Add FuzzySharp for NER

Author: Yanan Wang

BotSharp.sln

@@ -149,6 +149,8 @@ Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "BotSharp.Plugin.ExcelHandle
 EndProject
 Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "BotSharp.Plugin.ImageHandler", "src\Plugins\BotSharp.Plugin.ImageHandler\BotSharp.Plugin.ImageHandler.csproj", "{242F2D93-FCCE-4982-8075-F3052ECCA92C}"
 EndProject
+Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "BotSharp.Plugin.FuzzySharp", "src\Plugins\BotSharp.Plugin.FuzzySharp\BotSharp.Plugin.FuzzySharp.csproj", "{E7C243B9-E751-B3B4-8F16-95C76CA90D31}"
+EndProject
 Global
 	GlobalSection(SolutionConfigurationPlatforms) = preSolution
 		Debug|Any CPU = Debug|Any CPU
@@ -629,6 +631,14 @@ Global
 		{242F2D93-FCCE-4982-8075-F3052ECCA92C}.Release|Any CPU.Build.0 = Release|Any CPU
 		{242F2D93-FCCE-4982-8075-F3052ECCA92C}.Release|x64.ActiveCfg = Release|Any CPU
 		{242F2D93-FCCE-4982-8075-F3052ECCA92C}.Release|x64.Build.0 = Release|Any CPU
+		{E7C243B9-E751-B3B4-8F16-95C76CA90D31}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{E7C243B9-E751-B3B4-8F16-95C76CA90D31}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{E7C243B9-E751-B3B4-8F16-95C76CA90D31}.Debug|x64.ActiveCfg = Debug|Any CPU
+		{E7C243B9-E751-B3B4-8F16-95C76CA90D31}.Debug|x64.Build.0 = Debug|Any CPU
+		{E7C243B9-E751-B3B4-8F16-95C76CA90D31}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{E7C243B9-E751-B3B4-8F16-95C76CA90D31}.Release|Any CPU.Build.0 = Release|Any CPU
+		{E7C243B9-E751-B3B4-8F16-95C76CA90D31}.Release|x64.ActiveCfg = Release|Any CPU
+		{E7C243B9-E751-B3B4-8F16-95C76CA90D31}.Release|x64.Build.0 = Release|Any CPU
 	EndGlobalSection
 	GlobalSection(SolutionProperties) = preSolution
 		HideSolutionNode = FALSE
@@ -701,6 +711,7 @@ Global
 		{0428DEAA-E4FE-4259-A6D8-6EDD1A9D0702} = {51AFE054-AE99-497D-A593-69BAEFB5106F}
 		{FC63C875-E880-D8BB-B8B5-978AB7B62983} = {51AFE054-AE99-497D-A593-69BAEFB5106F}
 		{242F2D93-FCCE-4982-8075-F3052ECCA92C} = {51AFE054-AE99-497D-A593-69BAEFB5106F}
+		{E7C243B9-E751-B3B4-8F16-95C76CA90D31} = {51AFE054-AE99-497D-A593-69BAEFB5106F}
 	EndGlobalSection
 	GlobalSection(ExtensibilityGlobals) = postSolution
 		SolutionGuid = {A9969D89-C98B-40A5-A12B-FC87E55B3A19}

src/Infrastructure/BotSharp.Abstraction/FuzzSharp/Arguments/TextAnalysisRequest.cs

@@ -13,8 +13,8 @@ public class TextAnalysisRequest
         /// <summary>
         /// Folder path containing CSV files (will read all .csv files from the folder or its 'output' subfolder)
         /// </summary>
-        [JsonPropertyName("vocabulary_folder_path")]
-        public string? VocabularyFolderPath { get; set; }
+        [JsonPropertyName("vocabulary_folder_name")]
+        public string? VocabularyFolderName { get; set; }
 
         /// <summary>
         /// Domain term mapping CSV file

src/Plugins/BotSharp.Plugin.FuzzySharp/BotSharp.Plugin.FuzzySharp.csproj

@@ -1,9 +1,13 @@
 <Project Sdk="Microsoft.NET.Sdk">
 
   <PropertyGroup>
-    <TargetFramework>net8.0</TargetFramework>
-    <ImplicitUsings>enable</ImplicitUsings>
+    <TargetFramework>$(TargetFramework)</TargetFramework>
     <Nullable>enable</Nullable>
+    <LangVersion>$(LangVersion)</LangVersion>
+    <VersionPrefix>$(BotSharpVersion)</VersionPrefix>
+    <GeneratePackageOnBuild>$(GeneratePackageOnBuild)</GeneratePackageOnBuild>
+    <GenerateDocumentationFile>$(GenerateDocumentationFile)</GenerateDocumentationFile>
+    <OutputPath>$(SolutionDir)packages</OutputPath>
   </PropertyGroup>
 
   <ItemGroup>

src/Plugins/BotSharp.Plugin.FuzzySharp/Constants/FuzzyMatcher.cs

@@ -8,20 +8,23 @@ public static class TextConstants
         /// Includes: parentheses, brackets, braces, punctuation marks, special symbols, etc.
         /// This ensures "(IH)" is split into "(", "IH", ")"
         /// </summary>
-        public static readonly char[] TokenSeparationChars =
+        public static readonly char[] SeparatorChars =
         {
             // Parentheses and brackets
             '(', ')', '[', ']', '{', '}',
             // Punctuation marks
             ',', '.', ';', ':', '!', '?',
             // Special symbols
-            '=', '@', '#', '$', '%', '^', '&', '*', '+', '-', '/', '\\', '|', '<', '>', '~', '`'
+            '=', '@', '#', '$', '%', '^', '&', '*', '+', '-', '\\', '|', '<', '>', '~', '`'
         };
 
         /// <summary>
-        /// Text separators used for tokenization and n-gram processing
-        /// Includes: equals, colon, semicolon, question mark, exclamation mark, comma, period
+        /// Whitespace characters used as token separators during tokenization.
+        /// Includes: space, tab, newline, and carriage return.
         /// </summary>
-        public static readonly char[] SeparatorChars = { '=', ':', ';', '?', '!', ',', '.' };
+        public static readonly char[] TokenSeparators =
+        {
+            ' ', '\t', '\n', '\r'
+        };
     }
 }