428
|
1 ;;; japanese.el --- Japanese support -*- coding: iso-2022-7bit; -*-
|
|
2
|
|
3 ;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
|
|
4 ;; Licensed to the Free Software Foundation.
|
|
5 ;; Copyright (C) 1997 MORIOKA Tomohiko
|
|
6
|
|
7 ;; Keywords: multilingual, Japanese
|
|
8
|
|
9 ;; This file is part of XEmacs.
|
|
10
|
|
11 ;; XEmacs is free software; you can redistribute it and/or modify it
|
|
12 ;; under the terms of the GNU General Public License as published by
|
|
13 ;; the Free Software Foundation; either version 2, or (at your option)
|
|
14 ;; any later version.
|
|
15
|
|
16 ;; XEmacs is distributed in the hope that it will be useful, but
|
|
17 ;; WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
18 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
19 ;; General Public License for more details.
|
|
20
|
|
21 ;; You should have received a copy of the GNU General Public License
|
|
22 ;; along with XEmacs; see the file COPYING. If not, write to the Free
|
|
23 ;; Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
|
|
24 ;; 02111-1307, USA.
|
|
25
|
|
26 ;;; Commentary:
|
|
27
|
|
28 ;; For Japanese, character sets JISX0201, JISX0208, JISX0212 are
|
|
29 ;; supported.
|
|
30
|
|
31 ;;; Code:
|
|
32
|
|
33 ;;; Syntax of Japanese characters.
|
|
34 (modify-syntax-entry 'katakana-jisx0201 "w")
|
|
35 (modify-syntax-entry 'japanese-jisx0212 "w")
|
|
36
|
|
37 (modify-syntax-entry 'japanese-jisx0208 "w")
|
|
38 (loop for row in '(33 34 40)
|
|
39 do (modify-syntax-entry `[japanese-jisx0208 ,row] "_"))
|
|
40 (loop for char in '(?$B!<(B ?$B!+(B ?$B!,(B ?$B!3(B ?$B!4(B ?$B!5(B ?$B!6(B ?$B!7(B ?$B!8(B ?$B!9(B ?$B!:(B ?$B!;(B)
|
|
41 do (modify-syntax-entry char "w"))
|
|
42 (modify-syntax-entry ?\$B!J(B "($B!K(B")
|
|
43 (modify-syntax-entry ?\$B!N(B "($B!O(B")
|
|
44 (modify-syntax-entry ?\$B!P(B "($B!Q(B")
|
|
45 (modify-syntax-entry ?\$B!V(B "($B!W(B")
|
|
46 (modify-syntax-entry ?\$B!X(B "($B!Y(B")
|
|
47 (modify-syntax-entry ?\$B!K(B ")$B!J(B")
|
|
48 (modify-syntax-entry ?\$B!O(B ")$B!N(B")
|
|
49 (modify-syntax-entry ?\$B!Q(B ")$B!P(B")
|
|
50 (modify-syntax-entry ?\$B!W(B ")$B!V(B")
|
|
51 (modify-syntax-entry ?\$B!Y(B ")$B!X(B")
|
|
52
|
|
53 ;;; Character categories S, A, H, K, G, Y, and C
|
|
54 (define-category ?S "Japanese 2-byte symbol character.")
|
|
55 (modify-category-entry [japanese-jisx0208 33] ?S)
|
|
56 (modify-category-entry [japanese-jisx0208 34] ?S)
|
|
57 (modify-category-entry [japanese-jisx0208 40] ?S)
|
|
58 (define-category ?A "Japanese 2-byte Alphanumeric character.")
|
|
59 (modify-category-entry [japanese-jisx0208 35] ?A)
|
|
60 (define-category ?H "Japanese 2-byte Hiragana character.")
|
|
61 (modify-category-entry [japanese-jisx0208 36] ?H)
|
|
62 (define-category ?K "Japanese 2-byte Katakana character.")
|
|
63 (modify-category-entry [japanese-jisx0208 37] ?K)
|
|
64 (define-category ?G "Japanese 2-byte Greek character.")
|
|
65 (modify-category-entry [japanese-jisx0208 38] ?G)
|
|
66 (define-category ?Y "Japanese 2-byte Cyrillic character.")
|
|
67 (modify-category-entry [japanese-jisx0208 39] ?Y)
|
|
68 (define-category ?C "Japanese 2-byte Kanji characters.")
|
|
69 (loop for row from 48 to 126
|
|
70 do (modify-category-entry `[japanese-jisx0208 ,row] ?C))
|
|
71 (loop for char in '(?$B!<(B ?$B!+(B ?$B!,(B)
|
|
72 do (modify-category-entry char ?K)
|
|
73 (modify-category-entry char ?H))
|
|
74 (loop for char in '(?$B!3(B ?$B!4(B ?$B!5(B ?$B!6(B ?$B!7(B ?$B!8(B ?$B!9(B ?$B!:(B ?$B!;(B)
|
|
75 do (modify-category-entry char ?C))
|
|
76 (modify-category-entry 'japanese-jisx0212 ?C)
|
|
77
|
|
78 (defvar japanese-word-regexp
|
|
79 "\\cA+\\cH*\\|\\cK+\\cH*\\|\\cC+\\cH*\\|\\cH+\\|\\ck+\\|\\sw+"
|
|
80 "Regular expression used to match a Japanese word.")
|
|
81
|
|
82 (set-word-regexp japanese-word-regexp)
|
|
83 (setq forward-word-regexp "\\w\\>")
|
|
84 (setq backward-word-regexp "\\<\\w")
|
|
85
|
|
86 ;;; Paragraph setting
|
|
87 (setq sentence-end
|
|
88 (concat
|
|
89 "\\("
|
|
90 "\\("
|
|
91 "[.?!][]\"')}]*"
|
|
92 "\\|"
|
|
93 "[$B!%!)!*(B][$B!O!I!G!K!Q!M!S!U!W!Y(B]*"
|
|
94 "\\)"
|
|
95 "\\($\\|\t\\| \\)"
|
|
96 "\\|"
|
|
97 "$B!#(B"
|
|
98 "\\)"
|
|
99 "[ \t\n]*"))
|
|
100 (setq paragraph-start "^[ $B!!(B\t\n\f]")
|
|
101 (setq paragraph-separate "^[ $B!!(B\t\f]*$")
|
|
102
|
|
103 ;; EGG specific setup
|
|
104 (define-egg-environment 'japanese
|
|
105 "Japanese settings for egg."
|
|
106 (lambda ()
|
|
107 (when (not (featurep 'egg-jpn))
|
|
108 (load "its-hira")
|
|
109 (load "its-kata")
|
|
110 (load "its-hankaku")
|
|
111 (load "its-zenkaku")
|
|
112 (setq its:*standard-modes*
|
|
113 (append
|
|
114 (list (its:get-mode-map "roma-kana")
|
|
115 (its:get-mode-map "roma-kata")
|
|
116 (its:get-mode-map "downcase")
|
|
117 (its:get-mode-map "upcase")
|
|
118 (its:get-mode-map "zenkaku-downcase")
|
|
119 (its:get-mode-map "zenkaku-upcase"))
|
|
120 its:*standard-modes*))
|
|
121 (provide 'egg-jpn))
|
|
122 (setq wnn-server-type 'jserver)
|
|
123 ;; Can't do this here any more. Must do it when selecting egg-wnn
|
|
124 ;; or egg-sj3
|
|
125 ;; (setq egg-default-startup-file "eggrc-wnn")
|
|
126 (setq-default its:*current-map* (its:get-mode-map "roma-kana"))))
|
|
127
|
450
|
128 ;; stuff for providing grammatic processing of Japanese text
|
428
|
129 ;; something like this should probably be created for all environments...
|
450
|
130 ;; #### Arrgh. This stuff should defvar'd in either fill.el or kinsoku.el.
|
|
131 ;; Then the language environment should set these things, probably buffer-
|
|
132 ;; locally.
|
428
|
133
|
|
134 (defvar aletter (concat "\\(" ascii-char "\\|" kanji-char "\\)"))
|
|
135 (defvar kanji-space-insertable (concat
|
|
136 "$B!"(B" aletter "\\|"
|
|
137 "$B!#(B" aletter "\\|"
|
|
138 aletter "$B!J(B" "\\|"
|
|
139 "$B!K(B" aletter "\\|"
|
|
140 ascii-alphanumeric kanji-kanji-char "\\|"
|
|
141 kanji-kanji-char ascii-alphanumeric ))
|
|
142
|
450
|
143 ;; #### will be moved to fill.el
|
428
|
144 (defvar space-insertable (concat " " aletter "\\|" kanji-space-insertable)
|
|
145 "Regexp for finding points that can have spaces inserted into them for justification")
|
|
146
|
|
147 ;; (make-coding-system
|
|
148 ;; 'iso-2022-jp 2 ?J
|
|
149 ;; "ISO 2022 based 7bit encoding for Japanese (MIME:ISO-2022-JP)"
|
|
150 ;; '((ascii japanese-jisx0208-1978 japanese-jisx0208
|
|
151 ;; latin-jisx0201 japanese-jisx0212 katakana-jisx0201) nil nil nil
|
|
152 ;; short ascii-eol ascii-cntl seven)
|
|
153 ;; '((safe-charsets ascii japanese-jisx0208-1978 japanese-jisx0208
|
|
154 ;; latin-jisx0201 japanese-jisx0212 katakana-jisx0201)
|
|
155 ;; (mime-charset . iso-2022-jp)))
|
|
156
|
|
157 (make-coding-system
|
|
158 'iso-2022-jp 'iso2022
|
|
159 "Coding-system used for communication with mail and news in Japan."
|
|
160 '(charset-g0 ascii
|
|
161 short t
|
|
162 seven t
|
|
163 input-charset-conversion ((latin-jisx0201 ascii)
|
|
164 (japanese-jisx0208-1978 japanese-jisx0208))
|
|
165 mnemonic "MULE/7bit"
|
|
166 ))
|
|
167
|
|
168 (define-coding-system-alias 'junet 'iso-2022-jp)
|
|
169
|
|
170 ;; (make-coding-system
|
|
171 ;; 'iso-2022-jp-2 2 ?J
|
|
172 ;; "ISO 2022 based 7bit encoding for CJK, Latin-1, and Greek (MIME:ISO-2022-JP-2)"
|
|
173 ;; '((ascii japanese-jisx0208-1978 japanese-jisx0208
|
|
174 ;; latin-jisx0201 japanese-jisx0212 katakana-jisx0201
|
|
175 ;; chinese-gb2312 korean-ksc5601) nil
|
|
176 ;; (nil latin-iso8859-1 greek-iso8859-7) nil
|
|
177 ;; short ascii-eol ascii-cntl seven nil single-shift)
|
|
178 ;; '((safe-charsets ascii japanese-jisx0208-1978 japanese-jisx0208
|
|
179 ;; latin-jisx0201 japanese-jisx0212 katakana-jisx0201
|
|
180 ;; chinese-gb2312 korean-ksc5601
|
|
181 ;; latin-iso8859-1 greek-iso8859-7)
|
|
182 ;; (mime-charset . iso-2022-jp-2)))
|
|
183
|
|
184 ;; (make-coding-system
|
|
185 ;; 'japanese-shift-jis 1 ?S
|
|
186 ;; "Shift-JIS 8-bit encoding for Japanese (MIME:SHIFT_JIS)"
|
|
187 ;; nil
|
|
188 ;; '((safe-charsets ascii japanese-jisx0208 japanese-jisx0208-1978
|
|
189 ;; latin-jisx0201 katakana-jisx0201)
|
|
190 ;; (mime-charset . shift_jis)
|
|
191 ;; (charset-origin-alist (japanese-jisx0208 "SJIS" encode-sjis-char)
|
|
192 ;; (katakana-jisx0201 "SJIS" encode-sjis-char))))
|
|
193
|
|
194 (make-coding-system
|
|
195 'shift_jis 'shift-jis
|
|
196 "Coding-system of Shift-JIS used in Japan."
|
|
197 '(mnemonic "Ja/SJIS"))
|
|
198
|
|
199 ;; (define-coding-system-alias 'shift_jis 'japanese-shift-jis)
|
|
200 ;; (define-coding-system-alias 'sjis 'japanese-shift-jis)
|
|
201
|
|
202 ;; (make-coding-system
|
|
203 ;; 'japanese-iso-7bit-1978-irv 2 ?j
|
|
204 ;; "ISO 2022 based 7-bit encoding for Japanese JISX0208-1978 and JISX0201-Roman"
|
|
205 ;; '((ascii japanese-jisx0208-1978 japanese-jisx0208
|
|
206 ;; latin-jisx0201 japanese-jisx0212 katakana-jisx0201 t) nil nil nil
|
|
207 ;; short ascii-eol ascii-cntl seven nil nil use-roman use-oldjis)
|
|
208 ;; '(ascii japanese-jisx0208-1978 japanese-jisx0208 latin-jisx0201))
|
|
209
|
|
210 (make-coding-system
|
|
211 'iso-2022-jp-1978-irv 'iso2022
|
|
212 "Coding-system used for old JIS terminal."
|
|
213 '(charset-g0 ascii
|
|
214 short t
|
|
215 seven t
|
|
216 output-charset-conversion ((ascii latin-jisx0201)
|
|
217 (japanese-jisx0208 japanese-jisx0208-1978))
|
|
218 mnemonic "Ja-78/7bit"
|
|
219 ))
|
|
220
|
|
221 ;; (define-coding-system-alias 'iso-2022-jp-1978-irv 'japanese-iso-7bit-1978-irv)
|
|
222 ;; (define-coding-system-alias 'old-jis 'japanese-iso-7bit-1978-irv)
|
|
223
|
|
224 (define-coding-system-alias 'old-jis 'iso-2022-jp-1978-irv)
|
|
225
|
|
226 ;; (make-coding-system
|
|
227 ;; 'japanese-iso-8bit 2 ?E
|
|
228 ;; "ISO 2022 based EUC encoding for Japanese (MIME:EUC-JP)"
|
|
229 ;; '(ascii japanese-jisx0208 katakana-jisx0201 japanese-jisx0212
|
|
230 ;; short ascii-eol ascii-cntl nil nil single-shift)
|
|
231 ;; '((safe-charsets ascii latin-jisx0201 japanese-jisx0208 japanese-jisx0208-1978
|
|
232 ;; katakana-jisx0201 japanese-jisx0212)
|
|
233 ;; (mime-charset . euc-jp)))
|
|
234
|
|
235 (make-coding-system
|
|
236 'euc-jp 'iso2022
|
|
237 "Coding-system of Japanese EUC (Extended Unix Code)."
|
|
238 '(charset-g0 ascii
|
|
239 charset-g1 japanese-jisx0208
|
|
240 charset-g2 katakana-jisx0201
|
|
241 charset-g3 japanese-jisx0212
|
|
242 short t
|
|
243 mnemonic "Ja/EUC"
|
|
244 ))
|
|
245
|
|
246 ;; (define-coding-system-alias 'euc-japan-1990 'japanese-iso-8bit)
|
|
247 ;; (define-coding-system-alias 'euc-japan 'japanese-iso-8bit)
|
|
248 ;; (define-coding-system-alias 'euc-jp 'japanese-iso-8bit)
|
|
249
|
|
250 (define-coding-system-alias 'euc-japan 'euc-jp) ; only for w3
|
|
251 (define-coding-system-alias 'japanese-euc 'euc-jp)
|
|
252
|
|
253 (set-language-info-alist
|
|
254 "Japanese" '((setup-function . setup-japanese-environment-internal)
|
|
255 (exit-function . exit-japanese-environment)
|
|
256 (tutorial . "TUTORIAL.ja")
|
|
257 (charset japanese-jisx0208 japanese-jisx0208-1978
|
|
258 japanese-jisx0212 latin-jisx0201 katakana-jisx0201)
|
|
259 (coding-system iso-2022-jp euc-jp
|
|
260 shift_jis iso-2022-jp-2)
|
|
261 (coding-priority iso-2022-jp euc-jp
|
|
262 shift_jis iso-2022-jp-2)
|
|
263 ;; (input-method . "japanese")
|
|
264 (features japan-util)
|
450
|
265 (sample-text . "Japanese ($BF|K\8l(B) $B$3$s$K$A$O(B, (I:]FAJ(B")
|
428
|
266 (documentation . t)))
|
|
267
|
|
268 ;;; japanese.el ends here
|