view lisp/mule/european.el @ 771:943eaba38521

[xemacs-hg @ 2002-03-13 08:51:24 by ben] The big ben-mule-21-5 check-in! Various files were added and deleted. See CHANGES-ben-mule. There are still some test suite failures. No crashes, though. Many of the failures have to do with problems in the test suite itself rather than in the actual code. I'll be addressing these in the next day or so -- none of the test suite failures are at all critical. Meanwhile I'll be trying to address the biggest issues -- i.e. build or run failures, which will almost certainly happen on various platforms. All comments should be sent to ben@xemacs.org -- use a Cc: if necessary when sending to mailing lists. There will be pre- and post- tags, something like pre-ben-mule-21-5-merge-in, and post-ben-mule-21-5-merge-in.
author ben
date Wed, 13 Mar 2002 08:54:06 +0000
parents 4d00488244c1
children 2923009caf47
line wrap: on
line source

;;; european.el --- European languages -*- coding: iso-2022-7bit; -*-

;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
;; Licensed to the Free Software Foundation.
;; Copyright (C) 1997 MORIOKA Tomohiko
;; Copyright (C) 2001 Ben Wing.
;; Copyright (C) 2002 Free Software Foundation

;; Keywords: multilingual, European

;; This file is part of XEmacs.

;; XEmacs is free software; you can redistribute it and/or modify it
;; under the terms of the GNU General Public License as published by
;; the Free Software Foundation; either version 2, or (at your option)
;; any later version.

;; XEmacs is distributed in the hope that it will be useful, but
;; WITHOUT ANY WARRANTY; without even the implied warranty of
;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
;; General Public License for more details.

;; You should have received a copy of the GNU General Public License
;; along with XEmacs; see the file COPYING.  If not, write to the Free
;; Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
;; 02111-1307, USA.

;;; Commentary:

;; Support six Latin coded character sets ISO8859-1,2,3,4,9,15.

;; #### latin.el would be a better name for this file.

;;; Code:

;; For syntax of Latin-1 characters.
(loop for c from 64 to 127              ; from ',A@(B' to ',A(B'
      do (modify-syntax-entry (make-char 'latin-iso8859-1 c) "w"))

(modify-syntax-entry (make-char 'latin-iso8859-1 32) "w") ; no-break space
(modify-syntax-entry ?,AW(B "_")
(modify-syntax-entry ?,Aw(B "_")

;; For syntax of Latin-9 characters.
;; Based on Latin-1 and differences from Jukka Korpela
;; http://www.cs.tut.fi/~jkorpela/latin9.html
(loop for c in '(?,b&(B ?,b((B ?,b4(B ?,b8(B ?,b<(B ?,b=(B ?,b>(B)
      do (modify-syntax-entry c "w"))

(loop for c from 64 to 127              ; from ',b@(B' to ',b(B'
      do (modify-syntax-entry (make-char 'latin-iso8859-1 c) "w"))

(modify-syntax-entry (make-char 'latin-iso8859-15 32) "w") ; no-break space
(modify-syntax-entry ?,bW(B "_")
(modify-syntax-entry ?,bw(B "_")

;; For syntax of Latin-2
(loop for c in '(?,B!(B ?,B#(B ?,B%(B ?,B&(B ?,B)(B ?,B*(B ?,B+(B ?,B,(B ?,B.(B ?,B/(B ?,B1(B ?,B3(B ?,B5(B ?,B6(B ?,B9(B ?,B:(B ?,B;(B ?,B<(B)
      do (modify-syntax-entry c "w"))

(loop for c from 62 to 126
      do (modify-syntax-entry (make-char 'latin-iso8859-2 c) "w"))

(modify-syntax-entry (make-char 'latin-iso8859-2 32) "w") ; no-break space
(modify-syntax-entry ?,BW(B ".")
(modify-syntax-entry ?,Bw(B ".")

;; For syntax of Latin-3
(loop for c in '(?,C!(B ?,C&(B ?,C)(B ?,C*(B ?,C+(B ?,C,(B ?,C/(B ?,C1(B ?,C5(B ?,C6(B ?,C:(B ?,C;(B ?,C<(B ?,C?(B)
  do (modify-syntax-entry c "w"))

(loop for c from 64 to 126
  do (modify-syntax-entry (make-char 'latin-iso8859-3 c) "w"))

(modify-syntax-entry (make-char 'latin-iso8859-3 32) "w") ; no-break space
(modify-syntax-entry ?,CW(B ".")
(modify-syntax-entry ?,Cw(B ".")

;; For syntax of Latin-4
(loop for c in '(?,D!(B ?,D"(B ?,D#(B ?,D%(B ?,D&(B ?,D)(B ?,D*(B ?,D+(B ?,D,(B ?,D.(B ?,D1(B ?,D3(B ?,D5(B ?,D6(B ?,D9(B ?,D:(B ?,D;(B ?,D<(B ?,D=(B ?,D>(B ?,D?(B)
  do (modify-syntax-entry c "w"))

(loop for c from 64 to 126
  do (modify-syntax-entry (make-char 'latin-iso8859-4 c) "w"))

(modify-syntax-entry (make-char 'latin-iso8859-4 32) "w") ; no-break space
(modify-syntax-entry ?,DW(B ".")
(modify-syntax-entry ?,Dw(B ".")


;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;;; EUROPEANS
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;


;; Latin-1 (ISO-8859-1)

;; (make-coding-system
;;  'iso-latin-1 2 ?1
;;  "ISO 2022 based 8-bit encoding for Latin-1 (MIME:ISO-8859-1)"
;;  '(ascii latin-iso8859-1 nil nil
;;    nil nil nil nil nil nil nil nil nil nil nil nil t)
;;  '((safe-charsets ascii latin-iso8859-1)
;;    (mime-charset . iso-8859-1)))

;; (define-coding-system-alias 'iso-8859-1 'iso-latin-1)
;; (define-coding-system-alias 'latin-1 'iso-latin-1)

;; (make-coding-system
;;  'compound-text 2 ?1
;;  "ISO 2022 based encoding used in inter client communication of X"
;;  '((ascii t) (latin-iso8859-1 t) nil nil
;;    nil ascii-eol ascii-cntl nil nil nil nil nil nil nil nil nil t)
;;  '((safe-charsets . t)))

;; (define-coding-system-alias 'ctext 'compound-text)

;; "Hello, Hej, Tere, Hei, Bonjour, Gr,A|_(B Gott, Ciao, ,A!(BHola!"


;; Latin-9 (ISO-8859-15)
;; Latin-1 plus Euro, plus a few accented characters

;; (make-charset 'latin-iso8859-15
;;   "Latin-9, aka Latin-1 with Euro etc"
;;   '(short-name "Latin 9"
;;     long-name  "Latin-9 (typically GR of ISO 8859/15)"
;;     registry   "iso8859-15"
;;     dimension  1
;;     columns    1
;;     chars      96
;;     final      ?b                  ; ISO-IR-203
;;     graphic    1
;;     direction  l2r))

(make-coding-system
 'iso-8859-15 'iso2022
  "ISO 4873 conforming 8-bit code (ASCII + Latin 9; aka Latin-1 with Euro)"
  `(mnemonic "MIME/Ltn-9"		; bletch
    eol-type nil
    charset-g0 ascii
    charset-g1 latin-iso8859-15
    charset-g2 t
    charset-g3 t
    ))


;; Latin-2 (ISO-8859-2)

;; (make-coding-system
;;  'iso-latin-2 2 ?2
;;  "ISO 2022 based 8-bit encoding (MIME:ISO-8859-2)"
;;  '(ascii latin-iso8859-2 nil nil
;;    nil nil nil nil nil nil nil)
;;  '((safe-charsets ascii latin-iso8859-2)
;;    (mime-charset . iso-8859-2)))

;; (define-coding-system-alias 'iso-8859-2 'iso-latin-2)
;; (define-coding-system-alias 'latin-2 'iso-latin-2)

(make-coding-system
 'iso-8859-2 'iso2022 "ISO-8859-2 (Latin-2)"
 '(charset-g0 ascii
   charset-g1 latin-iso8859-2
   charset-g2 t
   charset-g3 t
   mnemonic "MIME/Ltn-2"
   ))

(provide 'romanian)

;; Czech support originally from czech.el
;; Author: Milan Zamazal <pdm@fi.muni.cz>
;; Maintainer(for XEmacs): David Sauer <davids@penguin.cz>

(provide 'czech)

;; Slovak support originally from slovak.el
;; Authors:    Tibor ,B)(Bimko <tibor.simko@fmph.uniba.sk>,
;;             Milan Zamazal <pdm@fi.muni.cz>
;; Maintainer: Milan Zamazal <pdm@fi.muni.cz>

(provide 'slovenian)


;; Latin-3 (ISO-8859-3)

;; (make-coding-system
;;  'iso-latin-3 2 ?3
;;  "ISO 2022 based 8-bit encoding (MIME:ISO-8859-3)"
;;  '(ascii latin-iso8859-3 nil nil
;;    nil nil nil nil nil nil nil)
;;  '((safe-charsets ascii latin-iso8859-3)
;;    (mime-charset . iso-8859-3)))

;; (define-coding-system-alias 'iso-8859-3 'iso-latin-3)
;; (define-coding-system-alias 'latin-3 'iso-latin-3)

(make-coding-system
 'iso-8859-3 'iso2022 "ISO-8859-3 (Latin-3)"
 '(charset-g0 ascii
   charset-g1 latin-iso8859-3
   charset-g2 t
   charset-g3 t
   mnemonic "MIME/Ltn-3"
   ))


;; Latin-4 (ISO-8859-4)

;; (make-coding-system
;;  'iso-latin-4 2 ?4
;;  "ISO 2022 based 8-bit encoding (MIME:ISO-8859-4)"
;;  '(ascii latin-iso8859-4 nil nil
;;    nil nil nil nil nil nil nil)
;;  '((safe-charsets ascii latin-iso8859-4)
;;    (mime-charset . iso-8895-4)))

;; (define-coding-system-alias 'iso-8859-4 'iso-latin-4)
;; (define-coding-system-alias 'latin-4 'iso-latin-4)

(make-coding-system
 'iso-8859-4 'iso2022 "ISO-8859-4 (Latin-4)"
 '(charset-g0 ascii
   charset-g1 latin-iso8859-4
   charset-g2 t
   charset-g3 t
   mnemonic "MIME/Ltn-4"
   ))


;; Latin-5 (ISO-8859-9)

;; (make-coding-system
;;  'iso-latin-5 2 ?9
;;  "ISO 2022 based 8-bit encoding (MIME:ISO-8859-9)"
;;  '(ascii latin-iso8859-9 nil nil
;;    nil nil nil nil nil nil nil)
;;  '((safe-charsets ascii latin-iso8859-9)
;;    (mime-charset . iso-8859-9)))

;; (define-coding-system-alias 'iso-8859-9 'iso-latin-5)
;; (define-coding-system-alias 'latin-5 'iso-latin-5)

(make-coding-system
 'iso-8859-9 'iso2022 "ISO-8859-9 (Latin-5)"
 '(charset-g0 ascii
   charset-g1 latin-iso8859-9
   charset-g2 t
   charset-g3 t
   mnemonic "MIME/Ltn-5"
   ))

(loop for ((charset codesys default-input nice-charset-1 nice-charset-2
		    supported-langs ;; a list if the doc string is replaced
				    ;; entirely
		    )
	   langenvs) in
  '(
    ((latin-iso8859-1 iso-8859-1 "latin-1-prefix" "Latin-1" "ISO-8859-1"
" Danish, Dutch, English, Faeroese, Finnish, French, German, Icelandic,
 Irish, Italian, Norwegian, Portuguese, Spanish, and Swedish.")
     (("Danish" "da")
      ("Dutch" "nl" "TUTORIAL.nl")
      ("Faeroese")
      ("Finnish" "fi")
      ("French" "fr" "TUTORIAL.fr" "Bonjour, ,Ag(Ba va?")
      ("German" "de" "TUTORIAL.de" "\
German (Deutsch Nord)	Guten Tag
German (Deutsch S,A|(Bd)	Gr,A|_(B Gott"
       "german-postfix")
      ("Icelandic" "is")
      ("Irish" "ga")
      ("Italian" "it")
      ("Norwegian" "no" "TUTORIAL.no")
      ("Portuguese" "pt" nil "Bem-vindo! Tudo bem?")
      ("Spanish" "es" "TUTORIAL.es" ",A!(BHola!")
      ("Swedish" "sv")))
    ((latin-iso8859-15 iso-8859-15 "latin-1-prefix" ;; #### FIXME
		       "Latin-9" "ISO-8859-15"
		       ("\
This language environment is a generic one for Latin-9 (ISO-8859-15)
character set which supports the Euro sign and the following languages
(they use the Latin-1 character set by default):
 Danish, Dutch, English, Faeroese, Finnish, French, German, Icelandic,
 Irish, Italian, Norwegian, Portuguese, Spanish, and Swedish.
Each also has its own specific language environment."))
     ())
    ((latin-iso8859-2 iso-8859-2 "latin-2-prefix" "Latin-2" "ISO-8859-2"
" Albanian, Czech, English, German, Hungarian, Polish, Romanian,
 Serbian, Croatian, Slovak, Slovene, Sorbian (upper and lower),
 and Swedish.")
     (("Albanian" nil)
      ("Croatian" ("hrvatski" "hr") "TUTORIAL.hr")
      ("Czech" ("cs" "cz") "TUTORIAL.cs" "P,Bx(Bejeme v,Ba(Bm hezk,B}(B den!"
       "latin-2-postfix")
      ("Hungarian" ("hungarian" "hu"))
      ("Polish" "po" "TUTORIAL.pl")
      ("Romanian" "ro" "TUTORIAL.ro" "Bun,Bc(B ziua, bine a,B~(Bi venit!"
       "latin-2-postfix")
      ("Serbian" "sr")
      ("Slovak" "sk" "TUTORIAL.sk" "Prajeme V,Ba(Bm pr,Bm(Bjemn,B}(B de,Br(B!"
       ;; !!#### FSF "slovak"
       "latin-2-postfix")
      ("Slovenian" "sl" "TUTORIAL.sl" ",B.(Belimo vam uspe,B9(Ben dan!"
       "latin-2-postfix")
      ("Sorbian" nil)))
    ((latin-iso8859-3 iso-8859-3 "latin-3-prefix" "Latin-3" "ISO-8859-3"
" Afrikaans, Catalan, Dutch, English, Esperanto, French, Galician,
 German, Italian, Maltese, Spanish, and Turkish.")
     (("Afrikaans" "af")
      ("Catalan" ("catalan" "ca"))
      ("Esperanto")
      ("Galician")
      ("Maltese")))
    ((latin-iso8859-4 iso-8859-4 "latin-4-prefix" "Latin-4" "ISO-8859-4"
" Danish, English, Estonian, Finnish, German, Greenlandic, Lappish,
 Latvian, Lithuanian, and Norwegian.")
     (("Estonian" "et")
      ("Greenlandic")
      ("Lappish")
      ("Latvian" "lv")
      ("Lithuanian" "li")))
    ((latin-iso8859-5 iso-8859-9 "latin-5-prefix" "Latin-5" "ISO-8859-9")
     (("Turkish" "tr"))))
  do
  (set-language-info-alist
   nice-charset-1
   `((charset ascii ,charset)
     (coding-system ,codesys)
     (coding-priority ,codesys)
     (documentation . ,(if (listp supported-langs) (car supported-langs)
			 (format "\
This language environment is a generic one for %s (%s)
character set which supports the following languages (not all of them may
use this character set by default):
%s
Each also has its own specific language environment."
				 nice-charset-1 nice-charset-2
				 supported-langs))))
   '("European"))
  (loop for (name locale tutorial sample-text input-method) in langenvs
    do
    (set-language-info-alist
     name
     `((charset ascii ,charset)
       (coding-system ,codesys)
       (coding-priority ,codesys)
       ,@(if locale `((locale . ,locale)))
       ,@(if tutorial `((tutorial . ,tutorial)))
       ,@(if sample-text `((sample-text . ,sample-text)))
       (input-method . ,(or input-method default-input))
       (documentation . ,(format "\
This language environment supports %s using the Latin-1 (ISO-8859-1)
character set.  Languages supported by Latin-1 are Danish, Dutch, English,
Faeroese, Finnish, French, German, Icelandic, Irish, Italian, Norwegian,
Portuguese, Spanish, and Swedish.  The various language environments for
these languages are similar to the Latin-1 environment, but typically have
their own locale specified (for subprocesses and for selection of the
correct language environment at startup), and may have their own tutorials
and/or a different input method."
			       name)))
     '("European"))
    ))

;;; european.el ends here