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
|
// Copyright 2021 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package typesniffer
import (
"bytes"
"encoding/base64"
"strings"
"testing"
"github.com/stretchr/testify/assert"
)
func TestDetectContentTypeLongerThanSniffLen(t *testing.T) {
// Pre-condition: Shorter than sniffLen detects SVG.
assert.Equal(t, "image/svg+xml", DetectContentType([]byte(`<!-- Comment --><svg></svg>`)).contentType)
// Longer than sniffLen detects something else.
assert.NotEqual(t, "image/svg+xml", DetectContentType([]byte(`<!-- `+strings.Repeat("x", sniffLen)+` --><svg></svg>`)).contentType)
}
func TestIsTextFile(t *testing.T) {
assert.True(t, DetectContentType([]byte{}).IsText())
assert.True(t, DetectContentType([]byte("lorem ipsum")).IsText())
}
func TestIsSvgImage(t *testing.T) {
assert.True(t, DetectContentType([]byte("<svg></svg>")).IsSvgImage())
assert.True(t, DetectContentType([]byte(" <svg></svg>")).IsSvgImage())
assert.True(t, DetectContentType([]byte(`<svg width="100"></svg>`)).IsSvgImage())
assert.True(t, DetectContentType([]byte(`<?xml version="1.0" encoding="UTF-8"?><svg></svg>`)).IsSvgImage())
assert.True(t, DetectContentType([]byte(`<!-- Comment -->
<svg></svg>`)).IsSvgImage())
assert.True(t, DetectContentType([]byte(`<!-- Multiple -->
<!-- Comments -->
<svg></svg>`)).IsSvgImage())
assert.True(t, DetectContentType([]byte(`<!-- Multiline
Comment -->
<svg></svg>`)).IsSvgImage())
assert.True(t, DetectContentType([]byte(`<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1 Basic//EN"
"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11-basic.dtd">
<svg></svg>`)).IsSvgImage())
assert.True(t, DetectContentType([]byte(`<?xml version="1.0" encoding="UTF-8"?>
<!-- Comment -->
<svg></svg>`)).IsSvgImage())
assert.True(t, DetectContentType([]byte(`<?xml version="1.0" encoding="UTF-8"?>
<!-- Multiple -->
<!-- Comments -->
<svg></svg>`)).IsSvgImage())
assert.True(t, DetectContentType([]byte(`<?xml version="1.0" encoding="UTF-8"?>
<!-- Multline
Comment -->
<svg></svg>`)).IsSvgImage())
assert.True(t, DetectContentType([]byte(`<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
<!-- Multline
Comment -->
<svg></svg>`)).IsSvgImage())
// the DetectContentType should work for incomplete data, because only beginning bytes are used for detection
assert.True(t, DetectContentType([]byte(`<svg>....`)).IsSvgImage())
assert.False(t, DetectContentType([]byte{}).IsSvgImage())
assert.False(t, DetectContentType([]byte("svg")).IsSvgImage())
assert.False(t, DetectContentType([]byte("<svgfoo></svgfoo>")).IsSvgImage())
assert.False(t, DetectContentType([]byte("text<svg></svg>")).IsSvgImage())
assert.False(t, DetectContentType([]byte("<html><body><svg></svg></body></html>")).IsSvgImage())
assert.False(t, DetectContentType([]byte(`<script>"<svg></svg>"</script>`)).IsSvgImage())
assert.False(t, DetectContentType([]byte(`<!-- <svg></svg> inside comment -->
<foo></foo>`)).IsSvgImage())
assert.False(t, DetectContentType([]byte(`<?xml version="1.0" encoding="UTF-8"?>
<!-- <svg></svg> inside comment -->
<foo></foo>`)).IsSvgImage())
assert.False(t, DetectContentType([]byte(`
<!-- comment1 -->
<div>
<!-- comment2 -->
<svg></svg>
</div>
`)).IsSvgImage())
assert.False(t, DetectContentType([]byte(`
<!-- comment1
-->
<div>
<!-- comment2
-->
<svg></svg>
</div>
`)).IsSvgImage())
assert.False(t, DetectContentType([]byte(`<html><body><!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd"><svg></svg></body></html>`)).IsSvgImage())
assert.False(t, DetectContentType([]byte(`<html><body><?xml version="1.0" encoding="UTF-8"?><svg></svg></body></html>`)).IsSvgImage())
}
func TestIsPDF(t *testing.T) {
pdf, _ := base64.StdEncoding.DecodeString("JVBERi0xLjYKJcOkw7zDtsOfCjIgMCBvYmoKPDwvTGVuZ3RoIDMgMCBSL0ZpbHRlci9GbGF0ZURlY29kZT4+CnN0cmVhbQp4nF3NPwsCMQwF8D2f4s2CNYk1baF0EHRwOwg4iJt/NsFb/PpevUE4Mjwe")
assert.True(t, DetectContentType(pdf).IsPDF())
assert.False(t, DetectContentType([]byte("plain text")).IsPDF())
}
func TestIsVideo(t *testing.T) {
mp4, _ := base64.StdEncoding.DecodeString("AAAAGGZ0eXBtcDQyAAAAAGlzb21tcDQyAAEI721vb3YAAABsbXZoZAAAAADaBlwX2gZcFwAAA+gA")
assert.True(t, DetectContentType(mp4).IsVideo())
assert.False(t, DetectContentType([]byte("plain text")).IsVideo())
}
func TestIsAudio(t *testing.T) {
mp3, _ := base64.StdEncoding.DecodeString("SUQzBAAAAAABAFRYWFgAAAASAAADbWFqb3JfYnJhbmQAbXA0MgBUWFhYAAAAEQAAA21pbm9yX3Zl")
assert.True(t, DetectContentType(mp3).IsAudio())
assert.False(t, DetectContentType([]byte("plain text")).IsAudio())
assert.True(t, DetectContentType([]byte("ID3Toy\000")).IsAudio())
assert.True(t, DetectContentType([]byte("ID3Toy\n====\t* hi 🌞, ...")).IsText()) // test ID3 tag for plain text
assert.True(t, DetectContentType([]byte("ID3Toy\n====\t* hi 🌞, ..."+"🌛"[0:2])).IsText()) // test ID3 tag with incomplete UTF8 char
}
func TestDetectContentTypeFromReader(t *testing.T) {
mp3, _ := base64.StdEncoding.DecodeString("SUQzBAAAAAABAFRYWFgAAAASAAADbWFqb3JfYnJhbmQAbXA0MgBUWFhYAAAAEQAAA21pbm9yX3Zl")
st, err := DetectContentTypeFromReader(bytes.NewReader(mp3))
assert.NoError(t, err)
assert.True(t, st.IsAudio())
}
|
