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
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
|
//! The flow content type.
//!
//! **Flow** represents the sections, such as headings and code, which are
//! parsed per line.
//! An example is HTML, which has a certain starting condition (such as
//! `<script>` on its own line), then continues for a while, until an end
//! condition is found (such as `</style>`).
//! If that line with an end condition is never found, that flow goes until
//! the end.
//!
//! The constructs found in flow are:
//!
//! * [Blank line][crate::construct::blank_line]
//! * [Code (fenced)][crate::construct::code_fenced]
//! * [Code (indented)][crate::construct::code_indented]
//! * [Definition][crate::construct::definition]
//! * [Heading (atx)][crate::construct::heading_atx]
//! * [Heading (setext)][crate::construct::heading_setext]
//! * [HTML (flow)][crate::construct::html_flow]
//! * [Thematic break][crate::construct::thematic_break]
use crate::construct::{
blank_line::start as blank_line, code_fenced::start as code_fenced,
code_indented::start as code_indented, definition::start as definition,
heading_atx::start as heading_atx, heading_setext::start as heading_setext,
html_flow::start as html_flow, paragraph::start as paragraph,
thematic_break::start as thematic_break,
};
use crate::token::Token;
use crate::tokenizer::{Code, State, Tokenizer};
/// Before flow.
///
/// First we assume a blank line.
//
/// ```markdown
/// |
/// |## alpha
/// | bravo
/// |***
/// ```
pub fn start(tokenizer: &mut Tokenizer, code: Code) -> State {
match code {
Code::None => State::Ok,
_ => tokenizer.attempt(blank_line, |ok| {
Box::new(if ok { blank_line_after } else { initial_before })
})(tokenizer, code),
}
}
/// Before flow (initial).
///
/// “Initial” flow means unprefixed flow, so right at the start of a line.
/// Interestingly, the only flow (initial) construct is indented code.
/// Move to `before` afterwards.
///
/// ```markdown
/// |qwe
/// | asd
/// |~~~js
/// |<div>
/// ```
fn initial_before(tokenizer: &mut Tokenizer, code: Code) -> State {
match code {
Code::None => State::Ok,
_ => tokenizer.attempt_n(
vec![
Box::new(code_indented),
Box::new(code_fenced),
Box::new(html_flow),
Box::new(heading_atx),
Box::new(heading_setext),
Box::new(thematic_break),
Box::new(definition),
],
|ok| Box::new(if ok { after } else { before_paragraph }),
)(tokenizer, code),
}
}
/// After a blank line.
///
/// Move to `start` afterwards.
///
/// ```markdown
/// ␠␠|
/// ```
fn blank_line_after(tokenizer: &mut Tokenizer, code: Code) -> State {
match code {
Code::None => State::Ok,
Code::CarriageReturnLineFeed | Code::Char('\n' | '\r') => {
tokenizer.enter(Token::BlankLineEnding);
tokenizer.consume(code);
tokenizer.exit(Token::BlankLineEnding);
// Feel free to interrupt.
tokenizer.interrupt = false;
State::Fn(Box::new(start))
}
_ => unreachable!("expected eol/eof"),
}
}
/// After something.
///
/// ```markdown
/// ## alpha|
/// |
/// ~~~js
/// asd
/// ~~~|
/// ```
fn after(tokenizer: &mut Tokenizer, code: Code) -> State {
match code {
Code::None => State::Ok,
Code::CarriageReturnLineFeed | Code::Char('\n' | '\r') => {
tokenizer.enter(Token::LineEnding);
tokenizer.consume(code);
tokenizer.exit(Token::LineEnding);
State::Fn(Box::new(start))
}
_ => unreachable!("expected eol/eof"),
}
}
/// Before a paragraph.
///
/// ```markdown
/// |asd
/// ```
fn before_paragraph(tokenizer: &mut Tokenizer, code: Code) -> State {
tokenizer.go(paragraph, after)(tokenizer, code)
}
|
