html-filter 0.2.3

Parse HTML into a typed tree, then search for tags, attributes, classes, filter out comments or find and extract the exact data you want with a short builder pattern - zero dependencies, zero overhead
Documentation 
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

use html_filter::*;

use super::test_maker;

macro_rules! make_tests {
    ($($name:ident: $filter:expr => $expect:expr)*) => {
        $(
            #[test]
            fn $name() {
                let tree = Html::parse(INPUT).unwrap().filter(&$filter);
                test_maker(stringify!($name), $expect, &tree, $filter, true)
            }
        )*
    };
}

/// !
pub const INPUT: &str = "
<!DOCTYPE html>
<!-- comment 1 -->
<html>
    A first text
    <!-- first comment -->
    <p>
        A <strong>first</strong> text
        <!-- second comment -->
        <img />
    </p>
</html>
";

make_tests!(

all: Filter::new() => "
<!DOCTYPE html>
<!-- comment 1 -->
<html>
    A first text
    <!-- first comment -->
    <p>
        A <strong>first</strong> text
        <!-- second comment -->
        <img />
    </p>
</html>
"

only_tags: Filter::new().all(false) => "
<html>
    <p>
        <strong></strong>
        <img />
    </p>
</html>
"

text: Filter::new().none_except_text() => "
<html>
    A first text
    <p>
        A <strong>first</strong> text
        <img />
    </p>
</html>"

comment: Filter::new().none_except_comment() => "
<!-- comment 1 -->
<html>
    <!-- first comment -->
    <p>
        <strong></strong>
        <!-- second comment -->
        <img />
    </p>
</html>"

doctype: Filter::new().none_except_doctype().no_tags() => "
<!DOCTYPE html>
"

text_comment: Filter::new().all_except_doctype() => "
<!-- comment 1 -->
<html>
    A first text
    <!-- first comment -->
    <p>
        A <strong>first</strong> text
        <!-- second comment -->
        <img />
    </p>
</html>"


// TODO: by default, if there is a filter, things outside a tag are deleted (comments, doctype,
// etc.), is this expected?
depth_default_doctype: Filter::new().comment(false).depth(3).tag_name("strong") => "
<html>
    A first text
    <p>
        A <strong>first</strong> text
        <img />
    </p>
</html>"


text_depth_doctype: Filter::new().doctype(true).comment(false).depth(2).tag_name("p") => "
<!DOCTYPE html>
<html>
    A first text
    <p>
        A <strong>first</strong> text
        <img />
    </p>
</html>"

no_depth_force_doctype: Filter::new().doctype(true).comment(false).depth(1).tag_name("p") => "
<!DOCTYPE html>
<html>
    A first text
    <p>
        A <strong>first</strong> text
        <img />
    </p>
</html>"



text_doctype: Filter::new().all_except_comment() => "
<!DOCTYPE html>
<html>
    A first text
    <p>
        A <strong>first</strong> text
        <img />
    </p>
</html>"

doctype_comment: Filter::new().all_except_text() => "
<!DOCTYPE html>
<!-- comment 1 -->
<html>
    <!-- first comment -->
    <p>
        <strong></strong>
        <!-- second comment -->
        <img />
    </p>
</html>"

);