;;; char-db-util.el --- Character Database utility -*- coding: utf-8-er; -*-
;; Copyright (C) 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006,
-;; 2007, 2008, 2009 MORIOKA Tomohiko.
+;; 2007, 2008, 2009, 2010 MORIOKA Tomohiko.
;; Author: MORIOKA Tomohiko <tomo@kanji.zinbun.kyoto-u.ac.jp>
;; Keywords: CHISE, Character Database, ISO/IEC 10646, UCS, Unicode, MULE.
;;; Code:
-(require 'alist)
+(require 'chise-subr)
+(require 'ideograph-subr)
(defconst unidata-normative-category-alist
'(("Lu" letter uppercase)
("So" symbol other)
))
-(defconst ideographic-radicals
- (let ((v (make-vector 215 nil))
- (i 1))
- (while (< i 215)
- (aset v i (decode-char '=ucs (+ #x2EFF i)))
- (setq i (1+ i)))
- v))
-
-(defun ideographic-radical (number)
- (aref ideographic-radicals number))
-
(defconst shuowen-radicals
[?一 ?上 ?示 ?三 ?王 ?玉 ?玨 ?气 ?士 ?丨 ; 010
?屮 ?艸 ?蓐 ?茻 ?小 ?八 ?釆 ?半 ?牛 ?犛 ; 020
(defvar char-db-ignored-attributes '(ideographic-products))
-(defun char-attribute-name< (ka kb)
- (cond
- ((eq '->denotational kb)
- t)
- ((eq '->subsumptive kb)
- (not (eq '->denotational ka)))
- ((eq '->denotational ka)
- nil)
- ((eq '->subsumptive ka)
- nil)
- ((and (symbolp ka)
- (string-match "^->" (symbol-name ka)))
- (cond ((and (symbolp kb)
- (string-match "^->" (symbol-name kb)))
- (string< (symbol-name ka)
- (symbol-name kb))
- ))
- )
- ((and (symbolp kb)
- (string-match "^->" (symbol-name kb)))
- t)
- ((and (symbolp ka)
- (string-match "^<-" (symbol-name ka)))
- (cond ((symbolp kb)
- (cond ((string-match "^<-" (symbol-name kb))
- (string< (symbol-name ka)
- (symbol-name kb))
- )
- ;; ((string-match "^->" (symbol-name kb))
- ;; t)
- )))
- )
- ((and (symbolp kb)
- (string-match "^<-" (symbol-name kb)))
- t
- ;; (not (string-match "^->" (symbol-name ka)))
- )
- ((find-charset ka)
- (if (find-charset kb)
- (let (a-ir b-ir)
- (if (and (setq a-ir (charset-property ka 'iso-ir))
- (if (= a-ir 177)
- (if (= (charset-id ka) -177)
- t
- (setq a-ir nil))
- t))
- (if (and (setq b-ir (charset-property kb 'iso-ir))
- (if (= b-ir 177)
- (if (= (charset-id kb) -177)
- t
- (setq b-ir nil))
- t))
- (cond
- ((= a-ir b-ir)
- (< (charset-id ka)(charset-id kb))
- )
- ;; ((= a-ir 177)
- ;; t)
- ;; ((= b-ir 177)
- ;; nil)
- ((= (charset-dimension ka)
- (charset-dimension kb))
- (< a-ir b-ir)
- )
- ((> (charset-dimension ka)
- (charset-dimension kb))
- ))
- t)
- (if (and (setq b-ir (charset-property kb 'iso-ir))
- (if (= b-ir 177)
- (if (= (charset-id kb) -177)
- t
- (setq b-ir nil))
- t))
- nil
- (< (charset-id ka)(charset-id kb)))))
- nil)
- )
- ((find-charset kb))
- ((symbolp ka)
- (cond ((symbolp kb)
- (string< (symbol-name ka)
- (symbol-name kb)))
- (t)))
- ((symbolp kb)
- nil)))
-
(defvar char-db-coded-charset-priority-list
'(ascii
control-1
chinese-cns11643-5
chinese-cns11643-6
chinese-cns11643-7
- =jis-x0213-1-2000
- =jis-x0213-2-2000
+ =jis-x0213-1
+ =jis-x0213-1@2000
+ =jis-x0213-1@2004
+ =jis-x0213-2
korean-ksc5601
chinese-isoir165
katakana-jisx0201
ethiopic-ucs
=big5-cdp
=gt
+ =>>gt
+ =>gt
ideograph-daikanwa-2
ideograph-daikanwa
=cbeta
=gt-k
=ucs@iso
=ucs@unicode
+ =>>ucs@unicode
+ =>>jis-x0208
+ =>>jis-x0213-1
+ =>>jis-x0213-1@2000
+ =>>jis-x0213-1@2004
+ =>>jis-x0213-2
+ =>>jis-x0208@1978
+ =>jis-x0208
+ =>jis-x0208@1997
+ =>jis-x0213-1
+ =>jis-x0213-1@2000
+ =>jis-x0213-1@2004
+ =>jis-x0213-2
=big5
=big5-eten
- =jis-x0208@1997
=zinbun-oracle
+ =>zinbun-oracle
=ruimoku-v6
- =jef-china3))
+ =jef-china3
+ =shinjigen))
+
+
+;;; @ char-db formatters
+;;;
(defun char-db-make-char-spec (char)
(let (ret char-spec)
;; =gt-k
=jis-x0208@1997
))
- ;; (string-match "=ucs@" (symbol-name ccs))
- )
+ (string-match "=ucs@" (symbol-name ccs)))
(setq ccs (charset-name ccs))
(null (assq ccs char-spec))
(setq ret (encode-char char ccs 'defined-only)))
"(%-18s . %04d)\t; %c")
((or (memq name '(=daikanwa
=daikanwa@rev1 =daikanwa@rev2
- =gt =gt-k =cbeta =zinbun-oracle))
+ =gt =>>gt =>gt =gt-k =cbeta
+ =zinbun-oracle =>zinbun-oracle))
(string-match "^=adobe-" (symbol-name name)))
"(%-18s . %05d)\t; %c")
((eq name 'mojikyo)
what-character-original-window-configuration)
(signal (car err) (cdr err)))))))
+
+;;; @ end
+;;;
+
(provide 'char-db-util)
;;; char-db-util.el ends here