-;;; european.el --- Support for European languages
+;;; european.el --- support for European languages -*- coding: iso-2022-7bit; -*-
-;; Copyright (C) 1995, 1997 Electrotechnical Laboratory, JAPAN.
+;; Copyright (C) 1995, 1997, 2001 Electrotechnical Laboratory, JAPAN.
;; Licensed to the Free Software Foundation.
+;; Copyright (C) 2001, 2002 Free Software Foundation, Inc.
;; Keywords: multilingual, European
;;; Commentary:
-;; For Europeans, five character sets ISO8859-1,2,3,4,9 are supported.
+;; For European scripts, character sets ISO8859-1,2,3,4,9,10,13,14,15,
+;; windows-1250,2,4,7, mac-roman, adobe-standard-encoding, cp850 and
+;; next are supported.
;;; Code:
-(define-prefix-command 'describe-european-environment-map)
-(define-key-after describe-language-environment-map [European]
- '("European" . describe-european-environment-map)
- t)
-
-(define-prefix-command 'setup-european-environment-map)
-(define-key-after setup-language-environment-map [European]
- '("European" . setup-european-environment-map)
- t)
-
-;; Setup for LANGAUGE which uses one-byte 8-bit CHARSET, one-byte
-;; 8-bit CODING-SYSTEM, and INPUT-METHOD.
-(defun setup-8-bit-environment (language charset coding-system input-method)
- (setup-english-environment)
- (set-default-coding-systems coding-system)
- (setq coding-category-iso-8-1 coding-system
- coding-category-iso-8-2 coding-system)
-
- (if charset
- (let ((nonascii-offset (- (make-char charset) 128)))
- ;; Set up for insertion of characters in this character set
- ;; when codes 0200 - 0377 are typed in.
- (setq nonascii-insert-offset nonascii-offset)))
-
- (if input-method
- (progn
- (setq default-input-method input-method)
- (setq-default default-input-method input-method)))
-
- ;; If this is a Latin-N character set, set up syntax for it in
- ;; single-byte mode.
- (if (string-match "^Latin-\\([1-9]\\)$" language)
- (load (downcase language))))
-\f
;; Latin-1 (ISO-8859-1)
-(make-coding-system
- 'iso-latin-1 2 ?1
- "ISO 2022 based 8-bit encoding (MIME:ISO-8859-1, Compound Text Encoding)"
- '((ascii t) (latin-iso8859-1 t) nil nil
- nil ascii-eol ascii-cntl))
-
-(define-coding-system-alias 'iso-8859-1 'iso-latin-1)
-(define-coding-system-alias 'latin-1 'iso-latin-1)
-(define-coding-system-alias 'ctext 'iso-latin-1)
-
-(defun setup-latin1-environment ()
- "Set up multilingual environment (MULE) for European Latin-1 users."
- (interactive)
- (setup-8-bit-environment "Latin-1" 'latin-iso8859-1 'iso-latin-1
- "latin-1-prefix"))
-
(set-language-info-alist
- "Latin-1" '((setup-function . (setup-latin1-environment
- . setup-european-environment-map))
- (charset . (ascii latin-iso8859-1))
- (coding-system . (iso-latin-1))
+ "Latin-1" '((charset iso-8859-1)
+ (coding-system iso-latin-1)
+ (coding-priority iso-latin-1)
+ (nonascii-translation . iso-8859-1)
+ (unibyte-syntax . "latin-1")
+ (unibyte-display . iso-latin-1)
+ (input-method . "latin-1-prefix")
(sample-text
. "Hello, Hej, Tere, Hei, Bonjour, Gr\e,A|_\e(B Gott, Ciao, \e,A!\e(BHola!")
- (documentation . ("\
-These languages are supported with the Latin-1 (ISO-8859-1) character set:
- Danish, Dutch, English, Faeroese, Finnish, French, German, Icelandic,
- Irish, Italian, Norwegian, Portuguese, Spanish, and Swedish.
-" . describe-european-environment-map))
- ))
+ (documentation . "\
+This language environment is a generic one for the Latin-1 (ISO-8859-1)
+character set which supports the following European languages:
+ Albanian, Basque, Breton, Catalan, Danish, Dutch, English, Faeroese,
+ Finnish, French (with restrictions -- see Latin-9), Frisian, Galician,
+ German, Greenlandic, Icelandic, Irish Gaelic (new orthography),
+ Italian, Latin, Luxemburgish, Norwegian, Portuguese, Rhaeto-Romanic,
+ Scottish Gaelic, Spanish, and Swedish.
+We also have specific language environments for the following languages:
+ For Dutch, \"Dutch\".
+ For German, \"German\".
+ For Spanish, \"Spanish\".
+ For French, \"French\".
+
+Latin-1 also covers several written languages outside Europe, including
+Indonesian/Malay, Tagalog (Philippines), Swahili and Afrikaans."))
+ '("European"))
+
\f
;; Latin-2 (ISO-8859-2)
-(make-coding-system
- 'iso-latin-2 2 ?2
- "ISO 2022 based 8-bit encoding (MIME:ISO-8859-2)"
- '((ascii t) (latin-iso8859-2 t) nil nil
- nil ascii-eol ascii-cntl nil nil nil nil))
+(define-coding-system 'iso-latin-2
+ "ISO 2022 based 8-bit encoding for Latin-2 (MIME:ISO-8859-2)."
+ :coding-type 'charset
+ :mnemonic ?2
+ :charset-list '(iso-8859-2)
+ :mime-charset 'iso-8859-2)
(define-coding-system-alias 'iso-8859-2 'iso-latin-2)
(define-coding-system-alias 'latin-2 'iso-latin-2)
-(defun setup-latin2-environment ()
- "Set up multilingual environment (MULE) for European Latin-2 users."
- (interactive)
- (setup-8-bit-environment "Latin-2" 'latin-iso8859-2 'iso-latin-2
- "latin-2-prefix"))
-
(set-language-info-alist
- "Latin-2" '((setup-function . (setup-latin2-environment
- . setup-european-environment-map))
- (charset . (ascii latin-iso8859-2))
- (coding-system . (iso-latin-2))
- (documentation . ("\
-These languages are supported with the Latin-2 (ISO-8859-2) character set:
+ "Latin-2" '((charset iso-8859-2)
+ (coding-system iso-latin-2)
+ (coding-priority iso-latin-2)
+ (nonascii-translation . iso-8859-2)
+ (unibyte-syntax . "latin-2")
+ (unibyte-display . iso-latin-2)
+ (input-method . "latin-2-prefix")
+ (documentation . "\
+This language environment is a generic one for the Latin-2 (ISO-8859-2)
+character set which supports the following languages:
Albanian, Czech, English, German, Hungarian, Polish, Romanian,
- Serbo-Croatian or Croatian, Slovak, Slovene, and Swedish.
-" . describe-european-environment-map))
- ))
+ Serbo-Croatian or Croatian, Slovak, Slovene, Sorbian (upper and lower),
+ and Swedish.
+We also have specific language environments for the following languages:
+ For Czech, \"Czech\".
+ For Romanian, \"Romanian\".
+ For Slovak, \"Slovak\"."))
+ '("European"))
+
\f
;; Latin-3 (ISO-8859-3)
-(make-coding-system
- 'iso-latin-3 2 ?3
- "ISO 2022 based 8-bit encoding (MIME:ISO-8859-3)"
- '((ascii t) (latin-iso8859-3 t) nil nil
- nil ascii-eol ascii-cntl nil nil nil nil))
+(define-coding-system 'iso-latin-3
+ "ISO 2022 based 8-bit encoding for Latin-3 (MIME:ISO-8859-3)."
+ :coding-type 'charset
+ :mnemonic ?3
+ :charset-list '(iso-8859-3)
+ :mime-charset 'iso-8859-3)
(define-coding-system-alias 'iso-8859-3 'iso-latin-3)
(define-coding-system-alias 'latin-3 'iso-latin-3)
-(defun setup-latin3-environment ()
- "Set up multilingual environment (MULE) for European Latin-3 users."
- (interactive)
- (setup-8-bit-environment "Latin-3" 'latin-iso8859-3 'iso-latin-3
- "latin-3-prefix"))
-
(set-language-info-alist
- "Latin-3" '((setup-function . (setup-latin3-environment
- . setup-european-environment-map))
- (charset . (ascii latin-iso8859-3))
- (coding-system . (iso-latin-3))
- (documentation . ("\
+ "Latin-3" '((charset iso-8859-3)
+ (coding-system iso-latin-3)
+ (coding-priority iso-latin-3)
+ (nonascii-translation . iso-8859-3)
+ (unibyte-syntax . "latin-3")
+ (unibyte-display . iso-latin-3)
+ (input-method . "latin-3-prefix")
+ (documentation . "\
These languages are supported with the Latin-3 (ISO-8859-3) character set:
Afrikaans, Catalan, Dutch, English, Esperanto, French, Galician,
- German, Italian, Maltese, Spanish, and Turkish.
-" . describe-european-environment-map))
- ))
+ German, Italian, Maltese, Spanish, and Turkish."))
+ '("European"))
+
\f
;; Latin-4 (ISO-8859-4)
-(make-coding-system
- 'iso-latin-4 2 ?4
- "ISO 2022 based 8-bit encoding (MIME:ISO-8859-4)"
- '((ascii t) (latin-iso8859-4 t) nil nil
- nil ascii-eol ascii-cntl nil nil nil nil))
+(define-coding-system 'iso-latin-4
+ "ISO 2022 based 8-bit encoding for Latin-4 (MIME:ISO-8859-4)."
+ :coding-type 'charset
+ :mnemonic ?4
+ :charset-list '(iso-8859-4)
+ :mime-charset 'iso-8859-4)
(define-coding-system-alias 'iso-8859-4 'iso-latin-4)
(define-coding-system-alias 'latin-4 'iso-latin-4)
-(defun setup-latin4-environment ()
- "Set up multilingual environment (MULE) for European Latin-4 users."
- (interactive)
- (setup-8-bit-environment "Latin-4" 'latin-iso8859-4 'iso-latin-4
- "latin-4-prefix"))
-
(set-language-info-alist
- "Latin-4" '((setup-function . (setup-latin4-environment
- . setup-european-environment-map))
- (charset . (ascii latin-iso8859-4))
- (coding-system . (iso-8859-4))
- (documentation . ("\
+ "Latin-4" '((charset iso-8859-4)
+ (coding-system iso-8859-4)
+ (coding-priority iso-8859-4)
+ (nonascii-translation . iso-8859-4)
+ (unibyte-syntax . "latin-4")
+ (unibyte-display . iso-8859-4)
+ (input-method . "latin-4-postfix")
+ (documentation . "\
These languages are supported with the Latin-4 (ISO-8859-4) character set:
Danish, English, Estonian, Finnish, German, Greenlandic, Lappish,
- Latvian, Lithuanian, and Norwegian.
-" . describe-european-environment-map))
- ))
+ Latvian, Lithuanian, and Norwegian."))
+ '("European"))
+
\f
;; Latin-5 (ISO-8859-9)
-(make-coding-system
- 'iso-latin-5 2 ?9
- "ISO 2022 based 8-bit encoding (MIME:ISO-8859-9)"
- '((ascii t) (latin-iso8859-9 t) nil nil
- nil ascii-eol ascii-cntl nil nil nil nil))
+(define-coding-system 'iso-latin-5
+ "ISO 2022 based 8-bit encoding for Latin-5 (MIME:ISO-8859-9)."
+ :coding-type 'charset
+ :mnemonic ?9
+ :charset-list '(iso-8859-9)
+ :mime-charset 'iso-8859-9)
(define-coding-system-alias 'iso-8859-9 'iso-latin-5)
(define-coding-system-alias 'latin-5 'iso-latin-5)
-(defun setup-latin5-environment ()
- "Set up multilingual environment (MULE) for European Latin-5 users."
+(set-language-info-alist
+ "Latin-5" '((charset iso-8859-9)
+ (coding-system iso-latin-5)
+ (coding-priority iso-latin-5)
+ (nonascii-translation . iso-8859-9)
+ (unibyte-syntax . "latin-5")
+ (unibyte-display . iso-latin-5)
+ (input-method . "latin-5-postfix")
+ (documentation . "Support for Turkish language."))
+ '("European"))
+
+\f
+;; Latin-6 (ISO-8859-10)
+
+(define-coding-system 'iso-latin-6
+ "ISO 2022 based 8-bit encoding for Latin-6 (MIME:ISO-8859-10)."
+ :coding-type 'charset
+ :mnemonic ?9
+ :charset-list '(iso-8859-10)
+ :mime-charset 'iso-8859-10)
+
+(define-coding-system-alias 'iso-8859-10 'iso-latin-6)
+(define-coding-system-alias 'latin-6 'iso-latin-6)
+
+(set-language-info-alist
+ "Latin-6" '((charset iso-8859-10)
+ (coding-system iso-latin-6)
+ (coding-priority iso-latin-6)
+ (nonascii-translation . iso-8859-10)
+ (unibyte-syntax . "latin-6")
+ (unibyte-display . iso-latin-6)
+ ;; Fixme: input method.
+ (documentation . "Support for generic Latin-6 (Northern European)."))
+ '("European"))
+
+\f
+;; Latin-7 (ISO-8859-13)
+
+(define-coding-system 'iso-latin-7
+ "ISO 2022 based 8-bit encoding for Latin-7 (MIME:ISO-8859-13)."
+ :coding-type 'charset
+ :mnemonic ?9
+ :charset-list '(iso-8859-13)
+ :mime-charset 'iso-8859-13)
+
+(define-coding-system-alias 'iso-8859-13 'iso-latin-7)
+(define-coding-system-alias 'latin-7 'iso-latin-7)
+
+(set-language-info-alist
+ "Latin-7" '((charset iso-8859-13)
+ (coding-system iso-latin-7)
+ (coding-priority iso-latin-7)
+ (nonascii-translation . iso-8859-13)
+ (unibyte-syntax . "latin-7")
+ (unibyte-display . iso-latin-7)
+ ;; Fixme: input method.
+ (documentation . "Support for generic Latin-7 (Baltic Rim)."))
+ '("European"))
+\f
+;; Latin-8 (ISO-8859-14)
+
+(define-coding-system 'iso-latin-8
+ "ISO 2022 based 8-bit encoding for Latin-8 (MIME:ISO-8859-14)."
+ :coding-type 'charset
+ ;; `W' for `Welsh', since `C' for `Celtic' is taken.
+ :mnemonic ?W
+ :charset-list '(iso-8859-14)
+ :mime-charset 'iso-8859-14)
+
+(define-coding-system-alias 'iso-8859-14 'iso-latin-8)
+(define-coding-system-alias 'latin-8 'iso-latin-8)
+
+(set-language-info-alist
+ "Latin-8" '((charset iso-8859-14)
+ (coding-system iso-latin-8)
+ (coding-priority iso-latin-8)
+ (nonascii-translation . iso-8859-14)
+ (unibyte-syntax . "latin-8")
+ (unibyte-display . iso-latin-8)
+ (input-method . "latin-8-prefix")
+ ;; Fixme: Welsh/Ga{e}lic greetings
+ (sample-text . "\e,_"\e(B \e,_p\e(B \e,_^\e(B")
+ (documentation . "\
+This language environment is a generic one for the Latin-8 (ISO-8859-14)
+character set which supports the Celtic languages, including those not
+covered by other ISO-8859 character sets:
+ Welsh, Manx Gaelic and Irish Gaelic (old orthography)."))
+ '("European"))
+\f
+;; Latin-9 (ISO-8859-15)
+
+(define-coding-system 'iso-latin-9
+ "ISO 2022 based 8-bit encoding for Latin-9 (MIME:ISO-8859-15)."
+ :coding-type 'charset
+ ;; `0' for `Latin-0'
+ :mnemonic ?0
+ :charset-list '(iso-8859-15)
+ :mime-charset 'iso-8859-15)
+
+(define-coding-system-alias 'iso-8859-15 'iso-latin-9)
+(define-coding-system-alias 'latin-9 'iso-latin-9)
+(define-coding-system-alias 'latin-0 'iso-latin-9)
+
+(set-language-info-alist
+ "Latin-9" '((charset iso-8859-15)
+ (coding-system iso-latin-9)
+ (coding-priority iso-latin-9)
+ (nonascii-translation . iso-8859-15)
+ (unibyte-syntax . "latin-9")
+ (unibyte-display . iso-latin-9)
+ (input-method . "latin-9-prefix")
+ (sample-text
+ . "AVE. \e,B)9.>\e,b<=\e,_/\e(B \e,b$\e(B")
+ (documentation . "\
+This language environment is a generic one for the Latin-9 (ISO-8859-15)
+character set which supports the same languages as Latin-1 with the
+addition of the Euro sign and some additional French and Finnish letters.
+Latin-9 is sometimes nicknamed `Latin-0'."))
+ '("European"))
+\f
+(define-coding-system 'iso-latin-7
+ "ISO 2022 based 8-bit encoding for Latin-7 (MIME:ISO-8859-13)."
+ :coding-type 'charset
+ ;; `0' for `Latin-0'
+ :mnemonic ?*
+ :charset-list '(iso-8859-13)
+ :mime-charset 'iso-8859-13)
+
+(define-coding-system-alias 'iso-8859-13 'iso-latin-7)
+(define-coding-system-alias 'latin-7 'iso-latin-7)
+\f
+(define-coding-system 'windows-1250
+ "windows-1250 (Central European) encoding (MIME: WINDOWS-1250)"
+ :coding-type 'charset
+ :mnemonic ?*
+ :charset-list '(windows-1250)
+ :mime-charset 'windows-1250)
+(define-coding-system-alias 'cp1250 'windows-1250)
+
+(define-coding-system 'windows-1252
+ "windows-1252 (Western European) encoding (MIME: WINDOWS-1252)"
+ :coding-type 'charset
+ :mnemonic ?*
+ :charset-list '(windows-1252)
+ :mime-charset 'windows-1252)
+(define-coding-system-alias 'cp1252 'windows-1252)
+
+(define-coding-system 'windows-1254
+ "windows-1254 (Turkish) encoding (MIME: WINDOWS-1254)"
+ :coding-type 'charset
+ :mnemonic ?*
+ :charset-list '(windows-1254)
+ :mime-charset 'windows-1254)
+(define-coding-system-alias 'cp1254 'windows-1254)
+
+(define-coding-system 'windows-1257
+ "windows-1257 (Baltic) encoding (MIME: WINDOWS-1257)"
+ :coding-type 'charset
+ :mnemonic ?*
+ :charset-list '(windows-1257)
+ :mime-charset 'windows-1257)
+(define-coding-system-alias 'cp1257 'windows-1257)
+
+(define-coding-system 'cp850
+ "DOS codepage 850 (Western European)"
+ :coding-type 'charset
+ :mnemonic ?D
+ :charset-list '(cp850)
+ :mime-charset 'cp850)
+(define-coding-system-alias 'ibm850 'cp850)
+
+(define-coding-system 'cp852
+ "DOS codepage 852 (Slavic)"
+ :coding-type 'charset
+ :mnemonic ?D
+ :charset-list '(cp852)
+ :mime-charset 'cp852)
+(define-coding-system-alias 'ibm852 'cp852)
+
+(define-coding-system 'cp857
+ "DOS codepage 857 (Turkish)"
+ :coding-type 'charset
+ :mnemonic ?D
+ :charset-list '(cp857)
+ :mime-charset 'cp857)
+(define-coding-system-alias 'ibm857 'cp857)
+
+(define-coding-system 'cp858
+ "Codepage 858 (Multilingual Latin I + Euro)"
+ :coding-type 'charset
+ :mnemonic ?D
+ :charset-list '(cp858)
+ :mime-charset 'cp858)
+
+(define-coding-system 'cp860
+ "DOS codepage 860 (Portuguese)"
+ :coding-type 'charset
+ :mnemonic ?D
+ :charset-list '(cp860)
+ :mime-charset 'cp860)
+(define-coding-system-alias 'ibm860 'cp860)
+
+(define-coding-system 'cp861
+ "DOS codepage 861 (Icelandic)"
+ :coding-type 'charset
+ :mnemonic ?D
+ :charset-list '(cp861)
+ :mime-charset 'cp861)
+(define-coding-system-alias 'ibm861 'cp861)
+
+(define-coding-system 'cp863
+ "DOS codepage 863 (French Canadian)"
+ :coding-type 'charset
+ :mnemonic ?D
+ :charset-list '(cp863)
+ :mime-charset 'cp863)
+(define-coding-system-alias 'ibm863 'cp863)
+
+(define-coding-system 'cp865
+ "DOS codepage 865 (Norwegian/Danish)"
+ :coding-type 'charset
+ :mnemonic ?D
+ :charset-list '(cp865)
+ :mime-charset 'cp865)
+(define-coding-system-alias 'ibm865 'cp865)
+
+(define-coding-system 'cp437
+ "DOS codepage 437"
+ :coding-type 'charset
+ :mnemonic ?D
+ :charset-list '(cp437)
+ :mime-charset 'cp437)
+(define-coding-system-alias 'ibm437 'cp437)
+\f
+(set-language-info-alist
+ "German" '((tutorial . "TUTORIAL.de")
+ (charset iso-8859-1)
+ (coding-system iso-latin-1 iso-latin-9)
+ (coding-priority iso-latin-1)
+ (nonascii-translation . iso-8859-1)
+ (input-method . "german-postfix")
+ (unibyte-syntax . "latin-1")
+ (unibyte-display . iso-latin-1)
+ (sample-text . "\
+German (Deutsch Nord) Guten Tag
+German (Deutsch S\e,A|\e(Bd) Gr\e,A|_\e(B Gott")
+ (documentation . "\
+This language environment is almost the same as Latin-1,
+but sets the default input method to \"german-postfix\".
+Additionally, it selects the German tutorial."))
+ '("European"))
+
+(set-language-info-alist
+ "French" '((tutorial . "TUTORIAL.fr")
+ (charset iso-8859-1)
+ (coding-system iso-latin-1 iso-latin-9)
+ (coding-priority iso-latin-1)
+ (nonascii-translation . iso-8859-1)
+ (unibyte-syntax . "latin-1")
+ (unibyte-display . iso-latin-1)
+ (input-method . "latin-1-prefix")
+ (sample-text . "French (Fran\e,Ag\e(Bais) Bonjour, Salut")
+ (documentation . "\
+This language environment is almost the same as Latin-1,
+but it selects the French tutorial."))
+ '("European"))
+
+(set-language-info-alist
+ "Slovenian" '((charset iso-8859-2)
+ (coding-system . (iso-8859-2 windows-1250))
+ (coding-priority . (iso-8859-2))
+ (nonascii-translation . iso-8859-2)
+ (input-method . "latin-2-postfix")
+ (unibyte-syntax . "latin-2")
+ (unibyte-display . iso-8859-2)
+ (tutorial . "TUTORIAL.sl")
+ (sample-text . "\e,B.\e(Belimo vam uspe\e,B9\e(Ben dan!")
+ (documentation . t))
+ '("European"))
+
+(set-language-info-alist
+ "Spanish" '((tutorial . "TUTORIAL.es")
+ (charset iso-8859-1)
+ (coding-system iso-latin-1 iso-latin-9)
+ (coding-priority iso-latin-1)
+ (nonascii-translation . iso-8859-1)
+ (input-method . "spanish-postfix")
+ (unibyte-syntax . "latin-1")
+ (unibyte-display . iso-latin-1)
+ (sample-text . "Spanish (Espa\e,Aq\e(Bol) \e,A!\e(BHola!")
+ (documentation . "\
+This language environment is almost the same as Latin-1,
+but it sets the default input method to \"spanish-postfix\",
+and it selects the Spanish tutorial."))
+ '("European"))
+
+(set-language-info-alist
+ "Dutch" '((tutorial . "TUTORIAL.nl")
+ (charset iso-8859-1)
+ (coding-system iso-latin-1 iso-latin-9)
+ (coding-priority iso-latin-1)
+ (nonascii-translation . iso-8859-1)
+ (unibyte-syntax . "latin-1")
+ (unibyte-display . iso-latin-1)
+ (input-method . "dutch")
+ (sample-text . "Er is een aantal manieren waarop je dit kan doen")
+ (documentation . "\
+This language environment is almost the same as Latin-1,
+but it selects the Dutch tutorial and input method."))
+ '("European"))
+
+;; For Turkish, the character set ISO-8859-9 (Latin-5) is used. But,
+;; before the introduction of ISO-8859-9 in 1988, ISO-8859-3 (Latin-3)
+;; was used for Turkish. Those who use Latin-3 for Turkish should use
+;; "Latin-3" language environment.
+
+(set-language-info-alist
+ "Turkish" '((charset iso-8859-9)
+ (coding-system iso-latin-5 windows-1254 iso-latin-3)
+ (coding-priority iso-latin-5)
+ (nonascii-translation . iso-8859-9)
+ (unibyte-syntax . "latin-5")
+ (unibyte-display . iso-latin-5)
+ (input-method . "turkish-postfix")
+ (sample-text . "Turkish (T\e,A|\e(Brk\e,Ag\e(Be) Merhaba")
+ (setup-function
+ . (lambda ()
+ (set-case-syntax-pair ?I ?\e,C9\e(B (standard-case-table))
+ (set-case-syntax-pair ?\e,C)\e(B ?i (standard-case-table))))
+ (exit-function
+ . (lambda ()
+ (set-case-syntax-pair ?I ?i (standard-case-table))
+ (set-case-syntax ?\e,C9\e(B "w" (standard-case-table))
+ (set-case-syntax ?\e,C)\e(B "w" (standard-case-table))))
+ (documentation . "Support for Turkish.
+Differs from the Latin-5 environment in using the `turkish-postfix' input
+method and applying Turkish case rules for the characters i, I, \e,C9\e(B, \e,C)\e(B.")))
+
+;; Polish ISO 8859-2 environment.
+;; Maintainer: Wlodek Bzyl <matwb@univ.gda.pl>
+;; Keywords: multilingual, Polish
+
+(set-language-info-alist
+ "Polish" '((charset . (iso-8859-2))
+ (coding-system . (iso-8859-2 windows-1250))
+ (coding-priority . (iso-8859-2))
+ (nonascii-translation . iso-8859-2)
+ (input-method . "polish-slash")
+ (unibyte-syntax . "latin-2")
+ (unibyte-display . iso-8859-2)
+ (tutorial . "TUTORIAL.pl")
+ (sample-text . "P\e,As\e(Bjd\e,B<\e(B, ki\e,Bq\e(B-\e,B?\e(Be t\e,Bj\e(B chmurno\e,B6f\e(B w g\e,B31\e(Bb flaszy")
+ (documentation . t))
+ '("European"))
+
+(set-language-info-alist
+ "Welsh" `((coding-system utf-8 latin-8) ; the input method is Unicode-based
+ (coding-priority utf-8 latin-8)
+ (nonascii-translation . iso-8859-14)
+ (input-method . "welsh")
+ (documentation . "Support for Welsh, using Unicode."))
+ '("European"))
+
+(set-language-info-alist
+ "Latin-7" `((coding-system latin-7)
+ (coding-priority latin-7)
+ (nonascii-translation . iso-8859-13)
+ ;; Fixme: input-method
+ (documentation . "Support for Latin-7, e.g. Latvian, Lithuanian."))
+ '("European"))
+
+(set-language-info-alist
+ "Lithuanian" `((coding-system latin-7 windows-1257)
+ (coding-priority latin-7)
+ (nonascii-translation . iso-8859-13)
+ (input-method . "lithuanian-keyboard")
+ (documentation . "Support for Lithuanian."))
+ '("European"))
+
+(set-language-info-alist
+ "Latvian" `((coding-system latin-7 windows-1257)
+ (coding-priority latin-7)
+ (nonascii-translation . iso-8859-13)
+ (input-method . "latvian-keyboard")
+ (documentation . "Support for Latvian."))
+ '("European"))
+
+\f
+(define-coding-system 'mac-roman
+ "Mac Roman Encoding (MIME:MACINTOSH)."
+ :coding-type 'charset
+ :mnemonic ?M
+ :charset-list '(mac-roman)
+ :mime-charset 'macintosh)
+
+(define-coding-system 'next
+ "NeXTstep encoding"
+ :coding-type 'charset
+ :mnemonic ?*
+ :charset-list '(next)
+ :mime-charset 'next)
+
+(define-coding-system 'hp-roman8
+ "Hewlet-Packard roman-8 encoding (MIME:ROMAN-8)"
+ :coding-type 'charset
+ :mnemonic ?*
+ :charset-list '(hp-roman8)
+ :mime-charset 'hp-roman8)
+(define-coding-system-alias 'roman8 'hp-roman8)
+
+(define-coding-system 'adobe-standard-encoding
+ "Adobe `standard' encoding for PostScript"
+ :coding-type 'charset
+ :mnemonic ?*
+ :charset-list '(adobe-standard-encoding)
+ :mime-charset 'adobe-standard-encoding)
+\f
+(defconst diacritic-composition-pattern "\\C^\\c^+")
+
+(defun diacritic-compose-region (beg end)
+ "Compose diacritic characters in the region.
+When called from a program, expects two arguments,
+positions (integers or markers) specifying the region."
+ (interactive "r")
+ (save-restriction
+ (narrow-to-region beg end)
+ (goto-char (point-min))
+ (while (re-search-forward diacritic-composition-pattern nil t)
+ (compose-region (match-beginning 0) (match-end 0)))))
+
+(defun diacritic-compose-string (string)
+ "Compose diacritic characters in STRING and return the resulting string."
+ (let ((idx 0))
+ (while (setq idx (string-match diacritic-composition-pattern string idx))
+ (compose-string string idx (match-end 0))
+ (setq idx (match-end 0))))
+ string)
+
+(defun diacritic-compose-buffer ()
+ "Compose diacritic characters in the current buffer."
(interactive)
- (setup-8-bit-environment "Latin-5" 'latin-iso8859-9 'iso-latin-5
- "latin-5-prefix"))
-
-(set-language-info-alist
- "Latin-5" '((setup-function . (setup-latin5-environment
- . setup-european-environment-map))
- (charset . (ascii latin-iso8859-9))
- (coding-system . (iso-latin-5))
- (documentation . ("\
-These languages are supported with the Latin-5 (ISO-8859-9) character set.
-" . describe-european-environment-map))
- ))
+ (diacritic-compose-region (point-min) (point-max)))
+
+(defun diacritic-post-read-conversion (len)
+ (diacritic-compose-region (point) (+ (point) len))
+ len)
+
+(defun diacritic-composition-function (from to pattern &optional string)
+ "Compose diacritic text in the region FROM and TO.
+The text matches the regular expression PATTERN.
+Optional 4th argument STRING, if non-nil, is a string containing text
+to compose.
+
+The return value is number of composed characters."
+ (if (< (1+ from) to)
+ (prog1 (- to from)
+ (if string
+ (compose-string string from to)
+ (compose-region from to))
+ (- to from))))
+
+;; Register a function to compose Unicode diacrtics and marks.
+(let ((patterns '(("\\C^\\c^+" . diacritic-composition-function))))
+ (let ((c #x300))
+ (while (<= c #x362)
+ (aset composition-function-table c patterns)
+ (setq c (1+ c)))
+ (setq c #x20d0)
+ (while (<= c #x20e3)
+ (aset composition-function-table c patterns)
+ (setq c (1+ c)))))
+
+(provide 'european)
;;; european.el ends here