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
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
#![cfg_attr(test, deny(missing_docs))]
#![cfg_attr(test, deny(warnings))]
#![doc(html_root_url = "https://docs.rs/unicase/2.1.0")]
#![cfg_attr(feature = "nightly", feature(test))]

//! # UniCase
//!
//! UniCase provices a way of specifying strings that are case-insensitive.
//!
//! UniCase supports full [Unicode case
//! folding](https://www.w3.org/International/wiki/Case_folding). It can also
//! utilize faster ASCII case comparisons, if both strings are ASCII.
//!
//! Using the `UniCase::new()` constructor will check the string to see if it
//! is all ASCII. When a `UniCase` is compared against another, if both are
//! ASCII, it will use the faster comparison.
//!
//! There also exists the `Ascii` type in this crate, which will always assume
//! to use the ASCII case comparisons, if the encoding is already known.
//!
//! ## Example
//!
//! ```rust
//! use unicase::UniCase;
//!
//! let a = UniCase::new("Maße");
//! let b = UniCase::new("MASSE");
//! let c = UniCase::new("mase");
//!
//! assert_eq!(a, b);
//! assert!(b != c);
//! ```
//!
//! ## Ascii
//!
//! ```rust
//! use unicase::Ascii;
//!
//! let a = Ascii::new("foobar");
//! let b = Ascii::new("FoObAr");
//!
//! assert_eq!(a, b);
//! ```

#[cfg(feature = "nightly")]
extern crate test;

#[cfg(__unicase__iter_cmp)]
use std::cmp::Ordering;
use std::fmt;
use std::hash::{Hash, Hasher};
use std::ops::{Deref, DerefMut};
use std::str::FromStr;

use self::unicode::Unicode;

mod ascii;
mod unicode;

/// Case Insensitive wrapper of strings.
#[derive(Clone, Copy)]
pub struct UniCase<S>(Encoding<S>);

/// Case Insensitive wrapper of Ascii strings.
#[derive(Clone, Copy, Debug)]
pub struct Ascii<S>(S);

/// Compare two string-like types for case-less equality, using unicode folding.
///
/// Equivalent to `UniCase::new(left) == UniCase::new(right)`.
///
/// Note: This will perform a scan for ASCII characters before doing the
/// the comparison. See `UniCase` for more information.
#[inline]
pub fn eq<S: AsRef<str> + ?Sized>(left: &S, right: &S) -> bool {
    UniCase::new(left) == UniCase::new(right)
}

/// Compare two string-like types for case-less equality, ignoring ASCII case.
///
/// Equivalent to `Ascii::new(left) == Ascii::new(right)`.
#[inline]
pub fn eq_ascii<S: AsRef<str> + ?Sized>(left: &S, right: &S) -> bool {
    Ascii(left) == Ascii(right)
}

#[derive(Clone, Copy, Debug)]
enum Encoding<S> {
    Ascii(Ascii<S>),
    Unicode(Unicode<S>),
}

macro_rules! inner {

    (mut $e:expr) => ({
        match &mut $e {
            &mut Encoding::Ascii(ref mut s) => &mut s.0,
            &mut Encoding::Unicode(ref mut s) => &mut s.0,
        }
    });
    ($e:expr) => ({
        match &$e {
            &Encoding::Ascii(ref s) => &s.0,
            &Encoding::Unicode(ref s) => &s.0,
        }
    });
}

impl<S: AsRef<str>> UniCase<S> {
    /// Creates a new `UniCase`.
    ///
    /// Note: This scans the text to determine if it is all ASCII or not.
    pub fn new(s: S) -> UniCase<S> {
        #[allow(unused)]
        use std::ascii::AsciiExt;
        if s.as_ref().is_ascii() {
            UniCase(Encoding::Ascii(Ascii(s)))
        } else {
            UniCase(Encoding::Unicode(Unicode(s)))
        }
    }

    /// Creates a new `UniCase`, skipping the ASCII check.
    pub fn unicode(s: S) -> UniCase<S> {
        UniCase(Encoding::Unicode(Unicode(s)))
    }
}

impl<S> Deref for UniCase<S> {
    type Target = S;
    #[inline]
    fn deref<'a>(&'a self) -> &'a S {
        inner!(self.0)
    }
}

impl<S> DerefMut for UniCase<S> {
    #[inline]
    fn deref_mut<'a>(&'a mut self) -> &'a mut S {
        inner!(mut self.0)
    }
}

impl<S: AsRef<str>> AsRef<str> for UniCase<S> {
    #[inline]
    fn as_ref(&self) -> &str {
        inner!(self.0).as_ref()
    }

}

impl<S: fmt::Debug> fmt::Debug for UniCase<S> {
    #[inline]
    fn fmt(&self, fmt: &mut fmt::Formatter) -> fmt::Result {
        fmt::Debug::fmt(inner!(self.0), fmt)
    }
}

impl<S: fmt::Display> fmt::Display for UniCase<S> {
    #[inline]
    fn fmt(&self, fmt: &mut fmt::Formatter) -> fmt::Result {
        fmt::Display::fmt(inner!(self.0), fmt)
    }
}


impl<S1: AsRef<str>, S2: AsRef<str>> PartialEq<UniCase<S2>> for UniCase<S1> {
    #[inline]
    fn eq(&self, other: &UniCase<S2>) -> bool {
        match (&self.0, &other.0) {
            (&Encoding::Ascii(ref x), &Encoding::Ascii(ref y)) => x == y,
            (&Encoding::Unicode(ref x), &Encoding::Unicode(ref y)) => x == y,
            (&Encoding::Ascii(ref x), &Encoding::Unicode(ref y)) => &Unicode(x.as_ref()) == y,
            (&Encoding::Unicode(ref x), &Encoding::Ascii(ref y)) => x == &Unicode(y.as_ref()),
        }
    }
}

impl<S: AsRef<str>> Eq for UniCase<S> {}

impl<S: AsRef<str>> Hash for UniCase<S> {
    #[inline]
    fn hash<H: Hasher>(&self, hasher: &mut H) {
        match self.0 {
            Encoding::Ascii(ref s) => s.hash(hasher),
            Encoding::Unicode(ref s) => s.hash(hasher)
        }
    }
}

macro_rules! from_impl {
    ($from:ty => $to:ty; $by:ident) => (
        impl<'a> From<$from> for UniCase<$to> {
            fn from(s: $from) -> Self {
                UniCase::unicode(s.$by())
            }
        }
    );
    ($from:ty => $to:ty) => ( from_impl!($from => $to; into); )
}

macro_rules! into_impl {
    ($to:ty) => (
        impl<'a> Into<$to> for UniCase<$to> {
            fn into(self) -> $to {
                match self.0 {
                    Encoding::Ascii(Ascii(s)) => s,
                    Encoding::Unicode(Unicode(s)) => s,
                }
            }
        }
    );
}

from_impl!(&'a str => &'a str);
from_impl!(&'a str => String);
from_impl!(&'a String => &'a str; as_ref);
from_impl!(String => String);

into_impl!(&'a str);
into_impl!(String);

#[cfg(__unicase__iter_cmp)]
impl<T: AsRef<str>> PartialOrd for UniCase<T> {
    #[inline]
    fn partial_cmp(&self, other: &Self) -> Option<Ordering> {
        Some(self.cmp(other))
    }
}

#[cfg(__unicase__iter_cmp)]
impl<T: AsRef<str>> Ord for UniCase<T> {
    #[inline]
    fn cmp(&self, other: &Self) -> Ordering {
        match (&self.0, &other.0) {
            (&Encoding::Ascii(ref x), &Encoding::Ascii(ref y)) => x.cmp(y),
            (&Encoding::Unicode(ref x), &Encoding::Unicode(ref y)) => x.cmp(y),
            (&Encoding::Ascii(ref x), &Encoding::Unicode(ref y)) => Unicode(x.as_ref()).cmp(&Unicode(y.0.as_ref())),
            (&Encoding::Unicode(ref x), &Encoding::Ascii(ref y)) => Unicode(x.0.as_ref()).cmp(&Unicode(y.as_ref())),
        }
    }
}



impl<S: FromStr + AsRef<str>> FromStr for UniCase<S> {
    type Err = <S as FromStr>::Err;
    fn from_str(s: &str) -> Result<UniCase<S>, Self::Err> {
        s.parse().map(UniCase::new)
    }
}

#[cfg(test)]
mod tests {
    use super::UniCase;
    use std::hash::{Hash, Hasher};
    #[cfg(not(__unicase__defauler_hasher))]
    use std::hash::SipHasher as DefaultHasher;
    #[cfg(__unicase__defauler_hasher)]
    use std::collections::hash_map::DefaultHasher;

    fn hash<T: Hash>(t: &T) -> u64 {
        let mut s = DefaultHasher::new();
        t.hash(&mut s);
        s.finish()
    }

    #[test]
    fn test_copy_for_refs() {
        fn foo<T>(_: UniCase<T>) {}

        let a = UniCase::new("foobar");
        foo(a);
        foo(a);
    }

    #[test]
    fn test_eq_ascii() {
        let a = UniCase::new("foobar");
        let b = UniCase::new("FOOBAR");

        assert_eq!(a, b);
        assert_eq!(hash(&a), hash(&b));
    }

    #[test]
    fn test_eq_unicode() {
        let a = UniCase::new("στιγμας");
        let b = UniCase::new("στιγμασ");
        assert_eq!(a, b);
        assert_eq!(hash(&a), hash(&b));
    }

    #[cfg(feature = "nightly")]
    #[bench]
    fn bench_unicase_ascii(b: &mut ::test::Bencher) {
        b.bytes = b"foobar".len() as u64;
        let x = UniCase::new("foobar");
        let y = UniCase::new("FOOBAR");
        b.iter(|| assert_eq!(x, y));
    }

    #[cfg(feature = "nightly")]
    static SUBJECT: &'static [u8] = b"ffoo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz foo bar baz oo bar baz quux herp derp";

    #[cfg(feature = "nightly")]
    #[inline(never)]
    fn is_ascii(bytes: &[u8]) -> bool {
        #[allow(unused)]
        use std::ascii::AsciiExt;
        bytes.is_ascii()
    }

    #[cfg(feature = "nightly")]
    #[bench]
    fn bench_is_ascii(b: &mut ::test::Bencher) {
        b.iter(|| assert!(is_ascii(SUBJECT)));
    }

    #[cfg(feature = "nightly")]
    #[bench]
    fn bench_is_utf8(b: &mut ::test::Bencher) {
        b.iter(|| assert!(::std::str::from_utf8(SUBJECT).is_ok()));
    }

    #[cfg(__unicase__iter_cmp)]
    #[test]
    fn test_case_cmp() {
        assert!(UniCase::new("a") < UniCase::new("B"));

        assert!(UniCase::new("A") < UniCase::new("b"));
        assert!(UniCase::new("aa") > UniCase::new("a"));

        assert!(UniCase::new("a") < UniCase::new("aa"));
        assert!(UniCase::new("a") < UniCase::new("AA"));
    }

    #[test]
    fn test_from_impls() {
        let view: &'static str = "foobar";
        let _: UniCase<&'static str> = view.into();
        let _: UniCase<&str> = view.into();
        let _: UniCase<String> = view.into();

        let owned: String = view.to_owned();
        let _: UniCase<&str> = (&owned).into();
        let _: UniCase<String> = owned.into();
    }

    #[test]
    fn test_into_impls() {
        let view: UniCase<&'static str> = UniCase::new("foobar");
        let _: &'static str = view.into();
        let _: &str = view.into();

        let owned: UniCase<String> = "foobar".into();
        let _: String = owned.clone().into();
        let _: &str = owned.as_ref();
    }
}