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
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
|
/*
* Copyright (C) 2015 The Android Open Source Project
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
#include <gtest/gtest.h>
#include <UnicodeUtils.h>
#include <minikin/GraphemeBreak.h>
using namespace android;
bool IsBreak(const char* src) {
const size_t BUF_SIZE = 256;
uint16_t buf[BUF_SIZE];
size_t offset;
size_t size;
ParseUnicode(buf, BUF_SIZE, src, &size, &offset);
return GraphemeBreak::isGraphemeBreak(buf, 0, size, offset);
}
TEST(GraphemeBreak, utf16) {
EXPECT_FALSE(IsBreak("U+D83C | U+DC31")); // emoji, U+1F431
// tests for invalid UTF-16
EXPECT_TRUE(IsBreak("U+D800 | U+D800")); // two leading surrogates
EXPECT_TRUE(IsBreak("U+DC00 | U+DC00")); // two trailing surrogates
EXPECT_TRUE(IsBreak("'a' | U+D800")); // lonely leading surrogate
EXPECT_TRUE(IsBreak("U+DC00 | 'a'")); // lonely trailing surrogate
EXPECT_TRUE(IsBreak("U+D800 | 'a'")); // leading surrogate followed by non-surrogate
EXPECT_TRUE(IsBreak("'a' | U+DC00")); // non-surrogate followed by trailing surrogate
}
TEST(GraphemeBreak, rules) {
// Rule GB1, sot ÷; Rule GB2, ÷ eot
EXPECT_TRUE(IsBreak("| 'a'"));
EXPECT_TRUE(IsBreak("'a' |"));
// Rule GB3, CR x LF
EXPECT_FALSE(IsBreak("U+000D | U+000A")); // CR x LF
// Rule GB4, (Control | CR | LF) ÷
EXPECT_TRUE(IsBreak("'a' | U+2028")); // Line separator
EXPECT_TRUE(IsBreak("'a' | U+000D")); // LF
EXPECT_TRUE(IsBreak("'a' | U+000A")); // CR
// Rule GB5, ÷ (Control | CR | LF)
EXPECT_TRUE(IsBreak("U+2028 | 'a'")); // Line separator
EXPECT_TRUE(IsBreak("U+000D | 'a'")); // LF
EXPECT_TRUE(IsBreak("U+000A | 'a'")); // CR
// Rule GB6, L x ( L | V | LV | LVT )
EXPECT_FALSE(IsBreak("U+1100 | U+1100")); // L x L
EXPECT_FALSE(IsBreak("U+1100 | U+1161")); // L x V
EXPECT_FALSE(IsBreak("U+1100 | U+AC00")); // L x LV
EXPECT_FALSE(IsBreak("U+1100 | U+AC01")); // L x LVT
// Rule GB7, ( LV | V ) x ( V | T )
EXPECT_FALSE(IsBreak("U+AC00 | U+1161")); // LV x V
EXPECT_FALSE(IsBreak("U+1161 | U+1161")); // V x V
EXPECT_FALSE(IsBreak("U+AC00 | U+11A8")); // LV x T
EXPECT_FALSE(IsBreak("U+1161 | U+11A8")); // V x T
// Rule GB8, ( LVT | T ) x T
EXPECT_FALSE(IsBreak("U+AC01 | U+11A8")); // LVT x T
EXPECT_FALSE(IsBreak("U+11A8 | U+11A8")); // T x T
// Other hangul pairs not counted above _are_ breaks (GB10)
EXPECT_TRUE(IsBreak("U+AC00 | U+1100")); // LV x L
EXPECT_TRUE(IsBreak("U+AC01 | U+1100")); // LVT x L
EXPECT_TRUE(IsBreak("U+11A8 | U+1100")); // T x L
EXPECT_TRUE(IsBreak("U+11A8 | U+AC00")); // T x LV
EXPECT_TRUE(IsBreak("U+11A8 | U+AC01")); // T x LVT
// Rule GB8a, Regional_Indicator x Regional_Indicator
EXPECT_FALSE(IsBreak("U+1F1FA | U+1F1F8"));
EXPECT_TRUE(IsBreak("U+1F1FA U+1F1F8 | U+1F1FA U+1F1F8")); // Regional indicator pair (flag)
EXPECT_FALSE(IsBreak("U+1F1FA | U+1F1F8 U+1F1FA U+1F1F8")); // Regional indicator pair (flag)
EXPECT_FALSE(IsBreak("U+1F1FA U+1F1F8 U+1F1FA | U+1F1F8")); // Regional indicator pair (flag)
EXPECT_TRUE(IsBreak("U+1F1FA U+1F1F8 | U+1F1FA")); // Regional indicator pair (flag)
EXPECT_FALSE(IsBreak("U+1F1FA | U+1F1F8 U+1F1FA")); // Regional indicator pair (flag)
EXPECT_TRUE(IsBreak("'a' U+1F1FA U+1F1F8 | U+1F1FA")); // Regional indicator pair (flag)
EXPECT_FALSE(IsBreak("'a' U+1F1FA | U+1F1F8 U+1F1FA")); // Regional indicator pair (flag)
EXPECT_TRUE(
IsBreak("'a' U+1F1FA U+1F1F8 | U+1F1FA U+1F1F8")); // Regional indicator pair (flag)
EXPECT_FALSE(
IsBreak("'a' U+1F1FA | U+1F1F8 U+1F1FA U+1F1F8")); // Regional indicator pair (flag)
EXPECT_FALSE(
IsBreak("'a' U+1F1FA U+1F1F8 U+1F1FA | U+1F1F8")); // Regional indicator pair (flag)
// Rule GB9, x Extend
EXPECT_FALSE(IsBreak("'a' | U+0301")); // combining accent
// Rule GB9a, x SpacingMark
EXPECT_FALSE(IsBreak("U+0915 | U+093E")); // KA, AA (spacing mark)
// Rule GB9b, Prepend x
// see tailoring test for prepend, as current ICU doesn't have any characters in the class
// Rule GB10, Any ÷ Any
EXPECT_TRUE(IsBreak("'a' | 'b'"));
EXPECT_TRUE(IsBreak("'f' | 'i'")); // probable ligature
EXPECT_TRUE(IsBreak("U+0644 | U+0627")); // probable ligature, lam + alef
EXPECT_TRUE(IsBreak("U+4E00 | U+4E00")); // CJK ideographs
EXPECT_TRUE(IsBreak("'a' | U+1F1FA U+1F1F8")); // Regional indicator pair (flag)
EXPECT_TRUE(IsBreak("U+1F1FA U+1F1F8 | 'a'")); // Regional indicator pair (flag)
}
TEST(GraphemeBreak, tailoring) {
// control characters that we interpret as "extend"
EXPECT_FALSE(IsBreak("'a' | U+00AD")); // soft hyphen
EXPECT_FALSE(IsBreak("'a' | U+200B")); // zwsp
EXPECT_FALSE(IsBreak("'a' | U+200E")); // lrm
EXPECT_FALSE(IsBreak("'a' | U+202A")); // lre
EXPECT_FALSE(IsBreak("'a' | U+E0041")); // tag character
// UTC-approved characters for the Prepend class
EXPECT_FALSE(IsBreak("U+06DD | U+0661")); // arabic subtending mark + digit one
EXPECT_TRUE(IsBreak("U+0E01 | U+0E33")); // Thai sara am
// virama is not a grapheme break, but "pure killer" is
EXPECT_FALSE(IsBreak("U+0915 | U+094D U+0915")); // Devanagari ka+virama+ka
EXPECT_FALSE(IsBreak("U+0915 U+094D | U+0915")); // Devanagari ka+virama+ka
EXPECT_FALSE(IsBreak("U+0E01 | U+0E3A U+0E01")); // thai phinthu = pure killer
EXPECT_TRUE(IsBreak("U+0E01 U+0E3A | U+0E01")); // thai phinthu = pure killer
// suppress grapheme breaks in zwj emoji sequences, see
// http://www.unicode.org/emoji/charts/emoji-zwj-sequences.html
EXPECT_FALSE(IsBreak("U+1F469 U+200D | U+2764 U+FE0F U+200D U+1F48B U+200D U+1F468"));
EXPECT_FALSE(IsBreak("U+1F469 U+200D U+2764 U+FE0F U+200D | U+1F48B U+200D U+1F468"));
EXPECT_FALSE(IsBreak("U+1F469 U+200D U+2764 U+FE0F U+200D U+1F48B U+200D | U+1F468"));
EXPECT_FALSE(IsBreak("U+1F468 U+200D | U+1F469 U+200D U+1F466"));
EXPECT_FALSE(IsBreak("U+1F468 U+200D U+1F469 U+200D | U+1F466"));
EXPECT_FALSE(IsBreak("U+1F469 U+200D | U+1F469 U+200D U+1F467 U+200D U+1F466"));
EXPECT_FALSE(IsBreak("U+1F469 U+200D U+1F469 U+200D | U+1F467 U+200D U+1F466"));
EXPECT_FALSE(IsBreak("U+1F469 U+200D U+1F469 U+200D U+1F467 U+200D | U+1F466"));
EXPECT_FALSE(IsBreak("U+1F441 U+200D | U+1F5E8"));
// ARABIC LETTER BEH + ZWJ + heart, not a zwj emoji sequence, so we preserve the break
EXPECT_TRUE(IsBreak("U+0628 U+200D | U+2764"));
}
TEST(GraphemeBreak, emojiModifiers) {
EXPECT_FALSE(IsBreak("U+261D | U+1F3FB")); // white up pointing index + modifier
EXPECT_FALSE(IsBreak("U+270C | U+1F3FB")); // victory hand + modifier
EXPECT_FALSE(IsBreak("U+1F466 | U+1F3FB")); // boy + modifier
EXPECT_FALSE(IsBreak("U+1F466 | U+1F3FC")); // boy + modifier
EXPECT_FALSE(IsBreak("U+1F466 | U+1F3FD")); // boy + modifier
EXPECT_FALSE(IsBreak("U+1F466 | U+1F3FE")); // boy + modifier
EXPECT_FALSE(IsBreak("U+1F466 | U+1F3FF")); // boy + modifier
EXPECT_FALSE(IsBreak("U+1F918 | U+1F3FF")); // sign of the horns + modifier
EXPECT_FALSE(IsBreak("U+1F933 | U+1F3FF")); // selfie (Unicode 9) + modifier
// adding emoji style variation selector doesn't affect grapheme cluster
EXPECT_TRUE(IsBreak("U+270C U+FE0E | U+1F3FB")); // victory hand + text style + modifier
EXPECT_FALSE(IsBreak("U+270C U+FE0F | U+1F3FB")); // heart + emoji style + modifier
// heart is not an emoji base
EXPECT_TRUE(IsBreak("U+2764 | U+1F3FB")); // heart + modifier
EXPECT_TRUE(IsBreak("U+2764 U+FE0E | U+1F3FB")); // heart + emoji style + modifier
EXPECT_TRUE(IsBreak("U+2764 U+FE0F | U+1F3FB")); // heart + emoji style + modifier
EXPECT_TRUE(IsBreak("U+1F3FB | U+1F3FB")); // modifier + modifier
// rat is not an emoji modifer
EXPECT_TRUE(IsBreak("U+1F466 | U+1F400")); // boy + rat
}
TEST(GraphemeBreak, offsets) {
uint16_t string[] = { 0x0041, 0x06DD, 0x0045, 0x0301, 0x0049, 0x0301 };
EXPECT_TRUE(GraphemeBreak::isGraphemeBreak(string, 2, 3, 2));
EXPECT_FALSE(GraphemeBreak::isGraphemeBreak(string, 2, 3, 3));
EXPECT_TRUE(GraphemeBreak::isGraphemeBreak(string, 2, 3, 4));
EXPECT_TRUE(GraphemeBreak::isGraphemeBreak(string, 2, 3, 5));
}
|
