/rust/registry/src/index.crates.io-6f17d22bba15001f/unicase-2.6.0/src/unicode/mod.rs
Line | Count | Source (jump to first uncovered line) |
1 | | #[cfg(__unicase__iter_cmp)] |
2 | | use core::cmp::Ordering; |
3 | | use core::hash::{Hash, Hasher}; |
4 | | |
5 | | use self::map::lookup; |
6 | | mod map; |
7 | | |
8 | 0 | #[derive(Clone, Copy, Debug, Default)] |
9 | | pub struct Unicode<S>(pub S); |
10 | | |
11 | | impl<S1: AsRef<str>, S2: AsRef<str>> PartialEq<Unicode<S2>> for Unicode<S1> { |
12 | | #[inline] |
13 | 0 | fn eq(&self, other: &Unicode<S2>) -> bool { |
14 | 0 | let mut left = self.0.as_ref().chars().flat_map(lookup); |
15 | 0 | let mut right = other.0.as_ref().chars().flat_map(lookup); |
16 | | |
17 | | // inline Iterator::eq since not added until Rust 1.5 |
18 | | loop { |
19 | 0 | let x = match left.next() { |
20 | 0 | None => return right.next().is_none(), |
21 | 0 | Some(val) => val, |
22 | | }; |
23 | | |
24 | 0 | let y = match right.next() { |
25 | 0 | None => return false, |
26 | 0 | Some(val) => val, |
27 | 0 | }; |
28 | 0 |
|
29 | 0 | if x != y { |
30 | 0 | return false; |
31 | 0 | } |
32 | | } |
33 | 0 | } Unexecuted instantiation: <unicase::unicode::Unicode<pulldown_cmark::strings::CowStr> as core::cmp::PartialEq>::eq Unexecuted instantiation: <unicase::unicode::Unicode<&str> as core::cmp::PartialEq<unicase::unicode::Unicode<pulldown_cmark::strings::CowStr>>>::eq Unexecuted instantiation: <unicase::unicode::Unicode<pulldown_cmark::strings::CowStr> as core::cmp::PartialEq<unicase::unicode::Unicode<&str>>>::eq Unexecuted instantiation: <unicase::unicode::Unicode<_> as core::cmp::PartialEq<unicase::unicode::Unicode<_>>>::eq |
34 | | } |
35 | | |
36 | | impl<S: AsRef<str>> Eq for Unicode<S> {} |
37 | | |
38 | | #[cfg(__unicase__iter_cmp)] |
39 | | impl<T: AsRef<str>> PartialOrd for Unicode<T> { |
40 | | #[inline] |
41 | 0 | fn partial_cmp(&self, other: &Self) -> Option<Ordering> { |
42 | 0 | Some(self.cmp(other)) |
43 | 0 | } |
44 | | } |
45 | | |
46 | | #[cfg(__unicase__iter_cmp)] |
47 | | impl<T: AsRef<str>> Ord for Unicode<T> { |
48 | | #[inline] |
49 | 0 | fn cmp(&self, other: &Self) -> Ordering { |
50 | 0 | let self_chars = self.0.as_ref().chars().flat_map(lookup); |
51 | 0 | let other_chars = other.0.as_ref().chars().flat_map(lookup); |
52 | 0 | self_chars.cmp(other_chars) |
53 | 0 | } |
54 | | } |
55 | | |
56 | | impl<S: AsRef<str>> Hash for Unicode<S> { |
57 | | #[inline] |
58 | 0 | fn hash<H: Hasher>(&self, hasher: &mut H) { |
59 | 0 | let mut buf = [0; 4]; |
60 | 0 | for c in self.0.as_ref().chars().flat_map(|c| lookup(c)) {Unexecuted instantiation: <unicase::unicode::Unicode<pulldown_cmark::strings::CowStr> as core::hash::Hash>::hash::<std::collections::hash::map::DefaultHasher>::{closure#0}Unexecuted instantiation: <unicase::unicode::Unicode<_> as core::hash::Hash>::hash::<_>::{closure#0} |
61 | 0 | let len = char_to_utf8(c, &mut buf); |
62 | 0 | hasher.write(&buf[..len]) |
63 | | } |
64 | 0 | } Unexecuted instantiation: <unicase::unicode::Unicode<pulldown_cmark::strings::CowStr> as core::hash::Hash>::hash::<std::collections::hash::map::DefaultHasher> Unexecuted instantiation: <unicase::unicode::Unicode<_> as core::hash::Hash>::hash::<_> |
65 | | } |
66 | | |
67 | | #[inline] |
68 | 0 | fn char_to_utf8(c: char, dst: &mut [u8; 4]) -> usize { |
69 | 0 | const TAG_CONT: u8 = 0b1000_0000; |
70 | 0 | const TAG_TWO_B: u8 = 0b1100_0000; |
71 | 0 | const TAG_THREE_B: u8 = 0b1110_0000; |
72 | 0 | const TAG_FOUR_B: u8 = 0b1111_0000; |
73 | 0 |
|
74 | 0 | let code = c as u32; |
75 | 0 | if code <= 0x7F { |
76 | 0 | dst[0] = code as u8; |
77 | 0 | 1 |
78 | 0 | } else if code <= 0x7FF { |
79 | 0 | dst[0] = (code >> 6 & 0x1F) as u8 | TAG_TWO_B; |
80 | 0 | dst[1] = (code & 0x3F) as u8 | TAG_CONT; |
81 | 0 | 2 |
82 | 0 | } else if code <= 0xFFFF { |
83 | 0 | dst[0] = (code >> 12 & 0x0F) as u8 | TAG_THREE_B; |
84 | 0 | dst[1] = (code >> 6 & 0x3F) as u8 | TAG_CONT; |
85 | 0 | dst[2] = (code & 0x3F) as u8 | TAG_CONT; |
86 | 0 | 3 |
87 | | } else { |
88 | 0 | dst[0] = (code >> 18 & 0x07) as u8 | TAG_FOUR_B; |
89 | 0 | dst[1] = (code >> 12 & 0x3F) as u8 | TAG_CONT; |
90 | 0 | dst[2] = (code >> 6 & 0x3F) as u8 | TAG_CONT; |
91 | 0 | dst[3] = (code & 0x3F) as u8 | TAG_CONT; |
92 | 0 | 4 |
93 | | } |
94 | 0 | } Unexecuted instantiation: unicase::unicode::char_to_utf8 Unexecuted instantiation: unicase::unicode::char_to_utf8 |
95 | | |
96 | | // internal mod so that the enum can be 'pub' |
97 | | // thanks privacy-checker :___( |
98 | | mod fold { |
99 | 0 | #[derive(Clone, Copy)] |
100 | | pub enum Fold { |
101 | | Zero, |
102 | | One(char), |
103 | | Two(char, char), |
104 | | Three(char, char, char), |
105 | | } |
106 | | |
107 | | impl Iterator for Fold { |
108 | | type Item = char; |
109 | | #[inline] |
110 | 0 | fn next(&mut self) -> Option<char> { |
111 | 0 | match *self { |
112 | 0 | Fold::Zero => None, |
113 | 0 | Fold::One(one) => { |
114 | 0 | *self = Fold::Zero; |
115 | 0 | Some(one) |
116 | | }, |
117 | 0 | Fold::Two(one, two) => { |
118 | 0 | *self = Fold::One(two); |
119 | 0 | Some(one) |
120 | | }, |
121 | 0 | Fold::Three(one, two, three) => { |
122 | 0 | *self = Fold::Two(one, two); |
123 | 0 | Some(three) |
124 | | } |
125 | | } |
126 | 0 | } Unexecuted instantiation: <unicase::unicode::fold::Fold as core::iter::traits::iterator::Iterator>::next Unexecuted instantiation: <unicase::unicode::fold::Fold as core::iter::traits::iterator::Iterator>::next |
127 | | |
128 | | #[inline] |
129 | 0 | fn size_hint(&self) -> (usize, Option<usize>) { |
130 | 0 | match *self { |
131 | 0 | Fold::Zero => (0, Some(0)), |
132 | 0 | Fold::One(..) => (1, Some(1)), |
133 | 0 | Fold::Two(..) => (2, Some(2)), |
134 | 0 | Fold::Three(..) => (3, Some(3)) |
135 | | } |
136 | 0 | } |
137 | | |
138 | | } |
139 | | impl From<(char,)> for Fold { |
140 | | #[inline] |
141 | 0 | fn from((one,): (char,)) -> Fold { |
142 | 0 | Fold::One(one) |
143 | 0 | } |
144 | | } |
145 | | |
146 | | impl From<(char, char)> for Fold { |
147 | | #[inline] |
148 | 0 | fn from((one, two): (char, char)) -> Fold { |
149 | 0 | Fold::Two(one, two) |
150 | 0 | } |
151 | | } |
152 | | |
153 | | impl From<(char, char, char)> for Fold { |
154 | | #[inline] |
155 | 0 | fn from((one, two, three): (char, char, char)) -> Fold { |
156 | 0 | Fold::Three(one, two, three) |
157 | 0 | } |
158 | | } |
159 | | } |
160 | | |
161 | | #[cfg(test)] |
162 | | mod tests { |
163 | | use super::Unicode; |
164 | | |
165 | | macro_rules! eq { |
166 | | ($left:expr, $right:expr) => ({ |
167 | | assert_eq!(Unicode($left), Unicode($right)); |
168 | | }); |
169 | | } |
170 | | |
171 | | #[test] |
172 | | fn test_ascii_folding() { |
173 | | eq!("foo bar", "FoO BAR"); |
174 | | } |
175 | | |
176 | | #[test] |
177 | | fn test_simple_case_folding() { |
178 | | eq!("στιγμας", "στιγμασ"); |
179 | | } |
180 | | |
181 | | #[test] |
182 | | fn test_full_case_folding() { |
183 | | eq!("flour", "flour"); |
184 | | eq!("Maße", "MASSE"); |
185 | | eq!("ᾲ στο διάολο", "ὰι στο διάολο"); |
186 | | } |
187 | | |
188 | | #[cfg(feature = "nightly")] |
189 | | #[bench] |
190 | | fn bench_ascii_folding(b: &mut ::test::Bencher) { |
191 | | b.bytes = b"foo bar".len() as u64; |
192 | | b.iter(|| eq!("foo bar", "FoO BAR")); |
193 | | } |
194 | | |
195 | | #[cfg(feature = "nightly")] |
196 | | #[bench] |
197 | | fn bench_simple_case_folding(b: &mut ::test::Bencher) { |
198 | | b.bytes = "στιγμας".len() as u64; |
199 | | b.iter(|| eq!("στιγμας", "στιγμασ")); |
200 | | } |
201 | | } |