1 /* vim: set expandtab tabstop=4 softtabstop=4 shiftwidth=4: */
4 * Word breaking in a Unicode sequence. Designed to be used in a
5 * generic text renderer.
7 * Copyright (C) 2013 Tom Hacohen <tom at stosb dot com>
8 * Copyright (C) 2013 Petr Filipsky <philodej at gmail dot com>
10 * This software is provided 'as-is', without any express or implied
11 * warranty. In no event will the author be held liable for any damages
12 * arising from the use of this software.
14 * Permission is granted to anyone to use this software for any purpose,
15 * including commercial applications, and to alter it and redistribute
16 * it freely, subject to the following restrictions:
18 * 1. The origin of this software must not be misrepresented; you must
19 * not claim that you wrote the original software. If you use this
20 * software in a product, an acknowledgement in the product
21 * documentation would be appreciated but is not required.
22 * 2. Altered source versions must be plainly marked as such, and must
23 * not be misrepresented as being the original software.
24 * 3. This notice may not be removed or altered from any source
27 * The main reference is Unicode Standard Annex 29 (UAX #29):
28 * <URL:http://unicode.org/reports/tr29>
30 * When this library was designed, this annex was at Revision 17, for
32 * <URL:http://www.unicode.org/reports/tr29/tr29-17.html>
34 * This library has been updated according to Revision 21, for
36 * <URL:http://www.unicode.org/reports/tr29/tr29-21.html>
38 * The Unicode Terms of Use are available at
39 * <URL:http://www.unicode.org/copyright.html>
43 * @file wordbreakdef.h
45 * Definitions of internal data structures, declarations of global
46 * variables, and function prototypes for the word breaking algorithm.
48 * @version 2.4, 2013/11/10
50 * @author Petr Filipsky
54 * Word break classes. This is a direct mapping of Table 3 of Unicode
55 * Standard Annex 29, Revision 23.
80 * Struct for entries of word break properties. The array of the
81 * entries \e must be sorted.
83 struct WordBreakProperties
85 utf32_t start; /**< Starting coding point */
86 utf32_t end; /**< End coding point */
87 enum WordBreakClass prop; /**< The word breaking property */