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
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
|
/* Grapheme cluster break function.
Copyright (C) 2010-2025 Free Software Foundation, Inc.
This file is free software.
It is dual-licensed under "the GNU LGPLv3+ or the GNU GPLv2+".
You can redistribute it and/or modify it under either
- the terms of the GNU Lesser General Public License as published
by the Free Software Foundation, either version 3, or (at your
option) any later version, or
- the terms of the GNU General Public License as published by the
Free Software Foundation; either version 2, or (at your option)
any later version, or
- the same dual license "the GNU LGPLv3+ or the GNU GPLv2+".
This file 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 and the GNU General Public License
for more details.
You should have received a copy of the GNU Lesser General Public
License and of the GNU General Public License along with this
program. If not, see <https://www.gnu.org/licenses/>. */
/* Written by Ben Pfaff, Daiki Ueno, Bruno Haible. */
/* This file implements section 3 "Grapheme Cluster Boundaries"
of Unicode Standard Annex #29 <https://www.unicode.org/reports/tr29/>. */
const UNIT *
FUNC (const UNIT *s, const UNIT *s_end)
{
if (s == s_end)
return NULL;
/* Grapheme Cluster break property of the last character.
-1 at the very beginning of the string. */
int last_char_prop = -1;
/* True if the last character ends a sequence of Indic_Conjunct_Break
values: consonant {extend|linker}* */
bool incb_consonant_extended = false;
/* True if the last character ends a sequence of Indic_Conjunct_Break
values: consonant {extend|linker}* linker */
bool incb_consonant_extended_linker = false;
/* True if the last character ends a sequence of Indic_Conjunct_Break
values: consonant {extend|linker}* linker {extend|linker}* */
bool incb_consonant_extended_linker_extended = false;
/* True if the last character ends an emoji modifier sequence
\p{Extended_Pictographic} Extend*. */
bool emoji_modifier_sequence = false;
/* True if the last character was immediately preceded by an
emoji modifier sequence \p{Extended_Pictographic} Extend*. */
bool emoji_modifier_sequence_before_last_char = false;
/* Number of consecutive regional indicator (RI) characters seen
immediately before the current point. */
size_t ri_count = 0;
do
{
ucs4_t uc;
int count = U_MBTOUC (&uc, s, s_end - s);
int prop = uc_graphemeclusterbreak_property (uc);
int incb = uc_indic_conjunct_break (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))
break /* *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 certain combinations of Indic_Conjunct_Break
values: Between
consonant {extend|linker}* linker {extend|linker}*
and
consonant
(GB9c). */
else if (incb_consonant_extended_linker_extended
&& incb == UC_INDIC_CONJUNCT_BREAK_CONSONANT)
/* *p = 0 */;
/* No break within emoji modifier sequences or emoji zwj sequences
(GB11). */
else if (last_char_prop == GBP_ZWJ
&& emoji_modifier_sequence_before_last_char
&& uc_is_property_extended_pictographic (uc))
/* *p = 0 */;
/* No break between RI if there is an odd number of RI
characters before (GB12, GB13). */
else if (prop == GBP_RI && (ri_count % 2) != 0)
/* *p = 0 */;
/* Break everywhere (GB999). */
else
break /* *p = 1 */;
}
incb_consonant_extended_linker =
incb_consonant_extended && incb == UC_INDIC_CONJUNCT_BREAK_LINKER;
incb_consonant_extended_linker_extended =
(incb_consonant_extended_linker
|| (incb_consonant_extended_linker_extended
&& incb >= UC_INDIC_CONJUNCT_BREAK_LINKER));
incb_consonant_extended =
(incb == UC_INDIC_CONJUNCT_BREAK_CONSONANT
|| (incb_consonant_extended
&& incb >= UC_INDIC_CONJUNCT_BREAK_LINKER));
emoji_modifier_sequence_before_last_char = emoji_modifier_sequence;
emoji_modifier_sequence =
(emoji_modifier_sequence && prop == GBP_EXTEND)
|| uc_is_property_extended_pictographic (uc);
last_char_prop = prop;
if (prop == GBP_RI)
ri_count++;
else
ri_count = 0;
s += count;
}
while (s < s_end);
return s;
}
|
