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, 2018, 2019,
5 ;; 2020, 2021 MORIOKA Tomohiko.
7 ;; Author: MORIOKA Tomohiko <tomo@kanji.zinbun.kyoto-u.ac.jp>
8 ;; Keywords: CHISE, Character Database, ISO/IEC 10646, UCS, Unicode, MULE.
10 ;; This file is part of XEmacs CHISE.
12 ;; XEmacs CHISE is free software; you can redistribute it and/or
13 ;; modify it under the terms of the GNU General Public License as
14 ;; published by the Free Software Foundation; either version 2, or (at
15 ;; your option) any later version.
17 ;; XEmacs CHISE is distributed in the hope that it will be useful,
18 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
19 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
20 ;; General Public License for more details.
22 ;; You should have received a copy of the GNU General Public License
23 ;; along with XEmacs CHISE; see the file COPYING. If not, write to
24 ;; the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
25 ;; Boston, MA 02111-1307, USA.
30 (require 'ideograph-subr)
32 (defconst unidata-normative-category-alist
33 '(("Lu" letter uppercase)
34 ("Ll" letter lowercase)
35 ("Lt" letter titlecase)
36 ("Mn" mark non-spacing)
37 ("Mc" mark spacing-combining)
39 ("Nd" number decimal-digit)
42 ("Zs" separator space)
44 ("Zp" separator paragraph)
47 ("Cs" other surrogate)
48 ("Co" other private-use)
49 ("Cn" other not-assigned)))
51 (defconst unidata-informative-category-alist
52 '(("Lm" letter modifier)
54 ("Pc" punctuation connector)
55 ("Pd" punctuation dash)
56 ("Ps" punctuation open)
57 ("Pe" punctuation close)
58 ("Pi" punctuation initial-quote)
59 ("Pf" punctuation final-quote)
60 ("Po" punctuation other)
62 ("Sc" symbol currency)
63 ("Sk" symbol modifier)
67 (defconst shuowen-radicals
68 [?一 ?上 ?示 ?三 ?王 ?玉 ?玨 ?气 ?士 ?丨 ; 010
69 ?屮 ?艸 ?蓐 ?茻 ?小 ?八 ?釆 ?半 ?牛 ?犛 ; 020
70 ?告 ?口 ?凵 ?吅 ?哭 ?走 ?止 ?癶 ?步 ?此 ; 030
71 ?正 ?是 ?辵 ?彳 ?廴 ?㢟 ?行 ?齒 ?牙 ?足 ; 040
72 ?疋 ?品 ?龠 ?冊 ?㗊 ?舌 ?干 ?𧮫 ?只 ?㕯 ; 050
73 ?句 ?丩 ?古 ?十 ?卅 ?言 ?誩 ?音 ?䇂 ?丵 ; 060
74 ?菐 ?𠬞 ?𠬜 ?共 ?異 ?舁 ?𦥑 ?䢅 ?爨 ?革 ; 070
75 ?鬲 ?䰜 ?爪 ?𠃨 ?鬥 ?又 ?𠂇 ?史 ?支 ?𦘒 ; 080
76 ?聿 ?畫 ?隶 ?臤 ?臣 ?殳 ?殺 ?𠘧 ?寸 ?皮 ; 090
77 ?㼱 ?攴 ?敎 ?卜 ?用 ?爻 ?㸚 ?𥄎 ?目 ?䀠 ; 100
78 ?眉 ?盾 ?自 ?白 ?鼻 ?皕 ?習 ?羽 ?隹 ?奞 ; 110
79 ?雈 ?𦫳 ?𥄕 ?羊 ?羴 ?瞿 ?雔 ?雥 ?鳥 ?烏 ; 120
80 ?𠦒 ?冓 ?幺 ?𢆶 ?叀 ?玄 ?予 ?放 ?𠬪 ?𣦼 ; 130
81 ?歺 ?死 ?冎 ?骨 ?肉 ?筋 ?刀 ?刃 ?㓞 ?丯 ; 140
82 ?耒 ?角 ?竹 ?箕 ?丌 ?左 ?工 ?㠭 ?巫 ?甘 ; 150
83 ?曰 ?乃 ?丂 ?可 ?兮 ?号 ?亏 ?旨 ?喜 ?壴 ; 160
84 ; ?旨 ?曰 ?乃 ?丂 ?可 ?兮 ?号 ?亏 ?喜 ?壴 ; 160
85 ?鼓 ?豈 ?豆 ?豊 ?豐 ?䖒 ?虍 ?虎 ?虤 ?皿 ; 170
86 ?𠙴 ?去 ?血 ?丶 ?丹 ?青 ?井 ?皀 ?鬯 ?食 ; 180
87 ?亼 ?會 ?倉 ?入 ?缶 ?矢 ?高 ?冂 ?𩫏 ?京 ; 190
88 ?亯 ?𣆪 ?畗 ?㐭 ?嗇 ?來 ?麥 ?夊 ?舛 ?䑞 ; 200
89 ?韋 ?弟 ?夂 ?久 ?桀 ?木 ?東 ?林 ?才 ?叒 ; 210
90 ?之 ?帀 ?出 ?𣎵 ?生 ?乇 ?𠂹 ?𠌶 ?華 ?𥝌 ; 220
91 ?稽 ?巢 ?桼 ?束 ?㯻 ?囗 ?員 ?貝 ?邑 ?𨛜 ; 230
92 ?日 ?旦 ?倝 ?㫃 ?冥 ?晶 ?月 ?有 ?明 ?囧 ; 240
93 ?夕 ?多 ?毌 ?𢎘 ?𣐺 ?卣 ?齊 ?朿 ?片 ?鼎 ; 250
94 ?克 ?彔 ?禾 ?秝 ?黍 ?香 ?米 ?毇 ?臼 ?凶 ; 260
95 ?𣎳 ?𣏟 ?麻 ?尗 ?耑 ?韭 ?瓜 ?瓠 ?宀 ?宮 ; 270
96 ?呂 ?穴 ?㝱 ?疒 ?冖 ?𠔼 ?冃 ?㒳 ?网 ?襾 ; 280
97 ?巾 ?巿 ?帛 ?白 ?㡀 ?黹 ?人 ?𠤎 ?匕 ?从 ; 290
98 ?比 ?北 ?丘 ?㐺 ?𡈼 ?重 ?臥 ?身 ?㐆 ?衣 ; 300
99 ?裘 ?老 ?毛 ?毳 ?尸 ?尺 ?尾 ?履 ?舟 ?方 ; 310
100 ?儿 ?兄 ?兂 ?皃 ?𠑹 ?先 ?秃 ?見 ?覞 ?欠 ; 320
101 ?㱃 ?㳄 ?旡 ?頁 ?𦣻 ?面 ?丏 ?首 ?𥄉 ?須 ; 330
102 ?彡 ?彣 ?文 ?髟 ?后 ?司 ?卮 ?卩 ?印 ?色 ; 340
103 ?𠨍 ?辟 ?勹 ?包 ?茍 ?鬼 ?甶 ?厶 ?嵬 ?山 ; 350
104 ?屾 ?屵 ?广 ?厂 ?丸 ?危 ?石 ?長 ?勿 ?冄 ; 360
105 ?而 ?豕 ?㣇 ?彑 ?豚 ?豸 ?𤉡 ?易 ?象 ?馬 ; 370
106 ?𢊁 ?鹿 ?麤 ?㲋 ?兔 ?萈 ?犬 ?㹜 ?鼠 ?能 ; 380
107 ?熊 ?火 ?炎 ?黑 ?囪 ?焱 ?炙 ?赤 ?大 ?亦 ; 390
108 ?夨 ?夭 ?交 ?尣 ?壺 ?壹 ?㚔 ?奢 ?亢 ?夲 ; 400
109 ?夰 ?亣 ?夫 ?立 ?竝 ?囟 ?思 ?心 ?惢 ?水 ; 410
110 ?沝 ?瀕 ?𡿨 ?巜 ?川 ?泉 ?灥 ?永 ?𠂢 ?谷 ; 420
111 ?仌 ?雨 ?雲 ?魚 ?𩺰 ?燕 ?龍 ?飛 ?非 ?卂 ; 430
112 ?𠃉 ?不 ?至 ?西 ?鹵 ?鹽 ?戶 ?門 ?耳 ?𦣝 ; 440
113 ?手 ?𠦬 ?女 ?毋 ?民 ?丿 ?𠂆 ?乁 ?氏 ?氐 ; 450
114 ?戈 ?戉 ?我 ?亅 ?琴 ?𠃊 ?亡 ?匸 ?匚 ?曲 ; 460
115 ?甾 ?瓦 ?弓 ?弜 ?弦 ?系 ?糸 ?素 ?絲 ?率 ; 470
116 ?虫 ?䖵 ?蟲 ?風 ?它 ?龜 ?黽 ?卵 ?二 ?土 ; 480
117 ?垚 ?堇 ?里 ?田 ?畕 ?黃 ?男 ?力 ?劦 ?金 ; 490
118 ?幵 ?勺 ?几 ?且 ?斤 ?斗 ?矛 ?車 ?𠂤 ?𨸏 ; 500
119 ?𨺅 ?厽 ?四 ?宁 ?叕 ?亞 ?五 ?六 ?七 ?九 ; 510
120 ?禸 ?嘼 ?甲 ?乙 ?丙 ?丁 ?戊 ?己 ?巴 ?庚 ; 520
121 ?辛 ?辡 ?壬 ?癸 ?子 ?了 ?孨 ?𠫓 ?丑 ?寅 ; 530
122 ?卯 ?辰 ?巳 ?午 ?未 ?申 ?酉 ?酋 ?戌 ?亥 ; 540
125 (defun shuowen-radical (number)
126 (aref shuowen-radicals (1- number)))
128 (defvar char-db-file-coding-system 'utf-8-mcs-er)
130 (defvar char-db-ignored-attributes '(ideographic-products))
132 (defvar char-db-coded-charset-priority-list
233 ;; =>>>adobe-japan1-0
234 ;; =>>>adobe-japan1-1
235 ;; =>>>adobe-japan1-2
236 ;; =>>>adobe-japan1-3
237 ;; =>>>adobe-japan1-4
238 ;; =>>>adobe-japan1-5
239 ;; =>>>adobe-japan1-6
243 ;; =>>>hanyo-denshi/ja
244 ;; =>>>hanyo-denshi/jb
245 ;; =>>>hanyo-denshi/jc
246 ;; =>>>hanyo-denshi/ft
247 ;; =>>>hanyo-denshi/ib
248 ;; =>>>hanyo-denshi/hg
249 ;; =>>>hanyo-denshi/jt
250 ;; =>>>hanyo-denshi/ks
290 ;; =>ucs@hanyo-denshi
403 =>big5-cdp-itaiji-001
404 =>big5-cdp-itaiji-002
405 =>big5-cdp-itaiji-003
406 =>big5-cdp-itaiji-004
411 =>ucs@iwds-1/normalized
412 =>ucs-itaiji-001@iwds-1
413 =>ucs-itaiji-002@iwds-1
414 =>ucs-itaiji-003@iwds-1
415 =>ucs-itaiji-006@iwds-1
428 ;;; @ char-db formatters
431 (defun char-db-make-char-spec (char)
433 (cond ((characterp char)
434 (cond ((and (setq ret (encode-char char '=ucs 'defined-only))
435 (not (and (<= #xE000 ret)(<= ret #xF8FF))))
436 (setq char-spec (list (cons '=ucs ret)))
437 (cond ((setq ret (get-char-attribute char 'name))
438 (setq char-spec (cons (cons 'name ret) char-spec))
440 ((setq ret (get-char-attribute char 'name*))
441 (setq char-spec (cons (cons 'name* ret) char-spec))
444 ((encode-char char '=mj 'defined-only)
446 (dolist (ccs (charset-list))
447 (if (and (or (eq ccs '=mj)
448 ;; (eq (charset-property ccs 'iso-ir) 177)
449 (string-match "=ucs@" (symbol-name ccs))
451 (setq ccs (charset-name ccs))
452 (null (assq ccs char-spec))
453 (setq ret (encode-char char ccs 'defined-only)))
454 (setq char-spec (cons (cons ccs ret) char-spec))))
456 ((encode-char char '==mj 'defined-only)
458 (dolist (ccs (charset-list))
459 (if (and (or (eq ccs '==mj)
460 ;; (eq (charset-property ccs 'iso-ir) 177)
461 (string-match "=ucs@" (symbol-name ccs))
463 (setq ccs (charset-name ccs))
464 (null (assq ccs char-spec))
465 (setq ret (encode-char char ccs 'defined-only)))
466 (setq char-spec (cons (cons ccs ret) char-spec))))
468 ((encode-char char '=adobe-japan1 'defined-only)
470 (dolist (ccs (charset-list))
471 (if (and (or (memq ccs
480 ;; (eq (charset-property ccs 'iso-ir) 177)
481 (string-match "=ucs@" (symbol-name ccs))
483 (setq ccs (charset-name ccs))
484 (null (assq ccs char-spec))
485 (setq ret (encode-char char ccs 'defined-only)))
486 (setq char-spec (cons (cons ccs ret) char-spec))))
488 ((encode-char char '==adobe-japan1 'defined-only)
490 (dolist (ccs (charset-list))
491 (if (and (or (memq ccs
500 ;; (eq (charset-property ccs 'iso-ir) 177)
501 (string-match "=ucs@" (symbol-name ccs))
503 (setq ccs (charset-name ccs))
504 (null (assq ccs char-spec))
505 (setq ret (encode-char char ccs 'defined-only)))
506 (setq char-spec (cons (cons ccs ret) char-spec))))
510 (let ((rest char-db-coded-charset-priority-list)
513 (setq ccs (charset-name
514 (find-charset (car rest))))
516 (encode-char char ccs
518 (throw 'tag (cons ccs ret)))
519 (setq rest (cdr rest))))))
520 (setq char-spec (list ret))
521 (dolist (ccs (delq (car ret) (charset-list)))
522 (if (and (or (charset-iso-final-char ccs)
529 (and (eq (charset-property ccs 'iso-ir) 177)
530 (not (eq (charset-name ccs) '=ucs@big5)))
531 ;; (string-match "=ucs@" (symbol-name ccs))
533 (setq ccs (charset-name ccs))
534 (null (assq ccs char-spec))
535 (setq ret (encode-char char ccs 'defined-only)))
536 (setq char-spec (cons (cons ccs ret) char-spec))))
538 (setq char-spec (split-char char)))
539 (cond ((setq ret (get-char-attribute char 'name))
540 (setq char-spec (cons (cons 'name ret) char-spec))
542 ((setq ret (get-char-attribute char 'name*))
543 (setq char-spec (cons (cons 'name* ret) char-spec))
546 ((setq ret (get-char-attribute
547 char 'ideographic-combination))
549 (cons (cons 'ideographic-combination ret)
556 (defun char-db-insert-char-spec (char &optional readable column
559 (setq column (current-column)))
560 (let (char-spec temp-char)
561 (setq char-spec (char-db-make-char-spec char))
562 (unless (or (characterp char) ; char
564 (setq char (find-char char-spec))
566 ;; define temporary character
567 ;; Current implementation is dirty.
568 (setq temp-char (define-char (cons '(ideograph-daikanwa . 0)
570 (remove-char-attribute temp-char 'ideograph-daikanwa)
571 (setq char temp-char))
572 (insert-char-attributes char
574 (union (mapcar #'car char-spec)
578 ;; undefine temporary character
579 ;; Current implementation is dirty.
580 (setq char-spec (char-attribute-alist temp-char))
582 (remove-char-attribute temp-char (car (car char-spec)))
583 (setq char-spec (cdr char-spec))))))
585 (defun char-db-insert-alist (alist &optional readable column)
587 (setq column (current-column)))
589 (concat "\n" (make-string (1+ column) ?\ )))
593 lbs cell rest separator)
596 (setq name (car (car alist))
597 value (cdr (car alist)))
598 (cond ((eq name 'char)
600 (if (setq ret (condition-case nil
608 (setq key (car (car value)))
609 ;; (if (find-charset key)
610 ;; (setq cal (cons key cal))
611 (setq al (cons key al))
613 (setq value (cdr value)))
614 (insert-char-attributes ret
618 (insert (prin1-to-string value)))
620 (insert line-breaking))
622 (insert (format "(%-18s " name))
623 (setq lbs (concat "\n" (make-string (current-column) ?\ )))
625 (setq cell (car value))
626 (if (and (consp cell)
628 (setq ret (condition-case nil
638 (setq key (car (car rest)))
639 ;; (if (find-charset key)
640 ;; (setq cal (cons key cal))
641 (setq al (cons key al))
643 (setq rest (cdr rest)))
646 (insert-char-attributes ret
650 (setq separator lbs))
653 (insert (prin1-to-string cell))
654 (setq separator " "))
655 (setq value (cdr value)))
657 (insert line-breaking))
659 (insert (format "(%-18s . %S)%s"
662 (setq alist (cdr alist))))
665 (defun char-db-insert-char-reference (plist &optional readable column)
667 (setq column (current-column)))
669 (concat "\n" (make-string (1+ column) ?\ )))
674 (setq name (pop plist))
675 (setq value (pop plist))
676 (cond ((eq name :char)
679 (cond ((numberp value)
680 (setq value (decode-char '=ucs value)))
682 ;; (setq value (or (find-char value)
685 (char-db-insert-char-spec value readable)
686 (insert line-breaking)
689 (insert (format "%s%s\t%d ; %c%s"
692 (ideographic-radical value)
696 (insert (format "%s%s\t%S" separator name value))
697 (setq separator line-breaking)))
701 (defun char-db-decode-isolated-char (ccs code-point)
704 (cond ((eq ccs 'arabic-iso8859-6)
705 (decode-char ccs code-point))
707 ;; (decode-builtin-char '==gt code-point))
708 ((and (memq ccs '(=gt-pj-1
719 (setq ret (decode-char ccs code-point))
720 (setq ret (encode-char ret '=gt 'defined-only)))
721 (decode-builtin-char '=gt ret))
723 (decode-builtin-char ccs code-point))))
725 (or (decode-char ccs code-point)
726 (define-char (list (cons ccs code-point)))))
727 ((and (<= 0 (char-int ret))
728 (<= (char-int ret) #x1F))
729 (decode-char '=ucs (+ #x2400 (char-int ret))))
730 ((= (char-int ret) #x7F)
734 (defvar char-db-convert-obsolete-format t)
736 (defun char-db-insert-ccs-feature (name value line-breaking)
742 ((memq name '(=>iwds-1
745 =shinjigen@1ed ==shinjigen@1ed
746 =shinjigen@rev ==shinjigen@rev
747 =shinjigen/+p@rev ==shinjigen/+p@rev
748 ===daikanwa/ho ==daikanwa/ho
749 =daikanwa/ho =>>daikanwa/ho =>daikanwa/ho))
750 "(%-18s . %04d)\t; %c")
751 ((eq name '=shinjigen@1ed/24pr)
752 "(%-18s . %04d)\t; %c")
756 ==daikanwa =daikanwa =>>daikanwa =>daikanwa
757 =daikanwa@rev1 =daikanwa@rev2
758 =daikanwa/+p ==daikanwa/+p ===daikanwa/+p
760 =daikanwa/+2p =>>daikanwa/+2p
765 =adobe-japan1-0 ==adobe-japan1-0 ===adobe-japan1-0
766 =adobe-japan1-1 ==adobe-japan1-1 ===adobe-japan1-1
767 =adobe-japan1-2 ==adobe-japan1-2 ===adobe-japan1-2
768 =adobe-japan1-3 ==adobe-japan1-3 ===adobe-japan1-3
769 =adobe-japan1-4 ==adobe-japan1-4 ===adobe-japan1-4
770 =adobe-japan1-5 ==adobe-japan1-5 ===adobe-japan1-5
771 =adobe-japan1-6 ==adobe-japan1-6 ===adobe-japan1-6
772 =>>adobe-japan1-0 =+>adobe-japan1-0
773 =>>adobe-japan1-1 =+>adobe-japan1-1
774 =>>adobe-japan1-2 =+>adobe-japan1-2
775 =>>adobe-japan1-3 =+>adobe-japan1-3
776 =>>adobe-japan1-4 =+>adobe-japan1-4
777 =>>adobe-japan1-5 =+>adobe-japan1-5
778 =>>adobe-japan1-6 =+>adobe-japan1-6
779 =>cbeta =cbeta =>>cbeta ==cbeta ===cbeta
780 =zinbun-oracle =>zinbun-oracle
781 =daijiten ==daijiten ===daijiten ==>daijiten
782 ===hng-jou ===hng-keg ===hng-dng ===hng-mam
783 ===hng-drt ===hng-kgk ===hng-myz ===hng-kda
784 ===hng-khi ===hng-khm ===hng-fhs ===hng-hok
785 ===hng-kyd ===hng-sok
786 ===hng-yhk ===hng-kak ===hng-kar ===hng-kae
787 ===hng-sys ===hng-tsu ===hng-tzj
788 ===hng-hos ===hng-kkh ===hng-nak ===hng-jhk
789 ===hng-hod ===hng-gok ===hng-ink ===hng-nto
790 ===hng-nkm ===hng-k24 ===hng-ini ===hng-nkk
791 ===hng-kcc ===hng-kcj ===hng-kbk ===hng-sik
792 ===hng-skk ===hng-kyu ===hng-ksk ===hng-wan
793 ===hng-okd ===hng-wad ===hng-kmi
794 ===hng-zkd ===hng-doh ===hng-jyu ===hng-tzs
795 ===hng-sai ===hng-kad ===hng-kss
796 ===hng-kyo ===hng-ykk ===hng-saa
797 ===hng-sab ===hng-wks ===hng-wke ===hng-smk
798 ===hng-sgs ===hng-sts ===hng-kkd
799 =shuowen-jiguge ===shuowen-jiguge4 ===shuowen-jiguge5))
800 ;; (string-match "^=adobe-" (symbol-name name))
802 "(%-18s . %05d)\t; %c")
803 ((memq name '(=hanyo-denshi/ks
804 ==hanyo-denshi/ks ===hanyo-denshi/ks
807 =mj ==mj ===mj =>>mj =>mj
809 "(%-18s . %06d)\t; %c")
810 ((memq name '(=hanyo-denshi/tk ==hanyo-denshi/tk))
811 "(%-18s . %08d)\t; %c")
812 ((>= (charset-dimension name) 2)
813 "(%-18s . #x%04X)\t; %c")
815 "(%-18s . #x%02X)\t; %c"))
817 (if (= (charset-iso-graphic-plane name) 1)
819 (cond ((= (charset-dimension name) 1)
821 ((= (charset-dimension name) 2)
823 ((= (charset-dimension name) 3)
827 (char-db-decode-isolated-char name value)))
828 (if (and (= (charset-chars name) 94)
829 (= (charset-dimension name) 2))
830 (insert (format " [%02d-%02d]"
831 (- (lsh value -8) 32)
832 (- (logand value 255) 32))))
835 (insert (format "(%-18s . %s)" name value))
837 (insert line-breaking))
839 (defun char-db-insert-relation-feature (char name value line-breaking
841 (insert (format "(%-18s%s " name line-breaking))
842 (let ((lbs (concat "\n" (make-string (current-column) ?\ )))
843 separator cell sources required-features
846 (setq cell (car value))
848 (setq cell (decode-char '=ucs cell)))
850 ((eq name '->subsumptive)
851 (when (or (not (some (lambda (atr)
852 (get-char-attribute cell atr))
853 char-db-ignored-attributes))
855 (encode-char cell ccs 'defined-only))
859 (let ((char-db-ignored-attributes
861 char-db-ignored-attributes)))
862 (insert-char-attributes cell readable nil nil 'for-sub-node))
863 (setq separator lbs))
868 char (intern (format "%s*sources" name))))
869 (setq required-features nil)
870 (dolist (source sources)
874 shinjigen shinjigen@1ed shinjigen@rev))
875 (setq required-features
876 (union required-features
888 =shinjigen/+p@rev))))
890 (setq required-features
891 (union required-features
896 ((find-charset (setq ret (intern (format "=%s" source))))
897 (setq required-features
898 (cons ret required-features)))
899 (t (setq required-features
900 (cons source required-features)))))
901 (cond ((string-match "@JP" (symbol-name name))
902 (setq required-features
903 (union required-features
911 ((string-match "@CN" (symbol-name name))
912 (setq required-features
913 (union required-features
920 (insert (format "%S" cell))
921 (char-db-insert-char-spec cell readable
924 (setq separator lbs))
928 (if (consp (car cell))
929 (char-db-insert-char-spec cell readable)
930 (char-db-insert-char-reference cell readable))
931 (setq separator lbs))
935 (insert (prin1-to-string cell))
936 (setq separator " ")))
937 (setq value (cdr value)))
939 (insert line-breaking)))
941 (defun insert-char-attributes (char &optional readable attributes column
944 (setq column (current-column)))
945 (let (name value ; has-long-ccs-name
949 (concat "\n" (make-string (1+ column) ?\ )))
950 lbs cell separator ret
952 dest-ccss ; sources required-features
957 (if (consp attributes)
959 (dolist (name attributes)
960 (unless (memq name char-db-ignored-attributes)
961 (if (find-charset name)
965 (dolist (name (char-attribute-list))
966 (unless (memq name char-db-ignored-attributes)
967 (if (find-charset name)
971 #'char-attribute-name<)))
973 (when (memq '<-subsumptive attributes)
974 (when (or readable (not for-sub-node))
975 (when (setq value (get-char-attribute char '<-subsumptive))
976 (char-db-insert-relation-feature char '<-subsumptive value
979 (setq attributes (delq '<-subsumptive attributes)))
980 (when (and (memq '<-denotational attributes)
981 (setq value (get-char-attribute char '<-denotational)))
982 (char-db-insert-relation-feature char '<-denotational value
985 (setq attributes (delq '<-denotational attributes)))
986 (when (and (memq '<-denotational@component attributes)
987 (setq value (get-char-attribute char '<-denotational@component)))
988 (char-db-insert-relation-feature char '<-denotational@component value
991 (setq attributes (delq '<-denotational@component attributes)))
992 (when (and (memq '<-denotational@usage attributes)
993 (setq value (get-char-attribute char '<-denotational@usage)))
994 (char-db-insert-relation-feature char '<-denotational@usage value
997 (setq attributes (delq '<-denotational@usage attributes)))
998 (when (and (memq 'name attributes)
999 (setq value (get-char-attribute char 'name)))
1001 (if (> (+ (current-column) (length value)) 48)
1004 value line-breaking))
1005 (setq attributes (delq 'name attributes))
1007 (when (and (memq 'name* attributes)
1008 (setq value (get-char-attribute char 'name*)))
1010 (if (> (+ (current-column) (length value)) 48)
1013 value line-breaking))
1014 (setq attributes (delq 'name* attributes))
1016 (when (and (memq 'script attributes)
1017 (setq value (get-char-attribute char 'script)))
1018 (insert (format "(script\t\t%s)%s"
1019 (mapconcat (function prin1-to-string)
1022 (setq attributes (delq 'script attributes))
1024 (dolist (name '(=>ucs =>ucs*))
1025 (when (and (memq name attributes)
1026 (setq value (get-char-attribute char name)))
1027 (insert (format "(%-18s . #x%04X)\t; %c%s"
1028 name value (decode-char '=ucs value)
1030 (setq attributes (delq name attributes))))
1031 (dolist (name '(=>ucs@gb =>ucs@big5))
1032 (when (and (memq name attributes)
1033 (setq value (get-char-attribute char name)))
1034 (insert (format "(%-18s . #x%04X)\t; %c%s"
1036 (decode-char (intern
1039 (symbol-name name) 2)))
1042 (setq attributes (delq name attributes))
1044 ;; (dolist (name '(=>daikanwa))
1045 ;; (when (and (memq name attributes)
1046 ;; (setq value (get-char-attribute char name)))
1048 ;; (if (integerp value)
1049 ;; (format "(%-18s . %05d)\t; %c%s"
1050 ;; name value (decode-char '=daikanwa value)
1052 ;; (format "(%-18s %s)\t; %c%s"
1054 ;; (mapconcat (function prin1-to-string)
1056 ;; (char-representative-of-daikanwa char)
1058 ;; (setq attributes (delq name attributes))))
1059 (when (and (memq 'general-category attributes)
1060 (setq value (get-char-attribute char 'general-category)))
1062 "(general-category\t%s) ; %s%s"
1063 (mapconcat (lambda (cell)
1066 (cond ((rassoc value unidata-normative-category-alist)
1067 "Normative Category")
1068 ((rassoc value unidata-informative-category-alist)
1069 "Informative Category")
1071 "Unknown Category"))
1073 (setq attributes (delq 'general-category attributes))
1075 (when (and (memq 'bidi-category attributes)
1076 (setq value (get-char-attribute char 'bidi-category)))
1077 (insert (format "(bidi-category\t. %S)%s"
1080 (setq attributes (delq 'bidi-category attributes))
1082 (unless (or (not (memq 'mirrored attributes))
1083 (eq (setq value (get-char-attribute char 'mirrored 'empty))
1085 (insert (format "(mirrored\t\t. %S)%s"
1088 (setq attributes (delq 'mirrored attributes))
1091 ((and (memq 'decimal-digit-value attributes)
1092 (setq value (get-char-attribute char 'decimal-digit-value)))
1093 (insert (format "(decimal-digit-value . %S)%s"
1096 (setq attributes (delq 'decimal-digit-value attributes))
1097 (when (and (memq 'digit-value attributes)
1098 (setq value (get-char-attribute char 'digit-value)))
1099 (insert (format "(digit-value\t . %S)%s"
1102 (setq attributes (delq 'digit-value attributes))
1104 (when (and (memq 'numeric-value attributes)
1105 (setq value (get-char-attribute char 'numeric-value)))
1106 (insert (format "(numeric-value\t . %S)%s"
1109 (setq attributes (delq 'numeric-value attributes))
1113 (when (and (memq 'digit-value attributes)
1114 (setq value (get-char-attribute char 'digit-value)))
1115 (insert (format "(digit-value\t. %S)%s"
1118 (setq attributes (delq 'digit-value attributes))
1120 (when (and (memq 'numeric-value attributes)
1121 (setq value (get-char-attribute char 'numeric-value)))
1122 (insert (format "(numeric-value\t. %S)%s"
1125 (setq attributes (delq 'numeric-value attributes))
1127 (when (and (memq 'iso-10646-comment attributes)
1128 (setq value (get-char-attribute char 'iso-10646-comment)))
1129 (insert (format "(iso-10646-comment\t. %S)%s"
1132 (setq attributes (delq 'iso-10646-comment attributes))
1134 (when (and (memq 'morohashi-daikanwa attributes)
1135 (setq value (get-char-attribute char 'morohashi-daikanwa)))
1136 (insert (format "(morohashi-daikanwa\t%s)%s"
1137 (mapconcat (function prin1-to-string) value " ")
1139 (setq attributes (delq 'morohashi-daikanwa attributes))
1143 (when (and (memq 'ideographic-radical attributes)
1144 (setq value (get-char-attribute char 'ideographic-radical)))
1145 (setq radical value)
1146 (insert (format "(ideographic-radical . %S)\t; %c%s"
1148 (ideographic-radical radical)
1150 (setq attributes (delq 'ideographic-radical attributes))
1152 (when (and (memq 'shuowen-radical attributes)
1153 (setq value (get-char-attribute char 'shuowen-radical)))
1154 (insert (format "(shuowen-radical\t. %S)\t; %c%s"
1156 (shuowen-radical value)
1158 (setq attributes (delq 'shuowen-radical attributes))
1163 char-db-feature-domains
1165 (dolist (feature (char-attribute-list))
1166 (setq feature (symbol-name feature))
1168 "\\(radical\\|strokes\\)@\\([^@*]+\\)\\(\\*\\|$\\)"
1170 (setq domain (intern (match-string 2 feature)))
1171 (unless (memq domain dest)
1172 (setq dest (cons domain dest)))))
1173 (sort dest #'string<))))
1174 (setq key (intern (format "%s@%s" 'ideographic-radical domain)))
1175 (when (and (memq key attributes)
1176 (setq value (get-char-attribute char key)))
1177 (setq radical value)
1178 (insert (format "(%s . %S)\t; %c%s"
1181 (ideographic-radical radical)
1183 (setq attributes (delq key attributes))
1185 (setq key (intern (format "%s@%s" 'ideographic-strokes domain)))
1186 (when (and (memq key attributes)
1187 (setq value (get-char-attribute char key)))
1188 (setq strokes value)
1189 (insert (format "(%s . %S)%s"
1193 (setq attributes (delq key attributes))
1195 (setq key (intern (format "%s@%s" 'total-strokes domain)))
1196 (when (and (memq key attributes)
1197 (setq value (get-char-attribute char key)))
1198 (insert (format "(%s . %S)%s"
1202 (setq attributes (delq key attributes))
1204 (dolist (feature '(ideographic-radical
1207 (setq key (intern (format "%s@%s*sources" feature domain)))
1208 (when (and (memq key attributes)
1209 (setq value (get-char-attribute char key)))
1210 (insert (format "(%s%s" key line-breaking))
1211 (dolist (cell value)
1212 (insert (format " %s" cell)))
1214 (insert line-breaking)
1215 (setq attributes (delq key attributes))
1218 (when (and (memq 'ideographic-strokes attributes)
1219 (setq value (get-char-attribute char 'ideographic-strokes)))
1220 (setq strokes value)
1221 (insert (format "(ideographic-strokes . %S)%s"
1224 (setq attributes (delq 'ideographic-strokes attributes))
1226 (when (and (memq 'kangxi-radical attributes)
1227 (setq value (get-char-attribute char 'kangxi-radical)))
1228 (unless (eq value radical)
1229 (insert (format "(kangxi-radical\t . %S)\t; %c%s"
1231 (ideographic-radical value)
1234 (setq radical value)))
1235 (setq attributes (delq 'kangxi-radical attributes))
1237 (when (and (memq 'kangxi-strokes attributes)
1238 (setq value (get-char-attribute char 'kangxi-strokes)))
1239 (unless (eq value strokes)
1240 (insert (format "(kangxi-strokes\t . %S)%s"
1244 (setq strokes value)))
1245 (setq attributes (delq 'kangxi-strokes attributes))
1247 ;; (when (and (memq 'japanese-radical attributes)
1248 ;; (setq value (get-char-attribute char 'japanese-radical)))
1249 ;; (unless (eq value radical)
1250 ;; (insert (format "(japanese-radical\t . %S)\t; %c%s"
1252 ;; (ideographic-radical value)
1255 ;; (setq radical value)))
1256 ;; (setq attributes (delq 'japanese-radical attributes))
1258 (when (and (memq 'japanese-strokes attributes)
1259 (setq value (get-char-attribute char 'japanese-strokes)))
1260 (unless (eq value strokes)
1261 (insert (format "(japanese-strokes\t . %S)%s"
1265 (setq strokes value)))
1266 (setq attributes (delq 'japanese-strokes attributes))
1268 (when (and (memq 'cns-radical attributes)
1269 (setq value (get-char-attribute char 'cns-radical)))
1270 (insert (format "(cns-radical\t . %S)\t; %c%s"
1272 (ideographic-radical value)
1274 (setq attributes (delq 'cns-radical attributes))
1276 (when (and (memq 'cns-strokes attributes)
1277 (setq value (get-char-attribute char 'cns-strokes)))
1278 (unless (eq value strokes)
1279 (insert (format "(cns-strokes\t . %S)%s"
1283 (setq strokes value)))
1284 (setq attributes (delq 'cns-strokes attributes))
1286 ;; (when (and (memq 'ideographic- attributes)
1287 ;; (setq value (get-char-attribute char 'ideographic-)))
1288 ;; (insert "(ideographic- ")
1289 ;; (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1291 ;; (while (consp value)
1292 ;; (setq cell (car value))
1293 ;; (if (integerp cell)
1294 ;; (setq cell (decode-char '=ucs cell)))
1295 ;; (cond ((characterp cell)
1299 ;; (insert (format "%S" cell))
1300 ;; (char-db-insert-char-spec cell readable))
1301 ;; (setq separator lbs))
1305 ;; (if (consp (car cell))
1306 ;; (char-db-insert-char-spec cell readable)
1307 ;; (char-db-insert-char-reference cell readable))
1308 ;; (setq separator lbs))
1311 ;; (insert separator))
1312 ;; (insert (prin1-to-string cell))
1313 ;; (setq separator " ")))
1314 ;; (setq value (cdr value)))
1316 ;; (insert line-breaking)
1317 ;; (setq attributes (delq 'ideographic- attributes)))
1318 (when (and (memq 'total-strokes attributes)
1319 (setq value (get-char-attribute char 'total-strokes)))
1320 (insert (format "(total-strokes . %S)%s"
1323 (setq attributes (delq 'total-strokes attributes))
1325 ;; (when (and (memq '->ideograph attributes)
1326 ;; (setq value (get-char-attribute char '->ideograph)))
1327 ;; (insert (format "(->ideograph\t%s)%s"
1328 ;; (mapconcat (lambda (code)
1329 ;; (cond ((symbolp code)
1330 ;; (symbol-name code))
1332 ;; (format "#x%04X" code))
1335 ;; line-breaking code))))
1338 ;; (setq attributes (delq '->ideograph attributes))
1340 ;; (when (and (memq '->decomposition attributes)
1341 ;; (setq value (get-char-attribute char '->decomposition)))
1342 ;; (insert (format "(->decomposition\t%s)%s"
1343 ;; (mapconcat (lambda (code)
1344 ;; (cond ((symbolp code)
1345 ;; (symbol-name code))
1346 ;; ((characterp code)
1348 ;; (format "%S" code)
1353 ;; (format "#x%04X" code))
1355 ;; (format "%s%S" line-breaking code))))
1358 ;; (setq attributes (delq '->decomposition attributes))
1360 (if (equal (get-char-attribute char '->titlecase)
1361 (get-char-attribute char '->uppercase))
1362 (setq attributes (delq '->titlecase attributes)))
1363 (when (and (memq '->mojikyo attributes)
1364 (setq value (get-char-attribute char '->mojikyo)))
1365 (insert (format "(->mojikyo\t\t. %06d)\t; %c%s"
1366 value (decode-char 'mojikyo value)
1368 (setq attributes (delq '->mojikyo attributes))
1371 (dolist (ignored '(composition
1372 ->denotational <-subsumptive ->ucs-unified
1373 ;; ->ideographic-component-forms
1375 (setq attributes (delq ignored attributes))))
1377 (setq name (car attributes))
1378 (unless (eq (setq value (get-char-attribute char name 'value-is-empty))
1380 (cond ((setq ret (find-charset name))
1381 (setq name (charset-name ret))
1382 (when (not (memq name dest-ccss))
1383 (setq dest-ccss (cons name dest-ccss))
1384 (char-db-insert-ccs-feature name value line-breaking))
1386 ((string-match "^=>ucs@" (symbol-name name))
1387 (insert (format "(%-18s . #x%04X)\t; %c%s"
1388 name value (decode-char '=ucs value)
1391 ((eq name 'jisx0208-1978/4X)
1392 (insert (format "(%-18s . #x%04X)%s"
1398 (not (eq name '->subsumptive))
1399 (not (eq name '->uppercase))
1400 (not (eq name '->lowercase))
1401 (not (eq name '->titlecase))
1402 (not (eq name '->canonical))
1403 (not (eq name '->Bopomofo))
1404 (not (eq name '->mistakable))
1405 (not (eq name '->ideographic-variants))
1406 (null (get-char-attribute
1407 char (intern (format "%s*sources" name))))
1408 (not (string-match "\\*sources$" (symbol-name name)))
1409 (null (get-char-attribute
1410 char (intern (format "%s*note" name))))
1411 (not (string-match "\\*note$" (symbol-name name)))
1412 (or (eq name '<-identical)
1413 (eq name '<-uppercase)
1414 (eq name '<-lowercase)
1415 (eq name '<-titlecase)
1416 (eq name '<-canonical)
1417 (eq name '<-ideographic-variants)
1418 ;; (eq name '<-synonyms)
1419 (string-match "^<-synonyms" (symbol-name name))
1420 (eq name '<-mistakable)
1421 (when (string-match "^->" (symbol-name name))
1423 ((string-match "^->fullwidth" (symbol-name name))
1424 (not (and (consp value)
1425 (characterp (car value))
1427 (car value) '=ucs 'defined-only)))
1432 ((or (eq name 'ideographic-structure)
1433 (eq name 'ideographic-structure@apparent)
1434 (eq name 'ideographic-structure@apparent/leftmost)
1435 (eq name 'ideographic-combination)
1436 ;; (eq name 'ideographic-)
1437 (eq name '=decomposition)
1438 (char-feature-base-name= '=decomposition name)
1439 (char-feature-base-name= '=>decomposition name)
1440 ;; (string-match "^=>*decomposition\\(@[^*]+\\)?$"
1441 ;; (symbol-name name))
1442 (string-match "^\\(->\\|<-\\)[^*]*$" (symbol-name name))
1443 (string-match "^\\(->\\|<-\\)[^*]*\\*sources$"
1446 (char-db-insert-relation-feature char name value
1449 ;; ((memq name '(ideograph=
1450 ;; original-ideograph-of
1451 ;; ancient-ideograph-of
1452 ;; vulgar-ideograph-of
1453 ;; wrong-ideograph-of
1454 ;; ;; simplified-ideograph-of
1455 ;; ideographic-variants
1456 ;; ;; ideographic-different-form-of
1458 ;; (insert (format "(%-18s%s " name line-breaking))
1459 ;; (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1461 ;; (while (consp value)
1462 ;; (setq cell (car value))
1463 ;; (if (and (consp cell)
1464 ;; (consp (car cell)))
1468 ;; (char-db-insert-alist cell readable)
1469 ;; (setq separator lbs))
1471 ;; (insert separator))
1472 ;; (insert (prin1-to-string cell))
1473 ;; (setq separator " "))
1474 ;; (setq value (cdr value)))
1476 ;; (insert line-breaking))
1478 (insert (format "(%-18s " name))
1479 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1481 (while (consp value)
1482 (setq cell (car value))
1483 (if (and (consp cell)
1485 (setq ret (condition-case nil
1493 (setq key (car (car rest)))
1494 (if (find-charset key)
1495 (setq cal (cons key cal))
1496 (setq al (cons key al)))
1497 (setq rest (cdr rest)))
1500 (insert-char-attributes ret
1504 (setq separator lbs))
1505 (setq ret (prin1-to-string cell))
1507 (if (< (+ (current-column)
1514 (setq separator " "))
1515 (setq value (cdr value)))
1517 (insert line-breaking))
1519 (insert (format "(%-18s" name))
1520 (setq ret (prin1-to-string value))
1521 (unless (< (+ (current-column)
1525 (insert line-breaking))
1526 (insert " . " ret ")" line-breaking)
1527 ;; (insert (format "(%-18s . %S)%s"
1532 (setq attributes (cdr attributes)))
1535 (defun insert-char-data (char &optional readable
1538 (narrow-to-region (point)(point))
1539 (insert "(define-char
1541 (insert-char-attributes char readable attributes)
1543 (goto-char (point-min))
1544 (while (re-search-forward "[ \t]+$" nil t)
1547 (goto-char (point-min))
1548 (while (re-search-forward "[ \t][ \t][ \t]*" nil t)
1549 (let ((column (current-column))
1550 (indent-tabs-mode t))
1551 (delete-region (match-beginning 0) (point))
1552 (indent-to column)))
1553 (goto-char (point-max))
1554 ;; (tabify (point-min)(point-max))
1557 (defun insert-char-data-with-variant (char &optional printable
1559 script excluded-script)
1560 (insert-char-data char printable)
1561 (let ((variants (char-variants char))
1564 (setq variants (sort variants #'<))
1565 (setq rest variants)
1566 (setq variants (cons char variants))
1568 (setq variant (car rest))
1569 (unless (get-char-attribute variant '<-subsumptive)
1570 (if (and (or (null script)
1571 (null (setq vs (get-char-attribute variant 'script)))
1573 (or (null excluded-script)
1574 (null (setq vs (get-char-attribute variant 'script)))
1575 (not (memq excluded-script vs))))
1576 (unless (and no-ucs-unified (get-char-attribute variant '=ucs))
1577 (insert-char-data variant printable)
1578 (if (setq ret (char-variants variant))
1580 (or (memq (car ret) variants)
1581 ;; (get-char-attribute (car ret) '<-subsumptive)
1582 (setq rest (nconc rest (list (car ret)))))
1583 (setq ret (cdr ret)))))))
1584 (setq rest (cdr rest)))))
1586 (defun insert-char-range-data (min max &optional script excluded-script)
1589 (while (<= code max)
1590 (setq char (decode-char '=ucs code))
1591 (if (encode-char char '=ucs 'defined-only)
1592 (insert-char-data-with-variant char nil 'no-ucs-unified
1593 script excluded-script))
1594 (setq code (1+ code)))))
1596 (defun write-char-range-data-to-file (min max file
1597 &optional script excluded-script)
1598 (let ((coding-system-for-write char-db-file-coding-system))
1600 (insert (format ";; -*- coding: %s -*-\n"
1601 char-db-file-coding-system))
1602 (insert-char-range-data min max script excluded-script)
1603 (write-region (point-min)(point-max) file))))
1605 (defvar what-character-original-window-configuration)
1608 (defun what-char-definition (char)
1609 (interactive (list (char-after)))
1610 (let ((buf (get-buffer-create "*Character Description*"))
1611 (the-buf (current-buffer))
1612 (win-conf (current-window-configuration)))
1614 (make-local-variable 'what-character-original-window-configuration)
1615 (setq what-character-original-window-configuration win-conf)
1616 (setq buffer-read-only nil)
1620 (insert-char-data-with-variant char 'printable)
1621 (unless (char-attribute-alist char)
1622 (insert (format ";; = %c\n"
1623 (let* ((rest (split-char char))
1627 (setq code (logior (lsh code 8)
1629 (decode-char ccs code)))))
1630 ;; (char-db-update-comment)
1631 (set-buffer-modified-p nil)
1632 (view-mode the-buf (lambda (buf)
1633 (set-window-configuration
1634 what-character-original-window-configuration)
1636 (goto-char (point-min)))
1638 (set-window-configuration
1639 what-character-original-window-configuration)
1640 (signal (car err) (cdr err)))))))
1646 (provide 'char-db-util)
1648 ;;; char-db-util.el ends here