1 ;;; char-db-util.el --- Character Database utility -*- coding: utf-8-er; -*-
3 ;; Copyright (C) 1998,1999,2000,2001,2002,2003,2004,2005,2006,2007,
4 ;; 2008,2009,2010,2011,2012,2013,2014,2015,2016,2017 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
98 ?裘 ?老 ?毛 ?毳 ?尸 ?尺 ?尾 ?履 ?舟 ?方 ; 310
99 ?儿 ?兄 ?兂 ?皃 ?𠑹 ?先 ?秃 ?見 ?覞 ?欠 ; 320
100 ?㱃 ?㳄 ?旡 ?頁 ?𦣻 ?面 ?丏 ?首 ?𥄉 ?須 ; 330
101 ?彡 ?彣 ?文 ?髟 ?后 ?司 ?卮 ?卩 ?印 ?色 ; 340
102 ?𠨍 ?辟 ?勹 ?包 ?茍 ?鬼 ?甶 ?厶 ?嵬 ?山 ; 350
103 ?屾 ?屵 ?广 ?厂 ?丸 ?危 ?石 ?長 ?勿 ?冄 ; 360
104 ?而 ?豕 ?㣇 ?彑 ?豚 ?豸 ?𤉡 ?易 ?象 ?馬 ; 370
105 ?𢊁 ?鹿 ?麤 ?㲋 ?兔 ?萈 ?犬 ?㹜 ?鼠 ?能 ; 380
106 ?熊 ?火 ?炎 ?黑 ?囪 ?焱 ?炙 ?赤 ?大 ?亦 ; 390
109 (defun shuowen-radical (number)
110 (aref shuowen-radicals (1- number)))
112 (defvar char-db-file-coding-system 'utf-8-mcs-er)
114 (defvar char-db-ignored-attributes '(ideographic-products))
116 (defvar char-db-coded-charset-priority-list
214 ;; =>>>adobe-japan1-0
215 ;; =>>>adobe-japan1-1
216 ;; =>>>adobe-japan1-2
217 ;; =>>>adobe-japan1-3
218 ;; =>>>adobe-japan1-4
219 ;; =>>>adobe-japan1-5
220 ;; =>>>adobe-japan1-6
224 ;; =>>>hanyo-denshi/ja
225 ;; =>>>hanyo-denshi/jb
226 ;; =>>>hanyo-denshi/jc
227 ;; =>>>hanyo-denshi/ft
228 ;; =>>>hanyo-denshi/ib
229 ;; =>>>hanyo-denshi/hg
230 ;; =>>>hanyo-denshi/jt
231 ;; =>>>hanyo-denshi/ks
349 =>big5-cdp-itaiji-001
362 ;;; @ char-db formatters
365 (defun char-db-make-char-spec (char)
367 (cond ((characterp char)
368 (cond ((and (setq ret (encode-char char '=ucs 'defined-only))
369 (not (and (<= #xE000 ret)(<= ret #xF8FF))))
370 (setq char-spec (list (cons '=ucs ret)))
371 (cond ((setq ret (get-char-attribute char 'name))
372 (setq char-spec (cons (cons 'name ret) char-spec))
374 ((setq ret (get-char-attribute char 'name*))
375 (setq char-spec (cons (cons 'name* ret) char-spec))
378 ((encode-char char '=mj 'defined-only)
380 (dolist (ccs (charset-list))
381 (if (and (or (eq ccs '=mj)
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 ((encode-char char '==mj 'defined-only)
392 (dolist (ccs (charset-list))
393 (if (and (or (eq ccs '==mj)
394 ;; (eq (charset-property ccs 'iso-ir) 177)
395 (string-match "=ucs@" (symbol-name ccs))
397 (setq ccs (charset-name ccs))
398 (null (assq ccs char-spec))
399 (setq ret (encode-char char ccs 'defined-only)))
400 (setq char-spec (cons (cons ccs ret) char-spec))))
402 ((encode-char char '=adobe-japan1 'defined-only)
404 (dolist (ccs (charset-list))
405 (if (and (or (memq ccs
414 ;; (eq (charset-property ccs 'iso-ir) 177)
415 (string-match "=ucs@" (symbol-name ccs))
417 (setq ccs (charset-name ccs))
418 (null (assq ccs char-spec))
419 (setq ret (encode-char char ccs 'defined-only)))
420 (setq char-spec (cons (cons ccs ret) char-spec))))
422 ((encode-char char '==adobe-japan1 'defined-only)
424 (dolist (ccs (charset-list))
425 (if (and (or (memq ccs
434 ;; (eq (charset-property ccs 'iso-ir) 177)
435 (string-match "=ucs@" (symbol-name ccs))
437 (setq ccs (charset-name ccs))
438 (null (assq ccs char-spec))
439 (setq ret (encode-char char ccs 'defined-only)))
440 (setq char-spec (cons (cons ccs ret) char-spec))))
444 (let ((rest char-db-coded-charset-priority-list)
447 (setq ccs (charset-name
448 (find-charset (car rest))))
450 (encode-char char ccs
452 (throw 'tag (cons ccs ret)))
453 (setq rest (cdr rest))))))
454 (setq char-spec (list ret))
455 (dolist (ccs (delq (car ret) (charset-list)))
456 (if (and (or (charset-iso-final-char ccs)
463 (eq (charset-property ccs 'iso-ir) 177)
464 ;; (string-match "=ucs@" (symbol-name ccs))
466 (setq ccs (charset-name ccs))
467 (null (assq ccs char-spec))
468 (setq ret (encode-char char ccs 'defined-only)))
469 (setq char-spec (cons (cons ccs ret) char-spec))))
471 (setq char-spec (split-char char)))
472 (cond ((setq ret (get-char-attribute char 'name))
473 (setq char-spec (cons (cons 'name ret) char-spec))
475 ((setq ret (get-char-attribute char 'name*))
476 (setq char-spec (cons (cons 'name* ret) char-spec))
479 ((setq ret (get-char-attribute
480 char 'ideographic-combination))
482 (cons (cons 'ideographic-combination ret)
489 (defun char-db-insert-char-spec (char &optional readable column
492 (setq column (current-column)))
493 (let (char-spec temp-char)
494 (setq char-spec (char-db-make-char-spec char))
495 (unless (or (characterp char) ; char
497 (setq char (find-char char-spec))
499 ;; define temporary character
500 ;; Current implementation is dirty.
501 (setq temp-char (define-char (cons '(ideograph-daikanwa . 0)
503 (remove-char-attribute temp-char 'ideograph-daikanwa)
504 (setq char temp-char))
505 (insert-char-attributes char
507 (union (mapcar #'car char-spec)
511 ;; undefine temporary character
512 ;; Current implementation is dirty.
513 (setq char-spec (char-attribute-alist temp-char))
515 (remove-char-attribute temp-char (car (car char-spec)))
516 (setq char-spec (cdr char-spec))))))
518 (defun char-db-insert-alist (alist &optional readable column)
520 (setq column (current-column)))
522 (concat "\n" (make-string (1+ column) ?\ )))
526 lbs cell rest separator)
529 (setq name (car (car alist))
530 value (cdr (car alist)))
531 (cond ((eq name 'char)
533 (if (setq ret (condition-case nil
541 (setq key (car (car value)))
542 ;; (if (find-charset key)
543 ;; (setq cal (cons key cal))
544 (setq al (cons key al))
546 (setq value (cdr value)))
547 (insert-char-attributes ret
551 (insert (prin1-to-string value)))
553 (insert line-breaking))
555 (insert (format "(%-18s " name))
556 (setq lbs (concat "\n" (make-string (current-column) ?\ )))
558 (setq cell (car value))
559 (if (and (consp cell)
561 (setq ret (condition-case nil
571 (setq key (car (car rest)))
572 ;; (if (find-charset key)
573 ;; (setq cal (cons key cal))
574 (setq al (cons key al))
576 (setq rest (cdr rest)))
579 (insert-char-attributes ret
583 (setq separator lbs))
586 (insert (prin1-to-string cell))
587 (setq separator " "))
588 (setq value (cdr value)))
590 (insert line-breaking))
592 (insert (format "(%-18s . %S)%s"
595 (setq alist (cdr alist))))
598 (defun char-db-insert-char-reference (plist &optional readable column)
600 (setq column (current-column)))
602 (concat "\n" (make-string (1+ column) ?\ )))
607 (setq name (pop plist))
608 (setq value (pop plist))
609 (cond ((eq name :char)
612 (cond ((numberp value)
613 (setq value (decode-char '=ucs value)))
615 ;; (setq value (or (find-char value)
618 (char-db-insert-char-spec value readable)
619 (insert line-breaking)
622 (insert (format "%s%s\t%d ; %c%s"
625 (ideographic-radical value)
629 (insert (format "%s%s\t%S" separator name value))
630 (setq separator line-breaking)))
634 (defun char-db-decode-isolated-char (ccs code-point)
637 (cond ((eq ccs 'arabic-iso8859-6)
638 (decode-char ccs code-point))
640 ;; (decode-builtin-char '==gt code-point))
641 ((and (memq ccs '(=gt-pj-1
652 (setq ret (decode-char ccs code-point))
653 (setq ret (encode-char ret '=gt 'defined-only)))
654 (decode-builtin-char '=gt ret))
656 (decode-builtin-char ccs code-point))))
658 (or (decode-char ccs code-point)
659 (define-char (list (cons ccs code-point)))))
660 ((and (<= 0 (char-int ret))
661 (<= (char-int ret) #x1F))
662 (decode-char '=ucs (+ #x2400 (char-int ret))))
663 ((= (char-int ret) #x7F)
667 (defvar char-db-convert-obsolete-format t)
669 (defun char-db-insert-ccs-feature (name value line-breaking)
675 ((memq name '(=>iwds-1
678 =shinjigen@1ed ==shinjigen@1ed
679 =shinjigen@rev ==shinjigen@rev
680 =shinjigen/+p@rev ==shinjigen/+p@rev
681 ===daikanwa/ho ==daikanwa/ho
682 =daikanwa/ho =>>daikanwa/ho =>daikanwa/ho))
683 "(%-18s . %04d)\t; %c")
684 ((eq name '=shinjigen@1ed/24pr)
685 "(%-18s . %04d)\t; %c")
689 ==daikanwa =daikanwa =>>daikanwa =>daikanwa
690 =daikanwa@rev1 =daikanwa@rev2
691 =daikanwa/+p ==daikanwa/+p ===daikanwa/+p
693 =daikanwa/+2p =>>daikanwa/+2p
698 =adobe-japan1-0 ==adobe-japan1-0 ===adobe-japan1-0
699 =adobe-japan1-1 ==adobe-japan1-1 ===adobe-japan1-1
700 =adobe-japan1-2 ==adobe-japan1-2 ===adobe-japan1-2
701 =adobe-japan1-3 ==adobe-japan1-3 ===adobe-japan1-3
702 =adobe-japan1-4 ==adobe-japan1-4 ===adobe-japan1-4
703 =adobe-japan1-5 ==adobe-japan1-5 ===adobe-japan1-5
704 =adobe-japan1-6 ==adobe-japan1-6 ===adobe-japan1-6
705 =>>adobe-japan1-0 =+>adobe-japan1-0
706 =>>adobe-japan1-1 =+>adobe-japan1-1
707 =>>adobe-japan1-2 =+>adobe-japan1-2
708 =>>adobe-japan1-3 =+>adobe-japan1-3
709 =>>adobe-japan1-4 =+>adobe-japan1-4
710 =>>adobe-japan1-5 =+>adobe-japan1-5
711 =>>adobe-japan1-6 =+>adobe-japan1-6
712 =>cbeta =cbeta =>>cbeta ==cbeta ===cbeta
713 =zinbun-oracle =>zinbun-oracle
714 ===hng-jou ===hng-keg ===hng-dng ===hng-mam
715 ===hng-drt ===hng-kgk ===hng-myz ===hng-kda
716 ===hng-khi ===hng-khm ===hng-hok ===hng-kyd ===hng-sok
717 ===hng-yhk ===hng-kak ===hng-kar ===hng-kae
718 ===hng-sys ===hng-tsu ===hng-tzj
719 ===hng-hos ===hng-nak ===hng-jhk
720 ===hng-hod ===hng-gok ===hng-ink ===hng-nto
721 ===hng-nkm ===hng-k24 ===hng-nkk
722 ===hng-kcc ===hng-kcj ===hng-kbk ===hng-sik
723 ===hng-skk ===hng-kyu ===hng-ksk ===hng-wan
724 ===hng-okd ===hng-wad ===hng-kmi
725 ===hng-zkd ===hng-doh ===hng-jyu
726 ===hng-tzs ===hng-kss ===hng-kyo
728 ;; (string-match "^=adobe-" (symbol-name name))
730 "(%-18s . %05d)\t; %c")
731 ((memq name '(=hanyo-denshi/ks
732 ==hanyo-denshi/ks ===hanyo-denshi/ks
735 =mj ==mj ===mj =>>mj =>mj
737 "(%-18s . %06d)\t; %c")
738 ((memq name '(=hanyo-denshi/tk ==hanyo-denshi/tk))
739 "(%-18s . %08d)\t; %c")
740 ((>= (charset-dimension name) 2)
741 "(%-18s . #x%04X)\t; %c")
743 "(%-18s . #x%02X)\t; %c"))
745 (if (= (charset-iso-graphic-plane name) 1)
747 (cond ((= (charset-dimension name) 1)
749 ((= (charset-dimension name) 2)
751 ((= (charset-dimension name) 3)
755 (char-db-decode-isolated-char name value)))
756 (if (and (= (charset-chars name) 94)
757 (= (charset-dimension name) 2))
758 (insert (format " [%02d-%02d]"
759 (- (lsh value -8) 32)
760 (- (logand value 255) 32))))
763 (insert (format "(%-18s . %s)" name value))
765 (insert line-breaking))
767 (defun char-db-insert-relation-feature (char name value line-breaking
769 (insert (format "(%-18s%s " name line-breaking))
770 (let ((lbs (concat "\n" (make-string (current-column) ?\ )))
771 separator cell sources required-features
774 (setq cell (car value))
776 (setq cell (decode-char '=ucs cell)))
778 ((eq name '->subsumptive)
779 (when (or (not (some (lambda (atr)
780 (get-char-attribute cell atr))
781 char-db-ignored-attributes))
783 (encode-char cell ccs 'defined-only))
787 (let ((char-db-ignored-attributes
789 char-db-ignored-attributes)))
790 (insert-char-attributes cell readable nil nil 'for-sub-node))
791 (setq separator lbs))
796 char (intern (format "%s*sources" name))))
797 (setq required-features nil)
798 (dolist (source sources)
802 shinjigen shinjigen@1ed shinjigen@rev))
803 (setq required-features
804 (union required-features
816 =shinjigen/+p@rev))))
818 (setq required-features
819 (union required-features
824 ((find-charset (setq ret (intern (format "=%s" source))))
825 (setq required-features
826 (cons ret required-features)))
827 (t (setq required-features
828 (cons source required-features)))))
829 (cond ((string-match "@JP" (symbol-name name))
830 (setq required-features
831 (union required-features
839 ((string-match "@CN" (symbol-name name))
840 (setq required-features
841 (union required-features
848 (insert (format "%S" cell))
849 (char-db-insert-char-spec cell readable
852 (setq separator lbs))
856 (if (consp (car cell))
857 (char-db-insert-char-spec cell readable)
858 (char-db-insert-char-reference cell readable))
859 (setq separator lbs))
863 (insert (prin1-to-string cell))
864 (setq separator " ")))
865 (setq value (cdr value)))
867 (insert line-breaking)))
869 (defun insert-char-attributes (char &optional readable attributes column
872 (setq column (current-column)))
873 (let (name value ; has-long-ccs-name
877 (concat "\n" (make-string (1+ column) ?\ )))
878 lbs cell separator ret
880 dest-ccss ; sources required-features
885 (if (consp attributes)
887 (dolist (name attributes)
888 (unless (memq name char-db-ignored-attributes)
889 (if (find-charset name)
893 (dolist (name (char-attribute-list))
894 (unless (memq name char-db-ignored-attributes)
895 (if (find-charset name)
899 #'char-attribute-name<)))
901 (when (memq '<-subsumptive attributes)
902 (when (or readable (not for-sub-node))
903 (when (setq value (get-char-attribute char '<-subsumptive))
904 (char-db-insert-relation-feature char '<-subsumptive value
907 (setq attributes (delq '<-subsumptive attributes)))
908 (when (and (memq '<-denotational attributes)
909 (setq value (get-char-attribute char '<-denotational)))
910 (char-db-insert-relation-feature char '<-denotational value
913 (setq attributes (delq '<-denotational attributes)))
914 (when (and (memq '<-denotational@component attributes)
915 (setq value (get-char-attribute char '<-denotational@component)))
916 (char-db-insert-relation-feature char '<-denotational@component value
919 (setq attributes (delq '<-denotational@component attributes)))
920 (when (and (memq 'name attributes)
921 (setq value (get-char-attribute char 'name)))
923 (if (> (+ (current-column) (length value)) 48)
926 value line-breaking))
927 (setq attributes (delq 'name attributes))
929 (when (and (memq 'name* attributes)
930 (setq value (get-char-attribute char 'name*)))
932 (if (> (+ (current-column) (length value)) 48)
935 value line-breaking))
936 (setq attributes (delq 'name* attributes))
938 (when (and (memq 'script attributes)
939 (setq value (get-char-attribute char 'script)))
940 (insert (format "(script\t\t%s)%s"
941 (mapconcat (function prin1-to-string)
944 (setq attributes (delq 'script attributes))
946 (dolist (name '(=>ucs =>ucs*))
947 (when (and (memq name attributes)
948 (setq value (get-char-attribute char name)))
949 (insert (format "(%-18s . #x%04X)\t; %c%s"
950 name value (decode-char '=ucs value)
952 (setq attributes (delq name attributes))))
953 (dolist (name '(=>ucs@gb =>ucs@big5))
954 (when (and (memq name attributes)
955 (setq value (get-char-attribute char name)))
956 (insert (format "(%-18s . #x%04X)\t; %c%s"
961 (symbol-name name) 2)))
964 (setq attributes (delq name attributes))
966 ;; (dolist (name '(=>daikanwa))
967 ;; (when (and (memq name attributes)
968 ;; (setq value (get-char-attribute char name)))
970 ;; (if (integerp value)
971 ;; (format "(%-18s . %05d)\t; %c%s"
972 ;; name value (decode-char '=daikanwa value)
974 ;; (format "(%-18s %s)\t; %c%s"
976 ;; (mapconcat (function prin1-to-string)
978 ;; (char-representative-of-daikanwa char)
980 ;; (setq attributes (delq name attributes))))
981 (when (and (memq 'general-category attributes)
982 (setq value (get-char-attribute char 'general-category)))
984 "(general-category\t%s) ; %s%s"
985 (mapconcat (lambda (cell)
988 (cond ((rassoc value unidata-normative-category-alist)
989 "Normative Category")
990 ((rassoc value unidata-informative-category-alist)
991 "Informative Category")
995 (setq attributes (delq 'general-category attributes))
997 (when (and (memq 'bidi-category attributes)
998 (setq value (get-char-attribute char 'bidi-category)))
999 (insert (format "(bidi-category\t. %S)%s"
1002 (setq attributes (delq 'bidi-category attributes))
1004 (unless (or (not (memq 'mirrored attributes))
1005 (eq (setq value (get-char-attribute char 'mirrored 'empty))
1007 (insert (format "(mirrored\t\t. %S)%s"
1010 (setq attributes (delq 'mirrored attributes))
1013 ((and (memq 'decimal-digit-value attributes)
1014 (setq value (get-char-attribute char 'decimal-digit-value)))
1015 (insert (format "(decimal-digit-value . %S)%s"
1018 (setq attributes (delq 'decimal-digit-value attributes))
1019 (when (and (memq 'digit-value attributes)
1020 (setq value (get-char-attribute char 'digit-value)))
1021 (insert (format "(digit-value\t . %S)%s"
1024 (setq attributes (delq 'digit-value attributes))
1026 (when (and (memq 'numeric-value attributes)
1027 (setq value (get-char-attribute char 'numeric-value)))
1028 (insert (format "(numeric-value\t . %S)%s"
1031 (setq attributes (delq 'numeric-value attributes))
1035 (when (and (memq 'digit-value attributes)
1036 (setq value (get-char-attribute char 'digit-value)))
1037 (insert (format "(digit-value\t. %S)%s"
1040 (setq attributes (delq 'digit-value attributes))
1042 (when (and (memq 'numeric-value attributes)
1043 (setq value (get-char-attribute char 'numeric-value)))
1044 (insert (format "(numeric-value\t. %S)%s"
1047 (setq attributes (delq 'numeric-value attributes))
1049 (when (and (memq 'iso-10646-comment attributes)
1050 (setq value (get-char-attribute char 'iso-10646-comment)))
1051 (insert (format "(iso-10646-comment\t. %S)%s"
1054 (setq attributes (delq 'iso-10646-comment attributes))
1056 (when (and (memq 'morohashi-daikanwa attributes)
1057 (setq value (get-char-attribute char 'morohashi-daikanwa)))
1058 (insert (format "(morohashi-daikanwa\t%s)%s"
1059 (mapconcat (function prin1-to-string) value " ")
1061 (setq attributes (delq 'morohashi-daikanwa attributes))
1065 (when (and (memq 'ideographic-radical attributes)
1066 (setq value (get-char-attribute char 'ideographic-radical)))
1067 (setq radical value)
1068 (insert (format "(ideographic-radical . %S)\t; %c%s"
1070 (ideographic-radical radical)
1072 (setq attributes (delq 'ideographic-radical attributes))
1074 (when (and (memq 'shuowen-radical attributes)
1075 (setq value (get-char-attribute char 'shuowen-radical)))
1076 (insert (format "(shuowen-radical\t. %S)\t; %c%s"
1078 (shuowen-radical value)
1080 (setq attributes (delq 'shuowen-radical attributes))
1085 char-db-feature-domains
1087 (dolist (feature (char-attribute-list))
1088 (setq feature (symbol-name feature))
1090 "\\(radical\\|strokes\\)@\\([^@*]+\\)\\(\\*\\|$\\)"
1092 (setq domain (intern (match-string 2 feature)))
1093 (unless (memq domain dest)
1094 (setq dest (cons domain dest)))))
1095 (sort dest #'string<))))
1096 (setq key (intern (format "%s@%s" 'ideographic-radical domain)))
1097 (when (and (memq key attributes)
1098 (setq value (get-char-attribute char key)))
1099 (setq radical value)
1100 (insert (format "(%s . %S)\t; %c%s"
1103 (ideographic-radical radical)
1105 (setq attributes (delq key attributes))
1107 (setq key (intern (format "%s@%s" 'ideographic-strokes domain)))
1108 (when (and (memq key attributes)
1109 (setq value (get-char-attribute char key)))
1110 (setq strokes value)
1111 (insert (format "(%s . %S)%s"
1115 (setq attributes (delq key attributes))
1117 (setq key (intern (format "%s@%s" 'total-strokes domain)))
1118 (when (and (memq key attributes)
1119 (setq value (get-char-attribute char key)))
1120 (insert (format "(%s . %S)%s"
1124 (setq attributes (delq key attributes))
1126 (dolist (feature '(ideographic-radical
1129 (setq key (intern (format "%s@%s*sources" feature domain)))
1130 (when (and (memq key attributes)
1131 (setq value (get-char-attribute char key)))
1132 (insert (format "(%s%s" key line-breaking))
1133 (dolist (cell value)
1134 (insert (format " %s" cell)))
1136 (insert line-breaking)
1137 (setq attributes (delq key attributes))
1140 (when (and (memq 'ideographic-strokes attributes)
1141 (setq value (get-char-attribute char 'ideographic-strokes)))
1142 (setq strokes value)
1143 (insert (format "(ideographic-strokes . %S)%s"
1146 (setq attributes (delq 'ideographic-strokes attributes))
1148 (when (and (memq 'kangxi-radical attributes)
1149 (setq value (get-char-attribute char 'kangxi-radical)))
1150 (unless (eq value radical)
1151 (insert (format "(kangxi-radical\t . %S)\t; %c%s"
1153 (ideographic-radical value)
1156 (setq radical value)))
1157 (setq attributes (delq 'kangxi-radical attributes))
1159 (when (and (memq 'kangxi-strokes attributes)
1160 (setq value (get-char-attribute char 'kangxi-strokes)))
1161 (unless (eq value strokes)
1162 (insert (format "(kangxi-strokes\t . %S)%s"
1166 (setq strokes value)))
1167 (setq attributes (delq 'kangxi-strokes attributes))
1169 ;; (when (and (memq 'japanese-radical attributes)
1170 ;; (setq value (get-char-attribute char 'japanese-radical)))
1171 ;; (unless (eq value radical)
1172 ;; (insert (format "(japanese-radical\t . %S)\t; %c%s"
1174 ;; (ideographic-radical value)
1177 ;; (setq radical value)))
1178 ;; (setq attributes (delq 'japanese-radical attributes))
1180 (when (and (memq 'japanese-strokes attributes)
1181 (setq value (get-char-attribute char 'japanese-strokes)))
1182 (unless (eq value strokes)
1183 (insert (format "(japanese-strokes\t . %S)%s"
1187 (setq strokes value)))
1188 (setq attributes (delq 'japanese-strokes attributes))
1190 (when (and (memq 'cns-radical attributes)
1191 (setq value (get-char-attribute char 'cns-radical)))
1192 (insert (format "(cns-radical\t . %S)\t; %c%s"
1194 (ideographic-radical value)
1196 (setq attributes (delq 'cns-radical attributes))
1198 (when (and (memq 'cns-strokes attributes)
1199 (setq value (get-char-attribute char 'cns-strokes)))
1200 (unless (eq value strokes)
1201 (insert (format "(cns-strokes\t . %S)%s"
1205 (setq strokes value)))
1206 (setq attributes (delq 'cns-strokes attributes))
1208 ;; (when (and (memq 'shinjigen-1-radical attributes)
1209 ;; (setq value (get-char-attribute char 'shinjigen-1-radical)))
1210 ;; (unless (eq value radical)
1211 ;; (insert (format "(shinjigen-1-radical . %S)\t; %c%s"
1213 ;; (ideographic-radical value)
1216 ;; (setq radical value)))
1217 ;; (setq attributes (delq 'shinjigen-1-radical attributes))
1219 ;; (when (and (memq 'ideographic- attributes)
1220 ;; (setq value (get-char-attribute char 'ideographic-)))
1221 ;; (insert "(ideographic- ")
1222 ;; (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1224 ;; (while (consp value)
1225 ;; (setq cell (car value))
1226 ;; (if (integerp cell)
1227 ;; (setq cell (decode-char '=ucs cell)))
1228 ;; (cond ((characterp cell)
1232 ;; (insert (format "%S" cell))
1233 ;; (char-db-insert-char-spec cell readable))
1234 ;; (setq separator lbs))
1238 ;; (if (consp (car cell))
1239 ;; (char-db-insert-char-spec cell readable)
1240 ;; (char-db-insert-char-reference cell readable))
1241 ;; (setq separator lbs))
1244 ;; (insert separator))
1245 ;; (insert (prin1-to-string cell))
1246 ;; (setq separator " ")))
1247 ;; (setq value (cdr value)))
1249 ;; (insert line-breaking)
1250 ;; (setq attributes (delq 'ideographic- attributes)))
1251 (when (and (memq 'total-strokes attributes)
1252 (setq value (get-char-attribute char 'total-strokes)))
1253 (insert (format "(total-strokes . %S)%s"
1256 (setq attributes (delq 'total-strokes attributes))
1258 ;; (when (and (memq '->ideograph attributes)
1259 ;; (setq value (get-char-attribute char '->ideograph)))
1260 ;; (insert (format "(->ideograph\t%s)%s"
1261 ;; (mapconcat (lambda (code)
1262 ;; (cond ((symbolp code)
1263 ;; (symbol-name code))
1265 ;; (format "#x%04X" code))
1268 ;; line-breaking code))))
1271 ;; (setq attributes (delq '->ideograph attributes))
1273 ;; (when (and (memq '->decomposition attributes)
1274 ;; (setq value (get-char-attribute char '->decomposition)))
1275 ;; (insert (format "(->decomposition\t%s)%s"
1276 ;; (mapconcat (lambda (code)
1277 ;; (cond ((symbolp code)
1278 ;; (symbol-name code))
1279 ;; ((characterp code)
1281 ;; (format "%S" code)
1286 ;; (format "#x%04X" code))
1288 ;; (format "%s%S" line-breaking code))))
1291 ;; (setq attributes (delq '->decomposition attributes))
1293 (if (equal (get-char-attribute char '->titlecase)
1294 (get-char-attribute char '->uppercase))
1295 (setq attributes (delq '->titlecase attributes)))
1296 (when (and (memq '->mojikyo attributes)
1297 (setq value (get-char-attribute char '->mojikyo)))
1298 (insert (format "(->mojikyo\t\t. %06d)\t; %c%s"
1299 value (decode-char 'mojikyo value)
1301 (setq attributes (delq '->mojikyo attributes))
1303 ;; (when (and (memq 'hanyu-dazidian-vol attributes)
1304 ;; (setq value (get-char-attribute char 'hanyu-dazidian-vol)))
1305 ;; (insert (format "(hanyu-dazidian-vol . %d)%s"
1306 ;; value line-breaking))
1307 ;; (setq attributes (delq 'hanyu-dazidian-vol attributes))
1309 ;; (when (and (memq 'hanyu-dazidian-page attributes)
1310 ;; (setq value (get-char-attribute char 'hanyu-dazidian-page)))
1311 ;; (insert (format "(hanyu-dazidian-page . %d)%s"
1312 ;; value line-breaking))
1313 ;; (setq attributes (delq 'hanyu-dazidian-page attributes))
1315 ;; (when (and (memq 'hanyu-dazidian-char attributes)
1316 ;; (setq value (get-char-attribute char 'hanyu-dazidian-char)))
1317 ;; (insert (format "(hanyu-dazidian-char . %d)%s"
1318 ;; value line-breaking))
1319 ;; (setq attributes (delq 'hanyu-dazidian-char attributes))
1322 (dolist (ignored '(composition
1323 ->denotational <-subsumptive ->ucs-unified
1324 ->ideographic-component-forms))
1325 (setq attributes (delq ignored attributes))))
1327 (setq name (car attributes))
1328 (unless (eq (setq value (get-char-attribute char name 'value-is-empty))
1330 (cond ((setq ret (find-charset name))
1331 (setq name (charset-name ret))
1332 (when (not (memq name dest-ccss))
1333 (setq dest-ccss (cons name dest-ccss))
1334 (char-db-insert-ccs-feature name value line-breaking))
1336 ((string-match "^=>ucs@" (symbol-name name))
1337 (insert (format "(%-18s . #x%04X)\t; %c%s"
1338 name value (decode-char '=ucs value)
1341 ((eq name 'jisx0208-1978/4X)
1342 (insert (format "(%-18s . #x%04X)%s"
1348 (not (eq name '->subsumptive))
1349 (not (eq name '->uppercase))
1350 (not (eq name '->lowercase))
1351 (not (eq name '->titlecase))
1352 (not (eq name '->canonical))
1353 (not (eq name '->Bopomofo))
1354 (not (eq name '->mistakable))
1355 (not (eq name '->ideographic-variants))
1356 (null (get-char-attribute
1357 char (intern (format "%s*sources" name))))
1358 (not (string-match "\\*sources$" (symbol-name name)))
1359 (null (get-char-attribute
1360 char (intern (format "%s*note" name))))
1361 (not (string-match "\\*note$" (symbol-name name)))
1362 (or (eq name '<-identical)
1363 (eq name '<-uppercase)
1364 (eq name '<-lowercase)
1365 (eq name '<-titlecase)
1366 (eq name '<-canonical)
1367 (eq name '<-ideographic-variants)
1368 ;; (eq name '<-synonyms)
1369 (string-match "^<-synonyms" (symbol-name name))
1370 (eq name '<-mistakable)
1371 (when (string-match "^->" (symbol-name name))
1373 ((string-match "^->fullwidth" (symbol-name name))
1374 (not (and (consp value)
1375 (characterp (car value))
1377 (car value) '=ucs 'defined-only)))
1382 ((or (eq name 'ideographic-structure)
1383 (eq name 'ideographic-combination)
1384 ;; (eq name 'ideographic-)
1385 (eq name '=decomposition)
1386 (char-feature-base-name= '=decomposition name)
1387 (char-feature-base-name= '=>decomposition name)
1388 ;; (string-match "^=>*decomposition\\(@[^*]+\\)?$"
1389 ;; (symbol-name name))
1390 (string-match "^\\(->\\|<-\\)[^*]*$" (symbol-name name))
1391 (string-match "^\\(->\\|<-\\)[^*]*\\*sources$"
1394 (char-db-insert-relation-feature char name value
1397 ;; ((memq name '(ideograph=
1398 ;; original-ideograph-of
1399 ;; ancient-ideograph-of
1400 ;; vulgar-ideograph-of
1401 ;; wrong-ideograph-of
1402 ;; ;; simplified-ideograph-of
1403 ;; ideographic-variants
1404 ;; ;; ideographic-different-form-of
1406 ;; (insert (format "(%-18s%s " name line-breaking))
1407 ;; (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1409 ;; (while (consp value)
1410 ;; (setq cell (car value))
1411 ;; (if (and (consp cell)
1412 ;; (consp (car cell)))
1416 ;; (char-db-insert-alist cell readable)
1417 ;; (setq separator lbs))
1419 ;; (insert separator))
1420 ;; (insert (prin1-to-string cell))
1421 ;; (setq separator " "))
1422 ;; (setq value (cdr value)))
1424 ;; (insert line-breaking))
1426 (insert (format "(%-18s " name))
1427 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1429 (while (consp value)
1430 (setq cell (car value))
1431 (if (and (consp cell)
1433 (setq ret (condition-case nil
1441 (setq key (car (car rest)))
1442 (if (find-charset key)
1443 (setq cal (cons key cal))
1444 (setq al (cons key al)))
1445 (setq rest (cdr rest)))
1448 (insert-char-attributes ret
1452 (setq separator lbs))
1453 (setq ret (prin1-to-string cell))
1455 (if (< (+ (current-column)
1462 (setq separator " "))
1463 (setq value (cdr value)))
1465 (insert line-breaking))
1467 (insert (format "(%-18s" name))
1468 (setq ret (prin1-to-string value))
1469 (unless (< (+ (current-column)
1473 (insert line-breaking))
1474 (insert " . " ret ")" line-breaking)
1475 ;; (insert (format "(%-18s . %S)%s"
1480 (setq attributes (cdr attributes)))
1483 (defun insert-char-data (char &optional readable
1486 (narrow-to-region (point)(point))
1487 (insert "(define-char
1489 (insert-char-attributes char readable attributes)
1491 (goto-char (point-min))
1492 (while (re-search-forward "[ \t]+$" nil t)
1495 (goto-char (point-min))
1496 (while (re-search-forward "[ \t][ \t][ \t]*" nil t)
1497 (let ((column (current-column))
1498 (indent-tabs-mode t))
1499 (delete-region (match-beginning 0) (point))
1500 (indent-to column)))
1501 (goto-char (point-max))
1502 ;; (tabify (point-min)(point-max))
1505 (defun insert-char-data-with-variant (char &optional printable
1507 script excluded-script)
1508 (insert-char-data char printable)
1509 (let ((variants (char-variants char))
1512 (setq variants (sort variants #'<))
1513 (setq rest variants)
1514 (setq variants (cons char variants))
1516 (setq variant (car rest))
1517 (unless (get-char-attribute variant '<-subsumptive)
1518 (if (and (or (null script)
1519 (null (setq vs (get-char-attribute variant 'script)))
1521 (or (null excluded-script)
1522 (null (setq vs (get-char-attribute variant 'script)))
1523 (not (memq excluded-script vs))))
1524 (unless (and no-ucs-unified (get-char-attribute variant '=ucs))
1525 (insert-char-data variant printable)
1526 (if (setq ret (char-variants variant))
1528 (or (memq (car ret) variants)
1529 ;; (get-char-attribute (car ret) '<-subsumptive)
1530 (setq rest (nconc rest (list (car ret)))))
1531 (setq ret (cdr ret)))))))
1532 (setq rest (cdr rest)))))
1534 (defun insert-char-range-data (min max &optional script excluded-script)
1537 (while (<= code max)
1538 (setq char (decode-char '=ucs code))
1539 (if (encode-char char '=ucs 'defined-only)
1540 (insert-char-data-with-variant char nil 'no-ucs-unified
1541 script excluded-script))
1542 (setq code (1+ code)))))
1544 (defun write-char-range-data-to-file (min max file
1545 &optional script excluded-script)
1546 (let ((coding-system-for-write char-db-file-coding-system))
1548 (insert (format ";; -*- coding: %s -*-\n"
1549 char-db-file-coding-system))
1550 (insert-char-range-data min max script excluded-script)
1551 (write-region (point-min)(point-max) file))))
1553 (defvar what-character-original-window-configuration)
1556 (defun what-char-definition (char)
1557 (interactive (list (char-after)))
1558 (let ((buf (get-buffer-create "*Character Description*"))
1559 (the-buf (current-buffer))
1560 (win-conf (current-window-configuration)))
1562 (make-local-variable 'what-character-original-window-configuration)
1563 (setq what-character-original-window-configuration win-conf)
1564 (setq buffer-read-only nil)
1568 (insert-char-data-with-variant char 'printable)
1569 (unless (char-attribute-alist char)
1570 (insert (format ";; = %c\n"
1571 (let* ((rest (split-char char))
1575 (setq code (logior (lsh code 8)
1577 (decode-char ccs code)))))
1578 ;; (char-db-update-comment)
1579 (set-buffer-modified-p nil)
1580 (view-mode the-buf (lambda (buf)
1581 (set-window-configuration
1582 what-character-original-window-configuration)
1584 (goto-char (point-min)))
1586 (set-window-configuration
1587 what-character-original-window-configuration)
1588 (signal (car err) (cdr err)))))))
1594 (provide 'char-db-util)
1596 ;;; char-db-util.el ends here