1 ;;; char-db-util.el --- Character Database utility -*- coding: utf-8-er; -*-
3 ;; Copyright (C) 1998,1999,2000,2001,2002,2003,2004,2005,2006,2007,
4 ;; 2008,2009,2010,2011,2012,2013,2014,2015,2016,2017 MORIOKA Tomohiko.
6 ;; Author: MORIOKA Tomohiko <tomo@kanji.zinbun.kyoto-u.ac.jp>
7 ;; Keywords: CHISE, Character Database, ISO/IEC 10646, UCS, Unicode, MULE.
9 ;; This file is part of XEmacs CHISE.
11 ;; XEmacs CHISE is free software; you can redistribute it and/or
12 ;; modify it under the terms of the GNU General Public License as
13 ;; published by the Free Software Foundation; either version 2, or (at
14 ;; your option) any later version.
16 ;; XEmacs CHISE is distributed in the hope that it will be useful,
17 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
18 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
19 ;; General Public License for more details.
21 ;; You should have received a copy of the GNU General Public License
22 ;; along with XEmacs CHISE; see the file COPYING. If not, write to
23 ;; the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
24 ;; Boston, MA 02111-1307, USA.
29 (require 'ideograph-subr)
31 (defconst unidata-normative-category-alist
32 '(("Lu" letter uppercase)
33 ("Ll" letter lowercase)
34 ("Lt" letter titlecase)
35 ("Mn" mark non-spacing)
36 ("Mc" mark spacing-combining)
38 ("Nd" number decimal-digit)
41 ("Zs" separator space)
43 ("Zp" separator paragraph)
46 ("Cs" other surrogate)
47 ("Co" other private-use)
48 ("Cn" other not-assigned)))
50 (defconst unidata-informative-category-alist
51 '(("Lm" letter modifier)
53 ("Pc" punctuation connector)
54 ("Pd" punctuation dash)
55 ("Ps" punctuation open)
56 ("Pe" punctuation close)
57 ("Pi" punctuation initial-quote)
58 ("Pf" punctuation final-quote)
59 ("Po" punctuation other)
61 ("Sc" symbol currency)
62 ("Sk" symbol modifier)
66 (defconst shuowen-radicals
67 [?一 ?上 ?示 ?三 ?王 ?玉 ?玨 ?气 ?士 ?丨 ; 010
68 ?屮 ?艸 ?蓐 ?茻 ?小 ?八 ?釆 ?半 ?牛 ?犛 ; 020
69 ?告 ?口 ?凵 ?吅 ?哭 ?走 ?止 ?癶 ?步 ?此 ; 030
70 ?正 ?是 ?辵 ?彳 ?廴 ?㢟 ?行 ?齒 ?牙 ?足 ; 040
71 ?疋 ?品 ?龠 ?冊 ?㗊 ?舌 ?干 ?谷 ?只 ?㕯 ; 050
72 ?句 ?丩 ?古 ?十 ?卅 ?言 ?誩 ?音 ?䇂 ?丵 ; 060
73 ?菐 ?𠬞 ?𠬜 ?共 ?異 ?舁 ?𦥑 ?䢅 ?爨 ?革 ; 070
74 ?鬲 ?䰜 ?爪 ?𠃨 ?鬥 ?又 ?𠂇 ?㕜 ?支 ?𦘒 ; 080
75 ?聿 ?畫 ?隶 ?臤 ?臣 ?殳 ?殺 ?𠘧 ?寸 ?皮 ; 090
76 ?㼱 ?攴 ?敎 ?卜 ?用 ?爻 ?㸚 ?𥄎 ?目 ?䀠 ; 100
77 ?眉 ?盾 ?自 ?白 ?鼻 ?皕 ?習 ?羽 ?隹 ?奞 ; 110
78 ?萑 ?𦫳 ?苜 ?羊 ?羴 ?瞿 ?雔 ?雥 ?鳥 ?烏 ; 120
79 ?𠦒 ?冓 ?幺 ?𢆶 ?叀 ?玄 ?予 ?放 ?𠬪 ?𣦼 ; 130
80 ?歺 ?死 ?冎 ?骨 ?肉 ?筋 ?刀 ?刃 ?㓞 ?丰 ; 140
81 ?耒 ?𧢲 ?竹 ?箕 ?丌 ?左 ?工 ?㠭 ?巫 ?甘 ; 150
82 ?曰 ?乃 ?丂 ?可 ?兮 ?号 ?亏 ?旨 ?喜 ?壴 ; 160
83 ; ?旨 ?曰 ?乃 ?丂 ?可 ?兮 ?号 ?亏 ?喜 ?壴 ; 160
84 ?鼓 ?豈 ?豆 ?豊 ?豐 ?䖒 ?虍 ?虎 ?虤 ?皿 ; 170
85 ?𠙴 ?去 ?血 ?丶 ?丹 ?青 ?井 ?皀 ?鬯 ?食 ; 180
86 ?亼 ?會 ?倉 ?入 ?缶 ?矢 ?高 ?冂 ?𩫏 ?京 ; 190
87 ?亯 ?𣆪 ?畗 ?㐭 ?嗇 ?來 ?麥 ?夊 ?舛 ?䑞 ; 200
88 ?韋 ?弟 ?夂 ?久 ?桀 ?木 ?東 ?林 ?才 ?叒 ; 210
89 ?之 ?帀 ?出 ?𣎵 ?生 ?乇 ?𠂹 ?𠌶 ?華 ?𥝌 ; 220
90 ?稽 ?巢 ?桼 ?束 ?㯻 ?囗 ?員 ?貝 ?邑 ?𨛜 ; 230
91 ?日 ?旦 ?倝 ?㫃 ?冥 ?晶 ?月 ?有 ?明 ?囧 ; 240
92 ?夕 ?多 ?毌 ?𢎘 ?𣐺 ?卣 ?齊 ?朿 ?片 ?鼎 ; 250
93 ?克 ?彔 ?禾 ?秝 ?黍 ?香 ?米 ?毇 ?臼 ?凶 ; 260
94 ?𣎳 ?林 ?麻 ?尗 ?耑 ?韭 ?瓜 ?瓠 ?宀 ?宮 ; 270
95 ?呂 ?穴 ?㝱 ?𤕫 ?冖 ?𠔼 ?冃 ?㒳 ?网 ?襾 ; 280
96 ?巾 ?巿 ?帛 ?白 ?㡀 ?黹 ?人 ?𠤎 ?匕 ?从 ; 290
97 ?比 ?北 ?丘 ?㐺 ?𡈼 ?重 ?臥 ?身 ?㐆 ?衣 ; 300
98 ?裘 ?老 ?毛 ?毳 ?尸 ?尺 ?尾 ?履 ?舟 ?方 ; 310
99 ?儿 ?兄 ?兂 ?皃 ?𠑹 ?先 ?秃 ?見 ?覞 ?欠 ; 320
100 ?㱃 ?㳄 ?旡 ?頁 ?𦣻 ?面 ?丏 ?首 ?𥄉 ?須 ; 330
101 ?彡 ?彣 ?文 ?髟 ?后 ?司 ?卮 ?卩 ?印 ?色 ; 340
102 ?𠨍 ?辟 ?勹 ?包 ?茍 ?鬼 ?甶 ?厶 ?嵬 ?山 ; 350
103 ?屾 ?屵 ?广 ?厂 ?丸 ?危 ?石 ?長 ?勿 ?冄 ; 360
104 ?而 ?豕 ?㣇 ?彑 ?豚 ?豸 ?𤉡 ?易 ?象 ?馬 ; 370
105 ?𢊁 ?鹿 ?麤 ?㲋 ?兔 ?萈 ?犬 ?㹜 ?鼠 ?能 ; 380
106 ?熊 ?火 ?炎 ?黑 ?囪 ?焱 ?炙 ?赤 ?大 ?亦 ; 390
109 (defun shuowen-radical (number)
110 (aref shuowen-radicals (1- number)))
112 (defvar char-db-file-coding-system 'utf-8-mcs-er)
114 (defvar char-db-ignored-attributes '(ideographic-products))
116 (defvar char-db-coded-charset-priority-list
214 ;; =>>>adobe-japan1-0
215 ;; =>>>adobe-japan1-1
216 ;; =>>>adobe-japan1-2
217 ;; =>>>adobe-japan1-3
218 ;; =>>>adobe-japan1-4
219 ;; =>>>adobe-japan1-5
220 ;; =>>>adobe-japan1-6
224 ;; =>>>hanyo-denshi/ja
225 ;; =>>>hanyo-denshi/jb
226 ;; =>>>hanyo-denshi/jc
227 ;; =>>>hanyo-denshi/ft
228 ;; =>>>hanyo-denshi/ib
229 ;; =>>>hanyo-denshi/hg
230 ;; =>>>hanyo-denshi/jt
231 ;; =>>>hanyo-denshi/ks
363 =>big5-cdp-itaiji-001
370 ;;; @ char-db formatters
373 (defun char-db-make-char-spec (char)
375 (cond ((characterp char)
376 (cond ((and (setq ret (encode-char char '=ucs 'defined-only))
377 (not (and (<= #xE000 ret)(<= ret #xF8FF))))
378 (setq char-spec (list (cons '=ucs ret)))
379 (cond ((setq ret (get-char-attribute char 'name))
380 (setq char-spec (cons (cons 'name ret) char-spec))
382 ((setq ret (get-char-attribute char 'name*))
383 (setq char-spec (cons (cons 'name* ret) char-spec))
386 ((encode-char char '=mj 'defined-only)
388 (dolist (ccs (charset-list))
389 (if (and (or (eq ccs '=mj)
390 ;; (eq (charset-property ccs 'iso-ir) 177)
391 (string-match "=ucs@" (symbol-name ccs))
393 (setq ccs (charset-name ccs))
394 (null (assq ccs char-spec))
395 (setq ret (encode-char char ccs 'defined-only)))
396 (setq char-spec (cons (cons ccs ret) char-spec))))
398 ((encode-char char '==mj 'defined-only)
400 (dolist (ccs (charset-list))
401 (if (and (or (eq ccs '==mj)
402 ;; (eq (charset-property ccs 'iso-ir) 177)
403 (string-match "=ucs@" (symbol-name ccs))
405 (setq ccs (charset-name ccs))
406 (null (assq ccs char-spec))
407 (setq ret (encode-char char ccs 'defined-only)))
408 (setq char-spec (cons (cons ccs ret) char-spec))))
410 ((encode-char char '=adobe-japan1 'defined-only)
412 (dolist (ccs (charset-list))
413 (if (and (or (memq ccs
422 ;; (eq (charset-property ccs 'iso-ir) 177)
423 (string-match "=ucs@" (symbol-name ccs))
425 (setq ccs (charset-name ccs))
426 (null (assq ccs char-spec))
427 (setq ret (encode-char char ccs 'defined-only)))
428 (setq char-spec (cons (cons ccs ret) char-spec))))
430 ((encode-char char '==adobe-japan1 'defined-only)
432 (dolist (ccs (charset-list))
433 (if (and (or (memq ccs
442 ;; (eq (charset-property ccs 'iso-ir) 177)
443 (string-match "=ucs@" (symbol-name ccs))
445 (setq ccs (charset-name ccs))
446 (null (assq ccs char-spec))
447 (setq ret (encode-char char ccs 'defined-only)))
448 (setq char-spec (cons (cons ccs ret) char-spec))))
452 (let ((rest char-db-coded-charset-priority-list)
455 (setq ccs (charset-name
456 (find-charset (car rest))))
458 (encode-char char ccs
460 (throw 'tag (cons ccs ret)))
461 (setq rest (cdr rest))))))
462 (setq char-spec (list ret))
463 (dolist (ccs (delq (car ret) (charset-list)))
464 (if (and (or (charset-iso-final-char ccs)
471 (eq (charset-property ccs 'iso-ir) 177)
472 ;; (string-match "=ucs@" (symbol-name ccs))
474 (setq ccs (charset-name ccs))
475 (null (assq ccs char-spec))
476 (setq ret (encode-char char ccs 'defined-only)))
477 (setq char-spec (cons (cons ccs ret) char-spec))))
479 (setq char-spec (split-char char)))
480 (cond ((setq ret (get-char-attribute char 'name))
481 (setq char-spec (cons (cons 'name ret) char-spec))
483 ((setq ret (get-char-attribute char 'name*))
484 (setq char-spec (cons (cons 'name* ret) char-spec))
487 ((setq ret (get-char-attribute
488 char 'ideographic-combination))
490 (cons (cons 'ideographic-combination ret)
497 (defun char-db-insert-char-spec (char &optional readable column
500 (setq column (current-column)))
501 (let (char-spec temp-char)
502 (setq char-spec (char-db-make-char-spec char))
503 (unless (or (characterp char) ; char
505 (setq char (find-char char-spec))
507 ;; define temporary character
508 ;; Current implementation is dirty.
509 (setq temp-char (define-char (cons '(ideograph-daikanwa . 0)
511 (remove-char-attribute temp-char 'ideograph-daikanwa)
512 (setq char temp-char))
513 (insert-char-attributes char
515 (union (mapcar #'car char-spec)
519 ;; undefine temporary character
520 ;; Current implementation is dirty.
521 (setq char-spec (char-attribute-alist temp-char))
523 (remove-char-attribute temp-char (car (car char-spec)))
524 (setq char-spec (cdr char-spec))))))
526 (defun char-db-insert-alist (alist &optional readable column)
528 (setq column (current-column)))
530 (concat "\n" (make-string (1+ column) ?\ )))
534 lbs cell rest separator)
537 (setq name (car (car alist))
538 value (cdr (car alist)))
539 (cond ((eq name 'char)
541 (if (setq ret (condition-case nil
549 (setq key (car (car value)))
550 ;; (if (find-charset key)
551 ;; (setq cal (cons key cal))
552 (setq al (cons key al))
554 (setq value (cdr value)))
555 (insert-char-attributes ret
559 (insert (prin1-to-string value)))
561 (insert line-breaking))
563 (insert (format "(%-18s " name))
564 (setq lbs (concat "\n" (make-string (current-column) ?\ )))
566 (setq cell (car value))
567 (if (and (consp cell)
569 (setq ret (condition-case nil
579 (setq key (car (car rest)))
580 ;; (if (find-charset key)
581 ;; (setq cal (cons key cal))
582 (setq al (cons key al))
584 (setq rest (cdr rest)))
587 (insert-char-attributes ret
591 (setq separator lbs))
594 (insert (prin1-to-string cell))
595 (setq separator " "))
596 (setq value (cdr value)))
598 (insert line-breaking))
600 (insert (format "(%-18s . %S)%s"
603 (setq alist (cdr alist))))
606 (defun char-db-insert-char-reference (plist &optional readable column)
608 (setq column (current-column)))
610 (concat "\n" (make-string (1+ column) ?\ )))
615 (setq name (pop plist))
616 (setq value (pop plist))
617 (cond ((eq name :char)
620 (cond ((numberp value)
621 (setq value (decode-char '=ucs value)))
623 ;; (setq value (or (find-char value)
626 (char-db-insert-char-spec value readable)
627 (insert line-breaking)
630 (insert (format "%s%s\t%d ; %c%s"
633 (ideographic-radical value)
637 (insert (format "%s%s\t%S" separator name value))
638 (setq separator line-breaking)))
642 (defun char-db-decode-isolated-char (ccs code-point)
645 (cond ((eq ccs 'arabic-iso8859-6)
646 (decode-char ccs code-point))
648 ;; (decode-builtin-char '==gt code-point))
649 ((and (memq ccs '(=gt-pj-1
660 (setq ret (decode-char ccs code-point))
661 (setq ret (encode-char ret '=gt 'defined-only)))
662 (decode-builtin-char '=gt ret))
664 (decode-builtin-char ccs code-point))))
666 (or (decode-char ccs code-point)
667 (define-char (list (cons ccs code-point)))))
668 ((and (<= 0 (char-int ret))
669 (<= (char-int ret) #x1F))
670 (decode-char '=ucs (+ #x2400 (char-int ret))))
671 ((= (char-int ret) #x7F)
675 (defvar char-db-convert-obsolete-format t)
677 (defun char-db-insert-ccs-feature (name value line-breaking)
683 ((memq name '(=>iwds-1
686 =shinjigen@1ed ==shinjigen@1ed
687 =shinjigen@rev ==shinjigen@rev
688 =shinjigen/+p@rev ==shinjigen/+p@rev
689 ===daikanwa/ho ==daikanwa/ho
690 =daikanwa/ho =>>daikanwa/ho =>daikanwa/ho))
691 "(%-18s . %04d)\t; %c")
692 ((eq name '=shinjigen@1ed/24pr)
693 "(%-18s . %04d)\t; %c")
697 ==daikanwa =daikanwa =>>daikanwa =>daikanwa
698 =daikanwa@rev1 =daikanwa@rev2
699 =daikanwa/+p ==daikanwa/+p ===daikanwa/+p
701 =daikanwa/+2p =>>daikanwa/+2p
706 =adobe-japan1-0 ==adobe-japan1-0 ===adobe-japan1-0
707 =adobe-japan1-1 ==adobe-japan1-1 ===adobe-japan1-1
708 =adobe-japan1-2 ==adobe-japan1-2 ===adobe-japan1-2
709 =adobe-japan1-3 ==adobe-japan1-3 ===adobe-japan1-3
710 =adobe-japan1-4 ==adobe-japan1-4 ===adobe-japan1-4
711 =adobe-japan1-5 ==adobe-japan1-5 ===adobe-japan1-5
712 =adobe-japan1-6 ==adobe-japan1-6 ===adobe-japan1-6
713 =>>adobe-japan1-0 =+>adobe-japan1-0
714 =>>adobe-japan1-1 =+>adobe-japan1-1
715 =>>adobe-japan1-2 =+>adobe-japan1-2
716 =>>adobe-japan1-3 =+>adobe-japan1-3
717 =>>adobe-japan1-4 =+>adobe-japan1-4
718 =>>adobe-japan1-5 =+>adobe-japan1-5
719 =>>adobe-japan1-6 =+>adobe-japan1-6
720 =>cbeta =cbeta =>>cbeta ==cbeta ===cbeta
721 =zinbun-oracle =>zinbun-oracle
722 ===hng-jou ===hng-keg ===hng-dng ===hng-mam
723 ===hng-drt ===hng-kgk ===hng-myz ===hng-kda
724 ===hng-khi ===hng-khm ===hng-hok ===hng-kyd ===hng-sok
725 ===hng-yhk ===hng-kak ===hng-kar ===hng-kae
726 ===hng-sys ===hng-tsu ===hng-tzj
727 ===hng-hos ===hng-nak ===hng-jhk
728 ===hng-hod ===hng-gok ===hng-ink ===hng-nto
729 ===hng-nkm ===hng-k24 ===hng-nkk
730 ===hng-kcc ===hng-kcj ===hng-kbk ===hng-sik
731 ===hng-skk ===hng-kyu ===hng-ksk ===hng-wan
732 ===hng-okd ===hng-wad ===hng-kmi
733 ===hng-zkd ===hng-doh ===hng-jyu
734 ===hng-tzs ===hng-kss ===hng-kyo
736 ;; (string-match "^=adobe-" (symbol-name name))
738 "(%-18s . %05d)\t; %c")
739 ((memq name '(=hanyo-denshi/ks
740 ==hanyo-denshi/ks ===hanyo-denshi/ks
743 =mj ==mj ===mj =>>mj =>mj
745 "(%-18s . %06d)\t; %c")
746 ((memq name '(=hanyo-denshi/tk ==hanyo-denshi/tk))
747 "(%-18s . %08d)\t; %c")
748 ((>= (charset-dimension name) 2)
749 "(%-18s . #x%04X)\t; %c")
751 "(%-18s . #x%02X)\t; %c"))
753 (if (= (charset-iso-graphic-plane name) 1)
755 (cond ((= (charset-dimension name) 1)
757 ((= (charset-dimension name) 2)
759 ((= (charset-dimension name) 3)
763 (char-db-decode-isolated-char name value)))
764 (if (and (= (charset-chars name) 94)
765 (= (charset-dimension name) 2))
766 (insert (format " [%02d-%02d]"
767 (- (lsh value -8) 32)
768 (- (logand value 255) 32))))
771 (insert (format "(%-18s . %s)" name value))
773 (insert line-breaking))
775 (defun char-db-insert-relation-feature (char name value line-breaking
777 (insert (format "(%-18s%s " name line-breaking))
778 (let ((lbs (concat "\n" (make-string (current-column) ?\ )))
779 separator cell sources required-features
782 (setq cell (car value))
784 (setq cell (decode-char '=ucs cell)))
786 ((eq name '->subsumptive)
787 (when (or (not (some (lambda (atr)
788 (get-char-attribute cell atr))
789 char-db-ignored-attributes))
791 (encode-char cell ccs 'defined-only))
795 (let ((char-db-ignored-attributes
797 char-db-ignored-attributes)))
798 (insert-char-attributes cell readable nil nil 'for-sub-node))
799 (setq separator lbs))
804 char (intern (format "%s*sources" name))))
805 (setq required-features nil)
806 (dolist (source sources)
810 shinjigen shinjigen@1ed shinjigen@rev))
811 (setq required-features
812 (union required-features
824 =shinjigen/+p@rev))))
826 (setq required-features
827 (union required-features
832 ((find-charset (setq ret (intern (format "=%s" source))))
833 (setq required-features
834 (cons ret required-features)))
835 (t (setq required-features
836 (cons source required-features)))))
837 (cond ((string-match "@JP" (symbol-name name))
838 (setq required-features
839 (union required-features
847 ((string-match "@CN" (symbol-name name))
848 (setq required-features
849 (union required-features
856 (insert (format "%S" cell))
857 (char-db-insert-char-spec cell readable
860 (setq separator lbs))
864 (if (consp (car cell))
865 (char-db-insert-char-spec cell readable)
866 (char-db-insert-char-reference cell readable))
867 (setq separator lbs))
871 (insert (prin1-to-string cell))
872 (setq separator " ")))
873 (setq value (cdr value)))
875 (insert line-breaking)))
877 (defun insert-char-attributes (char &optional readable attributes column
880 (setq column (current-column)))
881 (let (name value ; has-long-ccs-name
885 (concat "\n" (make-string (1+ column) ?\ )))
886 lbs cell separator ret
888 dest-ccss ; sources required-features
893 (if (consp attributes)
895 (dolist (name attributes)
896 (unless (memq name char-db-ignored-attributes)
897 (if (find-charset name)
901 (dolist (name (char-attribute-list))
902 (unless (memq name char-db-ignored-attributes)
903 (if (find-charset name)
907 #'char-attribute-name<)))
909 (when (memq '<-subsumptive attributes)
910 (when (or readable (not for-sub-node))
911 (when (setq value (get-char-attribute char '<-subsumptive))
912 (char-db-insert-relation-feature char '<-subsumptive value
915 (setq attributes (delq '<-subsumptive attributes)))
916 (when (and (memq '<-denotational attributes)
917 (setq value (get-char-attribute char '<-denotational)))
918 (char-db-insert-relation-feature char '<-denotational value
921 (setq attributes (delq '<-denotational attributes)))
922 (when (and (memq '<-denotational@component attributes)
923 (setq value (get-char-attribute char '<-denotational@component)))
924 (char-db-insert-relation-feature char '<-denotational@component value
927 (setq attributes (delq '<-denotational@component attributes)))
928 (when (and (memq 'name attributes)
929 (setq value (get-char-attribute char 'name)))
931 (if (> (+ (current-column) (length value)) 48)
934 value line-breaking))
935 (setq attributes (delq 'name attributes))
937 (when (and (memq 'name* attributes)
938 (setq value (get-char-attribute char 'name*)))
940 (if (> (+ (current-column) (length value)) 48)
943 value line-breaking))
944 (setq attributes (delq 'name* attributes))
946 (when (and (memq 'script attributes)
947 (setq value (get-char-attribute char 'script)))
948 (insert (format "(script\t\t%s)%s"
949 (mapconcat (function prin1-to-string)
952 (setq attributes (delq 'script attributes))
954 (dolist (name '(=>ucs =>ucs*))
955 (when (and (memq name attributes)
956 (setq value (get-char-attribute char name)))
957 (insert (format "(%-18s . #x%04X)\t; %c%s"
958 name value (decode-char '=ucs value)
960 (setq attributes (delq name attributes))))
961 (dolist (name '(=>ucs@gb =>ucs@big5))
962 (when (and (memq name attributes)
963 (setq value (get-char-attribute char name)))
964 (insert (format "(%-18s . #x%04X)\t; %c%s"
969 (symbol-name name) 2)))
972 (setq attributes (delq name attributes))
974 ;; (dolist (name '(=>daikanwa))
975 ;; (when (and (memq name attributes)
976 ;; (setq value (get-char-attribute char name)))
978 ;; (if (integerp value)
979 ;; (format "(%-18s . %05d)\t; %c%s"
980 ;; name value (decode-char '=daikanwa value)
982 ;; (format "(%-18s %s)\t; %c%s"
984 ;; (mapconcat (function prin1-to-string)
986 ;; (char-representative-of-daikanwa char)
988 ;; (setq attributes (delq name attributes))))
989 (when (and (memq 'general-category attributes)
990 (setq value (get-char-attribute char 'general-category)))
992 "(general-category\t%s) ; %s%s"
993 (mapconcat (lambda (cell)
996 (cond ((rassoc value unidata-normative-category-alist)
997 "Normative Category")
998 ((rassoc value unidata-informative-category-alist)
999 "Informative Category")
1001 "Unknown Category"))
1003 (setq attributes (delq 'general-category attributes))
1005 (when (and (memq 'bidi-category attributes)
1006 (setq value (get-char-attribute char 'bidi-category)))
1007 (insert (format "(bidi-category\t. %S)%s"
1010 (setq attributes (delq 'bidi-category attributes))
1012 (unless (or (not (memq 'mirrored attributes))
1013 (eq (setq value (get-char-attribute char 'mirrored 'empty))
1015 (insert (format "(mirrored\t\t. %S)%s"
1018 (setq attributes (delq 'mirrored attributes))
1021 ((and (memq 'decimal-digit-value attributes)
1022 (setq value (get-char-attribute char 'decimal-digit-value)))
1023 (insert (format "(decimal-digit-value . %S)%s"
1026 (setq attributes (delq 'decimal-digit-value attributes))
1027 (when (and (memq 'digit-value attributes)
1028 (setq value (get-char-attribute char 'digit-value)))
1029 (insert (format "(digit-value\t . %S)%s"
1032 (setq attributes (delq 'digit-value attributes))
1034 (when (and (memq 'numeric-value attributes)
1035 (setq value (get-char-attribute char 'numeric-value)))
1036 (insert (format "(numeric-value\t . %S)%s"
1039 (setq attributes (delq 'numeric-value attributes))
1043 (when (and (memq 'digit-value attributes)
1044 (setq value (get-char-attribute char 'digit-value)))
1045 (insert (format "(digit-value\t. %S)%s"
1048 (setq attributes (delq 'digit-value attributes))
1050 (when (and (memq 'numeric-value attributes)
1051 (setq value (get-char-attribute char 'numeric-value)))
1052 (insert (format "(numeric-value\t. %S)%s"
1055 (setq attributes (delq 'numeric-value attributes))
1057 (when (and (memq 'iso-10646-comment attributes)
1058 (setq value (get-char-attribute char 'iso-10646-comment)))
1059 (insert (format "(iso-10646-comment\t. %S)%s"
1062 (setq attributes (delq 'iso-10646-comment attributes))
1064 (when (and (memq 'morohashi-daikanwa attributes)
1065 (setq value (get-char-attribute char 'morohashi-daikanwa)))
1066 (insert (format "(morohashi-daikanwa\t%s)%s"
1067 (mapconcat (function prin1-to-string) value " ")
1069 (setq attributes (delq 'morohashi-daikanwa attributes))
1073 (when (and (memq 'ideographic-radical attributes)
1074 (setq value (get-char-attribute char 'ideographic-radical)))
1075 (setq radical value)
1076 (insert (format "(ideographic-radical . %S)\t; %c%s"
1078 (ideographic-radical radical)
1080 (setq attributes (delq 'ideographic-radical attributes))
1082 (when (and (memq 'shuowen-radical attributes)
1083 (setq value (get-char-attribute char 'shuowen-radical)))
1084 (insert (format "(shuowen-radical\t. %S)\t; %c%s"
1086 (shuowen-radical value)
1088 (setq attributes (delq 'shuowen-radical attributes))
1093 char-db-feature-domains
1095 (dolist (feature (char-attribute-list))
1096 (setq feature (symbol-name feature))
1098 "\\(radical\\|strokes\\)@\\([^@*]+\\)\\(\\*\\|$\\)"
1100 (setq domain (intern (match-string 2 feature)))
1101 (unless (memq domain dest)
1102 (setq dest (cons domain dest)))))
1103 (sort dest #'string<))))
1104 (setq key (intern (format "%s@%s" 'ideographic-radical domain)))
1105 (when (and (memq key attributes)
1106 (setq value (get-char-attribute char key)))
1107 (setq radical value)
1108 (insert (format "(%s . %S)\t; %c%s"
1111 (ideographic-radical radical)
1113 (setq attributes (delq key attributes))
1115 (setq key (intern (format "%s@%s" 'ideographic-strokes domain)))
1116 (when (and (memq key attributes)
1117 (setq value (get-char-attribute char key)))
1118 (setq strokes value)
1119 (insert (format "(%s . %S)%s"
1123 (setq attributes (delq key attributes))
1125 (setq key (intern (format "%s@%s" 'total-strokes domain)))
1126 (when (and (memq key attributes)
1127 (setq value (get-char-attribute char key)))
1128 (insert (format "(%s . %S)%s"
1132 (setq attributes (delq key attributes))
1134 (dolist (feature '(ideographic-radical
1137 (setq key (intern (format "%s@%s*sources" feature domain)))
1138 (when (and (memq key attributes)
1139 (setq value (get-char-attribute char key)))
1140 (insert (format "(%s%s" key line-breaking))
1141 (dolist (cell value)
1142 (insert (format " %s" cell)))
1144 (insert line-breaking)
1145 (setq attributes (delq key attributes))
1148 (when (and (memq 'ideographic-strokes attributes)
1149 (setq value (get-char-attribute char 'ideographic-strokes)))
1150 (setq strokes value)
1151 (insert (format "(ideographic-strokes . %S)%s"
1154 (setq attributes (delq 'ideographic-strokes attributes))
1156 (when (and (memq 'kangxi-radical attributes)
1157 (setq value (get-char-attribute char 'kangxi-radical)))
1158 (unless (eq value radical)
1159 (insert (format "(kangxi-radical\t . %S)\t; %c%s"
1161 (ideographic-radical value)
1164 (setq radical value)))
1165 (setq attributes (delq 'kangxi-radical attributes))
1167 (when (and (memq 'kangxi-strokes attributes)
1168 (setq value (get-char-attribute char 'kangxi-strokes)))
1169 (unless (eq value strokes)
1170 (insert (format "(kangxi-strokes\t . %S)%s"
1174 (setq strokes value)))
1175 (setq attributes (delq 'kangxi-strokes attributes))
1177 ;; (when (and (memq 'japanese-radical attributes)
1178 ;; (setq value (get-char-attribute char 'japanese-radical)))
1179 ;; (unless (eq value radical)
1180 ;; (insert (format "(japanese-radical\t . %S)\t; %c%s"
1182 ;; (ideographic-radical value)
1185 ;; (setq radical value)))
1186 ;; (setq attributes (delq 'japanese-radical attributes))
1188 (when (and (memq 'japanese-strokes attributes)
1189 (setq value (get-char-attribute char 'japanese-strokes)))
1190 (unless (eq value strokes)
1191 (insert (format "(japanese-strokes\t . %S)%s"
1195 (setq strokes value)))
1196 (setq attributes (delq 'japanese-strokes attributes))
1198 (when (and (memq 'cns-radical attributes)
1199 (setq value (get-char-attribute char 'cns-radical)))
1200 (insert (format "(cns-radical\t . %S)\t; %c%s"
1202 (ideographic-radical value)
1204 (setq attributes (delq 'cns-radical attributes))
1206 (when (and (memq 'cns-strokes attributes)
1207 (setq value (get-char-attribute char 'cns-strokes)))
1208 (unless (eq value strokes)
1209 (insert (format "(cns-strokes\t . %S)%s"
1213 (setq strokes value)))
1214 (setq attributes (delq 'cns-strokes attributes))
1216 ;; (when (and (memq 'shinjigen-1-radical attributes)
1217 ;; (setq value (get-char-attribute char 'shinjigen-1-radical)))
1218 ;; (unless (eq value radical)
1219 ;; (insert (format "(shinjigen-1-radical . %S)\t; %c%s"
1221 ;; (ideographic-radical value)
1224 ;; (setq radical value)))
1225 ;; (setq attributes (delq 'shinjigen-1-radical attributes))
1227 ;; (when (and (memq 'ideographic- attributes)
1228 ;; (setq value (get-char-attribute char 'ideographic-)))
1229 ;; (insert "(ideographic- ")
1230 ;; (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1232 ;; (while (consp value)
1233 ;; (setq cell (car value))
1234 ;; (if (integerp cell)
1235 ;; (setq cell (decode-char '=ucs cell)))
1236 ;; (cond ((characterp cell)
1240 ;; (insert (format "%S" cell))
1241 ;; (char-db-insert-char-spec cell readable))
1242 ;; (setq separator lbs))
1246 ;; (if (consp (car cell))
1247 ;; (char-db-insert-char-spec cell readable)
1248 ;; (char-db-insert-char-reference cell readable))
1249 ;; (setq separator lbs))
1252 ;; (insert separator))
1253 ;; (insert (prin1-to-string cell))
1254 ;; (setq separator " ")))
1255 ;; (setq value (cdr value)))
1257 ;; (insert line-breaking)
1258 ;; (setq attributes (delq 'ideographic- attributes)))
1259 (when (and (memq 'total-strokes attributes)
1260 (setq value (get-char-attribute char 'total-strokes)))
1261 (insert (format "(total-strokes . %S)%s"
1264 (setq attributes (delq 'total-strokes attributes))
1266 ;; (when (and (memq '->ideograph attributes)
1267 ;; (setq value (get-char-attribute char '->ideograph)))
1268 ;; (insert (format "(->ideograph\t%s)%s"
1269 ;; (mapconcat (lambda (code)
1270 ;; (cond ((symbolp code)
1271 ;; (symbol-name code))
1273 ;; (format "#x%04X" code))
1276 ;; line-breaking code))))
1279 ;; (setq attributes (delq '->ideograph attributes))
1281 ;; (when (and (memq '->decomposition attributes)
1282 ;; (setq value (get-char-attribute char '->decomposition)))
1283 ;; (insert (format "(->decomposition\t%s)%s"
1284 ;; (mapconcat (lambda (code)
1285 ;; (cond ((symbolp code)
1286 ;; (symbol-name code))
1287 ;; ((characterp code)
1289 ;; (format "%S" code)
1294 ;; (format "#x%04X" code))
1296 ;; (format "%s%S" line-breaking code))))
1299 ;; (setq attributes (delq '->decomposition attributes))
1301 (if (equal (get-char-attribute char '->titlecase)
1302 (get-char-attribute char '->uppercase))
1303 (setq attributes (delq '->titlecase attributes)))
1304 (when (and (memq '->mojikyo attributes)
1305 (setq value (get-char-attribute char '->mojikyo)))
1306 (insert (format "(->mojikyo\t\t. %06d)\t; %c%s"
1307 value (decode-char 'mojikyo value)
1309 (setq attributes (delq '->mojikyo attributes))
1311 ;; (when (and (memq 'hanyu-dazidian-vol attributes)
1312 ;; (setq value (get-char-attribute char 'hanyu-dazidian-vol)))
1313 ;; (insert (format "(hanyu-dazidian-vol . %d)%s"
1314 ;; value line-breaking))
1315 ;; (setq attributes (delq 'hanyu-dazidian-vol attributes))
1317 ;; (when (and (memq 'hanyu-dazidian-page attributes)
1318 ;; (setq value (get-char-attribute char 'hanyu-dazidian-page)))
1319 ;; (insert (format "(hanyu-dazidian-page . %d)%s"
1320 ;; value line-breaking))
1321 ;; (setq attributes (delq 'hanyu-dazidian-page attributes))
1323 ;; (when (and (memq 'hanyu-dazidian-char attributes)
1324 ;; (setq value (get-char-attribute char 'hanyu-dazidian-char)))
1325 ;; (insert (format "(hanyu-dazidian-char . %d)%s"
1326 ;; value line-breaking))
1327 ;; (setq attributes (delq 'hanyu-dazidian-char attributes))
1330 (dolist (ignored '(composition
1331 ->denotational <-subsumptive ->ucs-unified
1332 ->ideographic-component-forms))
1333 (setq attributes (delq ignored attributes))))
1335 (setq name (car attributes))
1336 (unless (eq (setq value (get-char-attribute char name 'value-is-empty))
1338 (cond ((setq ret (find-charset name))
1339 (setq name (charset-name ret))
1340 (when (not (memq name dest-ccss))
1341 (setq dest-ccss (cons name dest-ccss))
1342 (char-db-insert-ccs-feature name value line-breaking))
1344 ((string-match "^=>ucs@" (symbol-name name))
1345 (insert (format "(%-18s . #x%04X)\t; %c%s"
1346 name value (decode-char '=ucs value)
1349 ((eq name 'jisx0208-1978/4X)
1350 (insert (format "(%-18s . #x%04X)%s"
1356 (not (eq name '->subsumptive))
1357 (not (eq name '->uppercase))
1358 (not (eq name '->lowercase))
1359 (not (eq name '->titlecase))
1360 (not (eq name '->canonical))
1361 (not (eq name '->Bopomofo))
1362 (not (eq name '->mistakable))
1363 (not (eq name '->ideographic-variants))
1364 (null (get-char-attribute
1365 char (intern (format "%s*sources" name))))
1366 (not (string-match "\\*sources$" (symbol-name name)))
1367 (null (get-char-attribute
1368 char (intern (format "%s*note" name))))
1369 (not (string-match "\\*note$" (symbol-name name)))
1370 (or (eq name '<-identical)
1371 (eq name '<-uppercase)
1372 (eq name '<-lowercase)
1373 (eq name '<-titlecase)
1374 (eq name '<-canonical)
1375 (eq name '<-ideographic-variants)
1376 ;; (eq name '<-synonyms)
1377 (string-match "^<-synonyms" (symbol-name name))
1378 (eq name '<-mistakable)
1379 (when (string-match "^->" (symbol-name name))
1381 ((string-match "^->fullwidth" (symbol-name name))
1382 (not (and (consp value)
1383 (characterp (car value))
1385 (car value) '=ucs 'defined-only)))
1390 ((or (eq name 'ideographic-structure)
1391 (eq name 'ideographic-combination)
1392 ;; (eq name 'ideographic-)
1393 (eq name '=decomposition)
1394 (char-feature-base-name= '=decomposition name)
1395 (char-feature-base-name= '=>decomposition name)
1396 ;; (string-match "^=>*decomposition\\(@[^*]+\\)?$"
1397 ;; (symbol-name name))
1398 (string-match "^\\(->\\|<-\\)[^*]*$" (symbol-name name))
1399 (string-match "^\\(->\\|<-\\)[^*]*\\*sources$"
1402 (char-db-insert-relation-feature char name value
1405 ;; ((memq name '(ideograph=
1406 ;; original-ideograph-of
1407 ;; ancient-ideograph-of
1408 ;; vulgar-ideograph-of
1409 ;; wrong-ideograph-of
1410 ;; ;; simplified-ideograph-of
1411 ;; ideographic-variants
1412 ;; ;; ideographic-different-form-of
1414 ;; (insert (format "(%-18s%s " name line-breaking))
1415 ;; (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1417 ;; (while (consp value)
1418 ;; (setq cell (car value))
1419 ;; (if (and (consp cell)
1420 ;; (consp (car cell)))
1424 ;; (char-db-insert-alist cell readable)
1425 ;; (setq separator lbs))
1427 ;; (insert separator))
1428 ;; (insert (prin1-to-string cell))
1429 ;; (setq separator " "))
1430 ;; (setq value (cdr value)))
1432 ;; (insert line-breaking))
1434 (insert (format "(%-18s " name))
1435 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1437 (while (consp value)
1438 (setq cell (car value))
1439 (if (and (consp cell)
1441 (setq ret (condition-case nil
1449 (setq key (car (car rest)))
1450 (if (find-charset key)
1451 (setq cal (cons key cal))
1452 (setq al (cons key al)))
1453 (setq rest (cdr rest)))
1456 (insert-char-attributes ret
1460 (setq separator lbs))
1461 (setq ret (prin1-to-string cell))
1463 (if (< (+ (current-column)
1470 (setq separator " "))
1471 (setq value (cdr value)))
1473 (insert line-breaking))
1475 (insert (format "(%-18s" name))
1476 (setq ret (prin1-to-string value))
1477 (unless (< (+ (current-column)
1481 (insert line-breaking))
1482 (insert " . " ret ")" line-breaking)
1483 ;; (insert (format "(%-18s . %S)%s"
1488 (setq attributes (cdr attributes)))
1491 (defun insert-char-data (char &optional readable
1494 (narrow-to-region (point)(point))
1495 (insert "(define-char
1497 (insert-char-attributes char readable attributes)
1499 (goto-char (point-min))
1500 (while (re-search-forward "[ \t]+$" nil t)
1503 (goto-char (point-min))
1504 (while (re-search-forward "[ \t][ \t][ \t]*" nil t)
1505 (let ((column (current-column))
1506 (indent-tabs-mode t))
1507 (delete-region (match-beginning 0) (point))
1508 (indent-to column)))
1509 (goto-char (point-max))
1510 ;; (tabify (point-min)(point-max))
1513 (defun insert-char-data-with-variant (char &optional printable
1515 script excluded-script)
1516 (insert-char-data char printable)
1517 (let ((variants (char-variants char))
1520 (setq variants (sort variants #'<))
1521 (setq rest variants)
1522 (setq variants (cons char variants))
1524 (setq variant (car rest))
1525 (unless (get-char-attribute variant '<-subsumptive)
1526 (if (and (or (null script)
1527 (null (setq vs (get-char-attribute variant 'script)))
1529 (or (null excluded-script)
1530 (null (setq vs (get-char-attribute variant 'script)))
1531 (not (memq excluded-script vs))))
1532 (unless (and no-ucs-unified (get-char-attribute variant '=ucs))
1533 (insert-char-data variant printable)
1534 (if (setq ret (char-variants variant))
1536 (or (memq (car ret) variants)
1537 ;; (get-char-attribute (car ret) '<-subsumptive)
1538 (setq rest (nconc rest (list (car ret)))))
1539 (setq ret (cdr ret)))))))
1540 (setq rest (cdr rest)))))
1542 (defun insert-char-range-data (min max &optional script excluded-script)
1545 (while (<= code max)
1546 (setq char (decode-char '=ucs code))
1547 (if (encode-char char '=ucs 'defined-only)
1548 (insert-char-data-with-variant char nil 'no-ucs-unified
1549 script excluded-script))
1550 (setq code (1+ code)))))
1552 (defun write-char-range-data-to-file (min max file
1553 &optional script excluded-script)
1554 (let ((coding-system-for-write char-db-file-coding-system))
1556 (insert (format ";; -*- coding: %s -*-\n"
1557 char-db-file-coding-system))
1558 (insert-char-range-data min max script excluded-script)
1559 (write-region (point-min)(point-max) file))))
1561 (defvar what-character-original-window-configuration)
1564 (defun what-char-definition (char)
1565 (interactive (list (char-after)))
1566 (let ((buf (get-buffer-create "*Character Description*"))
1567 (the-buf (current-buffer))
1568 (win-conf (current-window-configuration)))
1570 (make-local-variable 'what-character-original-window-configuration)
1571 (setq what-character-original-window-configuration win-conf)
1572 (setq buffer-read-only nil)
1576 (insert-char-data-with-variant char 'printable)
1577 (unless (char-attribute-alist char)
1578 (insert (format ";; = %c\n"
1579 (let* ((rest (split-char char))
1583 (setq code (logior (lsh code 8)
1585 (decode-char ccs code)))))
1586 ;; (char-db-update-comment)
1587 (set-buffer-modified-p nil)
1588 (view-mode the-buf (lambda (buf)
1589 (set-window-configuration
1590 what-character-original-window-configuration)
1592 (goto-char (point-min)))
1594 (set-window-configuration
1595 what-character-original-window-configuration)
1596 (signal (car err) (cdr err)))))))
1602 (provide 'char-db-util)
1604 ;;; char-db-util.el ends here