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
|
/*
* Copyright (C) 2010 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.
*/
#define LOG_TAG "Unicode_test"
#include <utils/Log.h>
#include <utils/Unicode.h>
#include <gtest/gtest.h>
namespace android {
class UnicodeTest : public testing::Test {
protected:
virtual void SetUp() {
}
virtual void TearDown() {
}
char16_t const * const kSearchString = u"I am a leaf on the wind.";
};
TEST_F(UnicodeTest, UTF8toUTF16ZeroLength) {
ssize_t measured;
const uint8_t str[] = { };
measured = utf8_to_utf16_length(str, 0);
EXPECT_EQ(0, measured)
<< "Zero length input should return zero length output.";
}
TEST_F(UnicodeTest, UTF8toUTF16ASCIILength) {
ssize_t measured;
// U+0030 or ASCII '0'
const uint8_t str[] = { 0x30 };
measured = utf8_to_utf16_length(str, sizeof(str));
EXPECT_EQ(1, measured)
<< "ASCII glyphs should have a length of 1 char16_t";
}
TEST_F(UnicodeTest, UTF8toUTF16Plane1Length) {
ssize_t measured;
// U+2323 SMILE
const uint8_t str[] = { 0xE2, 0x8C, 0xA3 };
measured = utf8_to_utf16_length(str, sizeof(str));
EXPECT_EQ(1, measured)
<< "Plane 1 glyphs should have a length of 1 char16_t";
}
TEST_F(UnicodeTest, UTF8toUTF16SurrogateLength) {
ssize_t measured;
// U+10000
const uint8_t str[] = { 0xF0, 0x90, 0x80, 0x80 };
measured = utf8_to_utf16_length(str, sizeof(str));
EXPECT_EQ(2, measured)
<< "Surrogate pairs should have a length of 2 char16_t";
}
TEST_F(UnicodeTest, UTF8toUTF16TruncatedUTF8) {
ssize_t measured;
// Truncated U+2323 SMILE
// U+2323 SMILE
const uint8_t str[] = { 0xE2, 0x8C };
measured = utf8_to_utf16_length(str, sizeof(str));
EXPECT_EQ(-1, measured)
<< "Truncated UTF-8 should return -1 to indicate invalid";
}
TEST_F(UnicodeTest, UTF8toUTF16Normal) {
const uint8_t str[] = {
0x30, // U+0030, 1 UTF-16 character
0xC4, 0x80, // U+0100, 1 UTF-16 character
0xE2, 0x8C, 0xA3, // U+2323, 1 UTF-16 character
0xF0, 0x90, 0x80, 0x80, // U+10000, 2 UTF-16 character
};
char16_t output[1 + 1 + 1 + 2 + 1]; // Room for NULL
utf8_to_utf16(str, sizeof(str), output, sizeof(output) / sizeof(output[0]));
EXPECT_EQ(0x0030, output[0])
<< "should be U+0030";
EXPECT_EQ(0x0100, output[1])
<< "should be U+0100";
EXPECT_EQ(0x2323, output[2])
<< "should be U+2323";
EXPECT_EQ(0xD800, output[3])
<< "should be first half of surrogate U+10000";
EXPECT_EQ(0xDC00, output[4])
<< "should be second half of surrogate U+10000";
EXPECT_EQ(NULL, output[5])
<< "should be NULL terminated";
}
TEST_F(UnicodeTest, strstr16EmptyTarget) {
EXPECT_EQ(strstr16(kSearchString, u""), kSearchString)
<< "should return the original pointer";
}
TEST_F(UnicodeTest, strstr16SameString) {
const char16_t* result = strstr16(kSearchString, kSearchString);
EXPECT_EQ(kSearchString, result)
<< "should return the original pointer";
}
TEST_F(UnicodeTest, strstr16TargetStartOfString) {
const char16_t* result = strstr16(kSearchString, u"I am");
EXPECT_EQ(kSearchString, result)
<< "should return the original pointer";
}
TEST_F(UnicodeTest, strstr16TargetEndOfString) {
const char16_t* result = strstr16(kSearchString, u"wind.");
EXPECT_EQ(kSearchString+19, result);
}
TEST_F(UnicodeTest, strstr16TargetWithinString) {
const char16_t* result = strstr16(kSearchString, u"leaf");
EXPECT_EQ(kSearchString+7, result);
}
TEST_F(UnicodeTest, strstr16TargetNotPresent) {
const char16_t* result = strstr16(kSearchString, u"soar");
EXPECT_EQ(nullptr, result);
}
// http://b/29267949
// Test that overreading in utf8_to_utf16_length is detected
TEST_F(UnicodeTest, InvalidUtf8OverreadDetected) {
// An utf8 char starting with \xc4 is two bytes long.
// Add extra zeros so no extra memory is read in case the code doesn't
// work as expected.
static char utf8[] = "\xc4\x00\x00\x00";
ASSERT_DEATH(utf8_to_utf16_length((uint8_t *) utf8, strlen(utf8),
true /* overreadIsFatal */), "" /* regex for ASSERT_DEATH */);
}
}
|
