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
  17 using System;
  18
  19 namespace Lucene.Net.Analysis
  20 {
  21
  22         /// <summary>Filters LetterTokenizer with LowerCaseFilter and StopFilter. </summary>
  23
  24         public sealed class StopAnalyzer : Analyzer
  25         {
  26                 private System.Collections.Hashtable stopWords;
  27
  28                 /// <summary>An array containing some common English words that are not usually useful
  29                 /// for searching.
  30                 /// </summary>
  31                 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"};
  32
  33                 /// <summary>Builds an analyzer which removes words in ENGLISH_STOP_WORDS. </summary>
  34                 public StopAnalyzer()
  35                 {
  36                         stopWords = StopFilter.MakeStopSet(ENGLISH_STOP_WORDS);
  37                 }
  38
  39                 /// <summary>Builds an analyzer with the stop words from the given set.</summary>
  40                 public StopAnalyzer(System.Collections.Hashtable stopWords)
  41                 {
  42                         this.stopWords = stopWords;
  43                 }
  44
  45                 /// <summary>Builds an analyzer which removes words in the provided array. </summary>
  46                 public StopAnalyzer(System.String[] stopWords)
  47                 {
  48                         this.stopWords = StopFilter.MakeStopSet(stopWords);
  49                 }
  50
  51                 /// <summary>Builds an analyzer with the stop words from the given file.</summary>
  52                 /// <seealso cref="WordlistLoader.GetWordSet(File)">
  53                 /// </seealso>
  54                 public StopAnalyzer(System.IO.FileInfo stopwordsFile)
  55                 {
  56                         stopWords = WordlistLoader.GetWordSet(stopwordsFile);
  57                 }
  58
  59                 /// <summary>Builds an analyzer with the stop words from the given reader.</summary>
  60                 /// <seealso cref="WordlistLoader.GetWordSet(Reader)">
  61                 /// </seealso>
  62                 public StopAnalyzer(System.IO.TextReader stopwords)
  63                 {
  64                         stopWords = WordlistLoader.GetWordSet(stopwords);
  65                 }
  66
  67                 /// <summary>Filters LowerCaseTokenizer with StopFilter. </summary>
  68                 public override TokenStream TokenStream(System.String fieldName, System.IO.TextReader reader)
  69                 {
  70                         return new StopFilter(new LowerCaseTokenizer(reader), stopWords);
  71                 }
  72         }
  73 }