|
159
|
1 ;;; japanese.el --- Japanese support
|
|
|
2
|
|
|
3 ;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
|
|
197
|
4 ;; Licensed to the Free Software Foundation.
|
|
159
|
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
|
|
197
|
141 ;; (make-coding-system
|
|
|
142 ;; 'iso-2022-jp 2 ?J
|
|
|
143 ;; "ISO 2022 based 7bit encoding for Japanese (MIME:ISO-2022-JP)"
|
|
|
144 ;; '((ascii japanese-jisx0208-1978 japanese-jisx0208
|
|
|
145 ;; latin-jisx0201 japanese-jisx0212 katakana-jisx0201 t) nil nil nil
|
|
|
146 ;; short ascii-eol ascii-cntl seven))
|
|
|
147
|
|
|
148 ;; (define-coding-system-alias 'junet 'iso-2022-jp)
|
|
159
|
149
|
|
|
150 (make-coding-system
|
|
|
151 'iso-2022-jp 'iso2022
|
|
|
152 "Coding-system used for communication with mail and news in Japan."
|
|
|
153 '(charset-g0 ascii
|
|
|
154 short t
|
|
|
155 seven t
|
|
|
156 input-charset-conversion ((latin-jisx0201 ascii)
|
|
|
157 (japanese-jisx0208-1978 japanese-jisx0208))
|
|
|
158 mnemonic "MULE/7bit"
|
|
|
159 ))
|
|
|
160
|
|
|
161 (copy-coding-system 'iso-2022-jp 'junet)
|
|
|
162
|
|
|
163 ;; (make-coding-system
|
|
|
164 ;; 'shift_jis 1 ?S
|
|
|
165 ;; "Coding-system of Shift-JIS used in Japan." t)
|
|
|
166
|
|
|
167 (make-coding-system
|
|
|
168 'shift_jis 'shift-jis
|
|
|
169 "Coding-system of Shift-JIS used in Japan."
|
|
|
170 '(mnemonic "Ja/SJIS"))
|
|
|
171
|
|
|
172 ;;(define-coding-system-alias 'shift_jis 'sjis)
|
|
|
173
|
|
|
174 (copy-coding-system 'shift_jis 'sjis)
|
|
|
175
|
|
|
176 ;; (make-coding-system
|
|
|
177 ;; 'iso-2022-jp-1978-irv 2 ?J
|
|
|
178 ;; "Coding-system used for old jis terminal."
|
|
|
179 ;; '((ascii t) nil nil nil
|
|
|
180 ;; short ascii-eol ascii-cntl seven nil nil use-roman use-oldjis))
|
|
|
181
|
|
|
182 (make-coding-system
|
|
|
183 'iso-2022-jp-1978-irv 'iso2022
|
|
|
184 "Coding-system used for old JIS terminal."
|
|
|
185 '(charset-g0 ascii
|
|
|
186 short t
|
|
|
187 seven t
|
|
|
188 output-charset-conversion ((ascii latin-jisx0201)
|
|
|
189 (japanese-jisx0208 japanese-jisx0208-1978))
|
|
|
190 mnemonic "Ja-78/7bit"
|
|
|
191 ))
|
|
|
192
|
|
|
193 ;;(define-coding-system-alias 'iso-2022-jp-1978-irv 'old-jis)
|
|
|
194
|
|
|
195 (copy-coding-system 'iso-2022-jp-1978-irv 'old-jis)
|
|
|
196
|
|
|
197 ;; (make-coding-system
|
|
|
198 ;; 'euc-japan-1990 2 ?E
|
|
|
199 ;; "Coding-system of Japanese EUC (Extended Unix Code)."
|
|
|
200 ;; '(ascii japanese-jisx0208 katakana-jisx0201 japanese-jisx0212
|
|
|
201 ;; short ascii-eol ascii-cntl nil nil single-shift))
|
|
|
202
|
|
|
203 (make-coding-system
|
|
|
204 'euc-jp 'iso2022
|
|
|
205 "Coding-system of Japanese EUC (Extended Unix Code)."
|
|
|
206 '(charset-g0 ascii
|
|
|
207 charset-g1 japanese-jisx0208
|
|
|
208 charset-g2 katakana-jisx0201
|
|
|
209 charset-g3 japanese-jisx0212
|
|
|
210 short t
|
|
|
211 mnemonic "Ja/EUC"
|
|
|
212 ))
|
|
|
213
|
|
|
214 ;;(define-coding-system-alias 'euc-japan-1990 'euc-japan)
|
|
|
215
|
|
|
216 (copy-coding-system 'euc-jp 'euc-japan) ; only for w3
|
|
|
217 (copy-coding-system 'euc-jp 'japanese-euc)
|
|
|
218
|
|
|
219 (set-language-info-alist
|
|
|
220 "Japanese" '((setup-function . setup-japanese-environment)
|
|
|
221 (tutorial . "TUTORIAL.jp")
|
|
|
222 (charset . (japanese-jisx0208 japanese-jisx0208-1978
|
|
|
223 japanese-jisx0212 latin-jisx0201
|
|
|
224 katakana-jisx0201))
|
|
197
|
225 (coding-system . (iso-2022-jp euc-jp
|
|
|
226 shift_jis iso-2022-jp-1978-irv))
|
|
159
|
227 (sample-text . "Japanese ($BF|K\8l(B) $B$3$s$K$A$O(B, (I:]FAJ(B")
|
|
197
|
228 (documentation . t)))
|
|
159
|
229
|
|
|
230 ;;; japanese.el ends here
|
