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
|
// Copyright 2018 Google LLC
//
// Permission is hereby granted, free of charge, to any person obtaining a copy
// of this software and associated documentation files (the "Software"), to deal
// in the Software without restriction, including without limitation the rights
// to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
// copies of the Software, and to permit persons to whom the Software is
// furnished to do so, subject to the following conditions:
//
// The above copyright notice and this permission notice shall be included in
// all copies or substantial portions of the Software.
//
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
// IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
// FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
// AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
// LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
// OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
// THE SOFTWARE.
//! Link label parsing and matching.
use unicase::UniCase;
use crate::scanners::{is_ascii_whitespace, scan_eol};
use crate::strings::CowStr;
pub(crate) enum ReferenceLabel<'a> {
Link(CowStr<'a>),
Footnote(CowStr<'a>),
}
pub(crate) type LinkLabel<'a> = UniCase<CowStr<'a>>;
/// Assumes the opening bracket has already been scanned.
/// The line break handler determines what happens when a linebreak
/// is found. It is passed the bytes following the line break and
/// either returns `Some(k)`, where `k` is the number of bytes to skip,
/// or `None` to abort parsing the label.
/// Returns the number of bytes read (including closing bracket) and label on success.
pub(crate) fn scan_link_label_rest<'t>(
text: &'t str,
linebreak_handler: &dyn Fn(&[u8]) -> Option<usize>,
) -> Option<(usize, CowStr<'t>)> {
let bytes = text.as_bytes();
let mut ix = 0;
let mut only_white_space = true;
let mut codepoints = 0;
// no worries, doesn't allocate until we push things onto it
let mut label = String::new();
let mut mark = 0;
loop {
if codepoints >= 1000 {
return None;
}
match *bytes.get(ix)? {
b'[' => return None,
b']' => break,
b'\\' => {
ix += 2;
codepoints += 2;
only_white_space = false;
}
b if is_ascii_whitespace(b) => {
// normalize labels by collapsing whitespaces, including linebreaks
let mut whitespaces = 0;
let mut linebreaks = 0;
let whitespace_start = ix;
while ix < bytes.len() && is_ascii_whitespace(bytes[ix]) {
if let Some(eol_bytes) = scan_eol(&bytes[ix..]) {
linebreaks += 1;
if linebreaks > 1 {
return None;
}
ix += eol_bytes;
ix += linebreak_handler(&bytes[ix..])?;
whitespaces += 2; // indicate that we need to replace
} else {
whitespaces += if bytes[ix] == b' ' { 1 } else { 2 };
ix += 1;
}
}
if whitespaces > 1 {
label.push_str(&text[mark..whitespace_start]);
label.push(' ');
mark = ix;
codepoints += ix - whitespace_start;
} else {
codepoints += 1;
}
}
b => {
only_white_space = false;
ix += 1;
if b & 0b1000_0000 != 0 {
codepoints += 1;
}
}
}
}
if only_white_space {
None
} else {
let cow = if mark == 0 {
text[..ix].into()
} else {
label.push_str(&text[mark..ix]);
label.into()
};
Some((ix + 1, cow))
}
}
#[cfg(test)]
mod test {
use super::scan_link_label_rest;
#[test]
fn whitespace_normalization() {
let input = "«\t\tBlurry Eyes\t\t»][blurry_eyes]";
let expected_output = "« Blurry Eyes »"; // regular spaces!
let (_bytes, normalized_label) = scan_link_label_rest(input, &|_| None).unwrap();
assert_eq!(expected_output, normalized_label.as_ref());
}
#[test]
fn return_carriage_linefeed_ok() {
let input = "hello\r\nworld\r\n]";
assert!(scan_link_label_rest(input, &|_| Some(0)).is_some());
}
}
|
