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
|
#include "gmock/gmock.h"
#include "config.h"
#include "log.h"
#include "encodingspeculator.h"
using namespace std;
using namespace testing;
class EncodingSpeculatorBehaviour: public testing::Test {
public:
EncodingSpeculator speculator;
EncodingSpeculatorBehaviour() {
}
};
TEST_F( EncodingSpeculatorBehaviour, DefaultAsPureAscii ) {
ASSERT_THAT( speculator.guess(), Eq( EncodingSpeculator::Encoding::ASCII7 ) );
}
TEST_F( EncodingSpeculatorBehaviour, RecognisePureAscii ) {
for ( uint8_t i = 0; i < 127; ++i )
speculator.inject_byte( i );
ASSERT_THAT( speculator.guess(), Eq( EncodingSpeculator::Encoding::ASCII7 ) );
}
TEST_F( EncodingSpeculatorBehaviour, RecogniseRandom8bitEncoding ) {
for ( uint8_t i = 0; i < 127; ++i )
speculator.inject_byte( i );
speculator.inject_byte( 0xFF );
ASSERT_THAT( speculator.guess(), Eq( EncodingSpeculator::Encoding::ASCII8 ) );
}
pair<uint8_t,uint8_t> utf8encode2bytes( uint16_t code_point )
{
uint8_t cp_low = static_cast<uint8_t>(code_point & 0xFF);
uint8_t cp_hi = static_cast<uint8_t>((code_point & 0xFF00) >> 8);
uint8_t first_byte = 0xC0 | ( ( cp_hi & 0x7F ) << 2 ) | ( ( cp_low & 0xC0 ) >> 6 );
uint8_t second_byte = 0x80 | ( cp_low & 0x3F );
return { first_byte, second_byte };
}
vector<uint8_t> utf8encodeMultiBytes( uint32_t code_point )
{
vector<uint8_t> bytes = {};
if ( code_point <= 0xFFFF ) {
uint8_t lead = static_cast<uint8_t>( 0xE0 | ( ( code_point & 0xF000 ) >> 12 ) );
bytes.push_back( lead );
bytes.push_back( 0x80 | ( code_point & 0x0FC0 ) >> 6 );
bytes.push_back( 0x80 | ( code_point & 0x3F ) );
}
else if ( code_point <= 0x1FFFFF ) {
uint8_t lead = static_cast<uint8_t>( 0xF0 | ( ( code_point & 0x1C0000 ) >> 18 ) );
bytes.push_back( lead );
bytes.push_back( 0x80 | ( code_point & 0x3F000 ) >> 12 );
bytes.push_back( 0x80 | ( code_point & 0x00FC0 ) >> 6 );
bytes.push_back( 0x80 | ( code_point & 0x0003F ) );
}
return bytes;
}
TEST_F( EncodingSpeculatorBehaviour, RecogniseTwoBytesUTF8 ) {
// All the code points encodable as 2 bytes.
for ( uint16_t i = 0x80; i < ( 1 << 11 ); ++i ) {
auto utf8_bytes = utf8encode2bytes( i );
// cout << bitset<8>(first_byte) << " " << bitset<8>(second_byte) << endl;
speculator.inject_byte( utf8_bytes.first );
speculator.inject_byte( utf8_bytes.second );
}
ASSERT_THAT( speculator.guess(), Eq( EncodingSpeculator::Encoding::UTF8 ) );
}
TEST_F( EncodingSpeculatorBehaviour, RecogniseTwoBytesUTF8With7bitsInterleaved ) {
// All the code points encodable as 2 bytes.
for ( uint16_t i = 0x80; i < ( 1 << 11 ); ++i ) {
auto utf8_bytes = utf8encode2bytes( i );
speculator.inject_byte( ' ' );
speculator.inject_byte( utf8_bytes.first );
speculator.inject_byte( utf8_bytes.second );
}
ASSERT_THAT( speculator.guess(), Eq( EncodingSpeculator::Encoding::UTF8 ) );
}
TEST_F( EncodingSpeculatorBehaviour, RecogniseIncompleteTwoBytesUTF8 ) {
// All the code points encodable as 2 bytes.
for ( uint16_t i = 0x80; i < ( 1 << 11 ); ++i ) {
auto utf8_bytes = utf8encode2bytes( i );
speculator.inject_byte( ' ' );
speculator.inject_byte( utf8_bytes.first );
speculator.inject_byte( utf8_bytes.second );
}
// Lead byte only
speculator.inject_byte( 0xCF );
ASSERT_THAT( speculator.guess(), Eq( EncodingSpeculator::Encoding::ASCII8 ) );
}
TEST_F( EncodingSpeculatorBehaviour, RecogniseIncorrectTwoBytesUTF8 ) {
// All the code points encodable as 2 bytes.
for ( uint16_t i = 0x80; i < ( 1 << 11 ); ++i ) {
auto utf8_bytes = utf8encode2bytes( i );
speculator.inject_byte( ' ' );
speculator.inject_byte( utf8_bytes.first );
speculator.inject_byte( utf8_bytes.second );
}
// Lead byte
speculator.inject_byte( 0xCF );
// Incorrect continuation byte (should start with 1)
speculator.inject_byte( 0x00 );
ASSERT_THAT( speculator.guess(), Eq( EncodingSpeculator::Encoding::ASCII8 ) );
}
TEST_F( EncodingSpeculatorBehaviour, RecogniseOverlong2BytesUTF8 ) {
speculator.inject_byte( ' ' );
speculator.inject_byte( 0xC1 );
speculator.inject_byte( 0xBF );
ASSERT_THAT( speculator.guess(), Eq( EncodingSpeculator::Encoding::ASCII8 ) );
}
TEST_F( EncodingSpeculatorBehaviour, RecogniseThreeBytesUTF8 ) {
for ( uint32_t i = 0x800; i <= 0xFFFF; ++i ) {
auto utf8_bytes = utf8encodeMultiBytes( i );
speculator.inject_byte( ' ' );
for ( uint8_t byte: utf8_bytes ) {
// cout << hex << i << " " << static_cast<uint32_t>( byte ) << endl;
speculator.inject_byte( byte );
}
}
ASSERT_THAT( speculator.guess(), Eq( EncodingSpeculator::Encoding::UTF8 ) );
}
TEST_F( EncodingSpeculatorBehaviour, RecogniseOverlong3BytesUTF8 ) {
speculator.inject_byte( ' ' );
speculator.inject_byte( 0xA0 );
speculator.inject_byte( 0x80 );
speculator.inject_byte( 0x80 );
ASSERT_THAT( speculator.guess(), Eq( EncodingSpeculator::Encoding::ASCII8 ) );
}
TEST_F( EncodingSpeculatorBehaviour, RecogniseFourBytesUTF8 ) {
for ( uint32_t i = 0x10000; i <= 0x1FFFFF; ++i ) {
auto utf8_bytes = utf8encodeMultiBytes( i );
speculator.inject_byte( ' ' );
for ( uint8_t byte: utf8_bytes ) {
// cout << hex << i << " " << static_cast<uint32_t>( byte ) << endl;
speculator.inject_byte( byte );
}
}
ASSERT_THAT( speculator.guess(), Eq( EncodingSpeculator::Encoding::UTF8 ) );
}
TEST_F( EncodingSpeculatorBehaviour, RecogniseOverlong4BytesUTF8 ) {
speculator.inject_byte( ' ' );
speculator.inject_byte( 0xF0 );
speculator.inject_byte( 0x80 );
speculator.inject_byte( 0x80 );
speculator.inject_byte( 0x80 );
ASSERT_THAT( speculator.guess(), Eq( EncodingSpeculator::Encoding::ASCII8 ) );
}
|
