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) 2013-15 Tom Hacohen <tom at stosb dot com>
9 * This software is provided 'as-is', without any express or implied
10 * warranty. In no event will the author be held liable for any damages
11 * arising from the use of this software.
13 * Permission is granted to anyone to use this software for any purpose,
14 * including commercial applications, and to alter it and redistribute
15 * it freely, subject to the following restrictions:
17 * 1. The origin of this software must not be misrepresented; you must
18 * not claim that you wrote the original software. If you use this
19 * software in a product, an acknowledgement in the product
20 * documentation would be appreciated but is not required.
21 * 2. Altered source versions must be plainly marked as such, and must
22 * not be misrepresented as being the original software.
23 * 3. This notice may not be removed or altered from any source
26 * The main reference is Unicode Standard Annex 29 (UAX #29):
27 * <URL:http://unicode.org/reports/tr29>
29 * When this library was designed, this annex was at Revision 17, for
31 * <URL:http://www.unicode.org/reports/tr29/tr29-17.html>
33 * This library has been updated according to Revision 25, for
36 * The Unicode Terms of Use are available at
37 * <URL:http://www.unicode.org/copyright.html>
41 * @file wordbreakdef.h
43 * Definitions of internal data structures, declarations of global
44 * variables, and function prototypes for the word breaking algorithm.
46 * @version 2.6, 2015/04/19
50 #include "unibreakdef.h"
53 * Word break classes. This is a direct mapping of Table 3 of Unicode
54 * Standard Annex 29, Revision 23.
63 WBP_Regional_Indicator,
79 * Struct for entries of word break properties. The array of the
80 * entries \e must be sorted.
82 struct WordBreakProperties
84 utf32_t start; /**< Starting coding point */
85 utf32_t end; /**< End coding point */
86 enum WordBreakClass prop; /**< The word breaking property */