File: _CharacterRecognizer.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 (172 lines) | stat: -rw-r--r-- 4,886 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
//===----------------------------------------------------------------------===//
//
// This source file is part of the Swift Collections open source project
//
// Copyright (c) 2023 - 2024 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
//
//===----------------------------------------------------------------------===//

#if swift(>=5.8)

@available(macOS 13.3, iOS 16.4, watchOS 9.4, tvOS 16.4, *)
internal typealias _CharacterRecognizer = Unicode._CharacterRecognizer

@available(macOS 13.3, iOS 16.4, watchOS 9.4, tvOS 16.4, *)
extension _CharacterRecognizer {
  internal func _isKnownEqual(to other: Self) -> Bool {
    // FIXME: Enable when Swift 5.9 ships.
//  #if swift(>=5.9)
//    if #available(macOS 9999, iOS 9999, tvOS 9999, watchOS 9999, *) { // SwiftStdlib 5.9
//      return self == other
//    }
//  #endif
    return false
  }
}


@available(macOS 13.3, iOS 16.4, watchOS 9.4, tvOS 16.4, *)
extension _CharacterRecognizer {
  mutating func firstBreak(
    in str: Substring
  ) -> Range<String.Index>? {
    let r = str.utf8.withContiguousStorageIfAvailable { buffer in
      self._firstBreak(inUncheckedUnsafeUTF8Buffer: buffer)
    }
    if let r {
      guard let scalarRange = r else { return nil }
      let lower = str._utf8Index(at: scalarRange.lowerBound)
      let upper = str._utf8Index(at: scalarRange.upperBound)
      return lower ..< upper
    }
    guard !str.isEmpty else { return nil }

    var i = str.startIndex
    while i < str.endIndex {
      let next = str.unicodeScalars.index(after: i)
      let scalar = str.unicodeScalars[i]
      if self.hasBreak(before: scalar) {
        return i ..< next
      }
      i = next
    }
    return nil
  }
}

@available(macOS 13.3, iOS 16.4, watchOS 9.4, tvOS 16.4, *)
extension _CharacterRecognizer {
  init(partialCharacter: Substring.UnicodeScalarView) {
    self.init()
    var it = partialCharacter.makeIterator()
    guard let first = it.next() else { return }
    _ = hasBreak(before: first)
    while let next = it.next() {
      let b = hasBreak(before: next)
      assert(!b)
    }
  }
  
  init(partialCharacter: Substring) {
    self.init(partialCharacter: partialCharacter.unicodeScalars)
  }

  mutating func consumePartialCharacter(_ s: String) {
    for scalar in s.unicodeScalars {
      let b = hasBreak(before: scalar)
      assert(!b)
    }
  }

  mutating func consumePartialCharacter(_ s: Substring) {
    for scalar in s.unicodeScalars {
      let b = hasBreak(before: scalar)
      assert(!b)
    }
  }
  
  mutating func consumePartialCharacter(_ s: Substring.UnicodeScalarView) {
    for scalar in s {
      let b = hasBreak(before: scalar)
      assert(!b)
    }
  }
  
  mutating func consumeUntilFirstBreak(
    in s: Substring.UnicodeScalarView,
    from i: inout String.Index
  ) -> String.Index? {
    while i < s.endIndex {
      defer { s.formIndex(after: &i) }
      if hasBreak(before: s[i]) {
        return i
      }
    }
    return nil
  }
  
  init(consuming str: some StringProtocol) {
    self.init()
    _ = self.consume(str)
  }
  
  mutating func consume(
    _ s: some StringProtocol
  ) -> (characters: Int, firstBreak: String.Index, lastBreak: String.Index)? {
    consume(Substring(s))
  }
  
  mutating func consume(
    _ s: Substring
  ) -> (characters: Int, firstBreak: String.Index, lastBreak: String.Index)? {
    consume(s.unicodeScalars)
  }
  
  mutating func consume(
    _ s: Substring.UnicodeScalarView
  ) -> (characters: Int, firstBreak: String.Index, lastBreak: String.Index)? {
    var i = s.startIndex
    guard let first = consumeUntilFirstBreak(in: s, from: &i) else {
      return nil
    }
    var characters = 1
    var last = first
    while let next = consumeUntilFirstBreak(in: s, from: &i) {
      characters += 1
      last = next
    }
    return (characters, first, last)
  }
  
  mutating func consume(
    _ chunk: BigString._Chunk, upTo index: String.Index
  ) -> (firstBreak: String.Index, prevBreak: String.Index)? {
    let index = chunk.string.unicodeScalars._index(roundingDown: index)
    let first = chunk.firstBreak
    guard index > first else {
      consumePartialCharacter(chunk.string[..<index])
      return nil
    }
    let last = chunk.lastBreak
    let prev = index <= last ? chunk.string[first...].index(before: index) : last
    consumePartialCharacter(chunk.string[prev..<index])
    return (first, prev)
  }
  
  mutating func edgeCounts(
    consuming s: String
  ) -> (characters: Int, prefixCount: Int, suffixCount: Int) {
    let c = s.utf8.count
    guard let (chars, first, last) = consume(s[...]) else {
      return (0, c, c)
    }
    let prefix = s._utf8Offset(of: first)
    let suffix = c - s._utf8Offset(of: last)
    return (chars, prefix, suffix)
  }
}

#endif