X-Git-Url: http://git.chise.org/gitweb/?a=blobdiff_plain;f=lisp%2Futf-2000%2Fchar-db-util.el;h=e883475ce973e317e8b43043af8684ef050bf14e;hb=c1ba59b4860fd9193e3ed161858d83eb5d400c15;hp=a2c5529183d737c1ac3734f4b6ea444575382fe5;hpb=7bd395851f58b78b96549d13aa69bf2a8ef40b9d;p=chise%2Fxemacs-chise.git- diff --git a/lisp/utf-2000/char-db-util.el b/lisp/utf-2000/char-db-util.el index a2c5529..e883475 100644 --- a/lisp/utf-2000/char-db-util.el +++ b/lisp/utf-2000/char-db-util.el @@ -1,7 +1,7 @@ ;;; char-db-util.el --- Character Database utility -*- coding: utf-8-er; -*- ;; Copyright (C) 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, -;; 2007, 2008 MORIOKA Tomohiko. +;; 2007, 2008, 2009, 2010 MORIOKA Tomohiko. ;; Author: MORIOKA Tomohiko ;; Keywords: CHISE, Character Database, ISO/IEC 10646, UCS, Unicode, MULE. @@ -25,7 +25,8 @@ ;;; Code: -(require 'alist) +(require 'chise-subr) +(require 'ideograph-subr) (defconst unidata-normative-category-alist '(("Lu" letter uppercase) @@ -62,17 +63,6 @@ ("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 @@ -110,76 +100,8 @@ (defvar char-db-file-coding-system 'utf-8-mcs-er) -(defvar char-db-feature-domains - '(ucs ucs/compat daikanwa cns gt jis jis/alt jis/a jis/b - jis-x0212 jis-x0213 cdp shinjigen misc unknown)) - (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) - (if (<= (charset-id ka) 1) - (if (<= (charset-id kb) 1) - (cond - ((= (charset-dimension ka) - (charset-dimension kb)) - (> (charset-id ka)(charset-id kb))) - (t - (> (charset-dimension ka) - (charset-dimension kb)) - )) - t) - (if (<= (charset-id kb) 1) - nil - (< (charset-id ka)(charset-id kb)))) - nil)) - ((find-charset kb) - t) - ((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 @@ -205,8 +127,10 @@ 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 @@ -219,6 +143,7 @@ ideograph-daikanwa-2 ideograph-daikanwa =cbeta + =gt-k ideograph-hanziku-1 ideograph-hanziku-2 ideograph-hanziku-3 @@ -231,15 +156,36 @@ ideograph-hanziku-10 ideograph-hanziku-11 ideograph-hanziku-12 - =gt-k =ucs@iso =ucs@unicode + =>>ucs@unicode + =>>gt + =>>jis-x0208 + =>>jis-x0213-1 + =>>jis-x0213-1@2000 + =>>jis-x0213-1@2004 + =>>jis-x0213-2 + =>>jis-x0208@1978 + =>>big5-cdp + =>>gt-k + =>jis-x0208 + =>jis-x0208@1997 + =>jis-x0213-1 + =>jis-x0213-1@2000 + =>jis-x0213-1@2004 + =>jis-x0213-2 + =>gt =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) @@ -274,7 +220,8 @@ =daikanwa@rev2 ;; =gt-k =jis-x0208@1997 - ))) + )) + (string-match "=ucs@" (symbol-name ccs))) (setq ccs (charset-name ccs)) (null (assq ccs char-spec)) (setq ret (encode-char char ccs 'defined-only))) @@ -287,6 +234,12 @@ ((setq ret (get-char-attribute char 'name*)) (setq char-spec (cons (cons 'name* ret) char-spec)) )) + ) + ((setq ret (get-char-attribute + char 'ideographic-combination)) + (setq char-spec + (cons (cons 'ideographic-combination ret) + char-spec)) )) char-spec) ((consp char) @@ -469,14 +422,16 @@ (defun char-db-insert-ccs-feature (name value line-breaking) (insert (format - (cond ((memq name '(=shinjigen@1ed + (cond ((memq name '(=shinjigen + =shinjigen@1ed =shinjigen@rev =shinjigen/+p@rev)) "(%-18s . %04d)\t; %c") ((eq name '=shinjigen@1ed/24pr) "(%-18s . %04d)\t; %c") ((or (memq name '(=daikanwa =daikanwa@rev1 =daikanwa@rev2 - =gt =gt-k =cbeta =zinbun-oracle)) + =gt =>>gt =>gt =gt-k =>>gt-k =cbeta + =zinbun-oracle =>zinbun-oracle)) (string-match "^=adobe-" (symbol-name name))) "(%-18s . %05d)\t; %c") ((eq name 'mojikyo) @@ -537,7 +492,9 @@ (setq required-features nil) (dolist (source sources) (cond - ((memq source '(JP JP/Jouyou shinjigen@1ed shinjigen@rev)) + ((memq source '(JP + JP/Jouyou + shinjigen shinjigen@1ed shinjigen@rev)) (setq required-features (union required-features '(=jis-x0208 @@ -546,7 +503,8 @@ =jis-x0213-2-2000 =jis-x0212 =jis-x0208@1983 - =jis-x0208@1978)))) + =jis-x0208@1978 + =shinjigen)))) ((eq source 'CN) (setq required-features (union required-features @@ -1310,6 +1268,10 @@ what-character-original-window-configuration) (signal (car err) (cdr err))))))) + +;;; @ end +;;; + (provide 'char-db-util) ;;; char-db-util.el ends here