1 ;;; characters.el --- set syntax and category for multibyte characters
3 ;; Copyright (C) 1995, 1997 Electrotechnical Laboratory, JAPAN.
4 ;; Licensed to the Free Software Foundation.
6 ;; Keywords: multibyte character, character set, syntax, category
8 ;; This file is part of GNU Emacs.
10 ;; GNU Emacs is free software; you can redistribute it and/or modify
11 ;; it under the terms of the GNU General Public License as published by
12 ;; the Free Software Foundation; either version 2, or (at your option)
15 ;; GNU Emacs is distributed in the hope that it will be useful,
16 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
17 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
18 ;; GNU General Public License for more details.
20 ;; You should have received a copy of the GNU General Public License
21 ;; along with GNU Emacs; see the file COPYING. If not, write to the
22 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
23 ;; Boston, MA 02111-1307, USA.
27 ;; This file contains multibyte characters. Save this file always in
28 ;; the coding system `iso-2022-7bit'.
30 ;; This file does not define the syntax for Latin-N character sets;
31 ;; those are defined by the files latin-N.el.
33 ;;; Predefined categories.
35 ;; For each character set.
37 (define-category ?a "ASCII")
38 (define-category ?l "Latin")
39 (define-category ?t "Thai")
40 (define-category ?g "Greek")
41 (define-category ?b "Arabic")
42 (define-category ?w "Hebrew")
43 (define-category ?y "Cyrillic")
44 (define-category ?k "Japanese katakana")
45 (define-category ?r "Japanese roman")
46 (define-category ?c "Chinese")
47 (define-category ?j "Japanese")
48 (define-category ?h "Korean")
49 (define-category ?e "Ethiopic (Ge'ez)")
50 (define-category ?v "Vietnamese")
51 (define-category ?i "Indian")
52 (define-category ?o "Lao")
53 (define-category ?q "Tibetan")
55 ;; For each group (row) of 2-byte character sets.
57 (define-category ?A "Alpha-numeric characters of 2-byte character sets")
58 (define-category ?C "Chinese (Han) characters of 2-byte character sets")
59 (define-category ?G "Greek characters of 2-byte character sets")
60 (define-category ?H "Japanese Hiragana characters of 2-byte character sets")
61 (define-category ?K "Japanese Katakana characters of 2-byte character sets")
62 (define-category ?N "Korean Hangul characters of 2-byte character sets")
63 (define-category ?Y "Cyrillic characters of 2-byte character sets")
64 (define-category ?I "Indian Glyphs")
66 ;; For phonetic classifications.
68 (define-category ?0 "consonant")
69 (define-category ?1 "base (independent) vowel")
70 (define-category ?2 "upper diacritical mark (including upper vowel)")
71 (define-category ?3 "lower diacritical mark (including lower vowel)")
72 (define-category ?4 "tone mark")
73 (define-category ?5 "symbol")
74 (define-category ?6 "digit")
75 (define-category ?7 "vowel-modifying diacritical mark")
76 (define-category ?8 "vowel-signs")
77 (define-category ?9 "semivowel lower")
80 (define-category ?| "While filling, we can break a line at this character.")
82 ;; For indentation calculation.
84 "This character counts as a space for indentation purposes.")
86 ;; Keep the following for `kinsoku' processing. See comments in
88 (define-category ?> "A character which can't be placed at beginning of line.")
89 (define-category ?< "A character which can't be placed at end of line.")
92 ;;; Setting syntax and category.
97 (while (< ch 127) ; All ASCII characters have
98 (modify-category-entry ch ?a) ; the category `a' (ASCII)
99 (modify-category-entry ch ?l) ; and `l' (Latin).
102 ;; Arabic character set
104 (let ((charsets '(arabic-iso8859-6
109 (modify-syntax-entry (make-char (car charsets)) "w")
110 (modify-category-entry (make-char (car charsets)) ?b)
111 (setq charsets (cdr charsets))))
113 ;; Chinese character set (GB2312)
115 (modify-syntax-entry (make-char 'chinese-gb2312) "w")
116 (modify-syntax-entry (make-char 'chinese-gb2312 33) "_")
117 (modify-syntax-entry (make-char 'chinese-gb2312 34) "_")
118 (modify-syntax-entry (make-char 'chinese-gb2312 41) "_")
119 (modify-syntax-entry ?\
\e$A!2
\e(B "(
\e$A!3
\e(B")
120 (modify-syntax-entry ?\
\e$A!4
\e(B "(
\e$A!5
\e(B")
121 (modify-syntax-entry ?\
\e$A!6
\e(B "(
\e$A!7
\e(B")
122 (modify-syntax-entry ?\
\e$A!8
\e(B "(
\e$A!9
\e(B")
123 (modify-syntax-entry ?\
\e$A!:
\e(B "(
\e$A!;
\e(B")
124 (modify-syntax-entry ?\
\e$A!<
\e(B "(
\e$A!=
\e(B")
125 (modify-syntax-entry ?\
\e$A!>
\e(B "(
\e$A!?
\e(B")
126 (modify-syntax-entry ?\
\e$A!3
\e(B ")
\e$A!2
\e(B")
127 (modify-syntax-entry ?\
\e$A!5
\e(B ")
\e$A!4
\e(B")
128 (modify-syntax-entry ?\
\e$A!7
\e(B ")
\e$A!6
\e(B")
129 (modify-syntax-entry ?\
\e$A!9
\e(B ")
\e$A!8
\e(B")
130 (modify-syntax-entry ?\
\e$A!;
\e(B ")
\e$A!:
\e(B")
131 (modify-syntax-entry ?\
\e$A!=
\e(B ")
\e$A!<
\e(B")
132 (modify-syntax-entry ?\
\e$A!?
\e(B ")
\e$A!>
\e(B")
134 (modify-category-entry (make-char 'chinese-gb2312) ?c)
135 (modify-category-entry (make-char 'chinese-gb2312) ?\|)
136 (modify-category-entry (make-char 'chinese-gb2312 35) ?A)
137 (modify-category-entry (make-char 'chinese-gb2312 36) ?H)
138 (modify-category-entry (make-char 'chinese-gb2312 37) ?K)
139 (modify-category-entry (make-char 'chinese-gb2312 38) ?G)
140 (modify-category-entry (make-char 'chinese-gb2312 39) ?Y)
143 (modify-category-entry (make-char 'chinese-gb2312 row) ?C)
144 (setq row (1+ row))))
146 ;; Chinese character set (BIG5)
148 (let ((generic-big5-1-char (make-char 'chinese-big5-1))
149 (generic-big5-2-char (make-char 'chinese-big5-2)))
150 (modify-syntax-entry generic-big5-1-char "w")
151 (modify-syntax-entry generic-big5-2-char "w")
153 (modify-category-entry generic-big5-1-char ?c)
154 (modify-category-entry generic-big5-2-char ?c)
156 (modify-category-entry generic-big5-1-char ?C)
157 (modify-category-entry generic-big5-2-char ?C)
159 (modify-category-entry generic-big5-1-char ?\|)
160 (modify-category-entry generic-big5-2-char ?\|))
163 ;; Chinese character set (CNS11643)
165 (let ((cns-list '(chinese-cns11643-1
174 (setq generic-char (make-char (car cns-list)))
175 (modify-syntax-entry generic-char "w")
176 (modify-category-entry generic-char ?c)
177 (modify-category-entry generic-char ?C)
178 (modify-category-entry generic-char ?|)
179 (setq cns-list (cdr cns-list))))
181 ;; Cyrillic character set (ISO-8859-5)
183 (modify-category-entry (make-char 'cyrillic-iso8859-5) ?y)
185 (modify-syntax-entry (make-char 'cyrillic-iso8859-5 160) " ")
186 (modify-syntax-entry ?
\e,L-
\e(B ".")
187 (modify-syntax-entry ?
\e,Lp
\e(B ".")
188 (modify-syntax-entry ?
\e,L}
\e(B ".")
189 (let ((tbl (standard-case-table)))
190 (set-case-syntax-pair ?
\e,L!
\e(B ?
\e,Lq
\e(B tbl)
191 (set-case-syntax-pair ?
\e,L"
\e(B ?
\e,Lr
\e(B tbl)
192 (set-case-syntax-pair ?
\e,L#
\e(B ?
\e,Ls
\e(B tbl)
193 (set-case-syntax-pair ?
\e,L$
\e(B ?
\e,Lt
\e(B tbl)
194 (set-case-syntax-pair ?
\e,L%
\e(B ?
\e,Lu
\e(B tbl)
195 (set-case-syntax-pair ?
\e,L&
\e(B ?
\e,Lv
\e(B tbl)
196 (set-case-syntax-pair ?
\e,L'
\e(B ?
\e,Lw
\e(B tbl)
197 (set-case-syntax-pair ?
\e,L(
\e(B ?
\e,Lx
\e(B tbl)
198 (set-case-syntax-pair ?
\e,L)
\e(B ?
\e,Ly
\e(B tbl)
199 (set-case-syntax-pair ?
\e,L*
\e(B ?
\e,Lz
\e(B tbl)
200 (set-case-syntax-pair ?
\e,L+
\e(B ?
\e,L{
\e(B tbl)
201 (set-case-syntax-pair ?
\e,L,
\e(B ?
\e,L|
\e(B tbl)
202 (set-case-syntax-pair ?
\e,L.
\e(B ?
\e,L~
\e(B tbl)
203 (set-case-syntax-pair ?
\e,L/
\e(B ?
\e,L
\7f\e(B tbl)
204 (set-case-syntax-pair ?
\e,L0
\e(B ?
\e,LP
\e(B tbl)
205 (set-case-syntax-pair ?
\e,L1
\e(B ?
\e,LQ
\e(B tbl)
206 (set-case-syntax-pair ?
\e,L2
\e(B ?
\e,LR
\e(B tbl)
207 (set-case-syntax-pair ?
\e,L3
\e(B ?
\e,LS
\e(B tbl)
208 (set-case-syntax-pair ?
\e,L4
\e(B ?
\e,LT
\e(B tbl)
209 (set-case-syntax-pair ?
\e,L5
\e(B ?
\e,LU
\e(B tbl)
210 (set-case-syntax-pair ?
\e,L6
\e(B ?
\e,LV
\e(B tbl)
211 (set-case-syntax-pair ?
\e,L7
\e(B ?
\e,LW
\e(B tbl)
212 (set-case-syntax-pair ?
\e,L8
\e(B ?
\e,LX
\e(B tbl)
213 (set-case-syntax-pair ?
\e,L9
\e(B ?
\e,LY
\e(B tbl)
214 (set-case-syntax-pair ?
\e,L:
\e(B ?
\e,LZ
\e(B tbl)
215 (set-case-syntax-pair ?
\e,L;
\e(B ?
\e,L[
\e(B tbl)
216 (set-case-syntax-pair ?
\e,L<
\e(B ?
\e,L\
\e(B tbl)
217 (set-case-syntax-pair ?
\e,L=
\e(B ?
\e,L]
\e(B tbl)
218 (set-case-syntax-pair ?
\e,L>
\e(B ?
\e,L^
\e(B tbl)
219 (set-case-syntax-pair ?
\e,L?
\e(B ?
\e,L_
\e(B tbl)
220 (set-case-syntax-pair ?
\e,L@
\e(B ?
\e,L`
\e(B tbl)
221 (set-case-syntax-pair ?
\e,LA
\e(B ?
\e,La
\e(B tbl)
222 (set-case-syntax-pair ?
\e,LB
\e(B ?
\e,Lb
\e(B tbl)
223 (set-case-syntax-pair ?
\e,LC
\e(B ?
\e,Lc
\e(B tbl)
224 (set-case-syntax-pair ?
\e,LD
\e(B ?
\e,Ld
\e(B tbl)
225 (set-case-syntax-pair ?
\e,LE
\e(B ?
\e,Le
\e(B tbl)
226 (set-case-syntax-pair ?
\e,LF
\e(B ?
\e,Lf
\e(B tbl)
227 (set-case-syntax-pair ?
\e,LG
\e(B ?
\e,Lg
\e(B tbl)
228 (set-case-syntax-pair ?
\e,LH
\e(B ?
\e,Lh
\e(B tbl)
229 (set-case-syntax-pair ?
\e,LI
\e(B ?
\e,Li
\e(B tbl)
230 (set-case-syntax-pair ?
\e,LJ
\e(B ?
\e,Lj
\e(B tbl)
231 (set-case-syntax-pair ?
\e,LK
\e(B ?
\e,Lk
\e(B tbl)
232 (set-case-syntax-pair ?
\e,LL
\e(B ?
\e,Ll
\e(B tbl)
233 (set-case-syntax-pair ?
\e,LM
\e(B ?
\e,Lm
\e(B tbl)
234 (set-case-syntax-pair ?
\e,LN
\e(B ?
\e,Ln
\e(B tbl)
235 (set-case-syntax-pair ?
\e,LO
\e(B ?
\e,Lo
\e(B tbl))
237 ;; Devanagari character set
239 (let ((deflist '(;; chars syntax category
240 ("
\e$(5!!!"!#
\e(B" "w" ?7) ; vowel-modifying diacritical mark
241 ; chandrabindu, anuswar, visarga
242 ("
\e$(5!$
\e(B-
\e$(5!2
\e(B" "w" ?1) ; independent vowel
243 ("
\e$(5!3
\e(B-
\e$(5!X
\e(B" "w" ?0) ; consonant
244 ("
\e$(5!Z
\e(B-
\e$(5!g
\e(B" "w" ?8) ; matra
245 ("
\e$(5!q
\e(B-
\e$(5!z
\e(B" "w" ?6) ; digit
247 elm chars len syntax category to ch i)
249 (setq elm (car deflist))
250 (setq chars (car elm)
256 (if (= (aref chars i) ?-)
259 (setq ch (aref chars i)
262 (modify-syntax-entry ch syntax)
263 (modify-category-entry ch category)
266 (setq deflist (cdr deflist))))
268 ;; Ethiopic character set
270 (modify-category-entry (make-char 'ethiopic) ?e)
271 (modify-syntax-entry (make-char 'ethiopic) "w")
272 (let ((chars '(?
\e$(3$h
\e(B ?
\e$(3$i
\e(B ?
\e$(3$j
\e(B ?
\e$(3$k
\e(B ?
\e$(3$l
\e(B ?
\e$(3$m
\e(B ?
\e$(3$n
\e(B ?
\e$(3$o
\e(B ?
\e$(3%i
\e(B ?
\e$(3%t
\e(B ?
\e$(3%u
\e(B ?
\e$(3%v
\e(B ?
\e$(3%w
\e(B ?
\e$(3%x
\e(B)))
274 (modify-syntax-entry (car chars) ".")
275 (setq chars (cdr chars))))
277 ;; Greek character set (ISO-8859-7)
279 (modify-category-entry (make-char 'greek-iso8859-7) ?g)
283 (modify-syntax-entry (make-char 'greek-iso8859-7 c) "w")
285 (modify-syntax-entry (make-char 'greek-iso8859-7 160) "w") ; NBSP
286 (modify-syntax-entry ?
\e,F7
\e(B ".")
287 (modify-syntax-entry ?
\e,F;
\e(B ".")
288 (modify-syntax-entry ?
\e,F=
\e(B ".")
289 (let ((tbl (standard-case-table)))
290 (set-case-syntax-pair ?
\e,FA
\e(B ?
\e,Fa
\e(B tbl)
291 (set-case-syntax-pair ?
\e,FB
\e(B ?
\e,Fb
\e(B tbl)
292 (set-case-syntax-pair ?
\e,FC
\e(B ?
\e,Fc
\e(B tbl)
293 (set-case-syntax-pair ?
\e,FD
\e(B ?
\e,Fd
\e(B tbl)
294 (set-case-syntax-pair ?
\e,FE
\e(B ?
\e,Fe
\e(B tbl)
295 (set-case-syntax-pair ?
\e,FF
\e(B ?
\e,Ff
\e(B tbl)
296 (set-case-syntax-pair ?
\e,FG
\e(B ?
\e,Fg
\e(B tbl)
297 (set-case-syntax-pair ?
\e,FH
\e(B ?
\e,Fh
\e(B tbl)
298 (set-case-syntax-pair ?
\e,FI
\e(B ?
\e,Fi
\e(B tbl)
299 (set-case-syntax-pair ?
\e,FJ
\e(B ?
\e,Fj
\e(B tbl)
300 (set-case-syntax-pair ?
\e,FK
\e(B ?
\e,Fk
\e(B tbl)
301 (set-case-syntax-pair ?
\e,FL
\e(B ?
\e,Fl
\e(B tbl)
302 (set-case-syntax-pair ?
\e,FM
\e(B ?
\e,Fm
\e(B tbl)
303 (set-case-syntax-pair ?
\e,FN
\e(B ?
\e,Fn
\e(B tbl)
304 (set-case-syntax-pair ?
\e,FO
\e(B ?
\e,Fo
\e(B tbl)
305 (set-case-syntax-pair ?
\e,FP
\e(B ?
\e,Fp
\e(B tbl)
306 (set-case-syntax-pair ?
\e,FQ
\e(B ?
\e,Fq
\e(B tbl)
307 (set-case-syntax-pair ?
\e,FS
\e(B ?
\e,Fs
\e(B tbl)
308 (set-case-syntax-pair ?
\e,FT
\e(B ?
\e,Ft
\e(B tbl)
309 (set-case-syntax-pair ?
\e,FU
\e(B ?
\e,Fu
\e(B tbl)
310 (set-case-syntax-pair ?
\e,FV
\e(B ?
\e,Fv
\e(B tbl)
311 (set-case-syntax-pair ?
\e,FW
\e(B ?
\e,Fw
\e(B tbl)
312 (set-case-syntax-pair ?
\e,FX
\e(B ?
\e,Fx
\e(B tbl)
313 (set-case-syntax-pair ?
\e,FY
\e(B ?
\e,Fy
\e(B tbl)
314 (set-case-syntax-pair ?
\e,FZ
\e(B ?
\e,Fz
\e(B tbl)
315 (set-case-syntax-pair ?
\e,F[
\e(B ?
\e,F{
\e(B tbl)
316 (set-case-syntax-pair ?
\e,F?
\e(B ?
\e,F~
\e(B tbl)
317 (set-case-syntax-pair ?
\e,F>
\e(B ?
\e,F}
\e(B tbl)
318 (set-case-syntax-pair ?
\e,F<
\e(B ?
\e,F|
\e(B tbl)
319 (set-case-syntax-pair ?
\e,F6
\e(B ?
\e,F\
\e(B tbl)
320 (set-case-syntax-pair ?
\e,F8
\e(B ?
\e,F]
\e(B tbl)
321 (set-case-syntax-pair ?
\e,F9
\e(B ?
\e,F^
\e(B tbl)
322 (set-case-syntax-pair ?
\e,F:
\e(B ?
\e,F_
\e(B tbl))
324 ;; Hebrew character set (ISO-8859-8)
326 (modify-category-entry (make-char 'hebrew-iso8859-8) ?w)
330 (modify-syntax-entry (make-char 'hebrew-iso8859-8 c) "w")
332 (modify-syntax-entry (make-char 'hebrew-iso8859-8 160) "w") ; NBSP
334 ;; Indian character set (IS 13194 and other Emacs original Indian charsets)
336 (modify-category-entry (make-char 'indian-is13194) ?i)
337 (modify-category-entry (make-char 'indian-2-column) ?I)
338 (modify-category-entry (make-char 'indian-1-column) ?I)
341 '(;; chars syntax category
342 ("
\e(5!"#
\e(B" "w" ?7) ; vowel-modifying diacritical mark
343 ; chandrabindu, anuswar, visarga
344 ("
\e(5$
\e(B-
\e(52
\e(B" "w" ?1) ; base (independent) vowel
345 ("
\e(53
\e(B-
\e(5X
\e(B" "w" ?0) ; consonant
346 ("
\e(5Z
\e(B-
\e(5g
\e(B" "w" ?8) ; matra
347 ("
\e(5q
\e(B-
\e(5z
\e(B" "w" ?6) ; digit
349 elm chars len syntax category to ch i)
351 (setq elm (car deflist))
352 (setq chars (car elm)
358 (if (= (aref chars i) ?-)
361 (setq ch (aref chars i)
364 (modify-syntax-entry ch syntax)
365 (modify-category-entry ch category)
368 (setq deflist (cdr deflist))))
371 ;; Japanese character set (JISX0201-kana, JISX0201-roman, JISX0208, JISX0212)
373 (modify-category-entry (make-char 'katakana-jisx0201) ?k)
374 (modify-category-entry (make-char 'katakana-jisx0201) ?j)
375 (modify-category-entry (make-char 'latin-jisx0201) ?r)
376 (modify-category-entry (make-char 'japanese-jisx0208) ?j)
377 (modify-category-entry (make-char 'japanese-jisx0212) ?j)
378 (modify-category-entry (make-char 'katakana-jisx0201) ?\|)
379 (modify-category-entry (make-char 'japanese-jisx0208) ?\|)
380 (modify-category-entry (make-char 'japanese-jisx0212) ?\|)
383 (modify-syntax-entry (make-char 'japanese-jisx0208) "w")
384 (modify-syntax-entry (make-char 'japanese-jisx0208 33) "_")
385 (modify-syntax-entry (make-char 'japanese-jisx0208 34) "_")
386 (modify-syntax-entry (make-char 'japanese-jisx0208 40) "_")
387 (let ((chars '(?
\e$B!<
\e(B ?
\e$B!+
\e(B ?
\e$B!,
\e(B ?
\e$B!3
\e(B ?
\e$B!4
\e(B ?
\e$B!5
\e(B ?
\e$B!6
\e(B ?
\e$B!7
\e(B ?
\e$B!8
\e(B ?
\e$B!9
\e(B ?
\e$B!:
\e(B ?
\e$B!;
\e(B)))
389 (modify-syntax-entry (car chars) "w")
390 (setq chars (cdr chars))))
391 (modify-syntax-entry ?\
\e$B!J
\e(B "(
\e$B!K
\e(B")
392 (modify-syntax-entry ?\
\e$B!N
\e(B "(
\e$B!O
\e(B")
393 (modify-syntax-entry ?\
\e$B!P
\e(B "(
\e$B!Q
\e(B")
394 (modify-syntax-entry ?\
\e$B!V
\e(B "(
\e$B!W
\e(B")
395 (modify-syntax-entry ?\
\e$B!X
\e(B "(
\e$B!Y
\e(B")
396 (modify-syntax-entry ?\
\e$B!K
\e(B ")
\e$B!J
\e(B")
397 (modify-syntax-entry ?\
\e$B!O
\e(B ")
\e$B!N
\e(B")
398 (modify-syntax-entry ?\
\e$B!Q
\e(B ")
\e$B!P
\e(B")
399 (modify-syntax-entry ?\
\e$B!W
\e(B ")
\e$B!V
\e(B")
400 (modify-syntax-entry ?\
\e$B!Y
\e(B ")
\e$B!X
\e(B")
402 (modify-category-entry (make-char 'japanese-jisx0208 35) ?A)
403 (modify-category-entry (make-char 'japanese-jisx0208 36) ?H)
404 (modify-category-entry (make-char 'japanese-jisx0208 37) ?K)
405 (modify-category-entry (make-char 'japanese-jisx0208 38) ?G)
406 (modify-category-entry (make-char 'japanese-jisx0208 39) ?Y)
409 (modify-category-entry (make-char 'japanese-jisx0208 row) ?C)
410 (setq row (1+ row))))
411 (modify-category-entry ?
\e$B!<
\e(B ?K)
412 (let ((chars '(?
\e$B!+
\e(B ?
\e$B!,
\e(B)))
414 (modify-category-entry (car chars) ?K)
415 (modify-category-entry (car chars) ?H)
416 (setq chars (cdr chars))))
417 (let ((chars '(?
\e$B!3
\e(B ?
\e$B!4
\e(B ?
\e$B!5
\e(B ?
\e$B!6
\e(B ?
\e$B!7
\e(B ?
\e$B!8
\e(B ?
\e$B!9
\e(B ?
\e$B!:
\e(B ?
\e$B!;
\e(B)))
419 (modify-category-entry (car chars) ?C)
420 (setq chars (cdr chars))))
423 (modify-syntax-entry (make-char 'japanese-jisx0212) "w")
424 (modify-syntax-entry (make-char 'japanese-jisx0212 33) "_")
425 (modify-syntax-entry (make-char 'japanese-jisx0212 34) "_")
426 (modify-syntax-entry (make-char 'japanese-jisx0212 35) "_")
428 (modify-category-entry (make-char 'japanese-jisx0212 ) ?C)
431 (modify-syntax-entry (make-char 'katakana-jisx0201) "w")
432 (let ((chars '(?
\e(I!
\e(B ?
\e(I$
\e(B ?
\e(I%
\e(B)))
434 (modify-syntax-entry (car chars) ".")
435 (setq chars (cdr chars))))
437 (modify-syntax-entry ?\
\e(I"
\e(B "(
\e(I#
\e(B")
438 (modify-syntax-entry ?\
\e(I#
\e(B "(
\e(I"
\e(B")
440 ;; Korean character set (KSC5601)
442 (modify-syntax-entry (make-char 'korean-ksc5601) "w")
443 (modify-syntax-entry (make-char 'korean-ksc5601 33) "_")
444 (modify-syntax-entry (make-char 'korean-ksc5601 34) "_")
445 (modify-syntax-entry (make-char 'korean-ksc5601 38) "_")
446 (modify-syntax-entry (make-char 'korean-ksc5601 39) "_")
447 (modify-syntax-entry (make-char 'korean-ksc5601 40) "_")
448 (modify-syntax-entry (make-char 'korean-ksc5601 41) "_")
450 (modify-category-entry (make-char 'korean-ksc5601) ?h)
451 (modify-category-entry (make-char 'korean-ksc5601 35) ?A)
452 (modify-category-entry (make-char 'korean-ksc5601 37) ?G)
453 (modify-category-entry (make-char 'korean-ksc5601 42) ?H)
454 (modify-category-entry (make-char 'korean-ksc5601 43) ?K)
455 (modify-category-entry (make-char 'korean-ksc5601 44) ?Y)
457 ;; Latin character set (latin-1,2,3,4,5,8,9)
459 (modify-category-entry (make-char 'latin-iso8859-1) ?l)
460 (modify-category-entry (make-char 'latin-iso8859-2) ?l)
461 (modify-category-entry (make-char 'latin-iso8859-3) ?l)
462 (modify-category-entry (make-char 'latin-iso8859-4) ?l)
463 (modify-category-entry (make-char 'latin-iso8859-9) ?l)
464 (modify-category-entry (make-char 'latin-iso8859-14) ?l)
465 (modify-category-entry (make-char 'latin-iso8859-15) ?l)
467 (modify-category-entry (make-char 'latin-iso8859-1 160) ?\ )
468 (modify-category-entry (make-char 'latin-iso8859-2 160) ?\ )
469 (modify-category-entry (make-char 'latin-iso8859-3 160) ?\ )
470 (modify-category-entry (make-char 'latin-iso8859-4 160) ?\ )
471 (modify-category-entry (make-char 'latin-iso8859-9 160) ?\ )
472 (modify-category-entry (make-char 'latin-iso8859-14 160) ?\ )
473 (modify-category-entry (make-char 'latin-iso8859-15 160) ?\ )
477 (modify-category-entry (make-char 'lao) ?o)
479 (let ((deflist '(;; chars syntax category
480 ("
\e(1!
\e(B-
\e(1N
\e(B" "w" ?0) ; consonant
481 ("
\e(1PRS]`
\e(B-
\e(1d
\e(B" "w" ?1) ; vowel base
482 ("
\e(1QT
\e(B-
\e(1W[m
\e(B" "w" ?2) ; vowel upper
483 ("
\e(1XY
\e(B" "w" ?3) ; vowel lower
484 ("
\e(1h
\e(B-
\e(1l
\e(B" "w" ?4) ; tone mark
485 ("
\e(1\
\e(B" "w" ?9) ; semivowel lower
486 ("
\e(1p
\e(B-
\e(1y
\e(B" "w" ?6) ; digit
487 ("
\e(1Of
\e(B" "_" ?5) ; symbol
489 elm chars len syntax category to ch i)
491 (setq elm (car deflist))
492 (setq chars (car elm)
498 (if (= (aref chars i) ?-)
501 (setq ch (aref chars i)
504 (modify-syntax-entry ch syntax)
505 (modify-category-entry ch category)
508 (setq deflist (cdr deflist))))
510 ;; Thai character set (TIS620)
512 (modify-category-entry (make-char 'thai-tis620) ?t)
514 (let ((deflist '(;; chars syntax category
515 ("
\e,T!
\e(B-
\e,TCEG
\e(B-
\e,TN
\e(B" "w" ?0) ; consonant
516 ("
\e,TDFPRS`
\e(B-
\e,Te
\e(B" "w" ?1) ; vowel base
517 ("
\e,TQT
\e(B-
\e,TWgn
\e(B" "w" ?2) ; vowel upper
518 ("
\e,TX
\e(B-
\e,TZ
\e(B" "w" ?3) ; vowel lower
519 ("
\e,Th
\e(B-
\e,Tm
\e(B" "w" ?4) ; tone mark
520 ("
\e,Tp
\e(B-
\e,Ty
\e(B" "w" ?6) ; digit
521 ("
\e,TOf_oz{
\e(B" "_" ?5) ; symbol
523 elm chars len syntax category to ch i)
525 (setq elm (car deflist))
526 (setq chars (car elm)
532 (if (= (aref chars i) ?-)
535 (setq ch (aref chars i)
538 (modify-syntax-entry ch syntax)
539 (modify-category-entry ch category)
542 (setq deflist (cdr deflist))))
544 ;; Tibetan character set
546 (modify-category-entry (make-char 'tibetan) ?q)
547 (modify-category-entry (make-char 'tibetan-1-column) ?q)
549 (let ((deflist '(;; chars syntax category
550 ("
\e$(7"!
\e(B-
\e$(7"J"K
\e(B" "w" ?0) ; consonant
551 ("
\e$(7#!
\e(B-
\e$(7#J#K#L#M!"!#
\e(B" "w" ?0) ;
552 ("
\e$(7$!
\e(B-
\e$(7$e
\e(B" "w" ?0) ;
553 ("
\e$(7%!
\e(B-
\e$(7%u
\e(B" "w" ?0) ;
554 ("
\e$(7"S"["\"]"^"a
\e(B" "w" ?2) ; upper vowel
555 ("
\e$(7"_"c"d"g"h"i"j"k"l
\e(B" "w" ?2) ; upper modifier
556 ("
\e$(7!I"Q"R"U"e!e!g
\e(B" "w" ?3) ; lowel vowel/modifier
557 ("
\e$(7!P
\e(B-
\e$(7!Y!Z
\e(B-
\e$(7!c
\e(B" "w" ?6) ; digit
558 ("
\e$(7!;!=
\e(B-
\e$(7!B!D"`
\e(B" "." ?|) ; line-break char
559 ("
\e$(8!;!=!?!@!A!D"`
\e(B" "." ?|) ;
560 ("
\e$(7!8!;!=
\e(B-
\e$(7!B!D"`!m!d
\e(B" "." ?>) ; prohibition
561 ("
\e$(8!;!=!?!@!A!D"`
\e(B" "." ?>) ;
562 ("
\e$(7!0
\e(B-
\e$(7!:!l#R#S"f
\e(B" "." ?<) ; prohibition
563 ("
\e$(7!C!E
\e(B-
\e$(7!H!J
\e(B-
\e$(7!O!f!h
\e(B-
\e$(7!k!n!o#O#P
\e(B-
\e$(7#`
\e(B" "." ?q) ; others
565 elm chars len syntax category to ch i)
567 (setq elm (car deflist))
568 (setq chars (car elm)
574 (if (= (aref chars i) ?-)
577 (setq ch (aref chars i)
580 (modify-syntax-entry ch syntax)
581 (modify-category-entry ch category)
584 (setq deflist (cdr deflist))))
586 ;; Vietnamese character set
588 (let ((lower (make-char 'vietnamese-viscii-lower))
589 (upper (make-char 'vietnamese-viscii-upper)))
590 (modify-syntax-entry lower "w")
591 (modify-syntax-entry upper "w")
592 (modify-category-entry lower ?v)
593 (modify-category-entry upper ?v)
594 (modify-category-entry lower ?l) ; To make a word with
595 (modify-category-entry upper ?l) ; latin characters.
598 (let ((tbl (standard-case-table))
601 (set-case-syntax-pair (make-char 'vietnamese-viscii-upper i)
602 (make-char 'vietnamese-viscii-lower i)
606 ;; Unicode (mule-unicode-0100-24ff)
608 (let ((tbl (standard-case-table)) c)
610 ;; In some languages, U+0049 LATIN CAPITAL LETTER I and U+0131 LATIN
611 ;; SMALL LETTER DOTLESS I make a case pair, and so do U+0130 LATIN
612 ;; CAPITAL LETTER I WITH DOT ABOVE and U+0069 LATIN SMALL LETTER I.
613 ;; Thus we have to check language-environment to handle casing
614 ;; correctly. Currently only I<->i is available.
616 ;; case-syntax-pair's are not yet given for Latin Extendet-B
618 ;; Latin Extended-A, Latin Extended-B
621 (modify-category-entry (decode-char 'ucs c) ?l)
622 (and (or (<= c #x012e)
623 (and (>= c #x014a) (<= c #x0177)))
625 (set-case-syntax-pair
626 (decode-char 'ucs c) (decode-char 'ucs (1+ c)) tbl))
630 (set-case-syntax-pair
631 (decode-char 'ucs (1- c)) (decode-char 'ucs c) tbl))
633 (set-case-syntax-pair ?
\e$,1 R
\e(B ?
\e$,1 S
\e(B tbl)
634 (set-case-syntax-pair ?
\e$,1 T
\e(B ?
\e$,1 U
\e(B tbl)
635 (set-case-syntax-pair ?
\e$,1 V
\e(B ?
\e$,1 W
\e(B tbl)
636 ; (set-case-syntax-pair ?
\e$,1!8
\e(B ?
\e,A
\7f\e(B tbl) ; these two have different length!
637 (set-case-syntax-pair ?
\e$,1!9
\e(B ?
\e$,1!:
\e(B tbl)
638 (set-case-syntax-pair ?
\e$,1!;
\e(B ?
\e$,1!<
\e(B tbl)
639 (set-case-syntax-pair ?
\e$,1!=
\e(B ?
\e$,1!>
\e(B tbl)
641 ;; Latin Extended Additional
644 (modify-category-entry (decode-char 'ucs c) ?l)
646 (or (<= c #x1e94) (>= c #x1ea0))
647 (set-case-syntax-pair
648 (decode-char 'ucs c) (decode-char 'ucs (1+ c)) tbl))
654 (modify-category-entry (decode-char 'ucs c) ?g)
655 (if (or (and (>= c #x0391) (<= c #x03a1))
656 (and (>= c #x03a3) (<= c #x03ab)))
657 (set-case-syntax-pair
658 (decode-char 'ucs c) (decode-char 'ucs (+ c 32)) tbl))
662 (set-case-syntax-pair
663 (decode-char 'ucs c) (decode-char 'ucs (1+ c)) tbl))
665 (set-case-syntax-pair ?
\e$,1&f
\e(B ?
\e$,1',
\e(B tbl)
666 (set-case-syntax-pair ?
\e$,1&h
\e(B ?
\e$,1'-
\e(B tbl)
667 (set-case-syntax-pair ?
\e$,1&i
\e(B ?
\e$,1'.
\e(B tbl)
668 (set-case-syntax-pair ?
\e$,1&j
\e(B ?
\e$,1'/
\e(B tbl)
669 (set-case-syntax-pair ?
\e$,1&l
\e(B ?
\e$,1'L
\e(B tbl)
670 (set-case-syntax-pair ?
\e$,1&n
\e(B ?
\e$,1'M
\e(B tbl)
671 (set-case-syntax-pair ?
\e$,1&o
\e(B ?
\e$,1'N
\e(B tbl)
676 (modify-category-entry (decode-char 'ucs c) ?g)
677 (and (<= (logand c #x000f) 7)
679 (not (memq c '(#x1f50 #x1f52 #x1f54 #x1f56)))
680 (/= (logand c #x00f0) 7)
681 (set-case-syntax-pair
682 (decode-char 'ucs (+ c 8)) (decode-char 'ucs c) tbl))
684 (set-case-syntax-pair ?
\e$,1qx
\e(B ?
\e$,1qp
\e(B tbl)
685 (set-case-syntax-pair ?
\e$,1qy
\e(B ?
\e$,1qq
\e(B tbl)
686 (set-case-syntax-pair ?
\e$,1qz
\e(B ?
\e$,1q0
\e(B tbl)
687 (set-case-syntax-pair ?
\e$,1q{
\e(B ?
\e$,1q1
\e(B tbl)
688 (set-case-syntax-pair ?
\e$,1q|
\e(B ?
\e$,1qs
\e(B tbl)
689 (set-case-syntax-pair ?
\e$,1r(
\e(B ?
\e$,1q2
\e(B tbl)
690 (set-case-syntax-pair ?
\e$,1r)
\e(B ?
\e$,1q3
\e(B tbl)
691 (set-case-syntax-pair ?
\e$,1r*
\e(B ?
\e$,1q4
\e(B tbl)
692 (set-case-syntax-pair ?
\e$,1r+
\e(B ?
\e$,1q5
\e(B tbl)
693 (set-case-syntax-pair ?
\e$,1r,
\e(B ?
\e$,1r#
\e(B tbl)
694 (set-case-syntax-pair ?
\e$,1r8
\e(B ?
\e$,1r0
\e(B tbl)
695 (set-case-syntax-pair ?
\e$,1r9
\e(B ?
\e$,1r1
\e(B tbl)
696 (set-case-syntax-pair ?
\e$,1r:
\e(B ?
\e$,1q6
\e(B tbl)
697 (set-case-syntax-pair ?
\e$,1r;
\e(B ?
\e$,1q7
\e(B tbl)
698 (set-case-syntax-pair ?
\e$,1rH
\e(B ?
\e$,1r@
\e(B tbl)
699 (set-case-syntax-pair ?
\e$,1rI
\e(B ?
\e$,1rA
\e(B tbl)
700 (set-case-syntax-pair ?
\e$,1rJ
\e(B ?
\e$,1q:
\e(B tbl)
701 (set-case-syntax-pair ?
\e$,1rK
\e(B ?
\e$,1q;
\e(B tbl)
702 (set-case-syntax-pair ?
\e$,1rL
\e(B ?
\e$,1rE
\e(B tbl)
703 (set-case-syntax-pair ?
\e$,1rX
\e(B ?
\e$,1q8
\e(B tbl)
704 (set-case-syntax-pair ?
\e$,1rY
\e(B ?
\e$,1q9
\e(B tbl)
705 (set-case-syntax-pair ?
\e$,1rZ
\e(B ?
\e$,1q<
\e(B tbl)
706 (set-case-syntax-pair ?
\e$,1r[
\e(B ?
\e$,1q=
\e(B tbl)
707 (set-case-syntax-pair ?
\e$,1r\
\e(B ?
\e$,1rS
\e(B tbl)
712 (modify-category-entry (decode-char 'ucs c) ?y)
715 (set-case-syntax-pair
716 (decode-char 'ucs c) (decode-char 'ucs (+ c 80)) tbl))
719 (set-case-syntax-pair
720 (decode-char 'ucs c) (decode-char 'ucs (+ c 32)) tbl))
722 (or (and (>= c #x0460) (<= c #x0480))
723 (and (>= c #x048c) (<= c #x04be))
724 (and (>= c #x04d0) (<= c #x04f4)))
725 (set-case-syntax-pair
726 (decode-char 'ucs c) (decode-char 'ucs (1+ c)) tbl))
728 (set-case-syntax-pair ?
\e$,1*!
\e(B ?
\e$,1*"
\e(B tbl)
729 (set-case-syntax-pair ?
\e$,1*#
\e(B ?
\e$,1*$
\e(B tbl)
730 (set-case-syntax-pair ?
\e$,1*'
\e(B ?
\e$,1*(
\e(B tbl)
731 (set-case-syntax-pair ?
\e$,1*+
\e(B ?
\e$,1*,
\e(B tbl)
732 (set-case-syntax-pair ?
\e$,1*X
\e(B ?
\e$,1*Y
\e(B tbl)
734 ;; general punctuation
737 (set-case-syntax c " " tbl)
741 (set-case-syntax c "_" tbl)
746 ;;; Setting word boundary.
748 (setq word-combining-categories
751 (setq word-separating-categories ; (2-byte character sets)
752 '((?A . ?K) ; Alpha numeric - Katakana
753 (?A . ?C) ; Alpha numeric - Chinese
754 (?H . ?A) ; Hiragana - Alpha numeric
755 (?H . ?K) ; Hiragana - Katakana
756 (?H . ?C) ; Hiragana - Chinese
757 (?K . ?A) ; Katakana - Alpha numeric
758 (?K . ?C) ; Katakana - Chinese
759 (?C . ?A) ; Chinese - Alpha numeric
760 (?C . ?K) ; Chinese - Katakana
764 ;; For each character set, put the information of the most proper
765 ;; coding system to encode it by `preferred-coding-system' property.
767 (let ((l '((latin-iso8859-1 . iso-latin-1)
768 (latin-iso8859-2 . iso-latin-2)
769 (latin-iso8859-3 . iso-latin-3)
770 (latin-iso8859-4 . iso-latin-4)
771 (thai-tis620 . thai-tis620)
772 (greek-iso8859-7 . greek-iso-8bit)
773 (arabic-iso8859-6 . iso-2022-7bit)
774 (hebrew-iso8859-8 . hebrew-iso-8bit)
775 (katakana-jisx0201 . japanese-shift-jis)
776 (latin-jisx0201 . japanese-shift-jis)
777 (cyrillic-iso8859-5 . cyrillic-iso-8bit)
778 (latin-iso8859-9 . iso-latin-5)
779 (japanese-jisx0208-1978 . iso-2022-jp)
780 (chinese-gb2312 . cn-gb-2312)
781 (japanese-jisx0208 . iso-2022-jp)
782 (korean-ksc5601 . iso-2022-kr)
783 (japanese-jisx0212 . iso-2022-jp)
784 (chinese-cns11643-1 . iso-2022-cn)
785 (chinese-cns11643-2 . iso-2022-cn)
786 (chinese-big5-1 . chinese-big5)
787 (chinese-big5-2 . chinese-big5)
788 (chinese-sisheng . iso-2022-7bit)
789 (ipa . iso-2022-7bit)
790 (vietnamese-viscii-lower . vietnamese-viscii)
791 (vietnamese-viscii-upper . vietnamese-viscii)
792 (arabic-digit . iso-2022-7bit)
793 (arabic-1-column . iso-2022-7bit)
794 (ascii-right-to-left . iso-2022-7bit)
796 (arabic-2-column . iso-2022-7bit)
797 (indian-is13194 . devanagari)
798 (indian-1-column . devanagari)
799 (tibetan-1-column . tibetan)
800 (ethiopic . iso-2022-7bit)
801 (chinese-cns11643-3 . iso-2022-cn)
802 (chinese-cns11643-4 . iso-2022-cn)
803 (chinese-cns11643-5 . iso-2022-cn)
804 (chinese-cns11643-6 . iso-2022-cn)
805 (chinese-cns11643-7 . iso-2022-cn)
806 (indian-2-column . devanagari)
808 (latin-iso8859-14 . iso-latin-8)
809 (latin-iso8859-15 . iso-latin-9))))
811 (put-charset-property (car (car l)) 'preferred-coding-system (cdr (car l)))
815 ;; Setup auto-fill-chars for charsets that should invoke auto-filling.
816 ;; SPACE and NEWLIE are already set. Also put `nospace-between-words'
817 ;; property to the charsets.
818 (let ((l '(katakana-jisx0201
819 japanese-jisx0208 japanese-jisx0212
820 chinese-gb2312 chinese-big5-1 chinese-big5-2)))
822 (aset auto-fill-chars (make-char (car l)) t)
823 (put-charset-property (car l) 'nospace-between-words t)
827 ;;; coding: iso-2022-7bit
830 ;;; end of characters.el