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 (when (and (memq '=>ucs attributes)
479 (setq value (get-char-attribute char '=>ucs)))
480 (insert (format "(=>ucs\t\t. #x%04X)\t; %c%s"
481 value (decode-char '=ucs value)
483 (setq attributes (delq '=>ucs 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 (when (and (memq '=>ucs-gb attributes)
493 (setq value (get-char-attribute char '=>ucs-gb)))
494 (insert (format "(=>ucs-gb\t\t. #x%04X)\t; %c%s"
495 value (decode-char '=ucs value)
497 (setq attributes (delq '=>ucs-gb attributes))
499 (when (and (memq '=>ucs-cns attributes)
500 (setq value (get-char-attribute char '=>ucs-cns)))
501 (insert (format "(=>ucs-cns\t\t. #x%04X)\t; %c%s"
502 value (decode-char 'ucs-cns value)
504 (setq attributes (delq '=>ucs-cns attributes))
506 (when (and (memq '=>ucs-big5 attributes)
507 (setq value (get-char-attribute char '=>ucs-big5)))
508 (insert (format "(=>ucs-big5\t\t. #x%04X)\t; %c%s"
509 value (decode-char 'ucs-big5 value)
511 (setq attributes (delq '=>ucs-big5 attributes))
513 (when (and (memq '=>ucs-jis attributes)
514 (setq value (get-char-attribute char '=>ucs-jis)))
515 (insert (format "(=>ucs-jis\t\t. #x%04X)\t; %c%s"
516 value (decode-char 'ucs-jis value)
518 (setq attributes (delq '=>ucs-jis attributes))
520 (when (and (memq '=>ucs-ks attributes)
521 (setq value (get-char-attribute char '=>ucs-ks)))
522 (insert (format "(=>ucs-ks\t\t. #x%04X)\t; %c%s"
523 value (decode-char 'ucs-ks value)
525 (setq attributes (delq '=>ucs-ks attributes))
527 (when (and (memq '->ucs attributes)
528 (setq value (get-char-attribute char '->ucs)))
529 (insert (format (if char-db-convert-obsolete-format
530 "(=>ucs\t\t. #x%04X)\t; %c%s"
531 "(->ucs\t\t. #x%04X)\t; %c%s")
532 value (decode-char '=ucs value)
534 (setq attributes (delq '->ucs attributes))
536 (when (and (memq 'general-category attributes)
537 (setq value (get-char-attribute char 'general-category)))
539 "(general-category\t%s) ; %s%s"
540 (mapconcat (lambda (cell)
543 (cond ((rassoc value unidata-normative-category-alist)
544 "Normative Category")
545 ((rassoc value unidata-informative-category-alist)
546 "Informative Category")
550 (setq attributes (delq 'general-category attributes))
552 (when (and (memq 'bidi-category attributes)
553 (setq value (get-char-attribute char 'bidi-category)))
554 (insert (format "(bidi-category\t. %S)%s"
557 (setq attributes (delq 'bidi-category attributes))
559 (unless (or (not (memq 'mirrored attributes))
560 (eq (setq value (get-char-attribute char 'mirrored 'empty))
562 (insert (format "(mirrored\t\t. %S)%s"
565 (setq attributes (delq 'mirrored attributes))
568 ((and (memq 'decimal-digit-value attributes)
569 (setq value (get-char-attribute char 'decimal-digit-value)))
570 (insert (format "(decimal-digit-value . %S)%s"
573 (setq attributes (delq 'decimal-digit-value attributes))
574 (when (and (memq 'digit-value attributes)
575 (setq value (get-char-attribute char 'digit-value)))
576 (insert (format "(digit-value\t . %S)%s"
579 (setq attributes (delq 'digit-value attributes))
581 (when (and (memq 'numeric-value attributes)
582 (setq value (get-char-attribute char 'numeric-value)))
583 (insert (format "(numeric-value\t . %S)%s"
586 (setq attributes (delq 'numeric-value attributes))
590 (when (and (memq 'digit-value attributes)
591 (setq value (get-char-attribute char 'digit-value)))
592 (insert (format "(digit-value\t. %S)%s"
595 (setq attributes (delq 'digit-value attributes))
597 (when (and (memq 'numeric-value attributes)
598 (setq value (get-char-attribute char 'numeric-value)))
599 (insert (format "(numeric-value\t. %S)%s"
602 (setq attributes (delq 'numeric-value attributes))
604 (when (and (memq 'iso-10646-comment attributes)
605 (setq value (get-char-attribute char 'iso-10646-comment)))
606 (insert (format "(iso-10646-comment\t. %S)%s"
609 (setq attributes (delq 'iso-10646-comment attributes))
611 (when (and (memq 'morohashi-daikanwa attributes)
612 (setq value (get-char-attribute char 'morohashi-daikanwa)))
613 (insert (format "(morohashi-daikanwa\t%s)%s"
614 (mapconcat (function prin1-to-string) value " ")
616 (setq attributes (delq 'morohashi-daikanwa attributes))
620 (when (and (memq 'ideographic-radical attributes)
621 (setq value (get-char-attribute char 'ideographic-radical)))
623 (insert (format "(ideographic-radical . %S)\t; %c%s"
625 (aref ideographic-radicals radical)
627 (setq attributes (delq 'ideographic-radical attributes))
629 (when (and (memq 'ideographic-strokes attributes)
630 (setq value (get-char-attribute char 'ideographic-strokes)))
632 (insert (format "(ideographic-strokes . %S)%s"
635 (setq attributes (delq 'ideographic-strokes attributes))
637 (when (and (memq 'kangxi-radical attributes)
638 (setq value (get-char-attribute char 'kangxi-radical)))
639 (unless (eq value radical)
640 (insert (format "(kangxi-radical\t . %S)\t; %c%s"
642 (aref ideographic-radicals value)
645 (setq radical value)))
646 (setq attributes (delq 'kangxi-radical attributes))
648 (when (and (memq 'kangxi-strokes attributes)
649 (setq value (get-char-attribute char 'kangxi-strokes)))
650 (unless (eq value strokes)
651 (insert (format "(kangxi-strokes\t . %S)%s"
655 (setq strokes value)))
656 (setq attributes (delq 'kangxi-strokes attributes))
658 (when (and (memq 'japanese-radical attributes)
659 (setq value (get-char-attribute char 'japanese-radical)))
660 (unless (eq value radical)
661 (insert (format "(japanese-radical\t . %S)\t; %c%s"
663 (aref ideographic-radicals value)
666 (setq radical value)))
667 (setq attributes (delq 'japanese-radical attributes))
669 (when (and (memq 'japanese-strokes attributes)
670 (setq value (get-char-attribute char 'japanese-strokes)))
671 (unless (eq value strokes)
672 (insert (format "(japanese-strokes\t . %S)%s"
676 (setq strokes value)))
677 (setq attributes (delq 'japanese-strokes attributes))
679 (when (and (memq 'cns-radical attributes)
680 (setq value (get-char-attribute char 'cns-radical)))
681 (insert (format "(cns-radical\t . %S)\t; %c%s"
683 (aref ideographic-radicals value)
685 (setq attributes (delq 'cns-radical attributes))
687 (when (and (memq 'cns-strokes attributes)
688 (setq value (get-char-attribute char 'cns-strokes)))
689 (unless (eq value strokes)
690 (insert (format "(cns-strokes\t . %S)%s"
694 (setq strokes value)))
695 (setq attributes (delq 'cns-strokes attributes))
697 (when (and (memq 'shinjigen-1-radical attributes)
698 (setq value (get-char-attribute char 'shinjigen-1-radical)))
699 (unless (eq value radical)
700 (insert (format "(shinjigen-1-radical . %S)\t; %c%s"
702 (aref ideographic-radicals value)
705 (setq radical value)))
706 (setq attributes (delq 'shinjigen-1-radical attributes))
708 (when (and (memq 'ideographic- attributes)
709 (setq value (get-char-attribute char 'ideographic-)))
710 (insert "(ideographic- ")
711 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
714 (setq cell (car value))
716 (setq cell (decode-char '=ucs cell)))
717 (cond ((characterp cell)
721 (insert (format "%S" cell))
722 (char-db-insert-char-spec cell readable))
723 (setq separator lbs))
727 (if (consp (car cell))
728 (char-db-insert-char-spec cell readable)
729 (char-db-insert-char-reference cell readable))
730 (setq separator lbs))
734 (insert (prin1-to-string cell))
735 (setq separator " ")))
736 (setq value (cdr value)))
738 (insert line-breaking)
739 (setq attributes (delq 'ideographic- attributes)))
740 (when (and (memq 'total-strokes attributes)
741 (setq value (get-char-attribute char 'total-strokes)))
742 (insert (format "(total-strokes . %S)%s"
745 (setq attributes (delq 'total-strokes attributes))
747 (when (and (memq '->ideograph attributes)
748 (setq value (get-char-attribute char '->ideograph)))
749 (insert (format "(->ideograph\t%s)%s"
750 (mapconcat (lambda (code)
751 (cond ((symbolp code)
754 (format "#x%04X" code))
757 line-breaking code))))
760 (setq attributes (delq '->ideograph attributes))
762 (when (and (memq '->decomposition attributes)
763 (setq value (get-char-attribute char '->decomposition)))
764 (insert (format "(->decomposition\t%s)%s"
765 (mapconcat (lambda (code)
766 (cond ((symbolp code)
775 (format "#x%04X" code))
777 (format "%s%S" line-breaking code))))
780 (setq attributes (delq '->decomposition attributes))
782 (if (equal (get-char-attribute char '->titlecase)
783 (get-char-attribute char '->uppercase))
784 (setq attributes (delq '->titlecase attributes)))
785 (when (and (memq '->mojikyo attributes)
786 (setq value (get-char-attribute char '->mojikyo)))
787 (insert (format "(->mojikyo\t\t. %06d)\t; %c%s"
788 value (decode-char 'mojikyo value)
790 (setq attributes (delq '->mojikyo attributes))
792 (when (and (memq 'hanyu-dazidian-vol attributes)
793 (setq value (get-char-attribute char 'hanyu-dazidian-vol)))
794 (insert (format "(hanyu-dazidian-vol . %d)%s"
795 value line-breaking))
796 (setq attributes (delq 'hanyu-dazidian-vol attributes))
798 (when (and (memq 'hanyu-dazidian-page attributes)
799 (setq value (get-char-attribute char 'hanyu-dazidian-page)))
800 (insert (format "(hanyu-dazidian-page . %d)%s"
801 value line-breaking))
802 (setq attributes (delq 'hanyu-dazidian-page attributes))
804 (when (and (memq 'hanyu-dazidian-char attributes)
805 (setq value (get-char-attribute char 'hanyu-dazidian-char)))
806 (insert (format "(hanyu-dazidian-char . %d)%s"
807 value line-breaking))
808 (setq attributes (delq 'hanyu-dazidian-char attributes))
811 (when (memq '->ucs-variants attributes)
812 (setq attributes (delq '->ucs-variants attributes))
814 (when (memq 'composition attributes)
815 (setq attributes (delq 'composition attributes))
817 (setq rest ccs-attributes)
820 (setq value (get-char-attribute char (car rest)))
822 (if (>= (length (symbol-name (car rest))) 19)
824 (setq has-long-ccs-name t)
828 (setq rest (cdr rest)))
830 (setq name (car attributes))
831 (if (setq value (get-char-attribute char name))
832 (cond ((eq name 'jisx0208-1978/4X)
833 (insert (format "(%-18s . #x%04X)%s"
836 ((or (eq name 'ideographic-structure)
837 (eq name 'ideographic-)
838 (string-match "^\\(->\\|<-\\)" (symbol-name name)))
839 (insert (format "(%-18s%s " name line-breaking))
840 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
843 (setq cell (car value))
845 (setq cell (decode-char '=ucs cell)))
846 (cond ((characterp cell)
850 (insert (format "%S" cell))
851 (char-db-insert-char-spec cell readable))
852 (setq separator lbs))
856 (if (consp (car cell))
857 (char-db-insert-char-spec cell readable)
858 (char-db-insert-char-reference cell readable))
859 (setq separator lbs))
863 (insert (prin1-to-string cell))
864 (setq separator " ")))
865 (setq value (cdr value)))
867 (insert line-breaking))
868 ((memq name '(ideograph=
869 original-ideograph-of
873 simplified-ideograph-of
875 ideographic-different-form-of))
876 (insert (format "(%-18s%s " name line-breaking))
877 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
880 (setq cell (car value))
881 (if (and (consp cell)
886 (char-db-insert-alist cell readable)
887 (setq separator lbs))
890 (insert (prin1-to-string cell))
891 (setq separator " "))
892 (setq value (cdr value)))
894 (insert line-breaking))
895 ;; ((string-match "^->" (symbol-name name))
897 ;; (format "(%-18s %s)%s"
899 ;; (mapconcat (lambda (code)
900 ;; (cond ((symbolp code)
901 ;; (symbol-name code))
903 ;; (format "#x%04X" code))
906 ;; line-breaking code))))
910 (insert (format "(%-18s " name))
911 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
914 (setq cell (car value))
915 (if (and (consp cell)
917 (setq ret (condition-case nil
925 (setq key (car (car rest)))
926 (if (find-charset key)
927 (setq cal (cons key cal))
928 (setq al (cons key al)))
929 (setq rest (cdr rest)))
932 (insert-char-attributes ret
935 (setq separator lbs))
938 (insert (prin1-to-string cell))
939 (setq separator " "))
940 (setq value (cdr value)))
942 (insert line-breaking))
944 (insert (format "(%-18s . %S)%s"
948 (setq attributes (cdr attributes)))
949 (while ccs-attributes
950 (setq name (car ccs-attributes))
951 (if (and (eq name (charset-name name))
952 (setq value (get-char-attribute char name)))
955 (cond ((memq name '(ideograph-daikanwa
959 (if has-long-ccs-name
960 "(%-26s . %05d)\t; %c%s"
961 "(%-18s . %05d)\t; %c%s"))
963 (if has-long-ccs-name
964 "(%-26s . %06d)\t; %c%s"
965 "(%-18s . %06d)\t; %c%s"))
966 ((>= (charset-dimension name) 2)
967 (if has-long-ccs-name
968 "(%-26s . #x%04X)\t; %c%s"
969 "(%-18s . #x%04X)\t; %c%s"))
971 (if has-long-ccs-name
972 "(%-26s . #x%02X)\t; %c%s"
973 "(%-18s . #x%02X)\t; %c%s")))
975 (if (= (charset-iso-graphic-plane name) 1)
977 (cond ((= (charset-dimension name) 1)
979 ((= (charset-dimension name) 2)
981 ((= (charset-dimension name) 3)
985 (char-db-decode-isolated-char name value)
987 (setq ccs-attributes (cdr ccs-attributes)))
990 (defun insert-char-data (char &optional readable
991 attributes ccs-attributes)
993 (narrow-to-region (point)(point))
994 (insert "(define-char
996 (insert-char-attributes char readable
997 attributes ccs-attributes)
999 (goto-char (point-min))
1000 (while (re-search-forward "[ \t]+$" nil t)
1003 (goto-char (point-min))
1004 (while (re-search-forward "[ \t][ \t][ \t]*" nil t)
1005 (let ((column (current-column))
1006 (indent-tabs-mode t))
1007 (delete-region (match-beginning 0) (point))
1008 (indent-to column)))
1009 (goto-char (point-max))
1010 ;; (tabify (point-min)(point-max))
1013 (defun insert-char-data-with-variant (char &optional printable
1015 script excluded-script)
1016 (insert-char-data char printable)
1017 (let ((variants (or (char-variants char)
1018 (let ((ucs (get-char-attribute char '->ucs)))
1020 (delete char (char-variants (int-char ucs)))))))
1022 (setq variants (sort variants #'<))
1024 (setq variant (car variants))
1025 (if (and (or (null script)
1026 (null (setq vs (get-char-attribute variant 'script)))
1028 (or (null excluded-script)
1029 (null (setq vs (get-char-attribute variant 'script)))
1030 (not (memq excluded-script vs))))
1031 (or (and no-ucs-variant (get-char-attribute variant '=ucs))
1032 (insert-char-data variant printable)))
1033 (setq variants (cdr variants))
1036 (defun insert-char-range-data (min max &optional script excluded-script)
1039 (while (<= code max)
1040 (setq char (decode-char '=ucs code))
1041 (if (encode-char char '=ucs 'defined-only)
1042 (insert-char-data-with-variant char nil 'no-ucs-variant
1043 script excluded-script))
1044 (setq code (1+ code)))))
1046 (defun write-char-range-data-to-file (min max file
1047 &optional script excluded-script)
1048 (let ((coding-system-for-write 'utf-8))
1050 (insert-char-range-data min max script excluded-script)
1051 (write-region (point-min)(point-max) file))))
1053 (defvar what-character-original-window-configuration)
1056 (defun what-char-definition (char)
1057 (interactive (list (char-after)))
1058 (let ((buf (get-buffer-create "*Character Description*"))
1059 (the-buf (current-buffer))
1060 (win-conf (current-window-configuration)))
1062 (make-local-variable 'what-character-original-window-configuration)
1063 (setq what-character-original-window-configuration win-conf)
1064 (setq buffer-read-only nil)
1068 (insert-char-data-with-variant char 'printable)
1069 (unless (char-attribute-alist char)
1070 (insert (format ";; = %c\n"
1071 (let* ((rest (split-char char))
1075 (setq code (logior (lsh code 8)
1077 (decode-char ccs code)))))
1078 ;; (char-db-update-comment)
1079 (set-buffer-modified-p nil)
1080 (view-mode the-buf (lambda (buf)
1081 (set-window-configuration
1082 what-character-original-window-configuration)
1084 (goto-char (point-min)))
1086 (set-window-configuration
1087 what-character-original-window-configuration)
1088 (signal (car err) (cdr err)))))))
1090 (provide 'char-db-util)
1092 ;;; char-db-util.el ends here