1 ;;; chinese.el --- Support for Chinese -*- coding: iso-2022-7bit; -*-
3 ;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
4 ;; Licensed to the Free Software Foundation.
5 ;; Copyright (C) 1997 MORIOKA Tomohiko
7 ;; Keywords: multilingual, Chinese
9 ;; This file is part of XEmacs.
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)
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.
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
28 ;; For Chinese, three character sets GB2312, BIG5, and CNS11643 are
33 ;; Syntax of Chinese characters.
34 (modify-syntax-entry 'chinese-gb2312 "w")
35 (loop for row in '(33 34 41)
36 do (modify-syntax-entry `[chinese-gb2312 ,row] "."))
37 ;;(loop for row from 35 to 40
38 ;; do (modify-syntax-entry `[chinese-gb2312 ,row] "w"))
39 ;;(loop for row from 42 to 126
40 ;; do (modify-syntax-entry `[chinese-gb2312 ,row] "w"))
42 (modify-syntax-entry 'chinese-cns11643-1 "w")
43 (modify-syntax-entry 'chinese-cns11643-2 "w")
44 (modify-syntax-entry 'chinese-big5-1 "w")
45 (modify-syntax-entry 'chinese-big5-2 "w")
47 ;; CNS11643 Plane3 thru Plane7
48 ;; These represent more and more obscure Chinese characters.
49 ;; By the time you get to Plane 7, we're talking about characters
50 ;; that appear once in some ancient manuscript and whose meaning
53 (unless (featurep 'utf-2000)
55 ((make-chinese-cns11643-charset
58 name (concat "CNS 11643 Plane " plane " (Chinese traditional)")
60 ,(concat "CNS11643[.-]\\(.*[.-]\\)?" plane "$")
65 (modify-syntax-entry name "w")
66 (modify-category-entry name ?t)
68 (make-chinese-cns11643-charset 'chinese-cns11643-3 "3" ?I)
69 (make-chinese-cns11643-charset 'chinese-cns11643-4 "4" ?J)
70 (make-chinese-cns11643-charset 'chinese-cns11643-5 "5" ?K)
71 (make-chinese-cns11643-charset 'chinese-cns11643-6 "6" ?L)
72 (make-chinese-cns11643-charset 'chinese-cns11643-7 "7" ?M)
75 ;; ISO-IR-165 (CCITT Extended GB)
76 ;; It is based on CCITT Recommendation T.101, includes GB 2312-80 +
77 ;; GB 8565-88 table A4 + 293 characters.
80 "ISO-IR-165 (CCITT Extended GB; Chinese simplified)"
88 (make-charset 'sisheng "PinYin-ZhuYin"
89 '(registry "sisheng_cwnn\\|OMRON_UDC_ZH"
96 ;; If you prefer QUAIL to EGG, please modify below as you wish.
97 ;;(when (and (featurep 'egg) (featurep 'wnn))
98 ;; (setq wnn-server-type 'cserver)
100 ;; (setq its:*standard-modes*
101 ;; (cons (its:get-mode-map "PinYin") its:*standard-modes*)))
103 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
104 ;;; Chinese (general)
105 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
107 ;; (make-coding-system
109 ;; "ISO 2022 based 7bit encoding for Chinese GB and CNS (MIME:ISO-2022-CN)"
111 ;; (nil chinese-gb2312 chinese-cns11643-1)
112 ;; (nil chinese-cns11643-2)
114 ;; nil ascii-eol ascii-cntl seven locking-shift single-shift nil nil nil
116 ;; '((safe-charsets ascii chinese-gb2312 chinese-cns11643-1 chinese-cns11643-2)
117 ;; (mime-charset . iso-2022-cn)))
119 ;; (define-coding-system-alias 'chinese-iso-7bit 'iso-2022-cn)
121 ;; (make-coding-system
122 ;; 'iso-2022-cn-ext 2 ?C
123 ;; "ISO 2022 based 7bit encoding for Chinese GB and CNS (MIME:ISO-2022-CN-EXT)"
125 ;; (nil chinese-gb2312 chinese-cns11643-1)
126 ;; (nil chinese-cns11643-2)
127 ;; (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5
128 ;; chinese-cns11643-6 chinese-cns11643-7)
129 ;; nil ascii-eol ascii-cntl seven locking-shift single-shift nil nil nil
131 ;; '((safe-charsets ascii chinese-gb2312 chinese-cns11643-1 chinese-cns11643-2
132 ;; chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5
133 ;; chinese-cns11643-6 chinese-cns11643-7)
134 ;; (mime-charset . iso-2022-cn-ext)))
137 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
138 ;;; Chinese GB2312 (simplified)
139 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
141 ;; (make-coding-system
142 ;; 'chinese-iso-8bit 2 ?c
143 ;; "ISO 2022 based EUC encoding for Chinese GB2312 (MIME:CN-GB-2312)"
144 ;; '(ascii chinese-gb2312 nil nil
145 ;; nil ascii-eol ascii-cntl nil nil nil nil)
146 ;; '((safe-charsets ascii chinese-gb2312)
147 ;; (mime-charset . cn-gb-2312)))
151 "Coding-system of Chinese EUC (Extended Unix Code)."
153 charset-g1 chinese-gb2312
159 ;; (define-coding-system-alias 'cn-gb-2312 'chinese-iso-8bit)
160 ;; (define-coding-system-alias 'euc-china 'chinese-iso-8bit)
161 ;; (define-coding-system-alias 'euc-cn 'chinese-iso-8bit)
163 (define-coding-system-alias 'gb2312 'cn-gb-2312)
164 (define-coding-system-alias 'chinese-euc 'cn-gb-2312)
166 ;; (make-coding-system
168 ;; "Hz/ZW 7-bit encoding for Chinese GB2312 (MIME:HZ-GB-2312)"
170 ;; '((safe-charsets ascii chinese-gb2312)
171 ;; (mime-charset . hz-gb-2312)
172 ;; (post-read-conversion . post-read-decode-hz)
173 ;; (pre-write-conversion . pre-write-encode-hz)))
174 ;; (put 'chinese-hz 'post-read-conversion 'post-read-decode-hz)
175 ;; (put 'chinese-hz 'pre-write-conversion 'pre-write-encode-hz)
178 'hz-gb-2312 'no-conversion
179 "Coding-system of Hz/ZW used for Chinese."
180 '(mnemonic "Zh-GB/Hz"
182 post-read-conversion post-read-decode-hz
183 pre-write-conversion pre-write-encode-hz))
185 ;; (define-coding-system-alias 'hz-gb-2312 'chinese-hz)
186 ;; (define-coding-system-alias 'hz 'chinese-hz)
188 (define-coding-system-alias 'hz 'hz-gb-2312)
190 (defun post-read-decode-hz (len)
192 (buffer-modified-p (buffer-modified-p))
193 last-coding-system-used)
195 (decode-hz-region pos (+ pos len))
196 (set-buffer-modified-p buffer-modified-p))))
198 (defun pre-write-encode-hz (from to)
199 (let ((buf (current-buffer)))
200 (set-buffer (generate-new-buffer " *temp*"))
203 (insert-buffer-substring buf from to))
204 (let (last-coding-system-used)
205 (encode-hz-region 1 (point-max)))
208 (set-language-info-alist
209 "Chinese-GB" '((setup-function . setup-chinese-gb-environment-internal)
210 (charset chinese-gb2312 sisheng)
211 (coding-system cn-gb-2312 iso-2022-7bit hz-gb-2312)
212 (coding-priority cn-gb-2312 big5 iso-2022-7bit)
213 (input-method . "chinese-py-punct")
214 (features china-util)
215 (sample-text . "Chinese (
\e$AVPND
\e(B,
\e$AFUM(;0
\e(B,
\e$A::So
\e(B)
\e$ADc:C
\e(B")
216 (documentation . "Support for Chinese GB2312 character set."))
219 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
220 ;; Chinese BIG5 (traditional)
221 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
223 ;; (make-coding-system
224 ;; 'chinese-big5 3 ?B "BIG5 8-bit encoding for Chinese (MIME:CN-BIG5)"
226 ;; '((safe-charsets ascii chinese-big5-1 chinese-big5-2)
227 ;; (mime-charset . cn-big5)
228 ;; (charset-origin-alist (chinese-big5-1 "BIG5" encode-big5-char)
229 ;; (chinese-big5-2 "BIG5" encode-big5-char))))
233 "Coding-system of BIG5."
234 '(mnemonic "Zh/Big5"))
236 ;; (define-coding-system-alias 'big5 'chinese-big5)
237 ;; (define-coding-system-alias 'cn-big5 'chinese-big5)
239 (define-coding-system-alias 'cn-big5 'big5)
241 ;; Big5 font requires special encoding.
242 (define-ccl-program ccl-encode-big5-font
244 ;; In: R0:chinese-big5-1 or chinese-big5-2
245 ;; R1:position code 1
246 ;; R2:position code 2
247 ;; Out: R1:font code point 1
248 ;; R2:font code point 2
249 ((r2 = ((((r1 - ?\x21) * 94) + r2) - ?\x21))
250 (if (r0 == ,(charset-id 'chinese-big5-2)) (r2 += 6280))
251 (r1 = ((r2 / 157) + ?\xA1))
253 (if (r2 < ?\x3F) (r2 += ?\x40) (r2 += ?\x62))))
254 "CCL program to encode a Big5 code to code point of Big5 font.")
256 ;; (setq font-ccl-encoder-alist
257 ;; (cons (cons "big5" ccl-encode-big5-font) font-ccl-encoder-alist))
259 (set-charset-ccl-program 'chinese-big5-1 ccl-encode-big5-font)
260 (set-charset-ccl-program 'chinese-big5-2 ccl-encode-big5-font)
262 (set-language-info-alist
263 "Chinese-BIG5" '((charset chinese-big5-1 chinese-big5-2)
264 (coding-system big5 iso-2022-7bit)
265 (coding-priority big5 cn-gb-2312 iso-2022-7bit)
266 (input-method . "chinese-py-punct-b5")
267 (features china-util)
268 (sample-text . "Cantonese (
\e$(0GnM$
\e(B,
\e$(0N]0*Hd
\e(B)
\e$(0*/=(
\e(B,
\e$(0+$)p
\e(B")
269 (documentation . "Support for Chinese Big5 character set."))
272 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
273 ;; Chinese CNS11643 (traditional)
274 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
276 ;; (set-language-info-alist
277 ;; "Chinese-CNS" '((charset chinese-cns11643-1 chinese-cns11643-2
278 ;; chinese-cns11643-3 chinese-cns11643-4
279 ;; chinese-cns11643-5 chinese-cns11643-6
280 ;; chinese-cns11643-7)
281 ;; (coding-system iso-2022-cn)
282 ;; (coding-priority iso-2022-cn chinese-big5 chinese-iso-8bit)
283 ;; (features china-util)
284 ;; (input-method . "chinese-cns-quick")
285 ;; (documentation . "Support for Chinese CNS character sets."))
288 ;;; chinese.el ends here