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
|
//! Several helpers to parse whitespace (`space_or_tab`).
//!
//! ## References
//!
//! * [`micromark-factory-space/index.js` in `micromark`](https://github.com/micromark/micromark/blob/main/packages/micromark-factory-space/dev/index.js)
use crate::tokenizer::{Code, State, StateFn, StateFnResult, TokenType, Tokenizer};
/// Options to parse whitespace.
#[derive(Debug)]
pub struct Options {
/// Minimum allowed characters (inclusive).
pub min: usize,
/// Maximum allowed characters (inclusive).
pub max: usize,
/// Token type to use for whitespace events.
pub kind: TokenType,
}
/// Options to parse whitespace.
#[derive(Debug)]
struct Info {
/// Current size.
size: usize,
/// Configuration.
options: Options,
}
/// One or more `space_or_tab`.
///
/// ```bnf
/// space_or_tab ::= 1*( ' ' '\t' )
/// ```
pub fn space_or_tab() -> Box<StateFn> {
space_or_tab_min_max(1, usize::MAX)
}
pub fn space_or_tab_one_line_ending() -> Box<StateFn> {
Box::new(|tokenizer, code| {
tokenizer.attempt(space_or_tab(), move |ok| {
Box::new(move |tokenizer, code| match code {
Code::CarriageReturnLineFeed | Code::Char('\r' | '\n') => {
tokenizer.enter(TokenType::LineEnding);
tokenizer.consume(code);
tokenizer.exit(TokenType::LineEnding);
(
State::Fn(Box::new(tokenizer.attempt_opt(
space_or_tab(),
move |_t, code| {
if !matches!(
code,
Code::None
| Code::CarriageReturnLineFeed
| Code::Char('\r' | '\n')
) {
(State::Ok, Some(vec![code]))
} else {
(State::Nok, None)
}
},
))),
None,
)
}
_ => {
if ok {
(State::Ok, Some(vec![code]))
} else {
(State::Nok, None)
}
}
})
})(tokenizer, code)
})
}
/// Between `x` and `y` `space_or_tab`
///
/// ```bnf
/// space_or_tab_min_max ::= x*y( ' ' '\t' )
/// ```
pub fn space_or_tab_min_max(min: usize, max: usize) -> Box<StateFn> {
space_or_tab_with_options(Options {
kind: TokenType::SpaceOrTab,
min,
max,
})
}
/// Between `x` and `y` `space_or_tab`, with the given token type.
///
/// ```bnf
/// space_or_tab ::= x*y( ' ' '\t' )
/// ```
pub fn space_or_tab_with_options(options: Options) -> Box<StateFn> {
Box::new(|t, c| start(t, c, Info { size: 0, options }))
}
/// Before whitespace.
///
/// ```markdown
/// alpha| bravo
/// ```
fn start(tokenizer: &mut Tokenizer, code: Code, mut info: Info) -> StateFnResult {
match code {
Code::VirtualSpace | Code::Char('\t' | ' ') if info.options.max > 0 => {
tokenizer.enter(info.options.kind.clone());
tokenizer.consume(code);
info.size += 1;
(State::Fn(Box::new(|t, c| inside(t, c, info))), None)
}
_ => (
if info.options.min == 0 {
State::Ok
} else {
State::Nok
},
Some(vec![code]),
),
}
}
/// In whitespace.
///
/// ```markdown
/// alpha |bravo
/// alpha | bravo
/// ```
fn inside(tokenizer: &mut Tokenizer, code: Code, mut info: Info) -> StateFnResult {
match code {
Code::VirtualSpace | Code::Char('\t' | ' ') if info.size < info.options.max => {
tokenizer.consume(code);
info.size += 1;
(State::Fn(Box::new(|t, c| inside(t, c, info))), None)
}
_ => {
tokenizer.exit(info.options.kind.clone());
(
if info.size >= info.options.min {
State::Ok
} else {
State::Nok
},
Some(vec![code]),
)
}
}
}
|
