X-Git-Url: http://git.chise.org/gitweb/?a=blobdiff_plain;f=lisp%2Futf-2000%2Fchar-db-util.el;h=a86e3afedf02ff10fa7314d803928d138940730b;hb=297f928586d23ba4e0fc3c4d17b6c37885c3ba59;hp=b50c2ffb55cfff9a934f5801c3a6ba00189833a9;hpb=621d6bda0e5f8bc54c875f267d6e08892448b45a;p=chise%2Fxemacs-chise.git diff --git a/lisp/utf-2000/char-db-util.el b/lisp/utf-2000/char-db-util.el index b50c2ff..a86e3af 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, 2011 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 @@ -110,114 +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 (or (<= (charset-id ka) 1) - (and (charset-final ka) - (>= (charset-final ka) ?@))) - (if (or (<= (charset-id kb) 1) - (and (charset-final kb) - (>= (charset-final kb) ?@))) - (cond - ((= (charset-dimension ka) - (charset-dimension kb)) - (if (and (<= (charset-id ka) 1) - (<= (charset-id kb) 1)) - (> (charset-id ka)(charset-id kb)) - (if (and (charset-final ka) - (charset-final kb)) - (cond - ((= (charset-final ka)(charset-final kb)) - (if (<= (charset-id ka) 1) - (if (<= (charset-id kb) 1) - (> (charset-id ka)(charset-id kb)) - t) - (if (<= (charset-id kb) 1) - nil - (< (charset-id ka)(charset-id kb)))) - ) - ((< (charset-final ka)(charset-final kb)) - )) - (if (<= (charset-id ka) 1) - (if (<= (charset-id kb) 1) - (> (charset-id ka)(charset-id kb)) - t) - (if (<= (charset-id kb) 1) - nil - (cond ((and (charset-final ka) - (>= (charset-final ka) ?@)) - t) - ((and (charset-final kb) - (>= (charset-final kb) ?@)) - nil) - (t - (< (charset-id ka)(charset-id kb)) - )))))) - ) - (t - (> (charset-dimension ka) - (charset-dimension kb)) - )) - t) - (if (or (<= (charset-id kb) 1) - (and (charset-final kb) - (>= (charset-final kb) ?@))) - 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 @@ -243,8 +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 @@ -257,6 +143,7 @@ ideograph-daikanwa-2 ideograph-daikanwa =cbeta + =gt-k ideograph-hanziku-1 ideograph-hanziku-2 ideograph-hanziku-3 @@ -269,15 +156,49 @@ ideograph-hanziku-10 ideograph-hanziku-11 ideograph-hanziku-12 - =gt-k + =>>jis-x0208 + =>>jis-x0213-1 + =>>jis-x0213-1@2000 + =>>jis-x0213-1@2004 + =>>jis-x0213-2 + =>>jis-x0208@1978 + =>>gt + =>jis-x0208@usual + =>jis-x0208 + =>jis-x0208@1997 + =>jis-x0213-1 + =>jis-x0213-1@2000 + =>jis-x0213-1@2004 + =>jis-x0213-2@usual + =>jis-x0213-2 + ==>ucs@bucs + =>ucs@iso + =>ucs@unicode + =>ucs@jis + =>ucs@JP + =>ucs@cns + =>ucs@ks + =>>ucs@unicode + =>>ucs@jis + =>>ucs@cns =ucs@iso =ucs@unicode + =>>big5-cdp + =>>gt-k + =>gt + =>big5-cdp + =>daikanwa =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) @@ -312,7 +233,8 @@ =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))) @@ -325,6 +247,12 @@ ((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) @@ -515,7 +443,9 @@ "(%-18s . %04d)\t; %c") ((or (memq name '(=daikanwa =daikanwa@rev1 =daikanwa@rev2 - =gt =gt-k =cbeta =zinbun-oracle)) + =>>daikanwa =>daikanwa + =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) @@ -583,8 +513,9 @@ (union required-features '(=jis-x0208 =jis-x0208@1990 - =jis-x0213-1-2000 - =jis-x0213-2-2000 + =jis-x0213-1@2000 + =jis-x0213-1@2004 + =jis-x0213-2 =jis-x0212 =jis-x0208@1983 =jis-x0208@1978 @@ -718,7 +649,7 @@ name value (decode-char '=ucs value) line-breaking)) (setq attributes (delq name attributes)))) - (dolist (name '(=>ucs@gb =>ucs@cns =>ucs@jis =>ucs@ks =>ucs@big5)) + (dolist (name '(=>ucs@gb =>ucs@big5)) (when (and (memq name attributes) (setq value (get-char-attribute char name))) (insert (format "(%-18s . #x%04X)\t; %c%s" @@ -731,21 +662,21 @@ line-breaking)) (setq attributes (delq name attributes)) )) - (dolist (name '(=>daikanwa)) - (when (and (memq name attributes) - (setq value (get-char-attribute char name))) - (insert - (if (integerp value) - (format "(%-18s . %05d)\t; %c%s" - name value (decode-char '=daikanwa value) - line-breaking) - (format "(%-18s %s)\t; %c%s" - name - (mapconcat (function prin1-to-string) - value " ") - (char-representative-of-daikanwa char) - line-breaking))) - (setq attributes (delq name attributes)))) + ;; (dolist (name '(=>daikanwa)) + ;; (when (and (memq name attributes) + ;; (setq value (get-char-attribute char name))) + ;; (insert + ;; (if (integerp value) + ;; (format "(%-18s . %05d)\t; %c%s" + ;; name value (decode-char '=daikanwa value) + ;; line-breaking) + ;; (format "(%-18s %s)\t; %c%s" + ;; name + ;; (mapconcat (function prin1-to-string) + ;; value " ") + ;; (char-representative-of-daikanwa char) + ;; line-breaking))) + ;; (setq attributes (delq name attributes)))) (when (and (memq 'general-category attributes) (setq value (get-char-attribute char 'general-category))) (insert (format @@ -1352,6 +1283,10 @@ what-character-original-window-configuration) (signal (car err) (cdr err))))))) + +;;; @ end +;;; + (provide 'char-db-util) ;;; char-db-util.el ends here