aboutsummaryrefslogtreecommitdiffstats
path: root/src/content/string.rs
blob: efb6e6019b4ff20bc734bdfaa8c4abcc3eed6df6 (plain) (blame)
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
//! 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,
};
use crate::tokenizer::{Code, State, StateFnResult, TokenType, Tokenizer};

// To do: line endings?

/// Before string.
///
/// ```markdown
/// |&
/// |\&
/// |qwe
/// ```
pub fn start(tokenizer: &mut Tokenizer, code: Code) -> StateFnResult {
    match code {
        Code::None => (State::Ok, None),
        _ => tokenizer.attempt_2(character_reference, character_escape, |ok| {
            Box::new(if ok { start } else { before_data })
        })(tokenizer, code),
    }
}

/// Before string, not at a character reference or character escape.
///
/// We’re at data.
///
/// ```markdown
/// |qwe
/// ```
fn before_data(tokenizer: &mut Tokenizer, code: Code) -> StateFnResult {
    match code {
        Code::None => (State::Ok, None),
        Code::CarriageReturnLineFeed | Code::Char('\r' | '\n') => {
            tokenizer.enter(TokenType::LineEnding);
            tokenizer.consume(code);
            tokenizer.exit(TokenType::LineEnding);
            (State::Fn(Box::new(start)), None)
        }
        _ => {
            tokenizer.enter(TokenType::Data);
            tokenizer.consume(code);
            (State::Fn(Box::new(in_data)), None)
        }
    }

    // if let Code::None = code {
    //     (State::Ok, None)
    // } else {
    //     tokenizer.enter(TokenType::Data);
    //     tokenizer.consume(code);
    //     (State::Fn(Box::new(in_data)), None)
    // }
}

/// In data.
///
/// ```markdown
/// q|w|e
/// ```
fn in_data(tokenizer: &mut Tokenizer, code: Code) -> StateFnResult {
    match code {
        Code::None | Code::CarriageReturnLineFeed | Code::Char('\r' | '\n') => {
            tokenizer.exit(TokenType::Data);
            before_data(tokenizer, code)
        }
        // To do: somehow get these markers from constructs.
        Code::Char('&' | '\\') => {
            tokenizer.exit(TokenType::Data);
            start(tokenizer, code)
        }
        _ => {
            tokenizer.consume(code);
            (State::Fn(Box::new(in_data)), None)
        }
    }
}