File: text.rs

package info (click to toggle)
rustc 1.86.0%2Bdfsg1-1
  • links: PTS, VCS
  • area: main
  • in suites: experimental, forky, sid
  • size: 913,560 kB
  • sloc: xml: 158,127; python: 35,921; javascript: 19,689; sh: 19,600; cpp: 18,906; ansic: 13,124; asm: 4,376; makefile: 708; perl: 29; lisp: 29; ruby: 19; sql: 11
file content (60 lines) | stat: -rw-r--r-- 1,309 bytes parent folder | download | duplicates (5)
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
use html_parser::{Dom, Result};
use indoc::indoc;
use insta::assert_json_snapshot;

#[test]
fn it_can_parse_document_with_just_text() -> Result<()> {
    let html = "hello world";
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}

#[test]
fn it_can_parse_document_with_text_and_line_breaks() -> Result<()> {
    let html = indoc!(
        r"
        hello world
        here's another line for you!
        The end
    "
    );
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}

#[test]
fn it_can_parse_document_with_multiple_text_elements() -> Result<()> {
    let html = indoc!(
        r"
        hello world
        here's another line for you!
        <div/>
        The end
    "
    );
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}

#[test]
fn it_can_parse_text_with_chevron() -> Result<()> {
    let html = indoc!(r"hello <> world");
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}

#[test]
fn it_can_parse_text_in_paragraph_with_weird_formatting() -> Result<()> {
    let html = indoc!(r"
        <p>
            This is a <b>para</b>gra<b>ph</b> with some<i> weird </i> formatting.
        </p>
    ");
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}