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
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
|
//! Heading (atx) is a construct that occurs in the [flow] content type.
//!
//! They’re formed with the following BNF:
//!
//! ```bnf
//! heading_atx ::= 1*6'#' [ 1*space_or_tab text [ 1*space_or_tab 1*'#' ] ] *space_or_tab
//!
//! text ::= code - eol
//! space_or_tab ::= ' ' | '\t'
//! ```
//!
//! Headings in markdown relate to the `<h1>` through `<h6>` elements in HTML.
//! See [*§ 4.3.6 The `h1`, `h2`, `h3`, `h4`, `h5`, and `h6` elements* in the
//! HTML spec][html] for more info.
//!
//! `CommonMark` introduced the requirement on whitespace existing after the
//! opening sequence and before text.
//! In older markdown versions, this was not required, and headings would form
//! without it.
//!
//! In markdown, it is also possible to create headings with a
//! [heading (setext)][heading_setext] construct.
//! The benefit of setext headings is that their text can include line endings,
//! and by extensions also hard breaks (e.g., with
//! [hard break (escape)][hard_break_escape]).
//! However, their limit is that they cannot form `<h3>` through `<h6>`
//! headings.
//! Due to this limitation, it is recommended to use atx headings.
//!
//! > 🏛 **Background**: the word *setext* originates from a small markup
//! > language by Ian Feldman from 1991.
//! > See [*§ Setext* on Wikipedia][wiki-setext] for more info.
//! > The word *atx* originates from a tiny markup language by Aaron Swartz
//! > from 2002.
//! > See [*§ atx, the true structured text format* on `aaronsw.com`][atx] for
//! > more info.
//!
//! ## Tokens
//!
//! * [`HeadingAtx`][Token::HeadingAtx]
//! * [`HeadingAtxSequence`][Token::HeadingAtxSequence]
//! * [`HeadingAtxText`][Token::HeadingAtxText]
//! * [`SpaceOrTab`][Token::SpaceOrTab]
//!
//! ## References
//!
//! * [`heading-atx.js` in `micromark`](https://github.com/micromark/micromark/blob/main/packages/micromark-core-commonmark/dev/lib/heading-atx.js)
//! * [*§ 4.2 ATX headings* in `CommonMark`](https://spec.commonmark.org/0.30/#atx-headings)
//!
//! [flow]: crate::content::flow
//! [heading_setext]: crate::construct::heading_setext
//! [hard_break_escape]: crate::construct::hard_break_escape
//! [html]: https://html.spec.whatwg.org/multipage/sections.html#the-h1,-h2,-h3,-h4,-h5,-and-h6-elements
//! [wiki-setext]: https://en.wikipedia.org/wiki/Setext
//! [atx]: http://www.aaronsw.com/2002/atx/
use super::partial_space_or_tab::{space_or_tab, space_or_tab_min_max};
use crate::constant::{HEADING_ATX_OPENING_FENCE_SIZE_MAX, TAB_SIZE};
use crate::token::Token;
use crate::tokenizer::{Code, ContentType, Event, EventType, State, StateFnResult, Tokenizer};
use crate::util::edit_map::EditMap;
/// Start of a heading (atx).
///
/// ```markdown
/// |## alpha
/// ```
pub fn start(tokenizer: &mut Tokenizer, code: Code) -> StateFnResult {
tokenizer.enter(Token::HeadingAtx);
// To do: allow arbitrary when code (indented) is turned off.
tokenizer.go(space_or_tab_min_max(0, TAB_SIZE - 1), before)(tokenizer, code)
}
/// Start of a heading (atx), after whitespace.
///
/// ```markdown
/// |## alpha
/// ```
fn before(tokenizer: &mut Tokenizer, code: Code) -> StateFnResult {
if Code::Char('#') == code {
tokenizer.enter(Token::HeadingAtxSequence);
sequence_open(tokenizer, code, 0)
} else {
(State::Nok, None)
}
}
/// In the opening sequence.
///
/// ```markdown
/// #|# alpha
/// ```
fn sequence_open(tokenizer: &mut Tokenizer, code: Code, rank: usize) -> StateFnResult {
match code {
Code::None | Code::CarriageReturnLineFeed | Code::Char('\n' | '\r') if rank > 0 => {
tokenizer.exit(Token::HeadingAtxSequence);
at_break(tokenizer, code)
}
Code::Char('#') if rank < HEADING_ATX_OPENING_FENCE_SIZE_MAX => {
tokenizer.consume(code);
(
State::Fn(Box::new(move |tokenizer, code| {
sequence_open(tokenizer, code, rank + 1)
})),
None,
)
}
_ if rank > 0 => {
tokenizer.exit(Token::HeadingAtxSequence);
tokenizer.go(space_or_tab(), at_break)(tokenizer, code)
}
_ => (State::Nok, None),
}
}
/// After something but before something else.
///
/// ```markdown
/// ## |alpha
/// ## alpha| bravo
/// ## alpha |bravo
/// ## alpha bravo|##
/// ## alpha bravo ##|
/// ```
fn at_break(tokenizer: &mut Tokenizer, code: Code) -> StateFnResult {
match code {
Code::None | Code::CarriageReturnLineFeed | Code::Char('\n' | '\r') => {
tokenizer.exit(Token::HeadingAtx);
tokenizer.register_resolver("heading_atx".to_string(), Box::new(resolve));
// Feel free to interrupt.
tokenizer.interrupt = false;
(State::Ok, Some(vec![code]))
}
Code::VirtualSpace | Code::Char('\t' | ' ') => {
tokenizer.go(space_or_tab(), at_break)(tokenizer, code)
}
Code::Char('#') => {
tokenizer.enter(Token::HeadingAtxSequence);
further_sequence(tokenizer, code)
}
Code::Char(_) => {
tokenizer.enter_with_content(Token::Data, Some(ContentType::Text));
data(tokenizer, code)
}
}
}
/// In a further sequence (after whitespace).
/// Could be normal “visible” hashes in the heading or a final sequence.
///
/// ```markdown
/// ## alpha #|#
/// ```
fn further_sequence(tokenizer: &mut Tokenizer, code: Code) -> StateFnResult {
if let Code::Char('#') = code {
tokenizer.consume(code);
(State::Fn(Box::new(further_sequence)), None)
} else {
tokenizer.exit(Token::HeadingAtxSequence);
at_break(tokenizer, code)
}
}
/// In text.
///
/// ```markdown
/// ## al|pha
/// ```
fn data(tokenizer: &mut Tokenizer, code: Code) -> StateFnResult {
match code {
// Note: `#` for closing sequence must be preceded by whitespace, otherwise it’s just text.
Code::None | Code::CarriageReturnLineFeed | Code::Char('\t' | '\n' | '\r' | ' ') => {
tokenizer.exit(Token::Data);
at_break(tokenizer, code)
}
_ => {
tokenizer.consume(code);
(State::Fn(Box::new(data)), None)
}
}
}
/// Resolve heading (atx).
pub fn resolve(tokenizer: &mut Tokenizer) -> Vec<Event> {
let mut edit_map = EditMap::new();
let mut index = 0;
let mut heading_start: Option<usize> = None;
let mut data_start: Option<usize> = None;
let mut data_end: Option<usize> = None;
while index < tokenizer.events.len() {
let event = &tokenizer.events[index];
if event.token_type == Token::HeadingAtx {
if event.event_type == EventType::Enter {
heading_start = Some(index);
} else if let Some(start) = data_start {
// If `start` is some, `end` is too.
let end = data_end.unwrap();
edit_map.add(
start,
0,
vec![Event {
event_type: EventType::Enter,
token_type: Token::HeadingAtxText,
point: tokenizer.events[start].point.clone(),
index: tokenizer.events[start].index,
previous: None,
next: None,
content_type: None,
}],
);
// Remove everything between the start and the end.
edit_map.add(start + 1, end - start - 1, vec![]);
edit_map.add(
end + 1,
0,
vec![Event {
event_type: EventType::Exit,
token_type: Token::HeadingAtxText,
point: tokenizer.events[end].point.clone(),
index: tokenizer.events[end].index,
previous: None,
next: None,
content_type: None,
}],
);
heading_start = None;
data_start = None;
data_end = None;
}
} else if heading_start.is_some() && event.token_type == Token::Data {
if event.event_type == EventType::Enter {
if data_start.is_none() {
data_start = Some(index);
}
} else {
data_end = Some(index);
}
}
index += 1;
}
edit_map.consume(&mut tokenizer.events)
}
|
