2 * Copyright 2004 The Apache Software Foundation
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
8 * http://www.apache.org/licenses/LICENSE-2.0
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.
17 namespace Lucene
.Net
.Analysis
20 /// <summary>Transforms the token stream as per the Porter stemming algorithm.
21 /// Note: the input to the stemming filter must already be in lower case,
22 /// so you will need to use LowerCaseFilter or LowerCaseTokenizer farther
23 /// down the Tokenizer chain in order for this to work properly!
25 /// To use this filter with other analyzers, you'll want to write an
26 /// Analyzer class that sets up the TokenStream chain as you want it.
27 /// To use this with LowerCaseTokenizer, for example, you'd write an
28 /// analyzer like this:
31 /// class MyAnalyzer extends Analyzer {
32 /// public final TokenStream tokenStream(String fieldName, Reader reader) {
33 /// return new PorterStemFilter(new LowerCaseTokenizer(reader));
38 public sealed class PorterStemFilter
: TokenFilter
40 private PorterStemmer stemmer
;
42 public PorterStemFilter(TokenStream in_Renamed
) : base(in_Renamed
)
44 stemmer
= new PorterStemmer();
47 /// <summary>Returns the next input Token, after being stemmed </summary>
48 public override Token
Next()
50 Token token
= input
.Next();
55 System
.String s
= stemmer
.Stem(token
.termText
);
56 if ((System
.Object
) s
!= (System
.Object
) token
.termText
)
57 // Yes, I mean object reference comparison here