1 ;;; char-db-util.el --- Character Database utility
3 ;; Copyright (C) 1998,1999,2000,2001,2002,2003 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 XEmacs UTF-2000.
10 ;; XEmacs UTF-2000 is free software; you can redistribute it and/or
11 ;; modify it under the terms of the GNU General Public License as
12 ;; published by the Free Software Foundation; either version 2, or (at
13 ;; your option) any later version.
15 ;; XEmacs UTF-2000 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 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 UTF-2000; see the file COPYING. If not, write to
22 ;; the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
23 ;; Boston, MA 02111-1307, USA.
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 (decode-char '=ucs (+ #x2EFF i)))
72 (defvar char-db-ignored-attributes nil)
74 (defun char-attribute-name< (ka kb)
80 ((= (charset-dimension ka)
81 (charset-dimension kb))
82 (cond ((= (charset-chars ka)(charset-chars kb))
83 (if (charset-iso-final-char ka)
85 ((>= (charset-iso-final-char ka) ?@)
86 (if (and (charset-iso-final-char kb)
87 (>= (charset-iso-final-char kb) ?@))
88 (< (charset-iso-final-char ka)
89 (charset-iso-final-char kb))
92 (if (charset-iso-final-char kb)
93 (if (>= (charset-iso-final-char kb) ?@)
95 (< (charset-iso-final-char ka)
96 (charset-iso-final-char kb)))
98 (if (charset-iso-final-char kb)
100 (< (charset-id ka)(charset-id kb)))))
101 ((<= (charset-chars ka)(charset-chars kb)))))
103 (< (charset-dimension ka)
104 (charset-dimension kb))
114 (string< (symbol-name ka)
120 (defvar char-db-coded-charset-priority-list
135 japanese-jisx0208-1978
177 (defun char-db-make-char-spec (char)
179 (cond ((characterp char)
180 (cond ((and (setq ret (encode-char char '=ucs 'defined-only))
181 (not (and (<= #xE000 ret)(<= ret #xF8FF))))
182 (setq char-spec (list (cons '=ucs ret)))
183 (cond ((setq ret (get-char-attribute char 'name))
184 (setq char-spec (cons (cons 'name ret) char-spec))
186 ((setq ret (get-char-attribute char 'name*))
187 (setq char-spec (cons (cons 'name* ret) char-spec))
192 (let ((rest char-db-coded-charset-priority-list))
195 (get-char-attribute char (car rest)))
196 (throw 'tag (cons (car rest) ret)))
197 (setq rest (cdr rest))))))
198 (setq char-spec (list ret))
199 (dolist (ccs (delq (car ret) (charset-list)))
200 (if (and (or (charset-iso-final-char ccs)
206 (setq ret (get-char-attribute char ccs)))
207 (setq char-spec (cons (cons ccs ret) char-spec))))
209 (setq char-spec (split-char char)))
210 (cond ((setq ret (get-char-attribute char 'name))
211 (setq char-spec (cons (cons 'name ret) char-spec))
213 ((setq ret (get-char-attribute char 'name*))
214 (setq char-spec (cons (cons 'name* ret) char-spec))
221 (defun char-db-insert-char-spec (char &optional readable column)
223 (setq column (current-column)))
224 (let (char-spec ret al cal key temp-char)
225 (setq char-spec (char-db-make-char-spec char))
226 (unless (or (characterp char) ; char
228 (setq char (find-char char-spec))
230 ;; define temporary character
231 ;; Current implementation is dirty.
232 (setq temp-char (define-char (cons '(ideograph-daikanwa . 0)
234 (remove-char-attribute temp-char 'ideograph-daikanwa)
235 (setq char temp-char))
239 (setq key (car (car char-spec)))
240 (unless (memq key char-db-ignored-attributes)
241 (if (find-charset key)
242 (if (get-char-attribute char key)
243 (setq cal (cons key cal)))
244 (setq al (cons key al))))
245 (setq char-spec (cdr char-spec)))
247 (setq char-spec (char-db-make-char-spec char))
249 (setq key (car (car char-spec)))
250 (unless (memq key char-db-ignored-attributes)
251 (if (find-charset key)
252 (setq cal (cons key cal))
253 (setq al (cons key al))))
254 (setq char-spec (cdr char-spec)))
257 (memq 'ideographic-structure al))
258 (push 'ideographic-structure al))
259 (insert-char-attributes char
263 ;; undefine temporary character
264 ;; Current implementation is dirty.
265 (setq char-spec (char-attribute-alist temp-char))
267 (remove-char-attribute temp-char (car (car char-spec)))
268 (setq char-spec (cdr char-spec))))))
270 (defun char-db-insert-alist (alist &optional readable column)
272 (setq column (current-column)))
274 (concat "\n" (make-string (1+ column) ?\ )))
277 lbs cell rest separator)
280 (setq name (car (car alist))
281 value (cdr (car alist)))
282 (cond ((eq name 'char)
284 (if (setq ret (condition-case nil
291 (setq key (car (car value)))
292 (if (find-charset key)
293 (setq cal (cons key cal))
294 (setq al (cons key al)))
295 (setq value (cdr value)))
296 (insert-char-attributes ret
299 (insert (prin1-to-string value)))
301 (insert line-breaking))
303 (insert (format "(%-18s " name))
304 (setq lbs (concat "\n" (make-string (current-column) ?\ )))
306 (setq cell (car value))
307 (if (and (consp cell)
309 (setq ret (condition-case nil
318 (setq key (car (car rest)))
319 (if (find-charset key)
320 (setq cal (cons key cal))
321 (setq al (cons key al)))
322 (setq rest (cdr rest)))
325 (insert-char-attributes ret
328 (setq separator lbs))
331 (insert (prin1-to-string cell))
332 (setq separator " "))
333 (setq value (cdr value)))
335 (insert line-breaking))
337 (insert (format "(%-18s . %S)%s"
340 (setq alist (cdr alist))))
343 (defun char-db-insert-char-reference (plist &optional readable column)
345 (setq column (current-column)))
347 (concat "\n" (make-string (1+ column) ?\ )))
352 (setq name (pop plist))
353 (setq value (pop plist))
354 (cond ((eq name :char)
357 (cond ((numberp value)
358 (setq value (decode-char '=ucs value)))
360 ;; (setq value (or (find-char value)
363 (char-db-insert-char-spec value readable)
364 (insert line-breaking)
367 (insert (format "%s%s\t%d ; %c%s"
370 (aref ideographic-radicals value)
374 (insert (format "%s%s\t%S" separator name value))
375 (setq separator line-breaking)))
379 (defun char-db-decode-isolated-char (ccs code-point)
382 (cond ((eq ccs 'arabic-iso8859-6)
383 (decode-char ccs code-point))
384 ((and (memq ccs '(=gt-pj-1
395 (setq ret (decode-char ccs code-point))
396 (setq ret (get-char-attribute ret '=gt)))
397 (decode-builtin-char '=gt ret))
399 (decode-builtin-char ccs code-point))))
400 (cond ((and (<= 0 (char-int ret))
401 (<= (char-int ret) #x1F))
402 (decode-char '=ucs (+ #x2400 (char-int ret))))
403 ((= (char-int ret) #x7F)
407 (defvar char-db-convert-obsolete-format t)
409 (defun insert-char-attributes (char &optional readable
410 attributes ccs-attributes
415 (if (consp attributes)
417 (dolist (name attributes)
418 (unless (memq name char-db-ignored-attributes)
421 (dolist (name (char-attribute-list))
422 (unless (memq name char-db-ignored-attributes)
423 (if (find-charset name)
427 #'char-attribute-name<))
429 (sort (if ccs-attributes
432 (dolist (name ccs-attributes)
433 (unless (memq name char-db-ignored-attributes)
438 (dolist (name (charset-list))
439 (unless (memq name char-db-ignored-attributes)
442 #'char-attribute-name<)))
444 (setq column (current-column)))
445 (let (name value has-long-ccs-name rest
448 (concat "\n" (make-string (1+ column) ?\ )))
449 lbs cell separator ret
452 (when (and (memq 'name attributes)
453 (setq value (get-char-attribute char 'name)))
455 (if (> (+ (current-column) (length value)) 48)
458 value line-breaking))
459 (setq attributes (delq 'name attributes))
461 (when (and (memq 'name* attributes)
462 (setq value (get-char-attribute char 'name*)))
464 (if (> (+ (current-column) (length value)) 48)
467 value line-breaking))
468 (setq attributes (delq 'name* attributes))
470 (when (and (memq 'script attributes)
471 (setq value (get-char-attribute char 'script)))
472 (insert (format "(script\t\t%s)%s"
473 (mapconcat (function prin1-to-string)
476 (setq attributes (delq 'script attributes))
478 (dolist (name '(=>ucs =>ucs*))
479 (when (and (memq name attributes)
480 (setq value (get-char-attribute char name)))
481 (insert (format "(%-18s . #x%04X)\t; %c%s"
482 name value (decode-char '=ucs value)
484 (setq attributes (delq name attributes))))
485 ;; (when (and (memq '=>ucs* attributes)
486 ;; (setq value (get-char-attribute char '=>ucs*)))
487 ;; (insert (format "(=>ucs*\t\t. #x%04X)\t; %c%s"
488 ;; value (decode-char '=ucs value)
490 ;; (setq attributes (delq '=>ucs* attributes))
492 (dolist (name '(=>ucs@gb =>ucs@cns =>ucs@jis =>ucs@ks =>ucs@big5))
493 (when (and (memq name attributes)
494 (setq value (get-char-attribute char name)))
495 (insert (format "(%-18s . #x%04X)\t; %c%s"
500 (symbol-name name) 2)))
503 (setq attributes (delq name attributes))
505 (dolist (name '(=>ucs-gb =>ucs-cns =>ucs-jis =>ucs-ks =>ucs-big5))
506 (when (and (memq name attributes)
507 (setq value (get-char-attribute char name)))
508 (insert (format "(%-18s . #x%04X)\t; %c%s"
511 (substring (symbol-name name) 6)))
516 (symbol-name name) 6)))
519 (setq attributes (delq name attributes))))
520 ;; (when (and (memq '=>ucs-gb attributes)
521 ;; (setq value (get-char-attribute char '=>ucs-gb)))
522 ;; (insert (format "(=>ucs@gb\t\t. #x%04X)\t; %c%s"
523 ;; value (decode-char '=ucs@gb value)
525 ;; (setq attributes (delq '=>ucs-gb attributes))
527 ;; (when (and (memq '=>ucs-cns attributes)
528 ;; (setq value (get-char-attribute char '=>ucs-cns)))
529 ;; (insert (format "(=>ucs@cns\t\t. #x%04X)\t; %c%s"
530 ;; value (decode-char '=ucs@cns value)
532 ;; (setq attributes (delq '=>ucs-cns attributes))
534 ;; (when (and (memq '=>ucs-big5 attributes)
535 ;; (setq value (get-char-attribute char '=>ucs-big5)))
536 ;; (insert (format "(=>ucs-big5\t\t. #x%04X)\t; %c%s"
537 ;; value (decode-char 'ucs-big5 value)
539 ;; (setq attributes (delq '=>ucs-big5 attributes))
541 ;; (when (and (memq '=>ucs-jis attributes)
542 ;; (setq value (get-char-attribute char '=>ucs-jis)))
543 ;; (insert (format "(=>ucs@jis\t\t. #x%04X)\t; %c%s"
544 ;; value (decode-char '=ucs@jis value)
546 ;; (setq attributes (delq '=>ucs-jis attributes))
548 ;; (when (and (memq '=>ucs-ks attributes)
549 ;; (setq value (get-char-attribute char '=>ucs-ks)))
550 ;; (insert (format "(=>ucs-ks\t\t. #x%04X)\t; %c%s"
551 ;; value (decode-char 'ucs-ks value)
553 ;; (setq attributes (delq '=>ucs-ks attributes))
555 (when (and (memq '->ucs attributes)
556 (setq value (get-char-attribute char '->ucs)))
557 (insert (format (if char-db-convert-obsolete-format
558 "(=>ucs\t\t. #x%04X)\t; %c%s"
559 "(->ucs\t\t. #x%04X)\t; %c%s")
560 value (decode-char '=ucs value)
562 (setq attributes (delq '->ucs attributes))
564 (when (and (memq 'general-category attributes)
565 (setq value (get-char-attribute char 'general-category)))
567 "(general-category\t%s) ; %s%s"
568 (mapconcat (lambda (cell)
571 (cond ((rassoc value unidata-normative-category-alist)
572 "Normative Category")
573 ((rassoc value unidata-informative-category-alist)
574 "Informative Category")
578 (setq attributes (delq 'general-category attributes))
580 (when (and (memq 'bidi-category attributes)
581 (setq value (get-char-attribute char 'bidi-category)))
582 (insert (format "(bidi-category\t. %S)%s"
585 (setq attributes (delq 'bidi-category attributes))
587 (unless (or (not (memq 'mirrored attributes))
588 (eq (setq value (get-char-attribute char 'mirrored 'empty))
590 (insert (format "(mirrored\t\t. %S)%s"
593 (setq attributes (delq 'mirrored attributes))
596 ((and (memq 'decimal-digit-value attributes)
597 (setq value (get-char-attribute char 'decimal-digit-value)))
598 (insert (format "(decimal-digit-value . %S)%s"
601 (setq attributes (delq 'decimal-digit-value attributes))
602 (when (and (memq 'digit-value attributes)
603 (setq value (get-char-attribute char 'digit-value)))
604 (insert (format "(digit-value\t . %S)%s"
607 (setq attributes (delq 'digit-value attributes))
609 (when (and (memq 'numeric-value attributes)
610 (setq value (get-char-attribute char 'numeric-value)))
611 (insert (format "(numeric-value\t . %S)%s"
614 (setq attributes (delq 'numeric-value attributes))
618 (when (and (memq 'digit-value attributes)
619 (setq value (get-char-attribute char 'digit-value)))
620 (insert (format "(digit-value\t. %S)%s"
623 (setq attributes (delq 'digit-value attributes))
625 (when (and (memq 'numeric-value attributes)
626 (setq value (get-char-attribute char 'numeric-value)))
627 (insert (format "(numeric-value\t. %S)%s"
630 (setq attributes (delq 'numeric-value attributes))
632 (when (and (memq 'iso-10646-comment attributes)
633 (setq value (get-char-attribute char 'iso-10646-comment)))
634 (insert (format "(iso-10646-comment\t. %S)%s"
637 (setq attributes (delq 'iso-10646-comment attributes))
639 (when (and (memq 'morohashi-daikanwa attributes)
640 (setq value (get-char-attribute char 'morohashi-daikanwa)))
641 (insert (format "(morohashi-daikanwa\t%s)%s"
642 (mapconcat (function prin1-to-string) value " ")
644 (setq attributes (delq 'morohashi-daikanwa attributes))
648 (when (and (memq 'ideographic-radical attributes)
649 (setq value (get-char-attribute char 'ideographic-radical)))
651 (insert (format "(ideographic-radical . %S)\t; %c%s"
653 (aref ideographic-radicals radical)
655 (setq attributes (delq 'ideographic-radical attributes))
657 (when (and (memq 'ideographic-strokes attributes)
658 (setq value (get-char-attribute char 'ideographic-strokes)))
660 (insert (format "(ideographic-strokes . %S)%s"
663 (setq attributes (delq 'ideographic-strokes attributes))
665 (when (and (memq 'kangxi-radical attributes)
666 (setq value (get-char-attribute char 'kangxi-radical)))
667 (unless (eq value radical)
668 (insert (format "(kangxi-radical\t . %S)\t; %c%s"
670 (aref ideographic-radicals value)
673 (setq radical value)))
674 (setq attributes (delq 'kangxi-radical attributes))
676 (when (and (memq 'kangxi-strokes attributes)
677 (setq value (get-char-attribute char 'kangxi-strokes)))
678 (unless (eq value strokes)
679 (insert (format "(kangxi-strokes\t . %S)%s"
683 (setq strokes value)))
684 (setq attributes (delq 'kangxi-strokes attributes))
686 (when (and (memq 'japanese-radical attributes)
687 (setq value (get-char-attribute char 'japanese-radical)))
688 (unless (eq value radical)
689 (insert (format "(japanese-radical\t . %S)\t; %c%s"
691 (aref ideographic-radicals value)
694 (setq radical value)))
695 (setq attributes (delq 'japanese-radical attributes))
697 (when (and (memq 'japanese-strokes attributes)
698 (setq value (get-char-attribute char 'japanese-strokes)))
699 (unless (eq value strokes)
700 (insert (format "(japanese-strokes\t . %S)%s"
704 (setq strokes value)))
705 (setq attributes (delq 'japanese-strokes attributes))
707 (when (and (memq 'cns-radical attributes)
708 (setq value (get-char-attribute char 'cns-radical)))
709 (insert (format "(cns-radical\t . %S)\t; %c%s"
711 (aref ideographic-radicals value)
713 (setq attributes (delq 'cns-radical attributes))
715 (when (and (memq 'cns-strokes attributes)
716 (setq value (get-char-attribute char 'cns-strokes)))
717 (unless (eq value strokes)
718 (insert (format "(cns-strokes\t . %S)%s"
722 (setq strokes value)))
723 (setq attributes (delq 'cns-strokes attributes))
725 (when (and (memq 'shinjigen-1-radical attributes)
726 (setq value (get-char-attribute char 'shinjigen-1-radical)))
727 (unless (eq value radical)
728 (insert (format "(shinjigen-1-radical . %S)\t; %c%s"
730 (aref ideographic-radicals value)
733 (setq radical value)))
734 (setq attributes (delq 'shinjigen-1-radical attributes))
736 (when (and (memq 'ideographic- attributes)
737 (setq value (get-char-attribute char 'ideographic-)))
738 (insert "(ideographic- ")
739 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
742 (setq cell (car value))
744 (setq cell (decode-char '=ucs cell)))
745 (cond ((characterp cell)
749 (insert (format "%S" cell))
750 (char-db-insert-char-spec cell readable))
751 (setq separator lbs))
755 (if (consp (car cell))
756 (char-db-insert-char-spec cell readable)
757 (char-db-insert-char-reference cell readable))
758 (setq separator lbs))
762 (insert (prin1-to-string cell))
763 (setq separator " ")))
764 (setq value (cdr value)))
766 (insert line-breaking)
767 (setq attributes (delq 'ideographic- attributes)))
768 (when (and (memq 'total-strokes attributes)
769 (setq value (get-char-attribute char 'total-strokes)))
770 (insert (format "(total-strokes . %S)%s"
773 (setq attributes (delq 'total-strokes attributes))
775 (when (and (memq '->ideograph attributes)
776 (setq value (get-char-attribute char '->ideograph)))
777 (insert (format "(->ideograph\t%s)%s"
778 (mapconcat (lambda (code)
779 (cond ((symbolp code)
782 (format "#x%04X" code))
785 line-breaking code))))
788 (setq attributes (delq '->ideograph attributes))
790 (when (and (memq '->decomposition attributes)
791 (setq value (get-char-attribute char '->decomposition)))
792 (insert (format "(->decomposition\t%s)%s"
793 (mapconcat (lambda (code)
794 (cond ((symbolp code)
803 (format "#x%04X" code))
805 (format "%s%S" line-breaking code))))
808 (setq attributes (delq '->decomposition attributes))
810 (if (equal (get-char-attribute char '->titlecase)
811 (get-char-attribute char '->uppercase))
812 (setq attributes (delq '->titlecase attributes)))
813 (when (and (memq '->mojikyo attributes)
814 (setq value (get-char-attribute char '->mojikyo)))
815 (insert (format "(->mojikyo\t\t. %06d)\t; %c%s"
816 value (decode-char 'mojikyo value)
818 (setq attributes (delq '->mojikyo attributes))
820 (when (and (memq 'hanyu-dazidian-vol attributes)
821 (setq value (get-char-attribute char 'hanyu-dazidian-vol)))
822 (insert (format "(hanyu-dazidian-vol . %d)%s"
823 value line-breaking))
824 (setq attributes (delq 'hanyu-dazidian-vol attributes))
826 (when (and (memq 'hanyu-dazidian-page attributes)
827 (setq value (get-char-attribute char 'hanyu-dazidian-page)))
828 (insert (format "(hanyu-dazidian-page . %d)%s"
829 value line-breaking))
830 (setq attributes (delq 'hanyu-dazidian-page attributes))
832 (when (and (memq 'hanyu-dazidian-char attributes)
833 (setq value (get-char-attribute char 'hanyu-dazidian-char)))
834 (insert (format "(hanyu-dazidian-char . %d)%s"
835 value line-breaking))
836 (setq attributes (delq 'hanyu-dazidian-char attributes))
839 (when (memq '->ucs-variants attributes)
840 (setq attributes (delq '->ucs-variants attributes))
842 (when (memq 'composition attributes)
843 (setq attributes (delq 'composition attributes))
845 (setq rest ccs-attributes)
848 (setq value (get-char-attribute char (car rest)))
850 (if (>= (length (symbol-name (car rest))) 19)
852 (setq has-long-ccs-name t)
856 (setq rest (cdr rest)))
858 (setq name (car attributes))
859 (if (setq value (get-char-attribute char name))
860 (cond ((string-match "^=>ucs@" (symbol-name name))
861 (insert (format "(%-18s . #x%04X)\t; %c%s"
862 name value (decode-char '=ucs value)
865 ((eq name 'jisx0208-1978/4X)
866 (insert (format "(%-18s . #x%04X)%s"
869 ((or (eq name 'ideographic-structure)
870 (eq name 'ideographic-)
871 (string-match "^\\(->\\|<-\\)" (symbol-name name)))
872 (insert (format "(%-18s%s " name line-breaking))
873 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
876 (setq cell (car value))
878 (setq cell (decode-char '=ucs cell)))
879 (cond ((characterp cell)
883 (insert (format "%S" cell))
884 (char-db-insert-char-spec cell readable))
885 (setq separator lbs))
889 (if (consp (car cell))
890 (char-db-insert-char-spec cell readable)
891 (char-db-insert-char-reference cell readable))
892 (setq separator lbs))
896 (insert (prin1-to-string cell))
897 (setq separator " ")))
898 (setq value (cdr value)))
900 (insert line-breaking))
901 ((memq name '(ideograph=
902 original-ideograph-of
906 simplified-ideograph-of
908 ideographic-different-form-of))
909 (insert (format "(%-18s%s " name line-breaking))
910 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
913 (setq cell (car value))
914 (if (and (consp cell)
919 (char-db-insert-alist cell readable)
920 (setq separator lbs))
923 (insert (prin1-to-string cell))
924 (setq separator " "))
925 (setq value (cdr value)))
927 (insert line-breaking))
928 ;; ((string-match "^->" (symbol-name name))
930 ;; (format "(%-18s %s)%s"
932 ;; (mapconcat (lambda (code)
933 ;; (cond ((symbolp code)
934 ;; (symbol-name code))
936 ;; (format "#x%04X" code))
939 ;; line-breaking code))))
943 (insert (format "(%-18s " name))
944 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
947 (setq cell (car value))
948 (if (and (consp cell)
950 (setq ret (condition-case nil
958 (setq key (car (car rest)))
959 (if (find-charset key)
960 (setq cal (cons key cal))
961 (setq al (cons key al)))
962 (setq rest (cdr rest)))
965 (insert-char-attributes ret
968 (setq separator lbs))
971 (insert (prin1-to-string cell))
972 (setq separator " "))
973 (setq value (cdr value)))
975 (insert line-breaking))
977 (insert (format "(%-18s . %S)%s"
981 (setq attributes (cdr attributes)))
982 (while ccs-attributes
983 (setq name (car ccs-attributes))
984 (if (and (eq name (charset-name name))
985 (setq value (get-char-attribute char name)))
988 (cond ((memq name '(ideograph-daikanwa
992 (if has-long-ccs-name
993 "(%-26s . %05d)\t; %c%s"
994 "(%-18s . %05d)\t; %c%s"))
996 (if has-long-ccs-name
997 "(%-26s . %06d)\t; %c%s"
998 "(%-18s . %06d)\t; %c%s"))
999 ((>= (charset-dimension name) 2)
1000 (if has-long-ccs-name
1001 "(%-26s . #x%04X)\t; %c%s"
1002 "(%-18s . #x%04X)\t; %c%s"))
1004 (if has-long-ccs-name
1005 "(%-26s . #x%02X)\t; %c%s"
1006 "(%-18s . #x%02X)\t; %c%s")))
1008 (if (= (charset-iso-graphic-plane name) 1)
1010 (cond ((= (charset-dimension name) 1)
1012 ((= (charset-dimension name) 2)
1014 ((= (charset-dimension name) 3)
1018 (char-db-decode-isolated-char name value)
1020 (setq ccs-attributes (cdr ccs-attributes)))
1023 (defun insert-char-data (char &optional readable
1024 attributes ccs-attributes)
1026 (narrow-to-region (point)(point))
1027 (insert "(define-char
1029 (insert-char-attributes char readable
1030 attributes ccs-attributes)
1032 (goto-char (point-min))
1033 (while (re-search-forward "[ \t]+$" nil t)
1036 (goto-char (point-min))
1037 (while (re-search-forward "[ \t][ \t][ \t]*" nil t)
1038 (let ((column (current-column))
1039 (indent-tabs-mode t))
1040 (delete-region (match-beginning 0) (point))
1041 (indent-to column)))
1042 (goto-char (point-max))
1043 ;; (tabify (point-min)(point-max))
1046 (defun insert-char-data-with-variant (char &optional printable
1048 script excluded-script)
1049 (insert-char-data char printable)
1050 (let ((variants (or (char-variants char)
1051 (let ((ucs (get-char-attribute char '->ucs)))
1053 (delete char (char-variants (int-char ucs)))))))
1055 (setq variants (sort variants #'<))
1057 (setq variant (car variants))
1058 (if (and (or (null script)
1059 (null (setq vs (get-char-attribute variant 'script)))
1061 (or (null excluded-script)
1062 (null (setq vs (get-char-attribute variant 'script)))
1063 (not (memq excluded-script vs))))
1064 (or (and no-ucs-variant (get-char-attribute variant '=ucs))
1065 (insert-char-data variant printable)))
1066 (setq variants (cdr variants))
1069 (defun insert-char-range-data (min max &optional script excluded-script)
1072 (while (<= code max)
1073 (setq char (decode-char '=ucs code))
1074 (if (encode-char char '=ucs 'defined-only)
1075 (insert-char-data-with-variant char nil 'no-ucs-variant
1076 script excluded-script))
1077 (setq code (1+ code)))))
1079 (defun write-char-range-data-to-file (min max file
1080 &optional script excluded-script)
1081 (let ((coding-system-for-write 'utf-8))
1083 (insert-char-range-data min max script excluded-script)
1084 (write-region (point-min)(point-max) file))))
1086 (defvar what-character-original-window-configuration)
1089 (defun what-char-definition (char)
1090 (interactive (list (char-after)))
1091 (let ((buf (get-buffer-create "*Character Description*"))
1092 (the-buf (current-buffer))
1093 (win-conf (current-window-configuration)))
1095 (make-local-variable 'what-character-original-window-configuration)
1096 (setq what-character-original-window-configuration win-conf)
1097 (setq buffer-read-only nil)
1101 (insert-char-data-with-variant char 'printable)
1102 (unless (char-attribute-alist char)
1103 (insert (format ";; = %c\n"
1104 (let* ((rest (split-char char))
1108 (setq code (logior (lsh code 8)
1110 (decode-char ccs code)))))
1111 ;; (char-db-update-comment)
1112 (set-buffer-modified-p nil)
1113 (view-mode the-buf (lambda (buf)
1114 (set-window-configuration
1115 what-character-original-window-configuration)
1117 (goto-char (point-min)))
1119 (set-window-configuration
1120 what-character-original-window-configuration)
1121 (signal (car err) (cdr err)))))))
1123 (provide 'char-db-util)
1125 ;;; char-db-util.el ends here