beagled/Lucene.Net/Analysis/LengthFilter.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> Removes words that are too long and too short from the stream.
  23         ///
  24         /// </summary>
  25         /// <author>  David Spencer
  26         /// </author>
  27         /// <version>  $Id: LengthFilter.cs,v 1.2 2006/10/02 17:08:47 joeshaw Exp $
  28         /// </version>
  29         public sealed class LengthFilter : TokenFilter
  30         {
  31
  32                 internal int min;
  33                 internal int max;
  34
  35                 /// <summary> Build a filter that removes words that are too long or too
  36                 /// short from the text.
  37                 /// </summary>
  38                 public LengthFilter(TokenStream in_Renamed, int min, int max) : base(in_Renamed)
  39                 {
  40                         this.min = min;
  41                         this.max = max;
  42                 }
  43
  44                 /// <summary> Returns the next input Token whose termText() is the right len</summary>
  45                 public override Token Next()
  46                 {
  47                         // return the first non-stop word found
  48                         for (Token token = input.Next(); token != null; token = input.Next())
  49                         {
  50                                 int len = token.TermText().Length;
  51                                 if (len >= min && len <= max)
  52                                 {
  53                                         return token;
  54                                 }
  55                                 // note: else we ignore it but should we index each part of it?
  56                         }
  57                         // reached EOS -- return null
  58                         return null;
  59                 }
  60         }
  61 }