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 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
210 ;; =>>>adobe-japan1-0
211 ;; =>>>adobe-japan1-1
212 ;; =>>>adobe-japan1-2
213 ;; =>>>adobe-japan1-3
214 ;; =>>>adobe-japan1-4
215 ;; =>>>adobe-japan1-5
216 ;; =>>>adobe-japan1-6
220 ;; =>>>hanyo-denshi/ja
221 ;; =>>>hanyo-denshi/jb
222 ;; =>>>hanyo-denshi/jc
223 ;; =>>>hanyo-denshi/ft
224 ;; =>>>hanyo-denshi/ib
225 ;; =>>>hanyo-denshi/hg
226 ;; =>>>hanyo-denshi/jt
227 ;; =>>>hanyo-denshi/ks
333 ;;; @ char-db formatters
336 (defun char-db-make-char-spec (char)
338 (cond ((characterp char)
339 (cond ((and (setq ret (encode-char char '=ucs 'defined-only))
340 (not (and (<= #xE000 ret)(<= ret #xF8FF))))
341 (setq char-spec (list (cons '=ucs ret)))
342 (cond ((setq ret (get-char-attribute char 'name))
343 (setq char-spec (cons (cons 'name ret) char-spec))
345 ((setq ret (get-char-attribute char 'name*))
346 (setq char-spec (cons (cons 'name* ret) char-spec))
349 ((encode-char char '=mj 'defined-only)
351 (dolist (ccs (charset-list))
352 (if (and (or (eq ccs '=mj)
353 ;; (eq (charset-property ccs 'iso-ir) 177)
354 (string-match "=ucs@" (symbol-name ccs))
356 (setq ccs (charset-name ccs))
357 (null (assq ccs char-spec))
358 (setq ret (encode-char char ccs 'defined-only)))
359 (setq char-spec (cons (cons ccs 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 '=adobe-japan1 'defined-only)
375 (dolist (ccs (charset-list))
376 (if (and (or (memq ccs
385 ;; (eq (charset-property ccs 'iso-ir) 177)
386 (string-match "=ucs@" (symbol-name ccs))
388 (setq ccs (charset-name ccs))
389 (null (assq ccs char-spec))
390 (setq ret (encode-char char ccs 'defined-only)))
391 (setq char-spec (cons (cons ccs ret) char-spec))))
393 ((encode-char char '==adobe-japan1 'defined-only)
395 (dolist (ccs (charset-list))
396 (if (and (or (memq ccs
405 ;; (eq (charset-property ccs 'iso-ir) 177)
406 (string-match "=ucs@" (symbol-name ccs))
408 (setq ccs (charset-name ccs))
409 (null (assq ccs char-spec))
410 (setq ret (encode-char char ccs 'defined-only)))
411 (setq char-spec (cons (cons ccs ret) char-spec))))
415 (let ((rest char-db-coded-charset-priority-list)
418 (setq ccs (charset-name
419 (find-charset (car rest))))
421 (encode-char char ccs
423 (throw 'tag (cons ccs ret)))
424 (setq rest (cdr rest))))))
425 (setq char-spec (list ret))
426 (dolist (ccs (delq (car ret) (charset-list)))
427 (if (and (or (charset-iso-final-char ccs)
434 (eq (charset-property ccs 'iso-ir) 177)
435 ;; (string-match "=ucs@" (symbol-name ccs))
437 (setq ccs (charset-name ccs))
438 (null (assq ccs char-spec))
439 (setq ret (encode-char char ccs 'defined-only)))
440 (setq char-spec (cons (cons ccs ret) char-spec))))
442 (setq char-spec (split-char char)))
443 (cond ((setq ret (get-char-attribute char 'name))
444 (setq char-spec (cons (cons 'name ret) char-spec))
446 ((setq ret (get-char-attribute char 'name*))
447 (setq char-spec (cons (cons 'name* ret) char-spec))
450 ((setq ret (get-char-attribute
451 char 'ideographic-combination))
453 (cons (cons 'ideographic-combination ret)
460 (defun char-db-insert-char-spec (char &optional readable column
463 (setq column (current-column)))
464 (let (char-spec temp-char)
465 (setq char-spec (char-db-make-char-spec char))
466 (unless (or (characterp char) ; char
468 (setq char (find-char char-spec))
470 ;; define temporary character
471 ;; Current implementation is dirty.
472 (setq temp-char (define-char (cons '(ideograph-daikanwa . 0)
474 (remove-char-attribute temp-char 'ideograph-daikanwa)
475 (setq char temp-char))
476 (insert-char-attributes char
478 (union (mapcar #'car char-spec)
482 ;; undefine temporary character
483 ;; Current implementation is dirty.
484 (setq char-spec (char-attribute-alist temp-char))
486 (remove-char-attribute temp-char (car (car char-spec)))
487 (setq char-spec (cdr char-spec))))))
489 (defun char-db-insert-alist (alist &optional readable column)
491 (setq column (current-column)))
493 (concat "\n" (make-string (1+ column) ?\ )))
497 lbs cell rest separator)
500 (setq name (car (car alist))
501 value (cdr (car alist)))
502 (cond ((eq name 'char)
504 (if (setq ret (condition-case nil
512 (setq key (car (car value)))
513 ;; (if (find-charset key)
514 ;; (setq cal (cons key cal))
515 (setq al (cons key al))
517 (setq value (cdr value)))
518 (insert-char-attributes ret
522 (insert (prin1-to-string value)))
524 (insert line-breaking))
526 (insert (format "(%-18s " name))
527 (setq lbs (concat "\n" (make-string (current-column) ?\ )))
529 (setq cell (car value))
530 (if (and (consp cell)
532 (setq ret (condition-case nil
542 (setq key (car (car rest)))
543 ;; (if (find-charset key)
544 ;; (setq cal (cons key cal))
545 (setq al (cons key al))
547 (setq rest (cdr rest)))
550 (insert-char-attributes ret
554 (setq separator lbs))
557 (insert (prin1-to-string cell))
558 (setq separator " "))
559 (setq value (cdr value)))
561 (insert line-breaking))
563 (insert (format "(%-18s . %S)%s"
566 (setq alist (cdr alist))))
569 (defun char-db-insert-char-reference (plist &optional readable column)
571 (setq column (current-column)))
573 (concat "\n" (make-string (1+ column) ?\ )))
578 (setq name (pop plist))
579 (setq value (pop plist))
580 (cond ((eq name :char)
583 (cond ((numberp value)
584 (setq value (decode-char '=ucs value)))
586 ;; (setq value (or (find-char value)
589 (char-db-insert-char-spec value readable)
590 (insert line-breaking)
593 (insert (format "%s%s\t%d ; %c%s"
596 (ideographic-radical value)
600 (insert (format "%s%s\t%S" separator name value))
601 (setq separator line-breaking)))
605 (defun char-db-decode-isolated-char (ccs code-point)
608 (cond ((eq ccs 'arabic-iso8859-6)
609 (decode-char ccs code-point))
611 ;; (decode-builtin-char '==gt code-point))
612 ((and (memq ccs '(=gt-pj-1
623 (setq ret (decode-char ccs code-point))
624 (setq ret (encode-char ret '=gt 'defined-only)))
625 (decode-builtin-char '=gt ret))
627 (decode-builtin-char ccs code-point))))
629 (or (decode-char ccs code-point)
630 (define-char (list (cons ccs code-point)))))
631 ((and (<= 0 (char-int ret))
632 (<= (char-int ret) #x1F))
633 (decode-char '=ucs (+ #x2400 (char-int ret))))
634 ((= (char-int ret) #x7F)
638 (defvar char-db-convert-obsolete-format t)
640 (defun char-db-insert-ccs-feature (name value line-breaking)
646 ((memq name '(=>iwds-1
649 =shinjigen@1ed ==shinjigen@1ed
650 =shinjigen@rev ==shinjigen@rev
651 =shinjigen/+p@rev ==shinjigen/+p@rev
652 ===daikanwa/ho ==daikanwa/ho
653 =daikanwa/ho =>>daikanwa/ho =>daikanwa/ho))
654 "(%-18s . %04d)\t; %c")
655 ((eq name '=shinjigen@1ed/24pr)
656 "(%-18s . %04d)\t; %c")
660 ==daikanwa =daikanwa =>>daikanwa =>daikanwa
661 =daikanwa@rev1 =daikanwa@rev2
662 =daikanwa/+p ==daikanwa/+p ===daikanwa/+p
664 =daikanwa/+2p =>>daikanwa/+2p
669 =adobe-japan1-0 ==adobe-japan1-0 ===adobe-japan1-0
670 =adobe-japan1-1 ==adobe-japan1-1 ===adobe-japan1-1
671 =adobe-japan1-2 ==adobe-japan1-2 ===adobe-japan1-2
672 =adobe-japan1-3 ==adobe-japan1-3 ===adobe-japan1-3
673 =adobe-japan1-4 ==adobe-japan1-4 ===adobe-japan1-4
674 =adobe-japan1-5 ==adobe-japan1-5 ===adobe-japan1-5
675 =adobe-japan1-6 ==adobe-japan1-6 ===adobe-japan1-6
676 =>>adobe-japan1-0 =+>adobe-japan1-0
677 =>>adobe-japan1-1 =+>adobe-japan1-1
678 =>>adobe-japan1-2 =+>adobe-japan1-2
679 =>>adobe-japan1-3 =+>adobe-japan1-3
680 =>>adobe-japan1-4 =+>adobe-japan1-4
681 =>>adobe-japan1-5 =+>adobe-japan1-5
682 =>>adobe-japan1-6 =+>adobe-japan1-6
683 =>cbeta =cbeta =>>cbeta ==cbeta ===cbeta
684 =zinbun-oracle =>zinbun-oracle
685 ===hng-jou ===hng-keg ===hng-dng ===hng-mam
686 ===hng-drt ===hng-kgk ===hng-myz ===hng-kda
687 ===hng-khi ===hng-khm ===hng-hok ===hng-kyd ===hng-sok
688 ===hng-yhk ===hng-kak ===hng-kar ===hng-kae
689 ===hng-sys ===hng-tsu ===hng-tzj
690 ===hng-hos ===hng-nak ===hng-jhk
691 ===hng-hod ===hng-gok ===hng-ink ===hng-nto
692 ===hng-nkm ===hng-k24 ===hng-nkk
693 ===hng-kcc ===hng-kcj ===hng-kbk ===hng-sik
694 ===hng-skk ===hng-kyu ===hng-ksk ===hng-wan
695 ===hng-okd ===hng-wad ===hng-kmi
696 ===hng-zkd ===hng-doh ===hng-jyu
697 ===hng-tzs ===hng-kss ===hng-kyo
699 ;; (string-match "^=adobe-" (symbol-name name))
701 "(%-18s . %05d)\t; %c")
702 ((memq name '(=hanyo-denshi/ks
703 ==hanyo-denshi/ks ===hanyo-denshi/ks
708 "(%-18s . %06d)\t; %c")
709 ((>= (charset-dimension name) 2)
710 "(%-18s . #x%04X)\t; %c")
712 "(%-18s . #x%02X)\t; %c"))
714 (if (= (charset-iso-graphic-plane name) 1)
716 (cond ((= (charset-dimension name) 1)
718 ((= (charset-dimension name) 2)
720 ((= (charset-dimension name) 3)
724 (char-db-decode-isolated-char name value)))
725 (if (and (= (charset-chars name) 94)
726 (= (charset-dimension name) 2))
727 (insert (format " [%02d-%02d]"
728 (- (lsh value -8) 32)
729 (- (logand value 255) 32))))
732 (insert (format "(%-18s . %s)" name value))
734 (insert line-breaking))
736 (defun char-db-insert-relation-feature (char name value line-breaking
738 (insert (format "(%-18s%s " name line-breaking))
739 (let ((lbs (concat "\n" (make-string (current-column) ?\ )))
740 separator cell sources required-features
743 (setq cell (car value))
745 (setq cell (decode-char '=ucs cell)))
747 ((eq name '->subsumptive)
748 (when (or (not (some (lambda (atr)
749 (get-char-attribute cell atr))
750 char-db-ignored-attributes))
752 (encode-char cell ccs 'defined-only))
756 (let ((char-db-ignored-attributes
758 char-db-ignored-attributes)))
759 (insert-char-attributes cell readable nil nil 'for-sub-node))
760 (setq separator lbs))
765 char (intern (format "%s*sources" name))))
766 (setq required-features nil)
767 (dolist (source sources)
771 shinjigen shinjigen@1ed shinjigen@rev))
772 (setq required-features
773 (union required-features
785 =shinjigen/+p@rev))))
787 (setq required-features
788 (union required-features
793 ((find-charset (setq ret (intern (format "=%s" source))))
794 (setq required-features
795 (cons ret required-features)))
796 (t (setq required-features
797 (cons source required-features)))))
798 (cond ((string-match "@JP" (symbol-name name))
799 (setq required-features
800 (union required-features
808 ((string-match "@CN" (symbol-name name))
809 (setq required-features
810 (union required-features
817 (insert (format "%S" cell))
818 (char-db-insert-char-spec cell readable
821 (setq separator lbs))
825 (if (consp (car cell))
826 (char-db-insert-char-spec cell readable)
827 (char-db-insert-char-reference cell readable))
828 (setq separator lbs))
832 (insert (prin1-to-string cell))
833 (setq separator " ")))
834 (setq value (cdr value)))
836 (insert line-breaking)))
838 (defun insert-char-attributes (char &optional readable attributes column
841 (setq column (current-column)))
842 (let (name value ; has-long-ccs-name
846 (concat "\n" (make-string (1+ column) ?\ )))
847 lbs cell separator ret
849 dest-ccss ; sources required-features
854 (if (consp attributes)
856 (dolist (name attributes)
857 (unless (memq name char-db-ignored-attributes)
858 (if (find-charset name)
862 (dolist (name (char-attribute-list))
863 (unless (memq name char-db-ignored-attributes)
864 (if (find-charset name)
868 #'char-attribute-name<)))
870 (when (memq '<-subsumptive attributes)
871 (when (or readable (not for-sub-node))
872 (when (setq value (get-char-attribute char '<-subsumptive))
873 (char-db-insert-relation-feature char '<-subsumptive value
876 (setq attributes (delq '<-subsumptive attributes)))
877 (when (and (memq '<-denotational attributes)
878 (setq value (get-char-attribute char '<-denotational)))
879 (char-db-insert-relation-feature char '<-denotational value
882 (setq attributes (delq '<-denotational attributes)))
883 (when (and (memq '<-denotational@component attributes)
884 (setq value (get-char-attribute char '<-denotational@component)))
885 (char-db-insert-relation-feature char '<-denotational@component value
888 (setq attributes (delq '<-denotational@component attributes)))
889 (when (and (memq 'name attributes)
890 (setq value (get-char-attribute char 'name)))
892 (if (> (+ (current-column) (length value)) 48)
895 value line-breaking))
896 (setq attributes (delq 'name attributes))
898 (when (and (memq 'name* attributes)
899 (setq value (get-char-attribute char 'name*)))
901 (if (> (+ (current-column) (length value)) 48)
904 value line-breaking))
905 (setq attributes (delq 'name* attributes))
907 (when (and (memq 'script attributes)
908 (setq value (get-char-attribute char 'script)))
909 (insert (format "(script\t\t%s)%s"
910 (mapconcat (function prin1-to-string)
913 (setq attributes (delq 'script attributes))
915 (dolist (name '(=>ucs =>ucs*))
916 (when (and (memq name attributes)
917 (setq value (get-char-attribute char name)))
918 (insert (format "(%-18s . #x%04X)\t; %c%s"
919 name value (decode-char '=ucs value)
921 (setq attributes (delq name attributes))))
922 (dolist (name '(=>ucs@gb =>ucs@big5))
923 (when (and (memq name attributes)
924 (setq value (get-char-attribute char name)))
925 (insert (format "(%-18s . #x%04X)\t; %c%s"
930 (symbol-name name) 2)))
933 (setq attributes (delq name attributes))
935 ;; (dolist (name '(=>daikanwa))
936 ;; (when (and (memq name attributes)
937 ;; (setq value (get-char-attribute char name)))
939 ;; (if (integerp value)
940 ;; (format "(%-18s . %05d)\t; %c%s"
941 ;; name value (decode-char '=daikanwa value)
943 ;; (format "(%-18s %s)\t; %c%s"
945 ;; (mapconcat (function prin1-to-string)
947 ;; (char-representative-of-daikanwa char)
949 ;; (setq attributes (delq name attributes))))
950 (when (and (memq 'general-category attributes)
951 (setq value (get-char-attribute char 'general-category)))
953 "(general-category\t%s) ; %s%s"
954 (mapconcat (lambda (cell)
957 (cond ((rassoc value unidata-normative-category-alist)
958 "Normative Category")
959 ((rassoc value unidata-informative-category-alist)
960 "Informative Category")
964 (setq attributes (delq 'general-category attributes))
966 (when (and (memq 'bidi-category attributes)
967 (setq value (get-char-attribute char 'bidi-category)))
968 (insert (format "(bidi-category\t. %S)%s"
971 (setq attributes (delq 'bidi-category attributes))
973 (unless (or (not (memq 'mirrored attributes))
974 (eq (setq value (get-char-attribute char 'mirrored 'empty))
976 (insert (format "(mirrored\t\t. %S)%s"
979 (setq attributes (delq 'mirrored attributes))
982 ((and (memq 'decimal-digit-value attributes)
983 (setq value (get-char-attribute char 'decimal-digit-value)))
984 (insert (format "(decimal-digit-value . %S)%s"
987 (setq attributes (delq 'decimal-digit-value attributes))
988 (when (and (memq 'digit-value attributes)
989 (setq value (get-char-attribute char 'digit-value)))
990 (insert (format "(digit-value\t . %S)%s"
993 (setq attributes (delq 'digit-value attributes))
995 (when (and (memq 'numeric-value attributes)
996 (setq value (get-char-attribute char 'numeric-value)))
997 (insert (format "(numeric-value\t . %S)%s"
1000 (setq attributes (delq 'numeric-value attributes))
1004 (when (and (memq 'digit-value attributes)
1005 (setq value (get-char-attribute char 'digit-value)))
1006 (insert (format "(digit-value\t. %S)%s"
1009 (setq attributes (delq 'digit-value attributes))
1011 (when (and (memq 'numeric-value attributes)
1012 (setq value (get-char-attribute char 'numeric-value)))
1013 (insert (format "(numeric-value\t. %S)%s"
1016 (setq attributes (delq 'numeric-value attributes))
1018 (when (and (memq 'iso-10646-comment attributes)
1019 (setq value (get-char-attribute char 'iso-10646-comment)))
1020 (insert (format "(iso-10646-comment\t. %S)%s"
1023 (setq attributes (delq 'iso-10646-comment attributes))
1025 (when (and (memq 'morohashi-daikanwa attributes)
1026 (setq value (get-char-attribute char 'morohashi-daikanwa)))
1027 (insert (format "(morohashi-daikanwa\t%s)%s"
1028 (mapconcat (function prin1-to-string) value " ")
1030 (setq attributes (delq 'morohashi-daikanwa attributes))
1034 (when (and (memq 'ideographic-radical attributes)
1035 (setq value (get-char-attribute char 'ideographic-radical)))
1036 (setq radical value)
1037 (insert (format "(ideographic-radical . %S)\t; %c%s"
1039 (ideographic-radical radical)
1041 (setq attributes (delq 'ideographic-radical attributes))
1043 (when (and (memq 'shuowen-radical attributes)
1044 (setq value (get-char-attribute char 'shuowen-radical)))
1045 (insert (format "(shuowen-radical\t. %S)\t; %c%s"
1047 (shuowen-radical value)
1049 (setq attributes (delq 'shuowen-radical attributes))
1054 char-db-feature-domains
1056 (dolist (feature (char-attribute-list))
1057 (setq feature (symbol-name feature))
1059 "\\(radical\\|strokes\\)@\\([^@*]+\\)\\(\\*\\|$\\)"
1061 (setq domain (intern (match-string 2 feature)))
1062 (unless (memq domain dest)
1063 (setq dest (cons domain dest)))))
1064 (sort dest #'string<))))
1065 (setq key (intern (format "%s@%s" 'ideographic-radical domain)))
1066 (when (and (memq key attributes)
1067 (setq value (get-char-attribute char key)))
1068 (setq radical value)
1069 (insert (format "(%s . %S)\t; %c%s"
1072 (ideographic-radical radical)
1074 (setq attributes (delq key attributes))
1076 (setq key (intern (format "%s@%s" 'ideographic-strokes domain)))
1077 (when (and (memq key attributes)
1078 (setq value (get-char-attribute char key)))
1079 (setq strokes value)
1080 (insert (format "(%s . %S)%s"
1084 (setq attributes (delq key attributes))
1086 (setq key (intern (format "%s@%s" 'total-strokes domain)))
1087 (when (and (memq key attributes)
1088 (setq value (get-char-attribute char key)))
1089 (insert (format "(%s . %S)%s"
1093 (setq attributes (delq key attributes))
1095 (dolist (feature '(ideographic-radical
1098 (setq key (intern (format "%s@%s*sources" feature domain)))
1099 (when (and (memq key attributes)
1100 (setq value (get-char-attribute char key)))
1101 (insert (format "(%s%s" key line-breaking))
1102 (dolist (cell value)
1103 (insert (format " %s" cell)))
1105 (insert line-breaking)
1106 (setq attributes (delq key attributes))
1109 (when (and (memq 'ideographic-strokes attributes)
1110 (setq value (get-char-attribute char 'ideographic-strokes)))
1111 (setq strokes value)
1112 (insert (format "(ideographic-strokes . %S)%s"
1115 (setq attributes (delq 'ideographic-strokes attributes))
1117 (when (and (memq 'kangxi-radical attributes)
1118 (setq value (get-char-attribute char 'kangxi-radical)))
1119 (unless (eq value radical)
1120 (insert (format "(kangxi-radical\t . %S)\t; %c%s"
1122 (ideographic-radical value)
1125 (setq radical value)))
1126 (setq attributes (delq 'kangxi-radical attributes))
1128 (when (and (memq 'kangxi-strokes attributes)
1129 (setq value (get-char-attribute char 'kangxi-strokes)))
1130 (unless (eq value strokes)
1131 (insert (format "(kangxi-strokes\t . %S)%s"
1135 (setq strokes value)))
1136 (setq attributes (delq 'kangxi-strokes attributes))
1138 (when (and (memq 'japanese-radical attributes)
1139 (setq value (get-char-attribute char 'japanese-radical)))
1140 (unless (eq value radical)
1141 (insert (format "(japanese-radical\t . %S)\t; %c%s"
1143 (ideographic-radical value)
1146 (setq radical value)))
1147 (setq attributes (delq 'japanese-radical attributes))
1149 (when (and (memq 'japanese-strokes attributes)
1150 (setq value (get-char-attribute char 'japanese-strokes)))
1151 (unless (eq value strokes)
1152 (insert (format "(japanese-strokes\t . %S)%s"
1156 (setq strokes value)))
1157 (setq attributes (delq 'japanese-strokes attributes))
1159 (when (and (memq 'cns-radical attributes)
1160 (setq value (get-char-attribute char 'cns-radical)))
1161 (insert (format "(cns-radical\t . %S)\t; %c%s"
1163 (ideographic-radical value)
1165 (setq attributes (delq 'cns-radical attributes))
1167 (when (and (memq 'cns-strokes attributes)
1168 (setq value (get-char-attribute char 'cns-strokes)))
1169 (unless (eq value strokes)
1170 (insert (format "(cns-strokes\t . %S)%s"
1174 (setq strokes value)))
1175 (setq attributes (delq 'cns-strokes attributes))
1177 ;; (when (and (memq 'shinjigen-1-radical attributes)
1178 ;; (setq value (get-char-attribute char 'shinjigen-1-radical)))
1179 ;; (unless (eq value radical)
1180 ;; (insert (format "(shinjigen-1-radical . %S)\t; %c%s"
1182 ;; (ideographic-radical value)
1185 ;; (setq radical value)))
1186 ;; (setq attributes (delq 'shinjigen-1-radical attributes))
1188 (when (and (memq 'ideographic- attributes)
1189 (setq value (get-char-attribute char 'ideographic-)))
1190 (insert "(ideographic- ")
1191 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1193 (while (consp value)
1194 (setq cell (car value))
1196 (setq cell (decode-char '=ucs cell)))
1197 (cond ((characterp cell)
1201 (insert (format "%S" cell))
1202 (char-db-insert-char-spec cell readable))
1203 (setq separator lbs))
1207 (if (consp (car cell))
1208 (char-db-insert-char-spec cell readable)
1209 (char-db-insert-char-reference cell readable))
1210 (setq separator lbs))
1214 (insert (prin1-to-string cell))
1215 (setq separator " ")))
1216 (setq value (cdr value)))
1218 (insert line-breaking)
1219 (setq attributes (delq 'ideographic- attributes)))
1220 (when (and (memq 'total-strokes attributes)
1221 (setq value (get-char-attribute char 'total-strokes)))
1222 (insert (format "(total-strokes . %S)%s"
1225 (setq attributes (delq 'total-strokes attributes))
1227 (when (and (memq '->ideograph attributes)
1228 (setq value (get-char-attribute char '->ideograph)))
1229 (insert (format "(->ideograph\t%s)%s"
1230 (mapconcat (lambda (code)
1231 (cond ((symbolp code)
1234 (format "#x%04X" code))
1237 line-breaking code))))
1240 (setq attributes (delq '->ideograph attributes))
1242 ;; (when (and (memq '->decomposition attributes)
1243 ;; (setq value (get-char-attribute char '->decomposition)))
1244 ;; (insert (format "(->decomposition\t%s)%s"
1245 ;; (mapconcat (lambda (code)
1246 ;; (cond ((symbolp code)
1247 ;; (symbol-name code))
1248 ;; ((characterp code)
1250 ;; (format "%S" code)
1255 ;; (format "#x%04X" code))
1257 ;; (format "%s%S" line-breaking code))))
1260 ;; (setq attributes (delq '->decomposition attributes))
1262 (if (equal (get-char-attribute char '->titlecase)
1263 (get-char-attribute char '->uppercase))
1264 (setq attributes (delq '->titlecase attributes)))
1265 (when (and (memq '->mojikyo attributes)
1266 (setq value (get-char-attribute char '->mojikyo)))
1267 (insert (format "(->mojikyo\t\t. %06d)\t; %c%s"
1268 value (decode-char 'mojikyo value)
1270 (setq attributes (delq '->mojikyo attributes))
1272 (when (and (memq 'hanyu-dazidian-vol attributes)
1273 (setq value (get-char-attribute char 'hanyu-dazidian-vol)))
1274 (insert (format "(hanyu-dazidian-vol . %d)%s"
1275 value line-breaking))
1276 (setq attributes (delq 'hanyu-dazidian-vol attributes))
1278 (when (and (memq 'hanyu-dazidian-page attributes)
1279 (setq value (get-char-attribute char 'hanyu-dazidian-page)))
1280 (insert (format "(hanyu-dazidian-page . %d)%s"
1281 value line-breaking))
1282 (setq attributes (delq 'hanyu-dazidian-page attributes))
1284 (when (and (memq 'hanyu-dazidian-char attributes)
1285 (setq value (get-char-attribute char 'hanyu-dazidian-char)))
1286 (insert (format "(hanyu-dazidian-char . %d)%s"
1287 value line-breaking))
1288 (setq attributes (delq 'hanyu-dazidian-char attributes))
1291 (dolist (ignored '(composition
1292 ->denotational <-subsumptive ->ucs-unified
1293 ->ideographic-component-forms))
1294 (setq attributes (delq ignored attributes))))
1296 (setq name (car attributes))
1297 (unless (eq (setq value (get-char-attribute char name 'value-is-empty))
1299 (cond ((setq ret (find-charset name))
1300 (setq name (charset-name ret))
1301 (when (not (memq name dest-ccss))
1302 (setq dest-ccss (cons name dest-ccss))
1303 (char-db-insert-ccs-feature name value line-breaking))
1305 ((string-match "^=>ucs@" (symbol-name name))
1306 (insert (format "(%-18s . #x%04X)\t; %c%s"
1307 name value (decode-char '=ucs value)
1310 ((eq name 'jisx0208-1978/4X)
1311 (insert (format "(%-18s . #x%04X)%s"
1317 (not (eq name '->subsumptive))
1318 (not (eq name '->uppercase))
1319 (not (eq name '->lowercase))
1320 (not (eq name '->titlecase))
1321 (not (eq name '->canonical))
1322 (not (eq name '->Bopomofo))
1323 (not (eq name '->mistakable))
1324 (not (eq name '->ideographic-variants))
1325 (null (get-char-attribute
1326 char (intern (format "%s*sources" name))))
1327 (not (string-match "\\*sources$" (symbol-name name)))
1328 (null (get-char-attribute
1329 char (intern (format "%s*note" name))))
1330 (not (string-match "\\*note$" (symbol-name name)))
1331 (or (eq name '<-identical)
1332 (eq name '<-uppercase)
1333 (eq name '<-lowercase)
1334 (eq name '<-titlecase)
1335 (eq name '<-canonical)
1336 (eq name '<-ideographic-variants)
1337 ;; (eq name '<-synonyms)
1338 (string-match "^<-synonyms" (symbol-name name))
1339 (eq name '<-mistakable)
1340 (when (string-match "^->" (symbol-name name))
1342 ((string-match "^->fullwidth" (symbol-name name))
1343 (not (and (consp value)
1344 (characterp (car value))
1346 (car value) '=ucs 'defined-only)))
1351 ((or (eq name 'ideographic-structure)
1352 (eq name 'ideographic-combination)
1353 (eq name 'ideographic-)
1354 (eq name '=decomposition)
1355 (char-feature-base-name= '=decomposition name)
1356 (char-feature-base-name= '=>decomposition name)
1357 ;; (string-match "^=>*decomposition\\(@[^*]+\\)?$"
1358 ;; (symbol-name name))
1359 (string-match "^\\(->\\|<-\\)[^*]*$" (symbol-name name))
1360 (string-match "^\\(->\\|<-\\)[^*]*\\*sources$"
1363 (char-db-insert-relation-feature char name value
1366 ((memq name '(ideograph=
1367 original-ideograph-of
1368 ancient-ideograph-of
1371 ;; simplified-ideograph-of
1372 ideographic-variants
1373 ;; ideographic-different-form-of
1375 (insert (format "(%-18s%s " name line-breaking))
1376 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1378 (while (consp value)
1379 (setq cell (car value))
1380 (if (and (consp cell)
1385 (char-db-insert-alist cell readable)
1386 (setq separator lbs))
1389 (insert (prin1-to-string cell))
1390 (setq separator " "))
1391 (setq value (cdr value)))
1393 (insert line-breaking))
1395 (insert (format "(%-18s " name))
1396 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1398 (while (consp value)
1399 (setq cell (car value))
1400 (if (and (consp cell)
1402 (setq ret (condition-case nil
1410 (setq key (car (car rest)))
1411 (if (find-charset key)
1412 (setq cal (cons key cal))
1413 (setq al (cons key al)))
1414 (setq rest (cdr rest)))
1417 (insert-char-attributes ret
1421 (setq separator lbs))
1422 (setq ret (prin1-to-string cell))
1424 (if (< (+ (current-column)
1431 (setq separator " "))
1432 (setq value (cdr value)))
1434 (insert line-breaking))
1436 (insert (format "(%-18s" name))
1437 (setq ret (prin1-to-string value))
1438 (unless (< (+ (current-column)
1442 (insert line-breaking))
1443 (insert " . " ret ")" line-breaking)
1444 ;; (insert (format "(%-18s . %S)%s"
1449 (setq attributes (cdr attributes)))
1452 (defun insert-char-data (char &optional readable
1455 (narrow-to-region (point)(point))
1456 (insert "(define-char
1458 (insert-char-attributes char readable attributes)
1460 (goto-char (point-min))
1461 (while (re-search-forward "[ \t]+$" nil t)
1464 (goto-char (point-min))
1465 (while (re-search-forward "[ \t][ \t][ \t]*" nil t)
1466 (let ((column (current-column))
1467 (indent-tabs-mode t))
1468 (delete-region (match-beginning 0) (point))
1469 (indent-to column)))
1470 (goto-char (point-max))
1471 ;; (tabify (point-min)(point-max))
1474 (defun insert-char-data-with-variant (char &optional printable
1476 script excluded-script)
1477 (insert-char-data char printable)
1478 (let ((variants (char-variants char))
1481 (setq variants (sort variants #'<))
1482 (setq rest variants)
1483 (setq variants (cons char variants))
1485 (setq variant (car rest))
1486 (unless (get-char-attribute variant '<-subsumptive)
1487 (if (and (or (null script)
1488 (null (setq vs (get-char-attribute variant 'script)))
1490 (or (null excluded-script)
1491 (null (setq vs (get-char-attribute variant 'script)))
1492 (not (memq excluded-script vs))))
1493 (unless (and no-ucs-unified (get-char-attribute variant '=ucs))
1494 (insert-char-data variant printable)
1495 (if (setq ret (char-variants variant))
1497 (or (memq (car ret) variants)
1498 ;; (get-char-attribute (car ret) '<-subsumptive)
1499 (setq rest (nconc rest (list (car ret)))))
1500 (setq ret (cdr ret)))))))
1501 (setq rest (cdr rest)))))
1503 (defun insert-char-range-data (min max &optional script excluded-script)
1506 (while (<= code max)
1507 (setq char (decode-char '=ucs code))
1508 (if (encode-char char '=ucs 'defined-only)
1509 (insert-char-data-with-variant char nil 'no-ucs-unified
1510 script excluded-script))
1511 (setq code (1+ code)))))
1513 (defun write-char-range-data-to-file (min max file
1514 &optional script excluded-script)
1515 (let ((coding-system-for-write char-db-file-coding-system))
1517 (insert (format ";; -*- coding: %s -*-\n"
1518 char-db-file-coding-system))
1519 (insert-char-range-data min max script excluded-script)
1520 (write-region (point-min)(point-max) file))))
1522 (defvar what-character-original-window-configuration)
1525 (defun what-char-definition (char)
1526 (interactive (list (char-after)))
1527 (let ((buf (get-buffer-create "*Character Description*"))
1528 (the-buf (current-buffer))
1529 (win-conf (current-window-configuration)))
1531 (make-local-variable 'what-character-original-window-configuration)
1532 (setq what-character-original-window-configuration win-conf)
1533 (setq buffer-read-only nil)
1537 (insert-char-data-with-variant char 'printable)
1538 (unless (char-attribute-alist char)
1539 (insert (format ";; = %c\n"
1540 (let* ((rest (split-char char))
1544 (setq code (logior (lsh code 8)
1546 (decode-char ccs code)))))
1547 ;; (char-db-update-comment)
1548 (set-buffer-modified-p nil)
1549 (view-mode the-buf (lambda (buf)
1550 (set-window-configuration
1551 what-character-original-window-configuration)
1553 (goto-char (point-min)))
1555 (set-window-configuration
1556 what-character-original-window-configuration)
1557 (signal (car err) (cdr err)))))))
1563 (provide 'char-db-util)
1565 ;;; char-db-util.el ends here