1 ;;; char-db-util.el --- Character Database utility -*- coding: utf-8-er; -*-
3 ;; Copyright (C) 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006,
4 ;; 2007, 2008, 2009, 2010, 2011 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 ?旨 ?曰 ?乃 ?丂 ?可 ?兮 ?号 ?亏 ?喜 ?壴 ; 160
83 ?鼓 ?豈 ?豆 ?豊 ?豐 ?䖒 ?虍 ?虎 ?虤 ?皿 ; 170
84 ?𠙴 ?去 ?血 ?丶 ?丹 ?青 ?井 ?皀 ?鬯 ?食 ; 180
85 ?亼 ?會 ?倉 ?入 ?缶 ?矢 ?高 ?冂 ?𩫏 ?京 ; 190
86 ?亯 ?𣆪 ?畗 ?㐭 ?嗇 ?來 ?麥 ?夊 ?舛 ?䑞 ; 200
87 ?韋 ?弟 ?夂 ?久 ?桀 ?木 ?東 ?林 ?才 ?叒 ; 210
88 ?之 ?帀 ?出 ?𣎵 ?生 ?乇 ?𠂹 ?𠌶 ?華 ?𥝌 ; 220
89 ?稽 ?巢 ?桼 ?束 ?㯻 ?囗 ?員 ?貝 ?邑 ?𨛜 ; 230
90 ?日 ?旦 ?倝 ?㫃 ?冥 ?晶 ?月 ?有 ?明 ?囧 ; 240
91 ?夕 ?多 ?毌 ?𢎘 ?𣐺 ?卣 ?齊 ?朿 ?片 ?鼎 ; 250
92 ?克 ?彔 ?禾 ?秝 ?黍 ?香 ?米 ?毇 ?臼 ?凶 ; 260
93 ?𣎳 ?林 ?麻 ?尗 ?耑 ?韭 ?瓜 ?瓠 ?宀 ?宮 ; 270
94 ?呂 ?穴 ?㝱 ?𤕫 ?冖 ?𠔼 ?冃 ?㒳 ?网 ?襾 ; 280
95 ?巾 ?巿 ?帛 ?白 ?㡀 ?黹 ?人 ?𠤎 ?匕 ?从 ; 290
98 (defun shuowen-radical (number)
99 (aref shuowen-radicals (1- number)))
101 (defvar char-db-file-coding-system 'utf-8-mcs-er)
103 (defvar char-db-ignored-attributes '(ideographic-products))
105 (defvar char-db-coded-charset-priority-list
227 ;;; @ char-db formatters
230 (defun char-db-make-char-spec (char)
232 (cond ((characterp char)
233 (cond ((and (setq ret (encode-char char '=ucs 'defined-only))
234 (not (and (<= #xE000 ret)(<= ret #xF8FF))))
235 (setq char-spec (list (cons '=ucs ret)))
236 (cond ((setq ret (get-char-attribute char 'name))
237 (setq char-spec (cons (cons 'name ret) char-spec))
239 ((setq ret (get-char-attribute char 'name*))
240 (setq char-spec (cons (cons 'name* ret) char-spec))
245 (let ((rest char-db-coded-charset-priority-list)
248 (setq ccs (charset-name
249 (find-charset (car rest))))
251 (encode-char char ccs
253 (throw 'tag (cons ccs ret)))
254 (setq rest (cdr rest))))))
255 (setq char-spec (list ret))
256 (dolist (ccs (delq (car ret) (charset-list)))
257 (if (and (or (charset-iso-final-char ccs)
264 (string-match "=ucs@" (symbol-name ccs)))
265 (setq ccs (charset-name ccs))
266 (null (assq ccs char-spec))
267 (setq ret (encode-char char ccs 'defined-only)))
268 (setq char-spec (cons (cons ccs ret) char-spec))))
270 (setq char-spec (split-char char)))
271 (cond ((setq ret (get-char-attribute char 'name))
272 (setq char-spec (cons (cons 'name ret) char-spec))
274 ((setq ret (get-char-attribute char 'name*))
275 (setq char-spec (cons (cons 'name* ret) char-spec))
278 ((setq ret (get-char-attribute
279 char 'ideographic-combination))
281 (cons (cons 'ideographic-combination ret)
288 (defun char-db-insert-char-spec (char &optional readable column
291 (setq column (current-column)))
292 (let (char-spec temp-char)
293 (setq char-spec (char-db-make-char-spec char))
294 (unless (or (characterp char) ; char
296 (setq char (find-char char-spec))
298 ;; define temporary character
299 ;; Current implementation is dirty.
300 (setq temp-char (define-char (cons '(ideograph-daikanwa . 0)
302 (remove-char-attribute temp-char 'ideograph-daikanwa)
303 (setq char temp-char))
304 (insert-char-attributes char
306 (union (mapcar #'car char-spec)
310 ;; undefine temporary character
311 ;; Current implementation is dirty.
312 (setq char-spec (char-attribute-alist temp-char))
314 (remove-char-attribute temp-char (car (car char-spec)))
315 (setq char-spec (cdr char-spec))))))
317 (defun char-db-insert-alist (alist &optional readable column)
319 (setq column (current-column)))
321 (concat "\n" (make-string (1+ column) ?\ )))
325 lbs cell rest separator)
328 (setq name (car (car alist))
329 value (cdr (car alist)))
330 (cond ((eq name 'char)
332 (if (setq ret (condition-case nil
340 (setq key (car (car value)))
341 ;; (if (find-charset key)
342 ;; (setq cal (cons key cal))
343 (setq al (cons key al))
345 (setq value (cdr value)))
346 (insert-char-attributes ret
350 (insert (prin1-to-string value)))
352 (insert line-breaking))
354 (insert (format "(%-18s " name))
355 (setq lbs (concat "\n" (make-string (current-column) ?\ )))
357 (setq cell (car value))
358 (if (and (consp cell)
360 (setq ret (condition-case nil
370 (setq key (car (car rest)))
371 ;; (if (find-charset key)
372 ;; (setq cal (cons key cal))
373 (setq al (cons key al))
375 (setq rest (cdr rest)))
378 (insert-char-attributes ret
382 (setq separator lbs))
385 (insert (prin1-to-string cell))
386 (setq separator " "))
387 (setq value (cdr value)))
389 (insert line-breaking))
391 (insert (format "(%-18s . %S)%s"
394 (setq alist (cdr alist))))
397 (defun char-db-insert-char-reference (plist &optional readable column)
399 (setq column (current-column)))
401 (concat "\n" (make-string (1+ column) ?\ )))
406 (setq name (pop plist))
407 (setq value (pop plist))
408 (cond ((eq name :char)
411 (cond ((numberp value)
412 (setq value (decode-char '=ucs value)))
414 ;; (setq value (or (find-char value)
417 (char-db-insert-char-spec value readable)
418 (insert line-breaking)
421 (insert (format "%s%s\t%d ; %c%s"
424 (ideographic-radical value)
428 (insert (format "%s%s\t%S" separator name value))
429 (setq separator line-breaking)))
433 (defun char-db-decode-isolated-char (ccs code-point)
436 (cond ((eq ccs 'arabic-iso8859-6)
437 (decode-char ccs code-point))
438 ((and (memq ccs '(=gt-pj-1
449 (setq ret (decode-char ccs code-point))
450 (setq ret (encode-char ret '=gt 'defined-only)))
451 (decode-builtin-char '=gt ret))
453 (decode-builtin-char ccs code-point))))
454 (cond ((and (<= 0 (char-int ret))
455 (<= (char-int ret) #x1F))
456 (decode-char '=ucs (+ #x2400 (char-int ret))))
457 ((= (char-int ret) #x7F)
461 (defvar char-db-convert-obsolete-format t)
463 (defun char-db-insert-ccs-feature (name value line-breaking)
466 (cond ((memq name '(=shinjigen
468 =shinjigen@rev =shinjigen/+p@rev
470 "(%-18s . %04d)\t; %c")
471 ((eq name '=shinjigen@1ed/24pr)
472 "(%-18s . %04d)\t; %c")
473 ((or (memq name '(=daikanwa =>>daikanwa =>daikanwa
474 =daikanwa@rev1 =daikanwa@rev2
475 =daikanwa/+p =daikanwa/+2p
476 =gt =>>>gt =>>gt =>gt
480 =zinbun-oracle =>zinbun-oracle))
481 (string-match "^=adobe-" (symbol-name name)))
482 "(%-18s . %05d)\t; %c")
483 ((memq name '(=hanyo-denshi/ks =>>hanyo-denshi/ks mojikyo))
484 "(%-18s . %06d)\t; %c")
485 ((>= (charset-dimension name) 2)
486 "(%-18s . #x%04X)\t; %c")
488 "(%-18s . #x%02X)\t; %c"))
490 (if (= (charset-iso-graphic-plane name) 1)
492 (cond ((= (charset-dimension name) 1)
494 ((= (charset-dimension name) 2)
496 ((= (charset-dimension name) 3)
500 (char-db-decode-isolated-char name value)))
501 (if (and (= (charset-chars name) 94)
502 (= (charset-dimension name) 2))
503 (insert (format " [%02d-%02d]"
504 (- (lsh value -8) 32)
505 (- (logand value 255) 32))))
506 (insert line-breaking))
508 (defun char-db-insert-relation-feature (char name value line-breaking
510 (insert (format "(%-18s%s " name line-breaking))
511 (let ((lbs (concat "\n" (make-string (current-column) ?\ )))
512 separator cell sources required-features
515 (setq cell (car value))
517 (setq cell (decode-char '=ucs cell)))
519 ((eq name '->subsumptive)
520 (when (or (not (some (lambda (atr)
521 (get-char-attribute cell atr))
522 char-db-ignored-attributes))
524 (encode-char cell ccs 'defined-only))
528 (let ((char-db-ignored-attributes
530 char-db-ignored-attributes)))
531 (insert-char-attributes cell readable nil nil 'for-sub-node))
532 (setq separator lbs))
537 char (intern (format "%s*sources" name))))
538 (setq required-features nil)
539 (dolist (source sources)
543 shinjigen shinjigen@1ed shinjigen@rev))
544 (setq required-features
545 (union required-features
556 (setq required-features
557 (union required-features
562 ((find-charset (setq ret (intern (format "=%s" source))))
563 (setq required-features
564 (cons ret required-features)))
565 (t (setq required-features
566 (cons source required-features)))))
567 (cond ((string-match "@JP" (symbol-name name))
568 (setq required-features
569 (union required-features
577 ((string-match "@CN" (symbol-name name))
578 (setq required-features
579 (union required-features
586 (insert (format "%S" cell))
587 (char-db-insert-char-spec cell readable
590 (setq separator lbs))
594 (if (consp (car cell))
595 (char-db-insert-char-spec cell readable)
596 (char-db-insert-char-reference cell readable))
597 (setq separator lbs))
601 (insert (prin1-to-string cell))
602 (setq separator " ")))
603 (setq value (cdr value)))
605 (insert line-breaking)))
607 (defun insert-char-attributes (char &optional readable attributes column
610 (setq column (current-column)))
611 (let (name value ; has-long-ccs-name
615 (concat "\n" (make-string (1+ column) ?\ )))
616 lbs cell separator ret
618 dest-ccss ; sources required-features
623 (if (consp attributes)
625 (dolist (name attributes)
626 (unless (memq name char-db-ignored-attributes)
627 (if (find-charset name)
631 (dolist (name (char-attribute-list))
632 (unless (memq name char-db-ignored-attributes)
633 (if (find-charset name)
637 #'char-attribute-name<)))
639 (when (memq '<-subsumptive attributes)
640 (when (or readable (not for-sub-node))
641 (when (setq value (get-char-attribute char '<-subsumptive))
642 (char-db-insert-relation-feature char '<-subsumptive value
645 (setq attributes (delq '<-subsumptive attributes)))
646 (when (and (memq '<-denotational attributes)
647 (setq value (get-char-attribute char '<-denotational)))
648 (char-db-insert-relation-feature char '<-denotational value
651 (setq attributes (delq '<-denotational attributes)))
652 (when (and (memq 'name attributes)
653 (setq value (get-char-attribute char 'name)))
655 (if (> (+ (current-column) (length value)) 48)
658 value line-breaking))
659 (setq attributes (delq 'name attributes))
661 (when (and (memq 'name* attributes)
662 (setq value (get-char-attribute char 'name*)))
664 (if (> (+ (current-column) (length value)) 48)
667 value line-breaking))
668 (setq attributes (delq 'name* attributes))
670 (when (and (memq 'script attributes)
671 (setq value (get-char-attribute char 'script)))
672 (insert (format "(script\t\t%s)%s"
673 (mapconcat (function prin1-to-string)
676 (setq attributes (delq 'script attributes))
678 (dolist (name '(=>ucs =>ucs*))
679 (when (and (memq name attributes)
680 (setq value (get-char-attribute char name)))
681 (insert (format "(%-18s . #x%04X)\t; %c%s"
682 name value (decode-char '=ucs value)
684 (setq attributes (delq name attributes))))
685 (dolist (name '(=>ucs@gb =>ucs@big5))
686 (when (and (memq name attributes)
687 (setq value (get-char-attribute char name)))
688 (insert (format "(%-18s . #x%04X)\t; %c%s"
693 (symbol-name name) 2)))
696 (setq attributes (delq name attributes))
698 ;; (dolist (name '(=>daikanwa))
699 ;; (when (and (memq name attributes)
700 ;; (setq value (get-char-attribute char name)))
702 ;; (if (integerp value)
703 ;; (format "(%-18s . %05d)\t; %c%s"
704 ;; name value (decode-char '=daikanwa value)
706 ;; (format "(%-18s %s)\t; %c%s"
708 ;; (mapconcat (function prin1-to-string)
710 ;; (char-representative-of-daikanwa char)
712 ;; (setq attributes (delq name attributes))))
713 (when (and (memq 'general-category attributes)
714 (setq value (get-char-attribute char 'general-category)))
716 "(general-category\t%s) ; %s%s"
717 (mapconcat (lambda (cell)
720 (cond ((rassoc value unidata-normative-category-alist)
721 "Normative Category")
722 ((rassoc value unidata-informative-category-alist)
723 "Informative Category")
727 (setq attributes (delq 'general-category attributes))
729 (when (and (memq 'bidi-category attributes)
730 (setq value (get-char-attribute char 'bidi-category)))
731 (insert (format "(bidi-category\t. %S)%s"
734 (setq attributes (delq 'bidi-category attributes))
736 (unless (or (not (memq 'mirrored attributes))
737 (eq (setq value (get-char-attribute char 'mirrored 'empty))
739 (insert (format "(mirrored\t\t. %S)%s"
742 (setq attributes (delq 'mirrored attributes))
745 ((and (memq 'decimal-digit-value attributes)
746 (setq value (get-char-attribute char 'decimal-digit-value)))
747 (insert (format "(decimal-digit-value . %S)%s"
750 (setq attributes (delq 'decimal-digit-value attributes))
751 (when (and (memq 'digit-value attributes)
752 (setq value (get-char-attribute char 'digit-value)))
753 (insert (format "(digit-value\t . %S)%s"
756 (setq attributes (delq 'digit-value attributes))
758 (when (and (memq 'numeric-value attributes)
759 (setq value (get-char-attribute char 'numeric-value)))
760 (insert (format "(numeric-value\t . %S)%s"
763 (setq attributes (delq 'numeric-value attributes))
767 (when (and (memq 'digit-value attributes)
768 (setq value (get-char-attribute char 'digit-value)))
769 (insert (format "(digit-value\t. %S)%s"
772 (setq attributes (delq 'digit-value attributes))
774 (when (and (memq 'numeric-value attributes)
775 (setq value (get-char-attribute char 'numeric-value)))
776 (insert (format "(numeric-value\t. %S)%s"
779 (setq attributes (delq 'numeric-value attributes))
781 (when (and (memq 'iso-10646-comment attributes)
782 (setq value (get-char-attribute char 'iso-10646-comment)))
783 (insert (format "(iso-10646-comment\t. %S)%s"
786 (setq attributes (delq 'iso-10646-comment attributes))
788 (when (and (memq 'morohashi-daikanwa attributes)
789 (setq value (get-char-attribute char 'morohashi-daikanwa)))
790 (insert (format "(morohashi-daikanwa\t%s)%s"
791 (mapconcat (function prin1-to-string) value " ")
793 (setq attributes (delq 'morohashi-daikanwa attributes))
797 (when (and (memq 'ideographic-radical attributes)
798 (setq value (get-char-attribute char 'ideographic-radical)))
800 (insert (format "(ideographic-radical . %S)\t; %c%s"
802 (ideographic-radical radical)
804 (setq attributes (delq 'ideographic-radical attributes))
806 (when (and (memq 'shuowen-radical attributes)
807 (setq value (get-char-attribute char 'shuowen-radical)))
808 (insert (format "(shuowen-radical\t. %S)\t; %c%s"
810 (shuowen-radical value)
812 (setq attributes (delq 'shuowen-radical attributes))
817 char-db-feature-domains
819 (dolist (feature (char-attribute-list))
820 (setq feature (symbol-name feature))
822 "\\(radical\\|strokes\\)@\\([^@*]+\\)\\(\\*\\|$\\)"
824 (setq domain (intern (match-string 2 feature)))
825 (unless (memq domain dest)
826 (setq dest (cons domain dest)))))
827 (sort dest #'string<))))
828 (setq key (intern (format "%s@%s" 'ideographic-radical domain)))
829 (when (and (memq key attributes)
830 (setq value (get-char-attribute char key)))
832 (insert (format "(%s . %S)\t; %c%s"
835 (ideographic-radical radical)
837 (setq attributes (delq key attributes))
839 (setq key (intern (format "%s@%s" 'ideographic-strokes domain)))
840 (when (and (memq key attributes)
841 (setq value (get-char-attribute char key)))
843 (insert (format "(%s . %S)%s"
847 (setq attributes (delq key attributes))
849 (setq key (intern (format "%s@%s" 'total-strokes domain)))
850 (when (and (memq key attributes)
851 (setq value (get-char-attribute char key)))
852 (insert (format "(%s . %S)%s"
856 (setq attributes (delq key attributes))
858 (dolist (feature '(ideographic-radical
861 (setq key (intern (format "%s@%s*sources" feature domain)))
862 (when (and (memq key attributes)
863 (setq value (get-char-attribute char key)))
864 (insert (format "(%s%s" key line-breaking))
866 (insert (format " %s" cell)))
868 (insert line-breaking)
869 (setq attributes (delq key attributes))
872 (when (and (memq 'ideographic-strokes attributes)
873 (setq value (get-char-attribute char 'ideographic-strokes)))
875 (insert (format "(ideographic-strokes . %S)%s"
878 (setq attributes (delq 'ideographic-strokes attributes))
880 (when (and (memq 'kangxi-radical attributes)
881 (setq value (get-char-attribute char 'kangxi-radical)))
882 (unless (eq value radical)
883 (insert (format "(kangxi-radical\t . %S)\t; %c%s"
885 (ideographic-radical value)
888 (setq radical value)))
889 (setq attributes (delq 'kangxi-radical attributes))
891 (when (and (memq 'kangxi-strokes attributes)
892 (setq value (get-char-attribute char 'kangxi-strokes)))
893 (unless (eq value strokes)
894 (insert (format "(kangxi-strokes\t . %S)%s"
898 (setq strokes value)))
899 (setq attributes (delq 'kangxi-strokes attributes))
901 (when (and (memq 'japanese-radical attributes)
902 (setq value (get-char-attribute char 'japanese-radical)))
903 (unless (eq value radical)
904 (insert (format "(japanese-radical\t . %S)\t; %c%s"
906 (ideographic-radical value)
909 (setq radical value)))
910 (setq attributes (delq 'japanese-radical attributes))
912 (when (and (memq 'japanese-strokes attributes)
913 (setq value (get-char-attribute char 'japanese-strokes)))
914 (unless (eq value strokes)
915 (insert (format "(japanese-strokes\t . %S)%s"
919 (setq strokes value)))
920 (setq attributes (delq 'japanese-strokes attributes))
922 (when (and (memq 'cns-radical attributes)
923 (setq value (get-char-attribute char 'cns-radical)))
924 (insert (format "(cns-radical\t . %S)\t; %c%s"
926 (ideographic-radical value)
928 (setq attributes (delq 'cns-radical attributes))
930 (when (and (memq 'cns-strokes attributes)
931 (setq value (get-char-attribute char 'cns-strokes)))
932 (unless (eq value strokes)
933 (insert (format "(cns-strokes\t . %S)%s"
937 (setq strokes value)))
938 (setq attributes (delq 'cns-strokes attributes))
940 (when (and (memq 'shinjigen-1-radical attributes)
941 (setq value (get-char-attribute char 'shinjigen-1-radical)))
942 (unless (eq value radical)
943 (insert (format "(shinjigen-1-radical . %S)\t; %c%s"
945 (ideographic-radical value)
948 (setq radical value)))
949 (setq attributes (delq 'shinjigen-1-radical attributes))
951 (when (and (memq 'ideographic- attributes)
952 (setq value (get-char-attribute char 'ideographic-)))
953 (insert "(ideographic- ")
954 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
957 (setq cell (car value))
959 (setq cell (decode-char '=ucs cell)))
960 (cond ((characterp cell)
964 (insert (format "%S" cell))
965 (char-db-insert-char-spec cell readable))
966 (setq separator lbs))
970 (if (consp (car cell))
971 (char-db-insert-char-spec cell readable)
972 (char-db-insert-char-reference cell readable))
973 (setq separator lbs))
977 (insert (prin1-to-string cell))
978 (setq separator " ")))
979 (setq value (cdr value)))
981 (insert line-breaking)
982 (setq attributes (delq 'ideographic- attributes)))
983 (when (and (memq 'total-strokes attributes)
984 (setq value (get-char-attribute char 'total-strokes)))
985 (insert (format "(total-strokes . %S)%s"
988 (setq attributes (delq 'total-strokes attributes))
990 (when (and (memq '->ideograph attributes)
991 (setq value (get-char-attribute char '->ideograph)))
992 (insert (format "(->ideograph\t%s)%s"
993 (mapconcat (lambda (code)
994 (cond ((symbolp code)
997 (format "#x%04X" code))
1000 line-breaking code))))
1003 (setq attributes (delq '->ideograph attributes))
1005 ;; (when (and (memq '->decomposition attributes)
1006 ;; (setq value (get-char-attribute char '->decomposition)))
1007 ;; (insert (format "(->decomposition\t%s)%s"
1008 ;; (mapconcat (lambda (code)
1009 ;; (cond ((symbolp code)
1010 ;; (symbol-name code))
1011 ;; ((characterp code)
1013 ;; (format "%S" code)
1018 ;; (format "#x%04X" code))
1020 ;; (format "%s%S" line-breaking code))))
1023 ;; (setq attributes (delq '->decomposition attributes))
1025 (if (equal (get-char-attribute char '->titlecase)
1026 (get-char-attribute char '->uppercase))
1027 (setq attributes (delq '->titlecase attributes)))
1028 (when (and (memq '->mojikyo attributes)
1029 (setq value (get-char-attribute char '->mojikyo)))
1030 (insert (format "(->mojikyo\t\t. %06d)\t; %c%s"
1031 value (decode-char 'mojikyo value)
1033 (setq attributes (delq '->mojikyo attributes))
1035 (when (and (memq 'hanyu-dazidian-vol attributes)
1036 (setq value (get-char-attribute char 'hanyu-dazidian-vol)))
1037 (insert (format "(hanyu-dazidian-vol . %d)%s"
1038 value line-breaking))
1039 (setq attributes (delq 'hanyu-dazidian-vol attributes))
1041 (when (and (memq 'hanyu-dazidian-page attributes)
1042 (setq value (get-char-attribute char 'hanyu-dazidian-page)))
1043 (insert (format "(hanyu-dazidian-page . %d)%s"
1044 value line-breaking))
1045 (setq attributes (delq 'hanyu-dazidian-page attributes))
1047 (when (and (memq 'hanyu-dazidian-char attributes)
1048 (setq value (get-char-attribute char 'hanyu-dazidian-char)))
1049 (insert (format "(hanyu-dazidian-char . %d)%s"
1050 value line-breaking))
1051 (setq attributes (delq 'hanyu-dazidian-char attributes))
1054 (dolist (ignored '(composition
1055 ->denotational <-subsumptive ->ucs-unified
1056 ->ideographic-component-forms))
1057 (setq attributes (delq ignored attributes))))
1059 (setq name (car attributes))
1060 (if (setq value (get-char-attribute char name))
1061 (cond ((setq ret (find-charset name))
1062 (setq name (charset-name ret))
1063 (if (and (not (memq name dest-ccss))
1065 (setq value (get-char-attribute char name))
1066 (setq dest-ccss (cons name dest-ccss))))
1067 (char-db-insert-ccs-feature name value line-breaking))
1069 ((string-match "^=>ucs@" (symbol-name name))
1070 (insert (format "(%-18s . #x%04X)\t; %c%s"
1071 name value (decode-char '=ucs value)
1074 ((eq name 'jisx0208-1978/4X)
1075 (insert (format "(%-18s . #x%04X)%s"
1081 (not (eq name '->subsumptive))
1082 (not (eq name '->uppercase))
1083 (not (eq name '->lowercase))
1084 (not (eq name '->titlecase))
1085 (not (eq name '->canonical))
1086 (not (eq name '->Bopomofo))
1087 (not (eq name '->mistakable))
1088 (not (eq name '->ideographic-variants))
1089 (null (get-char-attribute
1090 char (intern (format "%s*sources" name))))
1091 (not (string-match "\\*sources$" (symbol-name name)))
1092 (null (get-char-attribute
1093 char (intern (format "%s*note" name))))
1094 (not (string-match "\\*note$" (symbol-name name)))
1095 (or (eq name '<-identical)
1096 (eq name '<-uppercase)
1097 (eq name '<-lowercase)
1098 (eq name '<-titlecase)
1099 (eq name '<-canonical)
1100 (eq name '<-ideographic-variants)
1101 ;; (eq name '<-synonyms)
1102 (string-match "^<-synonyms" (symbol-name name))
1103 (eq name '<-mistakable)
1104 (when (string-match "^->" (symbol-name name))
1106 ((string-match "^->fullwidth" (symbol-name name))
1107 (not (and (consp value)
1108 (characterp (car value))
1110 (car value) '=ucs 'defined-only)))
1115 ((or (eq name 'ideographic-structure)
1116 (eq name 'ideographic-combination)
1117 (eq name 'ideographic-)
1118 (eq name '=decomposition)
1119 (char-feature-base-name= '=decomposition name)
1120 (char-feature-base-name= '=>decomposition name)
1121 ;; (string-match "^=>*decomposition\\(@[^*]+\\)?$"
1122 ;; (symbol-name name))
1123 (string-match "^\\(->\\|<-\\)[^*]*$" (symbol-name name))
1124 (string-match "^\\(->\\|<-\\)[^*]*\\*sources$"
1127 (char-db-insert-relation-feature char name value
1130 ((memq name '(ideograph=
1131 original-ideograph-of
1132 ancient-ideograph-of
1135 ;; simplified-ideograph-of
1136 ideographic-variants
1137 ;; ideographic-different-form-of
1139 (insert (format "(%-18s%s " name line-breaking))
1140 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1142 (while (consp value)
1143 (setq cell (car value))
1144 (if (and (consp cell)
1149 (char-db-insert-alist cell readable)
1150 (setq separator lbs))
1153 (insert (prin1-to-string cell))
1154 (setq separator " "))
1155 (setq value (cdr value)))
1157 (insert line-breaking))
1159 (insert (format "(%-18s " name))
1160 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
1162 (while (consp value)
1163 (setq cell (car value))
1164 (if (and (consp cell)
1166 (setq ret (condition-case nil
1174 (setq key (car (car rest)))
1175 (if (find-charset key)
1176 (setq cal (cons key cal))
1177 (setq al (cons key al)))
1178 (setq rest (cdr rest)))
1181 (insert-char-attributes ret
1185 (setq separator lbs))
1186 (setq ret (prin1-to-string cell))
1188 (if (< (+ (current-column)
1195 (setq separator " "))
1196 (setq value (cdr value)))
1198 (insert line-breaking))
1200 (insert (format "(%-18s" name))
1201 (setq ret (prin1-to-string value))
1202 (unless (< (+ (current-column)
1206 (insert line-breaking))
1207 (insert " . " ret ")" line-breaking)
1208 ;; (insert (format "(%-18s . %S)%s"
1213 (setq attributes (cdr attributes)))
1216 (defun insert-char-data (char &optional readable
1219 (narrow-to-region (point)(point))
1220 (insert "(define-char
1222 (insert-char-attributes char readable attributes)
1224 (goto-char (point-min))
1225 (while (re-search-forward "[ \t]+$" nil t)
1228 (goto-char (point-min))
1229 (while (re-search-forward "[ \t][ \t][ \t]*" nil t)
1230 (let ((column (current-column))
1231 (indent-tabs-mode t))
1232 (delete-region (match-beginning 0) (point))
1233 (indent-to column)))
1234 (goto-char (point-max))
1235 ;; (tabify (point-min)(point-max))
1238 (defun insert-char-data-with-variant (char &optional printable
1240 script excluded-script)
1241 (insert-char-data char printable)
1242 (let ((variants (char-variants char))
1245 (setq variants (sort variants #'<))
1246 (setq rest variants)
1247 (setq variants (cons char variants))
1249 (setq variant (car rest))
1250 (unless (get-char-attribute variant '<-subsumptive)
1251 (if (and (or (null script)
1252 (null (setq vs (get-char-attribute variant 'script)))
1254 (or (null excluded-script)
1255 (null (setq vs (get-char-attribute variant 'script)))
1256 (not (memq excluded-script vs))))
1257 (unless (and no-ucs-unified (get-char-attribute variant '=ucs))
1258 (insert-char-data variant printable)
1259 (if (setq ret (char-variants variant))
1261 (or (memq (car ret) variants)
1262 ;; (get-char-attribute (car ret) '<-subsumptive)
1263 (setq rest (nconc rest (list (car ret)))))
1264 (setq ret (cdr ret)))))))
1265 (setq rest (cdr rest)))))
1267 (defun insert-char-range-data (min max &optional script excluded-script)
1270 (while (<= code max)
1271 (setq char (decode-char '=ucs code))
1272 (if (encode-char char '=ucs 'defined-only)
1273 (insert-char-data-with-variant char nil 'no-ucs-unified
1274 script excluded-script))
1275 (setq code (1+ code)))))
1277 (defun write-char-range-data-to-file (min max file
1278 &optional script excluded-script)
1279 (let ((coding-system-for-write char-db-file-coding-system))
1281 (insert (format ";; -*- coding: %s -*-\n"
1282 char-db-file-coding-system))
1283 (insert-char-range-data min max script excluded-script)
1284 (write-region (point-min)(point-max) file))))
1286 (defvar what-character-original-window-configuration)
1289 (defun what-char-definition (char)
1290 (interactive (list (char-after)))
1291 (let ((buf (get-buffer-create "*Character Description*"))
1292 (the-buf (current-buffer))
1293 (win-conf (current-window-configuration)))
1295 (make-local-variable 'what-character-original-window-configuration)
1296 (setq what-character-original-window-configuration win-conf)
1297 (setq buffer-read-only nil)
1301 (insert-char-data-with-variant char 'printable)
1302 (unless (char-attribute-alist char)
1303 (insert (format ";; = %c\n"
1304 (let* ((rest (split-char char))
1308 (setq code (logior (lsh code 8)
1310 (decode-char ccs code)))))
1311 ;; (char-db-update-comment)
1312 (set-buffer-modified-p nil)
1313 (view-mode the-buf (lambda (buf)
1314 (set-window-configuration
1315 what-character-original-window-configuration)
1317 (goto-char (point-min)))
1319 (set-window-configuration
1320 what-character-original-window-configuration)
1321 (signal (car err) (cdr err)))))))
1327 (provide 'char-db-util)
1329 ;;; char-db-util.el ends here