Refactor operations to be on String (#664)

Finish refactoring logic onto String

Sources/RegexBenchmark/Utils/Stats.swift

@@ -3,8 +3,8 @@ import Foundation
 enum Stats {}
 
 extension Stats {
- // Maximum allowed standard deviation is 5% of the median runtime
- static let maxAllowedStdev = 0.05
+ // Maximum allowed standard deviation is 7.5% of the median runtime
+ static let maxAllowedStdev = 0.075
 
  static func tTest(_ a: Measurement, _ b: Measurement) -> Bool {
  // Student's t-test

Sources/_StringProcessing/Engine/MEBuiltins.swift

@@ -15,7 +15,7 @@ extension Processor {
  isStrictASCII: Bool,
  isScalarSemantics: Bool
  ) -> Bool {
- guard let next = input._matchBuiltinCC(
+ guard let next = input.matchBuiltinCC(
  cc,
  at: currentPosition,
  isInverted: isInverted,
@@ -123,7 +123,7 @@ extension Processor {
 extension String {
  // TODO: Should the below have a `limitedBy` parameter?
 
- func _matchAnyNonNewline(
+ func matchAnyNonNewline(
  at currentPosition: String.Index,
  isScalarSemantics: Bool
  ) -> String.Index? {
@@ -145,7 +145,7 @@ extension String {
  }
 
  @inline(__always)
- func _quickMatchAnyNonNewline(
+ private func _quickMatchAnyNonNewline(
  at currentPosition: String.Index,
  isScalarSemantics: Bool
  ) -> QuickResult<String.Index?> {
@@ -165,7 +165,7 @@ extension String {
  }
 
  @inline(never)
- func _thoroughMatchAnyNonNewline(
+ private func _thoroughMatchAnyNonNewline(
  at currentPosition: String.Index,
  isScalarSemantics: Bool
  ) -> String.Index? {
@@ -187,7 +187,7 @@ extension String {
  // TODO: Should the below have a `limitedBy` parameter?
 
  // Mentioned in ProgrammersManual.md, update docs if redesigned
- func _matchBuiltinCC(
+ func matchBuiltinCC(
  _ cc: _CharacterClassModel.Representation,
  at currentPosition: String.Index,
  isInverted: Bool,
@@ -222,7 +222,7 @@ extension String {
 
  // Mentioned in ProgrammersManual.md, update docs if redesigned
  @inline(__always)
- func _quickMatchBuiltinCC(
+ private func _quickMatchBuiltinCC(
  _ cc: _CharacterClassModel.Representation,
  at currentPosition: String.Index,
  isInverted: Bool,
@@ -240,7 +240,7 @@ extension String {
 
  // Mentioned in ProgrammersManual.md, update docs if redesigned
  @inline(never)
- func _thoroughMatchBuiltinCC(
+ private func _thoroughMatchBuiltinCC(
  _ cc: _CharacterClassModel.Representation,
  at currentPosition: String.Index,
  isInverted: Bool,

Sources/_StringProcessing/Engine/MEQuantify.swift

@@ -1,21 +1,27 @@
 extension Processor {
  func _doQuantifyMatch(_ payload: QuantifyPayload) -> Input.Index? {
- // FIXME: is the below updated for scalar semantics?
+ // TODO: This optimization is only enabled for grapheme cluster semantics,
+ // we want these for scalar semantics as well.
+
  switch payload.type {
  case .bitset:
  return input.matchBitset(
- registers[payload.bitset], at: currentPosition, limitedBy: end)
+ registers[payload.bitset],
+ at: currentPosition,
+ limitedBy: end,
+ isScalarSemantics: false)
  case .asciiChar:
  return input.matchScalar(
  UnicodeScalar.init(_value: UInt32(payload.asciiChar)),
  at: currentPosition,
  limitedBy: end,
- boundaryCheck: true)
+ boundaryCheck: true,
+ isCaseInsensitive: false)
  case .builtin:
  // FIXME: bounds check? endIndex or end?
 
  // We only emit .quantify if it consumes a single character
- return input._matchBuiltinCC(
+ return input.matchBuiltinCC(
  payload.builtin,
  at: currentPosition,
  isInverted: payload.builtinIsInverted,
@@ -29,7 +35,7 @@ extension Processor {
  return input.index(after: currentPosition)
  }
 
- return input._matchAnyNonNewline(
+ return input.matchAnyNonNewline(
  at: currentPosition, isScalarSemantics: false)
  }
  }
@@ -41,7 +47,7 @@ extension Processor {
  var trips = 0
  var extraTrips = payload.extraTrips
  var savePoint = startQuantifierSavePoint()
- 
+
  while true {
  if trips >= payload.minTrips {
  if extraTrips == 0 { break }