1 ;;; char-db-util.el --- Character Database utility
3 ;; Copyright (C) 1998,1999,2000,2001 MORIOKA Tomohiko.
5 ;; Author: MORIOKA Tomohiko <tomo@kanji.zinbun.kyoto-u.ac.jp>
6 ;; Keywords: UTF-2000, ISO/IEC 10646, Unicode, UCS-4, MULE.
8 ;; This file is part of XEmacs UTF-2000.
10 ;; XEmacs UTF-2000 is free software; you can redistribute it and/or
11 ;; modify it under the terms of the GNU General Public License as
12 ;; published by the Free Software Foundation; either version 2, or (at
13 ;; your option) any later version.
15 ;; XEmacs UTF-2000 is distributed in the hope that it will be useful,
16 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
17 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
18 ;; General Public License for more details.
20 ;; You should have received a copy of the GNU General Public License
21 ;; along with XEmacs UTF-2000; see the file COPYING. If not, write to
22 ;; the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
23 ;; Boston, MA 02111-1307, USA.
29 (defconst unidata-normative-category-alist
30 '(("Lu" letter uppercase)
31 ("Ll" letter lowercase)
32 ("Lt" letter titlecase)
33 ("Mn" mark non-spacing)
34 ("Mc" mark spacing-combining)
36 ("Nd" number decimal-digit)
39 ("Zs" separator space)
41 ("Zp" separator paragraph)
44 ("Cs" other surrogate)
45 ("Co" other private-use)
46 ("Cn" other not-assigned)))
48 (defconst unidata-informative-category-alist
49 '(("Lm" letter modifier)
51 ("Pc" punctuation connector)
52 ("Pd" punctuation dash)
53 ("Ps" punctuation open)
54 ("Pe" punctuation close)
55 ("Pi" punctuation initial-quote)
56 ("Pf" punctuation final-quote)
57 ("Po" punctuation other)
59 ("Sc" symbol currency)
60 ("Sk" symbol modifier)
64 (defconst ideographic-radicals
65 (let ((v (make-vector 215 nil))
68 (aset v i (int-char (+ #x2EFF i)))
70 (if (< (charset-iso-final-char (car (split-char (aref v 34)))) ?0)
71 (aset v 34 (make-char 'chinese-gb2312 #x62 #x3A)))
74 (defun char-attribute-name< (ka kb)
80 ((= (charset-dimension ka)
81 (charset-dimension kb))
82 (cond ((= (charset-chars ka)(charset-chars kb))
84 ((>= (charset-iso-final-char ka) ?@)
85 (if (>= (charset-iso-final-char kb) ?@)
86 (< (charset-iso-final-char ka)
87 (charset-iso-final-char kb))
89 ((>= (charset-iso-final-char ka) ?0)
91 ((>= (charset-iso-final-char kb) ?@)
93 ((>= (charset-iso-final-char kb) ?0)
94 (< (charset-iso-final-char ka)
95 (charset-iso-final-char kb)))
97 (t (if (>= (charset-iso-final-char kb) ?0)
99 (> (charset-id ka)(charset-id kb))))))
100 ((<= (charset-chars ka)(charset-chars kb)))))
102 (< (charset-dimension ka)
103 (charset-dimension kb))
113 (string< (symbol-name ka)
119 (defun char-db-insert-char-spec (char &optional readable column)
121 (setq column (current-column)))
122 (let (char-spec ret al cal key)
123 (cond ((characterp char)
124 (cond ((setq ret (get-char-attribute char 'ucs))
125 (setq char-spec (list (cons 'ucs ret)))
126 (if (setq ret (get-char-attribute char 'name))
127 (setq char-spec (cons (cons 'name ret) char-spec)))
129 ((setq ret (split-char char))
130 (setq char-spec (list ret))
131 (dolist (ccs (delq (car ret) (charset-list)))
132 (if (and (>= (charset-iso-final-char ccs) ?0)
133 (setq ret (get-char-attribute char ccs)))
134 (setq char-spec (cons (cons ccs ret) char-spec))))
135 (if (setq ret (get-char-attribute char 'name))
136 (setq char-spec (cons (cons 'name ret) char-spec)))
139 (setq char-spec char)
142 (setq char (condition-case nil
143 (define-char char-spec)
149 (setq key (car (car char-spec)))
150 (if (find-charset key)
151 (setq cal (cons key cal))
152 (setq al (cons key al)))
153 (setq char-spec (cdr char-spec)))
154 (insert-char-attributes char
157 (insert (prin1-to-string char-spec)))))
159 (defun char-db-insert-alist (alist &optional readable column)
161 (setq column (current-column)))
163 (concat "\n" (make-string (1+ column) ?\ )))
166 lbs cell rest separator)
169 (setq name (car (car alist))
170 value (cdr (car alist)))
171 (cond ((eq name 'char)
173 (if (setq ret (condition-case nil
180 (setq key (car (car value)))
181 (if (find-charset key)
182 (setq cal (cons key cal))
183 (setq al (cons key al)))
184 (setq value (cdr value)))
185 (insert-char-attributes ret
188 (insert (prin1-to-string value)))
190 (insert line-breaking))
192 (insert (format "(%-18s " name))
193 (setq lbs (concat "\n" (make-string (current-column) ?\ )))
195 (setq cell (car value))
196 (if (and (consp cell)
198 (setq ret (condition-case nil
207 (setq key (car (car rest)))
208 (if (find-charset key)
209 (setq cal (cons key cal))
210 (setq al (cons key al)))
211 (setq rest (cdr rest)))
214 (insert-char-attributes ret
217 (setq separator lbs))
220 (insert (prin1-to-string cell))
221 (setq separator " "))
222 (setq value (cdr value)))
224 (insert line-breaking))
226 (insert (format "(%-18s . %S)%s"
229 (setq alist (cdr alist))))
232 (defun char-db-insert-char-reference (plist &optional readable column)
234 (setq column (current-column)))
236 (concat "\n" (make-string (1+ column) ?\ )))
240 (setq name (pop plist))
241 (setq value (pop plist))
242 (cond ((eq name :char)
244 (char-db-insert-char-spec value readable)
245 (insert line-breaking))
247 (insert (format "%s\t%S%s"
253 (defun char-db-decode-isolated-char (ccs code-point)
256 (cond ((eq ccs 'arabic-iso8859-6)
257 (decode-char ccs code-point))
258 ((and (memq ccs '(ideograph-gt-pj-1
269 (setq ret (decode-char ccs code-point))
270 (setq ret (get-char-attribute ret 'ideograph-gt)))
271 (decode-builtin-char 'ideograph-gt ret))
273 (decode-builtin-char ccs code-point))))
274 (cond ((and (<= 0 (char-int ret))
275 (<= (char-int ret) #x1F))
276 (decode-char 'ucs (+ #x2400 (char-int ret))))
277 ((= (char-int ret) #x7F)
281 (defvar char-db-convert-obsolete-format t)
283 (defun insert-char-attributes (char &optional readable
284 attributes ccs-attributes
288 (if (consp attributes)
289 (copy-sequence attributes))
290 (char-attribute-list))
291 #'char-attribute-name<))
293 (sort (if ccs-attributes
294 (copy-sequence ccs-attributes)
296 #'char-attribute-name<))
298 (setq column (current-column)))
299 (let (name value has-long-ccs-name rest
302 (concat "\n" (make-string (1+ column) ?\ )))
303 lbs cell separator ret
306 (when (and (memq 'name attributes)
307 (setq value (get-char-attribute char 'name)))
309 (if (> (length value) 47)
312 value line-breaking))
313 (setq attributes (delq 'name attributes))
315 (when (and (memq 'script attributes)
316 (setq value (get-char-attribute char 'script)))
317 (insert (format "(script\t\t%s)%s"
318 (mapconcat (function prin1-to-string)
321 (setq attributes (delq 'script attributes))
323 (when (and (memq '=>ucs attributes)
324 (setq value (get-char-attribute char '=>ucs)))
325 (insert (format "(=>ucs\t\t. #x%04X)\t; %c%s"
326 value (decode-char 'ucs value)
328 (setq attributes (delq '=>ucs attributes))
330 (when (and (memq '->ucs attributes)
331 (setq value (get-char-attribute char '->ucs)))
332 (insert (format (if char-db-convert-obsolete-format
333 "(=>ucs\t\t. #x%04X)\t; %c%s"
334 "(->ucs\t\t. #x%04X)\t; %c%s")
335 value (decode-char 'ucs value)
337 (setq attributes (delq '->ucs attributes))
339 (when (and (memq 'general-category attributes)
340 (setq value (get-char-attribute char 'general-category)))
342 "(general-category\t%s) ; %s%s"
343 (mapconcat (lambda (cell)
346 (cond ((rassoc value unidata-normative-category-alist)
347 "Normative Category")
348 ((rassoc value unidata-informative-category-alist)
349 "Informative Category")
353 (setq attributes (delq 'general-category attributes))
355 (when (and (memq 'bidi-category attributes)
356 (setq value (get-char-attribute char 'bidi-category)))
357 (insert (format "(bidi-category\t. %S)%s"
360 (setq attributes (delq 'bidi-category attributes))
362 (unless (or (not (memq 'mirrored attributes))
363 (eq (setq value (get-char-attribute char 'mirrored 'empty))
365 (insert (format "(mirrored\t\t. %S)%s"
368 (setq attributes (delq 'mirrored attributes))
371 ((and (memq 'decimal-digit-value attributes)
372 (setq value (get-char-attribute char 'decimal-digit-value)))
373 (insert (format "(decimal-digit-value . %S)%s"
376 (setq attributes (delq 'decimal-digit-value attributes))
377 (when (and (memq 'digit-value attributes)
378 (setq value (get-char-attribute char 'digit-value)))
379 (insert (format "(digit-value\t . %S)%s"
382 (setq attributes (delq 'digit-value attributes))
384 (when (and (memq 'numeric-value attributes)
385 (setq value (get-char-attribute char 'numeric-value)))
386 (insert (format "(numeric-value\t . %S)%s"
389 (setq attributes (delq 'numeric-value attributes))
393 (when (and (memq 'digit-value attributes)
394 (setq value (get-char-attribute char 'digit-value)))
395 (insert (format "(digit-value\t. %S)%s"
398 (setq attributes (delq 'digit-value attributes))
400 (when (and (memq 'numeric-value attributes)
401 (setq value (get-char-attribute char 'numeric-value)))
402 (insert (format "(numeric-value\t. %S)%s"
405 (setq attributes (delq 'numeric-value attributes))
407 (when (and (memq 'iso-10646-comment attributes)
408 (setq value (get-char-attribute char 'iso-10646-comment)))
409 (insert (format "(iso-10646-comment\t. %S)%s"
412 (setq attributes (delq 'iso-10646-comment attributes))
414 (when (and (memq 'morohashi-daikanwa attributes)
415 (setq value (get-char-attribute char 'morohashi-daikanwa)))
416 (insert (format "(morohashi-daikanwa\t%s)%s"
417 (mapconcat (function prin1-to-string) value " ")
419 (setq attributes (delq 'morohashi-daikanwa attributes))
423 (when (and (memq 'ideographic-radical attributes)
424 (setq value (get-char-attribute char 'ideographic-radical)))
426 (insert (format "(ideographic-radical . %S)\t; %c%s"
428 (aref ideographic-radicals radical)
430 (setq attributes (delq 'ideographic-radical attributes))
432 (when (and (memq 'ideographic-strokes attributes)
433 (setq value (get-char-attribute char 'ideographic-strokes)))
435 (insert (format "(ideographic-strokes . %S)%s"
438 (setq attributes (delq 'ideographic-strokes attributes))
440 (when (and (memq 'kangxi-radical attributes)
441 (setq value (get-char-attribute char 'kangxi-radical)))
442 (unless (eq value radical)
443 (insert (format "(kangxi-radical\t . %S)\t; %c%s"
445 (aref ideographic-radicals value)
448 (setq radical value)))
449 (setq attributes (delq 'kangxi-radical attributes))
451 (when (and (memq 'kangxi-strokes attributes)
452 (setq value (get-char-attribute char 'kangxi-strokes)))
453 (unless (eq value strokes)
454 (insert (format "(kangxi-strokes\t . %S)%s"
458 (setq strokes value)))
459 (setq attributes (delq 'kangxi-strokes attributes))
461 (when (and (memq 'japanese-radical attributes)
462 (setq value (get-char-attribute char 'japanese-radical)))
463 (unless (eq value radical)
464 (insert (format "(japanese-radical\t . %S)\t; %c%s"
466 (aref ideographic-radicals value)
469 (setq radical value)))
470 (setq attributes (delq 'japanese-radical attributes))
472 (when (and (memq 'japanese-strokes attributes)
473 (setq value (get-char-attribute char 'japanese-strokes)))
474 (unless (eq value strokes)
475 (insert (format "(japanese-strokes\t . %S)%s"
479 (setq strokes value)))
480 (setq attributes (delq 'japanese-strokes attributes))
482 (when (and (memq 'cns-radical attributes)
483 (setq value (get-char-attribute char 'cns-radical)))
484 (insert (format "(cns-radical\t . %S)\t; %c%s"
486 (aref ideographic-radicals value)
488 (setq attributes (delq 'cns-radical attributes))
490 (when (and (memq 'cns-strokes attributes)
491 (setq value (get-char-attribute char 'cns-strokes)))
492 (unless (eq value strokes)
493 (insert (format "(cns-strokes\t . %S)%s"
497 (setq strokes value)))
498 (setq attributes (delq 'cns-strokes attributes))
500 (when (and (memq 'shinjigen-1-radical attributes)
501 (setq value (get-char-attribute char 'shinjigen-1-radical)))
502 (unless (eq value radical)
503 (insert (format "(shinjigen-1-radical . %S)\t; %c%s"
505 (aref ideographic-radicals value)
508 (setq radical value)))
509 (setq attributes (delq 'shinjigen-1-radical attributes))
511 (when (and (memq 'total-strokes attributes)
512 (setq value (get-char-attribute char 'total-strokes)))
513 (insert (format "(total-strokes . %S)%s"
516 (setq attributes (delq 'total-strokes attributes))
518 (when (and (memq '->ideograph attributes)
519 (setq value (get-char-attribute char '->ideograph)))
520 (insert (format "(->ideograph\t%s)%s"
521 (mapconcat (lambda (code)
522 (cond ((symbolp code)
525 (format "#x%04X" code))
528 line-breaking code))))
531 (setq attributes (delq '->ideograph attributes))
533 (when (and (memq '->decomposition attributes)
534 (setq value (get-char-attribute char '->decomposition)))
535 (insert (format "(->decomposition\t%s)%s"
536 (mapconcat (lambda (code)
537 (cond ((symbolp code)
546 (format "#x%04X" code))
548 (format "%s%S" line-breaking code))))
551 (setq attributes (delq '->decomposition attributes))
553 (if (equal (get-char-attribute char '->titlecase)
554 (get-char-attribute char '->uppercase))
555 (setq attributes (delq '->titlecase attributes)))
556 (when (and (memq '->mojikyo attributes)
557 (setq value (get-char-attribute char '->mojikyo)))
558 (insert (format "(->mojikyo\t\t. %06d)\t; %c%s"
559 value (decode-char 'mojikyo value)
561 (setq attributes (delq '->mojikyo attributes))
563 (setq rest ccs-attributes)
566 (setq value (get-char-attribute char (car rest)))
568 (if (>= (length (symbol-name (car rest))) 19)
570 (setq has-long-ccs-name t)
574 (setq rest (cdr rest)))
576 (setq name (car attributes))
577 (if (setq value (get-char-attribute char name))
578 (cond ((eq name 'jisx0208-1978/4X)
579 (insert (format "(%-18s . #x%04X)%s"
582 ((memq name '(->lowercase
583 ->uppercase ->titlecase
584 ->fullwidth <-fullwidth
585 ->vulgar-ideograph <-vulgar-ideograph
586 ->ancient-ideograph <-ancient-ideograph
587 ->original-ideograph <-original-ideograph
588 ->simplified-ideograph <-simplified-ideograph
590 ->ideographic <-ideographic
591 ->bopomofo ->ideograph))
592 (insert (format "(%-18s%s " name line-breaking))
593 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
596 (setq cell (car value))
598 (setq cell (decode-char 'ucs cell)))
599 (cond ((characterp cell)
602 (char-db-insert-char-spec cell readable)
603 (setq separator lbs))
607 (if (consp (car cell))
608 (char-db-insert-char-spec cell readable)
609 (char-db-insert-char-reference cell readable))
610 (setq separator lbs))
614 (insert (prin1-to-string cell))
615 (setq separator " ")))
616 (setq value (cdr value)))
618 (insert line-breaking))
619 ((memq name '(ideograph=
620 original-ideograph-of
624 simplified-ideograph-of
626 ideographic-different-form-of))
627 (insert (format "(%-18s%s " name line-breaking))
628 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
631 (setq cell (car value))
632 (if (and (consp cell)
637 (char-db-insert-alist cell readable)
638 (setq separator lbs))
641 (insert (prin1-to-string cell))
642 (setq separator " "))
643 (setq value (cdr value)))
645 (insert line-breaking))
646 ((string-match "^->" (symbol-name name))
648 (format "(%-18s %s)%s"
650 (mapconcat (lambda (code)
651 (cond ((symbolp code)
654 (format "#x%04X" code))
657 line-breaking code))))
661 (insert (format "(%-18s " name))
662 (setq lbs (concat "\n" (make-string (current-column) ?\ ))
665 (setq cell (car value))
666 (if (and (consp cell)
668 (setq ret (condition-case nil
676 (setq key (car (car rest)))
677 (if (find-charset key)
678 (setq cal (cons key cal))
679 (setq al (cons key al)))
680 (setq rest (cdr rest)))
683 (insert-char-attributes ret
686 (setq separator lbs))
689 (insert (prin1-to-string cell))
690 (setq separator " "))
691 (setq value (cdr value)))
693 (insert line-breaking))
695 (insert (format "(%-18s . %S)%s"
699 (setq attributes (cdr attributes)))
700 (while ccs-attributes
701 (setq name (car ccs-attributes))
702 (if (and (eq name (charset-name name))
703 (setq value (get-char-attribute char name)))
706 (cond ((memq name '(ideograph-daikanwa ideograph-gt))
707 (if has-long-ccs-name
708 "(%-26s . %05d)\t; %c%s"
709 "(%-18s . %05d)\t; %c%s"))
711 (if has-long-ccs-name
712 "(%-26s . %06d)\t; %c%s"
713 "(%-18s . %06d)\t; %c%s"))
715 (if has-long-ccs-name
716 "(%-26s . #x%04X)\t; %c%s"
717 "(%-18s . #x%04X)\t; %c%s"))
719 (if has-long-ccs-name
720 "(%-26s . #x%02X)\t; %c%s"
721 "(%-18s . #x%02X)\t; %c%s")))
723 (if (= (charset-iso-graphic-plane name) 1)
725 (cond ((= (charset-dimension name) 1)
727 ((= (charset-dimension name) 2)
729 ((= (charset-dimension name) 3)
733 (char-db-decode-isolated-char name value)
735 (setq ccs-attributes (cdr ccs-attributes)))
738 (defun insert-char-data (char &optional readable
739 attributes ccs-attributes)
741 (narrow-to-region (point)(point))
742 (insert "(define-char
744 (insert-char-attributes char readable
745 attributes ccs-attributes)
747 (goto-char (point-min))
748 (while (re-search-forward "[ \t]+$" nil t)
750 (goto-char (point-max))
751 (tabify (point-min)(point-max))
755 (defun char-db-update-comment ()
758 (goto-char (point-min))
759 (let (cdef table char)
760 (while (re-search-forward "^[ \t]*\\(([^.()]+)\\)" nil t)
761 (goto-char (match-beginning 1))
762 (setq cdef (read (current-buffer)))
763 (when (find-charset (car cdef))
764 (goto-char (match-end 0))
767 (not (eq (car cdef) 'ideograph-daikanwa))
768 (or (memq (car cdef) '(ascii latin-viscii-upper
772 japanese-jisx0213-2))
773 (= (char-int (charset-iso-final-char (car cdef)))
775 (apply (function make-char) cdef)
776 (if (setq table (charset-mapping-table (car cdef)))
777 (set-charset-mapping-table (car cdef) nil))
779 (apply (function make-char) cdef)
781 (set-charset-mapping-table (car cdef) table)))))
782 (when (not (or (< (char-int char) 32)
783 (and (<= 128 (char-int char))
784 (< (char-int char) 160))))
785 (delete-region (point) (point-at-eol))
786 (insert (format "\t; %c" char)))
789 (defun insert-char-data-with-variant (char &optional printable
791 script excluded-script)
792 (insert-char-data char printable)
793 (let ((variants (or (char-variants char)
794 (let ((ucs (get-char-attribute char '->ucs)))
796 (delete char (char-variants (int-char ucs)))))))
798 (setq variants (sort variants #'<))
800 (setq variant (car variants))
801 (if (and (or (null script)
802 (null (setq vs (get-char-attribute variant 'script)))
804 (or (null excluded-script)
805 (null (setq vs (get-char-attribute variant 'script)))
806 (not (memq excluded-script vs))))
807 (or (and no-ucs-variant (get-char-attribute variant 'ucs))
808 (insert-char-data variant printable)))
809 (setq variants (cdr variants))
812 (defun insert-char-range-data (min max &optional script excluded-script)
816 (setq char (decode-char 'ucs code))
817 (if (get-char-attribute char 'ucs)
818 (insert-char-data-with-variant char nil 'no-ucs-variant
819 script excluded-script))
820 (setq code (1+ code))
823 (defun write-char-range-data-to-file (min max file
824 &optional script excluded-script)
825 (let ((coding-system-for-write 'utf-8))
827 (insert-char-range-data min max script excluded-script)
828 (write-region (point-min)(point-max) file))))
830 (defvar what-character-original-window-configuration)
833 (defun what-char-definition (char)
834 (interactive (list (char-after)))
835 (let ((buf (get-buffer-create "*Character Description*"))
836 (the-buf (current-buffer))
837 (win-conf (current-window-configuration)))
839 (make-local-variable 'what-character-original-window-configuration)
840 (setq what-character-original-window-configuration win-conf)
841 (setq buffer-read-only nil)
845 (insert-char-data-with-variant char 'printable)
846 ;; (char-db-update-comment)
847 (set-buffer-modified-p nil)
848 (view-mode the-buf (lambda (buf)
849 (set-window-configuration
850 what-character-original-window-configuration)
852 (goto-char (point-min)))
854 (set-window-configuration
855 what-character-original-window-configuration)
856 (signal (car err) (cdr err)))))))
858 (provide 'char-db-util)
860 ;;; char-db-util.el ends here