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 (apply #'ideographic-structure-find-chars* structure))
560 (defun ideographic-structure-find-chars* (operator component1 component2
561 &optional component3)
562 (let ((comp-alist (ideographic-structure-to-components-alist*
563 operator component1 component2 component3))
568 (sort (mapcar (lambda (cell)
569 (if (setq ret (get-char-attribute
570 (car cell) 'ideographic-products))
571 (cons ret (length ret))
575 (< (cdr a)(cdr b))))))
576 (when (and (setq str (get-char-attribute pc 'ideographic-structure))
578 (ideographic-structure-character= (car str) operator))
579 (setq c1 (nth 1 str))
580 (setq ret (ideographic-structure-character= c1 component1))
581 (setq var-alist (ids-find-merge-variables var-alist ret))
582 (setq c2 (nth 2 str))
583 (setq ret (ideographic-structure-character= c2 component2))
584 (setq var-alist (ids-find-merge-variables var-alist ret))
585 (cond ((memq (car str) '(?\u2FF2 ?\u2FF3))
586 (setq c3 (nth 3 str))
587 (and (setq ret (ideographic-structure-character=
589 (ids-find-merge-variables var-alist ret))
592 (setq pl (cons pc pl))
597 (defun ideographic-char-count-components (char component)
600 (cond ((eq char component)
602 ((setq structure (get-char-attribute char 'ideographic-structure))
603 (dolist (cell (ideographic-structure-to-components-alist structure))
606 (if (eq (car cell) char)
608 (* (ideographic-char-count-components (car cell) component)
616 (defun ideographic-character-get-structure (character)
617 "Return ideographic-structure of CHARACTER.
618 CHARACTER can be a character or char-spec."
620 (cond ((characterp character)
621 (get-char-attribute character 'ideographic-structure)
623 ((setq ret (assq 'ideographic-structure character))
626 ((setq ret (find-char character))
627 (get-char-attribute ret 'ideographic-structure)
631 (defun ideographic-char-match-component (char component)
632 "Return non-nil if character CHAR has COMPONENT in ideographic-structure.
633 COMPONENT can be a character or char-spec."
634 (or (ideographic-structure-character= char component)
635 (let ((str (ideographic-character-get-structure char)))
637 (or (ideographic-char-match-component (nth 1 str) component)
638 (ideographic-char-match-component (nth 2 str) component)
639 (if (memq (car str) '(?\u2FF2 ?\u2FF3))
640 (ideographic-char-match-component (nth 3 str) component)))))))
642 (defun ideographic-structure-char< (a b)
643 (let ((sa (get-char-attribute a 'ideographic-structure))
644 (sb (get-char-attribute b 'ideographic-structure))
648 (setq tsa (char-total-strokes a)
649 tsb (char-total-strokes b))
654 (ideograph-char< a b)))
658 (ideograph-char< a b))))
666 (setq tsa (char-total-strokes a)
667 tsb (char-total-strokes b))
672 (ideograph-char< a b)))
676 (ideograph-char< a b)))
681 (defun ideographic-chars-to-is-a-tree (chars)
682 (let (comp char products others dest rest
684 (setq chars (sort chars #'ideographic-structure-char<))
686 (setq comp (pop chars)
691 (setq char (pop rest))
693 ((ideographic-char-match-component char comp)
700 ;; (nreverse products)
702 (sort (ideographic-chars-to-is-a-tree products)
704 (setq la (length (cdr a))
708 (ideograph-char< (car a) (car b))
710 ;; (setq tsa (char-total-strokes (car a))
711 ;; tsb (char-total-strokes (car b)))
717 ;; (car a) (car b))))
721 ;; (ideograph-char< (car a) (car b)))))
729 (defun ids-find-chars-including-ids* (operator component1 component2
730 &optional component3)
731 (let ((comp-alist (ideographic-structure-to-components-alist*
732 operator component1 component2 component3))
734 (list (list* 'ideographic-structure
735 operator component1 component2
737 (list component3)))))
740 (sort (mapcar (lambda (cell)
741 (if (setq ret (get-char-attribute
742 (car cell) 'ideographic-products))
743 (cons ret (length ret))
747 (< (cdr a)(cdr b))))))
748 (when (and (every (lambda (cell)
749 (>= (ideographic-char-count-components pc (car cell))
752 (or (ideographic-char-match-component pc comp-spec)
753 (and (setq str (get-char-attribute pc 'ideographic-structure))
754 (ideographic-char-match-component
757 'ideographic-structure
758 (functional-ideographic-structure-to-apparent-structure
762 (ideographic-chars-to-is-a-tree rest)))
764 (defun ids-find-chars-including-ids (structure)
765 (if (characterp structure)
766 (setq structure (get-char-attribute structure 'ideographic-structure)))
767 (apply #'ids-find-chars-including-ids* structure))
769 (defun functional-ideographic-structure-to-apparent-structure (structure)
770 (let (enc enc-str enc2-str new-str)
772 ((eq (car structure) ?⿸)
773 (setq enc (nth 1 structure))
775 (cond ((characterp enc)
776 (get-char-attribute enc 'ideographic-structure)
779 (cdr (assq 'ideographic-structure enc))
782 ((eq (car enc-str) ?⿰)
783 (list ?⿰ (nth 1 enc-str)
784 (list (list 'ideographic-structure
789 ((and (eq (car enc-str) ?⿲)
790 (memq (char-ucs (nth 1 enc-str)) '(#x4EBB #x2E85))
791 (eq (nth 2 enc-str) ?丨))
793 (decode-char '=big5-cdp #x8B7A)
794 (list (list 'ideographic-structure
799 ((eq (car enc-str) ?⿱)
800 (list ?⿱ (nth 1 enc-str)
802 (cons 'ideographic-structure
803 (or (functional-ideographic-structure-to-apparent-structure
807 ((characterp (nth 2 enc-str))
808 (if (or (eq (encode-char
837 '=big5-cdp-itaiji-001))
842 'ideographic-structure))
848 (assq 'ideographic-structure
859 ((eq (car enc-str) ?⿸)
860 (list ?⿸ (nth 1 enc-str)
862 (cons 'ideographic-structure
866 ((characterp (nth 2 enc-str))
867 (if (memq (char-ucs (nth 2 enc-str))
875 (nth 2 structure))))))
878 ((eq (car structure) ?⿹)
879 (setq enc (nth 1 structure))
881 (cond ((characterp enc)
882 (get-char-attribute enc 'ideographic-structure)
885 (cdr (assq 'ideographic-structure enc))
888 ((eq (car enc-str) ?⿰)
890 (list (list 'ideographic-structure
897 ((eq (get-char-attribute (car structure) '=ucs-itaiji-001) #x2FF6)
898 (setq enc (nth 1 structure))
900 (cond ((characterp enc)
901 (get-char-attribute enc 'ideographic-structure)
904 (cdr (assq 'ideographic-structure enc))
907 ((eq (car enc-str) ?⿺)
909 (list (list 'ideographic-structure
915 ((eq (car enc-str) ?⿱)
917 (list (list 'ideographic-structure
925 ((eq (car structure) ?⿴)
926 (setq enc (nth 1 structure))
928 (cond ((characterp enc)
929 (get-char-attribute enc 'ideographic-structure)
932 (cdr (assq 'ideographic-structure enc))
935 ((eq (car enc-str) ?⿱)
937 ((and (characterp (nth 2 enc-str))
938 (or (memq (char-ucs (nth 2 enc-str)) '(#x56D7 #x5F51 #x897F))
939 (eq (char-feature (nth 2 enc-str) '=>big5-cdp)
943 (list (list 'ideographic-structure
949 ((and (characterp (nth 2 enc-str))
950 (eq (char-ucs (nth 2 enc-str)) #x51F5))
953 (list (list 'ideographic-structure
959 ((and (characterp (nth 1 enc-str))
960 (eq (char-feature (nth 1 enc-str) '=>ucs@component)
963 (list (list 'ideographic-structure
978 ((eq (car structure) ?⿶)
979 (setq enc (nth 1 structure))
981 (cond ((characterp enc)
982 (get-char-attribute enc 'ideographic-structure)
985 (cdr (assq 'ideographic-structure enc))
988 ((eq (car enc-str) ?⿱)
989 (setq enc2-str (ideographic-character-get-structure (nth 1 enc-str)))
991 (eq (car enc2-str) ?⿰))
993 (list (list 'ideographic-structure
1000 ((eq (car enc-str) ?⿳)
1001 (setq enc2-str (ideographic-character-get-structure (nth 1 enc-str)))
1003 (eq (car enc2-str) ?⿰))
1005 (list (list 'ideographic-structure
1013 ((eq (car enc-str) ?⿲)
1016 (list (list 'ideographic-structure
1022 ((eq (car enc-str) ?⿴)
1023 (setq enc2-str (ideographic-character-get-structure (nth 1 enc-str)))
1025 (eq (car enc2-str) ?⿰))
1028 (list (list 'ideographic-structure
1035 ((eq (car structure) ?⿵)
1036 (setq enc (nth 1 structure))
1038 (cond ((characterp enc)
1039 (get-char-attribute enc 'ideographic-structure)
1042 (cdr (assq 'ideographic-structure enc))
1045 ((eq (car enc-str) ?⿱)
1046 (setq enc2-str (ideographic-character-get-structure (nth 2 enc-str)))
1048 (eq (car enc2-str) ?⿰))
1051 (list (list 'ideographic-structure
1055 (nth 2 enc2-str)))))
1057 ((eq (car enc-str) ?⿳)
1058 (setq enc2-str (ideographic-character-get-structure (nth 3 enc-str)))
1060 (eq (car enc2-str) ?⿰))
1064 (list (list 'ideographic-structure
1068 (nth 2 enc2-str)))))
1070 ((eq (car enc-str) ?⿲)
1073 (list (list 'ideographic-structure
1079 ((eq (car enc-str) ?⿴)
1080 (setq enc2-str (ideographic-character-get-structure (nth 1 enc-str)))
1082 (eq (car enc2-str) ?⿰))
1085 (list (list 'ideographic-structure
1092 ((eq (car structure) ?⿻)
1093 (setq enc (nth 1 structure))
1095 (cond ((characterp enc)
1096 (get-char-attribute enc 'ideographic-structure)
1099 (cdr (assq 'ideographic-structure enc))
1102 ((eq (car enc-str) ?⿱)
1112 (defun ideographic-structure-compact (structure)
1113 (let ((rest structure)
1117 (setq cell (pop rest))
1120 (cond ((setq ret (assq 'ideographic-structure cell))
1121 (setq sub (cdr ret))
1127 (if (setq ret (ideographic-structure-find-chars sub))
1129 (list (cons 'ideographic-structure sub))))
1131 (setq dest (cons cell dest)))
1134 (defun ideographic-structure-compare-functional-and-apparent (structure
1136 (let (enc enc-str enc2-str new-str f-res a-res code)
1138 ((eq (car structure) ?⿸)
1139 (setq enc (nth 1 structure))
1141 (cond ((characterp enc)
1142 (get-char-attribute enc 'ideographic-structure)
1145 (cdr (assq 'ideographic-structure enc))
1148 ((eq (car enc-str) ?⿰)
1149 (setq f-res (ids-find-chars-including-ids enc-str))
1150 (setq new-str (list ?⿱
1153 (setq a-res (ids-find-chars-including-ids new-str))
1160 (list (cons 'ideographic-structure new-str)))
1163 ((and (eq (car enc-str) ?⿲)
1164 (memq (char-ucs (nth 1 enc-str)) '(#x4EBB #x2E85))
1165 (eq (nth 2 enc-str) ?丨))
1166 (setq f-res (ids-find-chars-including-ids enc-str))
1167 (setq new-str (list ?⿱
1170 (setq a-res (ids-find-chars-including-ids new-str))
1176 (decode-char '=big5-cdp #x8B7A)
1177 (list (cons 'ideographic-structure new-str)))
1180 ((eq (car enc-str) ?⿱)
1181 (setq f-res (ids-find-chars-including-ids enc-str))
1185 ((characterp (nth 2 enc-str))
1186 (if (or (eq (encode-char (nth 2 enc-str) '=>ucs@component)
1188 (eq (encode-char (nth 2 enc-str) '=>ucs@component)
1190 (eq (encode-char (nth 2 enc-str) '=>ucs@component)
1192 (eq (encode-char (nth 2 enc-str) '=big5-cdp)
1194 (eq (encode-char (nth 2 enc-str) '=>big5-cdp)
1196 (eq (encode-char (nth 2 enc-str) '=big5-cdp)
1198 (eq (or (encode-char (nth 2 enc-str) '=>big5-cdp)
1199 (encode-char (nth 2 enc-str) '=big5-cdp-itaiji-001))
1201 (eq (car (get-char-attribute (nth 2 enc-str)
1202 'ideographic-structure))
1206 ((eq (car (cdr (assq 'ideographic-structure (nth 2 enc-str))))
1213 (setq a-res (ids-find-chars-including-ids new-str))
1222 (cons 'ideographic-structure
1223 (or (functional-ideographic-structure-to-apparent-structure
1226 (if (eq (car new-str) ?⿸)
1230 ((eq (car enc-str) ?⿸)
1231 (setq f-res (ids-find-chars-including-ids enc-str))
1232 (setq new-str (list (cond
1233 ((characterp (nth 2 enc-str))
1234 (if (memq (char-ucs (nth 2 enc-str))
1243 (setq a-res (ids-find-chars-including-ids new-str))
1248 (list ?⿸ (nth 1 enc-str)
1249 (list (cons 'ideographic-structure new-str)))
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 (setq f-res (ids-find-chars-including-ids enc-str))
1267 (setq new-str (list ?⿱
1270 (setq a-res (ids-find-chars-including-ids new-str))
1276 (list (cons 'ideographic-structure new-str))
1281 ((eq (get-char-attribute (car structure) '=ucs-itaiji-001) #x2FF6)
1282 (setq enc (nth 1 structure))
1284 (cond ((characterp enc)
1285 (get-char-attribute enc 'ideographic-structure)
1288 (cdr (assq 'ideographic-structure enc))
1291 ((eq (car enc-str) ?⿺)
1292 (setq f-res (ids-find-chars-including-ids enc-str))
1293 (setq new-str (list ?⿱
1296 (setq a-res (ids-find-chars-including-ids new-str))
1302 (list (cons 'ideographic-structure new-str))
1306 ((eq (car enc-str) ?⿱)
1307 (setq f-res (ids-find-chars-including-ids enc-str))
1308 (setq new-str (list ?⿰
1311 (setq a-res (ids-find-chars-including-ids new-str))
1317 (list (cons 'ideographic-structure new-str))
1323 ((eq (car structure) ?⿴)
1324 (setq enc (nth 1 structure))
1326 (cond ((characterp enc)
1327 (get-char-attribute enc 'ideographic-structure)
1330 (cdr (assq 'ideographic-structure enc))
1333 ((eq (car enc-str) ?⿱)
1335 ((and (characterp (nth 2 enc-str))
1336 (or (memq (char-ucs (nth 2 enc-str)) '(#x56D7 #x5F51 #x897F))
1337 (eq (char-feature (nth 2 enc-str) '=>big5-cdp)
1339 (setq f-res (ids-find-chars-including-ids enc-str))
1340 (setq new-str (list ?⿴
1343 (setq a-res (ids-find-chars-including-ids new-str))
1350 (list (cons 'ideographic-structure new-str)))
1353 ((and (characterp (nth 2 enc-str))
1354 (eq (char-ucs (nth 2 enc-str)) #x51F5))
1355 (setq f-res (ids-find-chars-including-ids enc-str))
1356 (setq new-str (list ?⿶
1359 (setq a-res (ids-find-chars-including-ids new-str))
1366 (list (cons 'ideographic-structure
1370 ((and (characterp (nth 1 enc-str))
1371 (eq (char-feature (nth 1 enc-str) '=>ucs@component)
1373 (setq f-res (ids-find-chars-including-ids enc-str))
1374 (setq new-str (list ?⿵
1377 (setq a-res (ids-find-chars-including-ids new-str))
1383 (list (cons 'ideographic-structure new-str))
1388 (setq f-res (ids-find-chars-including-ids enc-str))
1402 ((eq (car structure) ?⿶)
1403 (setq enc (nth 1 structure))
1405 (cond ((characterp enc)
1406 (get-char-attribute enc 'ideographic-structure)
1409 (cdr (assq 'ideographic-structure enc))
1412 ((eq (car enc-str) ?⿱)
1413 (setq enc2-str (ideographic-character-get-structure (nth 1 enc-str)))
1415 (eq (car enc2-str) ?⿰))
1416 (setq f-res (ids-find-chars-including-ids enc-str))
1417 (setq new-str (list ?⿲
1421 (setq a-res (ids-find-chars-including-ids new-str))
1427 (list (cons 'ideographic-structure new-str))
1432 ((eq (car enc-str) ?⿳)
1433 (setq enc2-str (ideographic-character-get-structure (nth 1 enc-str)))
1435 (eq (car enc2-str) ?⿰))
1436 (setq f-res (ids-find-chars-including-ids enc-str))
1437 (setq new-str (list ?⿲
1441 (setq a-res (ids-find-chars-including-ids new-str))
1447 (list (cons 'ideographic-structure new-str))
1453 ((eq (car enc-str) ?⿲)
1454 (setq f-res (ids-find-chars-including-ids enc-str))
1455 (setq new-str (list ?⿱
1458 (setq a-res (ids-find-chars-including-ids new-str))
1465 (list (cons 'ideographic-structure new-str))
1469 ((eq (car enc-str) ?⿴)
1470 (setq enc2-str (ideographic-character-get-structure (nth 1 enc-str)))
1472 (eq (car enc2-str) ?⿰))
1473 (setq f-res (ids-find-chars-including-ids enc-str))
1474 (setq new-str (list ?⿱
1477 (setq a-res (ids-find-chars-including-ids new-str))
1484 (list (cons 'ideographic-structure new-str))
1490 ((eq (car structure) ?⿵)
1491 (setq enc (nth 1 structure))
1493 (cond ((characterp enc)
1494 (get-char-attribute enc 'ideographic-structure)
1497 (cdr (assq 'ideographic-structure enc))
1500 ((eq (car enc-str) ?⿱)
1501 (setq enc2-str (ideographic-character-get-structure (nth 2 enc-str)))
1503 (eq (car enc2-str) ?⿰))
1504 (setq f-res (ids-find-chars-including-ids enc-str))
1505 (setq new-str (list ?⿲
1509 (setq a-res (ids-find-chars-including-ids new-str))
1516 (list (cons 'ideographic-structure new-str)))
1520 ((eq (car enc-str) ?⿳)
1521 (setq enc2-str (ideographic-character-get-structure (nth 3 enc-str)))
1523 (eq (car enc2-str) ?⿰))
1524 (setq f-res (ids-find-chars-including-ids enc-str))
1525 (setq new-str (list ?⿲
1529 (setq a-res (ids-find-chars-including-ids new-str))
1537 (list (cons 'ideographic-structure new-str)))
1541 ((eq (car enc-str) ?⿲)
1542 (setq f-res (ids-find-chars-including-ids enc-str))
1543 (setq new-str (list ?⿱
1546 (setq a-res (ids-find-chars-including-ids new-str))
1553 (list (cons 'ideographic-structure new-str))
1557 ((eq (car enc-str) ?⿴)
1558 (setq enc2-str (ideographic-character-get-structure (nth 1 enc-str)))
1560 (eq (car enc2-str) ?⿰))
1561 (setq f-res (ids-find-chars-including-ids enc-str))
1562 (setq new-str (list ?⿱
1565 (setq a-res (ids-find-chars-including-ids new-str))
1572 (list (cons 'ideographic-structure new-str))
1578 ((eq (car structure) ?⿻)
1579 (setq enc (nth 1 structure))
1581 (cond ((characterp enc)
1582 (get-char-attribute enc 'ideographic-structure)
1585 (cdr (assq 'ideographic-structure enc))
1588 ((eq (car enc-str) ?⿱)
1589 (setq f-res (ids-find-chars-including-ids enc-str))
1609 ;;; ids-find.el ends here