;;; mule-cmds.el --- commands for mulitilingual environment -*-coding: iso-2022-7bit -*-
-;; Copyright (C) 2000, 2001, 2002, 2003, 2004 Free Software Foundation, Inc.
+;; 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.
t)
(define-key-after set-coding-system-map [set-terminal-coding-system]
'(menu-item "For Terminal" set-terminal-coding-system
- :enable (null (memq window-system '(x w32 mac)))
+ :enable (null (memq initial-window-system '(x w32 mac)))
:help "How to encode terminal output")
t)
(define-key-after set-coding-system-map [separator-3]
(or (local-variable-p 'buffer-file-coding-system buffer)
(ucs-set-table-for-input buffer))))
- (if default-enable-multibyte-characters
+ (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.
;; CODING-SYSTEM is no-conversion or undecided.
(error "Can't prefer the coding system `%s'" coding-system))
(set coding-category (or base coding-system))
+ ;; Changing the binding of a coding category requires this call.
(update-coding-systems-internal)
(or (eq coding-category (car coding-category-list))
;; We must change the order.
coding-category-ccl
coding-category-binary))
+ ;; Changing the binding of a coding category requires this call.
(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
(reset-language-environment)
-(defun set-display-table-and-terminal-coding-system (language-name)
+(defun set-display-table-and-terminal-coding-system (language-name &optional coding-system)
"Set up the display table and terminal coding system for LANGUAGE-NAME."
(let ((coding (get-language-info language-name 'unibyte-display)))
(if coding
(dotimes (i 128)
(aset standard-display-table (+ i 128) nil))))
(or (eq window-system 'pc)
- (set-terminal-coding-system coding))))
+ (set-terminal-coding-system (or coding-system coding)))))
(defun set-language-environment (language-name)
"Set up multi-lingual environment for using LANGUAGE-NAME.
;; 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 (make-char 'latin-iso8859-1 160) [32])
+ ;; 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,
;; fonts probably have the appropriate glyph at this position,
;; so they could use standard-display-8bit. It's better to use a
;; proper windows-1252 coding system. --fx]
- (aset standard-display-table 146 [39])
- ;; XFree86 4 has changed most of the fonts from their designed
- ;; versions such that `' no longer appears as balanced quotes.
- ;; Assume it has iso10646 fonts installed, so we can display
- ;; balanced quotes.
- (when (and (eq window-system 'x)
- (string= "The XFree86 Project, Inc" (x-server-vendor))
- (> (aref (number-to-string (nth 2 (x-server-version))) 0)
- ?3))
- ;; We suppress these setting for the moment because the
- ;; above assumption is wrong.
- ;; (aset standard-display-table ?' [?\e$,1ry\e(B])
- ;; (aset standard-display-table ?` [?\e$,1rx\e(B])
- ;; The fonts don't have the relevant bug.
- (aset standard-display-table 160 nil)
- (aset standard-display-table (make-char 'latin-iso8859-1 160)
- nil)))))
+ (aset standard-display-table 146 [39]))))
(defun set-language-environment-coding-systems (language-name
&optional eol-type)
(while priority
(set (car categories) (car priority))
(setq priority (cdr priority) categories (cdr categories)))
+ ;; Changing the binding of a coding category requires this call.
(update-coding-systems-internal)))))
(defsubst princ-list (&rest args)
(setq language-name (symbol-name language-name)))
(dolist (feature (get-language-info language-name 'features))
(require feature))
- (let ((doc (get-language-info language-name 'documentation))
- pos)
+ (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)
;; and Chinese are exceptions, which are listed in the
;; non-standard section at the bottom of locale-language-names.
- ; aa Afar
- ; ab Abkhazian
+ ("aa_DJ" . "Latin-1") ; Afar
+ ("aa" . "UTF-8")
+ ;; ab Abkhazian
("af" . "Latin-1") ; Afrikaans
- ("am" . "Ethiopic") ; Amharic
+ ("am" "Ethiopic" utf-8) ; Amharic
+ ("an" . "Latin-9") ; Aragonese
; ar Arabic glibc uses 8859-6
; as Assamese
; ay Aymara
- ; az Azerbaijani
+ ("az" . "UTF-8") ; Azerbaijani
; ba Bashkir
- ("be" . "Belarusian") ; Belarusian [Byelorussian until early 1990s]
- ("bg" . "Bulgarian") ; Bulgarian
+ ("be" "Belarusian" cp1251) ; Belarusian [Byelorussian until early 1990s]
+ ("bg" "Bulgarian" cp1251) ; Bulgarian
; bh Bihari
; bi Bislama
- ; bn Bengali, Bangla
+ ("bn" . "UTF-8") ; Bengali, Bangla
("bo" . "Tibetan")
("br" . "Latin-1") ; Breton
("bs" . "Latin-2") ; Bosnian
+ ("byn" . "UTF-8") ; Bilin; Blin
("ca" . "Latin-1") ; Catalan
; co Corsican
- ("cs" . "Czech")
- ("cy" . "Welsh") ; Welsh [glibc uses Latin-8. Did this change?]
+ ("cs" "Czech" iso-8859-2)
+ ("cy" "Welsh" iso-8859-14)
("da" . "Latin-1") ; Danish
- ("de" . "German")
+ ("de" "German" iso-8859-1)
; dz Bhutani
- ("el" . "Greek")
+ ("el" "Greek" iso-8859-7)
;; Users who specify "en" explicitly typically want Latin-1, not ASCII.
;; That's actually what the GNU locales define, modulo things like
;; en_IN -- fx.
+ ("en_IN" "English" utf-8) ; glibc uses utf-8 for English in India
("en" . "Latin-1") ; English
("eo" . "Latin-3") ; Esperanto
- ("es" . "Spanish")
- ("et" . "Latin-4") ; Estonian
+ ("es" "Spanish" iso-8859-1)
+ ("et" . "Latin-1") ; Estonian
("eu" . "Latin-1") ; Basque
- ; fa Persian glibc uses utf-8
+ ("fa" . "UTF-8") ; Persian
("fi" . "Latin-1") ; Finnish
- ; fj Fiji
+ ("fj" . "Latin-1") ; Fiji
("fo" . "Latin-1") ; Faroese
- ("fr" . "French") ; French
+ ("fr" "French" iso-8859-1) ; French
("fy" . "Latin-1") ; Frisian
("ga" . "Latin-1") ; Irish Gaelic (new orthography)
- ("gd" . "Latin-1") ; Scots Gaelic
- ("gl" . "Latin-1") ; Galician
+ ("gd" . "Latin-9") ; Scots Gaelic
+ ("gez" "Ethiopic" utf-8) ; Geez
+ ("gl" . "Latin-1") ; Gallegan; Galician
; gn Guarani
- ; gu Gujarati
- ("gv" . "Latin-8") ; Manx Gaelic glibc uses 8859-1
+ ("gu" . "UTF-8") ; Gujarati
+ ("gv" . "Latin-1") ; Manx Gaelic
; ha Hausa
- ("he" . "Hebrew")
- ("hi" . "Devanagari") ; Hindi glibc uses utf-8
- ("hr" . "Croatian") ; Croatian
+ ("he" "Hebrew" iso-8859-8)
+ ("hi" "Devanagari" utf-8) ; Hindi
+ ("hr" "Croatian" iso-8859-2) ; Croatian
("hu" . "Latin-2") ; Hungarian
; hy Armenian
; ia Interlingua
; ie Interlingue
; ik Inupiak
("is" . "Latin-1") ; Icelandic
- ("it" . "Italian") ; Italian
+ ("it" "Italian" iso-8859-1) ; Italian
; iu Inuktitut
- ("ja" . "Japanese")
+ ("iw" "Hebrew" iso-8859-8)
+ ("ja" "Japanese" euc-jp)
; jw Javanese
- ("ka" . "Georgian") ; Georgian
+ ("ka" "Georgian" georgian-ps) ; Georgian
; kk Kazakh
("kl" . "Latin-1") ; Greenlandic
; km Cambodian
- ; kn Kannada
- ("ko" . "Korean")
+ ("kn" "Kannada" utf-8)
+ ("ko" "Korean" euc-kr)
; ks Kashmiri
; ku Kurdish
("kw" . "Latin-1") ; Cornish
; ky Kirghiz
("la" . "Latin-1") ; Latin
("lb" . "Latin-1") ; Luxemburgish
+ ("lg" . "Laint-6") ; Ganda
; ln Lingala
- ("lo" . "Lao") ; Laothian
- ("lt" . "Lithuanian")
+ ("lo" "Lao" utf-8) ; Laothian
+ ("lt" "Lithuanian" iso-8859-13)
("lv" . "Latvian") ; Latvian, Lettish
; mg Malagasy
("mi" . "Latin-7") ; Maori
- ("mk" . "Cyrillic-ISO") ; Macedonian
- ; ml Malayalam
- ; mn Mongolian
+ ("mk" "Cyrillic-ISO" iso-8859-5) ; Macedonian
+ ("ml" "Malayalam" utf-8)
+ ("mn" . "UTF-8") ; Mongolian
; mo Moldavian
- ("mr" . "Devanagari") ; Marathi glibc uses utf-8
+ ("mr" "Devanagari" utf-8) ; Marathi
("ms" . "Latin-1") ; Malay
("mt" . "Latin-3") ; Maltese
; my Burmese
; na Nauru
- ("ne" . "Devanagari") ; Nepali
- ("nl" . "Dutch")
+ ("nb" . "Latin-1") ; Norwegian
+ ("ne" "Devanagari" utf-8) ; Nepali
+ ("nl" "Dutch" iso-8859-1)
("no" . "Latin-1") ; Norwegian
("oc" . "Latin-1") ; Occitan
- ; om (Afan) Oromo
+ ("om_ET" . "UTF-8") ; (Afan) Oromo
+ ("om" . "Latin-1") ; (Afan) Oromo
; or Oriya
- ; pa Punjabi
+ ("pa" . "UTF-8") ; Punjabi
("pl" . "Latin-2") ; Polish
; ps Pashto, Pushto
("pt" . "Latin-1") ; Portuguese
; qu Quechua
("rm" . "Latin-1") ; Rhaeto-Romanic
; rn Kirundi
- ("ro" . "Romanian")
- ("ru.*[_.]koi8" . "Russian")
- ("ru" . "Cyrillic-ISO") ; Russian
+ ("ro" "Romanian" iso-8859-2)
+ ("ru_RU" "Russian" iso-8859-5)
+ ("ru_UA" "Russian" koi8-u)
; rw Kinyarwanda
("sa" . "Devanagari") ; Sanskrit
; sd Sindhi
- ; se Northern Sami
+ ("se" . "UTF-8") ; Northern Sami
; sg Sangho
("sh" . "Latin-2") ; Serbo-Croatian
; si Sinhalese
- ("sk" . "Slovak")
- ("sl" . "Slovenian")
+ ("sid" . "UTF-8") ; Sidamo
+ ("sk" "Slovak" iso-8859-2)
+ ("sl" "Slovenian" iso-8859-2)
; sm Samoan
; sn Shona
- ; so Somali
+ ("so_ET" "UTF-8") ; Somali
+ ("so" "Latin-1") ; Somali
("sq" . "Latin-1") ; Albanian
+ ("sr_YU@cyrillic" . "Cyrillic-ISO") ; Serbian (Cyrillic alphabet)
("sr" . "Latin-2") ; Serbian (Latin alphabet)
- ("sr_YU@cyrillic" . "Cyrillic-ISO") ; per glibc
; ss Siswati
- ; st Sesotho
+ ("st" . "Latin-1") ; Sesotho
; su Sundanese
- ("sv" . "Swedish") ; Swedish
+ ("sv" "Swedish" iso-8859-1) ; Swedish
("sw" . "Latin-1") ; Swahili
- ; ta Tamil glibc uses utf-8
- ; te Telugu glibc uses utf-8
- ("tg" . "Tajik")
- ("th" . "Thai")
- ; ti Tigrinya
+ ("ta" "Tamil" utf-8)
+ ("te" . "UTF-8") ; Telugu
+ ("tg" "Tajik" koi8-t)
+ ("th" "Thai" tis-620)
+ ("ti" "Ethiopic" utf-8) ; Tigrinya
+ ("tig_ER" . "UTF-8") ; Tigre
; tk Turkmen
("tl" . "Latin-1") ; Tagalog
; tn Setswana
; to Tonga
- ("tr" . "Turkish")
+ ("tr" "Turkish" iso-8859-9)
; ts Tsonga
- ; tt Tatar
+ ("tt" . "UTF-8") ; Tatar
; tw Twi
; ug Uighur
- ("uk" . "Ukrainian") ; Ukrainian
- ; ur Urdu glibc uses utf-8
+ ("uk" "Ukrainian" koi8-u)
+ ("ur" . "UTF-8") ; Urdu
+ ("uz_UZ@cyrillic" . "UTF-8"); Uzbek
("uz" . "Latin-1") ; Uzbek
- ("vi" . "Vietnamese") ; glibc uses utf-8
+ ("vi" "Vietnamese" utf-8)
; vo Volapuk
("wa" . "Latin-1") ; Walloon
; wo Wolof
- ; xh Xhosa
+ ("xh" . "Latin-1") ; Xhosa
("yi" . "Windows-1255") ; Yiddish
; yo Yoruba
; za Zhuang
-
- ; glibc:
+ ("zh_HK" . "Chinese-Big5")
+ ("zh_TW" . "Chinese-Big5")
+ ("zh_CN" . "Chinese-GB")
+ ("zh" . "Chinese-GB")
; zh_CN.GB18030/GB18030 \
; zh_CN.GBK/GBK \
; zh_HK/BIG5-HKSCS \
-
- ("zh.*[._]big5" . "Chinese-BIG5")
- ("zh.*[._]gbk" . nil) ; Solaris 2.7; has gbk-0 as well as GB 2312.1980-0
- ("zh_tw" . "Chinese-CNS") ; glibc uses big5
- ("zh_tw[._]euc-tw" . "Chinese-EUC-TW")
- ("zh" . "Chinese-GB")
- ; zu Zulu
+ ("zu" . "Latin-1") ; Zulu
;; ISO standard locales
("c$" . "ASCII")
("chs" . "Chinese-GB") ; MS Windows Chinese Simplified
("cht" . "Chinese-BIG5") ; MS Windows Chinese Traditional
))
- "List of pairs of locale regexps and language names.
-The first element whose locale regexp matches the start of a downcased locale
-specifies the language name corresponding to that locale.
-If the language name is nil, there is no corresponding language environment.")
+ "Alist of locale regexps vs the corresponding languages and coding systems.
+Each element has these form:
+ \(LOCALE-REGEXP LANG-ENV CODING-SYSTEM)
+The first element whose LOCALE-REGEXP matches the start of a
+downcased locale specifies the LANG-ENV \(language environtment)
+and CODING-SYSTEM corresponding to that locale. If there is no
+appropriate language environment, the element may have this form:
+ \(LOCALE-REGEXP . LANG-ENV)
+In this case, LANG-ENV is one of generic language environments for an
+specific encoding such as \"Latin-1\" and \"UTF-8\".")
(defconst locale-charset-language-names
(purecopy
"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 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.")
+This language name is used if the locale is not listed in
+`locale-language-names'")
(defconst locale-preferred-coding-systems
(purecopy
- '(("ja.*[._]euc" . japanese-iso-8bit)
+ '((".*8859[-_]?1\\>" . iso-8859-1)
+ (".*8859[-_]?2\\>" . iso-8859-2)
+ (".*8859[-_]?3\\>" . iso-8859-3)
+ (".*8859[-_]?4\\>" . iso-8859-4)
+ (".*8859[-_]?9\\>" . iso-8859-9)
+ (".*8859[-_]?14\\>" . iso-8859-14)
+ (".*8859[-_]?15\\>" . iso-8859-15)
+ (".*utf\\(?:-?8\\)?" . utf-8)
+ ;; utf-8@euro exists, so put this after utf-8. (@euro really
+ ;; specifies the currency, rather than the charset.)
+ (".*@euro" . iso-8859-15)
+ ("koi8-?r" . koi8-r)
+ ("koi8-?u" . koi8-u)
+ ("tcvn" . tcvn)
+ ("big5" . big5)
+ ("euc-?tw" . euc-tw)
+ ;; We don't support GBK, but as it is upper compatible with
+ ;; GB-2312, we setup the default coding system to gb2312.
+ ("gbk" . gb2312)
+ ;; We don't support BIG5-HKSCS, but as it is upper compatible with
+ ;; BIG5, we setup the default coding system to big5.
+ ("big5hkscs" . big5)
+ ("ja.*[._]euc" . japanese-iso-8bit)
("ja.*[._]jis7" . iso-2022-jp)
("ja.*[._]pck" . japanese-shift-jis)
("ja.*[._]sjis" . japanese-shift-jis)
("jpn" . japanese-shift-jis) ; MS-Windows uses this.
- (".*[._]utf" . utf-8)))
+ ))
"List of pairs of locale regexps and preferred coding systems.
The first element whose locale regexp matches the start of a downcased locale
-specifies the coding system to prefer when using that locale.")
+specifies the coding system to prefer when using that locale.
+This coding system is used if the locale specifies a specific charset.")
(defun locale-name-match (key alist)
"Search for KEY in ALIST, which should be a list of regexp-value pairs.
(pop cs)))
(if c (coding-system-base c)))))
-(defun set-locale-translation-file-name ()
- "Set up the locale-translation-file-name on the current system.
-
-This needs to be done at runtime for the sake of binaries
-possibly transported to a system without X."
- (setq locale-translation-file-name
- (let ((files
- '("/usr/lib/X11/locale/locale.alias" ; e.g. X11R6.4
- "/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,
- ;; since the X-related names are what X actually uses.
- "/usr/share/locale/locale.alias" ; GNU/Linux sans X
- )))
- (while (and files (not (file-exists-p (car files))))
- (setq files (cdr files)))
- (car files))))
-
-(defun get-locale-real-name (&optional locale-name)
- "Return the canonicalized name of locale LOCALE-NAME.
-
-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).
-On server frames, the environment of the emacsclient process is
-used.
-
-See also `set-locale-environment'."
- (unless locale-name
- ;; Use the first of these three environment variables
- ;; that has a nonempty value.
- (let ((vars '("LC_ALL" "LC_CTYPE" "LANG")))
- (while (and vars
- (= 0 (length locale-name))) ; nil or empty string
- (setq locale-name (server-getenv (pop vars))))))
-
- (when locale-name
- ;; Translate "swedish" into "sv_SE.ISO8859-1", and so on,
- ;; using the translation file that many systems have.
- (when locale-translation-file-name
- (with-temp-buffer
- (insert-file-contents locale-translation-file-name)
- (when (re-search-forward
- (concat "^" (regexp-quote locale-name) ":?[ \t]+") nil t)
- (setq locale-name (buffer-substring (point) (line-end-position)))))))
- locale-name)
-
-(defun get-locale-coding-system (&optional locale)
- "Return the coding system corresponding to locale LOCALE."
- (setq locale (or locale (get-locale-real-name nil)))
- (when locale
- (or (locale-name-match locale locale-preferred-coding-systems)
- (when locale
- (if (string-match "\\.\\([^@]+\\)" locale)
- (locale-charset-to-coding-system
- (match-string 1 locale)))))))
-
-(defun configure-display-for-locale (&optional locale)
- "Set up terminal for locale LOCALE.
-
-The display table, the terminal coding system and the keyboard
-coding system of the current display device are set up for the
-given locale."
- (setq locale (or locale (get-locale-real-name nil)))
-
- (when locale
- (let ((language-name
- (locale-name-match locale locale-language-names))
- (charset-language-name
- (locale-name-match locale locale-charset-language-names))
- (coding-system
- (get-locale-coding-system locale)))
-
- ;; Give preference to charset-language-name over language-name.
- (if (and charset-language-name
- (not
- (equal (get-language-info language-name 'charset)
- (get-language-info charset-language-name 'charset))))
- (setq language-name charset-language-name))
-
- (when language-name
-
- ;; If default-enable-multibyte-characters is nil,
- ;; we are using single-byte characters,
- ;; so the display table and terminal coding system are irrelevant.
- (when default-enable-multibyte-characters
- ;; Override default-terminal-coding-system in case the
- ;; display coding can not be derived from the language
- ;; environment.
- (let ((default-terminal-coding-system coding-system))
- (set-display-table-and-terminal-coding-system language-name)))
-
- ;; Set the `keyboard-coding-system' if appropriate (tty
- ;; only). At least X and MS Windows can generate
- ;; multilingual input.
- (unless window-system
- (let ((kcs (or coding-system
- (car (get-language-info language-name
- 'coding-system)))))
- (if kcs (set-keyboard-coding-system kcs))))))))
-
;; 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.
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).
-On server frames, the environment of the emacsclient process is
-used.
The locale names supported by your system can typically be found in a
directory named `/usr/share/locale' or `/usr/lib/locale'. LOCALE-NAME
`locale-preferred-coding-systems' and `locale-coding-system'."
(interactive "sSet environment for locale: ")
- (let ((locale (get-locale-real-name locale-name)))
+ ;; Do this at runtime for the sake of binaries possibly transported
+ ;; to a system without X.
+ (setq locale-translation-file-name
+ (let ((files
+ '("/usr/lib/X11/locale/locale.alias" ; e.g. X11R6.4
+ "/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,
+ ;; since the X-related names are what X actually uses.
+ "/usr/share/locale/locale.alias" ; GNU/Linux sans X
+ )))
+ (while (and files (not (file-exists-p (car files))))
+ (setq files (cdr files)))
+ (car files)))
+
+ (let ((locale locale-name))
+
+ (unless locale
+ ;; Use the first of these three environment variables
+ ;; that has a nonempty value.
+ (let ((vars '("LC_ALL" "LC_CTYPE" "LANG")))
+ (while (and vars
+ (= 0 (length locale))) ; nil or empty string
+ (setq locale (getenv (pop vars))))))
+
+ (unless (or locale (not (fboundp 'mac-get-preference)))
+ (setq locale (mac-get-preference "AppleLocale"))
+ (unless locale
+ (let ((languages (mac-get-preference "AppleLanguages")))
+ (unless (= (length languages) 0) ; nil or empty vector
+ (setq locale (aref languages 0))))))
+ (unless (or locale (not (boundp 'mac-system-locale)))
+ (setq locale mac-system-locale))
(when locale
+ ;; Translate "swedish" into "sv_SE.ISO8859-1", and so on,
+ ;; using the translation file that many systems have.
+ (when locale-translation-file-name
+ (with-temp-buffer
+ (insert-file-contents locale-translation-file-name)
+ (when (re-search-forward
+ (concat "^" (regexp-quote locale) ":?[ \t]+") nil t)
+ (setq locale (buffer-substring (point) (line-end-position))))))
+
;; Leave the system locales alone if the caller did not specify
;; an explicit locale name, as their defaults are set from
;; LC_MESSAGES and LC_TIME, not LC_CTYPE, and the user might not
(setq locale (downcase locale))
- (configure-display-for-locale locale)
-
(let ((language-name
(locale-name-match locale locale-language-names))
(charset-language-name
(locale-name-match locale locale-charset-language-names))
(coding-system
- (get-locale-coding-system locale)))
-
- ;; Give preference to charset-language-name over language-name.
- (if (and charset-language-name
- (not
- (equal (get-language-info language-name 'charset)
- (get-language-info charset-language-name 'charset))))
- (setq language-name charset-language-name))
+ (or (locale-name-match locale locale-preferred-coding-systems)
+ (when locale
+ (if (string-match "\\.\\([^@]+\\)" locale)
+ (locale-charset-to-coding-system
+ (match-string 1 locale))))
+ (and (eq system-type 'macos) mac-system-coding-system))))
+
+ (if (consp language-name)
+ ;; locale-language-names specify both lang-env and coding.
+ ;; But, what specified in locale-preferred-coding-systems
+ ;; has higher priority.
+ (setq coding-system (or coding-system
+ (nth 1 language-name))
+ language-name (car language-name))
+ ;; Otherwise, if locale is not listed in locale-language-names,
+ ;; use what listed in locale-charset-language-names.
+ (if (not language-name)
+ (setq language-name charset-language-name)))
(when language-name
;; to do it for both unibyte and multibyte modes.
(set-language-environment language-name)
+ ;; If default-enable-multibyte-characters is nil,
+ ;; we are using single-byte characters,
+ ;; so the display table and terminal coding system are irrelevant.
+ (when default-enable-multibyte-characters
+ (set-display-table-and-terminal-coding-system
+ language-name coding-system))
+
+ ;; Set the `keyboard-coding-system' if appropriate (tty
+ ;; only). At least X and MS Windows can generate
+ ;; multilingual input.
+ (unless window-system
+ (let ((kcs (or coding-system
+ (car (get-language-info language-name
+ 'coding-system)))))
+ (if kcs (set-keyboard-coding-system kcs))))
+
(setq locale-coding-system
(car (get-language-info language-name 'coding-priority))))
- (when coding-system
+ (when (and coding-system
+ (not (coding-system-equal coding-system
+ locale-coding-system)))
(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.
+ ;; On Windows, override locale-coding-system,
+ ;; keyboard-coding-system with system codepage. Note:
+ ;; selection-coding-system is already set in w32select.c.
(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))))
+ (when (eq system-type 'darwin)
+ ;; On Darwin, file names are always encoded in utf-8, no matter
+ ;; the locale.
+ (setq default-file-name-coding-system 'utf-8)
+ ;; Mac OS X's Terminal.app by default uses utf-8 regardless of
+ ;; the locale.
+ (when (and (null window-system)
+ (equal (getenv "TERM_PROGRAM") "Apple_Terminal"))
+ (set-terminal-coding-system 'utf-8)
+ (set-keyboard-coding-system 'utf-8)))
+
;; Default to A4 paper if we're not in a C, POSIX or US locale.
;; (See comments in Flocale_info.)
(let ((locale locale)