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
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
|
//! Content occurs in the [flow][] content type.
//!
//! Content contains zero or more [definition][definition]s, followed by zero
//! or one [paragraph][].
//!
//! The constructs found in flow are:
//!
//! * [Definition][crate::construct::definition]
//! * [Paragraph][crate::construct::paragraph]
//!
//! ## Tokens
//!
//! * [`Content`][Name::Content]
//!
//! > 👉 **Note**: while parsing, [`Content`][Name::Content]
//! > is used, which is later compiled away.
//!
//! ## References
//!
//! * [`content.js` in `micromark`](https://github.com/micromark/micromark/blob/main/packages/micromark-core-commonmark/dev/lib/content.js)
//!
//! [flow]: crate::construct::flow
//! [definition]: crate::construct::definition
//! [paragraph]: crate::construct::paragraph
use crate::event::{Content, Kind, Link, Name};
use crate::resolve::Name as ResolveName;
use crate::state::{Name as StateName, State};
use crate::subtokenize::{subtokenize, Subresult};
use crate::tokenizer::Tokenizer;
use alloc::{string::String, vec};
/// Before a content content.
///
/// ```markdown
/// > | abc
/// ^
/// ```
pub fn chunk_start(tokenizer: &mut Tokenizer) -> State {
match tokenizer.current {
None | Some(b'\n') => unreachable!("unexpected eol/eof"),
_ => {
tokenizer.enter_link(
Name::Content,
Link {
previous: None,
next: None,
content: Content::Content,
},
);
State::Retry(StateName::ContentChunkInside)
}
}
}
/// In a content chunk.
///
/// ```markdown
/// > | abc
/// ^^^
/// ```
pub fn chunk_inside(tokenizer: &mut Tokenizer) -> State {
match tokenizer.current {
None | Some(b'\n') => {
tokenizer.exit(Name::Content);
tokenizer.register_resolver_before(ResolveName::Content);
// You’d be interrupting.
tokenizer.interrupt = true;
State::Ok
}
_ => {
tokenizer.consume();
State::Next(StateName::ContentChunkInside)
}
}
}
/// Before a definition.
///
/// ```markdown
/// > | [a]: b
/// ^
/// ```
pub fn definition_before(tokenizer: &mut Tokenizer) -> State {
tokenizer.attempt(
State::Next(StateName::ContentDefinitionAfter),
State::Next(StateName::ParagraphStart),
);
State::Retry(StateName::DefinitionStart)
}
/// After a definition.
///
/// ```markdown
/// > | [a]: b
/// ^
/// | c
/// ```
pub fn definition_after(tokenizer: &mut Tokenizer) -> State {
debug_assert!(matches!(tokenizer.current, None | Some(b'\n')));
if tokenizer.current.is_none() {
State::Ok
} else {
tokenizer.enter(Name::LineEnding);
tokenizer.consume();
tokenizer.exit(Name::LineEnding);
State::Next(StateName::ContentDefinitionBefore)
}
}
/// Merge `Content` chunks, which currently span a single line, into actual
/// `Content`s that span multiple lines.
pub fn resolve(tokenizer: &mut Tokenizer) -> Result<Option<Subresult>, String> {
let mut index = 0;
while index < tokenizer.events.len() {
let event = &tokenizer.events[index];
if event.kind == Kind::Enter && event.name == Name::Content {
// Exit:Content
let mut exit_index = index + 1;
loop {
let mut enter_index = exit_index + 1;
if enter_index == tokenizer.events.len()
|| tokenizer.events[enter_index].name != Name::LineEnding
{
break;
}
// Skip past line ending.
enter_index += 2;
// Skip past prefix.
while enter_index < tokenizer.events.len() {
let event = &tokenizer.events[enter_index];
if event.name != Name::SpaceOrTab
&& event.name != Name::BlockQuotePrefix
&& event.name != Name::BlockQuoteMarker
{
break;
}
enter_index += 1;
}
if enter_index == tokenizer.events.len()
|| tokenizer.events[enter_index].name != Name::Content
{
break;
}
// Set Exit:Content point to Exit:LineEnding.
tokenizer.events[exit_index].point = tokenizer.events[exit_index + 2].point.clone();
// Remove Enter:LineEnding, Exit:LineEnding.
tokenizer.map.add(exit_index + 1, 2, vec![]);
// Link Enter:Content to Enter:Content on this line and vice versa.
tokenizer.events[exit_index - 1].link.as_mut().unwrap().next = Some(enter_index);
tokenizer.events[enter_index]
.link
.as_mut()
.unwrap()
.previous = Some(exit_index - 1);
// Potential next start.
exit_index = enter_index + 1;
}
// Move to `Exit:Content`.
index = exit_index;
}
index += 1;
}
tokenizer.map.consume(&mut tokenizer.events);
let result = subtokenize(
&mut tokenizer.events,
tokenizer.parse_state,
&Some(Content::Content),
)?;
Ok(Some(result))
}
|
