1 | // Copyright 2018 Google LLC |
2 | // |
3 | // Permission is hereby granted, free of charge, to any person obtaining a copy |
4 | // of this software and associated documentation files (the "Software"), to deal |
5 | // in the Software without restriction, including without limitation the rights |
6 | // to use, copy, modify, merge, publish, distribute, sublicense, and/or sell |
7 | // copies of the Software, and to permit persons to whom the Software is |
8 | // furnished to do so, subject to the following conditions: |
9 | // |
10 | // The above copyright notice and this permission notice shall be included in |
11 | // all copies or substantial portions of the Software. |
12 | // |
13 | // THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR |
14 | // IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, |
15 | // FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE |
16 | // AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER |
17 | // LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, |
18 | // OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN |
19 | // THE SOFTWARE. |
20 | |
21 | //! Link label parsing and matching. |
22 | |
23 | use unicase::UniCase; |
24 | |
25 | use crate::scanners::{is_ascii_whitespace, scan_eol}; |
26 | use crate::strings::CowStr; |
27 | |
28 | pub(crate) enum ReferenceLabel<'a> { |
29 | Link(CowStr<'a>), |
30 | Footnote(CowStr<'a>), |
31 | } |
32 | |
33 | pub(crate) type LinkLabel<'a> = UniCase<CowStr<'a>>; |
34 | |
35 | /// Assumes the opening bracket has already been scanned. |
36 | /// The line break handler determines what happens when a linebreak |
37 | /// is found. It is passed the bytes following the line break and |
38 | /// either returns `Some(k)`, where `k` is the number of bytes to skip, |
39 | /// or `None` to abort parsing the label. |
40 | /// Returns the number of bytes read (including closing bracket) and label on success. |
41 | pub(crate) fn scan_link_label_rest<'t>( |
42 | text: &'t str, |
43 | linebreak_handler: &dyn Fn(&[u8]) -> Option<usize>, |
44 | ) -> Option<(usize, CowStr<'t>)> { |
45 | let bytes = text.as_bytes(); |
46 | let mut ix = 0; |
47 | let mut only_white_space = true; |
48 | let mut codepoints = 0; |
49 | // no worries, doesn't allocate until we push things onto it |
50 | let mut label = String::new(); |
51 | let mut mark = 0; |
52 | |
53 | loop { |
54 | if codepoints >= 1000 { |
55 | return None; |
56 | } |
57 | match *bytes.get(ix)? { |
58 | b'[' => return None, |
59 | b']' => break, |
60 | b' \\' => { |
61 | ix += 2; |
62 | codepoints += 2; |
63 | only_white_space = false; |
64 | } |
65 | b if is_ascii_whitespace(b) => { |
66 | // normalize labels by collapsing whitespaces, including linebreaks |
67 | let mut whitespaces = 0; |
68 | let mut linebreaks = 0; |
69 | let whitespace_start = ix; |
70 | |
71 | while ix < bytes.len() && is_ascii_whitespace(bytes[ix]) { |
72 | if let Some(eol_bytes) = scan_eol(&bytes[ix..]) { |
73 | linebreaks += 1; |
74 | if linebreaks > 1 { |
75 | return None; |
76 | } |
77 | ix += eol_bytes; |
78 | ix += linebreak_handler(&bytes[ix..])?; |
79 | whitespaces += 2; // indicate that we need to replace |
80 | } else { |
81 | whitespaces += if bytes[ix] == b' ' { 1 } else { 2 }; |
82 | ix += 1; |
83 | } |
84 | } |
85 | if whitespaces > 1 { |
86 | label.push_str(&text[mark..whitespace_start]); |
87 | label.push(' ' ); |
88 | mark = ix; |
89 | codepoints += ix - whitespace_start; |
90 | } else { |
91 | codepoints += 1; |
92 | } |
93 | } |
94 | b => { |
95 | only_white_space = false; |
96 | ix += 1; |
97 | if b & 0b1000_0000 != 0 { |
98 | codepoints += 1; |
99 | } |
100 | } |
101 | } |
102 | } |
103 | |
104 | if only_white_space { |
105 | None |
106 | } else { |
107 | let cow = if mark == 0 { |
108 | text[..ix].into() |
109 | } else { |
110 | label.push_str(&text[mark..ix]); |
111 | label.into() |
112 | }; |
113 | Some((ix + 1, cow)) |
114 | } |
115 | } |
116 | |
117 | #[cfg (test)] |
118 | mod test { |
119 | use super::scan_link_label_rest; |
120 | |
121 | #[test ] |
122 | fn whitespace_normalization() { |
123 | let input = "« \t\tBlurry Eyes \t\t»][blurry_eyes]" ; |
124 | let expected_output = "« Blurry Eyes »" ; // regular spaces! |
125 | |
126 | let (_bytes, normalized_label) = scan_link_label_rest(input, &|_| None).unwrap(); |
127 | assert_eq!(expected_output, normalized_label.as_ref()); |
128 | } |
129 | |
130 | #[test ] |
131 | fn return_carriage_linefeed_ok() { |
132 | let input = "hello \r\nworld \r\n]" ; |
133 | assert!(scan_link_label_rest(input, &|_| Some(0)).is_some()); |
134 | } |
135 | } |
136 | |