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
|
//! Utilities to decode character references.
use crate::constant::CHARACTER_REFERENCES;
/// Decode named character references.
///
/// Turn the name coming from a named character reference (without the `&` or
/// `;`) into a string.
/// This looks the given string up at `0` in the tuples of
/// [`CHARACTER_REFERENCES`][] and then takes the corresponding value from `1`.
///
/// The result is `String` instead of `char` because named character references
/// can expand into multiple characters.
///
/// ## Examples
///
/// ```rust ignore
/// use micromark::util::decode_character_reference::decode_named;
///
/// assert_eq!(decode_named("amp"), "&");
/// assert_eq!(decode_named("AElig"), "Æ");
/// assert_eq!(decode_named("aelig"), "æ");
/// ```
///
/// ## Panics
///
/// This function panics if a name not in [`CHARACTER_REFERENCES`][] is
/// given.
/// It is expected that figuring out whether a name is allowed is handled in
/// the parser.
/// When `micromark` is used, this function never panics.
///
/// ## References
///
/// * [`wooorm/decode-named-character-reference`](https://github.com/wooorm/decode-named-character-reference)
/// * [*§ 2.5 Entity and numeric character references* in `CommonMark`](https://spec.commonmark.org/0.30/#entity-and-numeric-character-references)
pub fn decode_named(value: &str) -> String {
let entry = CHARACTER_REFERENCES.iter().find(|d| d.0 == value);
let tuple = entry.expect("expected valid `name`");
tuple.1.to_string()
}
/// Decode numeric character references.
///
/// Turn the number (in string form as either hexadecimal or decimal) coming
/// from a numeric character reference into a character.
/// Whether the base of the string form is `10` (decimal) or `16` (hexadecimal)
/// must be passed as the `radix` parameter.
///
/// This returns the `char` associated with that number or a replacement
/// character for C0 control characters (except for ASCII whitespace), C1
/// control characters, lone surrogates, noncharacters, and out of range
/// characters.
///
/// ## Examples
///
/// ```rust ignore
/// use micromark::util::decode_character_reference::decode_numeric;
///
/// assert_eq!(decode_numeric("123", 10), "{");
/// assert_eq!(decode_numeric("9", 16), "\t");
/// assert_eq!(decode_numeric("0", 10), "�"); // Not allowed.
/// ```
///
/// ## Panics
///
/// This function panics if a invalid string or an out of bounds valid string
/// is given.
/// It is expected that figuring out whether a number is allowed is handled in
/// the parser.
/// When `micromark` is used, this function never panics.
///
/// ## References
///
/// * [`micromark-util-decode-numeric-character-reference` in `micromark`](https://github.com/micromark/micromark/tree/main/packages/micromark-util-decode-numeric-character-reference)
/// * [*§ 2.5 Entity and numeric character references* in `CommonMark`](https://spec.commonmark.org/0.30/#entity-and-numeric-character-references)
pub fn decode_numeric(value: &str, radix: u32) -> String {
if let Some(char) = char::from_u32(u32::from_str_radix(value, radix).unwrap()) {
if !matches!(char,
// C0 except for HT, LF, FF, CR, space
'\0'..='\u{08}' | '\u{0B}' | '\u{0E}'..='\u{1F}' |
// Control character (DEL) of c0, and C1 controls.
'\u{7F}'..='\u{9F}'
// Lone surrogates, noncharacters, and out of range are handled by
// Rust.
) {
return char.to_string();
}
}
char::REPLACEMENT_CHARACTER.to_string()
}
|
