lithtml 0.8.0

A lightweight and fast HTML parser for Rust, designed to handle both full HTML documents and fragments efficiently.
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

use insta::assert_json_snapshot;
use lithtml::{Dom, Result};

#[test]
fn it_can_parse_double_quote() -> Result<()> {
    let html = "<div id=\"one\"></div>";
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}
#[test]
fn it_can_parse_single_quote() -> Result<()> {
    let html = "<div id='one'></div>";
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}
#[test]
fn it_can_parse_no_quote() -> Result<()> {
    let html = "<div id=one></div>";
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}
#[test]
fn it_can_parse_attribute_key_mixed_case_symbols_only() -> Result<()> {
    let html = "<div data-cat />";
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}
#[test]
fn it_can_parse_attribute_key_mixed_case_symbols() -> Result<()> {
    let html = "<div data-cat='morris'></div>";
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}
#[test]
fn it_can_parse_multiple_attributes_single_quote() -> Result<()> {
    let html = "<div cat='mjau' dog='woff' ape=oh></div>";
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}
#[test]
fn it_can_parse_multiple_attributes_where_whitespace_does_not_matter_for_keys() -> Result<()> {
    let html = "<div    cat   =  \"mjau\" dog ='  woff  'ape = oh ></div>";
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}
#[test]
fn it_can_parse_multiple_attributes_double_quote() -> Result<()> {
    let html = "<div cat=\"mjau\" dog=\"woff\" ape=\"oh\"></div>";
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}
#[test]
fn it_can_parse_multiple_attributes_no_quote() -> Result<()> {
    let html = "<div cat=mjau dog=woff ape=oh></div>";
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}
#[test]
fn it_can_parse_attribute_multiple_values_single_quote() -> Result<()> {
    let html = "<div cat='mjau mjau' />";
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}
#[test]
fn it_can_parse_attribute_multiple_values_double_quote() -> Result<()> {
    let html = "<div cat=\"mjau mjau\" />";
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}
#[test]
fn it_can_parse_attribute_with_empty_value() -> Result<()> {
    let html = "<img hidden/>";
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}

#[test]
fn it_can_parse_id() -> Result<()> {
    let html = "<img id=a/>";
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}
#[test]
fn it_can_parse_classes() -> Result<()> {
    let html = "<img class='a b c'/>";
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}
#[test]
fn it_keeps_spaces_for_non_classes() -> Result<()> {
    let html = "<img attr=' a b     \n\t'/>";
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}
#[test]
fn it_can_parse_attribute_multiple_quotes() -> Result<()> {
    let html = "<div cat=\"she says: \'mjau mjau\'\" horse='horse says:\"pffff\"' />";
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}