1 /* Word breaks in Unicode strings.
2 Copyright (C) 2001-2003, 2005-2020 Free Software Foundation, Inc.
3 Written by Bruno Haible <bruno@clisp.org>, 2009.
5 This program is free software: you can redistribute it and/or modify it
6 under the terms of the GNU Lesser General Public License as published
7 by the Free Software Foundation; either version 3 of the License, or
8 (at your option) any later version.
10 This program is distributed in the hope that it will be useful,
11 but WITHOUT ANY WARRANTY; without even the implied warranty of
12 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
13 Lesser General Public License for more details.
15 You should have received a copy of the GNU Lesser General Public License
16 along with this program. If not, see <https://www.gnu.org/licenses/>. */
31 /* ========================================================================= */
33 /* Property defined in Unicode Standard Annex #29, section "Word Boundaries"
34 <https://www.unicode.org/reports/tr29/#Word_Boundaries> */
36 /* Possible values of the Word_Break property.
37 This enumeration may be extended in the future. */
64 /* Return the Word_Break property of a Unicode character. */
66 uc_wordbreak_property (ucs4_t uc
)
69 /* ========================================================================= */
73 /* Determine the word break points in S, and store the result at p[0..n-1].
74 p[i] = 1 means that there is a word boundary between s[i-1] and s[i].
75 p[i] = 0 means that s[i-1] and s[i] must not be separated.
78 u8_wordbreaks (const uint8_t *s
, size_t n
, char *p
);
80 u16_wordbreaks (const uint16_t *s
, size_t n
, char *p
);
82 u32_wordbreaks (const uint32_t *s
, size_t n
, char *p
);
84 ulc_wordbreaks (const char *s
, size_t n
, char *_UC_RESTRICT p
);
86 /* ========================================================================= */
93 #endif /* _UNIWBRK_H */