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
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
/*!
The `memchr` crate provides heavily optimized routines for searching bytes.

The `memchr` function is traditionally provided by libc, however, the
performance of `memchr` can vary significantly depending on the specific
implementation of libc that is used. They can range from manually tuned
Assembly implementations (like that found in GNU's libc) all the way to
non-vectorized C implementations (like that found in MUSL).

To smooth out the differences between implementations of libc, at least
on `x86_64` for Rust 1.27+, this crate provides its own implementation of
`memchr` that should perform competitively with the one found in GNU's libc.
The implementation is in pure Rust and has no dependency on a C compiler or an
Assembler.

Additionally, GNU libc also provides an extension, `memrchr`. This crate
provides its own implementation of `memrchr` as well, on top of `memchr2`,
`memchr3`, `memrchr2` and `memrchr3`. The difference between `memchr` and
`memchr2` is that that `memchr2` permits finding all occurrences of two bytes
instead of one. Similarly for `memchr3`.
*/

#![cfg_attr(not(feature = "std"), no_std)]
#![deny(missing_docs)]
#![doc(html_root_url = "https://docs.rs/memchr/2.0.0")]

// Supporting 8-bit (or others) would be fine. If you need it, please submit a
// bug report at https://github.com/BurntSushi/rust-memchr
#[cfg(not(any(
    target_pointer_width = "16",
    target_pointer_width = "32",
    target_pointer_width = "64"
)))]
compile_error!("memchr currently not supported on non-32 or non-64 bit");

#[cfg(feature = "std")]
extern crate core;

#[cfg(all(test, all(not(miri), feature = "std")))]
#[macro_use]
extern crate quickcheck;

use core::iter::Rev;

pub use iter::{Memchr, Memchr2, Memchr3};

// N.B. If you're looking for the cfg knobs for libc, see build.rs.
#[cfg(memchr_libc)]
mod c;
#[allow(dead_code)]
mod fallback;
mod iter;
mod naive;
#[cfg(all(test, all(not(miri), feature = "std")))]
mod tests;
#[cfg(all(test, any(miri, not(feature = "std"))))]
#[path = "tests/miri.rs"]
mod tests;
#[cfg(all(not(miri), target_arch = "x86_64", memchr_runtime_simd))]
mod x86;

/// An iterator over all occurrences of the needle in a haystack.
#[inline]
pub fn memchr_iter(needle: u8, haystack: &[u8]) -> Memchr {
    Memchr::new(needle, haystack)
}

/// An iterator over all occurrences of the needles in a haystack.
#[inline]
pub fn memchr2_iter(needle1: u8, needle2: u8, haystack: &[u8]) -> Memchr2 {
    Memchr2::new(needle1, needle2, haystack)
}

/// An iterator over all occurrences of the needles in a haystack.
#[inline]
pub fn memchr3_iter(
    needle1: u8,
    needle2: u8,
    needle3: u8,
    haystack: &[u8],
) -> Memchr3 {
    Memchr3::new(needle1, needle2, needle3, haystack)
}

/// An iterator over all occurrences of the needle in a haystack, in reverse.
#[inline]
pub fn memrchr_iter(needle: u8, haystack: &[u8]) -> Rev<Memchr> {
    Memchr::new(needle, haystack).rev()
}

/// An iterator over all occurrences of the needles in a haystack, in reverse.
#[inline]
pub fn memrchr2_iter(
    needle1: u8,
    needle2: u8,
    haystack: &[u8],
) -> Rev<Memchr2> {
    Memchr2::new(needle1, needle2, haystack).rev()
}

/// An iterator over all occurrences of the needles in a haystack, in reverse.
#[inline]
pub fn memrchr3_iter(
    needle1: u8,
    needle2: u8,
    needle3: u8,
    haystack: &[u8],
) -> Rev<Memchr3> {
    Memchr3::new(needle1, needle2, needle3, haystack).rev()
}

/// Search for the first occurrence of a byte in a slice.
///
/// This returns the index corresponding to the first occurrence of `needle` in
/// `haystack`, or `None` if one is not found.
///
/// While this is operationally the same as something like
/// `haystack.iter().position(|&b| b == needle)`, `memchr` will use a highly
/// optimized routine that can be up to an order of magnitude faster in some
/// cases.
///
/// # Example
///
/// This shows how to find the first position of a byte in a byte string.
///
/// ```
/// use memchr::memchr;
///
/// let haystack = b"the quick brown fox";
/// assert_eq!(memchr(b'k', haystack), Some(8));
/// ```
#[inline]
pub fn memchr(needle: u8, haystack: &[u8]) -> Option<usize> {
    #[cfg(miri)]
    #[inline(always)]
    fn imp(n1: u8, haystack: &[u8]) -> Option<usize> {
        naive::memchr(n1, haystack)
    }

    #[cfg(all(target_arch = "x86_64", memchr_runtime_simd, not(miri)))]
    #[inline(always)]
    fn imp(n1: u8, haystack: &[u8]) -> Option<usize> {
        x86::memchr(n1, haystack)
    }

    #[cfg(all(
        memchr_libc,
        not(all(target_arch = "x86_64", memchr_runtime_simd)),
        not(miri),
    ))]
    #[inline(always)]
    fn imp(n1: u8, haystack: &[u8]) -> Option<usize> {
        c::memchr(n1, haystack)
    }

    #[cfg(all(
        not(memchr_libc),
        not(all(target_arch = "x86_64", memchr_runtime_simd)),
        not(miri),
    ))]
    #[inline(always)]
    fn imp(n1: u8, haystack: &[u8]) -> Option<usize> {
        fallback::memchr(n1, haystack)
    }

    if haystack.is_empty() {
        None
    } else {
        imp(needle, haystack)
    }
}

/// Like `memchr`, but searches for either of two bytes instead of just one.
///
/// This returns the index corresponding to the first occurrence of `needle1`
/// or the first occurrence of `needle2` in `haystack` (whichever occurs
/// earlier), or `None` if neither one is found.
///
/// While this is operationally the same as something like
/// `haystack.iter().position(|&b| b == needle1 || b == needle2)`, `memchr2`
/// will use a highly optimized routine that can be up to an order of magnitude
/// faster in some cases.
///
/// # Example
///
/// This shows how to find the first position of either of two bytes in a byte
/// string.
///
/// ```
/// use memchr::memchr2;
///
/// let haystack = b"the quick brown fox";
/// assert_eq!(memchr2(b'k', b'q', haystack), Some(4));
/// ```
#[inline]
pub fn memchr2(needle1: u8, needle2: u8, haystack: &[u8]) -> Option<usize> {
    #[cfg(miri)]
    #[inline(always)]
    fn imp(n1: u8, n2: u8, haystack: &[u8]) -> Option<usize> {
        naive::memchr2(n1, n2, haystack)
    }

    #[cfg(all(target_arch = "x86_64", memchr_runtime_simd, not(miri)))]
    #[inline(always)]
    fn imp(n1: u8, n2: u8, haystack: &[u8]) -> Option<usize> {
        x86::memchr2(n1, n2, haystack)
    }

    #[cfg(all(
        not(all(target_arch = "x86_64", memchr_runtime_simd)),
        not(miri),
    ))]
    #[inline(always)]
    fn imp(n1: u8, n2: u8, haystack: &[u8]) -> Option<usize> {
        fallback::memchr2(n1, n2, haystack)
    }

    if haystack.is_empty() {
        None
    } else {
        imp(needle1, needle2, haystack)
    }
}

/// Like `memchr`, but searches for any of three bytes instead of just one.
///
/// This returns the index corresponding to the first occurrence of `needle1`,
/// the first occurrence of `needle2`, or the first occurrence of `needle3` in
/// `haystack` (whichever occurs earliest), or `None` if none are found.
///
/// While this is operationally the same as something like
/// `haystack.iter().position(|&b| b == needle1 || b == needle2 ||
/// b == needle3)`, `memchr3` will use a highly optimized routine that can be
/// up to an order of magnitude faster in some cases.
///
/// # Example
///
/// This shows how to find the first position of any of three bytes in a byte
/// string.
///
/// ```
/// use memchr::memchr3;
///
/// let haystack = b"the quick brown fox";
/// assert_eq!(memchr3(b'k', b'q', b'e', haystack), Some(2));
/// ```
#[inline]
pub fn memchr3(
    needle1: u8,
    needle2: u8,
    needle3: u8,
    haystack: &[u8],
) -> Option<usize> {
    #[cfg(miri)]
    #[inline(always)]
    fn imp(n1: u8, n2: u8, n3: u8, haystack: &[u8]) -> Option<usize> {
        naive::memchr3(n1, n2, n3, haystack)
    }

    #[cfg(all(target_arch = "x86_64", memchr_runtime_simd, not(miri)))]
    #[inline(always)]
    fn imp(n1: u8, n2: u8, n3: u8, haystack: &[u8]) -> Option<usize> {
        x86::memchr3(n1, n2, n3, haystack)
    }

    #[cfg(all(
        not(all(target_arch = "x86_64", memchr_runtime_simd)),
        not(miri),
    ))]
    #[inline(always)]
    fn imp(n1: u8, n2: u8, n3: u8, haystack: &[u8]) -> Option<usize> {
        fallback::memchr3(n1, n2, n3, haystack)
    }

    if haystack.is_empty() {
        None
    } else {
        imp(needle1, needle2, needle3, haystack)
    }
}

/// Search for the last occurrence of a byte in a slice.
///
/// This returns the index corresponding to the last occurrence of `needle` in
/// `haystack`, or `None` if one is not found.
///
/// While this is operationally the same as something like
/// `haystack.iter().rposition(|&b| b == needle)`, `memrchr` will use a highly
/// optimized routine that can be up to an order of magnitude faster in some
/// cases.
///
/// # Example
///
/// This shows how to find the last position of a byte in a byte string.
///
/// ```
/// use memchr::memrchr;
///
/// let haystack = b"the quick brown fox";
/// assert_eq!(memrchr(b'o', haystack), Some(17));
/// ```
#[inline]
pub fn memrchr(needle: u8, haystack: &[u8]) -> Option<usize> {
    #[cfg(miri)]
    #[inline(always)]
    fn imp(n1: u8, haystack: &[u8]) -> Option<usize> {
        naive::memrchr(n1, haystack)
    }

    #[cfg(all(target_arch = "x86_64", memchr_runtime_simd, not(miri)))]
    #[inline(always)]
    fn imp(n1: u8, haystack: &[u8]) -> Option<usize> {
        x86::memrchr(n1, haystack)
    }

    #[cfg(all(
        memchr_libc,
        target_os = "linux",
        not(all(target_arch = "x86_64", memchr_runtime_simd)),
        not(miri)
    ))]
    #[inline(always)]
    fn imp(n1: u8, haystack: &[u8]) -> Option<usize> {
        c::memrchr(n1, haystack)
    }

    #[cfg(all(
        not(all(memchr_libc, target_os = "linux")),
        not(all(target_arch = "x86_64", memchr_runtime_simd)),
        not(miri),
    ))]
    #[inline(always)]
    fn imp(n1: u8, haystack: &[u8]) -> Option<usize> {
        fallback::memrchr(n1, haystack)
    }

    if haystack.is_empty() {
        None
    } else {
        imp(needle, haystack)
    }
}

/// Like `memrchr`, but searches for either of two bytes instead of just one.
///
/// This returns the index corresponding to the last occurrence of `needle1`
/// or the last occurrence of `needle2` in `haystack` (whichever occurs later),
/// or `None` if neither one is found.
///
/// While this is operationally the same as something like
/// `haystack.iter().rposition(|&b| b == needle1 || b == needle2)`, `memrchr2`
/// will use a highly optimized routine that can be up to an order of magnitude
/// faster in some cases.
///
/// # Example
///
/// This shows how to find the last position of either of two bytes in a byte
/// string.
///
/// ```
/// use memchr::memrchr2;
///
/// let haystack = b"the quick brown fox";
/// assert_eq!(memrchr2(b'k', b'q', haystack), Some(8));
/// ```
#[inline]
pub fn memrchr2(needle1: u8, needle2: u8, haystack: &[u8]) -> Option<usize> {
    #[cfg(miri)]
    #[inline(always)]
    fn imp(n1: u8, n2: u8, haystack: &[u8]) -> Option<usize> {
        naive::memrchr2(n1, n2, haystack)
    }

    #[cfg(all(target_arch = "x86_64", memchr_runtime_simd, not(miri)))]
    #[inline(always)]
    fn imp(n1: u8, n2: u8, haystack: &[u8]) -> Option<usize> {
        x86::memrchr2(n1, n2, haystack)
    }

    #[cfg(all(
        not(all(target_arch = "x86_64", memchr_runtime_simd)),
        not(miri),
    ))]
    #[inline(always)]
    fn imp(n1: u8, n2: u8, haystack: &[u8]) -> Option<usize> {
        fallback::memrchr2(n1, n2, haystack)
    }

    if haystack.is_empty() {
        None
    } else {
        imp(needle1, needle2, haystack)
    }
}

/// Like `memrchr`, but searches for any of three bytes instead of just one.
///
/// This returns the index corresponding to the last occurrence of `needle1`,
/// the last occurrence of `needle2`, or the last occurrence of `needle3` in
/// `haystack` (whichever occurs later), or `None` if none are found.
///
/// While this is operationally the same as something like
/// `haystack.iter().rposition(|&b| b == needle1 || b == needle2 ||
/// b == needle3)`, `memrchr3` will use a highly optimized routine that can be
/// up to an order of magnitude faster in some cases.
///
/// # Example
///
/// This shows how to find the last position of any of three bytes in a byte
/// string.
///
/// ```
/// use memchr::memrchr3;
///
/// let haystack = b"the quick brown fox";
/// assert_eq!(memrchr3(b'k', b'q', b'e', haystack), Some(8));
/// ```
#[inline]
pub fn memrchr3(
    needle1: u8,
    needle2: u8,
    needle3: u8,
    haystack: &[u8],
) -> Option<usize> {
    #[cfg(miri)]
    #[inline(always)]
    fn imp(n1: u8, n2: u8, n3: u8, haystack: &[u8]) -> Option<usize> {
        naive::memrchr3(n1, n2, n3, haystack)
    }

    #[cfg(all(target_arch = "x86_64", memchr_runtime_simd, not(miri)))]
    #[inline(always)]
    fn imp(n1: u8, n2: u8, n3: u8, haystack: &[u8]) -> Option<usize> {
        x86::memrchr3(n1, n2, n3, haystack)
    }

    #[cfg(all(
        not(all(target_arch = "x86_64", memchr_runtime_simd)),
        not(miri),
    ))]
    #[inline(always)]
    fn imp(n1: u8, n2: u8, n3: u8, haystack: &[u8]) -> Option<usize> {
        fallback::memrchr3(n1, n2, n3, haystack)
    }

    if haystack.is_empty() {
        None
    } else {
        imp(needle1, needle2, needle3, haystack)
    }
}