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
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
|
//! Several helpers to parse whitespace (`space_or_tab`, `space_or_tab_eol`).
//!
//! ## References
//!
//! * [`micromark-factory-space/index.js` in `micromark`](https://github.com/micromark/micromark/blob/main/packages/micromark-factory-space/dev/index.js)
use crate::subtokenize::link;
use crate::token::Token;
use crate::tokenizer::{ContentType, State, StateName, Tokenizer};
/// Options to parse `space_or_tab`.
#[derive(Debug)]
pub struct Options {
/// Minimum allowed bytes (inclusive).
pub min: usize,
/// Maximum allowed bytes (inclusive).
pub max: usize,
/// Token type to use for whitespace events.
pub kind: Token,
/// Connect this whitespace to the previous.
pub connect: bool,
/// Embedded content type to use.
pub content_type: Option<ContentType>,
}
/// Options to parse `space_or_tab` and one optional eol, but no blank line.
#[derive(Debug)]
pub struct EolOptions {
/// Connect this whitespace to the previous.
pub connect: bool,
/// Embedded content type to use.
pub content_type: Option<ContentType>,
}
/// One or more `space_or_tab`.
///
/// ```bnf
/// space_or_tab ::= 1*( ' ' '\t' )
/// ```
pub fn space_or_tab(tokenizer: &mut Tokenizer) -> StateName {
space_or_tab_min_max(tokenizer, 1, usize::MAX)
}
/// Between `x` and `y` `space_or_tab`.
///
/// ```bnf
/// space_or_tab_min_max ::= x*y( ' ' '\t' )
/// ```
pub fn space_or_tab_min_max(tokenizer: &mut Tokenizer, min: usize, max: usize) -> StateName {
space_or_tab_with_options(
tokenizer,
Options {
kind: Token::SpaceOrTab,
min,
max,
content_type: None,
connect: false,
},
)
}
/// `space_or_tab`, with the given options.
pub fn space_or_tab_with_options(tokenizer: &mut Tokenizer, options: Options) -> StateName {
tokenizer.tokenize_state.space_or_tab_connect = options.connect;
tokenizer.tokenize_state.space_or_tab_content_type = options.content_type;
tokenizer.tokenize_state.space_or_tab_min = options.min;
tokenizer.tokenize_state.space_or_tab_max = options.max;
tokenizer.tokenize_state.space_or_tab_token = options.kind;
StateName::SpaceOrTabStart
}
/// `space_or_tab`, or optionally `space_or_tab`, one `eol`, and
/// optionally `space_or_tab`.
///
/// ```bnf
/// space_or_tab_eol ::= 1*( ' ' '\t' ) | 0*( ' ' '\t' ) eol 0*( ' ' '\t' )
/// ```
pub fn space_or_tab_eol(tokenizer: &mut Tokenizer) -> StateName {
space_or_tab_eol_with_options(
tokenizer,
EolOptions {
content_type: None,
connect: false,
},
)
}
/// `space_or_tab_eol`, with the given options.
pub fn space_or_tab_eol_with_options(tokenizer: &mut Tokenizer, options: EolOptions) -> StateName {
tokenizer.tokenize_state.space_or_tab_eol_content_type = options.content_type;
tokenizer.tokenize_state.space_or_tab_eol_connect = options.connect;
StateName::SpaceOrTabEolStart
}
/// Before `space_or_tab`.
///
/// ```markdown
/// > | a␠␠b
/// ^
/// ```
pub fn start(tokenizer: &mut Tokenizer) -> State {
match tokenizer.current {
Some(b'\t' | b' ') if tokenizer.tokenize_state.space_or_tab_max > 0 => {
tokenizer.enter_with_content(
tokenizer.tokenize_state.space_or_tab_token.clone(),
tokenizer.tokenize_state.space_or_tab_content_type.clone(),
);
if tokenizer.tokenize_state.space_or_tab_connect {
let index = tokenizer.events.len() - 1;
link(&mut tokenizer.events, index);
} else if tokenizer.tokenize_state.space_or_tab_content_type.is_some() {
tokenizer.tokenize_state.space_or_tab_connect = true;
}
inside(tokenizer)
}
_ => after(tokenizer),
}
}
/// In `space_or_tab`.
///
/// ```markdown
/// > | a␠␠b
/// ^
/// ```
pub fn inside(tokenizer: &mut Tokenizer) -> State {
match tokenizer.current {
Some(b'\t' | b' ')
if tokenizer.tokenize_state.space_or_tab_size
< tokenizer.tokenize_state.space_or_tab_max =>
{
tokenizer.consume();
tokenizer.tokenize_state.space_or_tab_size += 1;
State::Fn(StateName::SpaceOrTabInside)
}
_ => {
tokenizer.exit(tokenizer.tokenize_state.space_or_tab_token.clone());
after(tokenizer)
}
}
}
/// After `space_or_tab`.
///
/// ```markdown
/// > | a␠␠b
/// ^
/// ```
pub fn after(tokenizer: &mut Tokenizer) -> State {
let state = if tokenizer.tokenize_state.space_or_tab_size
>= tokenizer.tokenize_state.space_or_tab_min
{
State::Ok
} else {
State::Nok
};
tokenizer.tokenize_state.space_or_tab_connect = false;
tokenizer.tokenize_state.space_or_tab_content_type = None;
tokenizer.tokenize_state.space_or_tab_size = 0;
tokenizer.tokenize_state.space_or_tab_max = 0;
tokenizer.tokenize_state.space_or_tab_min = 0;
tokenizer.tokenize_state.space_or_tab_token = Token::SpaceOrTab;
state
}
pub fn eol_start(tokenizer: &mut Tokenizer) -> State {
let state_name = space_or_tab_with_options(
tokenizer,
Options {
kind: Token::SpaceOrTab,
min: 1,
max: usize::MAX,
content_type: tokenizer
.tokenize_state
.space_or_tab_eol_content_type
.clone(),
connect: tokenizer.tokenize_state.space_or_tab_eol_connect,
},
);
tokenizer.attempt(
state_name,
State::Fn(StateName::SpaceOrTabEolAfterFirst),
State::Fn(StateName::SpaceOrTabEolAtEol),
)
}
pub fn eol_after_first(tokenizer: &mut Tokenizer) -> State {
tokenizer.tokenize_state.space_or_tab_eol_ok = true;
if tokenizer
.tokenize_state
.space_or_tab_eol_content_type
.is_some()
{
tokenizer.tokenize_state.space_or_tab_eol_connect = true;
}
eol_at_eol(tokenizer)
}
/// `space_or_tab_eol`: after optionally first `space_or_tab`.
///
/// ```markdown
/// > | a
/// ^
/// | b
/// ```
pub fn eol_at_eol(tokenizer: &mut Tokenizer) -> State {
if let Some(b'\n') = tokenizer.current {
tokenizer.enter_with_content(
Token::LineEnding,
tokenizer
.tokenize_state
.space_or_tab_eol_content_type
.clone(),
);
if tokenizer.tokenize_state.space_or_tab_eol_connect {
let index = tokenizer.events.len() - 1;
link(&mut tokenizer.events, index);
} else if tokenizer
.tokenize_state
.space_or_tab_eol_content_type
.is_some()
{
tokenizer.tokenize_state.space_or_tab_eol_connect = true;
}
tokenizer.consume();
tokenizer.exit(Token::LineEnding);
State::Fn(StateName::SpaceOrTabEolAfterEol)
} else {
let ok = tokenizer.tokenize_state.space_or_tab_eol_ok;
tokenizer.tokenize_state.space_or_tab_eol_content_type = None;
tokenizer.tokenize_state.space_or_tab_eol_connect = false;
tokenizer.tokenize_state.space_or_tab_eol_ok = false;
if ok {
State::Ok
} else {
State::Nok
}
}
}
/// `space_or_tab_eol`: after eol.
///
/// ```markdown
/// | a
/// > | b
/// ^
/// ```
#[allow(clippy::needless_pass_by_value)]
pub fn eol_after_eol(tokenizer: &mut Tokenizer) -> State {
let state_name = space_or_tab_with_options(
tokenizer,
Options {
kind: Token::SpaceOrTab,
min: 1,
max: usize::MAX,
content_type: tokenizer
.tokenize_state
.space_or_tab_eol_content_type
.clone(),
connect: tokenizer.tokenize_state.space_or_tab_eol_connect,
},
);
tokenizer.attempt(
state_name,
State::Fn(StateName::SpaceOrTabEolAfterMore),
State::Fn(StateName::SpaceOrTabEolAfterMore),
)
}
/// `space_or_tab_eol`: after more (optional) `space_or_tab`.
///
/// ```markdown
/// | a
/// > | b
/// ^
/// ```
pub fn eol_after_more(tokenizer: &mut Tokenizer) -> State {
tokenizer.tokenize_state.space_or_tab_eol_content_type = None;
tokenizer.tokenize_state.space_or_tab_eol_connect = false;
tokenizer.tokenize_state.space_or_tab_eol_ok = false;
// Blank line not allowed.
if matches!(tokenizer.current, None | Some(b'\n')) {
State::Nok
} else {
State::Ok
}
}
|
