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
198
199
200
|
// Copyright 2023 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package syscall_test
import (
"fmt"
"slices"
"syscall"
"testing"
"unicode/utf16"
"unicode/utf8"
"unsafe"
)
var wtf8tests = []struct {
str string
wstr []uint16
}{
{
str: "\x00",
wstr: []uint16{0x00},
},
{
str: "\x5C",
wstr: []uint16{0x5C},
},
{
str: "\x7F",
wstr: []uint16{0x7F},
},
// 2-byte
{
str: "\xC2\x80",
wstr: []uint16{0x80},
},
{
str: "\xD7\x8A",
wstr: []uint16{0x05CA},
},
{
str: "\xDF\xBF",
wstr: []uint16{0x07FF},
},
// 3-byte
{
str: "\xE0\xA0\x80",
wstr: []uint16{0x0800},
},
{
str: "\xE2\xB0\xBC",
wstr: []uint16{0x2C3C},
},
{
str: "\xEF\xBF\xBF",
wstr: []uint16{0xFFFF},
},
// unmatched surrogate halves
// high surrogates: 0xD800 to 0xDBFF
{
str: "\xED\xA0\x80",
wstr: []uint16{0xD800},
},
{
// "High surrogate followed by another high surrogate"
str: "\xED\xA0\x80\xED\xA0\x80",
wstr: []uint16{0xD800, 0xD800},
},
{
// "High surrogate followed by a symbol that is not a surrogate"
str: string([]byte{0xED, 0xA0, 0x80, 0xA}),
wstr: []uint16{0xD800, 0xA},
},
{
// "Unmatched high surrogate, followed by a surrogate pair, followed by an unmatched high surrogate"
str: string([]byte{0xED, 0xA0, 0x80, 0xF0, 0x9D, 0x8C, 0x86, 0xED, 0xA0, 0x80}),
wstr: []uint16{0xD800, 0xD834, 0xDF06, 0xD800},
},
{
str: "\xED\xA6\xAF",
wstr: []uint16{0xD9AF},
},
{
str: "\xED\xAF\xBF",
wstr: []uint16{0xDBFF},
},
// low surrogates: 0xDC00 to 0xDFFF
{
str: "\xED\xB0\x80",
wstr: []uint16{0xDC00},
},
{
// "Low surrogate followed by another low surrogate"
str: "\xED\xB0\x80\xED\xB0\x80",
wstr: []uint16{0xDC00, 0xDC00},
},
{
// "Low surrogate followed by a symbol that is not a surrogate"
str: string([]byte{0xED, 0xB0, 0x80, 0xA}),
wstr: []uint16{0xDC00, 0xA},
},
{
// "Unmatched low surrogate, followed by a surrogate pair, followed by an unmatched low surrogate"
str: string([]byte{0xED, 0xB0, 0x80, 0xF0, 0x9D, 0x8C, 0x86, 0xED, 0xB0, 0x80}),
wstr: []uint16{0xDC00, 0xD834, 0xDF06, 0xDC00},
},
{
str: "\xED\xBB\xAE",
wstr: []uint16{0xDEEE},
},
{
str: "\xED\xBF\xBF",
wstr: []uint16{0xDFFF},
},
// 4-byte
{
str: "\xF0\x90\x80\x80",
wstr: []uint16{0xD800, 0xDC00},
},
{
str: "\xF0\x9D\x8C\x86",
wstr: []uint16{0xD834, 0xDF06},
},
{
str: "\xF4\x8F\xBF\xBF",
wstr: []uint16{0xDBFF, 0xDFFF},
},
}
func TestWTF16Rountrip(t *testing.T) {
for _, tt := range wtf8tests {
t.Run(fmt.Sprintf("%X", tt.str), func(t *testing.T) {
got := syscall.EncodeWTF16(tt.str, nil)
got2 := string(syscall.DecodeWTF16(got, nil))
if got2 != tt.str {
t.Errorf("got:\n%s\nwant:\n%s", got2, tt.str)
}
})
}
}
func TestWTF16Golden(t *testing.T) {
for _, tt := range wtf8tests {
t.Run(fmt.Sprintf("%X", tt.str), func(t *testing.T) {
got := syscall.EncodeWTF16(tt.str, nil)
if !slices.Equal(got, tt.wstr) {
t.Errorf("got:\n%v\nwant:\n%v", got, tt.wstr)
}
})
}
}
func FuzzEncodeWTF16(f *testing.F) {
for _, tt := range wtf8tests {
f.Add(tt.str)
}
f.Fuzz(func(t *testing.T, b string) {
// test that there are no panics
got := syscall.EncodeWTF16(b, nil)
syscall.DecodeWTF16(got, nil)
if utf8.ValidString(b) {
// if the input is a valid UTF-8 string, then
// test that syscall.EncodeWTF16 behaves as
// utf16.Encode
want := utf16.Encode([]rune(b))
if !slices.Equal(got, want) {
t.Errorf("got:\n%v\nwant:\n%v", got, want)
}
}
})
}
func FuzzDecodeWTF16(f *testing.F) {
for _, tt := range wtf8tests {
b := unsafe.Slice((*uint8)(unsafe.Pointer(unsafe.SliceData(tt.wstr))), len(tt.wstr)*2)
f.Add(b)
}
f.Fuzz(func(t *testing.T, b []byte) {
u16 := unsafe.Slice((*uint16)(unsafe.Pointer(unsafe.SliceData(b))), len(b)/2)
got := syscall.DecodeWTF16(u16, nil)
if utf8.Valid(got) {
// if the input is a valid UTF-8 string, then
// test that syscall.DecodeWTF16 behaves as
// utf16.Decode
want := utf16.Decode(u16)
if string(got) != string(want) {
t.Errorf("got:\n%s\nwant:\n%s", string(got), string(want))
}
}
// WTF-8 should always roundtrip
got2 := syscall.EncodeWTF16(string(got), nil)
if !slices.Equal(got2, u16) {
t.Errorf("got:\n%v\nwant:\n%v", got2, u16)
}
})
}
|
