Update Regex named blocks from Unicode 4.0 to Unicode 17.0

src/libraries/System.Private.CoreLib/Tools/GenUnicodeProp/Updating-Unicode-Versions.md

@@ -51,5 +51,6 @@ This should be done automatically by dependency-flow, so in theory there shouldn
     $ ./dotnet.sh run --project src/native/minipal/UnicodeDataGenerator /tmp/UnicodeData.txt > src/native/minipal/unicodedata.c
     ```
 5. Update the Regex casing equivalence table using the UnicodeData.txt file from the new Unicode version. You can find the instructions on how to do this [here](../../../System.Text.RegularExpressions/tools/Readme.md).
-6. Finally, last step is to update the license for the Unicode data into our [Third party notices](../../../../../THIRD-PARTY-NOTICES.TXT) by copying the contents located in `https://www.unicode.org/license.html` to the section that has the Unicode license in our notices.
-7. That's it, now commit all of the changed files, and send a PR into dotnet/runtime with the updates. If there were any special things you had to do that are not noted on this document, PLEASE UPDATE THESE INSTRUCTIONS to facilitate future updates.
+6. Update the Regex named blocks using the Blocks.txt file from the new Unicode version. Run the GenRegexNamedBlocks tool located at `src/libraries/System.Text.RegularExpressions/tools/GenRegexNamedBlocks` following the instructions in its [README.md](../../../System.Text.RegularExpressions/tools/GenRegexNamedBlocks/README.md).
+7. Finally, last step is to update the license for the Unicode data into our [Third party notices](../../../../../THIRD-PARTY-NOTICES.TXT) by copying the contents located in `https://www.unicode.org/license.html` to the section that has the Unicode license in our notices.
+8. That's it, now commit all of the changed files, and send a PR into dotnet/runtime with the updates. If there were any special things you had to do that are not noted on this document, PLEASE UPDATE THESE INSTRUCTIONS to facilitate future updates.

src/libraries/System.Text.RegularExpressions/gen/System.Text.RegularExpressions.Generator.csproj

@@ -38,6 +38,7 @@
     <Compile Include="..\src\System\Text\RegularExpressions\RegexCaseEquivalences.cs" Link="Production\RegexCaseEquivalences.cs" />
     <Compile Include="..\src\System\Text\RegularExpressions\RegexCaseBehavior.cs" Link="Production\RegexCaseBehavior.cs" />
     <Compile Include="..\src\System\Text\RegularExpressions\RegexCharClass.cs" Link="Production\RegexCharClass.cs" />
+    <Compile Include="..\src\System\Text\RegularExpressions\RegexCharClass.Tables.cs" Link="Production\RegexCharClass.Tables.cs" />
     <Compile Include="..\src\System\Text\RegularExpressions\RegexFindOptimizations.cs" Link="Production\RegexFindOptimizations.cs" />
     <Compile Include="..\src\System\Text\RegularExpressions\RegexNode.cs" Link="Production\RegexNode.cs" />
     <Compile Include="..\src\System\Text\RegularExpressions\RegexNodeKind.cs" Link="Production\RegexNodeKind.cs" />

src/libraries/System.Text.RegularExpressions/src/System.Text.RegularExpressions.csproj

@@ -34,6 +34,7 @@
     <Compile Include="System\Text\RegularExpressions\RegexCaseEquivalences.Data.cs" />
     <Compile Include="System\Text\RegularExpressions\RegexCaseEquivalences.cs" />
     <Compile Include="System\Text\RegularExpressions\RegexCharClass.cs" />
+    <Compile Include="System\Text\RegularExpressions\RegexCharClass.Tables.cs" />
     <Compile Include="System\Text\RegularExpressions\RegexCompilationInfo.cs" />
     <Compile Include="System\Text\RegularExpressions\RegexFindOptimizations.cs" />
     <Compile Include="System\Text\RegularExpressions\GeneratedRegexAttribute.cs" />

src/libraries/System.Text.RegularExpressions/tests/FunctionalTests/RegexCharacterSetTests.cs

@@ -245,7 +245,14 @@ public static IEnumerable<object[]> NamedBlocksInclusionsExpected_MemberData()
                 yield return new object[] { engine, @"\p{IsHebrew}", new[] { 0x0590, 0x05FF } };
                 yield return new object[] { engine, @"\p{IsArabic}", new[] { 0x0600, 0x06FF } };
                 yield return new object[] { engine, @"\p{IsSyriac}", new[] { 0x0700, 0x074F } };
+                yield return new object[] { engine, @"\p{IsArabicSupplement}", new[] { 0x0750, 0x077F } };
                 yield return new object[] { engine, @"\p{IsThaana}", new[] { 0x0780, 0x07BF } };
+                yield return new object[] { engine, @"\p{IsNKo}", new[] { 0x07C0, 0x07FF } };
+                yield return new object[] { engine, @"\p{IsSamaritan}", new[] { 0x0800, 0x083F } };
+                yield return new object[] { engine, @"\p{IsMandaic}", new[] { 0x0840, 0x085F } };
+                yield return new object[] { engine, @"\p{IsSyriacSupplement}", new[] { 0x0860, 0x086F } };
+                yield return new object[] { engine, @"\p{IsArabicExtended-B}", new[] { 0x0870, 0x089F } };
+                yield return new object[] { engine, @"\p{IsArabicExtended-A}", new[] { 0x08A0, 0x08FF } };
                 yield return new object[] { engine, @"\p{IsDevanagari}", new[] { 0x0900, 0x097F } };
                 yield return new object[] { engine, @"\p{IsBengali}", new[] { 0x0980, 0x09FF } };
                 yield return new object[] { engine, @"\p{IsGurmukhi}", new[] { 0x0A00, 0x0A7F } };
@@ -273,10 +280,26 @@ public static IEnumerable<object[]> NamedBlocksInclusionsExpected_MemberData()
                 yield return new object[] { engine, @"\p{IsTagbanwa}", new[] { 0x1760, 0x177F } };
                 yield return new object[] { engine, @"\p{IsKhmer}", new[] { 0x1780, 0x17FF } };
                 yield return new object[] { engine, @"\p{IsMongolian}", new[] { 0x1800, 0x18AF } };
+                yield return new object[] { engine, @"\p{IsUnifiedCanadianAboriginalSyllabicsExtended}", new[] { 0x18B0, 0x18FF } };
                 yield return new object[] { engine, @"\p{IsLimbu}", new[] { 0x1900, 0x194F } };
                 yield return new object[] { engine, @"\p{IsTaiLe}", new[] { 0x1950, 0x197F } };
+                yield return new object[] { engine, @"\p{IsNewTaiLue}", new[] { 0x1980, 0x19DF } };
                 yield return new object[] { engine, @"\p{IsKhmerSymbols}", new[] { 0x19E0, 0x19FF } };
+                yield return new object[] { engine, @"\p{IsBuginese}", new[] { 0x1A00, 0x1A1F } };
+                yield return new object[] { engine, @"\p{IsTaiTham}", new[] { 0x1A20, 0x1AAF } };
+                yield return new object[] { engine, @"\p{IsCombiningDiacriticalMarksExtended}", new[] { 0x1AB0, 0x1AFF } };
+                yield return new object[] { engine, @"\p{IsBalinese}", new[] { 0x1B00, 0x1B7F } };
+                yield return new object[] { engine, @"\p{IsSundanese}", new[] { 0x1B80, 0x1BBF } };
+                yield return new object[] { engine, @"\p{IsBatak}", new[] { 0x1BC0, 0x1BFF } };
+                yield return new object[] { engine, @"\p{IsLepcha}", new[] { 0x1C00, 0x1C4F } };
+                yield return new object[] { engine, @"\p{IsOlChiki}", new[] { 0x1C50, 0x1C7F } };
+                yield return new object[] { engine, @"\p{IsCyrillicExtended-C}", new[] { 0x1C80, 0x1C8F } };
+                yield return new object[] { engine, @"\p{IsGeorgianExtended}", new[] { 0x1C90, 0x1CBF } };
+                yield return new object[] { engine, @"\p{IsSundaneseSupplement}", new[] { 0x1CC0, 0x1CCF } };
+                yield return new object[] { engine, @"\p{IsVedicExtensions}", new[] { 0x1CD0, 0x1CFF } };
                 yield return new object[] { engine, @"\p{IsPhoneticExtensions}", new[] { 0x1D00, 0x1D7F } };
+                yield return new object[] { engine, @"\p{IsPhoneticExtensionsSupplement}", new[] { 0x1D80, 0x1DBF } };
+                yield return new object[] { engine, @"\p{IsCombiningDiacriticalMarksSupplement}", new[] { 0x1DC0, 0x1DFF } };
                 yield return new object[] { engine, @"\p{IsLatinExtendedAdditional}", new[] { 0x1E00, 0x1EFF } };
                 yield return new object[] { engine, @"\p{IsGreekExtended}", new[] { 0x1F00, 0x1FFF } };
                 yield return new object[] { engine, @"\p{IsGeneralPunctuation}", new[] { 0x2000, 0x206F } };
@@ -303,6 +326,14 @@ public static IEnumerable<object[]> NamedBlocksInclusionsExpected_MemberData()
                 yield return new object[] { engine, @"\p{IsMiscellaneousMathematicalSymbols-B}", new[] { 0x2980, 0x29FF } };
                 yield return new object[] { engine, @"\p{IsSupplementalMathematicalOperators}", new[] { 0x2A00, 0x2AFF } };
                 yield return new object[] { engine, @"\p{IsMiscellaneousSymbolsandArrows}", new[] { 0x2B00, 0x2BFF } };
+                yield return new object[] { engine, @"\p{IsGlagolitic}", new[] { 0x2C00, 0x2C5F } };
+                yield return new object[] { engine, @"\p{IsLatinExtended-C}", new[] { 0x2C60, 0x2C7F } };
+                yield return new object[] { engine, @"\p{IsCoptic}", new[] { 0x2C80, 0x2CFF } };
+                yield return new object[] { engine, @"\p{IsGeorgianSupplement}", new[] { 0x2D00, 0x2D2F } };
+                yield return new object[] { engine, @"\p{IsTifinagh}", new[] { 0x2D30, 0x2D7F } };
+                yield return new object[] { engine, @"\p{IsEthiopicExtended}", new[] { 0x2D80, 0x2DDF } };
+                yield return new object[] { engine, @"\p{IsCyrillicExtended-A}", new[] { 0x2DE0, 0x2DFF } };
+                yield return new object[] { engine, @"\p{IsSupplementalPunctuation}", new[] { 0x2E00, 0x2E7F } };
                 yield return new object[] { engine, @"\p{IsCJKRadicalsSupplement}", new[] { 0x2E80, 0x2EFF } };
                 yield return new object[] { engine, @"\p{IsKangxiRadicals}", new[] { 0x2F00, 0x2FDF } };
                 yield return new object[] { engine, @"\p{IsIdeographicDescriptionCharacters}", new[] { 0x2FF0, 0x2FFF } };
@@ -313,6 +344,7 @@ public static IEnumerable<object[]> NamedBlocksInclusionsExpected_MemberData()
                 yield return new object[] { engine, @"\p{IsHangulCompatibilityJamo}", new[] { 0x3130, 0x318F } };
                 yield return new object[] { engine, @"\p{IsKanbun}", new[] { 0x3190, 0x319F } };
                 yield return new object[] { engine, @"\p{IsBopomofoExtended}", new[] { 0x31A0, 0x31BF } };
+                yield return new object[] { engine, @"\p{IsCJKStrokes}", new[] { 0x31C0, 0x31EF } };
                 yield return new object[] { engine, @"\p{IsKatakanaPhoneticExtensions}", new[] { 0x31F0, 0x31FF } };
                 yield return new object[] { engine, @"\p{IsEnclosedCJKLettersandMonths}", new[] { 0x3200, 0x32FF } };
                 yield return new object[] { engine, @"\p{IsCJKCompatibility}", new[] { 0x3300, 0x33FF } };
@@ -321,7 +353,32 @@ public static IEnumerable<object[]> NamedBlocksInclusionsExpected_MemberData()
                 yield return new object[] { engine, @"\p{IsCJKUnifiedIdeographs}", new[] { 0x4E00, 0x9FFF } };
                 yield return new object[] { engine, @"\p{IsYiSyllables}", new[] { 0xA000, 0xA48F } };
                 yield return new object[] { engine, @"\p{IsYiRadicals}", new[] { 0xA490, 0xA4CF } };
+                yield return new object[] { engine, @"\p{IsLisu}", new[] { 0xA4D0, 0xA4FF } };
+                yield return new object[] { engine, @"\p{IsVai}", new[] { 0xA500, 0xA63F } };
+                yield return new object[] { engine, @"\p{IsCyrillicExtended-B}", new[] { 0xA640, 0xA69F } };
+                yield return new object[] { engine, @"\p{IsBamum}", new[] { 0xA6A0, 0xA6FF } };
+                yield return new object[] { engine, @"\p{IsModifierToneLetters}", new[] { 0xA700, 0xA71F } };
+                yield return new object[] { engine, @"\p{IsLatinExtended-D}", new[] { 0xA720, 0xA7FF } };
+                yield return new object[] { engine, @"\p{IsSylotiNagri}", new[] { 0xA800, 0xA82F } };
+                yield return new object[] { engine, @"\p{IsCommonIndicNumberForms}", new[] { 0xA830, 0xA83F } };
+                yield return new object[] { engine, @"\p{IsPhags-pa}", new[] { 0xA840, 0xA87F } };
+                yield return new object[] { engine, @"\p{IsSaurashtra}", new[] { 0xA880, 0xA8DF } };
+                yield return new object[] { engine, @"\p{IsDevanagariExtended}", new[] { 0xA8E0, 0xA8FF } };
+                yield return new object[] { engine, @"\p{IsKayahLi}", new[] { 0xA900, 0xA92F } };
+                yield return new object[] { engine, @"\p{IsRejang}", new[] { 0xA930, 0xA95F } };
+                yield return new object[] { engine, @"\p{IsHangulJamoExtended-A}", new[] { 0xA960, 0xA97F } };
+                yield return new object[] { engine, @"\p{IsJavanese}", new[] { 0xA980, 0xA9DF } };
+                yield return new object[] { engine, @"\p{IsMyanmarExtended-B}", new[] { 0xA9E0, 0xA9FF } };
+                yield return new object[] { engine, @"\p{IsCham}", new[] { 0xAA00, 0xAA5F } };
+                yield return new object[] { engine, @"\p{IsMyanmarExtended-A}", new[] { 0xAA60, 0xAA7F } };
+                yield return new object[] { engine, @"\p{IsTaiViet}", new[] { 0xAA80, 0xAADF } };
+                yield return new object[] { engine, @"\p{IsMeeteiMayekExtensions}", new[] { 0xAAE0, 0xAAFF } };
+                yield return new object[] { engine, @"\p{IsEthiopicExtended-A}", new[] { 0xAB00, 0xAB2F } };
+                yield return new object[] { engine, @"\p{IsLatinExtended-E}", new[] { 0xAB30, 0xAB6F } };
+                yield return new object[] { engine, @"\p{IsCherokeeSupplement}", new[] { 0xAB70, 0xABBF } };
+                yield return new object[] { engine, @"\p{IsMeeteiMayek}", new[] { 0xABC0, 0xABFF } };
                 yield return new object[] { engine, @"\p{IsHangulSyllables}", new[] { 0xAC00, 0xD7AF } };
+                yield return new object[] { engine, @"\p{IsHangulJamoExtended-B}", new[] { 0xD7B0, 0xD7FF } };
                 yield return new object[] { engine, @"\p{IsHighSurrogates}", new[] { 0xD800, 0xDB7F } };
                 yield return new object[] { engine, @"\p{IsHighPrivateUseSurrogates}", new[] { 0xDB80, 0xDBFF } };
                 yield return new object[] { engine, @"\p{IsLowSurrogates}", new[] { 0xDC00, 0xDFFF } };
@@ -330,6 +387,7 @@ public static IEnumerable<object[]> NamedBlocksInclusionsExpected_MemberData()
                 yield return new object[] { engine, @"\p{IsAlphabeticPresentationForms}", new[] { 0xFB00, 0xFB4F } };
                 yield return new object[] { engine, @"\p{IsArabicPresentationForms-A}", new[] { 0xFB50, 0xFDFF } };
                 yield return new object[] { engine, @"\p{IsVariationSelectors}", new[] { 0xFE00, 0xFE0F } };
+                yield return new object[] { engine, @"\p{IsVerticalForms}", new[] { 0xFE10, 0xFE1F } };
                 yield return new object[] { engine, @"\p{IsCombiningHalfMarks}", new[] { 0xFE20, 0xFE2F } };
                 yield return new object[] { engine, @"\p{IsCJKCompatibilityForms}", new[] { 0xFE30, 0xFE4F } };
                 yield return new object[] { engine, @"\p{IsSmallFormVariants}", new[] { 0xFE50, 0xFE6F } };

src/libraries/System.Text.RegularExpressions/tests/UnitTests/System.Text.RegularExpressions.Unit.Tests.csproj

@@ -31,6 +31,7 @@
     <Compile Include="..\..\src\System\Text\RegularExpressions\RegexCaseEquivalences.cs" Link="Production\RegexCaseEquivalences.cs" />
     <Compile Include="..\..\src\System\Text\RegularExpressions\RegexCaseBehavior.cs" Link="Production\RegexCaseBehavior.cs" />
     <Compile Include="..\..\src\System\Text\RegularExpressions\RegexCharClass.cs" Link="Production\RegexCharClass.cs" />
+    <Compile Include="..\..\src\System\Text\RegularExpressions\RegexCharClass.Tables.cs" Link="Production\RegexCharClass.Tables.cs" />
     <Compile Include="..\..\src\System\Text\RegularExpressions\RegexInterpreterCode.cs" Link="Production\RegexInterpreterCode.cs" />
     <Compile Include="..\..\src\System\Text\RegularExpressions\RegexFindOptimizations.cs" Link="Production\RegexFindOptimizations.cs" />
     <Compile Include="..\..\src\System\Text\RegularExpressions\RegexNode.cs" Link="Production\RegexNode.cs" />

src/libraries/System.Text.RegularExpressions/tools/GenRegexNamedBlocks/GenRegexNamedBlocks.csproj

@@ -0,0 +1,9 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>net10.0</TargetFramework>
+    <Nullable>enable</Nullable>
+  </PropertyGroup>
+
+</Project>