Class PatternAnalyzer

Namespace

Examine.Lucene.Analyzers

Assembly

Examine.Lucene.dll

Analyzer that uses regex to parse out tokens

public class PatternAnalyzer : Analyzer, IDisposable

Inheritance

object

Analyzer

PatternAnalyzer

Implements

IDisposable

Inherited Members

Analyzer.GLOBAL_REUSE_STRATEGY

Analyzer.PER_FIELD_REUSE_STRATEGY

Analyzer.NewAnonymous(Func<string, TextReader, TokenStreamComponents>)

Analyzer.NewAnonymous(Func<string, TextReader, TokenStreamComponents>, ReuseStrategy)

Analyzer.NewAnonymous(Func<string, TextReader, TokenStreamComponents>, Func<string, TextReader, TextReader>)

Analyzer.NewAnonymous(Func<string, TextReader, TokenStreamComponents>, Func<string, TextReader, TextReader>, ReuseStrategy)

Analyzer.GetTokenStream(string, TextReader)

Analyzer.GetTokenStream(string, string)

Analyzer.InitReader(string, TextReader)

Analyzer.GetPositionIncrementGap(string)

Analyzer.GetOffsetGap(string)

Analyzer.Dispose()

Analyzer.Dispose(bool)

Analyzer.Strategy

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Constructors

PatternAnalyzer(string, int, bool, CharArraySet?)

Creates a new PatternAnalyzer

public PatternAnalyzer(string format, int regexGroup, bool lowercase = false, CharArraySet? stopWords = null)

Parameters

format string

The regex pattern

regexGroup int

The regex group number to match. -1 to use as a split.

lowercase bool

Whether to lower case the tokens

stopWords CharArraySet

Any stop words that should be included

Methods

CreateComponents(string, TextReader)

Creates the analyzer components

protected override TokenStreamComponents CreateComponents(string fieldName, TextReader reader)

Parameters

fieldName string

The field name

reader TextReader

The TextReader

Returns

TokenStreamComponents

The Lucene.Net.Analysis.TokenStreamComponents