forked from golang/go
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathbytes.go
More file actions
1301 lines (1215 loc) · 31.7 KB
/
bytes.go
File metadata and controls
1301 lines (1215 loc) · 31.7 KB
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
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
// Copyright 2009 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 bytes implements functions for the manipulation of byte slices.
// It is analogous to the facilities of the strings package.
package bytes
import (
"internal/bytealg"
"unicode"
"unicode/utf8"
)
// Equal reports whether a and b
// are the same length and contain the same bytes.
// A nil argument is equivalent to an empty slice.
func Equal(a, b []byte) bool {
// Neither cmd/compile nor gccgo allocates for these string conversions.
return string(a) == string(b)
}
// Compare returns an integer comparing two byte slices lexicographically.
// The result will be 0 if a == b, -1 if a < b, and +1 if a > b.
// A nil argument is equivalent to an empty slice.
func Compare(a, b []byte) int {
return bytealg.Compare(a, b)
}
// explode splits s into a slice of UTF-8 sequences, one per Unicode code point (still slices of bytes),
// up to a maximum of n byte slices. Invalid UTF-8 sequences are chopped into individual bytes.
func explode(s []byte, n int) [][]byte {
if n <= 0 || n > len(s) {
n = len(s)
}
a := make([][]byte, n)
var size int
na := 0
for len(s) > 0 {
if na+1 >= n {
a[na] = s
na++
break
}
_, size = utf8.DecodeRune(s)
a[na] = s[0:size:size]
s = s[size:]
na++
}
return a[0:na]
}
// Count counts the number of non-overlapping instances of sep in s.
// If sep is an empty slice, Count returns 1 + the number of UTF-8-encoded code points in s.
func Count(s, sep []byte) int {
// special case
if len(sep) == 0 {
return utf8.RuneCount(s) + 1
}
if len(sep) == 1 {
return bytealg.Count(s, sep[0])
}
n := 0
for {
i := Index(s, sep)
if i == -1 {
return n
}
n++
s = s[i+len(sep):]
}
}
// Contains reports whether subslice is within b.
func Contains(b, subslice []byte) bool {
return Index(b, subslice) != -1
}
// ContainsAny reports whether any of the UTF-8-encoded code points in chars are within b.
func ContainsAny(b []byte, chars string) bool {
return IndexAny(b, chars) >= 0
}
// ContainsRune reports whether the rune is contained in the UTF-8-encoded byte slice b.
func ContainsRune(b []byte, r rune) bool {
return IndexRune(b, r) >= 0
}
// IndexByte returns the index of the first instance of c in b, or -1 if c is not present in b.
func IndexByte(b []byte, c byte) int {
return bytealg.IndexByte(b, c)
}
func indexBytePortable(s []byte, c byte) int {
for i, b := range s {
if b == c {
return i
}
}
return -1
}
// LastIndex returns the index of the last instance of sep in s, or -1 if sep is not present in s.
func LastIndex(s, sep []byte) int {
n := len(sep)
switch {
case n == 0:
return len(s)
case n == 1:
return LastIndexByte(s, sep[0])
case n == len(s):
if Equal(s, sep) {
return 0
}
return -1
case n > len(s):
return -1
}
// Rabin-Karp search from the end of the string
hashss, pow := bytealg.HashStrRevBytes(sep)
last := len(s) - n
var h uint32
for i := len(s) - 1; i >= last; i-- {
h = h*bytealg.PrimeRK + uint32(s[i])
}
if h == hashss && Equal(s[last:], sep) {
return last
}
for i := last - 1; i >= 0; i-- {
h *= bytealg.PrimeRK
h += uint32(s[i])
h -= pow * uint32(s[i+n])
if h == hashss && Equal(s[i:i+n], sep) {
return i
}
}
return -1
}
// LastIndexByte returns the index of the last instance of c in s, or -1 if c is not present in s.
func LastIndexByte(s []byte, c byte) int {
for i := len(s) - 1; i >= 0; i-- {
if s[i] == c {
return i
}
}
return -1
}
// IndexRune interprets s as a sequence of UTF-8-encoded code points.
// It returns the byte index of the first occurrence in s of the given rune.
// It returns -1 if rune is not present in s.
// If r is utf8.RuneError, it returns the first instance of any
// invalid UTF-8 byte sequence.
func IndexRune(s []byte, r rune) int {
switch {
case 0 <= r && r < utf8.RuneSelf:
return IndexByte(s, byte(r))
case r == utf8.RuneError:
for i := 0; i < len(s); {
r1, n := utf8.DecodeRune(s[i:])
if r1 == utf8.RuneError {
return i
}
i += n
}
return -1
case !utf8.ValidRune(r):
return -1
default:
var b [utf8.UTFMax]byte
n := utf8.EncodeRune(b[:], r)
return Index(s, b[:n])
}
}
// IndexAny interprets s as a sequence of UTF-8-encoded Unicode code points.
// It returns the byte index of the first occurrence in s of any of the Unicode
// code points in chars. It returns -1 if chars is empty or if there is no code
// point in common.
func IndexAny(s []byte, chars string) int {
if chars == "" {
// Avoid scanning all of s.
return -1
}
if len(s) == 1 {
r := rune(s[0])
if r >= utf8.RuneSelf {
// search utf8.RuneError.
for _, r = range chars {
if r == utf8.RuneError {
return 0
}
}
return -1
}
if bytealg.IndexByteString(chars, s[0]) >= 0 {
return 0
}
return -1
}
if len(chars) == 1 {
r := rune(chars[0])
if r >= utf8.RuneSelf {
r = utf8.RuneError
}
return IndexRune(s, r)
}
if len(s) > 8 {
if as, isASCII := makeASCIISet(chars); isASCII {
for i, c := range s {
if as.contains(c) {
return i
}
}
return -1
}
}
var width int
for i := 0; i < len(s); i += width {
r := rune(s[i])
if r < utf8.RuneSelf {
if bytealg.IndexByteString(chars, s[i]) >= 0 {
return i
}
width = 1
continue
}
r, width = utf8.DecodeRune(s[i:])
if r != utf8.RuneError {
// r is 2 to 4 bytes
if len(chars) == width {
if chars == string(r) {
return i
}
continue
}
// Use bytealg.IndexString for performance if available.
if bytealg.MaxLen >= width {
if bytealg.IndexString(chars, string(r)) >= 0 {
return i
}
continue
}
}
for _, ch := range chars {
if r == ch {
return i
}
}
}
return -1
}
// LastIndexAny interprets s as a sequence of UTF-8-encoded Unicode code
// points. It returns the byte index of the last occurrence in s of any of
// the Unicode code points in chars. It returns -1 if chars is empty or if
// there is no code point in common.
func LastIndexAny(s []byte, chars string) int {
if chars == "" {
// Avoid scanning all of s.
return -1
}
if len(s) > 8 {
if as, isASCII := makeASCIISet(chars); isASCII {
for i := len(s) - 1; i >= 0; i-- {
if as.contains(s[i]) {
return i
}
}
return -1
}
}
if len(s) == 1 {
r := rune(s[0])
if r >= utf8.RuneSelf {
for _, r = range chars {
if r == utf8.RuneError {
return 0
}
}
return -1
}
if bytealg.IndexByteString(chars, s[0]) >= 0 {
return 0
}
return -1
}
if len(chars) == 1 {
cr := rune(chars[0])
if cr >= utf8.RuneSelf {
cr = utf8.RuneError
}
for i := len(s); i > 0; {
r, size := utf8.DecodeLastRune(s[:i])
i -= size
if r == cr {
return i
}
}
return -1
}
for i := len(s); i > 0; {
r := rune(s[i-1])
if r < utf8.RuneSelf {
if bytealg.IndexByteString(chars, s[i-1]) >= 0 {
return i - 1
}
i--
continue
}
r, size := utf8.DecodeLastRune(s[:i])
i -= size
if r != utf8.RuneError {
// r is 2 to 4 bytes
if len(chars) == size {
if chars == string(r) {
return i
}
continue
}
// Use bytealg.IndexString for performance if available.
if bytealg.MaxLen >= size {
if bytealg.IndexString(chars, string(r)) >= 0 {
return i
}
continue
}
}
for _, ch := range chars {
if r == ch {
return i
}
}
}
return -1
}
// Generic split: splits after each instance of sep,
// including sepSave bytes of sep in the subslices.
func genSplit(s, sep []byte, sepSave, n int) [][]byte {
if n == 0 {
return nil
}
if len(sep) == 0 {
return explode(s, n)
}
if n < 0 {
n = Count(s, sep) + 1
}
if n > len(s)+1 {
n = len(s) + 1
}
a := make([][]byte, n)
n--
i := 0
for i < n {
m := Index(s, sep)
if m < 0 {
break
}
a[i] = s[: m+sepSave : m+sepSave]
s = s[m+len(sep):]
i++
}
a[i] = s
return a[:i+1]
}
// SplitN slices s into subslices separated by sep and returns a slice of
// the subslices between those separators.
// If sep is empty, SplitN splits after each UTF-8 sequence.
// The count determines the number of subslices to return:
//
// n > 0: at most n subslices; the last subslice will be the unsplit remainder.
// n == 0: the result is nil (zero subslices)
// n < 0: all subslices
//
// To split around the first instance of a separator, see Cut.
func SplitN(s, sep []byte, n int) [][]byte { return genSplit(s, sep, 0, n) }
// SplitAfterN slices s into subslices after each instance of sep and
// returns a slice of those subslices.
// If sep is empty, SplitAfterN splits after each UTF-8 sequence.
// The count determines the number of subslices to return:
//
// n > 0: at most n subslices; the last subslice will be the unsplit remainder.
// n == 0: the result is nil (zero subslices)
// n < 0: all subslices
func SplitAfterN(s, sep []byte, n int) [][]byte {
return genSplit(s, sep, len(sep), n)
}
// Split slices s into all subslices separated by sep and returns a slice of
// the subslices between those separators.
// If sep is empty, Split splits after each UTF-8 sequence.
// It is equivalent to SplitN with a count of -1.
//
// To split around the first instance of a separator, see Cut.
func Split(s, sep []byte) [][]byte { return genSplit(s, sep, 0, -1) }
// SplitAfter slices s into all subslices after each instance of sep and
// returns a slice of those subslices.
// If sep is empty, SplitAfter splits after each UTF-8 sequence.
// It is equivalent to SplitAfterN with a count of -1.
func SplitAfter(s, sep []byte) [][]byte {
return genSplit(s, sep, len(sep), -1)
}
var asciiSpace = [256]uint8{'\t': 1, '\n': 1, '\v': 1, '\f': 1, '\r': 1, ' ': 1}
// Fields interprets s as a sequence of UTF-8-encoded code points.
// It splits the slice s around each instance of one or more consecutive white space
// characters, as defined by unicode.IsSpace, returning a slice of subslices of s or an
// empty slice if s contains only white space.
func Fields(s []byte) [][]byte {
// First count the fields.
// This is an exact count if s is ASCII, otherwise it is an approximation.
n := 0
wasSpace := 1
// setBits is used to track which bits are set in the bytes of s.
setBits := uint8(0)
for i := 0; i < len(s); i++ {
r := s[i]
setBits |= r
isSpace := int(asciiSpace[r])
n += wasSpace & ^isSpace
wasSpace = isSpace
}
if setBits >= utf8.RuneSelf {
// Some runes in the input slice are not ASCII.
return FieldsFunc(s, unicode.IsSpace)
}
// ASCII fast path
a := make([][]byte, n)
na := 0
fieldStart := 0
i := 0
// Skip spaces in the front of the input.
for i < len(s) && asciiSpace[s[i]] != 0 {
i++
}
fieldStart = i
for i < len(s) {
if asciiSpace[s[i]] == 0 {
i++
continue
}
a[na] = s[fieldStart:i:i]
na++
i++
// Skip spaces in between fields.
for i < len(s) && asciiSpace[s[i]] != 0 {
i++
}
fieldStart = i
}
if fieldStart < len(s) { // Last field might end at EOF.
a[na] = s[fieldStart:len(s):len(s)]
}
return a
}
// FieldsFunc interprets s as a sequence of UTF-8-encoded code points.
// It splits the slice s at each run of code points c satisfying f(c) and
// returns a slice of subslices of s. If all code points in s satisfy f(c), or
// len(s) == 0, an empty slice is returned.
//
// FieldsFunc makes no guarantees about the order in which it calls f(c)
// and assumes that f always returns the same value for a given c.
func FieldsFunc(s []byte, f func(rune) bool) [][]byte {
// A span is used to record a slice of s of the form s[start:end].
// The start index is inclusive and the end index is exclusive.
type span struct {
start int
end int
}
spans := make([]span, 0, 32)
// Find the field start and end indices.
// Doing this in a separate pass (rather than slicing the string s
// and collecting the result substrings right away) is significantly
// more efficient, possibly due to cache effects.
start := -1 // valid span start if >= 0
for i := 0; i < len(s); {
size := 1
r := rune(s[i])
if r >= utf8.RuneSelf {
r, size = utf8.DecodeRune(s[i:])
}
if f(r) {
if start >= 0 {
spans = append(spans, span{start, i})
start = -1
}
} else {
if start < 0 {
start = i
}
}
i += size
}
// Last field might end at EOF.
if start >= 0 {
spans = append(spans, span{start, len(s)})
}
// Create subslices from recorded field indices.
a := make([][]byte, len(spans))
for i, span := range spans {
a[i] = s[span.start:span.end:span.end]
}
return a
}
// Join concatenates the elements of s to create a new byte slice. The separator
// sep is placed between elements in the resulting slice.
func Join(s [][]byte, sep []byte) []byte {
if len(s) == 0 {
return []byte{}
}
if len(s) == 1 {
// Just return a copy.
return append([]byte(nil), s[0]...)
}
n := len(sep) * (len(s) - 1)
for _, v := range s {
n += len(v)
}
b := make([]byte, n)
bp := copy(b, s[0])
for _, v := range s[1:] {
bp += copy(b[bp:], sep)
bp += copy(b[bp:], v)
}
return b
}
// HasPrefix tests whether the byte slice s begins with prefix.
func HasPrefix(s, prefix []byte) bool {
return len(s) >= len(prefix) && Equal(s[0:len(prefix)], prefix)
}
// HasSuffix tests whether the byte slice s ends with suffix.
func HasSuffix(s, suffix []byte) bool {
return len(s) >= len(suffix) && Equal(s[len(s)-len(suffix):], suffix)
}
// Map returns a copy of the byte slice s with all its characters modified
// according to the mapping function. If mapping returns a negative value, the character is
// dropped from the byte slice with no replacement. The characters in s and the
// output are interpreted as UTF-8-encoded code points.
func Map(mapping func(r rune) rune, s []byte) []byte {
// In the worst case, the slice can grow when mapped, making
// things unpleasant. But it's so rare we barge in assuming it's
// fine. It could also shrink but that falls out naturally.
maxbytes := len(s) // length of b
nbytes := 0 // number of bytes encoded in b
b := make([]byte, maxbytes)
for i := 0; i < len(s); {
wid := 1
r := rune(s[i])
if r >= utf8.RuneSelf {
r, wid = utf8.DecodeRune(s[i:])
}
r = mapping(r)
if r >= 0 {
rl := utf8.RuneLen(r)
if rl < 0 {
rl = len(string(utf8.RuneError))
}
if nbytes+rl > maxbytes {
// Grow the buffer.
maxbytes = maxbytes*2 + utf8.UTFMax
nb := make([]byte, maxbytes)
copy(nb, b[0:nbytes])
b = nb
}
nbytes += utf8.EncodeRune(b[nbytes:maxbytes], r)
}
i += wid
}
return b[0:nbytes]
}
// Repeat returns a new byte slice consisting of count copies of b.
//
// It panics if count is negative or if
// the result of (len(b) * count) overflows.
func Repeat(b []byte, count int) []byte {
if count == 0 {
return []byte{}
}
// Since we cannot return an error on overflow,
// we should panic if the repeat will generate
// an overflow.
// See Issue golang.org/issue/16237.
if count < 0 {
panic("bytes: negative Repeat count")
} else if len(b)*count/count != len(b) {
panic("bytes: Repeat count causes overflow")
}
nb := make([]byte, len(b)*count)
bp := copy(nb, b)
for bp < len(nb) {
copy(nb[bp:], nb[:bp])
bp *= 2
}
return nb
}
// ToUpper returns a copy of the byte slice s with all Unicode letters mapped to
// their upper case.
func ToUpper(s []byte) []byte {
isASCII, hasLower := true, false
for i := 0; i < len(s); i++ {
c := s[i]
if c >= utf8.RuneSelf {
isASCII = false
break
}
hasLower = hasLower || ('a' <= c && c <= 'z')
}
if isASCII { // optimize for ASCII-only byte slices.
if !hasLower {
// Just return a copy.
return append([]byte(""), s...)
}
b := make([]byte, len(s))
for i := 0; i < len(s); i++ {
c := s[i]
if 'a' <= c && c <= 'z' {
c -= 'a' - 'A'
}
b[i] = c
}
return b
}
return Map(unicode.ToUpper, s)
}
// ToLower returns a copy of the byte slice s with all Unicode letters mapped to
// their lower case.
func ToLower(s []byte) []byte {
isASCII, hasUpper := true, false
for i := 0; i < len(s); i++ {
c := s[i]
if c >= utf8.RuneSelf {
isASCII = false
break
}
hasUpper = hasUpper || ('A' <= c && c <= 'Z')
}
if isASCII { // optimize for ASCII-only byte slices.
if !hasUpper {
return append([]byte(""), s...)
}
b := make([]byte, len(s))
for i := 0; i < len(s); i++ {
c := s[i]
if 'A' <= c && c <= 'Z' {
c += 'a' - 'A'
}
b[i] = c
}
return b
}
return Map(unicode.ToLower, s)
}
// ToTitle treats s as UTF-8-encoded bytes and returns a copy with all the Unicode letters mapped to their title case.
func ToTitle(s []byte) []byte { return Map(unicode.ToTitle, s) }
// ToUpperSpecial treats s as UTF-8-encoded bytes and returns a copy with all the Unicode letters mapped to their
// upper case, giving priority to the special casing rules.
func ToUpperSpecial(c unicode.SpecialCase, s []byte) []byte {
return Map(c.ToUpper, s)
}
// ToLowerSpecial treats s as UTF-8-encoded bytes and returns a copy with all the Unicode letters mapped to their
// lower case, giving priority to the special casing rules.
func ToLowerSpecial(c unicode.SpecialCase, s []byte) []byte {
return Map(c.ToLower, s)
}
// ToTitleSpecial treats s as UTF-8-encoded bytes and returns a copy with all the Unicode letters mapped to their
// title case, giving priority to the special casing rules.
func ToTitleSpecial(c unicode.SpecialCase, s []byte) []byte {
return Map(c.ToTitle, s)
}
// ToValidUTF8 treats s as UTF-8-encoded bytes and returns a copy with each run of bytes
// representing invalid UTF-8 replaced with the bytes in replacement, which may be empty.
func ToValidUTF8(s, replacement []byte) []byte {
b := make([]byte, 0, len(s)+len(replacement))
invalid := false // previous byte was from an invalid UTF-8 sequence
for i := 0; i < len(s); {
c := s[i]
if c < utf8.RuneSelf {
i++
invalid = false
b = append(b, c)
continue
}
_, wid := utf8.DecodeRune(s[i:])
if wid == 1 {
i++
if !invalid {
invalid = true
b = append(b, replacement...)
}
continue
}
invalid = false
b = append(b, s[i:i+wid]...)
i += wid
}
return b
}
// isSeparator reports whether the rune could mark a word boundary.
// TODO: update when package unicode captures more of the properties.
func isSeparator(r rune) bool {
// ASCII alphanumerics and underscore are not separators
if r <= 0x7F {
switch {
case '0' <= r && r <= '9':
return false
case 'a' <= r && r <= 'z':
return false
case 'A' <= r && r <= 'Z':
return false
case r == '_':
return false
}
return true
}
// Letters and digits are not separators
if unicode.IsLetter(r) || unicode.IsDigit(r) {
return false
}
// Otherwise, all we can do for now is treat spaces as separators.
return unicode.IsSpace(r)
}
// Title treats s as UTF-8-encoded bytes and returns a copy with all Unicode letters that begin
// words mapped to their title case.
//
// Deprecated: The rule Title uses for word boundaries does not handle Unicode
// punctuation properly. Use golang.org/x/text/cases instead.
func Title(s []byte) []byte {
// Use a closure here to remember state.
// Hackish but effective. Depends on Map scanning in order and calling
// the closure once per rune.
prev := ' '
return Map(
func(r rune) rune {
if isSeparator(prev) {
prev = r
return unicode.ToTitle(r)
}
prev = r
return r
},
s)
}
// TrimLeftFunc treats s as UTF-8-encoded bytes and returns a subslice of s by slicing off
// all leading UTF-8-encoded code points c that satisfy f(c).
func TrimLeftFunc(s []byte, f func(r rune) bool) []byte {
i := indexFunc(s, f, false)
if i == -1 {
return nil
}
return s[i:]
}
// TrimRightFunc returns a subslice of s by slicing off all trailing
// UTF-8-encoded code points c that satisfy f(c).
func TrimRightFunc(s []byte, f func(r rune) bool) []byte {
i := lastIndexFunc(s, f, false)
if i >= 0 && s[i] >= utf8.RuneSelf {
_, wid := utf8.DecodeRune(s[i:])
i += wid
} else {
i++
}
return s[0:i]
}
// TrimFunc returns a subslice of s by slicing off all leading and trailing
// UTF-8-encoded code points c that satisfy f(c).
func TrimFunc(s []byte, f func(r rune) bool) []byte {
return TrimRightFunc(TrimLeftFunc(s, f), f)
}
// TrimPrefix returns s without the provided leading prefix string.
// If s doesn't start with prefix, s is returned unchanged.
func TrimPrefix(s, prefix []byte) []byte {
if HasPrefix(s, prefix) {
return s[len(prefix):]
}
return s
}
// TrimSuffix returns s without the provided trailing suffix string.
// If s doesn't end with suffix, s is returned unchanged.
func TrimSuffix(s, suffix []byte) []byte {
if HasSuffix(s, suffix) {
return s[:len(s)-len(suffix)]
}
return s
}
// IndexFunc interprets s as a sequence of UTF-8-encoded code points.
// It returns the byte index in s of the first Unicode
// code point satisfying f(c), or -1 if none do.
func IndexFunc(s []byte, f func(r rune) bool) int {
return indexFunc(s, f, true)
}
// LastIndexFunc interprets s as a sequence of UTF-8-encoded code points.
// It returns the byte index in s of the last Unicode
// code point satisfying f(c), or -1 if none do.
func LastIndexFunc(s []byte, f func(r rune) bool) int {
return lastIndexFunc(s, f, true)
}
// indexFunc is the same as IndexFunc except that if
// truth==false, the sense of the predicate function is
// inverted.
func indexFunc(s []byte, f func(r rune) bool, truth bool) int {
start := 0
for start < len(s) {
wid := 1
r := rune(s[start])
if r >= utf8.RuneSelf {
r, wid = utf8.DecodeRune(s[start:])
}
if f(r) == truth {
return start
}
start += wid
}
return -1
}
// lastIndexFunc is the same as LastIndexFunc except that if
// truth==false, the sense of the predicate function is
// inverted.
func lastIndexFunc(s []byte, f func(r rune) bool, truth bool) int {
for i := len(s); i > 0; {
r, size := rune(s[i-1]), 1
if r >= utf8.RuneSelf {
r, size = utf8.DecodeLastRune(s[0:i])
}
i -= size
if f(r) == truth {
return i
}
}
return -1
}
// asciiSet is a 32-byte value, where each bit represents the presence of a
// given ASCII character in the set. The 128-bits of the lower 16 bytes,
// starting with the least-significant bit of the lowest word to the
// most-significant bit of the highest word, map to the full range of all
// 128 ASCII characters. The 128-bits of the upper 16 bytes will be zeroed,
// ensuring that any non-ASCII character will be reported as not in the set.
// This allocates a total of 32 bytes even though the upper half
// is unused to avoid bounds checks in asciiSet.contains.
type asciiSet [8]uint32
// makeASCIISet creates a set of ASCII characters and reports whether all
// characters in chars are ASCII.
func makeASCIISet(chars string) (as asciiSet, ok bool) {
for i := 0; i < len(chars); i++ {
c := chars[i]
if c >= utf8.RuneSelf {
return as, false
}
as[c/32] |= 1 << (c % 32)
}
return as, true
}
// contains reports whether c is inside the set.
func (as *asciiSet) contains(c byte) bool {
return (as[c/32] & (1 << (c % 32))) != 0
}
// containsRune is a simplified version of strings.ContainsRune
// to avoid importing the strings package.
// We avoid bytes.ContainsRune to avoid allocating a temporary copy of s.
func containsRune(s string, r rune) bool {
for _, c := range s {
if c == r {
return true
}
}
return false
}
// Trim returns a subslice of s by slicing off all leading and
// trailing UTF-8-encoded code points contained in cutset.
func Trim(s []byte, cutset string) []byte {
if len(s) == 0 {
// This is what we've historically done.
return nil
}
if cutset == "" {
return s
}
if len(cutset) == 1 && cutset[0] < utf8.RuneSelf {
return trimLeftByte(trimRightByte(s, cutset[0]), cutset[0])
}
if as, ok := makeASCIISet(cutset); ok {
return trimLeftASCII(trimRightASCII(s, &as), &as)
}
return trimLeftUnicode(trimRightUnicode(s, cutset), cutset)
}
// TrimLeft returns a subslice of s by slicing off all leading
// UTF-8-encoded code points contained in cutset.
func TrimLeft(s []byte, cutset string) []byte {
if len(s) == 0 {
// This is what we've historically done.
return nil
}
if cutset == "" {
return s
}
if len(cutset) == 1 && cutset[0] < utf8.RuneSelf {
return trimLeftByte(s, cutset[0])
}
if as, ok := makeASCIISet(cutset); ok {
return trimLeftASCII(s, &as)
}
return trimLeftUnicode(s, cutset)
}
func trimLeftByte(s []byte, c byte) []byte {
for len(s) > 0 && s[0] == c {
s = s[1:]
}
if len(s) == 0 {
// This is what we've historically done.
return nil
}
return s
}
func trimLeftASCII(s []byte, as *asciiSet) []byte {
for len(s) > 0 {
if !as.contains(s[0]) {
break
}
s = s[1:]
}
if len(s) == 0 {
// This is what we've historically done.
return nil
}
return s
}
func trimLeftUnicode(s []byte, cutset string) []byte {
for len(s) > 0 {
r, n := rune(s[0]), 1
if r >= utf8.RuneSelf {
r, n = utf8.DecodeRune(s)
}
if !containsRune(cutset, r) {
break
}
s = s[n:]
}
if len(s) == 0 {
// This is what we've historically done.
return nil
}
return s
}
// TrimRight returns a subslice of s by slicing off all trailing
// UTF-8-encoded code points that are contained in cutset.
func TrimRight(s []byte, cutset string) []byte {
if len(s) == 0 || cutset == "" {
return s
}