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 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
212 ;; =>>>adobe-japan1-0
213 ;; =>>>adobe-japan1-1
214 ;; =>>>adobe-japan1-2
215 ;; =>>>adobe-japan1-3
216 ;; =>>>adobe-japan1-4
217 ;; =>>>adobe-japan1-5
218 ;; =>>>adobe-japan1-6
222 ;; =>>>hanyo-denshi/ja
223 ;; =>>>hanyo-denshi/jb
224 ;; =>>>hanyo-denshi/jc
225 ;; =>>>hanyo-denshi/ft
226 ;; =>>>hanyo-denshi/ib
227 ;; =>>>hanyo-denshi/hg
228 ;; =>>>hanyo-denshi/jt
229 ;; =>>>hanyo-denshi/ks
345 ;;; @ char-db formatters
348 (defun char-db-make-char-spec (char)
350 (cond ((characterp char)
351 (cond ((and (setq ret (encode-char char '=ucs 'defined-only))
352 (not (and (<= #xE000 ret)(<= ret #xF8FF))))
353 (setq char-spec (list (cons '=ucs ret)))
354 (cond ((setq ret (get-char-attribute char 'name))
355 (setq char-spec (cons (cons 'name ret) char-spec))
357 ((setq ret (get-char-attribute char 'name*))
358 (setq char-spec (cons (cons 'name* ret) char-spec))
361 ((encode-char char '=mj 'defined-only)
363 (dolist (ccs (charset-list))
364 (if (and (or (eq ccs '=mj)
365 ;; (eq (charset-property ccs 'iso-ir) 177)
366 (string-match "=ucs@" (symbol-name ccs))
368 (setq ccs (charset-name ccs))
369 (null (assq ccs char-spec))
370 (setq ret (encode-char char ccs 'defined-only)))
371 (setq char-spec (cons (cons ccs ret) char-spec))))
373 ((encode-char char '==mj 'defined-only)
375 (dolist (ccs (charset-list))
376 (if (and (or (eq ccs '==mj)
377 ;; (eq (charset-property ccs 'iso-ir) 177)
378 (string-match "=ucs@" (symbol-name ccs))
380 (setq ccs (charset-name ccs))
381 (null (assq ccs char-spec))
382 (setq ret (encode-char char ccs 'defined-only)))
383 (setq char-spec (cons (cons ccs ret) char-spec))))
385 ((encode-char char '=adobe-japan1 'defined-only)
387 (dolist (ccs (charset-list))
388 (if (and (or (memq ccs
397 ;; (eq (charset-property ccs 'iso-ir) 177)
398 (string-match "=ucs@" (symbol-name ccs))
400 (setq ccs (charset-name ccs))
401 (null (assq ccs char-spec))
402 (setq ret (encode-char char ccs 'defined-only)))
403 (setq char-spec (cons (cons ccs ret) char-spec))))
405 ((encode-char char '==adobe-japan1 'defined-only)
407 (dolist (ccs (charset-list))
408 (if (and (or (memq ccs
417 ;; (eq (charset-property ccs 'iso-ir) 177)
418 (string-match "=ucs@" (symbol-name ccs))
420 (setq ccs (charset-name ccs))
421 (null (assq ccs char-spec))
422 (setq ret (encode-char char ccs 'defined-only)))
423 (setq char-spec (cons (cons ccs ret) char-spec))))
427 (let ((rest char-db-coded-charset-priority-list)
430 (setq ccs (charset-name
431 (find-charset (car rest))))
433 (encode-char char ccs
435 (throw 'tag (cons ccs ret)))
436 (setq rest (cdr rest))))))
437 (setq char-spec (list ret))
438 (dolist (ccs (delq (car ret) (charset-list)))
439 (if (and (or (charset-iso-final-char ccs)
446 (eq (charset-property ccs 'iso-ir) 177)
447 ;; (string-match "=ucs@" (symbol-name ccs))
449 (setq ccs (charset-name ccs))
450 (null (assq ccs char-spec))
451 (setq ret (encode-char char ccs 'defined-only)))
452 (setq char-spec (cons (cons ccs ret) char-spec))))
454 (setq char-spec (split-char char)))
455 (cond ((setq ret (get-char-attribute char 'name))
456 (setq char-spec (cons (cons 'name ret) char-spec))
458 ((setq ret (get-char-attribute char 'name*))
459 (setq char-spec (cons (cons 'name* ret) char-spec))
462 ((setq ret (get-char-attribute
463 char 'ideographic-combination))
465 (cons (cons 'ideographic-combination ret)
472 (defun char-db-insert-char-spec (char &optional readable column
475 (setq column (current-column)))
476 (let (char-spec temp-char)
477 (setq char-spec (char-db-make-char-spec char))
478 (unless (or (characterp char) ; char
480 (setq char (find-char char-spec))
482 ;; define temporary character
483 ;; Current implementation is dirty.
484 (setq temp-char (define-char (cons '(ideograph-daikanwa . 0)
486 (remove-char-attribute temp-char 'ideograph-daikanwa)
487 (setq char temp-char))
488 (insert-char-attributes char
490 (union (mapcar #'car char-spec)
494 ;; undefine temporary character
495 ;; Current implementation is dirty.
496 (setq char-spec (char-attribute-alist temp-char))
498 (remove-char-attribute temp-char (car (car char-spec)))
499 (setq char-spec (cdr char-spec))))))
501 (defun char-db-insert-alist (alist &optional readable column)
503 (setq column (current-column)))
505 (concat "\n" (make-string (1+ column) ?\ )))
509 lbs cell rest separator)
512 (setq name (car (car alist))
513 value (cdr (car alist)))
514 (cond ((eq name 'char)
516 (if (setq ret (condition-case nil
524 (setq key (car (car value)))
525 ;; (if (find-charset key)
526 ;; (setq cal (cons key cal))
527 (setq al (cons key al))
529 (setq value (cdr value)))
530 (insert-char-attributes ret
534 (insert (prin1-to-string value)))
536 (insert line-breaking))
538 (insert (format "(%-18s " name))
539 (setq lbs (concat "\n" (make-string (current-column) ?\ )))
541 (setq cell (car value))
542 (if (and (consp cell)
544 (setq ret (condition-case nil
554 (setq key (car (car rest)))
555 ;; (if (find-charset key)
556 ;; (setq cal (cons key cal))
557 (setq al (cons key al))
559 (setq rest (cdr rest)))
562 (insert-char-attributes ret
566 (setq separator lbs))
569 (insert (prin1-to-string cell))
570 (setq separator " "))
571 (setq value (cdr value)))
573 (insert line-breaking))
575 (insert (format "(%-18s . %S)%s"
578 (setq alist (cdr alist))))
581 (defun char-db-insert-char-reference (plist &optional readable column)
583 (setq column (current-column)))
585 (concat "\n" (make-string (1+ column) ?\ )))
590 (setq name (pop plist))
591 (setq value (pop plist))
592 (cond ((eq name :char)
595 (cond ((numberp value)
596 (setq value (decode-char '=ucs value)))
598 ;; (setq value (or (find-char value)
601 (char-db-insert-char-spec value readable)
602 (insert line-breaking)
605 (insert (format "%s%s\t%d ; %c%s"
608 (ideographic-radical value)
612 (insert (format "%s%s\t%S" separator name value))
613 (setq separator line-breaking)))
617 (defun char-db-decode-isolated-char (ccs code-point)
620 (cond ((eq ccs 'arabic-iso8859-6)
621 (decode-char ccs code-point))
623 ;; (decode-builtin-char '==gt code-point))
624 ((and (memq ccs '(=gt-pj-1
635 (setq ret (decode-char ccs code-point))
636 (setq ret (encode-char ret '=gt 'defined-only)))
637 (decode-builtin-char '=gt ret))
639 (decode-builtin-char ccs code-point))))
641 (or (decode-char ccs code-point)
642 (define-char (list (cons ccs code-point)))))
643 ((and (<= 0 (char-int ret))
644 (<= (char-int ret) #x1F))
645 (decode-char '=ucs (+ #x2400 (char-int ret))))
646 ((= (char-int ret) #x7F)
650 (defvar char-db-convert-obsolete-format t)
652 (defun char-db-insert-ccs-feature (name value line-breaking)
658 ((memq name '(=>iwds-1
661 =shinjigen@1ed ==shinjigen@1ed
662 =shinjigen@rev ==shinjigen@rev
663 =shinjigen/+p@rev ==shinjigen/+p@rev
664 ===daikanwa/ho ==daikanwa/ho
665 =daikanwa/ho =>>daikanwa/ho =>daikanwa/ho))
666 "(%-18s . %04d)\t; %c")
667 ((eq name '=shinjigen@1ed/24pr)
668 "(%-18s . %04d)\t; %c")
672 ==daikanwa =daikanwa =>>daikanwa =>daikanwa
673 =daikanwa@rev1 =daikanwa@rev2
674 =daikanwa/+p ==daikanwa/+p ===daikanwa/+p
676 =daikanwa/+2p =>>daikanwa/+2p
681 =adobe-japan1-0 ==adobe-japan1-0 ===adobe-japan1-0
682 =adobe-japan1-1 ==adobe-japan1-1 ===adobe-japan1-1
683 =adobe-japan1-2 ==adobe-japan1-2 ===adobe-japan1-2
684 =adobe-japan1-3 ==adobe-japan1-3 ===adobe-japan1-3
685 =adobe-japan1-4 ==adobe-japan1-4 ===adobe-japan1-4
686 =adobe-japan1-5 ==adobe-japan1-5 ===adobe-japan1-5
687 =adobe-japan1-6 ==adobe-japan1-6 ===adobe-japan1-6
688 =>>adobe-japan1-0 =+>adobe-japan1-0
689 =>>adobe-japan1-1 =+>adobe-japan1-1
690 =>>adobe-japan1-2 =+>adobe-japan1-2
691 =>>adobe-japan1-3 =+>adobe-japan1-3
692 =>>adobe-japan1-4 =+>adobe-japan1-4
693 =>>adobe-japan1-5 =+>adobe-japan1-5
694 =>>adobe-japan1-6 =+>adobe-japan1-6
695 =>cbeta =cbeta =>>cbeta ==cbeta ===cbeta
696 =zinbun-oracle =>zinbun-oracle
697 ===hng-jou ===hng-keg ===hng-dng ===hng-mam
698 ===hng-drt ===hng-kgk ===hng-myz ===hng-kda
699 ===hng-khi ===hng-khm ===hng-hok ===hng-kyd ===hng-sok
700 ===hng-yhk ===hng-kak ===hng-kar ===hng-kae
701 ===hng-sys ===hng-tsu ===hng-tzj
702 ===hng-hos ===hng-nak ===hng-jhk
703 ===hng-hod ===hng-gok ===hng-ink ===hng-nto
704 ===hng-nkm ===hng-k24 ===hng-nkk
705 ===hng-kcc ===hng-kcj ===hng-kbk ===hng-sik
706 ===hng-skk ===hng-kyu ===hng-ksk ===hng-wan
707 ===hng-okd ===hng-wad ===hng-kmi
708 ===hng-zkd ===hng-doh ===hng-jyu
709 ===hng-tzs ===hng-kss ===hng-kyo
711 ;; (string-match "^=adobe-" (symbol-name name))
713 "(%-18s . %05d)\t; %c")
714 ((memq name '(=hanyo-denshi/ks
715 ==hanyo-denshi/ks ===hanyo-denshi/ks
718 =mj ==mj ===mj =>>mj =>mj
720 "(%-18s . %06d)\t; %c")
721 ((memq name '(=hanyo-denshi/tk ==hanyo-denshi/tk))
722 "(%-18s . %08d)\t; %c")
723 ((>= (charset-dimension name) 2)
724 "(%-18s . #x%04X)\t; %c")
726 "(%-18s . #x%02X)\t; %c"))
728 (if (= (charset-iso-graphic-plane name) 1)
730 (cond ((= (charset-dimension name) 1)
732 ((= (charset-dimension name) 2)
734 ((= (charset-dimension name) 3)
738 (char-db-decode-isolated-char name value)))
739 (if (and (= (charset-chars name) 94)
740 (= (charset-dimension name) 2))
741 (insert (format " [%02d-%02d]"
742 (- (lsh value -8) 32)
743 (- (logand value 255) 32))))
746 (insert (format "(%-18s . %s)" name value))
748 (insert line-breaking))
750 (defun char-db-insert-relation-feature (char name value line-breaking
752 (insert (format "(%-18s%s " name line-breaking))
753 (let ((lbs (concat "\n" (make-string (current-column) ?\ )))
754 separator cell sources required-features
757 (setq cell (car value))
759 (setq cell (decode-char '=ucs cell)))
761 ((eq name '->subsumptive)
762 (when (or (not (some (lambda (atr)
763 (get-char-attribute cell atr))
764 char-db-ignored-attributes))
766 (encode-char cell ccs 'defined-only))
770 (let ((char-db-ignored-attributes
772 char-db-ignored-attributes)))
773 (insert-char-attributes cell readable nil nil 'for-sub-node))
774 (setq separator lbs))
779 char (intern (format "%s*sources" name))))
780 (setq required-features nil)
781 (dolist (source sources)
785 shinjigen shinjigen@1ed shinjigen@rev))
786 (setq required-features
787 (union required-features
799 =shinjigen/+p@rev))))
801 (setq required-features
802 (union required-features
807 ((find-charset (setq ret (intern (format "=%s" source))))
808 (setq required-features
809 (cons ret required-features)))
810 (t (setq required-features
811 (cons source required-features)))))
812 (cond ((string-match "@JP" (symbol-name name))
813 (setq required-features
814 (union required-features
822 ((string-match "@CN" (symbol-name name))
823 (setq required-features
824 (union required-features
831 (insert (format "%S" cell))
832 (char-db-insert-char-spec cell readable
835 (setq separator lbs))
839 (if (consp (car cell))
840 (char-db-insert-char-spec cell readable)
841 (char-db-insert-char-reference cell readable))
842 (setq separator lbs))
846 (insert (prin1-to-string cell))
847 (setq separator " ")))
848 (setq value (cdr value)))
850 (insert line-breaking)))
852 (defun insert-char-attributes (char &optional readable attributes column
855 (setq column (current-column)))
856 (let (name value ; has-long-ccs-name
860 (concat "\n" (make-string (1+ column) ?\ )))
861 lbs cell separator ret
863 dest-ccss ; sources required-features
868 (if (consp attributes)
870 (dolist (name attributes)
871 (unless (memq name char-db-ignored-attributes)
872 (if (find-charset name)
876 (dolist (name (char-attribute-list))
877 (unless (memq name char-db-ignored-attributes)
878 (if (find-charset name)
882 #'char-attribute-name<)))
884 (when (memq '<-subsumptive attributes)
885 (when (or readable (not for-sub-node))
886 (when (setq value (get-char-attribute char '<-subsumptive))
887 (char-db-insert-relation-feature char '<-subsumptive value
890 (setq attributes (delq '<-subsumptive attributes)))
891 (when (and (memq '<-denotational attributes)
892 (setq value (get-char-attribute char '<-denotational)))
893 (char-db-insert-relation-feature char '<-denotational value
896 (setq attributes (delq '<-denotational attributes)))
897 (when (and (memq '<-denotational@component attributes)
898 (setq value (get-char-attribute char '<-denotational@component)))
899 (char-db-insert-relation-feature char '<-denotational@component value
902 (setq attributes (delq '<-denotational@component attributes)))
903 (when (and (memq 'name attributes)
904 (setq value (get-char-attribute char 'name)))
906 (if (> (+ (current-column) (length value)) 48)
909 value line-breaking))
910 (setq attributes (delq 'name attributes))
912 (when (and (memq 'name* attributes)
913 (setq value (get-char-attribute char 'name*)))
915 (if (> (+ (current-column) (length value)) 48)
918 value line-breaking))
919 (setq attributes (delq 'name* attributes))
921 (when (and (memq 'script attributes)
922 (setq value (get-char-attribute char 'script)))
923 (insert (format "(script\t\t%s)%s"
924 (mapconcat (function prin1-to-string)
927 (setq attributes (delq 'script attributes))
929 (dolist (name '(=>ucs =>ucs*))
930 (when (and (memq name attributes)
931 (setq value (get-char-attribute char name)))
932 (insert (format "(%-18s . #x%04X)\t; %c%s"
933 name value (decode-char '=ucs value)
935 (setq attributes (delq name attributes))))
936 (dolist (name '(=>ucs@gb =>ucs@big5))
937 (when (and (memq name attributes)
938 (setq value (get-char-attribute char name)))
939 (insert (format "(%-18s . #x%04X)\t; %c%s"
944 (symbol-name name) 2)))
947 (setq attributes (delq name attributes))
949 ;; (dolist (name '(=>daikanwa))
950 ;; (when (and (memq name attributes)
951 ;; (setq value (get-char-attribute char name)))
953 ;; (if (integerp value)
954 ;; (format "(%-18s . %05d)\t; %c%s"
955 ;; name value (decode-char '=daikanwa value)
957 ;; (format "(%-18s %s)\t; %c%s"
959 ;; (mapconcat (function prin1-to-string)
961 ;; (char-representative-of-daikanwa char)
963 ;; (setq attributes (delq name attributes))))
964 (when (and (memq 'general-category attributes)
965 (setq value (get-char-attribute char 'general-category)))
967 "(general-category\t%s) ; %s%s"
968 (mapconcat (lambda (cell)
971 (cond ((rassoc value unidata-normative-category-alist)
972 "Normative Category")
973 ((rassoc value unidata-informative-category-alist)
974 "Informative Category")
978 (setq attributes (delq 'general-category attributes))
980 (when (and (memq 'bidi-category attributes)
981 (setq value (get-char-attribute char 'bidi-category)))
982 (insert (format "(bidi-category\t. %S)%s"
985 (setq attributes (delq 'bidi-category attributes))
987 (unless (or (not (memq 'mirrored attributes))
988 (eq (setq value (get-char-attribute char 'mirrored 'empty))
990 (insert (format "(mirrored\t\t. %S)%s"
993 (setq attributes (delq 'mirrored attributes))
996 ((and (memq 'decimal-digit-value attributes)
997 (setq value (get-char-attribute char 'decimal-digit-value)))
998 (insert (format "(decimal-digit-value . %S)%s"
1001 (setq attributes (delq 'decimal-digit-value attributes))
1002 (when (and (memq 'digit-value attributes)
1003 (setq value (get-char-attribute char 'digit-value)))
1004 (insert (format "(digit-value\t . %S)%s"
1007 (setq attributes (delq 'digit-value attributes))
1009 (when (and (memq 'numeric-value attributes)
1010 (setq value (get-char-attribute char 'numeric-value)))
1011 (insert (format "(numeric-value\t . %S)%s"
1014 (setq attributes (delq 'numeric-value attributes))
1018 (when (and (memq 'digit-value attributes)
1019 (setq value (get-char-attribute char 'digit-value)))
1020 (insert (format "(digit-value\t. %S)%s"
1023 (setq attributes (delq 'digit-value attributes))
1025 (when (and (memq 'numeric-value attributes)
1026 (setq value (get-char-attribute char 'numeric-value)))
1027 (insert (format "(numeric-value\t. %S)%s"
1030 (setq attributes (delq 'numeric-value attributes))
1032 (when (and (memq 'iso-10646-comment attributes)
1033 (setq value (get-char-attribute char 'iso-10646-comment)))
1034 (insert (format "(iso-10646-comment\t. %S)%s"
1037 (setq attributes (delq 'iso-10646-comment attributes))
1039 (when (and (memq 'morohashi-daikanwa attributes)
1040 (setq value (get-char-attribute char 'morohashi-daikanwa)))
1041 (insert (format "(morohashi-daikanwa\t%s)%s"
1042 (mapconcat (function prin1-to-string) value " ")
1044 (setq attributes (delq 'morohashi-daikanwa attributes))
1048 (when (and (memq 'ideographic-radical attributes)
1049 (setq value (get-char-attribute char 'ideographic-radical)))
1050 (setq radical value)
1051 (insert (format "(ideographic-radical . %S)\t; %c%s"
1053 (ideographic-radical radical)
1055 (setq attributes (delq 'ideographic-radical attributes))
1057 (when (and (memq 'shuowen-radical attributes)
1058 (setq value (get-char-attribute char 'shuowen-radical)))
1059 (insert (format "(shuowen-radical\t. %S)\t; %c%s"
1061 (shuowen-radical value)
1063 (setq attributes (delq 'shuowen-radical attributes))
1068 char-db-feature-domains
1070 (dolist (feature (char-attribute-list))
1071 (setq feature (symbol-name feature))
1073 "\\(radical\\|strokes\\)@\\([^@*]+\\)\\(\\*\\|$\\)"
1075 (setq domain (intern (match-string 2 feature)))
1076 (unless (memq domain dest)
1077 (setq dest (cons domain dest)))))
1078 (sort dest #'string<))))
1079 (setq key (intern (format "%s@%s" 'ideographic-radical domain)))
1080 (when (and (memq key attributes)
1081 (setq value (get-char-attribute char key)))
1082 (setq radical value)
1083 (insert (format "(%s . %S)\t; %c%s"
1086 (ideographic-radical radical)
1088 (setq attributes (delq key attributes))
1090 (setq key (intern (format "%s@%s" 'ideographic-strokes domain)))
1091 (when (and (memq key attributes)
1092 (setq value (get-char-attribute char key)))
1093 (setq strokes value)
1094 (insert (format "(%s . %S)%s"
1098 (setq attributes (delq key attributes))
1100 (setq key (intern (format "%s@%s" 'total-strokes domain)))
1101 (when (and (memq key attributes)
1102 (setq value (get-char-attribute char key)))
1103 (insert (format "(%s . %S)%s"
1107 (setq attributes (delq key attributes))
1109 (dolist (feature '(ideographic-radical
1112 (setq key (intern (format "%s@%s*sources" feature domain)))
1113 (when (and (memq key attributes)
1114 (setq value (get-char-attribute char key)))
1115 (insert (format "(%s%s" key line-breaking))
1116 (dolist (cell value)
1117 (insert (format " %s" cell)))
1119 (insert line-breaking)
1120 (setq attributes (delq key attributes))
1123 (when (and (memq 'ideographic-strokes attributes)
1124 (setq value (get-char-attribute char 'ideographic-strokes)))
1125 (setq strokes value)
1126 (insert (format "(ideographic-strokes . %S)%s"
1129 (setq attributes (delq 'ideographic-strokes attributes))
1131 (when (and (memq 'kangxi-radical attributes)
1132 (setq value (get-char-attribute char 'kangxi-radical)))
1133 (unless (eq value radical)
1134 (insert (format "(kangxi-radical\t . %S)\t; %c%s"
1136 (ideographic-radical value)
1139 (setq radical value)))
1140 (setq attributes (delq 'kangxi-radical attributes))
1142 (when (and (memq 'kangxi-strokes attributes)
1143 (setq value (get-char-attribute char 'kangxi-strokes)))
1144 (unless (eq value strokes)
1145 (insert (format "(kangxi-strokes\t . %S)%s"
1149 (setq strokes value)))
1150 (setq attributes (delq 'kangxi-strokes attributes))
1152 (when (and (memq 'japanese-radical attributes)
1153 (setq value (get-char-attribute char 'japanese-radical)))
1154 (unless (eq value radical)
1155 (insert (format "(japanese-radical\t . %S)\t; %c%s"
1157 (ideographic-radical value)
1160 (setq radical value)))
1161 (setq attributes (delq 'japanese-radical attributes))
1163 (when (and (memq 'japanese-strokes attributes)
1164 (setq value (get-char-attribute char 'japanese-strokes)))
1165 (unless (eq value strokes)
1166 (insert (format "(japanese-strokes\t . %S)%s"
1170 (setq strokes value)))
1171 (setq attributes (delq 'japanese-strokes attributes))
1173 (when (and (memq 'cns-radical attributes)
1174 (setq value (get-char-attribute char 'cns-radical)))
1175 (insert (format "(cns-radical\t . %S)\t; %c%s"
1177 (ideographic-radical value)
1179 (setq attributes (delq 'cns-radical attributes))
1181 (when (and (memq 'cns-strokes attributes)
1182 (setq value (get-char-attribute char 'cns-strokes)))
1183 (unless (eq value strokes)
1184 (insert (format "(cns-strokes\t . %S)%s"
1188 (setq strokes value)))
1189 (setq attributes (delq 'cns-strokes attributes))
1191 ;; (when (and (memq 'shinjigen-1-radical attributes)
1192 ;; (setq value (get-char-attribute char 'shinjigen-1-radical)))
1193 ;; (unless (eq value radical)
1194 ;; (insert (format "(shinjigen-1-radical . %S)\t; %c%s"
1196 ;; (ideographic-radical value)
1199 ;; (setq radical value)))
1200 ;; (setq attributes (delq 'shinjigen-1-radical attributes))
1202 (when (and (memq 'ideographic- attributes)
1203 (setq value (get-char-attribute char 'ideographic-)))
1204 (insert "(ideographic- ")
1205 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1207 (while (consp value)
1208 (setq cell (car value))
1210 (setq cell (decode-char '=ucs cell)))
1211 (cond ((characterp cell)
1215 (insert (format "%S" cell))
1216 (char-db-insert-char-spec cell readable))
1217 (setq separator lbs))
1221 (if (consp (car cell))
1222 (char-db-insert-char-spec cell readable)
1223 (char-db-insert-char-reference cell readable))
1224 (setq separator lbs))
1228 (insert (prin1-to-string cell))
1229 (setq separator " ")))
1230 (setq value (cdr value)))
1232 (insert line-breaking)
1233 (setq attributes (delq 'ideographic- attributes)))
1234 (when (and (memq 'total-strokes attributes)
1235 (setq value (get-char-attribute char 'total-strokes)))
1236 (insert (format "(total-strokes . %S)%s"
1239 (setq attributes (delq 'total-strokes attributes))
1241 (when (and (memq '->ideograph attributes)
1242 (setq value (get-char-attribute char '->ideograph)))
1243 (insert (format "(->ideograph\t%s)%s"
1244 (mapconcat (lambda (code)
1245 (cond ((symbolp code)
1248 (format "#x%04X" code))
1251 line-breaking code))))
1254 (setq attributes (delq '->ideograph attributes))
1256 ;; (when (and (memq '->decomposition attributes)
1257 ;; (setq value (get-char-attribute char '->decomposition)))
1258 ;; (insert (format "(->decomposition\t%s)%s"
1259 ;; (mapconcat (lambda (code)
1260 ;; (cond ((symbolp code)
1261 ;; (symbol-name code))
1262 ;; ((characterp code)
1264 ;; (format "%S" code)
1269 ;; (format "#x%04X" code))
1271 ;; (format "%s%S" line-breaking code))))
1274 ;; (setq attributes (delq '->decomposition attributes))
1276 (if (equal (get-char-attribute char '->titlecase)
1277 (get-char-attribute char '->uppercase))
1278 (setq attributes (delq '->titlecase attributes)))
1279 (when (and (memq '->mojikyo attributes)
1280 (setq value (get-char-attribute char '->mojikyo)))
1281 (insert (format "(->mojikyo\t\t. %06d)\t; %c%s"
1282 value (decode-char 'mojikyo value)
1284 (setq attributes (delq '->mojikyo attributes))
1286 (when (and (memq 'hanyu-dazidian-vol attributes)
1287 (setq value (get-char-attribute char 'hanyu-dazidian-vol)))
1288 (insert (format "(hanyu-dazidian-vol . %d)%s"
1289 value line-breaking))
1290 (setq attributes (delq 'hanyu-dazidian-vol attributes))
1292 (when (and (memq 'hanyu-dazidian-page attributes)
1293 (setq value (get-char-attribute char 'hanyu-dazidian-page)))
1294 (insert (format "(hanyu-dazidian-page . %d)%s"
1295 value line-breaking))
1296 (setq attributes (delq 'hanyu-dazidian-page attributes))
1298 (when (and (memq 'hanyu-dazidian-char attributes)
1299 (setq value (get-char-attribute char 'hanyu-dazidian-char)))
1300 (insert (format "(hanyu-dazidian-char . %d)%s"
1301 value line-breaking))
1302 (setq attributes (delq 'hanyu-dazidian-char attributes))
1305 (dolist (ignored '(composition
1306 ->denotational <-subsumptive ->ucs-unified
1307 ->ideographic-component-forms))
1308 (setq attributes (delq ignored attributes))))
1310 (setq name (car attributes))
1311 (unless (eq (setq value (get-char-attribute char name 'value-is-empty))
1313 (cond ((setq ret (find-charset name))
1314 (setq name (charset-name ret))
1315 (when (not (memq name dest-ccss))
1316 (setq dest-ccss (cons name dest-ccss))
1317 (char-db-insert-ccs-feature name value line-breaking))
1319 ((string-match "^=>ucs@" (symbol-name name))
1320 (insert (format "(%-18s . #x%04X)\t; %c%s"
1321 name value (decode-char '=ucs value)
1324 ((eq name 'jisx0208-1978/4X)
1325 (insert (format "(%-18s . #x%04X)%s"
1331 (not (eq name '->subsumptive))
1332 (not (eq name '->uppercase))
1333 (not (eq name '->lowercase))
1334 (not (eq name '->titlecase))
1335 (not (eq name '->canonical))
1336 (not (eq name '->Bopomofo))
1337 (not (eq name '->mistakable))
1338 (not (eq name '->ideographic-variants))
1339 (null (get-char-attribute
1340 char (intern (format "%s*sources" name))))
1341 (not (string-match "\\*sources$" (symbol-name name)))
1342 (null (get-char-attribute
1343 char (intern (format "%s*note" name))))
1344 (not (string-match "\\*note$" (symbol-name name)))
1345 (or (eq name '<-identical)
1346 (eq name '<-uppercase)
1347 (eq name '<-lowercase)
1348 (eq name '<-titlecase)
1349 (eq name '<-canonical)
1350 (eq name '<-ideographic-variants)
1351 ;; (eq name '<-synonyms)
1352 (string-match "^<-synonyms" (symbol-name name))
1353 (eq name '<-mistakable)
1354 (when (string-match "^->" (symbol-name name))
1356 ((string-match "^->fullwidth" (symbol-name name))
1357 (not (and (consp value)
1358 (characterp (car value))
1360 (car value) '=ucs 'defined-only)))
1365 ((or (eq name 'ideographic-structure)
1366 (eq name 'ideographic-combination)
1367 (eq name 'ideographic-)
1368 (eq name '=decomposition)
1369 (char-feature-base-name= '=decomposition name)
1370 (char-feature-base-name= '=>decomposition name)
1371 ;; (string-match "^=>*decomposition\\(@[^*]+\\)?$"
1372 ;; (symbol-name name))
1373 (string-match "^\\(->\\|<-\\)[^*]*$" (symbol-name name))
1374 (string-match "^\\(->\\|<-\\)[^*]*\\*sources$"
1377 (char-db-insert-relation-feature char name value
1380 ((memq name '(ideograph=
1381 original-ideograph-of
1382 ancient-ideograph-of
1385 ;; simplified-ideograph-of
1386 ideographic-variants
1387 ;; ideographic-different-form-of
1389 (insert (format "(%-18s%s " name line-breaking))
1390 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1392 (while (consp value)
1393 (setq cell (car value))
1394 (if (and (consp cell)
1399 (char-db-insert-alist cell readable)
1400 (setq separator lbs))
1403 (insert (prin1-to-string cell))
1404 (setq separator " "))
1405 (setq value (cdr value)))
1407 (insert line-breaking))
1409 (insert (format "(%-18s " name))
1410 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1412 (while (consp value)
1413 (setq cell (car value))
1414 (if (and (consp cell)
1416 (setq ret (condition-case nil
1424 (setq key (car (car rest)))
1425 (if (find-charset key)
1426 (setq cal (cons key cal))
1427 (setq al (cons key al)))
1428 (setq rest (cdr rest)))
1431 (insert-char-attributes ret
1435 (setq separator lbs))
1436 (setq ret (prin1-to-string cell))
1438 (if (< (+ (current-column)
1445 (setq separator " "))
1446 (setq value (cdr value)))
1448 (insert line-breaking))
1450 (insert (format "(%-18s" name))
1451 (setq ret (prin1-to-string value))
1452 (unless (< (+ (current-column)
1456 (insert line-breaking))
1457 (insert " . " ret ")" line-breaking)
1458 ;; (insert (format "(%-18s . %S)%s"
1463 (setq attributes (cdr attributes)))
1466 (defun insert-char-data (char &optional readable
1469 (narrow-to-region (point)(point))
1470 (insert "(define-char
1472 (insert-char-attributes char readable attributes)
1474 (goto-char (point-min))
1475 (while (re-search-forward "[ \t]+$" nil t)
1478 (goto-char (point-min))
1479 (while (re-search-forward "[ \t][ \t][ \t]*" nil t)
1480 (let ((column (current-column))
1481 (indent-tabs-mode t))
1482 (delete-region (match-beginning 0) (point))
1483 (indent-to column)))
1484 (goto-char (point-max))
1485 ;; (tabify (point-min)(point-max))
1488 (defun insert-char-data-with-variant (char &optional printable
1490 script excluded-script)
1491 (insert-char-data char printable)
1492 (let ((variants (char-variants char))
1495 (setq variants (sort variants #'<))
1496 (setq rest variants)
1497 (setq variants (cons char variants))
1499 (setq variant (car rest))
1500 (unless (get-char-attribute variant '<-subsumptive)
1501 (if (and (or (null script)
1502 (null (setq vs (get-char-attribute variant 'script)))
1504 (or (null excluded-script)
1505 (null (setq vs (get-char-attribute variant 'script)))
1506 (not (memq excluded-script vs))))
1507 (unless (and no-ucs-unified (get-char-attribute variant '=ucs))
1508 (insert-char-data variant printable)
1509 (if (setq ret (char-variants variant))
1511 (or (memq (car ret) variants)
1512 ;; (get-char-attribute (car ret) '<-subsumptive)
1513 (setq rest (nconc rest (list (car ret)))))
1514 (setq ret (cdr ret)))))))
1515 (setq rest (cdr rest)))))
1517 (defun insert-char-range-data (min max &optional script excluded-script)
1520 (while (<= code max)
1521 (setq char (decode-char '=ucs code))
1522 (if (encode-char char '=ucs 'defined-only)
1523 (insert-char-data-with-variant char nil 'no-ucs-unified
1524 script excluded-script))
1525 (setq code (1+ code)))))
1527 (defun write-char-range-data-to-file (min max file
1528 &optional script excluded-script)
1529 (let ((coding-system-for-write char-db-file-coding-system))
1531 (insert (format ";; -*- coding: %s -*-\n"
1532 char-db-file-coding-system))
1533 (insert-char-range-data min max script excluded-script)
1534 (write-region (point-min)(point-max) file))))
1536 (defvar what-character-original-window-configuration)
1539 (defun what-char-definition (char)
1540 (interactive (list (char-after)))
1541 (let ((buf (get-buffer-create "*Character Description*"))
1542 (the-buf (current-buffer))
1543 (win-conf (current-window-configuration)))
1545 (make-local-variable 'what-character-original-window-configuration)
1546 (setq what-character-original-window-configuration win-conf)
1547 (setq buffer-read-only nil)
1551 (insert-char-data-with-variant char 'printable)
1552 (unless (char-attribute-alist char)
1553 (insert (format ";; = %c\n"
1554 (let* ((rest (split-char char))
1558 (setq code (logior (lsh code 8)
1560 (decode-char ccs code)))))
1561 ;; (char-db-update-comment)
1562 (set-buffer-modified-p nil)
1563 (view-mode the-buf (lambda (buf)
1564 (set-window-configuration
1565 what-character-original-window-configuration)
1567 (goto-char (point-min)))
1569 (set-window-configuration
1570 what-character-original-window-configuration)
1571 (signal (car err) (cdr err)))))))
1577 (provide 'char-db-util)
1579 ;;; char-db-util.el ends here