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
|
//! Deal with bytes, chars, and kinds.
use crate::util::unicode::PUNCTUATION;
use alloc::{format, string::String};
use core::str;
/// Character kinds.
#[derive(Debug, PartialEq, Eq)]
pub enum Kind {
/// Whitespace.
///
/// ## Example
///
/// ```markdown
/// > | **a_b_ c**.
/// ^ ^ ^
/// ```
Whitespace,
/// Punctuation.
///
/// ## Example
///
/// ```markdown
/// > | **a_b_ c**.
/// ^^ ^ ^ ^
/// ```
Punctuation,
/// Everything else.
///
/// ## Example
///
/// ```markdown
/// > | **a_b_ c**.
/// ^ ^ ^
/// ```
Other,
}
/// Get a [`char`][] right before `index` in bytes (`&[u8]`).
///
/// In most cases, markdown operates on ASCII bytes.
/// In a few cases, it is unicode aware, so we need to find an actual char.
pub fn before_index(bytes: &[u8], index: usize) -> Option<char> {
let start = if index < 4 { 0 } else { index - 4 };
String::from_utf8_lossy(&bytes[start..index]).chars().last()
}
/// Get a [`char`][] right at `index` in bytes (`&[u8]`).
///
/// In most cases, markdown operates on ASCII bytes.
/// In a few cases, it is unicode aware, so we need to find an actual char.
pub fn after_index(bytes: &[u8], index: usize) -> Option<char> {
let end = if index + 4 > bytes.len() {
bytes.len()
} else {
index + 4
};
String::from_utf8_lossy(&bytes[index..end]).chars().next()
}
/// Classify a char at `index` in bytes (`&[u8]`).
pub fn kind_after_index(bytes: &[u8], index: usize) -> Kind {
if index == bytes.len() {
Kind::Whitespace
} else {
let byte = bytes[index];
if byte.is_ascii_whitespace() {
Kind::Whitespace
} else if byte.is_ascii_punctuation() {
Kind::Punctuation
} else if byte.is_ascii_alphanumeric() {
Kind::Other
} else {
// Otherwise: seems to be an ASCII control, so it seems to be a
// non-ASCII `char`.
classify_opt(after_index(bytes, index))
}
}
}
/// Classify whether a `char` represents whitespace, punctuation, or something
/// else.
///
/// Used for attention (emphasis, strong), whose sequences can open or close
/// based on the class of surrounding characters.
///
/// ## References
///
/// * [`micromark-util-classify-character` in `micromark`](https://github.com/micromark/micromark/blob/main/packages/micromark-util-classify-character/dev/index.js)
pub fn classify(char: char) -> Kind {
// Unicode whitespace.
if char.is_whitespace() {
Kind::Whitespace
}
// Unicode punctuation.
else if PUNCTUATION.contains(&char) {
Kind::Punctuation
}
// Everything else.
else {
Kind::Other
}
}
/// Like [`classify`], but supports eof as whitespace.
pub fn classify_opt(char_opt: Option<char>) -> Kind {
char_opt.map_or(Kind::Whitespace, classify)
}
/// Format an optional `char` (`none` means eof).
pub fn format_opt(char: Option<char>) -> String {
char.map_or("end of file".into(), |char| {
format!("character {}", format(char))
})
}
/// Format an optional `byte` (`none` means eof).
pub fn format_byte_opt(byte: Option<u8>) -> String {
byte.map_or("end of file".into(), |byte| {
format!("byte {}", format_byte(byte))
})
}
/// Format a `char`.
pub fn format(char: char) -> String {
let representation = format!("U+{:>04X}", char as u32);
let printable = match char {
'`' => Some("`` ` ``".into()),
'!'..='~' => Some(format!("`{}`", char)),
_ => None,
};
if let Some(char) = printable {
format!("{} ({})", char, representation)
} else {
representation
}
}
/// Format a byte (`u8`).
pub fn format_byte(byte: u8) -> String {
let representation = format!("U+{:>04X}", byte);
let printable = match byte {
b'`' => Some("`` ` ``".into()),
b'!'..=b'~' => Some(format!("`{}`", str::from_utf8(&[byte]).unwrap())),
_ => None,
};
if let Some(char) = printable {
format!("{} ({})", char, representation)
} else {
representation
}
}
#[cfg(test)]
mod tests {
use super::*;
use alloc::string::ToString;
#[test]
fn test_classify() {
assert_eq!(
classify(' '),
Kind::Whitespace,
"should classify whitespace"
);
assert_eq!(
classify('.'),
Kind::Punctuation,
"should classify punctuation"
);
assert_eq!(classify('a'), Kind::Other, "should classify other");
}
#[test]
fn test_format_opt() {
assert_eq!(
format_opt(None),
"end of file".to_string(),
"should format an optional char: none -> eof"
);
assert_eq!(
format_opt(Some('!')),
"character `!` (U+0021)".to_string(),
"should format an optional char: char -> pretty"
);
}
#[test]
fn test_format_byte_opt() {
assert_eq!(
format_byte_opt(None),
"end of file".to_string(),
"should format an optional byte: none -> eof"
);
assert_eq!(
format_byte_opt(Some(b'!')),
"byte `!` (U+0021)".to_string(),
"should format an optional byte: char -> pretty"
);
}
#[test]
fn test_format() {
assert_eq!(
format('`'),
"`` ` `` (U+0060)".to_string(),
"should format a char: grave accent"
);
assert_eq!(
format('!'),
"`!` (U+0021)".to_string(),
"should format a char: regular"
);
assert_eq!(
format(' '),
"U+0020".to_string(),
"should format a char: unprintable"
);
}
#[test]
fn test_format_byte() {
assert_eq!(
format_byte(b'`'),
"`` ` `` (U+0060)".to_string(),
"should format a byte: grave accent"
);
assert_eq!(
format_byte(b'!'),
"`!` (U+0021)".to_string(),
"should format a byte: regular"
);
assert_eq!(
format_byte(b' '),
"U+0020".to_string(),
"should format a byte: unprintable"
);
}
}
|
