Update release 6.0 with main (#743)

Author: milseman

Package.swift

@@ -58,9 +58,10 @@ let package = Package(
         .executable(
             name: "VariadicsGenerator",
             targets: ["VariadicsGenerator"]),
-        .executable(
-            name: "RegexBenchmark",
-            targets: ["RegexBenchmark"])
+// Disable to work around rdar://126877024
+//        .executable(
+//            name: "RegexBenchmark",
+//            targets: ["RegexBenchmark"])
     ],
     dependencies: [
         .package(url: "https://github.com/apple/swift-argument-parser", from: "1.0.0"),
@@ -142,17 +143,17 @@ let package = Package(
                 "_StringProcessing"
             ],
             swiftSettings: [availabilityDefinition]),
-        .executableTarget(
-            name: "RegexBenchmark",
-            dependencies: [
-                .product(name: "ArgumentParser", package: "swift-argument-parser"),
-                "_RegexParser",
-                "_StringProcessing",
-                "RegexBuilder"
-            ],
-            swiftSettings: [
-                .unsafeFlags(["-Xfrontend", "-disable-availability-checking"]),
-            ]),
+//        .executableTarget(
+//            name: "RegexBenchmark",
+//            dependencies: [
+//                .product(name: "ArgumentParser", package: "swift-argument-parser"),
+//                "_RegexParser",
+//                "_StringProcessing",
+//                "RegexBuilder"
+//            ],
+//            swiftSettings: [
+//                .unsafeFlags(["-Xfrontend", "-disable-availability-checking"]),
+//            ]),
 
         // MARK: Exercises
         .target(

Sources/_RegexParser/Regex/Printing/PrettyPrinter.swift

@@ -43,6 +43,10 @@ public struct PrettyPrinter {
 
   // The current default quantification behavior
   public var quantificationBehavior: AST.Quantification.Kind = .eager
+
+  // A stack of the current added inline matching options, e.g. (?s) and a
+  // boolean indicating true = added (?s) and false = removed (?-s).
+  public var inlineMatchingOptions: [([AST.MatchingOption], Bool)] = []
 }
 
 // MARK: - Raw interface
@@ -142,4 +146,21 @@ extension PrettyPrinter {
     printIndented(f)
     print(endDelimiter)
   }
+
+  /// Pushes the list of matching options to the current stack of other matching
+  /// options and increases the indentation level by 1.
+  public mutating func pushMatchingOptions(
+    _ options: [AST.MatchingOption],
+    isAdded: Bool
+  ) {
+    indentLevel += 1
+    inlineMatchingOptions.append((options, isAdded))
+  }
+
+  /// Pops the most recent list of matching options from the printer and
+  /// decreases the indentation level by 1.
+  public mutating func popMatchingOptions() -> ([AST.MatchingOption], Bool) {
+    indentLevel -= 1
+    return inlineMatchingOptions.removeLast()
+  }
 }

Sources/_StringProcessing/ConsumerInterface.swift

@@ -208,9 +208,8 @@ extension DSLTree.CustomCharacterClass.Member {
 
       return { input, bounds in
         let curIdx = bounds.lowerBound
-        let nextIndex = isCharacterSemantic
-          ? input.index(after: curIdx)
-          : input.unicodeScalars.index(after: curIdx)
+        let nextIndex = input.index(
+          after: curIdx, isScalarSemantics: !isCharacterSemantic)
 
         // Under grapheme semantics, we compare based on single NFC scalars. If
         // such a character is not single scalar under NFC, the match fails. In
@@ -353,9 +352,9 @@ extension AST.Atom.CharacterProperty {
         if p(input, bounds) != nil { return nil }
 
         // TODO: bounds check
-        return opts.semanticLevel == .graphemeCluster
-          ? input.index(after: bounds.lowerBound)
-          : input.unicodeScalars.index(after: bounds.lowerBound)
+        return input.index(
+          after: bounds.lowerBound, 
+          isScalarSemantics: opts.semanticLevel == .unicodeScalar)
       }
     }
 

Sources/_StringProcessing/Engine/InstPayload.swift

@@ -381,7 +381,7 @@ struct QuantifyPayload: RawRepresentable {
     case asciiBitset = 0
     case asciiChar = 1
     case any = 2
-    case builtin = 4
+    case builtinCC = 4
   }
 
   // TODO: figure out how to better organize this...
@@ -408,6 +408,14 @@ struct QuantifyPayload: RawRepresentable {
   var typeMask: UInt64       { 7 }
   var payloadMask: UInt64    { 0xFF_FF }
 
+  // Calculate the maximum number of trips, else UInt64.max if unbounded
+  var maxTrips: UInt64 {
+    guard let maxExtraTrips else {
+      return UInt64.max
+    }
+    return minTrips + maxExtraTrips
+  }
+
   static func packInfoValues(
     _ kind: AST.Quantification.Kind,
     _ minTrips: Int,
@@ -489,7 +497,7 @@ struct QuantifyPayload: RawRepresentable {
       + (model.isInverted ? 1 << 9 : 0)
       + (model.isStrictASCII ? 1 << 10 : 0)
     self.rawValue = packedModel
-      + QuantifyPayload.packInfoValues(kind, minTrips, maxExtraTrips, .builtin, isScalarSemantics: isScalarSemantics)
+      + QuantifyPayload.packInfoValues(kind, minTrips, maxExtraTrips, .builtinCC, isScalarSemantics: isScalarSemantics)
   }
 
   var type: PayloadType {
@@ -535,7 +543,7 @@ struct QuantifyPayload: RawRepresentable {
     (self.rawValue & 1) == 1
   }
 
-  var builtin: _CharacterClassModel.Representation {
+  var builtinCC: _CharacterClassModel.Representation {
     _CharacterClassModel.Representation(rawValue: self.rawValue & 0xFF)!
   }
   var builtinIsInverted: Bool {

Sources/_StringProcessing/Engine/MEBuiltins.swift

@@ -223,6 +223,25 @@ extension String {
     else { return nil }
     return next
   }
+
+  internal func matchRegexDot(
+    at currentPosition: Index,
+    limitedBy end: Index,
+    anyMatchesNewline: Bool,
+    isScalarSemantics: Bool
+  ) -> Index? {
+    guard currentPosition < end else { return nil }
+
+    if anyMatchesNewline {
+      return index(
+        after: currentPosition, isScalarSemantics: isScalarSemantics)
+    }
+
+    return matchAnyNonNewline(
+      at: currentPosition,
+      limitedBy: end,
+      isScalarSemantics: isScalarSemantics)
+  }
 }
 
 // MARK: - Built-in character class matching