1 ;;; ids-find.el --- search utility based on Ideographic-structures ;; -*- coding: utf-8-mcs-er -*-
3 ;; Copyright (C) 2002, 2003, 2005, 2006, 2007, 2017, 2020 MORIOKA Tomohiko
5 ;; Author: MORIOKA Tomohiko <tomo@kanji.zinbun.kyoto-u.ac.jp>
6 ;; Keywords: Kanji, Ideographs, search, IDS, CHISE, UCS, Unicode
8 ;; This file is a part of CHISE-IDS.
10 ;; This program 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 ;; This program is distributed in the hope that it will be useful, but
16 ;; 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 this program; 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.
27 (defun ids-index-store-char (product component)
28 (let ((ret (get-char-attribute component 'ideographic-products)))
29 (unless (memq product ret)
30 (put-char-attribute component 'ideographic-products
32 (when (setq ret (char-feature component 'ideographic-structure))
33 (ids-index-store-structure product ret)))
36 (defun ids-index-store-structure (product structure)
38 (dolist (cell (cdr structure))
40 (setq cell (plist-get cell :char)))
41 (cond ((characterp cell)
42 (ids-index-store-char product cell))
43 ((setq ret (assq 'ideographic-structure cell))
44 (ids-index-store-structure product (cdr ret)))
45 ((setq ret (find-char cell))
46 (ids-index-store-char product ret))
50 (defun ids-update-index (&optional in-memory)
54 (ids-index-store-structure c v)
56 'ideographic-structure)
59 (ids-index-store-structure c v)
61 'ideographic-structure@apparent)
63 (save-char-attribute-table 'ideographic-products)))
66 (mount-char-attribute-table 'ideographic-products)
69 (defun ids-find-all-products (char)
71 (dolist (cell (char-feature char 'ideographic-products))
72 (unless (memq cell dest)
73 (setq dest (cons cell dest)))
74 (setq dest (union dest (ids-find-all-products cell))))
77 (defun of-component-features ()
79 (dolist (feature (char-attribute-list))
80 (when (string-match "^<-.*[@/]component\\(/[^*/]+\\)*$"
81 (symbol-name feature))
83 (list* '<-mistakable '->mistakable
86 '<-original '->original
90 (defun to-component-features ()
92 (dolist (feature (char-attribute-list))
93 (when (string-match "^->.*[@/]component\\(/[^*/]+\\)*$"
94 (symbol-name feature))
99 (defun char-component-variants (char)
100 (let ((dest (list char))
102 (dolist (feature (to-component-features))
103 (if (setq ret (get-char-attribute char feature))
105 (setq dest (union dest (char-component-variants c))))))
107 ;; ((setq ret (some (lambda (feature)
108 ;; (get-char-attribute char feature))
109 ;; (to-component-features)))
111 ;; (setq dest (union dest (char-component-variants c))))
113 ((setq ret (get-char-attribute char '->ucs-unified))
114 (setq dest (cons char ret))
116 (setq dest (union dest
117 (some (lambda (feature)
118 (get-char-attribute c feature))
119 (of-component-features))
122 ((and (setq ret (get-char-attribute char '=>ucs))
123 (setq uchr (decode-char '=ucs ret)))
124 (setq dest (cons uchr (char-variants uchr)))
126 (setq dest (union dest
127 (some (lambda (feature)
128 (get-char-attribute c feature))
129 (of-component-features))
135 (unless (memq c dest)
136 (setq dest (cons c dest)))
139 (some (lambda (feature)
140 (char-feature c feature))
141 (of-component-features))
149 (defun ideographic-products-find (&rest components)
150 (if (stringp (car components))
151 (setq components (string-to-char-list (car components))))
153 (dolist (variant (char-component-variants (car components)))
156 (get-char-attribute variant 'ideographic-products))))
159 (setq components (cdr components)))
161 (dolist (variant (char-component-variants (car components)))
164 (get-char-attribute variant 'ideographic-products))))
165 (setq dest (intersection dest products)))
168 (defun ideograph-find-products-with-variants (components &optional ignored-chars)
169 (if (stringp components)
170 (setq components (string-to-char-list components)))
172 (dolist (variant (char-component-variants (car components)))
176 (get-char-attribute variant 'ideographic-products)
180 (setq components (cdr components)))
182 (dolist (variant (char-component-variants (car components)))
186 (get-char-attribute variant 'ideographic-products)
188 (setq dest (intersection dest products)))
191 (defun ideograph-find-products (components &optional ignored-chars)
192 (if (stringp components)
193 (setq components (string-to-char-list components)))
195 ;; (dolist (variant (char-component-variants (car components)))
198 ;; (get-char-attribute variant 'ideographic-products))))
199 ;; (setq dest products)
200 (setq dest (get-char-attribute (car components) 'ideographic-products))
202 (setq components (cdr components)))
203 ;; (setq products nil)
204 ;; (dolist (variant (char-component-variants (car components)))
207 ;; (get-char-attribute variant 'ideographic-products))))
208 (setq products (get-char-attribute (car components) 'ideographic-products))
209 (setq dest (intersection dest products)))
213 (defun ideographic-structure-char= (c1 c2)
216 (let ((m1 (char-ucs c1))
220 (memq c1 (char-component-variants c2)))))))
222 (defun ideographic-structure-member-compare-components (component s-component)
224 (cond ((char-ref= component s-component #'ideographic-structure-char=))
226 (if (setq ret (assq 'ideographic-structure s-component))
227 (ideographic-structure-member component (cdr ret))))
228 ((setq ret (get-char-attribute s-component 'ideographic-structure))
229 (ideographic-structure-member component ret)))))
232 (defun ideographic-structure-member (component structure)
233 "Return non-nil if COMPONENT is included in STRUCTURE."
234 (or (memq component structure)
236 (setq structure (cdr structure))
237 (ideographic-structure-member-compare-components
238 component (car structure)))
240 (setq structure (cdr structure))
241 (ideographic-structure-member-compare-components
242 component (car structure)))
244 (setq structure (cdr structure))
246 (ideographic-structure-member-compare-components
247 component (car structure))))))
251 (defun ideographic-structure-repertoire-p (structure components)
252 "Return non-nil if STRUCTURE can be constructed by a subset of COMPONENTS."
254 (let (ret s-component)
256 (while (setq structure (cdr structure))
257 (setq s-component (car structure))
258 (unless (characterp s-component)
259 (if (setq ret (find-char s-component))
260 (setq s-component ret)))
263 (if (setq ret (assq 'ideographic-structure s-component))
264 (ideographic-structure-repertoire-p
265 (cdr ret) components)))
266 ((member* s-component components
267 :test #'ideographic-structure-char=))
269 (get-char-attribute s-component
270 'ideographic-structure))
271 (ideographic-structure-repertoire-p ret components)))
276 (defvar ids-find-result-buffer "*ids-chars*")
278 (defun ids-find-format-line (c v)
279 (format "%c\t%s\t%s\n"
281 (or (let ((ucs (or (char-ucs c)
282 (encode-char c 'ucs))))
284 (cond ((<= ucs #xFFFF)
285 (format " U+%04X" ucs))
287 (format "U-%08X" ucs)))))
289 (or (ideographic-structure-to-ids v)
292 (defun ids-insert-chars-including-components* (components
293 &optional level ignored-chars)
297 (dolist (c (sort (copy-tree (ideograph-find-products components
300 (if (setq as (char-total-strokes a))
301 (if (setq bs (char-total-strokes b))
303 (ideograph-char< a b)
306 (ideograph-char< a b)))))
307 (unless (memq c ignored-chars)
308 (setq is (char-feature c 'ideographic-structure))
313 (insert (ids-find-format-line c is))
315 (ids-insert-chars-including-components*
316 (char-to-string c) (1+ level)
317 (cons c ignored-chars))))
322 (defun ids-insert-chars-including-components (components
323 &optional level ignored-chars)
328 (ids-insert-chars-including-components* components
329 level ignored-chars)))
331 (dolist (c ignored-chars)
332 (dolist (vc (char-component-variants c))
333 (unless (memq vc ignored-chars)
334 (when (setq is (get-char-attribute vc 'ideographic-structure))
339 (insert (ids-find-format-line vc is))
341 (ids-insert-chars-including-components*
342 (char-to-string vc) (1+ level)
343 (cons vc ignored-chars)))))))
344 (dolist (c (sort (copy-tree (ideograph-find-products-with-variants
345 components ignored-chars))
347 (if (setq as (char-total-strokes a))
348 (if (setq bs (char-total-strokes b))
350 (ideograph-char< a b)
353 (ideograph-char< a b)))))
354 (unless (memq c ignored-chars)
355 (setq is (get-char-attribute c 'ideographic-structure))
360 (insert (ids-find-format-line c is))
362 (ids-insert-chars-including-components*
363 (char-to-string c) (1+ level)
364 (cons c ignored-chars))))
370 (defun ids-find-chars-including-components (components)
371 "Search Ideographs whose structures have COMPONENTS."
372 (interactive "sComponents : ")
373 (with-current-buffer (get-buffer-create ids-find-result-buffer)
374 (setq buffer-read-only nil)
376 (ids-insert-chars-including-components components 0 nil)
377 ;; (let ((ignored-chars
379 ;; (ids-insert-chars-including-components components 0 nil
380 ;; #'ideograph-find-products)))
382 ;; (setq rest ignored-chars)
383 ;; ;; (dolist (c rest)
384 ;; ;; (setq ignored-chars
385 ;; ;; (union ignored-chars
386 ;; ;; (ids-insert-chars-including-components
387 ;; ;; (list c) 0 ignored-chars
388 ;; ;; #'ideograph-find-products-with-variants))))
389 ;; (ids-insert-chars-including-components components 0 ignored-chars
390 ;; #'ideograph-find-products-with-variants))
391 (goto-char (point-min)))
392 (view-buffer ids-find-result-buffer))
395 (define-obsolete-function-alias 'ideographic-structure-search-chars
396 'ids-find-chars-including-components)
399 (defun ids-find-chars-covered-by-components (components)
400 "Search Ideographs which structures are consisted by subsets of COMPONENTS."
401 (interactive "sComponents: ")
402 (if (stringp components)
403 (setq components (string-to-char-list components)))
404 (with-current-buffer (get-buffer-create ids-find-result-buffer)
405 (setq buffer-read-only nil)
409 (when (ideographic-structure-repertoire-p v components)
410 (insert (ids-find-format-line c v))))
411 'ideographic-structure)
412 (goto-char (point-min)))
413 (view-buffer ids-find-result-buffer))
416 (defun ideographic-structure-merge-components-alist (ca1 ca2)
417 (let ((dest-alist ca1)
420 (if (setq ret (assq (car cell) dest-alist))
421 (setcdr ret (+ (cdr ret)(cdr cell)))
422 (setq dest-alist (cons cell dest-alist))))
425 (defun ideographic-structure-to-components-alist (structure)
426 (apply #'ideographic-structure-to-components-alist* structure))
428 (defun ideographic-structure-to-components-alist* (operator component1 component2
431 (let (dest-alist ret)
433 (cond ((characterp component1)
434 (unless (encode-char component1 'ascii)
435 (list (cons component1 1)))
437 ((setq ret (assq 'ideographic-structure component1))
438 (ideographic-structure-to-components-alist (cdr ret))
440 ((setq ret (find-char component1))
444 (ideographic-structure-merge-components-alist
446 (cond ((characterp component2)
447 (unless (encode-char component2 'ascii)
448 (list (cons component2 1)))
450 ((setq ret (assq 'ideographic-structure component2))
451 (ideographic-structure-to-components-alist (cdr ret))
453 ((setq ret (find-char component2))
456 (if (memq operator '(?\u2FF2 ?\u2FF3))
457 (ideographic-structure-merge-components-alist
459 (cond ((characterp component3)
460 (unless (encode-char component3 'ascii)
461 (list (cons component3 1)))
463 ((setq ret (assq 'ideographic-structure component3))
464 (ideographic-structure-to-components-alist (cdr ret))
466 ((setq ret (find-char component3))
471 (defun ids-find-merge-variables (ve1 ve2)
477 (let ((dest-alist ve1)
481 (setq cell (car rest))
482 (if (setq ret (assq (car cell) ve1))
483 (eq (cdr ret)(cdr cell))
484 (setq dest-alist (cons cell dest-alist))))
485 (setq rest (cdr rest)))
491 (defun ideographic-structure-equal (structure1 structure2)
492 (let (dest-alist ret)
493 (and (setq dest-alist (ideographic-structure-character=
494 (car structure1)(car structure2)))
495 (setq ret (ideographic-structure-character=
496 (nth 1 structure1)(nth 1 structure2)))
497 (setq dest-alist (ids-find-merge-variables dest-alist ret))
498 (setq ret (ideographic-structure-character=
499 (nth 2 structure1)(nth 2 structure2)))
500 (setq dest-alist (ids-find-merge-variables dest-alist ret))
501 (if (memq (car structure1) '(?\u2FF2 ?\u2FF3))
502 (and (setq ret (ideographic-structure-character=
503 (nth 3 structure1)(nth 3 structure2)))
504 (setq dest-alist (ids-find-merge-variables dest-alist ret)))
508 (defun ideographic-structure-character= (c1 c2)
510 (cond ((characterp c1)
511 (cond ((encode-char c1 'ascii)
515 (if (encode-char c2 'ascii)
519 ((setq ret2 (find-char c2))
522 ((setq ret2 (assq 'ideographic-structure c2))
523 (and (setq ret (get-char-attribute c1 'ideographic-structure))
524 (ideographic-structure-equal ret (cdr ret2)))
527 ((setq ret (assq 'ideographic-structure c1))
528 (cond ((characterp c2)
529 (if (encode-char c2 'ascii)
531 (and (setq ret2 (get-char-attribute c2 'ideographic-structure))
532 (ideographic-structure-equal (cdr ret) ret2)))
534 ((setq ret2 (find-char c2))
535 (and (setq ret2 (get-char-attribute ret2 'ideographic-structure))
536 (ideographic-structure-equal (cdr ret) ret2))
538 ((setq ret2 (assq 'ideographic-structure c2))
539 (ideographic-structure-equal (cdr ret)(cdr ret2))
542 ((setq ret (find-char c1))
543 (cond ((characterp c2)
544 (if (encode-char c2 'ascii)
548 ((setq ret2 (find-char c2))
551 ((setq ret2 (assq 'ideographic-structure c2))
552 (and (setq ret (get-char-attribute ret 'ideographic-structure))
553 (ideographic-structure-equal ret (cdr ret2))
557 (defun ideographic-structure-find-chars (structure)
558 (let ((comp-alist (ideographic-structure-to-components-alist structure))
561 (sort (mapcar (lambda (cell)
562 (if (setq ret (get-char-attribute
563 (car cell) 'ideographic-products))
564 (cons ret (length ret))
568 (< (cdr a)(cdr b))))))
569 (when (and (setq str (get-char-attribute pc 'ideographic-structure))
570 (ideographic-structure-equal str structure))
571 (setq pl (cons pc pl))
576 (defun ideographic-char-count-components (char component)
579 (cond ((eq char component)
581 ((setq structure (get-char-attribute char 'ideographic-structure))
582 (dolist (cell (ideographic-structure-to-components-alist structure))
585 (if (eq (car cell) char)
587 (* (ideographic-char-count-components (car cell) component)
595 (defun ideographic-character-get-structure (character)
596 "Return ideographic-structure of CHARACTER.
597 CHARACTER can be a character or char-spec."
599 (cond ((characterp character)
600 (get-char-attribute character 'ideographic-structure)
602 ((setq ret (assq 'ideographic-structure character))
605 ((setq ret (find-char character))
606 (get-char-attribute ret 'ideographic-structure)
610 (defun ideographic-char-match-component (char component)
611 "Return non-nil if character CHAR has COMPONENT in ideographic-structure.
612 COMPONENT can be a character or char-spec."
613 (or (ideographic-structure-character= char component)
614 (let ((str (ideographic-character-get-structure char)))
616 (or (ideographic-char-match-component (nth 1 str) component)
617 (ideographic-char-match-component (nth 2 str) component)
618 (if (memq (car str) '(?\u2FF2 ?\u2FF3))
619 (ideographic-char-match-component (nth 3 str) component)))))))
621 (defun ideographic-structure-char< (a b)
622 (let ((sa (get-char-attribute a 'ideographic-structure))
623 (sb (get-char-attribute b 'ideographic-structure))
627 (setq tsa (char-total-strokes a)
628 tsb (char-total-strokes b))
633 (ideograph-char< a b)))
637 (ideograph-char< a b))))
645 (setq tsa (char-total-strokes a)
646 tsb (char-total-strokes b))
651 (ideograph-char< a b)))
655 (ideograph-char< a b)))
660 (defun ideographic-chars-to-is-a-tree (chars)
661 (let (comp char products others dest rest
663 (setq chars (sort chars #'ideographic-structure-char<))
665 (setq comp (pop chars)
670 (setq char (pop rest))
672 ((ideographic-char-match-component char comp)
679 ;; (nreverse products)
681 (sort (ideographic-chars-to-is-a-tree products)
683 (setq la (length (cdr a))
687 (ideograph-char< (car a) (car b))
689 ;; (setq tsa (char-total-strokes (car a))
690 ;; tsb (char-total-strokes (car b)))
696 ;; (car a) (car b))))
700 ;; (ideograph-char< (car a) (car b)))))
708 (defun ids-find-chars-including-ids* (operator component1 component2
709 &optional component3)
710 (let ((comp-alist (ideographic-structure-to-components-alist*
711 operator component1 component2 component3))
713 (list (list* 'ideographic-structure
714 operator component1 component2
716 (list component3)))))
719 (sort (mapcar (lambda (cell)
720 (if (setq ret (get-char-attribute
721 (car cell) 'ideographic-products))
722 (cons ret (length ret))
726 (< (cdr a)(cdr b))))))
727 (when (and (every (lambda (cell)
728 (>= (ideographic-char-count-components pc (car cell))
731 (or (ideographic-char-match-component pc comp-spec)
732 (and (setq str (get-char-attribute pc 'ideographic-structure))
733 (ideographic-char-match-component
736 'ideographic-structure
737 (functional-ideographic-structure-to-apparent-structure
741 (ideographic-chars-to-is-a-tree rest)))
743 (defun ids-find-chars-including-ids (structure)
744 (if (characterp structure)
745 (setq structure (get-char-attribute structure 'ideographic-structure)))
746 (apply #'ids-find-chars-including-ids* structure))
748 (defun functional-ideographic-structure-to-apparent-structure (structure)
749 (ideographic-structure-compare-functional-and-apparent
750 structure nil 'conversion-only)
751 ;; (ideographic-structure-compact
752 ;; (let (enc enc-str enc2-str new-str)
754 ;; ((eq (car structure) ?⿸)
755 ;; (setq enc (nth 1 structure))
756 ;; (when (setq enc-str
757 ;; (cond ((characterp enc)
758 ;; (get-char-attribute enc 'ideographic-structure)
761 ;; (cdr (assq 'ideographic-structure enc))
764 ;; ((eq (car enc-str) ?⿰)
765 ;; (list ?⿰ (nth 1 enc-str)
766 ;; (list (list 'ideographic-structure
769 ;; (nth 2 structure))))
771 ;; ((and (eq (car enc-str) ?⿲)
772 ;; (memq (char-ucs (nth 1 enc-str)) '(#x4EBB #x2E85))
773 ;; (eq (nth 2 enc-str) ?丨))
775 ;; (decode-char '=big5-cdp #x8B7A)
776 ;; (list (list 'ideographic-structure
779 ;; (nth 2 structure))))
781 ;; ((eq (car enc-str) ?⿱)
782 ;; (list ?⿱ (nth 1 enc-str)
784 ;; (cons 'ideographic-structure
785 ;; (or (functional-ideographic-structure-to-apparent-structure
789 ;; ((characterp (nth 2 enc-str))
790 ;; (if (or (eq (encode-char
814 ;; (eq (or (encode-char
819 ;; '=big5-cdp-itaiji-001))
822 ;; (get-char-attribute
824 ;; 'ideographic-structure))
830 ;; (assq 'ideographic-structure
831 ;; (nth 2 enc-str))))
841 ;; ((eq (car enc-str) ?⿸)
842 ;; (list ?⿸ (nth 1 enc-str)
844 ;; (cons 'ideographic-structure
848 ;; ((characterp (nth 2 enc-str))
849 ;; (if (memq (char-ucs (nth 2 enc-str))
857 ;; (nth 2 structure))))))
860 ;; ((eq (car structure) ?⿹)
861 ;; (setq enc (nth 1 structure))
862 ;; (when (setq enc-str
863 ;; (cond ((characterp enc)
864 ;; (get-char-attribute enc 'ideographic-structure)
867 ;; (cdr (assq 'ideographic-structure enc))
870 ;; ((eq (car enc-str) ?⿰)
872 ;; (list (list 'ideographic-structure
875 ;; (nth 2 structure)))
879 ;; ((eq (get-char-attribute (car structure) '=ucs-itaiji-001) #x2FF6)
880 ;; (setq enc (nth 1 structure))
881 ;; (when (setq enc-str
882 ;; (cond ((characterp enc)
883 ;; (get-char-attribute enc 'ideographic-structure)
886 ;; (cdr (assq 'ideographic-structure enc))
889 ;; ((eq (car enc-str) ?⿺)
891 ;; (list (list 'ideographic-structure
897 ;; ((eq (car enc-str) ?⿱)
899 ;; (list (list 'ideographic-structure
907 ;; ((eq (car structure) ?⿴)
908 ;; (setq enc (nth 1 structure))
909 ;; (when (setq enc-str
910 ;; (cond ((characterp enc)
911 ;; (get-char-attribute enc 'ideographic-structure)
914 ;; (cdr (assq 'ideographic-structure enc))
917 ;; ((eq (car enc-str) ?⿱)
919 ;; ((and (characterp (nth 2 enc-str))
920 ;; (or (memq (char-ucs (nth 2 enc-str)) '(#x56D7 #x5F51 #x897F))
921 ;; (eq (char-feature (nth 2 enc-str) '=>big5-cdp)
925 ;; (list (list 'ideographic-structure
928 ;; (nth 2 structure)))
931 ;; ((and (characterp (nth 2 enc-str))
932 ;; (eq (char-ucs (nth 2 enc-str)) #x51F5))
935 ;; (list (list 'ideographic-structure
938 ;; (nth 2 structure)))
941 ;; ((and (characterp (nth 1 enc-str))
942 ;; (eq (char-feature (nth 1 enc-str) '=>ucs@component)
945 ;; (list (list 'ideographic-structure
948 ;; (nth 2 structure)))
960 ;; ((eq (car structure) ?⿶)
961 ;; (setq enc (nth 1 structure))
962 ;; (when (setq enc-str
963 ;; (cond ((characterp enc)
964 ;; (get-char-attribute enc 'ideographic-structure)
967 ;; (cdr (assq 'ideographic-structure enc))
970 ;; ((eq (car enc-str) ?⿱)
971 ;; (setq enc2-str (ideographic-character-get-structure (nth 1 enc-str)))
972 ;; (when (and enc2-str
973 ;; (eq (car enc2-str) ?⿰))
975 ;; (list (list 'ideographic-structure
979 ;; (nth 2 enc2-str)))
982 ;; ((eq (car enc-str) ?⿳)
983 ;; (setq enc2-str (ideographic-character-get-structure (nth 1 enc-str)))
984 ;; (when (and enc2-str
985 ;; (eq (car enc2-str) ?⿰))
987 ;; (list (list 'ideographic-structure
991 ;; (nth 2 enc2-str)))
995 ;; ((eq (car enc-str) ?⿲)
998 ;; (list (list 'ideographic-structure
1000 ;; (nth 2 structure)
1001 ;; (nth 2 enc-str)))
1004 ;; ((eq (car enc-str) ?⿴)
1005 ;; (setq enc2-str (ideographic-character-get-structure (nth 1 enc-str)))
1006 ;; (when (and enc2-str
1007 ;; (eq (car enc2-str) ?⿰))
1010 ;; (list (list 'ideographic-structure
1012 ;; (nth 2 structure)
1013 ;; (nth 2 enc-str)))
1014 ;; (nth 2 enc2-str)))
1017 ;; ((eq (car structure) ?⿵)
1018 ;; (setq enc (nth 1 structure))
1019 ;; (when (setq enc-str
1020 ;; (cond ((characterp enc)
1021 ;; (get-char-attribute enc 'ideographic-structure)
1024 ;; (cdr (assq 'ideographic-structure enc))
1027 ;; ((eq (car enc-str) ?⿱)
1028 ;; (setq enc2-str (ideographic-character-get-structure (nth 2 enc-str)))
1029 ;; (when (and enc2-str
1030 ;; (eq (car enc2-str) ?⿰))
1033 ;; (list (list 'ideographic-structure
1036 ;; (nth 2 structure)
1037 ;; (nth 2 enc2-str)))))
1039 ;; ((eq (car enc-str) ?⿳)
1040 ;; (setq enc2-str (ideographic-character-get-structure (nth 3 enc-str)))
1041 ;; (when (and enc2-str
1042 ;; (eq (car enc2-str) ?⿰))
1046 ;; (list (list 'ideographic-structure
1049 ;; (nth 2 structure)
1050 ;; (nth 2 enc2-str)))))
1052 ;; ((eq (car enc-str) ?⿲)
1055 ;; (list (list 'ideographic-structure
1058 ;; (nth 2 structure)))
1061 ;; ((eq (car enc-str) ?⿴)
1062 ;; (setq enc2-str (ideographic-character-get-structure (nth 1 enc-str)))
1063 ;; (when (and enc2-str
1064 ;; (eq (car enc2-str) ?⿰))
1067 ;; (list (list 'ideographic-structure
1070 ;; (nth 2 structure)))
1071 ;; (nth 2 enc2-str)))
1074 ;; ((eq (car structure) ?⿻)
1075 ;; (setq enc (nth 1 structure))
1076 ;; (when (setq enc-str
1077 ;; (cond ((characterp enc)
1078 ;; (get-char-attribute enc 'ideographic-structure)
1081 ;; (cdr (assq 'ideographic-structure enc))
1084 ;; ((eq (car enc-str) ?⿱)
1087 ;; (nth 2 structure)
1095 (defun ideographic-structure-compact (structure)
1096 (let ((rest structure)
1100 (setq cell (pop rest))
1103 (cond ((setq ret (assq 'ideographic-structure cell))
1104 (setq sub (cdr ret))
1110 (if (setq ret (ideographic-structure-find-chars sub))
1112 (list (cons 'ideographic-structure sub))))
1114 (setq dest (cons cell dest)))
1117 (defun ideographic-structure-compare-functional-and-apparent (structure
1120 (let (enc enc-str enc2-str new-str new-str-c f-res a-res ret)
1122 ((eq (car structure) ?⿸)
1123 (setq enc (nth 1 structure))
1125 (cond ((characterp enc)
1126 (get-char-attribute enc 'ideographic-structure)
1129 (cdr (assq 'ideographic-structure enc))
1132 ((eq (car enc-str) ?⿰)
1133 (unless conversion-only
1134 (setq f-res (ids-find-chars-including-ids enc-str)))
1135 (setq new-str (list ?⿱
1139 (if (setq ret (ideographic-structure-find-chars new-str))
1141 (list (cons 'ideographic-structure new-str))))
1143 (list ?⿰ (nth 1 enc-str) new-str-c)
1144 (setq a-res (ids-find-chars-including-ids new-str))
1149 (list ?⿰ (nth 1 enc-str) new-str-c)
1152 ((and (eq (car enc-str) ?⿲)
1153 (memq (char-ucs (nth 1 enc-str)) '(#x4EBB #x2E85))
1154 (eq (nth 2 enc-str) ?丨))
1155 (unless conversion-only
1156 (setq f-res (ids-find-chars-including-ids enc-str)))
1157 (setq new-str (list ?⿱
1161 (if (setq ret (ideographic-structure-find-chars new-str))
1163 (list (cons 'ideographic-structure new-str))))
1165 (list ?⿰ (decode-char '=big5-cdp #x8B7A) new-str-c)
1166 (setq a-res (ids-find-chars-including-ids new-str))
1171 (list ?⿰ (decode-char '=big5-cdp #x8B7A) new-str-c)
1174 ((eq (car enc-str) ?⿱)
1175 (unless conversion-only
1176 (setq f-res (ids-find-chars-including-ids enc-str)))
1180 ((characterp (nth 2 enc-str))
1181 (if (or (eq (encode-char (nth 2 enc-str) '=>ucs@component)
1183 (eq (encode-char (nth 2 enc-str) '=>ucs@component)
1185 (eq (encode-char (nth 2 enc-str) '=>ucs@component)
1187 (eq (encode-char (nth 2 enc-str) '=big5-cdp)
1189 (eq (encode-char (nth 2 enc-str) '=>big5-cdp)
1191 (eq (encode-char (nth 2 enc-str) '=big5-cdp)
1193 (eq (or (encode-char (nth 2 enc-str) '=>big5-cdp)
1194 (encode-char (nth 2 enc-str) '=big5-cdp-itaiji-001))
1196 (eq (car (get-char-attribute (nth 2 enc-str)
1197 'ideographic-structure))
1201 ((eq (car (cdr (assq 'ideographic-structure (nth 2 enc-str))))
1209 (if (setq ret (ideographic-structure-find-chars new-str))
1211 (list (cons 'ideographic-structure new-str))))
1213 (list ?⿱ (nth 1 enc-str) new-str-c)
1214 (setq a-res (ids-find-chars-including-ids new-str))
1219 (list ?⿱ (nth 1 enc-str) new-str-c)
1220 (if (eq (car new-str) ?⿸)
1224 ((eq (car enc-str) ?⿸)
1225 (unless conversion-only
1226 (setq f-res (ids-find-chars-including-ids enc-str)))
1227 (setq new-str (list (cond
1228 ((characterp (nth 2 enc-str))
1229 (if (memq (char-ucs (nth 2 enc-str))
1239 (if (setq ret (ideographic-structure-find-chars new-str))
1241 (list (cons 'ideographic-structure new-str))))
1243 (list ?⿸ (nth 1 enc-str) new-str-c)
1244 (setq a-res (ids-find-chars-including-ids new-str))
1249 (list ?⿸ (nth 1 enc-str) new-str-c)
1250 (if (eq (car new-str) ?⿰)
1255 ((eq (car structure) ?⿹)
1256 (setq enc (nth 1 structure))
1258 (cond ((characterp enc)
1259 (get-char-attribute enc 'ideographic-structure)
1262 (cdr (assq 'ideographic-structure enc))
1265 ((eq (car enc-str) ?⿰)
1266 (unless conversion-only
1267 (setq f-res (ids-find-chars-including-ids enc-str)))
1268 (setq new-str (list ?⿱
1272 (if (setq ret (ideographic-structure-find-chars new-str))
1274 (list (cons 'ideographic-structure new-str))))
1276 (list ?⿰ new-str-c (nth 2 enc-str))
1277 (setq a-res (ids-find-chars-including-ids new-str))
1282 (list ?⿰ new-str-c (nth 2 enc-str))
1286 ((eq (get-char-attribute (car structure) '=ucs-itaiji-001) #x2FF6)
1287 (setq enc (nth 1 structure))
1289 (cond ((characterp enc)
1290 (get-char-attribute enc 'ideographic-structure)
1293 (cdr (assq 'ideographic-structure enc))
1296 ((eq (car enc-str) ?⿺)
1297 (unless conversion-only
1298 (setq f-res (ids-find-chars-including-ids enc-str)))
1299 (setq new-str (list ?⿱
1303 (if (setq ret (ideographic-structure-find-chars new-str))
1305 (list (cons 'ideographic-structure new-str))))
1307 (list ?⿺ new-str-c (nth 2 enc-str))
1308 (setq a-res (ids-find-chars-including-ids new-str))
1313 (list ?⿺ new-str-c (nth 2 enc-str))
1316 ((eq (car enc-str) ?⿱)
1317 (unless conversion-only
1318 (setq f-res (ids-find-chars-including-ids enc-str)))
1319 (setq new-str (list ?⿰
1323 (if (setq ret (ideographic-structure-find-chars new-str))
1325 (list (cons 'ideographic-structure new-str))))
1327 (list ?⿱ new-str-c (nth 2 enc-str))
1328 (setq a-res (ids-find-chars-including-ids new-str))
1333 (list ?⿱ new-str-c (nth 2 enc-str))
1338 ((eq (car structure) ?⿴)
1339 (setq enc (nth 1 structure))
1341 (cond ((characterp enc)
1342 (get-char-attribute enc 'ideographic-structure)
1345 (cdr (assq 'ideographic-structure enc))
1348 ((eq (car enc-str) ?⿱)
1350 ((and (characterp (nth 2 enc-str))
1351 (or (memq (char-ucs (nth 2 enc-str)) '(#x56D7 #x5F51 #x897F))
1352 (eq (char-feature (nth 2 enc-str) '=>big5-cdp)
1354 (unless conversion-only
1355 (setq f-res (ids-find-chars-including-ids enc-str)))
1356 (setq new-str (list ?⿴
1360 (if (setq ret (ideographic-structure-find-chars new-str))
1362 (list (cons 'ideographic-structure new-str))))
1364 (list ?⿱ (nth 1 enc-str) new-str-c)
1365 (setq a-res (ids-find-chars-including-ids new-str))
1370 (list ?⿱ (nth 1 enc-str) new-str-c)
1373 ((and (characterp (nth 2 enc-str))
1374 (eq (char-ucs (nth 2 enc-str)) #x51F5))
1375 (unless conversion-only
1376 (setq f-res (ids-find-chars-including-ids enc-str)))
1377 (setq new-str (list ?⿶
1381 (if (setq ret (ideographic-structure-find-chars new-str))
1383 (list (cons 'ideographic-structure new-str))))
1385 (list ?⿱ (nth 1 enc-str) new-str-c)
1386 (setq a-res (ids-find-chars-including-ids new-str))
1391 (list ?⿱ (nth 1 enc-str) new-str-c)
1394 ((and (characterp (nth 1 enc-str))
1395 (eq (char-feature (nth 1 enc-str) '=>ucs@component)
1397 (unless conversion-only
1398 (setq f-res (ids-find-chars-including-ids enc-str)))
1399 (setq new-str (list ?⿵
1403 (if (setq ret (ideographic-structure-find-chars new-str))
1405 (list (cons 'ideographic-structure new-str))))
1407 (list ?⿱ new-str-c (nth 2 enc-str))
1408 (setq a-res (ids-find-chars-including-ids new-str))
1413 (list ?⿱ new-str-c (nth 2 enc-str))
1417 (unless conversion-only
1418 (setq f-res (ids-find-chars-including-ids enc-str)))
1419 (setq new-str (list ?⿱ (nth 2 structure) (nth 2 enc-str)))
1421 (if (setq ret (ideographic-structure-find-chars new-str))
1423 (list (cons 'ideographic-structure new-str))))
1425 (list ?⿱ (nth 1 enc-str) new-str-c)
1426 (setq a-res (ids-find-chars-including-ids new-str))
1431 (list ?⿱ (nth 1 enc-str) new-str-c)
1435 ((eq (car enc-str) ?⿳)
1437 ((and (characterp (nth 2 enc-str))
1438 (eq (char-ucs (nth 2 enc-str)) #x56D7))
1439 (unless conversion-only
1440 (setq f-res (ids-find-chars-including-ids enc-str)))
1441 (setq new-str (list ?⿴ (nth 2 enc-str) (nth 2 structure)))
1443 (if (setq ret (ideographic-structure-find-chars new-str))
1445 (list (cons 'ideographic-structure new-str))))
1446 (setq new-str (list ?⿱ (nth 1 enc-str) new-str-c))
1448 (if (setq ret (ideographic-structure-find-chars new-str))
1450 (list (cons 'ideographic-structure new-str))))
1452 (list ?⿱ new-str-c (nth 3 enc-str))
1453 (setq a-res (ids-find-chars-including-ids new-str))
1458 (list ?⿱ new-str-c (nth 3 enc-str))
1461 ((and (characterp (nth 2 enc-str))
1462 (eq (char-ucs (nth 2 enc-str)) #x5196))
1463 (unless conversion-only
1464 (setq f-res (ids-find-chars-including-ids enc-str)))
1465 (setq new-str (list ?⿱ (nth 1 enc-str) (nth 2 enc-str)))
1467 (if (setq ret (ideographic-structure-find-chars new-str))
1469 (list (cons 'ideographic-structure new-str))))
1470 (setq new-str (list ?⿱ new-str-c (nth 2 structure)))
1472 (if (setq ret (ideographic-structure-find-chars new-str))
1474 (list (cons 'ideographic-structure new-str))))
1476 (list ?⿱ new-str-c (nth 3 enc-str))
1477 (setq a-res (ids-find-chars-including-ids new-str))
1482 (list ?⿱ new-str-c (nth 3 enc-str))
1485 ((and (characterp (nth 2 enc-str))
1486 (or (eq (encode-char (nth 2 enc-str) '=>big5-cdp)
1488 (eq (encode-char (nth 2 enc-str) '=>gt-k)
1490 (eq (char-ucs (nth 2 enc-str)) #x2008A)))
1491 (unless conversion-only
1492 (setq f-res (ids-find-chars-including-ids enc-str)))
1493 (setq new-str (list ?⿱ (nth 2 structure) (nth 2 enc-str)))
1495 (if (setq ret (ideographic-structure-find-chars new-str))
1497 (list (cons 'ideographic-structure new-str))))
1498 (setq new-str (list ?⿸ new-str-c (nth 3 enc-str)))
1500 (if (setq ret (ideographic-structure-find-chars new-str))
1502 (list (cons 'ideographic-structure new-str))))
1504 (list ?⿱ (nth 1 enc-str) new-str-c)
1505 (setq a-res (ids-find-chars-including-ids new-str))
1510 (list ?⿱ (nth 1 enc-str) new-str-c)
1514 (unless conversion-only
1515 (setq f-res (ids-find-chars-including-ids enc-str)))
1516 (setq new-str (list ?⿻ (nth 2 enc-str) (nth 2 structure)))
1518 (if (setq ret (ideographic-structure-find-chars new-str))
1520 (list (cons 'ideographic-structure new-str))))
1521 (setq new-str (list ?⿱ (nth 1 enc-str) new-str-c))
1523 (if (setq ret (ideographic-structure-find-chars new-str))
1525 (list (cons 'ideographic-structure new-str))))
1527 (list ?⿱ new-str-c (nth 3 enc-str))
1528 (setq a-res (ids-find-chars-including-ids new-str))
1533 (list ?⿱ new-str-c (nth 3 enc-str))
1538 ((eq (car structure) ?⿶)
1539 (setq enc (nth 1 structure))
1541 (cond ((characterp enc)
1542 (get-char-attribute enc 'ideographic-structure)
1545 (cdr (assq 'ideographic-structure enc))
1548 ((eq (car enc-str) ?⿱)
1549 (setq enc2-str (ideographic-character-get-structure (nth 1 enc-str)))
1551 (eq (car enc2-str) ?⿰))
1552 (unless conversion-only
1553 (setq f-res (ids-find-chars-including-ids enc-str)))
1554 (setq new-str (list ?⿲
1559 (if (setq ret (ideographic-structure-find-chars new-str))
1561 (list (cons 'ideographic-structure new-str))))
1563 (list ?⿱ new-str-c (nth 2 enc-str))
1564 (setq a-res (ids-find-chars-including-ids new-str))
1569 (list ?⿱ new-str-c (nth 2 enc-str))
1573 ((eq (car enc-str) ?⿳)
1574 (setq enc2-str (ideographic-character-get-structure (nth 1 enc-str)))
1576 (eq (car enc2-str) ?⿰))
1577 (unless conversion-only
1578 (setq f-res (ids-find-chars-including-ids enc-str)))
1579 (setq new-str (list ?⿲
1584 (if (setq ret (ideographic-structure-find-chars new-str))
1586 (list (cons 'ideographic-structure new-str))))
1588 (list ?⿳ new-str-c (nth 2 enc-str) (nth 3 enc-str))
1589 (setq a-res (ids-find-chars-including-ids new-str))
1594 (list ?⿳ new-str-c (nth 2 enc-str) (nth 3 enc-str))
1598 ((eq (car enc-str) ?⿲)
1599 (unless conversion-only
1600 (setq f-res (ids-find-chars-including-ids enc-str)))
1601 (setq new-str (list ?⿱
1605 (if (setq ret (ideographic-structure-find-chars new-str))
1607 (list (cons 'ideographic-structure new-str))))
1609 (list ?⿲ (nth 1 enc-str) new-str-c (nth 3 enc-str))
1610 (setq a-res (ids-find-chars-including-ids new-str))
1615 (list ?⿲ (nth 1 enc-str) new-str-c (nth 3 enc-str))
1618 ((eq (car enc-str) ?⿴)
1619 (setq enc2-str (ideographic-character-get-structure (nth 1 enc-str)))
1621 (eq (car enc2-str) ?⿰))
1622 (unless conversion-only
1623 (setq f-res (ids-find-chars-including-ids enc-str)))
1624 (setq new-str (list ?⿱
1628 (if (setq ret (ideographic-structure-find-chars new-str))
1630 (list (cons 'ideographic-structure new-str))))
1632 (list ?⿲ (nth 1 enc2-str) new-str-c (nth 2 enc2-str))
1633 (setq a-res (ids-find-chars-including-ids new-str))
1638 (list ?⿲ (nth 1 enc2-str) new-str-c (nth 2 enc2-str))
1643 ((eq (car structure) ?⿵)
1644 (setq enc (nth 1 structure))
1646 (cond ((characterp enc)
1647 (get-char-attribute enc 'ideographic-structure)
1650 (cdr (assq 'ideographic-structure enc))
1653 ((eq (car enc-str) ?⿱)
1654 (setq enc2-str (ideographic-character-get-structure (nth 2 enc-str)))
1656 (eq (car enc2-str) ?⿰))
1657 (unless conversion-only
1658 (setq f-res (ids-find-chars-including-ids enc-str)))
1659 (setq new-str (list ?⿲
1664 (if (setq ret (ideographic-structure-find-chars new-str))
1666 (list (cons 'ideographic-structure new-str))))
1668 (list ?⿱ (nth 1 enc-str) new-str-c)
1669 (setq a-res (ids-find-chars-including-ids new-str))
1674 (list ?⿱ (nth 1 enc-str) new-str-c)
1678 ((eq (car enc-str) ?⿳)
1679 (setq enc2-str (ideographic-character-get-structure (nth 3 enc-str)))
1681 (eq (car enc2-str) ?⿰))
1682 (unless conversion-only
1683 (setq f-res (ids-find-chars-including-ids enc-str)))
1684 (setq new-str (list ?⿲
1689 (if (setq ret (ideographic-structure-find-chars new-str))
1691 (list (cons 'ideographic-structure new-str))))
1693 (list ?⿳ (nth 1 enc-str) (nth 2 enc-str) new-str-c)
1694 (setq a-res (ids-find-chars-including-ids new-str))
1699 (list ?⿳ (nth 1 enc-str) (nth 2 enc-str) new-str-c)
1703 ((eq (car enc-str) ?⿲)
1704 (unless conversion-only
1705 (setq f-res (ids-find-chars-including-ids enc-str)))
1706 (setq new-str (list ?⿱
1710 (if (setq ret (ideographic-structure-find-chars new-str))
1712 (list (cons 'ideographic-structure new-str))))
1714 (list ?⿲ (nth 1 enc-str) new-str-c (nth 3 enc-str))
1715 (setq a-res (ids-find-chars-including-ids new-str))
1720 (list ?⿲ (nth 1 enc-str) new-str-c (nth 3 enc-str))
1723 ((eq (car enc-str) ?⿴)
1724 (setq enc2-str (ideographic-character-get-structure (nth 1 enc-str)))
1726 (eq (car enc2-str) ?⿰))
1727 (unless conversion-only
1728 (setq f-res (ids-find-chars-including-ids enc-str)))
1729 (setq new-str (list ?⿱
1733 (if (setq ret (ideographic-structure-find-chars new-str))
1735 (list (cons 'ideographic-structure new-str))))
1737 (list ?⿲ (nth 1 enc2-str) new-str-c (nth 2 enc2-str))
1738 (setq a-res (ids-find-chars-including-ids new-str))
1743 (list ?⿲ (nth 1 enc2-str) new-str-c (nth 2 enc2-str))
1748 ((eq (car structure) ?⿷)
1749 (setq enc (nth 1 structure))
1751 (cond ((characterp enc)
1752 (get-char-attribute enc 'ideographic-structure)
1755 (cdr (assq 'ideographic-structure enc))
1758 ((eq (car enc-str) ?⿺)
1759 (unless conversion-only
1760 (setq f-res (ids-find-chars-including-ids enc-str)))
1761 (setq new-str (list ?⿱
1765 (if (setq ret (ideographic-structure-find-chars new-str))
1767 (list (cons 'ideographic-structure new-str))))
1769 (list ?⿺ (nth 1 enc-str) new-str-c)
1770 (setq a-res (ids-find-chars-including-ids new-str))
1775 (list ?⿺ (nth 1 enc-str) new-str-c)
1779 ((eq (car structure) ?⿻)
1780 (setq enc (nth 1 structure))
1782 (cond ((characterp enc)
1783 (get-char-attribute enc 'ideographic-structure)
1786 (cdr (assq 'ideographic-structure enc))
1789 ((eq (car enc-str) ?⿱)
1790 (unless conversion-only
1791 (setq f-res (ids-find-chars-including-ids enc-str)))
1793 (list ?⿳ (nth 1 enc-str) (nth 2 structure) (nth 2 enc-str))
1813 ;;; ids-find.el ends here