1 ;;; char-db-util.el --- Character Database utility
3 ;; Copyright (C) 1998,1999,2000 MORIOKA Tomohiko.
5 ;; Author: MORIOKA Tomohiko <tomo@kanji.zinbun.kyoto-u.ac.jp>
6 ;; Keywords: UTF-2000, ISO/IEC 10646, Unicode, UCS-4, MULE.
8 ;; This file is part of UTF-2000.
10 ;; UTF-2000 is free software; you can redistribute it and/or modify it
11 ;; 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 ;; UTF-2000 is distributed in the hope that it will be useful, but
16 ;; WITHOUT ANY WARRANTY; without even the implied warranty of
17 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
18 ;; General Public License for more details.
20 ;; You should have received a copy of the GNU General Public License
21 ;; along with XEmacs; see the file COPYING. If not, write to the Free
22 ;; Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
29 (defconst unidata-normative-category-alist
30 '(("Lu" letter uppercase)
31 ("Ll" letter lowercase)
32 ("Lt" letter titlecase)
33 ("Mn" mark non-spacing)
34 ("Mc" mark spacing-combining)
36 ("Nd" number decimal-digit)
39 ("Zs" separator space)
41 ("Zp" separator paragraph)
44 ("Cs" other surrogate)
45 ("Co" other private-use)
46 ("Cn" other not-assigned)))
48 (defconst unidata-informative-category-alist
49 '(("Lm" letter modifier)
51 ("Pc" punctuation connector)
52 ("Pd" punctuation dash)
53 ("Ps" punctuation open)
54 ("Pe" punctuation close)
55 ("Pi" punctuation initial-quote)
56 ("Pf" punctuation final-quote)
57 ("Po" punctuation other)
59 ("Sc" symbol currency)
60 ("Sk" symbol modifier)
64 (defconst ideographic-radicals
65 (let ((v (make-vector 215 nil))
68 (aset v i (int-char (+ #x2EFF i)))
70 (if (< (charset-iso-final-char (car (split-char (aref v 34)))) ?0)
71 (aset v 34 (make-char 'chinese-gb2312 #x62 #x3A)))
74 (defun char-attribute-name< (ka kb)
80 ((= (charset-dimension ka)
81 (charset-dimension kb))
82 (cond ((= (charset-chars ka)(charset-chars kb))
84 ((>= (charset-iso-final-char ka) ?@)
85 (if (>= (charset-iso-final-char kb) ?@)
86 (< (charset-iso-final-char ka)
87 (charset-iso-final-char kb))
89 ((>= (charset-iso-final-char ka) ?0)
91 ((>= (charset-iso-final-char kb) ?@)
93 ((>= (charset-iso-final-char kb) ?0)
94 (< (charset-iso-final-char ka)
95 (charset-iso-final-char kb)))
97 ((<= (charset-chars ka)(charset-chars kb)))))
99 (< (charset-dimension ka)
100 (charset-dimension kb))
110 (string< (symbol-name ka)
116 (defun insert-char-data (char &optional readable
117 attributes ccs-attributes)
120 (copy-sequence attributes)
121 (sort (char-attribute-list) #'char-attribute-name<)))
124 (copy-sequence ccs-attributes)
125 (sort (charset-list) #'char-attribute-name<)))
126 (let (name value has-long-ccs-name rest
129 (narrow-to-region (point)(point))
130 (insert "(define-char
132 (when (setq value (get-char-attribute char 'name))
134 (if (> (length value) 47)
140 (setq attributes (delq 'name attributes))
142 (when (setq value (get-char-attribute char 'script))
143 (insert (format "(script\t\t%s)
145 (mapconcat (function prin1-to-string)
147 (setq attributes (delq 'script attributes))
149 (when (setq value (get-char-attribute char '->ucs))
150 (insert (format "(->ucs\t\t. #x%04X)\t; %c
152 value (decode-char 'ucs value)))
153 (setq attributes (delq '->ucs attributes))
155 (when (setq value (get-char-attribute char 'general-category))
157 "(general-category\t%s) ; %s
159 (mapconcat (lambda (cell)
162 (cond ((rassoc value unidata-normative-category-alist)
163 "Normative Category")
164 ((rassoc value unidata-informative-category-alist)
165 "Informative Category")
167 "Unknown Category"))))
168 (setq attributes (delq 'general-category attributes))
170 (when (setq value (get-char-attribute char 'bidi-category))
171 (insert (format "(bidi-category\t. %S)
174 (setq attributes (delq 'bidi-category attributes))
176 (when (setq value (get-char-attribute char 'mirrored))
177 (insert (format "(mirrored\t\t. %S)
180 (setq attributes (delq 'mirrored attributes))
183 ((setq value (get-char-attribute char 'decimal-digit-value))
184 (insert (format "(decimal-digit-value . %S)
187 (setq attributes (delq 'decimal-digit-value attributes))
188 (when (setq value (get-char-attribute char 'digit-value))
189 (insert (format "(digit-value\t . %S)
192 (setq attributes (delq 'digit-value attributes))
194 (when (setq value (get-char-attribute char 'numeric-value))
195 (insert (format "(numeric-value\t . %S)
198 (setq attributes (delq 'numeric-value attributes))
202 (when (setq value (get-char-attribute char 'digit-value))
203 (insert (format "(digit-value\t. %S)
206 (setq attributes (delq 'digit-value attributes))
208 (when (setq value (get-char-attribute char 'numeric-value))
209 (insert (format "(numeric-value\t. %S)
212 (setq attributes (delq 'numeric-value attributes))
214 (when (setq value (get-char-attribute char 'iso-10646-comment))
215 (insert (format "(iso-10646-comment\t. %S)
218 (setq attributes (delq 'iso-10646-comment attributes))
220 (when (setq value (get-char-attribute char 'morohashi-daikanwa))
221 (insert (format "(morohashi-daikanwa\t%s)
223 (mapconcat (function prin1-to-string) value " ")))
224 (setq attributes (delq 'morohashi-daikanwa attributes))
228 (when (setq value (get-char-attribute char 'ideographic-radical))
230 (insert (format "(ideographic-radical . %S)\t; %c
233 (aref ideographic-radicals radical)))
234 (setq attributes (delq 'ideographic-radical attributes))
236 (when (setq value (get-char-attribute char 'ideographic-strokes))
238 (insert (format "(ideographic-strokes . %S)
241 (setq attributes (delq 'ideographic-strokes attributes))
243 (when (setq value (get-char-attribute char 'kangxi-radical))
244 (unless (eq value radical)
245 (insert (format "(kangxi-radical\t . %S)\t; %c
248 (aref ideographic-radicals value)))
250 (setq radical value)))
251 (setq attributes (delq 'kangxi-radical attributes))
253 (when (setq value (get-char-attribute char 'kangxi-strokes))
254 (unless (eq value strokes)
255 (insert (format "(kangxi-strokes\t . %S)
259 (setq strokes value)))
260 (setq attributes (delq 'kangxi-strokes attributes))
262 (when (setq value (get-char-attribute char 'japanese-radical))
263 (unless (eq value radical)
264 (insert (format "(japanese-radical\t . %S)\t; %c
267 (aref ideographic-radicals value)))
269 (setq radical value)))
270 (setq attributes (delq 'japanese-radical attributes))
272 (when (setq value (get-char-attribute char 'japanese-strokes))
273 (unless (eq value strokes)
274 (insert (format "(japanese-strokes\t . %S)
278 (setq strokes value)))
279 (setq attributes (delq 'japanese-strokes attributes))
281 (when (setq value (get-char-attribute char 'cns-radical))
282 (insert (format "(cns-radical\t . %S)\t; %c
285 (aref ideographic-radicals value)))
286 (setq attributes (delq 'cns-radical attributes))
288 (when (setq value (get-char-attribute char 'cns-strokes))
289 (unless (eq value strokes)
290 (insert (format "(cns-strokes\t . %S)
294 (setq strokes value)))
295 (setq attributes (delq 'cns-strokes attributes))
297 (when (setq value (get-char-attribute char 'shinjigen-1-radical))
298 (unless (eq value radical)
299 (insert (format "(shinjigen-1-radical . %S)\t; %c
302 (aref ideographic-radicals value)))
304 (setq radical value)))
305 (setq attributes (delq 'shinjigen-1-radical attributes))
307 (when (setq value (get-char-attribute char 'total-strokes))
308 (insert (format "(total-strokes\t . %S)
311 (setq attributes (delq 'total-strokes attributes))
313 (when (setq value (get-char-attribute char '->ideograph))
314 (insert (format "(->ideograph\t%s)
316 (mapconcat (lambda (code)
317 (cond ((symbolp code)
320 (format "#x%04X" code))
322 (format "\n %S" code))))
324 (setq attributes (delq '->ideograph attributes))
326 (when (setq value (get-char-attribute char '->decomposition))
327 (insert (format "(->decomposition\t%s)
329 (mapconcat (lambda (code)
330 (cond ((symbolp code)
339 (format "#x%04X" code))
341 (format "\n %S" code))))
343 (setq attributes (delq '->decomposition attributes))
345 (when (setq value (get-char-attribute char '->uppercase))
346 (insert (format "(->uppercase\t%s)
348 (mapconcat (lambda (code)
349 (cond ((symbolp code)
352 (format "#x%04X" code))
354 (format "\n %S" code))))
356 (setq attributes (delq '->uppercase attributes))
358 (when (setq value (get-char-attribute char '->lowercase))
359 (insert (format "(->lowercase\t%s)
361 (mapconcat (lambda (code)
362 (cond ((symbolp code)
365 (format "#x%04X" code))
367 (format "\n %S" code))))
369 (setq attributes (delq '->lowercase attributes))
371 (when (setq value (get-char-attribute char '->titlecase))
372 (insert (format "(->titlecase\t%s)
374 (mapconcat (lambda (code)
375 (cond ((symbolp code)
378 (format "#x%04X" code))
380 (format "\n %S" code))))
382 (setq attributes (delq '->titlecase attributes))
384 (when (setq value (get-char-attribute char '->mojikyo))
385 (insert (format "(->mojikyo\t\t. %06d)\t; %c
387 value (decode-char 'mojikyo value)))
388 (setq attributes (delq '->mojikyo attributes))
390 (setq rest ccs-attributes)
393 (setq value (get-char-attribute char (car rest)))
395 (if (>= (length (symbol-name (car rest))) 19)
397 (setq has-long-ccs-name t)
401 (setq rest (cdr rest)))
403 (setq name (car attributes))
404 (if (setq value (get-char-attribute char name))
405 (cond ((string-match "^->" (symbol-name name))
410 (mapconcat (lambda (code)
411 (cond ((symbolp code)
414 (format "#x%04X" code))
416 (format "\n %S" code))))
419 (insert (format "(%-18s %s)
422 (mapconcat (function prin1-to-string)
424 ((eq name 'jisx0208-1978/4X)
425 (insert (format "(%-18s . #x%04X)
429 (insert (format "(%-18s . %S)
433 (setq attributes (cdr attributes)))
434 (while ccs-attributes
435 (setq name (car ccs-attributes))
436 (if (setq value (get-char-attribute char name))
439 (if has-long-ccs-name
440 (cond ((eq name 'ideograph-daikanwa)
441 "(%-26s . %05d)\t; %c
445 "(%-26s . %06d)\t; %c
449 "(%-26s . #x%X)\t; %c
452 (cond ((eq name 'ideograph-daikanwa)
453 "(%-18s . %05d)\t; %c
457 "(%-18s . %06d)\t; %c
461 "(%-18s . #x%X)\t; %c
465 (if (= (charset-iso-graphic-plane name) 1)
467 (cond ((= (charset-dimension name) 1)
469 ((= (charset-dimension name) 2)
471 ((= (charset-dimension name) 3)
475 (decode-builtin-char name value))))
476 (setq ccs-attributes (cdr ccs-attributes)))
478 (goto-char (point-min))
479 (while (re-search-forward "[ \t]+$" nil t)
481 (goto-char (point-max))
482 (tabify (point-min)(point-max))
486 (defun char-db-update-comment ()
489 (goto-char (point-min))
490 (let (cdef table char)
491 (while (re-search-forward "^[ \t]*\\(([^.()]+)\\)" nil t)
492 (goto-char (match-beginning 1))
493 (setq cdef (read (current-buffer)))
494 (when (find-charset (car cdef))
495 (goto-char (match-end 0))
498 (not (eq (car cdef) 'ideograph-daikanwa))
499 (or (memq (car cdef) '(ascii latin-viscii-upper
503 japanese-jisx0213-2))
504 (= (char-int (charset-iso-final-char (car cdef)))
506 (apply (function make-char) cdef)
507 (if (setq table (charset-mapping-table (car cdef)))
508 (set-charset-mapping-table (car cdef) nil))
510 (apply (function make-char) cdef)
512 (set-charset-mapping-table (car cdef) table)))))
513 (when (not (or (< (char-int char) 32)
514 (and (<= 128 (char-int char))
515 (< (char-int char) 160))))
516 (delete-region (point) (point-at-eol))
517 (insert (format "\t; %c" char)))
520 (defun insert-char-data-with-variant (char &optional script printable)
521 (insert-char-data char printable)
522 (let ((variants (or (char-variants char)
523 (let ((ucs (get-char-attribute char '->ucs)))
525 (delete char (char-variants (int-char ucs)))))))
528 (setq variant (car variants))
529 (if (or (null script)
530 (null (setq vs (get-char-attribute variant 'script)))
532 (insert-char-data variant printable))
533 (setq variants (cdr variants))
536 (defun insert-char-range-data (min max &optional script)
540 (setq char (decode-char 'ucs code))
541 (if (get-char-attribute char 'ucs)
542 (insert-char-data-with-variant char script))
543 (setq code (1+ code))
546 (defun write-char-range-data-to-file (min max file &optional script)
547 (let ((coding-system-for-write 'utf-8))
549 (insert-char-range-data min max script)
550 (write-region (point-min)(point-max) file))))
552 (defvar what-character-original-window-configuration)
555 (defun what-char-definition (char)
556 (interactive (list (char-after)))
557 (let ((buf (get-buffer-create "*Character Description*"))
558 (the-buf (current-buffer))
559 (win-conf (current-window-configuration)))
561 (make-local-variable 'what-character-original-window-configuration)
562 (setq what-character-original-window-configuration win-conf)
563 (setq buffer-read-only nil)
567 (insert-char-data-with-variant char nil 'printable)
568 ;; (char-db-update-comment)
569 (set-buffer-modified-p nil)
570 (view-mode the-buf (lambda (buf)
571 (set-window-configuration
572 what-character-original-window-configuration)
574 (goto-char (point-min)))
576 (set-window-configuration
577 what-character-original-window-configuration)
578 (signal (car err) (cdr err)))))))
580 (provide 'char-db-util)
582 ;;; char-db-util.el ends here