1 ;;; characters.el --- set syntax and category for multibyte characters
3 ;; Copyright (C) 1997, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008
4 ;; Free Software Foundation, Inc.
5 ;; Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
6 ;; 2005, 2006, 2007, 2008
7 ;; National Institute of Advanced Industrial Science and Technology (AIST)
8 ;; Registration Number H14PRO021
10 ;; National Institute of Advanced Industrial Science and Technology (AIST)
11 ;; Registration Number H13PRO009
13 ;; Keywords: multibyte character, character set, syntax, category
15 ;; This file is part of GNU Emacs.
17 ;; GNU Emacs is free software: you can redistribute it and/or modify
18 ;; it under the terms of the GNU General Public License as published by
19 ;; the Free Software Foundation, either version 3 of the License, or
20 ;; (at your option) any later version.
22 ;; GNU Emacs is distributed in the hope that it will be useful,
23 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
24 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
25 ;; GNU General Public License for more details.
27 ;; You should have received a copy of the GNU General Public License
28 ;; along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>.
34 ;;; Predefined categories.
36 ;; For each character set.
38 (define-category ?a
"ASCII
39 ASCII graphic characters 32-126 (ISO646 IRV:1983[4/0])")
40 (define-category ?l
"Latin")
41 (define-category ?t
"Thai")
42 (define-category ?g
"Greek")
43 (define-category ?b
"Arabic")
44 (define-category ?w
"Hebrew")
45 (define-category ?y
"Cyrillic")
46 (define-category ?k
"Katakana
48 (define-category ?r
"Roman
50 (define-category ?c
"Chinese")
51 (define-category ?j
"Japanese")
52 (define-category ?h
"Korean")
53 (define-category ?e
"Ethiopic
55 (define-category ?v
"Viet
57 (define-category ?i
"Indian")
58 (define-category ?o
"Lao")
59 (define-category ?q
"Tibetan")
61 ;; For each group (row) of 2-byte character sets.
63 (define-category ?A
"2-byte alnum
64 Alpha-numeric characters of 2-byte character sets")
65 (define-category ?C
"2-byte han
66 Chinese (Han) characters of 2-byte character sets")
67 (define-category ?G
"2-byte Greek
68 Greek characters of 2-byte character sets")
69 (define-category ?H
"2-byte Hiragana
70 Japanese Hiragana characters of 2-byte character sets")
71 (define-category ?K
"2-byte Katakana
72 Japanese Katakana characters of 2-byte character sets")
73 (define-category ?N
"2-byte Korean
74 Korean Hangul characters of 2-byte character sets")
75 (define-category ?Y
"2-byte Cyrillic
76 Cyrillic characters of 2-byte character sets")
77 (define-category ?I
"Indian Glyphs")
79 ;; For phonetic classifications.
81 (define-category ?
0 "consonant")
82 (define-category ?
1 "base vowel
83 base (independent) vowel")
84 (define-category ?
2 "upper diacritic
85 upper diacritical mark (including upper vowel)")
86 (define-category ?
3 "lower diacritic
87 lower diacritical mark (including lower vowel)")
88 (define-category ?
4 "combining tone
90 (define-category ?
5 "symbol")
91 (define-category ?
6 "digit")
92 (define-category ?
7 "vowel diacritic
93 vowel-modifying diacritical mark")
94 (define-category ?
8 "vowel-signs")
95 (define-category ?
9 "semivowel lower")
98 (define-category ?|
"line breakable
99 While filling, we can break a line at this character.")
101 ;; For indentation calculation.
104 This character counts as a space for indentation purposes.")
106 ;; Keep the following for `kinsoku' processing. See comments in
108 (define-category ?
> "Not at bol
109 A character which can't be placed at beginning of line.")
110 (define-category ?
< "Not at eol
111 A character which can't be placed at end of line.")
114 (define-category ?^
"Combining
115 Combining diacritic or mark")
117 ;;; Setting syntax and category.
121 ;; All ASCII characters have the category `a' (ASCII) and `l' (Latin).
122 (modify-category-entry '(32 .
127) ?a
)
123 (modify-category-entry '(32 .
127) ?l
)
125 ;; Deal with the CJK charsets first. Since the syntax of blocks is
126 ;; defined per charset, and the charsets may contain e.g. Latin
127 ;; characters, we end up with the wrong syntax definitions if we're
130 ;; Chinese characters (Unicode)
131 (modify-category-entry '(#x2E80 .
#x312F
) ?|
)
132 (modify-category-entry '(#x3190 .
#x33FF
) ?|
)
133 (modify-category-entry '(#x3400 .
#x9FAF
) ?C
)
134 (modify-category-entry '(#x3400 .
#x9FAF
) ?c
)
135 (modify-category-entry '(#x3400 .
#x9FAF
) ?|
)
136 (modify-category-entry '(#xF900 .
#xFAFF
) ?C
)
137 (modify-category-entry '(#xF900 .
#xFAFF
) ?c
)
138 (modify-category-entry '(#xF900 .
#xFAFF
) ?|
)
139 (modify-category-entry '(#x20000 .
#x2AFFF
) ?|
)
140 (modify-category-entry '(#x2F800 .
#x2FFFF
) ?|
)
141 (modify-category-entry '(#x20000 .
#x2AFFF
) ?C
)
142 (modify-category-entry '(#x2F800 .
#x2FFFF
) ?C
)
145 ;; Chinese character set (GB2312)
147 (map-charset-chars #'modify-syntax-entry
'chinese-gb2312
"_" #x2121
#x217E
)
148 (map-charset-chars #'modify-syntax-entry
'chinese-gb2312
"_" #x2221
#x227E
)
149 (map-charset-chars #'modify-syntax-entry
'chinese-gb2312
"_" #x2921
#x297E
)
151 (map-charset-chars #'modify-category-entry
'chinese-gb2312 ?c
)
152 (map-charset-chars #'modify-category-entry
'chinese-gb2312 ?A
#x2330
#x2339
)
153 (map-charset-chars #'modify-category-entry
'chinese-gb2312 ?A
#x2341
#x235A
)
154 (map-charset-chars #'modify-category-entry
'chinese-gb2312 ?A
#x2361
#x237A
)
155 (map-charset-chars #'modify-category-entry
'chinese-gb2312 ?H
#x2421
#x247E
)
156 (map-charset-chars #'modify-category-entry
'chinese-gb2312 ?K
#x2521
#x257E
)
157 (map-charset-chars #'modify-category-entry
'chinese-gb2312 ?G
#x2621
#x267E
)
158 (map-charset-chars #'modify-category-entry
'chinese-gb2312 ?Y
#x2721
#x277E
)
159 (map-charset-chars #'modify-category-entry
'chinese-gb2312 ?C
#x3021
#x7E7E
)
161 ;; Chinese character set (BIG5)
163 (map-charset-chars #'modify-category-entry
'big5 ?c
)
164 (map-charset-chars #'modify-category-entry
'big5 ?C
#xA259
#xA25F
)
165 (map-charset-chars #'modify-category-entry
'big5 ?C
#xA440
#xC67E
)
166 (map-charset-chars #'modify-category-entry
'big5 ?C
#xC940
#xF9DF
)
168 ;; Chinese character set (CNS11643)
170 (dolist (c '(chinese-cns11643-1 chinese-cns11643-2 chinese-cns11643-3
171 chinese-cns11643-4 chinese-cns11643-5 chinese-cns11643-6
173 (map-charset-chars #'modify-category-entry c ?c
)
174 (if (eq c
'chinese-cns11643-1
)
175 (map-charset-chars #'modify-category-entry c ?C
#x4421
#x7E7E
)
176 (map-charset-chars #'modify-category-entry c ?C
)))
178 ;; Japanese character set (JISX0201, JISX0208, JISX0212, JISX0213)
180 (map-charset-chars #'modify-category-entry
'katakana-jisx0201 ?k
)
182 (map-charset-chars #'modify-category-entry
'latin-jisx0201 ?r
)
184 (dolist (l '(katakana-jisx0201 japanese-jisx0208 japanese-jisx0212
185 japanese-jisx0213-1 japanese-jisx0213-2
))
186 (map-charset-chars #'modify-category-entry l ?j
))
188 ;; Unicode equivalents of JISX0201-kana
189 (let ((range '(#xff61 .
#xff9f
)))
190 (modify-category-entry range ?k
)
191 (modify-category-entry range ?j
)
192 (modify-category-entry range ?\|
))
195 (let ((range '(#x30a0 .
#x30ff
)))
196 ;; ?K is double width, ?k isn't specified
197 (modify-category-entry range ?K
)
198 (modify-category-entry range ?\|
))
201 (let ((range '(#x3040 .
#x309d
)))
202 ;; ?H is actually defined to be double width
203 ;;(modify-category-entry range ?H)
204 (modify-category-entry range ?\|
)
208 (map-charset-chars #'modify-syntax-entry
'japanese-jisx0208
"_" #x2121
#x227E
)
209 (map-charset-chars #'modify-syntax-entry
'japanese-jisx0208
"_" #x2821
#x287E
)
210 (let ((chars '(?ー ?゛ ?゜ ?ヽ ?ヾ ?ゝ ?ゞ ?〃 ?仝 ?々 ?〆 ?〇
)))
212 (modify-syntax-entry (car chars
) "w")))
214 (map-charset-chars #'modify-category-entry
'japanese-jisx0208 ?A
#x2321
#x237E
)
215 (map-charset-chars #'modify-category-entry
'japanese-jisx0208 ?H
#x2421
#x247E
)
216 (map-charset-chars #'modify-category-entry
'japanese-jisx0208 ?K
#x2521
#x257E
)
217 (map-charset-chars #'modify-category-entry
'japanese-jisx0208 ?G
#x2621
#x267E
)
218 (map-charset-chars #'modify-category-entry
'japanese-jisx0208 ?Y
#x2721
#x277E
)
219 (map-charset-chars #'modify-category-entry
'japanese-jisx0208 ?C
#x3021
#x7E7E
)
220 (modify-category-entry ?ー ?K
)
221 (let ((chars '(?゛ ?゜
)))
223 (modify-category-entry (car chars
) ?K
)
224 (modify-category-entry (car chars
) ?H
)
225 (setq chars
(cdr chars
))))
226 (let ((chars '(?ヽ ?ヾ ?ゝ ?ゞ ?〃 ?仝 ?々 ?〆 ?〇
)))
228 (modify-category-entry (car chars
) ?C
)
229 (setq chars
(cdr chars
))))
233 (map-charset-chars #'modify-syntax-entry
'japanese-jisx0212
"_" #x2121
#x237E
)
237 (let ((chars '(?。 ?、 ?・
)))
239 (modify-syntax-entry (car chars
) ".")
240 (setq chars
(cdr chars
))))
242 (modify-syntax-entry ?\「
"(」")
243 (modify-syntax-entry ?\」
"(「")
245 ;; Korean character set (KSC5601)
247 (map-charset-chars #'modify-category-entry
'korean-ksc5601 ?h
)
249 (map-charset-chars #'modify-syntax-entry
'korean-ksc5601
"_" #x2121
#x227E
)
250 (map-charset-chars #'modify-syntax-entry
'korean-ksc5601
"_" #x2621
#x277E
)
251 (map-charset-chars #'modify-syntax-entry
'korean-ksc5601
"_" #x2830
#x287E
)
252 (map-charset-chars #'modify-syntax-entry
'korean-ksc5601
"_" #x2930
#x297E
)
253 (map-charset-chars #'modify-category-entry
'korean-ksc5601 ?A
#x2330
#x2339
)
254 (map-charset-chars #'modify-category-entry
'korean-ksc5601 ?A
#x2341
#x235A
)
255 (map-charset-chars #'modify-category-entry
'korean-ksc5601 ?A
#x2361
#x237A
)
256 (map-charset-chars #'modify-category-entry
'korean-ksc5601 ?G
#x2521
#x257E
)
257 (map-charset-chars #'modify-category-entry
'korean-ksc5601 ?H
#x2A21
#x2A7E
)
258 (map-charset-chars #'modify-category-entry
'korean-ksc5601 ?K
#x2B21
#x2B7E
)
259 (map-charset-chars #'modify-category-entry
'korean-ksc5601 ?Y
#x2C21
#x2C7E
)
261 ;; These are in more than one charset.
262 (let ((parens (concat "〈〉《》「」『』【】〔〕〖〗〘〙〚〛"
266 (dotimes (i (/ (length parens
) 2))
267 (setq open
(aref parens
(* i
2))
268 close
(aref parens
(1+ (* i
2))))
269 (modify-syntax-entry open
(format "(%c" close
))
270 (modify-syntax-entry close
(format ")%c" open
))))
272 ;; Arabic character set
274 (let ((charsets '(arabic-iso8859-6
279 (map-charset-chars #'modify-category-entry
(car charsets
) ?b
)
280 (setq charsets
(cdr charsets
))))
281 (modify-category-entry '(#x600 .
#x6ff
) ?b
)
282 (modify-category-entry '(#xfb50 .
#xfdff
) ?b
)
283 (modify-category-entry '(#xfe70 .
#xfefe
) ?b
)
285 ;; Cyrillic character set (ISO-8859-5)
287 (modify-syntax-entry ?№
".")
289 ;; Ethiopic character set
291 (modify-category-entry '(#x1200 .
#x1399
) ?e
)
292 (modify-category-entry '(#x2d80 .
#x2dde
) ?e
)
293 (let ((chars '(?፡ ?። ?፣ ?፤ ?፥ ?፦ ?፧ ?፨
)))
295 (modify-syntax-entry (car chars
) ".")
296 (setq chars
(cdr chars
))))
297 (map-charset-chars #'modify-category-entry
'ethiopic ?e
)
299 ;; Hebrew character set (ISO-8859-8)
301 (modify-syntax-entry #x5be
".") ; MAQAF
302 (modify-syntax-entry #x5c0
".") ; PASEQ
303 (modify-syntax-entry #x5c3
".") ; SOF PASUQ
304 (modify-syntax-entry #x5f3
".") ; GERESH
305 (modify-syntax-entry #x5f4
".") ; GERSHAYIM
307 ;; Indian character set (IS 13194 and other Emacs original Indian charsets)
309 (modify-category-entry '(#x901 .
#x970
) ?i
)
310 (map-charset-chars #'modify-category-entry
'indian-is13194 ?i
)
311 (map-charset-chars #'modify-category-entry
'indian-2-column ?i
)
315 (modify-category-entry '(#xe80 .
#xeff
) ?o
)
316 (map-charset-chars #'modify-category-entry
'lao ?o
)
318 (let ((deflist '(("ກ-ຮ" "w" ?
0) ; consonant
319 ("ະາຳຽເ-ໄ" "w" ?
1) ; vowel base
320 ("ັິ-ືົໍ" "w" ?
2) ; vowel upper
321 ("ຸູ" "w" ?
3) ; vowel lower
322 ("່-໋" "w" ?
4) ; tone mark
323 ("ຼຽ" "w" ?
9) ; semivowel lower
324 ("໐-໙" "w" ?
6) ; digit
325 ("ຯໆ" "_" ?
5) ; symbol
327 elm chars len syntax category to ch i
)
329 (setq elm
(car deflist
))
330 (setq chars
(car elm
)
336 (if (= (aref chars i
) ?-
)
339 (setq ch
(aref chars i
)
342 (unless (string-equal syntax
"w")
343 (modify-syntax-entry ch syntax
))
344 (modify-category-entry ch category
)
347 (setq deflist
(cdr deflist
))))
349 ;; Thai character set (TIS620)
351 (modify-category-entry '(#xe00 .
#xe7f
) ?t
)
352 (map-charset-chars #'modify-category-entry
'thai-tis620 ?t
)
354 (let ((deflist '(;; chars syntax category
355 ("ก-รลว-ฮ" "w" ?
0) ; consonant
356 ("ฤฦะาำเ-ๅ" "w" ?
1) ; vowel base
357 ("ัิ-ื็๎" "w" ?
2) ; vowel upper
358 ("ุ-ฺ" "w" ?
3) ; vowel lower
359 ("่-ํ" "w" ?
4) ; tone mark
360 ("๐-๙" "w" ?
6) ; digit
361 ("ฯๆ฿๏๚๛" "_" ?
5) ; symbol
363 elm chars len syntax category to ch i
)
365 (setq elm
(car deflist
))
366 (setq chars
(car elm
)
372 (if (= (aref chars i
) ?-
)
375 (setq ch
(aref chars i
)
378 (unless (string-equal syntax
"w")
379 (modify-syntax-entry ch syntax
))
380 (modify-category-entry ch category
)
383 (setq deflist
(cdr deflist
))))
385 ;; Tibetan character set
387 (modify-category-entry '(#xf00 .
#xfff
) ?q
)
388 (map-charset-chars #'modify-category-entry
'tibetan ?q
)
389 (map-charset-chars #'modify-category-entry
'tibetan-1-column ?q
)
391 (let ((deflist '(;; chars syntax category
392 ("ཀ-ཀྵཪ" "w" ?
0) ; consonant
394 ("ིེཻོཽྀ" "w" ?
2) ; upper vowel
395 ("ཾྂྃ྆྇ྈྉྊྋ" "w" ?
2) ; upper modifier
396 ("྄ཱུ༙༵༷" "w" ?
3) ; lowel vowel/modifier
397 ("" "w" ?
3) ; invisible vowel a
398 ("༠-༩༪-༳" "w" ?
6) ; digit
399 ("་།-༒༔ཿ" "." ?|
) ; line-break char
401 ("༈་།-༒༔ཿ༽༴" "." ?
>) ; prohibition
403 ("ༀ-༊༼࿁࿂྅" "." ?
<) ; prohibition
404 ("༓༕-༘༚-༟༶༸-༻༾༿྾྿-࿏" "." ?q
) ; others
406 elm chars len syntax category to ch i
)
408 (setq elm
(car deflist
))
409 (setq chars
(car elm
)
415 (if (= (aref chars i
) ?-
)
418 (setq ch
(aref chars i
)
421 (unless (string-equal syntax
"w")
422 (modify-syntax-entry ch syntax
))
423 (modify-category-entry ch category
)
426 (setq deflist
(cdr deflist
))))
428 ;; Vietnamese character set
430 ;; To make a word with Latin characters
431 (map-charset-chars #'modify-category-entry
'vietnamese-viscii-lower ?l
)
432 (map-charset-chars #'modify-category-entry
'vietnamese-viscii-lower ?v
)
434 (map-charset-chars #'modify-category-entry
'vietnamese-viscii-upper ?l
)
435 (map-charset-chars #'modify-category-entry
'vietnamese-viscii-upper ?v
)
437 (let ((tbl (standard-case-table))
440 (let* ((char (decode-char 'vietnamese-viscii-upper i
))
441 (charl (decode-char 'vietnamese-viscii-lower i
))
442 (uc (encode-char char
'ucs
))
443 (lc (encode-char charl
'ucs
)))
444 (set-case-syntax-pair char
(decode-char 'vietnamese-viscii-lower i
)
446 (if uc
(modify-category-entry uc ?v
))
447 (if lc
(modify-category-entry lc ?v
)))
451 (let ((deflist '(;; chars syntax category
452 ((?ꪀ. ?ꪯ
) "w" ?
0) ; cosonant
453 ("ꪱꪵꪶ" "w" ?
1) ; vowel base
454 ((?ꪹ . ?ꪽ
) "w" ?
1) ; vowel base
455 ("ꪰꪲꪳꪷꪸꪾ" "w" ?
2) ; vowel upper
456 ("ꪴ" "w" ?
3) ; vowel lower
457 ("ꫀꫂ" "w" ?
1) ; non-combining tone-mark
458 ("꪿꫁" "w" ?
4) ; combining tone-mark
459 ((?ꫛ . ?꫟
) "_" ?
5) ; symbol
461 (dolist (elm deflist
)
462 (let ((chars (car elm
))
464 (category (nth 2 elm
)))
467 (modify-syntax-entry chars syntax
)
468 (modify-category-entry chars category
))
470 (modify-syntax-entry x syntax
)
471 (modify-category-entry x category
))
476 (modify-category-entry '(#x80 .
#x024F
) ?l
)
478 (let ((tbl (standard-case-table)) c
)
482 ;; Fixme: Some of the non-word syntaxes here perhaps should be
483 ;; reviewed. (Note that the following all implicitly have word
484 ;; syntax: ¢£¤¥¨ª¯²³´¶¸¹º.) There should be a well-defined way of
485 ;; relating Unicode categories to Emacs syntax codes.
487 ;; NBSP isn't semantically interchangeable with other whitespace chars,
488 ;; so it's more like punctation.
489 (set-case-syntax ?
"." tbl
)
490 (set-case-syntax ?¡
"." tbl
)
491 (set-case-syntax ?¦
"_" tbl
)
492 (set-case-syntax ?§
"." tbl
)
493 (set-case-syntax ?©
"_" tbl
)
494 (set-case-syntax-delims 171 187 tbl
) ; « »
495 (set-case-syntax ?¬
"_" tbl
)
496 (set-case-syntax ?
"_" tbl
)
497 (set-case-syntax ?®
"_" tbl
)
498 (set-case-syntax ?°
"_" tbl
)
499 (set-case-syntax ?±
"_" tbl
)
500 (set-case-syntax ?µ
"_" tbl
)
501 (set-case-syntax ?·
"_" tbl
)
502 (set-case-syntax ?¼
"_" tbl
)
503 (set-case-syntax ?½
"_" tbl
)
504 (set-case-syntax ?¾
"_" tbl
)
505 (set-case-syntax ?¿
"." tbl
)
508 (set-case-syntax-pair c
(+ c
32) tbl
)
510 (set-case-syntax ?×
"_" tbl
)
511 (set-case-syntax ?ß
"w" tbl
)
512 (set-case-syntax ?÷
"_" tbl
)
515 ;; Latin Extended-A, Latin Extended-B
518 (modify-category-entry c ?l
)
521 (let ((pair-ranges '((#x0100 .
#x012F
)
544 (dolist (elt pair-ranges
)
545 (let ((from (car elt
)) (to (cdr elt
)))
547 (set-case-syntax-pair from
(1+ from
) tbl
)
548 (setq from
(+ from
2))))))
550 ;; In some languages, such as Turkish, U+0049 LATIN CAPITAL LETTER I
551 ;; and U+0131 LATIN SMALL LETTER DOTLESS I make a case pair, and so
552 ;; do U+0130 LATIN CAPITAL LETTER I WITH DOT ABOVE and U+0069 LATIN
555 ;; We used to set up half of those correspondence unconditionally,
556 ;; but that makes searches slow. So now we don't set up either half
557 ;; of these correspondences by default.
559 ;; (set-downcase-syntax ?İ ?i tbl)
560 ;; (set-upcase-syntax ?I ?ı tbl)
562 (set-case-syntax-pair ?DŽ ?dž tbl
)
563 (set-case-syntax-pair ?Dž ?dž tbl
)
564 (set-case-syntax-pair ?LJ ?lj tbl
)
565 (set-case-syntax-pair ?Lj ?lj tbl
)
566 (set-case-syntax-pair ?NJ ?nj tbl
)
567 (set-case-syntax-pair ?Nj ?nj tbl
)
569 ;; 01F0; F; 006A 030C; # LATIN SMALL LETTER J WITH CARON
570 (set-case-syntax-pair ?DZ ?dz tbl
)
571 (set-case-syntax-pair ?Dz ?dz tbl
)
572 (set-case-syntax-pair ?Ƕ ?ƕ tbl
)
573 (set-case-syntax-pair ?Ƿ ?ƿ tbl
)
575 ;; Latin Extended Additional
576 (modify-category-entry '(#x1e00 .
#x1ef9
) ?l
)
580 (or (<= c
#x1e94
) (>= c
#x1ea0
))
581 (set-case-syntax-pair c
(1+ c
) tbl
))
585 (modify-category-entry '(#x0370 .
#x03ff
) ?g
)
588 (if (or (and (>= c
#x0391
) (<= c
#x03a1
))
589 (and (>= c
#x03a3
) (<= c
#x03ab
)))
590 (set-case-syntax-pair c
(+ c
32) tbl
))
594 (set-case-syntax-pair c
(1+ c
) tbl
))
596 (set-case-syntax-pair ?Ά ?ά tbl
)
597 (set-case-syntax-pair ?Έ ?έ tbl
)
598 (set-case-syntax-pair ?Ή ?ή tbl
)
599 (set-case-syntax-pair ?Ί ?ί tbl
)
600 (set-case-syntax-pair ?Ό ?ό tbl
)
601 (set-case-syntax-pair ?Ύ ?ύ tbl
)
602 (set-case-syntax-pair ?Ώ ?ώ tbl
)
607 (set-case-syntax-pair c
(+ c
#x30
) tbl
)
611 (modify-category-entry '(#x1f00 .
#x1fff
) ?g
)
614 (and (<= (logand c
#x000f
) 7)
616 (not (memq c
'(#x1f50
#x1f52
#x1f54
#x1f56
)))
617 (/= (logand c
#x00f0
) 7)
618 (set-case-syntax-pair (+ c
8) c tbl
))
620 (set-case-syntax-pair ?Ᾰ ?ᾰ tbl
)
621 (set-case-syntax-pair ?Ᾱ ?ᾱ tbl
)
622 (set-case-syntax-pair ?Ὰ ?ὰ tbl
)
623 (set-case-syntax-pair ?Ά ?ά tbl
)
624 (set-case-syntax-pair ?ᾼ ?ᾳ tbl
)
625 (set-case-syntax-pair ?Ὲ ?ὲ tbl
)
626 (set-case-syntax-pair ?Έ ?έ tbl
)
627 (set-case-syntax-pair ?Ὴ ?ὴ tbl
)
628 (set-case-syntax-pair ?Ή ?ή tbl
)
629 (set-case-syntax-pair ?ῌ ?ῃ tbl
)
630 (set-case-syntax-pair ?Ῐ ?ῐ tbl
)
631 (set-case-syntax-pair ?Ῑ ?ῑ tbl
)
632 (set-case-syntax-pair ?Ὶ ?ὶ tbl
)
633 (set-case-syntax-pair ?Ί ?ί tbl
)
634 (set-case-syntax-pair ?Ῠ ?ῠ tbl
)
635 (set-case-syntax-pair ?Ῡ ?ῡ tbl
)
636 (set-case-syntax-pair ?Ὺ ?ὺ tbl
)
637 (set-case-syntax-pair ?Ύ ?ύ tbl
)
638 (set-case-syntax-pair ?Ῥ ?ῥ tbl
)
639 (set-case-syntax-pair ?Ὸ ?ὸ tbl
)
640 (set-case-syntax-pair ?Ό ?ό tbl
)
641 (set-case-syntax-pair ?Ὼ ?ὼ tbl
)
642 (set-case-syntax-pair ?Ώ ?ώ tbl
)
643 (set-case-syntax-pair ?ῼ ?ῳ tbl
)
646 (modify-category-entry '(#x0400 .
#x04FF
) ?y
)
651 (set-case-syntax-pair c
(+ c
80) tbl
))
654 (set-case-syntax-pair c
(+ c
32) tbl
))
656 (or (and (>= c
#x0460
) (<= c
#x0480
))
657 (and (>= c
#x048c
) (<= c
#x04be
))
658 (and (>= c
#x04d0
) (<= c
#x04f4
)))
659 (set-case-syntax-pair c
(1+ c
) tbl
))
661 (set-case-syntax-pair ?Ӂ ?ӂ tbl
)
662 (set-case-syntax-pair ?Ӄ ?ӄ tbl
)
663 (set-case-syntax-pair ?Ӈ ?ӈ tbl
)
664 (set-case-syntax-pair ?Ӌ ?ӌ tbl
)
665 (set-case-syntax-pair ?Ӹ ?ӹ tbl
)
667 ;; general punctuation
670 (set-case-syntax c
" " tbl
)
673 (set-case-syntax c
"." tbl
)
675 ;; Fixme: These aren't all right:
678 (set-case-syntax c
"_" tbl
)
680 ;; Punctuation syntax for quotation marks (like `)
682 (set-case-syntax c
"." tbl
)
684 ;; Fixme: These aren't all right:
686 (set-case-syntax c
"_" tbl
)
689 (set-case-syntax c
"." tbl
)
695 (set-case-syntax-pair c
(+ c
#x10
) tbl
)
698 ;; Fixme: The following blocks might be better as symbol rather than
703 (set-case-syntax c
"." tbl
)
705 ;; Mathematical Operators
707 (set-case-syntax c
"." tbl
)
709 ;; Miscellaneous Technical
711 (set-case-syntax c
"." tbl
)
715 (set-case-syntax c
"_" tbl
)
721 (set-case-syntax-pair c
(+ c
26) tbl
)
722 (modify-category-entry c ?l
)
723 (modify-category-entry (+ c
26) ?l
)
729 (set-case-syntax-pair c
(+ c
#x20
) tbl
)
730 (modify-category-entry c ?l
)
731 (modify-category-entry (+ c
#x20
) ?l
)
734 ;; Combining diacritics
735 (modify-category-entry '(#x300 .
#x362
) ?^
)
737 (modify-category-entry '(#x20d0 .
#x20e3
) ?^
)
739 ;; Fixme: syntax for symbols &c
743 '("⁅⁆" ; U+2045 U+2046
797 (modify-syntax-entry (aref elt
0) (string ?\
( (aref elt
1)))
798 (modify-syntax-entry (aref elt
1) (string ?\
) (aref elt
0)))))
801 ;; For each character set, put the information of the most proper
802 ;; coding system to encode it by `preferred-coding-system' property.
804 ;; Fixme: should this be junked?
805 (let ((l '((latin-iso8859-1 . iso-latin-1
)
806 (latin-iso8859-2 . iso-latin-2
)
807 (latin-iso8859-3 . iso-latin-3
)
808 (latin-iso8859-4 . iso-latin-4
)
809 (thai-tis620 . thai-tis620
)
810 (greek-iso8859-7 . greek-iso-8bit
)
811 (arabic-iso8859-6 . iso-2022-7bit
)
812 (hebrew-iso8859-8 . hebrew-iso-8bit
)
813 (katakana-jisx0201 . japanese-shift-jis
)
814 (latin-jisx0201 . japanese-shift-jis
)
815 (cyrillic-iso8859-5 . cyrillic-iso-8bit
)
816 (latin-iso8859-9 . iso-latin-5
)
817 (japanese-jisx0208-1978 . iso-2022-jp
)
818 (chinese-gb2312 . chinese-iso-8bit
)
819 (chinese-gbk . chinese-gbk
)
820 (gb18030-2-byte . chinese-gb18030
)
821 (gb18030-4-byte-bmp . chinese-gb18030
)
822 (gb18030-4-byte-smp . chinese-gb18030
)
823 (gb18030-4-byte-ext-1 . chinese-gb18030
)
824 (gb18030-4-byte-ext-2 . chinese-gb18030
)
825 (japanese-jisx0208 . iso-2022-jp
)
826 (korean-ksc5601 . iso-2022-kr
)
827 (japanese-jisx0212 . iso-2022-jp
)
828 (chinese-big5-1 . chinese-big5
)
829 (chinese-big5-2 . chinese-big5
)
830 (chinese-sisheng . iso-2022-7bit
)
831 (ipa . iso-2022-7bit
)
832 (vietnamese-viscii-lower . vietnamese-viscii
)
833 (vietnamese-viscii-upper . vietnamese-viscii
)
834 (arabic-digit . iso-2022-7bit
)
835 (arabic-1-column . iso-2022-7bit
)
837 (arabic-2-column . iso-2022-7bit
)
838 (indian-is13194 . devanagari
)
839 (indian-glyph . devanagari
)
840 (tibetan-1-column . tibetan
)
841 (ethiopic . iso-2022-7bit
)
842 (chinese-cns11643-1 . iso-2022-cn
)
843 (chinese-cns11643-2 . iso-2022-cn
)
844 (chinese-cns11643-3 . iso-2022-cn
)
845 (chinese-cns11643-4 . iso-2022-cn
)
846 (chinese-cns11643-5 . iso-2022-cn
)
847 (chinese-cns11643-6 . iso-2022-cn
)
848 (chinese-cns11643-7 . iso-2022-cn
)
849 (indian-2-column . devanagari
)
851 (latin-iso8859-14 . iso-latin-8
)
852 (latin-iso8859-15 . iso-latin-9
))))
854 (put-charset-property (car (car l
)) 'preferred-coding-system
(cdr (car l
)))
858 ;; Setup auto-fill-chars for charsets that should invoke auto-filling.
859 ;; SPACE and NEWLINE are already set.
861 (set-char-table-range auto-fill-chars
'(#x3041 .
#x30FF
) t
)
862 (set-char-table-range auto-fill-chars
'(#x3400 .
#x4DB5
) t
)
863 (set-char-table-range auto-fill-chars
'(#x4e00 .
#x9fbb
) t
)
864 (set-char-table-range auto-fill-chars
'(#xF900 .
#xFAFF
) t
)
865 (set-char-table-range auto-fill-chars
'(#xFF00 .
#xFF9F
) t
)
866 (set-char-table-range auto-fill-chars
'(#x20000 .
#x2FFFF
) t
)
869 ;;; Setting char-width-table. The default is 1.
871 ;; 0: non-spacing, enclosing combining, formatting, Hangul Jamo medial
872 ;; and final characters.
873 (let ((l '((#x0300 .
#x036F
)
996 (#xE0001 .
#xE01EF
))))
998 (set-char-table-range char-width-table elt
0)))
1000 ;; 2: East Asian Wide and Full-width characters.
1001 (let ((l '((#x1100 .
#x115F
)
1011 (#x30000 .
#x3FFFF
))))
1013 (set-char-table-range char-width-table elt
2)))
1015 ;; Other double width
1016 ;;(map-charset-chars
1017 ;; (lambda (range ignore) (set-char-table-range char-width-table range 2))
1019 ;; (map-charset-chars
1020 ;; (lambda (range ignore) (set-char-table-range char-width-table range 2))
1023 (lambda (range ignore
) (set-char-table-range char-width-table range
2))
1026 (lambda (range ignore
) (set-char-table-range char-width-table range
2))
1029 (defvar cjk-char-width-table
1030 (let ((table (make-char-table nil
)))
1031 (dolist (charset '(big5 chinese-gb2312 chinese-cns11643-1
1032 japanese-jisx0208 korean-ksc5601
))
1033 (map-charset-chars #'(lambda (range arg
)
1034 (set-char-table-range table range
2))
1036 (optimize-char-table table
)
1037 (set-char-table-parent table char-width-table
)
1039 "Character width table used in CJK language environment.")
1041 (defun use-cjk-char-width-table ()
1043 Setup char-width-table appropriate for CJK language environment."
1044 (setq char-width-table cjk-char-width-table
))
1046 (defun use-default-char-width-table ()
1048 Setup char-width-table appropriate for non-CJK language environment."
1049 (setq char-width-table
(char-table-parent cjk-char-width-table
)))
1051 (optimize-char-table (standard-case-table))
1052 (optimize-char-table (standard-category-table))
1053 (optimize-char-table (standard-syntax-table))
1056 ;; Setting char-script-table.
1058 ;; The Unicode blocks actually extend past some of these ranges with
1059 ;; undefined codepoints.
1060 (let ((script-list nil
))
1063 '((#x0000
#x007F latin
)
1064 (#x00A0
#x024F latin
)
1065 (#x0250
#x02AF phonetic
)
1066 (#x02B0
#x036F latin
)
1067 (#x0370
#x03E1 greek
)
1068 (#x03E2
#x03EF coptic
)
1069 (#x03F0
#x03F3 greek
)
1070 (#x0400
#x04FF cyrillic
)
1071 (#x0530
#x058F armenian
)
1072 (#x0590
#x05FF hebrew
)
1073 (#x0600
#x06FF arabic
)
1074 (#x0700
#x074F syriac
)
1076 (#x0780
#x07BF thaana
)
1077 (#x0900
#x097F devanagari
)
1078 (#x0980
#x09FF bengali
)
1079 (#x0A00
#x0A7F gurmukhi
)
1080 (#x0A80
#x0AFF gujarati
)
1081 (#x0B00
#x0B7F oriya
)
1082 (#x0B80
#x0BFF tamil
)
1083 (#x0C00
#x0C7F telugu
)
1084 (#x0C80
#x0CFF kannada
)
1085 (#x0D00
#x0D7F malayalam
)
1086 (#x0D80
#x0DFF sinhala
)
1087 (#x0E00
#x0E5F thai
)
1089 (#x0F00
#x0FFF tibetan
)
1090 (#x1000
#x105F myanmar
)
1091 (#x10A0
#x10FF georgian
)
1092 (#x1100
#x11FF hangul
)
1093 (#x1200
#x139F ethiopic
)
1094 (#x13A0
#x13FF cherokee
)
1095 (#x1400
#x167F canadian-aboriginal
)
1096 (#x1680
#x169F ogham
)
1097 (#x16A0
#x16FF runic
)
1098 (#x1780
#x17FF khmer
)
1099 (#x1800
#x18AF mongolian
)
1100 (#x1D00
#x1DFF phonetic
)
1101 (#x1E00
#x1EFF latin
)
1102 (#x1F00
#x1FFF greek
)
1103 (#x2000
#x27FF symbol
)
1104 (#x2800
#x28FF braille
)
1105 (#x2D80
#x2DDF ethiopic
)
1107 (#x2FF0
#x2FFF ideographic-description
)
1108 (#x3000
#x303F cjk-misc
)
1109 (#x3040
#x30FF kana
)
1110 (#x3100
#x312F bopomofo
)
1111 (#x3130
#x318F hangul
)
1112 (#x3190
#x319F kanbun
)
1113 (#x31A0
#x31BF bopomofo
)
1116 (#xAA00
#xAA5F cham
)
1117 (#xAA80
#xAADF tai-viet
)
1118 (#xAC00
#xD7AF hangul
)
1120 (#xFB1D
#xFB4F hebrew
)
1121 (#xFB50
#xFDFF arabic
)
1122 (#xFE70
#xFEFC arabic
)
1123 (#xFF00
#xFF5F cjk-misc
)
1124 (#xFF61
#xFF9F kana
)
1125 (#xFFE0
#xFFE6 cjk-misc
)
1126 (#x1D000
#x1D0FF byzantine-musical-symbol
)
1127 (#x1D100
#x1D1FF musical-symbol
)
1128 (#x1D400
#x1D7FF mathematical
)
1129 (#x20000
#x2AFFF han
)
1130 (#x2F800
#x2FFFF han
)))
1131 (set-char-table-range char-script-table
1132 (cons (car elt
) (nth 1 elt
)) (nth 2 elt
))
1133 (or (memq (nth 2 elt
) script-list
)
1134 (setq script-list
(cons (nth 2 elt
) script-list
))))
1135 (set-char-table-extra-slot char-script-table
0 (nreverse script-list
)))
1138 #'(lambda (range ignore
)
1139 (set-char-table-range char-script-table range
'tibetan
))
1143 ;;; Setting unicode-category-table.
1145 ;; This macro is to build unicode-category-table at compile time so
1146 ;; that C code can access the table efficiently.
1147 (defmacro build-unicode-category-table
()
1148 (let ((table (make-char-table 'unicode-category-table nil
)))
1149 (dotimes (i #x110000
)
1150 (if (or (< i
#xD800
)
1151 (and (> i
#xF900
) (< i
#x30000
))
1152 (and (> i
#xE0000
) (< i
#xE0200
)))
1153 (aset table i
(get-char-code-property i
'general-category
))))
1154 (set-char-table-range table
'(#xE000 .
#xF8FF
) 'Co
)
1155 (set-char-table-range table
'(#xF0000 .
#xFFFFD
) 'Co
)
1156 (set-char-table-range table
'(#x100000 .
#x10FFFD
) 'Co
)
1157 (optimize-char-table table
'eq
)
1160 (setq unicode-category-table
(build-unicode-category-table))
1163 ;;; Setting word boundary.
1165 (setq word-combining-categories
1171 (setq word-separating-categories
; (2-byte character sets)
1172 '((?H . ?K
) ; Hiragana - Katakana
1179 ;; arch-tag: 85889c35-9f4d-4912-9bf5-82de31b0d42d
1180 ;;; characters.el ends here