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
338 ;;; @ char-db formatters
341 (defun char-db-make-char-spec (char)
343 (cond ((characterp char)
344 (cond ((and (setq ret (encode-char char '=ucs 'defined-only))
345 (not (and (<= #xE000 ret)(<= ret #xF8FF))))
346 (setq char-spec (list (cons '=ucs ret)))
347 (cond ((setq ret (get-char-attribute char 'name))
348 (setq char-spec (cons (cons 'name ret) char-spec))
350 ((setq ret (get-char-attribute char 'name*))
351 (setq char-spec (cons (cons 'name* ret) char-spec))
354 ((encode-char char '=mj 'defined-only)
356 (dolist (ccs (charset-list))
357 (if (and (or (eq ccs '=mj)
358 ;; (eq (charset-property ccs 'iso-ir) 177)
359 (string-match "=ucs@" (symbol-name ccs))
361 (setq ccs (charset-name ccs))
362 (null (assq ccs char-spec))
363 (setq ret (encode-char char ccs 'defined-only)))
364 (setq char-spec (cons (cons ccs ret) char-spec))))
366 ((encode-char char '==mj 'defined-only)
368 (dolist (ccs (charset-list))
369 (if (and (or (eq ccs '==mj)
370 ;; (eq (charset-property ccs 'iso-ir) 177)
371 (string-match "=ucs@" (symbol-name ccs))
373 (setq ccs (charset-name ccs))
374 (null (assq ccs char-spec))
375 (setq ret (encode-char char ccs 'defined-only)))
376 (setq char-spec (cons (cons ccs ret) char-spec))))
378 ((encode-char char '=adobe-japan1 'defined-only)
380 (dolist (ccs (charset-list))
381 (if (and (or (memq ccs
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 '==adobe-japan1 'defined-only)
400 (dolist (ccs (charset-list))
401 (if (and (or (memq ccs
410 ;; (eq (charset-property ccs 'iso-ir) 177)
411 (string-match "=ucs@" (symbol-name ccs))
413 (setq ccs (charset-name ccs))
414 (null (assq ccs char-spec))
415 (setq ret (encode-char char ccs 'defined-only)))
416 (setq char-spec (cons (cons ccs ret) char-spec))))
420 (let ((rest char-db-coded-charset-priority-list)
423 (setq ccs (charset-name
424 (find-charset (car rest))))
426 (encode-char char ccs
428 (throw 'tag (cons ccs ret)))
429 (setq rest (cdr rest))))))
430 (setq char-spec (list ret))
431 (dolist (ccs (delq (car ret) (charset-list)))
432 (if (and (or (charset-iso-final-char ccs)
439 (eq (charset-property ccs 'iso-ir) 177)
440 ;; (string-match "=ucs@" (symbol-name ccs))
442 (setq ccs (charset-name ccs))
443 (null (assq ccs char-spec))
444 (setq ret (encode-char char ccs 'defined-only)))
445 (setq char-spec (cons (cons ccs ret) char-spec))))
447 (setq char-spec (split-char char)))
448 (cond ((setq ret (get-char-attribute char 'name))
449 (setq char-spec (cons (cons 'name ret) char-spec))
451 ((setq ret (get-char-attribute char 'name*))
452 (setq char-spec (cons (cons 'name* ret) char-spec))
455 ((setq ret (get-char-attribute
456 char 'ideographic-combination))
458 (cons (cons 'ideographic-combination ret)
465 (defun char-db-insert-char-spec (char &optional readable column
468 (setq column (current-column)))
469 (let (char-spec temp-char)
470 (setq char-spec (char-db-make-char-spec char))
471 (unless (or (characterp char) ; char
473 (setq char (find-char char-spec))
475 ;; define temporary character
476 ;; Current implementation is dirty.
477 (setq temp-char (define-char (cons '(ideograph-daikanwa . 0)
479 (remove-char-attribute temp-char 'ideograph-daikanwa)
480 (setq char temp-char))
481 (insert-char-attributes char
483 (union (mapcar #'car char-spec)
487 ;; undefine temporary character
488 ;; Current implementation is dirty.
489 (setq char-spec (char-attribute-alist temp-char))
491 (remove-char-attribute temp-char (car (car char-spec)))
492 (setq char-spec (cdr char-spec))))))
494 (defun char-db-insert-alist (alist &optional readable column)
496 (setq column (current-column)))
498 (concat "\n" (make-string (1+ column) ?\ )))
502 lbs cell rest separator)
505 (setq name (car (car alist))
506 value (cdr (car alist)))
507 (cond ((eq name 'char)
509 (if (setq ret (condition-case nil
517 (setq key (car (car value)))
518 ;; (if (find-charset key)
519 ;; (setq cal (cons key cal))
520 (setq al (cons key al))
522 (setq value (cdr value)))
523 (insert-char-attributes ret
527 (insert (prin1-to-string value)))
529 (insert line-breaking))
531 (insert (format "(%-18s " name))
532 (setq lbs (concat "\n" (make-string (current-column) ?\ )))
534 (setq cell (car value))
535 (if (and (consp cell)
537 (setq ret (condition-case nil
547 (setq key (car (car rest)))
548 ;; (if (find-charset key)
549 ;; (setq cal (cons key cal))
550 (setq al (cons key al))
552 (setq rest (cdr rest)))
555 (insert-char-attributes ret
559 (setq separator lbs))
562 (insert (prin1-to-string cell))
563 (setq separator " "))
564 (setq value (cdr value)))
566 (insert line-breaking))
568 (insert (format "(%-18s . %S)%s"
571 (setq alist (cdr alist))))
574 (defun char-db-insert-char-reference (plist &optional readable column)
576 (setq column (current-column)))
578 (concat "\n" (make-string (1+ column) ?\ )))
583 (setq name (pop plist))
584 (setq value (pop plist))
585 (cond ((eq name :char)
588 (cond ((numberp value)
589 (setq value (decode-char '=ucs value)))
591 ;; (setq value (or (find-char value)
594 (char-db-insert-char-spec value readable)
595 (insert line-breaking)
598 (insert (format "%s%s\t%d ; %c%s"
601 (ideographic-radical value)
605 (insert (format "%s%s\t%S" separator name value))
606 (setq separator line-breaking)))
610 (defun char-db-decode-isolated-char (ccs code-point)
613 (cond ((eq ccs 'arabic-iso8859-6)
614 (decode-char ccs code-point))
616 ;; (decode-builtin-char '==gt code-point))
617 ((and (memq ccs '(=gt-pj-1
628 (setq ret (decode-char ccs code-point))
629 (setq ret (encode-char ret '=gt 'defined-only)))
630 (decode-builtin-char '=gt ret))
632 (decode-builtin-char ccs code-point))))
634 (or (decode-char ccs code-point)
635 (define-char (list (cons ccs code-point)))))
636 ((and (<= 0 (char-int ret))
637 (<= (char-int ret) #x1F))
638 (decode-char '=ucs (+ #x2400 (char-int ret))))
639 ((= (char-int ret) #x7F)
643 (defvar char-db-convert-obsolete-format t)
645 (defun char-db-insert-ccs-feature (name value line-breaking)
651 ((memq name '(=>iwds-1
654 =shinjigen@1ed ==shinjigen@1ed
655 =shinjigen@rev ==shinjigen@rev
656 =shinjigen/+p@rev ==shinjigen/+p@rev
657 ===daikanwa/ho ==daikanwa/ho
658 =daikanwa/ho =>>daikanwa/ho =>daikanwa/ho))
659 "(%-18s . %04d)\t; %c")
660 ((eq name '=shinjigen@1ed/24pr)
661 "(%-18s . %04d)\t; %c")
665 ==daikanwa =daikanwa =>>daikanwa =>daikanwa
666 =daikanwa@rev1 =daikanwa@rev2
667 =daikanwa/+p ==daikanwa/+p ===daikanwa/+p
669 =daikanwa/+2p =>>daikanwa/+2p
674 =adobe-japan1-0 ==adobe-japan1-0 ===adobe-japan1-0
675 =adobe-japan1-1 ==adobe-japan1-1 ===adobe-japan1-1
676 =adobe-japan1-2 ==adobe-japan1-2 ===adobe-japan1-2
677 =adobe-japan1-3 ==adobe-japan1-3 ===adobe-japan1-3
678 =adobe-japan1-4 ==adobe-japan1-4 ===adobe-japan1-4
679 =adobe-japan1-5 ==adobe-japan1-5 ===adobe-japan1-5
680 =adobe-japan1-6 ==adobe-japan1-6 ===adobe-japan1-6
681 =>>adobe-japan1-0 =+>adobe-japan1-0
682 =>>adobe-japan1-1 =+>adobe-japan1-1
683 =>>adobe-japan1-2 =+>adobe-japan1-2
684 =>>adobe-japan1-3 =+>adobe-japan1-3
685 =>>adobe-japan1-4 =+>adobe-japan1-4
686 =>>adobe-japan1-5 =+>adobe-japan1-5
687 =>>adobe-japan1-6 =+>adobe-japan1-6
688 =>cbeta =cbeta =>>cbeta ==cbeta ===cbeta
689 =zinbun-oracle =>zinbun-oracle
690 ===hng-jou ===hng-keg ===hng-dng ===hng-mam
691 ===hng-drt ===hng-kgk ===hng-myz ===hng-kda
692 ===hng-khi ===hng-khm ===hng-hok ===hng-kyd ===hng-sok
693 ===hng-yhk ===hng-kak ===hng-kar ===hng-kae
694 ===hng-sys ===hng-tsu ===hng-tzj
695 ===hng-hos ===hng-nak ===hng-jhk
696 ===hng-hod ===hng-gok ===hng-ink ===hng-nto
697 ===hng-nkm ===hng-k24 ===hng-nkk
698 ===hng-kcc ===hng-kcj ===hng-kbk ===hng-sik
699 ===hng-skk ===hng-kyu ===hng-ksk ===hng-wan
700 ===hng-okd ===hng-wad ===hng-kmi
701 ===hng-zkd ===hng-doh ===hng-jyu
702 ===hng-tzs ===hng-kss ===hng-kyo
704 ;; (string-match "^=adobe-" (symbol-name name))
706 "(%-18s . %05d)\t; %c")
707 ((memq name '(=hanyo-denshi/ks
708 ==hanyo-denshi/ks ===hanyo-denshi/ks
713 "(%-18s . %06d)\t; %c")
714 ((>= (charset-dimension name) 2)
715 "(%-18s . #x%04X)\t; %c")
717 "(%-18s . #x%02X)\t; %c"))
719 (if (= (charset-iso-graphic-plane name) 1)
721 (cond ((= (charset-dimension name) 1)
723 ((= (charset-dimension name) 2)
725 ((= (charset-dimension name) 3)
729 (char-db-decode-isolated-char name value)))
730 (if (and (= (charset-chars name) 94)
731 (= (charset-dimension name) 2))
732 (insert (format " [%02d-%02d]"
733 (- (lsh value -8) 32)
734 (- (logand value 255) 32))))
737 (insert (format "(%-18s . %s)" name value))
739 (insert line-breaking))
741 (defun char-db-insert-relation-feature (char name value line-breaking
743 (insert (format "(%-18s%s " name line-breaking))
744 (let ((lbs (concat "\n" (make-string (current-column) ?\ )))
745 separator cell sources required-features
748 (setq cell (car value))
750 (setq cell (decode-char '=ucs cell)))
752 ((eq name '->subsumptive)
753 (when (or (not (some (lambda (atr)
754 (get-char-attribute cell atr))
755 char-db-ignored-attributes))
757 (encode-char cell ccs 'defined-only))
761 (let ((char-db-ignored-attributes
763 char-db-ignored-attributes)))
764 (insert-char-attributes cell readable nil nil 'for-sub-node))
765 (setq separator lbs))
770 char (intern (format "%s*sources" name))))
771 (setq required-features nil)
772 (dolist (source sources)
776 shinjigen shinjigen@1ed shinjigen@rev))
777 (setq required-features
778 (union required-features
790 =shinjigen/+p@rev))))
792 (setq required-features
793 (union required-features
798 ((find-charset (setq ret (intern (format "=%s" source))))
799 (setq required-features
800 (cons ret required-features)))
801 (t (setq required-features
802 (cons source required-features)))))
803 (cond ((string-match "@JP" (symbol-name name))
804 (setq required-features
805 (union required-features
813 ((string-match "@CN" (symbol-name name))
814 (setq required-features
815 (union required-features
822 (insert (format "%S" cell))
823 (char-db-insert-char-spec cell readable
826 (setq separator lbs))
830 (if (consp (car cell))
831 (char-db-insert-char-spec cell readable)
832 (char-db-insert-char-reference cell readable))
833 (setq separator lbs))
837 (insert (prin1-to-string cell))
838 (setq separator " ")))
839 (setq value (cdr value)))
841 (insert line-breaking)))
843 (defun insert-char-attributes (char &optional readable attributes column
846 (setq column (current-column)))
847 (let (name value ; has-long-ccs-name
851 (concat "\n" (make-string (1+ column) ?\ )))
852 lbs cell separator ret
854 dest-ccss ; sources required-features
859 (if (consp attributes)
861 (dolist (name attributes)
862 (unless (memq name char-db-ignored-attributes)
863 (if (find-charset name)
867 (dolist (name (char-attribute-list))
868 (unless (memq name char-db-ignored-attributes)
869 (if (find-charset name)
873 #'char-attribute-name<)))
875 (when (memq '<-subsumptive attributes)
876 (when (or readable (not for-sub-node))
877 (when (setq value (get-char-attribute char '<-subsumptive))
878 (char-db-insert-relation-feature char '<-subsumptive value
881 (setq attributes (delq '<-subsumptive attributes)))
882 (when (and (memq '<-denotational attributes)
883 (setq value (get-char-attribute char '<-denotational)))
884 (char-db-insert-relation-feature char '<-denotational value
887 (setq attributes (delq '<-denotational attributes)))
888 (when (and (memq '<-denotational@component attributes)
889 (setq value (get-char-attribute char '<-denotational@component)))
890 (char-db-insert-relation-feature char '<-denotational@component value
893 (setq attributes (delq '<-denotational@component attributes)))
894 (when (and (memq 'name attributes)
895 (setq value (get-char-attribute char 'name)))
897 (if (> (+ (current-column) (length value)) 48)
900 value line-breaking))
901 (setq attributes (delq 'name 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 'script attributes)
913 (setq value (get-char-attribute char 'script)))
914 (insert (format "(script\t\t%s)%s"
915 (mapconcat (function prin1-to-string)
918 (setq attributes (delq 'script attributes))
920 (dolist (name '(=>ucs =>ucs*))
921 (when (and (memq name attributes)
922 (setq value (get-char-attribute char name)))
923 (insert (format "(%-18s . #x%04X)\t; %c%s"
924 name value (decode-char '=ucs value)
926 (setq attributes (delq name attributes))))
927 (dolist (name '(=>ucs@gb =>ucs@big5))
928 (when (and (memq name attributes)
929 (setq value (get-char-attribute char name)))
930 (insert (format "(%-18s . #x%04X)\t; %c%s"
935 (symbol-name name) 2)))
938 (setq attributes (delq name attributes))
940 ;; (dolist (name '(=>daikanwa))
941 ;; (when (and (memq name attributes)
942 ;; (setq value (get-char-attribute char name)))
944 ;; (if (integerp value)
945 ;; (format "(%-18s . %05d)\t; %c%s"
946 ;; name value (decode-char '=daikanwa value)
948 ;; (format "(%-18s %s)\t; %c%s"
950 ;; (mapconcat (function prin1-to-string)
952 ;; (char-representative-of-daikanwa char)
954 ;; (setq attributes (delq name attributes))))
955 (when (and (memq 'general-category attributes)
956 (setq value (get-char-attribute char 'general-category)))
958 "(general-category\t%s) ; %s%s"
959 (mapconcat (lambda (cell)
962 (cond ((rassoc value unidata-normative-category-alist)
963 "Normative Category")
964 ((rassoc value unidata-informative-category-alist)
965 "Informative Category")
969 (setq attributes (delq 'general-category attributes))
971 (when (and (memq 'bidi-category attributes)
972 (setq value (get-char-attribute char 'bidi-category)))
973 (insert (format "(bidi-category\t. %S)%s"
976 (setq attributes (delq 'bidi-category attributes))
978 (unless (or (not (memq 'mirrored attributes))
979 (eq (setq value (get-char-attribute char 'mirrored 'empty))
981 (insert (format "(mirrored\t\t. %S)%s"
984 (setq attributes (delq 'mirrored attributes))
987 ((and (memq 'decimal-digit-value attributes)
988 (setq value (get-char-attribute char 'decimal-digit-value)))
989 (insert (format "(decimal-digit-value . %S)%s"
992 (setq attributes (delq 'decimal-digit-value attributes))
993 (when (and (memq 'digit-value attributes)
994 (setq value (get-char-attribute char 'digit-value)))
995 (insert (format "(digit-value\t . %S)%s"
998 (setq attributes (delq 'digit-value attributes))
1000 (when (and (memq 'numeric-value attributes)
1001 (setq value (get-char-attribute char 'numeric-value)))
1002 (insert (format "(numeric-value\t . %S)%s"
1005 (setq attributes (delq 'numeric-value attributes))
1009 (when (and (memq 'digit-value attributes)
1010 (setq value (get-char-attribute char 'digit-value)))
1011 (insert (format "(digit-value\t. %S)%s"
1014 (setq attributes (delq 'digit-value attributes))
1016 (when (and (memq 'numeric-value attributes)
1017 (setq value (get-char-attribute char 'numeric-value)))
1018 (insert (format "(numeric-value\t. %S)%s"
1021 (setq attributes (delq 'numeric-value attributes))
1023 (when (and (memq 'iso-10646-comment attributes)
1024 (setq value (get-char-attribute char 'iso-10646-comment)))
1025 (insert (format "(iso-10646-comment\t. %S)%s"
1028 (setq attributes (delq 'iso-10646-comment attributes))
1030 (when (and (memq 'morohashi-daikanwa attributes)
1031 (setq value (get-char-attribute char 'morohashi-daikanwa)))
1032 (insert (format "(morohashi-daikanwa\t%s)%s"
1033 (mapconcat (function prin1-to-string) value " ")
1035 (setq attributes (delq 'morohashi-daikanwa attributes))
1039 (when (and (memq 'ideographic-radical attributes)
1040 (setq value (get-char-attribute char 'ideographic-radical)))
1041 (setq radical value)
1042 (insert (format "(ideographic-radical . %S)\t; %c%s"
1044 (ideographic-radical radical)
1046 (setq attributes (delq 'ideographic-radical attributes))
1048 (when (and (memq 'shuowen-radical attributes)
1049 (setq value (get-char-attribute char 'shuowen-radical)))
1050 (insert (format "(shuowen-radical\t. %S)\t; %c%s"
1052 (shuowen-radical value)
1054 (setq attributes (delq 'shuowen-radical attributes))
1059 char-db-feature-domains
1061 (dolist (feature (char-attribute-list))
1062 (setq feature (symbol-name feature))
1064 "\\(radical\\|strokes\\)@\\([^@*]+\\)\\(\\*\\|$\\)"
1066 (setq domain (intern (match-string 2 feature)))
1067 (unless (memq domain dest)
1068 (setq dest (cons domain dest)))))
1069 (sort dest #'string<))))
1070 (setq key (intern (format "%s@%s" 'ideographic-radical domain)))
1071 (when (and (memq key attributes)
1072 (setq value (get-char-attribute char key)))
1073 (setq radical value)
1074 (insert (format "(%s . %S)\t; %c%s"
1077 (ideographic-radical radical)
1079 (setq attributes (delq key attributes))
1081 (setq key (intern (format "%s@%s" 'ideographic-strokes domain)))
1082 (when (and (memq key attributes)
1083 (setq value (get-char-attribute char key)))
1084 (setq strokes value)
1085 (insert (format "(%s . %S)%s"
1089 (setq attributes (delq key attributes))
1091 (setq key (intern (format "%s@%s" 'total-strokes domain)))
1092 (when (and (memq key attributes)
1093 (setq value (get-char-attribute char key)))
1094 (insert (format "(%s . %S)%s"
1098 (setq attributes (delq key attributes))
1100 (dolist (feature '(ideographic-radical
1103 (setq key (intern (format "%s@%s*sources" feature domain)))
1104 (when (and (memq key attributes)
1105 (setq value (get-char-attribute char key)))
1106 (insert (format "(%s%s" key line-breaking))
1107 (dolist (cell value)
1108 (insert (format " %s" cell)))
1110 (insert line-breaking)
1111 (setq attributes (delq key attributes))
1114 (when (and (memq 'ideographic-strokes attributes)
1115 (setq value (get-char-attribute char 'ideographic-strokes)))
1116 (setq strokes value)
1117 (insert (format "(ideographic-strokes . %S)%s"
1120 (setq attributes (delq 'ideographic-strokes attributes))
1122 (when (and (memq 'kangxi-radical attributes)
1123 (setq value (get-char-attribute char 'kangxi-radical)))
1124 (unless (eq value radical)
1125 (insert (format "(kangxi-radical\t . %S)\t; %c%s"
1127 (ideographic-radical value)
1130 (setq radical value)))
1131 (setq attributes (delq 'kangxi-radical attributes))
1133 (when (and (memq 'kangxi-strokes attributes)
1134 (setq value (get-char-attribute char 'kangxi-strokes)))
1135 (unless (eq value strokes)
1136 (insert (format "(kangxi-strokes\t . %S)%s"
1140 (setq strokes value)))
1141 (setq attributes (delq 'kangxi-strokes attributes))
1143 (when (and (memq 'japanese-radical attributes)
1144 (setq value (get-char-attribute char 'japanese-radical)))
1145 (unless (eq value radical)
1146 (insert (format "(japanese-radical\t . %S)\t; %c%s"
1148 (ideographic-radical value)
1151 (setq radical value)))
1152 (setq attributes (delq 'japanese-radical attributes))
1154 (when (and (memq 'japanese-strokes attributes)
1155 (setq value (get-char-attribute char 'japanese-strokes)))
1156 (unless (eq value strokes)
1157 (insert (format "(japanese-strokes\t . %S)%s"
1161 (setq strokes value)))
1162 (setq attributes (delq 'japanese-strokes attributes))
1164 (when (and (memq 'cns-radical attributes)
1165 (setq value (get-char-attribute char 'cns-radical)))
1166 (insert (format "(cns-radical\t . %S)\t; %c%s"
1168 (ideographic-radical value)
1170 (setq attributes (delq 'cns-radical attributes))
1172 (when (and (memq 'cns-strokes attributes)
1173 (setq value (get-char-attribute char 'cns-strokes)))
1174 (unless (eq value strokes)
1175 (insert (format "(cns-strokes\t . %S)%s"
1179 (setq strokes value)))
1180 (setq attributes (delq 'cns-strokes attributes))
1182 ;; (when (and (memq 'shinjigen-1-radical attributes)
1183 ;; (setq value (get-char-attribute char 'shinjigen-1-radical)))
1184 ;; (unless (eq value radical)
1185 ;; (insert (format "(shinjigen-1-radical . %S)\t; %c%s"
1187 ;; (ideographic-radical value)
1190 ;; (setq radical value)))
1191 ;; (setq attributes (delq 'shinjigen-1-radical attributes))
1193 (when (and (memq 'ideographic- attributes)
1194 (setq value (get-char-attribute char 'ideographic-)))
1195 (insert "(ideographic- ")
1196 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1198 (while (consp value)
1199 (setq cell (car value))
1201 (setq cell (decode-char '=ucs cell)))
1202 (cond ((characterp cell)
1206 (insert (format "%S" cell))
1207 (char-db-insert-char-spec cell readable))
1208 (setq separator lbs))
1212 (if (consp (car cell))
1213 (char-db-insert-char-spec cell readable)
1214 (char-db-insert-char-reference cell readable))
1215 (setq separator lbs))
1219 (insert (prin1-to-string cell))
1220 (setq separator " ")))
1221 (setq value (cdr value)))
1223 (insert line-breaking)
1224 (setq attributes (delq 'ideographic- attributes)))
1225 (when (and (memq 'total-strokes attributes)
1226 (setq value (get-char-attribute char 'total-strokes)))
1227 (insert (format "(total-strokes . %S)%s"
1230 (setq attributes (delq 'total-strokes attributes))
1232 (when (and (memq '->ideograph attributes)
1233 (setq value (get-char-attribute char '->ideograph)))
1234 (insert (format "(->ideograph\t%s)%s"
1235 (mapconcat (lambda (code)
1236 (cond ((symbolp code)
1239 (format "#x%04X" code))
1242 line-breaking code))))
1245 (setq attributes (delq '->ideograph attributes))
1247 ;; (when (and (memq '->decomposition attributes)
1248 ;; (setq value (get-char-attribute char '->decomposition)))
1249 ;; (insert (format "(->decomposition\t%s)%s"
1250 ;; (mapconcat (lambda (code)
1251 ;; (cond ((symbolp code)
1252 ;; (symbol-name code))
1253 ;; ((characterp code)
1255 ;; (format "%S" code)
1260 ;; (format "#x%04X" code))
1262 ;; (format "%s%S" line-breaking code))))
1265 ;; (setq attributes (delq '->decomposition attributes))
1267 (if (equal (get-char-attribute char '->titlecase)
1268 (get-char-attribute char '->uppercase))
1269 (setq attributes (delq '->titlecase attributes)))
1270 (when (and (memq '->mojikyo attributes)
1271 (setq value (get-char-attribute char '->mojikyo)))
1272 (insert (format "(->mojikyo\t\t. %06d)\t; %c%s"
1273 value (decode-char 'mojikyo value)
1275 (setq attributes (delq '->mojikyo attributes))
1277 (when (and (memq 'hanyu-dazidian-vol attributes)
1278 (setq value (get-char-attribute char 'hanyu-dazidian-vol)))
1279 (insert (format "(hanyu-dazidian-vol . %d)%s"
1280 value line-breaking))
1281 (setq attributes (delq 'hanyu-dazidian-vol attributes))
1283 (when (and (memq 'hanyu-dazidian-page attributes)
1284 (setq value (get-char-attribute char 'hanyu-dazidian-page)))
1285 (insert (format "(hanyu-dazidian-page . %d)%s"
1286 value line-breaking))
1287 (setq attributes (delq 'hanyu-dazidian-page attributes))
1289 (when (and (memq 'hanyu-dazidian-char attributes)
1290 (setq value (get-char-attribute char 'hanyu-dazidian-char)))
1291 (insert (format "(hanyu-dazidian-char . %d)%s"
1292 value line-breaking))
1293 (setq attributes (delq 'hanyu-dazidian-char attributes))
1296 (dolist (ignored '(composition
1297 ->denotational <-subsumptive ->ucs-unified
1298 ->ideographic-component-forms))
1299 (setq attributes (delq ignored attributes))))
1301 (setq name (car attributes))
1302 (unless (eq (setq value (get-char-attribute char name 'value-is-empty))
1304 (cond ((setq ret (find-charset name))
1305 (setq name (charset-name ret))
1306 (when (not (memq name dest-ccss))
1307 (setq dest-ccss (cons name dest-ccss))
1308 (char-db-insert-ccs-feature name value line-breaking))
1310 ((string-match "^=>ucs@" (symbol-name name))
1311 (insert (format "(%-18s . #x%04X)\t; %c%s"
1312 name value (decode-char '=ucs value)
1315 ((eq name 'jisx0208-1978/4X)
1316 (insert (format "(%-18s . #x%04X)%s"
1322 (not (eq name '->subsumptive))
1323 (not (eq name '->uppercase))
1324 (not (eq name '->lowercase))
1325 (not (eq name '->titlecase))
1326 (not (eq name '->canonical))
1327 (not (eq name '->Bopomofo))
1328 (not (eq name '->mistakable))
1329 (not (eq name '->ideographic-variants))
1330 (null (get-char-attribute
1331 char (intern (format "%s*sources" name))))
1332 (not (string-match "\\*sources$" (symbol-name name)))
1333 (null (get-char-attribute
1334 char (intern (format "%s*note" name))))
1335 (not (string-match "\\*note$" (symbol-name name)))
1336 (or (eq name '<-identical)
1337 (eq name '<-uppercase)
1338 (eq name '<-lowercase)
1339 (eq name '<-titlecase)
1340 (eq name '<-canonical)
1341 (eq name '<-ideographic-variants)
1342 ;; (eq name '<-synonyms)
1343 (string-match "^<-synonyms" (symbol-name name))
1344 (eq name '<-mistakable)
1345 (when (string-match "^->" (symbol-name name))
1347 ((string-match "^->fullwidth" (symbol-name name))
1348 (not (and (consp value)
1349 (characterp (car value))
1351 (car value) '=ucs 'defined-only)))
1356 ((or (eq name 'ideographic-structure)
1357 (eq name 'ideographic-combination)
1358 (eq name 'ideographic-)
1359 (eq name '=decomposition)
1360 (char-feature-base-name= '=decomposition name)
1361 (char-feature-base-name= '=>decomposition name)
1362 ;; (string-match "^=>*decomposition\\(@[^*]+\\)?$"
1363 ;; (symbol-name name))
1364 (string-match "^\\(->\\|<-\\)[^*]*$" (symbol-name name))
1365 (string-match "^\\(->\\|<-\\)[^*]*\\*sources$"
1368 (char-db-insert-relation-feature char name value
1371 ((memq name '(ideograph=
1372 original-ideograph-of
1373 ancient-ideograph-of
1376 ;; simplified-ideograph-of
1377 ideographic-variants
1378 ;; ideographic-different-form-of
1380 (insert (format "(%-18s%s " name line-breaking))
1381 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1383 (while (consp value)
1384 (setq cell (car value))
1385 (if (and (consp cell)
1390 (char-db-insert-alist cell readable)
1391 (setq separator lbs))
1394 (insert (prin1-to-string cell))
1395 (setq separator " "))
1396 (setq value (cdr value)))
1398 (insert line-breaking))
1400 (insert (format "(%-18s " name))
1401 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1403 (while (consp value)
1404 (setq cell (car value))
1405 (if (and (consp cell)
1407 (setq ret (condition-case nil
1415 (setq key (car (car rest)))
1416 (if (find-charset key)
1417 (setq cal (cons key cal))
1418 (setq al (cons key al)))
1419 (setq rest (cdr rest)))
1422 (insert-char-attributes ret
1426 (setq separator lbs))
1427 (setq ret (prin1-to-string cell))
1429 (if (< (+ (current-column)
1436 (setq separator " "))
1437 (setq value (cdr value)))
1439 (insert line-breaking))
1441 (insert (format "(%-18s" name))
1442 (setq ret (prin1-to-string value))
1443 (unless (< (+ (current-column)
1447 (insert line-breaking))
1448 (insert " . " ret ")" line-breaking)
1449 ;; (insert (format "(%-18s . %S)%s"
1454 (setq attributes (cdr attributes)))
1457 (defun insert-char-data (char &optional readable
1460 (narrow-to-region (point)(point))
1461 (insert "(define-char
1463 (insert-char-attributes char readable attributes)
1465 (goto-char (point-min))
1466 (while (re-search-forward "[ \t]+$" nil t)
1469 (goto-char (point-min))
1470 (while (re-search-forward "[ \t][ \t][ \t]*" nil t)
1471 (let ((column (current-column))
1472 (indent-tabs-mode t))
1473 (delete-region (match-beginning 0) (point))
1474 (indent-to column)))
1475 (goto-char (point-max))
1476 ;; (tabify (point-min)(point-max))
1479 (defun insert-char-data-with-variant (char &optional printable
1481 script excluded-script)
1482 (insert-char-data char printable)
1483 (let ((variants (char-variants char))
1486 (setq variants (sort variants #'<))
1487 (setq rest variants)
1488 (setq variants (cons char variants))
1490 (setq variant (car rest))
1491 (unless (get-char-attribute variant '<-subsumptive)
1492 (if (and (or (null script)
1493 (null (setq vs (get-char-attribute variant 'script)))
1495 (or (null excluded-script)
1496 (null (setq vs (get-char-attribute variant 'script)))
1497 (not (memq excluded-script vs))))
1498 (unless (and no-ucs-unified (get-char-attribute variant '=ucs))
1499 (insert-char-data variant printable)
1500 (if (setq ret (char-variants variant))
1502 (or (memq (car ret) variants)
1503 ;; (get-char-attribute (car ret) '<-subsumptive)
1504 (setq rest (nconc rest (list (car ret)))))
1505 (setq ret (cdr ret)))))))
1506 (setq rest (cdr rest)))))
1508 (defun insert-char-range-data (min max &optional script excluded-script)
1511 (while (<= code max)
1512 (setq char (decode-char '=ucs code))
1513 (if (encode-char char '=ucs 'defined-only)
1514 (insert-char-data-with-variant char nil 'no-ucs-unified
1515 script excluded-script))
1516 (setq code (1+ code)))))
1518 (defun write-char-range-data-to-file (min max file
1519 &optional script excluded-script)
1520 (let ((coding-system-for-write char-db-file-coding-system))
1522 (insert (format ";; -*- coding: %s -*-\n"
1523 char-db-file-coding-system))
1524 (insert-char-range-data min max script excluded-script)
1525 (write-region (point-min)(point-max) file))))
1527 (defvar what-character-original-window-configuration)
1530 (defun what-char-definition (char)
1531 (interactive (list (char-after)))
1532 (let ((buf (get-buffer-create "*Character Description*"))
1533 (the-buf (current-buffer))
1534 (win-conf (current-window-configuration)))
1536 (make-local-variable 'what-character-original-window-configuration)
1537 (setq what-character-original-window-configuration win-conf)
1538 (setq buffer-read-only nil)
1542 (insert-char-data-with-variant char 'printable)
1543 (unless (char-attribute-alist char)
1544 (insert (format ";; = %c\n"
1545 (let* ((rest (split-char char))
1549 (setq code (logior (lsh code 8)
1551 (decode-char ccs code)))))
1552 ;; (char-db-update-comment)
1553 (set-buffer-modified-p nil)
1554 (view-mode the-buf (lambda (buf)
1555 (set-window-configuration
1556 what-character-original-window-configuration)
1558 (goto-char (point-min)))
1560 (set-window-configuration
1561 what-character-original-window-configuration)
1562 (signal (car err) (cdr err)))))))
1568 (provide 'char-db-util)
1570 ;;; char-db-util.el ends here