;;; char-db-util.el --- Character Database utility
-;; Copyright (C) 1998,1999,2000,2001,2002 MORIOKA Tomohiko.
+;; Copyright (C) 1998,1999,2000,2001,2002,2003 MORIOKA Tomohiko.
;; Author: MORIOKA Tomohiko <tomo@kanji.zinbun.kyoto-u.ac.jp>
;; Keywords: UTF-2000, ISO/IEC 10646, Unicode, UCS-4, MULE.
(let ((v (make-vector 215 nil))
(i 1))
(while (< i 215)
- (aset v i (int-char (+ #x2EFF i)))
+ (aset v i (decode-char 'ucs (+ #x2EFF i)))
(setq i (1+ i)))
- (unless (charset-iso-final-char (car (split-char (aref v 34))))
- (aset v 34 (make-char 'chinese-gb2312 #x62 #x3A)))
v))
(defvar char-db-ignored-attributes nil)
nil)))
(defvar char-db-coded-charset-priority-list
- (let ((rest default-coded-charset-priority-list)
- dest)
- (while rest
- (when (symbolp (car rest))
- (cond ((memq (car rest)
- '(latin-viscii-lower
- latin-viscii-upper
- ipa
- lao
- ethiopic
- arabic-digit
- arabic-1-column
- arabic-2-column)))
- ((string-match "^mojikyo-" (symbol-name (car rest))))
- ((string-match "^chinese-big5" (symbol-name (car rest))))
- ((string-match "^ideograph-gt-pj-" (symbol-name (car rest)))
- (unless (memq 'ideograph-gt dest)
- (setq dest (cons 'ideograph-gt dest))))
- (t
- (setq dest (cons (car rest) dest)))))
- (setq rest (cdr rest)))
- (append (sort dest #'char-attribute-name<)
- '(chinese-big5-cdp chinese-big5-eten chinese-big5))))
+ '(ascii
+ control-1
+ latin-iso8859-1
+ latin-iso8859-2
+ latin-iso8859-3
+ latin-iso8859-4
+ latin-iso8859-9
+ latin-jisx0201
+ cyrillic-iso8859-5
+ greek-iso8859-7
+ thai-tis620
+ =jis-x0208
+ japanese-jisx0208
+ japanese-jisx0212
+ japanese-jisx0208-1978
+ chinese-gb2312
+ chinese-cns11643-1
+ chinese-cns11643-2
+ chinese-cns11643-3
+ chinese-cns11643-4
+ chinese-cns11643-5
+ chinese-cns11643-6
+ chinese-cns11643-7
+ japanese-jisx0208-1990
+ =jis-x0213-1-2000
+ =jis-x0213-2-2000
+ korean-ksc5601
+ ;; chinese-gb12345
+ chinese-isoir165
+ katakana-jisx0201
+ hebrew-iso8859-8
+ latin-viscii
+ ethiopic-ucs
+ =gt
+ =big5-cdp
+ =gt-k
+ ideograph-daikanwa-2
+ ideograph-daikanwa
+ ideograph-cbeta
+ ideograph-hanziku-1
+ ideograph-hanziku-2
+ ideograph-hanziku-3
+ ideograph-hanziku-4
+ ideograph-hanziku-5
+ ideograph-hanziku-6
+ ideograph-hanziku-7
+ ideograph-hanziku-8
+ ideograph-hanziku-9
+ ideograph-hanziku-10
+ ideograph-hanziku-11
+ ideograph-hanziku-12
+ =cbeta
+ =jef-china3
+ =big5-eten
+ =big5))
(defun char-db-make-char-spec (char)
(let (ret char-spec)
(cond ((and (setq ret (get-char-attribute char 'ucs))
(not (and (<= #xE000 ret)(<= ret #xF8FF))))
(setq char-spec (list (cons 'ucs ret)))
- (if (setq ret (get-char-attribute char 'name))
- (setq char-spec (cons (cons 'name ret) char-spec)))
+ (cond ((setq ret (get-char-attribute char 'name))
+ (setq char-spec (cons (cons 'name ret) char-spec))
+ )
+ ((setq ret (get-char-attribute char 'name*))
+ (setq char-spec (cons (cons 'name* ret) char-spec))
+ ))
)
((setq ret
- (let ((default-coded-charset-priority-list
- char-db-coded-charset-priority-list))
- (split-char char)))
+ (catch 'tag
+ (let ((rest char-db-coded-charset-priority-list))
+ (while rest
+ (if (setq ret
+ (get-char-attribute char (car rest)))
+ (throw 'tag (cons (car rest) ret)))
+ (setq rest (cdr rest))))))
(setq char-spec (list ret))
(dolist (ccs (delq (car ret) (charset-list)))
(if (or (and (charset-iso-final-char ccs)
(setq char-spec (cons (cons ccs ret) char-spec))))
(if (null char-spec)
(setq char-spec (split-char char)))
- (if (setq ret (get-char-attribute char 'name))
- (setq char-spec (cons (cons 'name ret) char-spec)))
+ (cond ((setq ret (get-char-attribute char 'name))
+ (setq char-spec (cons (cons 'name ret) char-spec))
+ )
+ ((setq ret (get-char-attribute char 'name*))
+ (setq char-spec (cons (cons 'name* ret) char-spec))
+ ))
))
char-spec)
((consp char)
(setq column (current-column)))
(let (char-spec ret al cal key temp-char)
(setq char-spec (char-db-make-char-spec char))
- ;; (cond ((characterp char)
- ;; (cond ((and (setq ret (get-char-attribute char 'ucs))
- ;; (not (and (<= #xE000 ret)(<= ret #xF8FF))))
- ;; (setq char-spec (list (cons 'ucs ret)))
- ;; (if (setq ret (get-char-attribute char 'name))
- ;; (setq char-spec (cons (cons 'name ret) char-spec)))
- ;; )
- ;; ((setq ret
- ;; (let ((default-coded-charset-priority-list
- ;; char-db-coded-charset-priority-list))
- ;; (split-char char)))
- ;; (setq char-spec (list ret))
- ;; (dolist (ccs (delq (car ret) (charset-list)))
- ;; (if (or (and (charset-iso-final-char ccs)
- ;; (setq ret (get-char-attribute char ccs)))
- ;; (eq ccs 'ideograph-daikanwa))
- ;; (setq char-spec (cons (cons ccs ret) char-spec))))
- ;; (if (null char-spec)
- ;; (setq char-spec (split-char char)))
- ;; (if (setq ret (get-char-attribute char 'name))
- ;; (setq char-spec (cons (cons 'name ret) char-spec)))
- ;; )))
- ;; ((consp char)
- ;; (setq char-spec char)
- ;; (setq char nil)))
(unless (or (characterp char) ; char
(condition-case nil
(setq char (find-char char-spec))
ideograph-gt-pj-10
ideograph-gt-pj-11))
(setq ret (decode-char ccs code-point))
- (setq ret (get-char-attribute ret 'ideograph-gt)))
- (decode-builtin-char 'ideograph-gt ret))
+ (setq ret (get-char-attribute ret '=gt)))
+ (decode-builtin-char '=gt ret))
(t
(decode-builtin-char ccs code-point))))
(cond ((and (<= 0 (char-int ret))
value line-breaking))
(setq attributes (delq 'name attributes))
)
+ (when (and (memq 'name* attributes)
+ (setq value (get-char-attribute char 'name*)))
+ (insert (format
+ (if (> (+ (current-column) (length value)) 48)
+ "(name* . %S)%s"
+ "(name* . %S)%s")
+ value line-breaking))
+ (setq attributes (delq 'name* attributes))
+ )
(when (and (memq 'script attributes)
(setq value (get-char-attribute char 'script)))
(insert (format "(script\t\t%s)%s"
line-breaking))
(setq attributes (delq '=>ucs-cns attributes))
)
+ (when (and (memq '=>ucs-big5 attributes)
+ (setq value (get-char-attribute char '=>ucs-big5)))
+ (insert (format "(=>ucs-big5\t\t. #x%04X)\t; %c%s"
+ value (decode-char 'ucs-big5 value)
+ line-breaking))
+ (setq attributes (delq '=>ucs-big5 attributes))
+ )
(when (and (memq '=>ucs-jis attributes)
(setq value (get-char-attribute char '=>ucs-jis)))
(insert (format "(=>ucs-jis\t\t. #x%04X)\t; %c%s"
(format
(cond ((memq name '(ideograph-daikanwa-2
ideograph-daikanwa
- ideograph-gt
- ideograph-gt-k
- ideograph-cbeta))
+ =gt =gt-k =cbeta))
(if has-long-ccs-name
"(%-26s . %05d)\t; %c%s"
"(%-18s . %05d)\t; %c%s"))
(if has-long-ccs-name
"(%-26s . %06d)\t; %c%s"
"(%-18s . %06d)\t; %c%s"))
- ((eq name 'ucs)
+ ((>= (charset-dimension name) 2)
(if has-long-ccs-name
"(%-26s . #x%04X)\t; %c%s"
"(%-18s . #x%04X)\t; %c%s"))