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
)
141 (modify-category-entry (make-char 'chinese-gb2312
35) ?A
)
144 (modify-category-entry (make-char 'chinese-gb2312 row
) ?C
)
145 (setq row
(1+ row
))))
147 ;; Chinese character set (BIG5)
149 (let ((generic-big5-1-char (make-char 'chinese-big5-1
))
150 (generic-big5-2-char (make-char 'chinese-big5-2
)))
151 (modify-syntax-entry generic-big5-1-char
"w")
152 (modify-syntax-entry generic-big5-2-char
"w")
154 (modify-category-entry generic-big5-1-char ?c
)
155 (modify-category-entry generic-big5-2-char ?c
)
157 (modify-category-entry generic-big5-1-char ?C
)
158 (modify-category-entry generic-big5-2-char ?C
)
160 (modify-category-entry generic-big5-1-char ?\|
)
161 (modify-category-entry generic-big5-2-char ?\|
))
164 ;; Chinese character set (CNS11643)
166 (let ((cns-list '(chinese-cns11643-1
175 (setq generic-char
(make-char (car cns-list
)))
176 (modify-syntax-entry generic-char
"w")
177 (modify-category-entry generic-char ?c
)
178 (modify-category-entry generic-char ?C
)
179 (modify-category-entry generic-char ?|
)
180 (setq cns-list
(cdr cns-list
))))
182 ;; Cyrillic character set (ISO-8859-5)
184 (modify-category-entry (make-char 'cyrillic-iso8859-5
) ?y
)
186 (modify-syntax-entry (make-char 'cyrillic-iso8859-5
160) " ")
187 (modify-syntax-entry ?
\e,L-
\e(B ".")
188 (modify-syntax-entry ?
\e,Lp
\e(B ".")
189 (modify-syntax-entry ?
\e,L
}\e(B ".")
190 (let ((tbl (standard-case-table)))
191 (set-case-syntax-pair ?
\e,L
!\e(B ?
\e,Lq
\e(B tbl
)
192 (set-case-syntax-pair ?
\e,L
"\e(B ?\e,Lr\e(B tbl)
193 (set-case-syntax-pair ?\e,L#\e(B ?\e,Ls\e(B tbl)
194 (set-case-syntax-pair ?\e,L$\e(B ?\e,Lt\e(B tbl)
195 (set-case-syntax-pair ?\e,L%\e(B ?\e,Lu\e(B tbl)
196 (set-case-syntax-pair ?\e,L&\e(B ?\e,Lv\e(B tbl)
197 (set-case-syntax-pair ?\e,L'\e(B ?\e,Lw\e(B tbl)
198 (set-case-syntax-pair ?\e,L(\e(B ?\e,Lx\e(B tbl)
199 (set-case-syntax-pair ?\e,L)\e(B ?\e,Ly\e(B tbl)
200 (set-case-syntax-pair ?\e,L*\e(B ?\e,Lz\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~\e(B tbl)
204 (set-case-syntax-pair ?\e,L/\e(B ?\e,L\7f\e(B tbl)
205 (set-case-syntax-pair ?\e,L0\e(B ?\e,LP\e(B tbl)
206 (set-case-syntax-pair ?\e,L1\e(B ?\e,LQ\e(B tbl)
207 (set-case-syntax-pair ?\e,L2\e(B ?\e,LR\e(B tbl)
208 (set-case-syntax-pair ?\e,L3\e(B ?\e,LS\e(B tbl)
209 (set-case-syntax-pair ?\e,L4\e(B ?\e,LT\e(B tbl)
210 (set-case-syntax-pair ?\e,L5\e(B ?\e,LU\e(B tbl)
211 (set-case-syntax-pair ?\e,L6\e(B ?\e,LV\e(B tbl)
212 (set-case-syntax-pair ?\e,L7\e(B ?\e,LW\e(B tbl)
213 (set-case-syntax-pair ?\e,L8\e(B ?\e,LX\e(B tbl)
214 (set-case-syntax-pair ?\e,L9\e(B ?\e,LY\e(B tbl)
215 (set-case-syntax-pair ?\e,L:\e(B ?\e,LZ\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,L@\e(B ?\e,L`\e(B tbl)
222 (set-case-syntax-pair ?\e,LA\e(B ?\e,La\e(B tbl)
223 (set-case-syntax-pair ?\e,LB\e(B ?\e,Lb\e(B tbl)
224 (set-case-syntax-pair ?\e,LC\e(B ?\e,Lc\e(B tbl)
225 (set-case-syntax-pair ?\e,LD\e(B ?\e,Ld\e(B tbl)
226 (set-case-syntax-pair ?\e,LE\e(B ?\e,Le\e(B tbl)
227 (set-case-syntax-pair ?\e,LF\e(B ?\e,Lf\e(B tbl)
228 (set-case-syntax-pair ?\e,LG\e(B ?\e,Lg\e(B tbl)
229 (set-case-syntax-pair ?\e,LH\e(B ?\e,Lh\e(B tbl)
230 (set-case-syntax-pair ?\e,LI\e(B ?\e,Li\e(B tbl)
231 (set-case-syntax-pair ?\e,LJ\e(B ?\e,Lj\e(B tbl)
232 (set-case-syntax-pair ?\e,LK\e(B ?\e,Lk\e(B tbl)
233 (set-case-syntax-pair ?\e,LL\e(B ?\e,Ll\e(B tbl)
234 (set-case-syntax-pair ?\e,LM\e(B ?\e,Lm\e(B tbl)
235 (set-case-syntax-pair ?\e,LN\e(B ?\e,Ln\e(B tbl)
236 (set-case-syntax-pair ?\e,LO\e(B ?\e,Lo\e(B tbl))
238 ;; Devanagari character set
240 (let ((deflist '(;; chars syntax category
241 ("\e$
(5!!!"!#\e(B" "w" ?
7) ; vowel-modifying diacritical mark
242 ; chandrabindu, anuswar, visarga
243 ("\e$(5!$\e(B-\e$(5!2\e(B" "w" ?
1) ; independent vowel
244 ("\e$(5!3\e(B-\e$(5!X\e(B" "w" ?
0) ; consonant
245 ("\e$(5!Z\e(B-\e$(5!g\e(B" "w" ?
8) ; matra
246 ("\e$(5!q\e(B-\e$(5!z\e(B" "w" ?
6) ; digit
248 elm chars len syntax category to ch i
)
250 (setq elm
(car deflist
))
251 (setq chars
(car elm
)
257 (if (= (aref chars i
) ?-
)
260 (setq ch
(aref chars i
)
263 (modify-syntax-entry ch syntax
)
264 (modify-category-entry ch category
)
267 (setq deflist
(cdr deflist
))))
269 ;; Ethiopic character set
271 (modify-category-entry (make-char 'ethiopic
) ?e
)
272 (modify-syntax-entry (make-char 'ethiopic
) "w")
273 (let ((chars '(?
\e$
(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)))
275 (modify-syntax-entry (car chars
) ".")
276 (setq chars
(cdr chars
))))
278 ;; European character set (Latin-1,2,3,4,5)
280 (modify-category-entry (make-char 'latin-iso8859-1
) ?l
)
281 (modify-category-entry (make-char 'latin-iso8859-2
) ?l
)
282 (modify-category-entry (make-char 'latin-iso8859-3
) ?l
)
283 (modify-category-entry (make-char 'latin-iso8859-4
) ?l
)
284 (modify-category-entry (make-char 'latin-iso8859-9
) ?l
)
286 (modify-category-entry (make-char 'latin-iso8859-1
160) ?\
)
287 (modify-category-entry (make-char 'latin-iso8859-2
160) ?\
)
288 (modify-category-entry (make-char 'latin-iso8859-3
160) ?\
)
289 (modify-category-entry (make-char 'latin-iso8859-4
160) ?\
)
290 (modify-category-entry (make-char 'latin-iso8859-9
160) ?\
)
292 ;; Greek character set (ISO-8859-7)
294 (modify-category-entry (make-char 'greek-iso8859-7
) ?g
)
298 (modify-syntax-entry (make-char 'greek-iso8859-7 c
) "w")
300 (modify-syntax-entry (make-char 'greek-iso8859-7
160) "w") ; NBSP
301 (modify-syntax-entry ?
\e,F7
\e(B ".")
302 (modify-syntax-entry ?
\e,F
;\e(B ".")
303 (modify-syntax-entry ?
\e,F
=\e(B ".")
305 ;; Hebrew character set (ISO-8859-8)
307 (modify-category-entry (make-char 'hebrew-iso8859-8
) ?w
)
311 (modify-syntax-entry (make-char 'hebrew-iso8859-8 c
) "w")
313 (modify-syntax-entry (make-char 'hebrew-iso8859-8
160) "w") ; NBSP
315 ;; Indian character set (IS 13194 and other Emacs original Indian charsets)
317 (modify-category-entry (make-char 'indian-is13194
) ?i
)
318 (modify-category-entry (make-char 'indian-2-column
) ?I
)
319 (modify-category-entry (make-char 'indian-1-column
) ?I
)
322 '(;; chars syntax category
323 ("\e(5!"#\e(B" "w
" ?7) ; vowel-modifying diacritical mark
324 ; chandrabindu, anuswar, visarga
325 ("\e(5$
\e(B-\e(52\e(B" "w
" ?1) ; base (independent) vowel
326 ("\e(53\e(B-\e(5X\e(B" "w
" ?0) ; consonant
327 ("\e(5Z\e(B-\e(5g\e(B" "w
" ?8) ; matra
328 ("\e(5q\e(B-\e(5z\e(B" "w
" ?6) ; digit
330 elm chars len syntax category to ch i)
332 (setq elm (car deflist))
333 (setq chars (car elm)
339 (if (= (aref chars i) ?-)
342 (setq ch (aref chars i)
345 (modify-syntax-entry ch syntax)
346 (modify-category-entry ch category)
349 (setq deflist (cdr deflist))))
352 ;; Japanese character set (JISX0201-kana, JISX0201-roman, JISX0208, JISX0212)
354 (modify-category-entry (make-char 'katakana-jisx0201) ?k)
355 (modify-category-entry (make-char 'latin-jisx0201) ?r)
356 (modify-category-entry (make-char 'japanese-jisx0208) ?j)
357 (modify-category-entry (make-char 'japanese-jisx0212) ?j)
358 (modify-category-entry (make-char 'katakana-jisx0201) ?\|)
359 (modify-category-entry (make-char 'japanese-jisx0208) ?\|)
360 (modify-category-entry (make-char 'japanese-jisx0212) ?\|)
363 (modify-syntax-entry (make-char 'japanese-jisx0208) "w
")
364 (modify-syntax-entry (make-char 'japanese-jisx0208 33) "_
")
365 (modify-syntax-entry (make-char 'japanese-jisx0208 34) "_
")
366 (modify-syntax-entry (make-char 'japanese-jisx0208 40) "_
")
367 (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)))
369 (modify-syntax-entry (car chars) "w
")
370 (setq chars (cdr chars))))
371 (modify-syntax-entry ?\\e$B!J\e(B "(\e$B
!K
\e(B")
372 (modify-syntax-entry ?\\e$B!N\e(B "(\e$B
!O
\e(B")
373 (modify-syntax-entry ?\\e$B!P\e(B "(\e$B
!Q
\e(B")
374 (modify-syntax-entry ?\\e$B!V\e(B "(\e$B
!W
\e(B")
375 (modify-syntax-entry ?\\e$B!X\e(B "(\e$B
!Y
\e(B")
376 (modify-syntax-entry ?\\e$B!K\e(B ")\e$B
!J
\e(B")
377 (modify-syntax-entry ?\\e$B!O\e(B ")\e$B
!N
\e(B")
378 (modify-syntax-entry ?\\e$B!Q\e(B ")\e$B
!P
\e(B")
379 (modify-syntax-entry ?\\e$B!W\e(B ")\e$B
!V
\e(B")
380 (modify-syntax-entry ?\\e$B!Y\e(B ")\e$B
!X
\e(B")
382 (modify-category-entry (make-char 'japanese-jisx0208 35) ?A)
383 (modify-category-entry (make-char 'japanese-jisx0208 36) ?H)
384 (modify-category-entry (make-char 'japanese-jisx0208 37) ?K)
385 (modify-category-entry (make-char 'japanese-jisx0208 38) ?G)
386 (modify-category-entry (make-char 'japanese-jisx0208 39) ?Y)
389 (modify-category-entry (make-char 'japanese-jisx0208 row) ?C)
390 (setq row (1+ row))))
391 (modify-category-entry ?\e$B!<\e(B ?K)
392 (let ((chars '(?\e$B!+\e(B ?\e$B!,\e(B)))
394 (modify-category-entry (car chars) ?K)
395 (modify-category-entry (car chars) ?H)
396 (setq chars (cdr chars))))
397 (let ((chars '(?\e$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)))
399 (modify-category-entry (car chars) ?C)
400 (setq chars (cdr chars))))
403 (modify-syntax-entry (make-char 'japanese-jisx0212) "w
")
404 (modify-syntax-entry (make-char 'japanese-jisx0212 33) "_
")
405 (modify-syntax-entry (make-char 'japanese-jisx0212 34) "_
")
406 (modify-syntax-entry (make-char 'japanese-jisx0212 35) "_
")
408 (modify-category-entry (make-char 'japanese-jisx0212 ) ?C)
411 (modify-syntax-entry (make-char 'katakana-jisx0201) "w
")
412 (let ((chars '(?\e(I!\e(B ?\e(I"\e(B ?
\e(I#\e(B ?
\e(I$
\e(B ?
\e(I%
\e(B)))
414 (modify-syntax-entry (car chars
) ".")
415 (setq chars
(cdr chars
))))
417 ;; Korean character set (KSC5601)
419 (modify-syntax-entry (make-char 'korean-ksc5601
) "w")
420 (modify-syntax-entry (make-char 'korean-ksc5601
33) "_")
421 (modify-syntax-entry (make-char 'korean-ksc5601
34) "_")
422 (modify-syntax-entry (make-char 'korean-ksc5601
38) "_")
423 (modify-syntax-entry (make-char 'korean-ksc5601
39) "_")
424 (modify-syntax-entry (make-char 'korean-ksc5601
40) "_")
425 (modify-syntax-entry (make-char 'korean-ksc5601
41) "_")
427 (modify-category-entry (make-char 'korean-ksc5601
) ?h
)
428 (modify-category-entry (make-char 'korean-ksc5601
35) ?A
)
429 (modify-category-entry (make-char 'korean-ksc5601
37) ?G
)
430 (modify-category-entry (make-char 'korean-ksc5601
42) ?H
)
431 (modify-category-entry (make-char 'korean-ksc5601
43) ?K
)
432 (modify-category-entry (make-char 'korean-ksc5601
44) ?Y
)
436 (modify-category-entry (make-char 'lao
) ?o
)
438 (let ((deflist '(;; chars syntax category
439 ("\e(1!\e(B-\e(1N\e(B" "w" ?
0) ; consonant
440 ("\e(1PRS]`\e(B-\e(1d\e(B" "w" ?
1) ; vowel base
441 ("\e(1QT\e(B-\e(1W[m\e(B" "w" ?
2) ; vowel upper
442 ("\e(1XY\e(B" "w" ?
3) ; vowel lower
443 ("\e(1h\e(B-\e(1l\e(B" "w" ?
4) ; tone mark
444 ("\e(1\\e(B" "w" ?
9) ; semivowel lower
445 ("\e(1p\e(B-\e(1y\e(B" "w" ?
6) ; digit
446 ("\e(1Of\e(B" "_" ?
0) ; symbol
448 elm chars len syntax category to ch i
)
450 (setq elm
(car deflist
))
451 (setq chars
(car elm
)
457 (if (= (aref chars i
) ?-
)
460 (setq ch
(aref chars i
)
463 (modify-syntax-entry ch syntax
)
464 (modify-category-entry ch category
)
467 (setq deflist
(cdr deflist
))))
469 ;; Thai character set (TIS620)
471 (modify-category-entry (make-char 'thai-tis620
) ?t
)
473 (let ((deflist '(;; chars syntax category
474 ("\e,T!\e(B-\e,TCEG\e(B-\e,TN\e(B" "w" ?
0) ; consonant
475 ("\e,TDFPRS`\e(B-\e,Te\e(B" "w" ?
1) ; vowel base
476 ("\e,TQT\e(B-\e,TWgn\e(B" "w" ?
2) ; vowel upper
477 ("\e,TX\e(B-\e,TZ\e(B" "w" ?
3) ; vowel lower
478 ("\e,Th\e(B-\e,Tm\e(B" "w" ?
4) ; tone mark
479 ("\e,Tp\e(B-\e,Ty\e(B" "w" ?
6) ; digit
480 ("\e,TOf_oz{\e(B" "_" ?
5) ; symbol
482 elm chars len syntax category to ch i
)
484 (setq elm
(car deflist
))
485 (setq chars
(car elm
)
491 (if (= (aref chars i
) ?-
)
494 (setq ch
(aref chars i
)
497 (modify-syntax-entry ch syntax
)
498 (modify-category-entry ch category
)
501 (setq deflist
(cdr deflist
))))
503 ;; Tibetan character set
507 (modify-category-entry (make-char 'tibetan row
) ?q
)
508 (setq row
(1+ row
))))
510 (modify-category-entry (make-char 'tibetan-1-column
33) ?q
)
512 (let ((deflist '(;; chars syntax category
513 ("\e$(7"!\e(B-\e$
(7"J\e(B" "w" ?
0) ; consonant
514 ("\e$(7#!\e(B-\e$(7#J#P#Q\e(B" "w" ?
0) ;
515 ("\e$(7$!\e(B-\e$(7$e\e(B" "w" ?
0) ;
516 ("\e$(7%!\e(B-\e$(7%u\e(B" "w" ?
0) ;
517 ("\e$(7"S
"["\"]"^"a
\e(B" "w
" ?2) ; upper vowel
518 ("\e$
(7"_"c
"d"g
"h"i
"j"k
"l\e(B" "w" ?
2) ; upper modifier
519 ("\e$(7!I"Q
"U"e
!e
!g
\e(B" "w
" ?3) ; lowel vowel/modifier
520 ("\e$
(7!P
\e(B-\e$
(7!Y
!Z
\e(B-\e$
(7!c
\e(B" "w
" ?6) ; digit
521 ("\e$
(7!;!=\e(B-\e$(7!B!D"`\e(B" "." ?|) ; line-break char
522 ("\e$(8!;!=!?!@!A!D"`\e(B" ".
" ?|) ;
523 ("\e$
(7!8!;!=\e(B-\e$(7!B!D"`!m!d\e(B" "." ?>) ; prohibition
524 ("\e$(8!;!=!?!@!A!D"`\e(B" ".
" ?>) ;
525 ("\e$
(7!0\e(B-\e$
(7!:!l
#R
#S
"f\e(B" "." ?
<) ; prohibition
526 ("\e$(7!C!E\e(B-\e$(7!H!J\e(B-\e$(7!O!f!h\e(B-\e$(7!k!n!o\e(B" "." ?q
) ; others
528 elm chars len syntax category to ch i
)
530 (setq elm
(car deflist
))
531 (setq chars
(car elm
)
537 (if (= (aref chars i
) ?-
)
540 (setq ch
(aref chars i
)
543 (modify-syntax-entry ch syntax
)
544 (modify-category-entry ch category
)
547 (setq deflist
(cdr deflist
))))
549 ;; Vietnamese character set
551 (let ((lower (make-char 'vietnamese-viscii-lower
))
552 (upper (make-char 'vietnamese-viscii-upper
)))
553 (modify-syntax-entry lower
"w")
554 (modify-syntax-entry upper
"w")
555 (modify-category-entry lower ?v
)
556 (modify-category-entry upper ?v
)
557 (modify-category-entry lower ?l
) ; To make a word with
558 (modify-category-entry upper ?l
) ; latin characters.
562 ;;; Setting word boundary.
564 (setq word-combining-categories
567 (setq word-separating-categories
; (2-byte character sets)
568 '((?A . ?K
) ; Alpha numeric - Katakana
569 (?A . ?C
) ; Alpha numeric - Chinese
570 (?H . ?A
) ; Hiragana - Alpha numeric
571 (?H . ?K
) ; Hiragana - Katakana
572 (?H . ?C
) ; Hiragana - Chinese
573 (?K . ?A
) ; Katakana - Alpha numeric
574 (?K . ?C
) ; Katakana - Chinese
575 (?C . ?A
) ; Chinese - Alpha numeric
576 (?C . ?K
) ; Chinese - Katakana
580 ;; For each character set, put the information of the most proper
581 ;; coding system to encode it by `prefered-coding-system' property.
583 (let ((l '((latin-iso8859-1 . iso-latin-1
)
584 (latin-iso8859-2 . iso-latin-2
)
585 (latin-iso8859-3 . iso-latin-3
)
586 (latin-iso8859-4 . iso-latin-4
)
587 (thai-tis620 . thai-tis620
)
588 (greek-iso8859-7 . greek-iso-8bit
)
589 (arabic-iso8859-6 . iso-2022-7bit
)
590 (hebrew-iso8859-8 . hebrew-iso-8bit
)
591 (katakana-jisx0201 . japanese-shift-jis
)
592 (latin-jisx0201 . japanese-shift-jis
)
593 (cyrillic-iso8859-5 . cyrillic-iso-8bit
)
594 (latin-iso8859-9 . iso-latin-5
)
595 (japanese-jisx0208-1978 . iso-2022-jp
)
596 (chinese-gb2312 . cn-gb-2312
)
597 (japanese-jisx0208 . iso-2022-jp
)
598 (korean-ksc5601 . iso-2022-kr
)
599 (japanese-jisx0212 . iso-2022-jp
)
600 (chinese-cns11643-1 . iso-2022-cn
)
601 (chinese-cns11643-2 . iso-2022-cn
)
602 (chinese-big5-1 . chinese-big5
)
603 (chinese-big5-2 . chinese-big5
)
604 (chinese-sisheng . iso-2022-7bit
)
605 (ipa . iso-2022-7bit
)
606 (vietnamese-viscii-lower . vietnamese-viscii
)
607 (vietnamese-viscii-upper . vietnamese-viscii
)
608 (arabic-digit . iso-2022-7bit
)
609 (arabic-1-column . iso-2022-7bit
)
610 (ascii-right-to-left . iso-2022-7bit
)
612 (arabic-2-column . iso-2022-7bit
)
613 (indian-is13194 . devanagari
)
614 (indian-1-column . devanagari
)
615 (tibetan-1-column . tibetan
)
616 (ethiopic . iso-2022-jp
)
617 (chinese-cns11643-3 . iso-2022-cn
)
618 (chinese-cns11643-4 . iso-2022-cn
)
619 (chinese-cns11643-5 . iso-2022-cn
)
620 (chinese-cns11643-6 . iso-2022-cn
)
621 (chinese-cns11643-7 . iso-2022-cn
)
622 (indian-2-column . devanagari
)
623 (tibetan . tibetan
))))
625 (put-charset-property (car (car l
)) 'prefered-coding-system
(cdr (car l
)))
630 ;;; coding: iso-2022-7bit
633 ;;; end of characters.el