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
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
|
//! Heading (atx) occurs in the [flow][] content type.
//!
//! ## Grammar
//!
//! Heading (atx) forms with the following BNF
//! (<small>see [construct][crate::construct] for character groups</small>):
//!
//! ```bnf
//! heading_atx ::= 1*6'#' [ 1*space_or_tab line [ 1*space_or_tab 1*'#' ] ] *space_or_tab
//! ```
//!
//! As this construct occurs in flow, like all flow constructs, it must be
//! followed by an eol (line ending) or eof (end of file).
//!
//! `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.
//!
//! > 🏛 **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.
//!
//! ## HTML
//!
//! 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.
//!
//! ## Recommendation
//!
//! Always use heading (atx), never heading (setext).
//!
//! ## Tokens
//!
//! * [`HeadingAtx`][Name::HeadingAtx]
//! * [`HeadingAtxSequence`][Name::HeadingAtxSequence]
//! * [`HeadingAtxText`][Name::HeadingAtxText]
//! * [`SpaceOrTab`][Name::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::construct::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 crate::construct::partial_space_or_tab::{space_or_tab, space_or_tab_min_max};
use crate::event::{Content, Event, Kind, Link, Name};
use crate::resolve::Name as ResolveName;
use crate::state::{Name as StateName, State};
use crate::subtokenize::Subresult;
use crate::tokenizer::Tokenizer;
use crate::util::constant::{HEADING_ATX_OPENING_FENCE_SIZE_MAX, TAB_SIZE};
use alloc::vec;
/// Start of a heading (atx).
///
/// ```markdown
/// > | ## aa
/// ^
/// ```
pub fn start(tokenizer: &mut Tokenizer) -> State {
if tokenizer.parse_state.options.constructs.heading_atx {
tokenizer.enter(Name::HeadingAtx);
if matches!(tokenizer.current, Some(b'\t' | b' ')) {
tokenizer.attempt(State::Next(StateName::HeadingAtxBefore), State::Nok);
State::Retry(space_or_tab_min_max(
tokenizer,
0,
if tokenizer.parse_state.options.constructs.code_indented {
TAB_SIZE - 1
} else {
usize::MAX
},
))
} else {
State::Retry(StateName::HeadingAtxBefore)
}
} else {
State::Nok
}
}
/// After optional whitespace, at `#`.
///
/// ```markdown
/// > | ## aa
/// ^
/// ```
pub fn before(tokenizer: &mut Tokenizer) -> State {
if Some(b'#') == tokenizer.current {
tokenizer.enter(Name::HeadingAtxSequence);
State::Retry(StateName::HeadingAtxSequenceOpen)
} else {
State::Nok
}
}
/// In opening sequence.
///
/// ```markdown
/// > | ## aa
/// ^
/// ```
pub fn sequence_open(tokenizer: &mut Tokenizer) -> State {
if tokenizer.current == Some(b'#')
&& tokenizer.tokenize_state.size < HEADING_ATX_OPENING_FENCE_SIZE_MAX
{
tokenizer.tokenize_state.size += 1;
tokenizer.consume();
State::Next(StateName::HeadingAtxSequenceOpen)
}
// Always at least one `#`.
else if matches!(tokenizer.current, None | Some(b'\t' | b'\n' | b' ')) {
tokenizer.tokenize_state.size = 0;
tokenizer.exit(Name::HeadingAtxSequence);
State::Retry(StateName::HeadingAtxAtBreak)
} else {
tokenizer.tokenize_state.size = 0;
State::Nok
}
}
/// After something, before something else.
///
/// ```markdown
/// > | ## aa
/// ^
/// ```
pub fn at_break(tokenizer: &mut Tokenizer) -> State {
match tokenizer.current {
None | Some(b'\n') => {
tokenizer.exit(Name::HeadingAtx);
tokenizer.register_resolver(ResolveName::HeadingAtx);
// Feel free to interrupt.
tokenizer.interrupt = false;
State::Ok
}
Some(b'\t' | b' ') => {
tokenizer.attempt(State::Next(StateName::HeadingAtxAtBreak), State::Nok);
State::Retry(space_or_tab(tokenizer))
}
Some(b'#') => {
tokenizer.enter(Name::HeadingAtxSequence);
State::Retry(StateName::HeadingAtxSequenceFurther)
}
Some(_) => {
tokenizer.enter_link(
Name::Data,
Link {
previous: None,
next: None,
content: Content::Text,
},
);
State::Retry(StateName::HeadingAtxData)
}
}
}
/// In further sequence (after whitespace).
///
/// Could be normal “visible” hashes in the heading or a final sequence.
///
/// ```markdown
/// > | ## aa ##
/// ^
/// ```
pub fn sequence_further(tokenizer: &mut Tokenizer) -> State {
if let Some(b'#') = tokenizer.current {
tokenizer.consume();
State::Next(StateName::HeadingAtxSequenceFurther)
} else {
tokenizer.exit(Name::HeadingAtxSequence);
State::Retry(StateName::HeadingAtxAtBreak)
}
}
/// In text.
///
/// ```markdown
/// > | ## aa
/// ^
/// ```
pub fn data(tokenizer: &mut Tokenizer) -> State {
match tokenizer.current {
// Note: `#` for closing sequence must be preceded by whitespace, otherwise it’s just text.
None | Some(b'\t' | b'\n' | b' ') => {
tokenizer.exit(Name::Data);
State::Retry(StateName::HeadingAtxAtBreak)
}
_ => {
tokenizer.consume();
State::Next(StateName::HeadingAtxData)
}
}
}
/// Resolve heading (atx).
pub fn resolve(tokenizer: &mut Tokenizer) -> Option<Subresult> {
let mut index = 0;
let mut heading_inside = false;
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.name == Name::HeadingAtx {
if event.kind == Kind::Enter {
heading_inside = true;
} else {
if let Some(start) = data_start {
// If `start` is some, `end` is too.
let end = data_end.unwrap();
tokenizer.map.add(
start,
0,
vec![Event {
kind: Kind::Enter,
name: Name::HeadingAtxText,
point: tokenizer.events[start].point.clone(),
link: None,
}],
);
// Remove everything between the start and the end.
tokenizer.map.add(start + 1, end - start - 1, vec![]);
tokenizer.map.add(
end + 1,
0,
vec![Event {
kind: Kind::Exit,
name: Name::HeadingAtxText,
point: tokenizer.events[end].point.clone(),
link: None,
}],
);
}
heading_inside = false;
data_start = None;
data_end = None;
}
} else if heading_inside && event.name == Name::Data {
if event.kind == Kind::Enter {
if data_start.is_none() {
data_start = Some(index);
}
} else {
data_end = Some(index);
}
}
index += 1;
}
tokenizer.map.consume(&mut tokenizer.events);
None
}
|