category.cs

来自「没的 没的 没的 没的 没的 没的 没的 没的 没的 没的 没的 没的 没的 没」· CS 代码 · 共 638 行 · 第 1/2 页

//
// assembly:	System
// namespace:	System.Text.RegularExpressions
// file:	category.cs
//
// author:	Dan Lewis ([e-mail])
// 		(c) 2002

using System;
using System.Globalization;

namespace System.Text.RegularExpressions {

	enum Category : ushort {
		None,

		// canonical classes
	
		Any,			// any character except newline		.
		AnySingleline,		// any character			. (s option)
		Word,			// any word character			\w
		Digit,			// any digit character			\d
		WhiteSpace,		// any whitespace character		\s
		
		// ECMAScript classes


		EcmaAny,
		EcmaAnySingleline,
		EcmaWord,		// [a-zA-Z_0-9]
		EcmaDigit,		// [0-9]
		EcmaWhiteSpace,		// [ \f\n\r\t\v]

		// unicode categories
		
		UnicodeL,		// Letter
		UnicodeM,		// Mark
		UnicodeN,		// Number
		UnicodeZ,		// Separator
		UnicodeP,		// Punctuation
		UnicodeS,		// Symbol
		UnicodeC,		// Other

		UnicodeLu,		// UppercaseLetter
		UnicodeLl,		// LowercaseLetter
		UnicodeLt,		// TitlecaseLetter
		UnicodeLm,		// ModifierLetter
		UnicodeLo,		// OtherLetter
		UnicodeMn,		// NonspacingMark
		UnicodeMe,		// EnclosingMark
		UnicodeMc,		// SpacingMark
		UnicodeNd,		// DecimalNumber
		UnicodeNl,		// LetterNumber
		UnicodeNo,		// OtherNumber
		UnicodeZs,		// SpaceSeparator
		UnicodeZl,		// LineSeparator
		UnicodeZp,		// ParagraphSeparator
		UnicodePd,		// DashPunctuation
		UnicodePs,		// OpenPunctuation
		UnicodePi,		// InitialPunctuation
		UnicodePe,		// ClosePunctuation
		UnicodePf,		// FinalPunctuation
		UnicodePc,		// ConnectorPunctuation
		UnicodePo,		// OtherPunctuation
		UnicodeSm,		// MathSymbol
		UnicodeSc,		// CurrencySymbol
		UnicodeSk,		// ModifierSymbol
		UnicodeSo,		// OtherSymbol
		UnicodeCc,		// Control
		UnicodeCf,		// Format
		UnicodeCo,		// PrivateUse
		UnicodeCs,		// Surrogate
		UnicodeCn,		// Unassigned

		// unicode block ranges

		// notes: the categories marked with a star are valid unicode block ranges,
		// but don't seem to be accepted by the MS parser using the /p{...} format.
		// any ideas?

		UnicodeBasicLatin,
		UnicodeLatin1Supplement,			// *
		UnicodeLatinExtendedA,				// *
		UnicodeLatinExtendedB,				// *
		UnicodeIPAExtensions,
		UnicodeSpacingModifierLetters,
		UnicodeCombiningDiacriticalMarks,
		UnicodeGreek,
		UnicodeCyrillic,
		UnicodeArmenian,
		UnicodeHebrew,
		UnicodeArabic,
		UnicodeSyriac,
		UnicodeThaana,
		UnicodeDevanagari,
		UnicodeBengali,
		UnicodeGurmukhi,
		UnicodeGujarati,
		UnicodeOriya,
		UnicodeTamil,
		UnicodeTelugu,
		UnicodeKannada,
		UnicodeMalayalam,
		UnicodeSinhala,
		UnicodeThai,
		UnicodeLao,
		UnicodeTibetan,
		UnicodeMyanmar,
		UnicodeGeorgian,
		UnicodeHangulJamo,
		UnicodeEthiopic,
		UnicodeCherokee,
		UnicodeUnifiedCanadianAboriginalSyllabics,
		UnicodeOgham,
		UnicodeRunic,
		UnicodeKhmer,
		UnicodeMongolian,
		UnicodeLatinExtendedAdditional,
		UnicodeGreekExtended,
		UnicodeGeneralPunctuation,
		UnicodeSuperscriptsandSubscripts,
		UnicodeCurrencySymbols,
		UnicodeCombiningMarksforSymbols,
		UnicodeLetterlikeSymbols,
		UnicodeNumberForms,
		UnicodeArrows,
		UnicodeMathematicalOperators,
		UnicodeMiscellaneousTechnical,
		UnicodeControlPictures,
		UnicodeOpticalCharacterRecognition,
		UnicodeEnclosedAlphanumerics,
		UnicodeBoxDrawing,
		UnicodeBlockElements,
		UnicodeGeometricShapes,
		UnicodeMiscellaneousSymbols,
		UnicodeDingbats,
		UnicodeBraillePatterns,
		UnicodeCJKRadicalsSupplement,
		UnicodeKangxiRadicals,
		UnicodeIdeographicDescriptionCharacters,
		UnicodeCJKSymbolsandPunctuation,
		UnicodeHiragana,
		UnicodeKatakana,
		UnicodeBopomofo,
		UnicodeHangulCompatibilityJamo,
		UnicodeKanbun,
		UnicodeBopomofoExtended,
		UnicodeEnclosedCJKLettersandMonths,
		UnicodeCJKCompatibility,
		UnicodeCJKUnifiedIdeographsExtensionA,
		UnicodeCJKUnifiedIdeographs,
		UnicodeYiSyllables,
		UnicodeYiRadicals,
		UnicodeHangulSyllables,
		UnicodeHighSurrogates,
		UnicodeHighPrivateUseSurrogates,
		UnicodeLowSurrogates,
		UnicodePrivateUse,
		UnicodeCJKCompatibilityIdeographs,
		UnicodeAlphabeticPresentationForms,
		UnicodeArabicPresentationFormsA,		// *
		UnicodeCombiningHalfMarks,
		UnicodeCJKCompatibilityForms,
		UnicodeSmallFormVariants,
		UnicodeArabicPresentationFormsB,		// *
		UnicodeSpecials,
		UnicodeHalfwidthandFullwidthForms,
		
		UnicodeOldItalic,
		UnicodeGothic,
		UnicodeDeseret,
		UnicodeByzantineMusicalSymbols,
		UnicodeMusicalSymbols,
		UnicodeMathematicalAlphanumericSymbols,
		UnicodeCJKUnifiedIdeographsExtensionB,
		UnicodeCJKCompatibilityIdeographsSupplement,
		UnicodeTags
	}

	class CategoryUtils {
		public static Category CategoryFromName (string name) {
			try {
				if (name.StartsWith ("Is"))	// remove prefix from block range
					name = name.Substring (2);

				return (Category)Enum.Parse (typeof (Category), "Unicode" + name);
			}
			catch (ArgumentException) {
				return Category.None;
			}
		}
	
		public static bool IsCategory (Category cat, char c) {
			switch (cat) {
			case Category.None:
				return false;
			
			case Category.Any:
				return c != '\n';

			case Category.AnySingleline:
				return true;

			case Category.Word:
				return
					Char.IsLetterOrDigit (c) ||
					IsCategory (UnicodeCategory.ConnectorPunctuation, c);

			case Category.Digit:
				return Char.IsDigit (c);

			case Category.WhiteSpace:
				return Char.IsWhiteSpace (c);

			// ECMA categories

			case Category.EcmaAny:
				return c != '\n';
				
			case Category.EcmaAnySingleline:
				return true;

			case Category.EcmaWord:
				return
					'a' <= c && c <= 'z' ||
					'A' <= c && c <= 'Z' ||
					'0' <= c && c <= '9' ||
					'_' == c;

			case Category.EcmaDigit:
				return
					'0' <= c && c <= 9;
			
			case Category.EcmaWhiteSpace:
				return
					c == ' '  ||
					c == '\f' ||
					c == '\n' ||
					c == '\r' ||
					c == '\t' ||
					c == '\v';

			// Unicode categories...

			// letter
			
			case Category.UnicodeLu: return IsCategory (UnicodeCategory.UppercaseLetter, c);
			case Category.UnicodeLl: return IsCategory (UnicodeCategory.LowercaseLetter, c);
			case Category.UnicodeLt: return IsCategory (UnicodeCategory.TitlecaseLetter, c);
			case Category.UnicodeLm: return IsCategory (UnicodeCategory.ModifierLetter, c);
			case Category.UnicodeLo: return IsCategory (UnicodeCategory.OtherLetter, c);

			// mark

			case Category.UnicodeMn: return IsCategory (UnicodeCategory.NonSpacingMark, c);
			case Category.UnicodeMe: return IsCategory (UnicodeCategory.EnclosingMark, c);
			case Category.UnicodeMc: return IsCategory (UnicodeCategory.SpacingCombiningMark, c);
			case Category.UnicodeNd: return IsCategory (UnicodeCategory.DecimalDigitNumber, c);

			// number

			case Category.UnicodeNl: return IsCategory (UnicodeCategory.LetterNumber, c);
			case Category.UnicodeNo: return IsCategory (UnicodeCategory.OtherNumber, c);

			// separator

			case Category.UnicodeZs: return IsCategory (UnicodeCategory.SpaceSeparator, c);
			case Category.UnicodeZl: return IsCategory (UnicodeCategory.LineSeparator, c);
			case Category.UnicodeZp: return IsCategory (UnicodeCategory.ParagraphSeparator, c);

			// punctuation

			case Category.UnicodePd: return IsCategory (UnicodeCategory.DashPunctuation, c);
			case Category.UnicodePs: return IsCategory (UnicodeCategory.OpenPunctuation, c);
			case Category.UnicodePi: return IsCategory (UnicodeCategory.InitialQuotePunctuation, c);
			case Category.UnicodePe: return IsCategory (UnicodeCategory.ClosePunctuation, c);
			case Category.UnicodePf: return IsCategory (UnicodeCategory.FinalQuotePunctuation, c);
			case Category.UnicodePc: return IsCategory (UnicodeCategory.ConnectorPunctuation, c);
			case Category.UnicodePo: return IsCategory (UnicodeCategory.OtherPunctuation, c);

			// symbol

			case Category.UnicodeSm: return IsCategory (UnicodeCategory.MathSymbol, c);
			case Category.UnicodeSc: return IsCategory (UnicodeCategory.CurrencySymbol, c);
			case Category.UnicodeSk: return IsCategory (UnicodeCategory.ModifierSymbol, c);
			case Category.UnicodeSo: return IsCategory (UnicodeCategory.OtherSymbol, c);

			// other

			case Category.UnicodeCc: return IsCategory (UnicodeCategory.Control, c);
			case Category.UnicodeCf: return IsCategory (UnicodeCategory.Format, c);
			case Category.UnicodeCo: return IsCategory (UnicodeCategory.PrivateUse, c);
			case Category.UnicodeCs: return IsCategory (UnicodeCategory.Surrogate, c);
			case Category.UnicodeCn: return IsCategory (UnicodeCategory.OtherNotAssigned, c); 

			case Category.UnicodeL:	// letter
				return
					IsCategory (UnicodeCategory.UppercaseLetter, c) ||
					IsCategory (UnicodeCategory.LowercaseLetter, c) ||
					IsCategory (UnicodeCategory.TitlecaseLetter, c) ||
					IsCategory (UnicodeCategory.ModifierLetter, c) ||
					IsCategory (UnicodeCategory.OtherLetter, c);
			
			case Category.UnicodeM:	// mark
				return
					IsCategory (UnicodeCategory.NonSpacingMark, c) ||
					IsCategory (UnicodeCategory.EnclosingMark, c) ||
					IsCategory (UnicodeCategory.SpacingCombiningMark, c);

			case Category.UnicodeN:	// number
				return
					IsCategory (UnicodeCategory.DecimalDigitNumber, c) ||
					IsCategory (UnicodeCategory.LetterNumber, c) ||
					IsCategory (UnicodeCategory.OtherNumber, c);

			case Category.UnicodeZ:	// separator
				return
					IsCategory (UnicodeCategory.SpaceSeparator, c) ||
					IsCategory (UnicodeCategory.LineSeparator, c) ||