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
365 =>big5-cdp-itaiji-001
374 ;;; @ char-db formatters
377 (defun char-db-make-char-spec (char)
379 (cond ((characterp char)
380 (cond ((and (setq ret (encode-char char '=ucs 'defined-only))
381 (not (and (<= #xE000 ret)(<= ret #xF8FF))))
382 (setq char-spec (list (cons '=ucs ret)))
383 (cond ((setq ret (get-char-attribute char 'name))
384 (setq char-spec (cons (cons 'name ret) char-spec))
386 ((setq ret (get-char-attribute char 'name*))
387 (setq char-spec (cons (cons 'name* ret) char-spec))
390 ((encode-char char '=mj 'defined-only)
392 (dolist (ccs (charset-list))
393 (if (and (or (eq ccs '=mj)
394 ;; (eq (charset-property ccs 'iso-ir) 177)
395 (string-match "=ucs@" (symbol-name ccs))
397 (setq ccs (charset-name ccs))
398 (null (assq ccs char-spec))
399 (setq ret (encode-char char ccs 'defined-only)))
400 (setq char-spec (cons (cons ccs ret) char-spec))))
402 ((encode-char char '==mj 'defined-only)
404 (dolist (ccs (charset-list))
405 (if (and (or (eq ccs '==mj)
406 ;; (eq (charset-property ccs 'iso-ir) 177)
407 (string-match "=ucs@" (symbol-name ccs))
409 (setq ccs (charset-name ccs))
410 (null (assq ccs char-spec))
411 (setq ret (encode-char char ccs 'defined-only)))
412 (setq char-spec (cons (cons ccs ret) char-spec))))
414 ((encode-char char '=adobe-japan1 'defined-only)
416 (dolist (ccs (charset-list))
417 (if (and (or (memq ccs
426 ;; (eq (charset-property ccs 'iso-ir) 177)
427 (string-match "=ucs@" (symbol-name ccs))
429 (setq ccs (charset-name ccs))
430 (null (assq ccs char-spec))
431 (setq ret (encode-char char ccs 'defined-only)))
432 (setq char-spec (cons (cons ccs ret) char-spec))))
434 ((encode-char char '==adobe-japan1 'defined-only)
436 (dolist (ccs (charset-list))
437 (if (and (or (memq ccs
446 ;; (eq (charset-property ccs 'iso-ir) 177)
447 (string-match "=ucs@" (symbol-name ccs))
449 (setq ccs (charset-name ccs))
450 (null (assq ccs char-spec))
451 (setq ret (encode-char char ccs 'defined-only)))
452 (setq char-spec (cons (cons ccs ret) char-spec))))
456 (let ((rest char-db-coded-charset-priority-list)
459 (setq ccs (charset-name
460 (find-charset (car rest))))
462 (encode-char char ccs
464 (throw 'tag (cons ccs ret)))
465 (setq rest (cdr rest))))))
466 (setq char-spec (list ret))
467 (dolist (ccs (delq (car ret) (charset-list)))
468 (if (and (or (charset-iso-final-char ccs)
475 (eq (charset-property ccs 'iso-ir) 177)
476 ;; (string-match "=ucs@" (symbol-name ccs))
478 (setq ccs (charset-name ccs))
479 (null (assq ccs char-spec))
480 (setq ret (encode-char char ccs 'defined-only)))
481 (setq char-spec (cons (cons ccs ret) char-spec))))
483 (setq char-spec (split-char char)))
484 (cond ((setq ret (get-char-attribute char 'name))
485 (setq char-spec (cons (cons 'name ret) char-spec))
487 ((setq ret (get-char-attribute char 'name*))
488 (setq char-spec (cons (cons 'name* ret) char-spec))
491 ((setq ret (get-char-attribute
492 char 'ideographic-combination))
494 (cons (cons 'ideographic-combination ret)
501 (defun char-db-insert-char-spec (char &optional readable column
504 (setq column (current-column)))
505 (let (char-spec temp-char)
506 (setq char-spec (char-db-make-char-spec char))
507 (unless (or (characterp char) ; char
509 (setq char (find-char char-spec))
511 ;; define temporary character
512 ;; Current implementation is dirty.
513 (setq temp-char (define-char (cons '(ideograph-daikanwa . 0)
515 (remove-char-attribute temp-char 'ideograph-daikanwa)
516 (setq char temp-char))
517 (insert-char-attributes char
519 (union (mapcar #'car char-spec)
523 ;; undefine temporary character
524 ;; Current implementation is dirty.
525 (setq char-spec (char-attribute-alist temp-char))
527 (remove-char-attribute temp-char (car (car char-spec)))
528 (setq char-spec (cdr char-spec))))))
530 (defun char-db-insert-alist (alist &optional readable column)
532 (setq column (current-column)))
534 (concat "\n" (make-string (1+ column) ?\ )))
538 lbs cell rest separator)
541 (setq name (car (car alist))
542 value (cdr (car alist)))
543 (cond ((eq name 'char)
545 (if (setq ret (condition-case nil
553 (setq key (car (car value)))
554 ;; (if (find-charset key)
555 ;; (setq cal (cons key cal))
556 (setq al (cons key al))
558 (setq value (cdr value)))
559 (insert-char-attributes ret
563 (insert (prin1-to-string value)))
565 (insert line-breaking))
567 (insert (format "(%-18s " name))
568 (setq lbs (concat "\n" (make-string (current-column) ?\ )))
570 (setq cell (car value))
571 (if (and (consp cell)
573 (setq ret (condition-case nil
583 (setq key (car (car rest)))
584 ;; (if (find-charset key)
585 ;; (setq cal (cons key cal))
586 (setq al (cons key al))
588 (setq rest (cdr rest)))
591 (insert-char-attributes ret
595 (setq separator lbs))
598 (insert (prin1-to-string cell))
599 (setq separator " "))
600 (setq value (cdr value)))
602 (insert line-breaking))
604 (insert (format "(%-18s . %S)%s"
607 (setq alist (cdr alist))))
610 (defun char-db-insert-char-reference (plist &optional readable column)
612 (setq column (current-column)))
614 (concat "\n" (make-string (1+ column) ?\ )))
619 (setq name (pop plist))
620 (setq value (pop plist))
621 (cond ((eq name :char)
624 (cond ((numberp value)
625 (setq value (decode-char '=ucs value)))
627 ;; (setq value (or (find-char value)
630 (char-db-insert-char-spec value readable)
631 (insert line-breaking)
634 (insert (format "%s%s\t%d ; %c%s"
637 (ideographic-radical value)
641 (insert (format "%s%s\t%S" separator name value))
642 (setq separator line-breaking)))
646 (defun char-db-decode-isolated-char (ccs code-point)
649 (cond ((eq ccs 'arabic-iso8859-6)
650 (decode-char ccs code-point))
652 ;; (decode-builtin-char '==gt code-point))
653 ((and (memq ccs '(=gt-pj-1
664 (setq ret (decode-char ccs code-point))
665 (setq ret (encode-char ret '=gt 'defined-only)))
666 (decode-builtin-char '=gt ret))
668 (decode-builtin-char ccs code-point))))
670 (or (decode-char ccs code-point)
671 (define-char (list (cons ccs code-point)))))
672 ((and (<= 0 (char-int ret))
673 (<= (char-int ret) #x1F))
674 (decode-char '=ucs (+ #x2400 (char-int ret))))
675 ((= (char-int ret) #x7F)
679 (defvar char-db-convert-obsolete-format t)
681 (defun char-db-insert-ccs-feature (name value line-breaking)
687 ((memq name '(=>iwds-1
690 =shinjigen@1ed ==shinjigen@1ed
691 =shinjigen@rev ==shinjigen@rev
692 =shinjigen/+p@rev ==shinjigen/+p@rev
693 ===daikanwa/ho ==daikanwa/ho
694 =daikanwa/ho =>>daikanwa/ho =>daikanwa/ho))
695 "(%-18s . %04d)\t; %c")
696 ((eq name '=shinjigen@1ed/24pr)
697 "(%-18s . %04d)\t; %c")
701 ==daikanwa =daikanwa =>>daikanwa =>daikanwa
702 =daikanwa@rev1 =daikanwa@rev2
703 =daikanwa/+p ==daikanwa/+p ===daikanwa/+p
705 =daikanwa/+2p =>>daikanwa/+2p
710 =adobe-japan1-0 ==adobe-japan1-0 ===adobe-japan1-0
711 =adobe-japan1-1 ==adobe-japan1-1 ===adobe-japan1-1
712 =adobe-japan1-2 ==adobe-japan1-2 ===adobe-japan1-2
713 =adobe-japan1-3 ==adobe-japan1-3 ===adobe-japan1-3
714 =adobe-japan1-4 ==adobe-japan1-4 ===adobe-japan1-4
715 =adobe-japan1-5 ==adobe-japan1-5 ===adobe-japan1-5
716 =adobe-japan1-6 ==adobe-japan1-6 ===adobe-japan1-6
717 =>>adobe-japan1-0 =+>adobe-japan1-0
718 =>>adobe-japan1-1 =+>adobe-japan1-1
719 =>>adobe-japan1-2 =+>adobe-japan1-2
720 =>>adobe-japan1-3 =+>adobe-japan1-3
721 =>>adobe-japan1-4 =+>adobe-japan1-4
722 =>>adobe-japan1-5 =+>adobe-japan1-5
723 =>>adobe-japan1-6 =+>adobe-japan1-6
724 =>cbeta =cbeta =>>cbeta ==cbeta ===cbeta
725 =zinbun-oracle =>zinbun-oracle
726 ===hng-jou ===hng-keg ===hng-dng ===hng-mam
727 ===hng-drt ===hng-kgk ===hng-myz ===hng-kda
728 ===hng-khi ===hng-khm ===hng-hok ===hng-kyd ===hng-sok
729 ===hng-yhk ===hng-kak ===hng-kar ===hng-kae
730 ===hng-sys ===hng-tsu ===hng-tzj
731 ===hng-hos ===hng-nak ===hng-jhk
732 ===hng-hod ===hng-gok ===hng-ink ===hng-nto
733 ===hng-nkm ===hng-k24 ===hng-nkk
734 ===hng-kcc ===hng-kcj ===hng-kbk ===hng-sik
735 ===hng-skk ===hng-kyu ===hng-ksk ===hng-wan
736 ===hng-okd ===hng-wad ===hng-kmi
737 ===hng-zkd ===hng-doh ===hng-jyu
738 ===hng-tzs ===hng-kss ===hng-kyo
740 ;; (string-match "^=adobe-" (symbol-name name))
742 "(%-18s . %05d)\t; %c")
743 ((memq name '(=hanyo-denshi/ks
744 ==hanyo-denshi/ks ===hanyo-denshi/ks
747 =mj ==mj ===mj =>>mj =>mj
749 "(%-18s . %06d)\t; %c")
750 ((memq name '(=hanyo-denshi/tk ==hanyo-denshi/tk))
751 "(%-18s . %08d)\t; %c")
752 ((>= (charset-dimension name) 2)
753 "(%-18s . #x%04X)\t; %c")
755 "(%-18s . #x%02X)\t; %c"))
757 (if (= (charset-iso-graphic-plane name) 1)
759 (cond ((= (charset-dimension name) 1)
761 ((= (charset-dimension name) 2)
763 ((= (charset-dimension name) 3)
767 (char-db-decode-isolated-char name value)))
768 (if (and (= (charset-chars name) 94)
769 (= (charset-dimension name) 2))
770 (insert (format " [%02d-%02d]"
771 (- (lsh value -8) 32)
772 (- (logand value 255) 32))))
775 (insert (format "(%-18s . %s)" name value))
777 (insert line-breaking))
779 (defun char-db-insert-relation-feature (char name value line-breaking
781 (insert (format "(%-18s%s " name line-breaking))
782 (let ((lbs (concat "\n" (make-string (current-column) ?\ )))
783 separator cell sources required-features
786 (setq cell (car value))
788 (setq cell (decode-char '=ucs cell)))
790 ((eq name '->subsumptive)
791 (when (or (not (some (lambda (atr)
792 (get-char-attribute cell atr))
793 char-db-ignored-attributes))
795 (encode-char cell ccs 'defined-only))
799 (let ((char-db-ignored-attributes
801 char-db-ignored-attributes)))
802 (insert-char-attributes cell readable nil nil 'for-sub-node))
803 (setq separator lbs))
808 char (intern (format "%s*sources" name))))
809 (setq required-features nil)
810 (dolist (source sources)
814 shinjigen shinjigen@1ed shinjigen@rev))
815 (setq required-features
816 (union required-features
828 =shinjigen/+p@rev))))
830 (setq required-features
831 (union required-features
836 ((find-charset (setq ret (intern (format "=%s" source))))
837 (setq required-features
838 (cons ret required-features)))
839 (t (setq required-features
840 (cons source required-features)))))
841 (cond ((string-match "@JP" (symbol-name name))
842 (setq required-features
843 (union required-features
851 ((string-match "@CN" (symbol-name name))
852 (setq required-features
853 (union required-features
860 (insert (format "%S" cell))
861 (char-db-insert-char-spec cell readable
864 (setq separator lbs))
868 (if (consp (car cell))
869 (char-db-insert-char-spec cell readable)
870 (char-db-insert-char-reference cell readable))
871 (setq separator lbs))
875 (insert (prin1-to-string cell))
876 (setq separator " ")))
877 (setq value (cdr value)))
879 (insert line-breaking)))
881 (defun insert-char-attributes (char &optional readable attributes column
884 (setq column (current-column)))
885 (let (name value ; has-long-ccs-name
889 (concat "\n" (make-string (1+ column) ?\ )))
890 lbs cell separator ret
892 dest-ccss ; sources required-features
897 (if (consp attributes)
899 (dolist (name attributes)
900 (unless (memq name char-db-ignored-attributes)
901 (if (find-charset name)
905 (dolist (name (char-attribute-list))
906 (unless (memq name char-db-ignored-attributes)
907 (if (find-charset name)
911 #'char-attribute-name<)))
913 (when (memq '<-subsumptive attributes)
914 (when (or readable (not for-sub-node))
915 (when (setq value (get-char-attribute char '<-subsumptive))
916 (char-db-insert-relation-feature char '<-subsumptive value
919 (setq attributes (delq '<-subsumptive attributes)))
920 (when (and (memq '<-denotational attributes)
921 (setq value (get-char-attribute char '<-denotational)))
922 (char-db-insert-relation-feature char '<-denotational value
925 (setq attributes (delq '<-denotational attributes)))
926 (when (and (memq '<-denotational@component attributes)
927 (setq value (get-char-attribute char '<-denotational@component)))
928 (char-db-insert-relation-feature char '<-denotational@component value
931 (setq attributes (delq '<-denotational@component attributes)))
932 (when (and (memq 'name attributes)
933 (setq value (get-char-attribute char 'name)))
935 (if (> (+ (current-column) (length value)) 48)
938 value line-breaking))
939 (setq attributes (delq 'name attributes))
941 (when (and (memq 'name* attributes)
942 (setq value (get-char-attribute char 'name*)))
944 (if (> (+ (current-column) (length value)) 48)
947 value line-breaking))
948 (setq attributes (delq 'name* attributes))
950 (when (and (memq 'script attributes)
951 (setq value (get-char-attribute char 'script)))
952 (insert (format "(script\t\t%s)%s"
953 (mapconcat (function prin1-to-string)
956 (setq attributes (delq 'script attributes))
958 (dolist (name '(=>ucs =>ucs*))
959 (when (and (memq name attributes)
960 (setq value (get-char-attribute char name)))
961 (insert (format "(%-18s . #x%04X)\t; %c%s"
962 name value (decode-char '=ucs value)
964 (setq attributes (delq name attributes))))
965 (dolist (name '(=>ucs@gb =>ucs@big5))
966 (when (and (memq name attributes)
967 (setq value (get-char-attribute char name)))
968 (insert (format "(%-18s . #x%04X)\t; %c%s"
973 (symbol-name name) 2)))
976 (setq attributes (delq name attributes))
978 ;; (dolist (name '(=>daikanwa))
979 ;; (when (and (memq name attributes)
980 ;; (setq value (get-char-attribute char name)))
982 ;; (if (integerp value)
983 ;; (format "(%-18s . %05d)\t; %c%s"
984 ;; name value (decode-char '=daikanwa value)
986 ;; (format "(%-18s %s)\t; %c%s"
988 ;; (mapconcat (function prin1-to-string)
990 ;; (char-representative-of-daikanwa char)
992 ;; (setq attributes (delq name attributes))))
993 (when (and (memq 'general-category attributes)
994 (setq value (get-char-attribute char 'general-category)))
996 "(general-category\t%s) ; %s%s"
997 (mapconcat (lambda (cell)
1000 (cond ((rassoc value unidata-normative-category-alist)
1001 "Normative Category")
1002 ((rassoc value unidata-informative-category-alist)
1003 "Informative Category")
1005 "Unknown Category"))
1007 (setq attributes (delq 'general-category attributes))
1009 (when (and (memq 'bidi-category attributes)
1010 (setq value (get-char-attribute char 'bidi-category)))
1011 (insert (format "(bidi-category\t. %S)%s"
1014 (setq attributes (delq 'bidi-category attributes))
1016 (unless (or (not (memq 'mirrored attributes))
1017 (eq (setq value (get-char-attribute char 'mirrored 'empty))
1019 (insert (format "(mirrored\t\t. %S)%s"
1022 (setq attributes (delq 'mirrored attributes))
1025 ((and (memq 'decimal-digit-value attributes)
1026 (setq value (get-char-attribute char 'decimal-digit-value)))
1027 (insert (format "(decimal-digit-value . %S)%s"
1030 (setq attributes (delq 'decimal-digit-value attributes))
1031 (when (and (memq 'digit-value attributes)
1032 (setq value (get-char-attribute char 'digit-value)))
1033 (insert (format "(digit-value\t . %S)%s"
1036 (setq attributes (delq 'digit-value attributes))
1038 (when (and (memq 'numeric-value attributes)
1039 (setq value (get-char-attribute char 'numeric-value)))
1040 (insert (format "(numeric-value\t . %S)%s"
1043 (setq attributes (delq 'numeric-value attributes))
1047 (when (and (memq 'digit-value attributes)
1048 (setq value (get-char-attribute char 'digit-value)))
1049 (insert (format "(digit-value\t. %S)%s"
1052 (setq attributes (delq 'digit-value attributes))
1054 (when (and (memq 'numeric-value attributes)
1055 (setq value (get-char-attribute char 'numeric-value)))
1056 (insert (format "(numeric-value\t. %S)%s"
1059 (setq attributes (delq 'numeric-value attributes))
1061 (when (and (memq 'iso-10646-comment attributes)
1062 (setq value (get-char-attribute char 'iso-10646-comment)))
1063 (insert (format "(iso-10646-comment\t. %S)%s"
1066 (setq attributes (delq 'iso-10646-comment attributes))
1068 (when (and (memq 'morohashi-daikanwa attributes)
1069 (setq value (get-char-attribute char 'morohashi-daikanwa)))
1070 (insert (format "(morohashi-daikanwa\t%s)%s"
1071 (mapconcat (function prin1-to-string) value " ")
1073 (setq attributes (delq 'morohashi-daikanwa attributes))
1077 (when (and (memq 'ideographic-radical attributes)
1078 (setq value (get-char-attribute char 'ideographic-radical)))
1079 (setq radical value)
1080 (insert (format "(ideographic-radical . %S)\t; %c%s"
1082 (ideographic-radical radical)
1084 (setq attributes (delq 'ideographic-radical attributes))
1086 (when (and (memq 'shuowen-radical attributes)
1087 (setq value (get-char-attribute char 'shuowen-radical)))
1088 (insert (format "(shuowen-radical\t. %S)\t; %c%s"
1090 (shuowen-radical value)
1092 (setq attributes (delq 'shuowen-radical attributes))
1097 char-db-feature-domains
1099 (dolist (feature (char-attribute-list))
1100 (setq feature (symbol-name feature))
1102 "\\(radical\\|strokes\\)@\\([^@*]+\\)\\(\\*\\|$\\)"
1104 (setq domain (intern (match-string 2 feature)))
1105 (unless (memq domain dest)
1106 (setq dest (cons domain dest)))))
1107 (sort dest #'string<))))
1108 (setq key (intern (format "%s@%s" 'ideographic-radical domain)))
1109 (when (and (memq key attributes)
1110 (setq value (get-char-attribute char key)))
1111 (setq radical value)
1112 (insert (format "(%s . %S)\t; %c%s"
1115 (ideographic-radical radical)
1117 (setq attributes (delq key attributes))
1119 (setq key (intern (format "%s@%s" 'ideographic-strokes domain)))
1120 (when (and (memq key attributes)
1121 (setq value (get-char-attribute char key)))
1122 (setq strokes value)
1123 (insert (format "(%s . %S)%s"
1127 (setq attributes (delq key attributes))
1129 (setq key (intern (format "%s@%s" 'total-strokes domain)))
1130 (when (and (memq key attributes)
1131 (setq value (get-char-attribute char key)))
1132 (insert (format "(%s . %S)%s"
1136 (setq attributes (delq key attributes))
1138 (dolist (feature '(ideographic-radical
1141 (setq key (intern (format "%s@%s*sources" feature domain)))
1142 (when (and (memq key attributes)
1143 (setq value (get-char-attribute char key)))
1144 (insert (format "(%s%s" key line-breaking))
1145 (dolist (cell value)
1146 (insert (format " %s" cell)))
1148 (insert line-breaking)
1149 (setq attributes (delq key attributes))
1152 (when (and (memq 'ideographic-strokes attributes)
1153 (setq value (get-char-attribute char 'ideographic-strokes)))
1154 (setq strokes value)
1155 (insert (format "(ideographic-strokes . %S)%s"
1158 (setq attributes (delq 'ideographic-strokes attributes))
1160 (when (and (memq 'kangxi-radical attributes)
1161 (setq value (get-char-attribute char 'kangxi-radical)))
1162 (unless (eq value radical)
1163 (insert (format "(kangxi-radical\t . %S)\t; %c%s"
1165 (ideographic-radical value)
1168 (setq radical value)))
1169 (setq attributes (delq 'kangxi-radical attributes))
1171 (when (and (memq 'kangxi-strokes attributes)
1172 (setq value (get-char-attribute char 'kangxi-strokes)))
1173 (unless (eq value strokes)
1174 (insert (format "(kangxi-strokes\t . %S)%s"
1178 (setq strokes value)))
1179 (setq attributes (delq 'kangxi-strokes attributes))
1181 ;; (when (and (memq 'japanese-radical attributes)
1182 ;; (setq value (get-char-attribute char 'japanese-radical)))
1183 ;; (unless (eq value radical)
1184 ;; (insert (format "(japanese-radical\t . %S)\t; %c%s"
1186 ;; (ideographic-radical value)
1189 ;; (setq radical value)))
1190 ;; (setq attributes (delq 'japanese-radical attributes))
1192 (when (and (memq 'japanese-strokes attributes)
1193 (setq value (get-char-attribute char 'japanese-strokes)))
1194 (unless (eq value strokes)
1195 (insert (format "(japanese-strokes\t . %S)%s"
1199 (setq strokes value)))
1200 (setq attributes (delq 'japanese-strokes attributes))
1202 (when (and (memq 'cns-radical attributes)
1203 (setq value (get-char-attribute char 'cns-radical)))
1204 (insert (format "(cns-radical\t . %S)\t; %c%s"
1206 (ideographic-radical value)
1208 (setq attributes (delq 'cns-radical attributes))
1210 (when (and (memq 'cns-strokes attributes)
1211 (setq value (get-char-attribute char 'cns-strokes)))
1212 (unless (eq value strokes)
1213 (insert (format "(cns-strokes\t . %S)%s"
1217 (setq strokes value)))
1218 (setq attributes (delq 'cns-strokes attributes))
1220 ;; (when (and (memq 'shinjigen-1-radical attributes)
1221 ;; (setq value (get-char-attribute char 'shinjigen-1-radical)))
1222 ;; (unless (eq value radical)
1223 ;; (insert (format "(shinjigen-1-radical . %S)\t; %c%s"
1225 ;; (ideographic-radical value)
1228 ;; (setq radical value)))
1229 ;; (setq attributes (delq 'shinjigen-1-radical attributes))
1231 ;; (when (and (memq 'ideographic- attributes)
1232 ;; (setq value (get-char-attribute char 'ideographic-)))
1233 ;; (insert "(ideographic- ")
1234 ;; (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1236 ;; (while (consp value)
1237 ;; (setq cell (car value))
1238 ;; (if (integerp cell)
1239 ;; (setq cell (decode-char '=ucs cell)))
1240 ;; (cond ((characterp cell)
1244 ;; (insert (format "%S" cell))
1245 ;; (char-db-insert-char-spec cell readable))
1246 ;; (setq separator lbs))
1250 ;; (if (consp (car cell))
1251 ;; (char-db-insert-char-spec cell readable)
1252 ;; (char-db-insert-char-reference cell readable))
1253 ;; (setq separator lbs))
1256 ;; (insert separator))
1257 ;; (insert (prin1-to-string cell))
1258 ;; (setq separator " ")))
1259 ;; (setq value (cdr value)))
1261 ;; (insert line-breaking)
1262 ;; (setq attributes (delq 'ideographic- attributes)))
1263 (when (and (memq 'total-strokes attributes)
1264 (setq value (get-char-attribute char 'total-strokes)))
1265 (insert (format "(total-strokes . %S)%s"
1268 (setq attributes (delq 'total-strokes attributes))
1270 ;; (when (and (memq '->ideograph attributes)
1271 ;; (setq value (get-char-attribute char '->ideograph)))
1272 ;; (insert (format "(->ideograph\t%s)%s"
1273 ;; (mapconcat (lambda (code)
1274 ;; (cond ((symbolp code)
1275 ;; (symbol-name code))
1277 ;; (format "#x%04X" code))
1280 ;; line-breaking code))))
1283 ;; (setq attributes (delq '->ideograph attributes))
1285 ;; (when (and (memq '->decomposition attributes)
1286 ;; (setq value (get-char-attribute char '->decomposition)))
1287 ;; (insert (format "(->decomposition\t%s)%s"
1288 ;; (mapconcat (lambda (code)
1289 ;; (cond ((symbolp code)
1290 ;; (symbol-name code))
1291 ;; ((characterp code)
1293 ;; (format "%S" code)
1298 ;; (format "#x%04X" code))
1300 ;; (format "%s%S" line-breaking code))))
1303 ;; (setq attributes (delq '->decomposition attributes))
1305 (if (equal (get-char-attribute char '->titlecase)
1306 (get-char-attribute char '->uppercase))
1307 (setq attributes (delq '->titlecase attributes)))
1308 (when (and (memq '->mojikyo attributes)
1309 (setq value (get-char-attribute char '->mojikyo)))
1310 (insert (format "(->mojikyo\t\t. %06d)\t; %c%s"
1311 value (decode-char 'mojikyo value)
1313 (setq attributes (delq '->mojikyo attributes))
1315 ;; (when (and (memq 'hanyu-dazidian-vol attributes)
1316 ;; (setq value (get-char-attribute char 'hanyu-dazidian-vol)))
1317 ;; (insert (format "(hanyu-dazidian-vol . %d)%s"
1318 ;; value line-breaking))
1319 ;; (setq attributes (delq 'hanyu-dazidian-vol attributes))
1321 ;; (when (and (memq 'hanyu-dazidian-page attributes)
1322 ;; (setq value (get-char-attribute char 'hanyu-dazidian-page)))
1323 ;; (insert (format "(hanyu-dazidian-page . %d)%s"
1324 ;; value line-breaking))
1325 ;; (setq attributes (delq 'hanyu-dazidian-page attributes))
1327 ;; (when (and (memq 'hanyu-dazidian-char attributes)
1328 ;; (setq value (get-char-attribute char 'hanyu-dazidian-char)))
1329 ;; (insert (format "(hanyu-dazidian-char . %d)%s"
1330 ;; value line-breaking))
1331 ;; (setq attributes (delq 'hanyu-dazidian-char attributes))
1334 (dolist (ignored '(composition
1335 ->denotational <-subsumptive ->ucs-unified
1336 ->ideographic-component-forms))
1337 (setq attributes (delq ignored attributes))))
1339 (setq name (car attributes))
1340 (unless (eq (setq value (get-char-attribute char name 'value-is-empty))
1342 (cond ((setq ret (find-charset name))
1343 (setq name (charset-name ret))
1344 (when (not (memq name dest-ccss))
1345 (setq dest-ccss (cons name dest-ccss))
1346 (char-db-insert-ccs-feature name value line-breaking))
1348 ((string-match "^=>ucs@" (symbol-name name))
1349 (insert (format "(%-18s . #x%04X)\t; %c%s"
1350 name value (decode-char '=ucs value)
1353 ((eq name 'jisx0208-1978/4X)
1354 (insert (format "(%-18s . #x%04X)%s"
1360 (not (eq name '->subsumptive))
1361 (not (eq name '->uppercase))
1362 (not (eq name '->lowercase))
1363 (not (eq name '->titlecase))
1364 (not (eq name '->canonical))
1365 (not (eq name '->Bopomofo))
1366 (not (eq name '->mistakable))
1367 (not (eq name '->ideographic-variants))
1368 (null (get-char-attribute
1369 char (intern (format "%s*sources" name))))
1370 (not (string-match "\\*sources$" (symbol-name name)))
1371 (null (get-char-attribute
1372 char (intern (format "%s*note" name))))
1373 (not (string-match "\\*note$" (symbol-name name)))
1374 (or (eq name '<-identical)
1375 (eq name '<-uppercase)
1376 (eq name '<-lowercase)
1377 (eq name '<-titlecase)
1378 (eq name '<-canonical)
1379 (eq name '<-ideographic-variants)
1380 ;; (eq name '<-synonyms)
1381 (string-match "^<-synonyms" (symbol-name name))
1382 (eq name '<-mistakable)
1383 (when (string-match "^->" (symbol-name name))
1385 ((string-match "^->fullwidth" (symbol-name name))
1386 (not (and (consp value)
1387 (characterp (car value))
1389 (car value) '=ucs 'defined-only)))
1394 ((or (eq name 'ideographic-structure)
1395 (eq name 'ideographic-combination)
1396 ;; (eq name 'ideographic-)
1397 (eq name '=decomposition)
1398 (char-feature-base-name= '=decomposition name)
1399 (char-feature-base-name= '=>decomposition name)
1400 ;; (string-match "^=>*decomposition\\(@[^*]+\\)?$"
1401 ;; (symbol-name name))
1402 (string-match "^\\(->\\|<-\\)[^*]*$" (symbol-name name))
1403 (string-match "^\\(->\\|<-\\)[^*]*\\*sources$"
1406 (char-db-insert-relation-feature char name value
1409 ;; ((memq name '(ideograph=
1410 ;; original-ideograph-of
1411 ;; ancient-ideograph-of
1412 ;; vulgar-ideograph-of
1413 ;; wrong-ideograph-of
1414 ;; ;; simplified-ideograph-of
1415 ;; ideographic-variants
1416 ;; ;; ideographic-different-form-of
1418 ;; (insert (format "(%-18s%s " name line-breaking))
1419 ;; (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1421 ;; (while (consp value)
1422 ;; (setq cell (car value))
1423 ;; (if (and (consp cell)
1424 ;; (consp (car cell)))
1428 ;; (char-db-insert-alist cell readable)
1429 ;; (setq separator lbs))
1431 ;; (insert separator))
1432 ;; (insert (prin1-to-string cell))
1433 ;; (setq separator " "))
1434 ;; (setq value (cdr value)))
1436 ;; (insert line-breaking))
1438 (insert (format "(%-18s " name))
1439 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1441 (while (consp value)
1442 (setq cell (car value))
1443 (if (and (consp cell)
1445 (setq ret (condition-case nil
1453 (setq key (car (car rest)))
1454 (if (find-charset key)
1455 (setq cal (cons key cal))
1456 (setq al (cons key al)))
1457 (setq rest (cdr rest)))
1460 (insert-char-attributes ret
1464 (setq separator lbs))
1465 (setq ret (prin1-to-string cell))
1467 (if (< (+ (current-column)
1474 (setq separator " "))
1475 (setq value (cdr value)))
1477 (insert line-breaking))
1479 (insert (format "(%-18s" name))
1480 (setq ret (prin1-to-string value))
1481 (unless (< (+ (current-column)
1485 (insert line-breaking))
1486 (insert " . " ret ")" line-breaking)
1487 ;; (insert (format "(%-18s . %S)%s"
1492 (setq attributes (cdr attributes)))
1495 (defun insert-char-data (char &optional readable
1498 (narrow-to-region (point)(point))
1499 (insert "(define-char
1501 (insert-char-attributes char readable attributes)
1503 (goto-char (point-min))
1504 (while (re-search-forward "[ \t]+$" nil t)
1507 (goto-char (point-min))
1508 (while (re-search-forward "[ \t][ \t][ \t]*" nil t)
1509 (let ((column (current-column))
1510 (indent-tabs-mode t))
1511 (delete-region (match-beginning 0) (point))
1512 (indent-to column)))
1513 (goto-char (point-max))
1514 ;; (tabify (point-min)(point-max))
1517 (defun insert-char-data-with-variant (char &optional printable
1519 script excluded-script)
1520 (insert-char-data char printable)
1521 (let ((variants (char-variants char))
1524 (setq variants (sort variants #'<))
1525 (setq rest variants)
1526 (setq variants (cons char variants))
1528 (setq variant (car rest))
1529 (unless (get-char-attribute variant '<-subsumptive)
1530 (if (and (or (null script)
1531 (null (setq vs (get-char-attribute variant 'script)))
1533 (or (null excluded-script)
1534 (null (setq vs (get-char-attribute variant 'script)))
1535 (not (memq excluded-script vs))))
1536 (unless (and no-ucs-unified (get-char-attribute variant '=ucs))
1537 (insert-char-data variant printable)
1538 (if (setq ret (char-variants variant))
1540 (or (memq (car ret) variants)
1541 ;; (get-char-attribute (car ret) '<-subsumptive)
1542 (setq rest (nconc rest (list (car ret)))))
1543 (setq ret (cdr ret)))))))
1544 (setq rest (cdr rest)))))
1546 (defun insert-char-range-data (min max &optional script excluded-script)
1549 (while (<= code max)
1550 (setq char (decode-char '=ucs code))
1551 (if (encode-char char '=ucs 'defined-only)
1552 (insert-char-data-with-variant char nil 'no-ucs-unified
1553 script excluded-script))
1554 (setq code (1+ code)))))
1556 (defun write-char-range-data-to-file (min max file
1557 &optional script excluded-script)
1558 (let ((coding-system-for-write char-db-file-coding-system))
1560 (insert (format ";; -*- coding: %s -*-\n"
1561 char-db-file-coding-system))
1562 (insert-char-range-data min max script excluded-script)
1563 (write-region (point-min)(point-max) file))))
1565 (defvar what-character-original-window-configuration)
1568 (defun what-char-definition (char)
1569 (interactive (list (char-after)))
1570 (let ((buf (get-buffer-create "*Character Description*"))
1571 (the-buf (current-buffer))
1572 (win-conf (current-window-configuration)))
1574 (make-local-variable 'what-character-original-window-configuration)
1575 (setq what-character-original-window-configuration win-conf)
1576 (setq buffer-read-only nil)
1580 (insert-char-data-with-variant char 'printable)
1581 (unless (char-attribute-alist char)
1582 (insert (format ";; = %c\n"
1583 (let* ((rest (split-char char))
1587 (setq code (logior (lsh code 8)
1589 (decode-char ccs code)))))
1590 ;; (char-db-update-comment)
1591 (set-buffer-modified-p nil)
1592 (view-mode the-buf (lambda (buf)
1593 (set-window-configuration
1594 what-character-original-window-configuration)
1596 (goto-char (point-min)))
1598 (set-window-configuration
1599 what-character-original-window-configuration)
1600 (signal (car err) (cdr err)))))))
1606 (provide 'char-db-util)
1608 ;;; char-db-util.el ends here