Implement RegExp v-flag (unicodeSets) syntax validation

src/Acornima/EcmaVersion.cs

@@ -15,6 +15,7 @@ public enum EcmaVersion
     ES12 = 12,
     ES13 = 13,
     ES14 = 14,
+    ES15 = 15,
 
     ES2015 = ES6,
     ES2016 = ES7,
@@ -25,9 +26,10 @@ public enum EcmaVersion
     ES2021 = ES12,
     ES2022 = ES13,
     ES2023 = ES14,
+    ES2024 = ES15,
 
     /// <summary>
-    /// The latest version which is fully supported (<see cref="ES2023"/>).
+    /// The latest version which is fully supported (<see cref="ES2024"/>).
     /// </summary>
-    Latest = ES2023,
+    Latest = ES2024,
 }

src/Acornima/Properties/RegExpConversionErrorMessages.resx

@@ -136,7 +136,7 @@
     <value>Inconvertible Unicode property escape</value>
   </data>
   <data name="RegExpUnicodeSetsModeNotSupported" xml:space="preserve">
-    <value>Unicode sets mode (flag v) is not supported currently</value>
+    <value>Conversion of Unicode sets mode (flag v) regular expressions to .NET Regex is not supported</value>
   </data>
   <data name="RegExpUnmappableGroupName" xml:space="preserve">
     <value>Cannot map group name '{0}' to a unique group name in the adapted regex</value>

src/Acornima/Properties/SyntaxErrorMessages.resx

@@ -398,6 +398,14 @@
     <value>Invalid regular expression: /{0}/{1}: Invalid character class</value>
     <comment>https://github.com/v8/v8/blob/14.8.3/src/regexp/regexp-error.h</comment>
   </data>
+  <data name="RegExpInvalidCharacterInCharacterClass" xml:space="preserve">
+    <value>Invalid regular expression: /{0}/{1}: Invalid character in character class</value>
+    <comment>https://github.com/v8/v8/blob/14.8.3/src/regexp/regexp-error.h</comment>
+  </data>
+  <data name="RegExpNegatedCharacterClassMayContainStrings" xml:space="preserve">
+    <value>Invalid regular expression: /{0}/{1}: Negated character class may contain strings</value>
+    <comment>https://github.com/v8/v8/blob/14.8.3/src/regexp/regexp-error.h</comment>
+  </data>
   <data name="RegExpInvalidClassPropertyName" xml:space="preserve">
     <value>Invalid regular expression: /{0}/{1}: Invalid property name in character class</value>
     <comment>https://github.com/v8/v8/blob/14.8.3/src/regexp/regexp-error.h</comment>

src/Acornima/Tokenizer.RegExpParser.Legacy.cs

@@ -457,6 +457,11 @@ public bool AdjustEscapeSequence(RegExpParser parser, out RegExpConversionError?
                 conversionError = null;
                 return true;
             }
+
+            public bool TryParseCharacterClass(RegExpParser parser)
+            {
+                return false;
+            }
         }
     }
 }

src/Acornima/Tokenizer.RegExpParser.Unicode.cs

@@ -534,59 +534,11 @@ private static void AddStandardCharClass(ref ArrayList<CodePointRange> set, char
                 set.AddRange(ranges);
             }
 
-            private static bool ValidateUnicodeProperty(ReadOnlyMemory<char> expression, bool translateToRanges, RegExpParser parser, out CodePointRange[]? codePointRanges)
+            // Delegates to the shared ValidateUnicodeProperty on RegExpParser.
+            [MethodImpl(MethodImplOptions.AggressiveInlining)]
+            private static bool ValidateUnicodePropertyForConversion(ReadOnlyMemory<char> expression, bool translateToRanges, RegExpParser parser, out CodePointRange[]? codePointRanges)
             {
-                var index = expression.Span.IndexOf('=');
-                if (index >= 0)
-                {
-                    // https://tc39.es/ecma262/#table-nonbinary-unicode-properties
-
-                    var propertyName = expression.Span.Slice(0, index);
-                    expression = expression.Slice(index + 1);
-                    switch (propertyName)
-                    {
-                        case "gc" or "General_Category":
-                            if (translateToRanges)
-                            {
-                                codePointRanges = UnicodeProperties.GetGeneralCategoryRange(expression, parser.GetCodePointRangeCache());
-                                return codePointRanges is not null;
-                            }
-                            else
-                            {
-                                codePointRanges = default;
-                                return UnicodeProperties.IsAllowedGeneralCategoryValue(expression);
-                            }
-
-                        case "sc" or "Script" or "scx" or "Script_Extensions":
-                            // Translating unicode properties other than General Categories is not implemented currently.
-                            codePointRanges = default;
-                            return UnicodeProperties.IsAllowedScriptValue(expression, parser._tokenizer._options._ecmaVersion);
-
-                        default:
-                            codePointRanges = default;
-                            return false;
-                    }
-                }
-                else
-                {
-                    if (translateToRanges)
-                    {
-                        codePointRanges = UnicodeProperties.GetGeneralCategoryRange(expression, parser.GetCodePointRangeCache());
-                        if (codePointRanges is not null)
-                        {
-                            return true;
-                        }
-                    }
-                    else if (UnicodeProperties.IsAllowedGeneralCategoryValue(expression))
-                    {
-                        codePointRanges = default;
-                        return true;
-                    }
-
-                    // Translating unicode properties other than General Categories is not implemented currently.
-                    codePointRanges = default;
-                    return UnicodeProperties.IsAllowedBinaryValue(expression, parser._tokenizer._options._ecmaVersion);
-                }
+                return ValidateUnicodeProperty(expression, translateToRanges, parser, out codePointRanges);
             }
 
             public void RewriteDot(RegExpParser parser)
@@ -874,7 +826,7 @@ public bool AdjustEscapeSequence(RegExpParser parser, out RegExpConversionError?
 
                                 endIndex = pattern.IndexOf('}', i + 2);
                                 if (endIndex < 0
-                                    || !ValidateUnicodeProperty(pattern.AsMemory(i + 2, endIndex - (i + 2)), translateToRanges: sb is not null, parser, out codePointRanges))
+                                    || !ValidateUnicodePropertyForConversion(pattern.AsMemory(i + 2, endIndex - (i + 2)), translateToRanges: sb is not null, parser, out codePointRanges))
                                 {
                                     if (!parser.WithinSet)
                                     {
@@ -987,6 +939,11 @@ public bool AdjustEscapeSequence(RegExpParser parser, out RegExpConversionError?
                 conversionError = null;
                 return true;
             }
+
+            public bool TryParseCharacterClass(RegExpParser parser)
+            {
+                return false;
+            }
         }
     }
 }