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
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
|
/* Grapheme cluster break function.
Copyright (C) 2010-2017 Free Software Foundation, Inc.
Written by Ben Pfaff <blp@cs.stanford.edu>, 2010.
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 <http://www.gnu.org/licenses/>. */
void
FUNC (const UNIT *s, size_t n, char *p)
{
if (n > 0)
{
const UNIT *s_end = s + n;
/* Grapheme Cluster break property of the last character.
-1 at the very beginning of the string. */
int last_char_prop = -1;
/* Grapheme Cluster break property of the last complex character.
-1 at the very beginning of the string. */
int last_compchar_prop = -1;
size_t ri_count = 0;
/* Don't break inside multibyte characters. */
memset (p, 0, n);
while (s < s_end)
{
ucs4_t uc;
int count = U_MBTOUC (&uc, s, s_end - s);
int prop = uc_graphemeclusterbreak_property (uc);
/* Break at the start of the string (GB1). */
if (last_char_prop < 0)
*p = 1;
else
{
/* No break between CR and LF (GB3). */
if (last_char_prop == GBP_CR && prop == GBP_LF)
/* *p = 0 */;
/* Break before and after newlines (GB4, GB5). */
else if ((last_char_prop == GBP_CR
|| last_char_prop == GBP_LF
|| last_char_prop == GBP_CONTROL)
|| (prop == GBP_CR
|| prop == GBP_LF
|| prop == GBP_CONTROL))
*p = 1;
/* No break between Hangul syllable sequences (GB6, GB7, GB8). */
else if ((last_char_prop == GBP_L
&& (prop == GBP_L
|| prop == GBP_V
|| prop == GBP_LV
|| prop == GBP_LVT))
|| ((last_char_prop == GBP_LV
|| last_char_prop == GBP_V)
&& (prop == GBP_V
|| prop == GBP_T))
|| ((last_char_prop == GBP_LVT
|| last_char_prop == GBP_T)
&& prop == GBP_T))
/* *p = 0 */;
/* No break before extending characters or ZWJ (GB9). */
else if (prop == GBP_EXTEND || prop == GBP_ZWJ)
/* *p = 0 */;
/* No break before SpacingMarks (GB9a). */
else if (prop == GBP_SPACINGMARK)
/* *p = 0 */;
/* No break after Prepend characters (GB9b). */
else if (last_char_prop == GBP_PREPEND)
/* *p = 0 */;
/* No break within emoji modifier sequences (GB10). */
else if ((last_compchar_prop == GBP_EB
|| last_compchar_prop == GBP_EBG)
&& prop == GBP_EM)
/* *p = 0 */;
/* No break within emoji zwj sequences (GB11). */
else if (last_char_prop == GBP_ZWJ
&& (prop == GBP_GAZ
|| prop == GBP_EBG))
/* *p = 0 */;
/* No break between RI if there is an odd number of RI
characters before (GB12, GB13). */
else if (prop == GBP_RI)
{
if (ri_count % 2 == 0)
*p = 1;
/* else *p = 0; */
}
/* Break everywhere (GBP999). */
else
*p = 1;
}
last_char_prop = prop;
if (!(prop == GBP_EXTEND
&& (last_compchar_prop == GBP_EB
|| last_compchar_prop == GBP_EBG)))
last_compchar_prop = prop;
if (prop == GBP_RI)
ri_count++;
else
ri_count = 0;
s += count;
p += count;
}
}
}
|
