Release v 4.0.0

.github/workflows/dotnet-core.yml

@@ -15,10 +15,10 @@ jobs:
     runs-on: ${{ matrix.os }}
     steps:
     - uses: actions/checkout@v3
-    - name: Setup .NET 8.0
+    - name: Setup .NET 10.0
       uses: actions/setup-dotnet@v3
       with:
-        dotnet-version: 8.0.x
+        dotnet-version: 10.0.x
         include-prerelease: false
     - name: Install dependencies
       run: dotnet restore

CHANGELOG.md

@@ -1,4 +1,14 @@
-## v3.0.0 - 5 Feb 2024
+## v4.0.0 - 19 Dez 2025
+* Switch to .Net 10.0
+* Switch to C# 14
+* Code refactoring
+* Fix code example 7 and 8 in readme
+* Add tests for readme code examples
+* Adjust readme code example to use filePath instead of filename or path
+* Suppress warnings CA2022 and S2674 due to expected dynamic array length
+* Remove Serializable annotation from EncodingSecurityException
+
+## v3.0.0 - 5 Feb 2024
 * Switch to .Net 8.0
 * Updated dependencies
 * Improved error handling for empty and whitespace path

Documentation/upgrade_guide_3_0_0_to_4_0_x.md

@@ -0,0 +1,8 @@
+# Upgrade Guide v3.0.0 to v4.0.*
+
+No code changes required!
+
+### Dependency Change
+
+Now requires .Net 10.0
+

MagicFileEncoding.sln

@@ -1,22 +1,22 @@
-
-Microsoft Visual Studio Solution File, Format Version 12.00
-Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "MagicFileEncoding", "MagicFileEncoding\MagicFileEncoding.csproj", "{89C8EAD5-218B-46A8-8DE9-93783166F9FC}"
-EndProject
-Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "UnitTests", "UnitTests\UnitTests.csproj", "{83F84B60-DBC5-4738-AC63-4EFB547BF9F7}"
-EndProject
-Global
-	GlobalSection(SolutionConfigurationPlatforms) = preSolution
-		Debug|Any CPU = Debug|Any CPU
-		Release|Any CPU = Release|Any CPU
-	EndGlobalSection
-	GlobalSection(ProjectConfigurationPlatforms) = postSolution
-		{89C8EAD5-218B-46A8-8DE9-93783166F9FC}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
-		{89C8EAD5-218B-46A8-8DE9-93783166F9FC}.Debug|Any CPU.Build.0 = Debug|Any CPU
-		{89C8EAD5-218B-46A8-8DE9-93783166F9FC}.Release|Any CPU.ActiveCfg = Release|Any CPU
-		{89C8EAD5-218B-46A8-8DE9-93783166F9FC}.Release|Any CPU.Build.0 = Release|Any CPU
-		{83F84B60-DBC5-4738-AC63-4EFB547BF9F7}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
-		{83F84B60-DBC5-4738-AC63-4EFB547BF9F7}.Debug|Any CPU.Build.0 = Debug|Any CPU
-		{83F84B60-DBC5-4738-AC63-4EFB547BF9F7}.Release|Any CPU.ActiveCfg = Release|Any CPU
-		{83F84B60-DBC5-4738-AC63-4EFB547BF9F7}.Release|Any CPU.Build.0 = Release|Any CPU
-	EndGlobalSection
-EndGlobal
+
+Microsoft Visual Studio Solution File, Format Version 12.00
+Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "MagicFileEncoding", "MagicFileEncoding\MagicFileEncoding.csproj", "{89C8EAD5-218B-46A8-8DE9-93783166F9FC}"
+EndProject
+Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "UnitTests", "UnitTests\UnitTests.csproj", "{83F84B60-DBC5-4738-AC63-4EFB547BF9F7}"
+EndProject
+Global
+	GlobalSection(SolutionConfigurationPlatforms) = preSolution
+		Debug|Any CPU = Debug|Any CPU
+		Release|Any CPU = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(ProjectConfigurationPlatforms) = postSolution
+		{89C8EAD5-218B-46A8-8DE9-93783166F9FC}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{89C8EAD5-218B-46A8-8DE9-93783166F9FC}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{89C8EAD5-218B-46A8-8DE9-93783166F9FC}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{89C8EAD5-218B-46A8-8DE9-93783166F9FC}.Release|Any CPU.Build.0 = Release|Any CPU
+		{83F84B60-DBC5-4738-AC63-4EFB547BF9F7}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{83F84B60-DBC5-4738-AC63-4EFB547BF9F7}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{83F84B60-DBC5-4738-AC63-4EFB547BF9F7}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{83F84B60-DBC5-4738-AC63-4EFB547BF9F7}.Release|Any CPU.Build.0 = Release|Any CPU
+	EndGlobalSection
+EndGlobal

MagicFileEncoding/ByteOrderMask.cs

@@ -24,9 +24,9 @@ public static readonly ByteOrderMaskInfo UTF8
     public static readonly ByteOrderMaskInfo UTF7
         = new (Encoding.UTF7, 0x2b, 0x2f, 0x76);
 
-    public static readonly List<ByteOrderMaskInfo> List = new ()
+    public static readonly IList<ByteOrderMaskInfo> List = new List<ByteOrderMaskInfo>()
     {
         UTF32BE, UTF32, UTF16BE, UTF16, UTF8, UTF7
-    };
+    }.AsReadOnly();
 }
 #pragma warning restore SYSLIB0001

MagicFileEncoding/EncodingSecurityException.cs

@@ -2,7 +2,6 @@
 
 namespace MagicFileEncoding;
 
-[Serializable]
 public class EncodingSecurityException : Exception
 {
     public EncodingSecurityException(string message) : base(message)

MagicFileEncoding/MagicFileEncoding.csproj

@@ -1,8 +1,8 @@
 <Project Sdk="Microsoft.NET.Sdk">
 
     <PropertyGroup>
-        <TargetFramework>net8.0</TargetFramework>
-        <PackageVersion>3.0.0</PackageVersion>
+        <TargetFramework>net10.0</TargetFramework>
+        <PackageVersion>4.0.0</PackageVersion>
         <Title>Magic File Encoding</Title>
         <Authors>Jan Schwien</Authors>
         <Copyright>by Jan Schwien</Copyright>
@@ -18,8 +18,9 @@ Be aware of possible transformation issues if the target encoding is simpler tha
 
 It is strongly recommended to write unit tests for your use case to ensure the load and transformation works as expected.</Description>
         <Nullable>enable</Nullable>
-        <LangVersion>11</LangVersion>
-        <AssemblyVersion>3.0.0</AssemblyVersion>
+        <LangVersion>14</LangVersion>
+        <AssemblyVersion>4.0.0</AssemblyVersion>
+        <GeneratePackageOnBuild>true</GeneratePackageOnBuild>
     </PropertyGroup>
 
     <PropertyGroup>

MagicFileEncoding/Tools/EncodingTools.cs

@@ -53,49 +53,9 @@ internal static byte[] AutomaticTransformBytes(byte[] bytes, Encoding targetEnco
         // For the below, false positives should be exceedingly rare (and would
         // be either slightly malformed UTF-8 (which would suit our purposes
         // anyway) or 8-bit extended ASCII/UTF-16/32 at a vanishingly long shot).
-        var i = 0;
-        var utf8 = false;
-        while (i < taster - 4)
-        {
-            if (bytes[i] <= 0x7F)
-            {
-                i += 1;
-                continue;
-            }
+
 
-            // If all characters are below 0x80, then it is valid UTF8,
-            // but UTF8 is not 'required' (and therefore the text is more desirable to be treated as
-            // the default codepage of the computer). Hence, there's no "utf8 = true;"
-            // code unlike the next three checks.
-
-            if (bytes[i] >= 0xC2 && bytes[i] <= 0xDF && bytes[i + 1] >= 0x80 && bytes[i + 1] < 0xC0)
-            {
-                i += 2;
-                utf8 = true;
-                continue;
-            }
-
-            if (bytes[i] >= 0xE0 && bytes[i] <= 0xF0 && bytes[i + 1] >= 0x80 && bytes[i + 1] < 0xC0 && bytes[i + 2] >= 0x80 &&
-                bytes[i + 2] < 0xC0)
-            {
-                i += 3;
-                utf8 = true;
-                continue;
-            }
-
-            if (bytes[i] >= 0xF0 && bytes[i] <= 0xF4 && bytes[i + 1] >= 0x80 && bytes[i + 1] < 0xC0 && 
-                bytes[i + 2] >= 0x80 && bytes[i + 2] < 0xC0 && bytes[i + 3] >= 0x80 && bytes[i + 3] < 0xC0)
-            {
-                i += 4;
-                utf8 = true;
-                continue;
-            }
-
-            utf8 = false;
-            break;
-        }
-
-        if (utf8)
+        if (CheckForUtf8(bytes, taster))
         {
             text = provideText ? Encoding.UTF8.GetString(bytes) : null;
             return Encoding.UTF8;
@@ -138,6 +98,53 @@ internal static byte[] AutomaticTransformBytes(byte[] bytes, Encoding targetEnco
         return fallbackEncoding ?? FileEncoding.DefaultFallback;
     }
 
+    private static bool CheckForUtf8(byte[] bytes, int taster)
+    {
+        var utf8 = false;
+        var i = 0;
+        while (i < taster - 4)
+        {
+            if (bytes[i] <= 0x7F)
+            {
+                i += 1;
+                continue;
+            }
+
+            // If all characters are below 0x80, then it is valid UTF8,
+            // but UTF8 is not 'required' (and therefore the text is more desirable to be treated as
+            // the default codepage of the computer). Hence, there's no "utf8 = true;"
+            // code unlike the next three checks.
+
+            if (bytes[i] >= 0xC2 && bytes[i] <= 0xDF && bytes[i + 1] >= 0x80 && bytes[i + 1] < 0xC0)
+            {
+                i += 2;
+                utf8 = true;
+                continue;
+            }
+
+            if (bytes[i] >= 0xE0 && bytes[i] <= 0xF0 && bytes[i + 1] >= 0x80 && bytes[i + 1] < 0xC0 && bytes[i + 2] >= 0x80 &&
+                bytes[i + 2] < 0xC0)
+            {
+                i += 3;
+                utf8 = true;
+                continue;
+            }
+
+            if (bytes[i] >= 0xF0 && bytes[i] <= 0xF4 && bytes[i + 1] >= 0x80 && bytes[i + 1] < 0xC0 && 
+                bytes[i + 2] >= 0x80 && bytes[i + 2] < 0xC0 && bytes[i + 3] >= 0x80 && bytes[i + 3] < 0xC0)
+            {
+                i += 4;
+                utf8 = true;
+                continue;
+            }
+
+            utf8 = false;
+            break;
+        }
+
+        return utf8;
+    }
+
     /// <summary>
     /// A long shot - let's see if we can find "charset=xyz" or
     /// "encoding=xyz" to identify the encoding:
@@ -153,28 +160,40 @@ private static bool LongShot(ref string? text, bool provideText, int taster, byt
         for (var n = 0; n < taster - 9; n++)
         {
             if (!IsCharsetMarker(bytes, n) && !IsEncodingMarker(bytes, n))
+            {
                 continue;
+            }
 
-            if (bytes[n + 0] == 'c' || bytes[n + 0] == 'C') n += 8;
-            else n += 9;
+            if (bytes[n + 0] == 'c' || bytes[n + 0] == 'C')
+            {
+                n += 8;
+            }
+            else
+            {
+                n += 9;
+            }
 
-            if (bytes[n] == '"' || bytes[n] == '\'') n++;
+            if (bytes[n] == '"' || bytes[n] == '\'')
+            {
+                n++;
+            }
 
             var oldN = n;
 
             while (IsCharsetNameRange(taster, bytes, n))
+            {
                 n++;
+            }
 
             var nb = new byte[n - oldN];
             Array.Copy(bytes, oldN, nb, 0, n - oldN);
             try
             {
                 var internalEnc = Encoding.ASCII.GetString(nb);
                 text = provideText ? Encoding.GetEncoding(internalEnc).GetString(bytes) : null;
-                {
-                    encoding = Encoding.GetEncoding(internalEnc);
-                    return true;
-                }
+
+                encoding = Encoding.GetEncoding(internalEnc);
+                return true;
             }
             catch
             {
@@ -252,9 +271,11 @@ private static bool IsCharsetNameRange(int taster, byte[] bytes, int n)
 
         var bom = new byte[4];
         fileStream.Position = 0;
-
-        // ReSharper disable once MustUseReturnValue
+
+        // read the BOM with dynamical length
+#pragma warning disable CA2022, S2674
         fileStream.Read(bom, 0, 4);
+#pragma warning restore CA2022
 
         return GetEncodingByBom(bom, fallbackEncoding, out _, false);
     }

README.md

@@ -12,7 +12,8 @@ comprehensive solution to handle various encoding scenarios effortlessly.
 [MagicFileEncoding at nuget.org](https://www.nuget.org/packages/MagicFileEncoding/)
 
 ## .Net Version
-- **.Net 8:** Magic File Encoding **3.0.0 and newer**
+- **.Net 10:** Magic File Encoding **4.0.0 and newer**
+- **.Net 8:** Magic File Encoding **3.0.0**
 - **.Net 6:** Magic File Encoding **2.0.1**
 
 ## Transformation Considerations