annotate admin/unidata/unidata-gen.el @ 90086:f16730ea4562

New file.
author Kenichi Handa <handa@m17n.org>
date Sun, 30 Jan 2005 11:22:05 +0000
parents
children 380964b11586
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
90086
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1 ;; unidata-gen.el -- Create files containing character property data.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
2 ;; Copyright (C) 2005
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
3 ;; National Institute of Advanced Industrial Science and Technology (AIST)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
4 ;; Registration Number H13PRO009
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
5
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
6 ;; This file is part of GNU Emacs.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
7
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
8 ;; GNU Emacs is free software; you can redistribute it and/or modify
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
9 ;; it under the terms of the GNU General Public License as published by
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
10 ;; the Free Software Foundation; either version 2, or (at your option)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
11 ;; any later version.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
12
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
13 ;; GNU Emacs is distributed in the hope that it will be useful,
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
14 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
15 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
16 ;; GNU General Public License for more details.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
17
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
18 ;; You should have received a copy of the GNU General Public License
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
19 ;; along with GNU Emacs; see the file COPYING. If not, write to the
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
20 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
21 ;; Boston, MA 02111-1307, USA.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
22
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
23 ;;; Commentary:
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
24
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
25 ;; FILES TO BE GENERATED
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
26 ;;
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
27 ;; The entry function `unidata-gen-files' generated these filese in
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
28 ;; the current directory.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
29 ;;
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
30 ;; charprop.el
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
31 ;; It contains a series of forms of this format:
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
32 ;; (char-code-property-register PROP FILE)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
33 ;; where PROP is a symbol representing a character property
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
34 ;; (name, geneirc-category, etc), and FILE is a name of one of
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
35 ;; the following files.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
36 ;;
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
37 ;; uni-name.el, uni-cat.el, uni-comb.el, uni-bidi.el
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
38 ;; It contains a single form of this format:
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
39 ;; (char-code-property-register PROP CHAR-TABLE)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
40 ;; where PROP is the same as above, and CHAR-TABLE is a
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
41 ;; char-table containing property values in a comporessed format.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
42 ;;
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
43 ;; When they are installed in .../lisp/international/, the file
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
44 ;; "charprop.el" is preloaded in loadup.el. The other files are
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
45 ;; automatically loaded when the functions `get-char-code-property'
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
46 ;; and `put-char-code-property' are called.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
47 ;;
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
48 ;; FORMAT OF A CHAR TABLE
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
49 ;;
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
50 ;; We want to make a file size containing a char-table small. We
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
51 ;; also want to load the file and get a property value fast. We
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
52 ;; also want to reduce the used memory after loading it. So,
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
53 ;; instead of naively storing a property value for each character in
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
54 ;; a char-table (and write it out into a file), we store compressed
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
55 ;; data in a char-table as below.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
56 ;;
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
57 ;; If succeeding 128*N characters have the same property value, we
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
58 ;; store that value for them. Otherwise, comporess values for
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
59 ;; succeeding 128 characters into a single string and store it as a
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
60 ;; value for those characters. The way of compression depends on a
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
61 ;; property. See the section "SIMPLE TABLE", "RUN-LENGTH TABLE",
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
62 ;; and "WORD-LIST TABLE".
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
63
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
64 ;; The char table has four extra slots:
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
65 ;; 1st: property symbol
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
66 ;; 2nd: function to call to get a property value
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
67 ;; 3nd: function to call to put a property value
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
68 ;; 4th: function to call to get a description of a property value
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
69 ;; 5th: data referred by the above functions
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
70 ;;
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
71 ;; The actual
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
72 ;; For more detail, see the comments in the section "SIMPLE TABLE"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
73 ;; and "NAME TABLE".
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
74
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
75 ;; The name of the file UnicodeData.txt.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
76 (defconst unidata-text-file
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
77 (expand-file-name "admin/unidata/UnicodeData.txt" source-directory))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
78
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
79 ;; List of elements of this form:
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
80 ;; (CHAR-or-RANGE PROP1 PROP2 ... PROPn)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
81 ;; CHAR-or-RANGE: a character code or a cons of character codes
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
82 ;; PROPn: string representing the nth property value
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
83
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
84 (defvar unidata-list
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
85 (let* ((table (list nil))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
86 (tail table)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
87 (block-names '(("^<CJK Ideograph" . CJK\ IDEOGRAPH)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
88 ("^<Hangul Syllable" . HANGUL\ SYLLABLE)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
89 ("^<.*Surrogate" . nil)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
90 ("^<.*Private Use" . PRIVATE\ USE)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
91 val char name)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
92 (or (file-readable-p unidata-text-file)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
93 (error "File not readable: %s" unidata-text-file))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
94 (with-temp-buffer
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
95 (call-process "sed" unidata-text-file t nil
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
96 "-e" "s/\\([^;]*\\);\\(.*\\)/(#x\\1 \\\"\\2\\\")/"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
97 "-e" "s/;/\\\" \\\"/g")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
98 (goto-char (point-min))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
99 (condition-case nil
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
100 (while t
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
101 (setq val (read (current-buffer))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
102 char (car val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
103 name (cadr val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
104
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
105 ;; Check this kind of block.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
106 ;; 4E00;<CJK Ideograph, First>;Lo;0;L;;;;;N;;;;;
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
107 ;; 9FA5;<CJK Ideograph, Last>;Lo;0;L;;;;;N;;;;;
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
108 (if (and (= (aref name 0) ?<)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
109 (string-match ", First>$" name))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
110 (let ((first char)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
111 (l block-names)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
112 block-name)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
113 (setq val (read (current-buffer))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
114 char (car val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
115 block-name (cadr val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
116 name nil)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
117 (while l
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
118 (if (string-match (caar l) block-name)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
119 (setq name (cdar l) l nil)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
120 (setq l (cdr l))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
121 (if (not name)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
122 ;; As this is a surrogate pair range, ignore it.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
123 (setq val nil)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
124 (setcar val (cons first char))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
125 (setcar (cdr val) name))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
126
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
127 (when val
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
128 (setcdr tail (list val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
129 (setq tail (cdr tail))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
130 (error nil)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
131 (cdr table)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
132
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
133 ;; Alist of this form:
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
134 ;; (PROP INDEX GENERATOR FILENAME)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
135 ;; PROP: character property
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
136 ;; INDEX: index to each element of unidata-list for PROP
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
137 ;; GENERATOR: function to generate a char-table
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
138 ;; FILENAME: filename to store the char-table
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
139 ;; DESCRIBER: function to call to get a description string of property value
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
140
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
141 (defconst unidata-prop-alist
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
142 '((name
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
143 1 unidata-gen-table-name "uni-name.el"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
144 "Unicode character name.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
145 Property value is a string.")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
146 (general-category
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
147 2 unidata-gen-table-symbol "uni-category.el"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
148 "Unicode general category.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
149 Property value is one of the following symbols:
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
150 Lu, Ll, Lt, Lm, Lo, Mn, Mc, Me, Nd, Nl, No, Pc, Pd, Ps, Pe, Pi, Pf, Po,
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
151 Sm, Sc, Sk, So, Zs, Zl, Zp, Cc, Cf, Cs, Co, Cn"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
152 unidata-describe-general-category)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
153 (canonical-combining-class
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
154 3 unidata-gen-table-integer "uni-combining.el"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
155 "Unicode canonical combining class.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
156 Property value is an integer."
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
157 unidata-describe-canonical-combining-class)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
158 (bidi-class
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
159 4 unidata-gen-table-symbol "uni-bidi.el"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
160 "Unicode bidi class.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
161 Property value is one of the following symbols:
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
162 L, LRE, LRO, R, AL, RLE, RLO, PDF, EN, ES, ET,
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
163 AN, CS, NSM, BN, B, S, WS, ON"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
164 unidata-describe-bidi-class)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
165 (decomposition
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
166 5 unidata-gen-table-decomposition "uni-decomposition.el"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
167 "Unicode decomposition mapping.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
168 Property value is a list of characters. The first element may be
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
169 one of these symbols representing compatiblity formatting tag:
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
170 <font>, <noBreak>, <initial>, <medial>, <final>, <isolated>, <circle>,
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
171 <super>, <sub>, <vertical>, <wide>, <narrow>, <small>, <square>, <fraction>,
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
172 <compat>"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
173 unidata-describe-decomposition)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
174 (decimal-digit-value
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
175 6 unidata-gen-table-integer "uni-decimal.el"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
176 "Unicode numeric value (decimal digit).
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
177 Property value is an integer.")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
178 (digit-value
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
179 7 unidata-gen-table-integer "uni-digit.el"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
180 "Unicode numeric value (digit).
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
181 Property value is an integer.")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
182 (numeric-value
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
183 8 unidata-gen-table-symbol "uni-numeric.el"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
184 "Unicode numeric value (numeric).
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
185 Property value is an symbol.")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
186 (mirrored
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
187 9 unidata-gen-table-symbol "uni-mirrored.el"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
188 "Unicode bidi mirrored flag.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
189 Property value is a symbol `Y' or `N'.")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
190 (old-name
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
191 10 unidata-gen-table-name "uni-old-name.el"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
192 "Unicode old names as published in Unicode 1.0.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
193 Property value is a string.")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
194 (iso-10646-comment
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
195 11 unidata-gen-table-name "uni-comment.el"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
196 "Unicode ISO 10646 comment.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
197 Property value is a string.")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
198 (uppercase
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
199 12 unidata-gen-table-character "uni-uppercase.el"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
200 "Unicode simple uppercase mapping.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
201 Property value is a character."
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
202 string)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
203 (lowercase
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
204 13 unidata-gen-table-character "uni-lowercase.el"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
205 "Unicode simple lowercase mapping.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
206 Property value is a character."
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
207 string)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
208 (titlecase
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
209 14 unidata-gen-table-character "uni-titlecase.el"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
210 "Unicode simple titlecase mapping.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
211 Property value is a character."
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
212 string)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
213
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
214 ;; Functions to access the above data.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
215 (defsubst unidata-prop-index (prop) (nth 1 (assq prop unidata-prop-alist)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
216 (defsubst unidata-prop-generator (prop) (nth 2 (assq prop unidata-prop-alist)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
217 (defsubst unidata-prop-file (prop) (nth 3 (assq prop unidata-prop-alist)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
218 (defsubst unidata-prop-docstring (prop) (nth 4 (assq prop unidata-prop-alist)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
219 (defsubst unidata-prop-describer (prop) (nth 5 (assq prop unidata-prop-alist)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
220
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
221
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
222 ;; SIMPLE TABLE
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
223 ;;
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
224 ;; If the type of character property value is character, and the
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
225 ;; values of succeeding character codes are usually different, we use
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
226 ;; a char-table described here to store such values.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
227 ;;
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
228 ;; If succeeding 128 characters has no property, a char-table has the
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
229 ;; symbol t is for them. Otherwise a char-table has a string of the
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
230 ;; following format for them.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
231 ;;
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
232 ;; The first character of the string is FIRST-INDEX.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
233 ;; The Nth (N > 0) character of the string is a property value of the
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
234 ;; character (BLOCk-HEAD + FIRST-INDEX + N - 1), where BLOCK-HEAD is
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
235 ;; the first of the characters in the block.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
236 ;;
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
237 ;; The 4th extra slot of a char-table is nil.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
238
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
239 (defun unidata-get-character (char val table)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
240 (cond
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
241 ((characterp val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
242 val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
243
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
244 ((stringp val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
245 (let* ((len (length val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
246 (block-head (lsh (lsh char -7) 7))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
247 (vec (make-vector 128 nil))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
248 (first-index (aref val 0)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
249 (dotimes (i (1- len))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
250 (let ((elt (aref val (1+ i))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
251 (if (> elt 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
252 (aset vec (+ first-index i) elt))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
253 (dotimes (i 128)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
254 (aset table (+ block-head i) (aref vec i)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
255 (aref vec (- char block-head))))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
256
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
257 (defun unidata-put-character (char val table)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
258 (or (characterp val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
259 (not val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
260 (error "Not an character nor nil: %S" val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
261 (let ((current-val (aref table char)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
262 (unless (eq current-val val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
263 (if (stringp current-val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
264 (funcall (char-table-extra-slot table 1) char current-val table))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
265 (aset table char val))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
266
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
267 (defun unidata-gen-table-character (prop)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
268 (let ((table (make-char-table 'char-code-property-table))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
269 (prop-idx (unidata-prop-index prop))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
270 (vec (make-vector 128 0))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
271 (tail unidata-list)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
272 elt range val idx slot)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
273 (set-char-table-range table (cons 0 (max-char)) t)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
274 (while tail
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
275 (setq elt (car tail) tail (cdr tail))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
276 (setq range (car elt)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
277 val (nth prop-idx elt))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
278 (if (= (length val) 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
279 (setq val nil)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
280 (setq val (string-to-number val 16)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
281 (if (consp range)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
282 (if val
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
283 (set-char-table-range table range val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
284 (let* ((start (lsh (lsh range -7) 7))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
285 (limit (+ start 127))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
286 first-index last-index)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
287 (fillarray vec 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
288 (if val
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
289 (aset vec (setq last-index (setq first-index (- range start)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
290 val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
291 (while (and (setq elt (car tail) range (car elt))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
292 (integerp range)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
293 (<= range limit))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
294 (setq val (nth prop-idx elt))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
295 (when (> (length val) 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
296 (aset vec (setq last-index (- range start))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
297 (string-to-number val 16))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
298 (or first-index
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
299 (setq first-index last-index)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
300 (setq tail (cdr tail)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
301 (when first-index
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
302 (let ((str (string first-index))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
303 c)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
304 (while (<= first-index last-index)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
305 (setq str (format "%s%c" str (or (aref vec first-index) 0))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
306 first-index (1+ first-index)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
307 (set-char-table-range table (cons start limit) str))))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
308
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
309 (set-char-table-extra-slot table 0 prop)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
310 (byte-compile 'unidata-get-character)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
311 (byte-compile 'unidata-put-character)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
312 (set-char-table-extra-slot table 1 (symbol-function 'unidata-get-character))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
313 (set-char-table-extra-slot table 2 (symbol-function 'unidata-put-character))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
314
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
315 table))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
316
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
317
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
318
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
319 ;; RUN-LENGTH TABLE
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
320 ;;
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
321 ;; If the type of character property value is symbol, integer,
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
322 ;; boolean, or character, we use a char-table described here to store
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
323 ;; the values.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
324 ;;
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
325 ;; The 4th extra slot is a vector of property values (VAL-TABLE), and
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
326 ;; values for succeeding 128 characters are encoded into this
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
327 ;; character sequence:
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
328 ;; ( VAL-CODE RUN-LENGTH ? ) +
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
329 ;; where:
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
330 ;; VAL-CODE (0..127):
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
331 ;; (VAL-CODE - 1) is an index into VAL-TABLE.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
332 ;; The value 0 means no-value.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
333 ;; RUN-LENGTH (130..255):
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
334 ;; (RUN-LENGTH - 128) specifies how many characters have the same
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
335 ;; value. If omitted, it means 1.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
336
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
337
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
338 ;; Return a symbol-type character property value of CHAR. VAL is the
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
339 ;; current value of (aref TABLE CHAR).
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
340
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
341 (defun unidata-get-symbol (char val table)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
342 (let ((val-table (char-table-extra-slot table 4)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
343 (cond ((symbolp val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
344 val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
345 ((stringp val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
346 (let ((first-char (lsh (lsh char -7) 7))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
347 (str val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
348 (len (length val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
349 (idx 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
350 this-val count)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
351 (set-char-table-range table (cons first-char (+ first-char 127))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
352 nil)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
353 (while (< idx len)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
354 (setq val (aref str idx) idx (1+ idx)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
355 count (if (< idx len) (aref str idx) 1))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
356 (setq val (and (> val 0) (aref val-table (1- val)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
357 count (if (< count 128)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
358 1
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
359 (prog1 (- count 128) (setq idx (1+ idx)))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
360 (dotimes (i count)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
361 (if val
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
362 (aset table first-char val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
363 (if (= first-char char)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
364 (setq this-val val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
365 (setq first-char (1+ first-char))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
366 this-val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
367 ((> val 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
368 (aref val-table (1- val))))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
369
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
370 ;; Return a integer-type character property value of CHAR. VAL is the
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
371 ;; current value of (aref TABLE CHAR).
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
372
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
373 (defun unidata-get-integer (char val table)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
374 (let ((val-table (char-table-extra-slot table 4)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
375 (cond ((integerp val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
376 val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
377 ((stringp val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
378 (let ((first-char (lsh (lsh char -7) 7))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
379 (str val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
380 (len (length val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
381 (idx 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
382 this-val count)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
383 (while (< idx len)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
384 (setq val (aref str idx) idx (1+ idx)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
385 count (if (< idx len) (aref str idx) 1))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
386 (setq val (and (> val 0) (aref val-table (1- val)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
387 count (if (< count 128)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
388 1
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
389 (prog1 (- count 128) (setq idx (1+ idx)))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
390 (dotimes (i count)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
391 (aset table first-char val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
392 (if (= first-char char)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
393 (setq this-val val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
394 (setq first-char (1+ first-char))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
395 this-val)))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
396
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
397 ;; Store VAL (symbol) as a character property value of CHAR in TABLE.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
398
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
399 (defun unidata-put-symbol (char val table)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
400 (or (symbolp val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
401 (error "Not a symbol: %S" val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
402 (let ((current-val (aref table char)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
403 (unless (eq current-val val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
404 (if (stringp current-val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
405 (funcall (char-table-extra-slot table 1) char current-val table))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
406 (aset table char val))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
407
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
408 ;; Store VAL (integer) as a character property value of CHAR in TABLE.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
409
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
410 (defun unidata-put-integer (char val table)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
411 (or (integerp val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
412 (not val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
413 (error "Not an integer nor nil: %S" val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
414 (let ((current-val (aref table char)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
415 (unless (eq current-val val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
416 (if (stringp current-val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
417 (funcall (char-table-extra-slot table 1) char current-val table))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
418 (aset table char val))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
419
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
420 ;; Encode the character property value VAL into an integer value by
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
421 ;; VAL-LIST. By side effect, VAL-LIST is modified.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
422 ;; VAL-LIST has this form:
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
423 ;; (t (VAL1 . VAL-CODE1) (VAL2 . VAL-CODE2) ...)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
424 ;; If VAL is one of VALn, just return VAL-CODEn. Otherwise,
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
425 ;; VAL-LIST is modified to this:
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
426 ;; (t (VAL . (1+ VAL-CODE1)) (VAL1 . VAL-CODE1) (VAL2 . VAL-CODE2) ...)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
427
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
428 (defun unidata-encode-val (val-list val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
429 (let ((slot (assq val val-list))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
430 val-code)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
431 (if slot
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
432 (cdr slot)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
433 (setq val-code (if (cdr val-list) (1+ (cdr (nth 1 val-list))) 1))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
434 (setcdr val-list (cons (cons val val-code) (cdr val-list)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
435 val-code)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
436
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
437 ;; Generate a char-table for the character property PROP.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
438
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
439 (defun unidata-gen-table (prop val-func default-value)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
440 (let ((table (make-char-table 'char-code-property-table))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
441 (prop-idx (unidata-prop-index prop))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
442 (val-list (list t))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
443 (vec (make-vector 128 0))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
444 tail elt range val val-code idx slot)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
445 (set-char-table-range table (cons 0 (max-char)) default-value)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
446 (setq tail unidata-list)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
447 (while tail
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
448 (setq elt (car tail) tail (cdr tail))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
449 (setq range (car elt)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
450 val (funcall val-func (nth prop-idx elt)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
451 (setq val-code (if val (unidata-encode-val val-list val)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
452 (if (consp range)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
453 (if val-code
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
454 (set-char-table-range table range val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
455 (let* ((start (lsh (lsh range -7) 7))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
456 (limit (+ start 127))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
457 str count new-val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
458 (fillarray vec 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
459 (if val-code
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
460 (aset vec (- range start) val-code))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
461 (while (and (setq elt (car tail) range (car elt))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
462 (integerp range)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
463 (<= range limit))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
464 (setq new-val (funcall val-func (nth prop-idx elt)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
465 (if (not (eq val new-val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
466 (setq val new-val
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
467 val-code (if val (unidata-encode-val val-list val))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
468 (if val-code
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
469 (aset vec (- range start) val-code))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
470 (setq tail (cdr tail)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
471 (setq str "" val-code -1 count 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
472 (mapc #'(lambda (x)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
473 (if (= val-code x)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
474 (setq count (1+ count))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
475 (if (> count 2)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
476 (setq str (concat str (string val-code
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
477 (+ count 128))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
478 (if (= count 2)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
479 (setq str (concat str (string val-code val-code)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
480 (if (= count 1)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
481 (setq str (concat str (string val-code))))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
482 (setq val-code x count 1)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
483 vec)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
484 (if (= count 128)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
485 (if val
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
486 (set-char-table-range table (cons start limit) val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
487 (if (= val-code 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
488 (set-char-table-range table (cons start limit) str)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
489 (if (> count 2)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
490 (setq str (concat str (string val-code (+ count 128))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
491 (if (= count 2)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
492 (setq str (concat str (string val-code val-code)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
493 (setq str (concat str (string val-code)))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
494 (set-char-table-range table (cons start limit) str))))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
495
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
496 (setq val-list (nreverse (cdr val-list)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
497 (set-char-table-extra-slot table 0 prop)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
498 (set-char-table-extra-slot table 4 (vconcat (mapcar 'car val-list)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
499 table))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
500
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
501 (defun unidata-gen-table-symbol (prop)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
502 (let ((table (unidata-gen-table prop
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
503 #'(lambda (x) (and (> (length x) 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
504 (intern x)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
505 0)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
506 (byte-compile 'unidata-get-symbol)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
507 (byte-compile 'unidata-put-symbol)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
508 (set-char-table-extra-slot table 1 (symbol-function 'unidata-get-symbol))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
509 (set-char-table-extra-slot table 2 (symbol-function 'unidata-put-symbol))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
510 table))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
511
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
512 (defun unidata-gen-table-integer (prop)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
513 (let ((table (unidata-gen-table prop
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
514 #'(lambda (x) (and (> (length x) 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
515 (string-to-number x)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
516 t)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
517 (byte-compile 'unidata-get-integer)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
518 (byte-compile 'unidata-put-integer)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
519 (set-char-table-extra-slot table 1 (symbol-function 'unidata-get-integer))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
520 (set-char-table-extra-slot table 2 (symbol-function 'unidata-put-integer))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
521 table))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
522
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
523
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
524 ;; WORD-LIST TABLE
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
525
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
526 ;; If the table is for `name' property, each character in the string
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
527 ;; is one of these:
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
528 ;; DIFF-HEAD-CODE (0, 1, or 2):
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
529 ;; specifies how to decode the following characters.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
530 ;; WORD-CODE (3..#x7FF excluding '-', '0'..'9', 'A'..'Z'):
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
531 ;; specifies an index number into WORD-TABLE (see below)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
532 ;; Otherwise (' ', '-', '0'..'9', 'A'..'Z'):
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
533 ;; specifies a literal word.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
534 ;;
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
535 ;; The 4th slots is a vector:
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
536 ;; [ WORD-TABLE BLOCK-NAME HANGUL-JAMO-TABLE ]
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
537 ;; WORD-TABLE is a vector of word symbols.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
538 ;; BLOCK-NAME is a vector of name symbols for a block of characters.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
539 ;; HANGUL-JAMO-TABLE is `unidata-name-jamo-name-table'.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
540
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
541 ;; Return the difference of symbol list L1 and L2 in this form:
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
542 ;; (DIFF-HEAD SYM1 SYM2 ...)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
543 ;; DIFF-HEAD is ((SAME-HEAD-LENGTH * 16) + SAME-TAIL-LENGTH).
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
544 ;; Ex: If L1 is (a b c d e f) and L2 is (a g h e f), this function
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
545 ;; returns ((+ (* 1 16) 2) g h).
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
546 ;; It means that we can get L2 from L1 by prepending the first element
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
547 ;; of L1 and appending the last 2 elements of L1 to the list (g h).
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
548 ;; If L1 and L2 don't have common elements at the head and tail,
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
549 ;; set DIFF-HEAD to -1 and SYM1 ... to the elements of L2.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
550
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
551 (defun unidata-word-list-diff (l1 l2)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
552 (let ((beg 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
553 (end 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
554 (len1 (length l1))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
555 (len2 (length l2))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
556 result)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
557 (when (< len1 16)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
558 (while (and l1 (eq (car l1) (car l2)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
559 (setq beg (1+ beg)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
560 l1 (cdr l1) len1 (1- len1) l2 (cdr l2) len2 (1- len2)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
561 (while (and (< end len1) (< end len2)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
562 (eq (nth (- len1 end 1) l1) (nth (- len2 end 1) l2)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
563 (setq end (1+ end))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
564 (if (= (+ beg end) 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
565 (setq result (list -1))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
566 (setq result (list (+ (* beg 16) (+ beg (- len1 end))))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
567 (while (< end len2)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
568 (setcdr result (cons (nth (- len2 end 1) l2) (cdr result)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
569 (setq end (1+ end)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
570 result))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
571
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
572 ;; Return a compressed form of the vector VEC. Each element of VEC is
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
573 ;; a list of symbols of which names can be concatenated to form a
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
574 ;; character name. This function changes those elements into
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
575 ;; compressed forms by utilizing the fact that diff of consecutive
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
576 ;; elements is usually small.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
577
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
578 (defun unidata-word-list-compress (vec)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
579 (let (last-elt last-idx diff-head tail elt val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
580 (dotimes (i 128)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
581 (setq elt (aref vec i))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
582 (when elt
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
583 (if (null last-elt)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
584 (setq diff-head -1
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
585 val (cons 0 elt))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
586 (setq val (unidata-word-list-diff last-elt elt))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
587 (if (= (car val) -1)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
588 (setq diff-head -1
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
589 val (cons 0 (cdr val)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
590 (if (eq diff-head (car val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
591 (setq val (cons 2 (cdr val)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
592 (setq diff-head (car val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
593 (if (>= diff-head 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
594 (setq val (cons 1 val))))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
595 (aset vec i val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
596 (setq last-idx i last-elt elt)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
597 (if (not last-idx)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
598 (setq vec nil)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
599 (if (< last-idx 127)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
600 (let ((shorter (make-vector (1+ last-idx) nil)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
601 (dotimes (i (1+ last-idx))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
602 (aset shorter i (aref vec i)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
603 (setq vec shorter))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
604 vec))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
605
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
606 ;; Encode the word index IDX into a characters code that can be
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
607 ;; embedded in a string.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
608
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
609 (defsubst unidata-encode-word (idx)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
610 ;; Exclude 0, 1, 2.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
611 (+ idx 3))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
612
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
613 ;; Decode the character code CODE (that is embedded in a string) into
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
614 ;; the corresponding word name by looking up WORD-TABLE.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
615
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
616 (defsubst unidata-decode-word (code word-table)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
617 (setq code (- code 3))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
618 (if (< code (length word-table))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
619 (aref word-table code)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
620
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
621 ;; Table of short transliterated name symbols of Hangul Jamo divided
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
622 ;; into Choseong, Jungseong, and Jongseong.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
623
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
624 (defconst unidata-name-jamo-name-table
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
625 [[G GG N D DD R M B BB S SS nil J JJ C K T P H]
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
626 [A AE YA YAE EO E YEO YE O WA WAE OE YO U WEO WE WI YU EU YI I]
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
627 [G GG GS N NJ NH D L LG LM LB LS LT LP LH M B BS S SS NG J C K T P H]])
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
628
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
629 ;; Return a name of CHAR. VAL is the current value of (aref TABLE
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
630 ;; CHAR).
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
631
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
632 (defun unidata-get-name (char val table)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
633 (cond
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
634 ((stringp val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
635 (if (> (aref val 0) 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
636 val
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
637 (let* ((first-char (lsh (lsh char -7) 7))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
638 (word-table (aref (char-table-extra-slot table 4) 0))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
639 (i 1)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
640 (len (length val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
641 (vec (make-vector 128 nil))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
642 (idx 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
643 (case-fold-search nil)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
644 c word-list tail-list last-list word diff-head)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
645 (while (< i len)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
646 (setq c (aref val i))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
647 (if (< c 3)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
648 (progn
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
649 (if (or word-list tail-list)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
650 (aset vec idx
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
651 (setq last-list (nconc word-list tail-list))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
652 (setq i (1+ i) idx (1+ idx)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
653 word-list nil tail-list nil)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
654 (if (> c 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
655 (let ((l last-list))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
656 (if (= c 1)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
657 (setq diff-head
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
658 (prog1 (aref val i) (setq i (1+ i)))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
659 (setq tail-list (nthcdr (% diff-head 16) last-list))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
660 (dotimes (i (/ diff-head 16))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
661 (setq word-list (nconc word-list (list (car l)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
662 l (cdr l))))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
663 (setq word-list
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
664 (nconc word-list
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
665 (list (symbol-name
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
666 (unidata-decode-word c word-table))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
667 i (1+ i))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
668 (if (or word-list tail-list)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
669 (aset vec idx (nconc word-list tail-list)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
670 (setq val nil)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
671 (dotimes (i 128)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
672 (setq c (+ first-char i))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
673 (let ((name (aref vec i)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
674 (if name
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
675 (let ((tail (cdr (setq name (copy-sequence name))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
676 elt)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
677 (while tail
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
678 (setq elt (car tail))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
679 (or (string= elt "-")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
680 (progn
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
681 (setcdr tail (cons elt (cdr tail)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
682 (setcar tail " ")))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
683 (setq tail (cddr tail)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
684 (setq name (apply 'concat name))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
685 (aset table c name)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
686 (if (= c char)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
687 (setq val name))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
688 val)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
689
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
690 ((and (integerp val) (> val 0))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
691 (let* ((symbol-table (aref (char-table-extra-slot table 4) 1))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
692 (sym (aref symbol-table (1- val))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
693 (cond ((eq sym 'HANGUL\ SYLLABLE)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
694 (let ((jamo-name-table (aref (char-table-extra-slot table 4) 2)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
695 ;; SIndex = S - SBase
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
696 (setq char (- char #xAC00))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
697 (let ( ;; LIndex = SIndex / NCount
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
698 (L (/ char 588))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
699 ;; VIndex = (SIndex % NCount) * TCount
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
700 (V (/ (% char 588) 28))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
701 ;; TIndex = SIndex % TCount
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
702 (T (% char 28)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
703 (format "HANGUL SYLLABLE %s%s%s"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
704 (aref (aref jamo-name-table 0) L)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
705 (aref (aref jamo-name-table 1) V)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
706 (if (= T 0) ""
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
707 (aref (aref jamo-name-table 2) (1- T)))))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
708 ((eq sym 'CJK\ COMPATIBILITY\ IDEOGRAPH)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
709 (format "%s-%04X" sym char))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
710 ((eq sym 'VARIATION\ SELECTOR)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
711 (format "%s-%d" sym (+ (- char #xe0100) 17))))))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
712
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
713 ;; Store VAL as the name of CHAR in TABLE.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
714
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
715 (defun unidata-put-name (char val table)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
716 (let ((current-val (aref table char)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
717 (if (and (stringp current-val) (= (aref current-val 0) 0))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
718 (funcall (char-table-extra-slot table 1) char current-val table))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
719 (aset table char val)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
720
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
721 (defun unidata-get-decomposition (char val table)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
722 (cond
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
723 ((consp val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
724 val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
725
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
726 ((stringp val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
727 (if (> (aref val 0) 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
728 val
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
729 (let* ((first-char (lsh (lsh char -7) 7))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
730 (word-table (char-table-extra-slot table 4))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
731 (i 1)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
732 (len (length val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
733 (vec (make-vector 128 nil))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
734 (idx 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
735 (case-fold-search nil)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
736 c word-list tail-list last-list word diff-head)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
737 (while (< i len)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
738 (setq c (aref val i))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
739 (if (< c 3)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
740 (progn
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
741 (if (or word-list tail-list)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
742 (aset vec idx
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
743 (setq last-list (nconc word-list tail-list))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
744 (setq i (1+ i) idx (1+ idx)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
745 word-list nil tail-list nil)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
746 (if (> c 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
747 (let ((l last-list))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
748 (if (= c 1)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
749 (setq diff-head
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
750 (prog1 (aref val i) (setq i (1+ i)))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
751 (setq tail-list (nthcdr (% diff-head 16) last-list))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
752 (dotimes (i (/ diff-head 16))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
753 (setq word-list (nconc word-list (list (car l)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
754 l (cdr l))))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
755 (setq word-list
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
756 (nconc word-list
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
757 (list (or (unidata-decode-word c word-table) c)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
758 i (1+ i))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
759 (if (or word-list tail-list)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
760 (aset vec idx (nconc word-list tail-list)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
761 (dotimes (i 128)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
762 (aset table (+ first-char i) (aref vec i)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
763 (aref vec (- char first-char)))))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
764
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
765 ;; Store VAL as the name of CHAR in TABLE.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
766
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
767 (defun unidata-put-decomposition (char val table)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
768 (let ((current-val (aref table char)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
769 (if (and (stringp current-val) (= (aref current-val 0) 0))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
770 (funcall (char-table-extra-slot table 1) char current-val table))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
771 (aset table char val)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
772
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
773 ;; UnicodeData.txt contains these lines:
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
774 ;; 0000;<control>;Cc;0;BN;;;;;N;NULL;;;;
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
775 ;; ...
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
776 ;; 0020;SPACE;Zs;0;WS;;;;;N;;;;;
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
777 ;; ...
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
778 ;; The following command yields a file of about 96K bytes.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
779 ;; % gawk -F ';' '{print $1,$2;}' < UnicodeData.txt | gzip > temp.gz
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
780 ;; With the following function, we can get a file of almost the same
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
781 ;; the size.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
782
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
783 ;; Generate a char-table for character names.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
784
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
785 (defun unidata-gen-table-word-list (prop val-func)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
786 (let ((table (make-char-table 'char-code-property-table))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
787 (prop-idx (unidata-prop-index prop))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
788 (word-list (list nil))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
789 word-table
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
790 block-list block-word-table block-end
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
791 tail elt range val idx slot)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
792 (set-char-table-range table (cons 0 (max-char)) 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
793 (setq tail unidata-list)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
794 (setq block-end -1)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
795 (while tail
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
796 (setq elt (car tail) tail (cdr tail))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
797 (setq range (car elt)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
798 val (funcall val-func (nth prop-idx elt)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
799 ;; Treat the sequence of "CJK COMPATIBILITY IDEOGRAPH-XXXX" and
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
800 ;; "VARIATION SELECTOR-XXX" as a block.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
801 (if (and (consp val) (eq prop 'name)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
802 (or (and (eq (car val) 'CJK)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
803 (eq (nth 1 val) 'COMPATIBILITY))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
804 (and (>= range #xe0100)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
805 (eq (car val) 'VARIATION)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
806 (eq (nth 1 val) 'SELECTOR))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
807 (let ((first (car val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
808 (second (nth 1 val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
809 (start range))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
810 (while (and (setq elt (car tail) range (car elt)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
811 val (funcall val-func (nth prop-idx elt)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
812 (consp val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
813 (eq first (car val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
814 (eq second (nth 1 val)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
815 (setq block-end range
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
816 tail (cdr tail)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
817 (setq range (cons start block-end)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
818 val (if (eq first 'CJK) 'CJK\ COMPATIBILITY\ IDEOGRAPH
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
819 'VARIATION\ SELECTOR))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
820
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
821 (if (consp range)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
822 (if val
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
823 (let ((slot (assq val block-list)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
824 (setq range (cons (car range) (cdr range)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
825 (setq block-end (cdr range))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
826 (if slot
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
827 (nconc slot (list range))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
828 (push (list val range) block-list))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
829 (let* ((start (lsh (lsh range -7) 7))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
830 (limit (+ start 127))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
831 (first tail)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
832 (vec (make-vector 128 nil))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
833 c name len)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
834 (if (<= start block-end)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
835 ;; START overlap with the previous block.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
836 (aset table range (nth prop-idx elt))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
837 (if val
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
838 (aset vec (- range start) val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
839 (while (and (setq elt (car tail) range (car elt))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
840 (integerp range)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
841 (<= range limit))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
842 (setq val (funcall val-func (nth prop-idx elt)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
843 (if val
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
844 (aset vec (- range start) val))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
845 (setq tail (cdr tail)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
846 (setq vec (unidata-word-list-compress vec))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
847 (when vec
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
848 (dotimes (i (length vec))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
849 (dolist (elt (aref vec i))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
850 (if (symbolp elt)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
851 (let ((slot (assq elt word-list)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
852 (if slot
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
853 (setcdr slot (1+ (cdr slot)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
854 (setcdr word-list
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
855 (cons (cons elt 1) (cdr word-list))))))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
856 (set-char-table-range table (cons start limit) vec))))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
857 (setq word-list (sort (cdr word-list)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
858 #'(lambda (x y) (> (cdr x) (cdr y)))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
859 (setq tail word-list idx 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
860 (while tail
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
861 (setcdr (car tail) (unidata-encode-word idx))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
862 (setq idx (1+ idx) tail (cdr tail)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
863 (setq word-table (make-vector (length word-list) nil))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
864 (setq idx 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
865 (dolist (elt word-list)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
866 (aset word-table idx (car elt))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
867 (setq idx (1+ idx)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
868
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
869 (if (and (eq prop 'decomposition)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
870 (> idx 32))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
871 (error "Too many symobls in decomposition data"))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
872
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
873 (dotimes (i (/ #x110000 128))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
874 (let* ((idx (* i 128))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
875 (vec (aref table idx)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
876 (when (vectorp vec)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
877 (dotimes (i (length vec))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
878 (let ((tail (aref vec i))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
879 elt code)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
880 (if (not tail)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
881 (aset vec i "\0")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
882 (while tail
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
883 (setq elt (car tail)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
884 code (if (integerp elt) elt
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
885 (cdr (assq elt word-list))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
886 (setcar tail (string code))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
887 (setq tail (cdr tail)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
888 (aset vec i (mapconcat 'identity (aref vec i) "")))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
889 (set-char-table-range
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
890 table (cons idx (+ idx 127))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
891 (mapconcat 'identity vec "")))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
892
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
893 (setq block-word-table (make-vector (length block-list) nil))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
894 (setq idx 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
895 (dolist (elt block-list)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
896 (dolist (e (cdr elt))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
897 (set-char-table-range table e (1+ idx)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
898 (aset block-word-table idx (car elt))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
899 (setq idx (1+ idx)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
900
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
901 (set-char-table-extra-slot table 0 prop)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
902 (set-char-table-extra-slot table 4 (cons word-table block-word-table))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
903 table))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
904
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
905 (defun unidata-split-name (str)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
906 (if (symbolp str)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
907 str
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
908 (let ((len (length str))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
909 (l nil)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
910 (idx 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
911 c)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
912 (if (= len 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
913 nil
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
914 (dotimes (i len)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
915 (setq c (aref str i))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
916 (if (= c 32)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
917 (setq l (cons (intern (substring str idx i)) l)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
918 idx (1+ i))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
919 (if (and (= c ?-) (< idx i)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
920 (< (1+ i) len) (/= (aref str (1+ i)) 32))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
921 (setq l (cons '- (cons (intern (substring str idx i)) l))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
922 idx (1+ i)))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
923 (nreverse (cons (intern (substring str idx)) l))))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
924
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
925 (defun unidata-gen-table-name (prop)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
926 (let* ((table (unidata-gen-table-word-list prop 'unidata-split-name))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
927 (word-tables (char-table-extra-slot table 4)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
928 (byte-compile 'unidata-get-name)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
929 (byte-compile 'unidata-put-name)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
930 (set-char-table-extra-slot table 1 (symbol-function 'unidata-get-name))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
931 (set-char-table-extra-slot table 2 (symbol-function 'unidata-put-name))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
932
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
933 (if (eq prop 'name)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
934 (set-char-table-extra-slot table 4
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
935 (vector (car word-tables)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
936 (cdr word-tables)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
937 unidata-name-jamo-name-table))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
938 (set-char-table-extra-slot table 4
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
939 (vector (car word-tables))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
940 table))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
941
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
942 (defun unidata-split-decomposition (str)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
943 (if (symbolp str)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
944 str
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
945 (let ((len (length str))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
946 (l nil)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
947 (idx 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
948 c)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
949 (if (= len 0)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
950 nil
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
951 (dotimes (i len)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
952 (setq c (aref str i))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
953 (if (= c 32)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
954 (setq l (if (= (aref str idx) ?<)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
955 (cons (intern (substring str idx i)) l)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
956 (cons (string-to-int (substring str idx i) 16) l))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
957 idx (1+ i))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
958 (if (= (aref str idx) ?<)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
959 (setq l (cons (intern (substring str idx len)) l))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
960 (setq l (cons (string-to-int (substring str idx len) 16) l)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
961 (nreverse l)))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
962
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
963
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
964 (defun unidata-gen-table-decomposition (prop)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
965 (let* ((table (unidata-gen-table-word-list prop 'unidata-split-decomposition))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
966 (word-tables (char-table-extra-slot table 4)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
967 (byte-compile 'unidata-get-decomposition)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
968 (byte-compile 'unidata-put-decomposition)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
969 (set-char-table-extra-slot table 1
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
970 (symbol-function 'unidata-get-decomposition))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
971 (set-char-table-extra-slot table 2
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
972 (symbol-function 'unidata-put-decomposition))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
973 (set-char-table-extra-slot table 4 (car word-tables))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
974 table))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
975
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
976
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
977
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
978 (defun unidata-describe-general-category (val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
979 (cdr (assq val
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
980 '((Lu . "Letter, Uppercase")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
981 (Ll . "Letter, Lowercase")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
982 (Lt . "Letter, Titlecase")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
983 (Lm . "Letter, Modifier")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
984 (Lo . "Letter, Other")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
985 (Mn . "Mark, Nonspacing")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
986 (Mc . "Mark, Spacing Combining")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
987 (Me . "Mark, Enclosing")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
988 (Nd . "Number, Decimal Digit")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
989 (Nl . "Number, Letter")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
990 (No . "Number, Other")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
991 (Pc . "Punctuation, Connector")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
992 (Pd . "Punctuation, Dash")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
993 (Ps . "Punctuation, Open")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
994 (Pe . "Punctuation, Close")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
995 (Pi . "Punctuation, Initial quote")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
996 (Pf . "Punctuation, Final quote")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
997 (Po . "Punctuation, Other")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
998 (Sm . "Symbol, Math")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
999 (Sc . "Symbol, Currency")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1000 (Sk . "Symbol, Modifier")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1001 (So . "Symbol, Other")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1002 (Zs . "Separator, Space")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1003 (Zl . "Separator, Line")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1004 (Zp . "Separator, Paragraph")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1005 (Cc . "Other, Control")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1006 (Cf . "Other, Format")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1007 (Cs . "Other, Surrogate")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1008 (Co . "Other, Private Use")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1009 (Cn . "Other, Not Assigned")))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1010
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1011 (defun unidata-describe-canonical-combining-class (val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1012 (cdr (assq val
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1013 '((0 . "Spacing, split, enclosing, reordrant, and Tibetan subjoined")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1014 (1 . "Overlays and interior")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1015 (7 . "Nuktas")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1016 (8 . "Hiragana/Katakana voicing marks")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1017 (9 . "Viramas")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1018 (10 . "Start of fixed position classes")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1019 (199 . "End of fixed position classes")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1020 (200 . "Below left attached")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1021 (202 . "Below attached")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1022 (204 . "Below right attached")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1023 (208 . "Left attached (reordrant around single base character)")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1024 (210 . "Right attached")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1025 (212 . "Above left attached")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1026 (214 . "Above attached")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1027 (216 . "Above right attached")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1028 (218 . "Below left")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1029 (220 . "Below")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1030 (222 . "Below right")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1031 (224 . "Left (reordrant around single base character)")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1032 (226 . "Right")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1033 (228 . "Above left")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1034 (230 . "Above")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1035 (232 . "Above right")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1036 (233 . "Double below")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1037 (234 . "Double above")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1038 (240 . "Below (iota subscript)")))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1039
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1040 (defun unidata-describe-bidi-class (val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1041 (cdr (assq val
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1042 '((L . "Left-to-Right")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1043 (LRE . "Left-to-Right Embedding")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1044 (LRO . "Left-to-Right Override")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1045 (R . "Right-to-Left")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1046 (AL . "Right-to-Left Arabic")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1047 (RLE . "Right-to-Left Embedding")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1048 (RLO . "Right-to-Left Override")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1049 (PDF . "Pop Directional Format")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1050 (EN . "European Number")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1051 (ES . "European Number Separator")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1052 (ET . "European Number Terminator")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1053 (AN . "Arabic Number")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1054 (CS . "Common Number Separator")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1055 (NSM . "Non-Spacing Mark")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1056 (BN . "Boundary Neutral")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1057 (B . "Paragraph Separator")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1058 (S . "Segment Separator")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1059 (WS . "Whitespace")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1060 (ON . "Other Neutrals")))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1061
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1062 (defun unidata-describe-decomposition (val)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1063 (mapconcat #'(lambda (x) (if (symbolp x) (symbol-name x) (string ?' x ?')))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1064 val " "))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1065
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1066 ;; Verify if we can retrieve correct values from the generated
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1067 ;; char-tables.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1068
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1069 (defun unidata-check ()
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1070 (dolist (elt unidata-prop-alist)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1071 (let* ((prop (car elt))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1072 (index (unidata-prop-index prop))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1073 (generator (unidata-prop-generator prop))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1074 (table (progn
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1075 (message "Generating %S table..." prop)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1076 (funcall generator prop)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1077 (decoder (char-table-extra-slot table 1))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1078 (check #x400))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1079 (dolist (e unidata-list)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1080 (let ((char (car e))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1081 (val1 (nth index e))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1082 val2)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1083 (if (and (stringp val1) (= (length val1) 0))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1084 (setq val1 nil))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1085 (unless (consp char)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1086 (setq val2 (funcall decoder char (aref table char) table))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1087 (if val1
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1088 (cond ((eq generator 'unidata-gen-table-symbol)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1089 (setq val1 (intern val1)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1090 ((eq generator 'unidata-gen-table-integer)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1091 (setq val1 (string-to-int val1)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1092 ((eq generator 'unidata-gen-table-character)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1093 (setq val1 (string-to-int val1 16)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1094 ((eq generator 'unidata-gen-table-decomposition)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1095 (setq val1 (unidata-split-decomposition val1)))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1096 (when (>= char check)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1097 (message "%S %04X" prop check)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1098 (setq check (+ check #x400)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1099 (or (equal val1 val2)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1100 (insert (format "> %04X %S\n< %04X %S\n"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1101 char val1 char val2)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1102 (sit-for 0)))))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1103
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1104 ;; The entry function. It generates files described in the header
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1105 ;; comment of this file.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1106
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1107 (defun unidata-gen-files ()
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1108 (interactive)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1109 (let ((coding-system-for-write 'utf-8)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1110 (charprop-file "charprop.el"))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1111 (with-temp-file charprop-file
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1112 (insert ";; Automatically generated by unidata-gen.el.\n")
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1113 (dolist (elt unidata-prop-alist)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1114 (let* ((prop (car elt))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1115 (generator (unidata-prop-generator prop))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1116 (file (unidata-prop-file prop))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1117 (docstring (unidata-prop-docstring prop))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1118 (describer (unidata-prop-describer prop))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1119 table)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1120 ;; Filename in this comment line is extracted by sed in
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1121 ;; Makefile.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1122 (insert (format ";; FILE: %s\n" file))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1123 (insert (format "(define-char-code-property '%S %S\n %S)\n"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1124 prop file docstring))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1125 (with-temp-file file
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1126 (message "Generating %s..." file)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1127 (setq table (funcall generator prop))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1128 (when describer
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1129 (unless (subrp (symbol-function describer))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1130 (byte-compile describer)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1131 (setq describer (symbol-function describer)))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1132 (set-char-table-extra-slot table 3 describer))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1133 (insert ";; Automatically generated from UnicodeData.txt.\n"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1134 (format "(define-char-code-property '%S %S %S)\n"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1135 prop table docstring)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1136 ;; \040 below is to avoid error on reading this file.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1137 ";; Local\040Variables:\n"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1138 ";; coding: utf-8\n"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1139 ";; no-byte-compile: t\n"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1140 ";; End:\n\n"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1141 (format ";; %s ends here\n" file)))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1142 (message "Writing %s..." charprop-file)
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1143 ;; \040 below is to avoid error on reading this file.
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1144 (insert ";; Local\040Variables:\n"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1145 ";; coding: utf-8\n"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1146 ";; no-byte-compile: t\n"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1147 ";; End:\n\n"
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1148 (format ";; %s ends here\n" charprop-file)))))
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1149
f16730ea4562 New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1150 ;;; unidata-gen.el ends here