1 |
;;; china-util.el --- utilities for Chinese |
;;; china-util.el --- utilities for Chinese -*- coding: iso-2022-7bit -*- |
2 |
|
|
3 |
;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN. |
;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN. |
4 |
;; Licensed to the Free Software Foundation. |
;; Licensed to the Free Software Foundation. |
5 |
|
;; Copyright (C) 1995, 2001 Free Software Foundation, Inc. |
6 |
|
|
7 |
;; Keywords: mule, multilingual, Chinese |
;; Keywords: mule, multilingual, Chinese |
8 |
|
|
27 |
|
|
28 |
;;; Code: |
;;; Code: |
29 |
|
|
30 |
;; Hz/ZW encoding stuffs |
;; Hz/ZW/EUC-TW encoding stuff |
31 |
|
|
32 |
;; HZ is an encoding method for Chinese character set GB2312 used |
;; HZ is an encoding method for Chinese character set GB2312 used |
33 |
;; widely in Internet. It is very similar to 7-bit environment of |
;; widely in Internet. It is very similar to 7-bit environment of |
39 |
;; encodes Chinese characters line by line by starting each line with |
;; encodes Chinese characters line by line by starting each line with |
40 |
;; the sequence "zW". It also uses only 7-bit as HZ. |
;; the sequence "zW". It also uses only 7-bit as HZ. |
41 |
|
|
42 |
|
;; EUC-TW is similar to EUC-KS or EUC-JP. Its main character set is |
43 |
|
;; plane 1 of CNS 11643; characters of planes 2 to 7 are accessed with |
44 |
|
;; a single shift escape followed by three bytes: the first gives the |
45 |
|
;; plane, the second and third the character code. Note that characters |
46 |
|
;; of plane 1 are (redundantly) accessible with a single shift escape |
47 |
|
;; also. |
48 |
|
|
49 |
;; ISO-2022 escape sequence to designate GB2312. |
;; ISO-2022 escape sequence to designate GB2312. |
50 |
(defvar iso2022-gb-designation "\e$A") |
(defvar iso2022-gb-designation "\e$A") |
51 |
;; HZ escape sequence to designate GB2312. |
;; HZ escape sequence to designate GB2312. |
164 |
(interactive) |
(interactive) |
165 |
(encode-hz-region (point-min) (point-max))) |
(encode-hz-region (point-min) (point-max))) |
166 |
|
|
167 |
|
;; The following sets up a translation table (big5-to-cns) from Big 5 |
168 |
|
;; to CNS encoding, using some auxiliary functions to make the code |
169 |
|
;; more readable. |
170 |
|
|
171 |
|
;; Many kudos to Himi! The used code has been adapted from his |
172 |
|
;; mule-ucs package. |
173 |
|
|
174 |
|
(defun big5-to-flat-code (num) |
175 |
|
"Convert NUM in Big 5 encoding to a `flat code'. |
176 |
|
0xA140 will be mapped to position 0, 0xA141 to position 1, etc. |
177 |
|
There are no gaps in the flat code." |
178 |
|
|
179 |
|
(let ((hi (/ num 256)) |
180 |
|
(lo (% num 256))) |
181 |
|
(+ (* 157 (- hi #xa1)) |
182 |
|
(- lo (if (>= lo #xa1) 98 64))))) |
183 |
|
|
184 |
|
(defun flat-code-to-big5 (num) |
185 |
|
"Convert NUM from a `flat code' to Big 5 encoding. |
186 |
|
This is the inverse function of `big5-to-flat-code'." |
187 |
|
|
188 |
|
(let ((hi (/ num 157)) |
189 |
|
(lo (% num 157))) |
190 |
|
(+ (* 256 (+ hi #xa1)) |
191 |
|
(+ lo (if (< lo 63) 64 98))))) |
192 |
|
|
193 |
|
(defun euc-to-flat-code (num) |
194 |
|
"Convert NUM in EUC encoding (in GL representation) to a `flat code'. |
195 |
|
0x2121 will be mapped to position 0, 0x2122 to position 1, etc. |
196 |
|
There are no gaps in the flat code." |
197 |
|
|
198 |
|
(let ((hi (/ num 256)) |
199 |
|
(lo (% num 256))) |
200 |
|
(+ (* 94 (- hi #x21)) |
201 |
|
(- lo #x21)))) |
202 |
|
|
203 |
|
(defun flat-code-to-euc (num) |
204 |
|
"Convert NUM from a `flat code' to EUC encoding (in GL representation). |
205 |
|
The inverse function of `euc-to-flat-code'. The high and low bytes are |
206 |
|
returned in a list." |
207 |
|
|
208 |
|
(let ((hi (/ num 94)) |
209 |
|
(lo (% num 94))) |
210 |
|
(list (+ hi #x21) (+ lo #x21)))) |
211 |
|
|
212 |
|
(defun expand-euc-big5-alist (alist) |
213 |
|
"Create a translation table and fills it with data given in ALIST. |
214 |
|
Elements of ALIST can be either given as |
215 |
|
|
216 |
|
((euc-charset . startchar) . (big5-range-begin . big5-range-end)) |
217 |
|
|
218 |
|
or as |
219 |
|
|
220 |
|
(euc-character . big5-charcode) |
221 |
|
|
222 |
|
The former maps a range of glyphs in an EUC charset (where STARTCHAR |
223 |
|
is in GL representation) to a certain range of Big 5 encoded |
224 |
|
characters, the latter maps a single glyph. Glyphs which can't be |
225 |
|
mapped will be represented with the byte 0xFF. |
226 |
|
|
227 |
|
The return value is the filled translation table." |
228 |
|
|
229 |
|
(let (chartable |
230 |
|
elem |
231 |
|
result |
232 |
|
char |
233 |
|
big5 |
234 |
|
i |
235 |
|
end |
236 |
|
codepoint |
237 |
|
charset) |
238 |
|
(setq chartable (make-char-table 'translation-table #xFF)) |
239 |
|
(while alist |
240 |
|
(setq elem (car alist) |
241 |
|
char (car elem) |
242 |
|
big5 (cdr elem) |
243 |
|
alist (cdr alist)) |
244 |
|
(cond ((and (consp char) |
245 |
|
(consp big5)) |
246 |
|
(setq i (big5-to-flat-code (car big5)) |
247 |
|
end (big5-to-flat-code (cdr big5)) |
248 |
|
codepoint (euc-to-flat-code (cdr char)) |
249 |
|
charset (car char)) |
250 |
|
(while (>= end i) |
251 |
|
(aset chartable |
252 |
|
(decode-big5-char (flat-code-to-big5 i)) |
253 |
|
(apply (function make-char) |
254 |
|
charset |
255 |
|
(flat-code-to-euc codepoint))) |
256 |
|
(setq i (1+ i) |
257 |
|
codepoint (1+ codepoint))) |
258 |
|
) |
259 |
|
((and (char-valid-p char) |
260 |
|
(numberp big5)) |
261 |
|
(setq i (decode-big5-char big5)) |
262 |
|
(aset chartable i char) |
263 |
|
) |
264 |
|
(t |
265 |
|
(error "Unknown slot type: %S" elem) |
266 |
|
) |
267 |
|
) |
268 |
|
) |
269 |
|
;; the return value |
270 |
|
chartable |
271 |
|
) |
272 |
|
) |
273 |
|
|
274 |
|
;; All non-CNS encodings are commented out. |
275 |
|
|
276 |
|
(define-translation-table 'big5-to-cns |
277 |
|
(expand-euc-big5-alist |
278 |
|
'( |
279 |
|
;; Symbols |
280 |
|
((chinese-cns11643-1 . #x2121) . (#xA140 . #xA1F5)) |
281 |
|
(?$(G"X(B . #xA1F6) |
282 |
|
(?$(G"W(B . #xA1F7) |
283 |
|
((chinese-cns11643-1 . #x2259) . (#xA1F8 . #xA2AE)) |
284 |
|
((chinese-cns11643-1 . #x2421) . (#xA2AF . #xA3BF)) |
285 |
|
;; Control codes (vendor dependent) |
286 |
|
((chinese-cns11643-1 . #x4221) . (#xA3C0 . #xA3E0)) |
287 |
|
;; Level 1 Ideographs |
288 |
|
((chinese-cns11643-1 . #x4421) . (#xA440 . #xACFD)) |
289 |
|
(?$(GWS(B . #xACFE) |
290 |
|
((chinese-cns11643-1 . #x5323) . (#xAD40 . #xAFCF)) |
291 |
|
((chinese-cns11643-1 . #x5754) . (#xAFD0 . #xBBC7)) |
292 |
|
((chinese-cns11643-1 . #x6B51) . (#xBBC8 . #xBE51)) |
293 |
|
(?$(GkP(B . #xBE52) |
294 |
|
((chinese-cns11643-1 . #x6F5C) . (#xBE53 . #xC1AA)) |
295 |
|
((chinese-cns11643-1 . #x7536) . (#xC1AB . #xC2CA)) |
296 |
|
(?$(Gu5(B . #xC2CB) |
297 |
|
((chinese-cns11643-1 . #x7737) . (#xC2CC . #xC360)) |
298 |
|
((chinese-cns11643-1 . #x782E) . (#xC361 . #xC3B8)) |
299 |
|
(?$(Gxe(B . #xC3B9) |
300 |
|
(?$(Gxd(B . #xC3BA) |
301 |
|
((chinese-cns11643-1 . #x7866) . (#xC3BB . #xC455)) |
302 |
|
(?$(Gx-(B . #xC456) |
303 |
|
((chinese-cns11643-1 . #x7962) . (#xC457 . #xC67E)) |
304 |
|
;; Symbols |
305 |
|
((chinese-cns11643-1 . #x2621) . (#xC6A1 . #xC6BE)) |
306 |
|
;; Radicals |
307 |
|
(?$(G'#(B . #xC6BF) |
308 |
|
(?$(G'$(B . #xC6C0) |
309 |
|
(?$(G'&(B . #xC6C1) |
310 |
|
(?$(G'((B . #xC6C2) |
311 |
|
(?$(G'-(B . #xC6C3) |
312 |
|
(?$(G'.(B . #xC6C4) |
313 |
|
(?$(G'/(B . #xC6C5) |
314 |
|
(?$(G'4(B . #xC6C6) |
315 |
|
(?$(G'7(B . #xC6C7) |
316 |
|
(?$(G':(B . #xC6C8) |
317 |
|
(?$(G'<(B . #xC6C9) |
318 |
|
(?$(G'B(B . #xC6CA) |
319 |
|
(?$(G'G(B . #xC6CB) |
320 |
|
(?$(G'N(B . #xC6CC) |
321 |
|
(?$(G'S(B . #xC6CD) |
322 |
|
(?$(G'T(B . #xC6CE) |
323 |
|
(?$(G'U(B . #xC6CF) |
324 |
|
(?$(G'Y(B . #xC6D0) |
325 |
|
(?$(G'Z(B . #xC6D1) |
326 |
|
(?$(G'a(B . #xC6D2) |
327 |
|
(?$(G'f(B . #xC6D3) |
328 |
|
(?$(G()(B . #xC6D4) |
329 |
|
(?$(G(*(B . #xC6D5) |
330 |
|
(?$(G(c(B . #xC6D6) |
331 |
|
(?$(G(l(B . #xC6D7) |
332 |
|
;; Diacritical Marks |
333 |
|
; ((japanese-jisx0208 . #x212F) . (#xC6D8 . #xC6D9)) |
334 |
|
;; Japanese Kana Supplement |
335 |
|
; ((japanese-jisx0208 . #x2133) . (#xC6DA . #xC6E3)) |
336 |
|
;; Japanese Hiragana |
337 |
|
; ((japanese-jisx0208 . #x2421) . (#xC6E7 . #xC77A)) |
338 |
|
;; Japanese Katakana |
339 |
|
; ((japanese-jisx0208 . #x2521) . (#xC77B . #xC7F2)) |
340 |
|
;; Cyrillic Characters |
341 |
|
; ((japanese-jisx0208 . #x2721) . (#xC7F3 . #xC854)) |
342 |
|
; ((japanese-jisx0208 . #x2751) . (#xC855 . #xC875)) |
343 |
|
;; Special Chinese Characters |
344 |
|
(?$(J!#(B . #xC879) |
345 |
|
(?$(J!$(B . #xC87B) |
346 |
|
(?$(J!*(B . #xC87D) |
347 |
|
(?$(J!R(B . #xC8A2) |
348 |
|
|
349 |
|
;; JIS X 0208 NOT SIGN (cf. U+00AC) |
350 |
|
; (?$B"L(B . #xC8CD) |
351 |
|
;; JIS X 0212 BROKEN BAR (cf. U+00A6) |
352 |
|
; (?$(D"C(B . #xC8CE) |
353 |
|
|
354 |
|
;; GB 2312 characters |
355 |
|
; (?$A!d(B . #xC8CF) |
356 |
|
; (?$A!e(B . #xC8D0) |
357 |
|
;;;;; C8D1 - Japanese `($B3t(B)' |
358 |
|
; (?$A!m(B . #xC8D2) |
359 |
|
;;;;; C8D2 - Tel. |
360 |
|
|
361 |
|
;; Level 2 Ideographs |
362 |
|
((chinese-cns11643-2 . #x2121) . (#xC940 . #xC949)) |
363 |
|
(?$(GDB(B . #xC94A);; a duplicate of #xA461 |
364 |
|
((chinese-cns11643-2 . #x212B) . (#xC94B . #xC96B)) |
365 |
|
((chinese-cns11643-2 . #x214D) . (#xC96C . #xC9BD)) |
366 |
|
(?$(H!L(B . #xC9BE) |
367 |
|
((chinese-cns11643-2 . #x217D) . (#xC9BF . #xC9EC)) |
368 |
|
((chinese-cns11643-2 . #x224E) . (#xC9ED . #xCAF6)) |
369 |
|
(?$(H"M(B . #xCAF7) |
370 |
|
((chinese-cns11643-2 . #x2439) . (#xCAF8 . #xD6CB)) |
371 |
|
(?$(H>c(B . #xD6CC) |
372 |
|
((chinese-cns11643-2 . #x3770) . (#xD6CD . #xD779)) |
373 |
|
(?$(H?j(B . #xD77A) |
374 |
|
((chinese-cns11643-2 . #x387E) . (#xD77B . #xDADE)) |
375 |
|
(?$(H7o(B . #xDADF) |
376 |
|
((chinese-cns11643-2 . #x3E64) . (#xDAE0 . #xDBA6)) |
377 |
|
((chinese-cns11643-2 . #x3F6B) . (#xDBA7 . #xDDFB)) |
378 |
|
(?$(HAv(B . #xDDFC);; a duplicate of #xDCD1 |
379 |
|
((chinese-cns11643-2 . #x4424) . (#xDDFD . #xE8A2)) |
380 |
|
((chinese-cns11643-2 . #x554C) . (#xE8A3 . #xE975)) |
381 |
|
((chinese-cns11643-2 . #x5723) . (#xE976 . #xEB5A)) |
382 |
|
((chinese-cns11643-2 . #x5A29) . (#xEB5B . #xEBF0)) |
383 |
|
(?$(HUK(B . #xEBF1) |
384 |
|
((chinese-cns11643-2 . #x5B3F) . (#xEBF2 . #xECDD)) |
385 |
|
(?$(HW"(B . #xECDE) |
386 |
|
((chinese-cns11643-2 . #x5C6A) . (#xECDF . #xEDA9)) |
387 |
|
((chinese-cns11643-2 . #x5D75) . (#xEDAA . #xEEEA)) |
388 |
|
(?$(Hd/(B . #xEEEB) |
389 |
|
((chinese-cns11643-2 . #x6039) . (#xEEEC . #xF055)) |
390 |
|
(?$(H]t(B . #xF056) |
391 |
|
((chinese-cns11643-2 . #x6243) . (#xF057 . #xF0CA)) |
392 |
|
(?$(HZ((B . #xF0CB) |
393 |
|
((chinese-cns11643-2 . #x6337) . (#xF0CC . #xF162)) |
394 |
|
((chinese-cns11643-2 . #x6430) . (#xF163 . #xF16A)) |
395 |
|
(?$(Hga(B . #xF16B) |
396 |
|
((chinese-cns11643-2 . #x6438) . (#xF16C . #xF267)) |
397 |
|
(?$(Hi4(B . #xF268) |
398 |
|
((chinese-cns11643-2 . #x6573) . (#xF269 . #xF2C2)) |
399 |
|
((chinese-cns11643-2 . #x664E) . (#xF2C3 . #xF374)) |
400 |
|
((chinese-cns11643-2 . #x6762) . (#xF375 . #xF465)) |
401 |
|
((chinese-cns11643-2 . #x6935) . (#xF466 . #xF4B4)) |
402 |
|
(?$(HfM(B . #xF4B5) |
403 |
|
((chinese-cns11643-2 . #x6962) . (#xF4B6 . #xF4FC)) |
404 |
|
((chinese-cns11643-2 . #x6A4C) . (#xF4FD . #xF662)) |
405 |
|
(?$(HjK(B . #xF663) |
406 |
|
((chinese-cns11643-2 . #x6C52) . (#xF664 . #xF976)) |
407 |
|
((chinese-cns11643-2 . #x7167) . (#xF977 . #xF9C3)) |
408 |
|
(?$(Hqf(B . #xF9C4) |
409 |
|
(?$(Hr4(B . #xF9C5) |
410 |
|
(?$(Hr@(B . #xF9C6) |
411 |
|
((chinese-cns11643-2 . #x7235) . (#xF9C7 . #xF9D1)) |
412 |
|
((chinese-cns11643-2 . #x7241) . (#xF9D2 . #xF9D5)) |
413 |
|
|
414 |
|
;; Additional Ideographs |
415 |
|
(?$(IC7(B . #xF9D6) |
416 |
|
(?$(IOP(B . #xF9D7) |
417 |
|
(?$(IDN(B . #xF9D8) |
418 |
|
(?$(IPJ(B . #xF9D9) |
419 |
|
(?$(I,](B . #xF9DA) |
420 |
|
(?$(I=~(B . #xF9DB) |
421 |
|
(?$(IK\(B . #xF9DC) |
422 |
|
) |
423 |
|
) |
424 |
|
) |
425 |
|
|
426 |
;; |
;; |
427 |
(provide 'china-util) |
(provide 'china-util) |
428 |
|
|