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
|
//! Destination occurs in [definition][] and label end.
//!
//! They’re formed with the following BNF:
//!
//! ```bnf
//! destination ::= destination_enclosed | destination_raw
//!
//! destination_enclosed ::= '<' *( destination_enclosed_text | destination_enclosed_escape ) '>'
//! destination_enclosed_text ::= code - '<' - '\\' - '>' - eol
//! destination_enclosed_escape ::= '\\' [ '<' | '\\' | '>' ]
//! destination_raw ::= 1*( destination_raw_text | destination_raw_escape )
//! ; Restriction: unbalanced `)` characters are not allowed.
//! destination_raw_text ::= code - '\\' - ascii_control - space_or_tab - eol
//! destination_raw_escape ::= '\\' [ '(' | ')' | '\\' ]
//! ```
//!
//! Balanced parens allowed in raw destinations.
//! They are counted with a counter that starts at `0`, and is incremented
//! every time `(` occurs and decremented every time `)` occurs.
//! If `)` is found when the counter is `0`, the destination closes immediately
//! after it.
//! Escaped parens do not count.
//!
//! It is recommended to use the enclosed variant of destinations, as it allows
//! arbitrary parens, and also allows for whitespace and other characters in
//! URLs.
//!
//! The destination is interpreted as the [string][] content type.
//! That means that [character escapes][character_escape] and
//! [character references][character_reference] are allowed.
//!
//! ## References
//!
//! * [`micromark-factory-destination/index.js` in `micromark`](https://github.com/micromark/micromark/blob/main/packages/micromark-factory-destination/dev/index.js)
//!
//! [definition]: crate::construct::definition
//! [string]: crate::content::string
//! [character_escape]: crate::construct::character_escape
//! [character_reference]: crate::construct::character_reference
//!
//! <!-- To do: link label end. -->
// To do: pass token types in.
use crate::tokenizer::{Code, State, StateFnResult, TokenType, Tokenizer};
/// Before a destination.
///
/// ```markdown
/// |<ab>
/// |ab
/// ```
pub fn start(tokenizer: &mut Tokenizer, code: Code) -> StateFnResult {
match code {
Code::Char('<') => {
tokenizer.enter(TokenType::DefinitionDestination);
tokenizer.enter(TokenType::DefinitionDestinationLiteral);
tokenizer.enter(TokenType::DefinitionDestinationLiteralMarker);
tokenizer.consume(code);
tokenizer.exit(TokenType::DefinitionDestinationLiteralMarker);
(State::Fn(Box::new(enclosed_before)), None)
}
Code::None | Code::CarriageReturnLineFeed | Code::VirtualSpace | Code::Char(' ' | ')') => {
(State::Nok, None)
}
Code::Char(char) if char.is_ascii_control() => (State::Nok, None),
Code::Char(_) => {
tokenizer.enter(TokenType::DefinitionDestination);
tokenizer.enter(TokenType::DefinitionDestinationRaw);
tokenizer.enter(TokenType::DefinitionDestinationString);
// To do: link.
tokenizer.enter(TokenType::ChunkString);
raw(tokenizer, code, 0)
}
}
}
/// After `<`, before an enclosed destination.
///
/// ```markdown
/// <|ab>
/// ```
fn enclosed_before(tokenizer: &mut Tokenizer, code: Code) -> StateFnResult {
if let Code::Char('>') = code {
tokenizer.enter(TokenType::DefinitionDestinationLiteralMarker);
tokenizer.consume(code);
tokenizer.exit(TokenType::DefinitionDestinationLiteralMarker);
tokenizer.exit(TokenType::DefinitionDestinationLiteral);
tokenizer.exit(TokenType::DefinitionDestination);
(State::Ok, None)
} else {
tokenizer.enter(TokenType::DefinitionDestinationString);
// To do: link.
tokenizer.enter(TokenType::ChunkString);
enclosed(tokenizer, code)
}
}
/// In an enclosed destination.
///
/// ```markdown
/// <u|rl>
/// ```
fn enclosed(tokenizer: &mut Tokenizer, code: Code) -> StateFnResult {
match code {
Code::Char('>') => {
tokenizer.exit(TokenType::ChunkString);
tokenizer.exit(TokenType::DefinitionDestinationString);
enclosed_before(tokenizer, code)
}
Code::None | Code::CarriageReturnLineFeed | Code::Char('\r' | '\n' | '<') => {
(State::Nok, None)
}
Code::Char('\\') => {
tokenizer.consume(code);
(State::Fn(Box::new(enclosed_escape)), None)
}
_ => {
tokenizer.consume(code);
(State::Fn(Box::new(enclosed)), None)
}
}
}
/// After `\`, in an enclosed destination.
///
/// ```markdown
/// <a\|>b>
/// ```
fn enclosed_escape(tokenizer: &mut Tokenizer, code: Code) -> StateFnResult {
match code {
Code::Char('<' | '>' | '\\') => {
tokenizer.consume(code);
(State::Fn(Box::new(enclosed)), None)
}
_ => enclosed(tokenizer, code),
}
}
/// In a raw destination.
///
/// ```markdown
/// a|b
/// ```
// To do: these arms can be improved?
fn raw(tokenizer: &mut Tokenizer, code: Code, balance: usize) -> StateFnResult {
// To do: configurable.
let limit = usize::MAX;
match code {
Code::Char('(') if balance >= limit => (State::Nok, None),
Code::Char('(') => {
tokenizer.consume(code);
(
State::Fn(Box::new(move |t, c| raw(t, c, balance + 1))),
None,
)
}
Code::Char(')') if balance == 0 => {
tokenizer.exit(TokenType::ChunkString);
tokenizer.exit(TokenType::DefinitionDestinationString);
tokenizer.exit(TokenType::DefinitionDestinationRaw);
tokenizer.exit(TokenType::DefinitionDestination);
(State::Ok, Some(vec![code]))
}
Code::Char(')') => {
tokenizer.consume(code);
(
State::Fn(Box::new(move |t, c| raw(t, c, balance - 1))),
None,
)
}
Code::None
| Code::CarriageReturnLineFeed
| Code::VirtualSpace
| Code::Char('\t' | '\r' | '\n' | ' ')
if balance > 0 =>
{
(State::Nok, None)
}
Code::None
| Code::CarriageReturnLineFeed
| Code::VirtualSpace
| Code::Char('\t' | '\r' | '\n' | ' ') => {
tokenizer.exit(TokenType::ChunkString);
tokenizer.exit(TokenType::DefinitionDestinationString);
tokenizer.exit(TokenType::DefinitionDestinationRaw);
tokenizer.exit(TokenType::DefinitionDestination);
(State::Ok, Some(vec![code]))
}
Code::Char(char) if char.is_ascii_control() => (State::Nok, None),
Code::Char('\\') => {
tokenizer.consume(code);
(
State::Fn(Box::new(move |t, c| raw_escape(t, c, balance))),
None,
)
}
Code::Char(_) => {
tokenizer.consume(code);
(State::Fn(Box::new(move |t, c| raw(t, c, balance))), None)
}
}
}
/// After `\`, in a raw destination.
///
/// ```markdown
/// a\|)b
/// ```
fn raw_escape(tokenizer: &mut Tokenizer, code: Code, balance: usize) -> StateFnResult {
match code {
Code::Char('(' | ')' | '\\') => {
tokenizer.consume(code);
(
State::Fn(Box::new(move |t, c| raw(t, c, balance + 1))),
None,
)
}
_ => raw(tokenizer, code, balance),
}
}
|
