1 ;;; characters.el --- set syntax and category for multibyte characters
3 ;; Copyright (C) 1997, 2000-2011 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
9 ;; National Institute of Advanced Industrial Science and Technology (AIST)
10 ;; Registration Number H13PRO009
12 ;; Keywords: multibyte character, character set, syntax, category
14 ;; This file is part of GNU Emacs.
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.
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.
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/>.
33 ;;; Predefined categories.
35 ;; For each character set.
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
47 (define-category ?r
"Roman
49 (define-category ?c
"Chinese")
50 (define-category ?j
"Japanese")
51 (define-category ?h
"Korean")
52 (define-category ?e
"Ethiopic
54 (define-category ?v
"Viet
56 (define-category ?i
"Indian")
57 (define-category ?o
"Lao")
58 (define-category ?q
"Tibetan")
60 ;; For each group (row) of 2-byte character sets.
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")
78 ;; For phonetic classifications.
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
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")
97 (define-category ?|
"line breakable
98 While filling, we can break a line at this character.")
100 ;; For indentation calculation.
103 This character counts as a space for indentation purposes.")
105 ;; Keep the following for `kinsoku' processing. See comments in
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.")
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)")
118 ;;; Setting syntax and category.
122 ;; All ASCII characters have the category `a' (ASCII) and `l' (Latin).
123 (modify-category-entry '(32 .
127) ?a
)
124 (modify-category-entry '(32 .
127) ?l
)
126 ;; Deal with the CJK charsets first. Since the syntax of blocks is
127 ;; defined per charset, and the charsets may contain e.g. Latin
128 ;; characters, we end up with the wrong syntax definitions if we're
131 ;; Chinese characters (Unicode)
132 (modify-category-entry '(#x2E80 .
#x312F
) ?|
)
133 (modify-category-entry '(#x3190 .
#x33FF
) ?|
)
134 (modify-category-entry '(#x3400 .
#x4DBF
) ?C
)
135 (modify-category-entry '(#x4E00 .
#x9FAF
) ?C
)
136 (modify-category-entry '(#x3400 .
#x9FAF
) ?c
)
137 (modify-category-entry '(#x3400 .
#x9FAF
) ?|
)
138 (modify-category-entry '(#xF900 .
#xFAFF
) ?C
)
139 (modify-category-entry '(#xF900 .
#xFAFF
) ?c
)
140 (modify-category-entry '(#xF900 .
#xFAFF
) ?|
)
141 (modify-category-entry '(#x20000 .
#x2FFFF
) ?|
)
142 (modify-category-entry '(#x20000 .
#x2FFFF
) ?C
)
143 (modify-category-entry '(#x20000 .
#x2FFFF
) ?c
)
146 ;; Chinese character set (GB2312)
148 (map-charset-chars #'modify-syntax-entry
'chinese-gb2312
"_" #x2121
#x217E
)
149 (map-charset-chars #'modify-syntax-entry
'chinese-gb2312
"_" #x2221
#x227E
)
150 (map-charset-chars #'modify-syntax-entry
'chinese-gb2312
"_" #x2921
#x297E
)
152 (map-charset-chars #'modify-category-entry
'chinese-gb2312 ?c
)
153 (map-charset-chars #'modify-category-entry
'chinese-gb2312 ?A
#x2330
#x2339
)
154 (map-charset-chars #'modify-category-entry
'chinese-gb2312 ?A
#x2341
#x235A
)
155 (map-charset-chars #'modify-category-entry
'chinese-gb2312 ?A
#x2361
#x237A
)
156 (map-charset-chars #'modify-category-entry
'chinese-gb2312 ?H
#x2421
#x247E
)
157 (map-charset-chars #'modify-category-entry
'chinese-gb2312 ?K
#x2521
#x257E
)
158 (map-charset-chars #'modify-category-entry
'chinese-gb2312 ?G
#x2621
#x267E
)
159 (map-charset-chars #'modify-category-entry
'chinese-gb2312 ?Y
#x2721
#x277E
)
160 (map-charset-chars #'modify-category-entry
'chinese-gb2312 ?C
#x3021
#x7E7E
)
162 ;; Chinese character set (BIG5)
164 (map-charset-chars #'modify-category-entry
'big5 ?c
)
165 (map-charset-chars #'modify-category-entry
'big5 ?C
#xA259
#xA261
)
166 (map-charset-chars #'modify-category-entry
'big5 ?C
#xA440
#xC67E
)
167 (map-charset-chars #'modify-category-entry
'big5 ?C
#xC940
#xF9DC
)
169 ;; Chinese character set (CNS11643)
171 (dolist (c '(chinese-cns11643-1 chinese-cns11643-2 chinese-cns11643-3
172 chinese-cns11643-4 chinese-cns11643-5 chinese-cns11643-6
174 (map-charset-chars #'modify-category-entry c ?c
)
175 (if (eq c
'chinese-cns11643-1
)
176 (map-charset-chars #'modify-category-entry c ?C
#x4421
#x7E7E
)
177 (map-charset-chars #'modify-category-entry c ?C
)))
179 ;; Japanese character set (JISX0201, JISX0208, JISX0212, JISX0213)
181 (map-charset-chars #'modify-category-entry
'katakana-jisx0201 ?k
)
183 (map-charset-chars #'modify-category-entry
'latin-jisx0201 ?r
)
185 (dolist (l '(katakana-jisx0201 japanese-jisx0208 japanese-jisx0212
186 japanese-jisx0213-1 japanese-jisx0213-2
188 (map-charset-chars #'modify-category-entry l ?j
))
190 ;; Fullwidth characters
191 (modify-category-entry '(#xff01 .
#xff60
) ?\|
)
193 ;; Unicode equivalents of JISX0201-kana
194 (let ((range '(#xff61 .
#xff9f
)))
195 (modify-category-entry range ?k
)
196 (modify-category-entry range ?j
)
197 (modify-category-entry range ?\|
))
200 (modify-category-entry '(#x3099 .
#x309C
) ?K
)
201 (modify-category-entry '(#x30A0 .
#x30FF
) ?K
)
202 (modify-category-entry '(#x31F0 .
#x31FF
) ?K
)
203 (modify-category-entry '(#x30A0 .
#x30FA
) ?\|
)
204 (modify-category-entry #x30FF ?\|
)
207 (modify-category-entry '(#x3040 .
#x309F
) ?H
)
208 (modify-category-entry '(#x3040 .
#x3096
) ?\|
)
209 (modify-category-entry #x309F ?\|
)
210 (modify-category-entry #x30A0 ?H
)
211 (modify-category-entry #x30FC ?H
)
215 (map-charset-chars #'modify-syntax-entry
'japanese-jisx0208
"_" #x2121
#x227E
)
216 (map-charset-chars #'modify-syntax-entry
'japanese-jisx0208
"_" #x2821
#x287E
)
217 (let ((chars '(?ー ?゛ ?゜ ?ヽ ?ヾ ?ゝ ?ゞ ?〃 ?仝 ?々 ?〆 ?〇
)))
219 (modify-syntax-entry (car chars
) "w")))
221 (map-charset-chars #'modify-category-entry
'japanese-jisx0208 ?A
#x2321
#x237E
)
222 (map-charset-chars #'modify-category-entry
'japanese-jisx0208 ?H
#x2421
#x247E
)
223 (map-charset-chars #'modify-category-entry
'japanese-jisx0208 ?K
#x2521
#x257E
)
224 (map-charset-chars #'modify-category-entry
'japanese-jisx0208 ?G
#x2621
#x267E
)
225 (map-charset-chars #'modify-category-entry
'japanese-jisx0208 ?Y
#x2721
#x277E
)
226 (map-charset-chars #'modify-category-entry
'japanese-jisx0208 ?C
#x3021
#x7E7E
)
227 (modify-category-entry ?ー ?K
)
228 (let ((chars '(?゛ ?゜
)))
230 (modify-category-entry (car chars
) ?K
)
231 (modify-category-entry (car chars
) ?H
)
232 (setq chars
(cdr chars
))))
233 (let ((chars '(?仝 ?々 ?〆 ?〇
)))
235 (modify-category-entry (car chars
) ?C
)
236 (setq chars
(cdr chars
))))
240 (map-charset-chars #'modify-syntax-entry
'japanese-jisx0212
"_" #x2121
#x237E
)
244 (let ((chars '(?。 ?、 ?・
)))
246 (modify-syntax-entry (car chars
) ".")
247 (setq chars
(cdr chars
))))
249 (modify-syntax-entry ?\「
"(」")
250 (modify-syntax-entry ?\」
"(「")
252 ;; Korean character set (KSC5601)
254 (map-charset-chars #'modify-category-entry
'korean-ksc5601 ?h
)
256 (map-charset-chars #'modify-syntax-entry
'korean-ksc5601
"_" #x2121
#x227E
)
257 (map-charset-chars #'modify-syntax-entry
'korean-ksc5601
"_" #x2621
#x277E
)
258 (map-charset-chars #'modify-syntax-entry
'korean-ksc5601
"_" #x2830
#x287E
)
259 (map-charset-chars #'modify-syntax-entry
'korean-ksc5601
"_" #x2930
#x297E
)
260 (map-charset-chars #'modify-category-entry
'korean-ksc5601 ?A
#x2330
#x2339
)
261 (map-charset-chars #'modify-category-entry
'korean-ksc5601 ?A
#x2341
#x235A
)
262 (map-charset-chars #'modify-category-entry
'korean-ksc5601 ?A
#x2361
#x237A
)
263 (map-charset-chars #'modify-category-entry
'korean-ksc5601 ?G
#x2521
#x257E
)
264 (map-charset-chars #'modify-category-entry
'korean-ksc5601 ?H
#x2A21
#x2A7E
)
265 (map-charset-chars #'modify-category-entry
'korean-ksc5601 ?K
#x2B21
#x2B7E
)
266 (map-charset-chars #'modify-category-entry
'korean-ksc5601 ?Y
#x2C21
#x2C7E
)
268 ;; These are in more than one charset.
269 (let ((parens (concat "〈〉《》「」『』【】〔〕〖〗〘〙〚〛"
273 (dotimes (i (/ (length parens
) 2))
274 (setq open
(aref parens
(* i
2))
275 close
(aref parens
(1+ (* i
2))))
276 (modify-syntax-entry open
(format "(%c" close
))
277 (modify-syntax-entry close
(format ")%c" open
))))
279 ;; Arabic character set
281 (let ((charsets '(arabic-iso8859-6
286 (map-charset-chars #'modify-category-entry
(car charsets
) ?b
)
287 (setq charsets
(cdr charsets
))))
288 (modify-category-entry '(#x600 .
#x6ff
) ?b
)
289 (modify-category-entry '(#xfb50 .
#xfdff
) ?b
)
290 (modify-category-entry '(#xfe70 .
#xfefe
) ?b
)
292 ;; Cyrillic character set (ISO-8859-5)
294 (modify-syntax-entry ?№
".")
296 ;; Ethiopic character set
298 (modify-category-entry '(#x1200 .
#x1399
) ?e
)
299 (modify-category-entry '(#x2d80 .
#x2dde
) ?e
)
300 (let ((chars '(?፡ ?። ?፣ ?፤ ?፥ ?፦ ?፧ ?፨
)))
302 (modify-syntax-entry (car chars
) ".")
303 (setq chars
(cdr chars
))))
304 (map-charset-chars #'modify-category-entry
'ethiopic ?e
)
306 ;; Hebrew character set (ISO-8859-8)
308 (modify-syntax-entry #x5be
".") ; MAQAF
309 (modify-syntax-entry #x5c0
".") ; PASEQ
310 (modify-syntax-entry #x5c3
".") ; SOF PASUQ
311 (modify-syntax-entry #x5f3
".") ; GERESH
312 (modify-syntax-entry #x5f4
".") ; GERSHAYIM
314 ;; Indian character set (IS 13194 and other Emacs original Indian charsets)
316 (modify-category-entry '(#x901 .
#x970
) ?i
)
317 (map-charset-chars #'modify-category-entry
'indian-is13194 ?i
)
318 (map-charset-chars #'modify-category-entry
'indian-2-column ?i
)
322 (modify-category-entry '(#xe80 .
#xeff
) ?o
)
323 (map-charset-chars #'modify-category-entry
'lao ?o
)
325 (let ((deflist '(("ກ-ຮ" "w" ?
0) ; consonant
326 ("ະາຳຽເ-ໄ" "w" ?
1) ; vowel base
327 ("ັິ-ືົໍ" "w" ?
2) ; vowel upper
328 ("ຸູ" "w" ?
3) ; vowel lower
329 ("່-໋" "w" ?
4) ; tone mark
330 ("ຼຽ" "w" ?
9) ; semivowel lower
331 ("໐-໙" "w" ?
6) ; digit
332 ("ຯໆ" "_" ?
5) ; symbol
334 elm chars len syntax category to ch i
)
336 (setq elm
(car deflist
))
337 (setq chars
(car elm
)
343 (if (= (aref chars i
) ?-
)
346 (setq ch
(aref chars i
)
349 (unless (string-equal syntax
"w")
350 (modify-syntax-entry ch syntax
))
351 (modify-category-entry ch category
)
354 (setq deflist
(cdr deflist
))))
356 ;; Thai character set (TIS620)
358 (modify-category-entry '(#xe00 .
#xe7f
) ?t
)
359 (map-charset-chars #'modify-category-entry
'thai-tis620 ?t
)
361 (let ((deflist '(;; chars syntax category
362 ("ก-รลว-ฮ" "w" ?
0) ; consonant
363 ("ฤฦะาำเ-ๅ" "w" ?
1) ; vowel base
364 ("ัิ-ื็๎" "w" ?
2) ; vowel upper
365 ("ุ-ฺ" "w" ?
3) ; vowel lower
366 ("่-ํ" "w" ?
4) ; tone mark
367 ("๐-๙" "w" ?
6) ; digit
368 ("ฯๆ฿๏๚๛" "_" ?
5) ; symbol
370 elm chars len syntax category to ch i
)
372 (setq elm
(car deflist
))
373 (setq chars
(car elm
)
379 (if (= (aref chars i
) ?-
)
382 (setq ch
(aref chars i
)
385 (unless (string-equal syntax
"w")
386 (modify-syntax-entry ch syntax
))
387 (modify-category-entry ch category
)
390 (setq deflist
(cdr deflist
))))
392 ;; Tibetan character set
394 (modify-category-entry '(#xf00 .
#xfff
) ?q
)
395 (map-charset-chars #'modify-category-entry
'tibetan ?q
)
396 (map-charset-chars #'modify-category-entry
'tibetan-1-column ?q
)
398 (let ((deflist '(;; chars syntax category
399 ("ཀ-ཀྵཪ" "w" ?
0) ; consonant
401 ("ིེཻོཽྀ" "w" ?
2) ; upper vowel
402 ("ཾྂྃ྆྇ྈྉྊྋ" "w" ?
2) ; upper modifier
403 ("྄ཱུ༙༵༷" "w" ?
3) ; lowel vowel/modifier
404 ("" "w" ?
3) ; invisible vowel a
405 ("༠-༩༪-༳" "w" ?
6) ; digit
406 ("་།-༒༔ཿ" "." ?|
) ; line-break char
408 ("༈་།-༒༔ཿ༽༴" "." ?
>) ; prohibition
410 ("ༀ-༊༼࿁࿂྅" "." ?
<) ; prohibition
411 ("༓༕-༘༚-༟༶༸-༻༾༿྾྿-࿏" "." ?q
) ; others
413 elm chars len syntax category to ch i
)
415 (setq elm
(car deflist
))
416 (setq chars
(car elm
)
422 (if (= (aref chars i
) ?-
)
425 (setq ch
(aref chars i
)
428 (unless (string-equal syntax
"w")
429 (modify-syntax-entry ch syntax
))
430 (modify-category-entry ch category
)
433 (setq deflist
(cdr deflist
))))
435 ;; Vietnamese character set
437 ;; To make a word with Latin characters
438 (map-charset-chars #'modify-category-entry
'vietnamese-viscii-lower ?l
)
439 (map-charset-chars #'modify-category-entry
'vietnamese-viscii-lower ?v
)
441 (map-charset-chars #'modify-category-entry
'vietnamese-viscii-upper ?l
)
442 (map-charset-chars #'modify-category-entry
'vietnamese-viscii-upper ?v
)
444 (let ((tbl (standard-case-table))
447 (let* ((char (decode-char 'vietnamese-viscii-upper i
))
448 (charl (decode-char 'vietnamese-viscii-lower i
))
449 (uc (encode-char char
'ucs
))
450 (lc (encode-char charl
'ucs
)))
451 (set-case-syntax-pair char
(decode-char 'vietnamese-viscii-lower i
)
453 (if uc
(modify-category-entry uc ?v
))
454 (if lc
(modify-category-entry lc ?v
)))
458 (let ((deflist '(;; chars syntax category
459 ((?ꪀ. ?ꪯ
) "w" ?
0) ; cosonant
460 ("ꪱꪵꪶ" "w" ?
1) ; vowel base
461 ((?ꪹ . ?ꪽ
) "w" ?
1) ; vowel base
462 ("ꪰꪲꪳꪷꪸꪾ" "w" ?
2) ; vowel upper
463 ("ꪴ" "w" ?
3) ; vowel lower
464 ("ꫀꫂ" "w" ?
1) ; non-combining tone-mark
465 ("꪿꫁" "w" ?
4) ; combining tone-mark
466 ((?ꫛ . ?꫟
) "_" ?
5) ; symbol
468 (dolist (elm deflist
)
469 (let ((chars (car elm
))
471 (category (nth 2 elm
)))
474 (modify-syntax-entry chars syntax
)
475 (modify-category-entry chars category
))
477 (modify-syntax-entry x syntax
)
478 (modify-category-entry x category
))
483 (modify-category-entry '(#x80 .
#x024F
) ?l
)
485 (let ((tbl (standard-case-table)) c
)
489 ;; Fixme: Some of the non-word syntaxes here perhaps should be
490 ;; reviewed. (Note that the following all implicitly have word
491 ;; syntax: ¢£¤¥¨ª¯²³´¶¸¹º.) There should be a well-defined way of
492 ;; relating Unicode categories to Emacs syntax codes.
494 ;; NBSP isn't semantically interchangeable with other whitespace chars,
495 ;; so it's more like punctation.
496 (set-case-syntax ?
"." tbl
)
497 (set-case-syntax ?¡
"." tbl
)
498 (set-case-syntax ?¦
"_" tbl
)
499 (set-case-syntax ?§
"." tbl
)
500 (set-case-syntax ?©
"_" tbl
)
501 (set-case-syntax-delims 171 187 tbl
) ; « »
502 (set-case-syntax ?¬
"_" tbl
)
503 (set-case-syntax ?
"_" tbl
)
504 (set-case-syntax ?®
"_" tbl
)
505 (set-case-syntax ?°
"_" tbl
)
506 (set-case-syntax ?±
"_" tbl
)
507 (set-case-syntax ?µ
"_" tbl
)
508 (set-case-syntax ?·
"_" tbl
)
509 (set-case-syntax ?¼
"_" tbl
)
510 (set-case-syntax ?½
"_" tbl
)
511 (set-case-syntax ?¾
"_" tbl
)
512 (set-case-syntax ?¿
"." tbl
)
515 (set-case-syntax-pair c
(+ c
32) tbl
)
517 (set-case-syntax ?×
"_" tbl
)
518 (set-case-syntax ?ß
"w" tbl
)
519 (set-case-syntax ?÷
"_" tbl
)
522 ;; Latin Extended-A, Latin Extended-B
525 (modify-category-entry c ?l
)
528 (let ((pair-ranges '((#x0100 .
#x012F
)
552 (dolist (elt pair-ranges
)
553 (let ((from (car elt
)) (to (cdr elt
)))
555 (set-case-syntax-pair from
(1+ from
) tbl
)
556 (setq from
(+ from
2))))))
558 (set-case-syntax-pair #x189
#x256 tbl
)
559 (set-case-syntax-pair #x18A
#x257 tbl
)
561 ;; In some languages, such as Turkish, U+0049 LATIN CAPITAL LETTER I
562 ;; and U+0131 LATIN SMALL LETTER DOTLESS I make a case pair, and so
563 ;; do U+0130 LATIN CAPITAL LETTER I WITH DOT ABOVE and U+0069 LATIN
566 ;; We used to set up half of those correspondence unconditionally,
567 ;; but that makes searches slow. So now we don't set up either half
568 ;; of these correspondences by default.
570 ;; (set-downcase-syntax ?İ ?i tbl)
571 ;; (set-upcase-syntax ?I ?ı tbl)
573 (set-case-syntax-pair ?DŽ ?dž tbl
)
574 (set-case-syntax-pair ?Dž ?dž tbl
)
575 (set-case-syntax-pair ?LJ ?lj tbl
)
576 (set-case-syntax-pair ?Lj ?lj tbl
)
577 (set-case-syntax-pair ?NJ ?nj tbl
)
578 (set-case-syntax-pair ?Nj ?nj tbl
)
580 ;; 01F0; F; 006A 030C; # LATIN SMALL LETTER J WITH CARON
581 (set-case-syntax-pair ?DZ ?dz tbl
)
582 (set-case-syntax-pair ?Dz ?dz tbl
)
583 (set-case-syntax-pair ?Ƕ ?ƕ tbl
)
584 (set-case-syntax-pair ?Ƿ ?ƿ tbl
)
586 ;; Latin Extended Additional
587 (modify-category-entry '(#x1e00 .
#x1ef9
) ?l
)
591 (or (<= c
#x1e94
) (>= c
#x1ea0
))
592 (set-case-syntax-pair c
(1+ c
) tbl
))
596 (modify-category-entry '(#x0370 .
#x03ff
) ?g
)
599 (if (or (and (>= c
#x0391
) (<= c
#x03a1
))
600 (and (>= c
#x03a3
) (<= c
#x03ab
)))
601 (set-case-syntax-pair c
(+ c
32) tbl
))
605 (set-case-syntax-pair c
(1+ c
) tbl
))
607 (set-case-syntax-pair ?Ά ?ά tbl
)
608 (set-case-syntax-pair ?Έ ?έ tbl
)
609 (set-case-syntax-pair ?Ή ?ή tbl
)
610 (set-case-syntax-pair ?Ί ?ί tbl
)
611 (set-case-syntax-pair ?Ό ?ό tbl
)
612 (set-case-syntax-pair ?Ύ ?ύ tbl
)
613 (set-case-syntax-pair ?Ώ ?ώ tbl
)
618 (set-case-syntax-pair c
(+ c
#x30
) tbl
)
622 (modify-category-entry '(#x1f00 .
#x1fff
) ?g
)
625 (and (<= (logand c
#x000f
) 7)
627 (not (memq c
'(#x1f16
#x1f17
#x1f56
#x1f57
628 #x1f50
#x1f52
#x1f54
#x1f56
)))
629 (/= (logand c
#x00f0
) #x70
)
630 (set-case-syntax-pair (+ c
8) c tbl
))
632 (set-case-syntax-pair ?Ᾰ ?ᾰ tbl
)
633 (set-case-syntax-pair ?Ᾱ ?ᾱ tbl
)
634 (set-case-syntax-pair ?Ὰ ?ὰ tbl
)
635 (set-case-syntax-pair ?Ά ?ά tbl
)
636 (set-case-syntax-pair ?ᾼ ?ᾳ tbl
)
637 (set-case-syntax-pair ?Ὲ ?ὲ tbl
)
638 (set-case-syntax-pair ?Έ ?έ tbl
)
639 (set-case-syntax-pair ?Ὴ ?ὴ tbl
)
640 (set-case-syntax-pair ?Ή ?ή tbl
)
641 (set-case-syntax-pair ?ῌ ?ῃ tbl
)
642 (set-case-syntax-pair ?Ῐ ?ῐ tbl
)
643 (set-case-syntax-pair ?Ῑ ?ῑ tbl
)
644 (set-case-syntax-pair ?Ὶ ?ὶ tbl
)
645 (set-case-syntax-pair ?Ί ?ί tbl
)
646 (set-case-syntax-pair ?Ῠ ?ῠ tbl
)
647 (set-case-syntax-pair ?Ῡ ?ῡ tbl
)
648 (set-case-syntax-pair ?Ὺ ?ὺ tbl
)
649 (set-case-syntax-pair ?Ύ ?ύ tbl
)
650 (set-case-syntax-pair ?Ῥ ?ῥ tbl
)
651 (set-case-syntax-pair ?Ὸ ?ὸ tbl
)
652 (set-case-syntax-pair ?Ό ?ό tbl
)
653 (set-case-syntax-pair ?Ὼ ?ὼ tbl
)
654 (set-case-syntax-pair ?Ώ ?ώ tbl
)
655 (set-case-syntax-pair ?ῼ ?ῳ tbl
)
658 (modify-category-entry '(#x0400 .
#x04FF
) ?y
)
663 (set-case-syntax-pair c
(+ c
80) tbl
))
666 (set-case-syntax-pair c
(+ c
32) tbl
))
668 (or (and (>= c
#x0460
) (<= c
#x0480
))
669 (and (>= c
#x048c
) (<= c
#x04be
))
670 (and (>= c
#x04d0
) (<= c
#x04f4
)))
671 (set-case-syntax-pair c
(1+ c
) tbl
))
673 (set-case-syntax-pair ?Ӂ ?ӂ tbl
)
674 (set-case-syntax-pair ?Ӄ ?ӄ tbl
)
675 (set-case-syntax-pair ?Ӈ ?ӈ tbl
)
676 (set-case-syntax-pair ?Ӌ ?ӌ tbl
)
677 (set-case-syntax-pair ?Ӹ ?ӹ tbl
)
679 ;; general punctuation
682 (set-case-syntax c
" " tbl
)
685 (set-case-syntax c
"." tbl
)
687 ;; Fixme: These aren't all right:
690 (set-case-syntax c
"_" tbl
)
692 ;; Punctuation syntax for quotation marks (like `)
694 (set-case-syntax c
"." tbl
)
696 ;; Fixme: These aren't all right:
698 (set-case-syntax c
"_" tbl
)
701 (set-case-syntax c
"." tbl
)
707 (set-case-syntax-pair c
(+ c
#x10
) tbl
)
710 ;; Fixme: The following blocks might be better as symbol rather than
715 (set-case-syntax c
"." tbl
)
717 ;; Mathematical Operators
719 (set-case-syntax c
"." tbl
)
721 ;; Miscellaneous Technical
723 (set-case-syntax c
"." tbl
)
727 (set-case-syntax c
"_" tbl
)
733 (set-case-syntax-pair c
(+ c
26) tbl
)
734 (modify-category-entry c ?l
)
735 (modify-category-entry (+ c
26) ?l
)
741 (set-case-syntax-pair c
(+ c
#x20
) tbl
)
742 (modify-category-entry c ?l
)
743 (modify-category-entry (+ c
#x20
) ?l
)
746 ;; Combining diacritics
747 (modify-category-entry '(#x300 .
#x362
) ?^
)
749 (modify-category-entry '(#x20d0 .
#x20e3
) ?^
)
751 ;; Fixme: syntax for symbols &c
755 '("⁅⁆" ; U+2045 U+2046
809 (modify-syntax-entry (aref elt
0) (string ?\
( (aref elt
1)))
810 (modify-syntax-entry (aref elt
1) (string ?\
) (aref elt
0)))))
813 ;; For each character set, put the information of the most proper
814 ;; coding system to encode it by `preferred-coding-system' property.
816 ;; Fixme: should this be junked?
817 (let ((l '((latin-iso8859-1 . iso-latin-1
)
818 (latin-iso8859-2 . iso-latin-2
)
819 (latin-iso8859-3 . iso-latin-3
)
820 (latin-iso8859-4 . iso-latin-4
)
821 (thai-tis620 . thai-tis620
)
822 (greek-iso8859-7 . greek-iso-8bit
)
823 (arabic-iso8859-6 . iso-2022-7bit
)
824 (hebrew-iso8859-8 . hebrew-iso-8bit
)
825 (katakana-jisx0201 . japanese-shift-jis
)
826 (latin-jisx0201 . japanese-shift-jis
)
827 (cyrillic-iso8859-5 . cyrillic-iso-8bit
)
828 (latin-iso8859-9 . iso-latin-5
)
829 (japanese-jisx0208-1978 . iso-2022-jp
)
830 (chinese-gb2312 . chinese-iso-8bit
)
831 (chinese-gbk . chinese-gbk
)
832 (gb18030-2-byte . chinese-gb18030
)
833 (gb18030-4-byte-bmp . chinese-gb18030
)
834 (gb18030-4-byte-smp . chinese-gb18030
)
835 (gb18030-4-byte-ext-1 . chinese-gb18030
)
836 (gb18030-4-byte-ext-2 . chinese-gb18030
)
837 (japanese-jisx0208 . iso-2022-jp
)
838 (korean-ksc5601 . iso-2022-kr
)
839 (japanese-jisx0212 . iso-2022-jp
)
840 (chinese-big5-1 . chinese-big5
)
841 (chinese-big5-2 . chinese-big5
)
842 (chinese-sisheng . iso-2022-7bit
)
843 (ipa . iso-2022-7bit
)
844 (vietnamese-viscii-lower . vietnamese-viscii
)
845 (vietnamese-viscii-upper . vietnamese-viscii
)
846 (arabic-digit . iso-2022-7bit
)
847 (arabic-1-column . iso-2022-7bit
)
849 (arabic-2-column . iso-2022-7bit
)
850 (indian-is13194 . devanagari
)
851 (indian-glyph . devanagari
)
852 (tibetan-1-column . tibetan
)
853 (ethiopic . iso-2022-7bit
)
854 (chinese-cns11643-1 . iso-2022-cn
)
855 (chinese-cns11643-2 . iso-2022-cn
)
856 (chinese-cns11643-3 . iso-2022-cn
)
857 (chinese-cns11643-4 . iso-2022-cn
)
858 (chinese-cns11643-5 . iso-2022-cn
)
859 (chinese-cns11643-6 . iso-2022-cn
)
860 (chinese-cns11643-7 . iso-2022-cn
)
861 (indian-2-column . devanagari
)
863 (latin-iso8859-14 . iso-latin-8
)
864 (latin-iso8859-15 . iso-latin-9
))))
866 (put-charset-property (car (car l
)) 'preferred-coding-system
(cdr (car l
)))
870 ;; Setup auto-fill-chars for charsets that should invoke auto-filling.
871 ;; SPACE and NEWLINE are already set.
873 (set-char-table-range auto-fill-chars
'(#x3041 .
#x30FF
) t
)
874 (set-char-table-range auto-fill-chars
'(#x3400 .
#x4DB5
) t
)
875 (set-char-table-range auto-fill-chars
'(#x4e00 .
#x9fbb
) t
)
876 (set-char-table-range auto-fill-chars
'(#xF900 .
#xFAFF
) t
)
877 (set-char-table-range auto-fill-chars
'(#xFF00 .
#xFF9F
) t
)
878 (set-char-table-range auto-fill-chars
'(#x20000 .
#x2FFFF
) t
)
881 ;;; Setting char-width-table. The default is 1.
883 ;; 0: non-spacing, enclosing combining, formatting, Hangul Jamo medial
884 ;; and final characters.
885 (let ((l '((#x0300 .
#x036F
)
1008 (#xE0001 .
#xE01EF
))))
1010 (set-char-table-range char-width-table elt
0)))
1012 ;; 2: East Asian Wide and Full-width characters.
1013 (let ((l '((#x1100 .
#x115F
)
1023 (#x30000 .
#x3FFFF
))))
1025 (set-char-table-range char-width-table elt
2)))
1027 ;; Other double width
1028 ;;(map-charset-chars
1029 ;; (lambda (range ignore) (set-char-table-range char-width-table range 2))
1031 ;; (map-charset-chars
1032 ;; (lambda (range ignore) (set-char-table-range char-width-table range 2))
1035 (lambda (range ignore
) (set-char-table-range char-width-table range
2))
1038 (lambda (range ignore
) (set-char-table-range char-width-table range
2))
1041 ;; Internal use only.
1042 ;; Alist of locale symbol vs charsets. In a language environment
1043 ;; corresponding to the locale, width of characters in the charsets is
1044 ;; set to 2. Each element has the form:
1045 ;; (LOCALE TABLE (CHARSET (FROM-CODE . TO-CODE) ...) ...)
1046 ;; LOCALE: locale symbol
1047 ;; TABLE: char-table used for char-width-table, initially nil.
1048 ;; CAHRSET: character set
1049 ;; FROM-CODE, TO-CODE: range of code-points in CHARSET
1051 (defvar cjk-char-width-table-list
1052 '((ja_JP nil
(japanese-jisx0208 (#x2121 .
#x287E
))
1053 (cp932-2-byte (#x8140 .
#x879F
)))
1054 (zh_CN nil
(chinese-gb2312 (#x2121 .
#x297E
)))
1055 (zh_HK nil
(big5-hkscs (#xA140 .
#xA3FE
) (#xC6A0 .
#xC8FE
)))
1056 (zh_TW nil
(big5 (#xA140 .
#xA3FE
))
1057 (chinese-cns11643-1 (#x2121 .
#x427E
)))
1058 (ko_KR nil
(korean-ksc5601 (#x2121 .
#x2C7E
)))))
1060 ;; Internal use only.
1061 ;; Setup char-width-table appropriate for a language environment
1062 ;; corresponding to LOCALE-NAME (symbol).
1064 (defun use-cjk-char-width-table (locale-name)
1065 (while (char-table-parent char-width-table
)
1066 (setq char-width-table
(char-table-parent char-width-table
)))
1067 (let ((slot (assq locale-name cjk-char-width-table-list
))
1069 (or slot
(error "Unknown locale for CJK language environment: %s"
1071 (unless (nth 1 slot
)
1072 (let ((table (make-char-table nil
)))
1073 (dolist (charset-info (nthcdr 2 slot
))
1074 (let ((charset (car charset-info
)))
1075 (dolist (code-range (cdr charset-info
))
1076 (map-charset-chars #'(lambda (range arg
)
1077 (set-char-table-range table range
2))
1079 (car code-range
) (cdr code-range
)))))
1080 (optimize-char-table table
)
1081 (set-char-table-parent table char-width-table
)
1082 (setcar (cdr slot
) table
)))
1083 (setq char-width-table
(nth 1 slot
))))
1085 (defun use-default-char-width-table ()
1087 Setup char-width-table appropriate for non-CJK language environment."
1088 (while (char-table-parent char-width-table
)
1089 (setq char-width-table
(char-table-parent char-width-table
))))
1091 (optimize-char-table (standard-case-table))
1092 (optimize-char-table (standard-syntax-table))
1095 ;; Setting char-script-table.
1097 ;; The Unicode blocks actually extend past some of these ranges with
1098 ;; undefined codepoints.
1099 (let ((script-list nil
))
1102 '((#x0000
#x007F latin
)
1103 (#x00A0
#x024F latin
)
1104 (#x0250
#x02AF phonetic
)
1105 (#x02B0
#x036F latin
)
1106 (#x0370
#x03E1 greek
)
1107 (#x03E2
#x03EF coptic
)
1108 (#x03F0
#x03F3 greek
)
1109 (#x0400
#x04FF cyrillic
)
1110 (#x0530
#x058F armenian
)
1111 (#x0590
#x05FF hebrew
)
1112 (#x0600
#x06FF arabic
)
1113 (#x0700
#x074F syriac
)
1115 (#x0780
#x07BF thaana
)
1116 (#x0900
#x097F devanagari
)
1117 (#x0980
#x09FF bengali
)
1118 (#x0A00
#x0A7F gurmukhi
)
1119 (#x0A80
#x0AFF gujarati
)
1120 (#x0B00
#x0B7F oriya
)
1121 (#x0B80
#x0BFF tamil
)
1122 (#x0C00
#x0C7F telugu
)
1123 (#x0C80
#x0CFF kannada
)
1124 (#x0D00
#x0D7F malayalam
)
1125 (#x0D80
#x0DFF sinhala
)
1126 (#x0E00
#x0E5F thai
)
1128 (#x0F00
#x0FFF tibetan
)
1129 (#x1000
#x109F burmese
)
1130 (#x10A0
#x10FF georgian
)
1131 (#x1100
#x11FF hangul
)
1132 (#x1200
#x139F ethiopic
)
1133 (#x13A0
#x13FF cherokee
)
1134 (#x1400
#x167F canadian-aboriginal
)
1135 (#x1680
#x169F ogham
)
1136 (#x16A0
#x16FF runic
)
1137 (#x1780
#x17FF khmer
)
1138 (#x1800
#x18AF mongolian
)
1139 (#x1D00
#x1DFF phonetic
)
1140 (#x1E00
#x1EFF latin
)
1141 (#x1F00
#x1FFF greek
)
1142 (#x2000
#x27FF symbol
)
1143 (#x2800
#x28FF braille
)
1144 (#x2D80
#x2DDF ethiopic
)
1146 (#x2FF0
#x2FFF ideographic-description
)
1147 (#x3000
#x303F cjk-misc
)
1148 (#x3040
#x30FF kana
)
1149 (#x3100
#x312F bopomofo
)
1150 (#x3130
#x318F hangul
)
1151 (#x3190
#x319F kanbun
)
1152 (#x31A0
#x31BF bopomofo
)
1155 (#xAA00
#xAA5F cham
)
1156 (#xAA60
#xAA7B burmese
)
1157 (#xAA80
#xAADF tai-viet
)
1158 (#xAC00
#xD7AF hangul
)
1160 (#xFB1D
#xFB4F hebrew
)
1161 (#xFB50
#xFDFF arabic
)
1162 (#xFE70
#xFEFC arabic
)
1163 (#xFF00
#xFF5F cjk-misc
)
1164 (#xFF61
#xFF9F kana
)
1165 (#xFFE0
#xFFE6 cjk-misc
)
1166 (#x10000
#x100FF linear-b
)
1167 (#x10100
#x1013F aegean-number
)
1168 (#x10140
#x1018A ancient-greek-number
)
1169 (#x10190
#x1019B ancient-symbol
)
1170 (#x101D0
#x101FF phaistos-disc
)
1171 (#x10280
#x1029F lycian
)
1172 (#x102A0
#x102DF carian
)
1173 (#x10300
#x1032F olt-italic
)
1174 (#x10380
#x1039F ugaritic
)
1175 (#x103A0
#x103DF old-persian
)
1176 (#x10400
#x1044F deseret
)
1177 (#x10450
#x1047F shavian
)
1178 (#x10480
#x104AF osmanya
)
1179 (#x10800
#x1083F cypriot-syllabary
)
1180 (#x10900
#x1091F phoenician
)
1181 (#x10920
#x1093F lydian
)
1182 (#x10A00
#x10A5F kharoshthi
)
1183 (#x12000
#x123FF cuneiform
)
1184 (#x12400
#x1247F cuneiform-numbers-and-punctuation
)
1185 (#x1D000
#x1D0FF byzantine-musical-symbol
)
1186 (#x1D100
#x1D1FF musical-symbol
)
1187 (#x1D200
#x1D24F ancient-greek-musical-notation
)
1188 (#x1D300
#x1D35F tai-xuan-jing-symbol
)
1189 (#x1D360
#x1D37F counting-rod-numeral
)
1190 (#x1D400
#x1D7FF mathematical
)
1191 (#x1F000
#x1F02F mahjong-tile
)
1192 (#x1F030
#x1F09F domino-tile
)
1193 (#x20000
#x2AFFF han
)
1194 (#x2F800
#x2FFFF han
)))
1195 (set-char-table-range char-script-table
1196 (cons (car elt
) (nth 1 elt
)) (nth 2 elt
))
1197 (or (memq (nth 2 elt
) script-list
)
1198 (setq script-list
(cons (nth 2 elt
) script-list
))))
1199 (set-char-table-extra-slot char-script-table
0 (nreverse script-list
)))
1202 #'(lambda (range ignore
)
1203 (set-char-table-range char-script-table range
'tibetan
))
1207 ;;; Setting unicode-category-table.
1209 (setq unicode-category-table
1210 (unicode-property-table-internal 'general-category
))
1211 (map-char-table #'(lambda (key val
)
1213 (or (and (/= (aref (symbol-name val
) 0) ?M
)
1214 (/= (aref (symbol-name val
) 0) ?C
))
1216 (modify-category-entry key ?.
)))
1217 unicode-category-table
)
1219 (optimize-char-table (standard-category-table))
1222 ;; Display of glyphless characters.
1224 (defvar char-acronym-table
1225 (make-char-table 'char-acronym-table nil
)
1226 "Char table of acronyms for non-graphic characters.")
1228 (let ((c0-acronyms '("NUL" "SOH" "STX" "ETX" "EOT" "ENQ" "ACK" "BEL"
1229 "BS" nil nil
"VT" "FF" "CR" "SO" "SI"
1230 "DLE" "DC1" "DC2" "DC3" "DC4" "NAK" "SYN" "ETB"
1231 "CAN" "EM" "SUB" "ESC" "FC" "GS" "RS" "US")))
1233 (aset char-acronym-table i
(car c0-acronyms
))
1234 (setq c0-acronyms
(cdr c0-acronyms
))))
1236 (let ((c1-acronyms '("XXX" "XXX" "BPH" "NBH" "IND" "NEL" "SSA" "ESA"
1237 "HTS" "HTJ" "VTS" "PLD" "PLU" "R1" "SS2" "SS1"
1238 "DCS" "PU1" "PU2" "STS" "CCH" "MW" "SPA" "EPA"
1239 "SOS" "XXX" "SC1" "CSI" "ST" "OSC" "PM" "APC")))
1241 (aset char-acronym-table
(+ #x0080 i
) (car c1-acronyms
))
1242 (setq c1-acronyms
(cdr c1-acronyms
))))
1244 (aset char-acronym-table
#x17B4
"KIVAQ") ; KHMER VOWEL INHERENT AQ
1245 (aset char-acronym-table
#x17B5
"KIVAA") ; KHMER VOWEL INHERENT AA
1246 (aset char-acronym-table
#x200B
"ZWSP") ; ZERO WIDTH SPACE
1247 (aset char-acronym-table
#x200C
"ZWNJ") ; ZERO WIDTH NON-JOINER
1248 (aset char-acronym-table
#x200D
"ZWJ") ; ZERO WIDTH JOINER
1249 (aset char-acronym-table
#x200E
"LRM") ; LEFT-TO-RIGHT MARK
1250 (aset char-acronym-table
#x200F
"RLM") ; RIGHT-TO-LEFT MARK
1251 (aset char-acronym-table
#x202A
"LRE") ; LEFT-TO-RIGHT EMBEDDING
1252 (aset char-acronym-table
#x202B
"RLE") ; RIGHT-TO-LEFT EMBEDDING
1253 (aset char-acronym-table
#x202C
"PDF") ; POP DIRECTIONAL FORMATTING
1254 (aset char-acronym-table
#x202D
"LRO") ; LEFT-TO-RIGHT OVERRIDE
1255 (aset char-acronym-table
#x202E
"RLO") ; RIGHT-TO-LEFT OVERRIDE
1256 (aset char-acronym-table
#x2060
"WJ") ; WORD JOINER
1257 (aset char-acronym-table
#x206A
"ISS") ; INHIBIT SYMMETRIC SWAPPING
1258 (aset char-acronym-table
#x206B
"ASS") ; ACTIVATE SYMMETRIC SWAPPING
1259 (aset char-acronym-table
#x206C
"IAFS") ; INHIBIT ARABIC FORM SHAPING
1260 (aset char-acronym-table
#x206D
"AAFS") ; ACTIVATE ARABIC FORM SHAPING
1261 (aset char-acronym-table
#x206E
"NADS") ; NATIONAL DIGIT SHAPES
1262 (aset char-acronym-table
#x206F
"NODS") ; NOMINAL DIGIT SHAPES
1263 (aset char-acronym-table
#xFEFF
"ZWNBSP") ; ZERO WIDTH NO-BREAK SPACE
1264 (aset char-acronym-table
#xFFF9
"IAA") ; INTERLINEAR ANNOTATION ANCHOR
1265 (aset char-acronym-table
#xFFFA
"IAS") ; INTERLINEAR ANNOTATION SEPARATOR
1266 (aset char-acronym-table
#xFFFB
"IAT") ; INTERLINEAR ANNOTATION TERMINATOR
1267 (aset char-acronym-table
#x1D173
"BEGBM") ; MUSICAL SYMBOL BEGIN BEAM
1268 (aset char-acronym-table
#x1D174
"ENDBM") ; MUSICAL SYMBOL END BEAM
1269 (aset char-acronym-table
#x1D175
"BEGTIE") ; MUSICAL SYMBOL BEGIN TIE
1270 (aset char-acronym-table
#x1D176
"END") ; MUSICAL SYMBOL END TIE
1271 (aset char-acronym-table
#x1D177
"BEGSLR") ; MUSICAL SYMBOL BEGIN SLUR
1272 (aset char-acronym-table
#x1D178
"ENDSLR") ; MUSICAL SYMBOL END SLUR
1273 (aset char-acronym-table
#x1D179
"BEGPHR") ; MUSICAL SYMBOL BEGIN PHRASE
1274 (aset char-acronym-table
#x1D17A
"ENDPHR") ; MUSICAL SYMBOL END PHRASE
1275 (aset char-acronym-table
#xE0001
"|->TAG") ; LANGUAGE TAG
1276 (aset char-acronym-table
#xE0020
"SP TAG") ; TAG SPACE
1278 (aset char-acronym-table
(+ #xE0021 i
) (format " %c TAG" (+ 33 i
))))
1279 (aset char-acronym-table
#xE007F
"->|TAG") ; CANCEL TAG
1281 (defun update-glyphless-char-display (&optional variable value
)
1282 "Make the setting of `glyphless-char-display-control' take effect.
1283 This function updates the char-table `glyphless-char-display'."
1285 (set-default variable value
))
1287 (let ((target (car elt
))
1289 (or (memq method
'(zero-width thin-space empty-box acronym hex-code
))
1290 (error "Invalid glyphless character display method: %s" method
))
1291 (cond ((eq target
'c0-control
)
1292 (set-char-table-range glyphless-char-display
'(#x00 .
#x1F
)
1294 ;; Users will not expect their newlines and TABs be
1295 ;; displayed as anything but themselves, so exempt those
1296 ;; two characters from c0-control.
1297 (set-char-table-range glyphless-char-display
#x9 nil
)
1298 (set-char-table-range glyphless-char-display
#xa nil
))
1299 ((eq target
'c1-control
)
1300 (set-char-table-range glyphless-char-display
'(#x80 .
#x9F
)
1302 ((eq target
'format-control
)
1304 #'(lambda (char category
)
1305 (if (eq category
'Cf
)
1306 (let ((this-method method
)
1309 (setq from
(car char
) to
(cdr char
))
1310 (setq from char to char
))
1312 (when (/= from
#xAD
)
1313 (if (eq method
'acronym
)
1315 (aref char-acronym-table from
)))
1316 (set-char-table-range glyphless-char-display
1318 (setq from
(1+ from
))))))
1319 unicode-category-table
))
1320 ((eq target
'no-font
)
1321 (set-char-table-extra-slot glyphless-char-display
0 method
))
1323 (error "Invalid glyphless character group: %s" target
))))))
1325 ;;; Control of displaying glyphless characters.
1326 (defcustom glyphless-char-display-control
1327 '((format-control . thin-space
)
1328 (no-font . hex-code
))
1329 "List of directives to control display of glyphless characters.
1331 Each element has the form (GROUP . METHOD), where GROUP is a
1332 symbol specifying the character group, and METHOD is a symbol
1333 specifying the method of displaying characters belonging to that
1336 GROUP must be one of these symbols:
1337 `c0-control': U+0000..U+001F, but excluding newline and TAB.
1338 `c1-control': U+0080..U+009F.
1339 `format-control': Characters of Unicode General Category `Cf',
1340 such as U+200C (ZWNJ), U+200E (LRM), but
1341 excluding characters that have graphic images,
1342 such as U+00AD (SHY).
1343 `no-font': characters for which no suitable font is found.
1344 For character terminals, characters that cannot
1345 be encoded by `terminal-coding-system'.
1347 METHOD must be one of these symbols:
1348 `zero-width': don't display.
1349 `thin-space': display a thin (1-pixel width) space. On character
1350 terminals, display as 1-character space.
1351 `empty-box': display an empty box.
1352 `acronym': display an acronym of the character in a box. The
1353 acronym is taken from `char-acronym-table', which see.
1354 `hex-code': display the hexadecimal character code in a box."
1356 :type
'(alist :key-type
(symbol :tag
"Character Group")
1357 :value-type
(symbol :tag
"Display Method"))
1358 :options
'((c0-control
1359 (choice (const :tag
"Don't display" zero-width
)
1360 (const :tag
"Display as thin space" thin-space
)
1361 (const :tag
"Display as empty box" empty-box
)
1362 (const :tag
"Display acronym" acronym
)
1363 (const :tag
"Display hex code in a box" hex-code
)))
1365 (choice (const :tag
"Don't display" zero-width
)
1366 (const :tag
"Display as thin space" thin-space
)
1367 (const :tag
"Display as empty box" empty-box
)
1368 (const :tag
"Display acronym" acronym
)
1369 (const :tag
"Display hex code in a box" hex-code
)))
1371 (choice (const :tag
"Don't display" zero-width
)
1372 (const :tag
"Display as thin space" thin-space
)
1373 (const :tag
"Display as empty box" empty-box
)
1374 (const :tag
"Display acronym" acronym
)
1375 (const :tag
"Display hex code in a box" hex-code
)))
1377 (choice (const :tag
"Don't display" zero-width
)
1378 (const :tag
"Display as thin space" thin-space
)
1379 (const :tag
"Display as empty box" empty-box
)
1380 (const :tag
"Display acronym" acronym
)
1381 (const :tag
"Display hex code in a box" hex-code
))))
1382 :set
'update-glyphless-char-display
1386 ;;; Setting word boundary.
1388 (setq word-combining-categories
1394 (setq word-separating-categories
; (2-byte character sets)
1395 '((?H . ?K
) ; Hiragana - Katakana
1402 ;;; characters.el ends here