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 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 ?廾 ?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 ?𠧪 ?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
232 ;; =>>>adobe-japan1-0
233 ;; =>>>adobe-japan1-1
234 ;; =>>>adobe-japan1-2
235 ;; =>>>adobe-japan1-3
236 ;; =>>>adobe-japan1-4
237 ;; =>>>adobe-japan1-5
238 ;; =>>>adobe-japan1-6
242 ;; =>>>hanyo-denshi/ja
243 ;; =>>>hanyo-denshi/jb
244 ;; =>>>hanyo-denshi/jc
245 ;; =>>>hanyo-denshi/ft
246 ;; =>>>hanyo-denshi/ib
247 ;; =>>>hanyo-denshi/hg
248 ;; =>>>hanyo-denshi/jt
249 ;; =>>>hanyo-denshi/ks
289 ;; =>ucs@hanyo-denshi
398 =>big5-cdp-itaiji-001
399 =>big5-cdp-itaiji-002
400 =>big5-cdp-itaiji-003
401 =>big5-cdp-itaiji-004
406 =>ucs@iwds-1/normalized
407 =>ucs-itaiji-001@iwds-1
408 =>ucs-itaiji-002@iwds-1
417 ;;; @ char-db formatters
420 (defun char-db-make-char-spec (char)
422 (cond ((characterp char)
423 (cond ((and (setq ret (encode-char char '=ucs 'defined-only))
424 (not (and (<= #xE000 ret)(<= ret #xF8FF))))
425 (setq char-spec (list (cons '=ucs ret)))
426 (cond ((setq ret (get-char-attribute char 'name))
427 (setq char-spec (cons (cons 'name ret) char-spec))
429 ((setq ret (get-char-attribute char 'name*))
430 (setq char-spec (cons (cons 'name* ret) char-spec))
433 ((encode-char char '=mj 'defined-only)
435 (dolist (ccs (charset-list))
436 (if (and (or (eq ccs '=mj)
437 ;; (eq (charset-property ccs 'iso-ir) 177)
438 (string-match "=ucs@" (symbol-name ccs))
440 (setq ccs (charset-name ccs))
441 (null (assq ccs char-spec))
442 (setq ret (encode-char char ccs 'defined-only)))
443 (setq char-spec (cons (cons ccs ret) char-spec))))
445 ((encode-char char '==mj 'defined-only)
447 (dolist (ccs (charset-list))
448 (if (and (or (eq ccs '==mj)
449 ;; (eq (charset-property ccs 'iso-ir) 177)
450 (string-match "=ucs@" (symbol-name ccs))
452 (setq ccs (charset-name ccs))
453 (null (assq ccs char-spec))
454 (setq ret (encode-char char ccs 'defined-only)))
455 (setq char-spec (cons (cons ccs ret) char-spec))))
457 ((encode-char char '=adobe-japan1 'defined-only)
459 (dolist (ccs (charset-list))
460 (if (and (or (memq ccs
469 ;; (eq (charset-property ccs 'iso-ir) 177)
470 (string-match "=ucs@" (symbol-name ccs))
472 (setq ccs (charset-name ccs))
473 (null (assq ccs char-spec))
474 (setq ret (encode-char char ccs 'defined-only)))
475 (setq char-spec (cons (cons ccs ret) char-spec))))
477 ((encode-char char '==adobe-japan1 'defined-only)
479 (dolist (ccs (charset-list))
480 (if (and (or (memq ccs
489 ;; (eq (charset-property ccs 'iso-ir) 177)
490 (string-match "=ucs@" (symbol-name ccs))
492 (setq ccs (charset-name ccs))
493 (null (assq ccs char-spec))
494 (setq ret (encode-char char ccs 'defined-only)))
495 (setq char-spec (cons (cons ccs ret) char-spec))))
499 (let ((rest char-db-coded-charset-priority-list)
502 (setq ccs (charset-name
503 (find-charset (car rest))))
505 (encode-char char ccs
507 (throw 'tag (cons ccs ret)))
508 (setq rest (cdr rest))))))
509 (setq char-spec (list ret))
510 (dolist (ccs (delq (car ret) (charset-list)))
511 (if (and (or (charset-iso-final-char ccs)
518 (and (eq (charset-property ccs 'iso-ir) 177)
519 (not (eq (charset-name ccs) '=ucs@big5)))
520 ;; (string-match "=ucs@" (symbol-name ccs))
522 (setq ccs (charset-name ccs))
523 (null (assq ccs char-spec))
524 (setq ret (encode-char char ccs 'defined-only)))
525 (setq char-spec (cons (cons ccs ret) char-spec))))
527 (setq char-spec (split-char char)))
528 (cond ((setq ret (get-char-attribute char 'name))
529 (setq char-spec (cons (cons 'name ret) char-spec))
531 ((setq ret (get-char-attribute char 'name*))
532 (setq char-spec (cons (cons 'name* ret) char-spec))
535 ((setq ret (get-char-attribute
536 char 'ideographic-combination))
538 (cons (cons 'ideographic-combination ret)
545 (defun char-db-insert-char-spec (char &optional readable column
548 (setq column (current-column)))
549 (let (char-spec temp-char)
550 (setq char-spec (char-db-make-char-spec char))
551 (unless (or (characterp char) ; char
553 (setq char (find-char char-spec))
555 ;; define temporary character
556 ;; Current implementation is dirty.
557 (setq temp-char (define-char (cons '(ideograph-daikanwa . 0)
559 (remove-char-attribute temp-char 'ideograph-daikanwa)
560 (setq char temp-char))
561 (insert-char-attributes char
563 (union (mapcar #'car char-spec)
567 ;; undefine temporary character
568 ;; Current implementation is dirty.
569 (setq char-spec (char-attribute-alist temp-char))
571 (remove-char-attribute temp-char (car (car char-spec)))
572 (setq char-spec (cdr char-spec))))))
574 (defun char-db-insert-alist (alist &optional readable column)
576 (setq column (current-column)))
578 (concat "\n" (make-string (1+ column) ?\ )))
582 lbs cell rest separator)
585 (setq name (car (car alist))
586 value (cdr (car alist)))
587 (cond ((eq name 'char)
589 (if (setq ret (condition-case nil
597 (setq key (car (car value)))
598 ;; (if (find-charset key)
599 ;; (setq cal (cons key cal))
600 (setq al (cons key al))
602 (setq value (cdr value)))
603 (insert-char-attributes ret
607 (insert (prin1-to-string value)))
609 (insert line-breaking))
611 (insert (format "(%-18s " name))
612 (setq lbs (concat "\n" (make-string (current-column) ?\ )))
614 (setq cell (car value))
615 (if (and (consp cell)
617 (setq ret (condition-case nil
627 (setq key (car (car rest)))
628 ;; (if (find-charset key)
629 ;; (setq cal (cons key cal))
630 (setq al (cons key al))
632 (setq rest (cdr rest)))
635 (insert-char-attributes ret
639 (setq separator lbs))
642 (insert (prin1-to-string cell))
643 (setq separator " "))
644 (setq value (cdr value)))
646 (insert line-breaking))
648 (insert (format "(%-18s . %S)%s"
651 (setq alist (cdr alist))))
654 (defun char-db-insert-char-reference (plist &optional readable column)
656 (setq column (current-column)))
658 (concat "\n" (make-string (1+ column) ?\ )))
663 (setq name (pop plist))
664 (setq value (pop plist))
665 (cond ((eq name :char)
668 (cond ((numberp value)
669 (setq value (decode-char '=ucs value)))
671 ;; (setq value (or (find-char value)
674 (char-db-insert-char-spec value readable)
675 (insert line-breaking)
678 (insert (format "%s%s\t%d ; %c%s"
681 (ideographic-radical value)
685 (insert (format "%s%s\t%S" separator name value))
686 (setq separator line-breaking)))
690 (defun char-db-decode-isolated-char (ccs code-point)
693 (cond ((eq ccs 'arabic-iso8859-6)
694 (decode-char ccs code-point))
696 ;; (decode-builtin-char '==gt code-point))
697 ((and (memq ccs '(=gt-pj-1
708 (setq ret (decode-char ccs code-point))
709 (setq ret (encode-char ret '=gt 'defined-only)))
710 (decode-builtin-char '=gt ret))
712 (decode-builtin-char ccs code-point))))
714 (or (decode-char ccs code-point)
715 (define-char (list (cons ccs code-point)))))
716 ((and (<= 0 (char-int ret))
717 (<= (char-int ret) #x1F))
718 (decode-char '=ucs (+ #x2400 (char-int ret))))
719 ((= (char-int ret) #x7F)
723 (defvar char-db-convert-obsolete-format t)
725 (defun char-db-insert-ccs-feature (name value line-breaking)
731 ((memq name '(=>iwds-1
734 =shinjigen@1ed ==shinjigen@1ed
735 =shinjigen@rev ==shinjigen@rev
736 =shinjigen/+p@rev ==shinjigen/+p@rev
737 ===daikanwa/ho ==daikanwa/ho
738 =daikanwa/ho =>>daikanwa/ho =>daikanwa/ho))
739 "(%-18s . %04d)\t; %c")
740 ((eq name '=shinjigen@1ed/24pr)
741 "(%-18s . %04d)\t; %c")
745 ==daikanwa =daikanwa =>>daikanwa =>daikanwa
746 =daikanwa@rev1 =daikanwa@rev2
747 =daikanwa/+p ==daikanwa/+p ===daikanwa/+p
749 =daikanwa/+2p =>>daikanwa/+2p
754 =adobe-japan1-0 ==adobe-japan1-0 ===adobe-japan1-0
755 =adobe-japan1-1 ==adobe-japan1-1 ===adobe-japan1-1
756 =adobe-japan1-2 ==adobe-japan1-2 ===adobe-japan1-2
757 =adobe-japan1-3 ==adobe-japan1-3 ===adobe-japan1-3
758 =adobe-japan1-4 ==adobe-japan1-4 ===adobe-japan1-4
759 =adobe-japan1-5 ==adobe-japan1-5 ===adobe-japan1-5
760 =adobe-japan1-6 ==adobe-japan1-6 ===adobe-japan1-6
761 =>>adobe-japan1-0 =+>adobe-japan1-0
762 =>>adobe-japan1-1 =+>adobe-japan1-1
763 =>>adobe-japan1-2 =+>adobe-japan1-2
764 =>>adobe-japan1-3 =+>adobe-japan1-3
765 =>>adobe-japan1-4 =+>adobe-japan1-4
766 =>>adobe-japan1-5 =+>adobe-japan1-5
767 =>>adobe-japan1-6 =+>adobe-japan1-6
768 =>cbeta =cbeta =>>cbeta ==cbeta ===cbeta
769 =zinbun-oracle =>zinbun-oracle
770 =daijiten ==daijiten ===daijiten ==>daijiten
771 ===hng-jou ===hng-keg ===hng-dng ===hng-mam
772 ===hng-drt ===hng-kgk ===hng-myz ===hng-kda
773 ===hng-khi ===hng-khm ===hng-fhs ===hng-hok
774 ===hng-kyd ===hng-sok
775 ===hng-yhk ===hng-kak ===hng-kar ===hng-kae
776 ===hng-sys ===hng-tsu ===hng-tzj
777 ===hng-hos ===hng-kkh ===hng-nak ===hng-jhk
778 ===hng-hod ===hng-gok ===hng-ink ===hng-nto
779 ===hng-nkm ===hng-k24 ===hng-ini ===hng-nkk
780 ===hng-kcc ===hng-kcj ===hng-kbk ===hng-sik
781 ===hng-skk ===hng-kyu ===hng-ksk ===hng-wan
782 ===hng-okd ===hng-wad ===hng-kmi
783 ===hng-zkd ===hng-doh ===hng-jyu ===hng-tzs
784 ===hng-sai ===hng-kad ===hng-kss
785 ===hng-kyo ===hng-ykk ===hng-saa
786 ===hng-sab ===hng-wks ===hng-wke ===hng-smk
787 ===hng-sgs ===hng-sts
788 =shuowen-jiguge ===shuowen-jiguge4 ===shuowen-jiguge5))
789 ;; (string-match "^=adobe-" (symbol-name name))
791 "(%-18s . %05d)\t; %c")
792 ((memq name '(=hanyo-denshi/ks
793 ==hanyo-denshi/ks ===hanyo-denshi/ks
796 =mj ==mj ===mj =>>mj =>mj
798 "(%-18s . %06d)\t; %c")
799 ((memq name '(=hanyo-denshi/tk ==hanyo-denshi/tk))
800 "(%-18s . %08d)\t; %c")
801 ((>= (charset-dimension name) 2)
802 "(%-18s . #x%04X)\t; %c")
804 "(%-18s . #x%02X)\t; %c"))
806 (if (= (charset-iso-graphic-plane name) 1)
808 (cond ((= (charset-dimension name) 1)
810 ((= (charset-dimension name) 2)
812 ((= (charset-dimension name) 3)
816 (char-db-decode-isolated-char name value)))
817 (if (and (= (charset-chars name) 94)
818 (= (charset-dimension name) 2))
819 (insert (format " [%02d-%02d]"
820 (- (lsh value -8) 32)
821 (- (logand value 255) 32))))
824 (insert (format "(%-18s . %s)" name value))
826 (insert line-breaking))
828 (defun char-db-insert-relation-feature (char name value line-breaking
830 (insert (format "(%-18s%s " name line-breaking))
831 (let ((lbs (concat "\n" (make-string (current-column) ?\ )))
832 separator cell sources required-features
835 (setq cell (car value))
837 (setq cell (decode-char '=ucs cell)))
839 ((eq name '->subsumptive)
840 (when (or (not (some (lambda (atr)
841 (get-char-attribute cell atr))
842 char-db-ignored-attributes))
844 (encode-char cell ccs 'defined-only))
848 (let ((char-db-ignored-attributes
850 char-db-ignored-attributes)))
851 (insert-char-attributes cell readable nil nil 'for-sub-node))
852 (setq separator lbs))
857 char (intern (format "%s*sources" name))))
858 (setq required-features nil)
859 (dolist (source sources)
863 shinjigen shinjigen@1ed shinjigen@rev))
864 (setq required-features
865 (union required-features
877 =shinjigen/+p@rev))))
879 (setq required-features
880 (union required-features
885 ((find-charset (setq ret (intern (format "=%s" source))))
886 (setq required-features
887 (cons ret required-features)))
888 (t (setq required-features
889 (cons source required-features)))))
890 (cond ((string-match "@JP" (symbol-name name))
891 (setq required-features
892 (union required-features
900 ((string-match "@CN" (symbol-name name))
901 (setq required-features
902 (union required-features
909 (insert (format "%S" cell))
910 (char-db-insert-char-spec cell readable
913 (setq separator lbs))
917 (if (consp (car cell))
918 (char-db-insert-char-spec cell readable)
919 (char-db-insert-char-reference cell readable))
920 (setq separator lbs))
924 (insert (prin1-to-string cell))
925 (setq separator " ")))
926 (setq value (cdr value)))
928 (insert line-breaking)))
930 (defun insert-char-attributes (char &optional readable attributes column
933 (setq column (current-column)))
934 (let (name value ; has-long-ccs-name
938 (concat "\n" (make-string (1+ column) ?\ )))
939 lbs cell separator ret
941 dest-ccss ; sources required-features
946 (if (consp attributes)
948 (dolist (name attributes)
949 (unless (memq name char-db-ignored-attributes)
950 (if (find-charset name)
954 (dolist (name (char-attribute-list))
955 (unless (memq name char-db-ignored-attributes)
956 (if (find-charset name)
960 #'char-attribute-name<)))
962 (when (memq '<-subsumptive attributes)
963 (when (or readable (not for-sub-node))
964 (when (setq value (get-char-attribute char '<-subsumptive))
965 (char-db-insert-relation-feature char '<-subsumptive value
968 (setq attributes (delq '<-subsumptive attributes)))
969 (when (and (memq '<-denotational attributes)
970 (setq value (get-char-attribute char '<-denotational)))
971 (char-db-insert-relation-feature char '<-denotational value
974 (setq attributes (delq '<-denotational attributes)))
975 (when (and (memq '<-denotational@component attributes)
976 (setq value (get-char-attribute char '<-denotational@component)))
977 (char-db-insert-relation-feature char '<-denotational@component value
980 (setq attributes (delq '<-denotational@component attributes)))
981 (when (and (memq '<-denotational@usage attributes)
982 (setq value (get-char-attribute char '<-denotational@usage)))
983 (char-db-insert-relation-feature char '<-denotational@usage value
986 (setq attributes (delq '<-denotational@usage attributes)))
987 (when (and (memq 'name attributes)
988 (setq value (get-char-attribute char 'name)))
990 (if (> (+ (current-column) (length value)) 48)
993 value line-breaking))
994 (setq attributes (delq 'name attributes))
996 (when (and (memq 'name* attributes)
997 (setq value (get-char-attribute char 'name*)))
999 (if (> (+ (current-column) (length value)) 48)
1002 value line-breaking))
1003 (setq attributes (delq 'name* attributes))
1005 (when (and (memq 'script attributes)
1006 (setq value (get-char-attribute char 'script)))
1007 (insert (format "(script\t\t%s)%s"
1008 (mapconcat (function prin1-to-string)
1011 (setq attributes (delq 'script attributes))
1013 (dolist (name '(=>ucs =>ucs*))
1014 (when (and (memq name attributes)
1015 (setq value (get-char-attribute char name)))
1016 (insert (format "(%-18s . #x%04X)\t; %c%s"
1017 name value (decode-char '=ucs value)
1019 (setq attributes (delq name attributes))))
1020 (dolist (name '(=>ucs@gb =>ucs@big5))
1021 (when (and (memq name attributes)
1022 (setq value (get-char-attribute char name)))
1023 (insert (format "(%-18s . #x%04X)\t; %c%s"
1025 (decode-char (intern
1028 (symbol-name name) 2)))
1031 (setq attributes (delq name attributes))
1033 ;; (dolist (name '(=>daikanwa))
1034 ;; (when (and (memq name attributes)
1035 ;; (setq value (get-char-attribute char name)))
1037 ;; (if (integerp value)
1038 ;; (format "(%-18s . %05d)\t; %c%s"
1039 ;; name value (decode-char '=daikanwa value)
1041 ;; (format "(%-18s %s)\t; %c%s"
1043 ;; (mapconcat (function prin1-to-string)
1045 ;; (char-representative-of-daikanwa char)
1047 ;; (setq attributes (delq name attributes))))
1048 (when (and (memq 'general-category attributes)
1049 (setq value (get-char-attribute char 'general-category)))
1051 "(general-category\t%s) ; %s%s"
1052 (mapconcat (lambda (cell)
1055 (cond ((rassoc value unidata-normative-category-alist)
1056 "Normative Category")
1057 ((rassoc value unidata-informative-category-alist)
1058 "Informative Category")
1060 "Unknown Category"))
1062 (setq attributes (delq 'general-category attributes))
1064 (when (and (memq 'bidi-category attributes)
1065 (setq value (get-char-attribute char 'bidi-category)))
1066 (insert (format "(bidi-category\t. %S)%s"
1069 (setq attributes (delq 'bidi-category attributes))
1071 (unless (or (not (memq 'mirrored attributes))
1072 (eq (setq value (get-char-attribute char 'mirrored 'empty))
1074 (insert (format "(mirrored\t\t. %S)%s"
1077 (setq attributes (delq 'mirrored attributes))
1080 ((and (memq 'decimal-digit-value attributes)
1081 (setq value (get-char-attribute char 'decimal-digit-value)))
1082 (insert (format "(decimal-digit-value . %S)%s"
1085 (setq attributes (delq 'decimal-digit-value attributes))
1086 (when (and (memq 'digit-value attributes)
1087 (setq value (get-char-attribute char 'digit-value)))
1088 (insert (format "(digit-value\t . %S)%s"
1091 (setq attributes (delq 'digit-value attributes))
1093 (when (and (memq 'numeric-value attributes)
1094 (setq value (get-char-attribute char 'numeric-value)))
1095 (insert (format "(numeric-value\t . %S)%s"
1098 (setq attributes (delq 'numeric-value attributes))
1102 (when (and (memq 'digit-value attributes)
1103 (setq value (get-char-attribute char 'digit-value)))
1104 (insert (format "(digit-value\t. %S)%s"
1107 (setq attributes (delq 'digit-value attributes))
1109 (when (and (memq 'numeric-value attributes)
1110 (setq value (get-char-attribute char 'numeric-value)))
1111 (insert (format "(numeric-value\t. %S)%s"
1114 (setq attributes (delq 'numeric-value attributes))
1116 (when (and (memq 'iso-10646-comment attributes)
1117 (setq value (get-char-attribute char 'iso-10646-comment)))
1118 (insert (format "(iso-10646-comment\t. %S)%s"
1121 (setq attributes (delq 'iso-10646-comment attributes))
1123 (when (and (memq 'morohashi-daikanwa attributes)
1124 (setq value (get-char-attribute char 'morohashi-daikanwa)))
1125 (insert (format "(morohashi-daikanwa\t%s)%s"
1126 (mapconcat (function prin1-to-string) value " ")
1128 (setq attributes (delq 'morohashi-daikanwa attributes))
1132 (when (and (memq 'ideographic-radical attributes)
1133 (setq value (get-char-attribute char 'ideographic-radical)))
1134 (setq radical value)
1135 (insert (format "(ideographic-radical . %S)\t; %c%s"
1137 (ideographic-radical radical)
1139 (setq attributes (delq 'ideographic-radical attributes))
1141 (when (and (memq 'shuowen-radical attributes)
1142 (setq value (get-char-attribute char 'shuowen-radical)))
1143 (insert (format "(shuowen-radical\t. %S)\t; %c%s"
1145 (shuowen-radical value)
1147 (setq attributes (delq 'shuowen-radical attributes))
1152 char-db-feature-domains
1154 (dolist (feature (char-attribute-list))
1155 (setq feature (symbol-name feature))
1157 "\\(radical\\|strokes\\)@\\([^@*]+\\)\\(\\*\\|$\\)"
1159 (setq domain (intern (match-string 2 feature)))
1160 (unless (memq domain dest)
1161 (setq dest (cons domain dest)))))
1162 (sort dest #'string<))))
1163 (setq key (intern (format "%s@%s" 'ideographic-radical domain)))
1164 (when (and (memq key attributes)
1165 (setq value (get-char-attribute char key)))
1166 (setq radical value)
1167 (insert (format "(%s . %S)\t; %c%s"
1170 (ideographic-radical radical)
1172 (setq attributes (delq key attributes))
1174 (setq key (intern (format "%s@%s" 'ideographic-strokes domain)))
1175 (when (and (memq key attributes)
1176 (setq value (get-char-attribute char key)))
1177 (setq strokes value)
1178 (insert (format "(%s . %S)%s"
1182 (setq attributes (delq key attributes))
1184 (setq key (intern (format "%s@%s" 'total-strokes domain)))
1185 (when (and (memq key attributes)
1186 (setq value (get-char-attribute char key)))
1187 (insert (format "(%s . %S)%s"
1191 (setq attributes (delq key attributes))
1193 (dolist (feature '(ideographic-radical
1196 (setq key (intern (format "%s@%s*sources" feature domain)))
1197 (when (and (memq key attributes)
1198 (setq value (get-char-attribute char key)))
1199 (insert (format "(%s%s" key line-breaking))
1200 (dolist (cell value)
1201 (insert (format " %s" cell)))
1203 (insert line-breaking)
1204 (setq attributes (delq key attributes))
1207 (when (and (memq 'ideographic-strokes attributes)
1208 (setq value (get-char-attribute char 'ideographic-strokes)))
1209 (setq strokes value)
1210 (insert (format "(ideographic-strokes . %S)%s"
1213 (setq attributes (delq 'ideographic-strokes attributes))
1215 (when (and (memq 'kangxi-radical attributes)
1216 (setq value (get-char-attribute char 'kangxi-radical)))
1217 (unless (eq value radical)
1218 (insert (format "(kangxi-radical\t . %S)\t; %c%s"
1220 (ideographic-radical value)
1223 (setq radical value)))
1224 (setq attributes (delq 'kangxi-radical attributes))
1226 (when (and (memq 'kangxi-strokes attributes)
1227 (setq value (get-char-attribute char 'kangxi-strokes)))
1228 (unless (eq value strokes)
1229 (insert (format "(kangxi-strokes\t . %S)%s"
1233 (setq strokes value)))
1234 (setq attributes (delq 'kangxi-strokes attributes))
1236 ;; (when (and (memq 'japanese-radical attributes)
1237 ;; (setq value (get-char-attribute char 'japanese-radical)))
1238 ;; (unless (eq value radical)
1239 ;; (insert (format "(japanese-radical\t . %S)\t; %c%s"
1241 ;; (ideographic-radical value)
1244 ;; (setq radical value)))
1245 ;; (setq attributes (delq 'japanese-radical attributes))
1247 (when (and (memq 'japanese-strokes attributes)
1248 (setq value (get-char-attribute char 'japanese-strokes)))
1249 (unless (eq value strokes)
1250 (insert (format "(japanese-strokes\t . %S)%s"
1254 (setq strokes value)))
1255 (setq attributes (delq 'japanese-strokes attributes))
1257 (when (and (memq 'cns-radical attributes)
1258 (setq value (get-char-attribute char 'cns-radical)))
1259 (insert (format "(cns-radical\t . %S)\t; %c%s"
1261 (ideographic-radical value)
1263 (setq attributes (delq 'cns-radical attributes))
1265 (when (and (memq 'cns-strokes attributes)
1266 (setq value (get-char-attribute char 'cns-strokes)))
1267 (unless (eq value strokes)
1268 (insert (format "(cns-strokes\t . %S)%s"
1272 (setq strokes value)))
1273 (setq attributes (delq 'cns-strokes attributes))
1275 ;; (when (and (memq 'ideographic- attributes)
1276 ;; (setq value (get-char-attribute char 'ideographic-)))
1277 ;; (insert "(ideographic- ")
1278 ;; (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1280 ;; (while (consp value)
1281 ;; (setq cell (car value))
1282 ;; (if (integerp cell)
1283 ;; (setq cell (decode-char '=ucs cell)))
1284 ;; (cond ((characterp cell)
1288 ;; (insert (format "%S" cell))
1289 ;; (char-db-insert-char-spec cell readable))
1290 ;; (setq separator lbs))
1294 ;; (if (consp (car cell))
1295 ;; (char-db-insert-char-spec cell readable)
1296 ;; (char-db-insert-char-reference cell readable))
1297 ;; (setq separator lbs))
1300 ;; (insert separator))
1301 ;; (insert (prin1-to-string cell))
1302 ;; (setq separator " ")))
1303 ;; (setq value (cdr value)))
1305 ;; (insert line-breaking)
1306 ;; (setq attributes (delq 'ideographic- attributes)))
1307 (when (and (memq 'total-strokes attributes)
1308 (setq value (get-char-attribute char 'total-strokes)))
1309 (insert (format "(total-strokes . %S)%s"
1312 (setq attributes (delq 'total-strokes attributes))
1314 ;; (when (and (memq '->ideograph attributes)
1315 ;; (setq value (get-char-attribute char '->ideograph)))
1316 ;; (insert (format "(->ideograph\t%s)%s"
1317 ;; (mapconcat (lambda (code)
1318 ;; (cond ((symbolp code)
1319 ;; (symbol-name code))
1321 ;; (format "#x%04X" code))
1324 ;; line-breaking code))))
1327 ;; (setq attributes (delq '->ideograph attributes))
1329 ;; (when (and (memq '->decomposition attributes)
1330 ;; (setq value (get-char-attribute char '->decomposition)))
1331 ;; (insert (format "(->decomposition\t%s)%s"
1332 ;; (mapconcat (lambda (code)
1333 ;; (cond ((symbolp code)
1334 ;; (symbol-name code))
1335 ;; ((characterp code)
1337 ;; (format "%S" code)
1342 ;; (format "#x%04X" code))
1344 ;; (format "%s%S" line-breaking code))))
1347 ;; (setq attributes (delq '->decomposition attributes))
1349 (if (equal (get-char-attribute char '->titlecase)
1350 (get-char-attribute char '->uppercase))
1351 (setq attributes (delq '->titlecase attributes)))
1352 (when (and (memq '->mojikyo attributes)
1353 (setq value (get-char-attribute char '->mojikyo)))
1354 (insert (format "(->mojikyo\t\t. %06d)\t; %c%s"
1355 value (decode-char 'mojikyo value)
1357 (setq attributes (delq '->mojikyo attributes))
1360 (dolist (ignored '(composition
1361 ->denotational <-subsumptive ->ucs-unified
1362 ;; ->ideographic-component-forms
1364 (setq attributes (delq ignored attributes))))
1366 (setq name (car attributes))
1367 (unless (eq (setq value (get-char-attribute char name 'value-is-empty))
1369 (cond ((setq ret (find-charset name))
1370 (setq name (charset-name ret))
1371 (when (not (memq name dest-ccss))
1372 (setq dest-ccss (cons name dest-ccss))
1373 (char-db-insert-ccs-feature name value line-breaking))
1375 ((string-match "^=>ucs@" (symbol-name name))
1376 (insert (format "(%-18s . #x%04X)\t; %c%s"
1377 name value (decode-char '=ucs value)
1380 ((eq name 'jisx0208-1978/4X)
1381 (insert (format "(%-18s . #x%04X)%s"
1387 (not (eq name '->subsumptive))
1388 (not (eq name '->uppercase))
1389 (not (eq name '->lowercase))
1390 (not (eq name '->titlecase))
1391 (not (eq name '->canonical))
1392 (not (eq name '->Bopomofo))
1393 (not (eq name '->mistakable))
1394 (not (eq name '->ideographic-variants))
1395 (null (get-char-attribute
1396 char (intern (format "%s*sources" name))))
1397 (not (string-match "\\*sources$" (symbol-name name)))
1398 (null (get-char-attribute
1399 char (intern (format "%s*note" name))))
1400 (not (string-match "\\*note$" (symbol-name name)))
1401 (or (eq name '<-identical)
1402 (eq name '<-uppercase)
1403 (eq name '<-lowercase)
1404 (eq name '<-titlecase)
1405 (eq name '<-canonical)
1406 (eq name '<-ideographic-variants)
1407 ;; (eq name '<-synonyms)
1408 (string-match "^<-synonyms" (symbol-name name))
1409 (eq name '<-mistakable)
1410 (when (string-match "^->" (symbol-name name))
1412 ((string-match "^->fullwidth" (symbol-name name))
1413 (not (and (consp value)
1414 (characterp (car value))
1416 (car value) '=ucs 'defined-only)))
1421 ((or (eq name 'ideographic-structure)
1422 (eq name 'ideographic-structure@apparent)
1423 (eq name 'ideographic-combination)
1424 ;; (eq name 'ideographic-)
1425 (eq name '=decomposition)
1426 (char-feature-base-name= '=decomposition name)
1427 (char-feature-base-name= '=>decomposition name)
1428 ;; (string-match "^=>*decomposition\\(@[^*]+\\)?$"
1429 ;; (symbol-name name))
1430 (string-match "^\\(->\\|<-\\)[^*]*$" (symbol-name name))
1431 (string-match "^\\(->\\|<-\\)[^*]*\\*sources$"
1434 (char-db-insert-relation-feature char name value
1437 ;; ((memq name '(ideograph=
1438 ;; original-ideograph-of
1439 ;; ancient-ideograph-of
1440 ;; vulgar-ideograph-of
1441 ;; wrong-ideograph-of
1442 ;; ;; simplified-ideograph-of
1443 ;; ideographic-variants
1444 ;; ;; ideographic-different-form-of
1446 ;; (insert (format "(%-18s%s " name line-breaking))
1447 ;; (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1449 ;; (while (consp value)
1450 ;; (setq cell (car value))
1451 ;; (if (and (consp cell)
1452 ;; (consp (car cell)))
1456 ;; (char-db-insert-alist cell readable)
1457 ;; (setq separator lbs))
1459 ;; (insert separator))
1460 ;; (insert (prin1-to-string cell))
1461 ;; (setq separator " "))
1462 ;; (setq value (cdr value)))
1464 ;; (insert line-breaking))
1466 (insert (format "(%-18s " name))
1467 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1469 (while (consp value)
1470 (setq cell (car value))
1471 (if (and (consp cell)
1473 (setq ret (condition-case nil
1481 (setq key (car (car rest)))
1482 (if (find-charset key)
1483 (setq cal (cons key cal))
1484 (setq al (cons key al)))
1485 (setq rest (cdr rest)))
1488 (insert-char-attributes ret
1492 (setq separator lbs))
1493 (setq ret (prin1-to-string cell))
1495 (if (< (+ (current-column)
1502 (setq separator " "))
1503 (setq value (cdr value)))
1505 (insert line-breaking))
1507 (insert (format "(%-18s" name))
1508 (setq ret (prin1-to-string value))
1509 (unless (< (+ (current-column)
1513 (insert line-breaking))
1514 (insert " . " ret ")" line-breaking)
1515 ;; (insert (format "(%-18s . %S)%s"
1520 (setq attributes (cdr attributes)))
1523 (defun insert-char-data (char &optional readable
1526 (narrow-to-region (point)(point))
1527 (insert "(define-char
1529 (insert-char-attributes char readable attributes)
1531 (goto-char (point-min))
1532 (while (re-search-forward "[ \t]+$" nil t)
1535 (goto-char (point-min))
1536 (while (re-search-forward "[ \t][ \t][ \t]*" nil t)
1537 (let ((column (current-column))
1538 (indent-tabs-mode t))
1539 (delete-region (match-beginning 0) (point))
1540 (indent-to column)))
1541 (goto-char (point-max))
1542 ;; (tabify (point-min)(point-max))
1545 (defun insert-char-data-with-variant (char &optional printable
1547 script excluded-script)
1548 (insert-char-data char printable)
1549 (let ((variants (char-variants char))
1552 (setq variants (sort variants #'<))
1553 (setq rest variants)
1554 (setq variants (cons char variants))
1556 (setq variant (car rest))
1557 (unless (get-char-attribute variant '<-subsumptive)
1558 (if (and (or (null script)
1559 (null (setq vs (get-char-attribute variant 'script)))
1561 (or (null excluded-script)
1562 (null (setq vs (get-char-attribute variant 'script)))
1563 (not (memq excluded-script vs))))
1564 (unless (and no-ucs-unified (get-char-attribute variant '=ucs))
1565 (insert-char-data variant printable)
1566 (if (setq ret (char-variants variant))
1568 (or (memq (car ret) variants)
1569 ;; (get-char-attribute (car ret) '<-subsumptive)
1570 (setq rest (nconc rest (list (car ret)))))
1571 (setq ret (cdr ret)))))))
1572 (setq rest (cdr rest)))))
1574 (defun insert-char-range-data (min max &optional script excluded-script)
1577 (while (<= code max)
1578 (setq char (decode-char '=ucs code))
1579 (if (encode-char char '=ucs 'defined-only)
1580 (insert-char-data-with-variant char nil 'no-ucs-unified
1581 script excluded-script))
1582 (setq code (1+ code)))))
1584 (defun write-char-range-data-to-file (min max file
1585 &optional script excluded-script)
1586 (let ((coding-system-for-write char-db-file-coding-system))
1588 (insert (format ";; -*- coding: %s -*-\n"
1589 char-db-file-coding-system))
1590 (insert-char-range-data min max script excluded-script)
1591 (write-region (point-min)(point-max) file))))
1593 (defvar what-character-original-window-configuration)
1596 (defun what-char-definition (char)
1597 (interactive (list (char-after)))
1598 (let ((buf (get-buffer-create "*Character Description*"))
1599 (the-buf (current-buffer))
1600 (win-conf (current-window-configuration)))
1602 (make-local-variable 'what-character-original-window-configuration)
1603 (setq what-character-original-window-configuration win-conf)
1604 (setq buffer-read-only nil)
1608 (insert-char-data-with-variant char 'printable)
1609 (unless (char-attribute-alist char)
1610 (insert (format ";; = %c\n"
1611 (let* ((rest (split-char char))
1615 (setq code (logior (lsh code 8)
1617 (decode-char ccs code)))))
1618 ;; (char-db-update-comment)
1619 (set-buffer-modified-p nil)
1620 (view-mode the-buf (lambda (buf)
1621 (set-window-configuration
1622 what-character-original-window-configuration)
1624 (goto-char (point-min)))
1626 (set-window-configuration
1627 what-character-original-window-configuration)
1628 (signal (car err) (cdr err)))))))
1634 (provide 'char-db-util)
1636 ;;; char-db-util.el ends here