view lisp/international/mule-conf.el @ 19860:c17fd465ea95 libc-970911 libc-970912 libc-970913 libc-970914 libc-970915 libc-970916 libc-970917 libc-970918 libc-970919 libc-970920 libc-970921 libc-970922 libc-970923 libc-970924 libc-970925 libc-970926 libc-970927 libc-970928 libc-970929 libc-970930 libc-971001 libc-971018 libc-971019 libc-971020 libc-971021 libc-971022 libc-971023 libc-971024 libc-971025 libc-971026 libc-971027 libc-971028 libc-971029 libc-971030 libc-971031 libc-971101 libc-971102 libc-971103 libc-971104 libc-971105 libc-971106 libc-971107 libc-971108 libc-971109 libc-971110 libc-971111 libc-971112 libc-971113 libc-971114 libc-971115 libc-971116 libc-971117 libc-971118 libc-971120 libc-971121 libc-971122 libc-971123 libc-971124 libc-971125 libc-971126 libc-971127 libc-971128 libc-971129 libc-971130 libc-971201 libc-971203 libc-971204 libc-971205 libc-971206 libc-971207 libc-971208 libc-971209 libc-971210 libc-971211 libc-971212 libc-971213 libc-971214 libc-971217 libc-971218 libc-971219 libc-971220 libc-971221 libc-971222 libc-971223 libc-971224 libc-971225 libc-971226 libc-971227 libc-971228 libc-971229 libc-971230 libc-971231 libc-980103 libc-980104 libc-980105 libc-980106 libc-980107 libc-980108 libc-980109 libc-980110 libc-980111 libc-980112 libc-980114 libc-980115 libc-980116 libc-980117 libc-980118 libc-980119 libc-980120 libc-980121 libc-980122 libc-980123 libc-980124 libc-980125 libc-980126 libc-980127 libc-980128

typos.
author Jeff Law <law@redhat.com>
date Wed, 10 Sep 1997 21:16:20 +0000
parents 59d864067cdb
children 99b8a866c50a
line wrap: on
line source

;;; mule-conf.el --- configure multilingual environment

;; Copyright (C) 1997 Electrotechnical Laboratory, JAPAN.
;; Licensed to the Free Software Foundation.

;; Keywords: mule, multilingual, character set, coding system

;; This file is part of GNU Emacs.

;; GNU Emacs 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.

;; GNU Emacs 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 GNU Emacs; see the file COPYING.  If not, write to the
;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
;; Boston, MA 02111-1307, USA.

;;; Commentary:

;; Don't byte-compile this file.

;;; Code:

;;; Definitions of character sets.

;; Basic (official) character sets.  These character sets are treated
;; effectively in the aspect of memory in a buffer.

;; Syntax:
;; (define-charset CHARSET-ID CHARSET
;;   [ DIMENSION CHARS WIDTH DIRECTION ISO-FINAL-CHAR ISO-GRAPHIC-PLANE
;;     SHORT-NAME LONG-NAME DESCRIPTION ])
;; ASCII charset is defined in src/charset.c as below.
;; (define-charset 0 ascii
;;    [1 94 1 0 ?B 0 "ASCII" "ASCII" "ASCII (ISO646 IRV)"])

(define-charset 129 'latin-iso8859-1
  [1 96 1 0 ?A 1 "Latin-1" "ISO8859-1 (Latin-1)" "ISO8859-1 (Latin-1)"])
(define-charset 130 'latin-iso8859-2
  [1 96 1 0 ?B 1 "Latin-2" "ISO8859-2 (Latin-2)" "ISO8859-2 (Latin-2)"])
(define-charset 131 'latin-iso8859-3
  [1 96 1 0 ?C 1 "Latin-3" "ISO8859-3 (Latin-3)" "ISO8859-3 (Latin-3)"])
(define-charset 132 'latin-iso8859-4
  [1 96 1 0 ?D 1 "Latin-4" "ISO8859-4 (Latin-4)" "ISO8859-4 (Latin-4)"])
(define-charset 133 'thai-tis620
  [1 96 1 0 ?T 1 "TIS620" "TIS620 (Thai)" "TIS620.2529 (Thai)"])
(define-charset 134 'greek-iso8859-7
  [1 96 1 0 ?F 1 "ISO8859-7" "ISO8859-7 (Greek)" "ISO8859-7 (Greek)"])
(define-charset 135 'arabic-iso8859-6
  [1 96 1 1 ?G 1 "ISO8859-6" "ISO8859-6 (Arabic)" "ISO8859-6 (Arabic)"])
(define-charset 136 'hebrew-iso8859-8
  [1 96 1 1 ?H 1 "ISO8859-8" "ISO8859-8 (Hebrew)" "ISO8859-8 (Hebrew)"])
(define-charset 137 'katakana-jisx0201
  [1 94 1 0 ?I 1 "JISX0201 Kana" "JISX0201.1976 (Japanese Kana)"
     "JISX0201.1976 Japanese Kana"])
(define-charset 138 'latin-jisx0201
  [1 94 1 0 ?J 0 "JISX0201 Roman" "JISX0201.1976 (Japanese Roman)"
     "JISX0201.1976 Japanese Roman"])
(define-charset 140 'cyrillic-iso8859-5
  [1 96 1 0 ?L 1 "ISO8859-5" "ISO8859-5 (Cyrillic)"
     "ISO8859-5 (Cyrillic)"])
(define-charset 141 'latin-iso8859-9
  [1 96 1 0 ?M 1 "Latin-5" "ISO8859-9 (Latin-5)" "ISO8859-9 (Latin-5)"])
(define-charset 144 'japanese-jisx0208-1978
  [2 94 2 0 ?@ 0 "JISX0208.1978" "JISX0208.1978 (Japanese)"
     "JISX0208.1978 Japanese Kanji (so called \"old JIS\")"])
(define-charset 145 'chinese-gb2312
  [2 94 2 0 ?A 0 "GB2312" "GB2312" "GB2312 Chinese simplified"])
(define-charset 146 'japanese-jisx0208
  [2 94 2 0 ?B 0 "JISX0208" "JISX0208.1983/1990 (Japanese)"
     "JISX0208.1983/1990 Japanese Kanji"])
(define-charset 147 'korean-ksc5601
  [2 94 2 0 ?C 0 "KSC5601" "KSC5601 (Korean)"
     "KSC5601 Korean Hangul and Hanja"])
(define-charset 148 'japanese-jisx0212
  [2 94 2 0 ?D 0 "JISX0212" "JISX0212 (Japanese)"
     "JISX0212 Japanese supplement"])
(define-charset 149 'chinese-cns11643-1
  [2 94 2 0 ?G 0 "CNS11643-1" "CNS11643-1 (Chinese traditional)"
     "CNS11643 Plane 1 Chinese traditional"])
(define-charset 150 'chinese-cns11643-2
  [2 94 2 0 ?H 0 "CNS11643-2" "CNS11643-2 (Chinese traditional)"
     "CNS11643 Plane 2 Chinese traditional"])
(define-charset 152 'chinese-big5-1
  [2 94 2 0 ?0 0 "Big5" "Big5 (Level-1)"
     "Big5 Level-1 Chinese traditional"])
(define-charset 153 'chinese-big5-2
  [2 94 2 0 ?1 0 "Big5" "Big5 (Level-2)"
     "Big5 Level-2 Chinese traditional"])

;; Additional (private) character sets.  These character sets are
;; treated less effectively in the aspect of memory in a buffer.

;; Syntax:
;; (define-charset nil CHARSET
;;   [ DIMENSION CHARS WIDTH DIRECTION ISO-FINAL-CHAR ISO-GRAPHIC-PLANE
;;     SHORT-NAME LONG-NAME DESCRIPTION ])

;; ISO-2022 allows a use of character sets not registered in ISO with
;; final characters `0' (0x30) through `?' (0x3F).  Among them, Emacs
;; reserves `0' through `9' to support several private character sets.
;; The remaining final characters `:' through `?' are for users.

(define-charset nil 'chinese-sisheng
  [1 94 1 0 ?0 0 "SiSheng" "SiSheng (PinYin/ZhuYin)"
     "SiSheng characters for PinYin/ZhuYin"])

;; IPA characters for phonetic symbols.
(define-charset nil 'ipa
  [1 96 1 0 ?0 1 "IPA" "IPA" "IPA (International Phonetic Association)"])

;; Vietnamese VISCII.  VISCII is 1-byte character set which contains
;; more than 96 characters.  Since Emacs can't handle it as one
;; character set, it is divided into two: lower case letters and upper
;; case letters.
(define-charset nil 'vietnamese-viscii-lower
  [1 96 1 0 ?1 1 "VISCII lower" "VISCII lower-case" "VISCII1.1 lower-case"])
(define-charset nil 'vietnamese-viscii-upper
  [1 96 1 0 ?2 1 "VISCII upper" "VISCII upper-case" "VISCII1.1 upper-case"])

;; For Arabic, we need three different types of character sets.
;; Digits are of direction left-to-right and of width 1-column.
;; Others are of direction right-to-left and of width 1-column or
;; 2-column.
(define-charset nil 'arabic-digit
  [1 94 1 0 ?2 0 "Arabic digit" "Arabic digit" "Arabic digit"])
(define-charset nil 'arabic-1-column
  [1 94 1 1 ?3 0 "Arabic 1-col" "Arabic 1-column" "Arabic 1-column"])
(define-charset nil 'arabic-2-column
  [1 94 2 1 ?4 0 "Arabic 2-col" "Arabic 2-column" "Arabic 2-column"])

;; Ethiopic characters (Amahric and Tigrigna).
(define-charset nil 'ethiopic
  [2 94 2 0 ?3 0 "Ethiopic" "Ethiopic characters" "Ethiopic characters"])

;; Chinese CNS11643 Plane3 thru Plane7.  Although these are official
;; character sets, the use is rare and don't have to be treated
;; effectively in the aspect of memory in a buffer.
(define-charset nil 'chinese-cns11643-3
  [2 94 2 0 ?I 0 "CNS11643-3" "CNS11643-3 (Chinese traditional)"
     "CNS11643 Plane 3 Chinese Traditional"])
(define-charset nil 'chinese-cns11643-4
  [2 94 2 0 ?J 0 "CNS11643-4" "CNS11643-4 (Chinese traditional)"
     "CNS11643 Plane 4 Chinese Traditional"])
(define-charset nil 'chinese-cns11643-5
  [2 94 2 0 ?K 0 "CNS11643-5" "CNS11643-5 (Chinese traditional)"
     "CNS11643 Plane 5 Chinese Traditional"])
(define-charset nil 'chinese-cns11643-6
  [2 94 2 0 ?L 0 "CNS11643-6" "CNS11643-6 (Chinese traditional)"
     "CNS11643 Plane 6 Chinese Traditional"])
(define-charset nil 'chinese-cns11643-7
  [2 94 2 0 ?M 0 "CNS11643-7" "CNS11643-7 (Chinese traditional)"
     "CNS11643 Plane 7 Chinese Traditional"])

;; ASCII with right-to-left direction.
(define-charset nil 'ascii-right-to-left
  [1 94 1 1 ?B 0 "rev ASCII" "ASCII with right-to-left direction"
     "ASCII (left half of ISO8859-1) with right-to-left direction"])

;; Indian scripts.  Symbolic charset for data exchange.  Glyphs are
;; not assigned.  They are automatically converted to each Indian
;; script which IS-13194 supports.

(define-charset nil 'indian-is13194
  [1 94 2 0 ?5 1 "IS 13194" "Indian IS 13194"
     "Generic Indian charset for data exchange with IS 13194"])
;; Actual Glyph for 2-column width.
(define-charset nil 'indian-2-column
  [2 94 2 0 ?5 0 "Indian 2-col" "Indian 2 Column"
     "Indian charset for 2-column width glyphs"])
;; Actual Glyph for 1-column width.
(define-charset nil 'indian-1-column
  [2 94 1 0 ?6 0 "Indian 1-col" "Indian 1 Column"
     "Indian charset for 2-column width glyphs"])

;; Lao script.
;; ISO10646's 0x0E80..0x0EDF are mapped to 0x20..0x7F.
(define-charset nil 'lao
  [1 94 1 0 ?1 0 "Lao" "Lao" "Lao characters (ISO10646 0E80..0EDF)"])

;; Tibetan script.
(define-charset nil 'tibetan
  [2 94 2 0 ?7 0 "Tibetan 2-col" "Tibetan 2 column" "Tibetan characters"])
(define-charset nil 'tibetan-1-column
  [2 94 1 0 ?8 0 "Tibetan 1-col" "Tibetan 1 column" "Tibetan 1 column glyph"])

;; Tell C code charset ID's of several charsets.
(setup-special-charsets)


;; These are tables for unifying characters on decoding and encoding.
(setq standard-character-unification-table-for-decode
      (make-unification-table
       (list (cons (make-char 'japanese-jisx0208-1978)
		   (make-char 'japanese-jisx0208))
	     (cons (make-char 'latin-jisx0201) (make-char 'ascii)))))

(setq standard-character-unification-table-for-encode nil)


;;; Make fundamental coding systems.

;; Miscellaneous coding systems which can't be made by
;; `make-coding-system'.

(put 'no-conversion 'coding-system
     (vector nil ?= "Do no conversion" nil nil))
(put 'no-conversion 'eol-type 0)

(define-coding-system-alias 'binary 'no-conversion)

(put 'undecided-unix 'coding-system 'undecided)
(put 'undecided-unix 'eol-type 0)
(put 'undecided-unix 'eol-variant t)
(put 'undecided-dos 'coding-system 'undecided)
(put 'undecided-dos 'eol-type 1)
(put 'undecided-dos 'eol-variant t)
(put 'undecided-mac 'coding-system 'undecided)
(put 'undecided-mac 'eol-type 2)
(put 'undecided-mac 'eol-variant t)
(put 'undecided 'coding-system
     (vector t ?- "No conversion on encoding, automatic conversion on decoding"
	     nil nil))
(put 'undecided 'eol-type
     (vector 'undecided-unix
	     'undecided-dos
	     'undecided-mac))

;; Coding systems not specific to each language environment.

(make-coding-system
 'emacs-mule 0 ?=
 "Emacs internal format used in buffer and string")

(make-coding-system
 'raw-text 5 ?t
 "Raw text, which means text contains random 8-bit codes.")

(make-coding-system
 'iso-2022-7bit 2 ?J
 "ISO 2022 based 7-bit encoding using only G0"
 '((ascii t) nil nil nil
   short ascii-eol ascii-cntl seven))

(make-coding-system
 'iso-2022-7bit-ss2 2 ?$
 "ISO 2022 based 7-bit encoding using SS2 for 96-charset"
 '((ascii t) nil t nil
   short ascii-eol ascii-cntl seven nil single-shift))

(make-coding-system
 'iso-2022-7bit-lock 2 ?&
 "ISO-2022 coding system using Locking-Shift for 96-charset"
 '((ascii t) t nil nil
   nil ascii-eol ascii-cntl seven locking-shift))

(define-coding-system-alias 'iso-2022-int-1 'iso-2022-7bit-lock)

(make-coding-system
 'iso-2022-7bit-lock-ss2 2 ?i
 "Mixture of ISO-2022-JP, ISO-2022-KR, and ISO-2022-CN"
 '((ascii t)
   (nil korean-ksc5601 chinese-gb2312 chinese-cns11643-1 t)
   (nil chinese-cns11643-2)
   (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5
	chinese-cns11643-6 chinese-cns11643-7)
   short ascii-eol ascii-cntl seven locking-shift single-shift nil nil nil
   init-bol))

(define-coding-system-alias 'iso-2022-cjk 'iso-2022-7bit-lock-ss2)

(make-coding-system
 'iso-2022-8bit-ss2 2 ?@
 "ISO 2022 based 8-bit encoding using SS2 for 96-charset"
 '((ascii t) nil t nil
   nil ascii-eol ascii-cntl nil nil single-shift))

(make-coding-system
 'iso-safe 2 ?-
 "Convert all characters but ASCII to `?'."
 '(ascii nil nil nil
   nil ascii-eol ascii-cntl nil nil nil nil nil nil nil nil t))

;; Use iso-safe for terminal output if some other coding system is
;; specified explicitely.
(set-safe-terminal-coding-system-internal 'iso-safe)

;; The other coding-systems are defined in each language specific
;; section of languages.el.

;; Setting coding system `undecided' for reading any files.  Though,
;; compiled Emacs Lisp files (*.elc) should never be decoded nor
;; encoded.  tar files too.

(setq file-coding-system-alist
      '(("\\.elc$" . (no-conversion . no-conversion))
	("\\(\\`\\|/\\)loaddefs.el$" . (no-conversion . no-conversion))
	("\\.tar$" . (no-conversion . no-conversion))
	("" . (undecided . nil))))


;;; Setting coding categories and their priorities.

;; This setting is just to read an Emacs Lisp source files which
;; contain multilingual text while dumping Emacs.  More appropriate
;; values are set by the command `set-language-environment' for each
;; language environment.

(setq coding-category-emacs-mule	'emacs-mule
      coding-category-sjis		'japanese-shift-jis
      coding-category-iso-7		'iso-2022-7bit
      coding-category-iso-8-1		'iso-latin-1
      coding-category-iso-8-2		'japanese-iso-8bit
      coding-category-iso-7-else	'iso-2022-7bit-lock
      coding-category-iso-8-else	'iso-2022-8bit-ss2
      coding-category-big5		'chinese-big5
      coding-category-raw-text		'raw-text
      coding-category-binary		'no-conversion)

(set-coding-priority
 '(coding-category-iso-7
   coding-category-iso-8-1
   coding-category-iso-8-2
   coding-category-iso-7-else
   coding-category-iso-8-else
   coding-category-emacs-mule
   coding-category-raw-text
   coding-category-sjis 
   coding-category-big5
   coding-category-binary))


;;; Miscellaneous settings.
(aset latin-extra-code-table ?\222 t)

;;; mule-conf.el ends here