X-Git-Url: http://git.chise.org/gitweb/?a=blobdiff_plain;f=lisp%2Futf-2000%2Fchar-db-util.el;h=84b6a98e1650019dfd196256140c25bba54a9425;hb=96e8582f57d87102b98e6eb0f746a291a01fd681;hp=a15b5878cb54933b0635815597d8a5ce655e2067;hpb=08000b7a842f62ae6bd34249959a09ce5f1b66b1;p=chise%2Fxemacs-chise.git- diff --git a/lisp/utf-2000/char-db-util.el b/lisp/utf-2000/char-db-util.el index a15b587..84b6a98 100644 --- a/lisp/utf-2000/char-db-util.el +++ b/lisp/utf-2000/char-db-util.el @@ -69,9 +69,11 @@ (setq i (1+ i))) v)) +(defvar char-db-file-coding-system 'utf-8-mcs-er) + (defvar char-db-feature-domains '(ucs daikanwa cns gt jis jis/alt jis/a jis/b - jis-x0213 misc unknown)) + jis-x0213 cdp shinjigen misc unknown)) (defvar char-db-ignored-attributes nil) @@ -87,8 +89,8 @@ nil) ((find-charset ka) (if (find-charset kb) - (if (<= (charset-id ka) 0) - (if (<= (charset-id kb) 0) + (if (<= (charset-id ka) 1) + (if (<= (charset-id kb) 1) (cond ((= (charset-dimension ka) (charset-dimension kb)) @@ -98,7 +100,7 @@ (charset-dimension kb)) )) t) - (if (<= (charset-id kb) 0) + (if (<= (charset-id kb) 1) nil (< (charset-id ka)(charset-id kb)))) nil)) @@ -390,10 +392,43 @@ (defvar char-db-convert-obsolete-format t) +(defun char-db-insert-ccs-feature (name value line-breaking) + (insert + (format + (cond ((memq name '(=daikanwa + =daikanwa-rev1 =daikanwa-rev2 + =gt =gt-k =cbeta)) + "(%-18s . %05d)\t; %c") + ((eq name 'mojikyo) + "(%-18s . %06d)\t; %c") + ((>= (charset-dimension name) 2) + "(%-18s . #x%04X)\t; %c") + (t + "(%-18s . #x%02X)\t; %c")) + name + (if (= (charset-iso-graphic-plane name) 1) + (logior value + (cond ((= (charset-dimension name) 1) + #x80) + ((= (charset-dimension name) 2) + #x8080) + ((= (charset-dimension name) 3) + #x808080) + (t 0))) + value) + (char-db-decode-isolated-char name value))) + (if (and (= (charset-chars name) 94) + (= (charset-dimension name) 2)) + (insert (format " [%02d-%02d]" + (- (lsh value -8) 32) + (- (logand value 255) 32)))) + (insert line-breaking)) + (defun insert-char-attributes (char &optional readable attributes column) (unless column (setq column (current-column))) - (let (name value has-long-ccs-name rest + (let (name value ; has-long-ccs-name + rest radical strokes (line-breaking (concat "\n" (make-string (1+ column) ?\ ))) @@ -447,6 +482,14 @@ line-breaking)) (setq attributes (delq 'script attributes)) ) + ;; (when (and (memq '<-denotational attributes) + ;; (setq value (get-char-attribute char '<-denotational)) + ;; (null (cdr value)) + ;; (setq value (encode-char (car value) 'ucs 'defined-only))) + ;; (insert (format "(%-18s . #x%04X)\t; %c%s" + ;; '=>ucs value (decode-char 'ucs value) + ;; line-breaking)) + ;; (setq attributes (delq '<-denotational attributes))) (dolist (name '(=>ucs =>ucs*)) (when (and (memq name attributes) (setq value (get-char-attribute char name))) @@ -828,7 +871,8 @@ ) (unless readable (dolist (ignored '(composition - ->denotational <-subsumptive ->ucs-unified)) + ->denotational <-subsumptive ->ucs-unified + ->ideographic-component-forms)) (setq attributes (delq ignored attributes)))) ;; (setq rest ccs-attributes) ;; (while (and rest @@ -851,39 +895,41 @@ (prog1 (setq value (get-char-attribute char name)) (setq dest-ccss (cons name dest-ccss)))) - (insert - (format - (cond ((memq name '(=daikanwa - =daikanwa-rev1 =daikanwa-rev2 - =gt =gt-k =cbeta)) - (if has-long-ccs-name - "(%-26s . %05d)\t; %c%s" - "(%-18s . %05d)\t; %c%s")) - ((eq name 'mojikyo) - (if has-long-ccs-name - "(%-26s . %06d)\t; %c%s" - "(%-18s . %06d)\t; %c%s")) - ((>= (charset-dimension name) 2) - (if has-long-ccs-name - "(%-26s . #x%04X)\t; %c%s" - "(%-18s . #x%04X)\t; %c%s")) - (t - (if has-long-ccs-name - "(%-26s . #x%02X)\t; %c%s" - "(%-18s . #x%02X)\t; %c%s"))) - name - (if (= (charset-iso-graphic-plane name) 1) - (logior value - (cond ((= (charset-dimension name) 1) - #x80) - ((= (charset-dimension name) 2) - #x8080) - ((= (charset-dimension name) 3) - #x808080) - (t 0))) - value) - (char-db-decode-isolated-char name value) - line-breaking))) + (char-db-insert-ccs-feature name value line-breaking) + ;; (insert + ;; (format + ;; (cond ((memq name '(=daikanwa + ;; =daikanwa-rev1 =daikanwa-rev2 + ;; =gt =gt-k =cbeta)) + ;; (if has-long-ccs-name + ;; "(%-26s . %05d)\t; %c%s" + ;; "(%-18s . %05d)\t; %c%s")) + ;; ((eq name 'mojikyo) + ;; (if has-long-ccs-name + ;; "(%-26s . %06d)\t; %c%s" + ;; "(%-18s . %06d)\t; %c%s")) + ;; ((>= (charset-dimension name) 2) + ;; (if has-long-ccs-name + ;; "(%-26s . #x%04X)\t; %c%s" + ;; "(%-18s . #x%04X)\t; %c%s")) + ;; (t + ;; (if has-long-ccs-name + ;; "(%-26s . #x%02X)\t; %c%s" + ;; "(%-18s . #x%02X)\t; %c%s"))) + ;; name + ;; (if (= (charset-iso-graphic-plane name) 1) + ;; (logior value + ;; (cond ((= (charset-dimension name) 1) + ;; #x80) + ;; ((= (charset-dimension name) 2) + ;; #x8080) + ;; ((= (charset-dimension name) 3) + ;; #x808080) + ;; (t 0))) + ;; value) + ;; (char-db-decode-isolated-char name value) + ;; line-breaking)) + ) ) ((string-match "^=>ucs@" (symbol-name name)) (insert (format "(%-18s . #x%04X)\t; %c%s" @@ -896,8 +942,20 @@ line-breaking)) ) ((and (not readable) + (null (get-char-attribute + char + (intern (format "%s*sources" name)))) + (not (string-match "\\*sources$" (symbol-name name))) (or (eq name '<-identical) - (string-match "^->simplified" (symbol-name name)))) + (string-match "^->simplified" (symbol-name name)) + ;; (string-match "^<-same" (symbol-name name)) + (string-match "^->same" (symbol-name name)) + ;; (string-match "^->ideographic-same" (symbol-name name)) + (string-match "^->vulgar" (symbol-name name)) + (string-match "^->wrong" (symbol-name name)) + (string-match "^->original" (symbol-name name)) + (string-match "^->ancient" (symbol-name name)) + )) ) ((or (eq name 'ideographic-structure) (eq name 'ideographic-) @@ -933,24 +991,47 @@ (intern (format "%s*sources" name)))) (setq required-features nil) (dolist (source sources) - (setq required-features - (cons - (if (find-charset - (setq ret (intern - (format "=%s" source)))) - ret - source) - required-features))) - (when (string-match "@JP" (symbol-name name)) - (setq required-features - (union required-features - '(=jis-x0208 - =jis-x0208-1990 - =jis-x0213-1-2000 - =jis-x0213-2-2000 - =jis-x0212 - =jis-x0208-1983 - =jis-x0208-1978)))) + (cond + ((memq source '(JP JP/Jouyou + shinjigen-1)) + (setq required-features + (union required-features + '(=jis-x0208 + =jis-x0208-1990 + =jis-x0213-1-2000 + =jis-x0213-2-2000 + =jis-x0212 + =jis-x0208-1983 + =jis-x0208-1978)))) + ((eq source 'CN) + (setq required-features + (union required-features + '(=gb2312 + =gb12345 + =iso-ir165))))) + (cond + ((find-charset + (setq ret (intern (format "=%s" source)))) + (setq required-features + (cons ret required-features))) + (t (setq required-features + (cons source required-features))))) + (cond ((string-match "@JP" (symbol-name name)) + (setq required-features + (union required-features + '(=jis-x0208 + =jis-x0208-1990 + =jis-x0213-1-2000 + =jis-x0213-2-2000 + =jis-x0212 + =jis-x0208-1983 + =jis-x0208-1978)))) + ((string-match "@CN" (symbol-name name)) + (setq required-features + (union required-features + '(=gb2312 + =gb12345 + =iso-ir165))))) (if separator (insert lbs)) (if readable @@ -1147,9 +1228,10 @@ (defun write-char-range-data-to-file (min max file &optional script excluded-script) - (let ((coding-system-for-write 'utf-8-mcs)) + (let ((coding-system-for-write char-db-file-coding-system)) (with-temp-buffer - (insert ";; -*- coding: utf-8-mcs -*-\n") + (insert (format ";; -*- coding: %s -*-\n" + char-db-file-coding-system)) (insert-char-range-data min max script excluded-script) (write-region (point-min)(point-max) file))))