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, 2014 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
593 =shinjigen@1ed ==shinjigen@1ed
594 =shinjigen@rev ==shinjigen@rev
595 =shinjigen/+p@rev ==shinjigen/+p@rev
597 =daikanwa/ho =>>daikanwa/ho =>daikanwa/ho))
598 "(%-18s . %04d)\t; %c")
599 ((eq name '=shinjigen@1ed/24pr)
600 "(%-18s . %04d)\t; %c")
601 ((or (memq name '(==daikanwa
602 =daikanwa =>>daikanwa =>daikanwa
603 =daikanwa@rev1 =daikanwa@rev2
604 =daikanwa/+p ==daikanwa/+p =>>daikanwa/+p
605 =daikanwa/+2p =>>daikanwa/+2p
608 =gt-k ==gt-k =>>gt-k =>gt-k
609 =adobe-japan1-0 ==adobe-japan1-0 ; =>>>adobe-japan1-0
610 =adobe-japan1-1 ==adobe-japan1-1 ; =>>>adobe-japan1-1
611 =adobe-japan1-2 ==adobe-japan1-2 ; =>>>adobe-japan1-2
612 =adobe-japan1-3 ==adobe-japan1-3 ; =>>>adobe-japan1-3
613 =adobe-japan1-4 ==adobe-japan1-4 ; =>>>adobe-japan1-4
614 =adobe-japan1-5 ==adobe-japan1-5 ; =>>>adobe-japan1-5
615 =adobe-japan1-6 ==adobe-japan1-6 ; =>>>adobe-japan1-6
616 =>>adobe-japan1-0 =+>adobe-japan1-0
617 =>>adobe-japan1-1 =+>adobe-japan1-1
618 =>>adobe-japan1-2 =+>adobe-japan1-2
619 =>>adobe-japan1-3 =+>adobe-japan1-3
620 =>>adobe-japan1-4 =+>adobe-japan1-4
621 =>>adobe-japan1-5 =+>adobe-japan1-5
622 =>>adobe-japan1-6 =+>adobe-japan1-6
624 =zinbun-oracle =>zinbun-oracle))
625 ;; (string-match "^=adobe-" (symbol-name name))
627 "(%-18s . %05d)\t; %c")
628 ((memq name '(=hanyo-denshi/ks
629 ==hanyo-denshi/ks ; =>>>hanyo-denshi/ks
633 "(%-18s . %06d)\t; %c")
634 ((>= (charset-dimension name) 2)
635 "(%-18s . #x%04X)\t; %c")
637 "(%-18s . #x%02X)\t; %c"))
639 (if (= (charset-iso-graphic-plane name) 1)
641 (cond ((= (charset-dimension name) 1)
643 ((= (charset-dimension name) 2)
645 ((= (charset-dimension name) 3)
649 (char-db-decode-isolated-char name value)))
650 (if (and (= (charset-chars name) 94)
651 (= (charset-dimension name) 2))
652 (insert (format " [%02d-%02d]"
653 (- (lsh value -8) 32)
654 (- (logand value 255) 32))))
657 (insert (format "(%-18s . %s)" name value))
659 (insert line-breaking))
661 (defun char-db-insert-relation-feature (char name value line-breaking
663 (insert (format "(%-18s%s " name line-breaking))
664 (let ((lbs (concat "\n" (make-string (current-column) ?\ )))
665 separator cell sources required-features
668 (setq cell (car value))
670 (setq cell (decode-char '=ucs cell)))
672 ((eq name '->subsumptive)
673 (when (or (not (some (lambda (atr)
674 (get-char-attribute cell atr))
675 char-db-ignored-attributes))
677 (encode-char cell ccs 'defined-only))
681 (let ((char-db-ignored-attributes
683 char-db-ignored-attributes)))
684 (insert-char-attributes cell readable nil nil 'for-sub-node))
685 (setq separator lbs))
690 char (intern (format "%s*sources" name))))
691 (setq required-features nil)
692 (dolist (source sources)
696 shinjigen shinjigen@1ed shinjigen@rev))
697 (setq required-features
698 (union required-features
710 =shinjigen/+p@rev))))
712 (setq required-features
713 (union required-features
718 ((find-charset (setq ret (intern (format "=%s" source))))
719 (setq required-features
720 (cons ret required-features)))
721 (t (setq required-features
722 (cons source required-features)))))
723 (cond ((string-match "@JP" (symbol-name name))
724 (setq required-features
725 (union required-features
733 ((string-match "@CN" (symbol-name name))
734 (setq required-features
735 (union required-features
742 (insert (format "%S" cell))
743 (char-db-insert-char-spec cell readable
746 (setq separator lbs))
750 (if (consp (car cell))
751 (char-db-insert-char-spec cell readable)
752 (char-db-insert-char-reference cell readable))
753 (setq separator lbs))
757 (insert (prin1-to-string cell))
758 (setq separator " ")))
759 (setq value (cdr value)))
761 (insert line-breaking)))
763 (defun insert-char-attributes (char &optional readable attributes column
766 (setq column (current-column)))
767 (let (name value ; has-long-ccs-name
771 (concat "\n" (make-string (1+ column) ?\ )))
772 lbs cell separator ret
774 dest-ccss ; sources required-features
779 (if (consp attributes)
781 (dolist (name attributes)
782 (unless (memq name char-db-ignored-attributes)
783 (if (find-charset name)
787 (dolist (name (char-attribute-list))
788 (unless (memq name char-db-ignored-attributes)
789 (if (find-charset name)
793 #'char-attribute-name<)))
795 (when (memq '<-subsumptive attributes)
796 (when (or readable (not for-sub-node))
797 (when (setq value (get-char-attribute char '<-subsumptive))
798 (char-db-insert-relation-feature char '<-subsumptive value
801 (setq attributes (delq '<-subsumptive attributes)))
802 (when (and (memq '<-denotational attributes)
803 (setq value (get-char-attribute char '<-denotational)))
804 (char-db-insert-relation-feature char '<-denotational value
807 (setq attributes (delq '<-denotational attributes)))
808 (when (and (memq 'name attributes)
809 (setq value (get-char-attribute char 'name)))
811 (if (> (+ (current-column) (length value)) 48)
814 value line-breaking))
815 (setq attributes (delq 'name attributes))
817 (when (and (memq 'name* attributes)
818 (setq value (get-char-attribute char 'name*)))
820 (if (> (+ (current-column) (length value)) 48)
823 value line-breaking))
824 (setq attributes (delq 'name* attributes))
826 (when (and (memq 'script attributes)
827 (setq value (get-char-attribute char 'script)))
828 (insert (format "(script\t\t%s)%s"
829 (mapconcat (function prin1-to-string)
832 (setq attributes (delq 'script attributes))
834 (dolist (name '(=>ucs =>ucs*))
835 (when (and (memq name attributes)
836 (setq value (get-char-attribute char name)))
837 (insert (format "(%-18s . #x%04X)\t; %c%s"
838 name value (decode-char '=ucs value)
840 (setq attributes (delq name attributes))))
841 (dolist (name '(=>ucs@gb =>ucs@big5))
842 (when (and (memq name attributes)
843 (setq value (get-char-attribute char name)))
844 (insert (format "(%-18s . #x%04X)\t; %c%s"
849 (symbol-name name) 2)))
852 (setq attributes (delq name attributes))
854 ;; (dolist (name '(=>daikanwa))
855 ;; (when (and (memq name attributes)
856 ;; (setq value (get-char-attribute char name)))
858 ;; (if (integerp value)
859 ;; (format "(%-18s . %05d)\t; %c%s"
860 ;; name value (decode-char '=daikanwa value)
862 ;; (format "(%-18s %s)\t; %c%s"
864 ;; (mapconcat (function prin1-to-string)
866 ;; (char-representative-of-daikanwa char)
868 ;; (setq attributes (delq name attributes))))
869 (when (and (memq 'general-category attributes)
870 (setq value (get-char-attribute char 'general-category)))
872 "(general-category\t%s) ; %s%s"
873 (mapconcat (lambda (cell)
876 (cond ((rassoc value unidata-normative-category-alist)
877 "Normative Category")
878 ((rassoc value unidata-informative-category-alist)
879 "Informative Category")
883 (setq attributes (delq 'general-category attributes))
885 (when (and (memq 'bidi-category attributes)
886 (setq value (get-char-attribute char 'bidi-category)))
887 (insert (format "(bidi-category\t. %S)%s"
890 (setq attributes (delq 'bidi-category attributes))
892 (unless (or (not (memq 'mirrored attributes))
893 (eq (setq value (get-char-attribute char 'mirrored 'empty))
895 (insert (format "(mirrored\t\t. %S)%s"
898 (setq attributes (delq 'mirrored attributes))
901 ((and (memq 'decimal-digit-value attributes)
902 (setq value (get-char-attribute char 'decimal-digit-value)))
903 (insert (format "(decimal-digit-value . %S)%s"
906 (setq attributes (delq 'decimal-digit-value attributes))
907 (when (and (memq 'digit-value attributes)
908 (setq value (get-char-attribute char 'digit-value)))
909 (insert (format "(digit-value\t . %S)%s"
912 (setq attributes (delq 'digit-value attributes))
914 (when (and (memq 'numeric-value attributes)
915 (setq value (get-char-attribute char 'numeric-value)))
916 (insert (format "(numeric-value\t . %S)%s"
919 (setq attributes (delq 'numeric-value attributes))
923 (when (and (memq 'digit-value attributes)
924 (setq value (get-char-attribute char 'digit-value)))
925 (insert (format "(digit-value\t. %S)%s"
928 (setq attributes (delq 'digit-value attributes))
930 (when (and (memq 'numeric-value attributes)
931 (setq value (get-char-attribute char 'numeric-value)))
932 (insert (format "(numeric-value\t. %S)%s"
935 (setq attributes (delq 'numeric-value attributes))
937 (when (and (memq 'iso-10646-comment attributes)
938 (setq value (get-char-attribute char 'iso-10646-comment)))
939 (insert (format "(iso-10646-comment\t. %S)%s"
942 (setq attributes (delq 'iso-10646-comment attributes))
944 (when (and (memq 'morohashi-daikanwa attributes)
945 (setq value (get-char-attribute char 'morohashi-daikanwa)))
946 (insert (format "(morohashi-daikanwa\t%s)%s"
947 (mapconcat (function prin1-to-string) value " ")
949 (setq attributes (delq 'morohashi-daikanwa attributes))
953 (when (and (memq 'ideographic-radical attributes)
954 (setq value (get-char-attribute char 'ideographic-radical)))
956 (insert (format "(ideographic-radical . %S)\t; %c%s"
958 (ideographic-radical radical)
960 (setq attributes (delq 'ideographic-radical attributes))
962 (when (and (memq 'shuowen-radical attributes)
963 (setq value (get-char-attribute char 'shuowen-radical)))
964 (insert (format "(shuowen-radical\t. %S)\t; %c%s"
966 (shuowen-radical value)
968 (setq attributes (delq 'shuowen-radical attributes))
973 char-db-feature-domains
975 (dolist (feature (char-attribute-list))
976 (setq feature (symbol-name feature))
978 "\\(radical\\|strokes\\)@\\([^@*]+\\)\\(\\*\\|$\\)"
980 (setq domain (intern (match-string 2 feature)))
981 (unless (memq domain dest)
982 (setq dest (cons domain dest)))))
983 (sort dest #'string<))))
984 (setq key (intern (format "%s@%s" 'ideographic-radical domain)))
985 (when (and (memq key attributes)
986 (setq value (get-char-attribute char key)))
988 (insert (format "(%s . %S)\t; %c%s"
991 (ideographic-radical radical)
993 (setq attributes (delq key attributes))
995 (setq key (intern (format "%s@%s" 'ideographic-strokes domain)))
996 (when (and (memq key attributes)
997 (setq value (get-char-attribute char key)))
999 (insert (format "(%s . %S)%s"
1003 (setq attributes (delq key attributes))
1005 (setq key (intern (format "%s@%s" 'total-strokes domain)))
1006 (when (and (memq key attributes)
1007 (setq value (get-char-attribute char key)))
1008 (insert (format "(%s . %S)%s"
1012 (setq attributes (delq key attributes))
1014 (dolist (feature '(ideographic-radical
1017 (setq key (intern (format "%s@%s*sources" feature domain)))
1018 (when (and (memq key attributes)
1019 (setq value (get-char-attribute char key)))
1020 (insert (format "(%s%s" key line-breaking))
1021 (dolist (cell value)
1022 (insert (format " %s" cell)))
1024 (insert line-breaking)
1025 (setq attributes (delq key attributes))
1028 (when (and (memq 'ideographic-strokes attributes)
1029 (setq value (get-char-attribute char 'ideographic-strokes)))
1030 (setq strokes value)
1031 (insert (format "(ideographic-strokes . %S)%s"
1034 (setq attributes (delq 'ideographic-strokes attributes))
1036 (when (and (memq 'kangxi-radical attributes)
1037 (setq value (get-char-attribute char 'kangxi-radical)))
1038 (unless (eq value radical)
1039 (insert (format "(kangxi-radical\t . %S)\t; %c%s"
1041 (ideographic-radical value)
1044 (setq radical value)))
1045 (setq attributes (delq 'kangxi-radical attributes))
1047 (when (and (memq 'kangxi-strokes attributes)
1048 (setq value (get-char-attribute char 'kangxi-strokes)))
1049 (unless (eq value strokes)
1050 (insert (format "(kangxi-strokes\t . %S)%s"
1054 (setq strokes value)))
1055 (setq attributes (delq 'kangxi-strokes attributes))
1057 (when (and (memq 'japanese-radical attributes)
1058 (setq value (get-char-attribute char 'japanese-radical)))
1059 (unless (eq value radical)
1060 (insert (format "(japanese-radical\t . %S)\t; %c%s"
1062 (ideographic-radical value)
1065 (setq radical value)))
1066 (setq attributes (delq 'japanese-radical attributes))
1068 (when (and (memq 'japanese-strokes attributes)
1069 (setq value (get-char-attribute char 'japanese-strokes)))
1070 (unless (eq value strokes)
1071 (insert (format "(japanese-strokes\t . %S)%s"
1075 (setq strokes value)))
1076 (setq attributes (delq 'japanese-strokes attributes))
1078 (when (and (memq 'cns-radical attributes)
1079 (setq value (get-char-attribute char 'cns-radical)))
1080 (insert (format "(cns-radical\t . %S)\t; %c%s"
1082 (ideographic-radical value)
1084 (setq attributes (delq 'cns-radical attributes))
1086 (when (and (memq 'cns-strokes attributes)
1087 (setq value (get-char-attribute char 'cns-strokes)))
1088 (unless (eq value strokes)
1089 (insert (format "(cns-strokes\t . %S)%s"
1093 (setq strokes value)))
1094 (setq attributes (delq 'cns-strokes attributes))
1096 ;; (when (and (memq 'shinjigen-1-radical attributes)
1097 ;; (setq value (get-char-attribute char 'shinjigen-1-radical)))
1098 ;; (unless (eq value radical)
1099 ;; (insert (format "(shinjigen-1-radical . %S)\t; %c%s"
1101 ;; (ideographic-radical value)
1104 ;; (setq radical value)))
1105 ;; (setq attributes (delq 'shinjigen-1-radical attributes))
1107 (when (and (memq 'ideographic- attributes)
1108 (setq value (get-char-attribute char 'ideographic-)))
1109 (insert "(ideographic- ")
1110 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1112 (while (consp value)
1113 (setq cell (car value))
1115 (setq cell (decode-char '=ucs cell)))
1116 (cond ((characterp cell)
1120 (insert (format "%S" cell))
1121 (char-db-insert-char-spec cell readable))
1122 (setq separator lbs))
1126 (if (consp (car cell))
1127 (char-db-insert-char-spec cell readable)
1128 (char-db-insert-char-reference cell readable))
1129 (setq separator lbs))
1133 (insert (prin1-to-string cell))
1134 (setq separator " ")))
1135 (setq value (cdr value)))
1137 (insert line-breaking)
1138 (setq attributes (delq 'ideographic- attributes)))
1139 (when (and (memq 'total-strokes attributes)
1140 (setq value (get-char-attribute char 'total-strokes)))
1141 (insert (format "(total-strokes . %S)%s"
1144 (setq attributes (delq 'total-strokes attributes))
1146 (when (and (memq '->ideograph attributes)
1147 (setq value (get-char-attribute char '->ideograph)))
1148 (insert (format "(->ideograph\t%s)%s"
1149 (mapconcat (lambda (code)
1150 (cond ((symbolp code)
1153 (format "#x%04X" code))
1156 line-breaking code))))
1159 (setq attributes (delq '->ideograph attributes))
1161 ;; (when (and (memq '->decomposition attributes)
1162 ;; (setq value (get-char-attribute char '->decomposition)))
1163 ;; (insert (format "(->decomposition\t%s)%s"
1164 ;; (mapconcat (lambda (code)
1165 ;; (cond ((symbolp code)
1166 ;; (symbol-name code))
1167 ;; ((characterp code)
1169 ;; (format "%S" code)
1174 ;; (format "#x%04X" code))
1176 ;; (format "%s%S" line-breaking code))))
1179 ;; (setq attributes (delq '->decomposition attributes))
1181 (if (equal (get-char-attribute char '->titlecase)
1182 (get-char-attribute char '->uppercase))
1183 (setq attributes (delq '->titlecase attributes)))
1184 (when (and (memq '->mojikyo attributes)
1185 (setq value (get-char-attribute char '->mojikyo)))
1186 (insert (format "(->mojikyo\t\t. %06d)\t; %c%s"
1187 value (decode-char 'mojikyo value)
1189 (setq attributes (delq '->mojikyo attributes))
1191 (when (and (memq 'hanyu-dazidian-vol attributes)
1192 (setq value (get-char-attribute char 'hanyu-dazidian-vol)))
1193 (insert (format "(hanyu-dazidian-vol . %d)%s"
1194 value line-breaking))
1195 (setq attributes (delq 'hanyu-dazidian-vol attributes))
1197 (when (and (memq 'hanyu-dazidian-page attributes)
1198 (setq value (get-char-attribute char 'hanyu-dazidian-page)))
1199 (insert (format "(hanyu-dazidian-page . %d)%s"
1200 value line-breaking))
1201 (setq attributes (delq 'hanyu-dazidian-page attributes))
1203 (when (and (memq 'hanyu-dazidian-char attributes)
1204 (setq value (get-char-attribute char 'hanyu-dazidian-char)))
1205 (insert (format "(hanyu-dazidian-char . %d)%s"
1206 value line-breaking))
1207 (setq attributes (delq 'hanyu-dazidian-char attributes))
1210 (dolist (ignored '(composition
1211 ->denotational <-subsumptive ->ucs-unified
1212 ->ideographic-component-forms))
1213 (setq attributes (delq ignored attributes))))
1215 (setq name (car attributes))
1216 (unless (eq (setq value (get-char-attribute char name 'value-is-empty))
1218 (cond ((setq ret (find-charset name))
1219 (setq name (charset-name ret))
1220 (when (not (memq name dest-ccss))
1221 (setq dest-ccss (cons name dest-ccss))
1222 (char-db-insert-ccs-feature name value line-breaking))
1224 ((string-match "^=>ucs@" (symbol-name name))
1225 (insert (format "(%-18s . #x%04X)\t; %c%s"
1226 name value (decode-char '=ucs value)
1229 ((eq name 'jisx0208-1978/4X)
1230 (insert (format "(%-18s . #x%04X)%s"
1236 (not (eq name '->subsumptive))
1237 (not (eq name '->uppercase))
1238 (not (eq name '->lowercase))
1239 (not (eq name '->titlecase))
1240 (not (eq name '->canonical))
1241 (not (eq name '->Bopomofo))
1242 (not (eq name '->mistakable))
1243 (not (eq name '->ideographic-variants))
1244 (null (get-char-attribute
1245 char (intern (format "%s*sources" name))))
1246 (not (string-match "\\*sources$" (symbol-name name)))
1247 (null (get-char-attribute
1248 char (intern (format "%s*note" name))))
1249 (not (string-match "\\*note$" (symbol-name name)))
1250 (or (eq name '<-identical)
1251 (eq name '<-uppercase)
1252 (eq name '<-lowercase)
1253 (eq name '<-titlecase)
1254 (eq name '<-canonical)
1255 (eq name '<-ideographic-variants)
1256 ;; (eq name '<-synonyms)
1257 (string-match "^<-synonyms" (symbol-name name))
1258 (eq name '<-mistakable)
1259 (when (string-match "^->" (symbol-name name))
1261 ((string-match "^->fullwidth" (symbol-name name))
1262 (not (and (consp value)
1263 (characterp (car value))
1265 (car value) '=ucs 'defined-only)))
1270 ((or (eq name 'ideographic-structure)
1271 (eq name 'ideographic-combination)
1272 (eq name 'ideographic-)
1273 (eq name '=decomposition)
1274 (char-feature-base-name= '=decomposition name)
1275 (char-feature-base-name= '=>decomposition name)
1276 ;; (string-match "^=>*decomposition\\(@[^*]+\\)?$"
1277 ;; (symbol-name name))
1278 (string-match "^\\(->\\|<-\\)[^*]*$" (symbol-name name))
1279 (string-match "^\\(->\\|<-\\)[^*]*\\*sources$"
1282 (char-db-insert-relation-feature char name value
1285 ((memq name '(ideograph=
1286 original-ideograph-of
1287 ancient-ideograph-of
1290 ;; simplified-ideograph-of
1291 ideographic-variants
1292 ;; ideographic-different-form-of
1294 (insert (format "(%-18s%s " name line-breaking))
1295 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1297 (while (consp value)
1298 (setq cell (car value))
1299 (if (and (consp cell)
1304 (char-db-insert-alist cell readable)
1305 (setq separator lbs))
1308 (insert (prin1-to-string cell))
1309 (setq separator " "))
1310 (setq value (cdr value)))
1312 (insert line-breaking))
1314 (insert (format "(%-18s " name))
1315 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1317 (while (consp value)
1318 (setq cell (car value))
1319 (if (and (consp cell)
1321 (setq ret (condition-case nil
1329 (setq key (car (car rest)))
1330 (if (find-charset key)
1331 (setq cal (cons key cal))
1332 (setq al (cons key al)))
1333 (setq rest (cdr rest)))
1336 (insert-char-attributes ret
1340 (setq separator lbs))
1341 (setq ret (prin1-to-string cell))
1343 (if (< (+ (current-column)
1350 (setq separator " "))
1351 (setq value (cdr value)))
1353 (insert line-breaking))
1355 (insert (format "(%-18s" name))
1356 (setq ret (prin1-to-string value))
1357 (unless (< (+ (current-column)
1361 (insert line-breaking))
1362 (insert " . " ret ")" line-breaking)
1363 ;; (insert (format "(%-18s . %S)%s"
1368 (setq attributes (cdr attributes)))
1371 (defun insert-char-data (char &optional readable
1374 (narrow-to-region (point)(point))
1375 (insert "(define-char
1377 (insert-char-attributes char readable attributes)
1379 (goto-char (point-min))
1380 (while (re-search-forward "[ \t]+$" nil t)
1383 (goto-char (point-min))
1384 (while (re-search-forward "[ \t][ \t][ \t]*" nil t)
1385 (let ((column (current-column))
1386 (indent-tabs-mode t))
1387 (delete-region (match-beginning 0) (point))
1388 (indent-to column)))
1389 (goto-char (point-max))
1390 ;; (tabify (point-min)(point-max))
1393 (defun insert-char-data-with-variant (char &optional printable
1395 script excluded-script)
1396 (insert-char-data char printable)
1397 (let ((variants (char-variants char))
1400 (setq variants (sort variants #'<))
1401 (setq rest variants)
1402 (setq variants (cons char variants))
1404 (setq variant (car rest))
1405 (unless (get-char-attribute variant '<-subsumptive)
1406 (if (and (or (null script)
1407 (null (setq vs (get-char-attribute variant 'script)))
1409 (or (null excluded-script)
1410 (null (setq vs (get-char-attribute variant 'script)))
1411 (not (memq excluded-script vs))))
1412 (unless (and no-ucs-unified (get-char-attribute variant '=ucs))
1413 (insert-char-data variant printable)
1414 (if (setq ret (char-variants variant))
1416 (or (memq (car ret) variants)
1417 ;; (get-char-attribute (car ret) '<-subsumptive)
1418 (setq rest (nconc rest (list (car ret)))))
1419 (setq ret (cdr ret)))))))
1420 (setq rest (cdr rest)))))
1422 (defun insert-char-range-data (min max &optional script excluded-script)
1425 (while (<= code max)
1426 (setq char (decode-char '=ucs code))
1427 (if (encode-char char '=ucs 'defined-only)
1428 (insert-char-data-with-variant char nil 'no-ucs-unified
1429 script excluded-script))
1430 (setq code (1+ code)))))
1432 (defun write-char-range-data-to-file (min max file
1433 &optional script excluded-script)
1434 (let ((coding-system-for-write char-db-file-coding-system))
1436 (insert (format ";; -*- coding: %s -*-\n"
1437 char-db-file-coding-system))
1438 (insert-char-range-data min max script excluded-script)
1439 (write-region (point-min)(point-max) file))))
1441 (defvar what-character-original-window-configuration)
1444 (defun what-char-definition (char)
1445 (interactive (list (char-after)))
1446 (let ((buf (get-buffer-create "*Character Description*"))
1447 (the-buf (current-buffer))
1448 (win-conf (current-window-configuration)))
1450 (make-local-variable 'what-character-original-window-configuration)
1451 (setq what-character-original-window-configuration win-conf)
1452 (setq buffer-read-only nil)
1456 (insert-char-data-with-variant char 'printable)
1457 (unless (char-attribute-alist char)
1458 (insert (format ";; = %c\n"
1459 (let* ((rest (split-char char))
1463 (setq code (logior (lsh code 8)
1465 (decode-char ccs code)))))
1466 ;; (char-db-update-comment)
1467 (set-buffer-modified-p nil)
1468 (view-mode the-buf (lambda (buf)
1469 (set-window-configuration
1470 what-character-original-window-configuration)
1472 (goto-char (point-min)))
1474 (set-window-configuration
1475 what-character-original-window-configuration)
1476 (signal (car err) (cdr err)))))))
1482 (provide 'char-db-util)
1484 ;;; char-db-util.el ends here