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-jis attributes)
486 (setq value (get-char-attribute char '=>ucs-jis)))
487 (insert (format "(=>ucs-jis\t\t. #x%04X)\t; %c%s"
488 value (decode-char 'ucs-jis value)
490 (setq attributes (delq '=>ucs-jis 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 attributes)
500 (setq value (get-char-attribute char '->ucs)))
501 (insert (format (if char-db-convert-obsolete-format
502 "(=>ucs\t\t. #x%04X)\t; %c%s"
503 "(->ucs\t\t. #x%04X)\t; %c%s")
504 value (decode-char 'ucs value)
506 (setq attributes (delq '->ucs attributes))
508 (when (and (memq 'general-category attributes)
509 (setq value (get-char-attribute char 'general-category)))
511 "(general-category\t%s) ; %s%s"
512 (mapconcat (lambda (cell)
515 (cond ((rassoc value unidata-normative-category-alist)
516 "Normative Category")
517 ((rassoc value unidata-informative-category-alist)
518 "Informative Category")
522 (setq attributes (delq 'general-category attributes))
524 (when (and (memq 'bidi-category attributes)
525 (setq value (get-char-attribute char 'bidi-category)))
526 (insert (format "(bidi-category\t. %S)%s"
529 (setq attributes (delq 'bidi-category attributes))
531 (unless (or (not (memq 'mirrored attributes))
532 (eq (setq value (get-char-attribute char 'mirrored 'empty))
534 (insert (format "(mirrored\t\t. %S)%s"
537 (setq attributes (delq 'mirrored attributes))
540 ((and (memq 'decimal-digit-value attributes)
541 (setq value (get-char-attribute char 'decimal-digit-value)))
542 (insert (format "(decimal-digit-value . %S)%s"
545 (setq attributes (delq 'decimal-digit-value attributes))
546 (when (and (memq 'digit-value attributes)
547 (setq value (get-char-attribute char 'digit-value)))
548 (insert (format "(digit-value\t . %S)%s"
551 (setq attributes (delq 'digit-value attributes))
553 (when (and (memq 'numeric-value attributes)
554 (setq value (get-char-attribute char 'numeric-value)))
555 (insert (format "(numeric-value\t . %S)%s"
558 (setq attributes (delq 'numeric-value attributes))
562 (when (and (memq 'digit-value attributes)
563 (setq value (get-char-attribute char 'digit-value)))
564 (insert (format "(digit-value\t. %S)%s"
567 (setq attributes (delq 'digit-value attributes))
569 (when (and (memq 'numeric-value attributes)
570 (setq value (get-char-attribute char 'numeric-value)))
571 (insert (format "(numeric-value\t. %S)%s"
574 (setq attributes (delq 'numeric-value attributes))
576 (when (and (memq 'iso-10646-comment attributes)
577 (setq value (get-char-attribute char 'iso-10646-comment)))
578 (insert (format "(iso-10646-comment\t. %S)%s"
581 (setq attributes (delq 'iso-10646-comment attributes))
583 (when (and (memq 'morohashi-daikanwa attributes)
584 (setq value (get-char-attribute char 'morohashi-daikanwa)))
585 (insert (format "(morohashi-daikanwa\t%s)%s"
586 (mapconcat (function prin1-to-string) value " ")
588 (setq attributes (delq 'morohashi-daikanwa attributes))
590 ;; (when (and (memq 'hanyu-dazidian attributes)
591 ;; (setq value (get-char-attribute char 'hanyu-dazidian)))
592 ;; (insert (format "(hanyu-dazidian %s)%s"
593 ;; (mapconcat #'number-to-string value " ")
595 ;; (setq attributes (delq 'hanyu-dazidian attributes))
599 (when (and (memq 'ideographic-radical attributes)
600 (setq value (get-char-attribute char 'ideographic-radical)))
602 (insert (format "(ideographic-radical . %S)\t; %c%s"
604 (aref ideographic-radicals radical)
606 (setq attributes (delq 'ideographic-radical attributes))
608 (when (and (memq 'ideographic-strokes attributes)
609 (setq value (get-char-attribute char 'ideographic-strokes)))
611 (insert (format "(ideographic-strokes . %S)%s"
614 (setq attributes (delq 'ideographic-strokes attributes))
616 (when (and (memq 'kangxi-radical attributes)
617 (setq value (get-char-attribute char 'kangxi-radical)))
618 (unless (eq value radical)
619 (insert (format "(kangxi-radical\t . %S)\t; %c%s"
621 (aref ideographic-radicals value)
624 (setq radical value)))
625 (setq attributes (delq 'kangxi-radical attributes))
627 (when (and (memq 'kangxi-strokes attributes)
628 (setq value (get-char-attribute char 'kangxi-strokes)))
629 (unless (eq value strokes)
630 (insert (format "(kangxi-strokes\t . %S)%s"
634 (setq strokes value)))
635 (setq attributes (delq 'kangxi-strokes attributes))
637 (when (and (memq 'japanese-radical attributes)
638 (setq value (get-char-attribute char 'japanese-radical)))
639 (unless (eq value radical)
640 (insert (format "(japanese-radical\t . %S)\t; %c%s"
642 (aref ideographic-radicals value)
645 (setq radical value)))
646 (setq attributes (delq 'japanese-radical attributes))
648 (when (and (memq 'japanese-strokes attributes)
649 (setq value (get-char-attribute char 'japanese-strokes)))
650 (unless (eq value strokes)
651 (insert (format "(japanese-strokes\t . %S)%s"
655 (setq strokes value)))
656 (setq attributes (delq 'japanese-strokes attributes))
658 (when (and (memq 'cns-radical attributes)
659 (setq value (get-char-attribute char 'cns-radical)))
660 (insert (format "(cns-radical\t . %S)\t; %c%s"
662 (aref ideographic-radicals value)
664 (setq attributes (delq 'cns-radical attributes))
666 (when (and (memq 'cns-strokes attributes)
667 (setq value (get-char-attribute char 'cns-strokes)))
668 (unless (eq value strokes)
669 (insert (format "(cns-strokes\t . %S)%s"
673 (setq strokes value)))
674 (setq attributes (delq 'cns-strokes attributes))
676 (when (and (memq 'shinjigen-1-radical attributes)
677 (setq value (get-char-attribute char 'shinjigen-1-radical)))
678 (unless (eq value radical)
679 (insert (format "(shinjigen-1-radical . %S)\t; %c%s"
681 (aref ideographic-radicals value)
684 (setq radical value)))
685 (setq attributes (delq 'shinjigen-1-radical attributes))
687 (when (and (memq 'ideographic- attributes)
688 (setq value (get-char-attribute char 'ideographic-)))
689 (insert "(ideographic- ")
690 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
693 (setq cell (car value))
695 (setq cell (decode-char 'ucs cell)))
696 (cond ((characterp cell)
700 (insert (format "%S" cell))
701 (char-db-insert-char-spec cell readable))
702 (setq separator lbs))
706 (if (consp (car cell))
707 (char-db-insert-char-spec cell readable)
708 (char-db-insert-char-reference cell readable))
709 (setq separator lbs))
713 (insert (prin1-to-string cell))
714 (setq separator " ")))
715 (setq value (cdr value)))
717 (insert line-breaking)
718 (setq attributes (delq 'ideographic- attributes)))
719 (when (and (memq 'total-strokes attributes)
720 (setq value (get-char-attribute char 'total-strokes)))
721 (insert (format "(total-strokes . %S)%s"
724 (setq attributes (delq 'total-strokes attributes))
726 (when (and (memq '->ideograph attributes)
727 (setq value (get-char-attribute char '->ideograph)))
728 (insert (format "(->ideograph\t%s)%s"
729 (mapconcat (lambda (code)
730 (cond ((symbolp code)
733 (format "#x%04X" code))
736 line-breaking code))))
739 (setq attributes (delq '->ideograph attributes))
741 (when (and (memq '->decomposition attributes)
742 (setq value (get-char-attribute char '->decomposition)))
743 (insert (format "(->decomposition\t%s)%s"
744 (mapconcat (lambda (code)
745 (cond ((symbolp code)
754 (format "#x%04X" code))
756 (format "%s%S" line-breaking code))))
759 (setq attributes (delq '->decomposition attributes))
761 (if (equal (get-char-attribute char '->titlecase)
762 (get-char-attribute char '->uppercase))
763 (setq attributes (delq '->titlecase attributes)))
764 (when (and (memq '->mojikyo attributes)
765 (setq value (get-char-attribute char '->mojikyo)))
766 (insert (format "(->mojikyo\t\t. %06d)\t; %c%s"
767 value (decode-char 'mojikyo value)
769 (setq attributes (delq '->mojikyo attributes))
771 (when (and (memq 'hanyu-dazidian-vol attributes)
772 (setq value (get-char-attribute char 'hanyu-dazidian-vol)))
773 (insert (format "(hanyu-dazidian-vol . %d)%s"
774 value line-breaking))
775 (setq attributes (delq 'hanyu-dazidian-vol attributes))
777 (when (and (memq 'hanyu-dazidian-page attributes)
778 (setq value (get-char-attribute char 'hanyu-dazidian-page)))
779 (insert (format "(hanyu-dazidian-page . %d)%s"
780 value line-breaking))
781 (setq attributes (delq 'hanyu-dazidian-page attributes))
783 (when (and (memq 'hanyu-dazidian-char attributes)
784 (setq value (get-char-attribute char 'hanyu-dazidian-char)))
785 (insert (format "(hanyu-dazidian-char . %d)%s"
786 value line-breaking))
787 (setq attributes (delq 'hanyu-dazidian-char attributes))
789 (setq rest ccs-attributes)
792 (setq value (get-char-attribute char (car rest)))
794 (if (>= (length (symbol-name (car rest))) 19)
796 (setq has-long-ccs-name t)
800 (setq rest (cdr rest)))
802 (setq name (car attributes))
803 (if (setq value (get-char-attribute char name))
804 (cond ((eq name 'jisx0208-1978/4X)
805 (insert (format "(%-18s . #x%04X)%s"
808 ((or (eq name 'ideographic-structure)
809 (eq name 'ideographic-)
810 (string-match "^\\(->\\|<-\\)" (symbol-name name)))
811 (insert (format "(%-18s%s " name line-breaking))
812 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
815 (setq cell (car value))
817 (setq cell (decode-char 'ucs cell)))
818 (cond ((characterp cell)
822 (insert (format "%S" cell))
823 (char-db-insert-char-spec cell readable))
824 (setq separator lbs))
828 (if (consp (car cell))
829 (char-db-insert-char-spec cell readable)
830 (char-db-insert-char-reference cell readable))
831 (setq separator lbs))
835 (insert (prin1-to-string cell))
836 (setq separator " ")))
837 (setq value (cdr value)))
839 (insert line-breaking))
840 ((memq name '(ideograph=
841 original-ideograph-of
845 simplified-ideograph-of
847 ideographic-different-form-of))
848 (insert (format "(%-18s%s " name line-breaking))
849 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
852 (setq cell (car value))
853 (if (and (consp cell)
858 (char-db-insert-alist cell readable)
859 (setq separator lbs))
862 (insert (prin1-to-string cell))
863 (setq separator " "))
864 (setq value (cdr value)))
866 (insert line-breaking))
867 ;; ((string-match "^->" (symbol-name name))
869 ;; (format "(%-18s %s)%s"
871 ;; (mapconcat (lambda (code)
872 ;; (cond ((symbolp code)
873 ;; (symbol-name code))
875 ;; (format "#x%04X" code))
878 ;; line-breaking code))))
882 (insert (format "(%-18s " name))
883 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
886 (setq cell (car value))
887 (if (and (consp cell)
889 (setq ret (condition-case nil
897 (setq key (car (car rest)))
898 (if (find-charset key)
899 (setq cal (cons key cal))
900 (setq al (cons key al)))
901 (setq rest (cdr rest)))
904 (insert-char-attributes ret
907 (setq separator lbs))
910 (insert (prin1-to-string cell))
911 (setq separator " "))
912 (setq value (cdr value)))
914 (insert line-breaking))
916 (insert (format "(%-18s . %S)%s"
920 (setq attributes (cdr attributes)))
921 (while ccs-attributes
922 (setq name (car ccs-attributes))
923 (if (and (eq name (charset-name name))
924 (setq value (get-char-attribute char name)))
927 (cond ((memq name '(ideograph-daikanwa-2
931 (if has-long-ccs-name
932 "(%-26s . %05d)\t; %c%s"
933 "(%-18s . %05d)\t; %c%s"))
935 (if has-long-ccs-name
936 "(%-26s . %06d)\t; %c%s"
937 "(%-18s . %06d)\t; %c%s"))
939 (if has-long-ccs-name
940 "(%-26s . #x%04X)\t; %c%s"
941 "(%-18s . #x%04X)\t; %c%s"))
943 (if has-long-ccs-name
944 "(%-26s . #x%02X)\t; %c%s"
945 "(%-18s . #x%02X)\t; %c%s")))
947 (if (= (charset-iso-graphic-plane name) 1)
949 (cond ((= (charset-dimension name) 1)
951 ((= (charset-dimension name) 2)
953 ((= (charset-dimension name) 3)
957 (char-db-decode-isolated-char name value)
959 (setq ccs-attributes (cdr ccs-attributes)))
962 (defun insert-char-data (char &optional readable
963 attributes ccs-attributes)
965 (narrow-to-region (point)(point))
966 (insert "(define-char
968 (insert-char-attributes char readable
969 attributes ccs-attributes)
971 (goto-char (point-min))
972 (while (re-search-forward "[ \t]+$" nil t)
974 (goto-char (point-max))
975 (tabify (point-min)(point-max))
979 (defun char-db-update-comment ()
982 (goto-char (point-min))
983 (let (cdef table char)
984 (while (re-search-forward "^[ \t]*\\(([^.()]+)\\)" nil t)
985 (goto-char (match-beginning 1))
986 (setq cdef (read (current-buffer)))
987 (when (find-charset (car cdef))
988 (goto-char (match-end 0))
991 (not (eq (car cdef) 'ideograph-daikanwa))
992 (or (memq (car cdef) '(ascii latin-viscii-upper
996 japanese-jisx0213-2))
997 (= (char-int (charset-iso-final-char (car cdef)))
999 (apply (function make-char) cdef)
1000 (if (setq table (charset-mapping-table (car cdef)))
1001 (set-charset-mapping-table (car cdef) nil))
1003 (apply (function make-char) cdef)
1005 (set-charset-mapping-table (car cdef) table)))))
1006 (when (not (or (< (char-int char) 32)
1007 (and (<= 128 (char-int char))
1008 (< (char-int char) 160))))
1009 (delete-region (point) (point-at-eol))
1010 (insert (format "\t; %c" char)))
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 (get-char-attribute char 'ucs)
1042 (insert-char-data-with-variant char nil 'no-ucs-variant
1043 script excluded-script))
1044 (setq code (1+ code))
1047 (defun write-char-range-data-to-file (min max file
1048 &optional script excluded-script)
1049 (let ((coding-system-for-write 'utf-8))
1051 (insert-char-range-data min max script excluded-script)
1052 (write-region (point-min)(point-max) file))))
1054 (defvar what-character-original-window-configuration)
1057 (defun what-char-definition (char)
1058 (interactive (list (char-after)))
1059 (let ((buf (get-buffer-create "*Character Description*"))
1060 (the-buf (current-buffer))
1061 (win-conf (current-window-configuration)))
1063 (make-local-variable 'what-character-original-window-configuration)
1064 (setq what-character-original-window-configuration win-conf)
1065 (setq buffer-read-only nil)
1069 (insert-char-data-with-variant char 'printable)
1070 (unless (char-attribute-alist char)
1071 (insert (format ";; = %c\n"
1072 (let* ((rest (split-char char))
1076 (setq code (logior (lsh code 8)
1078 (decode-char ccs code)))))
1079 ;; (char-db-update-comment)
1080 (set-buffer-modified-p nil)
1081 (view-mode the-buf (lambda (buf)
1082 (set-window-configuration
1083 what-character-original-window-configuration)
1085 (goto-char (point-min)))
1087 (set-window-configuration
1088 what-character-original-window-configuration)
1089 (signal (car err) (cdr err)))))))
1091 (provide 'char-db-util)
1093 ;;; char-db-util.el ends here