-
Notifications
You must be signed in to change notification settings - Fork 10.3k
/
String.swift
1217 lines (1126 loc) · 42.7 KB
/
String.swift
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
//===----------------------------------------------------------------------===//
//
// This source file is part of the Swift.org open source project
//
// Copyright (c) 2014 - 2017 Apple Inc. and the Swift project authors
// Licensed under Apache License v2.0 with Runtime Library Exception
//
// See https://swift.org/LICENSE.txt for license information
// See https://swift.org/CONTRIBUTORS.txt for the list of Swift project authors
//
//===----------------------------------------------------------------------===//
import SwiftShims
/// A type that can represent a string as a collection of characters.
public protocol StringProtocol
: BidirectionalCollection,
TextOutputStream, TextOutputStreamable,
LosslessStringConvertible, ExpressibleByStringLiteral,
Hashable, Comparable
where Iterator.Element == Character {
associatedtype UTF8View : /*Bidirectional*/Collection
where UTF8View.Element == UInt8 // Unicode.UTF8.CodeUnit
associatedtype UTF16View : BidirectionalCollection
where UTF16View.Element == UInt16 // Unicode.UTF16.CodeUnit
associatedtype UnicodeScalarView : BidirectionalCollection
where UnicodeScalarView.Element == Unicode.Scalar
var utf8: UTF8View { get }
var utf16: UTF16View { get }
var unicodeScalars: UnicodeScalarView { get }
#if _runtime(_ObjC)
func hasPrefix(_ prefix: String) -> Bool
func hasSuffix(_ prefix: String) -> Bool
#endif
func lowercased() -> String
func uppercased() -> String
/// Creates a string from the given Unicode code units in the specified
/// encoding.
///
/// - Parameters:
/// - codeUnits: A collection of code units encoded in the ecoding
/// specified in `sourceEncoding`.
/// - sourceEncoding: The encoding in which `codeUnits` should be
/// interpreted.
init<C: Collection, Encoding: Unicode.Encoding>(
decoding codeUnits: C, as sourceEncoding: Encoding.Type
)
where C.Iterator.Element == Encoding.CodeUnit
/// Creates a string from the null-terminated, UTF-8 encoded sequence of
/// bytes at the given pointer.
///
/// - Parameter nullTerminatedUTF8: A pointer to a sequence of contiguous,
/// UTF-8 encoded bytes ending just before the first zero byte.
init(cString nullTerminatedUTF8: UnsafePointer<CChar>)
/// Creates a string from the null-terminated sequence of bytes at the given
/// pointer.
///
/// - Parameters:
/// - nullTerminatedCodeUnits: A pointer to a sequence of contiguous code
/// units in the encoding specified in `sourceEncoding`, ending just
/// before the first zero code unit.
/// - sourceEncoding: The encoding in which the code units should be
/// interpreted.
init<Encoding: Unicode.Encoding>(
decodingCString nullTerminatedCodeUnits: UnsafePointer<Encoding.CodeUnit>,
as sourceEncoding: Encoding.Type)
/// Calls the given closure with a pointer to the contents of the string,
/// represented as a null-terminated sequence of UTF-8 code units.
///
/// The pointer passed as an argument to `body` is valid only during the
/// execution of `withCString(_:)`. Do not store or return the pointer for
/// later use.
///
/// - Parameter body: A closure with a pointer parameter that points to a
/// null-terminated sequence of UTF-8 code units. If `body` has a return
/// value, that value is also used as the return value for the
/// `withCString(_:)` method. The pointer argument is valid only for the
/// duration of the method's execution.
/// - Returns: The return value, if any, of the `body` closure parameter.
func withCString<Result>(
_ body: (UnsafePointer<CChar>) throws -> Result) rethrows -> Result
/// Calls the given closure with a pointer to the contents of the string,
/// represented as a null-terminated sequence of code units.
///
/// The pointer passed as an argument to `body` is valid only during the
/// execution of `withCString(encodedAs:_:)`. Do not store or return the
/// pointer for later use.
///
/// - Parameters:
/// - body: A closure with a pointer parameter that points to a
/// null-terminated sequence of code units. If `body` has a return
/// value, that value is also used as the return value for the
/// `withCString(encodedAs:_:)` method. The pointer argument is valid
/// only for the duration of the method's execution.
/// - targetEncoding: The encoding in which the code units should be
/// interpreted.
/// - Returns: The return value, if any, of the `body` closure parameter.
func withCString<Result, Encoding: Unicode.Encoding>(
encodedAs targetEncoding: Encoding.Type,
_ body: (UnsafePointer<Encoding.CodeUnit>) throws -> Result
) rethrows -> Result
}
extension StringProtocol {
//@available(swift, deprecated: 3.2, obsoleted: 4.0, message: "Please use the StringProtocol itself")
//public var characters: Self { return self }
@available(swift, deprecated: 3.2, obsoleted: 4.0, renamed: "UTF8View.Index")
public typealias UTF8Index = UTF8View.Index
@available(swift, deprecated: 3.2, obsoleted: 4.0, renamed: "UTF16View.Index")
public typealias UTF16Index = UTF16View.Index
@available(swift, deprecated: 3.2, obsoleted: 4.0, renamed: "UnicodeScalarView.Index")
public typealias UnicodeScalarIndex = UnicodeScalarView.Index
}
/// A protocol that provides fast access to a known representation of String.
///
/// Can be used to specialize generic functions that would otherwise end up
/// doing grapheme breaking to vend individual characters.
internal protocol _SwiftStringView {
/// A `String`, having the same contents as `self`, that may be unsuitable for
/// long-term storage.
var _ephemeralContent : String { get }
/// A `String`, having the same contents as `self`, that is suitable for
/// long-term storage.
var _persistentContent : String { get }
}
extension _SwiftStringView {
var _ephemeralContent : String { return _persistentContent }
}
extension StringProtocol {
public // Used in the Foundation overlay
var _ephemeralString : String {
if _fastPath(self is _SwiftStringView) {
return (self as! _SwiftStringView)._ephemeralContent
}
return String(String.CharacterView(self))
}
}
extension String : _SwiftStringView {
var _persistentContent : String { return characters._persistentContent }
}
/// Call body with a pointer to zero-terminated sequence of
/// `TargetEncoding.CodeUnit` representing the same string as `source`, when
/// `source` is interpreted as being encoded with `SourceEncoding`.
internal func _withCString<
Source : Collection,
SourceEncoding : Unicode.Encoding,
TargetEncoding : Unicode.Encoding,
Result
>(
encodedAs targetEncoding: TargetEncoding.Type,
from source: Source,
encodedAs sourceEncoding: SourceEncoding.Type,
execute body : (UnsafePointer<TargetEncoding.CodeUnit>) throws -> Result
) rethrows -> Result
where Source.Iterator.Element == SourceEncoding.CodeUnit {
return try _withCStringAndLength(
encodedAs: targetEncoding,
from: source,
encodedAs: sourceEncoding) { p, _ in try body(p) }
}
@_semantics("optimize.sil.specialize.generic.partial.never")
internal func _withCStringAndLength<
Source : Collection,
SourceEncoding : Unicode.Encoding,
TargetEncoding : Unicode.Encoding,
Result
>(
encodedAs targetEncoding: TargetEncoding.Type,
from source: Source,
encodedAs sourceEncoding: SourceEncoding.Type,
execute body : (UnsafePointer<TargetEncoding.CodeUnit>, Int) throws -> Result
) rethrows -> Result
where Source.Iterator.Element == SourceEncoding.CodeUnit {
var targetLength = 0 // nul terminator
var i = source.makeIterator()
SourceEncoding.ForwardParser._parse(&i) {
targetLength += numericCast(
targetEncoding._transcode($0, from: SourceEncoding.self).count)
}
var a: [TargetEncoding.CodeUnit] = []
a.reserveCapacity(targetLength + 1)
i = source.makeIterator()
SourceEncoding.ForwardParser._parse(&i) {
a.append(
contentsOf: targetEncoding._transcode($0, from: SourceEncoding.self))
}
a.append(0)
return try body(a, targetLength)
}
extension _StringCore {
/// Invokes `body` on a null-terminated sequence of code units in the given
/// encoding corresponding to the substring in `bounds`.
internal func _withCSubstring<Result, TargetEncoding: Unicode.Encoding>(
in bounds: Range<Index>,
encoding targetEncoding: TargetEncoding.Type,
_ body: (UnsafePointer<TargetEncoding.CodeUnit>) throws -> Result
) rethrows -> Result {
return try _withCSubstringAndLength(in: bounds, encoding: targetEncoding) {
p,_ in try body(p)
}
}
@_semantics("optimize.sil.specialize.generic.partial.never")
internal func _withCSubstringAndLength<
Result, TargetEncoding: Unicode.Encoding
>(
in bounds: Range<Index>,
encoding targetEncoding: TargetEncoding.Type,
_ body: (UnsafePointer<TargetEncoding.CodeUnit>, Int) throws -> Result
) rethrows -> Result {
if _fastPath(hasContiguousStorage) {
defer { _fixLifetime(self) }
if isASCII {
return try Swift._withCStringAndLength(
encodedAs: targetEncoding,
from: UnsafeBufferPointer(start: startASCII, count: count)[bounds],
encodedAs: Unicode.ASCII.self,
execute: body
)
}
else {
return try Swift._withCStringAndLength(
encodedAs: targetEncoding,
from: UnsafeBufferPointer(start: startUTF16, count: count)[bounds],
encodedAs: Unicode.UTF16.self,
execute: body
)
}
}
return try Swift._withCStringAndLength(
encodedAs: targetEncoding,
from: self[bounds],
encodedAs: Unicode.UTF16.self,
execute: body
)
}
}
extension String {
/// Creates a string from the given Unicode code units in the specified
/// encoding.
///
/// - Parameters:
/// - codeUnits: A collection of code units encoded in the ecoding
/// specified in `sourceEncoding`.
/// - sourceEncoding: The encoding in which `codeUnits` should be
/// interpreted.
public init<C: Collection, Encoding: Unicode.Encoding>(
decoding codeUnits: C, as sourceEncoding: Encoding.Type
) where C.Iterator.Element == Encoding.CodeUnit {
let (b,_) = _StringBuffer.fromCodeUnits(
codeUnits, encoding: sourceEncoding, repairIllFormedSequences: true)
self = String(_StringCore(b!))
}
/// Creates a string from the null-terminated sequence of bytes at the given
/// pointer.
///
/// - Parameters:
/// - nullTerminatedCodeUnits: A pointer to a sequence of contiguous code
/// units in the encoding specified in `sourceEncoding`, ending just
/// before the first zero code unit.
/// - sourceEncoding: The encoding in which the code units should be
/// interpreted.
public init<Encoding: Unicode.Encoding>(
decodingCString nullTerminatedCodeUnits: UnsafePointer<Encoding.CodeUnit>,
as sourceEncoding: Encoding.Type) {
let codeUnits = _SentinelCollection(
UnsafeBufferPointer(_unboundedStartingAt: nullTerminatedCodeUnits),
until: _IsZero()
)
self.init(decoding: codeUnits, as: sourceEncoding)
}
/// Calls the given closure with a pointer to the contents of the string,
/// represented as a null-terminated sequence of code units.
///
/// The pointer passed as an argument to `body` is valid only during the
/// execution of `withCString(encodedAs:_:)`. Do not store or return the
/// pointer for later use.
///
/// - Parameters:
/// - body: A closure with a pointer parameter that points to a
/// null-terminated sequence of code units. If `body` has a return
/// value, that value is also used as the return value for the
/// `withCString(encodedAs:_:)` method. The pointer argument is valid
/// only for the duration of the method's execution.
/// - targetEncoding: The encoding in which the code units should be
/// interpreted.
/// - Returns: The return value, if any, of the `body` closure parameter.
public func withCString<Result, TargetEncoding: Unicode.Encoding>(
encodedAs targetEncoding: TargetEncoding.Type,
_ body: (UnsafePointer<TargetEncoding.CodeUnit>) throws -> Result
) rethrows -> Result {
return try _core._withCSubstring(
in: _core.startIndex..<_core.endIndex, encoding: targetEncoding, body)
}
}
// FIXME: complexity documentation for most of methods on String ought to be
// qualified with "amortized" at least, as Characters are variable-length.
/// A Unicode string value that is a collection of characters.
///
/// A string is a series of characters, such as `"Swift"`, that forms a
/// collection. Strings in Swift are Unicode correct and locale insensitive,
/// and are designed to be efficient. The `String` type bridges with the
/// Objective-C class `NSString` and offers interoperability with C functions
/// that works with strings.
///
/// You can create new strings using string literals or string interpolations.
/// A *string literal* is a series of characters enclosed in quotes.
///
/// let greeting = "Welcome!"
///
/// *String interpolations* are string literals that evaluate any included
/// expressions and convert the results to string form. String interpolations
/// give you an easy way to build a string from multiple pieces. Wrap each
/// expression in a string interpolation in parentheses, prefixed by a
/// backslash.
///
/// let name = "Rosa"
/// let personalizedGreeting = "Welcome, \(name)!"
/// // personalizedGreeting == "Welcome, Rosa!"
///
/// let price = 2
/// let number = 3
/// let cookiePrice = "\(number) cookies: $\(price * number)."
/// // cookiePrice == "3 cookies: $6."
///
/// Combine strings using the concatenation operator (`+`).
///
/// let longerGreeting = greeting + " We're glad you're here!"
/// // longerGreeting == "Welcome! We're glad you're here!"
///
/// Multiline string literals are enclosed in three double quotation marks
/// (`"""`), with each delimiter on its own line. Indentation is stripped from
/// each line of a multiline string literal to match the indentation of the
/// closing delimiter.
///
/// let banner = """
/// __,
/// ( o /) _/_
/// `. , , , , // /
/// (___)(_(_/_(_ //_ (__
/// /)
/// (/
/// """
///
/// Modifying and Comparing Strings
/// ===============================
///
/// Strings always have value semantics. Modifying a copy of a string leaves
/// the original unaffected.
///
/// var otherGreeting = greeting
/// otherGreeting += " Have a nice time!"
/// // otherGreeting == "Welcome! Have a nice time!"
///
/// print(greeting)
/// // Prints "Welcome!"
///
/// Comparing strings for equality using the equal-to operator (`==`) or a
/// relational operator (like `<` or `>=`) is always performed using Unicode
/// canonical representation. As a result, different representations of a
/// string compare as being equal.
///
/// let cafe1 = "Cafe\u{301}"
/// let cafe2 = "Café"
/// print(cafe1 == cafe2)
/// // Prints "true"
///
/// The Unicode code point `"\u{301}"` modifies the preceding character to
/// include an accent, so `"e\u{301}"` has the same canonical representation
/// as the single Unicode code point `"é"`.
///
/// Basic string operations are not sensitive to locale settings, ensuring that
/// string comparisons and other operations always have a single, stable
/// result, allowing strings to be used as keys in `Dictionary` instances and
/// for other purposes.
///
/// Accessing String Elements
/// =========================
///
/// A string is a collection of *extended grapheme clusters*, which approximate
/// human-readable characters. Many individual characters, such as "é", "김",
/// and "🇮🇳", can be made up of multiple Unicode code points. These code points
/// are combined by Unicode's boundary algorithms into extended grapheme
/// clusters, represented by the Swift `Character` type. Each element of a
/// string is represented by a `Character` instance.
///
/// For example, to retrieve the first word of a longer string, you can search
/// for a space and then create a substring from a prefix of the string up to
/// that point:
///
/// let name = "Marie Curie"
/// let firstSpace = name.index(of: " ") ?? name.endIndex
/// let firstName = name[..<firstSpace]
/// // firstName == "Marie"
///
/// The `firstName` constant is an instance of the `Substring` type---a type
/// that represents substrings of a string while sharing the original string's
/// storage. Substrings present the same interface as strings.
///
/// print("\(name)'s first name has \(firstName.count) letters.")
/// // Prints "Marie Curie's first name has 5 letters."
///
/// Accessing a String's Unicode Representation
/// ===========================================
///
/// If you need to access the contents of a string as encoded in different
/// Unicode encodings, use one of the string's `unicodeScalars`, `utf16`, or
/// `utf8` properties. Each property provides access to a view of the string
/// as a series of code units, each encoded in a different Unicode encoding.
///
/// To demonstrate the different views available for every string, the
/// following examples use this `String` instance:
///
/// let cafe = "Cafe\u{301} du 🌍"
/// print(cafe)
/// // Prints "Café du 🌍"
///
/// The `cafe` string is a collection of the nine characters that are visible
/// when the string is displayed.
///
/// print(cafe.count)
/// // Prints "9"
/// print(Array(cafe))
/// // Prints "["C", "a", "f", "é", " ", "d", "u", " ", "🌍"]"
///
/// Unicode Scalar View
/// -------------------
///
/// A string's `unicodeScalars` property is a collection of Unicode scalar
/// values, the 21-bit codes that are the basic unit of Unicode. Each scalar
/// value is represented by a `Unicode.Scalar` instance and is equivalent to a
/// UTF-32 code unit.
///
/// print(cafe.unicodeScalars.count)
/// // Prints "10"
/// print(Array(cafe.unicodeScalars))
/// // Prints "["C", "a", "f", "e", "\u{0301}", " ", "d", "u", " ", "\u{0001F30D}"]"
/// print(cafe.unicodeScalars.map { $0.value })
/// // Prints "[67, 97, 102, 101, 769, 32, 100, 117, 32, 127757]"
///
/// The `unicodeScalars` view's elements comprise each Unicode scalar value in
/// the `cafe` string. In particular, because `cafe` was declared using the
/// decomposed form of the `"é"` character, `unicodeScalars` contains the code
/// points for both the letter `"e"` (101) and the accent character `"´"`
/// (769).
///
/// UTF-16 View
/// -----------
///
/// A string's `utf16` property is a collection of UTF-16 code units, the
/// 16-bit encoding form of the string's Unicode scalar values. Each code unit
/// is stored as a `UInt16` instance.
///
/// print(cafe.utf16.count)
/// // Prints "11"
/// print(Array(cafe.utf16))
/// // Prints "[67, 97, 102, 101, 769, 32, 100, 117, 32, 55356, 57101]"
///
/// The elements of the `utf16` view are the code units for the string when
/// encoded in UTF-16. These elements match those accessed through indexed
/// `NSString` APIs.
///
/// let nscafe = cafe as NSString
/// print(nscafe.length)
/// // Prints "11"
/// print(nscafe.character(at: 3))
/// // Prints "101"
///
/// UTF-8 View
/// ----------
///
/// A string's `utf8` property is a collection of UTF-8 code units, the 8-bit
/// encoding form of the string's Unicode scalar values. Each code unit is
/// stored as a `UInt8` instance.
///
/// print(cafe.utf8.count)
/// // Prints "14"
/// print(Array(cafe.utf8))
/// // Prints "[67, 97, 102, 101, 204, 129, 32, 100, 117, 32, 240, 159, 140, 141]"
///
/// The elements of the `utf8` view are the code units for the string when
/// encoded in UTF-8. This representation matches the one used when `String`
/// instances are passed to C APIs.
///
/// let cLength = strlen(cafe)
/// print(cLength)
/// // Prints "14"
///
/// Measuring the Length of a String
/// ================================
///
/// When you need to know the length of a string, you must first consider what
/// you'll use the length for. Are you measuring the number of characters that
/// will be displayed on the screen, or are you measuring the amount of
/// storage needed for the string in a particular encoding? A single string
/// can have greatly differing lengths when measured by its different views.
///
/// For example, an ASCII character like the capital letter *A* is represented
/// by a single element in each of its four views. The Unicode scalar value of
/// *A* is `65`, which is small enough to fit in a single code unit in both
/// UTF-16 and UTF-8.
///
/// let capitalA = "A"
/// print(capitalA.count)
/// // Prints "1"
/// print(capitalA.unicodeScalars.count)
/// // Prints "1"
/// print(capitalA.utf16.count)
/// // Prints "1"
/// print(capitalA.utf8.count)
/// // Prints "1"
///
/// On the other hand, an emoji flag character is constructed from a pair of
/// Unicode scalar values, like `"\u{1F1F5}"` and `"\u{1F1F7}"`. Each of
/// these scalar values, in turn, is too large to fit into a single UTF-16 or
/// UTF-8 code unit. As a result, each view of the string `"🇵🇷"` reports a
/// different length.
///
/// let flag = "🇵🇷"
/// print(flag.count)
/// // Prints "1"
/// print(flag.unicodeScalars.count)
/// // Prints "2"
/// print(flag.utf16.count)
/// // Prints "4"
/// print(flag.utf8.count)
/// // Prints "8"
///
/// To check whether a string is empty, use its `isEmpty` property instead of
/// comparing the length of one of the views to `0`. Unlike with `isEmpty`,
/// calculating a view's `count` property requires iterating through the
/// elements of the string.
///
/// Accessing String View Elements
/// ==============================
///
/// To find individual elements of a string, use the appropriate view for your
/// task. For example, to retrieve the first word of a longer string, you can
/// search the `characters` view for a space and then create a new string from
/// a prefix of the `characters` view up to that point.
///
/// let name = "Marie Curie"
/// let firstSpace = name.index(of: " ") ?? name.endIndex
/// let firstName = name[..<firstSpace]
/// print(firstName)
/// // Prints "Marie"
///
/// You can convert an index into one of a string's views to an index into
/// another view.
///
/// let firstSpaceUTF8 = firstSpace.samePosition(in: name.utf8)
/// print(Array(name.utf8[..<firstSpaceUTF8]))
/// // Prints "[77, 97, 114, 105, 101]"
///
/// Performance Optimizations
/// =========================
///
/// Although strings in Swift have value semantics, strings use a copy-on-write
/// strategy to store their data in a buffer. This buffer can then be shared
/// by different copies of a string. A string's data is only copied lazily,
/// upon mutation, when more than one string instance is using the same
/// buffer. Therefore, the first in any sequence of mutating operations may
/// cost O(*n*) time and space.
///
/// When a string's contiguous storage fills up, a new buffer must be allocated
/// and data must be moved to the new storage. String buffers use an
/// exponential growth strategy that makes appending to a string a constant
/// time operation when averaged over many append operations.
///
/// Bridging Between String and NSString
/// ====================================
///
/// Any `String` instance can be bridged to `NSString` using the type-cast
/// operator (`as`), and any `String` instance that originates in Objective-C
/// may use an `NSString` instance as its storage. Because any arbitrary
/// subclass of `NSString` can become a `String` instance, there are no
/// guarantees about representation or efficiency when a `String` instance is
/// backed by `NSString` storage. Because `NSString` is immutable, it is just
/// as though the storage was shared by a copy. The first in any sequence of
/// mutating operations causes elements to be copied into unique, contiguous
/// storage which may cost O(*n*) time and space, where *n* is the length of
/// the string's encoded representation (or more, if the underlying `NSString`
/// has unusual performance characteristics).
///
/// For more information about the Unicode terms used in this discussion, see
/// the [Unicode.org glossary][glossary]. In particular, this discussion
/// mentions [extended grapheme clusters][clusters], [Unicode scalar
/// values][scalars], and [canonical equivalence][equivalence].
///
/// [glossary]: http://www.unicode.org/glossary/
/// [clusters]: http://www.unicode.org/glossary/#extended_grapheme_cluster
/// [scalars]: http://www.unicode.org/glossary/#unicode_scalar_value
/// [equivalence]: http://www.unicode.org/glossary/#canonical_equivalent
@_fixed_layout
public struct String {
/// Creates an empty string.
public init() {
_core = _StringCore()
}
public // @testable
init(_ _core: _StringCore) {
self._core = _core
}
public // @testable
var _core: _StringCore
}
extension String {
public // @testable
static func _fromWellFormedCodeUnitSequence<
Encoding : Unicode.Encoding, Input : Collection
>(
_ encoding: Encoding.Type, input: Input
) -> String
where Input.Element == Encoding.CodeUnit {
return String._fromCodeUnitSequence(encoding, input: input)!
}
public // @testable
static func _fromCodeUnitSequence<
Encoding : Unicode.Encoding, Input : Collection
>(
_ encoding: Encoding.Type, input: Input
) -> String?
where Input.Element == Encoding.CodeUnit {
let (stringBufferOptional, _) =
_StringBuffer.fromCodeUnits(input, encoding: encoding,
repairIllFormedSequences: false)
return stringBufferOptional.map { String(_storage: $0) }
}
public // @testable
static func _fromCodeUnitSequenceWithRepair<
Encoding : Unicode.Encoding, Input : Collection
>(
_ encoding: Encoding.Type, input: Input
) -> (String, hadError: Bool)
where Input.Element == Encoding.CodeUnit {
let (stringBuffer, hadError) =
_StringBuffer.fromCodeUnits(input, encoding: encoding,
repairIllFormedSequences: true)
return (String(_storage: stringBuffer!), hadError)
}
}
extension String : _ExpressibleByBuiltinUnicodeScalarLiteral {
@effects(readonly)
public // @testable
init(_builtinUnicodeScalarLiteral value: Builtin.Int32) {
self = String._fromWellFormedCodeUnitSequence(
UTF32.self, input: CollectionOfOne(UInt32(value)))
}
}
extension String : _ExpressibleByBuiltinExtendedGraphemeClusterLiteral {
@_inlineable
@effects(readonly)
@_semantics("string.makeUTF8")
public init(
_builtinExtendedGraphemeClusterLiteral start: Builtin.RawPointer,
utf8CodeUnitCount: Builtin.Word,
isASCII: Builtin.Int1) {
self = String._fromWellFormedCodeUnitSequence(
UTF8.self,
input: UnsafeBufferPointer(
start: UnsafeMutablePointer<UTF8.CodeUnit>(start),
count: Int(utf8CodeUnitCount)))
}
}
extension String : _ExpressibleByBuiltinUTF16StringLiteral {
@_inlineable
@effects(readonly)
@_semantics("string.makeUTF16")
public init(
_builtinUTF16StringLiteral start: Builtin.RawPointer,
utf16CodeUnitCount: Builtin.Word
) {
self = String(
_StringCore(
baseAddress: UnsafeMutableRawPointer(start),
count: Int(utf16CodeUnitCount),
elementShift: 1,
hasCocoaBuffer: false,
owner: nil))
}
}
extension String : _ExpressibleByBuiltinStringLiteral {
@_inlineable
@effects(readonly)
@_semantics("string.makeUTF8")
public init(
_builtinStringLiteral start: Builtin.RawPointer,
utf8CodeUnitCount: Builtin.Word,
isASCII: Builtin.Int1) {
if Bool(isASCII) {
self = String(
_StringCore(
baseAddress: UnsafeMutableRawPointer(start),
count: Int(utf8CodeUnitCount),
elementShift: 0,
hasCocoaBuffer: false,
owner: nil))
}
else {
self = String._fromWellFormedCodeUnitSequence(
UTF8.self,
input: UnsafeBufferPointer(
start: UnsafeMutablePointer<UTF8.CodeUnit>(start),
count: Int(utf8CodeUnitCount)))
}
}
}
extension String : ExpressibleByStringLiteral {
/// Creates an instance initialized to the given string value.
///
/// Do not call this initializer directly. It is used by the compiler when you
/// initialize a string using a string literal. For example:
///
/// let nextStop = "Clark & Lake"
///
/// This assignment to the `nextStop` constant calls this string literal
/// initializer behind the scenes.
public init(stringLiteral value: String) {
self = value
}
}
extension String : CustomDebugStringConvertible {
/// A representation of the string that is suitable for debugging.
public var debugDescription: String {
var result = "\""
for us in self.unicodeScalars {
result += us.escaped(asASCII: false)
}
result += "\""
return result
}
}
extension String {
/// Returns the number of code units occupied by this string
/// in the given encoding.
func _encodedLength<
Encoding: Unicode.Encoding
>(_ encoding: Encoding.Type) -> Int {
var codeUnitCount = 0
self._encode(encoding, into: { _ in codeUnitCount += 1 })
return codeUnitCount
}
// FIXME: this function may not handle the case when a wrapped NSString
// contains unpaired surrogates. Fix this before exposing this function as a
// public API. But it is unclear if it is valid to have such an NSString in
// the first place. If it is not, we should not be crashing in an obscure
// way -- add a test for that.
// Related: <rdar://problem/17340917> Please document how NSString interacts
// with unpaired surrogates
func _encode<Encoding: Unicode.Encoding>(
_ encoding: Encoding.Type,
into processCodeUnit: (Encoding.CodeUnit) -> Void
) {
return _core.encode(encoding, into: processCodeUnit)
}
}
// Support for copy-on-write
extension String {
/// Appends the given string to this string.
///
/// The following example builds a customized greeting by using the
/// `append(_:)` method:
///
/// var greeting = "Hello, "
/// if let name = getUserName() {
/// greeting.append(name)
/// } else {
/// greeting.append("friend")
/// }
/// print(greeting)
/// // Prints "Hello, friend"
///
/// - Parameter other: Another string.
public mutating func append(_ other: String) {
_core.append(other._core)
}
/// Appends the given Unicode scalar to the string.
///
/// - Parameter x: A Unicode scalar value.
///
/// - Complexity: Appending a Unicode scalar to a string averages to O(1)
/// over many additions.
@available(*, unavailable, message: "Replaced by append(_: String)")
public mutating func append(_ x: Unicode.Scalar) {
Builtin.unreachable()
}
public // SPI(Foundation)
init(_storage: _StringBuffer) {
_core = _StringCore(_storage)
}
}
extension String {
@effects(readonly)
@_semantics("string.concat")
public static func + (lhs: String, rhs: String) -> String {
if lhs.isEmpty {
return rhs
}
var lhs = lhs
lhs._core.append(rhs._core)
return lhs
}
// String append
public static func += (lhs: inout String, rhs: String) {
if lhs.isEmpty {
lhs = rhs
}
else {
lhs._core.append(rhs._core)
}
}
/// Constructs a `String` in `resultStorage` containing the given UTF-8.
///
/// Low-level construction interface used by introspection
/// implementation in the runtime library.
@_inlineable
@_silgen_name("swift_stringFromUTF8InRawMemory")
public // COMPILER_INTRINSIC
static func _fromUTF8InRawMemory(
_ resultStorage: UnsafeMutablePointer<String>,
start: UnsafeMutablePointer<UTF8.CodeUnit>,
utf8CodeUnitCount: Int
) {
resultStorage.initialize(to:
String._fromWellFormedCodeUnitSequence(
UTF8.self,
input: UnsafeBufferPointer(start: start, count: utf8CodeUnitCount)))
}
}
extension Sequence where Element: StringProtocol {
/// Returns a new string by concatenating the elements of the sequence,
/// adding the given separator between each element.
///
/// The following example shows how an array of strings can be joined to a
/// single, comma-separated string:
///
/// let cast = ["Vivien", "Marlon", "Kim", "Karl"]
/// let list = cast.joined(separator: ", ")
/// print(list)
/// // Prints "Vivien, Marlon, Kim, Karl"
///
/// - Parameter separator: A string to insert between each of the elements
/// in this sequence. The default separator is an empty string.
/// - Returns: A single, concatenated string.
public func joined(separator: String = "") -> String {
return _joined(separator: separator)
}
@inline(__always)
internal func _joined(separator: String = "") -> String {
var result = ""
// FIXME(performance): this code assumes UTF-16 in-memory representation.
// It should be switched to low-level APIs.
let separatorSize = separator.utf16.count
let reservation = self._preprocessingPass {
() -> Int in
var r = 0
for chunk in self {
// FIXME(performance): this code assumes UTF-16 in-memory representation.
// It should be switched to low-level APIs.
r += separatorSize + chunk._ephemeralString.utf16.count
}
return r - separatorSize
}
if let n = reservation {
result.reserveCapacity(n)
}
if separatorSize == 0 {
for x in self {
result.append(x._ephemeralString)
}
return result
}
var iter = makeIterator()
if let first = iter.next() {
result.append(first._ephemeralString)
while let next = iter.next() {
result.append(separator)
result.append(next._ephemeralString)
}
}
return result
}
}
// This overload is necessary because String now conforms to
// BidirectionalCollection, and there are other `joined` overloads that are
// considered more specific. See Flatten.swift.gyb.
extension BidirectionalCollection where Iterator.Element == String {
/// Returns a new string by concatenating the elements of the sequence,
/// adding the given separator between each element.
///
/// The following example shows how an array of strings can be joined to a
/// single, comma-separated string:
///
/// let cast = ["Vivien", "Marlon", "Kim", "Karl"]
/// let list = cast.joined(separator: ", ")
/// print(list)
/// // Prints "Vivien, Marlon, Kim, Karl"
///
/// - Parameter separator: A string to insert between each of the elements
/// in this sequence. The default separator is an empty string.
/// - Returns: A single, concatenated string.
public func joined(separator: String = "") -> String {
return _joined(separator: separator)
}
}
#if _runtime(_ObjC)
@_silgen_name("swift_stdlib_NSStringLowercaseString")
func _stdlib_NSStringLowercaseString(_ str: AnyObject) -> _CocoaString
@_silgen_name("swift_stdlib_NSStringUppercaseString")
func _stdlib_NSStringUppercaseString(_ str: AnyObject) -> _CocoaString
#else
internal func _nativeUnicodeLowercaseString(_ str: String) -> String {
var buffer = _StringBuffer(
capacity: str._core.count, initialSize: str._core.count, elementWidth: 2)
// Allocation of a StringBuffer requires binding the memory to the correct
// encoding type.
let dest = buffer.start.bindMemory(
to: UTF16.CodeUnit.self, capacity: str._core.count)
// Try to write it out to the same length.
let z = _swift_stdlib_unicode_strToLower(
dest, Int32(str._core.count),
str._core.startUTF16, Int32(str._core.count))
let correctSize = Int(z)
// If more space is needed, do it again with the correct buffer size.
if correctSize != str._core.count {
buffer = _StringBuffer(
capacity: correctSize, initialSize: correctSize, elementWidth: 2)
let dest = buffer.start.bindMemory(
to: UTF16.CodeUnit.self, capacity: str._core.count)
_swift_stdlib_unicode_strToLower(
dest, Int32(correctSize), str._core.startUTF16, Int32(str._core.count))
}
return String(_storage: buffer)
}
internal func _nativeUnicodeUppercaseString(_ str: String) -> String {
var buffer = _StringBuffer(
capacity: str._core.count, initialSize: str._core.count, elementWidth: 2)