| blob | f02c470c8b58980274f50aa66f2e228364e7da25 |
1 ;;; mule-cmds.el --- Commands for mulitilingual environment
3 ;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
4 ;; Licensed to the Free Software Foundation.
5 ;; Copyright (C) 2000 Free Software Foundation, Inc.
7 ;; Keywords: mule, multilingual
9 ;; This file is part of GNU Emacs.
11 ;; GNU Emacs is free software; you can redistribute it and/or modify
12 ;; it under the terms of the GNU General Public License as published by
13 ;; the Free Software Foundation; either version 2, or (at your option)
14 ;; any later version.
16 ;; GNU Emacs is distributed in the hope that it will be useful,
17 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
18 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
19 ;; GNU General Public License for more details.
21 ;; You should have received a copy of the GNU General Public License
22 ;; along with GNU Emacs; see the file COPYING. If not, write to the
23 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
24 ;; Boston, MA 02111-1307, USA.
26 ;;; Code:
30 ;;; MULE related key bindings and menus.
35 ;; Keep "C-x C-m ..." for mule specific commands.
77 t)
80 t)
83 t)
88 t)
97 t)
100 t)
103 describe-language-environment-map
105 t)
109 t)
112 t)
119 t)
124 t)
128 t)
133 t)
137 t)
143 t)
148 t)
153 t)
155 [Default] '(menu-item "Default" setup-specified-language-environment))
157 (define-key describe-language-environment-map
160 ;; This should be a single character key binding because users use it
161 ;; very frequently while editing multilingual text. Now we can use
162 ;; only two such keys: "\C-\\" and "\C-^", but the latter is not
163 ;; convenient because it requires shifting on most keyboards. An
164 ;; alternative is "\C-\]" which is now bound to `abort-recursive-edit'
165 ;; but it won't be used that frequently.
168 ;;; This is no good because people often type Shift-SPC
169 ;;; meaning to type SPC. -- rms.
170 ;;; ;; Here's an alternative key binding for X users (Shift-SPACE).
171 ;;; (define-key global-map [?\S- ] 'toggle-input-method)
173 ;;; Mule related hyperlinks.
181 ;; Note starting with word-syntax character:
185 "Return a coding system which differs from CODING-SYSTEM in eol conversion.
186 The returned coding system converts end-of-line by EOL-TYPE
187 but text as the same way as CODING-SYSTEM.
188 EOL-TYPE should be `unix', `dos', `mac', or nil.
189 If EOL-TYPE is nil, the returned coding system detects
190 how end-of-line is formatted automatically while decoding.
192 EOL-TYPE can be specified by an integer 0, 1, or 2.
193 They means `unix', `dos', and `mac' respectively."
202 coding-system
206 base
208 coding-system
214 "Return a coding system which differs from CODING-SYSTEM in text conversion.
215 The returned coding system converts text by CODING
216 but end-of-line as the same way as CODING-SYSTEM.
217 If CODING is nil, the returned coding system detects
218 how text is formatted automatically while decoding."
223 coding
227 "Change whether this buffer uses multibyte characters.
228 With arg, use multibyte characters if the arg is positive.
230 Note that this command does not convert the byte contents of
231 the buffer; it only changes the way those bytes are interpreted.
232 In general, therefore, this command *changes* the sequence of
233 characters that the current buffer contains.
235 We suggest you avoid using use this command unless you know what you
236 are doing. If you use it by mistake, and the buffer is now displayed
237 wrong, use this command again to toggle back to the right mode."
246 "Display the HELLO file which list up many languages and characters."
248 ;; We have to decode the file in any environment.
254 "Execute an I/O command using the specified coding system."
258 t))
259 buffer-file-coding-system))
264 default))
274 "Set default value of various coding systems to CODING-SYSTEM.
275 This sets the following coding systems:
276 o coding system of a newly created buffer
277 o default coding system for subprocess I/O
278 This also sets the following values:
279 o default value used as file-name-coding-system for converting file names.
280 o default value for the command `set-terminal-coding-system' (not on MSDOS)
281 o default value for the command `set-keyboard-coding-system'."
286 ;; If coding-system is nil, honor that on MS-DOS as well, so
287 ;; that they could reset the terminal coding system.
297 "Add CODING-SYSTEM at the front of the priority list for automatic detection.
298 This also sets the following coding systems:
299 o coding system of a newly created buffer
300 o default coding system for subprocess I/O
301 This also sets the following values:
302 o default value used as file-name-coding-system for converting file names.
303 o default value for the command `set-terminal-coding-system' (not on MSDOS)
304 o default value for the command `set-keyboard-coding-system'
306 If CODING-SYSTEM specifies a certain type of EOL conversion, the coding
307 systems set by this function will use that type of EOL conversion.
309 This command does not change the default value of terminal coding system
310 for MS-DOS terminal, because DOS terminals only support a single coding
311 system, and Emacs automatically sets the default to that coding system at
312 startup."
320 ;; CODING-SYSTEM is no-conversion or undecided.
325 ;; We must change the order.
329 base coding-system))
330 ;; If they asked for specific EOL conversion, honor that.
338 "If non-nil, a predicate function to sort coding systems.
340 It is called with two coding systems, and should return t if the first
346 "Sort coding system list CODINGS by a priority of each coding system.
348 If a coding system is most preferred, it has the highest priority.
349 Otherwise, a coding system corresponds to some MIME charset has higher
350 priorities. Among them, a coding system included in `coding-system'
351 key of the current language environment has higher priorities. See
352 also the documentation of `language-info-alist'.
354 If the variable `sort-coding-systems-predicate' (which see) is
355 non-nil, it is used to sort CODINGS in the different way than above."
374 ;; For ISO based coding systems, prefer
375 ;; one that doesn't use escape sequences.
382 0
390 "Return a list of proper coding systems to encode a text between FROM and TO.
391 All coding systems in the list can safely encode any multibyte characters
392 in the text.
394 If the text contains no multibyte characters, return a list of a single
395 element `undecided'."
398 ;; The text contains only ASCII characters. Any coding
399 ;; systems are safe.
401 ;; We need copy-sequence because sorting will alter the argument.
405 "Return a list of proper coding systems to encode STRING.
406 All coding systems in the list can safely encode any multibyte characters
407 in STRING.
409 If STRING contains no multibyte characters, return a list of a single
410 element `undecided'."
414 "Return a list of proper coding systems to encode characters of CHARSETS.
415 CHARSETS is a list of character sets."
425 charset l ll)
442 "Find multibyte characters in the region specified by FROM and TO.
443 If FROM is a string, find multibyte characters in the string.
444 The return value is an alist of the following format:
445 ((CHARSET COUNT CHAR ...) ...)
446 where
447 CHARSET is a character set,
448 COUNT is a number of characters,
449 CHARs are found characters of the character set.
450 Optional 3rd arg MAXCOUNT limits how many CHARs are put in the above list.
451 Optional 4th arg EXCLUDE is a list of character sets to be ignored.
453 For invalid characters, CHARs are actually strings."
455 charset char)
464 eight-bit-control eight-bit-graphic))
495 "Most recent coding system explicitly specified by the user when asked.
496 This variable is set whenever Emacs asks the user which coding system
497 to use in order to write a file. If you set it to nil explicitly,
498 then call `write-region', then afterward this variable will be non-nil
502 "If non-nil, a function to control the behaviour of coding system selection.
503 The meaning is the same as the argument ACCEPT-DEFAULT-P of the
504 function `select-safe-coding-system' (which see). This variable
508 accept-default-p)
509 "Ask a user to select a safe coding system from candidates.
510 The candidates of coding systems which can safely encode a text
511 between FROM and TO are shown in a popup window. Among them, the most
512 proper one is suggested as the default.
514 The list of `buffer-file-coding-system' of the current buffer and the
515 most preferred coding system (if it corresponds to a MIME charset) is
516 treated as the default coding system list. Among them, the first one
517 that safely encodes the text is silently selected and returned without
518 any user interaction. See also the command `prefer-coding-system'.
520 Optional 3rd arg DEFAULT-CODING-SYSTEM specifies a coding system or a
521 list of coding systems to be prepended to the default coding system
522 list.
524 Optional 4th arg ACCEPT-DEFAULT-P, if non-nil, is a function to
525 determine the acceptability of the silently selected coding system.
526 It is called with that coding system, and should return nil if it
527 should not be silently selected and thus user interaction is required.
529 The variable `select-safe-coding-system-accept-default-p', if
530 non-nil, overrides ACCEPT-DEFAULT-P.
532 Kludgy feature: if FROM is a string, the string is the target text,
533 and TO is ignored."
538 ;; Change elements of the list to (coding . base-coding).
541 default-coding-system))
543 ;; If buffer-file-coding-system is not nil nor undecided, append it
544 ;; to the defaults.
554 ;; If the most preferred coding system has the property mime-charset,
555 ;; append it to the defaults.
571 ;; Any coding system is ok.
573 ;; Try the defaults.
582 ;; If all the defaults failed, ask a user.
584 ;; At first, change each coding system to the corresponding
585 ;; mime-charset name if it is also a coding system. Such a name
586 ;; is more friendly to users.
588 mime-charset)
595 ;; Then ask users to select one form CODINGS.
606 from)
612 default-coding-system)
629 codings)
633 ;; Read a coding system.
637 codings))
641 safe-names nil t nil nil
644 coding-system last-coding-system-specified)))
655 coding-system))
660 "Return a coding system to encode the outgoing message of the current buffer.
661 It at first tries the first coding system found in these variables
662 in this order:
663 (1) local value of `buffer-file-coding-system'
664 (2) value of `sendmail-coding-system'
665 (3) value of `default-sendmail-coding-system'
666 (4) value of `default-buffer-file-coding-system'
667 If the found coding system can't encode the current buffer,
668 or none of them are bound to a coding system,
669 it asks the user to select a proper coding system."
671 buffer-file-coding-system)
672 sendmail-coding-system
673 default-sendmail-coding-system
674 default-buffer-file-coding-system)))
676 ;; We should never use no-conversion for outgoing mails.
682 coding)))
683 \f
684 ;;; Language support stuff.
687 "Alist of language environment definitions.
688 Each element looks like:
689 (LANGUAGE-NAME . ((KEY . INFO) ...))
690 where LANGUAGE-NAME is a string, the name of the language environment,
691 KEY is a symbol denoting the kind of information, and
692 INFO is the data associated with KEY.
693 Meaningful values for KEY include
695 documentation value is documentation of what this language environment
696 is meant for, and how to use it.
697 charset value is a list of the character sets used by this
698 language environment.
699 sample-text value is one line of text,
700 written using those character sets,
701 appropriate for this language environment.
702 setup-function value is a function to call to switch to this
703 language environment.
704 exit-function value is a function to call to leave this
705 language environment.
706 coding-system value is a list of coding systems that are good
707 for saving text written in this language environment.
708 This list serves as suggestions to the user;
709 in effect, as a kind of documentation.
710 coding-priority value is a list of coding systems for this language
711 environment, in order of decreasing priority.
712 This is used to set up the coding system priority
713 list when you switch to this language environment.
714 nonascii-translation
715 value is a translation table to be set in the
716 variable `nonascii-translation-table' in this
717 language environment, or a character set from
718 which `nonascii-insert-offset' is calculated.
719 input-method value is a default input method for this language
720 environment.
721 features value is a list of features requested in this
722 language environment.
724 The following keys take effect only when multibyte characters are
725 globally disabled, i.e. the value of `default-enable-multibyte-characters'
726 is nil.
728 unibyte-syntax value is a library name to load to set
729 unibyte 8-bit character syntaxes for this
730 language environment.
732 unibyte-display value is a coding system to encode characters
733 for the terminal. Characters in the range
734 of 160 to 255 display not as octal escapes,
735 but as non-ASCII characters in this language
739 "Return information listed under KEY for language environment LANG-ENV.
740 KEY is a symbol denoting the kind of information.
741 For a list of useful values for KEY and their meanings,
742 see `language-info-alist'."
750 "Modify part of the definition of language environment LANG-ENV.
751 Specifically, this stores the information INFO under KEY
752 in the definition of this language environment.
753 KEY is a symbol denoting the kind of information.
754 INFO is the value for that information.
756 For a list of useful values for KEY and their meanings,
757 see `language-info-alist'."
773 "Store ALIST as the definition of language environment LANG-ENV.
774 ALIST is an alist of KEY and INFO values. See the documentation of
775 `language-info-alist' for the meanings of KEY and INFO.
777 Optional arg PARENTS is a list of parent menu names; it specifies
778 where to put this language environment in the
779 Describe Language Environment and Set Language Environment menus.
781 in the European submenu in each of those two menus."
788 map parent-symbol parent prompt)
794 ;; This prompt string is for define-prefix-command, so
795 ;; that the map it creates will be suitable for a menu.
816 ;; Set up menu items for this language env.
829 "Read a language environment name which has information for KEY.
830 If KEY is nil, read any language environment.
831 Prompt with PROMPT. DEFAULT is the default choice of language environment.
832 This returns a language environment name as a string."
835 language-info-alist
838 t nil nil default)))
842 name)))
843 \f
844 ;;; Multilingual input methods.
846 "LEIM: Libraries of Emacs Input Methods."
850 "Name of LEIM list file.
851 This file contains a list of libraries of Emacs input methods (LEIM)
852 in the format of Lisp expression for registering each input method.
856 ";;; %s -- list of LEIM (Library of Emacs Input Method)
857 ;;
858 ;; This file contains a list of LEIM (Library of Emacs Input Method)
859 ;; in the same directory as this file. Loading this file registers
860 ;; the whole input methods in Emacs.
861 ;;
862 ;; Each entry has the form:
863 ;; (register-input-method
864 ;; INPUT-METHOD LANGUAGE-NAME ACTIVATE-FUNC
865 ;; TITLE DESCRIPTION
866 ;; ARG ...)
867 ;; See the function `register-input-method' for the meanings of arguments.
868 ;;
869 ;; If this directory is included in load-path, Emacs automatically
870 ;; loads this file at startup time.
872 "
873 leim-list-file-name)
877 "Regexp matching head of each entry in LEIM list file.
882 "List of functions to call to update LEIM list file.
886 "Update LEIM list file in directories DIRS."
893 "The current input method for multilingual text.
904 "*Default input method for multilingual text (a string).
905 This is the input method activated automatically by the command
919 "Function to call for inactivating the current input method.
920 Every input method should set this to an appropriate value when activated.
921 This function is called with no argument.
923 This function should never change the value of `current-input-method'.
929 "Function to call for describing the current input method.
935 "Alist of input method names vs how to use them.
936 Each element has the form:
937 (INPUT-METHOD LANGUAGE-ENV ACTIVATE-FUNC TITLE DESCRIPTION ARGS...)
941 "Register INPUT-METHOD as an input method for language environment ENV.
942 INPUT-METHOD and LANG-ENV are symbols or strings.
944 The remaining arguments are:
945 ACTIVATE-FUNC, TITLE, DESCRIPTION, and ARGS...
946 ACTIVATE-FUNC is a function to call to activate this method.
947 TITLE is a string to show in the mode line when this method is active.
948 DESCRIPTION is a string describing this method and what it is good for.
949 The ARGS, if any, are passed as arguments to ACTIVATE-FUNC.
950 All told, the arguments to ACTIVATE-FUNC are INPUT-METHOD and the ARGS.
953 created at building time of emacs, registering all quail input methods
954 contained in the emacs distribution.
956 In case you want to register a new quail input method by yourself, be
957 careful to use the same input method title as given in the third
958 parameter of `quail-define-package' (if the values are different, the
959 string specified in this function takes precedence).
961 The commands `describe-input-method' and `list-input-methods' need
962 this duplicated values to show some information about input methods
963 without loading the affected quail packages."
976 "Read a name of input method from a minibuffer prompting with PROMPT.
977 If DEFAULT is non-nil, use that as the default,
978 and substitute it into PROMPT at the first `%s'.
979 If INHIBIT-NULL is non-nil, null input signals an error.
981 The return value is a string."
985 ;; This binding is necessary because input-method-history is
986 ;; buffer local.
988 nil t nil 'input-method-history
989 default)))
993 input-method
998 "Switch to input method INPUT-METHOD for the current buffer.
999 If some other input method is already active, turn it off first.
1000 If INPUT-METHOD is nil, deactivate any current input method."
1025 "Turn off the current input method."
1038 current-input-method-title nil)
1042 "Select and activate input method INPUT-METHOD for the current buffer.
1043 This also sets the default input method to the one you specify."
1048 default t))))
1053 "Turn on or off a multilingual text input method for the current buffer.
1055 With no prefix argument, if an input method is currently activated,
1056 turn it off. Otherwise, activate an input method -- the one most
1057 recently used, or the one specified in `default-input-method', or
1058 the one read from the minibuffer.
1060 With a prefix argument, read an input method from the minibuffer and
1061 turn it on.
1063 The default is to use the most recent input method specified
1064 \(not including the currently active input method, if any)."
1077 default t))
1078 default))
1083 "Describe input method INPUT-METHOD."
1107 "Describe the input method currently in use."
1113 current-input-method)
1118 "Read a multilingual string from minibuffer, prompting with string PROMPT.
1119 The input method selected last time is activated in minibuffer.
1120 If optional second arg INITIAL-INPUT is non-nil, insert it in the minibuffer
1121 initially.
1122 Optional 3rd argument INPUT-METHOD specifies the input method
1123 to be activated instead of the one selected last time. It is a symbol
1124 or a string."
1127 current-input-method
1128 default-input-method
1139 ;; Variables to control behavior of input methods. All input methods
1140 ;; should react to these variables.
1143 "*A flag to control extra guidance given by input methods.
1144 The value should be nil, t, `complex-only', or `default'.
1146 The extra guidance is done by showing list of available keys in echo
1147 area. When you use the input method in the minibuffer, the guidance
1148 is shown at the bottom short window (split from the existing window).
1150 If the value is t, extra guidance is always given, if the value is
1151 nil, extra guidance is always suppressed.
1153 If the value is `complex-only', only complex input methods such as
1154 `chinese-py' and `japanese' give extra guidance.
1156 If the value is `default', complex input methods always give extra
1157 guidance, but simple input methods give it only when you are not in
1158 the minibuffer.
1160 See also the variable `input-method-highlight-flag'."
1165 "*If this flag is non-nil, input methods highlight partially-entered text.
1166 For instance, while you are in the middle of a Quail input method sequence,
1167 the text inserted so far is temporarily underlined.
1168 The underlining goes away when you finish or abort the input method sequence.
1169 See also the variable `input-method-verbose-flag'."
1174 "Normal hook run just after an input method is activated.
1176 The variable `current-input-method' keeps the input method name
1180 "Normal hook run just after an input method is inactivated.
1182 The variable `current-input-method' still keeps the input method name
1189 "This flag controls a timing when an input method returns.
1190 Usually, the input method does not return while there's a possibility
1191 that it may find a different translation if a user types another key.
1192 But, it this flag is non-nil, the input method returns as soon as
1196 "This flag controls how an input method shows an intermediate key sequence.
1197 Usually, the input method inserts the intermediate key sequence,
1198 or candidate translations corresponding to the sequence,
1199 at point in the current buffer.
1203 "This flag controls the behaviour of an input method on invalid key input.
1204 Usually, when a user types a key which doesn't start any character
1205 handled by the input method, the key is handled by turning off the
1206 input method temporarily. After that key, the input method is re-enabled.
1209 \f
1211 "Normal hook run after some language environment is set.
1213 When you set some hook function here, that effect usually should not
1214 be inherited to another language environment. So, you had better set
1215 another function in `exit-language-environment-hook' (which see) to
1219 "Normal hook run after exiting from some language environment.
1220 When this hook is run, the variable `current-language-environment'
1221 is still bound to the language environment being exited.
1223 This hook is mainly used for canceling the effect of
1229 "Switch to a specified language environment."
1240 "The last language environment specified with `set-language-environment'.
1242 to using the function `set-language-environment'."
1249 current-language-environment)
1250 language-info-alist))
1254 language-info-alist))
1260 "Reset multilingual environment of Emacs to the default status.
1262 The default status is as follows:
1264 The default value of buffer-file-coding-system is nil.
1265 The default coding system for process I/O is nil.
1266 The default value for the command `set-terminal-coding-system' is nil.
1267 The default value for the command `set-keyboard-coding-system' is nil.
1269 The order of priorities of coding categories and the coding system
1270 bound to each category are as follows
1271 coding category coding system
1272 --------------------------------------------------
1273 coding-category-iso-8-2 iso-latin-1
1274 coding-category-iso-8-1 iso-latin-1
1275 coding-category-iso-7-tight iso-2022-jp
1276 coding-category-iso-7 iso-2022-7bit
1277 coding-category-iso-7-else iso-2022-7bit-lock
1278 coding-category-iso-8-else iso-2022-8bit-ss2
1279 coding-category-emacs-mule emacs-mule
1280 coding-category-raw-text raw-text
1281 coding-category-sjis japanese-shift-jis
1282 coding-category-big5 chinese-big5
1283 coding-category-ccl nil
1284 coding-category-binary no-conversion
1285 "
1287 ;; This function formerly set default-enable-multibyte-characters to t,
1288 ;; but that is incorrect. It should not alter the unibyte/multibyte choice.
1291 coding-category-iso-7 'iso-2022-7bit
1292 coding-category-iso-8-1 'iso-latin-1
1293 coding-category-iso-8-2 'iso-latin-1
1294 coding-category-iso-7-else 'iso-2022-7bit-lock
1295 coding-category-iso-8-else 'iso-2022-8bit-ss2
1296 coding-category-emacs-mule 'emacs-mule
1297 coding-category-raw-text 'raw-text
1298 coding-category-sjis 'japanese-shift-jis
1299 coding-category-big5 'chinese-big5
1300 coding-category-utf-8 nil
1301 coding-category-utf-16-be nil
1302 coding-category-utf-16-le nil
1303 coding-category-ccl nil
1308 coding-category-iso-8-2
1309 coding-category-iso-7-tight
1310 coding-category-iso-7
1311 coding-category-iso-7-else
1312 coding-category-iso-8-else
1313 coding-category-emacs-mule
1314 coding-category-raw-text
1315 coding-category-sjis
1316 coding-category-big5
1317 coding-category-ccl
1318 coding-category-binary
1319 coding-category-utf-16-be
1320 coding-category-utf-16-le
1321 coding-category-utf-8))
1329 ;; Don't alter the terminal and keyboard coding systems here.
1330 ;; The terminal still supports the same coding system
1331 ;; that it supported a minute ago.
1332 ;;; (set-terminal-coding-system-internal nil)
1333 ;;; (set-keyboard-coding-system-internal nil)
1341 "Set up the display table and terminal coding system for LANGUAGE-NAME."
1351 "Set up multi-lingual environment for using LANGUAGE-NAME.
1352 This sets the coding system priority and the default input method
1353 and sometimes other things. LANGUAGE-NAME should be a string
1355 specifies the character set for the major languages of Western Europe."
1357 nil
1371 default-buffer-file-coding-system)))
1392 ;; DOS terminals' default is to use a special non-ASCII translation
1393 ;; table as appropriate for the installed codepage.
1398 ;; Unibyte setups if necessary.
1400 ;; Syntax and case table.
1405 ;; No information for syntax and case. Reset to the defaults.
1435 ;; Actually set up direct output of non-ASCII characters.
1437 ;; Unibyte Emacs on MS-DOS wants to display all 8-bit characters with
1438 ;; the native font, and codes 160 and 146 stand for something very
1439 ;; different there.
1442 ;; Make non-line-break space display as a plain space.
1443 ;; Most X fonts do the wrong thing for code 160.
1446 ;; don't contain a character at that position. Map it to the ASCII
1447 ;; apostrophe.
1448 (aset standard-display-table 146 [39]))))
1450 (defun set-language-environment-coding-systems (language-name
1451 &optional eol-type)
1452 "Do various coding system setups for language environment LANGUAGE-NAME.
1454 The optional arg EOL-TYPE specifies the eol-type of the default value
1455 of buffer-file-coding-system set by this function."
1456 (let* ((priority (get-language-info language-name 'coding-priority))
1457 (default-coding (car priority)))
1458 (if priority
1459 (let ((categories (mapcar 'coding-system-category priority)))
1460 (set-default-coding-systems
1461 (if (memq eol-type '(0 1 2 unix dos mac))
1462 (coding-system-change-eol-conversion default-coding eol-type)
1463 default-coding))
1464 (setq default-sendmail-coding-system default-coding)
1465 (set-coding-priority categories)
1466 (while priority
1467 (set (car categories) (car priority))
1468 (setq priority (cdr priority) categories (cdr categories)))
1469 (update-coding-systems-internal)))))
1472 (defsubst princ-list (&rest args)
1473 (while args (princ (car args)) (setq args (cdr args)))
1476 (put 'describe-specified-language-support 'apropos-inhibit t)
1478 ;; Print a language specific information such as input methods,
1479 ;; charsets, and coding systems. This function is intended to be
1480 ;; called from the menu:
1481 ;; [menu-bar mule describe-language-environment LANGUAGE]
1482 ;; and should not run it by `M-x describe-current-input-method-function'.
1483 (defun describe-specified-language-support ()
1484 "Describe how Emacs supports the specified language environment."
1485 (interactive)
1486 (let (language-name)
1487 (if (not (and (symbolp last-command-event)
1488 (or (not (eq last-command-event 'Default))
1489 (setq last-command-event 'English))
1490 (setq language-name (symbol-name last-command-event))))
1491 (error "Bogus calling sequence"))
1492 (describe-language-environment language-name)))
1494 (defun describe-language-environment (language-name)
1495 "Describe how Emacs supports language environment LANGUAGE-NAME."
1496 (interactive
1497 (list (read-language-name
1498 'documentation
1499 "Describe language environment (default, current choice): ")))
1500 (if (null language-name)
1501 (setq language-name current-language-environment))
1502 (if (or (null language-name)
1503 (null (get-language-info language-name 'documentation)))
1504 (error "No documentation for the specified language"))
1505 (if (symbolp language-name)
1506 (setq language-name (symbol-name language-name)))
1507 (let ((doc (get-language-info language-name 'documentation))
1508 pos)
1509 (with-output-to-temp-buffer "*Help*"
1510 (save-excursion
1511 (set-buffer standard-output)
1513 (if (stringp doc)
1515 (let ((str (get-language-info language-name 'sample-text)))
1516 (if (stringp str)
1518 (let ((input-method (get-language-info language-name 'input-method))
1519 (l (copy-sequence input-method-alist)))
1520 (insert "Input methods")
1521 (when input-method
1522 (insert " (default, " input-method ")")
1523 (setq input-method (assoc input-method input-method-alist))
1524 (setq l (cons input-method (delete input-method l))))
1526 (while l
1527 (when (string= language-name (nth 1 (car l)))
1528 (insert " " (car (car l)))
1529 (search-backward (car (car l)))
1530 (help-xref-button 0 #'describe-input-method (car (car l))
1531 "mouse-2, RET: describe this input method")
1532 (goto-char (point-max))
1534 (setq l (cdr l)))
1537 (let ((l (get-language-info language-name 'charset)))
1538 (if (null l)
1540 (while l
1541 (insert " " (symbol-name (car l)))
1542 (search-backward (symbol-name (car l)))
1543 (help-xref-button 0 #'describe-character-set (car l)
1544 "mouse-2, RET: describe this character set")
1545 (goto-char (point-max))
1547 (setq l (cdr l)))))
1550 (let ((l (get-language-info language-name 'coding-system)))
1551 (if (null l)
1553 (while l
1554 (insert " " (symbol-name (car l)))
1555 (search-backward (symbol-name (car l)))
1556 (help-xref-button 0 #'describe-coding-system (car l)
1557 "mouse-2, RET: describe this coding system")
1558 (goto-char (point-max))
1559 (insert " (`"
1560 (coding-system-mnemonic (car l))
1562 (coding-system-doc-string (car l))
1564 (let ((aliases (coding-system-get (car l)
1565 'alias-coding-systems)))
1566 (when aliases
1568 (while aliases
1569 (insert " " (symbol-name (car aliases)))
1570 (setq aliases (cdr aliases)))
1572 (setq l (cdr l)))))
1573 (help-setup-xref (list #'describe-language-environment language-name)
1574 (interactive-p))))))
1575 \f
1576 ;;; Locales.
1578 (defvar locale-translation-file-name nil
1579 "File name for the system's file of locale-name aliases, or nil if none.")
1581 (defvar locale-language-names
1582 '(
1583 ;; UTF-8 is not yet implemented.
1584 ;; Put this first, so that e.g. "ko.UTF-8" does not match "ko" below.
1585 (".*[._]utf" . nil)
1587 ;; Locale names of the form LANGUAGE[_TERRITORY][.CODESET][@MODIFIER]
1588 ;; as specified in the Single Unix Spec, Version 2.
1589 ;; LANGUAGE is a language code taken from ISO 639:1988 (E/F)
1590 ;; with additions from ISO 639/RA Newsletter No.1/1989;
1591 ;; see Internet RFC 2165 (1997-06).
1592 ;; TERRITORY is a country code taken from ISO 3166.
1593 ;; CODESET and MODIFIER are implementation-dependent.
1594 ;;
1595 ; aa Afar
1596 ; ab Abkhazian
1597 ("af" . "Latin-1") ; Afrikaans
1598 ("am" . "Ethiopic") ; Amharic
1599 ; ar Arabic
1600 ; as Assamese
1601 ; ay Aymara
1602 ; az Azerbaijani
1603 ; ba Bashkir
1604 ("be" . "Latin-5") ; Byelorussian
1605 ("bg" . "Latin-5") ; Bulgarian
1606 ; bh Bihari
1607 ; bi Bislama
1608 ; bn Bengali, Bangla
1609 ("bo" . "Tibetan")
1610 ("br" . "Latin-1") ; Breton
1611 ("ca" . "Latin-1") ; Catalan
1612 ; co Corsican
1613 ("cs" . "Czech")
1614 ("cy" . "Latin-8") ; Welsh
1615 ("da" . "Latin-1") ; Danish
1616 ("de" . "German")
1617 ; dz Bhutani
1618 ("el" . "Greek")
1619 ;; Users who specify "en" explicitly typically want Latin-1, not ASCII.
1620 ("en" . "Latin-1") ; English
1621 ("eo" . "Latin-3") ; Esperanto
1622 ("es" . "Latin-1") ; Spanish
1623 ("et" . "Latin-4") ; Estonian
1624 ("eu" . "Latin-1") ; Basque
1625 ; fa Persian
1626 ("fi" . "Latin-1") ; Finnish
1627 ; fj Fiji
1628 ("fo" . "Latin-1") ; Faroese
1629 ("fr" . "Latin-1") ; French
1630 ("fy" . "Latin-1") ; Frisian
1631 ("ga" . "Latin-1") ; Irish Gaelic (new orthography)
1632 ("gd" . "Latin-1") ; Scots Gaelic
1633 ("gl" . "Latin-1") ; Galician
1634 ; gn Guarani
1635 ; gu Gujarati
1636 ; ha Hausa
1637 ("he" . "Hebrew")
1638 ("hi" . "Devanagari") ; Hindi
1639 ("hr" . "Latin-2") ; Croatian
1640 ("hu" . "Latin-2") ; Hungarian
1641 ; hy Armenian
1642 ; ia Interlingua
1643 ("id" . "Latin-1") ; Indonesian
1644 ; ie Interlingue
1645 ; ik Inupiak
1646 ("is" . "Latin-1") ; Icelandic
1647 ("it" . "Latin-1") ; Italian
1648 ; iu Inuktitut
1649 ("ja" . "Japanese")
1650 ; jw Javanese
1651 ; ka Georgian
1652 ; kk Kazakh
1653 ("kl" . "Latin-1") ; Greenlandic
1654 ; km Cambodian
1655 ; kn Kannada
1656 ("ko" . "Korean")
1657 ; ks Kashmiri
1658 ; ku Kurdish
1659 ; ky Kirghiz
1660 ("la" . "Latin-1") ; Latin
1661 ; ln Lingala
1662 ("lo" . "Lao") ; Laothian
1663 ("lt" . "Latin-4") ; Lithuanian
1664 ("lv" . "Latin-4") ; Latvian, Lettish
1665 ; mg Malagasy
1666 ; mi Maori
1667 ("mk" . "Latin-5") ; Macedonian
1668 ; ml Malayalam
1669 ; mn Mongolian
1670 ; mo Moldavian
1671 ("mr" . "Devanagari") ; Marathi
1672 ; ms Malay
1673 ("mt" . "Latin-3") ; Maltese
1674 ; my Burmese
1675 ; na Nauru
1676 ("ne" . "Devanagari") ; Nepali
1677 ("nl" . "Latin-1") ; Dutch
1678 ("no" . "Latin-1") ; Norwegian
1679 ; oc Occitan
1680 ; om (Afan) Oromo
1681 ; or Oriya
1682 ; pa Punjabi
1683 ("pl" . "Latin-2") ; Polish
1684 ; ps Pashto, Pushto
1685 ("pt" . "Latin-1") ; Portuguese
1686 ; qu Quechua
1687 ("rm" . "Latin-1") ; Rhaeto-Romanic
1688 ; rn Kirundi
1689 ("ro" . "Romanian")
1690 ("ru.*[_.]koi8" . "Cyrillic-KOI8") ; Russian
1691 ("ru" . "Latin-5") ; Russian
1692 ; rw Kinyarwanda
1693 ("sa" . "Devanagari") ; Sanskrit
1694 ; sd Sindhi
1695 ; sg Sangho
1696 ("sh" . "Latin-2") ; Serbo-Croatian
1697 ; si Sinhalese
1698 ("sk" . "Slovak")
1699 ("sl" . "Slovenian")
1700 ; sm Samoan
1701 ; sn Shona
1702 ; so Somali
1703 ("sq" . "Latin-1") ; Albanian
1704 ("sr" . "Latin-2") ; Serbian (Latin alphabet)
1705 ; ss Siswati
1706 ; st Sesotho
1707 ; su Sundanese
1708 ("sv" . "Latin-1") ; Swedish
1709 ("sw" . "Latin-1") ; Swahili
1710 ; ta Tamil
1711 ; te Telugu
1712 ; tg Tajik
1713 ("th" . "Thai")
1714 ; ti Tigrinya
1715 ; tk Turkmen
1716 ("tl" . "Latin-1") ; Tagalog
1717 ; tn Setswana
1718 ; to Tonga
1719 ("tr" . "Latin-5") ; Turkish
1720 ; ts Tsonga
1721 ; tt Tatar
1722 ; tw Twi
1723 ; ug Uighur
1724 ("uk" . "Latin-5") ; Ukrainian
1725 ; ur Urdu
1726 ; uz Uzbek
1727 ("vi" . "Vietnamese")
1728 ; vo Volapuk
1729 ; wo Wolof
1730 ; xh Xhosa
1731 ; yi Yiddish
1732 ; yo Yoruba
1733 ; za Zhuang
1734 ("zh.*[._]big5" . "Chinese-BIG5")
1735 ("zh.*[._]gbk" . nil) ; Solaris 2.7; has gbk-0 as well as GB 2312.1980-0
1736 ("zh_tw" . "Chinese-CNS")
1737 ("zh" . "Chinese-GB")
1738 ; zu Zulu
1740 ;; ISO standard locales
1741 ("c$" . "ASCII")
1742 ("posix$" . "ASCII")
1744 ;; The "IPA" Emacs language environment does not correspond
1745 ;; to any ISO 639 code, so let it stand for itself.
1746 ("ipa$" . "IPA")
1748 ;; Nonstandard or obsolete language codes
1749 ("cz" . "Czech") ; e.g. Solaris 2.6
1750 ("ee" . "Latin-4") ; Estonian, e.g. X11R6.4
1751 ("iw" . "Hebrew") ; e.g. X11R6.4
1752 ("sp" . "Latin-5") ; Serbian (Cyrillic alphabet), e.g. X11R6.4
1753 ("su" . "Latin-1") ; Finnish, e.g. Solaris 2.6
1754 )
1755 "List of pairs of locale regexps and language names.
1756 The first element whose locale regexp matches the start of a downcased locale
1757 specifies the language name corresponding to that locale.
1758 If the language name is nil, there is no corresponding language environment.")
1760 (defvar locale-charset-language-names
1768 )
1769 "List of pairs of locale regexps and charset language names.
1770 The first element whose locale regexp matches the start of a downcased locale
1771 specifies the language name whose charsets corresponds to that locale.
1772 This language name is used if its charsets disagree with the charsets of
1773 the language name that would otherwise be used for this locale.")
1775 (defvar locale-preferred-coding-systems
1776 '(("ja.*[._]euc" . japanese-iso-8bit)
1777 ("ja.*[._]jis7" . iso-2022-jp)
1778 ("ja.*[._]pck" . japanese-shift-jis)
1779 ("ja.*[._]sjis" . japanese-shift-jis)
1780 )
1781 "List of pairs of locale regexps and preferred coding systems.
1782 The first element whose locale regexp matches the start of a downcased locale
1783 specifies the coding system to prefer when using that locale.")
1785 (defun locale-name-match (key alist)
1786 "Search for KEY in ALIST, which should be a list of regexp-value pairs.
1787 Return the value corresponding to the first regexp that matches the
1788 start of KEY, or nil if there is no match."
1789 (let (element)
1790 (while (and alist (not element))
1792 (setq element (car alist)))
1793 (setq alist (cdr alist)))
1794 (cdr element)))
1796 (defun set-locale-environment (locale-name)
1797 "Set up multi-lingual environment for using LOCALE-NAME.
1798 This sets the coding system priority and the default input method
1799 and sometimes other things. LOCALE-NAME should be a string
1800 which is the name of a locale supported by the system;
1801 often it is of the form xx_XX.CODE, where xx is a language,
1802 XX is a country, and CODE specifies a character set and coding system.
1804 for Japanese in Japan using the `japanese-iso-8bit' coding-system.
1806 If LOCALE-NAME is nil, its value is taken from the environment.
1808 The locale names supported by your system can typically be found in a
1809 directory named `/usr/share/locale' or `/usr/lib/locale'. LOCALE-NAME
1810 may be translated according to the table specified by
1811 `locale-translation-file-name'.
1813 See also `locale-charset-language-names', `locale-language-names',
1814 `locale-preferred-coding-systems' and `locale-coding-system'."
1816 ;; Do this at runtime for the sake of binaries possibly transported
1817 ;; to a system without X.
1818 (setq locale-translation-file-name
1819 (let ((files
1820 '("/usr/lib/X11/locale/locale.alias" ; e.g. X11R6.4
1821 "/usr/X11R6/lib/X11/locale/locale.alias" ; e.g. RedHat 4.2
1822 "/usr/openwin/lib/locale/locale.alias" ; e.g. Solaris 2.6
1823 ;;
1824 ;; The following name appears after the X-related names above,
1825 ;; since the X-related names are what X actually uses.
1826 "/usr/share/locale/locale.alias" ; GNU/Linux sans X
1827 )))
1828 (while (and files (not (file-exists-p (car files))))
1829 (setq files (cdr files)))
1830 (car files)))
1832 (unless locale-name
1833 ;; Use the first of these three environment variables
1834 ;; that has a nonempty value.
1835 (let ((vars '("LC_ALL" "LC_CTYPE" "LANG")))
1836 (while (and vars (not (setq locale-name (getenv (car vars)))))
1837 (setq vars (cdr vars)))))
1839 (when locale-name
1841 ;; Translate "swedish" into "sv_SE.ISO8859-1", and so on,
1842 ;; using the translation file that many systems have.
1843 (when locale-translation-file-name
1844 (with-temp-buffer
1845 (insert-file-contents locale-translation-file-name)
1846 (when (re-search-forward
1848 (setq locale-name (buffer-substring (point) (line-end-position))))))
1850 (setq locale-name (downcase locale-name))
1852 (let ((language-name
1853 (locale-name-match locale-name locale-language-names))
1854 (charset-language-name
1855 (locale-name-match locale-name locale-charset-language-names))
1856 (coding-system
1857 (locale-name-match locale-name locale-preferred-coding-systems)))
1859 (if (and charset-language-name
1860 (not
1861 (equal (get-language-info language-name 'charset)
1862 (get-language-info charset-language-name 'charset))))
1863 (setq language-name charset-language-name))
1865 (when language-name
1867 ;; Set up for this character set. This is now the right way
1868 ;; to do it for both unibyte and multibyte modes.
1869 (set-language-environment language-name)
1871 ;; If default-enable-multibyte-characters is nil,
1872 ;; we are using single-byte characters,
1873 ;; so the display table and terminal coding system are irrelevant.
1874 (when default-enable-multibyte-characters
1875 (set-display-table-and-terminal-coding-system language-name))
1877 (setq locale-coding-system
1878 (car (get-language-info language-name 'coding-priority))))
1880 (when coding-system
1881 (prefer-coding-system coding-system)
1882 (setq locale-coding-system coding-system)))))
1883 \f
1884 ;;; Charset property
1886 (defun get-charset-property (charset propname)
1887 "Return the value of CHARSET's PROPNAME property.
1888 This is the last value stored with
1889 (put-charset-property CHARSET PROPNAME VALUE)."
1890 (and (not (eq charset 'composition))
1891 (plist-get (charset-plist charset) propname)))
1893 (defun put-charset-property (charset propname value)
1894 "Store CHARSETS's PROPNAME property with value VALUE.
1895 It can be retrieved with `(get-charset-property CHARSET PROPNAME)'."
1896 (or (eq charset 'composition)
1897 (set-charset-plist charset
1898 (plist-put (charset-plist charset) propname value))))
1900 ;;; Character code property
1901 (put 'char-code-property-table 'char-table-extra-slots 0)
1903 (defvar char-code-property-table
1904 (make-char-table 'char-code-property-table)
1905 "Char-table containing a property list of each character code.
1907 See also the documentation of `get-char-code-property' and
1908 `put-char-code-property'.")
1910 (defun get-char-code-property (char propname)
1911 "Return the value of CHAR's PROPNAME property in `char-code-property-table'."
1912 (let ((plist (aref char-code-property-table char)))
1913 (if (listp plist)
1914 (car (cdr (memq propname plist))))))
1916 (defun put-char-code-property (char propname value)
1917 "Store CHAR's PROPNAME property with VALUE in `char-code-property-table'.
1918 It can be retrieved with `(get-char-code-property CHAR PROPNAME)'."
1919 (let ((plist (aref char-code-property-table char)))
1920 (if plist
1921 (let ((slot (memq propname plist)))
1922 (if slot
1923 (setcar (cdr slot) value)
1924 (nconc plist (list propname value))))
1925 (aset char-code-property-table char (list propname value)))))
1927 \f
1928 ;; Pretty description of encoded string
1930 ;; Alist of ISO 2022 control code vs the corresponding mnemonic string.
1931 (defvar iso-2022-control-alist
1939 (defun encoded-string-description (str coding-system)
1940 "Return a pretty description of STR that is encoded by CODING-SYSTEM."
1941 (setq str (string-as-unibyte str))
1942 (mapconcat
1943 (if (and coding-system (eq (coding-system-type coding-system) 2))
1944 ;; Try to get a pretty description for ISO 2022 escape sequences.
1945 (function (lambda (x) (or (cdr (assq x iso-2022-control-alist))
1946 (format "%02X" x))))
1947 (function (lambda (x) (format "0x%02X" x))))
1948 str " "))
1950 (defun encode-coding-char (char coding-system)
1951 "Encode CHAR by CODING-SYSTEM and return the resulting string.
1952 If CODING-SYSTEM can't safely encode CHAR, return nil."
1953 (let ((str1 (string-as-multibyte (char-to-string char)))
1954 (str2 (string-as-multibyte (make-string 2 char)))
1955 (safe-chars (and coding-system
1956 (coding-system-get coding-system 'safe-chars)))
1957 (charset (char-charset char))
1958 enc1 enc2 i1 i2)
1959 (when (or (eq safe-chars t)
1960 (eq charset 'ascii)
1961 (and safe-chars (aref safe-chars char)))
1962 ;; We must find the encoded string of CHAR. But, just encoding
1963 ;; CHAR will put extra control sequences (usually to designate
1964 ;; ASCII charaset) at the tail if type of CODING is ISO 2022.
1965 ;; To exclude such tailing bytes, we at first encode one-char
1966 ;; string and two-char string, then check how many bytes at the
1967 ;; tail of both encoded strings are the same.
1969 (setq enc1 (encode-coding-string str1 coding-system)
1970 i1 (length enc1)
1971 enc2 (encode-coding-string str2 coding-system)
1972 i2 (length enc2))
1973 (while (and (> i1 0) (= (aref enc1 (1- i1)) (aref enc2 (1- i2))))
1974 (setq i1 (1- i1) i2 (1- i2)))
1976 ;; Now (substring enc1 i1) and (substring enc2 i2) are the same,
1977 ;; and they are the extra control sequences at the tail to
1978 ;; exclude.
1979 (substring enc2 0 i2))))
1982 ;;; mule-cmds.el ends here