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
|
//! Paragraph occurs in the [flow][] content type.
//!
//! ## Grammar
//!
//! Paragraph forms with the following BNF
//! (<small>see [construct][crate::construct] for character groups</small>):
//!
//! ```bnf
//! ; Restriction: lines cannot start other flow constructs.
//! ; Restriction: lines cannot be blank.
//! paragraph ::= 1*line *(eol 1*line)
//! ```
//!
//! As this construct occurs in flow, like all flow constructs, it must be
//! followed by an eol (line ending) or eof (end of file).
//!
//! Paragraphs can contain line endings and whitespace, but they are not
//! allowed to contain blank lines, or to be blank themselves.
//!
//! The paragraph is interpreted as the [text][] content type.
//! That means that [autolinks][autolink], [code (text)][raw_text], etc are allowed.
//!
//! ## HTML
//!
//! Paragraphs in markdown relate to the `<p>` element in HTML.
//! See [*§ 4.4.1 The `p` element* in the HTML spec][html] for more info.
//!
//! ## Tokens
//!
//! * [`Paragraph`][Name::Paragraph]
//!
//! ## References
//!
//! * [`content.js` in `micromark`](https://github.com/micromark/micromark/blob/main/packages/micromark-core-commonmark/dev/lib/content.js)
//! * [*§ 4.8 Paragraphs* in `CommonMark`](https://spec.commonmark.org/0.30/#paragraphs)
//!
//! [flow]: crate::construct::flow
//! [text]: crate::construct::text
//! [autolink]: crate::construct::autolink
//! [raw_text]: crate::construct::raw_text
//! [html]: https://html.spec.whatwg.org/multipage/grouping-content.html#the-p-element
use crate::event::{Content, Kind, Link, Name};
use crate::resolve::Name as ResolveName;
use crate::state::{Name as StateName, State};
use crate::tokenizer::Tokenizer;
use alloc::vec;
/// Before paragraph.
///
/// ```markdown
/// > | abc
/// ^
/// ```
pub fn start(tokenizer: &mut Tokenizer) -> State {
match tokenizer.current {
None | Some(b'\n') => unreachable!("unexpected eol/eof"),
_ => {
tokenizer.enter(Name::Paragraph);
tokenizer.enter_link(
Name::Data,
Link {
previous: None,
next: None,
content: Content::Text,
},
);
State::Retry(StateName::ParagraphInside)
}
}
}
/// In paragraph.
///
/// ```markdown
/// > | abc
/// ^^^
/// ```
pub fn inside(tokenizer: &mut Tokenizer) -> State {
match tokenizer.current {
None | Some(b'\n') => {
tokenizer.exit(Name::Data);
tokenizer.exit(Name::Paragraph);
tokenizer.register_resolver_before(ResolveName::Paragraph);
// You’d be interrupting.
tokenizer.interrupt = true;
State::Ok
}
_ => {
tokenizer.consume();
State::Next(StateName::ParagraphInside)
}
}
}
/// Merge “`Paragraph`”s, which currently span a single line, into actual
/// `Paragraph`s that span multiple lines.
pub fn resolve(tokenizer: &mut Tokenizer) {
let mut index = 0;
while index < tokenizer.events.len() {
let event = &tokenizer.events[index];
if event.kind == Kind::Enter && event.name == Name::Paragraph {
// Exit:Paragraph
let mut exit_index = index + 3;
loop {
let mut enter_index = exit_index + 1;
if enter_index == tokenizer.events.len()
|| tokenizer.events[enter_index].name != Name::LineEnding
{
break;
}
enter_index += 2;
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::Paragraph
{
break;
}
// Remove Exit:Paragraph, Enter:LineEnding, Exit:LineEnding.
tokenizer.map.add(exit_index, 3, vec![]);
// Remove Enter:Paragraph.
tokenizer.map.add(enter_index, 1, vec![]);
// Add Exit:LineEnding position info to Exit:Data.
tokenizer.events[exit_index - 1].point =
tokenizer.events[exit_index + 2].point.clone();
// Link Enter:Data on the previous line to Enter:Data on this line.
if let Some(link) = &mut tokenizer.events[exit_index - 2].link {
link.next = Some(enter_index + 1);
}
if let Some(link) = &mut tokenizer.events[enter_index + 1].link {
link.previous = Some(exit_index - 2);
}
// Potential next start.
exit_index = enter_index + 3;
}
// Move to `Exit:Paragraph`.
index = exit_index;
}
index += 1;
}
tokenizer.map.consume(&mut tokenizer.events);
}
|
