Fix firstRange(of:) search (#656)

Calls to `ranges(of:)` and `firstRange(of:)` with a string parameter actually use two different string searching algorithms. `ranges(of:)` uses the "z-searcher" algorithm, while `firstRange(of:)` uses a two-way search. Since it's better to align on a single path for these searches, the z-searcher has lower requirements, and the two-way search implementation has a correctness bug, this change removes the two-way search algorithm and uses z-search for `firstRange(of:)`. The correctness bug in `firstRange(of:)` appears only when searching for the second (or later) occurrence of a substring, which you have to be fairly deliberate about. In the example below, the substring at offsets `7..<12` is missed: let text = "ADACBADADACBADACB" // ===== -----===== let pattern = "ADACB" let firstRange = text.firstRange(of: pattern)! // firstRange ~= 0..<5 let secondRange = text[firstRange.upperBound...].firstRange(of: pattern)! // secondRange ~= 12..<17 This change also removes some unrelated, unused code in Split.swift, in addition to removing an (unused) usage of `TwoWaySearcher`. rdar://92794248

Author: natecook1000

Sources/_StringProcessing/Algorithms/Algorithms/FirstRange.swift

@@ -50,11 +50,8 @@ extension BidirectionalCollection where Element: Comparable {
  public func firstRange<C: Collection>(
  of other: C
  ) -> Range<Index>? where C.Element == Element {
- let searcher = PatternOrEmpty(
- searcher: TwoWaySearcher<SubSequence>(pattern: Array(other)))
- let slice = self[...]
- var state = searcher.state(for: slice, in: startIndex..<endIndex)
- return searcher.search(slice, &state)
+ let searcher = ZSearcher<SubSequence>(pattern: Array(other), by: ==)
+ return searcher.search(self[...], in: startIndex..<endIndex)
  }
 }
 

Sources/_StringProcessing/Algorithms/Algorithms/Split.swift

@@ -122,31 +122,6 @@ extension Collection {
  }
 }
 
-// MARK: Predicate algorithms
-
-extension Collection {
- // TODO: Non-escaping and throwing
- func split(
- whereSeparator predicate: @escaping (Element) -> Bool,
- maxSplits: Int,
- omittingEmptySubsequences: Bool
- ) -> SplitCollection<PredicateConsumer<Self>> {
- split(by: PredicateConsumer(predicate: predicate), maxSplits: maxSplits, omittingEmptySubsequences: omittingEmptySubsequences)
- }
-}
-
-// MARK: Single element algorithms
-
-extension Collection where Element: Equatable {
- func split(
- by separator: Element,
- maxSplits: Int,
- omittingEmptySubsequences: Bool
- ) -> SplitCollection<PredicateConsumer<Self>> {
- split(whereSeparator: { $0 == separator }, maxSplits: maxSplits, omittingEmptySubsequences: omittingEmptySubsequences)
- }
-}
-
 // MARK: Fixed pattern algorithms
 
 extension Collection where Element: Equatable {
@@ -180,41 +155,6 @@ extension Collection where Element: Equatable {
  }
 }
 
-extension BidirectionalCollection where Element: Equatable {
- // FIXME
-// public func splitFromBack<S: Sequence>(
-// separator: S
-// ) -> ReversedSplitCollection<ZSearcher<SubSequence>>
-// where S.Element == Element
-// {
-// splitFromBack(separator: ZSearcher(pattern: Array(separator), by: ==))
-// }
-}
-
-extension BidirectionalCollection where Element: Comparable {
- func split<C: Collection>(
- by separator: C,
- maxSplits: Int,
- omittingEmptySubsequences: Bool
- ) -> SplitCollection<PatternOrEmpty<TwoWaySearcher<Self>>>
- where C.Element == Element
- {
- split(
- by: PatternOrEmpty(searcher: TwoWaySearcher(pattern: Array(separator))),
- maxSplits: maxSplits, omittingEmptySubsequences: omittingEmptySubsequences)
- }
- 
- // FIXME
-// public func splitFromBack<S: Sequence>(
-// separator: S
-// ) -> ReversedSplitCollection<PatternOrEmpty<TwoWaySearcher<SubSequence>>>
-// where S.Element == Element
-// {
-// splitFromBack(separator: PatternOrEmpty(
-// searcher: TwoWaySearcher(pattern: Array(separator))))
-// }
-}
-
 // String split overload breakers
 //
 // These are underscored and marked as SPI so that the *actual* public overloads

Sources/_StringProcessing/Algorithms/Searchers/TwoWaySearcher.swift

@@ -23,7 +23,6 @@ add_library(_StringProcessing
  Algorithms/Searchers/NaivePatternSearcher.swift
  Algorithms/Searchers/PatternOrEmpty.swift
  Algorithms/Searchers/PredicateSearcher.swift
- Algorithms/Searchers/TwoWaySearcher.swift
  Algorithms/Searchers/ZSearcher.swift
  Engine/Backtracking.swift
  Engine/Consume.swift

Sources/_StringProcessing/CMakeLists.txt

@@ -165,8 +165,12 @@ class AlgorithmTests: XCTestCase {
  let actualCol: [Range<Int>] = input.ranges(of: pattern)[...].map(input.offsets(of:))
  XCTAssertEqual(actualCol, expected, file: file, line: line)
 
- let firstRange = input.firstRange(of: pattern).map(input.offsets(of:))
- XCTAssertEqual(firstRange, expected.first, file: file, line: line)
+ let firstRange = input.firstRange(of: pattern)
+ XCTAssertEqual(firstRange.map(input.offsets(of:)), expected.first, file: file, line: line)
+ if let upperBound = firstRange?.upperBound, !pattern.isEmpty {
+ let secondRange = input[upperBound...].firstRange(of: pattern).map(input.offsets(of:))
+ XCTAssertEqual(secondRange, expected.dropFirst().first, file: file, line: line)
+ }
  }
 
  expectRanges("", "", [0..<0])
@@ -176,6 +180,9 @@ class AlgorithmTests: XCTestCase {
  expectRanges("abcde", "bcd", [1..<4])
  expectRanges("ababacabababa", "abababa", [6..<13])
  expectRanges("ababacabababa", "aba", [0..<3, 6..<9, 10..<13])
+ 
+ // Test for rdar://92794248
+ expectRanges("ADACBADADACBADACB", "ADACB", [0..<5, 7..<12, 12..<17])
  }
 
  // rdar://105154010