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
176 (defun char-db-make-char-spec (char)
178 (cond ((characterp char)
179 (cond ((and (setq ret (encode-char char '=ucs 'defined-only))
180 (not (and (<= #xE000 ret)(<= ret #xF8FF))))
181 (setq char-spec (list (cons '=ucs ret)))
182 (cond ((setq ret (get-char-attribute char 'name))
183 (setq char-spec (cons (cons 'name ret) char-spec))
185 ((setq ret (get-char-attribute char 'name*))
186 (setq char-spec (cons (cons 'name* ret) char-spec))
191 (let ((rest char-db-coded-charset-priority-list)
194 (setq ccs (charset-name
195 (find-charset (car rest))))
197 (encode-char char ccs
199 (throw 'tag (cons ccs ret)))
200 (setq rest (cdr rest))))))
201 (setq char-spec (list ret))
202 (dolist (ccs (delq (car ret) (charset-list)))
203 (if (and (or (charset-iso-final-char ccs)
209 (setq ret (encode-char char ccs 'defined-only)))
210 (setq char-spec (cons (cons ccs ret) char-spec))))
212 (setq char-spec (split-char char)))
213 (cond ((setq ret (get-char-attribute char 'name))
214 (setq char-spec (cons (cons 'name ret) char-spec))
216 ((setq ret (get-char-attribute char 'name*))
217 (setq char-spec (cons (cons 'name* ret) char-spec))
224 (defun char-db-insert-char-spec (char &optional readable column)
226 (setq column (current-column)))
227 (let (char-spec ret al cal key temp-char)
228 (setq char-spec (char-db-make-char-spec char))
229 (unless (or (characterp char) ; char
231 (setq char (find-char char-spec))
233 ;; define temporary character
234 ;; Current implementation is dirty.
235 (setq temp-char (define-char (cons '(ideograph-daikanwa . 0)
237 (remove-char-attribute temp-char 'ideograph-daikanwa)
238 (setq char temp-char))
242 (setq key (car (car char-spec)))
243 (unless (memq key char-db-ignored-attributes)
244 (if (find-charset key)
245 (if (encode-char char key 'defined-only)
246 (setq cal (cons key cal)))
247 (setq al (cons key al))))
248 (setq char-spec (cdr char-spec)))
250 (setq char-spec (char-db-make-char-spec char))
252 (setq key (car (car char-spec)))
253 (unless (memq key char-db-ignored-attributes)
254 (if (find-charset key)
255 (setq cal (cons key cal))
256 (setq al (cons key al))))
257 (setq char-spec (cdr char-spec)))
260 (memq 'ideographic-structure al))
261 (push 'ideographic-structure al))
262 (insert-char-attributes char
266 ;; undefine temporary character
267 ;; Current implementation is dirty.
268 (setq char-spec (char-attribute-alist temp-char))
270 (remove-char-attribute temp-char (car (car char-spec)))
271 (setq char-spec (cdr char-spec))))))
273 (defun char-db-insert-alist (alist &optional readable column)
275 (setq column (current-column)))
277 (concat "\n" (make-string (1+ column) ?\ )))
280 lbs cell rest separator)
283 (setq name (car (car alist))
284 value (cdr (car alist)))
285 (cond ((eq name 'char)
287 (if (setq ret (condition-case nil
294 (setq key (car (car value)))
295 (if (find-charset key)
296 (setq cal (cons key cal))
297 (setq al (cons key al)))
298 (setq value (cdr value)))
299 (insert-char-attributes ret
302 (insert (prin1-to-string value)))
304 (insert line-breaking))
306 (insert (format "(%-18s " name))
307 (setq lbs (concat "\n" (make-string (current-column) ?\ )))
309 (setq cell (car value))
310 (if (and (consp cell)
312 (setq ret (condition-case nil
321 (setq key (car (car rest)))
322 (if (find-charset key)
323 (setq cal (cons key cal))
324 (setq al (cons key al)))
325 (setq rest (cdr rest)))
328 (insert-char-attributes ret
331 (setq separator lbs))
334 (insert (prin1-to-string cell))
335 (setq separator " "))
336 (setq value (cdr value)))
338 (insert line-breaking))
340 (insert (format "(%-18s . %S)%s"
343 (setq alist (cdr alist))))
346 (defun char-db-insert-char-reference (plist &optional readable column)
348 (setq column (current-column)))
350 (concat "\n" (make-string (1+ column) ?\ )))
355 (setq name (pop plist))
356 (setq value (pop plist))
357 (cond ((eq name :char)
360 (cond ((numberp value)
361 (setq value (decode-char '=ucs value)))
363 ;; (setq value (or (find-char value)
366 (char-db-insert-char-spec value readable)
367 (insert line-breaking)
370 (insert (format "%s%s\t%d ; %c%s"
373 (aref ideographic-radicals value)
377 (insert (format "%s%s\t%S" separator name value))
378 (setq separator line-breaking)))
382 (defun char-db-decode-isolated-char (ccs code-point)
385 (cond ((eq ccs 'arabic-iso8859-6)
386 (decode-char ccs code-point))
387 ((and (memq ccs '(=gt-pj-1
398 (setq ret (decode-char ccs code-point))
399 (setq ret (encode-char ret '=gt 'defined-only)))
400 (decode-builtin-char '=gt ret))
402 (decode-builtin-char ccs code-point))))
403 (cond ((and (<= 0 (char-int ret))
404 (<= (char-int ret) #x1F))
405 (decode-char '=ucs (+ #x2400 (char-int ret))))
406 ((= (char-int ret) #x7F)
410 (defvar char-db-convert-obsolete-format t)
412 (defun insert-char-attributes (char &optional readable
413 attributes ccs-attributes
418 (if (consp attributes)
420 (dolist (name attributes)
421 (unless (memq name char-db-ignored-attributes)
424 (dolist (name (char-attribute-list))
425 (unless (memq name char-db-ignored-attributes)
426 (if (find-charset name)
430 #'char-attribute-name<))
432 (sort (if ccs-attributes
435 (dolist (name ccs-attributes)
436 (unless (memq name char-db-ignored-attributes)
441 (dolist (name (charset-list))
442 (unless (memq name char-db-ignored-attributes)
445 #'char-attribute-name<)))
447 (setq column (current-column)))
448 (let (name value has-long-ccs-name rest
451 (concat "\n" (make-string (1+ column) ?\ )))
452 lbs cell separator ret
455 (when (and (memq 'name attributes)
456 (setq value (get-char-attribute char 'name)))
458 (if (> (+ (current-column) (length value)) 48)
461 value line-breaking))
462 (setq attributes (delq 'name attributes))
464 (when (and (memq 'name* attributes)
465 (setq value (get-char-attribute char 'name*)))
467 (if (> (+ (current-column) (length value)) 48)
470 value line-breaking))
471 (setq attributes (delq 'name* attributes))
473 (when (and (memq 'script attributes)
474 (setq value (get-char-attribute char 'script)))
475 (insert (format "(script\t\t%s)%s"
476 (mapconcat (function prin1-to-string)
479 (setq attributes (delq 'script attributes))
481 (dolist (name '(=>ucs =>ucs*))
482 (when (and (memq name attributes)
483 (setq value (get-char-attribute char name)))
484 (insert (format "(%-18s . #x%04X)\t; %c%s"
485 name value (decode-char '=ucs value)
487 (setq attributes (delq name attributes))))
488 ;; (when (and (memq '=>ucs* attributes)
489 ;; (setq value (get-char-attribute char '=>ucs*)))
490 ;; (insert (format "(=>ucs*\t\t. #x%04X)\t; %c%s"
491 ;; value (decode-char '=ucs value)
493 ;; (setq attributes (delq '=>ucs* attributes))
495 (dolist (name '(=>ucs@gb =>ucs@cns =>ucs@jis =>ucs@ks =>ucs@big5))
496 (when (and (memq name attributes)
497 (setq value (get-char-attribute char name)))
498 (insert (format "(%-18s . #x%04X)\t; %c%s"
503 (symbol-name name) 2)))
506 (setq attributes (delq name attributes))
508 (dolist (name '(=>ucs-gb =>ucs-cns =>ucs-jis =>ucs-ks =>ucs-big5))
509 (when (and (memq name attributes)
510 (setq value (get-char-attribute char name)))
511 (insert (format "(%-18s . #x%04X)\t; %c%s"
514 (substring (symbol-name name) 6)))
519 (symbol-name name) 6)))
522 (setq attributes (delq name attributes))))
523 ;; (when (and (memq '=>ucs-gb attributes)
524 ;; (setq value (get-char-attribute char '=>ucs-gb)))
525 ;; (insert (format "(=>ucs@gb\t\t. #x%04X)\t; %c%s"
526 ;; value (decode-char '=ucs@gb value)
528 ;; (setq attributes (delq '=>ucs-gb attributes))
530 ;; (when (and (memq '=>ucs-cns attributes)
531 ;; (setq value (get-char-attribute char '=>ucs-cns)))
532 ;; (insert (format "(=>ucs@cns\t\t. #x%04X)\t; %c%s"
533 ;; value (decode-char '=ucs@cns value)
535 ;; (setq attributes (delq '=>ucs-cns attributes))
537 ;; (when (and (memq '=>ucs-big5 attributes)
538 ;; (setq value (get-char-attribute char '=>ucs-big5)))
539 ;; (insert (format "(=>ucs-big5\t\t. #x%04X)\t; %c%s"
540 ;; value (decode-char 'ucs-big5 value)
542 ;; (setq attributes (delq '=>ucs-big5 attributes))
544 ;; (when (and (memq '=>ucs-jis attributes)
545 ;; (setq value (get-char-attribute char '=>ucs-jis)))
546 ;; (insert (format "(=>ucs@jis\t\t. #x%04X)\t; %c%s"
547 ;; value (decode-char '=ucs@jis value)
549 ;; (setq attributes (delq '=>ucs-jis attributes))
551 ;; (when (and (memq '=>ucs-ks attributes)
552 ;; (setq value (get-char-attribute char '=>ucs-ks)))
553 ;; (insert (format "(=>ucs-ks\t\t. #x%04X)\t; %c%s"
554 ;; value (decode-char 'ucs-ks value)
556 ;; (setq attributes (delq '=>ucs-ks attributes))
558 (when (and (memq '->ucs attributes)
559 (setq value (get-char-attribute char '->ucs)))
560 (insert (format (if char-db-convert-obsolete-format
561 "(=>ucs\t\t. #x%04X)\t; %c%s"
562 "(->ucs\t\t. #x%04X)\t; %c%s")
563 value (decode-char '=ucs value)
565 (setq attributes (delq '->ucs attributes))
567 (when (and (memq 'general-category attributes)
568 (setq value (get-char-attribute char 'general-category)))
570 "(general-category\t%s) ; %s%s"
571 (mapconcat (lambda (cell)
574 (cond ((rassoc value unidata-normative-category-alist)
575 "Normative Category")
576 ((rassoc value unidata-informative-category-alist)
577 "Informative Category")
581 (setq attributes (delq 'general-category attributes))
583 (when (and (memq 'bidi-category attributes)
584 (setq value (get-char-attribute char 'bidi-category)))
585 (insert (format "(bidi-category\t. %S)%s"
588 (setq attributes (delq 'bidi-category attributes))
590 (unless (or (not (memq 'mirrored attributes))
591 (eq (setq value (get-char-attribute char 'mirrored 'empty))
593 (insert (format "(mirrored\t\t. %S)%s"
596 (setq attributes (delq 'mirrored attributes))
599 ((and (memq 'decimal-digit-value attributes)
600 (setq value (get-char-attribute char 'decimal-digit-value)))
601 (insert (format "(decimal-digit-value . %S)%s"
604 (setq attributes (delq 'decimal-digit-value attributes))
605 (when (and (memq 'digit-value attributes)
606 (setq value (get-char-attribute char 'digit-value)))
607 (insert (format "(digit-value\t . %S)%s"
610 (setq attributes (delq 'digit-value attributes))
612 (when (and (memq 'numeric-value attributes)
613 (setq value (get-char-attribute char 'numeric-value)))
614 (insert (format "(numeric-value\t . %S)%s"
617 (setq attributes (delq 'numeric-value attributes))
621 (when (and (memq 'digit-value attributes)
622 (setq value (get-char-attribute char 'digit-value)))
623 (insert (format "(digit-value\t. %S)%s"
626 (setq attributes (delq 'digit-value attributes))
628 (when (and (memq 'numeric-value attributes)
629 (setq value (get-char-attribute char 'numeric-value)))
630 (insert (format "(numeric-value\t. %S)%s"
633 (setq attributes (delq 'numeric-value attributes))
635 (when (and (memq 'iso-10646-comment attributes)
636 (setq value (get-char-attribute char 'iso-10646-comment)))
637 (insert (format "(iso-10646-comment\t. %S)%s"
640 (setq attributes (delq 'iso-10646-comment attributes))
642 (when (and (memq 'morohashi-daikanwa attributes)
643 (setq value (get-char-attribute char 'morohashi-daikanwa)))
644 (insert (format "(morohashi-daikanwa\t%s)%s"
645 (mapconcat (function prin1-to-string) value " ")
647 (setq attributes (delq 'morohashi-daikanwa attributes))
651 (when (and (memq 'ideographic-radical attributes)
652 (setq value (get-char-attribute char 'ideographic-radical)))
654 (insert (format "(ideographic-radical . %S)\t; %c%s"
656 (aref ideographic-radicals radical)
658 (setq attributes (delq 'ideographic-radical attributes))
660 (when (and (memq 'ideographic-strokes attributes)
661 (setq value (get-char-attribute char 'ideographic-strokes)))
663 (insert (format "(ideographic-strokes . %S)%s"
666 (setq attributes (delq 'ideographic-strokes attributes))
668 (when (and (memq 'kangxi-radical attributes)
669 (setq value (get-char-attribute char 'kangxi-radical)))
670 (unless (eq value radical)
671 (insert (format "(kangxi-radical\t . %S)\t; %c%s"
673 (aref ideographic-radicals value)
676 (setq radical value)))
677 (setq attributes (delq 'kangxi-radical attributes))
679 (when (and (memq 'kangxi-strokes attributes)
680 (setq value (get-char-attribute char 'kangxi-strokes)))
681 (unless (eq value strokes)
682 (insert (format "(kangxi-strokes\t . %S)%s"
686 (setq strokes value)))
687 (setq attributes (delq 'kangxi-strokes attributes))
689 (when (and (memq 'japanese-radical attributes)
690 (setq value (get-char-attribute char 'japanese-radical)))
691 (unless (eq value radical)
692 (insert (format "(japanese-radical\t . %S)\t; %c%s"
694 (aref ideographic-radicals value)
697 (setq radical value)))
698 (setq attributes (delq 'japanese-radical attributes))
700 (when (and (memq 'japanese-strokes attributes)
701 (setq value (get-char-attribute char 'japanese-strokes)))
702 (unless (eq value strokes)
703 (insert (format "(japanese-strokes\t . %S)%s"
707 (setq strokes value)))
708 (setq attributes (delq 'japanese-strokes attributes))
710 (when (and (memq 'cns-radical attributes)
711 (setq value (get-char-attribute char 'cns-radical)))
712 (insert (format "(cns-radical\t . %S)\t; %c%s"
714 (aref ideographic-radicals value)
716 (setq attributes (delq 'cns-radical attributes))
718 (when (and (memq 'cns-strokes attributes)
719 (setq value (get-char-attribute char 'cns-strokes)))
720 (unless (eq value strokes)
721 (insert (format "(cns-strokes\t . %S)%s"
725 (setq strokes value)))
726 (setq attributes (delq 'cns-strokes attributes))
728 (when (and (memq 'shinjigen-1-radical attributes)
729 (setq value (get-char-attribute char 'shinjigen-1-radical)))
730 (unless (eq value radical)
731 (insert (format "(shinjigen-1-radical . %S)\t; %c%s"
733 (aref ideographic-radicals value)
736 (setq radical value)))
737 (setq attributes (delq 'shinjigen-1-radical attributes))
739 (when (and (memq 'ideographic- attributes)
740 (setq value (get-char-attribute char 'ideographic-)))
741 (insert "(ideographic- ")
742 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
745 (setq cell (car value))
747 (setq cell (decode-char '=ucs cell)))
748 (cond ((characterp cell)
752 (insert (format "%S" cell))
753 (char-db-insert-char-spec cell readable))
754 (setq separator lbs))
758 (if (consp (car cell))
759 (char-db-insert-char-spec cell readable)
760 (char-db-insert-char-reference cell readable))
761 (setq separator lbs))
765 (insert (prin1-to-string cell))
766 (setq separator " ")))
767 (setq value (cdr value)))
769 (insert line-breaking)
770 (setq attributes (delq 'ideographic- attributes)))
771 (when (and (memq 'total-strokes attributes)
772 (setq value (get-char-attribute char 'total-strokes)))
773 (insert (format "(total-strokes . %S)%s"
776 (setq attributes (delq 'total-strokes attributes))
778 (when (and (memq '->ideograph attributes)
779 (setq value (get-char-attribute char '->ideograph)))
780 (insert (format "(->ideograph\t%s)%s"
781 (mapconcat (lambda (code)
782 (cond ((symbolp code)
785 (format "#x%04X" code))
788 line-breaking code))))
791 (setq attributes (delq '->ideograph attributes))
793 (when (and (memq '->decomposition attributes)
794 (setq value (get-char-attribute char '->decomposition)))
795 (insert (format "(->decomposition\t%s)%s"
796 (mapconcat (lambda (code)
797 (cond ((symbolp code)
806 (format "#x%04X" code))
808 (format "%s%S" line-breaking code))))
811 (setq attributes (delq '->decomposition attributes))
813 (if (equal (get-char-attribute char '->titlecase)
814 (get-char-attribute char '->uppercase))
815 (setq attributes (delq '->titlecase attributes)))
816 (when (and (memq '->mojikyo attributes)
817 (setq value (get-char-attribute char '->mojikyo)))
818 (insert (format "(->mojikyo\t\t. %06d)\t; %c%s"
819 value (decode-char 'mojikyo value)
821 (setq attributes (delq '->mojikyo attributes))
823 (when (and (memq 'hanyu-dazidian-vol attributes)
824 (setq value (get-char-attribute char 'hanyu-dazidian-vol)))
825 (insert (format "(hanyu-dazidian-vol . %d)%s"
826 value line-breaking))
827 (setq attributes (delq 'hanyu-dazidian-vol attributes))
829 (when (and (memq 'hanyu-dazidian-page attributes)
830 (setq value (get-char-attribute char 'hanyu-dazidian-page)))
831 (insert (format "(hanyu-dazidian-page . %d)%s"
832 value line-breaking))
833 (setq attributes (delq 'hanyu-dazidian-page attributes))
835 (when (and (memq 'hanyu-dazidian-char attributes)
836 (setq value (get-char-attribute char 'hanyu-dazidian-char)))
837 (insert (format "(hanyu-dazidian-char . %d)%s"
838 value line-breaking))
839 (setq attributes (delq 'hanyu-dazidian-char attributes))
842 (when (memq '->ucs-variants attributes)
843 (setq attributes (delq '->ucs-variants attributes))
845 (when (memq 'composition attributes)
846 (setq attributes (delq 'composition attributes))
848 (setq rest ccs-attributes)
851 (setq value (get-char-attribute char (car rest)))
853 (if (>= (length (symbol-name (car rest))) 19)
855 (setq has-long-ccs-name t)
859 (setq rest (cdr rest)))
861 (setq name (car attributes))
862 (if (setq value (get-char-attribute char name))
863 (cond ((string-match "^=>ucs@" (symbol-name name))
864 (insert (format "(%-18s . #x%04X)\t; %c%s"
865 name value (decode-char '=ucs value)
868 ((eq name 'jisx0208-1978/4X)
869 (insert (format "(%-18s . #x%04X)%s"
872 ((or (eq name 'ideographic-structure)
873 (eq name 'ideographic-)
874 (string-match "^\\(->\\|<-\\)" (symbol-name name)))
875 (insert (format "(%-18s%s " name line-breaking))
876 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
879 (setq cell (car value))
881 (setq cell (decode-char '=ucs cell)))
882 (cond ((characterp cell)
886 (insert (format "%S" cell))
887 (char-db-insert-char-spec cell readable))
888 (setq separator lbs))
892 (if (consp (car cell))
893 (char-db-insert-char-spec cell readable)
894 (char-db-insert-char-reference cell readable))
895 (setq separator lbs))
899 (insert (prin1-to-string cell))
900 (setq separator " ")))
901 (setq value (cdr value)))
903 (insert line-breaking))
904 ((memq name '(ideograph=
905 original-ideograph-of
909 simplified-ideograph-of
911 ideographic-different-form-of))
912 (insert (format "(%-18s%s " name line-breaking))
913 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
916 (setq cell (car value))
917 (if (and (consp cell)
922 (char-db-insert-alist cell readable)
923 (setq separator lbs))
926 (insert (prin1-to-string cell))
927 (setq separator " "))
928 (setq value (cdr value)))
930 (insert line-breaking))
931 ;; ((string-match "^->" (symbol-name name))
933 ;; (format "(%-18s %s)%s"
935 ;; (mapconcat (lambda (code)
936 ;; (cond ((symbolp code)
937 ;; (symbol-name code))
939 ;; (format "#x%04X" code))
942 ;; line-breaking code))))
946 (insert (format "(%-18s " name))
947 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
950 (setq cell (car value))
951 (if (and (consp cell)
953 (setq ret (condition-case nil
961 (setq key (car (car rest)))
962 (if (find-charset key)
963 (setq cal (cons key cal))
964 (setq al (cons key al)))
965 (setq rest (cdr rest)))
968 (insert-char-attributes ret
971 (setq separator lbs))
974 (insert (prin1-to-string cell))
975 (setq separator " "))
976 (setq value (cdr value)))
978 (insert line-breaking))
980 (insert (format "(%-18s . %S)%s"
984 (setq attributes (cdr attributes)))
985 (while ccs-attributes
986 (setq name (car ccs-attributes))
987 (if (and (eq name (charset-name name))
988 (setq value (get-char-attribute char name)))
991 (cond ((memq name '(ideograph-daikanwa
995 (if has-long-ccs-name
996 "(%-26s . %05d)\t; %c%s"
997 "(%-18s . %05d)\t; %c%s"))
999 (if has-long-ccs-name
1000 "(%-26s . %06d)\t; %c%s"
1001 "(%-18s . %06d)\t; %c%s"))
1002 ((>= (charset-dimension name) 2)
1003 (if has-long-ccs-name
1004 "(%-26s . #x%04X)\t; %c%s"
1005 "(%-18s . #x%04X)\t; %c%s"))
1007 (if has-long-ccs-name
1008 "(%-26s . #x%02X)\t; %c%s"
1009 "(%-18s . #x%02X)\t; %c%s")))
1011 (if (= (charset-iso-graphic-plane name) 1)
1013 (cond ((= (charset-dimension name) 1)
1015 ((= (charset-dimension name) 2)
1017 ((= (charset-dimension name) 3)
1021 (char-db-decode-isolated-char name value)
1023 (setq ccs-attributes (cdr ccs-attributes)))
1026 (defun insert-char-data (char &optional readable
1027 attributes ccs-attributes)
1029 (narrow-to-region (point)(point))
1030 (insert "(define-char
1032 (insert-char-attributes char readable
1033 attributes ccs-attributes)
1035 (goto-char (point-min))
1036 (while (re-search-forward "[ \t]+$" nil t)
1039 (goto-char (point-min))
1040 (while (re-search-forward "[ \t][ \t][ \t]*" nil t)
1041 (let ((column (current-column))
1042 (indent-tabs-mode t))
1043 (delete-region (match-beginning 0) (point))
1044 (indent-to column)))
1045 (goto-char (point-max))
1046 ;; (tabify (point-min)(point-max))
1049 (defun insert-char-data-with-variant (char &optional printable
1051 script excluded-script)
1052 (insert-char-data char printable)
1053 (let ((variants (or (char-variants char)
1054 (let ((ucs (get-char-attribute char '->ucs)))
1056 (delete char (char-variants (int-char ucs)))))))
1058 (setq variants (sort variants #'<))
1060 (setq variant (car variants))
1061 (if (and (or (null script)
1062 (null (setq vs (get-char-attribute variant 'script)))
1064 (or (null excluded-script)
1065 (null (setq vs (get-char-attribute variant 'script)))
1066 (not (memq excluded-script vs))))
1067 (or (and no-ucs-variant (get-char-attribute variant '=ucs))
1068 (insert-char-data variant printable)))
1069 (setq variants (cdr variants))
1072 (defun insert-char-range-data (min max &optional script excluded-script)
1075 (while (<= code max)
1076 (setq char (decode-char '=ucs code))
1077 (if (encode-char char '=ucs 'defined-only)
1078 (insert-char-data-with-variant char nil 'no-ucs-variant
1079 script excluded-script))
1080 (setq code (1+ code)))))
1082 (defun write-char-range-data-to-file (min max file
1083 &optional script excluded-script)
1084 (let ((coding-system-for-write 'utf-8))
1086 (insert-char-range-data min max script excluded-script)
1087 (write-region (point-min)(point-max) file))))
1089 (defvar what-character-original-window-configuration)
1092 (defun what-char-definition (char)
1093 (interactive (list (char-after)))
1094 (let ((buf (get-buffer-create "*Character Description*"))
1095 (the-buf (current-buffer))
1096 (win-conf (current-window-configuration)))
1098 (make-local-variable 'what-character-original-window-configuration)
1099 (setq what-character-original-window-configuration win-conf)
1100 (setq buffer-read-only nil)
1104 (insert-char-data-with-variant char 'printable)
1105 (unless (char-attribute-alist char)
1106 (insert (format ";; = %c\n"
1107 (let* ((rest (split-char char))
1111 (setq code (logior (lsh code 8)
1113 (decode-char ccs code)))))
1114 ;; (char-db-update-comment)
1115 (set-buffer-modified-p nil)
1116 (view-mode the-buf (lambda (buf)
1117 (set-window-configuration
1118 what-character-original-window-configuration)
1120 (goto-char (point-min)))
1122 (set-window-configuration
1123 what-character-original-window-configuration)
1124 (signal (car err) (cdr err)))))))
1126 (provide 'char-db-util)
1128 ;;; char-db-util.el ends here