rearrange

Directory.Build.props

@@ -0,0 +1,27 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="15.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+
+  <PropertyGroup>
+    <Authors>Russ Cam and Contributors</Authors>
+    <Copyright>Russ Cam</Copyright>
+    <PackageLicenseExpression>Apache-2.0</PackageLicenseExpression>
+    <RepositoryUrl>https://github.com/russcam/lingua-dotnet</RepositoryUrl>
+    <PackageProjectUrl>https://github.com/russcam/lingua-dotnet</PackageProjectUrl>
+    <PackageReleaseNotes>https://github.com/russcam/lingua-dotnet/releases</PackageReleaseNotes>
+    <PackageTags>lingua, language detection</PackageTags>
+    <SolutionRoot>$([MSBuild]::GetDirectoryNameOfFileAbove($(MSBuildThisFileDirectory), Lingua.sln))</SolutionRoot>
+<!--    <AssemblyOriginatorKeyFile>$(SolutionRoot)build\keys\keypair.snk</AssemblyOriginatorKeyFile>-->
+<!--    <PublicKey>97ab15215fab2a5d</PublicKey>-->
+    <LangVersion>latest</LangVersion>
+<!--    <TreatWarningsAsErrors>true</TreatWarningsAsErrors>-->
+    <IsPackable>False</IsPackable>
+    <Nullable>enable</Nullable>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <MinVerMinimumMajorMinor>1.0</MinVerMinimumMajorMinor>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="MinVer" Version="4.3.0" PrivateAssets="all"/>
+  </ItemGroup>
+
+</Project>

Lingua.sln

@@ -2,10 +2,20 @@
 Microsoft Visual Studio Solution File, Format Version 12.00
 Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "Lingua", "src\Lingua\Lingua.csproj", "{835F7E5D-80DB-40FC-9240-DE251FAE63DC}"
 EndProject
-Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "UnicodeScriptGenerator", "src\UnicodeScriptGenerator\UnicodeScriptGenerator.csproj", "{77954C87-8D00-40FA-9617-DFAF3499DE9C}"
+Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "UnicodeScriptGenerator", "build\UnicodeScriptGenerator\UnicodeScriptGenerator.csproj", "{77954C87-8D00-40FA-9617-DFAF3499DE9C}"
 EndProject
 Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "Lingua.Tests", "tests\Lingua.Tests\Lingua.Tests.csproj", "{120D07F4-AAF1-4D00-BF86-48836F819C1F}"
 EndProject
+Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "Solution Root", "Solution Root", "{C4287977-4407-47E3-A452-57DB92BC5432}"
+	ProjectSection(SolutionItems) = preProject
+		.editorconfig = .editorconfig
+		.gitattributes = .gitattributes
+		.gitignore = .gitignore
+		global.json = global.json
+		README.md = README.md
+		Directory.Build.props = Directory.Build.props
+	EndProjectSection
+EndProject
 Global
 	GlobalSection(SolutionConfigurationPlatforms) = preSolution
 		Debug|Any CPU = Debug|Any CPU

src/UnicodeScriptGenerator/Program.cs → build/UnicodeScriptGenerator/Program.cs

@@ -23,6 +23,7 @@ public static async Task Main(string[] args)
 		var firstLine = File.ReadLines(fileName).First();
 		var version = VersionRegex().Match(firstLine).Groups[1].Value;
 		var builder = new StringBuilder($@"using System.Globalization;
+using static Lingua.UnicodeScript;
 
 namespace Lingua;
 
@@ -56,7 +57,7 @@ public static class CharExtensions
 		for (var i = 0; i < orderedScripts.Count; i++)
 		{
 			builder.AppendLine(
-				$"        0x{orderedScripts[i].CodePointRange.Start.ToString("X4")}, // {orderedScripts[i].CodePointRange.Start.ToString("X4")}..{orderedScripts[i].CodePointRange.End.ToString("X4")}; {orderedScripts[i].Name}");
+				$"        0x{orderedScripts[i].CodePointRange.Start.ToString("X4")}, // {orderedScripts[i].CodePointRange.ToString()}; {orderedScripts[i].Name}");
 		}
 
 		builder.AppendLine(@"    };
@@ -67,7 +68,7 @@ public static class CharExtensions
 		for (var i = 0; i < orderedScripts.Count; i++)
 		{
 			builder.AppendLine(
-				$"        UnicodeScript.{orderedScripts[i].Name.Replace("_", "")},\t// {orderedScripts[i].CodePointRange.Start.ToString("X4")}..{orderedScripts[i].CodePointRange.End.ToString("X4")}");
+				$"        {orderedScripts[i].Name.Replace("_", "")},\t// {orderedScripts[i].CodePointRange.ToString()}");
 		}
 
 		builder.AppendLine(@"    };
@@ -118,18 +119,18 @@ private static string FindSolutionRoot()
 			$"Could not find solution root directory from the current directory {startDir}");
 	}
 
-	private static List<((int Start, int End)[] CodePointRanges, string Name)> ReadUnicodeScriptsFromFile(
+	private static List<(CodePointRange[] CodePointRanges, string Name)> ReadUnicodeScriptsFromFile(
 		string fileName)
 	{
 		using var stream = File.OpenRead(fileName);
 		using var reader = new UnicodeDataFileReader(stream, ';');
-		var unicodeScripts = new List<((int, int)[], string)>();
-		var unicodePointRanges = new List<(int, int)>(100);
+		var unicodeScripts = new List<(CodePointRange[], string)>();
+		var unicodePointRanges = new List<CodePointRange>(100);
 		string? name = null;
 
 		while (reader.MoveToNextLine())
 		{
-			var unicodeCodePointRange = ParseCodepointRange(reader.ReadField());
+			var unicodeCodePointRange = ParseCodepointRange(reader.ReadField()!);
 			var currentName = reader.ReadTrimmedField();
 			if (name == null || name.Equals(currentName, StringComparison.OrdinalIgnoreCase))
 			{
@@ -149,7 +150,7 @@ private static string FindSolutionRoot()
 		return unicodeScripts;
 	}
 
-	private static (int, int) ParseCodepointRange(string range)
+	private static CodePointRange ParseCodepointRange(string range)
 	{
 		int start, end;
 		var rangeSeparatorOffset = range.IndexOf("..", StringComparison.InvariantCulture);
@@ -166,18 +167,18 @@ private static (int, int) ParseCodepointRange(string range)
 				break;
 		}
 
-		return (start, end);
+		return new(start, end);
 	}
 
-	private static List<((int Start, int End) CodePointRange, string Name)> CreateCollapsedOrderedRange(
-		List<((int Start, int End)[] CodePointRanges, string Name)> unicodeScripts)
+	private static List<(CodePointRange CodePointRange, string Name)> CreateCollapsedOrderedRange(
+		List<(CodePointRange[] CodePointRanges, string Name)> unicodeScripts)
 	{
-		List<((int Start, int End) CodePointRange, string Name)> orderedScripts = unicodeScripts
+		List<(CodePointRange CodePointRange, string Name)> orderedScripts = unicodeScripts
 			.SelectMany(s => s.CodePointRanges.Select(range => (range, s.Name)))
 			.OrderBy(v => v.range.Start)
 			.ToList();
 
-		List<((int Start, int End) CodePointRange, string Name)> orderedScriptsWithUnknownInsertions =
+		List<(CodePointRange CodePointRange, string Name)> orderedScriptsWithUnknownInsertions =
 			new(orderedScripts.Count);
 		var currentRangeStart = orderedScripts[0].CodePointRange.Start;
 		var currentRangeEnd = orderedScripts[0].CodePointRange.End;
@@ -199,11 +200,11 @@ private static (int, int) ParseCodepointRange(string range)
 			else
 			{
 				// Add the current collapsed range to the result
-				orderedScriptsWithUnknownInsertions.Add(((currentRangeStart, currentRangeEnd), currentScriptName));
+				orderedScriptsWithUnknownInsertions.Add((new(currentRangeStart, currentRangeEnd), currentScriptName));
 
 				// If there's a gap between the current range's end and the next range's start, add an Unknown range
 				if (nextRangeStart > currentRangeEnd + 1)
-					orderedScriptsWithUnknownInsertions.Add(((currentRangeEnd + 1, nextRangeStart - 1), "Unknown"));
+					orderedScriptsWithUnknownInsertions.Add((new(currentRangeEnd + 1, nextRangeStart - 1), "Unknown"));
 
 				// Update currentRangeStart and currentRangeEnd
 				currentRangeStart = nextRangeStart;
@@ -214,12 +215,19 @@ private static (int, int) ParseCodepointRange(string range)
 
 		// Add the last collapsed range to the result
 		orderedScriptsWithUnknownInsertions
-			.Add(((currentRangeStart, currentRangeEnd), currentScriptName));
+			.Add((new(currentRangeStart, currentRangeEnd), currentScriptName));
 
 		// Add Unknown to cover the remaining range
 		orderedScriptsWithUnknownInsertions
-			.Add(((orderedScripts[^1].CodePointRange.End + 1, 0x10FFFF), "Unknown"));
+			.Add((new(orderedScripts[^1].CodePointRange.End + 1, 0x10FFFF), "Unknown"));
 
 		return orderedScriptsWithUnknownInsertions;
 	}
 }
+
+public readonly record struct CodePointRange(int Start, int End)
+{
+	public override string ToString() => Start == End
+		? Start.ToString("X4")
+		: $"{Start:X4}..{End:X4}";
+}

src/Directory.Build.props

@@ -0,0 +1,28 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="15.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+  <Import Project="$([MSBuild]::GetPathOfFileAbove('Directory.Build.props', '$(MSBuildThisFileDirectory)../'))"/>
+  <PropertyGroup>
+    <IsPackable>true</IsPackable>
+    <!-- <SignAssembly>true</SignAssembly> -->
+    <PackageIcon>nuget-icon.png</PackageIcon>
+    <PackageReadmeFile>README.md</PackageReadmeFile>
+    <AllowedOutputExtensionsInPackageBuildOutputFolder>$(AllowedOutputExtensionsInPackageBuildOutputFolder);.pdb</AllowedOutputExtensionsInPackageBuildOutputFolder>
+    <GenerateDocumentationFile>true</GenerateDocumentationFile>
+    <DebugSymbols>true</DebugSymbols>
+    <PublishRepositoryUrl>true</PublishRepositoryUrl>
+    <EmbedUntrackedSources>true</EmbedUntrackedSources>
+    <ContinuousIntegrationBuild>true</ContinuousIntegrationBuild>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <None Include="$(SolutionRoot)README.md" Pack="true" PackagePath="." />
+    <None Include="$(SolutionRoot)LICENSE" Pack="true" PackagePath="." />
+    <None Include="$(SolutionRoot)\images\nuget-icon.png" Pack="true" PackagePath="." />
+  </ItemGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Microsoft.SourceLink.GitHub" Version="1.1.1" PrivateAssets="All"/>
+    <PackageReference Include="ConfigureAwaitChecker.Analyzer" Version="5.0.0.1" PrivateAssets="All" />
+    <PackageReference Include="SauceControl.InheritDoc" Version="1.3.0" PrivateAssets="All" />
+  </ItemGroup>
+</Project>

src/Lingua/Internal/Ngram.cs

@@ -2,10 +2,18 @@
 
 namespace Lingua.Internal;
 
+/// <summary>
+/// A connected string of N items from a sample of text.
+/// </summary>
 public readonly struct Ngram : IEquatable<Ngram>
 {
     private readonly string _value;
 
+    /// <summary>
+    /// Initializes a new instance of <see cref="Ngram"/>
+    /// </summary>
+    /// <param name="value">The sample of text.</param>
+    /// <exception cref="ArgumentException">If <paramref name="value"/> is greater than 5</exception>
     public Ngram(string value)
     {
         if (value.Length > 5)
@@ -14,25 +22,44 @@ public Ngram(string value)
         _value = value;
     }
 
+    /// <summary>
+    /// An Ngram of zero length
+    /// </summary>
     public static readonly Ngram Zerogram = new("");
 
+    /// <summary>
+    /// Whether value is empty.
+    /// </summary>
     public bool IsEmpty => _value.Length == 0;
 
+    /// <summary>
+    /// Gets the length of the value.
+    /// </summary>
     public int Length => _value.Length;
 
+    /// <summary>
+    /// Decrements and returns a new instance of an <see cref="Ngram"/> that is a substring of this instance.
+    /// </summary>
+    /// <returns>A new instance of <see cref="Ngram"/></returns>
+    /// <exception cref="InvalidOperationException">If the Ngram has a length of 0.</exception>
     public Ngram Dec() =>
 	    _value.Length switch
 	    {
-		    0 => throw new Exception("Zerogram is ngram type of lowest order and can not be decremented"),
+		    0 => throw new InvalidOperationException("Zerogram is ngram type of lowest order and can not be decremented"),
 		    1 => Zerogram,
 		    _ => new Ngram(_value.Substring(0, _value.Length - 1))
 	    };
 
+    /// <inheritdoc />
     public override string ToString() => _value;
+
+    /// <inheritdoc />
     public bool Equals(Ngram other) => _value == other._value;
 
+    /// <inheritdoc />
     public override bool Equals(object? obj) => obj is Ngram other && Equals(other);
 
+    /// <inheritdoc />
     public override int GetHashCode() => _value.GetHashCode();
 
     public IEnumerable<Ngram> RangeOfLowerOrderNGrams() =>
@@ -50,7 +77,7 @@ internal static string GetNgramNameByLength(int ngramLength) =>
 	    };
 }
 
-public class NgramEnumerable : IEnumerable<Ngram>
+public struct NgramEnumerable : IEnumerable<Ngram>
 {
     private readonly Ngram _start;
 
@@ -62,18 +89,24 @@ public NgramEnumerable(Ngram start, Ngram endInclusive)
         _start = start;
     }
 
+    /// <inheritdoc />
     public IEnumerator<Ngram> GetEnumerator() => new NgramEnumerator(_start);
 
     IEnumerator IEnumerable.GetEnumerator() => GetEnumerator();
 }
 
-public class NgramEnumerator : IEnumerator<Ngram>
+public struct NgramEnumerator : IEnumerator<Ngram>
 {
     private readonly Ngram _start;
     private Ngram? _current;
 
+    /// <summary>
+    /// Initializes a new instance of <see cref="NgramEnumerator"/>
+    /// </summary>
+    /// <param name="start"></param>
     public NgramEnumerator(Ngram start) => _start = start;
 
+    /// <inheritdoc />
     public bool MoveNext()
     {
         if (_current is null)
@@ -89,12 +122,15 @@ public bool MoveNext()
         return !_current.Value.IsEmpty;
     }
 
+    /// <inheritdoc />
     public void Reset() => _current = null;
 
+    /// <inheritdoc />
     public Ngram Current => _current!.Value;
 
     object IEnumerator.Current => Current;
 
+    /// <inheritdoc />
     public void Dispose()
     {
     }

src/Lingua/Internal/TestDataLanguageModel.cs

@@ -2,28 +2,25 @@
 
 namespace Lingua.Internal;
 
-public record TestDataLanguageModel(HashSet<Ngram> Ngrams)
+public partial record struct TestDataLanguageModel(HashSet<Ngram> Ngrams)
 {
-    private static readonly Regex LetterRegex = new("^\\p{L}+$", RegexOptions.Compiled);
+	[GeneratedRegex("^\\p{L}+$")]
+    private static partial Regex LetterRegex();
 
     public static TestDataLanguageModel FromText(string text, int ngramLength)
     {
         if (ngramLength is < 1 or > 5)
-        {
-            throw new ArgumentException($"ngram length {ngramLength} is not in range 1..5");
-        }
+	        throw new ArgumentOutOfRangeException(nameof(ngramLength),$"ngram length {ngramLength} is not in range 1..5");
 
         var ngrams = new HashSet<Ngram>();
         var textSpan = text.AsSpan();
         for (var i = 0; i <= text.Length - ngramLength; i++)
         {
             var textSlice = textSpan.Slice(i, ngramLength);
-            if (LetterRegex.IsMatch(textSlice))
-            {
-                ngrams.Add(new Ngram(textSlice.ToString()));
-            }
+            if (LetterRegex().IsMatch(textSlice))
+	            ngrams.Add(new Ngram(textSlice.ToString()));
         }
 
-        return new TestDataLanguageModel(ngrams);
+        return new(ngrams);
     }
-}
+}

src/Lingua/Lingua.csproj

@@ -1,10 +1,9 @@
 <Project Sdk="Microsoft.NET.Sdk">
 
     <PropertyGroup>
+        <Title>Lingua</Title>
+        <Description>Natural language detection library for .NET, suitable for long and short text alike</Description>
         <TargetFramework>net8.0</TargetFramework>
-        <RootNamespace>Lingua</RootNamespace>
-        <ImplicitUsings>enable</ImplicitUsings>
-        <Nullable>enable</Nullable>
     </PropertyGroup>
 
     <ItemGroup>
@@ -19,9 +18,8 @@
     </ItemGroup>
 
     <ItemGroup>
-        <AssemblyAttribute Include="System.Runtime.CompilerServices.InternalsVisibleToAttribute">
-            <_Parameter1>$(AssemblyName).Tests</_Parameter1>
-        </AssemblyAttribute>
+<!--      <InternalsVisibleTo Include="$(AssemblyName).Tests" Key="$(PublicKey)" />-->
+      <InternalsVisibleTo Include="$(AssemblyName).Tests" />
     </ItemGroup>
 
 </Project>