Lucene.Net  3.0.3
Lucene.Net is a port of the Lucene search engine library, written in C# and targeted at .NET runtime users.
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Properties Pages
LengthFilter.cs
Go to the documentation of this file.
1 /*
2  * Licensed to the Apache Software Foundation (ASF) under one or more
3  * contributor license agreements. See the NOTICE file distributed with
4  * this work for additional information regarding copyright ownership.
5  * The ASF licenses this file to You under the Apache License, Version 2.0
6  * (the "License"); you may not use this file except in compliance with
7  * the License. You may obtain a copy of the License at
8  *
9  * http://www.apache.org/licenses/LICENSE-2.0
10  *
11  * Unless required by applicable law or agreed to in writing, software
12  * distributed under the License is distributed on an "AS IS" BASIS,
13  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14  * See the License for the specific language governing permissions and
15  * limitations under the License.
16  */
17 
18 using Lucene.Net.Analysis.Tokenattributes;
19 
20 namespace Lucene.Net.Analysis
21 {
22 
23  /// <summary>Removes words that are too long or too short from the stream.</summary>
24  public sealed class LengthFilter:TokenFilter
25  {
26 
27  internal int min;
28  internal int max;
29 
30  private readonly ITermAttribute termAtt;
31 
32  /// <summary> Build a filter that removes words that are too long or too
33  /// short from the text.
34  /// </summary>
35  public LengthFilter(TokenStream in_Renamed, int min, int max)
36  : base(in_Renamed)
37  {
38  this.min = min;
39  this.max = max;
40  termAtt = AddAttribute<ITermAttribute>();
41  }
42 
43  /// <summary> Returns the next input Token whose term() is the right len</summary>
44  public override bool IncrementToken()
45  {
46  // return the first non-stop word found
47  while (input.IncrementToken())
48  {
49  var len = termAtt.TermLength();
50  if (len >= min && len <= max)
51  {
52  return true;
53  }
54  // note: else we ignore it but should we index each part of it?
55  }
56  // reached EOS -- return false
57  return false;
58  }
59  }
60 }