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
187
188
189
190
191
192
193
194
195
196
197
|
//===-- Unittests for character_converter utf8->utf32 ---------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
#include "hdr/errno_macros.h"
#include "src/__support/error_or.h"
#include "src/__support/wchar/character_converter.h"
#include "src/__support/wchar/mbstate.h"
#include "test/UnitTest/Test.h"
TEST(LlvmLibcCharacterConverterUTF8To32Test, OneByte) {
LIBC_NAMESPACE::internal::mbstate state;
state.bytes_stored = 0;
state.total_bytes = 0;
char ch = 'A';
LIBC_NAMESPACE::internal::CharacterConverter char_conv(&state);
int err = char_conv.push(static_cast<char8_t>(ch));
auto wch = char_conv.pop_utf32();
ASSERT_EQ(err, 0);
ASSERT_TRUE(wch.has_value());
ASSERT_EQ(static_cast<int>(wch.value()), 65);
}
TEST(LlvmLibcCharacterConverterUTF8To32Test, TwoBytes) {
LIBC_NAMESPACE::internal::mbstate state;
state.bytes_stored = 0;
state.total_bytes = 0;
const char ch[2] = {static_cast<char>(0xC2),
static_cast<char>(0x8E)}; // car symbol
LIBC_NAMESPACE::internal::CharacterConverter char_conv(&state);
char_conv.push(static_cast<char8_t>(ch[0]));
char_conv.push(static_cast<char8_t>(ch[1]));
auto wch = char_conv.pop_utf32();
ASSERT_TRUE(wch.has_value());
ASSERT_EQ(static_cast<int>(wch.value()), 142);
}
TEST(LlvmLibcCharacterConverterUTF8To32Test, ThreeBytes) {
LIBC_NAMESPACE::internal::mbstate state;
state.bytes_stored = 0;
state.total_bytes = 0;
const char ch[3] = {static_cast<char>(0xE2), static_cast<char>(0x88),
static_cast<char>(0x91)}; // ∑ sigma symbol
LIBC_NAMESPACE::internal::CharacterConverter char_conv(&state);
char_conv.push(static_cast<char8_t>(ch[0]));
char_conv.push(static_cast<char8_t>(ch[1]));
char_conv.push(static_cast<char8_t>(ch[2]));
auto wch = char_conv.pop_utf32();
ASSERT_TRUE(wch.has_value());
ASSERT_EQ(static_cast<int>(wch.value()), 8721);
}
TEST(LlvmLibcCharacterConverterUTF8To32Test, FourBytes) {
LIBC_NAMESPACE::internal::mbstate state;
state.bytes_stored = 0;
state.total_bytes = 0;
const char ch[4] = {static_cast<char>(0xF0), static_cast<char>(0x9F),
static_cast<char>(0xA4),
static_cast<char>(0xA1)}; // 🤡 clown emoji
LIBC_NAMESPACE::internal::CharacterConverter char_conv(&state);
char_conv.push(static_cast<char8_t>(ch[0]));
char_conv.push(static_cast<char8_t>(ch[1]));
char_conv.push(static_cast<char8_t>(ch[2]));
char_conv.push(static_cast<char8_t>(ch[3]));
auto wch = char_conv.pop_utf32();
ASSERT_TRUE(wch.has_value());
ASSERT_EQ(static_cast<int>(wch.value()), 129313);
}
TEST(LlvmLibcCharacterConverterUTF8To32Test, InvalidByte) {
LIBC_NAMESPACE::internal::mbstate state;
state.bytes_stored = 0;
state.total_bytes = 0;
const char ch = static_cast<char>(0x80); // invalid starting bit sequence
LIBC_NAMESPACE::internal::CharacterConverter char_conv(&state);
int err = char_conv.push(static_cast<char8_t>(ch));
ASSERT_EQ(err, EILSEQ);
}
TEST(LlvmLibcCharacterConverterUTF8To32Test, InvalidMultiByte) {
LIBC_NAMESPACE::internal::mbstate state;
state.bytes_stored = 0;
state.total_bytes = 0;
const char ch[4] = {
static_cast<char>(0x80), static_cast<char>(0x00), static_cast<char>(0x80),
static_cast<char>(0x00)}; // first and third bytes are invalid
LIBC_NAMESPACE::internal::CharacterConverter char_conv(&state);
int err = char_conv.push(static_cast<char8_t>(ch[0]));
ASSERT_EQ(err, EILSEQ);
err = char_conv.push(static_cast<char8_t>(ch[1]));
ASSERT_EQ(err, 0);
// Prev byte was single byte so trying to push another should error.
err = char_conv.push(static_cast<char8_t>(ch[2]));
ASSERT_EQ(err, EILSEQ);
err = char_conv.push(static_cast<char8_t>(ch[3]));
ASSERT_EQ(err, 0);
}
TEST(LlvmLibcCharacterConverterUTF8To32Test, InvalidLastByte) {
LIBC_NAMESPACE::internal::mbstate state;
state.bytes_stored = 0;
state.total_bytes = 0;
// Last byte is invalid since it does not have correct starting sequence.
// 0xC0 --> 11000000 starting sequence should be 10xxxxxx
const char ch[4] = {static_cast<char>(0xF1), static_cast<char>(0x80),
static_cast<char>(0x80), static_cast<char>(0xC0)};
LIBC_NAMESPACE::internal::CharacterConverter char_conv(&state);
int err = char_conv.push(static_cast<char8_t>(ch[0]));
ASSERT_EQ(err, 0);
err = char_conv.push(static_cast<char8_t>(ch[1]));
ASSERT_EQ(err, 0);
err = char_conv.push(static_cast<char8_t>(ch[2]));
ASSERT_EQ(err, 0);
err = char_conv.push(static_cast<char8_t>(ch[3]));
ASSERT_EQ(err, EILSEQ);
}
TEST(LlvmLibcCharacterConverterUTF8To32Test, ValidTwoByteWithExtraRead) {
LIBC_NAMESPACE::internal::mbstate state;
state.bytes_stored = 0;
state.total_bytes = 0;
const char ch[3] = {static_cast<char>(0xC2), static_cast<char>(0x8E),
static_cast<char>(0x80)};
LIBC_NAMESPACE::internal::CharacterConverter char_conv(&state);
int err = char_conv.push(static_cast<char8_t>(ch[0]));
ASSERT_EQ(err, 0);
err = char_conv.push(static_cast<char8_t>(ch[1]));
ASSERT_EQ(err, 0);
// Should produce an error on 3rd byte
err = char_conv.push(static_cast<char8_t>(ch[2]));
ASSERT_EQ(err, EILSEQ);
// Should produce an error since mbstate was reset
auto wch = char_conv.pop_utf32();
ASSERT_FALSE(wch.has_value());
}
TEST(LlvmLibcCharacterConverterUTF8To32Test, TwoValidTwoBytes) {
LIBC_NAMESPACE::internal::mbstate state;
state.bytes_stored = 0;
state.total_bytes = 0;
const char ch[4] = {static_cast<char>(0xC2), static_cast<char>(0x8E),
static_cast<char>(0xC7), static_cast<char>(0x8C)};
LIBC_NAMESPACE::internal::CharacterConverter char_conv(&state);
int err = char_conv.push(static_cast<char8_t>(ch[0]));
ASSERT_EQ(err, 0);
err = char_conv.push(static_cast<char8_t>(ch[1]));
ASSERT_EQ(err, 0);
auto wch = char_conv.pop_utf32();
ASSERT_TRUE(wch.has_value());
ASSERT_EQ(static_cast<int>(wch.value()), 142);
// Second two byte character
err = char_conv.push(static_cast<char8_t>(ch[2]));
ASSERT_EQ(err, 0);
err = char_conv.push(static_cast<char8_t>(ch[3]));
ASSERT_EQ(err, 0);
wch = char_conv.pop_utf32();
ASSERT_TRUE(wch.has_value());
ASSERT_EQ(static_cast<int>(wch.value()), 460);
}
TEST(LlvmLibcCharacterConverterUTF8To32Test, InvalidPop) {
LIBC_NAMESPACE::internal::mbstate state;
state.bytes_stored = 0;
state.total_bytes = 0;
LIBC_NAMESPACE::internal::CharacterConverter char_conv(&state);
const char ch[2] = {static_cast<char>(0xC2), static_cast<char>(0x8E)};
int err = char_conv.push(static_cast<char8_t>(ch[0]));
ASSERT_EQ(err, 0);
auto wch = char_conv.pop_utf32();
ASSERT_FALSE(
wch.has_value()); // Should fail since we have not read enough bytes
err = char_conv.push(static_cast<char8_t>(ch[1]));
ASSERT_EQ(err, 0);
wch = char_conv.pop_utf32();
ASSERT_TRUE(wch.has_value());
ASSERT_EQ(static_cast<int>(wch.value()), 142);
}
|
