setq unsafe
+ (mapcar #'(lambda (coding)
+ (cons coding
+ (if (stringp from)
+ (mapcar #'(lambda (pos)
+ (cons pos (aref from pos)))
+ (unencodable-char-position
+ 0 (length from) coding
+ 11 from))
+ (mapcar #'(lambda (pos)
+ (cons pos (char-after pos)))
+ (unencodable-char-position
+ from to coding 11)))))
+ unsafe)))
+
+ ;; Change each safe coding system to the corresponding
+ ;; mime-charset name if it is also a coding system. Such a name
+ ;; is more friendly to users.
+ (let ((l codings)
+ mime-charset)
+ (while l
+ (setq mime-charset (coding-system-get (car l) 'mime-charset))
+ (if (and mime-charset (coding-system-p mime-charset))
+ (setcar l mime-charset))
+ (setq l (cdr l))))
+
+ ;; Don't offer variations with locking shift, which you
+ ;; basically never want.
+ (let (l)
+ (dolist (elt codings (setq codings (nreverse l)))
+ (unless (or (eq 'coding-category-iso-7-else
+ (coding-system-category elt))
+ (eq 'coding-category-iso-8-else
+ (coding-system-category elt)))
+ (push elt l))))
+
+ ;; Remove raw-text, emacs-mule and no-conversion unless nothing
+ ;; else is available.
+ (setq codings
+ (or (delq 'raw-text
+ (delq 'emacs-mule
+ (delq 'no-conversion codings)))
+ '(raw-text emacs-mule no-conversion)))
+
+ (let ((window-configuration (current-window-configuration))
+ (bufname (buffer-name))
+ coding-system)
+ (save-excursion
+ ;; If some defaults are unsafe, make sure the offending
+ ;; buffer is displayed.
+ (when (and unsafe (not (stringp from)))
+ (pop-to-buffer bufname)
+ (goto-char (apply 'min (mapcar #'(lambda (x) (car (cadr x)))
+ unsafe))))
+ ;; Then ask users to select one from CODINGS while showing
+ ;; the reason why none of the defaults are not used.
+ (with-output-to-temp-buffer "*Warning*"
+ (with-current-buffer standard-output
+ (if (and (null rejected) (null unsafe))
+ (insert "No default coding systems to try for "
+ (if (stringp from)
+ (format "string \"%s\"." from)
+ (format "buffer `%s'." bufname)))
+ (insert
+ "These default coding systems were tried to encode"
+ (if (stringp from)
+ (concat " \"" (if (> (length from) 10)
+ (concat (substring from 0 10) "...\"")
+ (concat from "\"")))
+ (format " text\nin the buffer `%s'" bufname))
+ ":\n")
+ (let ((pos (point))
+ (fill-prefix " "))
+ (dolist (x (append rejected unsafe))
+ (princ " ") (princ (car x)))
+ (insert "\n")
+ (fill-region-as-paragraph pos (point)))
+ (when rejected
+ (insert "These safely encodes the target text,
+but it is not recommended for encoding text in this context,
+e.g., for sending an email message.\n ")
+ (dolist (x rejected)
+ (princ " ") (princ x))
+ (insert "\n"))
+ (when unsafe
+ (insert (if rejected "And the others"
+ "However, each of them")
+ " encountered these problematic characters:\n")
+ (dolist (coding unsafe)
+ (insert (format " %s:" (car coding)))
+ (let ((i 0)
+ (func1
+ #'(lambda (bufname pos)
+ (when (buffer-live-p (get-buffer bufname))
+ (pop-to-buffer bufname)
+ (goto-char pos))))
+ (func2
+ #'(lambda (bufname pos coding)
+ (when (buffer-live-p (get-buffer bufname))
+ (pop-to-buffer bufname)
+ (if (< (point) pos)
+ (goto-char pos)
+ (forward-char 1)
+ (search-unencodable-char coding)
+ (forward-char -1))))))
+ (dolist (elt (cdr coding))
+ (insert " ")
+ (if (stringp from)
+ (insert (if (< i 10) (cdr elt) "..."))
+ (if (< i 10)
+ (insert-text-button
+ (cdr elt)
+ :type 'help-xref
+ 'help-echo
+ "mouse-2, RET: jump to this character"
+ 'help-function func1
+ 'help-args (list bufname (car elt)))
+ (insert-text-button
+ "..."
+ :type 'help-xref
+ 'help-echo
+ "mouse-2, RET: next unencodable character"
+ 'help-function func2
+ 'help-args (list bufname (car elt)
+ (car coding)))))
+ (setq i (1+ i))))
+ (insert "\n"))
+ (insert "\
+The first problematic character is at point in the displayed buffer,\n"
+ (substitute-command-keys "\
+and \\[universal-argument] \\[what-cursor-position] will give information about it.\n"))))
+ (insert "\nSelect \
+one of the following safe coding systems, or edit the buffer:\n")
+ (let ((pos (point))
+ (fill-prefix " "))
+ (dolist (x codings)
+ (princ " ") (princ x))
+ (insert "\n")
+ (fill-region-as-paragraph pos (point)))
+ (insert "Or specify any other coding system
+at the risk of losing the problematic characters.\n")))
+
+ ;; Read a coding system.
+ (setq coding-system
+ (read-coding-system
+ (format "Select coding system (default %s): " default)
+ default))
+ (setq last-coding-system-specified coding-system))
+
+ (kill-buffer "*Warning*")
+ (set-window-configuration window-configuration)
+ coding-system))
+
(defun select-safe-coding-system (from to &optional default-coding-system
accept-default-p file)
"Ask a user to select a safe coding system from candidates.
between FROM and TO are shown in a popup window. Among them, the most
proper one is suggested as the default.
-The list of `buffer-file-coding-system' of the current buffer and the
+The list of `buffer-file-coding-system' of the current buffer,
+the `default-buffer-file-coding-system', and the
most preferred coding system (if it corresponds to a MIME charset) is
treated as the default coding system list. Among them, the first one
that safely encodes the text is normally selected silently and
list of coding systems to be prepended to the default coding system
list. However, if DEFAULT-CODING-SYSTEM is a list and the first
element is t, the cdr part is used as the defualt coding system list,
-i.e. `buffer-file-coding-system' and the most prepended coding system
-is not used.
+i.e. `buffer-file-coding-system', `default-buffer-file-coding-system',
+and the most preferred coding system are not used.
Optional 4th arg ACCEPT-DEFAULT-P, if non-nil, is a function to
determine the acceptability of the silently selected coding system.
(mapcar (function (lambda (x) (cons x (coding-system-base x))))
default-coding-system))
+ ;; From now on, the list of defaults is reversed.
+ (setq default-coding-system (nreverse default-coding-system))
+
(unless no-other-defaults
;; If buffer-file-coding-system is not nil nor undecided, append it
;; to the defaults.
(let ((base (coding-system-base buffer-file-coding-system)))
(or (eq base 'undecided)
(rassq base default-coding-system)
- (setq default-coding-system
- (append default-coding-system
- (list (cons buffer-file-coding-system base)))))))
+ (push (cons buffer-file-coding-system base)
+ default-coding-system))))
+
+ ;; If default-buffer-file-coding-system is not nil nor undecided,
+ ;; append it to the defaults.
+ (if default-buffer-file-coding-system
+ (let ((base (coding-system-base default-buffer-file-coding-system)))
+ (or (eq base 'undecided)
+ (rassq base default-coding-system)
+ (push (cons default-buffer-file-coding-system base)
+ default-coding-system))))
;; If the most preferred coding system has the property mime-charset,
;; append it to the defaults.
(let ((tail coding-category-list)
preferred base)
- (while (and tail
- (not (setq preferred (symbol-value (car tail)))))
+ (while (and tail (not (setq preferred (symbol-value (car tail)))))
(setq tail (cdr tail)))
(and (coding-system-p preferred)
(setq base (coding-system-base preferred))
(coding-system-get preferred 'mime-charset)
(not (rassq base default-coding-system))
- (setq default-coding-system
- (append default-coding-system
- (list (cons preferred base))))))))
+ (push (cons preferred base)
+ default-coding-system)))))
(if select-safe-coding-system-accept-default-p
(setq accept-default-p select-safe-coding-system-accept-default-p))
(let ((codings (find-coding-systems-region from to))
(coding-system nil)
- (bufname (buffer-name))
safe rejected unsafe)
(if (eq (car codings) 'undecided)
;; Any coding system is ok.
(push (car elt) safe))
(push (car elt) unsafe)))
(if safe
- (setq coding-system (car (last safe)))))
+ (setq coding-system (car safe))))
;; If all the defaults failed, ask a user.
(when (not coding-system)
- ;; At first, if some defaults are unsafe, record at most 11
- ;; problematic characters and their positions for them by turning
- ;; (CODING ...)
- ;; into
- ;; ((CODING (POS . CHAR) (POS . CHAR) ...) ...)
- (if unsafe
- (if (stringp from)
- (setq unsafe
- (mapcar #'(lambda (coding)
- (cons coding
- (mapcar #'(lambda (pos)
- (cons pos (aref from pos)))
- (unencodable-char-position
- 0 (length from) coding
- 11 from))))
- unsafe))
- (setq unsafe
- (mapcar #'(lambda (coding)
- (cons coding
- (mapcar #'(lambda (pos)
- (cons pos (char-after pos)))
- (unencodable-char-position
- from to coding 11))))
- unsafe))))
-
- ;; Change each safe coding system to the corresponding
- ;; mime-charset name if it is also a coding system. Such a name
- ;; is more friendly to users.
- (let ((l codings)
- mime-charset)
- (while l
- (setq mime-charset (coding-system-get (car l) 'mime-charset))
- (if (and mime-charset (coding-system-p mime-charset))
- (setcar l mime-charset))
- (setq l (cdr l))))
-
- ;; Don't offer variations with locking shift, which you
- ;; basically never want.
- (let (l)
- (dolist (elt codings (setq codings (nreverse l)))
- (unless (or (eq 'coding-category-iso-7-else
- (coding-system-category elt))
- (eq 'coding-category-iso-8-else
- (coding-system-category elt)))
- (push elt l))))
-
- ;; Remove raw-text, emacs-mule and no-conversion unless nothing
- ;; else is available.
- (setq codings
- (or (delq 'raw-text
- (delq 'emacs-mule
- (delq 'no-conversion codings)))
- '(raw-text emacs-mule no-conversion)))
-
- (let ((window-configuration (current-window-configuration)))
- (save-excursion
- ;; If some defaults are unsafe, make sure the offending
- ;; buffer is displayed.
- (when (and unsafe (not (stringp from)))
- (pop-to-buffer bufname)
- (goto-char (apply 'min (mapcar #'(lambda (x) (car (cadr x)))
- unsafe))))
- ;; Then ask users to select one from CODINGS while showing
- ;; the reason why none of the defaults are not used.
- (with-output-to-temp-buffer "*Warning*"
- (save-excursion
- (set-buffer standard-output)
- (if (not default-coding-system)
- (insert "No default coding systems to try for "
- (if (stringp from)
- (format "string \"%s\"." from)
- (format "buffer `%s'." bufname)))
- (insert
- "These default coding systems were tried to encode"
- (if (stringp from)
- (concat " \"" (if (> (length from) 10)
- (concat (substring from 0 10) "...\"")
- (concat from "\"")))
- (format " text\nin the buffer `%s'" bufname))
- ":\n")
- (let ((pos (point))
- (fill-prefix " "))
- (mapc #'(lambda (x) (princ " ") (princ (car x)))
- default-coding-system)
- (insert "\n")
- (fill-region-as-paragraph pos (point)))
- (when rejected
- (insert "These safely encodes the target text,
-but it is not recommended for encoding text in this context,
-e.g., for sending an email message.\n ")
- (mapc #'(lambda (x) (princ " ") (princ x)) rejected)
- (insert "\n"))
- (when unsafe
- (insert (if rejected "And the others"
- "However, each of them")
- " encountered these problematic characters:\n")
- (mapc
- #'(lambda (coding)
- (insert (format " %s:" (car coding)))
- (let ((i 0)
- (func1
- #'(lambda (bufname pos)
- (when (buffer-live-p (get-buffer bufname))
- (pop-to-buffer bufname)
- (goto-char pos))))
- (func2
- #'(lambda (bufname pos coding)
- (when (buffer-live-p (get-buffer bufname))
- (pop-to-buffer bufname)
- (if (< (point) pos)
- (goto-char pos)
- (forward-char 1)
- (search-unencodable-char coding)
- (forward-char -1))))))
- (dolist (elt (cdr coding))
- (insert " ")
- (if (stringp from)
- (insert (if (< i 10) (cdr elt) "..."))
- (if (< i 10)
- (insert-text-button
- (cdr elt)
- :type 'help-xref
- 'help-echo
- "mouse-2, RET: jump to this character"
- 'help-function func1
- 'help-args (list bufname (car elt)))
- (insert-text-button
- "..."
- :type 'help-xref
- 'help-echo
- "mouse-2, RET: next unencodable character"
- 'help-function func2
- 'help-args (list bufname (car elt)
- (car coding)))))
- (setq i (1+ i))))
- (insert "\n"))
- unsafe)
- (insert "\
-The first problematic character is at point in the displayed buffer,\n"
- (substitute-command-keys "\
-and \\[universal-argument] \\[what-cursor-position] will give information about it.\n"))))
- (insert (if safe
- "\nSelect the above, or "
- "\nSelect ")
- "\
-one of the following safe coding systems, or edit the buffer:\n")
- (let ((pos (point))
- (fill-prefix " "))
- (mapcar (function (lambda (x) (princ " ") (princ x)))
- codings)
- (insert "\n")
- (fill-region-as-paragraph pos (point)))
- (insert "Or specify any other coding system
-on your risk of losing the problematic characters.\n")))
-
- ;; Read a coding system.
- (setq default-coding-system (or (car safe) (car codings)))
- (setq coding-system
- (read-coding-system
- (format "Select coding system (default %s): "
- default-coding-system)
- default-coding-system))
- (setq last-coding-system-specified coding-system))
-
- (kill-buffer "*Warning*")
- (set-window-configuration window-configuration)))
+ (setq coding-system (select-safe-coding-system-interactively
+ from to codings unsafe rejected (car codings))))
(if (vectorp (coding-system-eol-type coding-system))
(let ((eol (coding-system-eol-type buffer-file-coding-system)))
(goto-char (point-min))
(set-auto-coding (or file buffer-file-name "")
(buffer-size))))))
- (if (and auto-cs coding-system
+ ;; Merge coding-system and auto-cs as far as possible.
+ (if (not coding-system)
+ (setq coding-system auto-cs)
+ (if (not auto-cs)
+ (setq auto-cs coding-system)
+ (let ((eol-type-1 (coding-system-eol-type coding-system))
+ (eol-type-2 (coding-system-eol-type auto-cs)))
+ (if (eq (coding-system-base coding-system) 'undecided)
+ (setq coding-system (coding-system-change-text-conversion
+ coding-system auto-cs))
+ (if (eq (coding-system-base auto-cs) 'undecided)
+ (setq auto-cs (coding-system-change-text-conversion
+ auto-cs coding-system))))
+ (if (vectorp eol-type-1)
+ (or (vectorp eol-type-2)
+ (setq coding-system (coding-system-change-eol-conversion
+ coding-system eol-type-2)))
+ (if (vectorp eol-type-2)
+ (setq auto-cs (coding-system-change-eol-conversion
+ auto-cs eol-type-1)))))))
+
+ (if (and auto-cs
;; Don't barf if writing a compressed file, say.
;; This check perhaps isn't ideal, but is probably
;; the best thing to do.
(not (auto-coding-alist-lookup (or file buffer-file-name "")))
- (not (coding-system-equal (coding-system-base coding-system)
- (coding-system-base auto-cs))))
+ (not (coding-system-equal coding-system auto-cs)))
(unless (yes-or-no-p
(format "Selected encoding %s disagrees with \
%s specified by file contents. Really save (else edit coding cookies \
environment.
features value is a list of features requested in this
language environment.
+ ctext-non-standard-encodings
+ value is a list of non-standard encoding
+ names used in extended segments of CTEXT.
+ See the variable
+ `ctext-non-standard-encodings' for more
+ detail.
The following keys take effect only when multibyte characters are
globally disabled, i.e. the value of `default-enable-multibyte-characters'
see `language-info-alist'."
(if (symbolp lang-env)
(setq lang-env (symbol-name lang-env)))
- (let ((lang-slot (assoc-ignore-case lang-env language-info-alist)))
+ (let ((lang-slot (assoc-string lang-env language-info-alist t)))
(if lang-slot
(cdr (assq key (cdr lang-slot))))))
"*Default input method for multilingual text (a string).
This is the input method activated automatically by the command
`toggle-input-method' (\\[toggle-input-method])."
+ :link '(custom-manual "(emacs)Input Methods")
:group 'mule
- :type '(choice (const nil) string)
+ :type '(choice (const nil) (string
+ :completion-ignore-case t
+ :complete-function widget-string-complete
+ :completion-alist input-method-alist
+ :prompt-history input-method-history))
:set-after '(current-language-environment))
(put 'input-method-function 'permanent-local t)
current-input-method-title nil)
(force-mode-line-update)))))
-(defun set-input-method (input-method)
+(defun set-input-method (input-method &optional interactive)
"Select and activate input method INPUT-METHOD for the current buffer.
This also sets the default input method to the one you specify.
If INPUT-METHOD is nil, this function turns off the input method, and
also causes you to be prompted for a name of an input method the next
time you invoke \\[toggle-input-method].
+When called interactively, the optional arg INTERACTIVE is non-nil,
+which marks the variable `default-input-method' as set for Custom buffers.
To deactivate the input method interactively, use \\[toggle-input-method].
To deactivate it programmatically, use \\[inactivate-input-method]."
(let* ((default (or (car input-method-history) default-input-method)))
(list (read-input-method-name
(if default "Select input method (default %s): " "Select input method: ")
- default t))))
+ default t)
+ t)))
(activate-input-method input-method)
(setq default-input-method input-method)
- (when (interactive-p)
+ (when interactive
(customize-mark-as-set 'default-input-method))
default-input-method)
-(defun toggle-input-method (&optional arg)
+(defun toggle-input-method (&optional arg interactive)
"Enable or disable multilingual text input method for the current buffer.
Only one input method can be enabled at any time in a given buffer.
With a prefix argument, read an input method name with the minibuffer
and enable that one. The default is the most recent input method specified
-\(not including the currently active input method, if any)."
+\(not including the currently active input method, if any).
- (interactive "P")
+When called interactively, the optional arg INTERACTIVE is non-nil,
+which marks the variable `default-input-method' as set for Custom buffers."
+
+ (interactive "P\np")
(if (and current-input-method (not arg))
(inactivate-input-method)
(let ((default (or (car input-method-history) default-input-method)))
(unless default-input-method
(prog1
(setq default-input-method current-input-method)
- (when (interactive-p)
+ (when interactive
(customize-mark-as-set 'default-input-method)))))))
(defun describe-input-method (input-method)
:link '(custom-manual "(emacs)Language Environments")
:set (lambda (symbol value) (set-language-environment value))
:get (lambda (x)
- (or (car-safe (assoc-ignore-case
+ (or (car-safe (assoc-string
(if (symbolp current-language-environment)
(symbol-name current-language-environment)
current-language-environment)
- language-info-alist))
+ language-info-alist t))
"English"))
;; custom type will be updated with `set-language-info'.
:type (if language-info-alist
bound to each category are as follows
coding category coding system
--------------------------------------------------
- coding-category-iso-8-2 iso-latin-1
coding-category-iso-8-1 iso-latin-1
+ coding-category-iso-8-2 iso-latin-1
+ coding-category-utf-8 mule-utf-8
+ coding-category-utf-16-be mule-utf-16be-with-signature
+ coding-category-utf-16-le mule-utf-16le-with-signature
coding-category-iso-7-tight iso-2022-jp
coding-category-iso-7 iso-2022-7bit
coding-category-iso-7-else iso-2022-7bit-lock
coding-category-sjis japanese-shift-jis
coding-category-big5 chinese-big5
coding-category-ccl nil
- coding-category-binary no-conversion
- coding-category-utf-16-be nil
- coding-category-utf-16-le nil
- coding-category-utf-8 mule-utf-8"
+ coding-category-binary no-conversion"
(interactive)
;; This function formerly set default-enable-multibyte-characters to t,
;; but that is incorrect. It should not alter the unibyte/multibyte choice.
coding-category-raw-text 'raw-text
coding-category-sjis 'japanese-shift-jis
coding-category-big5 'chinese-big5
- coding-category-utf-16-be nil
- coding-category-utf-16-le nil
+ coding-category-utf-16-be 'mule-utf-16be-with-signature
+ coding-category-utf-16-le 'mule-utf-16le-with-signature
coding-category-utf-8 'mule-utf-8
coding-category-ccl nil
coding-category-binary 'no-conversion)
(set-coding-priority
'(coding-category-iso-8-1
coding-category-iso-8-2
+ coding-category-utf-8
+ coding-category-utf-16-be
+ coding-category-utf-16-le
coding-category-iso-7-tight
coding-category-iso-7
coding-category-iso-7-else
coding-category-sjis
coding-category-big5
coding-category-ccl
- coding-category-binary
- coding-category-utf-16-be
- coding-category-utf-16-le
- coding-category-utf-8))
+ coding-category-binary))
(update-coding-systems-internal)
(set-default-coding-systems nil)
(setq default-sendmail-coding-system 'iso-latin-1)
+ ;; On Darwin systems, this should be utf-8, but when this file is loaded
+ ;; utf-8 is not yet defined, so we set it in set-locale-environment instead.
+ (setq default-file-name-coding-system 'iso-latin-1)
;; Preserve eol-type from existing default-process-coding-systems.
;; On non-unix-like systems in particular, these may have been set
;; carefully by the user, or by the startup code, to deal with the
;; (set-keyboard-coding-system-internal nil)
(setq nonascii-translation-table nil
- nonascii-insert-offset 0))
+ nonascii-insert-offset 0)
+
+ ;; Don't invoke fontset-related functions if fontsets aren't
+ ;; supported in this build of Emacs.
+ (and (fboundp 'fontset-list)
+ (set-overriding-fontspec-internal nil)))
(reset-language-environment)
(let ((coding (get-language-info language-name 'unibyte-display)))
(if coding
(standard-display-european-internal)
- (standard-display-default (if (eq window-system 'pc) 128 160) 255)
- (aset standard-display-table 146 nil))
+ ;; The following 2 lines undo the 8-bit display that we set up
+ ;; in standard-display-european-internal, which see. This is in
+ ;; case the user has used standard-display-european earlier in
+ ;; this session. (The MS-DOS port doesn't use that setup, so it
+ ;; doesn't need to undo it.)
+ (when standard-display-table
+ (dotimes (i 128)
+ (aset standard-display-table (+ i 128) nil))))
(or (eq window-system 'pc)
- (set-terminal-coding-system coding))))
+ (set-terminal-coding-system coding))))
(defun set-language-environment (language-name)
"Set up multi-lingual environment for using LANGUAGE-NAME.
(if (symbolp language-name)
(setq language-name (symbol-name language-name)))
(setq language-name "English"))
- (or (assoc-ignore-case language-name language-info-alist)
+ (let ((slot (assoc-string language-name language-info-alist t)))
+ (unless slot
(error "Language environment not defined: %S" language-name))
+ (setq language-name (car slot)))
(if current-language-environment
(let ((func (get-language-info current-language-environment
'exit-function)))
(while required-features
(require (car required-features))
(setq required-features (cdr required-features))))
+
+ ;; Don't invoke fontset-related functions if fontsets aren't
+ ;; supported in this build of Emacs.
+ (when (fboundp 'fontset-list)
+ (let ((overriding-fontspec (get-language-info language-name
+ 'overriding-fontspec)))
+ (if overriding-fontspec
+ (set-overriding-fontspec-internal overriding-fontspec))))
+
(let ((func (get-language-info language-name 'setup-function)))
(if (functionp func)
(funcall func)))
+ (if (and utf-translate-cjk-mode
+ utf-translate-cjk-lang-env
+ (not (eq utf-translate-cjk-lang-env language-name))
+ (catch 'tag
+ (dolist (charset (get-language-info language-name 'charset))
+ (if (memq charset utf-translate-cjk-charsets)
+ (throw 'tag t)))
+ nil))
+ (utf-translate-cjk-load-tables))
(run-hooks 'set-language-environment-hook)
(force-mode-line-update t))
;; different there.
(or (and (eq window-system 'pc) (not default-enable-multibyte-characters))
(progn
- ;; Make non-line-break space display as a plain space.
- ;; Most X fonts do the wrong thing for code 160.
- (aset standard-display-table 160 [32])
- ;; With luck, non-Latin-1 fonts are more recent and so don't
- ;; have this bug.
- (aset standard-display-table 2208 [32]) ; Latin-1 NBSP
+ ;; Most X fonts used to do the wrong thing for latin-1 code 160.
+ (unless (and (eq window-system 'x)
+ ;; XFree86 4 has fixed the fonts.
+ (string= "The XFree86 Project, Inc" (x-server-vendor))
+ (> (aref (number-to-string (nth 2 (x-server-version))) 0)
+ ?3))
+ ;; Make non-line-break space display as a plain space.
+ (aset standard-display-table 160 [32]))
;; Most Windows programs send out apostrophes as \222. Most X fonts
;; don't contain a character at that position. Map it to the ASCII
;; apostrophe. [This is actually RIGHT SINGLE QUOTATION MARK,
(put 'describe-specified-language-support 'apropos-inhibit t)
-;; Print a language specific information such as input methods,
+;; Print language-specific information such as input methods,
;; charsets, and coding systems. This function is intended to be
;; called from the menu:
;; [menu-bar mule describe-language-environment LANGUAGE]
(error "No documentation for the specified language"))
(if (symbolp language-name)
(setq language-name (symbol-name language-name)))
- (let ((doc (get-language-info language-name 'documentation))
- pos)
+ (dolist (feature (get-language-info language-name 'features))
+ (require feature))
+ (let ((doc (get-language-info language-name 'documentation)))
(help-setup-xref (list #'describe-language-environment language-name)
(interactive-p))
(with-output-to-temp-buffer (help-buffer)
;; http://www.din.de/gremien/nas/nabd/iso3166ma/codlstp1/en_listp1.html.
;; CODESET and MODIFIER are implementation-dependent.
+ ;; jasonr comments: MS Windows uses three letter codes for
+ ;; languages instead of the two letter ISO codes that POSIX
+ ;; uses. In most cases the first two letters are the same, so
+ ;; most of the regexps in locale-language-names work. Japanese
+ ;; and Chinese are exceptions, which are listed in the
+ ;; non-standard section at the bottom of locale-language-names.
+
; aa Afar
; ab Abkhazian
("af" . "Latin-1") ; Afrikaans
(".*8859[-_]?9\\>" . "Latin-5")
(".*8859[-_]?14\\>" . "Latin-8")
(".*8859[-_]?15\\>" . "Latin-9")
- (".*utf\\(-?8\\)\\>" . "UTF-8")
+ (".*utf\\(?:-?8\\)?\\>" . "UTF-8")
;; utf-8@euro exists, so put this last. (@euro really specifies
;; the currency, rather than the charset.)
(".*@euro\\>" . "Latin-9")))
"List of pairs of locale regexps and charset language names.
The first element whose locale regexp matches the start of a downcased locale
-specifies the language name whose charsets corresponds to that locale.
+specifies the language name whose charset corresponds to that locale.
This language name is used if its charsets disagree with the charsets of
the language name that would otherwise be used for this locale.")
(setq alist (cdr alist)))
(cdr element)))
+(defun locale-charset-match-p (charset1 charset2)
+ "Whether charset names (strings) CHARSET1 and CHARSET2 are equivalent.
+Matching is done ignoring case and any hyphens and underscores in the
+names. E.g. `ISO_8859-1' and `iso88591' both match `iso-8859-1'."
+ (setq charset1 (replace-regexp-in-string "[-_]" "" charset1))
+ (setq charset2 (replace-regexp-in-string "[-_]" "" charset2))
+ (eq t (compare-strings charset1 nil nil charset2 nil nil t)))
+
+(defvar locale-charset-alist nil
+ "Coding system alist keyed on locale-style charset name.
+Used by `locale-charset-to-coding-system'.")
+
+(defun locale-charset-to-coding-system (charset)
+ "Find coding system corresponding to CHARSET.
+CHARSET is any sort of non-Emacs charset name, such as might be used
+in a locale codeset, or elsewhere. It is matched to a coding system
+first by case-insensitive lookup in `locale-charset-alist'. Then
+matches are looked for in the coding system list, treating case and
+the characters `-' and `_' as insignificant. The coding system base
+is returned. Thus, for instance, if charset \"ISO8859-2\",
+`iso-latin-2' is returned."
+ (or (car (assoc-string charset locale-charset-alist t))
+ (let ((cs coding-system-alist)
+ c)
+ (while (and (not c) cs)
+ (if (locale-charset-match-p charset (caar cs))
+ (setq c (intern (caar cs)))
+ (pop cs)))
+ (if c (coding-system-base c)))))
+
+;; Fixme: This ought to deal with the territory part of the locale
+;; too, for setting things such as calendar holidays, ps-print paper
+;; size, spelling dictionary.
+
(defun set-locale-environment (&optional locale-name)
"Set up multi-lingual environment for using LOCALE-NAME.
This sets the language environment, the coding system priority,
the default input method and sometimes other things.
-LOCALE-NAME should be a string
-which is the name of a locale supported by the system;
-often it is of the form xx_XX.CODE, where xx is a language,
-XX is a country, and CODE specifies a character set and coding system.
-For example, the locale name \"ja_JP.EUC\" might name a locale
-for Japanese in Japan using the `japanese-iso-8bit' coding-system.
+LOCALE-NAME should be a string which is the name of a locale supported
+by the system. Often it is of the form xx_XX.CODE, where xx is a
+language, XX is a country, and CODE specifies a character set and
+coding system. For example, the locale name \"ja_JP.EUC\" might name
+a locale for Japanese in Japan using the `japanese-iso-8bit'
+coding-system. The name may also have a modifier suffix, e.g. `@euro'
+or `@cyrillic'.
If LOCALE-NAME is nil, its value is taken from the environment
variables LC_ALL, LC_CTYPE and LANG (the first one that is set).
(setq locale-translation-file-name
(let ((files
'("/usr/lib/X11/locale/locale.alias" ; e.g. X11R6.4
- "/usr/X11R6/lib/X11/locale/locale.alias" ; e.g. RedHat 4.2
+ "/usr/X11R6/lib/X11/locale/locale.alias" ; XFree86, e.g. RedHat 4.2
"/usr/openwin/lib/locale/locale.alias" ; e.g. Solaris 2.6
;;
;; The following name appears after the X-related names above,
(charset-language-name
(locale-name-match locale locale-charset-language-names))
(coding-system
- (locale-name-match locale locale-preferred-coding-systems)))
+ (or (locale-name-match locale locale-preferred-coding-systems)
+ (when locale
+ (if (string-match "\\.\\([^@]+\\)" locale)
+ (locale-charset-to-coding-system
+ (match-string 1 locale)))))))
;; Give preference to charset-language-name over language-name.
(if (and charset-language-name
(prefer-coding-system coding-system)
(setq locale-coding-system coding-system))))
+ ;; On Windows, override locale-coding-system, keyboard-coding-system,
+ ;; selection-coding-system with system codepage.
+ (when (boundp 'w32-ansi-code-page)
+ (let ((code-page-coding (intern (format "cp%d" w32-ansi-code-page))))
+ (when (coding-system-p code-page-coding)
+ (setq locale-coding-system code-page-coding)
+ (set-selection-coding-system code-page-coding)
+ (set-keyboard-coding-system code-page-coding)
+ (set-terminal-coding-system code-page-coding))))
+
+ ;; On Darwin, file names are always encoded in utf-8, no matter the locale.
+ (when (eq system-type 'darwin)
+ (setq default-file-name-coding-system 'utf-8))
+
;; Default to A4 paper if we're not in a C, POSIX or US locale.
- ;; (See comments in Flanginfo.)
+ ;; (See comments in Flocale_info.)
(let ((locale locale)
- (paper (langinfo 'paper)))
+ (paper (locale-info 'paper)))
(if paper
;; This will always be null at the time of writing.
(cond
("posix$" . letter)
(".._us" . letter)
(".._pr" . letter)
- (".._ca" . letter)))
+ (".._ca" . letter)
+ ("enu$" . letter) ; Windows
+ ("esu$" . letter)
+ ("enc$" . letter)
+ ("frc$" . letter)))
'a4))))))
nil)
\f
(if (and coding-system (eq (coding-system-type coding-system) 2))
;; Try to get a pretty description for ISO 2022 escape sequences.
(function (lambda (x) (or (cdr (assq x iso-2022-control-alist))
- (format "%02X" x))))
+ (format "0x%02X" x))))
(function (lambda (x) (format "0x%02X" x))))
str " "))
(and safe-chars (aref safe-chars char)))
;; We must find the encoded string of CHAR. But, just encoding
;; CHAR will put extra control sequences (usually to designate
- ;; ASCII charaset) at the tail if type of CODING is ISO 2022.
+ ;; ASCII charset) at the tail if type of CODING is ISO 2022.
;; To exclude such tailing bytes, we at first encode one-char
;; string and two-char string, then check how many bytes at the
;; tail of both encoded strings are the same.
(substring enc2 0 i2))))
+;; arch-tag: b382c432-4b36-460e-bf4c-05efd0bb18dc
;;; mule-cmds.el ends here