1506return new RegexCharClass(IsNegated(charClass, start), ranges, categoriesBuilder, sub);

1028prevCharClass = new RegexCharClass();

555RegexCharClass? charClass = scanOnly ? null : new RegexCharClass(); 1131var cc = new RegexCharClass();

948cc ??= new RegexCharClass(); 957cc ??= new RegexCharClass(); 994cc ??= new RegexCharClass();

147var rcc = new RegexCharClass();

316private RegexCharClass? _subtractor; 349private RegexCharClass(bool negate, List<(char First, char Last)>? ranges, StringBuilder? categories, RegexCharClass? subtraction) 369public void AddCharClass(RegexCharClass cc) 387public bool TryAddCharClass(RegexCharClass cc) 425public void AddSubtraction(RegexCharClass sub) 1481public static RegexCharClass Parse(string charClass) => ParseRecursive(charClass, 0); 1483private static RegexCharClass ParseRecursive(string charClass, int start) 1494RegexCharClass? sub = null;

867primarySet.Set != RegexCharClass.NotNewLineClass && 868primarySet.Set != RegexCharClass.AnyClass; 965else if (RegexCharClass.IsUnicodeCategoryOfSmallCharCount(primarySet.Set, out char[]? setChars, out bool negated, out _)) 983if (!RegexCharClass.CharInClass((char)i, primarySet.Set)) 3730node.Str == RegexCharClass.AnyClass && 4269if (node.IsSetFamily && node.Str == RegexCharClass.AnyClass) 4446else if (node.IsSetFamily && maxIterations == int.MaxValue && node.Str == RegexCharClass.AnyClass) 5143if (RegexCharClass.TryGetSingleRange(node.Str, out _, out _) || 5144RegexCharClass.GetSetChars(node.Str, setChars) > 0) 5193bool negated = RegexCharClass.IsNegated(node.Str) ^ negate; 5197if (RegexCharClass.TryGetSingleRange(node.Str, out char lowInclusive, out char highInclusive) && 5214int setCharsCount = RegexCharClass.GetSetChars(node.Str, setChars); 5485case RegexCharClass.AnyClass: 5491case RegexCharClass.DigitClass: 5492case RegexCharClass.NotDigitClass: 5495NegateIf(charClass == RegexCharClass.NotDigitClass); 5498case RegexCharClass.SpaceClass: 5499case RegexCharClass.NotSpaceClass: 5502NegateIf(charClass == RegexCharClass.NotSpaceClass); 5505case RegexCharClass.WordClass: 5506case RegexCharClass.NotWordClass: 5509NegateIf(charClass == RegexCharClass.NotWordClass); 5512case RegexCharClass.ControlClass: 5513case RegexCharClass.NotControlClass: 5516NegateIf(charClass == RegexCharClass.NotControlClass); 5519case RegexCharClass.LetterClass: 5520case RegexCharClass.NotLetterClass: 5523NegateIf(charClass == RegexCharClass.NotLetterClass); 5526case RegexCharClass.LetterOrDigitClass: 5527case RegexCharClass.NotLetterOrDigitClass: 5530NegateIf(charClass == RegexCharClass.NotLetterOrDigitClass); 5533case RegexCharClass.LowerClass: 5534case RegexCharClass.NotLowerClass: 5537NegateIf(charClass == RegexCharClass.NotLowerClass); 5540case RegexCharClass.UpperClass: 5541case RegexCharClass.NotUpperClass: 5544NegateIf(charClass == RegexCharClass.NotUpperClass); 5547case RegexCharClass.NumberClass: 5548case RegexCharClass.NotNumberClass: 5551NegateIf(charClass == RegexCharClass.NotNumberClass); 5554case RegexCharClass.PunctuationClass: 5555case RegexCharClass.NotPunctuationClass: 5558NegateIf(charClass == RegexCharClass.NotPunctuationClass); 5561case RegexCharClass.SeparatorClass: 5562case RegexCharClass.NotSeparatorClass: 5565NegateIf(charClass == RegexCharClass.NotSeparatorClass); 5568case RegexCharClass.SymbolClass: 5569case RegexCharClass.NotSymbolClass: 5572NegateIf(charClass == RegexCharClass.NotSymbolClass); 5575case RegexCharClass.AsciiLetterClass: 5576case RegexCharClass.NotAsciiLetterClass: 5579NegateIf(charClass == RegexCharClass.NotAsciiLetterClass); 5582case RegexCharClass.AsciiLetterOrDigitClass: 5583case RegexCharClass.NotAsciiLetterOrDigitClass: 5586NegateIf(charClass == RegexCharClass.NotAsciiLetterOrDigitClass); 5589case RegexCharClass.HexDigitClass: 5590case RegexCharClass.NotHexDigitClass: 5593NegateIf(charClass == RegexCharClass.NotHexDigitClass); 5596case RegexCharClass.HexDigitLowerClass: 5597case RegexCharClass.NotHexDigitLowerClass: 5600NegateIf(charClass == RegexCharClass.NotHexDigitLowerClass); 5603case RegexCharClass.HexDigitUpperClass: 5604case RegexCharClass.NotHexDigitUpperClass: 5607NegateIf(charClass == RegexCharClass.NotHexDigitUpperClass); 5612if (RegexCharClass.TryGetSingleRange(charClass, out char lowInclusive, out char highInclusive)) 5630NegateIf(RegexCharClass.IsNegated(charClass)); 5641if (RegexCharClass.TryGetOnlyCategories(charClass, categories, out int numCategories, out bool negated)) 5659int numChars = RegexCharClass.GetSetChars(charClass, setChars); 5662if (RegexCharClass.DifferByOneBit(setChars[0], setChars[1], out int mask)) // special-case common case of an upper and lowercase ASCII letter combination 5692NegateIf(RegexCharClass.IsNegated(charClass)); 5698if (RegexCharClass.TryGetDoubleRange(charClass, out (char LowInclusive, char HighInclusive) rangeLower, out (char LowInclusive, char HighInclusive) rangeUpper) && 5705bool negate = RegexCharClass.IsNegated(charClass); 5720RegexCharClass.CharClassAnalysisResults analysis = RegexCharClass.Analyze(charClass); 5731bool negatedClass = RegexCharClass.IsNegated(charClass); 5734if (RegexCharClass.CharInClass((char)i, charClass) ^ negatedClass) 5789bool negatedClass = RegexCharClass.IsNegated(charClass); 5792if (RegexCharClass.CharInClass((char)i, charClass) ^ negatedClass) 5840if (RegexCharClass.TryGetDoubleRange(charClass, out (char LowInclusive, char HighInclusive) range0, out (char LowInclusive, char HighInclusive) range1)) 5842bool negate = RegexCharClass.IsNegated(charClass); 5978if (RegexCharClass.CharInClass(c, charClass)) 6160if (chars.Length is 4 or 5 && !RegexCharClass.IsAscii(chars))

131if (!RegexCharClass.IsNegated(charClass) && 132(scratchCount = RegexCharClass.GetSetChars(charClass, scratch)) > 0) 142Debug.Assert(!RegexCharClass.IsNegated(charClass)); 149Debug.Assert(!RegexCharClass.IsNegated(charClass) || chars is null); 498if (RegexCharClass.CharInClass(span[i], set, ref startingAsciiLookup)) 677if (RegexCharClass.CharInClass(span[i], primarySet.Set, ref startingAsciiLookup)) 771if (!RegexCharClass.CharInClass(c, nextSet.Set, ref _asciiLookups![i])) 790if (!RegexCharClass.CharInClass(c, primarySet.Set, ref startingAsciiLookup)) 799if (!RegexCharClass.CharInClass(c, nextSet.Set, ref _asciiLookups![i])) 841while ((uint)--prev < (uint)slice.Length && RegexCharClass.CharInClass(slice[prev], loopNode.Str!, ref _asciiLookups![0])) ;

842if (!RegexCharClass.CharInClass(Forwardcharnext(inputSpan), _code.Strings[operand], ref _code.StringsAsciiLookup[operand])) 934if (!RegexCharClass.CharInClass(Forwardcharnext(inputSpan), set, ref setLookup)) 1021if (!RegexCharClass.CharInClass(Forwardcharnext(inputSpan), set, ref setLookup)) 1112if (!RegexCharClass.CharInClass(Forwardcharnext(inputSpan), _code.Strings[operand0], ref _code.StringsAsciiLookup[operand0]))

165sb.Append(Indent()).Append('\'').Append(RegexCharClass.DescribeChar((char)Codes[opcodeOffset + 1])).Append('\''); 173sb.Append(Indent()).Append(RegexCharClass.DescribeSet(Strings[Codes[opcodeOffset + 1]]));

26/// <remarks>For a <see cref="RegexNodeKind.Multi"/>, this is the string from the expression. For an <see cref="IsSetFamily"/> node, this is the character class string from <see cref="RegexCharClass"/>.</remarks> 126string stringSet = RegexCharClass.CharsToStringClass(equivalences); 879if (RegexCharClass.IsEmpty(Str)) 884else if (RegexCharClass.IsSingleton(Str)) 886Ch = RegexCharClass.SingletonChar(Str); 894else if (RegexCharClass.IsSingletonInverse(Str)) 896Ch = RegexCharClass.SingletonChar(Str); 909case RegexCharClass.WordNotWordClass: 910case RegexCharClass.NotWordWordClass: 911case RegexCharClass.DigitNotDigitClass: 912case RegexCharClass.NotDigitDigitClass: 913case RegexCharClass.SpaceNotSpaceClass: 914case RegexCharClass.NotSpaceSpaceClass: 915Str = RegexCharClass.AnyClass; 1004if (!wasLastSet || optionsLast != optionsAt || lastNodeCannotMerge || !RegexCharClass.IsMergeable(at.Str!)) 1007lastNodeCannotMerge = !RegexCharClass.IsMergeable(at.Str!); 1025RegexCharClass prevCharClass; 1033prevCharClass = RegexCharClass.Parse(prev.Str!); 1042RegexCharClass atCharClass = RegexCharClass.Parse(at.Str!); 1446if (RegexCharClass.TryGetSingleRange(node.Str!, out char lowInclusive, out char highInclusive) && 1450return new StartingLiteralData(range: (lowInclusive, highInclusive), negated: RegexCharClass.IsNegated(node.Str!)); 1455if ((numChars = RegexCharClass.GetSetChars(node.Str!, setChars)) != 0) 1457return new StartingLiteralData(setChars: setChars.Slice(0, numChars).ToString(), negated: RegexCharClass.IsNegated(node.Str!)); 2126case RegexNodeKind.Set when !RegexCharClass.CharInClass(node.Ch, subsequent.Str!): 2129case RegexNodeKind.Setlazy or RegexNodeKind.Setloop or RegexNodeKind.Setloopatomic when subsequent.M > 0 && !RegexCharClass.CharInClass(node.Ch, subsequent.Str!): 2137case RegexNodeKind.Setlazy or RegexNodeKind.Setloop or RegexNodeKind.Setloopatomic when subsequent.M == 0 && !RegexCharClass.CharInClass(node.Ch, subsequent.Str!): 2138case RegexNodeKind.Boundary when node.M > 0 && RegexCharClass.IsBoundaryWordChar(node.Ch): 2139case RegexNodeKind.NonBoundary when node.M > 0 && !RegexCharClass.IsBoundaryWordChar(node.Ch): 2140case RegexNodeKind.ECMABoundary when node.M > 0 && RegexCharClass.IsECMAWordChar(node.Ch): 2141case RegexNodeKind.NonECMABoundary when node.M > 0 && !RegexCharClass.IsECMAWordChar(node.Ch): 2173case RegexNodeKind.One when !RegexCharClass.CharInClass(subsequent.Ch, node.Str!): 2174case RegexNodeKind.Set when !RegexCharClass.MayOverlap(node.Str!, subsequent.Str!): 2175case RegexNodeKind.Onelazy or RegexNodeKind.Oneloop or RegexNodeKind.Oneloopatomic when subsequent.M > 0 && !RegexCharClass.CharInClass(subsequent.Ch, node.Str!): 2176case RegexNodeKind.Setlazy or RegexNodeKind.Setloop or RegexNodeKind.Setloopatomic when subsequent.M > 0 && !RegexCharClass.MayOverlap(node.Str!, subsequent.Str!): 2177case RegexNodeKind.Multi when !RegexCharClass.CharInClass(subsequent.Str![0], node.Str!): 2179case RegexNodeKind.EndZ or RegexNodeKind.Eol when !RegexCharClass.CharInClass('\n', node.Str!): 2182case RegexNodeKind.Onelazy or RegexNodeKind.Oneloop or RegexNodeKind.Oneloopatomic when subsequent.M == 0 && !RegexCharClass.CharInClass(subsequent.Ch, node.Str!): 2183case RegexNodeKind.Setlazy or RegexNodeKind.Setloop or RegexNodeKind.Setloopatomic when subsequent.M == 0 && !RegexCharClass.MayOverlap(node.Str!, subsequent.Str!): 2184case RegexNodeKind.Boundary when node.M > 0 && node.Str is RegexCharClass.WordClass or RegexCharClass.DigitClass: 2185case RegexNodeKind.NonBoundary when node.M > 0 && node.Str is RegexCharClass.NotWordClass or RegexCharClass.NotDigitClass: 2186case RegexNodeKind.ECMABoundary when node.M > 0 && node.Str is RegexCharClass.ECMAWordClass or RegexCharClass.ECMADigitClass: 2187case RegexNodeKind.NonECMABoundary when node.M > 0 && node.Str is RegexCharClass.NotECMAWordClass or RegexCharClass.NotDigitClass: 2539RegexCharClass.ParticipatesInCaseConversion(child.Ch)) 2550if (!RegexCharClass.IsAscii(child.Str.AsSpan()) || 2551RegexCharClass.ParticipatesInCaseConversion(child.Str.AsSpan())) 2563if (!RegexCharClass.SetContainsAsciiOrdinalIgnoreCaseCharacter(child.Str!, twoChars)) 2902sb.Append(" '").Append(RegexCharClass.DescribeChar(Ch)).Append('\''); 2919sb.Append(RegexCharClass.DescribeChar(c)); 2927sb.Append(' ').Append(RegexCharClass.DescribeSet(Str!));

22/// <remarks>The <see cref="RegexCharClass"/> set string is specified in <see cref="RegexNode.Str"/>.</remarks> 40/// <remarks>The <see cref="RegexCharClass"/> set string is specified in <see cref="RegexNode.Str"/>, the minimum number of iterations in <see cref="RegexNode.M"/>, and the maximum number of iterations in <see cref="RegexNode.N"/>.</remarks> 53/// <remarks>The <see cref="RegexCharClass"/> set string is specified in <see cref="RegexNode.Str"/>, the minimum number of iterations in <see cref="RegexNode.M"/>, and the maximum number of iterations in <see cref="RegexNode.N"/>.</remarks> 71/// The <see cref="RegexCharClass"/> set string is specified in <see cref="RegexNode.Str"/>, the minimum number of iterations in <see cref="RegexNode.M"/>, and the maximum number of iterations in <see cref="RegexNode.N"/>.

403new RegexNode(RegexNodeKind.Set, _options & ~RegexOptions.IgnoreCase, RegexCharClass.AnyClass) : 547private RegexCharClass? ScanCharClass(bool caseInsensitive, bool scanOnly) 555RegexCharClass? charClass = scanOnly ? null : new RegexCharClass(); 710RegexCharClass? rcc = ScanCharClass(caseInsensitive, scanOnly); 865else if (RegexCharClass.IsBoundaryWordChar(ch)) 912else if (RegexCharClass.IsBoundaryWordChar(ch)) 967else if (RegexCharClass.IsBoundaryWordChar(ch)) 1096new RegexNode(RegexNodeKind.Set, (_options & ~RegexOptions.IgnoreCase), (_options & RegexOptions.ECMAScript) != 0 ? RegexCharClass.ECMAWordClass : RegexCharClass.WordClass); 1101new RegexNode(RegexNodeKind.Set, (_options & ~RegexOptions.IgnoreCase), (_options & RegexOptions.ECMAScript) != 0 ? RegexCharClass.NotECMAWordClass : RegexCharClass.NotWordClass); 1106new RegexNode(RegexNodeKind.Set, (_options & ~RegexOptions.IgnoreCase), (_options & RegexOptions.ECMAScript) != 0 ? RegexCharClass.ECMASpaceClass : RegexCharClass.SpaceClass); 1111new RegexNode(RegexNodeKind.Set, (_options & ~RegexOptions.IgnoreCase), (_options & RegexOptions.ECMAScript) != 0 ? RegexCharClass.NotECMASpaceClass : RegexCharClass.NotSpaceClass); 1116new RegexNode(RegexNodeKind.Set, (_options & ~RegexOptions.IgnoreCase), (_options & RegexOptions.ECMAScript) != 0 ? RegexCharClass.ECMADigitClass : RegexCharClass.DigitClass); 1121new RegexNode(RegexNodeKind.Set, (_options & ~RegexOptions.IgnoreCase), (_options & RegexOptions.ECMAScript) != 0 ? RegexCharClass.NotECMADigitClass : RegexCharClass.NotDigitClass); 1131var cc = new RegexCharClass(); 1261else if (angled && RegexCharClass.IsBoundaryWordChar(ch)) 1360else if (angled && RegexCharClass.IsBoundaryWordChar(ch)) 1422if (!RegexCharClass.IsBoundaryWordChar(_pattern[_pos++])) 1609if ((_options & RegexOptions.ECMAScript) == 0 && RegexCharClass.IsBoundaryWordChar(ch)) 1635if (!(RegexCharClass.IsBoundaryWordChar(ch) || ch == '-')) 1728if (ch != '0' && RegexCharClass.IsBoundaryWordChar(ch)) 2021case > 1 when (_options & RegexOptions.IgnoreCase) == 0 || isReplacement || !RegexCharClass.ParticipatesInCaseConversion(_pattern.AsSpan(pos, cch)):

112case RegexNodeKind.One or RegexNodeKind.Oneloop or RegexNodeKind.Onelazy or RegexNodeKind.Oneloopatomic when !ignoreCase || !RegexCharClass.ParticipatesInCaseConversion(node.Ch): 138if (RegexCharClass.ParticipatesInCaseConversion(c)) 156case RegexNodeKind.Set or RegexNodeKind.Setloop or RegexNodeKind.Setlazy or RegexNodeKind.Setloopatomic when !RegexCharClass.IsNegated(node.Str!): // negated sets are too complex to analyze 158int charCount = RegexCharClass.GetSetChars(node.Str!, setChars); 197if (!RegexCharClass.SetContainsAsciiOrdinalIgnoreCaseCharacter(node.Str!, setChars)) 530if (results[i].Set == RegexCharClass.AnyClass) 532results.RemoveAll(s => s.Set == RegexCharClass.AnyClass); 543charClass == RegexCharClass.AnyClass) // weed out match-all, same as above 557result.Negated = RegexCharClass.IsNegated(result.Set); 559if (RegexCharClass.TryGetSingleRange(result.Set, out char lowInclusive, out char highInclusive) && 566int count = RegexCharClass.GetSetChars(result.Set, scratch); 603string setString = RegexCharClass.OneToStringClass(node.Ch); 611string setString = RegexCharClass.OneToStringClass(node.Ch); 627string setString = RegexCharClass.OneToStringClass(s[i]); 714var combined = new Dictionary<int, (RegexCharClass Set, int Count)>(); 742if (combined.TryGetValue(fixedSet.Distance, out (RegexCharClass Set, int Count) value)) 744if (value.Set.TryAddCharClass(RegexCharClass.Parse(fixedSet.Set))) 752combined[fixedSet.Distance] = (RegexCharClass.Parse(fixedSet.Set), 1); 757foreach (KeyValuePair<int, (RegexCharClass Set, int Count)> pair in combined) 829if (!RegexCharClass.IsAscii(s1Chars) && !RegexCharClass.IsAscii(s2Chars)) 915RegexCharClass? cc = null; 933static bool? TryFindFirstCharClass(RegexNode node, ref RegexCharClass? cc) 977cc = RegexCharClass.Parse(node.Str!); 980else if (cc.CanMerge && RegexCharClass.Parse(node.Str!) is { CanMerge: true } setCc) 1160RegexCharClass.CharInClass(prefix[0], firstChild.Str!) ? null : 1176!RegexCharClass.ParticipatesInCaseConversion(ordinalCaseInsensitivePrefix[0]) || 1179if (RegexCharClass.ParticipatesInCaseConversion(ordinalCaseInsensitivePrefix[0])) 1181if (RegexCharClass.CharInClass((char)(ordinalCaseInsensitivePrefix[0] | 0x20), firstChild.Str!) || 1182RegexCharClass.CharInClass((char)(ordinalCaseInsensitivePrefix[0] & ~0x20), firstChild.Str!)) 1187else if (RegexCharClass.CharInClass(ordinalCaseInsensitivePrefix[0], firstChild.Str!)) 1208!RegexCharClass.IsNegated(nextChild.Str!) && 1212chars = chars.Slice(0, RegexCharClass.GetSetChars(nextChild.Str!, chars)); 1217if (RegexCharClass.CharInClass(c, firstChild.Str!))

410return (index > startpos && RegexCharClass.IsBoundaryWordChar(runtext![index - 1])) != 411(index < endpos && RegexCharClass.IsBoundaryWordChar(runtext![index])); 417return ((uint)indexM1 < (uint)inputSpan.Length && RegexCharClass.IsBoundaryWordChar(inputSpan[indexM1])) != 418((uint)index < (uint)inputSpan.Length && RegexCharClass.IsBoundaryWordChar(inputSpan[index])); 422internal static bool IsWordChar(char ch) => RegexCharClass.IsWordChar(ch); 426return (index > startpos && RegexCharClass.IsECMAWordChar(runtext![index - 1])) != 427(index < endpos && RegexCharClass.IsECMAWordChar(runtext![index])); 433return ((uint)indexM1 < (uint)inputSpan.Length && RegexCharClass.IsECMAWordChar(inputSpan[indexM1])) != 434((uint)index < (uint)inputSpan.Length && RegexCharClass.IsECMAWordChar(inputSpan[index])); 440string charClass = RegexCharClass.ConvertOldStringsToClass(set, category); 441return RegexCharClass.CharInClass(ch, charClass); 446return RegexCharClass.CharInClass(ch, charClass);

147var rcc = new RegexCharClass(); 152return RegexCharClass.DescribeSet(rcc.ToStringClass());

22/// <summary>Cache of BDDs created to represent <see cref="RegexCharClass"/> set strings.</summary> 323/// <summary>Creates a BDD from the <see cref="RegexCharClass"/> set string to determine whether a char is in the set.</summary> 355bool negate = RegexCharClass.IsNegated(set); 361List<(char First, char Last)>? ranges = RegexCharClass.ComputeRanges(set); 381int setLength = set[RegexCharClass.SetLengthIndex]; 382int catLength = set[RegexCharClass.CategoryLengthIndex]; 383int catStart = setLength + RegexCharClass.SetStartIndex; 523Debug.Assert(Enum.IsDefined(code) || code == (UnicodeCategory)(RegexCharClass.SpaceConst - 1), $"Unknown category: {code}"); 524return code == (UnicodeCategory)(RegexCharClass.SpaceConst - 1) ?