1 ;;; char-db-util.el --- Character Database utility
3 ;; Copyright (C) 1998,1999,2000,2001,2002 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 (int-char (+ #x2EFF i)))
70 (unless (charset-iso-final-char (car (split-char (aref v 34))))
71 (aset v 34 (make-char 'chinese-gb2312 #x62 #x3A)))
74 (defvar char-db-ignored-attributes nil)
77 (defun char-ref= (cr1 cr2)
78 (cond ((char-ref-p cr1)
80 (char-spec= (plist-get cr1 :char)
81 (plist-get cr2 :char))
82 (char-spec= (plist-get cr1 :char) cr2)))
90 (defun char-spec= (cs1 cs2)
94 (eq cs1 (find-char cs2)))
96 (eq (find-char cs1) cs2)
97 (eq (find-char cs1) (find-char cs2)))))
99 (defun char-attribute-name< (ka kb)
105 ((= (charset-dimension ka)
106 (charset-dimension kb))
107 (cond ((= (charset-chars ka)(charset-chars kb))
108 (if (charset-iso-final-char ka)
110 ((>= (charset-iso-final-char ka) ?@)
111 (if (and (charset-iso-final-char kb)
112 (>= (charset-iso-final-char kb) ?@))
113 (< (charset-iso-final-char ka)
114 (charset-iso-final-char kb))
117 (if (charset-iso-final-char kb)
118 (if (>= (charset-iso-final-char kb) ?@)
120 (< (charset-iso-final-char ka)
121 (charset-iso-final-char kb)))
123 (if (charset-iso-final-char kb)
125 (< (charset-id ka)(charset-id kb)))))
126 ((<= (charset-chars ka)(charset-chars kb)))))
128 (< (charset-dimension ka)
129 (charset-dimension kb))
139 (string< (symbol-name ka)
145 (defvar char-db-coded-charset-priority-list
146 (let ((rest default-coded-charset-priority-list)
149 (when (symbolp (car rest))
150 (cond ((memq (car rest)
159 ((string-match "^mojikyo-" (symbol-name (car rest))))
160 ((string-match "^chinese-big5" (symbol-name (car rest))))
161 ((string-match "^ideograph-gt-pj-" (symbol-name (car rest)))
162 (unless (memq 'ideograph-gt dest)
163 (setq dest (cons 'ideograph-gt dest))))
165 (setq dest (cons (car rest) dest)))))
166 (setq rest (cdr rest)))
167 (append (sort dest #'char-attribute-name<)
168 '(chinese-big5-cdp chinese-big5-eten chinese-big5))))
170 (defun char-db-make-char-spec (char)
172 (cond ((characterp char)
173 (cond ((and (setq ret (get-char-attribute char 'ucs))
174 (not (and (<= #xE000 ret)(<= ret #xF8FF))))
175 (setq char-spec (list (cons 'ucs ret)))
176 (if (setq ret (get-char-attribute char 'name))
177 (setq char-spec (cons (cons 'name ret) char-spec)))
180 (let ((default-coded-charset-priority-list
181 char-db-coded-charset-priority-list))
183 (setq char-spec (list ret))
184 (dolist (ccs (delq (car ret) (charset-list)))
185 (if (or (and (charset-iso-final-char ccs)
186 (setq ret (get-char-attribute char ccs)))
187 (eq ccs 'ideograph-daikanwa))
188 (setq char-spec (cons (cons ccs ret) char-spec))))
190 (setq char-spec (split-char char)))
191 (if (setq ret (get-char-attribute char 'name))
192 (setq char-spec (cons (cons 'name ret) char-spec)))
198 (defun char-db-insert-char-spec (char &optional readable column)
200 (setq column (current-column)))
201 (let (char-spec ret al cal key temp-char)
202 (setq char-spec (char-db-make-char-spec char))
203 ;; (cond ((characterp char)
204 ;; (cond ((and (setq ret (get-char-attribute char 'ucs))
205 ;; (not (and (<= #xE000 ret)(<= ret #xF8FF))))
206 ;; (setq char-spec (list (cons 'ucs ret)))
207 ;; (if (setq ret (get-char-attribute char 'name))
208 ;; (setq char-spec (cons (cons 'name ret) char-spec)))
211 ;; (let ((default-coded-charset-priority-list
212 ;; char-db-coded-charset-priority-list))
213 ;; (split-char char)))
214 ;; (setq char-spec (list ret))
215 ;; (dolist (ccs (delq (car ret) (charset-list)))
216 ;; (if (or (and (charset-iso-final-char ccs)
217 ;; (setq ret (get-char-attribute char ccs)))
218 ;; (eq ccs 'ideograph-daikanwa))
219 ;; (setq char-spec (cons (cons ccs ret) char-spec))))
220 ;; (if (null char-spec)
221 ;; (setq char-spec (split-char char)))
222 ;; (if (setq ret (get-char-attribute char 'name))
223 ;; (setq char-spec (cons (cons 'name ret) char-spec)))
226 ;; (setq char-spec char)
228 (unless (or (characterp char) ; char
230 (setq char (find-char char-spec))
232 ;; define temporary character
233 ;; Current implementation is dirty.
234 (setq temp-char (define-char (cons '(ideograph-daikanwa . 0)
236 (remove-char-attribute temp-char 'ideograph-daikanwa)
237 (setq char temp-char))
241 (setq key (car (car char-spec)))
242 (unless (memq key char-db-ignored-attributes)
243 (if (find-charset key)
244 (if (get-char-attribute char key)
245 (setq cal (cons key cal)))
246 (setq al (cons key al))))
247 (setq char-spec (cdr char-spec)))
249 (setq char-spec (char-db-make-char-spec char))
251 (setq key (car (car char-spec)))
252 (unless (memq key char-db-ignored-attributes)
253 (if (find-charset key)
254 (setq cal (cons key cal))
255 (setq al (cons key al))))
256 (setq char-spec (cdr char-spec)))
259 (memq 'ideographic-structure al))
260 (push 'ideographic-structure al))
261 (insert-char-attributes char
265 ;; undefine temporary character
266 ;; Current implementation is dirty.
267 (setq char-spec (char-attribute-alist temp-char))
269 (remove-char-attribute temp-char (car (car char-spec)))
270 (setq char-spec (cdr char-spec))))))
272 (defun char-db-insert-alist (alist &optional readable column)
274 (setq column (current-column)))
276 (concat "\n" (make-string (1+ column) ?\ )))
279 lbs cell rest separator)
282 (setq name (car (car alist))
283 value (cdr (car alist)))
284 (cond ((eq name 'char)
286 (if (setq ret (condition-case nil
293 (setq key (car (car value)))
294 (if (find-charset key)
295 (setq cal (cons key cal))
296 (setq al (cons key al)))
297 (setq value (cdr value)))
298 (insert-char-attributes ret
301 (insert (prin1-to-string value)))
303 (insert line-breaking))
305 (insert (format "(%-18s " name))
306 (setq lbs (concat "\n" (make-string (current-column) ?\ )))
308 (setq cell (car value))
309 (if (and (consp cell)
311 (setq ret (condition-case nil
320 (setq key (car (car rest)))
321 (if (find-charset key)
322 (setq cal (cons key cal))
323 (setq al (cons key al)))
324 (setq rest (cdr rest)))
327 (insert-char-attributes ret
330 (setq separator lbs))
333 (insert (prin1-to-string cell))
334 (setq separator " "))
335 (setq value (cdr value)))
337 (insert line-breaking))
339 (insert (format "(%-18s . %S)%s"
342 (setq alist (cdr alist))))
345 (defun char-db-insert-char-reference (plist &optional readable column)
347 (setq column (current-column)))
349 (concat "\n" (make-string (1+ column) ?\ )))
354 (setq name (pop plist))
355 (setq value (pop plist))
356 (cond ((eq name :char)
359 (cond ((numberp value)
360 (setq value (decode-char 'ucs value)))
362 ;; (setq value (or (find-char value)
365 (char-db-insert-char-spec value readable)
366 (insert line-breaking)
369 (insert (format "%s%s\t%d ; %c%s"
372 (aref ideographic-radicals value)
376 (insert (format "%s%s\t%S" separator name value))
377 (setq separator line-breaking)))
381 (defun char-db-decode-isolated-char (ccs code-point)
384 (cond ((eq ccs 'arabic-iso8859-6)
385 (decode-char ccs code-point))
386 ((and (memq ccs '(ideograph-gt-pj-1
397 (setq ret (decode-char ccs code-point))
398 (setq ret (get-char-attribute ret 'ideograph-gt)))
399 (decode-builtin-char 'ideograph-gt ret))
401 (decode-builtin-char ccs code-point))))
402 (cond ((and (<= 0 (char-int ret))
403 (<= (char-int ret) #x1F))
404 (decode-char 'ucs (+ #x2400 (char-int ret))))
405 ((= (char-int ret) #x7F)
409 (defvar char-db-convert-obsolete-format t)
411 (defun insert-char-attributes (char &optional readable
412 attributes ccs-attributes
417 (if (consp attributes)
419 (dolist (name attributes)
420 (unless (memq name char-db-ignored-attributes)
423 (dolist (name (char-attribute-list))
424 (unless (memq name char-db-ignored-attributes)
425 (if (find-charset name)
429 #'char-attribute-name<))
431 (sort (if ccs-attributes
434 (dolist (name ccs-attributes)
435 (unless (memq name char-db-ignored-attributes)
440 (dolist (name (charset-list))
441 (unless (memq name char-db-ignored-attributes)
444 #'char-attribute-name<)))
446 (setq column (current-column)))
447 (let (name value has-long-ccs-name rest
450 (concat "\n" (make-string (1+ column) ?\ )))
451 lbs cell separator ret
454 (when (and (memq 'name attributes)
455 (setq value (get-char-attribute char 'name)))
457 (if (> (+ (current-column) (length value)) 48)
460 value line-breaking))
461 (setq attributes (delq 'name attributes))
463 (when (and (memq 'script attributes)
464 (setq value (get-char-attribute char 'script)))
465 (insert (format "(script\t\t%s)%s"
466 (mapconcat (function prin1-to-string)
469 (setq attributes (delq 'script attributes))
471 (when (and (memq '=>ucs attributes)
472 (setq value (get-char-attribute char '=>ucs)))
473 (insert (format "(=>ucs\t\t. #x%04X)\t; %c%s"
474 value (decode-char 'ucs value)
476 (setq attributes (delq '=>ucs 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-gb attributes)
486 (setq value (get-char-attribute char '=>ucs-gb)))
487 (insert (format "(=>ucs-gb\t\t. #x%04X)\t; %c%s"
488 value (decode-char 'ucs value)
490 (setq attributes (delq '=>ucs-gb attributes))
492 (when (and (memq '=>ucs-cns attributes)
493 (setq value (get-char-attribute char '=>ucs-cns)))
494 (insert (format "(=>ucs-cns\t\t. #x%04X)\t; %c%s"
495 value (decode-char 'ucs-cns value)
497 (setq attributes (delq '=>ucs-cns attributes))
499 (when (and (memq '=>ucs-jis attributes)
500 (setq value (get-char-attribute char '=>ucs-jis)))
501 (insert (format "(=>ucs-jis\t\t. #x%04X)\t; %c%s"
502 value (decode-char 'ucs-jis value)
504 (setq attributes (delq '=>ucs-jis attributes))
506 (when (and (memq '=>ucs-ks attributes)
507 (setq value (get-char-attribute char '=>ucs-ks)))
508 (insert (format "(=>ucs-ks\t\t. #x%04X)\t; %c%s"
509 value (decode-char 'ucs-ks value)
511 (setq attributes (delq '=>ucs-ks attributes))
513 (when (and (memq '->ucs attributes)
514 (setq value (get-char-attribute char '->ucs)))
515 (insert (format (if char-db-convert-obsolete-format
516 "(=>ucs\t\t. #x%04X)\t; %c%s"
517 "(->ucs\t\t. #x%04X)\t; %c%s")
518 value (decode-char 'ucs value)
520 (setq attributes (delq '->ucs attributes))
522 (when (and (memq 'general-category attributes)
523 (setq value (get-char-attribute char 'general-category)))
525 "(general-category\t%s) ; %s%s"
526 (mapconcat (lambda (cell)
529 (cond ((rassoc value unidata-normative-category-alist)
530 "Normative Category")
531 ((rassoc value unidata-informative-category-alist)
532 "Informative Category")
536 (setq attributes (delq 'general-category attributes))
538 (when (and (memq 'bidi-category attributes)
539 (setq value (get-char-attribute char 'bidi-category)))
540 (insert (format "(bidi-category\t. %S)%s"
543 (setq attributes (delq 'bidi-category attributes))
545 (unless (or (not (memq 'mirrored attributes))
546 (eq (setq value (get-char-attribute char 'mirrored 'empty))
548 (insert (format "(mirrored\t\t. %S)%s"
551 (setq attributes (delq 'mirrored attributes))
554 ((and (memq 'decimal-digit-value attributes)
555 (setq value (get-char-attribute char 'decimal-digit-value)))
556 (insert (format "(decimal-digit-value . %S)%s"
559 (setq attributes (delq 'decimal-digit-value attributes))
560 (when (and (memq 'digit-value attributes)
561 (setq value (get-char-attribute char 'digit-value)))
562 (insert (format "(digit-value\t . %S)%s"
565 (setq attributes (delq 'digit-value attributes))
567 (when (and (memq 'numeric-value attributes)
568 (setq value (get-char-attribute char 'numeric-value)))
569 (insert (format "(numeric-value\t . %S)%s"
572 (setq attributes (delq 'numeric-value attributes))
576 (when (and (memq 'digit-value attributes)
577 (setq value (get-char-attribute char 'digit-value)))
578 (insert (format "(digit-value\t. %S)%s"
581 (setq attributes (delq 'digit-value attributes))
583 (when (and (memq 'numeric-value attributes)
584 (setq value (get-char-attribute char 'numeric-value)))
585 (insert (format "(numeric-value\t. %S)%s"
588 (setq attributes (delq 'numeric-value attributes))
590 (when (and (memq 'iso-10646-comment attributes)
591 (setq value (get-char-attribute char 'iso-10646-comment)))
592 (insert (format "(iso-10646-comment\t. %S)%s"
595 (setq attributes (delq 'iso-10646-comment attributes))
597 (when (and (memq 'morohashi-daikanwa attributes)
598 (setq value (get-char-attribute char 'morohashi-daikanwa)))
599 (insert (format "(morohashi-daikanwa\t%s)%s"
600 (mapconcat (function prin1-to-string) value " ")
602 (setq attributes (delq 'morohashi-daikanwa attributes))
606 (when (and (memq 'ideographic-radical attributes)
607 (setq value (get-char-attribute char 'ideographic-radical)))
609 (insert (format "(ideographic-radical . %S)\t; %c%s"
611 (aref ideographic-radicals radical)
613 (setq attributes (delq 'ideographic-radical attributes))
615 (when (and (memq 'ideographic-strokes attributes)
616 (setq value (get-char-attribute char 'ideographic-strokes)))
618 (insert (format "(ideographic-strokes . %S)%s"
621 (setq attributes (delq 'ideographic-strokes attributes))
623 (when (and (memq 'kangxi-radical attributes)
624 (setq value (get-char-attribute char 'kangxi-radical)))
625 (unless (eq value radical)
626 (insert (format "(kangxi-radical\t . %S)\t; %c%s"
628 (aref ideographic-radicals value)
631 (setq radical value)))
632 (setq attributes (delq 'kangxi-radical attributes))
634 (when (and (memq 'kangxi-strokes attributes)
635 (setq value (get-char-attribute char 'kangxi-strokes)))
636 (unless (eq value strokes)
637 (insert (format "(kangxi-strokes\t . %S)%s"
641 (setq strokes value)))
642 (setq attributes (delq 'kangxi-strokes attributes))
644 (when (and (memq 'japanese-radical attributes)
645 (setq value (get-char-attribute char 'japanese-radical)))
646 (unless (eq value radical)
647 (insert (format "(japanese-radical\t . %S)\t; %c%s"
649 (aref ideographic-radicals value)
652 (setq radical value)))
653 (setq attributes (delq 'japanese-radical attributes))
655 (when (and (memq 'japanese-strokes attributes)
656 (setq value (get-char-attribute char 'japanese-strokes)))
657 (unless (eq value strokes)
658 (insert (format "(japanese-strokes\t . %S)%s"
662 (setq strokes value)))
663 (setq attributes (delq 'japanese-strokes attributes))
665 (when (and (memq 'cns-radical attributes)
666 (setq value (get-char-attribute char 'cns-radical)))
667 (insert (format "(cns-radical\t . %S)\t; %c%s"
669 (aref ideographic-radicals value)
671 (setq attributes (delq 'cns-radical attributes))
673 (when (and (memq 'cns-strokes attributes)
674 (setq value (get-char-attribute char 'cns-strokes)))
675 (unless (eq value strokes)
676 (insert (format "(cns-strokes\t . %S)%s"
680 (setq strokes value)))
681 (setq attributes (delq 'cns-strokes attributes))
683 (when (and (memq 'shinjigen-1-radical attributes)
684 (setq value (get-char-attribute char 'shinjigen-1-radical)))
685 (unless (eq value radical)
686 (insert (format "(shinjigen-1-radical . %S)\t; %c%s"
688 (aref ideographic-radicals value)
691 (setq radical value)))
692 (setq attributes (delq 'shinjigen-1-radical attributes))
694 (when (and (memq 'ideographic- attributes)
695 (setq value (get-char-attribute char 'ideographic-)))
696 (insert "(ideographic- ")
697 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
700 (setq cell (car value))
702 (setq cell (decode-char 'ucs cell)))
703 (cond ((characterp cell)
707 (insert (format "%S" cell))
708 (char-db-insert-char-spec cell readable))
709 (setq separator lbs))
713 (if (consp (car cell))
714 (char-db-insert-char-spec cell readable)
715 (char-db-insert-char-reference cell readable))
716 (setq separator lbs))
720 (insert (prin1-to-string cell))
721 (setq separator " ")))
722 (setq value (cdr value)))
724 (insert line-breaking)
725 (setq attributes (delq 'ideographic- attributes)))
726 (when (and (memq 'total-strokes attributes)
727 (setq value (get-char-attribute char 'total-strokes)))
728 (insert (format "(total-strokes . %S)%s"
731 (setq attributes (delq 'total-strokes attributes))
733 (when (and (memq '->ideograph attributes)
734 (setq value (get-char-attribute char '->ideograph)))
735 (insert (format "(->ideograph\t%s)%s"
736 (mapconcat (lambda (code)
737 (cond ((symbolp code)
740 (format "#x%04X" code))
743 line-breaking code))))
746 (setq attributes (delq '->ideograph attributes))
748 (when (and (memq '->decomposition attributes)
749 (setq value (get-char-attribute char '->decomposition)))
750 (insert (format "(->decomposition\t%s)%s"
751 (mapconcat (lambda (code)
752 (cond ((symbolp code)
761 (format "#x%04X" code))
763 (format "%s%S" line-breaking code))))
766 (setq attributes (delq '->decomposition attributes))
768 (if (equal (get-char-attribute char '->titlecase)
769 (get-char-attribute char '->uppercase))
770 (setq attributes (delq '->titlecase attributes)))
771 (when (and (memq '->mojikyo attributes)
772 (setq value (get-char-attribute char '->mojikyo)))
773 (insert (format "(->mojikyo\t\t. %06d)\t; %c%s"
774 value (decode-char 'mojikyo value)
776 (setq attributes (delq '->mojikyo attributes))
778 (when (and (memq 'hanyu-dazidian-vol attributes)
779 (setq value (get-char-attribute char 'hanyu-dazidian-vol)))
780 (insert (format "(hanyu-dazidian-vol . %d)%s"
781 value line-breaking))
782 (setq attributes (delq 'hanyu-dazidian-vol attributes))
784 (when (and (memq 'hanyu-dazidian-page attributes)
785 (setq value (get-char-attribute char 'hanyu-dazidian-page)))
786 (insert (format "(hanyu-dazidian-page . %d)%s"
787 value line-breaking))
788 (setq attributes (delq 'hanyu-dazidian-page attributes))
790 (when (and (memq 'hanyu-dazidian-char attributes)
791 (setq value (get-char-attribute char 'hanyu-dazidian-char)))
792 (insert (format "(hanyu-dazidian-char . %d)%s"
793 value line-breaking))
794 (setq attributes (delq 'hanyu-dazidian-char attributes))
796 (setq rest ccs-attributes)
799 (setq value (get-char-attribute char (car rest)))
801 (if (>= (length (symbol-name (car rest))) 19)
803 (setq has-long-ccs-name t)
807 (setq rest (cdr rest)))
809 (setq name (car attributes))
810 (if (setq value (get-char-attribute char name))
811 (cond ((eq name 'jisx0208-1978/4X)
812 (insert (format "(%-18s . #x%04X)%s"
815 ((or (eq name 'ideographic-structure)
816 (eq name 'ideographic-)
817 (string-match "^\\(->\\|<-\\)" (symbol-name name)))
818 (insert (format "(%-18s%s " name line-breaking))
819 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
822 (setq cell (car value))
824 (setq cell (decode-char 'ucs cell)))
825 (cond ((characterp cell)
829 (insert (format "%S" cell))
830 (char-db-insert-char-spec cell readable))
831 (setq separator lbs))
835 (if (consp (car cell))
836 (char-db-insert-char-spec cell readable)
837 (char-db-insert-char-reference cell readable))
838 (setq separator lbs))
842 (insert (prin1-to-string cell))
843 (setq separator " ")))
844 (setq value (cdr value)))
846 (insert line-breaking))
847 ((memq name '(ideograph=
848 original-ideograph-of
852 simplified-ideograph-of
854 ideographic-different-form-of))
855 (insert (format "(%-18s%s " name line-breaking))
856 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
859 (setq cell (car value))
860 (if (and (consp cell)
865 (char-db-insert-alist cell readable)
866 (setq separator lbs))
869 (insert (prin1-to-string cell))
870 (setq separator " "))
871 (setq value (cdr value)))
873 (insert line-breaking))
874 ;; ((string-match "^->" (symbol-name name))
876 ;; (format "(%-18s %s)%s"
878 ;; (mapconcat (lambda (code)
879 ;; (cond ((symbolp code)
880 ;; (symbol-name code))
882 ;; (format "#x%04X" code))
885 ;; line-breaking code))))
889 (insert (format "(%-18s " name))
890 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
893 (setq cell (car value))
894 (if (and (consp cell)
896 (setq ret (condition-case nil
904 (setq key (car (car rest)))
905 (if (find-charset key)
906 (setq cal (cons key cal))
907 (setq al (cons key al)))
908 (setq rest (cdr rest)))
911 (insert-char-attributes ret
914 (setq separator lbs))
917 (insert (prin1-to-string cell))
918 (setq separator " "))
919 (setq value (cdr value)))
921 (insert line-breaking))
923 (insert (format "(%-18s . %S)%s"
927 (setq attributes (cdr attributes)))
928 (while ccs-attributes
929 (setq name (car ccs-attributes))
930 (if (and (eq name (charset-name name))
931 (setq value (get-char-attribute char name)))
934 (cond ((memq name '(ideograph-daikanwa-2
938 (if has-long-ccs-name
939 "(%-26s . %05d)\t; %c%s"
940 "(%-18s . %05d)\t; %c%s"))
942 (if has-long-ccs-name
943 "(%-26s . %06d)\t; %c%s"
944 "(%-18s . %06d)\t; %c%s"))
946 (if has-long-ccs-name
947 "(%-26s . #x%04X)\t; %c%s"
948 "(%-18s . #x%04X)\t; %c%s"))
950 (if has-long-ccs-name
951 "(%-26s . #x%02X)\t; %c%s"
952 "(%-18s . #x%02X)\t; %c%s")))
954 (if (= (charset-iso-graphic-plane name) 1)
956 (cond ((= (charset-dimension name) 1)
958 ((= (charset-dimension name) 2)
960 ((= (charset-dimension name) 3)
964 (char-db-decode-isolated-char name value)
966 (setq ccs-attributes (cdr ccs-attributes)))
969 (defun insert-char-data (char &optional readable
970 attributes ccs-attributes)
972 (narrow-to-region (point)(point))
973 (insert "(define-char
975 (insert-char-attributes char readable
976 attributes ccs-attributes)
978 (goto-char (point-min))
979 (while (re-search-forward "[ \t]+$" nil t)
981 (goto-char (point-max))
982 (tabify (point-min)(point-max))
985 (defun insert-char-data-with-variant (char &optional printable
987 script excluded-script)
988 (insert-char-data char printable)
989 (let ((variants (or (char-variants char)
990 (let ((ucs (get-char-attribute char '->ucs)))
992 (delete char (char-variants (int-char ucs)))))))
994 (setq variants (sort variants #'<))
996 (setq variant (car variants))
997 (if (and (or (null script)
998 (null (setq vs (get-char-attribute variant 'script)))
1000 (or (null excluded-script)
1001 (null (setq vs (get-char-attribute variant 'script)))
1002 (not (memq excluded-script vs))))
1003 (or (and no-ucs-variant (get-char-attribute variant 'ucs))
1004 (insert-char-data variant printable)))
1005 (setq variants (cdr variants))
1008 (defun insert-char-range-data (min max &optional script excluded-script)
1011 (while (<= code max)
1012 (setq char (decode-char 'ucs code))
1013 (if (get-char-attribute char 'ucs)
1014 (insert-char-data-with-variant char nil 'no-ucs-variant
1015 script excluded-script))
1016 (setq code (1+ code))
1019 (defun write-char-range-data-to-file (min max file
1020 &optional script excluded-script)
1021 (let ((coding-system-for-write 'utf-8))
1023 (insert-char-range-data min max script excluded-script)
1024 (write-region (point-min)(point-max) file))))
1026 (defvar what-character-original-window-configuration)
1029 (defun what-char-definition (char)
1030 (interactive (list (char-after)))
1031 (let ((buf (get-buffer-create "*Character Description*"))
1032 (the-buf (current-buffer))
1033 (win-conf (current-window-configuration)))
1035 (make-local-variable 'what-character-original-window-configuration)
1036 (setq what-character-original-window-configuration win-conf)
1037 (setq buffer-read-only nil)
1041 (insert-char-data-with-variant char 'printable)
1042 (unless (char-attribute-alist char)
1043 (insert (format ";; = %c\n"
1044 (let* ((rest (split-char char))
1048 (setq code (logior (lsh code 8)
1050 (decode-char ccs code)))))
1051 ;; (char-db-update-comment)
1052 (set-buffer-modified-p nil)
1053 (view-mode the-buf (lambda (buf)
1054 (set-window-configuration
1055 what-character-original-window-configuration)
1057 (goto-char (point-min)))
1059 (set-window-configuration
1060 what-character-original-window-configuration)
1061 (signal (car err) (cdr err)))))))
1063 (provide 'char-db-util)
1065 ;;; char-db-util.el ends here