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)
76 (defun char-attribute-name< (ka kb)
82 ((= (charset-dimension ka)
83 (charset-dimension kb))
84 (cond ((= (charset-chars ka)(charset-chars kb))
85 (if (charset-iso-final-char ka)
87 ((>= (charset-iso-final-char ka) ?@)
88 (if (and (charset-iso-final-char kb)
89 (>= (charset-iso-final-char kb) ?@))
90 (< (charset-iso-final-char ka)
91 (charset-iso-final-char kb))
94 (if (charset-iso-final-char kb)
95 (if (>= (charset-iso-final-char kb) ?@)
97 (< (charset-iso-final-char ka)
98 (charset-iso-final-char kb)))
100 (if (charset-iso-final-char kb)
102 (< (charset-id ka)(charset-id kb)))))
103 ((<= (charset-chars ka)(charset-chars kb)))))
105 (< (charset-dimension ka)
106 (charset-dimension kb))
116 (string< (symbol-name ka)
122 (defvar char-db-coded-charset-priority-list
123 (let ((rest default-coded-charset-priority-list)
126 (when (symbolp (car rest))
127 (cond ((memq (car rest)
136 ((string-match "^chinese-big5" (symbol-name (car rest))))
137 ((string-match "^ideograph-gt-pj-" (symbol-name (car rest)))
138 (unless (memq 'ideograph-gt dest)
139 (setq dest (cons 'ideograph-gt dest))))
141 (setq dest (cons (car rest) dest)))))
142 (setq rest (cdr rest)))
143 (append (sort dest #'char-attribute-name<)
144 '(chinese-big5-cdp chinese-big5-eten chinese-big5))))
146 (defun char-db-make-char-spec (char)
148 (cond ((characterp char)
149 (cond ((and (setq ret (get-char-attribute char 'ucs))
150 (not (and (<= #xE000 ret)(<= ret #xF8FF))))
151 (setq char-spec (list (cons 'ucs ret)))
152 (if (setq ret (get-char-attribute char 'name))
153 (setq char-spec (cons (cons 'name ret) char-spec)))
156 (let ((default-coded-charset-priority-list
157 char-db-coded-charset-priority-list))
159 (setq char-spec (list ret))
160 (dolist (ccs (delq (car ret) (charset-list)))
161 (if (or (and (charset-iso-final-char ccs)
162 (setq ret (get-char-attribute char ccs)))
163 (eq ccs 'ideograph-daikanwa))
164 (setq char-spec (cons (cons ccs ret) char-spec))))
166 (setq char-spec (split-char char)))
167 (if (setq ret (get-char-attribute char 'name))
168 (setq char-spec (cons (cons 'name ret) char-spec)))
174 (defun char-db-insert-char-spec (char &optional readable column)
176 (setq column (current-column)))
177 (let (char-spec ret al cal key temp-char)
178 (setq char-spec (char-db-make-char-spec char))
179 ;; (cond ((characterp char)
180 ;; (cond ((and (setq ret (get-char-attribute char 'ucs))
181 ;; (not (and (<= #xE000 ret)(<= ret #xF8FF))))
182 ;; (setq char-spec (list (cons 'ucs ret)))
183 ;; (if (setq ret (get-char-attribute char 'name))
184 ;; (setq char-spec (cons (cons 'name ret) char-spec)))
187 ;; (let ((default-coded-charset-priority-list
188 ;; char-db-coded-charset-priority-list))
189 ;; (split-char char)))
190 ;; (setq char-spec (list ret))
191 ;; (dolist (ccs (delq (car ret) (charset-list)))
192 ;; (if (or (and (charset-iso-final-char ccs)
193 ;; (setq ret (get-char-attribute char ccs)))
194 ;; (eq ccs 'ideograph-daikanwa))
195 ;; (setq char-spec (cons (cons ccs ret) char-spec))))
196 ;; (if (null char-spec)
197 ;; (setq char-spec (split-char char)))
198 ;; (if (setq ret (get-char-attribute char 'name))
199 ;; (setq char-spec (cons (cons 'name ret) char-spec)))
202 ;; (setq char-spec char)
204 (unless (or (characterp char) ; char
206 (setq char (find-char char-spec))
208 ;; define temporary character
209 ;; Current implementation is dirty.
210 (setq temp-char (define-char (cons '(ideograph-daikanwa . 0)
212 (remove-char-attribute temp-char 'ideograph-daikanwa)
213 (setq char temp-char))
217 (setq key (car (car char-spec)))
218 (unless (memq key char-db-ignored-attributes)
219 (if (find-charset key)
220 (if (get-char-attribute char key)
221 (setq cal (cons key cal)))
222 (setq al (cons key al))))
223 (setq char-spec (cdr char-spec)))
225 (setq char-spec (char-db-make-char-spec char))
227 (setq key (car (car char-spec)))
228 (unless (memq key char-db-ignored-attributes)
229 (if (find-charset key)
230 (setq cal (cons key cal))
231 (setq al (cons key al))))
232 (setq char-spec (cdr char-spec)))
235 (memq 'ideographic-structure al))
236 (push 'ideographic-structure al))
237 (insert-char-attributes char
241 ;; undefine temporary character
242 ;; Current implementation is dirty.
243 (setq char-spec (char-attribute-alist temp-char))
245 (remove-char-attribute temp-char (car (car char-spec)))
246 (setq char-spec (cdr char-spec))))))
248 (defun char-db-insert-alist (alist &optional readable column)
250 (setq column (current-column)))
252 (concat "\n" (make-string (1+ column) ?\ )))
255 lbs cell rest separator)
258 (setq name (car (car alist))
259 value (cdr (car alist)))
260 (cond ((eq name 'char)
262 (if (setq ret (condition-case nil
269 (setq key (car (car value)))
270 (if (find-charset key)
271 (setq cal (cons key cal))
272 (setq al (cons key al)))
273 (setq value (cdr value)))
274 (insert-char-attributes ret
277 (insert (prin1-to-string value)))
279 (insert line-breaking))
281 (insert (format "(%-18s " name))
282 (setq lbs (concat "\n" (make-string (current-column) ?\ )))
284 (setq cell (car value))
285 (if (and (consp cell)
287 (setq ret (condition-case nil
296 (setq key (car (car rest)))
297 (if (find-charset key)
298 (setq cal (cons key cal))
299 (setq al (cons key al)))
300 (setq rest (cdr rest)))
303 (insert-char-attributes ret
306 (setq separator lbs))
309 (insert (prin1-to-string cell))
310 (setq separator " "))
311 (setq value (cdr value)))
313 (insert line-breaking))
315 (insert (format "(%-18s . %S)%s"
318 (setq alist (cdr alist))))
321 (defun char-db-insert-char-reference (plist &optional readable column)
323 (setq column (current-column)))
325 (concat "\n" (make-string (1+ column) ?\ )))
330 (setq name (pop plist))
331 (setq value (pop plist))
332 (cond ((eq name :char)
335 (cond ((numberp value)
336 (setq value (decode-char 'ucs value)))
338 ;; (setq value (or (find-char value)
341 (char-db-insert-char-spec value readable)
342 (insert line-breaking)
345 (insert (format "%s%s\t%d ; %c%s"
348 (aref ideographic-radicals value)
352 (insert (format "%s%s\t%S" separator name value))
353 (setq separator line-breaking)))
357 (defun char-db-decode-isolated-char (ccs code-point)
360 (cond ((eq ccs 'arabic-iso8859-6)
361 (decode-char ccs code-point))
362 ((and (memq ccs '(ideograph-gt-pj-1
373 (setq ret (decode-char ccs code-point))
374 (setq ret (get-char-attribute ret 'ideograph-gt)))
375 (decode-builtin-char 'ideograph-gt ret))
377 (decode-builtin-char ccs code-point))))
378 (cond ((and (<= 0 (char-int ret))
379 (<= (char-int ret) #x1F))
380 (decode-char 'ucs (+ #x2400 (char-int ret))))
381 ((= (char-int ret) #x7F)
385 (defvar char-db-convert-obsolete-format t)
387 (defun insert-char-attributes (char &optional readable
388 attributes ccs-attributes
393 (if (consp attributes)
395 (dolist (name attributes)
396 (unless (memq name char-db-ignored-attributes)
399 (dolist (name (char-attribute-list))
400 (unless (memq name char-db-ignored-attributes)
401 (if (find-charset name)
405 #'char-attribute-name<))
407 (sort (if ccs-attributes
410 (dolist (name ccs-attributes)
411 (unless (memq name char-db-ignored-attributes)
416 (dolist (name (charset-list))
417 (unless (memq name char-db-ignored-attributes)
420 #'char-attribute-name<)))
422 (setq column (current-column)))
423 (let (name value has-long-ccs-name rest
426 (concat "\n" (make-string (1+ column) ?\ )))
427 lbs cell separator ret
430 (when (and (memq 'name attributes)
431 (setq value (get-char-attribute char 'name)))
433 (if (> (+ (current-column) (length value)) 48)
436 value line-breaking))
437 (setq attributes (delq 'name attributes))
439 (when (and (memq 'script attributes)
440 (setq value (get-char-attribute char 'script)))
441 (insert (format "(script\t\t%s)%s"
442 (mapconcat (function prin1-to-string)
445 (setq attributes (delq 'script attributes))
447 (when (and (memq '=>ucs attributes)
448 (setq value (get-char-attribute char '=>ucs)))
449 (insert (format "(=>ucs\t\t. #x%04X)\t; %c%s"
450 value (decode-char 'ucs value)
452 (setq attributes (delq '=>ucs attributes))
454 (when (and (memq '=>ucs* attributes)
455 (setq value (get-char-attribute char '=>ucs*)))
456 (insert (format "(=>ucs*\t\t. #x%04X)\t; %c%s"
457 value (decode-char 'ucs value)
459 (setq attributes (delq '=>ucs* attributes))
461 (when (and (memq '=>ucs-jis attributes)
462 (setq value (get-char-attribute char '=>ucs-jis)))
463 (insert (format "(=>ucs-jis\t\t. #x%04X)\t; %c%s"
464 value (decode-char 'ucs-jis value)
466 (setq attributes (delq '=>ucs-jis attributes))
468 (when (and (memq '=>ucs-cns attributes)
469 (setq value (get-char-attribute char '=>ucs-cns)))
470 (insert (format "(=>ucs-cns\t\t. #x%04X)\t; %c%s"
471 value (decode-char 'ucs-cns value)
473 (setq attributes (delq '=>ucs-cns attributes))
475 (when (and (memq '->ucs attributes)
476 (setq value (get-char-attribute char '->ucs)))
477 (insert (format (if char-db-convert-obsolete-format
478 "(=>ucs\t\t. #x%04X)\t; %c%s"
479 "(->ucs\t\t. #x%04X)\t; %c%s")
480 value (decode-char 'ucs value)
482 (setq attributes (delq '->ucs attributes))
484 (when (and (memq 'general-category attributes)
485 (setq value (get-char-attribute char 'general-category)))
487 "(general-category\t%s) ; %s%s"
488 (mapconcat (lambda (cell)
491 (cond ((rassoc value unidata-normative-category-alist)
492 "Normative Category")
493 ((rassoc value unidata-informative-category-alist)
494 "Informative Category")
498 (setq attributes (delq 'general-category attributes))
500 (when (and (memq 'bidi-category attributes)
501 (setq value (get-char-attribute char 'bidi-category)))
502 (insert (format "(bidi-category\t. %S)%s"
505 (setq attributes (delq 'bidi-category attributes))
507 (unless (or (not (memq 'mirrored attributes))
508 (eq (setq value (get-char-attribute char 'mirrored 'empty))
510 (insert (format "(mirrored\t\t. %S)%s"
513 (setq attributes (delq 'mirrored attributes))
516 ((and (memq 'decimal-digit-value attributes)
517 (setq value (get-char-attribute char 'decimal-digit-value)))
518 (insert (format "(decimal-digit-value . %S)%s"
521 (setq attributes (delq 'decimal-digit-value attributes))
522 (when (and (memq 'digit-value attributes)
523 (setq value (get-char-attribute char 'digit-value)))
524 (insert (format "(digit-value\t . %S)%s"
527 (setq attributes (delq 'digit-value attributes))
529 (when (and (memq 'numeric-value attributes)
530 (setq value (get-char-attribute char 'numeric-value)))
531 (insert (format "(numeric-value\t . %S)%s"
534 (setq attributes (delq 'numeric-value attributes))
538 (when (and (memq 'digit-value attributes)
539 (setq value (get-char-attribute char 'digit-value)))
540 (insert (format "(digit-value\t. %S)%s"
543 (setq attributes (delq 'digit-value attributes))
545 (when (and (memq 'numeric-value attributes)
546 (setq value (get-char-attribute char 'numeric-value)))
547 (insert (format "(numeric-value\t. %S)%s"
550 (setq attributes (delq 'numeric-value attributes))
552 (when (and (memq 'iso-10646-comment attributes)
553 (setq value (get-char-attribute char 'iso-10646-comment)))
554 (insert (format "(iso-10646-comment\t. %S)%s"
557 (setq attributes (delq 'iso-10646-comment attributes))
559 (when (and (memq 'morohashi-daikanwa attributes)
560 (setq value (get-char-attribute char 'morohashi-daikanwa)))
561 (insert (format "(morohashi-daikanwa\t%s)%s"
562 (mapconcat (function prin1-to-string) value " ")
564 (setq attributes (delq 'morohashi-daikanwa attributes))
568 (when (and (memq 'ideographic-radical attributes)
569 (setq value (get-char-attribute char 'ideographic-radical)))
571 (insert (format "(ideographic-radical . %S)\t; %c%s"
573 (aref ideographic-radicals radical)
575 (setq attributes (delq 'ideographic-radical attributes))
577 (when (and (memq 'ideographic-strokes attributes)
578 (setq value (get-char-attribute char 'ideographic-strokes)))
580 (insert (format "(ideographic-strokes . %S)%s"
583 (setq attributes (delq 'ideographic-strokes attributes))
585 (when (and (memq 'kangxi-radical attributes)
586 (setq value (get-char-attribute char 'kangxi-radical)))
587 (unless (eq value radical)
588 (insert (format "(kangxi-radical\t . %S)\t; %c%s"
590 (aref ideographic-radicals value)
593 (setq radical value)))
594 (setq attributes (delq 'kangxi-radical attributes))
596 (when (and (memq 'kangxi-strokes attributes)
597 (setq value (get-char-attribute char 'kangxi-strokes)))
598 (unless (eq value strokes)
599 (insert (format "(kangxi-strokes\t . %S)%s"
603 (setq strokes value)))
604 (setq attributes (delq 'kangxi-strokes attributes))
606 (when (and (memq 'japanese-radical attributes)
607 (setq value (get-char-attribute char 'japanese-radical)))
608 (unless (eq value radical)
609 (insert (format "(japanese-radical\t . %S)\t; %c%s"
611 (aref ideographic-radicals value)
614 (setq radical value)))
615 (setq attributes (delq 'japanese-radical attributes))
617 (when (and (memq 'japanese-strokes attributes)
618 (setq value (get-char-attribute char 'japanese-strokes)))
619 (unless (eq value strokes)
620 (insert (format "(japanese-strokes\t . %S)%s"
624 (setq strokes value)))
625 (setq attributes (delq 'japanese-strokes attributes))
627 (when (and (memq 'cns-radical attributes)
628 (setq value (get-char-attribute char 'cns-radical)))
629 (insert (format "(cns-radical\t . %S)\t; %c%s"
631 (aref ideographic-radicals value)
633 (setq attributes (delq 'cns-radical attributes))
635 (when (and (memq 'cns-strokes attributes)
636 (setq value (get-char-attribute char 'cns-strokes)))
637 (unless (eq value strokes)
638 (insert (format "(cns-strokes\t . %S)%s"
642 (setq strokes value)))
643 (setq attributes (delq 'cns-strokes attributes))
645 (when (and (memq 'shinjigen-1-radical attributes)
646 (setq value (get-char-attribute char 'shinjigen-1-radical)))
647 (unless (eq value radical)
648 (insert (format "(shinjigen-1-radical . %S)\t; %c%s"
650 (aref ideographic-radicals value)
653 (setq radical value)))
654 (setq attributes (delq 'shinjigen-1-radical attributes))
656 (when (and (memq 'ideographic- attributes)
657 (setq value (get-char-attribute char 'ideographic-)))
658 (insert "(ideographic- ")
659 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
662 (setq cell (car value))
664 (setq cell (decode-char 'ucs cell)))
665 (cond ((characterp cell)
669 (insert (format "%S" cell))
670 (char-db-insert-char-spec cell readable))
671 (setq separator lbs))
675 (if (consp (car cell))
676 (char-db-insert-char-spec cell readable)
677 (char-db-insert-char-reference cell readable))
678 (setq separator lbs))
682 (insert (prin1-to-string cell))
683 (setq separator " ")))
684 (setq value (cdr value)))
686 (insert line-breaking)
687 (setq attributes (delq 'ideographic- attributes)))
688 (when (and (memq 'total-strokes attributes)
689 (setq value (get-char-attribute char 'total-strokes)))
690 (insert (format "(total-strokes . %S)%s"
693 (setq attributes (delq 'total-strokes attributes))
695 (when (and (memq '->ideograph attributes)
696 (setq value (get-char-attribute char '->ideograph)))
697 (insert (format "(->ideograph\t%s)%s"
698 (mapconcat (lambda (code)
699 (cond ((symbolp code)
702 (format "#x%04X" code))
705 line-breaking code))))
708 (setq attributes (delq '->ideograph attributes))
710 (when (and (memq '->decomposition attributes)
711 (setq value (get-char-attribute char '->decomposition)))
712 (insert (format "(->decomposition\t%s)%s"
713 (mapconcat (lambda (code)
714 (cond ((symbolp code)
723 (format "#x%04X" code))
725 (format "%s%S" line-breaking code))))
728 (setq attributes (delq '->decomposition attributes))
730 (if (equal (get-char-attribute char '->titlecase)
731 (get-char-attribute char '->uppercase))
732 (setq attributes (delq '->titlecase attributes)))
733 (when (and (memq '->mojikyo attributes)
734 (setq value (get-char-attribute char '->mojikyo)))
735 (insert (format "(->mojikyo\t\t. %06d)\t; %c%s"
736 value (decode-char 'mojikyo value)
738 (setq attributes (delq '->mojikyo attributes))
740 (when (and (memq 'hanyu-dazidian-vol attributes)
741 (setq value (get-char-attribute char 'hanyu-dazidian-vol)))
742 (insert (format "(hanyu-dazidian-vol . %d)%s"
743 value line-breaking))
744 (setq attributes (delq 'hanyu-dazidian-vol attributes))
746 (when (and (memq 'hanyu-dazidian-page attributes)
747 (setq value (get-char-attribute char 'hanyu-dazidian-page)))
748 (insert (format "(hanyu-dazidian-page . %d)%s"
749 value line-breaking))
750 (setq attributes (delq 'hanyu-dazidian-page attributes))
752 (when (and (memq 'hanyu-dazidian-char attributes)
753 (setq value (get-char-attribute char 'hanyu-dazidian-char)))
754 (insert (format "(hanyu-dazidian-char . %d)%s"
755 value line-breaking))
756 (setq attributes (delq 'hanyu-dazidian-char attributes))
759 (when (memq '->ucs-variants attributes)
760 (setq attributes (delq '->ucs-variants attributes))
762 (when (memq 'composition attributes)
763 (setq attributes (delq 'composition attributes))
765 (setq rest ccs-attributes)
768 (setq value (get-char-attribute char (car rest)))
770 (if (>= (length (symbol-name (car rest))) 19)
772 (setq has-long-ccs-name t)
776 (setq rest (cdr rest)))
778 (setq name (car attributes))
779 (if (setq value (get-char-attribute char name))
780 (cond ((eq name 'jisx0208-1978/4X)
781 (insert (format "(%-18s . #x%04X)%s"
784 ((or (eq name 'ideographic-structure)
785 (eq name 'ideographic-)
786 (string-match "^\\(->\\|<-\\)" (symbol-name name)))
787 (insert (format "(%-18s%s " name line-breaking))
788 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
791 (setq cell (car value))
793 (setq cell (decode-char 'ucs cell)))
794 (cond ((characterp cell)
798 (insert (format "%S" cell))
799 (char-db-insert-char-spec cell readable))
800 (setq separator lbs))
804 (if (consp (car cell))
805 (char-db-insert-char-spec cell readable)
806 (char-db-insert-char-reference cell readable))
807 (setq separator lbs))
811 (insert (prin1-to-string cell))
812 (setq separator " ")))
813 (setq value (cdr value)))
815 (insert line-breaking))
816 ((memq name '(ideograph=
817 original-ideograph-of
821 simplified-ideograph-of
823 ideographic-different-form-of))
824 (insert (format "(%-18s%s " name line-breaking))
825 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
828 (setq cell (car value))
829 (if (and (consp cell)
834 (char-db-insert-alist cell readable)
835 (setq separator lbs))
838 (insert (prin1-to-string cell))
839 (setq separator " "))
840 (setq value (cdr value)))
842 (insert line-breaking))
843 ;; ((string-match "^->" (symbol-name name))
845 ;; (format "(%-18s %s)%s"
847 ;; (mapconcat (lambda (code)
848 ;; (cond ((symbolp code)
849 ;; (symbol-name code))
851 ;; (format "#x%04X" code))
854 ;; line-breaking code))))
858 (insert (format "(%-18s " name))
859 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
862 (setq cell (car value))
863 (if (and (consp cell)
865 (setq ret (condition-case nil
873 (setq key (car (car rest)))
874 (if (find-charset key)
875 (setq cal (cons key cal))
876 (setq al (cons key al)))
877 (setq rest (cdr rest)))
880 (insert-char-attributes ret
883 (setq separator lbs))
886 (insert (prin1-to-string cell))
887 (setq separator " "))
888 (setq value (cdr value)))
890 (insert line-breaking))
892 (insert (format "(%-18s . %S)%s"
896 (setq attributes (cdr attributes)))
897 (while ccs-attributes
898 (setq name (car ccs-attributes))
899 (if (and (eq name (charset-name name))
900 (setq value (get-char-attribute char name)))
903 (cond ((memq name '(ideograph-daikanwa-2
907 (if has-long-ccs-name
908 "(%-26s . %05d)\t; %c%s"
909 "(%-18s . %05d)\t; %c%s"))
911 (if has-long-ccs-name
912 "(%-26s . %06d)\t; %c%s"
913 "(%-18s . %06d)\t; %c%s"))
915 (if has-long-ccs-name
916 "(%-26s . #x%04X)\t; %c%s"
917 "(%-18s . #x%04X)\t; %c%s"))
919 (if has-long-ccs-name
920 "(%-26s . #x%02X)\t; %c%s"
921 "(%-18s . #x%02X)\t; %c%s")))
923 (if (= (charset-iso-graphic-plane name) 1)
925 (cond ((= (charset-dimension name) 1)
927 ((= (charset-dimension name) 2)
929 ((= (charset-dimension name) 3)
933 (char-db-decode-isolated-char name value)
935 (setq ccs-attributes (cdr ccs-attributes)))
938 (defun insert-char-data (char &optional readable
939 attributes ccs-attributes)
941 (narrow-to-region (point)(point))
942 (insert "(define-char
944 (insert-char-attributes char readable
945 attributes ccs-attributes)
947 (goto-char (point-min))
948 (while (re-search-forward "[ \t]+$" nil t)
950 (goto-char (point-max))
951 (tabify (point-min)(point-max))
954 (defun insert-char-data-with-variant (char &optional printable
956 script excluded-script)
957 (insert-char-data char printable)
958 (let ((variants (or (char-variants char)
959 (let ((ucs (get-char-attribute char '->ucs)))
961 (delete char (char-variants (int-char ucs)))))))
963 (setq variants (sort variants #'<))
965 (setq variant (car variants))
966 (if (and (or (null script)
967 (null (setq vs (get-char-attribute variant 'script)))
969 (or (null excluded-script)
970 (null (setq vs (get-char-attribute variant 'script)))
971 (not (memq excluded-script vs))))
972 (or (and no-ucs-variant (get-char-attribute variant 'ucs))
973 (insert-char-data variant printable)))
974 (setq variants (cdr variants))
977 (defun insert-char-range-data (min max &optional script excluded-script)
981 (setq char (decode-char 'ucs code))
982 (if (get-char-attribute char 'ucs)
983 (insert-char-data-with-variant char nil 'no-ucs-variant
984 script excluded-script))
985 (setq code (1+ code))
988 (defun write-char-range-data-to-file (min max file
989 &optional script excluded-script)
990 (let ((coding-system-for-write 'utf-8))
992 (insert-char-range-data min max script excluded-script)
993 (write-region (point-min)(point-max) file))))
995 (defvar what-character-original-window-configuration)
998 (defun what-char-definition (char)
999 (interactive (list (char-after)))
1000 (let ((buf (get-buffer-create "*Character Description*"))
1001 (the-buf (current-buffer))
1002 (win-conf (current-window-configuration)))
1004 (make-local-variable 'what-character-original-window-configuration)
1005 (setq what-character-original-window-configuration win-conf)
1006 (setq buffer-read-only nil)
1010 (insert-char-data-with-variant char 'printable)
1011 (unless (char-attribute-alist char)
1012 (insert (format ";; = %c\n"
1013 (let* ((rest (split-char char))
1017 (setq code (logior (lsh code 8)
1019 (decode-char ccs code)))))
1020 ;; (char-db-update-comment)
1021 (set-buffer-modified-p nil)
1022 (view-mode the-buf (lambda (buf)
1023 (set-window-configuration
1024 what-character-original-window-configuration)
1026 (goto-char (point-min)))
1028 (set-window-configuration
1029 what-character-original-window-configuration)
1030 (signal (car err) (cdr err)))))))
1032 (provide 'char-db-util)
1034 ;;; char-db-util.el ends here