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
|
// SPDX-FileCopyrightText: Copyright The Miniflux Authors. All rights reserved.
// SPDX-License-Identifier: Apache-2.0
package readability // import "miniflux.app/v2/internal/reader/readability"
import (
"bytes"
"os"
"strings"
"testing"
)
func TestBaseURL(t *testing.T) {
html := `
<html>
<head>
<base href="https://example.org/ ">
</head>
<body>
<article>
Some content
</article>
</body>
</html>`
baseURL, _, err := ExtractContent(strings.NewReader(html))
if err != nil {
t.Fatal(err)
}
if baseURL != "https://example.org/" {
t.Errorf(`Unexpected base URL, got %q instead of "https://example.org/"`, baseURL)
}
}
func TestMultipleBaseURL(t *testing.T) {
html := `
<html>
<head>
<base href="https://example.org/ ">
<base href="https://example.com/ ">
</head>
<body>
<article>
Some content
</article>
</body>
</html>`
baseURL, _, err := ExtractContent(strings.NewReader(html))
if err != nil {
t.Fatal(err)
}
if baseURL != "https://example.org/" {
t.Errorf(`Unexpected base URL, got %q instead of "https://example.org/"`, baseURL)
}
}
func TestRelativeBaseURL(t *testing.T) {
html := `
<html>
<head>
<base href="/test/ ">
</head>
<body>
<article>
Some content
</article>
</body>
</html>`
baseURL, _, err := ExtractContent(strings.NewReader(html))
if err != nil {
t.Fatal(err)
}
if baseURL != "" {
t.Errorf(`Unexpected base URL, got %q`, baseURL)
}
}
func TestWithoutBaseURL(t *testing.T) {
html := `
<html>
<head>
<title>Test</title>
</head>
<body>
<article>
Some content
</article>
</body>
</html>`
baseURL, _, err := ExtractContent(strings.NewReader(html))
if err != nil {
t.Fatal(err)
}
if baseURL != "" {
t.Errorf(`Unexpected base URL, got %q instead of ""`, baseURL)
}
}
func TestRemoveStyleScript(t *testing.T) {
html := `
<html>
<head>
<title>Test</title>
<script src="tololo.js"></script>
</head>
<body>
<script src="tololo.js"></script>
<style>
h1 {color:red;}
p {color:blue;}
</style>
<article>Some content</article>
</body>
</html>`
want := `<div><div><article>Somecontent</article></div></div>`
_, content, err := ExtractContent(strings.NewReader(html))
if err != nil {
t.Fatal(err)
}
content = strings.ReplaceAll(content, "\n", "")
content = strings.ReplaceAll(content, " ", "")
content = strings.ReplaceAll(content, "\t", "")
if content != want {
t.Errorf(`Invalid content, got %s instead of %s`, content, want)
}
}
func TestRemoveBlacklist(t *testing.T) {
html := `
<html>
<head>
<title>Test</title>
</head>
<body>
<article class="super-ad">Some content</article>
<article class="g-plus-crap">Some other thing</article>
<article class="stuff popupbody">And more</article>
<article class="legit">Valid!</article>
</body>
</html>`
want := `<div><div><articleclass="legit">Valid!</article></div></div>`
_, content, err := ExtractContent(strings.NewReader(html))
if err != nil {
t.Fatal(err)
}
content = strings.ReplaceAll(content, "\n", "")
content = strings.ReplaceAll(content, " ", "")
content = strings.ReplaceAll(content, "\t", "")
if content != want {
t.Errorf(`Invalid content, got %s instead of %s`, content, want)
}
}
func BenchmarkExtractContent(b *testing.B) {
var testCases = map[string][]byte{
"miniflux_github.html": {},
"miniflux_wikipedia.html": {},
}
for filename := range testCases {
data, err := os.ReadFile("testdata/" + filename)
if err != nil {
b.Fatalf(`Unable to read file %q: %v`, filename, err)
}
testCases[filename] = data
}
for range b.N {
for _, v := range testCases {
ExtractContent(bytes.NewReader(v))
}
}
}
|
