1 ;;; char-db-util.el --- Character Database utility
3 ;; Copyright (C) 1998,1999,2000,2001 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-attributes (char &optional readable
117 attributes ccs-attributes
121 (copy-sequence attributes)
122 (sort (char-attribute-list) #'char-attribute-name<)))
125 (copy-sequence ccs-attributes)
126 (sort (charset-list) #'char-attribute-name<)))
128 (setq column (current-column)))
129 (let (name value has-long-ccs-name rest
132 (concat "\n" (make-string (1+ column) ?\ ))))
134 (when (setq value (get-char-attribute char 'name))
136 (if (> (length value) 47)
139 value line-breaking))
140 (setq attributes (delq 'name attributes))
142 (when (setq value (get-char-attribute char 'script))
143 (insert (format "(script\t\t%s)%s"
144 (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%s"
151 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%s"
158 (mapconcat (lambda (cell)
161 (cond ((rassoc value unidata-normative-category-alist)
162 "Normative Category")
163 ((rassoc value unidata-informative-category-alist)
164 "Informative 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)%s"
174 (setq attributes (delq 'bidi-category attributes))
176 (unless (eq (setq value (get-char-attribute char 'mirrored 'empty))
178 (insert (format "(mirrored\t\t. %S)%s"
181 (setq attributes (delq 'mirrored attributes))
184 ((setq value (get-char-attribute char 'decimal-digit-value))
185 (insert (format "(decimal-digit-value . %S)%s"
188 (setq attributes (delq 'decimal-digit-value attributes))
189 (when (setq value (get-char-attribute char 'digit-value))
190 (insert (format "(digit-value\t . %S)%s"
193 (setq attributes (delq 'digit-value attributes))
195 (when (setq value (get-char-attribute char 'numeric-value))
196 (insert (format "(numeric-value\t . %S)%s"
199 (setq attributes (delq 'numeric-value attributes))
203 (when (setq value (get-char-attribute char 'digit-value))
204 (insert (format "(digit-value\t. %S)%s"
207 (setq attributes (delq 'digit-value attributes))
209 (when (setq value (get-char-attribute char 'numeric-value))
210 (insert (format "(numeric-value\t. %S)%s"
213 (setq attributes (delq 'numeric-value attributes))
215 (when (setq value (get-char-attribute char 'iso-10646-comment))
216 (insert (format "(iso-10646-comment\t. %S)%s"
219 (setq attributes (delq 'iso-10646-comment attributes))
221 (when (setq value (get-char-attribute char 'morohashi-daikanwa))
222 (insert (format "(morohashi-daikanwa\t%s)%s"
223 (mapconcat (function prin1-to-string) value " ")
225 (setq attributes (delq 'morohashi-daikanwa attributes))
229 (when (setq value (get-char-attribute char 'ideographic-radical))
231 (insert (format "(ideographic-radical . %S)\t; %c%s"
233 (aref ideographic-radicals radical)
235 (setq attributes (delq 'ideographic-radical attributes))
237 (when (setq value (get-char-attribute char 'ideographic-strokes))
239 (insert (format "(ideographic-strokes . %S)%s"
242 (setq attributes (delq 'ideographic-strokes attributes))
244 (when (setq value (get-char-attribute char 'kangxi-radical))
245 (unless (eq value radical)
246 (insert (format "(kangxi-radical\t . %S)\t; %c%s"
248 (aref ideographic-radicals value)
251 (setq radical value)))
252 (setq attributes (delq 'kangxi-radical attributes))
254 (when (setq value (get-char-attribute char 'kangxi-strokes))
255 (unless (eq value strokes)
256 (insert (format "(kangxi-strokes\t . %S)%s"
260 (setq strokes value)))
261 (setq attributes (delq 'kangxi-strokes attributes))
263 (when (setq value (get-char-attribute char 'japanese-radical))
264 (unless (eq value radical)
265 (insert (format "(japanese-radical\t . %S)\t; %c%s"
267 (aref ideographic-radicals value)
270 (setq radical value)))
271 (setq attributes (delq 'japanese-radical attributes))
273 (when (setq value (get-char-attribute char 'japanese-strokes))
274 (unless (eq value strokes)
275 (insert (format "(japanese-strokes\t . %S)%s"
279 (setq strokes value)))
280 (setq attributes (delq 'japanese-strokes attributes))
282 (when (setq value (get-char-attribute char 'cns-radical))
283 (insert (format "(cns-radical\t . %S)\t; %c%s"
285 (aref ideographic-radicals value)
287 (setq attributes (delq 'cns-radical attributes))
289 (when (setq value (get-char-attribute char 'cns-strokes))
290 (unless (eq value strokes)
291 (insert (format "(cns-strokes\t . %S)%s"
295 (setq strokes value)))
296 (setq attributes (delq 'cns-strokes attributes))
298 (when (setq value (get-char-attribute char 'shinjigen-1-radical))
299 (unless (eq value radical)
300 (insert (format "(shinjigen-1-radical . %S)\t; %c%s"
302 (aref ideographic-radicals value)
305 (setq radical value)))
306 (setq attributes (delq 'shinjigen-1-radical attributes))
308 (when (setq value (get-char-attribute char 'total-strokes))
309 (insert (format "(total-strokes . %S)%s"
312 (setq attributes (delq 'total-strokes attributes))
314 (when (setq value (get-char-attribute char '->ideograph))
315 (insert (format "(->ideograph\t%s)%s"
316 (mapconcat (lambda (code)
317 (cond ((symbolp code)
320 (format "#x%04X" code))
322 (format "%s%S" line-breaking code))))
325 (setq attributes (delq '->ideograph attributes))
327 (when (setq value (get-char-attribute char '->decomposition))
328 (insert (format "(->decomposition\t%s)%s"
329 (mapconcat (lambda (code)
330 (cond ((symbolp code)
339 (format "#x%04X" code))
341 (format "%s%S" line-breaking code))))
344 (setq attributes (delq '->decomposition attributes))
346 (when (setq value (get-char-attribute char '->uppercase))
347 (insert (format "(->uppercase\t%s)%s"
348 (mapconcat (lambda (code)
349 (cond ((symbolp code)
352 (format "#x%04X" code))
354 (format "%s%S" line-breaking code))))
357 (setq attributes (delq '->uppercase attributes))
359 (when (setq value (get-char-attribute char '->lowercase))
360 (insert (format "(->lowercase\t%s)%s"
361 (mapconcat (lambda (code)
362 (cond ((symbolp code)
365 (format "#x%04X" code))
367 (format "%s%S" line-breaking code))))
370 (setq attributes (delq '->lowercase attributes))
372 (when (setq value (get-char-attribute char '->titlecase))
373 (insert (format "(->titlecase\t%s)%s"
374 (mapconcat (lambda (code)
375 (cond ((symbolp code)
378 (format "#x%04X" code))
380 (format "%s%S" line-breaking code))))
383 (setq attributes (delq '->titlecase attributes))
385 (when (setq value (get-char-attribute char '->mojikyo))
386 (insert (format "(->mojikyo\t\t. %06d)\t; %c%s"
387 value (decode-char 'mojikyo value)
389 (setq attributes (delq '->mojikyo attributes))
391 (setq rest ccs-attributes)
394 (setq value (get-char-attribute char (car rest)))
396 (if (>= (length (symbol-name (car rest))) 19)
398 (setq has-long-ccs-name t)
402 (setq rest (cdr rest)))
404 (setq name (car attributes))
405 (if (setq value (get-char-attribute char name))
406 (cond ((string-match "^->" (symbol-name name))
408 (format "(%-18s %s)%s"
410 (mapconcat (lambda (code)
411 (cond ((symbolp code)
414 (format "#x%04X" code))
417 line-breaking code))))
421 (insert (format "(%-18s " name))
422 (let ((lbs (concat "\n" (make-string (current-column) ?\ )))
427 (setq cell (car value))
428 (if (and (consp cell)
430 (setq ret (condition-case nil
438 (setq key (car (car rest)))
439 (if (find-charset key)
440 (setq cal (cons key cal))
441 (setq al (cons key al)))
442 (setq rest (cdr rest)))
445 (insert-char-attributes ret
448 (setq separator lbs))
451 (insert (prin1-to-string cell))
452 (setq separator " "))
453 (setq value (cdr value))))
455 (insert line-breaking))
456 ((eq name 'jisx0208-1978/4X)
457 (insert (format "(%-18s . #x%04X)%s"
461 (insert (format "(%-18s . %S)%s"
465 (setq attributes (cdr attributes)))
466 (while ccs-attributes
467 (setq name (car ccs-attributes))
468 (if (setq value (get-char-attribute char name))
471 (if has-long-ccs-name
472 (cond ((eq name 'ideograph-daikanwa)
473 "(%-26s . %05d)\t; %c%s"
476 "(%-26s . %06d)\t; %c%s"
479 "(%-26s . #x%X)\t; %c%s"
481 (cond ((eq name 'ideograph-daikanwa)
482 "(%-18s . %05d)\t; %c%s"
485 "(%-18s . %06d)\t; %c%s"
488 "(%-18s . #x%X)\t; %c%s"
491 (if (= (charset-iso-graphic-plane name) 1)
493 (cond ((= (charset-dimension name) 1)
495 ((= (charset-dimension name) 2)
497 ((= (charset-dimension name) 3)
501 (decode-builtin-char name value)
503 (setq ccs-attributes (cdr ccs-attributes)))
506 (defun insert-char-data (char &optional readable
507 attributes ccs-attributes)
509 (narrow-to-region (point)(point))
510 (insert "(define-char
512 (insert-char-attributes char readable
513 attributes ccs-attributes)
515 (goto-char (point-min))
516 (while (re-search-forward "[ \t]+$" nil t)
518 (goto-char (point-max))
519 (tabify (point-min)(point-max))
523 (defun char-db-update-comment ()
526 (goto-char (point-min))
527 (let (cdef table char)
528 (while (re-search-forward "^[ \t]*\\(([^.()]+)\\)" nil t)
529 (goto-char (match-beginning 1))
530 (setq cdef (read (current-buffer)))
531 (when (find-charset (car cdef))
532 (goto-char (match-end 0))
535 (not (eq (car cdef) 'ideograph-daikanwa))
536 (or (memq (car cdef) '(ascii latin-viscii-upper
540 japanese-jisx0213-2))
541 (= (char-int (charset-iso-final-char (car cdef)))
543 (apply (function make-char) cdef)
544 (if (setq table (charset-mapping-table (car cdef)))
545 (set-charset-mapping-table (car cdef) nil))
547 (apply (function make-char) cdef)
549 (set-charset-mapping-table (car cdef) table)))))
550 (when (not (or (< (char-int char) 32)
551 (and (<= 128 (char-int char))
552 (< (char-int char) 160))))
553 (delete-region (point) (point-at-eol))
554 (insert (format "\t; %c" char)))
557 (defun insert-char-data-with-variant (char &optional script printable
559 (insert-char-data char printable)
560 (let ((variants (or (char-variants char)
561 (let ((ucs (get-char-attribute char '->ucs)))
563 (delete char (char-variants (int-char ucs)))))))
566 (setq variant (car variants))
567 (if (or (null script)
568 (null (setq vs (get-char-attribute variant 'script)))
570 (or (and no-ucs-variant (get-char-attribute variant 'ucs))
571 (insert-char-data variant printable)))
572 (setq variants (cdr variants))
575 (defun insert-char-range-data (min max &optional script)
579 (setq char (decode-char 'ucs code))
580 (if (get-char-attribute char 'ucs)
581 (insert-char-data-with-variant char script nil 'no-ucs-variant))
582 (setq code (1+ code))
585 (defun write-char-range-data-to-file (min max file &optional script)
586 (let ((coding-system-for-write 'utf-8))
588 (insert-char-range-data min max script)
589 (write-region (point-min)(point-max) file))))
591 (defvar what-character-original-window-configuration)
594 (defun what-char-definition (char)
595 (interactive (list (char-after)))
596 (let ((buf (get-buffer-create "*Character Description*"))
597 (the-buf (current-buffer))
598 (win-conf (current-window-configuration)))
600 (make-local-variable 'what-character-original-window-configuration)
601 (setq what-character-original-window-configuration win-conf)
602 (setq buffer-read-only nil)
606 (insert-char-data-with-variant char nil 'printable)
607 ;; (char-db-update-comment)
608 (set-buffer-modified-p nil)
609 (view-mode the-buf (lambda (buf)
610 (set-window-configuration
611 what-character-original-window-configuration)
613 (goto-char (point-min)))
615 (set-window-configuration
616 what-character-original-window-configuration)
617 (signal (car err) (cdr err)))))))
619 (provide 'char-db-util)
621 ;;; char-db-util.el ends here