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
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
|
/*!
An implementation of the [Two-Way substring search algorithm][two-way].
[`Finder`] can be built for forward searches, while [`FinderRev`] can be built
for reverse searches.
Two-Way makes for a nice general purpose substring search algorithm because of
its time and space complexity properties. It also performs well in practice.
Namely, with `m = len(needle)` and `n = len(haystack)`, Two-Way takes `O(m)`
time to create a finder, `O(1)` space and `O(n)` search time. In other words,
the preprocessing step is quick, doesn't require any heap memory and the worst
case search time is guaranteed to be linear in the haystack regardless of the
size of the needle.
While vector algorithms will usually beat Two-Way handedly, vector algorithms
also usually have pathological or edge cases that are better handled by Two-Way.
Moreover, not all targets support vector algorithms or implementations for them
simply may not exist yet.
Two-Way can be found in the `memmem` implementations in at least [GNU libc] and
[musl].
[two-way]: https://en.wikipedia.org/wiki/Two-way_string-matching_algorithm
[GNU libc]: https://www.gnu.org/software/libc/
[musl]: https://www.musl-libc.org/
*/
use core::cmp;
use crate::{
arch::all::{is_prefix, is_suffix},
memmem::Pre,
};
/// A forward substring searcher that uses the Two-Way algorithm.
#[derive(Clone, Copy, Debug)]
pub struct Finder(TwoWay);
/// A reverse substring searcher that uses the Two-Way algorithm.
#[derive(Clone, Copy, Debug)]
pub struct FinderRev(TwoWay);
/// An implementation of the TwoWay substring search algorithm.
///
/// This searcher supports forward and reverse search, although not
/// simultaneously. It runs in `O(n + m)` time and `O(1)` space, where
/// `n ~ len(needle)` and `m ~ len(haystack)`.
///
/// The implementation here roughly matches that which was developed by
/// Crochemore and Perrin in their 1991 paper "Two-way string-matching." The
/// changes in this implementation are 1) the use of zero-based indices, 2) a
/// heuristic skip table based on the last byte (borrowed from Rust's standard
/// library) and 3) the addition of heuristics for a fast skip loop. For (3),
/// callers can pass any kind of prefilter they want, but usually it's one
/// based on a heuristic that uses an approximate background frequency of bytes
/// to choose rare bytes to quickly look for candidate match positions. Note
/// though that currently, this prefilter functionality is not exposed directly
/// in the public API. (File an issue if you want it and provide a use case
/// please.)
///
/// The heuristic for fast skipping is automatically shut off if it's
/// detected to be ineffective at search time. Generally, this only occurs in
/// pathological cases. But this is generally necessary in order to preserve
/// a `O(n + m)` time bound.
///
/// The code below is fairly complex and not obviously correct at all. It's
/// likely necessary to read the Two-Way paper cited above in order to fully
/// grok this code. The essence of it is:
///
/// 1. Do something to detect a "critical" position in the needle.
/// 2. For the current position in the haystack, look if `needle[critical..]`
/// matches at that position.
/// 3. If so, look if `needle[..critical]` matches.
/// 4. If a mismatch occurs, shift the search by some amount based on the
/// critical position and a pre-computed shift.
///
/// This type is wrapped in the forward and reverse finders that expose
/// consistent forward or reverse APIs.
#[derive(Clone, Copy, Debug)]
struct TwoWay {
/// A small bitset used as a quick prefilter (in addition to any prefilter
/// given by the caller). Namely, a bit `i` is set if and only if `b%64==i`
/// for any `b == needle[i]`.
///
/// When used as a prefilter, if the last byte at the current candidate
/// position is NOT in this set, then we can skip that entire candidate
/// position (the length of the needle). This is essentially the shift
/// trick found in Boyer-Moore, but only applied to bytes that don't appear
/// in the needle.
///
/// N.B. This trick was inspired by something similar in std's
/// implementation of Two-Way.
byteset: ApproximateByteSet,
/// A critical position in needle. Specifically, this position corresponds
/// to beginning of either the minimal or maximal suffix in needle. (N.B.
/// See SuffixType below for why "minimal" isn't quite the correct word
/// here.)
///
/// This is the position at which every search begins. Namely, search
/// starts by scanning text to the right of this position, and only if
/// there's a match does the text to the left of this position get scanned.
critical_pos: usize,
/// The amount we shift by in the Two-Way search algorithm. This
/// corresponds to the "small period" and "large period" cases.
shift: Shift,
}
impl Finder {
/// Create a searcher that finds occurrences of the given `needle`.
///
/// An empty `needle` results in a match at every position in a haystack,
/// including at `haystack.len()`.
#[inline]
pub fn new(needle: &[u8]) -> Finder {
let byteset = ApproximateByteSet::new(needle);
let min_suffix = Suffix::forward(needle, SuffixKind::Minimal);
let max_suffix = Suffix::forward(needle, SuffixKind::Maximal);
let (period_lower_bound, critical_pos) =
if min_suffix.pos > max_suffix.pos {
(min_suffix.period, min_suffix.pos)
} else {
(max_suffix.period, max_suffix.pos)
};
let shift = Shift::forward(needle, period_lower_bound, critical_pos);
Finder(TwoWay { byteset, critical_pos, shift })
}
/// Returns the first occurrence of `needle` in the given `haystack`, or
/// `None` if no such occurrence could be found.
///
/// The `needle` given must be the same as the `needle` provided to
/// [`Finder::new`].
///
/// An empty `needle` results in a match at every position in a haystack,
/// including at `haystack.len()`.
#[inline]
pub fn find(&self, haystack: &[u8], needle: &[u8]) -> Option<usize> {
self.find_with_prefilter(None, haystack, needle)
}
/// This is like [`Finder::find`], but it accepts a prefilter for
/// accelerating searches.
///
/// Currently this is not exposed in the public API because, at the time
/// of writing, I didn't want to spend time thinking about how to expose
/// the prefilter infrastructure (if at all). If you have a compelling use
/// case for exposing this routine, please create an issue. Do *not* open
/// a PR that just exposes `Pre` and friends. Exporting this routine will
/// require API design.
#[inline(always)]
pub(crate) fn find_with_prefilter(
&self,
pre: Option<Pre<'_>>,
haystack: &[u8],
needle: &[u8],
) -> Option<usize> {
match self.0.shift {
Shift::Small { period } => {
self.find_small_imp(pre, haystack, needle, period)
}
Shift::Large { shift } => {
self.find_large_imp(pre, haystack, needle, shift)
}
}
}
// Each of the two search implementations below can be accelerated by a
// prefilter, but it is not always enabled. To avoid its overhead when
// its disabled, we explicitly inline each search implementation based on
// whether a prefilter will be used or not. The decision on which to use
// is made in the parent meta searcher.
#[inline(always)]
fn find_small_imp(
&self,
mut pre: Option<Pre<'_>>,
haystack: &[u8],
needle: &[u8],
period: usize,
) -> Option<usize> {
let mut pos = 0;
let mut shift = 0;
let last_byte_pos = match needle.len().checked_sub(1) {
None => return Some(pos),
Some(last_byte) => last_byte,
};
while pos + needle.len() <= haystack.len() {
let mut i = cmp::max(self.0.critical_pos, shift);
if let Some(pre) = pre.as_mut() {
if pre.is_effective() {
pos += pre.find(&haystack[pos..])?;
shift = 0;
i = self.0.critical_pos;
if pos + needle.len() > haystack.len() {
return None;
}
}
}
if !self.0.byteset.contains(haystack[pos + last_byte_pos]) {
pos += needle.len();
shift = 0;
continue;
}
while i < needle.len() && needle[i] == haystack[pos + i] {
i += 1;
}
if i < needle.len() {
pos += i - self.0.critical_pos + 1;
shift = 0;
} else {
let mut j = self.0.critical_pos;
while j > shift && needle[j] == haystack[pos + j] {
j -= 1;
}
if j <= shift && needle[shift] == haystack[pos + shift] {
return Some(pos);
}
pos += period;
shift = needle.len() - period;
}
}
None
}
#[inline(always)]
fn find_large_imp(
&self,
mut pre: Option<Pre<'_>>,
haystack: &[u8],
needle: &[u8],
shift: usize,
) -> Option<usize> {
let mut pos = 0;
let last_byte_pos = match needle.len().checked_sub(1) {
None => return Some(pos),
Some(last_byte) => last_byte,
};
'outer: while pos + needle.len() <= haystack.len() {
if let Some(pre) = pre.as_mut() {
if pre.is_effective() {
pos += pre.find(&haystack[pos..])?;
if pos + needle.len() > haystack.len() {
return None;
}
}
}
if !self.0.byteset.contains(haystack[pos + last_byte_pos]) {
pos += needle.len();
continue;
}
let mut i = self.0.critical_pos;
while i < needle.len() && needle[i] == haystack[pos + i] {
i += 1;
}
if i < needle.len() {
pos += i - self.0.critical_pos + 1;
} else {
for j in (0..self.0.critical_pos).rev() {
if needle[j] != haystack[pos + j] {
pos += shift;
continue 'outer;
}
}
return Some(pos);
}
}
None
}
}
impl FinderRev {
/// Create a searcher that finds occurrences of the given `needle`.
///
/// An empty `needle` results in a match at every position in a haystack,
/// including at `haystack.len()`.
#[inline]
pub fn new(needle: &[u8]) -> FinderRev {
let byteset = ApproximateByteSet::new(needle);
let min_suffix = Suffix::reverse(needle, SuffixKind::Minimal);
let max_suffix = Suffix::reverse(needle, SuffixKind::Maximal);
let (period_lower_bound, critical_pos) =
if min_suffix.pos < max_suffix.pos {
(min_suffix.period, min_suffix.pos)
} else {
(max_suffix.period, max_suffix.pos)
};
let shift = Shift::reverse(needle, period_lower_bound, critical_pos);
FinderRev(TwoWay { byteset, critical_pos, shift })
}
/// Returns the last occurrence of `needle` in the given `haystack`, or
/// `None` if no such occurrence could be found.
///
/// The `needle` given must be the same as the `needle` provided to
/// [`FinderRev::new`].
///
/// An empty `needle` results in a match at every position in a haystack,
/// including at `haystack.len()`.
#[inline]
pub fn rfind(&self, haystack: &[u8], needle: &[u8]) -> Option<usize> {
// For the reverse case, we don't use a prefilter. It's plausible that
// perhaps we should, but it's a lot of additional code to do it, and
// it's not clear that it's actually worth it. If you have a really
// compelling use case for this, please file an issue.
match self.0.shift {
Shift::Small { period } => {
self.rfind_small_imp(haystack, needle, period)
}
Shift::Large { shift } => {
self.rfind_large_imp(haystack, needle, shift)
}
}
}
#[inline(always)]
fn rfind_small_imp(
&self,
haystack: &[u8],
needle: &[u8],
period: usize,
) -> Option<usize> {
let nlen = needle.len();
let mut pos = haystack.len();
let mut shift = nlen;
let first_byte = match needle.get(0) {
None => return Some(pos),
Some(&first_byte) => first_byte,
};
while pos >= nlen {
if !self.0.byteset.contains(haystack[pos - nlen]) {
pos -= nlen;
shift = nlen;
continue;
}
let mut i = cmp::min(self.0.critical_pos, shift);
while i > 0 && needle[i - 1] == haystack[pos - nlen + i - 1] {
i -= 1;
}
if i > 0 || first_byte != haystack[pos - nlen] {
pos -= self.0.critical_pos - i + 1;
shift = nlen;
} else {
let mut j = self.0.critical_pos;
while j < shift && needle[j] == haystack[pos - nlen + j] {
j += 1;
}
if j >= shift {
return Some(pos - nlen);
}
pos -= period;
shift = period;
}
}
None
}
#[inline(always)]
fn rfind_large_imp(
&self,
haystack: &[u8],
needle: &[u8],
shift: usize,
) -> Option<usize> {
let nlen = needle.len();
let mut pos = haystack.len();
let first_byte = match needle.get(0) {
None => return Some(pos),
Some(&first_byte) => first_byte,
};
while pos >= nlen {
if !self.0.byteset.contains(haystack[pos - nlen]) {
pos -= nlen;
continue;
}
let mut i = self.0.critical_pos;
while i > 0 && needle[i - 1] == haystack[pos - nlen + i - 1] {
i -= 1;
}
if i > 0 || first_byte != haystack[pos - nlen] {
pos -= self.0.critical_pos - i + 1;
} else {
let mut j = self.0.critical_pos;
while j < nlen && needle[j] == haystack[pos - nlen + j] {
j += 1;
}
if j == nlen {
return Some(pos - nlen);
}
pos -= shift;
}
}
None
}
}
/// A representation of the amount we're allowed to shift by during Two-Way
/// search.
///
/// When computing a critical factorization of the needle, we find the position
/// of the critical factorization by finding the needle's maximal (or minimal)
/// suffix, along with the period of that suffix. It turns out that the period
/// of that suffix is a lower bound on the period of the needle itself.
///
/// This lower bound is equivalent to the actual period of the needle in
/// some cases. To describe that case, we denote the needle as `x` where
/// `x = uv` and `v` is the lexicographic maximal suffix of `v`. The lower
/// bound given here is always the period of `v`, which is `<= period(x)`. The
/// case where `period(v) == period(x)` occurs when `len(u) < (len(x) / 2)` and
/// where `u` is a suffix of `v[0..period(v)]`.
///
/// This case is important because the search algorithm for when the
/// periods are equivalent is slightly different than the search algorithm
/// for when the periods are not equivalent. In particular, when they aren't
/// equivalent, we know that the period of the needle is no less than half its
/// length. In this case, we shift by an amount less than or equal to the
/// period of the needle (determined by the maximum length of the components
/// of the critical factorization of `x`, i.e., `max(len(u), len(v))`)..
///
/// The above two cases are represented by the variants below. Each entails
/// a different instantiation of the Two-Way search algorithm.
///
/// N.B. If we could find a way to compute the exact period in all cases,
/// then we could collapse this case analysis and simplify the algorithm. The
/// Two-Way paper suggests this is possible, but more reading is required to
/// grok why the authors didn't pursue that path.
#[derive(Clone, Copy, Debug)]
enum Shift {
Small { period: usize },
Large { shift: usize },
}
impl Shift {
/// Compute the shift for a given needle in the forward direction.
///
/// This requires a lower bound on the period and a critical position.
/// These can be computed by extracting both the minimal and maximal
/// lexicographic suffixes, and choosing the right-most starting position.
/// The lower bound on the period is then the period of the chosen suffix.
fn forward(
needle: &[u8],
period_lower_bound: usize,
critical_pos: usize,
) -> Shift {
let large = cmp::max(critical_pos, needle.len() - critical_pos);
if critical_pos * 2 >= needle.len() {
return Shift::Large { shift: large };
}
let (u, v) = needle.split_at(critical_pos);
if !is_suffix(&v[..period_lower_bound], u) {
return Shift::Large { shift: large };
}
Shift::Small { period: period_lower_bound }
}
/// Compute the shift for a given needle in the reverse direction.
///
/// This requires a lower bound on the period and a critical position.
/// These can be computed by extracting both the minimal and maximal
/// lexicographic suffixes, and choosing the left-most starting position.
/// The lower bound on the period is then the period of the chosen suffix.
fn reverse(
needle: &[u8],
period_lower_bound: usize,
critical_pos: usize,
) -> Shift {
let large = cmp::max(critical_pos, needle.len() - critical_pos);
if (needle.len() - critical_pos) * 2 >= needle.len() {
return Shift::Large { shift: large };
}
let (v, u) = needle.split_at(critical_pos);
if !is_prefix(&v[v.len() - period_lower_bound..], u) {
return Shift::Large { shift: large };
}
Shift::Small { period: period_lower_bound }
}
}
/// A suffix extracted from a needle along with its period.
#[derive(Debug)]
struct Suffix {
/// The starting position of this suffix.
///
/// If this is a forward suffix, then `&bytes[pos..]` can be used. If this
/// is a reverse suffix, then `&bytes[..pos]` can be used. That is, for
/// forward suffixes, this is an inclusive starting position, where as for
/// reverse suffixes, this is an exclusive ending position.
pos: usize,
/// The period of this suffix.
///
/// Note that this is NOT necessarily the period of the string from which
/// this suffix comes from. (It is always less than or equal to the period
/// of the original string.)
period: usize,
}
impl Suffix {
fn forward(needle: &[u8], kind: SuffixKind) -> Suffix {
// suffix represents our maximal (or minimal) suffix, along with
// its period.
let mut suffix = Suffix { pos: 0, period: 1 };
// The start of a suffix in `needle` that we are considering as a
// more maximal (or minimal) suffix than what's in `suffix`.
let mut candidate_start = 1;
// The current offset of our suffixes that we're comparing.
//
// When the characters at this offset are the same, then we mush on
// to the next position since no decision is possible. When the
// candidate's character is greater (or lesser) than the corresponding
// character than our current maximal (or minimal) suffix, then the
// current suffix is changed over to the candidate and we restart our
// search. Otherwise, the candidate suffix is no good and we restart
// our search on the next candidate.
//
// The three cases above correspond to the three cases in the loop
// below.
let mut offset = 0;
while candidate_start + offset < needle.len() {
let current = needle[suffix.pos + offset];
let candidate = needle[candidate_start + offset];
match kind.cmp(current, candidate) {
SuffixOrdering::Accept => {
suffix = Suffix { pos: candidate_start, period: 1 };
candidate_start += 1;
offset = 0;
}
SuffixOrdering::Skip => {
candidate_start += offset + 1;
offset = 0;
suffix.period = candidate_start - suffix.pos;
}
SuffixOrdering::Push => {
if offset + 1 == suffix.period {
candidate_start += suffix.period;
offset = 0;
} else {
offset += 1;
}
}
}
}
suffix
}
fn reverse(needle: &[u8], kind: SuffixKind) -> Suffix {
// See the comments in `forward` for how this works.
let mut suffix = Suffix { pos: needle.len(), period: 1 };
if needle.len() == 1 {
return suffix;
}
let mut candidate_start = match needle.len().checked_sub(1) {
None => return suffix,
Some(candidate_start) => candidate_start,
};
let mut offset = 0;
while offset < candidate_start {
let current = needle[suffix.pos - offset - 1];
let candidate = needle[candidate_start - offset - 1];
match kind.cmp(current, candidate) {
SuffixOrdering::Accept => {
suffix = Suffix { pos: candidate_start, period: 1 };
candidate_start -= 1;
offset = 0;
}
SuffixOrdering::Skip => {
candidate_start -= offset + 1;
offset = 0;
suffix.period = suffix.pos - candidate_start;
}
SuffixOrdering::Push => {
if offset + 1 == suffix.period {
candidate_start -= suffix.period;
offset = 0;
} else {
offset += 1;
}
}
}
}
suffix
}
}
/// The kind of suffix to extract.
#[derive(Clone, Copy, Debug)]
enum SuffixKind {
/// Extract the smallest lexicographic suffix from a string.
///
/// Technically, this doesn't actually pick the smallest lexicographic
/// suffix. e.g., Given the choice between `a` and `aa`, this will choose
/// the latter over the former, even though `a < aa`. The reasoning for
/// this isn't clear from the paper, but it still smells like a minimal
/// suffix.
Minimal,
/// Extract the largest lexicographic suffix from a string.
///
/// Unlike `Minimal`, this really does pick the maximum suffix. e.g., Given
/// the choice between `z` and `zz`, this will choose the latter over the
/// former.
Maximal,
}
/// The result of comparing corresponding bytes between two suffixes.
#[derive(Clone, Copy, Debug)]
enum SuffixOrdering {
/// This occurs when the given candidate byte indicates that the candidate
/// suffix is better than the current maximal (or minimal) suffix. That is,
/// the current candidate suffix should supplant the current maximal (or
/// minimal) suffix.
Accept,
/// This occurs when the given candidate byte excludes the candidate suffix
/// from being better than the current maximal (or minimal) suffix. That
/// is, the current candidate suffix should be dropped and the next one
/// should be considered.
Skip,
/// This occurs when no decision to accept or skip the candidate suffix
/// can be made, e.g., when corresponding bytes are equivalent. In this
/// case, the next corresponding bytes should be compared.
Push,
}
impl SuffixKind {
/// Returns true if and only if the given candidate byte indicates that
/// it should replace the current suffix as the maximal (or minimal)
/// suffix.
fn cmp(self, current: u8, candidate: u8) -> SuffixOrdering {
use self::SuffixOrdering::*;
match self {
SuffixKind::Minimal if candidate < current => Accept,
SuffixKind::Minimal if candidate > current => Skip,
SuffixKind::Minimal => Push,
SuffixKind::Maximal if candidate > current => Accept,
SuffixKind::Maximal if candidate < current => Skip,
SuffixKind::Maximal => Push,
}
}
}
/// A bitset used to track whether a particular byte exists in a needle or not.
///
/// Namely, bit 'i' is set if and only if byte%64==i for any byte in the
/// needle. If a particular byte in the haystack is NOT in this set, then one
/// can conclude that it is also not in the needle, and thus, one can advance
/// in the haystack by needle.len() bytes.
#[derive(Clone, Copy, Debug)]
struct ApproximateByteSet(u64);
impl ApproximateByteSet {
/// Create a new set from the given needle.
fn new(needle: &[u8]) -> ApproximateByteSet {
let mut bits = 0;
for &b in needle {
bits |= 1 << (b % 64);
}
ApproximateByteSet(bits)
}
/// Return true if and only if the given byte might be in this set. This
/// may return a false positive, but will never return a false negative.
#[inline(always)]
fn contains(&self, byte: u8) -> bool {
self.0 & (1 << (byte % 64)) != 0
}
}
#[cfg(test)]
mod tests {
use alloc::vec::Vec;
use super::*;
/// Convenience wrapper for computing the suffix as a byte string.
fn get_suffix_forward(needle: &[u8], kind: SuffixKind) -> (&[u8], usize) {
let s = Suffix::forward(needle, kind);
(&needle[s.pos..], s.period)
}
/// Convenience wrapper for computing the reverse suffix as a byte string.
fn get_suffix_reverse(needle: &[u8], kind: SuffixKind) -> (&[u8], usize) {
let s = Suffix::reverse(needle, kind);
(&needle[..s.pos], s.period)
}
/// Return all of the non-empty suffixes in the given byte string.
fn suffixes(bytes: &[u8]) -> Vec<&[u8]> {
(0..bytes.len()).map(|i| &bytes[i..]).collect()
}
/// Return the lexicographically maximal suffix of the given byte string.
fn naive_maximal_suffix_forward(needle: &[u8]) -> &[u8] {
let mut sufs = suffixes(needle);
sufs.sort();
sufs.pop().unwrap()
}
/// Return the lexicographically maximal suffix of the reverse of the given
/// byte string.
fn naive_maximal_suffix_reverse(needle: &[u8]) -> Vec<u8> {
let mut reversed = needle.to_vec();
reversed.reverse();
let mut got = naive_maximal_suffix_forward(&reversed).to_vec();
got.reverse();
got
}
define_substring_forward_quickcheck!(|h, n| Some(
Finder::new(n).find(h, n)
));
define_substring_reverse_quickcheck!(|h, n| Some(
FinderRev::new(n).rfind(h, n)
));
#[test]
fn forward() {
crate::tests::substring::Runner::new()
.fwd(|h, n| Some(Finder::new(n).find(h, n)))
.run();
}
#[test]
fn reverse() {
crate::tests::substring::Runner::new()
.rev(|h, n| Some(FinderRev::new(n).rfind(h, n)))
.run();
}
#[test]
fn suffix_forward() {
macro_rules! assert_suffix_min {
($given:expr, $expected:expr, $period:expr) => {
let (got_suffix, got_period) =
get_suffix_forward($given.as_bytes(), SuffixKind::Minimal);
let got_suffix = core::str::from_utf8(got_suffix).unwrap();
assert_eq!(($expected, $period), (got_suffix, got_period));
};
}
macro_rules! assert_suffix_max {
($given:expr, $expected:expr, $period:expr) => {
let (got_suffix, got_period) =
get_suffix_forward($given.as_bytes(), SuffixKind::Maximal);
let got_suffix = core::str::from_utf8(got_suffix).unwrap();
assert_eq!(($expected, $period), (got_suffix, got_period));
};
}
assert_suffix_min!("a", "a", 1);
assert_suffix_max!("a", "a", 1);
assert_suffix_min!("ab", "ab", 2);
assert_suffix_max!("ab", "b", 1);
assert_suffix_min!("ba", "a", 1);
assert_suffix_max!("ba", "ba", 2);
assert_suffix_min!("abc", "abc", 3);
assert_suffix_max!("abc", "c", 1);
assert_suffix_min!("acb", "acb", 3);
assert_suffix_max!("acb", "cb", 2);
assert_suffix_min!("cba", "a", 1);
assert_suffix_max!("cba", "cba", 3);
assert_suffix_min!("abcabc", "abcabc", 3);
assert_suffix_max!("abcabc", "cabc", 3);
assert_suffix_min!("abcabcabc", "abcabcabc", 3);
assert_suffix_max!("abcabcabc", "cabcabc", 3);
assert_suffix_min!("abczz", "abczz", 5);
assert_suffix_max!("abczz", "zz", 1);
assert_suffix_min!("zzabc", "abc", 3);
assert_suffix_max!("zzabc", "zzabc", 5);
assert_suffix_min!("aaa", "aaa", 1);
assert_suffix_max!("aaa", "aaa", 1);
assert_suffix_min!("foobar", "ar", 2);
assert_suffix_max!("foobar", "r", 1);
}
#[test]
fn suffix_reverse() {
macro_rules! assert_suffix_min {
($given:expr, $expected:expr, $period:expr) => {
let (got_suffix, got_period) =
get_suffix_reverse($given.as_bytes(), SuffixKind::Minimal);
let got_suffix = core::str::from_utf8(got_suffix).unwrap();
assert_eq!(($expected, $period), (got_suffix, got_period));
};
}
macro_rules! assert_suffix_max {
($given:expr, $expected:expr, $period:expr) => {
let (got_suffix, got_period) =
get_suffix_reverse($given.as_bytes(), SuffixKind::Maximal);
let got_suffix = core::str::from_utf8(got_suffix).unwrap();
assert_eq!(($expected, $period), (got_suffix, got_period));
};
}
assert_suffix_min!("a", "a", 1);
assert_suffix_max!("a", "a", 1);
assert_suffix_min!("ab", "a", 1);
assert_suffix_max!("ab", "ab", 2);
assert_suffix_min!("ba", "ba", 2);
assert_suffix_max!("ba", "b", 1);
assert_suffix_min!("abc", "a", 1);
assert_suffix_max!("abc", "abc", 3);
assert_suffix_min!("acb", "a", 1);
assert_suffix_max!("acb", "ac", 2);
assert_suffix_min!("cba", "cba", 3);
assert_suffix_max!("cba", "c", 1);
assert_suffix_min!("abcabc", "abca", 3);
assert_suffix_max!("abcabc", "abcabc", 3);
assert_suffix_min!("abcabcabc", "abcabca", 3);
assert_suffix_max!("abcabcabc", "abcabcabc", 3);
assert_suffix_min!("abczz", "a", 1);
assert_suffix_max!("abczz", "abczz", 5);
assert_suffix_min!("zzabc", "zza", 3);
assert_suffix_max!("zzabc", "zz", 1);
assert_suffix_min!("aaa", "aaa", 1);
assert_suffix_max!("aaa", "aaa", 1);
}
#[cfg(not(miri))]
quickcheck::quickcheck! {
fn qc_suffix_forward_maximal(bytes: Vec<u8>) -> bool {
if bytes.is_empty() {
return true;
}
let (got, _) = get_suffix_forward(&bytes, SuffixKind::Maximal);
let expected = naive_maximal_suffix_forward(&bytes);
got == expected
}
fn qc_suffix_reverse_maximal(bytes: Vec<u8>) -> bool {
if bytes.is_empty() {
return true;
}
let (got, _) = get_suffix_reverse(&bytes, SuffixKind::Maximal);
let expected = naive_maximal_suffix_reverse(&bytes);
expected == got
}
}
// This is a regression test caught by quickcheck that exercised a bug in
// the reverse small period handling. The bug was that we were using 'if j
// == shift' to determine if a match occurred, but the correct guard is 'if
// j >= shift', which matches the corresponding guard in the forward impl.
#[test]
fn regression_rev_small_period() {
let rfind = |h, n| FinderRev::new(n).rfind(h, n);
let haystack = "ababaz";
let needle = "abab";
assert_eq!(Some(0), rfind(haystack.as_bytes(), needle.as_bytes()));
}
}
|