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
133
134
135
136
137
|
//! Thematic breaks, sometimes called horizontal rules, are a construct that
//! occurs in the flow content type.
//!
//! They’re formed with the following BNF:
//!
//! ```bnf
//! ; Restriction: all markers must be identical.
//! ; Restriction: at least 3 markers must be used.
//! thematic_break ::= *space_or_tab 1*(1*marker *space_or_tab)
//!
//! space_or_tab ::= ' ' | '\t'
//! marker ::= '*' | '-' | '_'
//! ```
//!
//! Thematic breaks in markdown typically relate to the HTML element `<hr>`.
//! See [*§ 4.4.2 The `hr` element* in the HTML spec][html] for more info.
//!
//! It is recommended to use exactly three asterisks without whitespace when
//! writing markdown.
//! As using more than three markers has no effect other than wasting space,
//! it is recommended to use exactly three markers.
//! Thematic breaks formed with asterisks or dashes can interfere with lists
//! in if there is whitespace between them: `* * *` and `- - -`.
//! For these reasons, it is recommend to not use spaces or tabs between the
//! markers.
//! Thematic breaks formed with dashes (without whitespace) can also form
//! setext headings.
//! As dashes and underscores frequently occur in natural language and URLs, it
//! is recommended to use asterisks for thematic breaks to distinguish from
//! such use.
//! Because asterisks can be used to form the most markdown constructs, using
//! them has the added benefit of making it easier to gloss over markdown: you
//! can look for asterisks to find syntax while not worrying about other
//! characters.
//!
//! ## References
//!
//! * [`thematic-break.js` in `micromark`](https://github.com/micromark/micromark/blob/main/packages/micromark-core-commonmark/dev/lib/thematic-break.js)
//! * [*§ 4.1 Thematic breaks* in `CommonMark`](https://spec.commonmark.org/0.30/#thematic-breaks)
//!
//! [html]: https://html.spec.whatwg.org/multipage/grouping-content.html#the-hr-element
//!
//! <!-- To do: link `flow` -->
use crate::constant::THEMATIC_BREAK_MARKER_COUNT_MIN;
use crate::tokenizer::{Code, State, StateFnResult, TokenType, Tokenizer};
/// Start of a thematic break.
///
/// ```markdown
/// |***
/// ```
pub fn start(tokenizer: &mut Tokenizer, code: Code) -> StateFnResult {
match code {
Code::Char(char) if char == '*' || char == '-' || char == '_' => {
tokenizer.enter(TokenType::ThematicBreak);
at_break(tokenizer, code, char, 0)
}
_ => (State::Nok, None),
}
}
/// After something but before something else.
///
/// ```markdown
/// |***
/// *| * *
/// * |* *
/// ```
fn at_break(tokenizer: &mut Tokenizer, code: Code, marker: char, size: usize) -> StateFnResult {
match code {
Code::Char(char) if char == marker => {
tokenizer.enter(TokenType::ThematicBreakSequence);
sequence(tokenizer, code, marker, size)
}
Code::VirtualSpace | Code::Char('\t' | ' ') => {
tokenizer.enter(TokenType::ThematicBreakWhitespace);
whitespace(tokenizer, code, marker, size)
}
Code::None | Code::CarriageReturnLineFeed | Code::Char('\n' | '\r')
if size >= THEMATIC_BREAK_MARKER_COUNT_MIN =>
{
tokenizer.exit(TokenType::ThematicBreak);
(State::Ok, Some(vec![code]))
}
_ => (State::Nok, None),
}
}
/// In a sequence of markers.
///
/// ```markdown
/// |***
/// *|**
/// **|*
/// ```
fn sequence(tokenizer: &mut Tokenizer, code: Code, marker: char, size: usize) -> StateFnResult {
match code {
Code::Char(char) if char == marker => {
tokenizer.consume(code);
(
State::Fn(Box::new(move |tokenizer, code| {
sequence(tokenizer, code, marker, size + 1)
})),
None,
)
}
_ => {
tokenizer.exit(TokenType::ThematicBreakSequence);
at_break(tokenizer, code, marker, size)
}
}
}
/// In whitespace.
///
/// ```markdown
/// * |* *
/// * | * *
/// ```
fn whitespace(tokenizer: &mut Tokenizer, code: Code, marker: char, size: usize) -> StateFnResult {
match code {
Code::VirtualSpace | Code::Char('\t' | ' ') => {
tokenizer.consume(code);
(
State::Fn(Box::new(move |tokenizer, code| {
whitespace(tokenizer, code, marker, size)
})),
None,
)
}
_ => {
tokenizer.exit(TokenType::ThematicBreakWhitespace);
at_break(tokenizer, code, marker, size)
}
}
}
|
