[bpt/emacs.git] / lisp / international / mule-conf.el

;;; 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)

\f
;; 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)

\f
;;; 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
 '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))

;; 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))))

\f
;;; 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-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-emacs-mule
   coding-category-sjis 
   coding-category-big5
   coding-category-iso-8-else
   coding-category-binary))

;;; mule-conf.el ends here
Commit	Line	Data
08c19a27 KH	1	;;; mule-conf.el --- configure multilingual environment
08c19a27 KH	2
08c19a27	3	;; Copyright (C) 1997 Electrotechnical Laboratory, JAPAN.
fa526c4a	4	;; Licensed to the Free Software Foundation.
08c19a27 KH	5
	6	;; Keywords: mule, multilingual, character set, coding system
	7
	8	;; This file is part of GNU Emacs.
	9
	10	;; GNU Emacs is free software; you can redistribute it and/or modify
	11	;; it under the terms of the GNU General Public License as published by
	12	;; the Free Software Foundation; either version 2, or (at your option)
	13	;; any later version.
	14
	15	;; GNU Emacs is distributed in the hope that it will be useful,
	16	;; but WITHOUT ANY WARRANTY; without even the implied warranty of
	17	;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
	18	;; GNU General Public License for more details.
	19
	20	;; You should have received a copy of the GNU General Public License
	21	;; along with GNU Emacs; see the file COPYING. If not, write to the
	22	;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
	23	;; Boston, MA 02111-1307, USA.
	24
	25	;;; Commentary:
	26
	27	;; Don't byte-compile this file.
	28
	29	;;; Code:
	30
	31	;;; Definitions of character sets.
	32
	33	;; Basic (official) character sets. These character sets are treated
	34	;; effectively in the aspect of memory in a buffer.
	35
	36	;; Syntax:
	37	;; (define-charset CHARSET-ID CHARSET
	38	;; [ DIMENSION CHARS WIDTH DIRECTION ISO-FINAL-CHAR ISO-GRAPHIC-PLANE
	39	;; SHORT-NAME LONG-NAME DESCRIPTION ])
	40	;; ASCII charset is defined in src/charset.c as below.
	41	;; (define-charset 0 ascii
	42	;; [1 94 1 0 ?B 0 "ASCII" "ASCII" "ASCII (ISO646 IRV)"])
	43
	44	(define-charset 129 'latin-iso8859-1
	45	[1 96 1 0 ?A 1 "Latin-1" "ISO8859-1 (Latin-1)" "ISO8859-1 (Latin-1)"])
	46	(define-charset 130 'latin-iso8859-2
	47	[1 96 1 0 ?B 1 "Latin-2" "ISO8859-2 (Latin-2)" "ISO8859-2 (Latin-2)"])
	48	(define-charset 131 'latin-iso8859-3
	49	[1 96 1 0 ?C 1 "Latin-3" "ISO8859-3 (Latin-3)" "ISO8859-3 (Latin-3)"])
	50	(define-charset 132 'latin-iso8859-4
	51	[1 96 1 0 ?D 1 "Latin-4" "ISO8859-4 (Latin-4)" "ISO8859-4 (Latin-4)"])
	52	(define-charset 133 'thai-tis620
	53	[1 96 1 0 ?T 1 "TIS620" "TIS620 (Thai)" "TIS620.2529 (Thai)"])
	54	(define-charset 134 'greek-iso8859-7
	55	[1 96 1 0 ?F 1 "ISO8859-7" "ISO8859-7 (Greek)" "ISO8859-7 (Greek)"])
	56	(define-charset 135 'arabic-iso8859-6
	57	[1 96 1 1 ?G 1 "ISO8859-6" "ISO8859-6 (Arabic)" "ISO8859-6 (Arabic)"])
	58	(define-charset 136 'hebrew-iso8859-8
	59	[1 96 1 1 ?H 1 "ISO8859-8" "ISO8859-8 (Hebrew)" "ISO8859-8 (Hebrew)"])
	60	(define-charset 137 'katakana-jisx0201
	61	[1 94 1 0 ?I 1 "JISX0201 Kana" "JISX0201.1976 (Japanese Kana)"
	62	"JISX0201.1976 Japanese Kana"])
	63	(define-charset 138 'latin-jisx0201
	64	[1 94 1 0 ?J 0 "JISX0201 Roman" "JISX0201.1976 (Japanese Roman)"
	65	"JISX0201.1976 Japanese Roman"])
	66	(define-charset 140 'cyrillic-iso8859-5
	67	[1 96 1 0 ?L 1 "ISO8859-5" "ISO8859-5 (Cyrillic)"
	68	"ISO8859-5 (Cyrillic)"])
69	(define-charset 141 'latin-iso8859-9
70	[1 96 1 0 ?M 1 "Latin-5" "ISO8859-9 (Latin-5)" "ISO8859-9 (Latin-5)"])
71	(define-charset 144 'japanese-jisx0208-1978
72	[2 94 2 0 ?@ 0 "JISX0208.1978" "JISX0208.1978 (Japanese)"
73	"JISX0208.1978 Japanese Kanji (so called \"old JIS\")"])
74	(define-charset 145 'chinese-gb2312
75	[2 94 2 0 ?A 0 "GB2312" "GB2312" "GB2312 Chinese simplified"])
76	(define-charset 146 'japanese-jisx0208
77	[2 94 2 0 ?B 0 "JISX0208" "JISX0208.1983/1990 (Japanese)"
78	"JISX0208.1983/1990 Japanese Kanji"])
79	(define-charset 147 'korean-ksc5601
80	[2 94 2 0 ?C 0 "KSC5601" "KSC5601 (Korean)"
81	"KSC5601 Korean Hangul and Hanja"])
82	(define-charset 148 'japanese-jisx0212
83	[2 94 2 0 ?D 0 "JISX0212" "JISX0212 (Japanese)"
84	"JISX0212 Japanese supplement"])
85	(define-charset 149 'chinese-cns11643-1
86	[2 94 2 0 ?G 0 "CNS11643-1" "CNS11643-1 (Chinese traditional)"
87	"CNS11643 Plane 1 Chinese traditional"])
88	(define-charset 150 'chinese-cns11643-2
89	[2 94 2 0 ?H 0 "CNS11643-2" "CNS11643-2 (Chinese traditional)"
90	"CNS11643 Plane 2 Chinese traditional"])
91	(define-charset 152 'chinese-big5-1
92	[2 94 2 0 ?0 0 "Big5" "Big5 (Level-1)"
93	"Big5 Level-1 Chinese traditional"])
94	(define-charset 153 'chinese-big5-2
95	[2 94 2 0 ?1 0 "Big5" "Big5 (Level-2)"
96	"Big5 Level-2 Chinese traditional"])
97
98	;; Additional (private) character sets. These character sets are
99	;; treated less effectively in the aspect of memory in a buffer.
100
101	;; Syntax:
102	;; (define-charset nil CHARSET
103	;; [ DIMENSION CHARS WIDTH DIRECTION ISO-FINAL-CHAR ISO-GRAPHIC-PLANE
104	;; SHORT-NAME LONG-NAME DESCRIPTION ])
105
106	;; ISO-2022 allows a use of character sets not registered in ISO with
107	;; final characters `0' (0x30) through `?' (0x3F). Among them, Emacs
108	;; reserves `0' through `9' to support several private character sets.
109	;; The remaining final characters `:' through `?' are for users.
110
111	(define-charset nil 'chinese-sisheng
112	[1 94 1 0 ?0 0 "SiSheng" "SiSheng (PinYin/ZhuYin)"
113	"SiSheng characters for PinYin/ZhuYin"])
114
115	;; IPA characters for phonetic symbols.
116	(define-charset nil 'ipa
117	[1 96 1 0 ?0 1 "IPA" "IPA" "IPA (International Phonetic Association)"])
118
119	;; Vietnamese VISCII. VISCII is 1-byte character set which contains
120	;; more than 96 characters. Since Emacs can't handle it as one
121	;; character set, it is divided into two: lower case letters and upper
122	;; case letters.
123	(define-charset nil 'vietnamese-viscii-lower
2aa72de7	124	[1 96 1 0 ?1 1 "VISCII lower" "VISCII lower-case" "VISCII1.1 lower-case"])
08c19a27	125	(define-charset nil 'vietnamese-viscii-upper
2aa72de7	126	[1 96 1 0 ?2 1 "VISCII upper" "VISCII upper-case" "VISCII1.1 upper-case"])
08c19a27 KH	127
	128	;; For Arabic, we need three different types of character sets.
	129	;; Digits are of direction left-to-right and of width 1-column.
	130	;; Others are of direction right-to-left and of width 1-column or
	131	;; 2-column.
	132	(define-charset nil 'arabic-digit
2aa72de7	133	[1 94 1 0 ?2 0 "Arabic digit" "Arabic digit" "Arabic digit"])
08c19a27	134	(define-charset nil 'arabic-1-column
2aa72de7	135	[1 94 1 1 ?3 0 "Arabic 1-col" "Arabic 1-column" "Arabic 1-column"])
08c19a27	136	(define-charset nil 'arabic-2-column
2aa72de7	137	[1 94 2 1 ?4 0 "Arabic 2-col" "Arabic 2-column" "Arabic 2-column"])
08c19a27 KH	138
	139	;; Ethiopic characters (Amahric and Tigrigna).
	140	(define-charset nil 'ethiopic
d2382a1d	141	[2 94 2 0 ?3 0 "Ethiopic" "Ethiopic characters" "Ethiopic characters"])
08c19a27 KH	142
	143	;; Chinese CNS11643 Plane3 thru Plane7. Although these are official
	144	;; character sets, the use is rare and don't have to be treated
	145	;; effectively in the aspect of memory in a buffer.
	146	(define-charset nil 'chinese-cns11643-3
	147	[2 94 2 0 ?I 0 "CNS11643-3" "CNS11643-3 (Chinese traditional)"
	148	"CNS11643 Plane 3 Chinese Traditional"])
	149	(define-charset nil 'chinese-cns11643-4
	150	[2 94 2 0 ?J 0 "CNS11643-4" "CNS11643-4 (Chinese traditional)"
	151	"CNS11643 Plane 4 Chinese Traditional"])
	152	(define-charset nil 'chinese-cns11643-5
	153	[2 94 2 0 ?K 0 "CNS11643-5" "CNS11643-5 (Chinese traditional)"
	154	"CNS11643 Plane 5 Chinese Traditional"])
	155	(define-charset nil 'chinese-cns11643-6
	156	[2 94 2 0 ?L 0 "CNS11643-6" "CNS11643-6 (Chinese traditional)"
	157	"CNS11643 Plane 6 Chinese Traditional"])
	158	(define-charset nil 'chinese-cns11643-7
	159	[2 94 2 0 ?M 0 "CNS11643-7" "CNS11643-7 (Chinese traditional)"
	160	"CNS11643 Plane 7 Chinese Traditional"])
	161
	162	;; ASCII with right-to-left direction.
	163	(define-charset nil 'ascii-right-to-left
	164	[1 94 1 1 ?B 0 "rev ASCII" "ASCII with right-to-left direction"
	165	"ASCII (left half of ISO8859-1) with right-to-left direction"])
	166
	167	;; Indian scripts. Symbolic charset for data exchange. Glyphs are
	168	;; not assigned. They are automatically converted to each Indian
	169	;; script which IS-13194 supports.
	170
	171	(define-charset nil 'indian-is13194
	172	[1 94 2 0 ?5 1 "IS 13194" "Indian IS 13194"
	173	"Generic Indian charset for data exchange with IS 13194"])
	174	;; Actual Glyph for 2-column width.
	175	(define-charset nil 'indian-2-column
2aa72de7	176	[2 94 2 0 ?5 0 "Indian 2-col" "Indian 2 Column"
08c19a27 KH	177	"Indian charset for 2-column width glyphs"])
	178	;; Actual Glyph for 1-column width.
	179	(define-charset nil 'indian-1-column
2aa72de7	180	[2 94 1 0 ?6 0 "Indian 1-col" "Indian 1 Column"
49733613	181	"Indian charset for 2-column width glyphs"])
08c19a27 KH	182
	183	;; Lao script.
	184	;; ISO10646's 0x0E80..0x0EDF are mapped to 0x20..0x7F.
	185	(define-charset nil 'lao
	186	[1 94 1 0 ?1 0 "Lao" "Lao" "Lao characters (ISO10646 0E80..0EDF)"])
	187
2aa72de7 KH	188	;; Tibetan script.
	189	(define-charset nil 'tibetan
	190	[2 94 2 0 ?7 0 "Tibetan 2-col" "Tibetan 2 column" "Tibetan characters"])
	191	(define-charset nil 'tibetan-1-column
	192	[2 94 1 0 ?8 0 "Tibetan 1-col" "Tibetan 1 column" "Tibetan 1 column glyph"])
	193
85f789f7 KH	194	;; Tell C code charset ID's of several charsets.
85f789f7 KH	195	(setup-special-charsets)
08c19a27	196
85f789f7	197	\f
49733613 KH	198	;; These are tables for unifying characters on decoding and encoding.
49733613 KH	199	(setq standard-character-unification-table-for-decode
85f789f7 KH	200	(make-unification-table
	201	(list (cons (make-char 'japanese-jisx0208-1978)
	202	(make-char 'japanese-jisx0208))
	203	(cons (make-char 'latin-jisx0201) (make-char 'ascii)))))
08c19a27	204
49733613	205	(setq standard-character-unification-table-for-encode nil)
08c19a27 KH	206
	207	\f
	208	;;; Make fundamental coding systems.
	209
	210	;; Miscellaneous coding systems which can't be made by
	211	;; `make-coding-system'.
	212
	213	(put 'no-conversion 'coding-system
	214	(vector nil ?= "Do no conversion" nil nil))
	215	(put 'no-conversion 'eol-type 0)
	216
8da035d0 RS	217	(define-coding-system-alias 'binary 'no-conversion)
8da035d0 RS	218
426591c3 KH	219	(put 'undecided-unix 'coding-system 'undecided)
426591c3 KH	220	(put 'undecided-unix 'eol-type 0)
4951a271	221	(put 'undecided-unix 'eol-variant t)
426591c3 KH	222	(put 'undecided-dos 'coding-system 'undecided)
426591c3 KH	223	(put 'undecided-dos 'eol-type 1)
4951a271	224	(put 'undecided-dos 'eol-variant t)
426591c3 KH	225	(put 'undecided-mac 'coding-system 'undecided)
426591c3 KH	226	(put 'undecided-mac 'eol-type 2)
4951a271	227	(put 'undecided-mac 'eol-variant t)
426591c3	228	(put 'undecided 'coding-system
76810f60	229	(vector t ?- "No conversion on encoding, automatic conversion on decoding"
4951a271	230	nil nil))
426591c3 KH	231	(put 'undecided 'eol-type
	232	(vector 'undecided-unix
	233	'undecided-dos
	234	'undecided-mac))
08c19a27 KH	235
	236	;; Coding systems not specific to each language environment.
	237
	238	(make-coding-system
426591c3	239	'emacs-mule 0 ?=
4951a271	240	"Emacs internal format used in buffer and string")
08c19a27 KH	241
08c19a27 KH	242	(make-coding-system
4951a271 KH	243	'iso-2022-7bit 2 ?J
4951a271 KH	244	"ISO 2022 based 7-bit encoding using only G0"
08c19a27 KH	245	'((ascii t) nil nil nil
	246	short ascii-eol ascii-cntl seven))
	247
	248	(make-coding-system
2792ce16	249	'iso-2022-7bit-ss2 2 ?$
4951a271 KH	250	"ISO 2022 based 7-bit encoding using SS2 for 96-charset"
	251	'((ascii t) nil t nil
	252	short ascii-eol ascii-cntl seven nil single-shift))
	253
	254	(make-coding-system
2792ce16	255	'iso-2022-7bit-lock 2 ?&
4951a271 KH	256	"ISO-2022 coding system using Locking-Shift for 96-charset"
4951a271 KH	257	'((ascii t) t nil nil
2792ce16	258	nil ascii-eol ascii-cntl seven locking-shift))
4951a271	259
2e21aa27	260	(define-coding-system-alias 'iso-2022-int-1 'iso-2022-7bit-lock)
08c19a27 KH	261
08c19a27 KH	262	(make-coding-system
4951a271	263	'iso-2022-7bit-lock-ss2 2 ?i
d0c5d809	264	"Mixture of ISO-2022-JP, ISO-2022-KR, and ISO-2022-CN"
08c19a27 KH	265	'((ascii t)
	266	(nil korean-ksc5601 chinese-gb2312 chinese-cns11643-1 t)
	267	(nil chinese-cns11643-2)
	268	(nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5
	269	chinese-cns11643-6 chinese-cns11643-7)
d0c5d809 KH	270	short ascii-eol ascii-cntl seven locking-shift single-shift nil nil nil
d0c5d809 KH	271	init-bol))
08c19a27	272
2e21aa27	273	(define-coding-system-alias 'iso-2022-cjk 'iso-2022-7bit-lock-ss2)
08c19a27 KH	274
08c19a27 KH	275	(make-coding-system
4951a271 KH	276	'iso-2022-8bit-ss2 2 ?@
4951a271 KH	277	"ISO 2022 based 8-bit encoding using SS2 for 96-charset"
08c19a27	278	'((ascii t) nil t nil
4951a271	279	nil ascii-eol ascii-cntl nil nil single-shift))
08c19a27 KH	280
	281	;; The other coding-systems are defined in each language specific
	282	;; section of languages.el.
	283
4951a271	284	;; Setting coding system `undecided' for reading any files. Though,
426591c3	285	;; compiled Emacs Lisp files (*.elc) should never be decoded nor
9f993a10	286	;; encoded. tar files too.
08c19a27	287
4951a271 KH	288	(setq file-coding-system-alist
	289	'(("\\.elc$" . (no-conversion . no-conversion))
	290	("loaddefs.el$" . (no-conversion . no-conversion))
9f993a10	291	("\\.tar$" . (no-conversion . no-conversion))
4951a271	292	("" . (undecided . nil))))
08c19a27 KH	293
	294	\f
	295	;;; Setting coding categories and their priorities.
	296
	297	;; This setting is just to read an Emacs Lisp source files which
	298	;; contain multilingual text while dumping Emacs. More appropriate
2792ce16	299	;; values are set by the command `set-language-environment' for each
08c19a27 KH	300	;; language environment.
08c19a27 KH	301
29742cb5 KH	302	(setq coding-category-emacs-mule 'emacs-mule
	303	coding-category-sjis 'japanese-shift-jis
	304	coding-category-iso-7 'iso-2022-7bit
	305	coding-category-iso-8-1 'iso-latin-1
	306	coding-category-iso-8-2 'japanese-iso-8bit
	307	coding-category-iso-7-else 'iso-2022-7bit-lock
	308	coding-category-iso-8-else 'iso-2022-8bit-ss2
	309	coding-category-big5 'chinese-big5
	310	coding-category-binary 'no-conversion)
08c19a27 KH	311
	312	(set-coding-priority
	313	'(coding-category-iso-7
08c19a27	314	coding-category-iso-8-1
69b73c8a	315	coding-category-iso-8-2
29742cb5	316	coding-category-iso-7-else
e4e6cfa0	317	coding-category-emacs-mule
08c19a27 KH	318	coding-category-sjis
08c19a27 KH	319	coding-category-big5
29742cb5	320	coding-category-iso-8-else
e4e6cfa0	321	coding-category-binary))
08c19a27 KH	322
08c19a27 KH	323	;;; mule-conf.el ends here