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
|
/**
* Big-Endian/Little-endian tests.
*/
#include "simdutf.h"
#include <tests/helpers/test.h>
// We use explicit arrays so that no funny business is possible.
const unsigned char utf8_string[] = {0x40, 0xc2, 0xa7, 0xe2, 0x88,
0x88, 0xf0, 0x9d, 0x92, 0xaa};
const char *utf8 = reinterpret_cast<const char *>(utf8_string);
const size_t utf8_size = sizeof(utf8_string) / sizeof(uint8_t);
alignas(char16_t) const unsigned char utf16le_string[] = {
0x40, 0x00, 0xa7, 0x00, 0x08, 0x22, 0x35, 0xd8, 0xaa, 0xdc};
const char16_t *utf16le = reinterpret_cast<const char16_t *>(utf16le_string);
const size_t utf16_size = sizeof(utf16le_string) / sizeof(uint16_t);
alignas(char16_t) const unsigned char utf16be_string[] = {
0x00, 0x40, 0x00, 0xa7, 0x22, 0x08, 0xd8, 0x35, 0xdc, 0xaa};
const char16_t *utf16be = reinterpret_cast<const char16_t *>(utf16be_string);
#if SIMDUTF_IS_BIG_ENDIAN
const char16_t *utf16 = utf16be;
#else
const char16_t *utf16 = utf16le;
#endif
// Native order
#if SIMDUTF_IS_BIG_ENDIAN
alignas(char32_t) const unsigned char utf32_string[] = {
0x00, 0x00, 0x00, 0x40, 0x00, 0x00, 0x00, 0xa7,
0x00, 0x00, 0x22, 0x08, 0x00, 0x01, 0xd4, 0xaa};
const char32_t *utf32 = reinterpret_cast<const char32_t *>(utf32_string);
#else
alignas(char32_t) const unsigned char utf32_string[] = {
0x40, 0x00, 0x00, 0x00, 0xa7, 0x00, 0x00, 0x00,
0x08, 0x22, 0x00, 0x00, 0xaa, 0xd4, 0x01, 0x00};
const char32_t *utf32 = reinterpret_cast<const char32_t *>(utf32_string);
#endif
const size_t utf32_size = sizeof(utf32_string) / sizeof(char32_t);
const size_t number_of_code_points = utf32_size;
TEST(validate_utf8) {
simdutf::result res =
implementation.validate_utf8_with_errors(utf8, utf8_size);
ASSERT_EQUAL(res.error, simdutf::error_code::SUCCESS);
}
TEST(validate_utf16le) {
simdutf::result res =
implementation.validate_utf16le_with_errors(utf16le, utf16_size);
ASSERT_EQUAL(res.error, simdutf::error_code::SUCCESS);
}
TEST(validate_utf16be) {
simdutf::result res =
implementation.validate_utf16be_with_errors(utf16be, utf16_size);
ASSERT_EQUAL(res.error, simdutf::error_code::SUCCESS);
}
TEST(validate_utf32) {
simdutf::result res =
implementation.validate_utf32_with_errors(utf32, utf32_size);
ASSERT_EQUAL(res.error, simdutf::error_code::SUCCESS);
}
TEST(count_utf8) {
size_t count = implementation.count_utf8(utf8, utf8_size);
ASSERT_EQUAL(count, number_of_code_points);
}
TEST(count_utf16le) {
size_t count = implementation.count_utf16le(utf16le, utf16_size);
ASSERT_EQUAL(count, number_of_code_points);
}
TEST(count_utf16be) {
size_t count = implementation.count_utf16be(
reinterpret_cast<const char16_t *>(utf16be_string),
sizeof(utf16be_string) / sizeof(uint16_t));
ASSERT_EQUAL(count, number_of_code_points);
}
TEST(convert_utf8_to_utf16le) {
char16_t buffer[utf16_size];
size_t count =
implementation.convert_utf8_to_utf16le(utf8, utf8_size, buffer);
ASSERT_EQUAL(count, utf16_size);
for (size_t i = 0; i < utf16_size; i++) {
ASSERT_EQUAL(uint16_t(buffer[i]), uint16_t(utf16le[i]));
}
}
TEST(convert_utf8_to_utf16be) {
char16_t buffer[utf16_size];
size_t count =
implementation.convert_utf8_to_utf16be(utf8, utf8_size, buffer);
ASSERT_EQUAL(count, utf16_size);
for (size_t i = 0; i < utf16_size; i++) {
ASSERT_EQUAL(uint16_t(buffer[i]), uint16_t(utf16be[i]));
}
}
TEST(convert_utf8_to_utf32) {
char32_t buffer[utf32_size];
size_t count = implementation.convert_utf8_to_utf32(utf8, utf8_size, buffer);
ASSERT_EQUAL(count, utf32_size);
for (size_t i = 0; i < utf32_size; i++) {
ASSERT_EQUAL(uint32_t(buffer[i]), uint32_t(utf32[i]));
}
}
TEST(convert_utf32_to_utf8) {
char buffer[utf8_size];
size_t count =
implementation.convert_utf32_to_utf8(utf32, utf32_size, buffer);
ASSERT_EQUAL(count, utf8_size);
for (size_t i = 0; i < utf8_size; i++) {
ASSERT_EQUAL(buffer[i], utf8[i]);
}
}
TEST(convert_utf32_to_utf16be) {
char buffer[utf8_size];
size_t count =
implementation.convert_utf32_to_utf8(utf32, utf32_size, buffer);
ASSERT_EQUAL(count, utf8_size);
for (size_t i = 0; i < utf8_size; i++) {
ASSERT_EQUAL(buffer[i], utf8[i]);
}
}
TEST(convert_utf32_to_utf16le) {
char buffer[utf8_size];
size_t count =
implementation.convert_utf32_to_utf8(utf32, utf32_size, buffer);
ASSERT_EQUAL(count, utf8_size);
for (size_t i = 0; i < utf8_size; i++) {
ASSERT_EQUAL(buffer[i], utf8[i]);
}
}
TEST(convert_utf16le_to_utf8) {
char buffer[utf8_size];
size_t count =
implementation.convert_utf16le_to_utf8(utf16le, utf16_size, buffer);
ASSERT_EQUAL(count, utf8_size);
for (size_t i = 0; i < utf8_size; i++) {
ASSERT_EQUAL(buffer[i], utf8[i]);
}
}
TEST(convert_utf16le_to_utf32) {
char32_t buffer[utf32_size];
size_t count =
implementation.convert_utf16le_to_utf32(utf16le, utf16_size, buffer);
ASSERT_EQUAL(count, utf32_size);
for (size_t i = 0; i < utf32_size; i++) {
ASSERT_EQUAL(uint32_t(buffer[i]), uint32_t(utf32[i]));
}
}
TEST(convert_utf16be_to_utf8) {
char buffer[utf8_size];
size_t count =
implementation.convert_utf16be_to_utf8(utf16be, utf16_size, buffer);
ASSERT_EQUAL(count, utf8_size);
for (size_t i = 0; i < utf8_size; i++) {
ASSERT_EQUAL(buffer[i], utf8[i]);
}
}
TEST(convert_utf16be_to_utf32) {
char32_t buffer[utf32_size];
size_t count =
implementation.convert_utf16be_to_utf32(utf16be, utf16_size, buffer);
ASSERT_EQUAL(count, utf32_size);
for (size_t i = 0; i < utf32_size; i++) {
ASSERT_EQUAL(uint32_t(buffer[i]), uint32_t(utf32[i]));
}
}
TEST_MAIN
|
