rusthtml 0.2.4

A html parser written in rust
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

use crate::*;
#[test]
fn tag_works() {
    let parsed = HtmlTag::parse(r#"<p class=abc def="ghi jkl" mno>Hello World!</p>"#);
    assert_eq!(
        parsed,
        vec![
            HtmlTag::OpeningTag(
                "p",
                vec![
                    ("class", Some("abc")),
                    ("def", Some("ghi jkl")),
                    ("mno", None)
                ]
            ),
            HtmlTag::Unparsable("Hello World!"),
            HtmlTag::ClosingTag("p")
        ]
    )
}
#[test]
fn element_works() {
    let parsed = ElementContent::parse(tag_optimize(HtmlTag::parse(
        r#"<p class=abc>Hello!<img src="abc" def></p><title>This is a test</title>"#,
    )));
    assert_eq!(
        parsed,
        Ok(vec![
            ElementContent::HtmlElement(Box::new(HtmlElement {
                name: "p",
                attributes: vec![("class", Some("abc"))],
                tag_state: ElementTagState::BothTag,
                content: vec![
                    ElementContent::LiteralContent("Hello!"),
                    ElementContent::HtmlElement(Box::new(HtmlElement {
                        name: "img",
                        attributes: vec![("src", Some("abc")), ("def", None)],
                        tag_state: ElementTagState::BothTag,
                        content: Vec::new()
                    }))
                ]
            })),
            ElementContent::HtmlElement(Box::new(HtmlElement {
                name: "title",
                attributes: Vec::new(),
                tag_state: ElementTagState::BothTag,
                content: vec![ElementContent::LiteralContent("This is a test")]
            }))
        ])
    );
}
#[test]
fn almost_all() {
    let source = include_str!("../benches/example.html");
    ElementContent::parse(tag_optimize(HtmlTag::parse(source))).unwrap();
}
#[test]
fn unicode_characters() {
    let parsed = ElementContent::parse(tag_optimize(HtmlTag::parse(
        r#"<p class=❤>Hello!<img src="abc"></p><title>Löwe 老虎 Léopard</title><script><this should not be parsed>This should not too</script>"#,
    )));
    assert_eq!(
        parsed,
        Ok(vec![
            ElementContent::HtmlElement(Box::new(HtmlElement {
                name: "p",
                attributes: vec![("class", Some("❤"))],
                tag_state: ElementTagState::BothTag,
                content: vec![
                    ElementContent::LiteralContent("Hello!"),
                    ElementContent::HtmlElement(Box::new(HtmlElement {
                        name: "img",
                        attributes: vec![("src", Some("abc"))],
                        tag_state: ElementTagState::BothTag,
                        content: Vec::new()
                    }))
                ]
            })),
            ElementContent::HtmlElement(Box::new(HtmlElement {
                name: "title",
                attributes: Vec::new(),
                tag_state: ElementTagState::BothTag,
                content: vec![ElementContent::LiteralContent("Löwe 老虎 Léopard")]
            })),
            ElementContent::HtmlElement(Box::new(HtmlElement {
                name: "script",
                attributes: Vec::new(),
                tag_state: ElementTagState::BothTag,
                content: vec![ElementContent::LiteralContent("<this should not be parsed>This should not too")]
            }))
        ])
    );
}