1 ;;; char-db-util.el --- Character Database utility -*- coding: utf-8-er; -*-
3 ;; Copyright (C) 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006,
4 ;; 2007, 2008, 2009, 2010, 2011 MORIOKA Tomohiko.
6 ;; Author: MORIOKA Tomohiko <tomo@kanji.zinbun.kyoto-u.ac.jp>
7 ;; Keywords: CHISE, Character Database, ISO/IEC 10646, UCS, Unicode, MULE.
9 ;; This file is part of XEmacs CHISE.
11 ;; XEmacs CHISE is free software; you can redistribute it and/or
12 ;; modify it under the terms of the GNU General Public License as
13 ;; published by the Free Software Foundation; either version 2, or (at
14 ;; your option) any later version.
16 ;; XEmacs CHISE is distributed in the hope that it will be useful,
17 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
18 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
19 ;; General Public License for more details.
21 ;; You should have received a copy of the GNU General Public License
22 ;; along with XEmacs CHISE; see the file COPYING. If not, write to
23 ;; the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
24 ;; Boston, MA 02111-1307, USA.
29 (require 'ideograph-subr)
31 (defconst unidata-normative-category-alist
32 '(("Lu" letter uppercase)
33 ("Ll" letter lowercase)
34 ("Lt" letter titlecase)
35 ("Mn" mark non-spacing)
36 ("Mc" mark spacing-combining)
38 ("Nd" number decimal-digit)
41 ("Zs" separator space)
43 ("Zp" separator paragraph)
46 ("Cs" other surrogate)
47 ("Co" other private-use)
48 ("Cn" other not-assigned)))
50 (defconst unidata-informative-category-alist
51 '(("Lm" letter modifier)
53 ("Pc" punctuation connector)
54 ("Pd" punctuation dash)
55 ("Ps" punctuation open)
56 ("Pe" punctuation close)
57 ("Pi" punctuation initial-quote)
58 ("Pf" punctuation final-quote)
59 ("Po" punctuation other)
61 ("Sc" symbol currency)
62 ("Sk" symbol modifier)
66 (defconst shuowen-radicals
67 [?一 ?上 ?示 ?三 ?王 ?玉 ?玨 ?气 ?士 ?丨 ; 010
68 ?屮 ?艸 ?蓐 ?茻 ?小 ?八 ?釆 ?半 ?牛 ?犛 ; 020
69 ?告 ?口 ?凵 ?吅 ?哭 ?走 ?止 ?癶 ?步 ?此 ; 030
70 ?正 ?是 ?辵 ?彳 ?廴 ?㢟 ?行 ?齒 ?牙 ?足 ; 040
71 ?疋 ?品 ?龠 ?冊 ?㗊 ?舌 ?干 ?谷 ?只 ?㕯 ; 050
72 ?句 ?丩 ?古 ?十 ?卅 ?言 ?誩 ?音 ?䇂 ?丵 ; 060
73 ?菐 ?𠬞 ?廾 ?共 ?異 ?舁 ?𦥑 ?䢅 ?爨 ?革 ; 070
74 ?鬲 ?䰜 ?爪 ?𠃨 ?鬥 ?又 ?𠂇 ?㕜 ?支 ?𦘒 ; 080
75 ?聿 ?畫 ?隶 ?臤 ?臣 ?殳 ?殺 ?𠘧 ?寸 ?皮 ; 090
76 ?㼱 ?攴 ?敎 ?卜 ?用 ?爻 ?㸚 ?𥄎 ?目 ?䀠 ; 100
77 ?眉 ?盾 ?自 ?白 ?鼻 ?皕 ?習 ?羽 ?隹 ?奞 ; 110
78 ?萑 ?𦫳 ?苜 ?羊 ?羴 ?瞿 ?雔 ?雥 ?鳥 ?烏 ; 120
79 ?𠦒 ?冓 ?幺 ?𢆶 ?叀 ?玄 ?予 ?放 ?𠬪 ?𣦼 ; 130
80 ?歺 ?死 ?冎 ?骨 ?肉 ?筋 ?刀 ?刃 ?㓞 ?丰 ; 140
81 ?耒 ?𧢲 ?竹 ?箕 ?丌 ?左 ?工 ?㠭 ?巫 ?甘 ; 150
82 ?曰 ?乃 ?丂 ?可 ?兮 ?号 ?亏 ?旨 ?喜 ?壴 ; 160
83 ?鼓 ?豈 ?豆 ?豊 ?豐 ?䖒 ?虍 ?虎 ?虤 ?皿 ; 170
84 ?𠙴 ?去 ?血 ?丶 ?丹 ?青 ?井 ?皀 ?鬯 ?食 ; 180
85 ?亼 ?會 ?倉 ?入 ?缶 ?矢 ?高 ?冂 ?𩫏 ?京 ; 190
86 ?亯 ?𣆪 ?畗 ?㐭 ?嗇 ?來 ?麥 ?夊 ?舛 ?䑞 ; 200
87 ?韋 ?弟 ?夂 ?久 ?桀 ?木 ?東 ?林 ?才 ?叒 ; 210
88 ?之 ?帀 ?出 ?𣎵 ?生 ?乇 ?𠂹 ?𠌶 ?華 ?𥝌 ; 220
89 ?稽 ?巢 ?桼 ?束 ?㯻 ?囗 ?員 ?貝 ?邑 ?𨛜 ; 230
90 ?日 ?旦 ?倝 ?㫃 ?冥 ?晶 ?月 ?有 ?明 ?囧 ; 240
91 ?夕 ?多 ?毌 ?𢎘 ?𣐺 ?卣 ?齊 ?朿 ?片 ?鼎 ; 250
92 ?克 ?彔 ?禾 ?秝 ?黍 ?香 ?米 ?毇 ?臼 ?凶 ; 260
93 ?𣎳 ?林 ?麻 ?尗 ?耑 ?韭 ?瓜 ?瓠 ?宀 ?宮 ; 270
94 ?呂 ?穴 ?㝱 ?𤕫 ?冖 ?𠔼 ?冃 ?㒳 ?网 ?襾 ; 280
95 ?巾 ?巿 ?帛 ?白 ?㡀 ?黹 ?人 ?𠤎 ?匕 ?从 ; 290
98 (defun shuowen-radical (number)
99 (aref shuowen-radicals (1- number)))
101 (defvar char-db-file-coding-system 'utf-8-mcs-er)
103 (defvar char-db-ignored-attributes '(ideographic-products))
105 (defvar char-db-coded-charset-priority-list
227 ;;; @ char-db formatters
230 (defun char-db-make-char-spec (char)
232 (cond ((characterp char)
233 (cond ((and (setq ret (encode-char char '=ucs 'defined-only))
234 (not (and (<= #xE000 ret)(<= ret #xF8FF))))
235 (setq char-spec (list (cons '=ucs ret)))
236 (cond ((setq ret (get-char-attribute char 'name))
237 (setq char-spec (cons (cons 'name ret) char-spec))
239 ((setq ret (get-char-attribute char 'name*))
240 (setq char-spec (cons (cons 'name* ret) char-spec))
245 (let ((rest char-db-coded-charset-priority-list)
248 (setq ccs (charset-name
249 (find-charset (car rest))))
251 (encode-char char ccs
253 (throw 'tag (cons ccs ret)))
254 (setq rest (cdr rest))))))
255 (setq char-spec (list ret))
256 (dolist (ccs (delq (car ret) (charset-list)))
257 (if (and (or (charset-iso-final-char ccs)
264 (string-match "=ucs@" (symbol-name ccs)))
265 (setq ccs (charset-name ccs))
266 (null (assq ccs char-spec))
267 (setq ret (encode-char char ccs 'defined-only)))
268 (setq char-spec (cons (cons ccs ret) char-spec))))
270 (setq char-spec (split-char char)))
271 (cond ((setq ret (get-char-attribute char 'name))
272 (setq char-spec (cons (cons 'name ret) char-spec))
274 ((setq ret (get-char-attribute char 'name*))
275 (setq char-spec (cons (cons 'name* ret) char-spec))
278 ((setq ret (get-char-attribute
279 char 'ideographic-combination))
281 (cons (cons 'ideographic-combination ret)
288 (defun char-db-insert-char-spec (char &optional readable column
291 (setq column (current-column)))
292 (let (char-spec temp-char)
293 (setq char-spec (char-db-make-char-spec char))
294 (unless (or (characterp char) ; char
296 (setq char (find-char char-spec))
298 ;; define temporary character
299 ;; Current implementation is dirty.
300 (setq temp-char (define-char (cons '(ideograph-daikanwa . 0)
302 (remove-char-attribute temp-char 'ideograph-daikanwa)
303 (setq char temp-char))
304 (insert-char-attributes char
306 (union (mapcar #'car char-spec)
310 ;; undefine temporary character
311 ;; Current implementation is dirty.
312 (setq char-spec (char-attribute-alist temp-char))
314 (remove-char-attribute temp-char (car (car char-spec)))
315 (setq char-spec (cdr char-spec))))))
317 (defun char-db-insert-alist (alist &optional readable column)
319 (setq column (current-column)))
321 (concat "\n" (make-string (1+ column) ?\ )))
325 lbs cell rest separator)
328 (setq name (car (car alist))
329 value (cdr (car alist)))
330 (cond ((eq name 'char)
332 (if (setq ret (condition-case nil
340 (setq key (car (car value)))
341 ;; (if (find-charset key)
342 ;; (setq cal (cons key cal))
343 (setq al (cons key al))
345 (setq value (cdr value)))
346 (insert-char-attributes ret
350 (insert (prin1-to-string value)))
352 (insert line-breaking))
354 (insert (format "(%-18s " name))
355 (setq lbs (concat "\n" (make-string (current-column) ?\ )))
357 (setq cell (car value))
358 (if (and (consp cell)
360 (setq ret (condition-case nil
370 (setq key (car (car rest)))
371 ;; (if (find-charset key)
372 ;; (setq cal (cons key cal))
373 (setq al (cons key al))
375 (setq rest (cdr rest)))
378 (insert-char-attributes ret
382 (setq separator lbs))
385 (insert (prin1-to-string cell))
386 (setq separator " "))
387 (setq value (cdr value)))
389 (insert line-breaking))
391 (insert (format "(%-18s . %S)%s"
394 (setq alist (cdr alist))))
397 (defun char-db-insert-char-reference (plist &optional readable column)
399 (setq column (current-column)))
401 (concat "\n" (make-string (1+ column) ?\ )))
406 (setq name (pop plist))
407 (setq value (pop plist))
408 (cond ((eq name :char)
411 (cond ((numberp value)
412 (setq value (decode-char '=ucs value)))
414 ;; (setq value (or (find-char value)
417 (char-db-insert-char-spec value readable)
418 (insert line-breaking)
421 (insert (format "%s%s\t%d ; %c%s"
424 (ideographic-radical value)
428 (insert (format "%s%s\t%S" separator name value))
429 (setq separator line-breaking)))
433 (defun char-db-decode-isolated-char (ccs code-point)
436 (cond ((eq ccs 'arabic-iso8859-6)
437 (decode-char ccs code-point))
438 ((and (memq ccs '(=gt-pj-1
449 (setq ret (decode-char ccs code-point))
450 (setq ret (encode-char ret '=gt 'defined-only)))
451 (decode-builtin-char '=gt ret))
453 (decode-builtin-char ccs code-point))))
454 (cond ((and (<= 0 (char-int ret))
455 (<= (char-int ret) #x1F))
456 (decode-char '=ucs (+ #x2400 (char-int ret))))
457 ((= (char-int ret) #x7F)
461 (defvar char-db-convert-obsolete-format t)
463 (defun char-db-insert-ccs-feature (name value line-breaking)
466 (cond ((memq name '(=shinjigen
468 =shinjigen@rev =shinjigen/+p@rev
470 "(%-18s . %04d)\t; %c")
471 ((eq name '=shinjigen@1ed/24pr)
472 "(%-18s . %04d)\t; %c")
473 ((or (memq name '(=daikanwa =>>daikanwa =>daikanwa
474 =daikanwa@rev1 =daikanwa@rev2
475 =daikanwa/+p =daikanwa/+2p
476 =gt =>>>gt =>>gt =>gt
479 =cbeta =zinbun-oracle =>zinbun-oracle))
480 (string-match "^=adobe-" (symbol-name name)))
481 "(%-18s . %05d)\t; %c")
482 ((memq name '(=hanyo-denshi/ks =>>hanyo-denshi/ks mojikyo))
483 "(%-18s . %06d)\t; %c")
484 ((>= (charset-dimension name) 2)
485 "(%-18s . #x%04X)\t; %c")
487 "(%-18s . #x%02X)\t; %c"))
489 (if (= (charset-iso-graphic-plane name) 1)
491 (cond ((= (charset-dimension name) 1)
493 ((= (charset-dimension name) 2)
495 ((= (charset-dimension name) 3)
499 (char-db-decode-isolated-char name value)))
500 (if (and (= (charset-chars name) 94)
501 (= (charset-dimension name) 2))
502 (insert (format " [%02d-%02d]"
503 (- (lsh value -8) 32)
504 (- (logand value 255) 32))))
505 (insert line-breaking))
507 (defun char-db-insert-relation-feature (char name value line-breaking
509 (insert (format "(%-18s%s " name line-breaking))
510 (let ((lbs (concat "\n" (make-string (current-column) ?\ )))
511 separator cell sources required-features
514 (setq cell (car value))
516 (setq cell (decode-char '=ucs cell)))
518 ((eq name '->subsumptive)
519 (when (or (not (some (lambda (atr)
520 (get-char-attribute cell atr))
521 char-db-ignored-attributes))
523 (encode-char cell ccs 'defined-only))
527 (let ((char-db-ignored-attributes
529 char-db-ignored-attributes)))
530 (insert-char-attributes cell readable nil nil 'for-sub-node))
531 (setq separator lbs))
536 char (intern (format "%s*sources" name))))
537 (setq required-features nil)
538 (dolist (source sources)
542 shinjigen shinjigen@1ed shinjigen@rev))
543 (setq required-features
544 (union required-features
555 (setq required-features
556 (union required-features
561 ((find-charset (setq ret (intern (format "=%s" source))))
562 (setq required-features
563 (cons ret required-features)))
564 (t (setq required-features
565 (cons source required-features)))))
566 (cond ((string-match "@JP" (symbol-name name))
567 (setq required-features
568 (union required-features
576 ((string-match "@CN" (symbol-name name))
577 (setq required-features
578 (union required-features
585 (insert (format "%S" cell))
586 (char-db-insert-char-spec cell readable
589 (setq separator lbs))
593 (if (consp (car cell))
594 (char-db-insert-char-spec cell readable)
595 (char-db-insert-char-reference cell readable))
596 (setq separator lbs))
600 (insert (prin1-to-string cell))
601 (setq separator " ")))
602 (setq value (cdr value)))
604 (insert line-breaking)))
606 (defun insert-char-attributes (char &optional readable attributes column
609 (setq column (current-column)))
610 (let (name value ; has-long-ccs-name
614 (concat "\n" (make-string (1+ column) ?\ )))
615 lbs cell separator ret
617 dest-ccss ; sources required-features
622 (if (consp attributes)
624 (dolist (name attributes)
625 (unless (memq name char-db-ignored-attributes)
626 (if (find-charset name)
630 (dolist (name (char-attribute-list))
631 (unless (memq name char-db-ignored-attributes)
632 (if (find-charset name)
636 #'char-attribute-name<)))
638 (when (memq '<-subsumptive attributes)
639 (when (or readable (not for-sub-node))
640 (when (setq value (get-char-attribute char '<-subsumptive))
641 (char-db-insert-relation-feature char '<-subsumptive value
644 (setq attributes (delq '<-subsumptive attributes)))
645 (when (and (memq '<-denotational attributes)
646 (setq value (get-char-attribute char '<-denotational)))
647 (char-db-insert-relation-feature char '<-denotational value
650 (setq attributes (delq '<-denotational attributes)))
651 (when (and (memq 'name attributes)
652 (setq value (get-char-attribute char 'name)))
654 (if (> (+ (current-column) (length value)) 48)
657 value line-breaking))
658 (setq attributes (delq 'name attributes))
660 (when (and (memq 'name* attributes)
661 (setq value (get-char-attribute char 'name*)))
663 (if (> (+ (current-column) (length value)) 48)
666 value line-breaking))
667 (setq attributes (delq 'name* attributes))
669 (when (and (memq 'script attributes)
670 (setq value (get-char-attribute char 'script)))
671 (insert (format "(script\t\t%s)%s"
672 (mapconcat (function prin1-to-string)
675 (setq attributes (delq 'script attributes))
677 (dolist (name '(=>ucs =>ucs*))
678 (when (and (memq name attributes)
679 (setq value (get-char-attribute char name)))
680 (insert (format "(%-18s . #x%04X)\t; %c%s"
681 name value (decode-char '=ucs value)
683 (setq attributes (delq name attributes))))
684 (dolist (name '(=>ucs@gb =>ucs@big5))
685 (when (and (memq name attributes)
686 (setq value (get-char-attribute char name)))
687 (insert (format "(%-18s . #x%04X)\t; %c%s"
692 (symbol-name name) 2)))
695 (setq attributes (delq name attributes))
697 ;; (dolist (name '(=>daikanwa))
698 ;; (when (and (memq name attributes)
699 ;; (setq value (get-char-attribute char name)))
701 ;; (if (integerp value)
702 ;; (format "(%-18s . %05d)\t; %c%s"
703 ;; name value (decode-char '=daikanwa value)
705 ;; (format "(%-18s %s)\t; %c%s"
707 ;; (mapconcat (function prin1-to-string)
709 ;; (char-representative-of-daikanwa char)
711 ;; (setq attributes (delq name attributes))))
712 (when (and (memq 'general-category attributes)
713 (setq value (get-char-attribute char 'general-category)))
715 "(general-category\t%s) ; %s%s"
716 (mapconcat (lambda (cell)
719 (cond ((rassoc value unidata-normative-category-alist)
720 "Normative Category")
721 ((rassoc value unidata-informative-category-alist)
722 "Informative Category")
726 (setq attributes (delq 'general-category attributes))
728 (when (and (memq 'bidi-category attributes)
729 (setq value (get-char-attribute char 'bidi-category)))
730 (insert (format "(bidi-category\t. %S)%s"
733 (setq attributes (delq 'bidi-category attributes))
735 (unless (or (not (memq 'mirrored attributes))
736 (eq (setq value (get-char-attribute char 'mirrored 'empty))
738 (insert (format "(mirrored\t\t. %S)%s"
741 (setq attributes (delq 'mirrored attributes))
744 ((and (memq 'decimal-digit-value attributes)
745 (setq value (get-char-attribute char 'decimal-digit-value)))
746 (insert (format "(decimal-digit-value . %S)%s"
749 (setq attributes (delq 'decimal-digit-value attributes))
750 (when (and (memq 'digit-value attributes)
751 (setq value (get-char-attribute char 'digit-value)))
752 (insert (format "(digit-value\t . %S)%s"
755 (setq attributes (delq 'digit-value attributes))
757 (when (and (memq 'numeric-value attributes)
758 (setq value (get-char-attribute char 'numeric-value)))
759 (insert (format "(numeric-value\t . %S)%s"
762 (setq attributes (delq 'numeric-value attributes))
766 (when (and (memq 'digit-value attributes)
767 (setq value (get-char-attribute char 'digit-value)))
768 (insert (format "(digit-value\t. %S)%s"
771 (setq attributes (delq 'digit-value attributes))
773 (when (and (memq 'numeric-value attributes)
774 (setq value (get-char-attribute char 'numeric-value)))
775 (insert (format "(numeric-value\t. %S)%s"
778 (setq attributes (delq 'numeric-value attributes))
780 (when (and (memq 'iso-10646-comment attributes)
781 (setq value (get-char-attribute char 'iso-10646-comment)))
782 (insert (format "(iso-10646-comment\t. %S)%s"
785 (setq attributes (delq 'iso-10646-comment attributes))
787 (when (and (memq 'morohashi-daikanwa attributes)
788 (setq value (get-char-attribute char 'morohashi-daikanwa)))
789 (insert (format "(morohashi-daikanwa\t%s)%s"
790 (mapconcat (function prin1-to-string) value " ")
792 (setq attributes (delq 'morohashi-daikanwa attributes))
796 (when (and (memq 'ideographic-radical attributes)
797 (setq value (get-char-attribute char 'ideographic-radical)))
799 (insert (format "(ideographic-radical . %S)\t; %c%s"
801 (ideographic-radical radical)
803 (setq attributes (delq 'ideographic-radical attributes))
805 (when (and (memq 'shuowen-radical attributes)
806 (setq value (get-char-attribute char 'shuowen-radical)))
807 (insert (format "(shuowen-radical\t. %S)\t; %c%s"
809 (shuowen-radical value)
811 (setq attributes (delq 'shuowen-radical attributes))
816 char-db-feature-domains
818 (dolist (feature (char-attribute-list))
819 (setq feature (symbol-name feature))
821 "\\(radical\\|strokes\\)@\\([^@*]+\\)\\(\\*\\|$\\)"
823 (setq domain (intern (match-string 2 feature)))
824 (unless (memq domain dest)
825 (setq dest (cons domain dest)))))
826 (sort dest #'string<))))
827 (setq key (intern (format "%s@%s" 'ideographic-radical domain)))
828 (when (and (memq key attributes)
829 (setq value (get-char-attribute char key)))
831 (insert (format "(%s . %S)\t; %c%s"
834 (ideographic-radical radical)
836 (setq attributes (delq key attributes))
838 (setq key (intern (format "%s@%s" 'ideographic-strokes domain)))
839 (when (and (memq key attributes)
840 (setq value (get-char-attribute char key)))
842 (insert (format "(%s . %S)%s"
846 (setq attributes (delq key attributes))
848 (setq key (intern (format "%s@%s" 'total-strokes domain)))
849 (when (and (memq key attributes)
850 (setq value (get-char-attribute char key)))
851 (insert (format "(%s . %S)%s"
855 (setq attributes (delq key attributes))
857 (dolist (feature '(ideographic-radical
860 (setq key (intern (format "%s@%s*sources" feature domain)))
861 (when (and (memq key attributes)
862 (setq value (get-char-attribute char key)))
863 (insert (format "(%s%s" key line-breaking))
865 (insert (format " %s" cell)))
867 (insert line-breaking)
868 (setq attributes (delq key attributes))
871 (when (and (memq 'ideographic-strokes attributes)
872 (setq value (get-char-attribute char 'ideographic-strokes)))
874 (insert (format "(ideographic-strokes . %S)%s"
877 (setq attributes (delq 'ideographic-strokes attributes))
879 (when (and (memq 'kangxi-radical attributes)
880 (setq value (get-char-attribute char 'kangxi-radical)))
881 (unless (eq value radical)
882 (insert (format "(kangxi-radical\t . %S)\t; %c%s"
884 (ideographic-radical value)
887 (setq radical value)))
888 (setq attributes (delq 'kangxi-radical attributes))
890 (when (and (memq 'kangxi-strokes attributes)
891 (setq value (get-char-attribute char 'kangxi-strokes)))
892 (unless (eq value strokes)
893 (insert (format "(kangxi-strokes\t . %S)%s"
897 (setq strokes value)))
898 (setq attributes (delq 'kangxi-strokes attributes))
900 (when (and (memq 'japanese-radical attributes)
901 (setq value (get-char-attribute char 'japanese-radical)))
902 (unless (eq value radical)
903 (insert (format "(japanese-radical\t . %S)\t; %c%s"
905 (ideographic-radical value)
908 (setq radical value)))
909 (setq attributes (delq 'japanese-radical attributes))
911 (when (and (memq 'japanese-strokes attributes)
912 (setq value (get-char-attribute char 'japanese-strokes)))
913 (unless (eq value strokes)
914 (insert (format "(japanese-strokes\t . %S)%s"
918 (setq strokes value)))
919 (setq attributes (delq 'japanese-strokes attributes))
921 (when (and (memq 'cns-radical attributes)
922 (setq value (get-char-attribute char 'cns-radical)))
923 (insert (format "(cns-radical\t . %S)\t; %c%s"
925 (ideographic-radical value)
927 (setq attributes (delq 'cns-radical attributes))
929 (when (and (memq 'cns-strokes attributes)
930 (setq value (get-char-attribute char 'cns-strokes)))
931 (unless (eq value strokes)
932 (insert (format "(cns-strokes\t . %S)%s"
936 (setq strokes value)))
937 (setq attributes (delq 'cns-strokes attributes))
939 (when (and (memq 'shinjigen-1-radical attributes)
940 (setq value (get-char-attribute char 'shinjigen-1-radical)))
941 (unless (eq value radical)
942 (insert (format "(shinjigen-1-radical . %S)\t; %c%s"
944 (ideographic-radical value)
947 (setq radical value)))
948 (setq attributes (delq 'shinjigen-1-radical attributes))
950 (when (and (memq 'ideographic- attributes)
951 (setq value (get-char-attribute char 'ideographic-)))
952 (insert "(ideographic- ")
953 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
956 (setq cell (car value))
958 (setq cell (decode-char '=ucs cell)))
959 (cond ((characterp cell)
963 (insert (format "%S" cell))
964 (char-db-insert-char-spec cell readable))
965 (setq separator lbs))
969 (if (consp (car cell))
970 (char-db-insert-char-spec cell readable)
971 (char-db-insert-char-reference cell readable))
972 (setq separator lbs))
976 (insert (prin1-to-string cell))
977 (setq separator " ")))
978 (setq value (cdr value)))
980 (insert line-breaking)
981 (setq attributes (delq 'ideographic- attributes)))
982 (when (and (memq 'total-strokes attributes)
983 (setq value (get-char-attribute char 'total-strokes)))
984 (insert (format "(total-strokes . %S)%s"
987 (setq attributes (delq 'total-strokes attributes))
989 (when (and (memq '->ideograph attributes)
990 (setq value (get-char-attribute char '->ideograph)))
991 (insert (format "(->ideograph\t%s)%s"
992 (mapconcat (lambda (code)
993 (cond ((symbolp code)
996 (format "#x%04X" code))
999 line-breaking code))))
1002 (setq attributes (delq '->ideograph attributes))
1004 ;; (when (and (memq '->decomposition attributes)
1005 ;; (setq value (get-char-attribute char '->decomposition)))
1006 ;; (insert (format "(->decomposition\t%s)%s"
1007 ;; (mapconcat (lambda (code)
1008 ;; (cond ((symbolp code)
1009 ;; (symbol-name code))
1010 ;; ((characterp code)
1012 ;; (format "%S" code)
1017 ;; (format "#x%04X" code))
1019 ;; (format "%s%S" line-breaking code))))
1022 ;; (setq attributes (delq '->decomposition attributes))
1024 (if (equal (get-char-attribute char '->titlecase)
1025 (get-char-attribute char '->uppercase))
1026 (setq attributes (delq '->titlecase attributes)))
1027 (when (and (memq '->mojikyo attributes)
1028 (setq value (get-char-attribute char '->mojikyo)))
1029 (insert (format "(->mojikyo\t\t. %06d)\t; %c%s"
1030 value (decode-char 'mojikyo value)
1032 (setq attributes (delq '->mojikyo attributes))
1034 (when (and (memq 'hanyu-dazidian-vol attributes)
1035 (setq value (get-char-attribute char 'hanyu-dazidian-vol)))
1036 (insert (format "(hanyu-dazidian-vol . %d)%s"
1037 value line-breaking))
1038 (setq attributes (delq 'hanyu-dazidian-vol attributes))
1040 (when (and (memq 'hanyu-dazidian-page attributes)
1041 (setq value (get-char-attribute char 'hanyu-dazidian-page)))
1042 (insert (format "(hanyu-dazidian-page . %d)%s"
1043 value line-breaking))
1044 (setq attributes (delq 'hanyu-dazidian-page attributes))
1046 (when (and (memq 'hanyu-dazidian-char attributes)
1047 (setq value (get-char-attribute char 'hanyu-dazidian-char)))
1048 (insert (format "(hanyu-dazidian-char . %d)%s"
1049 value line-breaking))
1050 (setq attributes (delq 'hanyu-dazidian-char attributes))
1053 (dolist (ignored '(composition
1054 ->denotational <-subsumptive ->ucs-unified
1055 ->ideographic-component-forms))
1056 (setq attributes (delq ignored attributes))))
1058 (setq name (car attributes))
1059 (if (setq value (get-char-attribute char name))
1060 (cond ((setq ret (find-charset name))
1061 (setq name (charset-name ret))
1062 (if (and (not (memq name dest-ccss))
1064 (setq value (get-char-attribute char name))
1065 (setq dest-ccss (cons name dest-ccss))))
1066 (char-db-insert-ccs-feature name value line-breaking))
1068 ((string-match "^=>ucs@" (symbol-name name))
1069 (insert (format "(%-18s . #x%04X)\t; %c%s"
1070 name value (decode-char '=ucs value)
1073 ((eq name 'jisx0208-1978/4X)
1074 (insert (format "(%-18s . #x%04X)%s"
1080 (not (eq name '->subsumptive))
1081 (not (eq name '->uppercase))
1082 (not (eq name '->lowercase))
1083 (not (eq name '->titlecase))
1084 (not (eq name '->canonical))
1085 (not (eq name '->Bopomofo))
1086 (not (eq name '->mistakable))
1087 (not (eq name '->ideographic-variants))
1088 (null (get-char-attribute
1089 char (intern (format "%s*sources" name))))
1090 (not (string-match "\\*sources$" (symbol-name name)))
1091 (null (get-char-attribute
1092 char (intern (format "%s*note" name))))
1093 (not (string-match "\\*note$" (symbol-name name)))
1094 (or (eq name '<-identical)
1095 (eq name '<-uppercase)
1096 (eq name '<-lowercase)
1097 (eq name '<-titlecase)
1098 (eq name '<-canonical)
1099 (eq name '<-ideographic-variants)
1100 ;; (eq name '<-synonyms)
1101 (string-match "^<-synonyms" (symbol-name name))
1102 (eq name '<-mistakable)
1103 (when (string-match "^->" (symbol-name name))
1105 ((string-match "^->fullwidth" (symbol-name name))
1106 (not (and (consp value)
1107 (characterp (car value))
1109 (car value) '=ucs 'defined-only)))
1114 ((or (eq name 'ideographic-structure)
1115 (eq name 'ideographic-combination)
1116 (eq name 'ideographic-)
1117 (eq name '=decomposition)
1118 (char-feature-base-name= '=decomposition name)
1119 (char-feature-base-name= '=>decomposition name)
1120 ;; (string-match "^=>*decomposition\\(@[^*]+\\)?$"
1121 ;; (symbol-name name))
1122 (string-match "^\\(->\\|<-\\)[^*]*$" (symbol-name name))
1123 (string-match "^\\(->\\|<-\\)[^*]*\\*sources$"
1126 (char-db-insert-relation-feature char name value
1129 ((memq name '(ideograph=
1130 original-ideograph-of
1131 ancient-ideograph-of
1134 ;; simplified-ideograph-of
1135 ideographic-variants
1136 ;; ideographic-different-form-of
1138 (insert (format "(%-18s%s " name line-breaking))
1139 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1141 (while (consp value)
1142 (setq cell (car value))
1143 (if (and (consp cell)
1148 (char-db-insert-alist cell readable)
1149 (setq separator lbs))
1152 (insert (prin1-to-string cell))
1153 (setq separator " "))
1154 (setq value (cdr value)))
1156 (insert line-breaking))
1158 (insert (format "(%-18s " name))
1159 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1161 (while (consp value)
1162 (setq cell (car value))
1163 (if (and (consp cell)
1165 (setq ret (condition-case nil
1173 (setq key (car (car rest)))
1174 (if (find-charset key)
1175 (setq cal (cons key cal))
1176 (setq al (cons key al)))
1177 (setq rest (cdr rest)))
1180 (insert-char-attributes ret
1184 (setq separator lbs))
1185 (setq ret (prin1-to-string cell))
1187 (if (< (+ (current-column)
1194 (setq separator " "))
1195 (setq value (cdr value)))
1197 (insert line-breaking))
1199 (insert (format "(%-18s" name))
1200 (setq ret (prin1-to-string value))
1201 (unless (< (+ (current-column)
1205 (insert line-breaking))
1206 (insert " . " ret ")" line-breaking)
1207 ;; (insert (format "(%-18s . %S)%s"
1212 (setq attributes (cdr attributes)))
1215 (defun insert-char-data (char &optional readable
1218 (narrow-to-region (point)(point))
1219 (insert "(define-char
1221 (insert-char-attributes char readable attributes)
1223 (goto-char (point-min))
1224 (while (re-search-forward "[ \t]+$" nil t)
1227 (goto-char (point-min))
1228 (while (re-search-forward "[ \t][ \t][ \t]*" nil t)
1229 (let ((column (current-column))
1230 (indent-tabs-mode t))
1231 (delete-region (match-beginning 0) (point))
1232 (indent-to column)))
1233 (goto-char (point-max))
1234 ;; (tabify (point-min)(point-max))
1237 (defun insert-char-data-with-variant (char &optional printable
1239 script excluded-script)
1240 (insert-char-data char printable)
1241 (let ((variants (char-variants char))
1244 (setq variants (sort variants #'<))
1245 (setq rest variants)
1246 (setq variants (cons char variants))
1248 (setq variant (car rest))
1249 (unless (get-char-attribute variant '<-subsumptive)
1250 (if (and (or (null script)
1251 (null (setq vs (get-char-attribute variant 'script)))
1253 (or (null excluded-script)
1254 (null (setq vs (get-char-attribute variant 'script)))
1255 (not (memq excluded-script vs))))
1256 (unless (and no-ucs-unified (get-char-attribute variant '=ucs))
1257 (insert-char-data variant printable)
1258 (if (setq ret (char-variants variant))
1260 (or (memq (car ret) variants)
1261 ;; (get-char-attribute (car ret) '<-subsumptive)
1262 (setq rest (nconc rest (list (car ret)))))
1263 (setq ret (cdr ret)))))))
1264 (setq rest (cdr rest)))))
1266 (defun insert-char-range-data (min max &optional script excluded-script)
1269 (while (<= code max)
1270 (setq char (decode-char '=ucs code))
1271 (if (encode-char char '=ucs 'defined-only)
1272 (insert-char-data-with-variant char nil 'no-ucs-unified
1273 script excluded-script))
1274 (setq code (1+ code)))))
1276 (defun write-char-range-data-to-file (min max file
1277 &optional script excluded-script)
1278 (let ((coding-system-for-write char-db-file-coding-system))
1280 (insert (format ";; -*- coding: %s -*-\n"
1281 char-db-file-coding-system))
1282 (insert-char-range-data min max script excluded-script)
1283 (write-region (point-min)(point-max) file))))
1285 (defvar what-character-original-window-configuration)
1288 (defun what-char-definition (char)
1289 (interactive (list (char-after)))
1290 (let ((buf (get-buffer-create "*Character Description*"))
1291 (the-buf (current-buffer))
1292 (win-conf (current-window-configuration)))
1294 (make-local-variable 'what-character-original-window-configuration)
1295 (setq what-character-original-window-configuration win-conf)
1296 (setq buffer-read-only nil)
1300 (insert-char-data-with-variant char 'printable)
1301 (unless (char-attribute-alist char)
1302 (insert (format ";; = %c\n"
1303 (let* ((rest (split-char char))
1307 (setq code (logior (lsh code 8)
1309 (decode-char ccs code)))))
1310 ;; (char-db-update-comment)
1311 (set-buffer-modified-p nil)
1312 (view-mode the-buf (lambda (buf)
1313 (set-window-configuration
1314 what-character-original-window-configuration)
1316 (goto-char (point-min)))
1318 (set-window-configuration
1319 what-character-original-window-configuration)
1320 (signal (car err) (cdr err)))))))
1326 (provide 'char-db-util)
1328 ;;; char-db-util.el ends here