?  search:
summary | log | graphiclog1 | graphiclog2 | commit | commitdiff | tree | refs | edit | fork
blame | history | raw | HEAD
; Minor copyedits in manuals.
[emacs.git] / lisp / international / characters.el
blobe48fc83c3dff2e85de31560f870f65d6a90ef33f
1 ;;; characters.el --- set syntax and category for multibyte characters
2
3 ;; Copyright (C) 1997, 2000-2017 Free Software Foundation, Inc.
4 ;; Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
5 ;; 2005, 2006, 2007, 2008, 2009, 2010, 2011
6 ;; National Institute of Advanced Industrial Science and Technology (AIST)
7 ;; Registration Number H14PRO021
8 ;; Copyright (C) 2003
9 ;; National Institute of Advanced Industrial Science and Technology (AIST)
10 ;; Registration Number H13PRO009
11
12 ;; Keywords: multibyte character, character set, syntax, category
13
14 ;; This file is part of GNU Emacs.
15
16 ;; GNU Emacs is free software: you can redistribute it and/or modify
17 ;; it under the terms of the GNU General Public License as published by
18 ;; the Free Software Foundation, either version 3 of the License, or
19 ;; (at your option) any later version.
20
21 ;; GNU Emacs is distributed in the hope that it will be useful,
22 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
23 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
24 ;; GNU General Public License for more details.
25
26 ;; You should have received a copy of the GNU General Public License
27 ;; along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>.
28
29 ;;; Commentary:
30
31 ;;; Code:
32
33 ;;; Predefined categories.
34
35 ;; For each character set.
36
37 (define-category ?a "ASCII
38 ASCII graphic characters 32-126 (ISO646 IRV:1983[4/0])")
39 (define-category ?l "Latin")
40 (define-category ?t "Thai")
41 (define-category ?g "Greek")
42 (define-category ?b "Arabic")
43 (define-category ?w "Hebrew")
44 (define-category ?y "Cyrillic")
45 (define-category ?k "Katakana
46 Japanese katakana")
47 (define-category ?r "Roman
48 Japanese roman")
49 (define-category ?c "Chinese")
50 (define-category ?j "Japanese")
51 (define-category ?h "Korean")
52 (define-category ?e "Ethiopic
53 Ethiopic (Ge'ez)")
54 (define-category ?v "Viet
55 Vietnamese")
56 (define-category ?i "Indian")
57 (define-category ?o "Lao")
58 (define-category ?q "Tibetan")
59
60 ;; For each group (row) of 2-byte character sets.
61
62 (define-category ?A "2-byte alnum
63 Alpha-numeric characters of 2-byte character sets")
64 (define-category ?C "2-byte han
65 Chinese (Han) characters of 2-byte character sets")
66 (define-category ?G "2-byte Greek
67 Greek characters of 2-byte character sets")
68 (define-category ?H "2-byte Hiragana
69 Japanese Hiragana characters of 2-byte character sets")
70 (define-category ?K "2-byte Katakana
71 Japanese Katakana characters of 2-byte character sets")
72 (define-category ?N "2-byte Korean
73 Korean Hangul characters of 2-byte character sets")
74 (define-category ?Y "2-byte Cyrillic
75 Cyrillic characters of 2-byte character sets")
76 (define-category ?I "Indian Glyphs")
77
78 ;; For phonetic classifications.
79
80 (define-category ?0 "consonant")
81 (define-category ?1 "base vowel
82 Base (independent) vowel")
83 (define-category ?2 "upper diacritic
84 Upper diacritical mark (including upper vowel)")
85 (define-category ?3 "lower diacritic
86 Lower diacritical mark (including lower vowel)")
87 (define-category ?4 "combining tone
88 Combining tone mark")
89 (define-category ?5 "symbol")
90 (define-category ?6 "digit")
91 (define-category ?7 "vowel diacritic
92 Vowel-modifying diacritical mark")
93 (define-category ?8 "vowel-signs")
94 (define-category ?9 "semivowel lower")
95
96 ;; For filling.
97 (define-category ?| "line breakable
98 While filling, we can break a line at this character.")
99
100 ;; For indentation calculation.
101 (define-category ?\s
102 "space for indent
103 This character counts as a space for indentation purposes.")
104
105 ;; Keep the following for `kinsoku' processing. See comments in
106 ;; kinsoku.el.
107 (define-category ?> "Not at bol
108 A character which can't be placed at beginning of line.")
109 (define-category ?< "Not at eol
110 A character which can't be placed at end of line.")
111
112 ;; Base and Combining
113 (define-category ?. "Base
114 Base characters (Unicode General Category L,N,P,S,Zs)")
115 (define-category ?^ "Combining
116 Combining diacritic or mark (Unicode General Category M)")
117
118 ;; bidi types
119 (define-category ?R "Right-to-left (strong)
120 Characters with \"strong\" right-to-left directionality, i.e.
121 with R, AL, RLE, or RLO Unicode bidi character type.")
122
123 (define-category ?L "Left-to-right (strong)
124 Characters with \"strong\" left-to-right directionality, i.e.
125 with L, LRE, or LRO Unicode bidi character type.")
126
127 \f
128 ;;; Setting syntax and category.
129
130 ;; ASCII
131
132 ;; All ASCII characters have the category `a' (ASCII) and `l' (Latin).
133 (modify-category-entry '(32 . 127) ?a)
134 (modify-category-entry '(32 . 127) ?l)
135
136 ;; Deal with the CJK charsets first. Since the syntax of blocks is
137 ;; defined per charset, and the charsets may contain e.g. Latin
138 ;; characters, we end up with the wrong syntax definitions if we're
139 ;; not careful.
140
141 ;; Chinese characters (Unicode)
142 (modify-category-entry '(#x2E80 . #x312F) ?|)
143 (modify-category-entry '(#x3190 . #x33FF) ?|)
144 (modify-category-entry '(#x3400 . #x4DB5) ?C)
145 (modify-category-entry '(#x4E00 . #x9FD5) ?C)
146 (modify-category-entry '(#x3400 . #x9FD5) ?c)
147 (modify-category-entry '(#x3400 . #x9FD5) ?|)
148 (modify-category-entry '(#xF900 . #xFAFF) ?C)
149 (modify-category-entry '(#xF900 . #xFAFF) ?c)
150 (modify-category-entry '(#xF900 . #xFAFF) ?|)
151 (modify-category-entry '(#x1B170 . #x1B2FF) ?c)
152 (modify-category-entry '(#x20000 . #x2FFFF) ?|)
153 (modify-category-entry '(#x20000 . #x2FFFF) ?C)
154 (modify-category-entry '(#x20000 . #x2FFFF) ?c)
155
156
157 ;; Chinese character set (GB2312)
158
159 (map-charset-chars #'modify-syntax-entry 'chinese-gb2312 "_" #x2121 #x217E)
160 (map-charset-chars #'modify-syntax-entry 'chinese-gb2312 "_" #x2221 #x227E)
161 (map-charset-chars #'modify-syntax-entry 'chinese-gb2312 "_" #x2921 #x297E)
162
163 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?c)
164 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?A #x2330 #x2339)
165 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?A #x2341 #x235A)
166 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?A #x2361 #x237A)
167 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?H #x2421 #x247E)
168 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?K #x2521 #x257E)
169 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?G #x2621 #x267E)
170 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?Y #x2721 #x277E)
171 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?C #x3021 #x7E7E)
172
173 ;; Chinese character set (BIG5)
174
175 (map-charset-chars #'modify-category-entry 'big5 ?c)
176 (map-charset-chars #'modify-category-entry 'big5 ?C #xA259 #xA261)
177 (map-charset-chars #'modify-category-entry 'big5 ?C #xA440 #xC67E)
178 (map-charset-chars #'modify-category-entry 'big5 ?C #xC940 #xF9DC)
179
180 ;; Chinese character set (CNS11643)
181
182 (dolist (c '(chinese-cns11643-1 chinese-cns11643-2 chinese-cns11643-3
183 chinese-cns11643-4 chinese-cns11643-5 chinese-cns11643-6
184 chinese-cns11643-7))
185 (map-charset-chars #'modify-category-entry c ?c)
186 (if (eq c 'chinese-cns11643-1)
187 (map-charset-chars #'modify-category-entry c ?C #x4421 #x7E7E)
188 (map-charset-chars #'modify-category-entry c ?C)))
189
190 ;; Japanese character set (JISX0201, JISX0208, JISX0212, JISX0213)
191
192 (map-charset-chars #'modify-category-entry 'katakana-jisx0201 ?k)
193
194 (map-charset-chars #'modify-category-entry 'latin-jisx0201 ?r)
195
196 (dolist (l '(katakana-jisx0201 japanese-jisx0208 japanese-jisx0212
197 japanese-jisx0213-1 japanese-jisx0213-2
198 japanese-jisx0213.2004-1
199 cp932-2-byte))
200 (map-charset-chars #'modify-category-entry l ?j))
201
202 ;; Fullwidth characters
203 (modify-category-entry '(#xff01 . #xff60) ?\|)
204
205 ;; Unicode equivalents of JISX0201-kana
206 (let ((range '(#xff61 . #xff9f)))
207 (modify-category-entry range ?k)
208 (modify-category-entry range ?j)
209 (modify-category-entry range ?\|))
210
211 ;; Katakana block
212 (modify-category-entry '(#x3099 . #x309C) ?K)
213 (modify-category-entry '(#x30A0 . #x30FF) ?K)
214 (modify-category-entry '(#x31F0 . #x31FF) ?K)
215 (modify-category-entry '(#x30A0 . #x30FA) ?\|)
216 (modify-category-entry #x30FF ?\|)
217
218 ;; Hiragana block
219 (modify-category-entry '(#x3040 . #x309F) ?H)
220 (modify-category-entry '(#x3040 . #x3096) ?\|)
221 (modify-category-entry #x309F ?\|)
222 (modify-category-entry #x30A0 ?H)
223 (modify-category-entry #x30FC ?H)
224
225 (modify-category-entry '(#x1B000 . #x1B1FF) ?j)
226
227
228 ;; JISX0208
229 (map-charset-chars #'modify-syntax-entry 'japanese-jisx0208 "_" #x2121 #x227E)
230 (map-charset-chars #'modify-syntax-entry 'japanese-jisx0208 "_" #x2821 #x287E)
231 (let ((chars '(?ー ?゛ ?゜ ?ヽ ?ヾ ?ゝ ?ゞ ?〃 ?仝 ?々 ?〆 ?〇)))
232 (dolist (elt chars)
233 (modify-syntax-entry elt "w")))
234
235 (map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?A #x2321 #x237E)
236 (map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?H #x2421 #x247E)
237 (map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?K #x2521 #x257E)
238 (map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?G #x2621 #x267E)
239 (map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?Y #x2721 #x277E)
240 (map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?C #x3021 #x7E7E)
241 (let ((chars '(?仝 ?々 ?〆 ?〇)))
242 (while chars
243 (modify-category-entry (car chars) ?C)
244 (setq chars (cdr chars))))
245
246 ;; JISX0212
247
248 (map-charset-chars #'modify-syntax-entry 'japanese-jisx0212 "_" #x2121 #x237E)
249
250 ;; JISX0201-Kana
251
252 (let ((chars '(?｡ ?､ ?･)))
253 (while chars
254 (modify-syntax-entry (car chars) ".")
255 (setq chars (cdr chars))))
256
257 (modify-syntax-entry ?\｢ "(｣")
258 (modify-syntax-entry ?\｣ "(｢")
259
260 ;; Korean character set (KSC5601)
261
262 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?h)
263
264 (map-charset-chars #'modify-syntax-entry 'korean-ksc5601 "_" #x2121 #x227E)
265 (map-charset-chars #'modify-syntax-entry 'korean-ksc5601 "_" #x2621 #x277E)
266 (map-charset-chars #'modify-syntax-entry 'korean-ksc5601 "_" #x2830 #x287E)
267 (map-charset-chars #'modify-syntax-entry 'korean-ksc5601 "_" #x2930 #x297E)
268 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?A #x2330 #x2339)
269 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?A #x2341 #x235A)
270 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?A #x2361 #x237A)
271 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?G #x2521 #x257E)
272 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?H #x2A21 #x2A7E)
273 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?K #x2B21 #x2B7E)
274 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?Y #x2C21 #x2C7E)
275
276 ;; These are in more than one charset.
277 (let ((parens (concat "〈〉《》「」『』【】〔〕〖〗〘〙〚〛"
278 "︵︶︷︸︹︺︻︼︽︾︿﹀﹁﹂﹃﹄"
279 "（）［］｛｝"))
280 open close)
281 (dotimes (i (/ (length parens) 2))
282 (setq open (aref parens (* i 2))
283 close (aref parens (1+ (* i 2))))
284 (modify-syntax-entry open (format "(%c" close))
285 (modify-syntax-entry close (format ")%c" open))))
286
287 ;; Arabic character set
288
289 (let ((charsets '(arabic-iso8859-6
290 arabic-digit
291 arabic-1-column
292 arabic-2-column)))
293 (while charsets
294 (map-charset-chars #'modify-category-entry (car charsets) ?b)
295 (setq charsets (cdr charsets))))
296 (modify-category-entry '(#x600 . #x6ff) ?b)
297 (modify-category-entry '(#x8a0 . #x8ff) ?b)
298 (modify-category-entry '(#xfb50 . #xfdff) ?b)
299 (modify-category-entry '(#xfe70 . #xfefe) ?b)
300
301 ;; Cyrillic character set (ISO-8859-5)
302
303 (modify-syntax-entry ?№ ".")
304
305 ;; Ethiopic character set
306
307 (modify-category-entry '(#x1200 . #x1399) ?e)
308 (modify-category-entry '(#x2d80 . #x2dde) ?e)
309 (let ((chars '(?፡ ?። ?፣ ?፤ ?፥ ?፦ ?፧ ?፨)))
310 (while chars
311 (modify-syntax-entry (car chars) ".")
312 (setq chars (cdr chars))))
313 (map-charset-chars #'modify-category-entry 'ethiopic ?e)
314
315 ;; Hebrew character set (ISO-8859-8)
316
317 (modify-syntax-entry #x5be ".") ; MAQAF
318 (modify-syntax-entry #x5c0 ".") ; PASEQ
319 (modify-syntax-entry #x5c3 ".") ; SOF PASUQ
320 (modify-syntax-entry #x5f3 ".") ; GERESH
321 (modify-syntax-entry #x5f4 ".") ; GERSHAYIM
322
323 ;; Indian character set (IS 13194 and other Emacs original Indian charsets)
324
325 (modify-category-entry '(#x901 . #x970) ?i)
326 (map-charset-chars #'modify-category-entry 'indian-is13194 ?i)
327 (map-charset-chars #'modify-category-entry 'indian-2-column ?i)
328
329 ;; Lao character set
330
331 (modify-category-entry '(#xe80 . #xeff) ?o)
332 (map-charset-chars #'modify-category-entry 'lao ?o)
333
334 (let ((deflist '(("ກ-ຮ" "w" ?0) ; consonant
335 ("ະາຳຽເ-ໄ" "w" ?1) ; vowel base
336 ("ັິ-ືົໍ" "w" ?2) ; vowel upper
337 ("ຸູ" "w" ?3) ; vowel lower
338 ("່-໋" "w" ?4) ; tone mark
339 ("ຼຽ" "w" ?9) ; semivowel lower
340 ("໐-໙" "w" ?6) ; digit
341 ("ຯໆ" "_" ?5) ; symbol
342 ))
343 elm chars len syntax category to ch i)
344 (while deflist
345 (setq elm (car deflist))
346 (setq chars (car elm)
347 len (length chars)
348 syntax (nth 1 elm)
349 category (nth 2 elm)
350 i 0)
351 (while (< i len)
352 (if (= (aref chars i) ?-)
353 (setq i (1+ i)
354 to (aref chars i))
355 (setq ch (aref chars i)
356 to ch))
357 (while (<= ch to)
358 (unless (string-equal syntax "w")
359 (modify-syntax-entry ch syntax))
360 (modify-category-entry ch category)
361 (setq ch (1+ ch)))
362 (setq i (1+ i)))
363 (setq deflist (cdr deflist))))
364
365 ;; Thai character set (TIS620)
366
367 (modify-category-entry '(#xe00 . #xe7f) ?t)
368 (map-charset-chars #'modify-category-entry 'thai-tis620 ?t)
369
370 (let ((deflist '(;; chars syntax category
371 ("ก-รลว-ฮ" "w" ?0) ; consonant
372 ("ฤฦะาำเ-ๅ" "w" ?1) ; vowel base
373 ("ัิ-ื็๎" "w" ?2) ; vowel upper
374 ("ุ-ฺ" "w" ?3) ; vowel lower
375 ("่-ํ" "w" ?4) ; tone mark
376 ("๐-๙" "w" ?6) ; digit
377 ("ฯๆ฿๏๚๛" "_" ?5) ; symbol
378 ))
379 elm chars len syntax category to ch i)
380 (while deflist
381 (setq elm (car deflist))
382 (setq chars (car elm)
383 len (length chars)
384 syntax (nth 1 elm)
385 category (nth 2 elm)
386 i 0)
387 (while (< i len)
388 (if (= (aref chars i) ?-)
389 (setq i (1+ i)
390 to (aref chars i))
391 (setq ch (aref chars i)
392 to ch))
393 (while (<= ch to)
394 (unless (string-equal syntax "w")
395 (modify-syntax-entry ch syntax))
396 (modify-category-entry ch category)
397 (setq ch (1+ ch)))
398 (setq i (1+ i)))
399 (setq deflist (cdr deflist))))
400
401 ;; Tibetan character set
402
403 (modify-category-entry '(#xf00 . #xfff) ?q)
404 (map-charset-chars #'modify-category-entry 'tibetan ?q)
405 (map-charset-chars #'modify-category-entry 'tibetan-1-column ?q)
406
407 (let ((deflist '(;; chars syntax category
408 ("ཀ-ཀྵཪ" "w" ?0) ; consonant
409 ("ྐ-ྐྵྺྻྼ" "w" ?0) ;
410 ("ིེཻོཽྀ" "w" ?2) ; upper vowel
411 ("ཾྂྃ྆྇ྈྉྊྋ" "w" ?2) ; upper modifier
412 ("྄ཱུ༙༵༷" "w" ?3) ; lower vowel/modifier
413 ("཰" "w" ?3) ; invisible vowel a
414 ("༠-༩༪-༳" "w" ?6) ; digit
415 ("་།-༒༔ཿ" "." ?|) ; line-break char
416 ("་།༏༐༑༔ཿ" "." ?|) ;
417 ("༈་།-༒༔ཿ༽༴" "." ?>) ; prohibition
418 ("་།༏༐༑༔ཿ" "." ?>) ;
419 ("ༀ-༊༼࿁࿂྅" "." ?<) ; prohibition
420 ("༓༕-༘༚-༟༶༸-༻༾༿྾྿-࿏" "." ?q) ; others
421 ))
422 elm chars len syntax category to ch i)
423 (while deflist
424 (setq elm (car deflist))
425 (setq chars (car elm)
426 len (length chars)
427 syntax (nth 1 elm)
428 category (nth 2 elm)
429 i 0)
430 (while (< i len)
431 (if (= (aref chars i) ?-)
432 (setq i (1+ i)
433 to (aref chars i))
434 (setq ch (aref chars i)
435 to ch))
436 (while (<= ch to)
437 (unless (string-equal syntax "w")
438 (modify-syntax-entry ch syntax))
439 (modify-category-entry ch category)
440 (setq ch (1+ ch)))
441 (setq i (1+ i)))
442 (setq deflist (cdr deflist))))
443
444 ;; Vietnamese character set
445
446 ;; To make a word with Latin characters
447 (map-charset-chars #'modify-category-entry 'vietnamese-viscii-lower ?l)
448 (map-charset-chars #'modify-category-entry 'vietnamese-viscii-lower ?v)
449
450 (map-charset-chars #'modify-category-entry 'vietnamese-viscii-upper ?l)
451 (map-charset-chars #'modify-category-entry 'vietnamese-viscii-upper ?v)
452
453 (let ((tbl (standard-case-table))
454 (i 32))
455 (while (< i 128)
456 (let* ((char (decode-char 'vietnamese-viscii-upper i))
457 (charl (decode-char 'vietnamese-viscii-lower i))
458 (uc (encode-char char 'ucs))
459 (lc (encode-char charl 'ucs)))
460 (set-case-syntax-pair char (decode-char 'vietnamese-viscii-lower i)
461 tbl)
462 (if uc (modify-category-entry uc ?v))
463 (if lc (modify-category-entry lc ?v)))
464 (setq i (1+ i))))
465
466 ;; Tai Viet
467 (let ((deflist '(;; chars syntax category
468 ((?ꪀ. ?ꪯ) "w" ?0) ; consonant
469 ("ꪱꪵꪶ" "w" ?1) ; vowel base
470 ((?ꪹ . ?ꪽ) "w" ?1) ; vowel base
471 ("ꪰꪲꪳꪷꪸꪾ" "w" ?2) ; vowel upper
472 ("ꪴ" "w" ?3) ; vowel lower
473 ("ꫀꫂ" "w" ?1) ; non-combining tone-mark
474 ("꪿꫁" "w" ?4) ; combining tone-mark
475 ((?ꫛ . ?꫟) "_" ?5) ; symbol
476 )))
477 (dolist (elm deflist)
478 (let ((chars (car elm))
479 (syntax (nth 1 elm))
480 (category (nth 2 elm)))
481 (if (consp chars)
482 (progn
483 (modify-syntax-entry chars syntax)
484 (modify-category-entry chars category))
485 (mapc #'(lambda (x)
486 (modify-syntax-entry x syntax)
487 (modify-category-entry x category))
488 chars)))))
489
490 ;; Bidi categories
491
492 ;; If bootstrapping without generated uni-*.el files, table not defined.
493 (let ((table (unicode-property-table-internal 'bidi-class)))
494 (when table
495 (map-char-table (lambda (key val)
496 (cond
497 ((memq val '(R AL RLO RLE))
498 (modify-category-entry key ?R))
499 ((memq val '(L LRE LRO))
500 (modify-category-entry key ?L))))
501 table)))
502
503 ;; Load uni-mirrored.el and uni-brackets.el if available, so that they
504 ;; get dumped into Emacs. This allows starting Emacs with
505 ;; force-load-messages in ~/.emacs, and avoid infinite recursion in
506 ;; bidi_initialize, which needs to load uni-mirrored.el and
507 ;; uni-brackets.el in order to display the "Loading" messages.
508 (unicode-property-table-internal 'mirroring)
509 (unicode-property-table-internal 'bracket-type)
510
511 ;; Latin
512
513 (modify-category-entry '(#x80 . #x024F) ?l)
514
515 (let ((tbl (standard-case-table)) c)
516
517 ;; Latin-1
518
519 ;; Fixme: Some of the non-word syntaxes here perhaps should be
520 ;; reviewed. (Note that the following all implicitly have word
521 ;; syntax: ¢£¤¥¨ª¯²³´¶¸¹º.) There should be a well-defined way of
522 ;; relating Unicode categories to Emacs syntax codes.
523
524 ;; NBSP isn't semantically interchangeable with other whitespace chars,
525 ;; so it's more like punctuation.
526 (set-case-syntax ?  "." tbl)
527 (set-case-syntax ?¡ "." tbl)
528 (set-case-syntax ?¦ "_" tbl)
529 (set-case-syntax ?§ "." tbl)
530 (set-case-syntax ?© "_" tbl)
531 ;; French wants
532 ;; (set-case-syntax-delims ?« ?» tbl)
533 ;; And German wants
534 ;; (set-case-syntax-delims ?» ?« tbl)
535 ;; So let's stay neutral and let users set these up if/when they want to.
536 (set-case-syntax ?« "." tbl)
537 (set-case-syntax ?» "." tbl)
538 (set-case-syntax ?¬ "_" tbl)
539 (set-case-syntax ?­ "_" tbl)
540 (set-case-syntax ?® "_" tbl)
541 (set-case-syntax ?° "_" tbl)
542 (set-case-syntax ?± "_" tbl)
543 (set-case-syntax ?µ "_" tbl)
544 (set-case-syntax ?· "_" tbl)
545 (set-case-syntax ?¼ "_" tbl)
546 (set-case-syntax ?½ "_" tbl)
547 (set-case-syntax ?¾ "_" tbl)
548 (set-case-syntax ?¿ "." tbl)
549 (set-case-syntax ?× "_" tbl)
550 (set-case-syntax ?ß "w" tbl)
551 (set-case-syntax ?÷ "_" tbl)
552 ;; See below for ÿ.
553
554 ;; Latin Extended-A, Latin Extended-B
555 (setq c #x0100)
556 (while (<= c #x02B8)
557 (modify-category-entry c ?l)
558 (setq c (1+ c)))
559
560 ;; Latin Extended Additional
561 (modify-category-entry '(#x1e00 . #x1ef9) ?l)
562
563 ;; Latin Extended-C
564 (setq c #x2C60)
565 (while (<= c #x2C7F)
566 (modify-category-entry c ?l)
567 (setq c (1+ c)))
568
569 ;; Latin Extended-D
570 (setq c #xA720)
571 (while (<= c #xA7FF)
572 (modify-category-entry c ?l)
573 (setq c (1+ c)))
574
575 ;; Latin Extended-E
576 (setq c #xAB30)
577 (while (<= c #xAB64)
578 (modify-category-entry c ?l)
579 (setq c (1+ c)))
580
581 ;; Greek
582 (modify-category-entry '(#x0370 . #x03ff) ?g)
583
584 ;; Armenian
585 (setq c #x531)
586
587 ;; Greek Extended
588 (modify-category-entry '(#x1f00 . #x1fff) ?g)
589
590 ;; cyrillic
591 (modify-category-entry '(#x0400 . #x04FF) ?y)
592 (modify-category-entry '(#xA640 . #xA69F) ?y)
593
594 ;; Georgian
595 (setq c #x10A0)
596
597 ;; Cyrillic Extended-C
598 (modify-category-entry '(#x1C80 . #x1C8F) ?y)
599
600 ;; general punctuation
601 (setq c #x2000)
602 (while (<= c #x200b)
603 (set-case-syntax c " " tbl)
604 (setq c (1+ c)))
605 (while (<= c #x200F)
606 (set-case-syntax c "." tbl)
607 (setq c (1+ c)))
608 ;; Fixme: These aren't all right:
609 (setq c #x2010)
610 (while (<= c #x2016)
611 (set-case-syntax c "_" tbl)
612 (setq c (1+ c)))
613 ;; Punctuation syntax for quotation marks (like `)
614 (while (<= c #x201f)
615 (set-case-syntax c "." tbl)
616 (setq c (1+ c)))
617 ;; Fixme: These aren't all right:
618 (while (<= c #x2027)
619 (set-case-syntax c "_" tbl)
620 (setq c (1+ c)))
621 (while (<= c #x206F)
622 (set-case-syntax c "." tbl)
623 (setq c (1+ c)))
624
625 ;; Fixme: The following blocks might be better as symbol rather than
626 ;; punctuation.
627 ;; Arrows
628 (setq c #x2190)
629 (while (<= c #x21FF)
630 (set-case-syntax c "." tbl)
631 (setq c (1+ c)))
632 ;; Mathematical Operators
633 (while (<= c #x22FF)
634 (set-case-syntax c "." tbl)
635 (setq c (1+ c)))
636 ;; Miscellaneous Technical
637 (while (<= c #x23FF)
638 (set-case-syntax c "." tbl)
639 (setq c (1+ c)))
640 ;; Control Pictures
641 (while (<= c #x243F)
642 (set-case-syntax c "_" tbl)
643 (setq c (1+ c)))
644
645 ;; Circled Latin
646 (setq c #x24b6)
647 (while (<= c #x24cf)
648 (modify-category-entry c ?l)
649 (modify-category-entry (+ c 26) ?l)
650 (setq c (1+ c)))
651
652 ;; Coptic
653 ;; There's no Coptic category. However, Coptic letters that are
654 ;; part of the Greek block above get the Greek category, and those
655 ;; in this block are derived from Greek letters, so let's be
656 ;; consistent about their category.
657 (modify-category-entry '(#x2C80 . #x2CFF) ?g)
658
659 ;; Fullwidth Latin
660 (setq c #xff21)
661 (while (<= c #xff3a)
662 (modify-category-entry c ?l)
663 (modify-category-entry (+ c #x20) ?l)
664 (setq c (1+ c)))
665
666 ;; Combining diacritics
667 (modify-category-entry '(#x300 . #x362) ?^)
668 ;; Combining marks
669 (modify-category-entry '(#x20d0 . #x20ff) ?^)
670
671 (let ((gc (unicode-property-table-internal 'general-category))
672 (syn-table (standard-syntax-table)))
673 ;; In early bootstrapping Unicode tables are not available so we need to
674 ;; skip this step in those cases.
675 (when gc
676 ;; Set all Letter, uppercase; Letter, lowercase and Letter,
677 ;; titlecase syntax to word.
678 (map-char-table
679 (lambda (ch cat)
680 (when (memq cat '(Lu Ll Lt))
681 (modify-syntax-entry ch "w " syn-table)))
682 gc)
683 ;; Ⅰ through Ⅻ had word syntax in the past so set it here as well.
684 ;; The general category of those characters is Number, Letter.
685 (modify-syntax-entry '(#x2160 . #x216b) "w " syn-table)
686
687 ;; ⓐ through ⓩ are symbols, other according to Unicode but Emacs set
688 ;; their syntax to word in the past so keep backwards compatibility.
689 (modify-syntax-entry '(#x24D0 . #x24E9) "w " syn-table)
690
691 ;; Set downcase and upcase from Unicode properties
692
693 ;; In some languages, such as Turkish, U+0049 LATIN CAPITAL LETTER I and
694 ;; U+0131 LATIN SMALL LETTER DOTLESS I make a case pair, and so do U+0130
695 ;; LATIN CAPITAL LETTER I WITH DOT ABOVE and U+0069 LATIN SMALL LETTER I.
696
697 ;; We used to set up half of those correspondence unconditionally, but
698 ;; that makes searches slow. So now we don't set up either half of these
699 ;; correspondences by default.
700
701 ;; (set-downcase-syntax ?İ ?i tbl)
702 ;; (set-upcase-syntax ?I ?ı tbl)
703
704 (let ((map-unicode-property
705 (lambda (property func)
706 (map-char-table
707 (lambda (ch cased)
708 ;; ASCII characters skipped due to reasons outlined above. As
709 ;; of Unicode 9.0, this exception affects the following:
710 ;; lc(U+0130 İ) = i
711 ;; uc(U+0131 ı) = I
712 ;; uc(U+017F ſ) = S
713 ;; uc(U+212A K) = k
714 (when (> cased 127)
715 (let ((end (if (consp ch) (cdr ch) ch)))
716 (setq ch (max 128 (if (consp ch) (car ch) ch)))
717 (while (<= ch end)
718 (funcall func ch cased)
719 (setq ch (1+ ch))))))
720 (unicode-property-table-internal property))))
721 (down tbl)
722 (up (case-table-get-table tbl 'up)))
723
724 ;; This works on an assumption that if toUpper(x) != x then toLower(x)
725 ;; == x (and the opposite for toLower/toUpper). This doesn’t hold for
726 ;; title case characters but those incorrect mappings will be
727 ;; overwritten later.
728 (funcall map-unicode-property 'uppercase
729 (lambda (lc uc) (aset down lc lc) (aset up uc uc)))
730 (funcall map-unicode-property 'lowercase
731 (lambda (uc lc) (aset down lc lc) (aset up uc uc)))
732
733 ;; Now deal with the actual mapping. This will correctly assign casing
734 ;; for title-case characters.
735 (funcall map-unicode-property 'uppercase
736 (lambda (lc uc) (aset up lc uc) (aset up uc uc)))
737 (funcall map-unicode-property 'lowercase
738 (lambda (uc lc) (aset down uc lc) (aset down lc lc))))))
739
740 ;; Clear out the extra slots so that they will be recomputed from the main
741 ;; (downcase) table and upcase table. Since we’re side-stepping the usual
742 ;; set-case-syntax-* functions, we need to do it explicitly.
743 (set-char-table-extra-slot tbl 1 nil)
744 (set-char-table-extra-slot tbl 2 nil)
745
746 ;; Fixme: syntax for symbols &c
747 )
748
749 (let ((pairs
750 '("⁅⁆" ; U+2045 U+2046
751 "⁽⁾" ; U+207D U+207E
752 "₍₎" ; U+208D U+208E
753 "〈〉" ; U+2329 U+232A
754 "⎴⎵" ; U+23B4 U+23B5
755 "❨❩" ; U+2768 U+2769
756 "❪❫" ; U+276A U+276B
757 "❬❭" ; U+276C U+276D
758 "❰❱" ; U+2770 U+2771
759 "❲❳" ; U+2772 U+2773
760 "❴❵" ; U+2774 U+2775
761 "⟦⟧" ; U+27E6 U+27E7
762 "⟨⟩" ; U+27E8 U+27E9
763 "⟪⟫" ; U+27EA U+27EB
764 "⦃⦄" ; U+2983 U+2984
765 "⦅⦆" ; U+2985 U+2986
766 "⦇⦈" ; U+2987 U+2988
767 "⦉⦊" ; U+2989 U+298A
768 "⦋⦌" ; U+298B U+298C
769 "⦍⦎" ; U+298D U+298E
770 "⦏⦐" ; U+298F U+2990
771 "⦑⦒" ; U+2991 U+2992
772 "⦓⦔" ; U+2993 U+2994
773 "⦕⦖" ; U+2995 U+2996
774 "⦗⦘" ; U+2997 U+2998
775 "⧼⧽" ; U+29FC U+29FD
776 "〈〉" ; U+3008 U+3009
777 "《》" ; U+300A U+300B
778 "「」" ; U+300C U+300D
779 "『』" ; U+300E U+300F
780 "【】" ; U+3010 U+3011
781 "〔〕" ; U+3014 U+3015
782 "〖〗" ; U+3016 U+3017
783 "〘〙" ; U+3018 U+3019
784 "〚〛" ; U+301A U+301B
785 "﴾﴿" ; U+FD3E U+FD3F
786 "︵︶" ; U+FE35 U+FE36
787 "︷︸" ; U+FE37 U+FE38
788 "︹︺" ; U+FE39 U+FE3A
789 "︻︼" ; U+FE3B U+FE3C
790 "︽︾" ; U+FE3D U+FE3E
791 "︿﹀" ; U+FE3F U+FE40
792 "﹁﹂" ; U+FE41 U+FE42
793 "﹃﹄" ; U+FE43 U+FE44
794 "﹙﹚" ; U+FE59 U+FE5A
795 "﹛﹜" ; U+FE5B U+FE5C
796 "﹝﹞" ; U+FE5D U+FE5E
797 "（）" ; U+FF08 U+FF09
798 "［］" ; U+FF3B U+FF3D
799 "｛｝" ; U+FF5B U+FF5D
800 "｟｠" ; U+FF5F U+FF60
801 "｢｣" ; U+FF62 U+FF63
802 )))
803 (dolist (elt pairs)
804 (modify-syntax-entry (aref elt 0) (string ?\( (aref elt 1)))
805 (modify-syntax-entry (aref elt 1) (string ?\) (aref elt 0)))))
806
807 \f
808 ;; For each character set, put the information of the most proper
809 ;; coding system to encode it by `preferred-coding-system' property.
810
811 ;; Fixme: should this be junked?
812 (let ((l '((latin-iso8859-1 . iso-latin-1)
813 (latin-iso8859-2 . iso-latin-2)
814 (latin-iso8859-3 . iso-latin-3)
815 (latin-iso8859-4 . iso-latin-4)
816 (thai-tis620 . thai-tis620)
817 (greek-iso8859-7 . greek-iso-8bit)
818 (arabic-iso8859-6 . iso-2022-7bit)
819 (hebrew-iso8859-8 . hebrew-iso-8bit)
820 (katakana-jisx0201 . japanese-shift-jis)
821 (latin-jisx0201 . japanese-shift-jis)
822 (cyrillic-iso8859-5 . cyrillic-iso-8bit)
823 (latin-iso8859-9 . iso-latin-5)
824 (japanese-jisx0208-1978 . iso-2022-jp)
825 (chinese-gb2312 . chinese-iso-8bit)
826 (chinese-gbk . chinese-gbk)
827 (gb18030-2-byte . chinese-gb18030)
828 (gb18030-4-byte-bmp . chinese-gb18030)
829 (gb18030-4-byte-smp . chinese-gb18030)
830 (gb18030-4-byte-ext-1 . chinese-gb18030)
831 (gb18030-4-byte-ext-2 . chinese-gb18030)
832 (japanese-jisx0208 . iso-2022-jp)
833 (korean-ksc5601 . iso-2022-kr)
834 (japanese-jisx0212 . iso-2022-jp)
835 (chinese-big5-1 . chinese-big5)
836 (chinese-big5-2 . chinese-big5)
837 (chinese-sisheng . iso-2022-7bit)
838 (ipa . iso-2022-7bit)
839 (vietnamese-viscii-lower . vietnamese-viscii)
840 (vietnamese-viscii-upper . vietnamese-viscii)
841 (arabic-digit . iso-2022-7bit)
842 (arabic-1-column . iso-2022-7bit)
843 (lao . lao)
844 (arabic-2-column . iso-2022-7bit)
845 (indian-is13194 . devanagari)
846 (indian-glyph . devanagari)
847 (tibetan-1-column . tibetan)
848 (ethiopic . iso-2022-7bit)
849 (chinese-cns11643-1 . iso-2022-cn)
850 (chinese-cns11643-2 . iso-2022-cn)
851 (chinese-cns11643-3 . iso-2022-cn)
852 (chinese-cns11643-4 . iso-2022-cn)
853 (chinese-cns11643-5 . iso-2022-cn)
854 (chinese-cns11643-6 . iso-2022-cn)
855 (chinese-cns11643-7 . iso-2022-cn)
856 (indian-2-column . devanagari)
857 (tibetan . tibetan)
858 (latin-iso8859-14 . iso-latin-8)
859 (latin-iso8859-15 . iso-latin-9))))
860 (while l
861 (put-charset-property (car (car l)) 'preferred-coding-system (cdr (car l)))
862 (setq l (cdr l))))
863
864 \f
865 ;; Setup auto-fill-chars for charsets that should invoke auto-filling.
866 ;; SPACE and NEWLINE are already set.
867
868 (set-char-table-range auto-fill-chars '(#x3041 . #x30FF) t)
869 (set-char-table-range auto-fill-chars '(#x3400 . #x4DB5) t)
870 (set-char-table-range auto-fill-chars '(#x4e00 . #x9fbb) t)
871 (set-char-table-range auto-fill-chars '(#xF900 . #xFAFF) t)
872 (set-char-table-range auto-fill-chars '(#xFF00 . #xFF9F) t)
873 (set-char-table-range auto-fill-chars '(#x20000 . #x2FFFF) t)
874
875 \f
876 ;;; Setting char-width-table. The default is 1.
877
878 ;; 0: non-spacing, enclosing combining, formatting, Hangul Jamo medial
879 ;; and final characters.
880 (let ((l '((#x0300 . #x036F)
881 (#x0483 . #x0489)
882 (#x0591 . #x05BD)
883 (#x05BF . #x05BF)
884 (#x05C1 . #x05C2)
885 (#x05C4 . #x05C5)
886 (#x05C7 . #x05C7)
887 (#x0600 . #x0605)
888 (#x0610 . #x061C)
889 (#x064B . #x065F)
890 (#x0670 . #x0670)
891 (#x06D6 . #x06E4)
892 (#x06E7 . #x06E8)
893 (#x06EA . #x06ED)
894 (#x070F . #x070F)
895 (#x0711 . #x0711)
896 (#x0730 . #x074A)
897 (#x07A6 . #x07B0)
898 (#x07EB . #x07F3)
899 (#x0816 . #x0823)
900 (#x0825 . #x082D)
901 (#x0859 . #x085B)
902 (#x08D4 . #x0902)
903 (#x093A . #x093A)
904 (#x093C . #x093C)
905 (#x0941 . #x0948)
906 (#x094D . #x094D)
907 (#x0951 . #x0957)
908 (#x0962 . #x0963)
909 (#x0981 . #x0981)
910 (#x09BC . #x09BC)
911 (#x09C1 . #x09C4)
912 (#x09CD . #x09CD)
913 (#x09E2 . #x09E3)
914 (#x0A01 . #x0A02)
915 (#x0A3C . #x0A3C)
916 (#x0A41 . #x0A4D)
917 (#x0A41 . #x0A42)
918 (#x0A47 . #x0A48)
919 (#x0A4B . #x0A4D)
920 (#x0A51 . #x0A51)
921 (#x0A70 . #x0A71)
922 (#x0A75 . #x0A75)
923 (#x0A81 . #x0A82)
924 (#x0ABC . #x0ABC)
925 (#x0AC1 . #x0AC8)
926 (#x0ACD . #x0ACD)
927 (#x0AE2 . #x0AE3)
928 (#x0B01 . #x0B01)
929 (#x0B3C . #x0B3C)
930 (#x0B3F . #x0B3F)
931 (#x0B41 . #x0B44)
932 (#x0B4D . #x0B56)
933 (#x0B62 . #x0B63)
934 (#x0B82 . #x0B82)
935 (#x0BC0 . #x0BC0)
936 (#x0BCD . #x0BCD)
937 (#x0C00 . #x0C00)
938 (#x0C3E . #x0C40)
939 (#x0C46 . #x0C56)
940 (#x0C62 . #x0C63)
941 (#x0C81 . #x0C81)
942 (#x0CBC . #x0CBC)
943 (#x0CCC . #x0CCD)
944 (#x0CE2 . #x0CE3)
945 (#x0D01 . #x0D01)
946 (#x0D41 . #x0D44)
947 (#x0D4D . #x0D4D)
948 (#x0D62 . #x0D63)
949 (#x0DCA . #x0DCA)
950 (#x0DD2 . #x0DD6)
951 (#x0E31 . #x0E31)
952 (#x0E34 . #x0E3A)
953 (#x0E47 . #x0E4E)
954 (#x0EB1 . #x0EB1)
955 (#x0EB4 . #x0EBC)
956 (#x0EC8 . #x0ECD)
957 (#x0F18 . #x0F19)
958 (#x0F35 . #x0F35)
959 (#x0F37 . #x0F37)
960 (#x0F39 . #x0F39)
961 (#x0F71 . #x0F7E)
962 (#x0F80 . #x0F84)
963 (#x0F86 . #x0F87)
964 (#x0F8D . #x0FBC)
965 (#x0FC6 . #x0FC6)
966 (#x102D . #x1030)
967 (#x1032 . #x1037)
968 (#x1039 . #x103A)
969 (#x103D . #x103E)
970 (#x1058 . #x1059)
971 (#x105E . #x1160)
972 (#x1171 . #x1074)
973 (#x1082 . #x1082)
974 (#x1085 . #x1086)
975 (#x108D . #x108D)
976 (#x109D . #x109D)
977 (#x135D . #x135F)
978 (#x1712 . #x1714)
979 (#x1732 . #x1734)
980 (#x1752 . #x1753)
981 (#x1772 . #x1773)
982 (#x17B4 . #x17B5)
983 (#x17B7 . #x17BD)
984 (#x17C6 . #x17C6)
985 (#x17C9 . #x17D3)
986 (#x17DD . #x17DD)
987 (#x180B . #x180E)
988 (#x18A9 . #x18A9)
989 (#x1885 . #x1886)
990 (#x18A9 . #x18A9)
991 (#x1920 . #x1922)
992 (#x1927 . #x1928)
993 (#x1932 . #x1932)
994 (#x1939 . #x193B)
995 (#x1A17 . #x1A18)
996 (#x1A1B . #x1A1B)
997 (#x1A56 . #x1A56)
998 (#x1A58 . #x1A5E)
999 (#x1A60 . #x1A60)
1000 (#x1A62 . #x1A62)
1001 (#x1A65 . #x1A6C)
1002 (#x1A73 . #x1A7C)
1003 (#x1A7F . #x1A7F)
1004 (#x1AB0 . #x1ABE)
1005 (#x1B00 . #x1B03)
1006 (#x1B34 . #x1B34)
1007 (#x1B36 . #x1B3A)
1008 (#x1B3C . #x1B3C)
1009 (#x1B42 . #x1B42)
1010 (#x1B6B . #x1B73)
1011 (#x1B80 . #x1B81)
1012 (#x1BA2 . #x1BA5)
1013 (#x1BA8 . #x1BA9)
1014 (#x1BAB . #x1BAD)
1015 (#x1BE6 . #x1BE6)
1016 (#x1BE8 . #x1BE9)
1017 (#x1BED . #x1BED)
1018 (#x1BEF . #x1BF1)
1019 (#x1C2C . #x1C33)
1020 (#x1C36 . #x1C37)
1021 (#x1CD0 . #x1CD2)
1022 (#x1CD4 . #x1CE0)
1023 (#x1CE2 . #x1CE8)
1024 (#x1CED . #x1CED)
1025 (#x1CF4 . #x1CF4)
1026 (#x1CF8 . #x1CF9)
1027 (#x1DC0 . #x1DFF)
1028 (#x200B . #x200F)
1029 (#x202A . #x202E)
1030 (#x2060 . #x206F)
1031 (#x20D0 . #x20F0)
1032 (#x2CEF . #x2CF1)
1033 (#x2D7F . #x2D7F)
1034 (#x2DE0 . #x2DFF)
1035 (#xA66F . #xA672)
1036 (#xA674 . #xA69F)
1037 (#xA6F0 . #xA6F1)
1038 (#xA802 . #xA802)
1039 (#xA806 . #xA806)
1040 (#xA80B . #xA80B)
1041 (#xA825 . #xA826)
1042 (#xA8C4 . #xA8C5)
1043 (#xA8E0 . #xA8F1)
1044 (#xA926 . #xA92D)
1045 (#xA947 . #xA951)
1046 (#xA980 . #xA9B3)
1047 (#xA9B6 . #xA9B9)
1048 (#xA9BC . #xA9BC)
1049 (#xA9E5 . #xA9E5)
1050 (#xAA29 . #xAA2E)
1051 (#xAA31 . #xAA32)
1052 (#xAA35 . #xAA36)
1053 (#xAA43 . #xAA43)
1054 (#xAA4C . #xAA4C)
1055 (#xAA7C . #xAA7C)
1056 (#xAAB0 . #xAAB0)
1057 (#xAAB2 . #xAAB4)
1058 (#xAAB7 . #xAAB8)
1059 (#xAABE . #xAABF)
1060 (#xAAC1 . #xAAC1)
1061 (#xAAEC . #xAAED)
1062 (#xAAF6 . #xAAF6)
1063 (#xABE5 . #xABE5)
1064 (#xABE8 . #xABE8)
1065 (#xABED . #xABED)
1066 (#xFB1E . #xFB1E)
1067 (#xFE00 . #xFE0F)
1068 (#xFE20 . #xFE2F)
1069 (#xFEFF . #xFEFF)
1070 (#xFFF9 . #xFFFB)
1071 (#x101FD . #x101FD)
1072 (#x102E0 . #x102E0)
1073 (#x10376 . #x1037A)
1074 (#x10A01 . #x10A0F)
1075 (#x10A38 . #x10A3F)
1076 (#x10AE5 . #x10AE6)
1077 (#x11001 . #x11001)
1078 (#x11038 . #x11046)
1079 (#x1107F . #x11081)
1080 (#x110B3 . #x110B6)
1081 (#x110B9 . #x110BA)
1082 (#x110BD . #x110BD)
1083 (#x11100 . #x11102)
1084 (#x11127 . #x1112B)
1085 (#x1112D . #x11134)
1086 (#x11173 . #x11173)
1087 (#x11180 . #x11181)
1088 (#x111B6 . #x111BE)
1089 (#x111CA . #x111CC)
1090 (#x1122F . #x11231)
1091 (#x11234 . #x11234)
1092 (#x11236 . #x11237)
1093 (#x1123E . #x1123E)
1094 (#x112DF . #x112DF)
1095 (#x112E3 . #x112EA)
1096 (#x11300 . #x11301)
1097 (#x1133C . #x1133C)
1098 (#x11340 . #x11340)
1099 (#x11366 . #x1136C)
1100 (#x11370 . #x11374)
1101 (#x11438 . #x1143F)
1102 (#x11442 . #x11444)
1103 (#x11446 . #x11446)
1104 (#x114B3 . #x114B8)
1105 (#x114BA . #x114C0)
1106 (#x114C2 . #x114C3)
1107 (#x115B2 . #x115B5)
1108 (#x115BC . #x115BD)
1109 (#x115BF . #x115C0)
1110 (#x115DC . #x115DD)
1111 (#x11633 . #x1163A)
1112 (#x1163D . #x1163D)
1113 (#x1163F . #x11640)
1114 (#x116AB . #x116AB)
1115 (#x116AD . #x116AD)
1116 (#x116B0 . #x116B5)
1117 (#x116B7 . #x116B7)
1118 (#x1171D . #x1171F)
1119 (#x11722 . #x11725)
1120 (#x11727 . #x1172B)
1121 (#x11C30 . #x11C36)
1122 (#x11C38 . #x11C3D)
1123 (#x11C92 . #x11CA7)
1124 (#x11CAA . #x11CB0)
1125 (#x11CB2 . #x11CB3)
1126 (#x11CB5 . #x11CB6)
1127 (#x16AF0 . #x16AF4)
1128 (#x16B30 . #x16B36)
1129 (#x16F8F . #x16F92)
1130 (#x1BC9D . #x1BC9E)
1131 (#x1BCA0 . #x1BCA3)
1132 (#x1D167 . #x1D169)
1133 (#x1D173 . #x1D182)
1134 (#x1D185 . #x1D18B)
1135 (#x1D1AA . #x1D1AD)
1136 (#x1D242 . #x1D244)
1137 (#x1DA00 . #x1DA36)
1138 (#x1DA3B . #x1DA6C)
1139 (#x1DA75 . #x1DA75)
1140 (#x1DA84 . #x1DA84)
1141 (#x1DA9B . #x1DA9F)
1142 (#x1DAA1 . #x1DAAF)
1143 (#x1E000 . #x1E006)
1144 (#x1E008 . #x1E018)
1145 (#x1E01B . #x1E021)
1146 (#x1E023 . #x1E024)
1147 (#x1E026 . #x1E02A)
1148 (#x1E8D0 . #x1E8D6)
1149 (#x1E944 . #x1E94A)
1150 (#xE0001 . #xE01EF))))
1151 (dolist (elt l)
1152 (set-char-table-range char-width-table elt 0)))
1153
1154 ;; 2: East Asian Wide and Full-width characters.
1155 (let ((l '((#x1100 . #x115F)
1156 (#x231A . #x231B)
1157 (#x2329 . #x232A)
1158 (#x23E9 . #x23EC)
1159 (#x23F0 . #x23F0)
1160 (#x23F3 . #x23F3)
1161 (#x25FD . #x25FE)
1162 (#x2614 . #x2615)
1163 (#x2648 . #x2653)
1164 (#x267F . #x267F)
1165 (#x2693 . #x2693)
1166 (#x26A1 . #x26A1)
1167 (#x26AA . #x26AB)
1168 (#x26BD . #x26BE)
1169 (#x26C4 . #x26C5)
1170 (#x26CE . #x26CE)
1171 (#x26D4 . #x26D4)
1172 (#x26EA . #x26EA)
1173 (#x26F2 . #x26F3)
1174 (#x26F5 . #x26F5)
1175 (#x26FA . #x26FA)
1176 (#x26FD . #x26FD)
1177 (#x2705 . #x2705)
1178 (#x270A . #x270B)
1179 (#x2728 . #x2728)
1180 (#x274C . #x274C)
1181 (#x274E . #x274E)
1182 (#x2753 . #x2755)
1183 (#x2757 . #x2757)
1184 (#x2795 . #x2797)
1185 (#x27B0 . #x27B0)
1186 (#x27BF . #x27BF)
1187 (#x2B1B . #x2B1C)
1188 (#x2B50 . #x2B50)
1189 (#x2B55 . #x2B55)
1190 (#x2E80 . #x303E)
1191 (#x3040 . #x3247)
1192 (#x3250 . #x4DBF)
1193 (#x4E00 . #xA4CF)
1194 (#xA490 . #xA4C6)
1195 (#xA960 . #xA97F)
1196 (#xAC00 . #xD7A3)
1197 (#xF900 . #xFAFF)
1198 (#xFE10 . #xFE19)
1199 (#xFE30 . #xFE6F)
1200 (#xFF01 . #xFF60)
1201 (#xFFE0 . #xFFE6)
1202 (#x16FE0 . #x16FE1)
1203 (#x17000 . #x187EC)
1204 (#x18800 . #x18AF2)
1205 (#x1B000 . #x1B11E)
1206 (#x1B170 . #x1B2FB)
1207 (#x1F004 . #x1F004)
1208 (#x1F0CF . #x1F0CF)
1209 (#x1F18E . #x1F18E)
1210 (#x1F191 . #x1F19A)
1211 (#x1F200 . #x1F320)
1212 (#x1F32D . #x1F335)
1213 (#x1F337 . #x1F37C)
1214 (#x1F37E . #x1F393)
1215 (#x1F3A0 . #x1F3CA)
1216 (#x1F3CF . #x1F3D3)
1217 (#x1F3E0 . #x1F3F0)
1218 (#x1F3F4 . #x1F3F4)
1219 (#x1F3F8 . #x1F3FA)
1220 (#x1F3FB . #x1F3FF)
1221 (#x1F400 . #x1F43E)
1222 (#x1F440 . #x1F440)
1223 (#x1F442 . #x1F4FC)
1224 (#x1F4FF . #x1F53D)
1225 (#x1F54B . #x1F54E)
1226 (#x1F550 . #x1F567)
1227 (#x1F57A . #x1F57A)
1228 (#x1F595 . #x1F596)
1229 (#x1F5A4 . #x1F5A4)
1230 (#x1F5FB . #x1F5FF)
1231 (#x1F600 . #x1F64F)
1232 (#x1F680 . #x1F6C5)
1233 (#x1F6CC . #x1F6CC)
1234 (#x1F6D0 . #x1F6D2)
1235 (#x1F6EB . #x1F6EC)
1236 (#x1F6F4 . #x1F6F8)
1237 (#x1F910 . #x1F93E)
1238 (#x1F940 . #x1F94C)
1239 (#x1F950 . #x1F96B)
1240 (#x1F980 . #x1F997)
1241 (#x1F9C0 . #x1F9C0)
1242 (#x1F9D0 . #x1F9E6)
1243 (#x20000 . #x2FFFF)
1244 (#x30000 . #x3FFFF))))
1245 (dolist (elt l)
1246 (set-char-table-range char-width-table elt 2)))
1247
1248 ;; Other double width
1249 ;;(map-charset-chars
1250 ;; (lambda (range ignore) (set-char-table-range char-width-table range 2))
1251 ;; 'ethiopic)
1252 ;; (map-charset-chars
1253 ;; (lambda (range ignore) (set-char-table-range char-width-table range 2))
1254 ;; 'tibetan)
1255 (map-charset-chars
1256 (lambda (range _ignore) (set-char-table-range char-width-table range 2))
1257 'indian-2-column)
1258 (map-charset-chars
1259 (lambda (range _ignore) (set-char-table-range char-width-table range 2))
1260 'arabic-2-column)
1261
1262 ;; Internal use only.
1263 ;; Alist of locale symbol vs charsets. In a language environment
1264 ;; corresponding to the locale, width of characters in the charsets is
1265 ;; set to 2. Each element has the form:
1266 ;; (LOCALE TABLE (CHARSET (FROM-CODE . TO-CODE) ...) ...)
1267 ;; LOCALE: locale symbol
1268 ;; TABLE: char-table used for char-width-table, initially nil.
1269 ;; CHARSET: character set
1270 ;; FROM-CODE, TO-CODE: range of code-points in CHARSET
1271
1272 (defvar cjk-char-width-table-list
1273 '((ja_JP nil (japanese-jisx0208 (#x2121 . #x287E))
1274 (cp932-2-byte (#x8140 . #x879F)))
1275 (zh_CN nil (chinese-gb2312 (#x2121 . #x297E)))
1276 (zh_HK nil (big5-hkscs (#xA140 . #xA3FE) (#xC6A0 . #xC8FE)))
1277 (zh_TW nil (big5 (#xA140 . #xA3FE))
1278 (chinese-cns11643-1 (#x2121 . #x427E)))
1279 (ko_KR nil (korean-ksc5601 (#x2121 . #x2C7E)))))
1280
1281 ;; Internal use only.
1282 ;; Setup char-width-table appropriate for a language environment
1283 ;; corresponding to LOCALE-NAME (symbol).
1284
1285 (defun use-cjk-char-width-table (locale-name)
1286 (while (char-table-parent char-width-table)
1287 (setq char-width-table (char-table-parent char-width-table)))
1288 (let ((slot (assq locale-name cjk-char-width-table-list)))
1289 (or slot (error "Unknown locale for CJK language environment: %s"
1290 locale-name))
1291 (unless (nth 1 slot)
1292 (let ((table (make-char-table nil)))
1293 (dolist (charset-info (nthcdr 2 slot))
1294 (let ((charset (car charset-info)))
1295 (dolist (code-range (cdr charset-info))
1296 (map-charset-chars #'(lambda (range _arg)
1297 (set-char-table-range table range 2))
1298 charset nil
1299 (car code-range) (cdr code-range)))))
1300 (optimize-char-table table)
1301 (set-char-table-parent table char-width-table)
1302 (setcar (cdr slot) table)))
1303 (setq char-width-table (nth 1 slot))))
1304
1305 (defun use-default-char-width-table ()
1306 "Internal use only.
1307 Setup char-width-table appropriate for non-CJK language environment."
1308 (while (char-table-parent char-width-table)
1309 (setq char-width-table (char-table-parent char-width-table))))
1310
1311 (optimize-char-table (standard-case-table))
1312 (optimize-char-table (standard-syntax-table))
1313
1314 \f
1315 ;; Setting char-script-table.
1316 (if purify-flag
1317 ;; While dumping, we can't use require, and international is not
1318 ;; in load-path.
1319 (load "international/charscript")
1320 (require 'charscript))
1321
1322 (map-charset-chars
1323 #'(lambda (range _ignore)
1324 (set-char-table-range char-script-table range 'tibetan))
1325 'tibetan)
1326
1327 \f
1328 ;;; Setting unicode-category-table.
1329
1330 (when (setq unicode-category-table
1331 (unicode-property-table-internal 'general-category))
1332 (map-char-table #'(lambda (key val)
1333 (if val
1334 (cond ((or (and (/= (aref (symbol-name val) 0) ?M)
1335 (/= (aref (symbol-name val) 0) ?C))
1336 (eq val 'Zs))
1337 (modify-category-entry key ?.))
1338 ((eq val 'Mn)
1339 (modify-category-entry key ?^)))))
1340 unicode-category-table))
1341
1342 (optimize-char-table (standard-category-table))
1343
1344 \f
1345 ;; Display of glyphless characters.
1346
1347 (defvar char-acronym-table
1348 (make-char-table 'char-acronym-table nil)
1349 "Char table of acronyms for non-graphic characters.")
1350
1351 (let ((c0-acronyms '("NUL" "SOH" "STX" "ETX" "EOT" "ENQ" "ACK" "BEL"
1352 "BS" nil nil "VT" "FF" "CR" "SO" "SI"
1353 "DLE" "DC1" "DC2" "DC3" "DC4" "NAK" "SYN" "ETB"
1354 "CAN" "EM" "SUB" "ESC" "FC" "GS" "RS" "US")))
1355 (dotimes (i 32)
1356 (aset char-acronym-table i (car c0-acronyms))
1357 (setq c0-acronyms (cdr c0-acronyms))))
1358
1359 (let ((c1-acronyms '("PAD" "HOP" "BPH" "NBH" "IND" "NEL" "SSA" "ESA"
1360 "HTS" "HTJ" "VTS" "PLD" "PLU" "R1" "SS2" "SS1"
1361 "DCS" "PU1" "PU2" "STS" "CCH" "MW" "SPA" "EPA"
1362 "SOS" "SGCI" "SC1" "CSI" "ST" "OSC" "PM" "APC")))
1363 (dotimes (i 32)
1364 (aset char-acronym-table (+ #x0080 i) (car c1-acronyms))
1365 (setq c1-acronyms (cdr c1-acronyms))))
1366
1367 (aset char-acronym-table #x17B4 "KIVAQ") ; KHMER VOWEL INHERENT AQ
1368 (aset char-acronym-table #x17B5 "KIVAA") ; KHMER VOWEL INHERENT AA
1369 (aset char-acronym-table #x200B "ZWSP") ; ZERO WIDTH SPACE
1370 (aset char-acronym-table #x200C "ZWNJ") ; ZERO WIDTH NON-JOINER
1371 (aset char-acronym-table #x200D "ZWJ") ; ZERO WIDTH JOINER
1372 (aset char-acronym-table #x200E "LRM") ; LEFT-TO-RIGHT MARK
1373 (aset char-acronym-table #x200F "RLM") ; RIGHT-TO-LEFT MARK
1374 (aset char-acronym-table #x202A "LRE") ; LEFT-TO-RIGHT EMBEDDING
1375 (aset char-acronym-table #x202B "RLE") ; RIGHT-TO-LEFT EMBEDDING
1376 (aset char-acronym-table #x202C "PDF") ; POP DIRECTIONAL FORMATTING
1377 (aset char-acronym-table #x202D "LRO") ; LEFT-TO-RIGHT OVERRIDE
1378 (aset char-acronym-table #x202E "RLO") ; RIGHT-TO-LEFT OVERRIDE
1379 (aset char-acronym-table #x2060 "WJ") ; WORD JOINER
1380 (aset char-acronym-table #x206A "ISS") ; INHIBIT SYMMETRIC SWAPPING
1381 (aset char-acronym-table #x206B "ASS") ; ACTIVATE SYMMETRIC SWAPPING
1382 (aset char-acronym-table #x206C "IAFS") ; INHIBIT ARABIC FORM SHAPING
1383 (aset char-acronym-table #x206D "AAFS") ; ACTIVATE ARABIC FORM SHAPING
1384 (aset char-acronym-table #x206E "NADS") ; NATIONAL DIGIT SHAPES
1385 (aset char-acronym-table #x206F "NODS") ; NOMINAL DIGIT SHAPES
1386 (aset char-acronym-table #xFEFF "ZWNBSP") ; ZERO WIDTH NO-BREAK SPACE
1387 (aset char-acronym-table #xFFF9 "IAA") ; INTERLINEAR ANNOTATION ANCHOR
1388 (aset char-acronym-table #xFFFA "IAS") ; INTERLINEAR ANNOTATION SEPARATOR
1389 (aset char-acronym-table #xFFFB "IAT") ; INTERLINEAR ANNOTATION TERMINATOR
1390 (aset char-acronym-table #x1D173 "BEGBM") ; MUSICAL SYMBOL BEGIN BEAM
1391 (aset char-acronym-table #x1D174 "ENDBM") ; MUSICAL SYMBOL END BEAM
1392 (aset char-acronym-table #x1D175 "BEGTIE") ; MUSICAL SYMBOL BEGIN TIE
1393 (aset char-acronym-table #x1D176 "END") ; MUSICAL SYMBOL END TIE
1394 (aset char-acronym-table #x1D177 "BEGSLR") ; MUSICAL SYMBOL BEGIN SLUR
1395 (aset char-acronym-table #x1D178 "ENDSLR") ; MUSICAL SYMBOL END SLUR
1396 (aset char-acronym-table #x1D179 "BEGPHR") ; MUSICAL SYMBOL BEGIN PHRASE
1397 (aset char-acronym-table #x1D17A "ENDPHR") ; MUSICAL SYMBOL END PHRASE
1398 (aset char-acronym-table #xE0001 "|->TAG") ; LANGUAGE TAG
1399 (aset char-acronym-table #xE0020 "SP TAG") ; TAG SPACE
1400 (dotimes (i 94)
1401 (aset char-acronym-table (+ #xE0021 i) (format " %c TAG" (+ 33 i))))
1402 (aset char-acronym-table #xE007F "->|TAG") ; CANCEL TAG
1403
1404 (defun update-glyphless-char-display (&optional variable value)
1405 "Make the setting of `glyphless-char-display-control' take effect.
1406 This function updates the char-table `glyphless-char-display'."
1407 (when value
1408 (set-default variable value))
1409 (dolist (elt value)
1410 (let ((target (car elt))
1411 (method (cdr elt)))
1412 (or (memq method '(zero-width thin-space empty-box acronym hex-code))
1413 (error "Invalid glyphless character display method: %s" method))
1414 (cond ((eq target 'c0-control)
1415 (glyphless-set-char-table-range glyphless-char-display
1416 #x00 #x1F method)
1417 ;; Users will not expect their newlines and TABs be
1418 ;; displayed as anything but themselves, so exempt those
1419 ;; two characters from c0-control.
1420 (set-char-table-range glyphless-char-display #x9 nil)
1421 (set-char-table-range glyphless-char-display #xa nil))
1422 ((eq target 'c1-control)
1423 (glyphless-set-char-table-range glyphless-char-display
1424 #x80 #x9F method))
1425 ((eq target 'format-control)
1426 (when unicode-category-table
1427 (map-char-table
1428 #'(lambda (char category)
1429 (if (eq category 'Cf)
1430 (let ((this-method method)
1431 from to)
1432 (if (consp char)
1433 (setq from (car char) to (cdr char))
1434 (setq from char to char))
1435 (while (<= from to)
1436 (when (/= from #xAD)
1437 (if (eq method 'acronym)
1438 (setq this-method
1439 (aref char-acronym-table from)))
1440 (set-char-table-range glyphless-char-display
1441 from this-method))
1442 (setq from (1+ from))))))
1443 unicode-category-table)))
1444 ((eq target 'no-font)
1445 (set-char-table-extra-slot glyphless-char-display 0 method))
1446 (t
1447 (error "Invalid glyphless character group: %s" target))))))
1448
1449 (defun glyphless-set-char-table-range (chartable from to method)
1450 (if (eq method 'acronym)
1451 (let ((i from))
1452 (while (<= i to)
1453 (set-char-table-range chartable i (aref char-acronym-table i))
1454 (setq i (1+ i))))
1455 (set-char-table-range chartable (cons from to) method)))
1456
1457 ;;; Control of displaying glyphless characters.
1458 (defcustom glyphless-char-display-control
1459 '((format-control . thin-space)
1460 (no-font . hex-code))
1461 "List of directives to control display of glyphless characters.
1462
1463 Each element has the form (GROUP . METHOD), where GROUP is a
1464 symbol specifying the character group, and METHOD is a symbol
1465 specifying the method of displaying characters belonging to that
1466 group.
1467
1468 GROUP must be one of these symbols:
1469 `c0-control': U+0000..U+001F, but excluding newline and TAB.
1470 `c1-control': U+0080..U+009F.
1471 `format-control': Characters of Unicode General Category `Cf',
1472 such as U+200C (ZWNJ), U+200E (LRM), but
1473 excluding characters that have graphic images,
1474 such as U+00AD (SHY).
1475 `no-font': characters for which no suitable font is found.
1476 For character terminals, characters that cannot
1477 be encoded by `terminal-coding-system'.
1478
1479 METHOD must be one of these symbols:
1480 `zero-width': don't display.
1481 `thin-space': display a thin (1-pixel width) space. On character
1482 terminals, display as 1-character space.
1483 `empty-box': display an empty box.
1484 `acronym': display an acronym of the character in a box. The
1485 acronym is taken from `char-acronym-table', which see.
1486 `hex-code': display the hexadecimal character code in a box.
1487
1488 Do not set its value directly from Lisp; the value takes effect
1489 only via a custom `:set'
1490 function (`update-glyphless-char-display'), which updates
1491 `glyphless-char-display'."
1492 :version "24.1"
1493 :type '(alist :key-type (symbol :tag "Character Group")
1494 :value-type (symbol :tag "Display Method"))
1495 :options '((c0-control
1496 (choice (const :tag "Don't display" zero-width)
1497 (const :tag "Display as thin space" thin-space)
1498 (const :tag "Display as empty box" empty-box)
1499 (const :tag "Display acronym" acronym)
1500 (const :tag "Display hex code in a box" hex-code)))
1501 (c1-control
1502 (choice (const :tag "Don't display" zero-width)
1503 (const :tag "Display as thin space" thin-space)
1504 (const :tag "Display as empty box" empty-box)
1505 (const :tag "Display acronym" acronym)
1506 (const :tag "Display hex code in a box" hex-code)))
1507 (format-control
1508 (choice (const :tag "Don't display" zero-width)
1509 (const :tag "Display as thin space" thin-space)
1510 (const :tag "Display as empty box" empty-box)
1511 (const :tag "Display acronym" acronym)
1512 (const :tag "Display hex code in a box" hex-code)))
1513 (no-font
1514 (choice (const :tag "Don't display" zero-width)
1515 (const :tag "Display as thin space" thin-space)
1516 (const :tag "Display as empty box" empty-box)
1517 (const :tag "Display acronym" acronym)
1518 (const :tag "Display hex code in a box" hex-code))))
1519 :set 'update-glyphless-char-display
1520 :group 'display)
1521
1522 \f
1523 ;;; Setting word boundary.
1524
1525 (setq word-combining-categories
1526 '((nil . ?^)
1527 (?^ . nil)
1528 (?C . ?H)
1529 (?C . ?K)))
1530
1531 (setq word-separating-categories ; (2-byte character sets)
1532 '((?H . ?K) ; Hiragana - Katakana
1533 ))
1534
1535 ;; Local Variables:
1536 ;; coding: utf-8
1537 ;; End:
1538
1539 ;;; characters.el ends here
Emacs repository mirror