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
|
package jsonparser
import (
"bytes"
"testing"
)
func TestH2I(t *testing.T) {
hexChars := []byte{'0', '9', 'A', 'F', 'a', 'f', 'x', '\000'}
hexValues := []int{0, 9, 10, 15, 10, 15, -1, -1}
for i, c := range hexChars {
if v := h2I(c); v != hexValues[i] {
t.Errorf("h2I('%c') returned wrong value (obtained %d, expected %d)", c, v, hexValues[i])
}
}
}
type escapedUnicodeRuneTest struct {
in string
isErr bool
out rune
len int
}
var commonUnicodeEscapeTests = []escapedUnicodeRuneTest{
{in: `\u0041`, out: 'A', len: 6},
{in: `\u0000`, out: 0, len: 6},
{in: `\u00b0`, out: '°', len: 6},
{in: `\u00B0`, out: '°', len: 6},
{in: `\x1234`, out: 0x1234, len: 6}, // These functions do not check the \u prefix
{in: ``, isErr: true},
{in: `\`, isErr: true},
{in: `\u`, isErr: true},
{in: `\u1`, isErr: true},
{in: `\u11`, isErr: true},
{in: `\u111`, isErr: true},
{in: `\u123X`, isErr: true},
}
var singleUnicodeEscapeTests = append([]escapedUnicodeRuneTest{
{in: `\uD83D`, out: 0xD83D, len: 6},
{in: `\uDE03`, out: 0xDE03, len: 6},
{in: `\uFFFF`, out: 0xFFFF, len: 6},
{in: `\uFF11`, out: '１', len: 6},
}, commonUnicodeEscapeTests...)
var multiUnicodeEscapeTests = append([]escapedUnicodeRuneTest{
{in: `\uD83D`, isErr: true},
{in: `\uDE03`, isErr: true},
{in: `\uFFFF`, out: '\uFFFF', len: 6},
{in: `\uFF11`, out: '１', len: 6},
{in: `\uD83D\uDE03`, out: '\U0001F603', len: 12},
{in: `\uD800\uDC00`, out: '\U00010000', len: 12},
{in: `\uD800\`, isErr: true},
{in: `\uD800\u`, isErr: true},
{in: `\uD800\uD`, isErr: true},
{in: `\uD800\uDC`, isErr: true},
{in: `\uD800\uDC0`, isErr: true},
{in: `\uD800\uDBFF`, isErr: true}, // invalid low surrogate
}, commonUnicodeEscapeTests...)
func TestDecodeSingleUnicodeEscape(t *testing.T) {
for _, test := range singleUnicodeEscapeTests {
r, ok := decodeSingleUnicodeEscape([]byte(test.in))
isErr := !ok
if isErr != test.isErr {
t.Errorf("decodeSingleUnicodeEscape(%s) returned isErr mismatch: expected %t, obtained %t", test.in, test.isErr, isErr)
} else if isErr {
continue
} else if r != test.out {
t.Errorf("decodeSingleUnicodeEscape(%s) returned rune mismatch: expected %x (%c), obtained %x (%c)", test.in, test.out, test.out, r, r)
}
}
}
func TestDecodeUnicodeEscape(t *testing.T) {
for _, test := range multiUnicodeEscapeTests {
r, len := decodeUnicodeEscape([]byte(test.in))
isErr := (len == -1)
if isErr != test.isErr {
t.Errorf("decodeUnicodeEscape(%s) returned isErr mismatch: expected %t, obtained %t", test.in, test.isErr, isErr)
} else if isErr {
continue
} else if len != test.len {
t.Errorf("decodeUnicodeEscape(%s) returned length mismatch: expected %d, obtained %d", test.in, test.len, len)
} else if r != test.out {
t.Errorf("decodeUnicodeEscape(%s) returned rune mismatch: expected %x (%c), obtained %x (%c)", test.in, test.out, test.out, r, r)
}
}
}
type unescapeTest struct {
in string // escaped string
out string // expected unescaped string
canAlloc bool // can unescape cause an allocation (depending on buffer size)? true iff 'in' contains escape sequence(s)
isErr bool // should this operation result in an error
}
var unescapeTests = []unescapeTest{
{in: ``, out: ``, canAlloc: false},
{in: `a`, out: `a`, canAlloc: false},
{in: `abcde`, out: `abcde`, canAlloc: false},
{in: `ab\\de`, out: `ab\de`, canAlloc: true},
{in: `ab\"de`, out: `ab"de`, canAlloc: true},
{in: `ab \u00B0 de`, out: `ab ° de`, canAlloc: true},
{in: `ab \uFF11 de`, out: `ab １ de`, canAlloc: true},
{in: `\uFFFF`, out: "\uFFFF", canAlloc: true},
{in: `ab \uD83D\uDE03 de`, out: "ab \U0001F603 de", canAlloc: true},
{in: `\u0000\u0000\u0000\u0000\u0000`, out: "\u0000\u0000\u0000\u0000\u0000", canAlloc: true},
{in: `\u0000 \u0000 \u0000 \u0000 \u0000`, out: "\u0000 \u0000 \u0000 \u0000 \u0000", canAlloc: true},
{in: ` \u0000 \u0000 \u0000 \u0000 \u0000 `, out: " \u0000 \u0000 \u0000 \u0000 \u0000 ", canAlloc: true},
{in: `\uD800`, isErr: true},
{in: `abcde\`, isErr: true},
{in: `abcde\x`, isErr: true},
{in: `abcde\u`, isErr: true},
{in: `abcde\u1`, isErr: true},
{in: `abcde\u12`, isErr: true},
{in: `abcde\u123`, isErr: true},
{in: `abcde\uD800`, isErr: true},
{in: `ab\uD800de`, isErr: true},
{in: `\uD800abcde`, isErr: true},
}
// isSameMemory checks if two slices contain the same memory pointer (meaning one is a
// subslice of the other, with possibly differing lengths/capacities).
func isSameMemory(a, b []byte) bool {
if cap(a) == 0 || cap(b) == 0 {
return cap(a) == cap(b)
} else if a, b = a[:1], b[:1]; a[0] != b[0] {
return false
} else {
a[0]++
same := (a[0] == b[0])
a[0]--
return same
}
}
func TestUnescape(t *testing.T) {
for _, test := range unescapeTests {
type bufferTestCase struct {
buf []byte
isTooSmall bool
}
var bufs []bufferTestCase
if len(test.in) == 0 {
// If the input string is length 0, only a buffer of size 0 is a meaningful test
bufs = []bufferTestCase{{nil, false}}
} else {
// For non-empty input strings, we can try several buffer sizes (0, len-1, len)
bufs = []bufferTestCase{
{nil, true},
{make([]byte, 0, len(test.in)-1), true},
{make([]byte, 0, len(test.in)), false},
}
}
for _, buftest := range bufs {
in := []byte(test.in)
buf := buftest.buf
out, err := Unescape(in, buf)
isErr := (err != nil)
isAlloc := !isSameMemory(out, in) && !isSameMemory(out, buf)
if isErr != test.isErr {
t.Errorf("Unescape(`%s`, bufsize=%d) returned isErr mismatch: expected %t, obtained %t", test.in, cap(buf), test.isErr, isErr)
break
} else if isErr {
continue
} else if !bytes.Equal(out, []byte(test.out)) {
t.Errorf("Unescape(`%s`, bufsize=%d) returned unescaped mismatch: expected `%s` (%v, len %d), obtained `%s` (%v, len %d)", test.in, cap(buf), test.out, []byte(test.out), len(test.out), string(out), out, len(out))
break
} else if isAlloc != (test.canAlloc && buftest.isTooSmall) {
t.Errorf("Unescape(`%s`, bufsize=%d) returned isAlloc mismatch: expected %t, obtained %t", test.in, cap(buf), buftest.isTooSmall, isAlloc)
break
}
}
}
}
|
