-
Notifications
You must be signed in to change notification settings - Fork 10.4k
/
Copy pathCString.swift
205 lines (194 loc) · 8.1 KB
/
CString.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
//===----------------------------------------------------------------------===//
//
// 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
//
//===----------------------------------------------------------------------===//
// String interop with C
//===----------------------------------------------------------------------===//
import SwiftShims
extension String {
/// Creates a new string by copying the null-terminated UTF-8 data referenced
/// by the given pointer.
///
/// If `cString` contains ill-formed UTF-8 code unit sequences, this
/// initializer replaces them with the Unicode replacement character
/// (`"\u{FFFD}"`).
///
/// The following example calls this initializer with pointers to the
/// contents of two different `CChar` arrays---the first with well-formed
/// UTF-8 code unit sequences and the second with an ill-formed sequence at
/// the end.
///
/// let validUTF8: [CChar] = [67, 97, 102, -61, -87, 0]
/// validUTF8.withUnsafeBufferPointer { ptr in
/// let s = String(cString: ptr.baseAddress!)
/// print(s)
/// }
/// // Prints "Café"
///
/// let invalidUTF8: [CChar] = [67, 97, 102, -61, 0]
/// invalidUTF8.withUnsafeBufferPointer { ptr in
/// let s = String(cString: ptr.baseAddress!)
/// print(s)
/// }
/// // Prints "Caf�"
///
/// - Parameter cString: A pointer to a null-terminated UTF-8 code sequence.
public init(cString: UnsafePointer<CChar>) {
let len = UTF8._nullCodeUnitOffset(in: cString)
self = String._fromUTF8Repairing(
UnsafeBufferPointer(start: cString._asUInt8, count: len)).0
}
/// Creates a new string by copying the null-terminated UTF-8 data referenced
/// by the given pointer.
///
/// This is identical to init(cString: UnsafePointer<CChar> but operates on an
/// unsigned sequence of bytes.
public init(cString: UnsafePointer<UInt8>) {
let len = UTF8._nullCodeUnitOffset(in: cString)
self = String._fromUTF8Repairing(
UnsafeBufferPointer(start: cString, count: len)).0
}
/// Creates a new string by copying and validating the null-terminated UTF-8
/// data referenced by the given pointer.
///
/// This initializer does not try to repair ill-formed UTF-8 code unit
/// sequences. If any are found, the result of the initializer is `nil`.
///
/// The following example calls this initializer with pointers to the
/// contents of two different `CChar` arrays---the first with well-formed
/// UTF-8 code unit sequences and the second with an ill-formed sequence at
/// the end.
///
/// let validUTF8: [CChar] = [67, 97, 102, -61, -87, 0]
/// validUTF8.withUnsafeBufferPointer { ptr in
/// let s = String(validatingUTF8: ptr.baseAddress!)
/// print(s)
/// }
/// // Prints "Optional(Café)"
///
/// let invalidUTF8: [CChar] = [67, 97, 102, -61, 0]
/// invalidUTF8.withUnsafeBufferPointer { ptr in
/// let s = String(validatingUTF8: ptr.baseAddress!)
/// print(s)
/// }
/// // Prints "nil"
///
/// - Parameter cString: A pointer to a null-terminated UTF-8 code sequence.
public init?(validatingUTF8 cString: UnsafePointer<CChar>) {
let len = UTF8._nullCodeUnitOffset(in: cString)
guard let str = String._tryFromUTF8(
UnsafeBufferPointer(start: cString._asUInt8, count: len))
else { return nil }
self = str
}
/// Creates a new string by copying the null-terminated data referenced by
/// the given pointer using the specified encoding.
///
/// When you pass `true` as `isRepairing`, this method replaces ill-formed
/// sequences with the Unicode replacement character (`"\u{FFFD}"`);
/// otherwise, an ill-formed sequence causes this method to stop decoding
/// and return `nil`.
///
/// The following example calls this method with pointers to the contents of
/// two different `CChar` arrays---the first with well-formed UTF-8 code
/// unit sequences and the second with an ill-formed sequence at the end.
///
/// let validUTF8: [UInt8] = [67, 97, 102, 195, 169, 0]
/// validUTF8.withUnsafeBufferPointer { ptr in
/// let s = String.decodeCString(ptr.baseAddress,
/// as: UTF8.self,
/// repairingInvalidCodeUnits: true)
/// print(s)
/// }
/// // Prints "Optional((Café, false))"
///
/// let invalidUTF8: [UInt8] = [67, 97, 102, 195, 0]
/// invalidUTF8.withUnsafeBufferPointer { ptr in
/// let s = String.decodeCString(ptr.baseAddress,
/// as: UTF8.self,
/// repairingInvalidCodeUnits: true)
/// print(s)
/// }
/// // Prints "Optional((Caf�, true))"
///
/// - Parameters:
/// - cString: A pointer to a null-terminated code sequence encoded in
/// `encoding`.
/// - encoding: The Unicode encoding of the data referenced by `cString`.
/// - isRepairing: Pass `true` to create a new string, even when the data
/// referenced by `cString` contains ill-formed sequences. Ill-formed
/// sequences are replaced with the Unicode replacement character
/// (`"\u{FFFD}"`). Pass `false` to interrupt the creation of the new
/// string if an ill-formed sequence is detected.
/// - Returns: A tuple with the new string and a Boolean value that indicates
/// whether any repairs were made. If `isRepairing` is `false` and an
/// ill-formed sequence is detected, this method returns `nil`.
@_specialize(where Encoding == Unicode.UTF8)
@_specialize(where Encoding == Unicode.UTF16)
@inlinable // Fold away specializations
public static func decodeCString<Encoding : _UnicodeEncoding>(
_ cString: UnsafePointer<Encoding.CodeUnit>?,
as encoding: Encoding.Type,
repairingInvalidCodeUnits isRepairing: Bool = true
) -> (result: String, repairsMade: Bool)? {
guard let cPtr = cString else { return nil }
if _fastPath(encoding == Unicode.UTF8.self) {
let ptr = UnsafeRawPointer(cPtr).assumingMemoryBound(to: UInt8.self)
let len = UTF8._nullCodeUnitOffset(in: ptr)
let codeUnits = UnsafeBufferPointer(start: ptr, count: len)
if isRepairing {
return String._fromUTF8Repairing(codeUnits)
} else {
guard let str = String._tryFromUTF8(codeUnits) else { return nil }
return (str, false)
}
}
var end = cPtr
while end.pointee != 0 { end += 1 }
let len = end - cPtr
let codeUnits = UnsafeBufferPointer(start: cPtr, count: len)
return String._fromCodeUnits(
codeUnits, encoding: encoding, repair: isRepairing)
}
/// 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.
@_specialize(where Encoding == Unicode.UTF8)
@_specialize(where Encoding == Unicode.UTF16)
@inlinable // Fold away specializations
public init<Encoding: Unicode.Encoding>(
decodingCString ptr: UnsafePointer<Encoding.CodeUnit>,
as sourceEncoding: Encoding.Type
) {
self = String.decodeCString(ptr, as: sourceEncoding)!.0
}
}
extension UnsafePointer where Pointee == UInt8 {
@inlinable
internal var _asCChar: UnsafePointer<CChar> {
@inline(__always) get {
return UnsafeRawPointer(self).assumingMemoryBound(to: CChar.self)
}
}
}
extension UnsafePointer where Pointee == CChar {
@inlinable
internal var _asUInt8: UnsafePointer<UInt8> {
@inline(__always) get {
return UnsafeRawPointer(self).assumingMemoryBound(to: UInt8.self)
}
}
}