1 ;;; ids.el --- Parser and utility for Ideographic Description Sequence.
3 ;; Copyright (C) 2001,2002 MORIOKA Tomohiko
5 ;; Author: MORIOKA Tomohiko <tomo@kanji.zinbun.kyoto-u.ac.jp>
6 ;; Keywords: IDS, IDC, Ideographs, UCS, Unicode
8 ;; This file is a part of Tomoyo-Tools.
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 ;; Ideographic Description Sequence (IDS) is defined in ISO/IEC
28 ;; 10646-1:2000 Annex F.
32 (defun ids-parse-terminal (string)
33 (if (>= (length string) 1)
34 (let* ((chr (aref string 0))
35 (ucs (get-char-attribute chr 'ucs))
37 (unless (and ucs (<= #x2FF0 ucs)(<= ucs #x2FFF))
38 (if (and ucs (<= #xE000 ucs)(<= ucs #xF8FF)
39 (setq big5 (get-char-attribute chr 'chinese-big5)))
40 (setq chr (decode-char 'chinese-big5-cdp big5)))
42 (substring string 1))))))
44 (defun ids-parse-op-2 (string)
45 (if (>= (length string) 1)
46 (let* ((chr (aref string 0))
47 (ucs (get-char-attribute chr 'ucs)))
48 (if (or (eq ucs #x2FF0)
50 (and (<= #x2FF4 ucs)(<= ucs #x2FFB)))
52 (substring string 1))))))
54 (defun ids-parse-op-3 (string)
55 (if (>= (length string) 1)
56 (let ((chr (aref string 0)))
57 (if (memq chr '(?\u2FF2 ?\u2FF3))
59 (substring string 1))))))
61 (defun ids-parse-component (string simplify)
62 (let ((ret (ids-parse-element string simplify))
67 (setq rret (ideographic-structure-find-char
68 (cdr (assq 'ideographic-structure (car ret))))))
72 (defun ids-parse-element (string simplify)
73 (let (ret op arg1 arg2 arg3)
74 (cond ((ids-parse-terminal string))
75 ((setq ret (ids-parse-op-2 string))
77 (when (setq ret (ids-parse-component (cdr ret) simplify))
79 (when (setq ret (ids-parse-component (cdr ret) simplify))
81 (cons (list (list 'ideographic-structure op arg1 arg2))
83 ((setq ret (ids-parse-op-3 string))
85 (when (setq ret (ids-parse-component (cdr ret) simplify))
87 (when (setq ret (ids-parse-component (cdr ret) simplify))
89 (when (setq ret (ids-parse-component (cdr ret) simplify))
91 (cons (list (list 'ideographic-structure op arg1 arg2 arg3))
95 (defun ids-parse-string (ids-string &optional simplify)
96 "Parse IDS-STRING and return the result."
97 (let ((ret (ids-parse-element ids-string simplify)))
98 (if (= (length (cdr ret)) 0)
101 (defun ids-format-unit (ids-char)
103 (cond ((characterp ids-char)
104 (char-to-string ids-char))
106 (char-to-string (decode-char 'ucs ids-char)))
107 ((setq ret (find-char ids-char))
108 (char-to-string ret))
109 ((setq ret (assq 'ideographic-structure ids-char))
110 (ids-format-list (cdr ret))))))
113 (defun ids-format-list (ids-list)
114 "Format ideographic-structure IDS-LIST as an IDS-string."
115 (mapconcat (lambda (cell)
117 (if (char-ref-p cell)
118 (plist-get cell :char)