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
|
//! Label occurs in [definition][] and [label end][label_end].
//!
//! ## Grammar
//!
//! Label forms with the following BNF
//! (<small>see [construct][crate::construct] for character groups</small>):
//!
//! ```bnf
//! ; Restriction: maximum `999` codes allowed between brackets.
//! ; Restriction: no blank lines.
//! ; Restriction: at least 1 `text` byte must exist.
//! label ::= '[' *(label_byte | label_escape) ']'
//! label_byte ::= code - '[' - '\\' - ']'
//! label_escape ::= '\\' ['[' | '\\' | ']']
//! ```
//!
//! The maximum allowed size of the label, without the brackets, is `999`
//! (inclusive), which is defined in
//! [`LINK_REFERENCE_SIZE_MAX`][link_reference_size_max].
//!
//! Labels can contain line endings and whitespace, but they are not allowed to
//! contain blank lines, and they must not be blank themselves.
//!
//! The label is interpreted as the [string][] content type.
//! That means that [character escapes][character_escape] and
//! [character references][character_reference] are allowed.
//!
//! > 👉 **Note**: this label relates to, but is not, the initial “label” of
//! > what is know as a reference in markdown:
//! >
//! > | Kind | Link | Image |
//! > | --------- | -------- | --------- |
//! > | Shortcut | `[x]` | `![x]` |
//! > | Collapsed | `[x][]` | `![x][]` |
//! > | Full | `[x][y]` | `![x][y]` |
//! >
//! > The 6 above things are references, in the three kinds they come in, as
//! > links and images.
//! > The label that this module focusses on is only the thing that contains
//! > `y`.
//! >
//! > The thing that contains `x` is not a single thing when parsing markdown,
//! > but instead constists of an opening
//! > ([label start (image)][label_start_image] or
//! > [label start (link)][label_start_link]) and a closing
//! > ([label end][label_end]), so as to allow further phrasing such as
//! > [code (text)][raw_text] or [attention][].
//!
//! ## References
//!
//! * [`micromark-factory-label/index.js` in `micromark`](https://github.com/micromark/micromark/blob/main/packages/micromark-factory-label/dev/index.js)
//!
//! [definition]: crate::construct::definition
//! [string]: crate::construct::string
//! [attention]: crate::construct::attention
//! [character_escape]: crate::construct::character_escape
//! [character_reference]: crate::construct::character_reference
//! [label_start_image]: crate::construct::label_start_image
//! [label_start_link]: crate::construct::label_start_link
//! [label_end]: crate::construct::label_end
//! [raw_text]: crate::construct::raw_text
//! [link_reference_size_max]: crate::util::constant::LINK_REFERENCE_SIZE_MAX
use crate::construct::partial_space_or_tab_eol::{space_or_tab_eol_with_options, Options};
use crate::event::{Content, Link, Name};
use crate::state::{Name as StateName, State};
use crate::subtokenize::link;
use crate::tokenizer::Tokenizer;
use crate::util::constant::LINK_REFERENCE_SIZE_MAX;
/// Start of label.
///
/// ```markdown
/// > | [a]
/// ^
/// ```
pub fn start(tokenizer: &mut Tokenizer) -> State {
match tokenizer.current {
Some(b'[') => {
tokenizer.enter(tokenizer.tokenize_state.token_1.clone());
tokenizer.enter(tokenizer.tokenize_state.token_2.clone());
tokenizer.consume();
tokenizer.exit(tokenizer.tokenize_state.token_2.clone());
State::Next(StateName::LabelAtMarker)
}
_ => State::Nok,
}
}
/// At an optional extra marker.
///
/// Used for footnotes.
///
/// ```markdown
/// > | [^a]
/// ^
/// ```
pub fn at_marker(tokenizer: &mut Tokenizer) -> State {
// For footnotes (and potentially other custom things in the future),
// We need to make sure there is a certain marker after `[`.
if tokenizer.tokenize_state.marker == 0 {
tokenizer.enter(tokenizer.tokenize_state.token_3.clone());
State::Retry(StateName::LabelAtBreak)
} else if tokenizer.current == Some(tokenizer.tokenize_state.marker) {
tokenizer.enter(tokenizer.tokenize_state.token_4.clone());
tokenizer.consume();
tokenizer.exit(tokenizer.tokenize_state.token_4.clone());
tokenizer.enter(tokenizer.tokenize_state.token_3.clone());
State::Next(StateName::LabelAtBreak)
} else {
State::Nok
}
}
/// In label, at something, before something else.
///
/// ```markdown
/// > | [a]
/// ^
/// ```
pub fn at_break(tokenizer: &mut Tokenizer) -> State {
if tokenizer.tokenize_state.size > LINK_REFERENCE_SIZE_MAX
|| matches!(tokenizer.current, None | Some(b'['))
|| (matches!(tokenizer.current, Some(b']')) && !tokenizer.tokenize_state.seen)
{
tokenizer.tokenize_state.connect = false;
tokenizer.tokenize_state.seen = false;
tokenizer.tokenize_state.size = 0;
State::Nok
} else {
match tokenizer.current {
Some(b'\n') => {
tokenizer.attempt(
State::Next(StateName::LabelEolAfter),
State::Next(StateName::LabelAtBlankLine),
);
State::Retry(space_or_tab_eol_with_options(
tokenizer,
Options {
content: Some(Content::String),
connect: tokenizer.tokenize_state.connect,
},
))
}
Some(b']') => {
tokenizer.exit(tokenizer.tokenize_state.token_3.clone());
tokenizer.enter(tokenizer.tokenize_state.token_2.clone());
tokenizer.consume();
tokenizer.exit(tokenizer.tokenize_state.token_2.clone());
tokenizer.exit(tokenizer.tokenize_state.token_1.clone());
tokenizer.tokenize_state.connect = false;
tokenizer.tokenize_state.seen = false;
tokenizer.tokenize_state.size = 0;
State::Ok
}
_ => {
tokenizer.enter_link(
Name::Data,
Link {
previous: None,
next: None,
content: Content::String,
},
);
if tokenizer.tokenize_state.connect {
let index = tokenizer.events.len() - 1;
link(&mut tokenizer.events, index);
} else {
tokenizer.tokenize_state.connect = true;
}
State::Retry(StateName::LabelInside)
}
}
}
}
/// In label, after whitespace.
///
/// ```markdown
/// | [a␊
/// > | b]
/// ^
/// ```
pub fn eol_after(tokenizer: &mut Tokenizer) -> State {
tokenizer.tokenize_state.connect = true;
State::Retry(StateName::LabelAtBreak)
}
/// In label, at blank line.
///
/// ```markdown
/// | [a␊
/// > | ␊
/// ^
/// | b]
/// ```
pub fn at_blank_line(tokenizer: &mut Tokenizer) -> State {
tokenizer.tokenize_state.marker = 0;
tokenizer.tokenize_state.connect = false;
State::Nok
}
/// In label, in text.
///
/// ```markdown
/// > | [a]
/// ^
/// ```
pub fn inside(tokenizer: &mut Tokenizer) -> State {
match tokenizer.current {
None | Some(b'\n' | b'[' | b']') => {
tokenizer.exit(Name::Data);
State::Retry(StateName::LabelAtBreak)
}
Some(byte) => {
if tokenizer.tokenize_state.size > LINK_REFERENCE_SIZE_MAX {
tokenizer.exit(Name::Data);
State::Retry(StateName::LabelAtBreak)
} else {
tokenizer.consume();
tokenizer.tokenize_state.size += 1;
if !tokenizer.tokenize_state.seen && !matches!(byte, b'\t' | b' ') {
tokenizer.tokenize_state.seen = true;
}
State::Next(if matches!(byte, b'\\') {
StateName::LabelEscape
} else {
StateName::LabelInside
})
}
}
}
}
/// After `\`, at a special character.
///
/// ```markdown
/// > | [a\*a]
/// ^
/// ```
pub fn escape(tokenizer: &mut Tokenizer) -> State {
match tokenizer.current {
Some(b'[' | b'\\' | b']') => {
tokenizer.consume();
tokenizer.tokenize_state.size += 1;
State::Next(StateName::LabelInside)
}
_ => State::Retry(StateName::LabelInside),
}
}
|
