beagled/Lucene.Net/Analysis/PorterStemFilter.cs

   1 /*
   2  * Copyright 2004 The Apache Software Foundation
   3  *
   4  * Licensed under the Apache License, Version 2.0 (the "License");
   5  * you may not use this file except in compliance with the License.
   6  * You may obtain a copy of the License at
   7  *
   8  * http://www.apache.org/licenses/LICENSE-2.0
   9  *
  10  * Unless required by applicable law or agreed to in writing, software
  11  * distributed under the License is distributed on an "AS IS" BASIS,
  12  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  13  * See the License for the specific language governing permissions and
  14  * limitations under the License.
  15  */
  16
  17 using System;
  18
  19 namespace Lucene.Net.Analysis
  20 {
  21
  22         /// <summary>Transforms the token stream as per the Porter stemming algorithm.
  23         /// Note: the input to the stemming filter must already be in lower case,
  24         /// so you will need to use LowerCaseFilter or LowerCaseTokenizer farther
  25         /// down the Tokenizer chain in order for this to work properly!
  26         /// <P>
  27         /// To use this filter with other analyzers, you'll want to write an
  28         /// Analyzer class that sets up the TokenStream chain as you want it.
  29         /// To use this with LowerCaseTokenizer, for example, you'd write an
  30         /// analyzer like this:
  31         /// <P>
  32         /// <PRE>
  33         /// class MyAnalyzer extends Analyzer {
  34         /// public final TokenStream tokenStream(String fieldName, Reader reader) {
  35         /// return new PorterStemFilter(new LowerCaseTokenizer(reader));
  36         /// }
  37         /// }
  38         /// </PRE>
  39         /// </summary>
  40         public sealed class PorterStemFilter : TokenFilter
  41         {
  42                 private PorterStemmer stemmer;
  43
  44                 public PorterStemFilter(TokenStream in_Renamed) : base(in_Renamed)
  45                 {
  46                         stemmer = new PorterStemmer();
  47                 }
  48
  49                 /// <summary>Returns the next input Token, after being stemmed </summary>
  50                 public override Token Next()
  51                 {
  52                         Token token = input.Next();
  53                         if (token == null)
  54                                 return null;
  55                         else
  56                         {
  57                                 System.String s = stemmer.Stem(token.termText);
  58                                 if ((System.Object) s != (System.Object) token.termText)
  59                                 // Yes, I mean object reference comparison here
  60                                         token.termText = s;
  61                                 return token;
  62                         }
  63                 }
  64         }
  65 }