-
Notifications
You must be signed in to change notification settings - Fork 9
/
exec_test.go
731 lines (689 loc) · 21.6 KB
/
exec_test.go
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
// Copyright 2010 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package regexp
import (
"bufio"
"compress/bzip2"
"fmt"
"io"
"os"
"path/filepath"
"matloob.io/regexp/syntax"
"strconv"
"strings"
"testing"
"unicode/utf8"
)
// TestRE2 tests this package's regexp API against test cases
// considered during RE2's exhaustive tests, which run all possible
// regexps over a given set of atoms and operators, up to a given
// complexity, over all possible strings over a given alphabet,
// up to a given size. Rather than try to link with RE2, we read a
// log file containing the test cases and the expected matches.
// The log file, re2-exhaustive.txt, is generated by running 'make log'
// in the open source RE2 distribution https://github.com/google/re2/.
//
// The test file format is a sequence of stanzas like:
//
// strings
// "abc"
// "123x"
// regexps
// "[a-z]+"
// 0-3;0-3
// -;-
// "([0-9])([0-9])([0-9])"
// -;-
// -;0-3 0-1 1-2 2-3
//
// The stanza begins by defining a set of strings, quoted
// using Go double-quote syntax, one per line. Then the
// regexps section gives a sequence of regexps to run on
// the strings. In the block that follows a regexp, each line
// gives the semicolon-separated match results of running
// the regexp on the corresponding string.
// Each match result is either a single -, meaning no match, or a
// space-separated sequence of pairs giving the match and
// submatch indices. An unmatched subexpression formats
// its pair as a single - (not illustrated above). For now
// each regexp run produces two match results, one for a
// ``full match'' that restricts the regexp to matching the entire
// string or nothing, and one for a ``partial match'' that gives
// the leftmost first match found in the string.
//
// Lines beginning with # are comments. Lines beginning with
// a capital letter are test names printed during RE2's test suite
// and are echoed into t but otherwise ignored.
//
// At time of writing, re2-exhaustive.txt is 59 MB but compresses to 385 kB,
// so we store re2-exhaustive.txt.bz2 in the repository and decompress it on the fly.
//
func TestRE2Search(t *testing.T) {
testRE2(t, "testdata/re2-search.txt")
}
func testRE2(t *testing.T, file string) {
f, err := os.Open(file)
if err != nil {
t.Fatal(err)
}
defer f.Close()
var txt io.Reader
if strings.HasSuffix(file, ".bz2") {
z := bzip2.NewReader(f)
txt = z
file = file[:len(file)-len(".bz2")] // for error messages
} else {
txt = f
}
lineno := 0
scanner := bufio.NewScanner(txt)
var (
str []string
input []string
inStrings bool
re *Regexp
refull *Regexp
nfail int
ncase int
)
for lineno := 1; scanner.Scan(); lineno++ {
line := scanner.Text()
switch {
case line == "":
t.Fatalf("%s:%d: unexpected blank line", file, lineno)
case line[0] == '#':
continue
case 'A' <= line[0] && line[0] <= 'Z':
// Test name.
t.Logf("%s\n", line)
continue
case line == "strings":
str = str[:0]
inStrings = true
case line == "regexps":
inStrings = false
case line[0] == '"':
q, err := strconv.Unquote(line)
if err != nil {
// Fatal because we'll get out of sync.
t.Fatalf("%s:%d: unquote %s: %v", file, lineno, line, err)
}
if inStrings {
str = append(str, q)
continue
}
// Is a regexp.
if len(input) != 0 {
t.Fatalf("%s:%d: out of sync: have %d strings left before %#q", file, lineno, len(input), q)
}
re, err = tryCompile(q)
if err != nil {
if err.Error() == "error parsing regexp: invalid escape sequence: `\\C`" {
// We don't and likely never will support \C; keep going.
continue
}
t.Errorf("%s:%d: compile %#q: %v", file, lineno, q, err)
if nfail++; nfail >= 100 {
t.Fatalf("stopping after %d errors", nfail)
}
continue
}
full := `\A(?:` + q + `)\z`
refull, err = tryCompile(full)
if err != nil {
// Fatal because q worked, so this should always work.
t.Fatalf("%s:%d: compile full %#q: %v", file, lineno, full, err)
}
input = str
case line[0] == '-' || '0' <= line[0] && line[0] <= '9':
// A sequence of match results.
ncase++
if re == nil {
// Failed to compile: skip results.
continue
}
if len(input) == 0 {
t.Fatalf("%s:%d: out of sync: no input remaining", file, lineno)
}
var text string
text, input = input[0], input[1:]
if !isSingleBytes(text) && strings.Contains(re.String(), `\B`) {
// RE2's \B considers every byte position,
// so it sees 'not word boundary' in the
// middle of UTF-8 sequences. This package
// only considers the positions between runes,
// so it disagrees. Skip those cases.
continue
}
res := strings.Split(line, ";")
if len(res) != len(run) {
t.Fatalf("%s:%d: have %d test results, want %d", file, lineno, len(res), len(run))
}
for i := range res {
have, suffix := run[i](re, refull, text)
want := parseResult(t, file, lineno, res[i])
if !same(have, want) {
t.Errorf("%s:%d: %#q%s.FindSubmatchIndex(%#q) = %v, want %v", file, lineno, re, suffix, text, have, want)
if nfail++; nfail >= 100 {
t.Fatalf("stopping after %d errors", nfail)
}
continue
}
b, suffix := match[i](re, refull, text)
if b != (want != nil) {
t.Errorf("%s:%d: %#q%s.MatchString(%#q) = %v, want %v", file, lineno, re, suffix, text, b, !b)
if nfail++; nfail >= 100 {
t.Fatalf("stopping after %d errors", nfail)
}
continue
}
}
default:
t.Fatalf("%s:%d: out of sync: %s\n", file, lineno, line)
}
}
if err := scanner.Err(); err != nil {
t.Fatalf("%s:%d: %v", file, lineno, err)
}
if len(input) != 0 {
t.Fatalf("%s:%d: out of sync: have %d strings left at EOF", file, lineno, len(input))
}
t.Logf("%d cases tested", ncase)
}
var run = []func(*Regexp, *Regexp, string) ([]int, string){
runFull,
runPartial,
runFullLongest,
runPartialLongest,
}
func runFull(re, refull *Regexp, text string) ([]int, string) {
refull.longest = false
return refull.FindStringSubmatchIndex(text), "[full]"
}
func runPartial(re, refull *Regexp, text string) ([]int, string) {
re.longest = false
return re.FindStringSubmatchIndex(text), ""
}
func runFullLongest(re, refull *Regexp, text string) ([]int, string) {
refull.longest = true
return refull.FindStringSubmatchIndex(text), "[full,longest]"
}
func runPartialLongest(re, refull *Regexp, text string) ([]int, string) {
re.longest = true
return re.FindStringSubmatchIndex(text), "[longest]"
}
var match = []func(*Regexp, *Regexp, string) (bool, string){
matchFull,
matchPartial,
matchFullLongest,
matchPartialLongest,
}
func matchFull(re, refull *Regexp, text string) (bool, string) {
refull.longest = false
return refull.MatchString(text), "[full]"
}
func matchPartial(re, refull *Regexp, text string) (bool, string) {
re.longest = false
return re.MatchString(text), ""
}
func matchFullLongest(re, refull *Regexp, text string) (bool, string) {
refull.longest = true
return refull.MatchString(text), "[full,longest]"
}
func matchPartialLongest(re, refull *Regexp, text string) (bool, string) {
re.longest = true
return re.MatchString(text), "[longest]"
}
func isSingleBytes(s string) bool {
for _, c := range s {
if c >= utf8.RuneSelf {
return false
}
}
return true
}
func tryCompile(s string) (re *Regexp, err error) {
// Protect against panic during Compile.
defer func() {
if r := recover(); r != nil {
err = fmt.Errorf("panic: %v", r)
}
}()
return Compile(s)
}
func parseResult(t *testing.T, file string, lineno int, res string) []int {
// A single - indicates no match.
if res == "-" {
return nil
}
// Otherwise, a space-separated list of pairs.
n := 1
for j := 0; j < len(res); j++ {
if res[j] == ' ' {
n++
}
}
out := make([]int, 2*n)
i := 0
n = 0
for j := 0; j <= len(res); j++ {
if j == len(res) || res[j] == ' ' {
// Process a single pair. - means no submatch.
pair := res[i:j]
if pair == "-" {
out[n] = -1
out[n+1] = -1
} else {
k := strings.Index(pair, "-")
if k < 0 {
t.Fatalf("%s:%d: invalid pair %s", file, lineno, pair)
}
lo, err1 := strconv.Atoi(pair[:k])
hi, err2 := strconv.Atoi(pair[k+1:])
if err1 != nil || err2 != nil || lo > hi {
t.Fatalf("%s:%d: invalid pair %s", file, lineno, pair)
}
out[n] = lo
out[n+1] = hi
}
n += 2
i = j + 1
}
}
return out
}
func same(x, y []int) bool {
if len(x) != len(y) {
return false
}
for i, xi := range x {
if xi != y[i] {
return false
}
}
return true
}
// TestFowler runs this package's regexp API against the
// POSIX regular expression tests collected by Glenn Fowler
// at http://www2.research.att.com/~astopen/testregex/testregex.html.
func TestFowler(t *testing.T) {
files, err := filepath.Glob("testdata/*.dat")
if err != nil {
t.Fatal(err)
}
for _, file := range files {
t.Log(file)
testFowler(t, file)
}
}
var notab = MustCompilePOSIX(`[^\t]+`)
func testFowler(t *testing.T, file string) {
f, err := os.Open(file)
if err != nil {
t.Error(err)
return
}
defer f.Close()
b := bufio.NewReader(f)
lineno := 0
lastRegexp := ""
Reading:
for {
lineno++
line, err := b.ReadString('\n')
if err != nil {
if err != io.EOF {
t.Errorf("%s:%d: %v", file, lineno, err)
}
break Reading
}
// http://www2.research.att.com/~astopen/man/man1/testregex.html
//
// INPUT FORMAT
// Input lines may be blank, a comment beginning with #, or a test
// specification. A specification is five fields separated by one
// or more tabs. NULL denotes the empty string and NIL denotes the
// 0 pointer.
if line[0] == '#' || line[0] == '\n' {
continue Reading
}
line = line[:len(line)-1]
field := notab.FindAllString(line, -1)
for i, f := range field {
if f == "NULL" {
field[i] = ""
}
if f == "NIL" {
t.Logf("%s:%d: skip: %s", file, lineno, line)
continue Reading
}
}
if len(field) == 0 {
continue Reading
}
// Field 1: the regex(3) flags to apply, one character per REG_feature
// flag. The test is skipped if REG_feature is not supported by the
// implementation. If the first character is not [BEASKLP] then the
// specification is a global control line. One or more of [BEASKLP] may be
// specified; the test will be repeated for each mode.
//
// B basic BRE (grep, ed, sed)
// E REG_EXTENDED ERE (egrep)
// A REG_AUGMENTED ARE (egrep with negation)
// S REG_SHELL SRE (sh glob)
// K REG_SHELL|REG_AUGMENTED KRE (ksh glob)
// L REG_LITERAL LRE (fgrep)
//
// a REG_LEFT|REG_RIGHT implicit ^...$
// b REG_NOTBOL lhs does not match ^
// c REG_COMMENT ignore space and #...\n
// d REG_SHELL_DOT explicit leading . match
// e REG_NOTEOL rhs does not match $
// f REG_MULTIPLE multiple \n separated patterns
// g FNM_LEADING_DIR testfnmatch only -- match until /
// h REG_MULTIREF multiple digit backref
// i REG_ICASE ignore case
// j REG_SPAN . matches \n
// k REG_ESCAPE \ to escape [...] delimiter
// l REG_LEFT implicit ^...
// m REG_MINIMAL minimal match
// n REG_NEWLINE explicit \n match
// o REG_ENCLOSED (|&) magic inside [@|&](...)
// p REG_SHELL_PATH explicit / match
// q REG_DELIMITED delimited pattern
// r REG_RIGHT implicit ...$
// s REG_SHELL_ESCAPED \ not special
// t REG_MUSTDELIM all delimiters must be specified
// u standard unspecified behavior -- errors not counted
// v REG_CLASS_ESCAPE \ special inside [...]
// w REG_NOSUB no subexpression match array
// x REG_LENIENT let some errors slide
// y REG_LEFT regexec() implicit ^...
// z REG_NULL NULL subexpressions ok
// $ expand C \c escapes in fields 2 and 3
// / field 2 is a regsubcomp() expression
// = field 3 is a regdecomp() expression
//
// Field 1 control lines:
//
// C set LC_COLLATE and LC_CTYPE to locale in field 2
//
// ?test ... output field 5 if passed and != EXPECTED, silent otherwise
// &test ... output field 5 if current and previous passed
// |test ... output field 5 if current passed and previous failed
// ; ... output field 2 if previous failed
// {test ... skip if failed until }
// } end of skip
//
// : comment comment copied as output NOTE
// :comment:test :comment: ignored
// N[OTE] comment comment copied as output NOTE
// T[EST] comment comment
//
// number use number for nmatch (20 by default)
flag := field[0]
switch flag[0] {
case '?', '&', '|', ';', '{', '}':
// Ignore all the control operators.
// Just run everything.
flag = flag[1:]
if flag == "" {
continue Reading
}
case ':':
i := strings.Index(flag[1:], ":")
if i < 0 {
t.Logf("skip: %s", line)
continue Reading
}
flag = flag[1+i+1:]
case 'C', 'N', 'T', '0', '1', '2', '3', '4', '5', '6', '7', '8', '9':
t.Logf("skip: %s", line)
continue Reading
}
// Can check field count now that we've handled the myriad comment formats.
if len(field) < 4 {
t.Errorf("%s:%d: too few fields: %s", file, lineno, line)
continue Reading
}
// Expand C escapes (a.k.a. Go escapes).
if strings.Contains(flag, "$") {
f := `"` + field[1] + `"`
if field[1], err = strconv.Unquote(f); err != nil {
t.Errorf("%s:%d: cannot unquote %s", file, lineno, f)
}
f = `"` + field[2] + `"`
if field[2], err = strconv.Unquote(f); err != nil {
t.Errorf("%s:%d: cannot unquote %s", file, lineno, f)
}
}
// Field 2: the regular expression pattern; SAME uses the pattern from
// the previous specification.
//
if field[1] == "SAME" {
field[1] = lastRegexp
}
lastRegexp = field[1]
// Field 3: the string to match.
text := field[2]
// Field 4: the test outcome...
ok, shouldCompile, shouldMatch, pos := parseFowlerResult(field[3])
if !ok {
t.Errorf("%s:%d: cannot parse result %#q", file, lineno, field[3])
continue Reading
}
// Field 5: optional comment appended to the report.
Testing:
// Run test once for each specified capital letter mode that we support.
for _, c := range flag {
pattern := field[1]
syn := syntax.POSIX | syntax.ClassNL
switch c {
default:
continue Testing
case 'E':
// extended regexp (what we support)
case 'L':
// literal
pattern = QuoteMeta(pattern)
}
for _, c := range flag {
switch c {
case 'i':
syn |= syntax.FoldCase
}
}
re, err := compile(pattern, syn, true)
if err != nil {
if shouldCompile {
t.Errorf("%s:%d: %#q did not compile", file, lineno, pattern)
}
continue Testing
}
if !shouldCompile {
t.Errorf("%s:%d: %#q should not compile", file, lineno, pattern)
continue Testing
}
match := re.MatchString(text)
if match != shouldMatch {
t.Errorf("%s:%d: %#q.Match(%#q) = %v, want %v", file, lineno, pattern, text, match, shouldMatch)
continue Testing
}
have := re.FindStringSubmatchIndex(text)
if (len(have) > 0) != match {
t.Errorf("%s:%d: %#q.Match(%#q) = %v, but %#q.FindSubmatchIndex(%#q) = %v", file, lineno, pattern, text, match, pattern, text, have)
continue Testing
}
if len(have) > len(pos) {
have = have[:len(pos)]
}
if !same(have, pos) {
t.Errorf("%s:%d: %#q.FindSubmatchIndex(%#q) = %v, want %v", file, lineno, pattern, text, have, pos)
}
}
}
}
func parseFowlerResult(s string) (ok, compiled, matched bool, pos []int) {
// Field 4: the test outcome. This is either one of the posix error
// codes (with REG_ omitted) or the match array, a list of (m,n)
// entries with m and n being first and last+1 positions in the
// field 3 string, or NULL if REG_NOSUB is in effect and success
// is expected. BADPAT is acceptable in place of any regcomp(3)
// error code. The match[] array is initialized to (-2,-2) before
// each test. All array elements from 0 to nmatch-1 must be specified
// in the outcome. Unspecified endpoints (offset -1) are denoted by ?.
// Unset endpoints (offset -2) are denoted by X. {x}(o:n) denotes a
// matched (?{...}) expression, where x is the text enclosed by {...},
// o is the expression ordinal counting from 1, and n is the length of
// the unmatched portion of the subject string. If x starts with a
// number then that is the return value of re_execf(), otherwise 0 is
// returned.
switch {
case s == "":
// Match with no position information.
ok = true
compiled = true
matched = true
return
case s == "NOMATCH":
// Match failure.
ok = true
compiled = true
matched = false
return
case 'A' <= s[0] && s[0] <= 'Z':
// All the other error codes are compile errors.
ok = true
compiled = false
return
}
compiled = true
var x []int
for s != "" {
var end byte = ')'
if len(x)%2 == 0 {
if s[0] != '(' {
ok = false
return
}
s = s[1:]
end = ','
}
i := 0
for i < len(s) && s[i] != end {
i++
}
if i == 0 || i == len(s) {
ok = false
return
}
var v = -1
var err error
if s[:i] != "?" {
v, err = strconv.Atoi(s[:i])
if err != nil {
ok = false
return
}
}
x = append(x, v)
s = s[i+1:]
}
if len(x)%2 != 0 {
ok = false
return
}
ok = true
matched = true
pos = x
return
}
var text []byte
func makeText(n int) []byte {
if len(text) >= n {
return text[:n]
}
text = make([]byte, n)
x := ^uint32(0)
for i := range text {
x += x
x ^= 1
if int32(x) < 0 {
x ^= 0x88888eef
}
if x%31 == 0 {
text[i] = '\n'
} else {
text[i] = byte(x%(0x7E+1-0x20) + 0x20)
}
}
return text
}
func benchmark(b *testing.B, re string, n int) {
r := MustCompile(re)
t := makeText(n)
b.ResetTimer()
b.SetBytes(int64(n))
for i := 0; i < b.N; i++ {
if r.Match(t) {
b.Fatal("match!")
}
}
}
const (
easy0 = "ABCDEFGHIJKLMNOPQRSTUVWXYZ$"
easy1 = "A[AB]B[BC]C[CD]D[DE]E[EF]F[FG]G[GH]H[HI]I[IJ]J$"
medium = "[XYZ]ABCDEFGHIJKLMNOPQRSTUVWXYZ$"
hard = "[ -~]*ABCDEFGHIJKLMNOPQRSTUVWXYZ$"
hard1 = "ABCE|CDEG|GHIK|HIJM|IJKN|KLMO|LMNP|PQRT|STUW|WXYA"
)
func BenchmarkMatchEasy0_32(b *testing.B) { benchmark(b, easy0, 32<<0) }
func BenchmarkMatchEasy0_1K(b *testing.B) { benchmark(b, easy0, 1<<10) }
func BenchmarkMatchEasy0_32K(b *testing.B) { benchmark(b, easy0, 32<<10) }
func BenchmarkMatchEasy0_1M(b *testing.B) { benchmark(b, easy0, 1<<20) }
func BenchmarkMatchEasy0_32M(b *testing.B) { benchmark(b, easy0, 32<<20) }
func BenchmarkMatchEasy1_32(b *testing.B) { benchmark(b, easy1, 32<<0) }
func BenchmarkMatchEasy1_1K(b *testing.B) { benchmark(b, easy1, 1<<10) }
func BenchmarkMatchEasy1_32K(b *testing.B) { benchmark(b, easy1, 32<<10) }
func BenchmarkMatchEasy1_1M(b *testing.B) { benchmark(b, easy1, 1<<20) }
func BenchmarkMatchEasy1_32M(b *testing.B) { benchmark(b, easy1, 32<<20) }
func BenchmarkMatchMedium_32(b *testing.B) { benchmark(b, medium, 32<<0) }
func BenchmarkMatchMedium_1K(b *testing.B) { benchmark(b, medium, 1<<10) }
func BenchmarkMatchMedium_32K(b *testing.B) { benchmark(b, medium, 32<<10) }
func BenchmarkMatchMedium_1M(b *testing.B) { benchmark(b, medium, 1<<20) }
func BenchmarkMatchMedium_32M(b *testing.B) { benchmark(b, medium, 32<<20) }
func BenchmarkMatchHard_32(b *testing.B) { benchmark(b, hard, 32<<0) }
func BenchmarkMatchHard_1K(b *testing.B) { benchmark(b, hard, 1<<10) }
func BenchmarkMatchHard_32K(b *testing.B) { benchmark(b, hard, 32<<10) }
func BenchmarkMatchHard_1M(b *testing.B) { benchmark(b, hard, 1<<20) }
func BenchmarkMatchHard_32M(b *testing.B) { benchmark(b, hard, 32<<20) }
func BenchmarkMatchHard1_32(b *testing.B) { benchmark(b, hard1, 32<<0) }
func BenchmarkMatchHard1_1K(b *testing.B) { benchmark(b, hard1, 1<<10) }
func BenchmarkMatchHard1_32K(b *testing.B) { benchmark(b, hard1, 32<<10) }
func BenchmarkMatchHard1_1M(b *testing.B) { benchmark(b, hard1, 1<<20) }
func BenchmarkMatchHard1_32M(b *testing.B) { benchmark(b, hard1, 32<<20) }
func TestLongest(t *testing.T) {
re, err := Compile(`a(|b)`)
if err != nil {
t.Fatal(err)
}
if g, w := re.FindString("ab"), "a"; g != w {
t.Errorf("first match was %q, want %q", g, w)
}
re.Longest()
if g, w := re.FindString("ab"), "ab"; g != w {
t.Errorf("longest match was %q, want %q", g, w)
}
}
// TestProgramTooLongForBacktrack tests that a regex which is too long
// for the backtracker still executes properly.
func TestProgramTooLongForBacktrack(t *testing.T) {
longRegex := MustCompile(`(one|two|three|four|five|six|seven|eight|nine|ten|eleven|twelve|thirteen|fourteen|fifteen|sixteen|seventeen|eighteen|nineteen|twenty|twentyone|twentytwo|twentythree|twentyfour|twentyfive|twentysix|twentyseven|twentyeight|twentynine|thirty|thirtyone|thirtytwo|thirtythree|thirtyfour|thirtyfive|thirtysix|thirtyseven|thirtyeight|thirtynine|forty|fortyone|fortytwo|fortythree|fortyfour|fortyfive|fortysix|fortyseven|fortyeight|fortynine|fifty|fiftyone|fiftytwo|fiftythree|fiftyfour|fiftyfive|fiftysix|fiftyseven|fiftyeight|fiftynine|sixty|sixtyone|sixtytwo|sixtythree|sixtyfour|sixtyfive|sixtysix|sixtyseven|sixtyeight|sixtynine|seventy|seventyone|seventytwo|seventythree|seventyfour|seventyfive|seventysix|seventyseven|seventyeight|seventynine|eighty|eightyone|eightytwo|eightythree|eightyfour|eightyfive|eightysix|eightyseven|eightyeight|eightynine|ninety|ninetyone|ninetytwo|ninetythree|ninetyfour|ninetyfive|ninetysix|ninetyseven|ninetyeight|ninetynine|onehundred)`)
if !longRegex.MatchString("two") {
t.Errorf("longRegex.MatchString(\"two\") was false, want true")
}
if longRegex.MatchString("xxx") {
t.Errorf("longRegex.MatchString(\"xxx\") was true, want false")
}
}