beagled/Lucene.Net/Analysis/StopAnalyzer.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 using System;
  17 namespace Lucene.Net.Analysis
  18 {
  19
  20         /// <summary>Filters LetterTokenizer with LowerCaseFilter and StopFilter. </summary>
  21
  22         public sealed class StopAnalyzer:Analyzer
  23         {
  24                 private System.Collections.Hashtable stopWords;
  25
  26                 /// <summary>An array containing some common English words that are not usually useful
  27                 /// for searching.
  28                 /// </summary>
  29                 public static readonly System.String[] ENGLISH_STOP_WORDS = new System.String[]{"a", "an", "and", "are", "as", "at", "be", "but", "by", "for", "if", "in", "into", "is", "it", "no", "not", "of", "on", "or", "s", "such", "t", "that", "the", "their", "then", "there", "these", "they", "this", "to", "was", "will", "with"};
  30
  31                 /// <summary>Builds an analyzer which removes words in ENGLISH_STOP_WORDS. </summary>
  32                 public StopAnalyzer()
  33                 {
  34                         stopWords = StopFilter.MakeStopSet(ENGLISH_STOP_WORDS);
  35                 }
  36
  37                 /// <summary>Builds an analyzer which removes words in the provided array. </summary>
  38                 public StopAnalyzer(System.String[] stopWords)
  39                 {
  40                         this.stopWords = StopFilter.MakeStopSet(stopWords);
  41                 }
  42
  43                 /// <summary>Filters LowerCaseTokenizer with StopFilter. </summary>
  44                 public override TokenStream TokenStream(System.String fieldName, System.IO.TextReader reader)
  45                 {
  46                         return new StopFilter(new LowerCaseTokenizer(reader), stopWords);
  47                 }
  48         }
  49 }