[rel/3.8] Handle if RootNamespace contains invalid identifier charact…

…ers (#5069)

Co-authored-by: Youssef1313 <youssefvictor00@gmail.com>

src/Platform/Microsoft.Testing.Platform.MSBuild/Tasks/NamespaceHelpers.cs

@@ -0,0 +1,51 @@
+// Copyright (c) Microsoft Corporation. All rights reserved.
+// Licensed under the MIT license. See LICENSE file in the project root for full license information.
+
+namespace Microsoft.Testing.Platform.MSBuild;
+
+internal static class NamespaceHelpers
+{
+    internal static string ToSafeNamespace(string value)
+    {
+        const char invalidCharacterReplacement = '_';
+
+        value = value.Trim();
+
+        StringBuilder safeValueStr = new(value.Length);
+
+        for (int i = 0; i < value.Length; i++)
+        {
+            if (i < value.Length - 1 && char.IsSurrogatePair(value[i], value[i + 1]))
+            {
+                safeValueStr.Append(invalidCharacterReplacement);
+                // Skip both chars that make up this symbol.
+                i++;
+                continue;
+            }
+
+            bool isFirstCharacterOfIdentifier = safeValueStr.Length == 0 || safeValueStr[safeValueStr.Length - 1] == '.';
+            bool isValidFirstCharacter = UnicodeCharacterUtilities.IsIdentifierStartCharacter(value[i]);
+            bool isValidPartCharacter = UnicodeCharacterUtilities.IsIdentifierPartCharacter(value[i]);
+
+            if (isFirstCharacterOfIdentifier && !isValidFirstCharacter && isValidPartCharacter)
+            {
+                // This character cannot be at the beginning, but is good otherwise. Prefix it with something valid.
+                safeValueStr.Append(invalidCharacterReplacement);
+                safeValueStr.Append(value[i]);
+            }
+            else if ((isFirstCharacterOfIdentifier && isValidFirstCharacter) ||
+                    (!isFirstCharacterOfIdentifier && isValidPartCharacter) ||
+                    (safeValueStr.Length > 0 && i < value.Length - 1 && value[i] == '.'))
+            {
+                // This character is allowed to be where it is.
+                safeValueStr.Append(value[i]);
+            }
+            else
+            {
+                safeValueStr.Append(invalidCharacterReplacement);
+            }
+        }
+
+        return safeValueStr.ToString();
+    }
+}

src/Platform/Microsoft.Testing.Platform.MSBuild/Tasks/TestingPlatformAutoRegisteredExtensions.cs

@@ -194,6 +194,11 @@ private static void GenerateCode(string language, string rootNamespace, ITaskIte
 
     private static string GetSourceCode(string language, string rootNamespace, string extensionsFragments)
     {
+        if (language != VBLanguageSymbol && !string.IsNullOrEmpty(rootNamespace))
+        {
+            rootNamespace = NamespaceHelpers.ToSafeNamespace(rootNamespace);
+        }
+
         if (language == CSharpLanguageSymbol)
         {
             return string.IsNullOrEmpty(rootNamespace)

src/Platform/Microsoft.Testing.Platform.MSBuild/Tasks/TestingPlatformEntryPointTask.cs

@@ -92,6 +92,11 @@ private static void GenerateEntryPoint(string language, string rootNamespace, IT
 
     private static string GetEntryPointSourceCode(string language, string rootNamespace)
     {
+        if (language != VBLanguageSymbol && !string.IsNullOrEmpty(rootNamespace))
+        {
+            rootNamespace = NamespaceHelpers.ToSafeNamespace(rootNamespace);
+        }
+
         if (language == CSharpLanguageSymbol)
         {
             return string.IsNullOrEmpty(rootNamespace)

src/Platform/Microsoft.Testing.Platform.MSBuild/Tasks/UnicodeCharacterUtilities.cs

@@ -0,0 +1,160 @@
+// Copyright (c) Microsoft Corporation. All rights reserved.
+// Licensed under the MIT license. See LICENSE file in the project root for full license information.
+
+namespace Microsoft.Testing.Platform.MSBuild;
+
+/// <summary>
+/// Defines a set of helper methods to classify Unicode characters.
+/// </summary>
+internal static partial class UnicodeCharacterUtilities
+{
+    public static bool IsIdentifierStartCharacter(char ch)
+    {
+        // identifier-start-character:
+        //   letter-character
+        //   _ (the underscore character U+005F)
+        if (ch < 'a') // '\u0061'
+        {
+            if (ch < 'A') // '\u0041'
+            {
+                return false;
+            }
+
+            return ch is <= 'Z' // '\u005A'
+                or '_'; // '\u005F'
+        }
+
+        if (ch <= 'z') // '\u007A'
+        {
+            return true;
+        }
+
+        if (ch <= '\u007F') // max ASCII
+        {
+            return false;
+        }
+
+        // The ASCII range is handled above Only a-z, A-Z, and underscore are valid.
+        // Now, we allow unicode characters that are classified as letters.
+        return IsLetterChar(CharUnicodeInfo.GetUnicodeCategory(ch));
+    }
+
+    /// <summary>
+    /// Returns true if the Unicode character can be a part of an identifier.
+    /// </summary>
+    /// <param name="ch">The Unicode character.</param>
+    public static bool IsIdentifierPartCharacter(char ch)
+    {
+        // identifier-part-character:
+        //   letter-character
+        //   decimal-digit-character
+        //   connecting-character
+        //   combining-character
+        //   formatting-character
+        if (ch < 'a') // '\u0061'
+        {
+            if (ch < 'A') // '\u0041'
+            {
+                return ch is >= '0' // '\u0030'
+                    and <= '9'; // '\u0039'
+            }
+
+            return ch is <= 'Z' // '\u005A'
+                or '_'; // '\u005F'
+        }
+
+        if (ch <= 'z') // '\u007A'
+        {
+            return true;
+        }
+
+        if (ch <= '\u007F') // max ASCII
+        {
+            return false;
+        }
+
+        UnicodeCategory cat = CharUnicodeInfo.GetUnicodeCategory(ch);
+        return IsLetterChar(cat)
+            || IsDecimalDigitChar(cat)
+            || IsConnectingChar(cat)
+            || IsCombiningChar(cat)
+            || IsFormattingChar(cat);
+    }
+
+    /// <summary>
+    /// Check that the name is a valid Unicode identifier.
+    /// </summary>
+    public static bool IsValidIdentifier(string? name)
+    {
+        if (string.IsNullOrEmpty(name))
+        {
+            return false;
+        }
+
+        if (!IsIdentifierStartCharacter(name![0]))
+        {
+            return false;
+        }
+
+        int nameLength = name.Length;
+        for (int i = 1; i < nameLength; i++) // NB: start at 1
+        {
+            if (!IsIdentifierPartCharacter(name[i]))
+            {
+                return false;
+            }
+        }
+
+        return true;
+    }
+
+    /// <summary>
+    /// Returns true if the Unicode character is a formatting character (Unicode class Cf).
+    /// </summary>
+    /// <param name="ch">The Unicode character.</param>
+    internal static bool IsFormattingChar(char ch)
+        // There are no FormattingChars in ASCII range
+        => ch > 127 && IsFormattingChar(CharUnicodeInfo.GetUnicodeCategory(ch));
+
+    private static bool IsLetterChar(UnicodeCategory cat)
+        // letter-character:
+        //   A Unicode character of classes Lu, Ll, Lt, Lm, Lo, or Nl
+        //   A Unicode-escape-sequence representing a character of classes Lu, Ll, Lt, Lm, Lo, or Nl
+        => cat switch
+        {
+            UnicodeCategory.UppercaseLetter or UnicodeCategory.LowercaseLetter or UnicodeCategory.TitlecaseLetter or UnicodeCategory.ModifierLetter or UnicodeCategory.OtherLetter or UnicodeCategory.LetterNumber => true,
+            _ => false,
+        };
+
+    private static bool IsCombiningChar(UnicodeCategory cat)
+        // combining-character:
+        //   A Unicode character of classes Mn or Mc
+        //   A Unicode-escape-sequence representing a character of classes Mn or Mc
+        => cat switch
+        {
+            UnicodeCategory.NonSpacingMark or UnicodeCategory.SpacingCombiningMark => true,
+            _ => false,
+        };
+
+    private static bool IsDecimalDigitChar(UnicodeCategory cat)
+        // decimal-digit-character:
+        //   A Unicode character of the class Nd
+        //   A unicode-escape-sequence representing a character of the class Nd
+        => cat == UnicodeCategory.DecimalDigitNumber;
+
+    private static bool IsConnectingChar(UnicodeCategory cat)
+        // connecting-character:
+        //   A Unicode character of the class Pc
+        //   A unicode-escape-sequence representing a character of the class Pc
+        => cat == UnicodeCategory.ConnectorPunctuation;
+
+    /// <summary>
+    /// Returns true if the Unicode character is a formatting character (Unicode class Cf).
+    /// </summary>
+    /// <param name="cat">The Unicode character.</param>
+    private static bool IsFormattingChar(UnicodeCategory cat)
+        // formatting-character:
+        //   A Unicode character of the class Cf
+        //   A unicode-escape-sequence representing a character of the class Cf
+        => cat == UnicodeCategory.Format;
+}

test/IntegrationTests/Microsoft.Testing.Platform.Acceptance.IntegrationTests/MSBuild.KnownExtensionRegistration.cs

@@ -62,6 +62,8 @@ public async Task Microsoft_Testing_Platform_Extensions_ShouldBe_Correctly_Regis
         <OutputType>Exe</OutputType>
         <!-- Do not warn about package downgrade. NuGet uses alphabetical sort as ordering so -dev or -ci are considered downgrades of -preview. -->
         <NoWarn>$(NoWarn);NETSDK1201</NoWarn>
+
+        <RootNamespace>(MSBuild Tests)</RootNamespace>
     </PropertyGroup>
 
     <ItemGroup>