File: uniwbrk.in.h

package info (click to toggle)
libunistring 0.9.10-4
  • links: PTS, VCS
  • area: main
  • in suites: bullseye, sid
  • size: 28,668 kB
  • sloc: ansic: 91,149; perl: 15,827; sh: 7,478; makefile: 367; lisp: 308
file content (102 lines) | stat: -rw-r--r-- 2,963 bytes parent folder | download | duplicates (3)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
/* Word breaks in Unicode strings.
   Copyright (C) 2001-2003, 2005-2018 Free Software Foundation, Inc.
   Written by Bruno Haible <bruno@clisp.org>, 2009.

   This program is free software: you can redistribute it and/or
   modify it under the terms of either:

     * the GNU Lesser General Public License as published by the Free
       Software Foundation; either version 3 of the License, or (at your
       option) any later version.

   or

     * the GNU General Public License as published by the Free
       Software Foundation; either version 2 of the License, or (at your
       option) any later version.

   or both in parallel, as here.
   This program is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
   Lesser General Public License for more details.

   You should have received a copy of the GNU Lesser General Public License
   along with this program.  If not, see <https://www.gnu.org/licenses/>.  */

#ifndef _UNIWBRK_H
#define _UNIWBRK_H

/* Get size_t.  */
#include <stddef.h>

#include "unitypes.h"


#ifdef __cplusplus
extern "C" {
#endif

/* ========================================================================= */

/* Property defined in Unicode Standard Annex #29, section "Word Boundaries"
   <http://www.unicode.org/reports/tr29/#Word_Boundaries>  */

/* Possible values of the Word_Break property.
   This enumeration may be extended in the future.  */
enum
{
  WBP_OTHER        = 0,
  WBP_CR           = 11,
  WBP_LF           = 12,
  WBP_NEWLINE      = 10,
  WBP_EXTEND       = 8,
  WBP_FORMAT       = 9,
  WBP_KATAKANA     = 1,
  WBP_ALETTER      = 2,
  WBP_MIDNUMLET    = 3,
  WBP_MIDLETTER    = 4,
  WBP_MIDNUM       = 5,
  WBP_NUMERIC      = 6,
  WBP_EXTENDNUMLET = 7,
  WBP_RI           = 13,
  WBP_DQ           = 14,
  WBP_SQ           = 15,
  WBP_HL           = 16,
  WBP_ZWJ          = 17,
  WBP_EB           = 18,
  WBP_EM           = 19,
  WBP_GAZ          = 20,
  WBP_EBG          = 21
};

/* Return the Word_Break property of a Unicode character.  */
extern int
       uc_wordbreak_property (ucs4_t uc)
       _UC_ATTRIBUTE_CONST;

/* ========================================================================= */

/* Word breaks.  */

/* Determine the word break points in S, and store the result at p[0..n-1].
   p[i] = 1 means that there is a word boundary between s[i-1] and s[i].
   p[i] = 0 means that s[i-1] and s[i] must not be separated.
 */
extern void
       u8_wordbreaks (const uint8_t *s, size_t n, char *p);
extern void
       u16_wordbreaks (const uint16_t *s, size_t n, char *p);
extern void
       u32_wordbreaks (const uint32_t *s, size_t n, char *p);
extern void
       ulc_wordbreaks (const char *s, size_t n, char *p);

/* ========================================================================= */

#ifdef __cplusplus
}
#endif


#endif /* _UNIWBRK_H */