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
|
//! Utility to normalize identifiers.
/// Normalize an identifier, as found in references and
/// [definitions][definition], so it can be compared when matching.
///
/// This collapsed whitespace found in markdown (`\t`, `\r`, `\n`, and ` `)
/// into one space, trims it (as in, dropping the first and last space),
/// and then performs unicode case folding twice: first by uppercasing
/// lowercase characters, and then lowercasing uppercase characters.
///
/// Some characters are considered “uppercase”, such as U+03F4 (`ϴ`), but if
/// their lowercase counterpart (U+03B8 (`θ`)) is uppercased will result in a
/// different uppercase character (U+0398 (`Θ`)).
/// Hence, to get that form, we perform both upper- and lowercase.
///
/// ## Examples
///
/// ```rust ignore
/// micromark::util::normalize_identifier::normalize_identifier;
///
/// assert_eq!(normalize_identifier(" a "), "a");
/// assert_eq!(normalize_identifier("a\t\r\nb"), "a b");
/// assert_eq!(normalize_identifier("ПРИВЕТ"), "привет");
/// assert_eq!(normalize_identifier("Привет"), "привет");
/// assert_eq!(normalize_identifier("привет"), "привет");
/// ```
///
/// ## References
///
/// * [`micromark-util-normalize-identifier` in `micromark`](https://github.com/micromark/micromark/tree/main/packages/micromark-util-normalize-identifier)
///
/// [definition]: crate::construct::definition
///
/// <!--To do: link resource.-->
pub fn normalize_identifier(value: &str) -> String {
let mut codes = vec![];
let mut at_start = true;
let mut at_whitespace = true;
// Collapse markdown whitespace and trim it.
for char in value.chars() {
match char {
'\t' | '\r' | '\n' | ' ' => {
at_whitespace = true;
}
_ => {
if at_whitespace && !at_start {
codes.push(' ');
}
codes.push(char);
at_start = false;
at_whitespace = false;
}
}
}
// To do: test if this matches unicode.
// Some characters are considered “uppercase”, but if their lowercase
// counterpart is uppercased will result in a different uppercase
// character.
// Hence, to get that form, we perform both lower- and uppercase.
codes
.iter()
.collect::<String>()
.to_uppercase()
.to_lowercase()
}
|
