Mercurial > hg > xemacs-beta

comparison lisp/language/japanese.el @ 159:3bb7ccffb0c0 r20-3b6

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Import from CVS: tag r20-3b6
author cvs
date Mon, 13 Aug 2007 09:41:43 +0200
parents
children acd284d43ca1
comparison
equal deleted inserted replaced
158:558dfa75ffb3 159:3bb7ccffb0c0
1 ;;; japanese.el --- Japanese support
2
3 ;; Copyright (C) 1995 Free Software Foundation, Inc.
4 ;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
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/its-hira")
109 (load "its/its-kata")
110 (load "its/its-hankaku")
111 (load "its/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 (setq egg-default-startup-file "eggrc-wnn")
124 (setq-default its:*current-map* (its:get-mode-map "roma-kana"))))
125
126 ;; stuff for providing gramatic processing of Japanese text
127 ;; something like this should probably be created for all environments...
128
129 (defvar aletter (concat "\\(" ascii-char "\\|" kanji-char "\\)"))
130 (defvar kanji-space-insertable (concat
131 "$B!"(B" aletter "\\|"
132 "$B!#(B" aletter "\\|"
133 aletter "$B!J(B" "\\|"
134 "$B!K(B" aletter "\\|"
135 ascii-alphanumeric kanji-kanji-char "\\|"
136 kanji-kanji-char ascii-alphanumeric ))
137
138 (defvar space-insertable (concat " " aletter "\\|" kanji-space-insertable)
139 "Regexp for finding points that can have spaces inserted into them for justification")
140
141 ;; (define-coding-system-alias 'iso-2022-7 'iso-2022-jp)
142 ;; (define-coding-system-alias 'iso-2022-7 'junet)
143
144 (make-coding-system
145 'iso-2022-jp 'iso2022
146 "Coding-system used for communication with mail and news in Japan."
147 '(charset-g0 ascii
148 short t
149 seven t
150 input-charset-conversion ((latin-jisx0201 ascii)
151 (japanese-jisx0208-1978 japanese-jisx0208))
152 mnemonic "MULE/7bit"
153 ))
154
155 (copy-coding-system 'iso-2022-jp 'junet)
156
157 ;; (make-coding-system
158 ;; 'shift_jis 1 ?S
159 ;; "Coding-system of Shift-JIS used in Japan." t)
160
161 (make-coding-system
162 'shift_jis 'shift-jis
163 "Coding-system of Shift-JIS used in Japan."
164 '(mnemonic "Ja/SJIS"))
165
166 ;;(define-coding-system-alias 'shift_jis 'sjis)
167
168 (copy-coding-system 'shift_jis 'sjis)
169
170 ;; (make-coding-system
171 ;; 'iso-2022-jp-1978-irv 2 ?J
172 ;; "Coding-system used for old jis terminal."
173 ;; '((ascii t) nil nil nil
174 ;; short ascii-eol ascii-cntl seven nil nil use-roman use-oldjis))
175
176 (make-coding-system
177 'iso-2022-jp-1978-irv 'iso2022
178 "Coding-system used for old JIS terminal."
179 '(charset-g0 ascii
180 short t
181 seven t
182 output-charset-conversion ((ascii latin-jisx0201)
183 (japanese-jisx0208 japanese-jisx0208-1978))
184 mnemonic "Ja-78/7bit"
185 ))
186
187 ;;(define-coding-system-alias 'iso-2022-jp-1978-irv 'old-jis)
188
189 (copy-coding-system 'iso-2022-jp-1978-irv 'old-jis)
190
191 ;; (make-coding-system
192 ;; 'euc-japan-1990 2 ?E
193 ;; "Coding-system of Japanese EUC (Extended Unix Code)."
194 ;; '(ascii japanese-jisx0208 katakana-jisx0201 japanese-jisx0212
195 ;; short ascii-eol ascii-cntl nil nil single-shift))
196
197 (make-coding-system
198 'euc-jp 'iso2022
199 "Coding-system of Japanese EUC (Extended Unix Code)."
200 '(charset-g0 ascii
201 charset-g1 japanese-jisx0208
202 charset-g2 katakana-jisx0201
203 charset-g3 japanese-jisx0212
204 short t
205 mnemonic "Ja/EUC"
206 ))
207
208 ;;(define-coding-system-alias 'euc-japan-1990 'euc-japan)
209
210 (copy-coding-system 'euc-jp 'euc-japan) ; only for w3
211 (copy-coding-system 'euc-jp 'japanese-euc)
212
213 (register-input-method
214 "Japanese" '("quail-ja-hiragana" quail-use-package "quail/japanese"))
215 (register-input-method
216 "Japanese" '("quail-ja" quail-use-package "quail/japanese"))
217
218 (defun setup-japanese-environment ()
219 "Setup multilingual environment (MULE) for Japanese."
220 (interactive)
221 (setq coding-category-iso-8-2 'euc-jp)
222
223 (set-coding-priority
224 '(coding-category-iso-7
225 coding-category-iso-8-2
226 coding-category-sjis
227 coding-category-iso-8-1
228 coding-category-iso-else
229 coding-category-internal))
230
231 (if (eq system-type 'ms-dos)
232 (progn
233 (setq-default buffer-file-coding-system 'shift_jis)
234 (set-terminal-coding-system 'shift_jis)
235 (set-keyboard-coding-system 'shift_jis)
236 (setq default-process-coding-system '(shift_jis-dos . shift_jis-dos)))
237 (setq-default buffer-file-coding-system 'iso-2022-jp)
238 (set-terminal-coding-system 'iso-2022-jp)
239 (set-keyboard-coding-system 'iso-2022-jp))
240
241 (set-default-input-method "Japanese" "quail-ja")
242
243 (setq sendmail-coding-system 'iso-2022-jp
244 rmail-file-coding-system 'iso-2022-jp)
245 )
246
247 (defun describe-japanese-support ()
248 "Describe how Emacs supports Japanese."
249 (interactive)
250 (describe-language-support-internal "Japanese"))
251
252 (set-language-info-alist
253 "Japanese" '((setup-function . setup-japanese-environment)
254 (describe-function . describe-japanese-support)
255 (tutorial . "TUTORIAL.jp")
256 (charset . (japanese-jisx0208 japanese-jisx0208-1978
257 japanese-jisx0212 latin-jisx0201
258 katakana-jisx0201))
259 (coding-system . (euc-jp shift_jis
260 iso-2022-jp iso-2022-jp-1978-irv))
261 (sample-text . "Japanese ($BF|K\8l(B) $B$3$s$K$A$O(B, (I:]FAJ(B")
262 (documentation . nil)))
263
264 ;; for XEmacs (will be obsoleted)
265
266 (define-language-environment 'japanese
267 "Japanese (includes JIS and EUC)"
268 (lambda ()
269 (set-coding-category-system 'iso-7 'iso-2022-jp)
270 (set-coding-category-system 'iso-8-2 'euc-jp)
271 (set-coding-priority-list '(iso-7 iso-8-2 shift-jis no-conversion))
272 ;;'(iso-8-2 iso-8-designate iso-8-1 shift-jis big5)
273
274 ;; Added by mrb, who doesn't speak japanese - so be sceptical...
275 ;; (when (string-match "solaris\\|sunos" system-configuration)
276 ;;(set-native-coding-system 'euc-japan) ; someday
277 (set-pathname-coding-system 'euc-jp)
278 (add-hook 'comint-exec-hook
279 (lambda ()
280 (let ((proc (get-buffer-process (current-buffer))))
281 (set-process-input-coding-system proc 'euc-jp)
282 (set-process-output-coding-system proc 'euc-jp))))
283 ;;(set-buffer-file-coding-system-for-read 'automatic-conversion)
284 (set-default-buffer-file-coding-system 'euc-jp)
285 (setq keyboard-coding-system 'euc-jp)
286 (setq terminal-coding-system 'euc-jp)
287 (when (eq 'x (device-type (selected-device)))
288 (x-use-halfwidth-roman-font 'japanese-jisx0208 "jisx0201"))
289
290 (when (eq system-type 'ms-dos)
291 ;; Shift-JIS is the standard coding system under Japanese MS-DOS
292 ;; This isn't really code - just a hint to future implementors
293 (setq keyboard-coding-system 'shift_jis-dos)
294 (setq terminal-coding-system 'shift_jis-dos)
295 (set-default-buffer-file-coding-system 'shift_jis-dos)
296 ;;(set-default-process-coding-system 'shift_jis-dos 'shift_jis-dos)
297 )
298 ))
299
300 (set-coding-category-system 'shift-jis 'shift_jis)
301
302 ;;; japanese.el ends here