1/* Word breaks in Unicode strings.
2   Copyright (C) 2001-2003, 2005-2010 Free Software Foundation, Inc.
3   Written by Bruno Haible <bruno@clisp.org>, 2009.
4
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.
9
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.
14
15   You should have received a copy of the GNU Lesser General Public License
16   along with this program.  If not, see <http://www.gnu.org/licenses/>.  */
17
18#ifndef _UNIWBRK_H
19#define _UNIWBRK_H
20
21/* Get size_t.  */
22#include <stddef.h>
23
24#include "unitypes.h"
25
26
27#ifdef __cplusplus
28extern "C" {
29#endif
30
31/* ========================================================================= */
32
33/* Property defined in Unicode Standard Annex #29, section "Word Boundaries"
34   <http://www.unicode.org/reports/tr29/#Word_Boundaries>  */
35
36/* Possible values of the Word_Break property.
37   This enumeration may be extended in the future.  */
38enum
39{
40  WBP_OTHER        = 0,
41  WBP_CR           = 11,
42  WBP_LF           = 12,
43  WBP_NEWLINE      = 10,
44  WBP_EXTEND       = 8,
45  WBP_FORMAT       = 9,
46  WBP_KATAKANA     = 1,
47  WBP_ALETTER      = 2,
48  WBP_MIDNUMLET    = 3,
49  WBP_MIDLETTER    = 4,
50  WBP_MIDNUM       = 5,
51  WBP_NUMERIC      = 6,
52  WBP_EXTENDNUMLET = 7
53};
54
55/* Return the Word_Break property of a Unicode character.  */
56extern int
57       uc_wordbreak_property (ucs4_t uc);
58
59/* ========================================================================= */
60
61/* Word breaks.  */
62
63/* Determine the word break points in S, and store the result at p[0..n-1].
64   p[i] = 1 means that there is a word boundary between s[i-1] and s[i].
65   p[i] = 0 means that s[i-1] and s[i] must not be separated.
66 */
67extern void
68       u8_wordbreaks (const uint8_t *s, size_t n, char *p);
69extern void
70       u16_wordbreaks (const uint16_t *s, size_t n, char *p);
71extern void
72       u32_wordbreaks (const uint32_t *s, size_t n, char *p);
73extern void
74       ulc_wordbreaks (const char *s, size_t n, char *p);
75
76/* ========================================================================= */
77
78#ifdef __cplusplus
79}
80#endif
81
82
83#endif /* _UNIWBRK_H */
84