File: Anchor.swift

package info (click to toggle)
swiftlang 6.0.3-2
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 2,519,992 kB
  • sloc: cpp: 9,107,863; ansic: 2,040,022; asm: 1,135,751; python: 296,500; objc: 82,456; f90: 60,502; lisp: 34,951; pascal: 19,946; sh: 18,133; perl: 7,482; ml: 4,937; javascript: 4,117; makefile: 3,840; awk: 3,535; xml: 914; fortran: 619; cs: 573; ruby: 573
file content (228 lines) | stat: -rw-r--r-- 7,416 bytes parent folder | download
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
//===----------------------------------------------------------------------===//
//
// This source file is part of the Swift.org open source project
//
// Copyright (c) 2021-2022 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
//
//===----------------------------------------------------------------------===//

@_implementationOnly import _RegexParser
@_spi(RegexBuilder) import _StringProcessing

/// A regex component that matches a specific condition at a particular position
/// in an input string.
///
/// You can use anchors to guarantee that a match only occurs at certain points
/// in an input string, such as at the beginning of the string or at the end of
/// a line.
@available(SwiftStdlib 5.7, *)
public struct Anchor {
  internal enum Kind {
    case startOfSubject
    case endOfSubjectBeforeNewline
    case endOfSubject
    case firstMatchingPositionInSubject
    case textSegmentBoundary
    case startOfLine
    case endOfLine
    case wordBoundary
  }
  
  var kind: Kind
  var isInverted: Bool = false
}

@available(SwiftStdlib 5.7, *)
extension Anchor: RegexComponent {
  var baseAssertion: DSLTree.Atom.Assertion {
    switch kind {
    case .startOfSubject:
      // FIXME: Inverted?
      return .startOfSubject
    case .endOfSubjectBeforeNewline:
      // FIXME: Inverted?
      return .endOfSubjectBeforeNewline
    case .endOfSubject:
      // FIXME: Inverted?
      return .endOfSubject
    case .firstMatchingPositionInSubject:
      // FIXME: Inverted?
      return .firstMatchingPositionInSubject
    case .textSegmentBoundary:
      return isInverted ? .notTextSegment : .textSegment
    case .startOfLine:
      // FIXME: Inverted?
      return .startOfLine
    case .endOfLine:
      // FIXME: Inverted?
      return .endOfLine
    case .wordBoundary:
      return isInverted ? .notWordBoundary : .wordBoundary
    }
  }
  
  public var regex: Regex<Substring> {
    _RegexFactory().assertion(baseAssertion)
  }
}

// MARK: - Public API

@available(SwiftStdlib 5.7, *)
extension Anchor {
  /// An anchor that matches at the start of the input string.
  ///
  /// This anchor is equivalent to `\A` in regex syntax.
  public static var startOfSubject: Anchor {
    Anchor(kind: .startOfSubject)
  }
  
  /// An anchor that matches at the end of the input string or at the end of
  /// the line immediately before the end of the string.
  ///
  /// This anchor is equivalent to `\Z` in regex syntax.
  public static var endOfSubjectBeforeNewline: Anchor {
    Anchor(kind: .endOfSubjectBeforeNewline)
  }
  
  /// An anchor that matches at the end of the input string.
  ///
  /// This anchor is equivalent to `\z` in regex syntax.
  public static var endOfSubject: Anchor {
    Anchor(kind: .endOfSubject)
  }

  // TODO: Are we supporting this?
//  public static var resetStartOfMatch: Anchor {
//    Anchor(kind: resetStartOfMatch)
//  }

  /// An anchor that matches at the first position of a match in the input
  /// string.
  public static var firstMatchingPositionInSubject: Anchor {
    Anchor(kind: .firstMatchingPositionInSubject)
  }

  /// An anchor that matches at a grapheme cluster boundary.
  ///
  /// This anchor is equivalent to `\y` in regex syntax.
  public static var textSegmentBoundary: Anchor {
    Anchor(kind: .textSegmentBoundary)
  }
  
  /// An anchor that matches at the start of a line, including the start of
  /// the input string.
  ///
  /// This anchor is equivalent to `^` in regex syntax when the `m` option
  /// has been enabled or `anchorsMatchLineEndings(true)` has been called.
  ///
  /// For example, the following regexes are all equivalent:
  ///
  /// - `Regex { Anchor.startOfLine }`
  /// - `/(?m)^/` or `/(?m:^)/`
  /// - `/^/.anchorsMatchLineEndings(true)`
  public static var startOfLine: Anchor {
    Anchor(kind: .startOfLine)
  }

  /// An anchor that matches at the end of a line, including at the end of
  /// the input string.
  ///
  /// This anchor is equivalent to `$` in regex syntax when the `m` option
  /// has been enabled or `anchorsMatchLineEndings(true)` has been called.
  ///
  /// For example, the following regexes are all equivalent:
  ///
  /// - `Regex { Anchor.endOfLine }`
  /// - `/(?m)$/` or `/(?m:$)/`
  /// - `/$/.anchorsMatchLineEndings(true)`
  public static var endOfLine: Anchor {
    Anchor(kind: .endOfLine)
  }

  /// An anchor that matches at a word boundary.
  ///
  /// Word boundaries are identified using the Unicode default word boundary
  /// algorithm by default. To specify a different word boundary algorithm,
  /// use the `wordBoundaryKind(_:)` method.
  ///
  /// This anchor is equivalent to `\b` in regex syntax.
  public static var wordBoundary: Anchor {
    Anchor(kind: .wordBoundary)
  }
  
  /// The inverse of this anchor, which matches at every position that this
  /// anchor does not.
  ///
  /// For the ``wordBoundary`` and ``textSegmentBoundary`` anchors, the inverted
  /// version corresponds to `\B` and `\Y`, respectively.
  public var inverted: Anchor {
    var result = self
    result.isInverted.toggle()
    return result
  }
}

/// A regex component that allows a match to continue only if its contents
/// match at the given location.
///
/// A lookahead is a zero-length assertion that its included regex matches at
/// a particular position. Lookaheads do not advance the overall matching
/// position in the input string — once a lookahead succeeds, matching continues
/// in the regex from the same position.
@available(SwiftStdlib 5.7, *)
public struct Lookahead<Output>: _BuiltinRegexComponent {
  public var regex: Regex<Output>

  init(_ regex: Regex<Output>) {
    self.regex = regex
  }

  /// Creates a lookahead from the given regex component.
  public init<R: RegexComponent>(
    _ component: R
  ) where R.RegexOutput == Output {
    self.init(_RegexFactory().lookaheadNonCapturing(component))
  }
  
  /// Creates a lookahead from the regex generated by the given builder closure.
  public init<R: RegexComponent>(
    @RegexComponentBuilder _ component: () -> R
  ) where R.RegexOutput == Output {
    self.init(_RegexFactory().lookaheadNonCapturing(component()))
  }
}

/// A regex component that allows a match to continue only if its contents
/// do not match at the given location.
///
/// A negative lookahead is a zero-length assertion that its included regex
/// does not match at a particular position. Lookaheads do not advance the
/// overall matching position in the input string — once a lookahead succeeds,
/// matching continues in the regex from the same position.
@available(SwiftStdlib 5.7, *)
public struct NegativeLookahead<Output>: _BuiltinRegexComponent {
  public var regex: Regex<Output>
  
  init(_ regex: Regex<Output>) {
    self.regex = regex
  }
  
  /// Creates a negative lookahead from the given regex component.
  public init<R: RegexComponent>(
    _ component: R
  ) where R.RegexOutput == Output {
    self.init(_RegexFactory().negativeLookaheadNonCapturing(component))
  }
  
  /// Creates a negative lookahead from the regex generated by the given builder
  /// closure.
  public init<R: RegexComponent>(
    @RegexComponentBuilder _ component: () -> R
  ) where R.RegexOutput == Output {
    self.init(_RegexFactory().negativeLookaheadNonCapturing(component()))
  }
}