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
|
//! The string content type.
//!
//! **String** is a limited [text][] like content type which only allows
//! character escapes and character references.
//! It exists in things such as identifiers (media references, definitions),
//! titles, URLs, code (fenced) info and meta parts.
//!
//! The constructs found in string are:
//!
//! * [Character escape][crate::construct::character_escape]
//! * [Character reference][crate::construct::character_reference]
//!
//! [text]: crate::content::text
use crate::construct::{
character_escape::start as character_escape, character_reference::start as character_reference,
partial_data::start as data, partial_whitespace::whitespace,
};
use crate::tokenizer::{Code, State, StateFnResult, Tokenizer};
/// Before string.
pub fn start(tokenizer: &mut Tokenizer, code: Code) -> StateFnResult {
let mut markers = vec![
Code::VirtualSpace, // `whitespace`
Code::Char('\t'), // `whitespace`
Code::Char(' '), // `hard_break_trailing`, `whitespace`
];
if tokenizer.parse_state.constructs.character_reference {
markers.push(Code::Char('&'));
}
if tokenizer.parse_state.constructs.character_escape {
markers.push(Code::Char('\\'));
}
before_marker(tokenizer, code, markers)
}
/// Before string.
fn before_marker(tokenizer: &mut Tokenizer, code: Code, markers: Vec<Code>) -> StateFnResult {
match code {
Code::None => (State::Ok, None),
_ => tokenizer.attempt_n(
vec![
Box::new(character_reference),
Box::new(character_escape),
Box::new(whitespace),
],
|ok| {
let func = if ok { before_marker } else { before_data };
Box::new(move |t, c| func(t, c, markers))
},
)(tokenizer, code),
}
}
/// At data.
fn before_data(tokenizer: &mut Tokenizer, code: Code, markers: Vec<Code>) -> StateFnResult {
let copy = markers.clone();
tokenizer.go(|t, c| data(t, c, copy), |t, c| before_marker(t, c, markers))(tokenizer, code)
}
|
