Performance optimization

FuzzySharp.Benchmarks/BenchmarkAll.cs

@@ -0,0 +1,120 @@
+using BenchmarkDotNet.Attributes;
+using FuzzySharp.Extractor;
+using FuzzySharp.PreProcess;
+
+namespace FuzzySharp.Benchmarks;
+
+[MemoryDiagnoser]
+public class BenchmarkAll
+{
+    [Benchmark]
+    public int Ratio1()
+    {
+        return Fuzz.Ratio("mysmilarstring", "myawfullysimilarstirng");
+    }
+
+    [Benchmark]
+    public int Ratio2()
+    {
+        return Fuzz.Ratio("mysmilarstring", "mysimilarstring");
+    }
+
+    [Benchmark]
+    public int PartialRatio()
+    {
+        return Fuzz.PartialRatio("similar", "somewhresimlrbetweenthisstring");
+    }
+
+    [Benchmark]
+    public int TokenSortRatio()
+    {
+        return Fuzz.TokenSortRatio("order words out of", "  words out of order");
+    }
+
+    [Benchmark]
+    public int PartialTokenSortRatio()
+    {
+        return Fuzz.PartialTokenSortRatio("order words out of", "  words out of order");
+    }
+
+    [Benchmark]
+    public int TokenSetRatio()
+    {
+        return Fuzz.TokenSetRatio("fuzzy was a bear", "fuzzy fuzzy fuzzy bear");
+    }
+
+    [Benchmark]
+    public int PartialTokenSetRatio()
+    {
+        return Fuzz.PartialTokenSetRatio("fuzzy was a bear", "fuzzy fuzzy fuzzy bear");
+    }
+
+    [Benchmark]
+    public int WeightedRatio()
+    {
+        return Fuzz.WeightedRatio("The quick brown fox jimps ofver the small lazy dog", "the quick brown fox jumps over the small lazy dog");
+    }
+
+    [Benchmark]
+    public int TokenInitialismRatio1()
+    {
+        return Fuzz.TokenInitialismRatio("NASA", "National Aeronautics and Space Administration");
+    }
+
+    [Benchmark]
+    public int TokenInitialismRatio2()
+    {
+        return Fuzz.TokenInitialismRatio("NASA", "National Aeronautics Space Administration");
+    }
+
+    [Benchmark]
+    public int TokenInitialismRatio3()
+    {
+        return Fuzz.TokenInitialismRatio("NASA", "National Aeronautics Space Administration, Kennedy Space Center, Cape Canaveral, Florida 32899");
+    }
+
+    [Benchmark]
+    public int PartialTokenInitialismRatio()
+    {
+        return Fuzz.PartialTokenInitialismRatio("NASA", "National Aeronautics Space Administration, Kennedy Space Center, Cape Canaveral, Florida 32899");
+    }
+
+    [Benchmark]
+    public int TokenAbbreviationRatio()
+    {
+        return Fuzz.TokenAbbreviationRatio("bl 420", "Baseline section 420", PreprocessMode.Full);
+    }
+
+    [Benchmark]
+    public int PartialTokenAbbreviationRatio()
+    {
+        return Fuzz.PartialTokenAbbreviationRatio("bl 420", "Baseline section 420", PreprocessMode.Full);
+    }
+
+    private static readonly string[][] Events =
+    [
+        ["chicago cubs vs new york mets", "CitiField", "2011-05-11", "8pm"],
+        ["new york yankees vs boston red sox", "Fenway Park", "2011-05-11", "8pm"],
+        ["atlanta braves vs pittsburgh pirates", "PNC Park", "2011-05-11", "8pm"]
+    ];
+
+    private static readonly string[] Query = ["new york mets vs chicago cubs", "CitiField", "2017-03-19", "8pm"];
+
+    [Benchmark]
+    public ExtractedResult<string[]> ExtractOne()
+    {
+        return Process.ExtractOne(Query, Events, static strings => strings[0]);
+    }
+
+    [Benchmark]
+    public int LevenshteinDistance()
+    {
+        return Levenshtein.EditDistance("chicago cubs vs new york mets".AsSpan(), "new york mets vs chicago cubs".AsSpan());
+    }
+
+    [Benchmark]
+    public int FastenshteinDistance()
+    {
+        return Fastenshtein.Levenshtein.Distance("chicago cubs vs new york mets", "new york mets vs chicago cubs");
+    }
+}

FuzzySharp.Benchmarks/FuzzySharp.Benchmarks.csproj

@@ -0,0 +1,19 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>net8.0</TargetFramework>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <Nullable>enable</Nullable>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="BenchmarkDotNet" Version="0.14.0" />
+    <PackageReference Include="Fastenshtein" Version="1.0.10" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <ProjectReference Include="..\FuzzySharp\FuzzySharp.csproj" />
+  </ItemGroup>
+
+</Project>

FuzzySharp.Benchmarks/Program.cs

@@ -0,0 +1,6 @@
+using BenchmarkDotNet.Running;
+using FuzzySharp;
+
+BenchmarkRunner.Run(typeof(Program).Assembly);
+
+//Console.WriteLine(Fuzz.WeightedRatio("The quick brown fox jimps ofver the small lazy dog", "the quick brown fox jumps over the small lazy dog"));

FuzzySharp.Test/EvaluationTests/EvaluationTests.cs

@@ -36,20 +36,20 @@ public void Evaluate()
 
 
 
-            var h1 = Process.ExtractOne("cowboys", new[] { "Atlanta Falcons", "New York Jets", "New York Giants", "Dallas Cowboys" });
-            var h2 = string.Join(", ", Process.ExtractTop("goolge", new[] { "google", "bing", "facebook", "linkedin", "twitter", "googleplus", "bingnews", "plexoogl" }, limit: 3));
-            var h3 = string.Join(", ", Process.ExtractAll("goolge", new [] {"google", "bing", "facebook", "linkedin", "twitter", "googleplus", "bingnews", "plexoogl" }));
-            var h4 = string.Join(", ", Process.ExtractAll("goolge", new[] { "google", "bing", "facebook", "linkedin", "twitter", "googleplus", "bingnews", "plexoogl" }, cutoff: 40));
-            var h5 = string.Join(", ", Process.ExtractSorted("goolge", new [] {"google", "bing", "facebook", "linkedin", "twitter", "googleplus", "bingnews", "plexoogl" }));
-
-            var i1 = Process.ExtractOne("cowboys", new[] { "Atlanta Falcons", "New York Jets", "New York Giants", "Dallas Cowboys" }, s => s, ScorerCache.Get<DefaultRatioScorer>());
-
-            var events = new[]
-            {
-                new[] { "chicago cubs vs new york mets", "CitiField", "2011-05-11", "8pm" },
-                new[] { "new york yankees vs boston red sox", "Fenway Park", "2011-05-11", "8pm" },
-                new[] { "atlanta braves vs pittsburgh pirates", "PNC Park", "2011-05-11", "8pm" },
-            };
+            var h1 = Process.ExtractOne("cowboys", ["Atlanta Falcons", "New York Jets", "New York Giants", "Dallas Cowboys"]);
+            var h2 = string.Join(", ", Process.ExtractTop("goolge", ["google", "bing", "facebook", "linkedin", "twitter", "googleplus", "bingnews", "plexoogl"], limit: 3));
+            var h3 = string.Join(", ", Process.ExtractAll("goolge", ["google", "bing", "facebook", "linkedin", "twitter", "googleplus", "bingnews", "plexoogl"]));
+            var h4 = string.Join(", ", Process.ExtractAll("goolge", ["google", "bing", "facebook", "linkedin", "twitter", "googleplus", "bingnews", "plexoogl"], cutoff: 40));
+            var h5 = string.Join(", ", Process.ExtractSorted("goolge", ["google", "bing", "facebook", "linkedin", "twitter", "googleplus", "bingnews", "plexoogl"]));
+
+            var i1 = Process.ExtractOne("cowboys", ["Atlanta Falcons", "New York Jets", "New York Giants", "Dallas Cowboys"], s => s, ScorerCache.Get<DefaultRatioScorer>());
+
+            string[][] events =
+            [
+                ["chicago cubs vs new york mets", "CitiField", "2011-05-11", "8pm"],
+                ["new york yankees vs boston red sox", "Fenway Park", "2011-05-11", "8pm"],
+                ["atlanta braves vs pittsburgh pirates", "PNC Park", "2011-05-11", "8pm"]
+            ];
             var query = new[] { "new york mets vs chicago cubs", "CitiField", "2017-03-19", "8pm" };
 
             var best = Process.ExtractOne(query, events, strings => strings[0]);

FuzzySharp.Test/FuzzySharp.Test.csproj

@@ -1,19 +1,19 @@
 <Project Sdk="Microsoft.NET.Sdk">
 
   <PropertyGroup>
-    <TargetFramework>netcoreapp3.1</TargetFramework>
-
+    <TargetFrameworks>NET8.0;netcoreapp3.1;netframework4.7.2</TargetFrameworks>
     <IsPackable>false</IsPackable>
+	<LangVersion>12.0</LangVersion>
   </PropertyGroup>
 
   <ItemGroup>
     <PackageReference Include="nunit" Version="3.12.0" />
     <PackageReference Include="NUnit.Console" Version="3.11.1" />
-    <PackageReference Include="NUnit3TestAdapter" Version="3.16.1">
+    <PackageReference Include="NUnit3TestAdapter" Version="4.6.0">
       <PrivateAssets>all</PrivateAssets>
       <IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
     </PackageReference>
-    <PackageReference Include="Microsoft.NET.Test.Sdk" Version="16.4.0" />
+    <PackageReference Include="Microsoft.NET.Test.Sdk" Version="17.10.0" />
   </ItemGroup>
 
   <ItemGroup>

FuzzySharp.Test/FuzzyTests/RegressionTests.cs

@@ -12,43 +12,37 @@ namespace FuzzySharp.Test.FuzzyTests
     public class RegressionTests
     {
 
-
         /// <summary>
         /// Test to ensure that all IRatioScorer implementations handle scoring empty strings & whitespace strings
         /// </summary>
         [Test]
         public void TestScoringEmptyString()
         {
-
             var scorerType = typeof(IRatioScorer);
             var assemblies = AppDomain.CurrentDomain.GetAssemblies().ToList();
             var types = assemblies.SelectMany(s =>
             {
-                Type[] types = new Type[] { }; ;
                 try
                 {
-                    types = s.GetTypes();
+                    return s.GetTypes();
                 }
                 catch {}
-                return types;
+                return [];
             }).ToList();
             var scorerTypes = types.Where(t => scorerType.IsAssignableFrom(t) && !t.IsAbstract && t.IsClass).ToList();
-            //var scorerTypes = AppDomain.CurrentDomain.GetAssemblies().SelectMany(s => s.GetTypes()).Where(p => scorerType.IsAssignableFrom(p) && p.IsClass && !p.IsAbstract);
-
-
-            MethodInfo getScorerCacheMethodInfo = typeof(ScorerCache).GetMethod("Get");
-
+
             string nullString = null;  //Null doesnt seem to be handled by any scorer
             string emptyString = "";
             string whitespaceString = " ";
 
-            string[] nullOrWhitespaceStrings = { emptyString, whitespaceString };
+            string[] nullOrWhitespaceStrings = [emptyString, whitespaceString];
+            MethodInfo getScorerCacheMethodInfo = typeof(ScorerCache).GetMethod("Get");
 
-            foreach (Type t in scorerTypes)
+            foreach (var t in scorerTypes)
             {
                 System.Diagnostics.Debug.WriteLine($"Testing {t.Name}");
                 MethodInfo m = getScorerCacheMethodInfo.MakeGenericMethod(t);
-                IRatioScorer scorer = m.Invoke(this, new object[] { }) as IRatioScorer;
+                IRatioScorer scorer = m.Invoke(this, []) as IRatioScorer;
 
                 foreach(string s in nullOrWhitespaceStrings)
                 {
@@ -79,7 +73,6 @@ public void TestScoringEmptyString()
 
                 }
 
-
             }
 
         }

FuzzySharp.Test/FuzzyTests/ScorerTests/TokenSetScorerBaseTest.cs

@@ -2,9 +2,6 @@
 using FuzzySharp.SimilarityRatio.Scorer;
 using FuzzySharp.SimilarityRatio.Scorer.StrategySensitive;
 using NUnit.Framework;
-using System;
-using System.Collections.Generic;
-using System.Text;
 
 namespace FuzzySharp.Test.FuzzyTests.ScorerTests
 {

FuzzySharp.sln

@@ -1,11 +1,13 @@
 
 Microsoft Visual Studio Solution File, Format Version 12.00
-# Visual Studio Version 16
-VisualStudioVersion = 16.0.29806.167
+# Visual Studio Version 17
+VisualStudioVersion = 17.10.35122.118
 MinimumVisualStudioVersion = 10.0.40219.1
 Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "FuzzySharp", "FuzzySharp\FuzzySharp.csproj", "{348B90DA-DA44-45AD-B857-D3A69D05AE46}"
 EndProject
-Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "FuzzySharp.Test", "FuzzySharp.Test\FuzzySharp.Test.csproj", "{48F4C7CB-E669-410C-A455-DE3330347807}"
+Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "FuzzySharp.Test", "FuzzySharp.Test\FuzzySharp.Test.csproj", "{48F4C7CB-E669-410C-A455-DE3330347807}"
+EndProject
+Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "FuzzySharp.Benchmarks", "FuzzySharp.Benchmarks\FuzzySharp.Benchmarks.csproj", "{480CAE39-ACA7-411A-BF6B-72E61ED6E129}"
 EndProject
 Global
 	GlobalSection(SolutionConfigurationPlatforms) = preSolution
@@ -21,6 +23,10 @@ Global
 		{48F4C7CB-E669-410C-A455-DE3330347807}.Debug|Any CPU.Build.0 = Debug|Any CPU
 		{48F4C7CB-E669-410C-A455-DE3330347807}.Release|Any CPU.ActiveCfg = Release|Any CPU
 		{48F4C7CB-E669-410C-A455-DE3330347807}.Release|Any CPU.Build.0 = Release|Any CPU
+		{480CAE39-ACA7-411A-BF6B-72E61ED6E129}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{480CAE39-ACA7-411A-BF6B-72E61ED6E129}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{480CAE39-ACA7-411A-BF6B-72E61ED6E129}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{480CAE39-ACA7-411A-BF6B-72E61ED6E129}.Release|Any CPU.Build.0 = Release|Any CPU
 	EndGlobalSection
 	GlobalSection(SolutionProperties) = preSolution
 		HideSolutionNode = FALSE

FuzzySharp/Edits/MatchingBlock.cs

@@ -6,9 +6,6 @@ public class MatchingBlock
         public int DestPos { get; set; }
         public int Length { get; set; }
 
-        public override string ToString()
-        {
-            return $"({SourcePos},{DestPos},{Length})";
-        }
+        public override string ToString() => $"({SourcePos},{DestPos},{Length})";
     }
 }

FuzzySharp/Extensions/StringExtensions.cs

@@ -0,0 +1,67 @@
+using System;
+using System.Collections.Generic;
+
+namespace FuzzySharp.Extensions
+{
+    internal static class StringExtensions
+    {
+        public static List<string> ExtractTokens(this string input)
+        {
+            var result = new List<string>();
+
+            if (string.IsNullOrEmpty(input))
+                return result;
+
+            var span = input.AsSpan();
+
+            var start = 0;
+            for (var i = 0; i < span.Length; i++)
+            {
+                if (char.IsLetter(span[i])) continue;
+
+                if (i - start > 0)
+                {
+                    result.Add(span[start..i].ToString());
+                }
+
+                start = i+1;
+            }
+
+            if (span.Length - start > 0)
+                result.Add(span[start..].ToString());
+
+            return result;
+        }
+
+        public static string[] SplitByAnySpace(this string input)
+        {
+            if (string.IsNullOrWhiteSpace(input))
+                return [];
+
+            var words = input.Split(EmptyArray<char>(), StringSplitOptions.RemoveEmptyEntries);
+
+            return words;
+        }
+
+        public static string[] GetSortedWords(this string input)
+        {
+            var words = SplitByAnySpace(input);
+
+            Array.Sort(words);
+
+            return words;
+        }
+
+        public static string NormalizeSpacesAndSort(this string input)
+        {
+            var words = GetSortedWords(input);
+
+            return string.Join(" ", words);
+        }
+
+        private static T[] EmptyArray<T>()
+        {
+            return [];
+        }
+    }
+}

FuzzySharp/Extractor/ExtractedResult.cs

@@ -34,7 +34,7 @@ public override string ToString()
             {
                 return $"(string: {Value}, score: {Score}, index: {Index})";
             }
-            return $"(value: {Value.ToString()}, score: {Score}, index: {Index})";
+            return $"(value: {Value}, score: {Score}, index: {Index})";
         }
     }
 }