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
|
//===----------------------------------------------------------------------===//
//
// 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
//
//===----------------------------------------------------------------------===//
internal import _RegexParser
@_spi(_Unicode)
import Swift
// TODO: Sink onto String
extension Processor {
func atSimpleBoundary(
_ usesAsciiWord: Bool,
_ semanticLevel: MatchingOptions.SemanticLevel
) -> Bool {
func matchesWord(at i: Input.Index) -> Bool {
switch semanticLevel {
case .graphemeCluster:
// TODO: needs benchmark coverage
let c = input[i]
return c.isWordCharacter && (c.isASCII || !usesAsciiWord)
case .unicodeScalar:
// TODO: needs benchmark coverage
let c = input.unicodeScalars[i]
return (c.properties.isAlphabetic || c == "_") && (c.isASCII || !usesAsciiWord)
}
}
// FIXME: How should we handle bounds?
// We probably need two concepts
if subjectBounds.isEmpty { return false }
if currentPosition == subjectBounds.lowerBound {
return matchesWord(at: currentPosition)
}
let priorIdx = semanticLevel == .graphemeCluster
? input.index(before: currentPosition)
: input.unicodeScalars.index(before: currentPosition)
if currentPosition == subjectBounds.upperBound {
return matchesWord(at: priorIdx)
}
let prior = matchesWord(at: priorIdx)
let current = matchesWord(at: currentPosition)
return prior != current
}
}
extension String {
func isOnWordBoundary(
at i: String.Index,
in range: Range<String.Index>,
using cache: inout Set<String.Index>?,
_ maxIndex: inout String.Index?
) -> Bool {
// TODO: needs benchmark coverage
guard i != range.lowerBound, i != range.upperBound else {
return true
}
assert(range.contains(i))
// If our index is already in our cache, then this is obviously on a
// boundary.
if let cache = cache, cache.contains(i) {
return true
}
// If its not in the cache AND our max index is larger than our index, it
// means this index is never on a word boundary in our string. If our index
// is larger than max index, we may need to still do work to determine if
// i is on a boundary. If it's equal to max index, then it should've been
// taken the cache path.
if let maxIndex = maxIndex, i < maxIndex {
return false
}
if #available(SwiftStdlib 5.7, *) {
if cache == nil {
cache = []
}
var j = maxIndex ?? range.lowerBound
while j < range.upperBound, j <= i {
cache!.insert(j)
j = _wordIndex(after: j)
}
maxIndex = j
return cache!.contains(i)
} else {
return false
}
}
}
|
