|
502
|
1 ;;; mule-charset.el --- Charset functions for Mule. -*- coding: iso-2022-7bit; -*-
|
|
428
|
2
|
|
788
|
3 ;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
|
|
|
4 ;; Copyright (C) 1992, 2001 Free Software Foundation, Inc.
|
|
|
5 ;; Licensed to the Free Software Foundation.
|
|
428
|
6 ;; Copyright (C) 1995 Amdahl Corporation.
|
|
|
7 ;; Copyright (C) 1996 Sun Microsystems.
|
|
777
|
8 ;; Copyright (C) 2002 Ben Wing.
|
|
428
|
9
|
|
|
10 ;; Author: Unknown
|
|
|
11 ;; Keywords: i18n, mule, internal
|
|
|
12
|
|
|
13 ;; This file is part of XEmacs.
|
|
|
14
|
|
|
15 ;; XEmacs is free software; you can redistribute it and/or modify it
|
|
|
16 ;; under the terms of the GNU General Public License as published by
|
|
|
17 ;; the Free Software Foundation; either version 2, or (at your option)
|
|
|
18 ;; any later version.
|
|
|
19
|
|
|
20 ;; XEmacs is distributed in the hope that it will be useful, but
|
|
|
21 ;; WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
22 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
|
23 ;; General Public License for more details.
|
|
|
24
|
|
|
25 ;; You should have received a copy of the GNU General Public License
|
|
|
26 ;; along with XEmacs; see the file COPYING. If not, write to the
|
|
|
27 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
|
|
|
28 ;; Boston, MA 02111-1307, USA.
|
|
|
29
|
|
|
30 ;;; Synched up with: Not synched. API at source level synched with FSF 20.3.9.
|
|
|
31
|
|
|
32 ;;; Commentary:
|
|
|
33
|
|
|
34 ;; These functions are not compatible at the bytecode level with Emacs/Mule,
|
|
|
35 ;; and they never will be. -sb [1999-05-26]
|
|
|
36
|
|
|
37 ;;; Code:
|
|
|
38
|
|
|
39 ;;;; Classifying text according to charsets
|
|
|
40
|
|
|
41 (defun charsets-in-string (string)
|
|
|
42 "Return a list of the charsets in STRING."
|
|
3681
|
43 (let (res)
|
|
|
44 (with-string-as-buffer-contents string
|
|
|
45 ;; charsets-in-region now in C.
|
|
|
46 (setq res (charsets-in-region (point-min) (point-max))))
|
|
|
47 res))
|
|
428
|
48
|
|
771
|
49 (defalias 'find-charset-string 'charsets-in-string)
|
|
3681
|
50
|
|
771
|
51 (defalias 'find-charset-region 'charsets-in-region)
|
|
818
|
52
|
|
428
|
53
|
|
|
54 ;;;; Charset accessors
|
|
|
55
|
|
|
56 (defun charset-iso-graphic-plane (charset)
|
|
|
57 "Return the `graphic' property of CHARSET.
|
|
|
58 See `make-charset'."
|
|
|
59 (charset-property charset 'graphic))
|
|
|
60
|
|
|
61 (defun charset-iso-final-char (charset)
|
|
|
62 "Return the final byte of the ISO 2022 escape sequence designating CHARSET."
|
|
|
63 (charset-property charset 'final))
|
|
|
64
|
|
|
65 (defun charset-chars (charset)
|
|
|
66 "Return the number of characters per dimension of CHARSET."
|
|
|
67 (charset-property charset 'chars))
|
|
|
68
|
|
|
69 (defun charset-width (charset)
|
|
|
70 "Return the number of display columns per character of CHARSET.
|
|
|
71 This only applies to TTY mode (under X, the actual display width can
|
|
|
72 be automatically determined)."
|
|
|
73 (charset-property charset 'columns))
|
|
|
74
|
|
|
75 ;; #### FSFmacs returns 0
|
|
|
76 (defun charset-direction (charset)
|
|
|
77 "Return the display direction (0 for `l2r' or 1 for `r2l') of CHARSET.
|
|
|
78 Only left-to-right is currently implemented."
|
|
|
79 (if (eq (charset-property charset 'direction) 'l2r)
|
|
|
80 0
|
|
|
81 1))
|
|
|
82
|
|
3659
|
83 ;; Not in GNU Emacs/Mule
|
|
428
|
84 (defun charset-registry (charset)
|
|
3712
|
85 "Obsolete; use charset-registries instead. "
|
|
3659
|
86 (lwarn 'xintl 'warning
|
|
|
87 "charset-registry is obsolete--use charset-registries instead. ")
|
|
|
88 (when (charset-property charset 'registries)
|
|
|
89 (elt (charset-property charset 'registries) 0)))
|
|
|
90
|
|
3712
|
91 (make-obsolete 'charset-registry 'charset-registries)
|
|
|
92
|
|
3659
|
93 (defun charset-registries (charset)
|
|
|
94 "Return the registries of CHARSET."
|
|
|
95 (charset-property charset 'registries))
|
|
|
96
|
|
|
97 (defun set-charset-registry (charset registry)
|
|
|
98 "Obsolete; use set-charset-registries instead. "
|
|
|
99 (check-argument-type 'stringp registry)
|
|
|
100 (check-argument-type 'charsetp (find-charset charset))
|
|
|
101 (unless (equal registry (regexp-quote registry))
|
|
|
102 (lwarn 'xintl 'warning
|
|
|
103 "Regexps no longer allowed for charset-registry. Treating %s%s"
|
|
|
104 registry " as a string."))
|
|
|
105 (set-charset-registries
|
|
|
106 charset
|
|
|
107 (apply 'vector registry (append (charset-registries charset) nil))))
|
|
428
|
108
|
|
3712
|
109 (make-obsolete 'set-charset-registry 'set-charset-registries)
|
|
|
110
|
|
428
|
111 (defun charset-ccl-program (charset)
|
|
|
112 "Return the CCL program of CHARSET.
|
|
|
113 See `make-charset'."
|
|
|
114 (charset-property charset 'ccl-program))
|
|
|
115
|
|
|
116 (defun charset-bytes (charset)
|
|
|
117 "Useless in XEmacs, returns 1."
|
|
|
118 1)
|
|
|
119
|
|
|
120 (define-obsolete-function-alias 'charset-columns 'charset-width) ;; 19990409
|
|
|
121 (define-obsolete-function-alias 'charset-final 'charset-iso-final-char) ;; 19990409
|
|
|
122 (define-obsolete-function-alias 'charset-graphic 'charset-iso-graphic-plane) ;; 19990409
|
|
|
123 (define-obsolete-function-alias 'charset-doc-string 'charset-description) ;; 19990409
|
|
|
124
|
|
|
125 ;;;; Define setf methods for all settable Charset properties
|
|
|
126
|
|
|
127 (defsetf charset-registry set-charset-registry)
|
|
|
128 (defsetf charset-ccl-program set-charset-ccl-program)
|
|
3712
|
129 (defsetf charset-registries set-charset-registries)
|
|
428
|
130
|
|
|
131 ;;; FSF compatibility functions
|
|
|
132 (defun charset-after (&optional pos)
|
|
|
133 "Return charset of a character in current buffer at position POS.
|
|
|
134 If POS is nil, it defauls to the current point.
|
|
|
135 If POS is out of range, the value is nil."
|
|
|
136 (when (null pos)
|
|
|
137 (setq pos (point)))
|
|
|
138 (check-argument-type 'integerp pos)
|
|
|
139 (unless (or (< pos (point-min))
|
|
|
140 (> pos (point-max)))
|
|
|
141 (char-charset (char-after pos))))
|
|
|
142
|
|
|
143 ;; Yuck!
|
|
771
|
144 ;; We're not going to support these.
|
|
|
145 ;(defun charset-info (charset) [incredibly broken function with random vectors]
|
|
|
146 ;(defun define-charset (...) [incredibly broken function with random vectors]
|
|
428
|
147
|
|
|
148 ;;; Charset property
|
|
|
149
|
|
|
150 (defalias 'get-charset-property 'get)
|
|
|
151 (defalias 'put-charset-property 'put)
|
|
|
152 (defalias 'charset-plist 'object-plist)
|
|
|
153 (defalias 'set-charset-plist 'setplist)
|
|
|
154
|
|
771
|
155
|
|
788
|
156 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
|
|
|
157 ; translation tables ;
|
|
|
158 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
|
|
|
159
|
|
|
160 (defstruct (translation-table (:constructor internal-make-translation-table))
|
|
|
161 forward
|
|
|
162 reverse)
|
|
|
163
|
|
|
164 (defun make-translation-table (&rest args)
|
|
|
165 "Make a translation table from arguments.
|
|
2116
|
166 A translation table is a char table intended for character translation
|
|
|
167 in CCL programs.
|
|
788
|
168
|
|
|
169 Each argument is a list of elemnts of the form (FROM . TO), where FROM
|
|
|
170 is a character to be translated to TO.
|
|
|
171
|
|
|
172 FROM can be a generic character (see `make-char'). In this case, TO is
|
|
|
173 a generic character containing the same number of characters, or a
|
|
|
174 ordinary character. If FROM and TO are both generic characters, all
|
|
|
175 characters belonging to FROM are translated to characters belonging to TO
|
|
|
176 without changing their position code(s).
|
|
|
177
|
|
|
178 The arguments and forms in each argument are processed in the given
|
|
|
179 order, and if a previous form already translates TO to some other
|
|
|
180 character, say TO-ALT, FROM is also translated to TO-ALT."
|
|
|
181 (let ((table (internal-make-translation-table
|
|
|
182 :forward (make-char-table 'generic)))
|
|
|
183 revlist)
|
|
|
184 (while args
|
|
|
185 (let ((elts (car args)))
|
|
|
186 (while elts
|
|
|
187 (let* ((from (car (car elts)))
|
|
|
188 (from-i 0) ; degree of freedom of FROM
|
|
|
189 (from-rev (nreverse (split-char from)))
|
|
|
190 (to (cdr (car elts)))
|
|
|
191 (to-i 0) ; degree of freedom of TO
|
|
|
192 (to-rev (nreverse (split-char to))))
|
|
|
193 ;; Check numbers of heading 0s in FROM-REV and TO-REV.
|
|
|
194 (while (eq (car from-rev) 0)
|
|
|
195 (setq from-i (1+ from-i) from-rev (cdr from-rev)))
|
|
|
196 (while (eq (car to-rev) 0)
|
|
|
197 (setq to-i (1+ to-i) to-rev (cdr to-rev)))
|
|
|
198 (if (and (/= from-i to-i) (/= to-i 0))
|
|
|
199 (error "Invalid character pair (%d . %d)" from to))
|
|
|
200 ;; If we have already translated TO to TO-ALT, FROM should
|
|
|
201 ;; also be translated to TO-ALT. But, this is only if TO
|
|
|
202 ;; is a generic character or TO-ALT is not a generic
|
|
|
203 ;; character.
|
|
|
204 (let ((to-alt (get-char-table to table)))
|
|
|
205 (if (and to-alt
|
|
|
206 (or (> to-i 0) (not (find-charset to-alt))))
|
|
|
207 (setq to to-alt)))
|
|
|
208 (if (> from-i 0)
|
|
|
209 (set-char-table-default table from to)
|
|
|
210 (put-char-table from to table))
|
|
|
211 ;; If we have already translated some chars to FROM, they
|
|
|
212 ;; should also be translated to TO.
|
|
|
213 (let ((l (assq from revlist)))
|
|
|
214 (if l
|
|
|
215 (let ((ch (car l)))
|
|
|
216 (setcar l to)
|
|
|
217 (setq l (cdr l))
|
|
|
218 (while l
|
|
|
219 (put-char-table ch to table)
|
|
|
220 (setq l (cdr l)) ))))
|
|
|
221 ;; Now update REVLIST.
|
|
|
222 (let ((l (assq to revlist)))
|
|
|
223 (if l
|
|
|
224 (setcdr l (cons from (cdr l)))
|
|
|
225 (setq revlist (cons (list to from) revlist)))))
|
|
|
226 (setq elts (cdr elts))))
|
|
|
227 (setq args (cdr args)))
|
|
|
228 ;; Return TABLE just created.
|
|
|
229 table))
|
|
|
230
|
|
|
231 ;; Do we really need this?
|
|
|
232 ; (defun make-translation-table-from-vector (vec)
|
|
|
233 ; "Make translation table from decoding vector VEC.
|
|
|
234 ; VEC is an array of 256 elements to map unibyte codes to multibyte characters.
|
|
|
235 ; See also the variable `nonascii-translation-table'."
|
|
|
236 ; (let ((table (make-char-table 'translation-table))
|
|
|
237 ; (rev-table (make-char-table 'translation-table))
|
|
|
238 ; (i 0)
|
|
|
239 ; ch)
|
|
|
240 ; (while (< i 256)
|
|
|
241 ; (setq ch (aref vec i))
|
|
|
242 ; (aset table i ch)
|
|
|
243 ; (if (>= ch 256)
|
|
|
244 ; (aset rev-table ch i))
|
|
|
245 ; (setq i (1+ i)))
|
|
|
246 ; (set-char-table-extra-slot table 0 rev-table)
|
|
|
247 ; table))
|
|
|
248
|
|
|
249 (defvar named-translation-table-hash-table (make-hash-table))
|
|
|
250
|
|
|
251 (defun define-translation-table (symbol &rest args)
|
|
|
252 "Define SYMBOL as the name of translation table made by ARGS.
|
|
|
253 This sets up information so that the table can be used for
|
|
|
254 translations in a CCL program.
|
|
|
255
|
|
|
256 If the first element of ARGS is a translation table, just define SYMBOL to
|
|
|
257 name it. (Note that this function does not bind SYMBOL.)
|
|
|
258
|
|
|
259 Any other ARGS should be suitable as arguments of the function
|
|
|
260 `make-translation-table' (which see).
|
|
|
261
|
|
|
262 Look up a named translation table using `find-translation-table' or
|
|
|
263 `get-translation-table'."
|
|
|
264 (let ((table (if (translation-table-p (car args))
|
|
|
265 (car args)
|
|
|
266 (apply 'make-translation-table args))))
|
|
|
267 (puthash symbol table named-translation-table-hash-table)))
|
|
|
268
|
|
|
269 (defun find-translation-table (table-or-name)
|
|
|
270 "Retrieve the translation table of the given name.
|
|
|
271 If TABLE-OR-NAME is a translation table object, it is simply returned.
|
|
|
272 Otherwise, TABLE-OR-NAME should be a symbol. If there is no such
|
|
|
273 translation table, nil is returned. Otherwise the associated translation
|
|
|
274 table object is returned."
|
|
|
275 (if (translation-table-p table-or-name)
|
|
|
276 table-or-name
|
|
|
277 (check-argument-type 'symbolp table-or-name)
|
|
|
278 (gethash table-or-name named-translation-table-hash-table)))
|
|
|
279
|
|
|
280 (defun get-translation-table (table-or-name)
|
|
|
281 "Retrieve the translation table of the given name.
|
|
|
282 Same as `find-translation-table' except an error is signalled if there is
|
|
|
283 no such translation table instead of returning nil."
|
|
|
284 (or (find-translation-table table-or-name)
|
|
|
285 (error 'invalid-argument "No such translation table" table-or-name)))
|
|
|
286
|
|
|
287
|
|
442
|
288 ;; Setup auto-fill-chars for charsets that should invoke auto-filling.
|
|
777
|
289 ;; SPACE and NEWLINE are already set.
|
|
442
|
290 (let ((l '(katakana-jisx0201
|
|
|
291 japanese-jisx0208 japanese-jisx0212
|
|
|
292 chinese-gb2312 chinese-big5-1 chinese-big5-2)))
|
|
|
293 (while l
|
|
|
294 (put-char-table (car l) t auto-fill-chars)
|
|
|
295 (setq l (cdr l))))
|
|
|
296
|
|
778
|
297
|
|
|
298 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
|
|
|
299 ; charsets ;
|
|
|
300 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
|
|
|
301
|
|
|
302 ;; Synched up with: FSF 21.1.
|
|
|
303
|
|
|
304 ;; All FSF charset definitions are in mule-conf.el. I copied the relevant
|
|
|
305 ;; part of that file below, then converted all charset definitions using
|
|
|
306 ;; the macro below, then globally replaced 'direction 0' with 'direction
|
|
|
307 ;; l2r' and 'direction 1' with 'direction r2l', then commented everything
|
|
|
308 ;; out. Copy the definitions as necessary to individual files.
|
|
|
309
|
|
|
310 ;; Kbd macro to convert from FSF-style define-charset to our make-charset.
|
|
|
311
|
|
|
312 ; (setq last-kbd-macro (read-kbd-macro
|
|
|
313 ; "<right> M-d make <M-right> M-d <home> <down> TAB '[dimension DEL SPC <M-right> RET TAB chars SPC <M-right> RET TAB columns SPC <M-right> RET TAB direction SPC <M-right> RET TAB final SPC <M-right> RET TAB graphic SPC <M-right> RET TAB short- name SPC <M-right> RET TAB long- name SPC <M-right> RET TAB <S-M-right> <f2> DEL TAB <end> ] <M-left> <end> SPC <f4> 3*<M-left> <left> <M-right> RET <down>"))
|
|
|
314
|
|
|
315 ;; Kbd macro to take one registry entry from the list of registry entries,
|
|
|
316 ;; find the appropriate make-charset call, and add the appropriate registry
|
|
|
317 ;; property.
|
|
|
318
|
|
|
319 ; (setq last-kbd-macro (read-kbd-macro
|
|
|
320 ; "3*<right> <S-M-right> C-x x 1 <right> <S-M-right> C-x x 2 <home> C-x r m foo RET <M-down> M-x sear TAB for TAB RET C-x g 1 RET C-s dimen RET <end> RET TAB 3*<backspace> registry SPC C-x g 2 C-x r b RET <down>"))
|
|
|
321
|
|
|
322 ;; List from FSF international/fontset.el of registries for charsets.
|
|
|
323
|
|
|
324 ;; latin-iso8859-1 "ISO8859-1"
|
|
|
325 ;; latin-iso8859-2 "ISO8859-2"
|
|
|
326 ;; latin-iso8859-3 "ISO8859-3"
|
|
|
327 ;; latin-iso8859-4 "ISO8859-4"
|
|
|
328 ;; thai-tis620 "TIS620"
|
|
|
329 ;; greek-iso8859-7 "ISO8859-7"
|
|
|
330 ;; arabic-iso8859-6 "ISO8859-6"
|
|
|
331 ;; hebrew-iso8859-8 "ISO8859-8"
|
|
|
332 ;; katakana-jisx0201 "JISX0201"
|
|
|
333 ;; latin-jisx0201 "JISX0201"
|
|
|
334 ;; cyrillic-iso8859-5 "ISO8859-5"
|
|
|
335 ;; latin-iso8859-9 "ISO8859-9"
|
|
|
336 ;; japanese-jisx0208-1978 "JISX0208.1978"
|
|
|
337 ;; chinese-gb2312 "GB2312.1980"
|
|
|
338 ;; japanese-jisx0208 "JISX0208.1990"
|
|
|
339 ;; korean-ksc5601 "KSC5601.1989"
|
|
|
340 ;; japanese-jisx0212 "JISX0212"
|
|
|
341 ;; chinese-cns11643-1 "CNS11643.1992-1"
|
|
|
342 ;; chinese-cns11643-2 "CNS11643.1992-2"
|
|
|
343 ;; chinese-cns11643-3 "CNS11643.1992-3"
|
|
|
344 ;; chinese-cns11643-4 "CNS11643.1992-4"
|
|
|
345 ;; chinese-cns11643-5 "CNS11643.1992-5"
|
|
|
346 ;; chinese-cns11643-6 "CNS11643.1992-6"
|
|
|
347 ;; chinese-cns11643-7 "CNS11643.1992-7"
|
|
|
348 ;; chinese-big5-1 "Big5"
|
|
|
349 ;; chinese-big5-2 "Big5"
|
|
|
350 ;; chinese-sisheng "sisheng_cwnn"
|
|
|
351 ;; vietnamese-viscii-lower "VISCII1.1"
|
|
|
352 ;; vietnamese-viscii-upper "VISCII1.1"
|
|
|
353 ;; arabic-digit "MuleArabic-0"
|
|
|
354 ;; arabic-1-column "MuleArabic-1"
|
|
|
355 ;; arabic-2-column "MuleArabic-2"
|
|
|
356 ;; ipa "MuleIPA"
|
|
|
357 ;; ethiopic "Ethiopic-Unicode"
|
|
|
358 ;; ascii-right-to-left "ISO8859-1"
|
|
|
359 ;; indian-is13194 "IS13194-Devanagari"
|
|
|
360 ;; indian-2-column "MuleIndian-2"
|
|
|
361 ;; indian-1-column "MuleIndian-1"
|
|
|
362 ;; lao "MuleLao-1"
|
|
|
363 ;; tibetan "MuleTibetan-2"
|
|
|
364 ;; tibetan-1-column "MuleTibetan-1"
|
|
|
365 ;; latin-iso8859-14 "ISO8859-14"
|
|
|
366 ;; latin-iso8859-15 "ISO8859-15"
|
|
|
367 ;; mule-unicode-0100-24ff "ISO10646-1"
|
|
|
368 ;; mule-unicode-2500-33ff "ISO10646-1"
|
|
|
369 ;; mule-unicode-e000-ffff "ISO10646-1"
|
|
|
370 ;; japanese-jisx0213-1 "JISX0213.2000-1"
|
|
|
371 ;; japanese-jisx0213-2 "JISX0213.2000-2"
|
|
|
372
|
|
|
373 ;;; Begin stuff from international/mule-conf.el.
|
|
|
374
|
|
|
375 ; ;;; Definitions of character sets.
|
|
|
376
|
|
|
377 ; ;; Basic (official) character sets. These character sets are treated
|
|
|
378 ; ;; efficiently with respect to buffer memory.
|
|
|
379
|
|
|
380 ; ;; Syntax:
|
|
|
381 ; ;; (define-charset CHARSET-ID CHARSET
|
|
|
382 ; ;; [ DIMENSION CHARS WIDTH DIRECTION ISO-FINAL-CHAR ISO-GRAPHIC-PLANE
|
|
|
383 ; ;; SHORT-NAME LONG-NAME DESCRIPTION ])
|
|
|
384 ; ;; ASCII charset is defined in src/charset.c as below.
|
|
|
385 ; ;; (define-charset 0 ascii
|
|
|
386 ; ;; [1 94 1 0 ?B 0 "ASCII" "ASCII" "ASCII (ISO646 IRV)"])
|
|
|
387
|
|
|
388 ; ;; 1-byte charsets. Valid range of CHARSET-ID is 128..143.
|
|
|
389
|
|
|
390 ; ;; CHARSET-ID 128 is not used.
|
|
|
391
|
|
|
392 ; ; An extra level of commenting means an official (done in C) charset.
|
|
|
393 ; ; (make-charset 'latin-iso8859-1
|
|
|
394 ; ; "Right-Hand Part of Latin Alphabet 1 (ISO/IEC 8859-1): ISO-IR-100"
|
|
|
395 ; ; '(dimension
|
|
|
396 ; ; 1
|
|
|
397 ; ; registry "ISO8859-1"
|
|
|
398 ; ; chars 96
|
|
|
399 ; ; columns 1
|
|
|
400 ; ; direction l2r
|
|
|
401 ; ; final ?A
|
|
|
402 ; ; graphic 1
|
|
|
403 ; ; short-name "RHP of Latin-1"
|
|
|
404 ; ; long-name "RHP of Latin-1 (ISO 8859-1): ISO-IR-100"
|
|
|
405 ; ; ))
|
|
|
406
|
|
|
407 ; ; (make-charset 'latin-iso8859-2
|
|
|
408 ; ; "Right-Hand Part of Latin Alphabet 2 (ISO/IEC 8859-2): ISO-IR-101"
|
|
|
409 ; ; '(dimension
|
|
|
410 ; ; 1
|
|
|
411 ; ; registry "ISO8859-2"
|
|
|
412 ; ; chars 96
|
|
|
413 ; ; columns 1
|
|
|
414 ; ; direction l2r
|
|
|
415 ; ; final ?B
|
|
|
416 ; ; graphic 1
|
|
|
417 ; ; short-name "RHP of Latin-2"
|
|
|
418 ; ; long-name "RHP of Latin-2 (ISO 8859-2): ISO-IR-101"
|
|
|
419 ; ; ))
|
|
|
420
|
|
|
421 ; ; (make-charset 'latin-iso8859-3
|
|
|
422 ; ; "Right-Hand Part of Latin Alphabet 3 (ISO/IEC 8859-3): ISO-IR-109"
|
|
|
423 ; ; '(dimension
|
|
|
424 ; ; 1
|
|
|
425 ; ; registry "ISO8859-3"
|
|
|
426 ; ; chars 96
|
|
|
427 ; ; columns 1
|
|
|
428 ; ; direction l2r
|
|
|
429 ; ; final ?C
|
|
|
430 ; ; graphic 1
|
|
|
431 ; ; short-name "RHP of Latin-3"
|
|
|
432 ; ; long-name "RHP of Latin-3 (ISO 8859-3): ISO-IR-109"
|
|
|
433 ; ; ))
|
|
|
434
|
|
|
435 ; ; (make-charset 'latin-iso8859-4
|
|
|
436 ; ; "Right-Hand Part of Latin Alphabet 4 (ISO/IEC 8859-4): ISO-IR-110"
|
|
|
437 ; ; '(dimension
|
|
|
438 ; ; 1
|
|
|
439 ; ; registry "ISO8859-4"
|
|
|
440 ; ; chars 96
|
|
|
441 ; ; columns 1
|
|
|
442 ; ; direction l2r
|
|
|
443 ; ; final ?D
|
|
|
444 ; ; graphic 1
|
|
|
445 ; ; short-name "RHP of Latin-4"
|
|
|
446 ; ; long-name "RHP of Latin-4 (ISO 8859-4): ISO-IR-110"
|
|
|
447 ; ; ))
|
|
|
448
|
|
|
449 ; ; (make-charset 'thai-tis620
|
|
|
450 ; ; "Right-Hand Part of TIS620.2533 (Thai): ISO-IR-166"
|
|
|
451 ; ; '(dimension
|
|
|
452 ; ; 1
|
|
|
453 ; ; registry "TIS620"
|
|
|
454 ; ; chars 96
|
|
|
455 ; ; columns 1
|
|
|
456 ; ; direction l2r
|
|
|
457 ; ; final ?T
|
|
|
458 ; ; graphic 1
|
|
|
459 ; ; short-name "RHP of TIS620"
|
|
|
460 ; ; long-name "RHP of Thai (TIS620): ISO-IR-166"
|
|
|
461 ; ; ))
|
|
|
462
|
|
|
463 ; ; (make-charset 'greek-iso8859-7
|
|
|
464 ; ; "Right-Hand Part of Latin/Greek Alphabet (ISO/IEC 8859-7): ISO-IR-126"
|
|
|
465 ; ; '(dimension
|
|
|
466 ; ; 1
|
|
|
467 ; ; registry "ISO8859-7"
|
|
|
468 ; ; chars 96
|
|
|
469 ; ; columns 1
|
|
|
470 ; ; direction l2r
|
|
|
471 ; ; final ?F
|
|
|
472 ; ; graphic 1
|
|
|
473 ; ; short-name "RHP of ISO8859/7"
|
|
|
474 ; ; long-name "RHP of Greek (ISO 8859-7): ISO-IR-126"
|
|
|
475 ; ; ))
|
|
|
476
|
|
|
477 ; ; (make-charset 'arabic-iso8859-6
|
|
|
478 ; ; "Right-Hand Part of Latin/Arabic Alphabet (ISO/IEC 8859-6): ISO-IR-127"
|
|
|
479 ; ; '(dimension
|
|
|
480 ; ; 1
|
|
|
481 ; ; registry "ISO8859-6"
|
|
|
482 ; ; chars 96
|
|
|
483 ; ; columns 1
|
|
|
484 ; ; direction r2l
|
|
|
485 ; ; final ?G
|
|
|
486 ; ; graphic 1
|
|
|
487 ; ; short-name "RHP of ISO8859/6"
|
|
|
488 ; ; long-name "RHP of Arabic (ISO 8859-6): ISO-IR-127"
|
|
|
489 ; ; ))
|
|
|
490
|
|
|
491 ; ; (make-charset 'hebrew-iso8859-8
|
|
|
492 ; ; "Right-Hand Part of Latin/Hebrew Alphabet (ISO/IEC 8859-8): ISO-IR-138"
|
|
|
493 ; ; '(dimension
|
|
|
494 ; ; 1
|
|
|
495 ; ; registry "ISO8859-8"
|
|
|
496 ; ; chars 96
|
|
|
497 ; ; columns 1
|
|
|
498 ; ; direction r2l
|
|
|
499 ; ; final ?H
|
|
|
500 ; ; graphic 1
|
|
|
501 ; ; short-name "RHP of ISO8859/8"
|
|
|
502 ; ; long-name "RHP of Hebrew (ISO 8859-8): ISO-IR-138"
|
|
|
503 ; ; ))
|
|
|
504
|
|
|
505 ; ; (make-charset 'katakana-jisx0201
|
|
|
506 ; ; "Katakana Part of JISX0201.1976"
|
|
|
507 ; ; '(dimension
|
|
|
508 ; ; 1
|
|
|
509 ; ; registry "JISX0201"
|
|
|
510 ; ; chars 94
|
|
|
511 ; ; columns 1
|
|
|
512 ; ; direction l2r
|
|
|
513 ; ; final ?I
|
|
|
514 ; ; graphic 1
|
|
|
515 ; ; short-name "JISX0201 Katakana"
|
|
|
516 ; ; long-name "Japanese Katakana (JISX0201.1976)"
|
|
|
517 ; ; ))
|
|
|
518
|
|
|
519 ; ; (make-charset 'latin-jisx0201
|
|
|
520 ; ; "Roman Part of JISX0201.1976"
|
|
|
521 ; ; '(dimension
|
|
|
522 ; ; 1
|
|
|
523 ; ; registry "JISX0201"
|
|
|
524 ; ; chars 94
|
|
|
525 ; ; columns 1
|
|
|
526 ; ; direction l2r
|
|
|
527 ; ; final ?J
|
|
|
528 ; ; graphic 0
|
|
|
529 ; ; short-name "JISX0201 Roman"
|
|
|
530 ; ; long-name "Japanese Roman (JISX0201.1976)"
|
|
|
531 ; ; ))
|
|
|
532
|
|
|
533
|
|
|
534 ; ;; CHARSET-ID is not used 139.
|
|
|
535
|
|
|
536 ; ; (make-charset 'cyrillic-iso8859-5
|
|
|
537 ; ; "Right-Hand Part of Latin/Cyrillic Alphabet (ISO/IEC 8859-5): ISO-IR-144"
|
|
|
538 ; ; '(dimension
|
|
|
539 ; ; 1
|
|
|
540 ; ; registry "ISO8859-5"
|
|
|
541 ; ; chars 96
|
|
|
542 ; ; columns 1
|
|
|
543 ; ; direction l2r
|
|
|
544 ; ; final ?L
|
|
|
545 ; ; graphic 1
|
|
|
546 ; ; short-name "RHP of ISO8859/5"
|
|
|
547 ; ; long-name "RHP of Cyrillic (ISO 8859-5): ISO-IR-144"
|
|
|
548 ; ; ))
|
|
|
549
|
|
|
550 ; ; (make-charset 'latin-iso8859-9
|
|
|
551 ; ; "Right-Hand Part of Latin Alphabet 5 (ISO/IEC 8859-9): ISO-IR-148"
|
|
|
552 ; ; '(dimension
|
|
|
553 ; ; 1
|
|
|
554 ; ; registry "ISO8859-9"
|
|
|
555 ; ; chars 96
|
|
|
556 ; ; columns 1
|
|
|
557 ; ; direction l2r
|
|
|
558 ; ; final ?M
|
|
|
559 ; ; graphic 1
|
|
|
560 ; ; short-name "RHP of Latin-5"
|
|
|
561 ; ; long-name "RHP of Latin-5 (ISO 8859-9): ISO-IR-148"
|
|
|
562 ; ; ))
|
|
|
563
|
|
|
564 ; ; (make-charset 'latin-iso8859-15
|
|
|
565 ; ; "Right-Hand Part of Latin Alphabet 9 (ISO/IEC 8859-15): ISO-IR-203"
|
|
|
566 ; ; '(dimension
|
|
|
567 ; ; 1
|
|
|
568 ; ; registry "ISO8859-15"
|
|
|
569 ; ; chars 96
|
|
|
570 ; ; columns 1
|
|
|
571 ; ; direction l2r
|
|
|
572 ; ; final ?b
|
|
|
573 ; ; graphic 1
|
|
|
574 ; ; short-name "RHP of Latin-9"
|
|
|
575 ; ; long-name "RHP of Latin-9 (ISO 8859-15): ISO-IR-203"
|
|
|
576 ; ; ))
|
|
|
577
|
|
|
578 ; (make-charset 'latin-iso8859-14
|
|
|
579 ; "Right-Hand Part of Latin Alphabet 8 (ISO/IEC 8859-14)"
|
|
|
580 ; '(dimension
|
|
|
581 ; 1
|
|
|
582 ; registry "ISO8859-14"
|
|
|
583 ; chars 96
|
|
|
584 ; columns 1
|
|
|
585 ; direction l2r
|
|
|
586 ; final ?_
|
|
|
587 ; graphic 1
|
|
|
588 ; short-name "RHP of Latin-8"
|
|
|
589 ; long-name "RHP of Latin-8 (ISO 8859-14)"
|
|
|
590 ; ))
|
|
|
591
|
|
|
592
|
|
|
593 ; ;; 2-byte charsets. Valid range of CHARSET-ID is 144..153.
|
|
|
594
|
|
|
595 ; ; (make-charset 'japanese-jisx0208-1978
|
|
|
596 ; ; "JISX0208.1978 Japanese Kanji (so called \"old JIS\"): ISO-IR-42"
|
|
|
597 ; ; '(dimension
|
|
|
598 ; ; 2
|
|
|
599 ; ; registry "JISX0208.1990"
|
|
|
600 ; ; registry "JISX0208.1978"
|
|
|
601 ; ; chars 94
|
|
|
602 ; ; columns 2
|
|
|
603 ; ; direction l2r
|
|
|
604 ; ; final ?@
|
|
|
605 ; ; graphic 0
|
|
|
606 ; ; short-name "JISX0208.1978"
|
|
|
607 ; ; long-name "JISX0208.1978 (Japanese): ISO-IR-42"
|
|
|
608 ; ; ))
|
|
|
609
|
|
|
610 ; ; (make-charset 'chinese-gb2312
|
|
|
611 ; ; "GB2312 Chinese simplified: ISO-IR-58"
|
|
|
612 ; ; '(dimension
|
|
|
613 ; ; 2
|
|
|
614 ; ; registry "GB2312.1980"
|
|
|
615 ; ; chars 94
|
|
|
616 ; ; columns 2
|
|
|
617 ; ; direction l2r
|
|
|
618 ; ; final ?A
|
|
|
619 ; ; graphic 0
|
|
|
620 ; ; short-name "GB2312"
|
|
|
621 ; ; long-name "GB2312: ISO-IR-58"
|
|
|
622 ; ; ))
|
|
|
623
|
|
|
624 ; ; (make-charset 'japanese-jisx0208
|
|
|
625 ; ; "JISX0208.1983/1990 Japanese Kanji: ISO-IR-87"
|
|
|
626 ; ; '(dimension
|
|
|
627 ; ; 2
|
|
|
628 ; ; chars 94
|
|
|
629 ; ; columns 2
|
|
|
630 ; ; direction l2r
|
|
|
631 ; ; final ?B
|
|
|
632 ; ; graphic 0
|
|
|
633 ; ; short-name "JISX0208"
|
|
|
634 ; ; long-name "JISX0208.1983/1990 (Japanese): ISO-IR-87"
|
|
|
635 ; ; ))
|
|
|
636
|
|
|
637 ; ; (make-charset 'korean-ksc5601
|
|
|
638 ; ; "KSC5601 Korean Hangul and Hanja: ISO-IR-149"
|
|
|
639 ; ; '(dimension
|
|
|
640 ; ; 2
|
|
|
641 ; ; registry "KSC5601.1989"
|
|
|
642 ; ; chars 94
|
|
|
643 ; ; columns 2
|
|
|
644 ; ; direction l2r
|
|
|
645 ; ; final ?C
|
|
|
646 ; ; graphic 0
|
|
|
647 ; ; short-name "KSC5601"
|
|
|
648 ; ; long-name "KSC5601 (Korean): ISO-IR-149"
|
|
|
649 ; ; ))
|
|
|
650
|
|
|
651 ; ; (make-charset 'japanese-jisx0212
|
|
|
652 ; ; "JISX0212 Japanese supplement: ISO-IR-159"
|
|
|
653 ; ; '(dimension
|
|
|
654 ; ; 2
|
|
|
655 ; ; registry "JISX0212"
|
|
|
656 ; ; chars 94
|
|
|
657 ; ; columns 2
|
|
|
658 ; ; direction l2r
|
|
|
659 ; ; final ?D
|
|
|
660 ; ; graphic 0
|
|
|
661 ; ; short-name "JISX0212"
|
|
|
662 ; ; long-name "JISX0212 (Japanese): ISO-IR-159"
|
|
|
663 ; ; ))
|
|
|
664
|
|
|
665 ; ; (make-charset 'chinese-cns11643-1
|
|
|
666 ; ; "CNS11643 Plane 1 Chinese traditional: ISO-IR-171"
|
|
|
667 ; ; '(dimension
|
|
|
668 ; ; 2
|
|
|
669 ; ; registry "CNS11643.1992-1"
|
|
|
670 ; ; chars 94
|
|
|
671 ; ; columns 2
|
|
|
672 ; ; direction l2r
|
|
|
673 ; ; final ?G
|
|
|
674 ; ; graphic 0
|
|
|
675 ; ; short-name "CNS11643-1"
|
|
|
676 ; ; long-name "CNS11643-1 (Chinese traditional): ISO-IR-171"
|
|
|
677 ; ; ))
|
|
|
678
|
|
|
679 ; ; (make-charset 'chinese-cns11643-2
|
|
|
680 ; ; "CNS11643 Plane 2 Chinese traditional: ISO-IR-172"
|
|
|
681 ; ; '(dimension
|
|
|
682 ; ; 2
|
|
|
683 ; ; registry "CNS11643.1992-2"
|
|
|
684 ; ; chars 94
|
|
|
685 ; ; columns 2
|
|
|
686 ; ; direction l2r
|
|
|
687 ; ; final ?H
|
|
|
688 ; ; graphic 0
|
|
|
689 ; ; short-name "CNS11643-2"
|
|
|
690 ; ; long-name "CNS11643-2 (Chinese traditional): ISO-IR-172"
|
|
|
691 ; ; ))
|
|
|
692
|
|
|
693 ; (make-charset 'japanese-jisx0213-1 "JISX0213 Plane 1 (Japanese)"
|
|
|
694 ; '(dimension
|
|
|
695 ; 2
|
|
|
696 ; registry "JISX0213.2000-1"
|
|
|
697 ; chars 94
|
|
|
698 ; columns 2
|
|
|
699 ; direction l2r
|
|
|
700 ; final ?O
|
|
|
701 ; graphic 0
|
|
|
702 ; short-name "JISX0213-1"
|
|
|
703 ; long-name "JISX0213-1"
|
|
|
704 ; ))
|
|
|
705
|
|
|
706 ; ; (make-charset 'chinese-big5-1
|
|
|
707 ; ; "Frequently used part (A141-C67F) of Big5 (Chinese traditional)"
|
|
|
708 ; ; '(dimension
|
|
|
709 ; ; 2
|
|
|
710 ; ; registry "Big5"
|
|
|
711 ; ; chars 94
|
|
|
712 ; ; columns 2
|
|
|
713 ; ; direction l2r
|
|
|
714 ; ; final ?0
|
|
|
715 ; ; graphic 0
|
|
|
716 ; ; short-name "Big5 (Level-1)"
|
|
|
717 ; ; long-name "Big5 (Level-1) A141-C67F"
|
|
|
718 ; ; ))
|
|
|
719
|
|
|
720 ; ; (make-charset 'chinese-big5-2
|
|
|
721 ; ; "Less frequently used part (C940-FEFE) of Big5 (Chinese traditional)"
|
|
|
722 ; ; '(dimension
|
|
|
723 ; ; 2
|
|
|
724 ; ; registry "Big5"
|
|
|
725 ; ; chars 94
|
|
|
726 ; ; columns 2
|
|
|
727 ; ; direction l2r
|
|
|
728 ; ; final ?1
|
|
|
729 ; ; graphic 0
|
|
|
730 ; ; short-name "Big5 (Level-2)"
|
|
|
731 ; ; long-name "Big5 (Level-2) C940-FEFE"
|
|
|
732 ; ; ))
|
|
|
733
|
|
|
734
|
|
|
735 ; ;; Additional (private) character sets. These character sets are
|
|
|
736 ; ;; treated less space-efficiently in the buffer.
|
|
|
737
|
|
|
738 ; ;; Syntax:
|
|
|
739 ; ;; (define-charset CHARSET-ID CHARSET
|
|
|
740 ; ;; [ DIMENSION CHARS WIDTH DIRECTION ISO-FINAL-CHAR ISO-GRAPHIC-PLANE
|
|
|
741 ; ;; SHORT-NAME LONG-NAME DESCRIPTION ])
|
|
|
742
|
|
|
743 ; ;; ISO-2022 allows a use of character sets not registered in ISO with
|
|
|
744 ; ;; final characters `0' (0x30) through `?' (0x3F). Among them, Emacs
|
|
|
745 ; ;; reserves `0' through `9' to support several private character sets.
|
|
|
746 ; ;; The remaining final characters `:' through `?' are for users.
|
|
|
747
|
|
|
748 ; ;; 1-byte 1-column charsets. Valid range of CHARSET-ID is 160..223.
|
|
|
749
|
|
|
750 ; (make-charset 'chinese-sisheng
|
|
|
751 ; "SiSheng characters for PinYin/ZhuYin"
|
|
|
752 ; '(dimension
|
|
|
753 ; 1
|
|
|
754 ; registry "sisheng_cwnn"
|
|
|
755 ; chars 94
|
|
|
756 ; columns 1
|
|
|
757 ; direction l2r
|
|
|
758 ; final ?0
|
|
|
759 ; graphic 0
|
|
|
760 ; short-name "SiSheng"
|
|
|
761 ; long-name "SiSheng (PinYin/ZhuYin)"
|
|
|
762 ; ))
|
|
|
763
|
|
|
764
|
|
|
765 ; ;; IPA characters for phonetic symbols.
|
|
|
766 ; (make-charset 'ipa "IPA (International Phonetic Association)"
|
|
|
767 ; '(dimension
|
|
|
768 ; 1
|
|
|
769 ; registry "MuleIPA"
|
|
|
770 ; chars 96
|
|
|
771 ; columns 1
|
|
|
772 ; direction l2r
|
|
|
773 ; final ?0
|
|
|
774 ; graphic 1
|
|
|
775 ; short-name "IPA"
|
|
|
776 ; long-name "IPA"
|
|
|
777 ; ))
|
|
|
778
|
|
|
779
|
|
|
780 ; ;; Vietnamese VISCII. VISCII is 1-byte character set which contains
|
|
|
781 ; ;; more than 96 characters. Since Emacs can't handle it as one
|
|
|
782 ; ;; character set, it is divided into two: lower case letters and upper
|
|
|
783 ; ;; case letters.
|
|
|
784 ; (make-charset 'vietnamese-viscii-lower "VISCII1.1 lower-case"
|
|
|
785 ; '(dimension
|
|
|
786 ; 1
|
|
|
787 ; registry "VISCII1.1"
|
|
|
788 ; chars 96
|
|
|
789 ; columns 1
|
|
|
790 ; direction l2r
|
|
|
791 ; final ?1
|
|
|
792 ; graphic 1
|
|
|
793 ; short-name "VISCII lower"
|
|
|
794 ; long-name "VISCII lower-case"
|
|
|
795 ; ))
|
|
|
796
|
|
|
797 ; (make-charset 'vietnamese-viscii-upper "VISCII1.1 upper-case"
|
|
|
798 ; '(dimension
|
|
|
799 ; 1
|
|
|
800 ; registry "VISCII1.1"
|
|
|
801 ; chars 96
|
|
|
802 ; columns 1
|
|
|
803 ; direction l2r
|
|
|
804 ; final ?2
|
|
|
805 ; graphic 1
|
|
|
806 ; short-name "VISCII upper"
|
|
|
807 ; long-name "VISCII upper-case"
|
|
|
808 ; ))
|
|
|
809
|
|
|
810
|
|
|
811 ; ;; For Arabic, we need three different types of character sets.
|
|
|
812 ; ;; Digits are of direction left-to-right and of width 1-column.
|
|
|
813 ; ;; Others are of direction right-to-left and of width 1-column or
|
|
|
814 ; ;; 2-column.
|
|
|
815 ; (make-charset 'arabic-digit "Arabic digit"
|
|
|
816 ; '(dimension
|
|
|
817 ; 1
|
|
|
818 ; registry "MuleArabic-0"
|
|
|
819 ; chars 94
|
|
|
820 ; columns 1
|
|
|
821 ; direction l2r
|
|
|
822 ; final ?2
|
|
|
823 ; graphic 0
|
|
|
824 ; short-name "Arabic digit"
|
|
|
825 ; long-name "Arabic digit"
|
|
|
826 ; ))
|
|
|
827
|
|
|
828 ; (make-charset 'arabic-1-column "Arabic 1-column"
|
|
|
829 ; '(dimension
|
|
|
830 ; 1
|
|
|
831 ; registry "MuleArabic-1"
|
|
|
832 ; chars 94
|
|
|
833 ; columns 1
|
|
|
834 ; direction r2l
|
|
|
835 ; final ?3
|
|
|
836 ; graphic 0
|
|
|
837 ; short-name "Arabic 1-col"
|
|
|
838 ; long-name "Arabic 1-column"
|
|
|
839 ; ))
|
|
|
840
|
|
|
841
|
|
|
842 ; ;; ASCII with right-to-left direction.
|
|
|
843 ; (make-charset 'ascii-right-to-left
|
|
|
844 ; "ASCII (left half of ISO 8859-1) with right-to-left direction"
|
|
|
845 ; '(dimension
|
|
|
846 ; 1
|
|
|
847 ; registry "ISO8859-1"
|
|
|
848 ; chars 94
|
|
|
849 ; columns 1
|
|
|
850 ; direction r2l
|
|
|
851 ; final ?B
|
|
|
852 ; graphic 0
|
|
|
853 ; short-name "rev ASCII"
|
|
|
854 ; long-name "ASCII with right-to-left direction"
|
|
|
855 ; ))
|
|
|
856
|
|
|
857
|
|
|
858 ; ;; Lao script.
|
|
|
859 ; ;; ISO10646's 0x0E80..0x0EDF are mapped to 0x20..0x7F.
|
|
|
860 ; (make-charset 'lao "Lao characters (ISO10646 0E80..0EDF)"
|
|
|
861 ; '(dimension
|
|
|
862 ; 1
|
|
|
863 ; registry "MuleLao-1"
|
|
|
864 ; chars 94
|
|
|
865 ; columns 1
|
|
|
866 ; direction l2r
|
|
|
867 ; final ?1
|
|
|
868 ; graphic 0
|
|
|
869 ; short-name "Lao"
|
|
|
870 ; long-name "Lao"
|
|
|
871 ; ))
|
|
|
872
|
|
|
873
|
|
|
874 ; ;; CHARSET-IDs 168..223 are not used.
|
|
|
875
|
|
|
876 ; ;; 1-byte 2-column charsets. Valid range of CHARSET-ID is 224..239.
|
|
|
877
|
|
|
878 ; (make-charset 'arabic-2-column "Arabic 2-column"
|
|
|
879 ; '(dimension
|
|
|
880 ; 1
|
|
|
881 ; registry "MuleArabic-2"
|
|
|
882 ; chars 94
|
|
|
883 ; columns 2
|
|
|
884 ; direction r2l
|
|
|
885 ; final ?4
|
|
|
886 ; graphic 0
|
|
|
887 ; short-name "Arabic 2-col"
|
|
|
888 ; long-name "Arabic 2-column"
|
|
|
889 ; ))
|
|
|
890
|
|
|
891
|
|
|
892 ; ;; Indian scripts. Symbolic charset for data exchange. Glyphs are
|
|
|
893 ; ;; not assigned. They are automatically converted to each Indian
|
|
|
894 ; ;; script which IS-13194 supports.
|
|
|
895
|
|
|
896 ; (make-charset 'indian-is13194
|
|
|
897 ; "Generic Indian charset for data exchange with IS 13194"
|
|
|
898 ; '(dimension
|
|
|
899 ; 1
|
|
|
900 ; registry "IS13194-Devanagari"
|
|
|
901 ; chars 94
|
|
|
902 ; columns 2
|
|
|
903 ; direction l2r
|
|
|
904 ; final ?5
|
|
|
905 ; graphic 1
|
|
|
906 ; short-name "IS 13194"
|
|
|
907 ; long-name "Indian IS 13194"
|
|
|
908 ; ))
|
|
|
909
|
|
|
910
|
|
|
911 ; ;; CHARSET-IDs 226..239 are not used.
|
|
|
912
|
|
|
913 ; ;; 2-byte 1-column charsets. Valid range of CHARSET-ID is 240..244.
|
|
|
914
|
|
|
915 ; ;; Actual Glyph for 1-column width.
|
|
|
916 ; (make-charset 'indian-1-column
|
|
|
917 ; "Indian charset for 2-column width glyphs"
|
|
|
918 ; '(dimension
|
|
|
919 ; 2
|
|
|
920 ; registry "MuleIndian-1"
|
|
|
921 ; chars 94
|
|
|
922 ; columns 1
|
|
|
923 ; direction l2r
|
|
|
924 ; final ?6
|
|
|
925 ; graphic 0
|
|
|
926 ; short-name "Indian 1-col"
|
|
|
927 ; long-name "Indian 1 Column"
|
|
|
928 ; ))
|
|
|
929
|
|
|
930
|
|
|
931 ; (make-charset 'tibetan-1-column "Tibetan 1 column glyph"
|
|
|
932 ; '(dimension
|
|
|
933 ; 2
|
|
|
934 ; registry "MuleTibetan-1"
|
|
|
935 ; chars 94
|
|
|
936 ; columns 1
|
|
|
937 ; direction l2r
|
|
|
938 ; final ?8
|
|
|
939 ; graphic 0
|
|
|
940 ; short-name "Tibetan 1-col"
|
|
|
941 ; long-name "Tibetan 1 column"
|
|
|
942 ; ))
|
|
|
943
|
|
|
944
|
|
|
945 ; ;; Subsets of Unicode.
|
|
|
946
|
|
|
947 ; (make-charset 'mule-unicode-2500-33ff
|
|
|
948 ; "Unicode characters of the range U+2500..U+33FF."
|
|
|
949 ; '(dimension
|
|
|
950 ; 2
|
|
|
951 ; registry "ISO10646-1"
|
|
|
952 ; chars 96
|
|
|
953 ; columns 1
|
|
|
954 ; direction l2r
|
|
|
955 ; final ?2
|
|
|
956 ; graphic 0
|
|
|
957 ; short-name "Unicode subset 2"
|
|
|
958 ; long-name "Unicode subset (U+2500..U+33FF)"
|
|
|
959 ; ))
|
|
|
960
|
|
|
961
|
|
|
962 ; (make-charset 'mule-unicode-e000-ffff
|
|
|
963 ; "Unicode characters of the range U+E000..U+FFFF."
|
|
|
964 ; '(dimension
|
|
|
965 ; 2
|
|
|
966 ; registry "ISO10646-1"
|
|
|
967 ; chars 96
|
|
|
968 ; columns 1
|
|
|
969 ; direction l2r
|
|
|
970 ; final ?3
|
|
|
971 ; graphic 0
|
|
|
972 ; short-name "Unicode subset 3"
|
|
|
973 ; long-name "Unicode subset (U+E000+FFFF)"
|
|
|
974 ; ))
|
|
|
975
|
|
|
976
|
|
|
977 ; (make-charset 'mule-unicode-0100-24ff
|
|
|
978 ; "Unicode characters of the range U+0100..U+24FF."
|
|
|
979 ; '(dimension
|
|
|
980 ; 2
|
|
|
981 ; registry "ISO10646-1"
|
|
|
982 ; chars 96
|
|
|
983 ; columns 1
|
|
|
984 ; direction l2r
|
|
|
985 ; final ?1
|
|
|
986 ; graphic 0
|
|
|
987 ; short-name "Unicode subset"
|
|
|
988 ; long-name "Unicode subset (U+0100..U+24FF)"
|
|
|
989 ; ))
|
|
|
990
|
|
|
991
|
|
|
992 ; ;; 2-byte 2-column charsets. Valid range of CHARSET-ID is 245..254.
|
|
|
993
|
|
|
994 ; ;; Ethiopic characters (Amahric and Tigrigna).
|
|
|
995 ; (make-charset 'ethiopic "Ethiopic characters"
|
|
|
996 ; '(dimension
|
|
|
997 ; 2
|
|
|
998 ; registry "Ethiopic-Unicode"
|
|
|
999 ; chars 94
|
|
|
1000 ; columns 2
|
|
|
1001 ; direction l2r
|
|
|
1002 ; final ?3
|
|
|
1003 ; graphic 0
|
|
|
1004 ; short-name "Ethiopic"
|
|
|
1005 ; long-name "Ethiopic characters"
|
|
|
1006 ; ))
|
|
|
1007
|
|
|
1008
|
|
|
1009 ; ;; Chinese CNS11643 Plane3 thru Plane7. Although these are official
|
|
|
1010 ; ;; character sets, the use is rare and don't have to be treated
|
|
|
1011 ; ;; space-efficiently in the buffer.
|
|
|
1012 ; (make-charset 'chinese-cns11643-3
|
|
|
1013 ; "CNS11643 Plane 3 Chinese Traditional: ISO-IR-183"
|
|
|
1014 ; '(dimension
|
|
|
1015 ; 2
|
|
|
1016 ; registry "CNS11643.1992-3"
|
|
|
1017 ; chars 94
|
|
|
1018 ; columns 2
|
|
|
1019 ; direction l2r
|
|
|
1020 ; final ?I
|
|
|
1021 ; graphic 0
|
|
|
1022 ; short-name "CNS11643-3"
|
|
|
1023 ; long-name "CNS11643-3 (Chinese traditional): ISO-IR-183"
|
|
|
1024 ; ))
|
|
|
1025
|
|
|
1026 ; (make-charset 'chinese-cns11643-4
|
|
|
1027 ; "CNS11643 Plane 4 Chinese Traditional: ISO-IR-184"
|
|
|
1028 ; '(dimension
|
|
|
1029 ; 2
|
|
|
1030 ; registry "CNS11643.1992-4"
|
|
|
1031 ; chars 94
|
|
|
1032 ; columns 2
|
|
|
1033 ; direction l2r
|
|
|
1034 ; final ?J
|
|
|
1035 ; graphic 0
|
|
|
1036 ; short-name "CNS11643-4"
|
|
|
1037 ; long-name "CNS11643-4 (Chinese traditional): ISO-IR-184"
|
|
|
1038 ; ))
|
|
|
1039
|
|
|
1040 ; (make-charset 'chinese-cns11643-5
|
|
|
1041 ; "CNS11643 Plane 5 Chinese Traditional: ISO-IR-185"
|
|
|
1042 ; '(dimension
|
|
|
1043 ; 2
|
|
|
1044 ; registry "CNS11643.1992-5"
|
|
|
1045 ; chars 94
|
|
|
1046 ; columns 2
|
|
|
1047 ; direction l2r
|
|
|
1048 ; final ?K
|
|
|
1049 ; graphic 0
|
|
|
1050 ; short-name "CNS11643-5"
|
|
|
1051 ; long-name "CNS11643-5 (Chinese traditional): ISO-IR-185"
|
|
|
1052 ; ))
|
|
|
1053
|
|
|
1054 ; (make-charset 'chinese-cns11643-6
|
|
|
1055 ; "CNS11643 Plane 6 Chinese Traditional: ISO-IR-186"
|
|
|
1056 ; '(dimension
|
|
|
1057 ; 2
|
|
|
1058 ; registry "CNS11643.1992-6"
|
|
|
1059 ; chars 94
|
|
|
1060 ; columns 2
|
|
|
1061 ; direction l2r
|
|
|
1062 ; final ?L
|
|
|
1063 ; graphic 0
|
|
|
1064 ; short-name "CNS11643-6"
|
|
|
1065 ; long-name "CNS11643-6 (Chinese traditional): ISO-IR-186"
|
|
|
1066 ; ))
|
|
|
1067
|
|
|
1068 ; (make-charset 'chinese-cns11643-7
|
|
|
1069 ; "CNS11643 Plane 7 Chinese Traditional: ISO-IR-187"
|
|
|
1070 ; '(dimension
|
|
|
1071 ; 2
|
|
|
1072 ; registry "CNS11643.1992-7"
|
|
|
1073 ; chars 94
|
|
|
1074 ; columns 2
|
|
|
1075 ; direction l2r
|
|
|
1076 ; final ?M
|
|
|
1077 ; graphic 0
|
|
|
1078 ; short-name "CNS11643-7"
|
|
|
1079 ; long-name "CNS11643-7 (Chinese traditional): ISO-IR-187"
|
|
|
1080 ; ))
|
|
|
1081
|
|
|
1082
|
|
|
1083 ; ;; Actual Glyph for 2-column width.
|
|
|
1084 ; (make-charset 'indian-2-column
|
|
|
1085 ; "Indian charset for 2-column width glyphs"
|
|
|
1086 ; '(dimension
|
|
|
1087 ; 2
|
|
|
1088 ; registry "MuleIndian-2"
|
|
|
1089 ; chars 94
|
|
|
1090 ; columns 2
|
|
|
1091 ; direction l2r
|
|
|
1092 ; final ?5
|
|
|
1093 ; graphic 0
|
|
|
1094 ; short-name "Indian 2-col"
|
|
|
1095 ; long-name "Indian 2 Column"
|
|
|
1096 ; ))
|
|
|
1097
|
|
|
1098
|
|
|
1099 ; ;; Tibetan script.
|
|
|
1100 ; (make-charset 'tibetan "Tibetan characters"
|
|
|
1101 ; '(dimension
|
|
|
1102 ; 2
|
|
|
1103 ; registry "MuleTibetan-2"
|
|
|
1104 ; chars 94
|
|
|
1105 ; columns 2
|
|
|
1106 ; direction l2r
|
|
|
1107 ; final ?7
|
|
|
1108 ; graphic 0
|
|
|
1109 ; short-name "Tibetan 2-col"
|
|
|
1110 ; long-name "Tibetan 2 column"
|
|
|
1111 ; ))
|
|
|
1112
|
|
|
1113
|
|
|
1114 ; ;; CHARSET-ID 253 is not used.
|
|
|
1115
|
|
|
1116 ; ;; JISX0213 Plane 2
|
|
|
1117 ; (make-charset 'japanese-jisx0213-2 "JISX0213 Plane 2 (Japanese)"
|
|
|
1118 ; '(dimension
|
|
|
1119 ; 2
|
|
|
1120 ; registry "JISX0213.2000-2"
|
|
|
1121 ; chars 94
|
|
|
1122 ; columns 2
|
|
|
1123 ; direction l2r
|
|
|
1124 ; final ?P
|
|
|
1125 ; graphic 0
|
|
|
1126 ; short-name "JISX0213-2"
|
|
|
1127 ; long-name "JISX0213-2"
|
|
|
1128 ; ))
|
|
|
1129
|
|
428
|
1130 ;;; mule-charset.el ends here
|
|
778
|
1131
|
