Analyzer.cs :  » Search-Engines » dotLucene » Lucene » Net » Analysis » C# / CSharp Open Source

Home
C# / CSharp Open Source
1.2.6.4 mono .net core
2.2.6.4 mono core
3.Aspect Oriented Frameworks
4.Bloggers
5.Build Systems
6.Business Application
7.Charting Reporting Tools
8.Chat Servers
9.Code Coverage Tools
10.Content Management Systems CMS
11.CRM ERP
12.Database
13.Development
14.Email
15.Forum
16.Game
17.GIS
18.GUI
19.IDEs
20.Installers Generators
21.Inversion of Control Dependency Injection
22.Issue Tracking
23.Logging Tools
24.Message
25.Mobile
26.Network Clients
27.Network Servers
28.Office
29.PDF
30.Persistence Frameworks
31.Portals
32.Profilers
33.Project Management
34.RSS RDF
35.Rule Engines
36.Script
37.Search Engines
38.Sound Audio
39.Source Control
40.SQL Clients
41.Template Engines
42.Testing
43.UML
44.Web Frameworks
45.Web Service
46.Web Testing
47.Wiki Engines
48.Windows Presentation Foundation
49.Workflows
50.XML Parsers
C# / C Sharp
C# / C Sharp by API
C# / CSharp Tutorial
C# / CSharp Open Source » Search Engines » dotLucene 
dotLucene » Lucene » Net » Analysis » Analyzer.cs
/*
 * Copyright 2004 The Apache Software Foundation
 * 
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 * 
 * http://www.apache.org/licenses/LICENSE-2.0
 * 
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

using System;

namespace Lucene.Net.Analysis{
  
  /// <summary>An Analyzer builds TokenStreams, which analyze text.  It thus represents a
  /// policy for extracting index terms from text.
  /// <p>
  /// Typical implementations first build a Tokenizer, which breaks the stream of
  /// characters from the Reader into raw Tokens.  One or more TokenFilters may
  /// then be applied to the output of the Tokenizer.
  /// <p>
  /// WARNING: You must override one of the methods defined by this class in your
  /// subclass or the Analyzer will enter an infinite loop.
  /// </summary>
  public abstract class Analyzer
  {
    /// <summary>Creates a TokenStream which tokenizes all the text in the provided
    /// Reader.  Default implementation forwards to tokenStream(Reader) for 
    /// compatibility with older version.  Override to allow Analyzer to choose 
    /// strategy based on document and/or field.  Must be able to handle null
    /// field name for backward compatibility. 
    /// </summary>
    public virtual TokenStream TokenStream(System.String fieldName, System.IO.TextReader reader)
    {
      // implemented for backward compatibility
      return TokenStream(reader);
    }
    
    /// <summary>Creates a TokenStream which tokenizes all the text in the provided
    /// Reader.  Provided for backward compatibility only.
    /// </summary>
    /// <deprecated> use tokenStream(String, Reader) instead.
    /// </deprecated>
    /// <seealso cref="TokenStream(String, Reader)">
    /// </seealso>
    public virtual TokenStream TokenStream(System.IO.TextReader reader)
    {
      return TokenStream(null, reader);
    }
    
    /// <summary> Invoked before indexing a Field instance if
    /// terms have already been added to that field.  This allows custom
    /// analyzers to place an automatic position increment gap between
    /// Field instances using the same field name.  The default value
    /// position increment gap is 0.  With a 0 position increment gap and
    /// the typical default token position increment of 1, all terms in a field,
    /// including across Field instances, are in successive positions, allowing
    /// exact PhraseQuery matches, for instance, across Field instance boundaries.
    /// 
    /// </summary>
    /// <param name="fieldName">Field name being indexed.
    /// </param>
    /// <returns> position increment gap, added to the next token emitted from {@link #TokenStream(String,Reader)}
    /// </returns>
    public virtual int GetPositionIncrementGap(System.String fieldName)
    {
      return 0;
    }
  }
}
www.java2v.com | Contact Us
Copyright 2009 - 12 Demo Source and Support. All rights reserved.
All other trademarks are property of their respective owners.