-
Notifications
You must be signed in to change notification settings - Fork 1
/
xstring.go
818 lines (689 loc) · 18.1 KB
/
xstring.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
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
/*
* Copyright 2021 chenquan
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package xstring
import (
"errors"
"fmt"
"github.com/chenquan/go-pkg/internal/hack"
"github.com/chenquan/go-pkg/xmath"
"math"
"math/rand"
"regexp"
"strings"
"unicode"
"unicode/utf8"
)
const (
empty = "" // 空字符串
indexNotFound = -1
)
var (
// ErrDecodeChar error occurred on char decoding
ErrDecodeChar = errors.New("error occurred on char decoding")
)
// Char is rune Alias.
type Char = rune
// PadLeftChar left pad a string with a specified character in a larger string (specified size).
// if the size is less than the param string, the param string is returned.
// NOTE: size is unicode size.
func PadLeftChar(s string, size int, ch Char) string {
return padCharLeftOrRight(s, size, ch, true)
}
// PadLeftSpace left pad a string with space character(' ') in a larger string(specified size).
// if the size is less than the param string, the param string is returned.
// NOTE: size is unicode size.
func PadLeftSpace(s string, size int) string {
return PadLeftChar(s, size, ' ')
}
// PadRightChar right pad a string with a specified character in a larger string(specified size).
// if the size is less than the param string, the param string is returned.
// NOTE: size is unicode size.
func PadRightChar(s string, size int, ch Char) string {
return padCharLeftOrRight(s, size, ch, false)
}
// PadRightSpace right pad a string with space character(' ') in a large string(specified size).
// if the size is less than the param string, the param string is returned.
// NOTE: size is unicode size.
func PadRightSpace(s string, size int) string {
return PadRightChar(s, size, ' ')
}
// PadCenterChar center pad a string with a specified character in a larger string(specified size).
// if the size is less than the param string, the param string is returned.
// NOTE: size is unicode size.
func PadCenterChar(s string, size int, ch Char) string {
if size <= 0 {
return s
}
length := Len(s)
pads := size - length
if pads <= 0 {
return s
}
// pad left
leftPads := pads / 2
if leftPads > 0 {
s = padRawLeftChar(s, ch, leftPads)
}
// pad right
rightPads := size - leftPads - length
if rightPads > 0 {
s = padRawRightChar(s, ch, rightPads)
}
return s
}
// PadCenterSpace center pad a string with space character(' ') in a larger string(specified size).
// if the size is less than the param string, the param string is returned.
// NOTE: size is unicode size.
func PadCenterSpace(s string, size int) string {
return PadCenterChar(s, size, ' ')
}
func padCharLeftOrRight(s string, size int, ch Char, isLeft bool) string {
if size <= 0 {
return s
}
pads := size - Len(s)
if pads <= 0 {
return s
}
if isLeft {
return padRawLeftChar(s, ch, pads)
}
return padRawRightChar(s, ch, pads)
}
func padRawLeftChar(s string, ch Char, padSize int) string {
return RepeatChar(ch, padSize) + s
}
func padRawRightChar(s string, ch Char, padSize int) string {
return s + RepeatChar(ch, padSize)
}
// RepeatChar returns padding using the specified delimiter repeated to a given length.
func RepeatChar(ch Char, repeat int) string {
if repeat <= 0 {
return ""
}
sb := strings.Builder{}
sb.Grow(repeat)
for i := 0; i < repeat; i++ {
sb.WriteRune(ch)
}
return sb.String()
}
// RemoveChar removes all occurrences of a specified character from the string.
func RemoveChar(s string, rmVal Char) string {
if s == "" {
return s
}
sb := strings.Builder{}
sb.Grow(len(s) / 2)
for _, v := range s {
if v != rmVal {
sb.WriteRune(v)
}
}
return sb.String()
}
// RemoveString removes all occurrences of a substring from the string.
func RemoveString(s, rmStr string) string {
if s == "" || rmStr == "" {
return s
}
return strings.ReplaceAll(s, rmStr, "")
}
// Rotate rotates(circular shift) a string of shift characters.
func Rotate(s string, shift int) string {
if shift == 0 {
return s
}
sLen := len(s)
if sLen == 0 {
return s
}
shiftMod := shift % sLen
if shiftMod == 0 {
return s
}
offset := -(shiftMod)
sb := strings.Builder{}
sb.Grow(sLen)
_, _ = sb.WriteString(Right(s, offset))
_, _ = sb.WriteString(Left(s, offset))
return sb.String()
}
// Sub returns substring from specified string avoiding panics with index start and end.
// start, end are based on unicode(utf8) count.
func Sub(s string, start, end int) string {
return sub(s, start, end)
}
// Left returns substring from specified string avoiding panics with start.
// start, end are based on unicode(utf8) count.
func Left(s string, end int) string {
return sub(s, 0, end)
}
// Right returns substring from specified string avoiding panics with end.
// start, end are based on unicode(utf8) count.
func Right(s string, start int) string {
return sub(s, start, math.MaxInt)
}
func sub(s string, start, end int) string {
if s == "" {
return ""
}
unicodeLen := Len(s)
// end
if end < 0 {
end += unicodeLen
}
if end > unicodeLen {
end = unicodeLen
}
// start
if start < 0 {
start += unicodeLen
}
if start > end {
return ""
}
// start <= end
if start < 0 {
start = 0
}
if end < 0 {
end = 0
}
if start == 0 && end == unicodeLen {
return s
}
sb := strings.Builder{}
sb.Grow(end - start)
runeIndex := 0
for _, v := range s {
if runeIndex >= end {
break
}
if runeIndex >= start {
sb.WriteRune(v)
}
runeIndex++
}
return sb.String()
}
// MustReverse reverses a string, panics when error happens.
func MustReverse(s string) string {
result, err := Reverse(s)
if err != nil {
panic(err)
}
return result
}
// Reverse reverses a string with error status returned.
func Reverse(s string) (string, error) {
if s == "" {
return s, nil
}
src := hack.StringToBytes(s)
dst := make([]byte, len(s))
srcIndex := len(s)
dstIndex := 0
for srcIndex > 0 {
r, n := utf8.DecodeLastRune(src[:srcIndex])
if r == utf8.RuneError {
return hack.BytesToString(dst), ErrDecodeChar
}
utf8.EncodeRune(dst[dstIndex:], r)
srcIndex -= n
dstIndex += n
}
return hack.BytesToString(dst), nil
}
// Shuffle shuffles runes in a string and returns.
func Shuffle(s string) string {
if s == "" {
return s
}
runes := []rune(s)
index := 0
for i := len(runes) - 1; i > 0; i-- {
index = rand.Intn(i + 1)
if i != index {
runes[i], runes[index] = runes[index], runes[i]
}
}
return string(runes)
}
// ContainsAnySubstrings returns whether s contains any of substring in slice.
func ContainsAnySubstrings(s string, subs []string) bool {
if len(subs) == 0 {
return false
}
for _, v := range subs {
if strings.Contains(s, v) {
return true
}
}
return false
}
// IsAlpha checks if the string contains only unicode letters.
func IsAlpha(s string) bool {
if s == empty {
return false
}
for _, v := range s {
if !unicode.IsLetter(v) {
return false
}
}
return true
}
// IsAlphanumeric checks if the string contains only Unicode letters or digits.
func IsAlphanumeric(s string) bool {
if s == empty {
return false
}
for _, v := range s {
if !isAlphanumeric(v) {
return false
}
}
return true
}
func isAlphanumeric(v Char) bool {
return unicode.IsDigit(v) || unicode.IsLetter(v)
}
// IsNumeric checks if the string contains only digits. A decimal point is not a digit and returns false.
func IsNumeric(s string) bool {
if s == empty {
return false
}
for _, v := range s {
if !unicode.IsDigit(v) {
return false
}
}
return true
}
// IsEmpty returns ture if s is empty.
func IsEmpty(s string) bool {
return s == empty
}
// IsNotEmpty returns ture if s isn't empty.
func IsNotEmpty(s string) bool {
return !IsEmpty(s)
}
// IsAnyEmpty returns ture if strings exist empty of string.
func IsAnyEmpty(strings ...string) bool {
if len(strings) == 0 {
return true
}
for _, s := range strings {
if IsEmpty(s) {
return true
}
}
return false
}
// IsNoneEmpty returns false if strings exist empty of string.
func IsNoneEmpty(strings ...string) bool {
return !IsAnyEmpty(strings...)
}
// IsBlank returns ture if the string is empty or has a length of 0 or consists of whitespace.
func IsBlank(s string) bool {
if s == empty {
return true
}
for _, c := range s {
if !unicode.IsSpace(c) {
return false
}
}
return true
}
//IsNotBlank returns false if the string is empty or has a length of 0 or consists of whitespace.
func IsNotBlank(s string) bool {
return !IsBlank(s)
}
// IsAnyBlank returns true if there is a blank string in strings.
func IsAnyBlank(strings ...string) bool {
if len(strings) == 0 {
return true
}
for _, s := range strings {
if IsBlank(s) {
return true
}
}
return false
}
// IsNoneBlank returns true if there is no blank string in strings.
func IsNoneBlank(strings ...string) bool {
return !IsAnyBlank(strings...)
}
// TrimSpace returns a slice of the string s, with all leading
// and trailing white space removed, as defined by Unicode.
func TrimSpace(s string) string {
return strings.TrimSpace(s)
}
// Trim returns a slice of the string s with all leading and
// trailing Unicode code points contained in cutSet removed.
func Trim(s string, cutSet string) string {
if IsEmpty(s) {
return s
}
return strings.Trim(s, cutSet)
}
// TrimLeft returns a slice of the string s with all leading
// Unicode code points contained in cutset removed.
//
// To remove a prefix, use TrimPrefix instead.
func TrimLeft(str string, stripStr string) string {
return strings.TrimLeft(str, stripStr)
}
// TrimRight returns a slice of the string s, with all trailing
// Unicode code points contained in cutset removed.
//
// To remove a suffix, use TrimSuffix instead.
func TrimRight(str string, stripStr string) string {
return strings.TrimRight(str, stripStr)
}
// Contains reports whether substr is within s.
func Contains(s string, searchChar string) bool {
if s == empty {
return false
}
return strings.Contains(s, searchChar)
}
// IsNumerical returns ture if a numerical.
func IsNumerical(s string) bool {
reg, _ := regexp.Compile(`^\d+.?\d*$`)
return reg.MatchString(s)
}
// IndexOfDifference compares all strings in an array and returns the index at which the
// string begin to differ.
func IndexOfDifference(strings ...string) int {
stringsLen := len(strings)
if len(strings) > 1 {
allStringsNull := true
shortestStrLen := 2<<32 - 1
longestStrLen := 0
firstDiff := 0
for ; firstDiff < stringsLen; firstDiff++ {
allStringsNull = false
runes := []rune(strings[firstDiff])
shortestStrLen = xmath.MinInt(len(runes), shortestStrLen)
longestStrLen = xmath.MaxInt(len(runes), longestStrLen)
}
if allStringsNull || longestStrLen == 0 {
return indexNotFound
} else if shortestStrLen == 0 {
return 0
} else {
firstDiff = -1
runes := []rune(strings[0])
for stringPos := 0; stringPos < shortestStrLen; stringPos++ {
comparisonChar := runes[stringPos]
for arrayPos := 1; arrayPos < stringsLen; arrayPos++ {
if []rune(strings[arrayPos])[stringPos] != comparisonChar {
firstDiff = stringPos
break
}
}
if firstDiff != -1 {
break
}
}
if firstDiff == -1 && shortestStrLen != longestStrLen {
return shortestStrLen
}
return firstDiff
}
} else {
return indexNotFound
}
}
// IndexOfDifferenceWithTwoStr Compares two string, and returns the index at which the
// string begin to differ.
func IndexOfDifferenceWithTwoStr(a, b string) int {
if a == b {
return indexNotFound
}
aRunes := []rune(a)
bRunes := []rune(b)
aLen := len(aRunes)
bLen := len(bRunes)
i := 0
for ; i < aLen && i < bLen && aRunes[i] == bRunes[i]; i++ {
}
if i >= aLen && i >= bLen {
return indexNotFound
}
return i
}
// Difference Compares two Strings, and returns the portion where they differ.
// More precisely, return the remainder of the second String,
// starting from where it's different from the first. This means that
// the difference between "abc" and "ab" is the empty String and not "c".
func Difference(a, b string) string {
i := IndexOfDifferenceWithTwoStr(a, b)
if i == -1 {
return empty
}
runes := []rune(b)
return string(runes[i:])
}
// CommonPrefix returns common prefix.
func CommonPrefix(strings ...string) string {
if len(strings) != 0 {
smallestIndexOfDiff := IndexOfDifference(strings...)
if smallestIndexOfDiff == -1 {
return strings[0]
}
if smallestIndexOfDiff == 0 {
return empty
}
runes := []rune(strings[0])
return string(runes[0:smallestIndexOfDiff])
}
return empty
}
// Index returns the index of the first instance of substr in s, or -1 if substr is not present in s.
func Index(s, substr string) int {
return strings.Index(s, substr)
}
// IndexAny returns the index of the first instance of any Unicode code point
// from chars in s, or -1 if no Unicode code point from chars is present in s.
func IndexAny(s, chars string) int {
return strings.IndexAny(s, chars)
}
// ContainsIgnoreCase checks if string contains a search string irrespective of case.
func ContainsIgnoreCase(str, searchStr string) bool {
length := Len(searchStr)
max := Len(str) - length
for i := 0; i <= max; i++ {
if RegionMatches(str, true, i, searchStr, 0, length) {
return true
}
}
return false
}
// RegionMatches Green implementation of regionMatches.
func RegionMatches(str string, ignoreCase bool, thisStart int, substr string, start int, length int) bool {
if ignoreCase {
str = strings.ToLower(str)
substr = strings.ToLower(substr)
}
// Check the validity of the parameters
if thisStart < 0 || start < 0 || length < 0 {
return false
}
// The length of the remaining part of the string
thisRetLen := Len(str) - thisStart
subRetLen := Len(substr) - start
if thisRetLen < length || subRetLen < length {
return false
}
strToRunes := []rune(str)
substrToRunes := []rune(substr)
for ; length > 0; length-- {
c1 := strToRunes[thisStart]
c2 := substrToRunes[start]
thisStart++
start++
if c1 == c2 {
continue
}
if ignoreCase {
c1 = unicode.ToUpper(c1)
c2 = unicode.ToUpper(c2)
if c1 == c2 {
continue
}
if unicode.ToLower(c1) == unicode.ToLower(c2) {
continue
}
}
return false
}
return true
}
// Len returns str length.
func Len(str string) int {
return utf8.RuneCountInString(str)
}
// DefaultIfBlank returns default String if str is blank.
func DefaultIfBlank(str, defaultStr string) string {
if IsBlank(str) {
return defaultStr
}
return str
}
// DefaultIfEmpty returns default String if str is empty.
func DefaultIfEmpty(str, defaultStr string) string {
if IsEmpty(str) {
return defaultStr
}
return str
}
// DeleteWhitespace deletes whitespace.
func DeleteWhitespace(str string) string {
if str == empty {
return empty
}
strLen := Len(str)
builder := strings.Builder{}
builder.Grow(strLen)
for _, r := range str {
if !unicode.IsSpace(r) {
builder.WriteRune(r)
}
}
if builder.Len() == strLen {
return str
}
if builder.Len() == 0 {
return empty
}
return builder.String()
}
// EndsWith returns true if the str
func EndsWith(str, suffix string, ignoreCase bool) bool {
if str == suffix {
return true
}
strLen := Len(str)
suffixLen := Len(suffix)
if suffixLen > strLen {
return false
}
strOffset := strLen - suffixLen
return RegionMatches(str, ignoreCase, strOffset, suffix, 0, suffixLen)
}
// EndsWithIgnoreCase case-insensitive check if a str ends with a specified suffix.
func EndsWithIgnoreCase(str, suffix string) bool {
return EndsWith(str, suffix, true)
}
// EndsWithCase case-insensitive check if a str ends with a specified suffix.
func EndsWithCase(str, suffix string) bool {
return EndsWith(str, suffix, false)
}
// EndsWithAny check if a sequence ends with any of an array of specified strings.
func EndsWithAny(sequence string, searchStrings ...string) bool {
if IsEmpty(sequence) || len(searchStrings) == 0 {
return false
}
for _, str := range searchStrings {
if EndsWith(sequence, str, false) {
return true
}
}
return false
}
// EqualsIgnoreCase returns true if the two strings are equal ignoring case.
func EqualsIgnoreCase(str1, str2 string) bool {
if str1 == str2 {
return true
}
return RegionMatches(str1, true, 0, str2, 0, Len(str1))
}
// EqualsAny returns ture if str exists in strings.
func EqualsAny(str1 string, strings ...string) bool {
if len(strings) != 0 {
for _, str2 := range strings {
if str1 == str2 {
return true
}
}
}
return false
}
// Abbreviate abbreviates a string using ellipses or another given string.
func Abbreviate(str, abbrevMarker string, offset, maxWidth int) (string, error) {
if IsNotEmpty(str) && abbrevMarker == empty && maxWidth > 0 {
return Sub(str, 0, maxWidth), nil
} else if IsAnyEmpty(str, abbrevMarker) {
// 其中有一个字符串为,则直接返回原字符串
return str, nil
}
abbrevMarkerLen := Len(abbrevMarker)
// 最小缩减宽度
minAbbrevWidth := abbrevMarkerLen + 1
if maxWidth < minAbbrevWidth {
return empty, fmt.Errorf("minimum abbreviation width is %d", minAbbrevWidth)
}
minAbbrevWidthOffset := 2*abbrevMarkerLen + 1
strLen := Len(str)
if strLen <= maxWidth {
return str, nil
}
if offset > strLen {
offset = strLen
}
if strLen-offset < maxWidth-abbrevMarkerLen {
offset = strLen - (maxWidth - abbrevMarkerLen)
}
if offset <= abbrevMarkerLen+1 {
return Sub(str, 0, maxWidth-abbrevMarkerLen) + abbrevMarker, nil
}
if maxWidth < minAbbrevWidthOffset {
return empty, fmt.Errorf("minimum abbreviation width with offset is %d", minAbbrevWidthOffset)
}
if offset+maxWidth-abbrevMarkerLen < strLen {
substr, err := Abbreviate(Sub(str, 0, offset), abbrevMarker, 0, maxWidth-abbrevMarkerLen)
if err == nil {
return abbrevMarker + substr, nil
}
return empty, err
}
return abbrevMarker + Sub(str, 0, strLen-(maxWidth-abbrevMarkerLen)), nil
}