Migrate scoring APIs to double precision for v6.0.0

.github/workflows/build-nuget-packages.yml

@@ -0,0 +1,44 @@
+name: Build, Test, and Package
+
+on:
+  push:
+  pull_request:
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  build:
+    name: Build, test, and pack
+    runs-on: windows-latest
+
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v4
+
+      - name: Set up .NET
+        uses: actions/setup-dotnet@v4
+        with:
+          dotnet-version: 10.0.x
+
+      - name: Restore
+        run: dotnet restore FuzzySharp.slnx
+
+      - name: Build
+        run: dotnet build FuzzySharp.slnx --configuration Release --no-restore -p:GeneratePackageOnBuild=false
+
+      - name: Test
+        run: dotnet test FuzzySharp.Test/FuzzySharp.Test.csproj --configuration Release --no-restore --no-build
+
+      - name: Pack
+        run: dotnet pack FuzzySharp/FuzzySharp.csproj --configuration Release --no-restore --no-build --output artifacts -p:GeneratePackageOnBuild=false -p:IncludeSymbols=true -p:SymbolPackageFormat=snupkg
+
+      - name: Upload NuGet packages
+        uses: actions/upload-artifact@v4
+        with:
+          name: nuget-packages
+          path: |
+            artifacts/*.nupkg
+            artifacts/*.snupkg
+          if-no-files-found: error

CHANGELOG.md

@@ -1,5 +1,14 @@
 # Changelog
 
+## v6.0.0
+
+*Double-precision scoring and simplified distance APIs*
+
+- **Breaking:** Removed `scoreCutoff` from the Indel, Levenshtein, LCS, and partial-ratio APIs.
+- **Breaking:** Scorers, scoring strategies, `Fuzz` methods, and extracted-result scores now use `double` and preserve fractional similarity values.
+- Extraction `cutoff` parameters now accept `double` values.
+- Optimized pattern-match-vector construction with bulk character population, a dedicated single-block fast path, lazy non-ASCII storage, and direct dense-mask lookup for ASCII characters.
+
 ## v5.0.3
 
 *Extractor selection performance and allocation improvements*

FuzzySharp.Benchmarks/ExtractSelectionBenchmarks.cs

@@ -203,20 +203,20 @@ internal static IEnumerable<ExtractedResult<string>> LegacyParallelCachedExtract
 
     private sealed class CheapScorer : IRatioScorer
     {
-        public int Score(string input1, string input2)
+        public double Score(string input1, string input2)
         {
             return ScoreFromChoice(input2);
         }
 
-        public int Score(string input1, string input2, Func<string, string> preprocessor)
+        public double Score(string input1, string input2, Func<string, string> preprocessor)
         {
             return Score(preprocessor(input1), preprocessor(input2));
         }
     }
 
     private sealed class CheapCachedScorer : ICachedRatioScorer
     {
-        public int Score(string input2)
+        public double Score(string input2)
         {
             return ScoreFromChoice(input2);
         }
@@ -335,20 +335,20 @@ public List<ExtractedResult<string>> Legacy_ParallelCached_ExtractTop()
 
     private sealed class CheapScorer : IRatioScorer
     {
-        public int Score(string input1, string input2)
+        public double Score(string input1, string input2)
         {
             return ScoreFromChoice(input2);
         }
 
-        public int Score(string input1, string input2, Func<string, string> preprocessor)
+        public double Score(string input1, string input2, Func<string, string> preprocessor)
         {
             return Score(preprocessor(input1), preprocessor(input2));
         }
     }
 
     private sealed class CheapCachedScorer : ICachedRatioScorer
     {
-        public int Score(string input2)
+        public double Score(string input2)
         {
             return ScoreFromChoice(input2);
         }
@@ -497,20 +497,20 @@ public List<ExtractedResult<string>> Legacy_ParallelCached_ExtractTop()
 
     private sealed class CheapScorer : IRatioScorer
     {
-        public int Score(string input1, string input2)
+        public double Score(string input1, string input2)
         {
             return ScoreFromChoice(input2);
         }
 
-        public int Score(string input1, string input2, Func<string, string> preprocessor)
+        public double Score(string input1, string input2, Func<string, string> preprocessor)
         {
             return Score(preprocessor(input1), preprocessor(input2));
         }
     }
 
     private sealed class CheapCachedScorer : ICachedRatioScorer
     {
-        public int Score(string input2)
+        public double Score(string input2)
         {
             return ScoreFromChoice(input2);
         }

FuzzySharp.Benchmarks/LevenshteinDistance/LevenshteinLarge.cs

@@ -31,7 +31,7 @@ public void NaiveDp()
     }
 
     [Benchmark]
-    public void FuzzySharpClassic()
+    public void FuzzySharp()
     {
         for (var i = 0; i < _words.Length; i++)
         {
@@ -67,8 +67,8 @@ public void Quickenshtein()
         }
     }
 
-    [Benchmark]
-    public void FuzzySharp()
+    [Benchmark(Description = "Raffinert.FuzzySharp")]
+    public void ThisLibrary()
     {
         for (var i = 0; i < _words.Length; i++)
         {

FuzzySharp.Benchmarks/LevenshteinDistance/LevenshteinNormal.cs

@@ -32,7 +32,7 @@ public void NaiveDp()
     }
 
     [Benchmark]
-    public void FuzzySharpClassic()
+    public void FuzzySharp()
     {
         for (var i = 0; i < _words.Length; i++)
         {
@@ -68,8 +68,8 @@ public void Quickenshtein()
         }
     }
 
-    [Benchmark]
-    public void FuzzySharp()
+    [Benchmark(Description = "Raffinert.FuzzySharp")]
+    public void ThisLibrary()
     {
         for (var i = 0; i < _words.Length; i++)
         {

FuzzySharp.Benchmarks/LevenshteinDistance/LevenshteinSmall.cs

@@ -31,7 +31,7 @@ public void NaiveDp()
     }
 
     [Benchmark]
-    public void FuzzySharpClassic()
+    public void FuzzySharp()
     {
         for (var i = 0; i < _words.Length; i++)
         {
@@ -67,8 +67,8 @@ public void Quickenshtein()
         }
     }
 
-    [Benchmark]
-    public void FuzzySharp()
+    [Benchmark(Description = "Raffinert.FuzzySharp")]
+    public void ThisLibrary()
     {
         for (var i = 0; i < _words.Length; i++)
         {

FuzzySharp.Benchmarks/PartialRatioBenchmarks.cs

@@ -8,13 +8,13 @@ namespace Raffinert.FuzzySharp.Benchmarks;
 public class PartialRatioBenchmarks
 {
     [Benchmark]
-    public int PartialRatio()
+    public double PartialRatio()
     {
         return Fuzz.PartialRatio("similar", "somewhresimlrbetweenthisstring");
     }
 
     [Benchmark]
-    public int PartialRatioClassic()
+    public double PartialRatioClassic()
     {
         return Classic.Fuzz.PartialRatio("similar", "somewhresimlrbetweenthisstring");
     }

FuzzySharp.Benchmarks/PartialRatioLongBenchmarks.cs

@@ -32,13 +32,13 @@ private static string GenerateString(int length, Random rnd)
     }
 
     [Benchmark]
-    public int PartialRatio()
+    public double PartialRatio()
     {
         return Fuzz.PartialRatio(_s1, _s2);
     }
 
     [Benchmark]
-    public int PartialRatioClassic()
+    public double PartialRatioClassic()
     {
         return Classic.Fuzz.PartialRatio(_s1, _s2);
     }

FuzzySharp.Benchmarks/PartialTokenAbbreviationRatioBenchmarks.cs

@@ -9,13 +9,13 @@ namespace Raffinert.FuzzySharp.Benchmarks;
 public class PartialTokenAbbreviationRatioBenchmarks
 {
     [Benchmark]
-    public int PartialTokenAbbreviationRatio()
+    public double PartialTokenAbbreviationRatio()
     {
         return Fuzz.PartialTokenAbbreviationRatio("bl 420", "Baseline section 420", StringPreprocessor.Full);
     }
 
     [Benchmark]
-    public int PartialTokenAbbreviationRatioClassic()
+    public double PartialTokenAbbreviationRatioClassic()
     {
         return Classic.Fuzz.PartialTokenAbbreviationRatio("bl 420", "Baseline section 420", Classic.PreProcess.PreprocessMode.Full);
     }

FuzzySharp.Benchmarks/PartialTokenInitialismRatioBenchmarks.cs

@@ -8,13 +8,13 @@ namespace Raffinert.FuzzySharp.Benchmarks;
 public class PartialTokenInitialismRatioBenchmarks
 {
     [Benchmark]
-    public int PartialTokenInitialismRatio()
+    public double PartialTokenInitialismRatio()
     {
         return Fuzz.PartialTokenInitialismRatio("NASA", "National Aeronautics Space Administration, Kennedy Space Center, Cape Canaveral, Florida 32899");
     }
 
     [Benchmark]
-    public int PartialTokenInitialismRatioClassic()
+    public double PartialTokenInitialismRatioClassic()
     {
         return Classic.Fuzz.PartialTokenInitialismRatio("NASA", "National Aeronautics Space Administration, Kennedy Space Center, Cape Canaveral, Florida 32899");
     }

FuzzySharp.Benchmarks/PartialTokenSetRatioBenchmarks.cs

@@ -18,25 +18,25 @@ public void GlobalSetup()
     }
 
     [Benchmark]
-    public int PartialTokenSetRatio()
+    public double PartialTokenSetRatio()
     {
         return Fuzz.PartialTokenSetRatio("fuzzy was a bear", "fuzzy fuzzy fuzzy bear");
     }
 
     [Benchmark]
-    public int PartialTokenSetRatioClassic()
+    public double PartialTokenSetRatioClassic()
     {
         return Classic.Fuzz.PartialTokenSetRatio("fuzzy was a bear", "fuzzy fuzzy fuzzy bear");
     }
 
     [Benchmark]
-    public int PartialTokenSetRatioCached()
+    public double PartialTokenSetRatioCached()
     {
         return new CachedPartialTokenSetScorer("fuzzy was a bear").Score("fuzzy fuzzy fuzzy bear");
     }
 
     [Benchmark]
-    public int PartialTokenSetRatioAcrossRunsCached()
+    public double PartialTokenSetRatioAcrossRunsCached()
     {
         return _cachedPartialTokenSetScorer.Score("fuzzy fuzzy fuzzy bear");
     }

FuzzySharp.Benchmarks/PartialTokenSortRatioBenchmarks.cs

@@ -8,13 +8,13 @@ namespace Raffinert.FuzzySharp.Benchmarks;
 public class PartialTokenSortRatioBenchmarks
 {
     [Benchmark]
-    public int PartialTokenSortRatio()
+    public double PartialTokenSortRatio()
     {
         return Fuzz.PartialTokenSortRatio("order words out of", "  words out of order");
     }
 
     [Benchmark]
-    public int PartialTokenSortRatioClassic()
+    public double PartialTokenSortRatioClassic()
     {
         return Classic.Fuzz.PartialTokenSortRatio("order words out of", "  words out of order");
     }