Class HMMChineseTokenizerFactory

Factory for HMMChineseTokenizer

Note: this class will currently emit tokens for punctuation. So you should either add a Lucene.Net.Analysis.Miscellaneous.WordDelimiterFilter after to remove these (with concatenate off), or use the SmartChinese stoplist with a StopFilterFactory via:

words="org/apache/lucene/analysis/cn/smart/stopwords.txt"

This is a Lucene.NET EXPERIMENTAL API, use at your own risk

Inheritance

System.Object

Lucene.Net.Analysis.Util.AbstractAnalysisFactory

Lucene.Net.Analysis.Util.TokenizerFactory

HMMChineseTokenizerFactory

Inherited Members

Lucene.Net.Analysis.Util.TokenizerFactory.ForName(System.String, System.Collections.Generic.IDictionary<System.String, System.String>)

Lucene.Net.Analysis.Util.TokenizerFactory.LookupClass(System.String)

Lucene.Net.Analysis.Util.TokenizerFactory.AvailableTokenizers

Lucene.Net.Analysis.Util.TokenizerFactory.ReloadTokenizers()

Lucene.Net.Analysis.Util.TokenizerFactory.Create(System.IO.TextReader)

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.LUCENE_MATCH_VERSION_PARAM

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.m_luceneMatchVersion

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.OriginalArgs

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.AssureMatchVersion()

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.LuceneMatchVersion

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.Require(System.Collections.Generic.IDictionary<System.String, System.String>, System.String)

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.Require(System.Collections.Generic.IDictionary<System.String, System.String>, System.String, System.Collections.Generic.ICollection<System.String>)

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.Require(System.Collections.Generic.IDictionary<System.String, System.String>, System.String, System.Collections.Generic.ICollection<System.String>, System.Boolean)

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.Get(System.Collections.Generic.IDictionary<System.String, System.String>, System.String, System.String)

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.Get(System.Collections.Generic.IDictionary<System.String, System.String>, System.String, System.Collections.Generic.ICollection<System.String>)

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.Get(System.Collections.Generic.IDictionary<System.String, System.String>, System.String, System.Collections.Generic.ICollection<System.String>, System.String)

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.RequireInt32(System.Collections.Generic.IDictionary<System.String, System.String>, System.String)

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.GetInt32(System.Collections.Generic.IDictionary<System.String, System.String>, System.String, System.Int32)

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.RequireBoolean(System.Collections.Generic.IDictionary<System.String, System.String>, System.String)

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.GetBoolean(System.Collections.Generic.IDictionary<System.String, System.String>, System.String, System.Boolean)

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.RequireSingle(System.Collections.Generic.IDictionary<System.String, System.String>, System.String)

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.GetSingle(System.Collections.Generic.IDictionary<System.String, System.String>, System.String, System.Single)

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.RequireChar(System.Collections.Generic.IDictionary<System.String, System.String>, System.String)

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.GetChar(System.Collections.Generic.IDictionary<System.String, System.String>, System.String, System.Char)

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.GetSet(System.Collections.Generic.IDictionary<System.String, System.String>, System.String)

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.GetPattern(System.Collections.Generic.IDictionary<System.String, System.String>, System.String)

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.GetCulture(System.Collections.Generic.IDictionary<System.String, System.String>, System.String, System.Globalization.CultureInfo)

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.GetWordSet(Lucene.Net.Analysis.Util.IResourceLoader, System.String, System.Boolean)

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.GetLines(Lucene.Net.Analysis.Util.IResourceLoader, System.String)

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.GetSnowballWordSet(Lucene.Net.Analysis.Util.IResourceLoader, System.String, System.Boolean)

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.SplitFileNames(System.String)

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.GetClassArg()

Lucene.Net.Analysis.Util.AbstractAnalysisFactory.IsExplicitLuceneMatchVersion

System.Object.Equals(System.Object)

System.Object.Equals(System.Object, System.Object)

System.Object.GetHashCode()

System.Object.GetType()

System.Object.MemberwiseClone()

System.Object.ReferenceEquals(System.Object, System.Object)

System.Object.ToString()

Namespace: Lucene.Net.Analysis.Cn.Smart

Assembly: Lucene.Net.Analysis.SmartCn.dll

Syntax

public sealed class HMMChineseTokenizerFactory : TokenizerFactory

Constructors

| Improve this Doc View Source

HMMChineseTokenizerFactory(IDictionary<String, String>)

Creates a new HMMChineseTokenizerFactory

Declaration

public HMMChineseTokenizerFactory(IDictionary<string, string> args)

Parameters

Type	Name	Description
System.Collections.Generic.IDictionary<System.String, System.String>	args

Methods

| Improve this Doc View Source

Create(AttributeSource.AttributeFactory, TextReader)

Declaration

public override Tokenizer Create(AttributeSource.AttributeFactory factory, TextReader reader)

Parameters

Type	Name	Description
Lucene.Net.Util.AttributeSource.AttributeFactory	factory
System.IO.TextReader	reader

Returns

Type	Description
Lucene.Net.Analysis.Tokenizer

Overrides

Lucene.Net.Analysis.Util.TokenizerFactory.Create(Lucene.Net.Util.AttributeSource.AttributeFactory, System.IO.TextReader)