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
|
package charset
import (
"testing"
)
const xmlDoc = `<?xml version="1.0" encoding="UTF-8"?>
<note>
<to>Tove</to>
<from>Jani</from>
<heading>Reminder</heading>
<body>Don't forget me this weekend!</body>
</note>`
const htmlDoc = `<!DOCTYPE html>
<html>
<head><!--[if lt IE 9]><script language="javascript" type="text/javascript" src="//html5shim.googlecode.com/svn/trunk/html5.js"></script><![endif]-->
<meta charset="UTF-8"><style>/*
</style>
<link rel="stylesheet" href="css/animation.css"><!--[if IE 7]><link rel="stylesheet" href="css/" + font.fontname + "-ie7.css"><![endif]-->
<script>
</script>
</head>
<body>
<div class="container footer">さ</div>
</body>
</html>`
const htmlDocWithIncorrectCharset = `<!DOCTYPE html>
<!--
Some comment
-->
<html dir="ltr" mozdisallowselectionprint>
<head>
<meta charset="ISO-8859-16">
<meta name="viewport" content="width=device-width, initial-scale=1, maximum-scale=1">
<meta name="some name" content="notranslate">
<title>test</title>
<link rel="stylesheet" href="html.utf8bom.css">
</head>
<body tabindex="1">
<div id="printContainer"></div>
</body>
</html>`
func TestFromXML(t *testing.T) {
charset := FromXML([]byte(xmlDoc))
if charset != "utf-8" {
t.Errorf("expected: utf-8; got: %s", charset)
}
}
func TestFromHTML(t *testing.T) {
charset := FromHTML([]byte(htmlDoc))
if charset != "utf-8" {
t.Errorf("expected: utf-8; got: %s", charset)
}
}
func TestFromHTMLWithBOM(t *testing.T) {
charset := FromHTML(append([]byte{0xEF, 0xBB, 0xBF}, []byte(htmlDocWithIncorrectCharset)...))
if charset != "utf-8" {
t.Errorf("expected: utf-8; got: %s", charset)
}
}
func TestFromPlain(t *testing.T) {
tcases := []struct {
raw []byte
charset string
}{
{[]byte{0xe6, 0xf8, 0xe5, 0x85, 0x85}, "windows-1252"},
{[]byte{0xe6, 0xf8, 0xe5}, "iso-8859-1"},
{[]byte("æøå"), "utf-8"},
{[]byte{}, ""},
}
for _, tc := range tcases {
if cs := FromPlain(tc.raw); cs != tc.charset {
t.Errorf("in: %v; expected: %s; got: %s", tc.raw, tc.charset, cs)
}
}
}
func FuzzFromPlain(f *testing.F) {
samples := [][]byte{
[]byte{0xe6, 0xf8, 0xe5, 0x85, 0x85},
[]byte{0xe6, 0xf8, 0xe5},
[]byte("æøå"),
}
for _, s := range samples {
f.Add(s)
}
f.Fuzz(func(t *testing.T, d []byte) {
if charset := FromPlain(d); charset == "" {
t.Skip()
}
})
}
func FuzzFromHTML(f *testing.F) {
samples := []string{
`<meta charset="c">`,
`<meta charset="щ">`,
`<meta http-equiv="content-type" content="a/b; charset=c">`,
`<meta http-equiv="content-type" content="a/b; charset=щ">`,
`<f 1=2 /><meta charset="c">`,
`<f a=2><meta http-equiv="content-type" content="a/b; charset=c">`,
`<f 1=2 /><meta b="b" charset="c">`,
`<f a=2><meta b="b" http-equiv="content-type" content="a/b; charset=c">`,
}
for _, s := range samples {
f.Add([]byte(s))
}
f.Fuzz(func(t *testing.T, d []byte) {
if charset := FromHTML(d); charset == "" {
t.Skip()
}
})
}
func FuzzFromXML(f *testing.F) {
samples := []string{
`<?xml version="1.0" encoding="c"?>`,
}
for _, s := range samples {
f.Add([]byte(s))
}
f.Fuzz(func(t *testing.T, d []byte) {
if charset := FromXML(d); charset == "" {
t.Skip()
}
})
}
|
