Mercurial > hg > xemacs-beta

view lisp/mule/european.el @ 788:026c5bf9c134

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
[xemacs-hg @ 2002-03-21 07:29:57 by ben] chartab.c: Fix bugs in implementation and doc strings. config.h.in: Add foo_checking_assert_at_line() macros. Not clear whether these are actually useful, though; I'll take them out if not. symsinit.h, emacs.c: Some improvements to the timeline. Rearrange a bit the init calls. Add call for reinit_vars_of_object_mswindows() and declare in symsinit.h. event-Xt.c, event-gtk.c, event-msw.c, event-stream.c, event-tty.c, events.c, events.h: Introduce new event methods for printing, comparing, and hashing magic events, to avoid event-type-specific stuff that had crept into events.c. (And was crashing, since the channel in MS Windows magic events may be nil.) Implement the methods in event-{tty,gtk,Xt,mswindows}.c. Make wrapping functions event_stream_{compare,hash,format}_magic_event() to check if everything's OK and call the actual callback. Fix events.c to use the new methods. Add a new event-stream-operation EVENT_STREAM_NOTHING -- event stream not actually required to be able to do anything, just be open. (#### This event-stream-operation stuff needs to be rethought.) Fixed describe_event() in event-Xt.c to print its output to a stream, not always to stderr, so it can be used elsewhere. (e.g. in print-event when a magic event is encountered?) lisp.h, lrecord.h: Define new assert_at_line(), for use in asserts inside of inline functions. The assert will report the line and file of the inline function, which is almost certainly not what you want as it's useless. what you want to see is where the pseudo-macro was called from. So, when error-checking is on, we pass in the line and file into the macros, for accurate printout using assert_at_line(). Happens only when error-checking is defined so doesn't slow down non-error-checking builds. Fix XCHAR, XINT, XCHAR_OR_INT, XFOO, and wrap_foo() in this fashion. lstream.c, lstream.h: Add resizing_buffer_to_lisp_string(). objects-gtk.c: Fix typo. objects-msw.c: Implement a smarter way of determining whether a font matches a charset. Formerly we just looked at the "script" element of the font spec, converted it to a code page, and compared it with the code page derived from the charset. Now, as well as doing this, we ask the font for the list of unicode ranges it supports, see what range the charset falls into (#### bogus! need to do this char-by-char), and see if any of the font's supported ranges include the charset's range. also do some caching in Vfont_signature_data of previous inquiries. charset.h, text.c, mule-charset.c: New fun; extracted out of Fmake_char() and declare prototype in charset.h. text.h: introduce assert_by_line() to make REP_BYTES_BY_FIRST_BYTE report the file and line more accurately in an assertion failure. unicode.c: make non-static (used in objects-msw.c), declare in charset.h. mule\mule-category.el: Start implementing a category API compatible with FSF. Not there yet. We need improvements to char-tables. mule\mule-charset.el: Copy translation table code from FSF 21.1 and fix up. Eventually we'll have them in XEmacs. (used in ccl) Not here quite yet, and we need some improvements to char-tables. mule\cyril-util.el, mule\cyrillic.el, mule\devan-util.el, mule\ethio-util.el, mule\korea-util.el, mule\mule-tty-init.el, mule\tibet-util.el, mule\viet-util.el, mule\vietnamese.el: Fix numerous compilation warnings. Fix up code related to translation tables and other types of char-tables. menubar-items.el: Move the frame commands from the View menu to the File menu, to be consistent with how most other programs do things. Move less-used revert/recover items to a submenu. Make "recover" not prompt for a file, but recover the current buffer. TODO.ben-mule-21-5: Create bug list for latest problems.
author ben
date Thu, 21 Mar 2002 07:31:30 +0000
parents 2923009caf47
children 602aa4ed9900
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:
; (make-charset 'latin-iso8859-1 
; 	      "Right-Hand Part of Latin Alphabet 1 (ISO/IEC 8859-1): ISO-IR-100"
; 	      '(dimension
; 		1
; 		registry "ISO8859-1"
; 		chars 96
; 		columns 1
; 		direction l2r
; 		final ?A
; 		graphic 1
; 		short-name "RHP of Latin-1"
; 		long-name "RHP of Latin-1 (ISO 8859-1): ISO-IR-100"
; 		))

; (make-charset 'latin-iso8859-2 
; 	      "Right-Hand Part of Latin Alphabet 2 (ISO/IEC 8859-2): ISO-IR-101"
; 	      '(dimension
; 		1
; 		registry "ISO8859-2"
; 		chars 96
; 		columns 1
; 		direction l2r
; 		final ?B
; 		graphic 1
; 		short-name "RHP of Latin-2"
; 		long-name "RHP of Latin-2 (ISO 8859-2): ISO-IR-101"
; 		))

; (make-charset 'latin-iso8859-3 
; 	      "Right-Hand Part of Latin Alphabet 3 (ISO/IEC 8859-3): ISO-IR-109"
; 	      '(dimension
; 		1
; 		registry "ISO8859-3"
; 		chars 96
; 		columns 1
; 		direction l2r
; 		final ?C
; 		graphic 1
; 		short-name "RHP of Latin-3"
; 		long-name "RHP of Latin-3 (ISO 8859-3): ISO-IR-109"
; 		))

; (make-charset 'latin-iso8859-4 
; 	      "Right-Hand Part of Latin Alphabet 4 (ISO/IEC 8859-4): ISO-IR-110"
; 	      '(dimension
; 		1
; 		registry "ISO8859-4"
; 		chars 96
; 		columns 1
; 		direction l2r
; 		final ?D
; 		graphic 1
; 		short-name "RHP of Latin-4"
; 		long-name "RHP of Latin-4 (ISO 8859-4): ISO-IR-110"
; 		))

; (make-charset 'latin-iso8859-9 
; 	      "Right-Hand Part of Latin Alphabet 5 (ISO/IEC 8859-9): ISO-IR-148"
; 	      '(dimension
; 		1
; 		registry "ISO8859-9"
; 		chars 96
; 		columns 1
; 		direction l2r
; 		final ?M
; 		graphic 1
; 		short-name "RHP of Latin-5"
; 		long-name "RHP of Latin-5 (ISO 8859-9): ISO-IR-148"
; 		))

; (make-charset 'latin-iso8859-15 
; 	      "Right-Hand Part of Latin Alphabet 9 (ISO/IEC 8859-15): ISO-IR-203"
; 	      '(dimension
; 		1
; 		registry "ISO8859-15"
; 		chars 96
; 		columns 1
; 		direction l2r
; 		final ?b
; 		graphic 1
; 		short-name "RHP of Latin-9"
; 		long-name "RHP of Latin-9 (ISO 8859-15): ISO-IR-203"
; 		))

(make-charset 'latin-iso8859-14 
	      "Right-Hand Part of Latin Alphabet 8 (ISO/IEC 8859-14)"
	      '(dimension
		1
		registry "ISO8859-14"
		chars 96
		columns 1
		direction l2r
		final ?_
		graphic 1
		short-name "RHP of Latin-8"
		long-name "RHP of Latin-8 (ISO 8859-14)"
		))


;; 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@zamazal.org>
;; Maintainer (FSF): Pavel Jan,Am(Bk <Pavel@Janik.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