New benchmark: word boundaries in urls

Author: milseman

Package.swift

@@ -59,9 +59,9 @@ let package = Package(
             name: "VariadicsGenerator",
             targets: ["VariadicsGenerator"]),
 // Disable to work around rdar://126877024
-//        .executable(
-//            name: "RegexBenchmark",
-//            targets: ["RegexBenchmark"])
+        .executable(
+          name: "RegexBenchmark",
+          targets: ["RegexBenchmark"])
     ],
     dependencies: [
         .package(url: "https://github.com/apple/swift-argument-parser", from: "1.0.0"),
@@ -143,17 +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/RegexBenchmark/Benchmark.swift

@@ -153,29 +153,34 @@ struct CrossBenchmark {
   /// Whether to also run scalar-semantic mode
   var alsoRunScalarSemantic: Bool = true
 
+  var alsoRunSimpleWordBoundaries: Bool = false
+
   func register(_ runner: inout BenchmarkRunner) {
     if isWhole {
       runner.registerCrossBenchmark(
         nameBase: baseName,
         input: input,
         pattern: regex,
         .whole,
-        alsoRunScalarSemantic: alsoRunScalarSemantic)
+        alsoRunScalarSemantic: alsoRunScalarSemantic,
+        alsoRunSimpleWordBoundaries: alsoRunSimpleWordBoundaries)
     } else {
       runner.registerCrossBenchmark(
         nameBase: baseName,
         input: input,
         pattern: regex,
         .allMatches,
-        alsoRunScalarSemantic: alsoRunScalarSemantic)
+        alsoRunScalarSemantic: alsoRunScalarSemantic,
+        alsoRunSimpleWordBoundaries: alsoRunSimpleWordBoundaries)
 
       if includeFirst || runner.includeFirstOverride {
         runner.registerCrossBenchmark(
           nameBase: baseName,
           input: input,
           pattern: regex,
           .first,
-          alsoRunScalarSemantic: alsoRunScalarSemantic)
+          alsoRunScalarSemantic: alsoRunScalarSemantic,
+          alsoRunSimpleWordBoundaries: alsoRunSimpleWordBoundaries)
       }
     }
   }

Sources/RegexBenchmark/BenchmarkRegistration.swift

@@ -18,6 +18,8 @@ extension BenchmarkRunner {
     self.addDiceNotation()
     self.addErrorMessages()
     self.addIpAddress()
+
+    self.addURLWithWordBoundaries()
     // -- end of registrations --
   }
 }

Sources/RegexBenchmark/BenchmarkRunner.swift

@@ -33,7 +33,8 @@ struct BenchmarkRunner {
     input: String,
     pattern: String,
     _ type: Benchmark.MatchType,
-    alsoRunScalarSemantic: Bool = true
+    alsoRunScalarSemantic: Bool = true,
+    alsoRunSimpleWordBoundaries: Bool
   ) {
     let swiftRegex = try! Regex(pattern)
     let nsRegex: NSRegularExpression
@@ -58,6 +59,16 @@ struct BenchmarkRunner {
         type: .init(type),
         target: input))
 
+    if alsoRunSimpleWordBoundaries {
+      register(
+        Benchmark(
+          name: nameBase + nameSuffix + "_SimpleWordBoundaries",
+          regex: swiftRegex.wordBoundaryKind(.simple),
+          pattern: pattern,
+          type: type,
+          target: input))
+    }
+
     if alsoRunScalarSemantic {
       register(
         Benchmark(

Sources/RegexBenchmark/Inputs/URL.swift

@@ -0,0 +1,22 @@
+extension Inputs {
+  static let url: String = {
+    let element = """
+        Item 1     |        Item 2®                 •Item 3  Item4
+
+
+          \t\t\t
+
+        Check it out here: http://www.test.com/this-is-a-fake-url-that-should-be-replaced?a=1
+        Check it out here: https://www.test.com/this-is-a-fake-url-that-should-be-replaced?a=1
+        This is not a web link ftp://user@host:domain.com/path
+        This is a link without a scheme www.apple.com/mac
+
+        This is some good text and should not be removed.
+        Thanks.
+        😀🩷🤵🏿
+        """
+    let multiplier = 30
+    return Array(repeating: element, count: multiplier).joined()
+  }()
+
+}

Sources/RegexBenchmark/Suite/URLRegex.swift

@@ -0,0 +1,14 @@
+import _StringProcessing
+
+extension BenchmarkRunner {
+  mutating func addURLWithWordBoundaries() {
+    let urlRegex = #"https?://([-a-zA-Z0-9@:%._+~#=]{1,256}\.[a-zA-Z0-9()]{1,6})\b[-a-zA-Z0-9()@:%_+.~#?&=]*"#
+    let url = CrossBenchmark(
+      baseName: "URLWithWordBoundaries",
+      regex: urlRegex,
+      input: Inputs.url,
+      alsoRunSimpleWordBoundaries: true
+    )
+    url.register(&self)
+  }
+}