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, 2012, 2013 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 ?𠬜 ?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 ; ?旨 ?曰 ?乃 ?丂 ?可 ?兮 ?号 ?亏 ?喜 ?壴 ; 160
84 ?鼓 ?豈 ?豆 ?豊 ?豐 ?䖒 ?虍 ?虎 ?虤 ?皿 ; 170
85 ?𠙴 ?去 ?血 ?丶 ?丹 ?青 ?井 ?皀 ?鬯 ?食 ; 180
86 ?亼 ?會 ?倉 ?入 ?缶 ?矢 ?高 ?冂 ?𩫏 ?京 ; 190
87 ?亯 ?𣆪 ?畗 ?㐭 ?嗇 ?來 ?麥 ?夊 ?舛 ?䑞 ; 200
88 ?韋 ?弟 ?夂 ?久 ?桀 ?木 ?東 ?林 ?才 ?叒 ; 210
89 ?之 ?帀 ?出 ?𣎵 ?生 ?乇 ?𠂹 ?𠌶 ?華 ?𥝌 ; 220
90 ?稽 ?巢 ?桼 ?束 ?㯻 ?囗 ?員 ?貝 ?邑 ?𨛜 ; 230
91 ?日 ?旦 ?倝 ?㫃 ?冥 ?晶 ?月 ?有 ?明 ?囧 ; 240
92 ?夕 ?多 ?毌 ?𢎘 ?𣐺 ?卣 ?齊 ?朿 ?片 ?鼎 ; 250
93 ?克 ?彔 ?禾 ?秝 ?黍 ?香 ?米 ?毇 ?臼 ?凶 ; 260
94 ?𣎳 ?林 ?麻 ?尗 ?耑 ?韭 ?瓜 ?瓠 ?宀 ?宮 ; 270
95 ?呂 ?穴 ?㝱 ?𤕫 ?冖 ?𠔼 ?冃 ?㒳 ?网 ?襾 ; 280
96 ?巾 ?巿 ?帛 ?白 ?㡀 ?黹 ?人 ?𠤎 ?匕 ?从 ; 290
97 ?比 ?北 ?丘 ?㐺 ?𡈼 ?重 ?臥 ?身 ?㐆 ?衣 ; 300
100 (defun shuowen-radical (number)
101 (aref shuowen-radicals (1- number)))
103 (defvar char-db-file-coding-system 'utf-8-mcs-er)
105 (defvar char-db-ignored-attributes '(ideographic-products))
107 (defvar char-db-coded-charset-priority-list
198 ;; =>>>adobe-japan1-0
199 ;; =>>>adobe-japan1-1
200 ;; =>>>adobe-japan1-2
201 ;; =>>>adobe-japan1-3
202 ;; =>>>adobe-japan1-4
203 ;; =>>>adobe-japan1-5
204 ;; =>>>adobe-japan1-6
208 ;; =>>>hanyo-denshi/ja
209 ;; =>>>hanyo-denshi/jb
210 ;; =>>>hanyo-denshi/jc
211 ;; =>>>hanyo-denshi/ft
212 ;; =>>>hanyo-denshi/ib
213 ;; =>>>hanyo-denshi/hg
214 ;; =>>>hanyo-denshi/jt
215 ;; =>>>hanyo-denshi/ks
305 ;;; @ char-db formatters
308 (defun char-db-make-char-spec (char)
310 (cond ((characterp char)
311 (cond ((and (setq ret (encode-char char '=ucs 'defined-only))
312 (not (and (<= #xE000 ret)(<= ret #xF8FF))))
313 (setq char-spec (list (cons '=ucs ret)))
314 (cond ((setq ret (get-char-attribute char 'name))
315 (setq char-spec (cons (cons 'name ret) char-spec))
317 ((setq ret (get-char-attribute char 'name*))
318 (setq char-spec (cons (cons 'name* ret) char-spec))
321 ((encode-char char '=adobe-japan1 'defined-only)
323 (dolist (ccs (charset-list))
324 (if (and (or (memq ccs
333 ;; (eq (charset-property ccs 'iso-ir) 177)
334 (string-match "=ucs@" (symbol-name ccs))
336 (setq ccs (charset-name ccs))
337 (null (assq ccs char-spec))
338 (setq ret (encode-char char ccs 'defined-only)))
339 (setq char-spec (cons (cons ccs ret) char-spec))))
341 ((encode-char char '==adobe-japan1 'defined-only)
343 (dolist (ccs (charset-list))
344 (if (and (or (memq ccs
353 ;; (eq (charset-property ccs 'iso-ir) 177)
354 (string-match "=ucs@" (symbol-name ccs))
356 (setq ccs (charset-name ccs))
357 (null (assq ccs char-spec))
358 (setq ret (encode-char char ccs 'defined-only)))
359 (setq char-spec (cons (cons ccs ret) char-spec))))
363 (let ((rest char-db-coded-charset-priority-list)
366 (setq ccs (charset-name
367 (find-charset (car rest))))
369 (encode-char char ccs
371 (throw 'tag (cons ccs ret)))
372 (setq rest (cdr rest))))))
373 (setq char-spec (list ret))
374 (dolist (ccs (delq (car ret) (charset-list)))
375 (if (and (or (charset-iso-final-char ccs)
382 (eq (charset-property ccs 'iso-ir) 177)
383 ;; (string-match "=ucs@" (symbol-name ccs))
385 (setq ccs (charset-name ccs))
386 (null (assq ccs char-spec))
387 (setq ret (encode-char char ccs 'defined-only)))
388 (setq char-spec (cons (cons ccs ret) char-spec))))
390 (setq char-spec (split-char char)))
391 (cond ((setq ret (get-char-attribute char 'name))
392 (setq char-spec (cons (cons 'name ret) char-spec))
394 ((setq ret (get-char-attribute char 'name*))
395 (setq char-spec (cons (cons 'name* ret) char-spec))
398 ((setq ret (get-char-attribute
399 char 'ideographic-combination))
401 (cons (cons 'ideographic-combination ret)
408 (defun char-db-insert-char-spec (char &optional readable column
411 (setq column (current-column)))
412 (let (char-spec temp-char)
413 (setq char-spec (char-db-make-char-spec char))
414 (unless (or (characterp char) ; char
416 (setq char (find-char char-spec))
418 ;; define temporary character
419 ;; Current implementation is dirty.
420 (setq temp-char (define-char (cons '(ideograph-daikanwa . 0)
422 (remove-char-attribute temp-char 'ideograph-daikanwa)
423 (setq char temp-char))
424 (insert-char-attributes char
426 (union (mapcar #'car char-spec)
430 ;; undefine temporary character
431 ;; Current implementation is dirty.
432 (setq char-spec (char-attribute-alist temp-char))
434 (remove-char-attribute temp-char (car (car char-spec)))
435 (setq char-spec (cdr char-spec))))))
437 (defun char-db-insert-alist (alist &optional readable column)
439 (setq column (current-column)))
441 (concat "\n" (make-string (1+ column) ?\ )))
445 lbs cell rest separator)
448 (setq name (car (car alist))
449 value (cdr (car alist)))
450 (cond ((eq name 'char)
452 (if (setq ret (condition-case nil
460 (setq key (car (car value)))
461 ;; (if (find-charset key)
462 ;; (setq cal (cons key cal))
463 (setq al (cons key al))
465 (setq value (cdr value)))
466 (insert-char-attributes ret
470 (insert (prin1-to-string value)))
472 (insert line-breaking))
474 (insert (format "(%-18s " name))
475 (setq lbs (concat "\n" (make-string (current-column) ?\ )))
477 (setq cell (car value))
478 (if (and (consp cell)
480 (setq ret (condition-case nil
490 (setq key (car (car rest)))
491 ;; (if (find-charset key)
492 ;; (setq cal (cons key cal))
493 (setq al (cons key al))
495 (setq rest (cdr rest)))
498 (insert-char-attributes ret
502 (setq separator lbs))
505 (insert (prin1-to-string cell))
506 (setq separator " "))
507 (setq value (cdr value)))
509 (insert line-breaking))
511 (insert (format "(%-18s . %S)%s"
514 (setq alist (cdr alist))))
517 (defun char-db-insert-char-reference (plist &optional readable column)
519 (setq column (current-column)))
521 (concat "\n" (make-string (1+ column) ?\ )))
526 (setq name (pop plist))
527 (setq value (pop plist))
528 (cond ((eq name :char)
531 (cond ((numberp value)
532 (setq value (decode-char '=ucs value)))
534 ;; (setq value (or (find-char value)
537 (char-db-insert-char-spec value readable)
538 (insert line-breaking)
541 (insert (format "%s%s\t%d ; %c%s"
544 (ideographic-radical value)
548 (insert (format "%s%s\t%S" separator name value))
549 (setq separator line-breaking)))
553 (defun char-db-decode-isolated-char (ccs code-point)
556 (cond ((eq ccs 'arabic-iso8859-6)
557 (decode-char ccs code-point))
559 ;; (decode-builtin-char '==gt code-point))
560 ((and (memq ccs '(=gt-pj-1
571 (setq ret (decode-char ccs code-point))
572 (setq ret (encode-char ret '=gt 'defined-only)))
573 (decode-builtin-char '=gt ret))
575 (decode-builtin-char ccs code-point))))
576 (cond ((and (<= 0 (char-int ret))
577 (<= (char-int ret) #x1F))
578 (decode-char '=ucs (+ #x2400 (char-int ret))))
579 ((= (char-int ret) #x7F)
583 (defvar char-db-convert-obsolete-format t)
585 (defun char-db-insert-ccs-feature (name value line-breaking)
591 ((memq name '(==shinjigen
594 =shinjigen@rev ==shinjigen@rev
596 =daikanwa/ho =>>daikanwa/ho =>daikanwa/ho))
597 "(%-18s . %04d)\t; %c")
598 ((eq name '=shinjigen@1ed/24pr)
599 "(%-18s . %04d)\t; %c")
600 ((or (memq name '(==daikanwa
601 =daikanwa =>>daikanwa =>daikanwa
602 =daikanwa@rev1 =daikanwa@rev2
603 =daikanwa/+p ==daikanwa/+p =>>daikanwa/+p
604 =daikanwa/+2p =>>daikanwa/+2p
607 =gt-k ==gt-k =>>gt-k =>gt-k
608 =adobe-japan1-0 ==adobe-japan1-0 ; =>>>adobe-japan1-0
609 =adobe-japan1-1 ==adobe-japan1-1 ; =>>>adobe-japan1-1
610 =adobe-japan1-2 ==adobe-japan1-2 ; =>>>adobe-japan1-2
611 =adobe-japan1-3 ==adobe-japan1-3 ; =>>>adobe-japan1-3
612 =adobe-japan1-4 ==adobe-japan1-4 ; =>>>adobe-japan1-4
613 =adobe-japan1-5 ==adobe-japan1-5 ; =>>>adobe-japan1-5
614 =adobe-japan1-6 ==adobe-japan1-6 ; =>>>adobe-japan1-6
615 =>>adobe-japan1-0 =+>adobe-japan1-0
616 =>>adobe-japan1-1 =+>adobe-japan1-1
617 =>>adobe-japan1-2 =+>adobe-japan1-2
618 =>>adobe-japan1-3 =+>adobe-japan1-3
619 =>>adobe-japan1-4 =+>adobe-japan1-4
620 =>>adobe-japan1-5 =+>adobe-japan1-5
621 =>>adobe-japan1-6 =+>adobe-japan1-6
623 =zinbun-oracle =>zinbun-oracle))
624 ;; (string-match "^=adobe-" (symbol-name name))
626 "(%-18s . %05d)\t; %c")
627 ((memq name '(=hanyo-denshi/ks
628 ==hanyo-denshi/ks ; =>>>hanyo-denshi/ks
631 "(%-18s . %06d)\t; %c")
632 ((>= (charset-dimension name) 2)
633 "(%-18s . #x%04X)\t; %c")
635 "(%-18s . #x%02X)\t; %c"))
637 (if (= (charset-iso-graphic-plane name) 1)
639 (cond ((= (charset-dimension name) 1)
641 ((= (charset-dimension name) 2)
643 ((= (charset-dimension name) 3)
647 (char-db-decode-isolated-char name value)))
648 (if (and (= (charset-chars name) 94)
649 (= (charset-dimension name) 2))
650 (insert (format " [%02d-%02d]"
651 (- (lsh value -8) 32)
652 (- (logand value 255) 32))))
655 (insert (format "(%-18s . %s)" name value))
657 (insert line-breaking))
659 (defun char-db-insert-relation-feature (char name value line-breaking
661 (insert (format "(%-18s%s " name line-breaking))
662 (let ((lbs (concat "\n" (make-string (current-column) ?\ )))
663 separator cell sources required-features
666 (setq cell (car value))
668 (setq cell (decode-char '=ucs cell)))
670 ((eq name '->subsumptive)
671 (when (or (not (some (lambda (atr)
672 (get-char-attribute cell atr))
673 char-db-ignored-attributes))
675 (encode-char cell ccs 'defined-only))
679 (let ((char-db-ignored-attributes
681 char-db-ignored-attributes)))
682 (insert-char-attributes cell readable nil nil 'for-sub-node))
683 (setq separator lbs))
688 char (intern (format "%s*sources" name))))
689 (setq required-features nil)
690 (dolist (source sources)
694 shinjigen shinjigen@1ed shinjigen@rev))
695 (setq required-features
696 (union required-features
708 =shinjigen/+p@rev))))
710 (setq required-features
711 (union required-features
716 ((find-charset (setq ret (intern (format "=%s" source))))
717 (setq required-features
718 (cons ret required-features)))
719 (t (setq required-features
720 (cons source required-features)))))
721 (cond ((string-match "@JP" (symbol-name name))
722 (setq required-features
723 (union required-features
731 ((string-match "@CN" (symbol-name name))
732 (setq required-features
733 (union required-features
740 (insert (format "%S" cell))
741 (char-db-insert-char-spec cell readable
744 (setq separator lbs))
748 (if (consp (car cell))
749 (char-db-insert-char-spec cell readable)
750 (char-db-insert-char-reference cell readable))
751 (setq separator lbs))
755 (insert (prin1-to-string cell))
756 (setq separator " ")))
757 (setq value (cdr value)))
759 (insert line-breaking)))
761 (defun insert-char-attributes (char &optional readable attributes column
764 (setq column (current-column)))
765 (let (name value ; has-long-ccs-name
769 (concat "\n" (make-string (1+ column) ?\ )))
770 lbs cell separator ret
772 dest-ccss ; sources required-features
777 (if (consp attributes)
779 (dolist (name attributes)
780 (unless (memq name char-db-ignored-attributes)
781 (if (find-charset name)
785 (dolist (name (char-attribute-list))
786 (unless (memq name char-db-ignored-attributes)
787 (if (find-charset name)
791 #'char-attribute-name<)))
793 (when (memq '<-subsumptive attributes)
794 (when (or readable (not for-sub-node))
795 (when (setq value (get-char-attribute char '<-subsumptive))
796 (char-db-insert-relation-feature char '<-subsumptive value
799 (setq attributes (delq '<-subsumptive attributes)))
800 (when (and (memq '<-denotational attributes)
801 (setq value (get-char-attribute char '<-denotational)))
802 (char-db-insert-relation-feature char '<-denotational value
805 (setq attributes (delq '<-denotational attributes)))
806 (when (and (memq 'name attributes)
807 (setq value (get-char-attribute char 'name)))
809 (if (> (+ (current-column) (length value)) 48)
812 value line-breaking))
813 (setq attributes (delq 'name attributes))
815 (when (and (memq 'name* attributes)
816 (setq value (get-char-attribute char 'name*)))
818 (if (> (+ (current-column) (length value)) 48)
821 value line-breaking))
822 (setq attributes (delq 'name* attributes))
824 (when (and (memq 'script attributes)
825 (setq value (get-char-attribute char 'script)))
826 (insert (format "(script\t\t%s)%s"
827 (mapconcat (function prin1-to-string)
830 (setq attributes (delq 'script attributes))
832 (dolist (name '(=>ucs =>ucs*))
833 (when (and (memq name attributes)
834 (setq value (get-char-attribute char name)))
835 (insert (format "(%-18s . #x%04X)\t; %c%s"
836 name value (decode-char '=ucs value)
838 (setq attributes (delq name attributes))))
839 (dolist (name '(=>ucs@gb =>ucs@big5))
840 (when (and (memq name attributes)
841 (setq value (get-char-attribute char name)))
842 (insert (format "(%-18s . #x%04X)\t; %c%s"
847 (symbol-name name) 2)))
850 (setq attributes (delq name attributes))
852 ;; (dolist (name '(=>daikanwa))
853 ;; (when (and (memq name attributes)
854 ;; (setq value (get-char-attribute char name)))
856 ;; (if (integerp value)
857 ;; (format "(%-18s . %05d)\t; %c%s"
858 ;; name value (decode-char '=daikanwa value)
860 ;; (format "(%-18s %s)\t; %c%s"
862 ;; (mapconcat (function prin1-to-string)
864 ;; (char-representative-of-daikanwa char)
866 ;; (setq attributes (delq name attributes))))
867 (when (and (memq 'general-category attributes)
868 (setq value (get-char-attribute char 'general-category)))
870 "(general-category\t%s) ; %s%s"
871 (mapconcat (lambda (cell)
874 (cond ((rassoc value unidata-normative-category-alist)
875 "Normative Category")
876 ((rassoc value unidata-informative-category-alist)
877 "Informative Category")
881 (setq attributes (delq 'general-category attributes))
883 (when (and (memq 'bidi-category attributes)
884 (setq value (get-char-attribute char 'bidi-category)))
885 (insert (format "(bidi-category\t. %S)%s"
888 (setq attributes (delq 'bidi-category attributes))
890 (unless (or (not (memq 'mirrored attributes))
891 (eq (setq value (get-char-attribute char 'mirrored 'empty))
893 (insert (format "(mirrored\t\t. %S)%s"
896 (setq attributes (delq 'mirrored attributes))
899 ((and (memq 'decimal-digit-value attributes)
900 (setq value (get-char-attribute char 'decimal-digit-value)))
901 (insert (format "(decimal-digit-value . %S)%s"
904 (setq attributes (delq 'decimal-digit-value attributes))
905 (when (and (memq 'digit-value attributes)
906 (setq value (get-char-attribute char 'digit-value)))
907 (insert (format "(digit-value\t . %S)%s"
910 (setq attributes (delq 'digit-value attributes))
912 (when (and (memq 'numeric-value attributes)
913 (setq value (get-char-attribute char 'numeric-value)))
914 (insert (format "(numeric-value\t . %S)%s"
917 (setq attributes (delq 'numeric-value attributes))
921 (when (and (memq 'digit-value attributes)
922 (setq value (get-char-attribute char 'digit-value)))
923 (insert (format "(digit-value\t. %S)%s"
926 (setq attributes (delq 'digit-value attributes))
928 (when (and (memq 'numeric-value attributes)
929 (setq value (get-char-attribute char 'numeric-value)))
930 (insert (format "(numeric-value\t. %S)%s"
933 (setq attributes (delq 'numeric-value attributes))
935 (when (and (memq 'iso-10646-comment attributes)
936 (setq value (get-char-attribute char 'iso-10646-comment)))
937 (insert (format "(iso-10646-comment\t. %S)%s"
940 (setq attributes (delq 'iso-10646-comment attributes))
942 (when (and (memq 'morohashi-daikanwa attributes)
943 (setq value (get-char-attribute char 'morohashi-daikanwa)))
944 (insert (format "(morohashi-daikanwa\t%s)%s"
945 (mapconcat (function prin1-to-string) value " ")
947 (setq attributes (delq 'morohashi-daikanwa attributes))
951 (when (and (memq 'ideographic-radical attributes)
952 (setq value (get-char-attribute char 'ideographic-radical)))
954 (insert (format "(ideographic-radical . %S)\t; %c%s"
956 (ideographic-radical radical)
958 (setq attributes (delq 'ideographic-radical attributes))
960 (when (and (memq 'shuowen-radical attributes)
961 (setq value (get-char-attribute char 'shuowen-radical)))
962 (insert (format "(shuowen-radical\t. %S)\t; %c%s"
964 (shuowen-radical value)
966 (setq attributes (delq 'shuowen-radical attributes))
971 char-db-feature-domains
973 (dolist (feature (char-attribute-list))
974 (setq feature (symbol-name feature))
976 "\\(radical\\|strokes\\)@\\([^@*]+\\)\\(\\*\\|$\\)"
978 (setq domain (intern (match-string 2 feature)))
979 (unless (memq domain dest)
980 (setq dest (cons domain dest)))))
981 (sort dest #'string<))))
982 (setq key (intern (format "%s@%s" 'ideographic-radical domain)))
983 (when (and (memq key attributes)
984 (setq value (get-char-attribute char key)))
986 (insert (format "(%s . %S)\t; %c%s"
989 (ideographic-radical radical)
991 (setq attributes (delq key attributes))
993 (setq key (intern (format "%s@%s" 'ideographic-strokes domain)))
994 (when (and (memq key attributes)
995 (setq value (get-char-attribute char key)))
997 (insert (format "(%s . %S)%s"
1001 (setq attributes (delq key attributes))
1003 (setq key (intern (format "%s@%s" 'total-strokes domain)))
1004 (when (and (memq key attributes)
1005 (setq value (get-char-attribute char key)))
1006 (insert (format "(%s . %S)%s"
1010 (setq attributes (delq key attributes))
1012 (dolist (feature '(ideographic-radical
1015 (setq key (intern (format "%s@%s*sources" feature domain)))
1016 (when (and (memq key attributes)
1017 (setq value (get-char-attribute char key)))
1018 (insert (format "(%s%s" key line-breaking))
1019 (dolist (cell value)
1020 (insert (format " %s" cell)))
1022 (insert line-breaking)
1023 (setq attributes (delq key attributes))
1026 (when (and (memq 'ideographic-strokes attributes)
1027 (setq value (get-char-attribute char 'ideographic-strokes)))
1028 (setq strokes value)
1029 (insert (format "(ideographic-strokes . %S)%s"
1032 (setq attributes (delq 'ideographic-strokes attributes))
1034 (when (and (memq 'kangxi-radical attributes)
1035 (setq value (get-char-attribute char 'kangxi-radical)))
1036 (unless (eq value radical)
1037 (insert (format "(kangxi-radical\t . %S)\t; %c%s"
1039 (ideographic-radical value)
1042 (setq radical value)))
1043 (setq attributes (delq 'kangxi-radical attributes))
1045 (when (and (memq 'kangxi-strokes attributes)
1046 (setq value (get-char-attribute char 'kangxi-strokes)))
1047 (unless (eq value strokes)
1048 (insert (format "(kangxi-strokes\t . %S)%s"
1052 (setq strokes value)))
1053 (setq attributes (delq 'kangxi-strokes attributes))
1055 (when (and (memq 'japanese-radical attributes)
1056 (setq value (get-char-attribute char 'japanese-radical)))
1057 (unless (eq value radical)
1058 (insert (format "(japanese-radical\t . %S)\t; %c%s"
1060 (ideographic-radical value)
1063 (setq radical value)))
1064 (setq attributes (delq 'japanese-radical attributes))
1066 (when (and (memq 'japanese-strokes attributes)
1067 (setq value (get-char-attribute char 'japanese-strokes)))
1068 (unless (eq value strokes)
1069 (insert (format "(japanese-strokes\t . %S)%s"
1073 (setq strokes value)))
1074 (setq attributes (delq 'japanese-strokes attributes))
1076 (when (and (memq 'cns-radical attributes)
1077 (setq value (get-char-attribute char 'cns-radical)))
1078 (insert (format "(cns-radical\t . %S)\t; %c%s"
1080 (ideographic-radical value)
1082 (setq attributes (delq 'cns-radical attributes))
1084 (when (and (memq 'cns-strokes attributes)
1085 (setq value (get-char-attribute char 'cns-strokes)))
1086 (unless (eq value strokes)
1087 (insert (format "(cns-strokes\t . %S)%s"
1091 (setq strokes value)))
1092 (setq attributes (delq 'cns-strokes attributes))
1094 ;; (when (and (memq 'shinjigen-1-radical attributes)
1095 ;; (setq value (get-char-attribute char 'shinjigen-1-radical)))
1096 ;; (unless (eq value radical)
1097 ;; (insert (format "(shinjigen-1-radical . %S)\t; %c%s"
1099 ;; (ideographic-radical value)
1102 ;; (setq radical value)))
1103 ;; (setq attributes (delq 'shinjigen-1-radical attributes))
1105 (when (and (memq 'ideographic- attributes)
1106 (setq value (get-char-attribute char 'ideographic-)))
1107 (insert "(ideographic- ")
1108 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1110 (while (consp value)
1111 (setq cell (car value))
1113 (setq cell (decode-char '=ucs cell)))
1114 (cond ((characterp cell)
1118 (insert (format "%S" cell))
1119 (char-db-insert-char-spec cell readable))
1120 (setq separator lbs))
1124 (if (consp (car cell))
1125 (char-db-insert-char-spec cell readable)
1126 (char-db-insert-char-reference cell readable))
1127 (setq separator lbs))
1131 (insert (prin1-to-string cell))
1132 (setq separator " ")))
1133 (setq value (cdr value)))
1135 (insert line-breaking)
1136 (setq attributes (delq 'ideographic- attributes)))
1137 (when (and (memq 'total-strokes attributes)
1138 (setq value (get-char-attribute char 'total-strokes)))
1139 (insert (format "(total-strokes . %S)%s"
1142 (setq attributes (delq 'total-strokes attributes))
1144 (when (and (memq '->ideograph attributes)
1145 (setq value (get-char-attribute char '->ideograph)))
1146 (insert (format "(->ideograph\t%s)%s"
1147 (mapconcat (lambda (code)
1148 (cond ((symbolp code)
1151 (format "#x%04X" code))
1154 line-breaking code))))
1157 (setq attributes (delq '->ideograph attributes))
1159 ;; (when (and (memq '->decomposition attributes)
1160 ;; (setq value (get-char-attribute char '->decomposition)))
1161 ;; (insert (format "(->decomposition\t%s)%s"
1162 ;; (mapconcat (lambda (code)
1163 ;; (cond ((symbolp code)
1164 ;; (symbol-name code))
1165 ;; ((characterp code)
1167 ;; (format "%S" code)
1172 ;; (format "#x%04X" code))
1174 ;; (format "%s%S" line-breaking code))))
1177 ;; (setq attributes (delq '->decomposition attributes))
1179 (if (equal (get-char-attribute char '->titlecase)
1180 (get-char-attribute char '->uppercase))
1181 (setq attributes (delq '->titlecase attributes)))
1182 (when (and (memq '->mojikyo attributes)
1183 (setq value (get-char-attribute char '->mojikyo)))
1184 (insert (format "(->mojikyo\t\t. %06d)\t; %c%s"
1185 value (decode-char 'mojikyo value)
1187 (setq attributes (delq '->mojikyo attributes))
1189 (when (and (memq 'hanyu-dazidian-vol attributes)
1190 (setq value (get-char-attribute char 'hanyu-dazidian-vol)))
1191 (insert (format "(hanyu-dazidian-vol . %d)%s"
1192 value line-breaking))
1193 (setq attributes (delq 'hanyu-dazidian-vol attributes))
1195 (when (and (memq 'hanyu-dazidian-page attributes)
1196 (setq value (get-char-attribute char 'hanyu-dazidian-page)))
1197 (insert (format "(hanyu-dazidian-page . %d)%s"
1198 value line-breaking))
1199 (setq attributes (delq 'hanyu-dazidian-page attributes))
1201 (when (and (memq 'hanyu-dazidian-char attributes)
1202 (setq value (get-char-attribute char 'hanyu-dazidian-char)))
1203 (insert (format "(hanyu-dazidian-char . %d)%s"
1204 value line-breaking))
1205 (setq attributes (delq 'hanyu-dazidian-char attributes))
1208 (dolist (ignored '(composition
1209 ->denotational <-subsumptive ->ucs-unified
1210 ->ideographic-component-forms))
1211 (setq attributes (delq ignored attributes))))
1213 (setq name (car attributes))
1214 (unless (eq (setq value (get-char-attribute char name 'value-is-empty))
1216 (cond ((setq ret (find-charset name))
1217 (setq name (charset-name ret))
1218 (when (not (memq name dest-ccss))
1219 (setq dest-ccss (cons name dest-ccss))
1220 (char-db-insert-ccs-feature name value line-breaking))
1222 ((string-match "^=>ucs@" (symbol-name name))
1223 (insert (format "(%-18s . #x%04X)\t; %c%s"
1224 name value (decode-char '=ucs value)
1227 ((eq name 'jisx0208-1978/4X)
1228 (insert (format "(%-18s . #x%04X)%s"
1234 (not (eq name '->subsumptive))
1235 (not (eq name '->uppercase))
1236 (not (eq name '->lowercase))
1237 (not (eq name '->titlecase))
1238 (not (eq name '->canonical))
1239 (not (eq name '->Bopomofo))
1240 (not (eq name '->mistakable))
1241 (not (eq name '->ideographic-variants))
1242 (null (get-char-attribute
1243 char (intern (format "%s*sources" name))))
1244 (not (string-match "\\*sources$" (symbol-name name)))
1245 (null (get-char-attribute
1246 char (intern (format "%s*note" name))))
1247 (not (string-match "\\*note$" (symbol-name name)))
1248 (or (eq name '<-identical)
1249 (eq name '<-uppercase)
1250 (eq name '<-lowercase)
1251 (eq name '<-titlecase)
1252 (eq name '<-canonical)
1253 (eq name '<-ideographic-variants)
1254 ;; (eq name '<-synonyms)
1255 (string-match "^<-synonyms" (symbol-name name))
1256 (eq name '<-mistakable)
1257 (when (string-match "^->" (symbol-name name))
1259 ((string-match "^->fullwidth" (symbol-name name))
1260 (not (and (consp value)
1261 (characterp (car value))
1263 (car value) '=ucs 'defined-only)))
1268 ((or (eq name 'ideographic-structure)
1269 (eq name 'ideographic-combination)
1270 (eq name 'ideographic-)
1271 (eq name '=decomposition)
1272 (char-feature-base-name= '=decomposition name)
1273 (char-feature-base-name= '=>decomposition name)
1274 ;; (string-match "^=>*decomposition\\(@[^*]+\\)?$"
1275 ;; (symbol-name name))
1276 (string-match "^\\(->\\|<-\\)[^*]*$" (symbol-name name))
1277 (string-match "^\\(->\\|<-\\)[^*]*\\*sources$"
1280 (char-db-insert-relation-feature char name value
1283 ((memq name '(ideograph=
1284 original-ideograph-of
1285 ancient-ideograph-of
1288 ;; simplified-ideograph-of
1289 ideographic-variants
1290 ;; ideographic-different-form-of
1292 (insert (format "(%-18s%s " name line-breaking))
1293 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1295 (while (consp value)
1296 (setq cell (car value))
1297 (if (and (consp cell)
1302 (char-db-insert-alist cell readable)
1303 (setq separator lbs))
1306 (insert (prin1-to-string cell))
1307 (setq separator " "))
1308 (setq value (cdr value)))
1310 (insert line-breaking))
1312 (insert (format "(%-18s " name))
1313 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1315 (while (consp value)
1316 (setq cell (car value))
1317 (if (and (consp cell)
1319 (setq ret (condition-case nil
1327 (setq key (car (car rest)))
1328 (if (find-charset key)
1329 (setq cal (cons key cal))
1330 (setq al (cons key al)))
1331 (setq rest (cdr rest)))
1334 (insert-char-attributes ret
1338 (setq separator lbs))
1339 (setq ret (prin1-to-string cell))
1341 (if (< (+ (current-column)
1348 (setq separator " "))
1349 (setq value (cdr value)))
1351 (insert line-breaking))
1353 (insert (format "(%-18s" name))
1354 (setq ret (prin1-to-string value))
1355 (unless (< (+ (current-column)
1359 (insert line-breaking))
1360 (insert " . " ret ")" line-breaking)
1361 ;; (insert (format "(%-18s . %S)%s"
1366 (setq attributes (cdr attributes)))
1369 (defun insert-char-data (char &optional readable
1372 (narrow-to-region (point)(point))
1373 (insert "(define-char
1375 (insert-char-attributes char readable attributes)
1377 (goto-char (point-min))
1378 (while (re-search-forward "[ \t]+$" nil t)
1381 (goto-char (point-min))
1382 (while (re-search-forward "[ \t][ \t][ \t]*" nil t)
1383 (let ((column (current-column))
1384 (indent-tabs-mode t))
1385 (delete-region (match-beginning 0) (point))
1386 (indent-to column)))
1387 (goto-char (point-max))
1388 ;; (tabify (point-min)(point-max))
1391 (defun insert-char-data-with-variant (char &optional printable
1393 script excluded-script)
1394 (insert-char-data char printable)
1395 (let ((variants (char-variants char))
1398 (setq variants (sort variants #'<))
1399 (setq rest variants)
1400 (setq variants (cons char variants))
1402 (setq variant (car rest))
1403 (unless (get-char-attribute variant '<-subsumptive)
1404 (if (and (or (null script)
1405 (null (setq vs (get-char-attribute variant 'script)))
1407 (or (null excluded-script)
1408 (null (setq vs (get-char-attribute variant 'script)))
1409 (not (memq excluded-script vs))))
1410 (unless (and no-ucs-unified (get-char-attribute variant '=ucs))
1411 (insert-char-data variant printable)
1412 (if (setq ret (char-variants variant))
1414 (or (memq (car ret) variants)
1415 ;; (get-char-attribute (car ret) '<-subsumptive)
1416 (setq rest (nconc rest (list (car ret)))))
1417 (setq ret (cdr ret)))))))
1418 (setq rest (cdr rest)))))
1420 (defun insert-char-range-data (min max &optional script excluded-script)
1423 (while (<= code max)
1424 (setq char (decode-char '=ucs code))
1425 (if (encode-char char '=ucs 'defined-only)
1426 (insert-char-data-with-variant char nil 'no-ucs-unified
1427 script excluded-script))
1428 (setq code (1+ code)))))
1430 (defun write-char-range-data-to-file (min max file
1431 &optional script excluded-script)
1432 (let ((coding-system-for-write char-db-file-coding-system))
1434 (insert (format ";; -*- coding: %s -*-\n"
1435 char-db-file-coding-system))
1436 (insert-char-range-data min max script excluded-script)
1437 (write-region (point-min)(point-max) file))))
1439 (defvar what-character-original-window-configuration)
1442 (defun what-char-definition (char)
1443 (interactive (list (char-after)))
1444 (let ((buf (get-buffer-create "*Character Description*"))
1445 (the-buf (current-buffer))
1446 (win-conf (current-window-configuration)))
1448 (make-local-variable 'what-character-original-window-configuration)
1449 (setq what-character-original-window-configuration win-conf)
1450 (setq buffer-read-only nil)
1454 (insert-char-data-with-variant char 'printable)
1455 (unless (char-attribute-alist char)
1456 (insert (format ";; = %c\n"
1457 (let* ((rest (split-char char))
1461 (setq code (logior (lsh code 8)
1463 (decode-char ccs code)))))
1464 ;; (char-db-update-comment)
1465 (set-buffer-modified-p nil)
1466 (view-mode the-buf (lambda (buf)
1467 (set-window-configuration
1468 what-character-original-window-configuration)
1470 (goto-char (point-min)))
1472 (set-window-configuration
1473 what-character-original-window-configuration)
1474 (signal (car err) (cdr err)))))))
1480 (provide 'char-db-util)
1482 ;;; char-db-util.el ends here