/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
using System;
namespace Lucene.Net.Analysis
{
/// Filters LetterTokenizer with LowerCaseFilter and StopFilter.
public sealed class StopAnalyzer : Analyzer
{
private System.Collections.Hashtable stopWords;
/// An array containing some common English words that are not usually useful
/// for searching.
///
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"};
/// Builds an analyzer which removes words in ENGLISH_STOP_WORDS.
public StopAnalyzer()
{
stopWords = StopFilter.MakeStopSet(ENGLISH_STOP_WORDS);
}
/// Builds an analyzer with the stop words from the given set.
public StopAnalyzer(System.Collections.Hashtable stopWords)
{
this.stopWords = stopWords;
}
/// Builds an analyzer which removes words in the provided array.
public StopAnalyzer(System.String[] stopWords)
{
this.stopWords = StopFilter.MakeStopSet(stopWords);
}
/// Builds an analyzer with the stop words from the given file.
///
///
public StopAnalyzer(System.IO.FileInfo stopwordsFile)
{
stopWords = WordlistLoader.GetWordSet(stopwordsFile);
}
/// Builds an analyzer with the stop words from the given reader.
///
///
public StopAnalyzer(System.IO.TextReader stopwords)
{
stopWords = WordlistLoader.GetWordSet(stopwords);
}
/// Filters LowerCaseTokenizer with StopFilter.
public override TokenStream TokenStream(System.String fieldName, System.IO.TextReader reader)
{
return new StopFilter(new LowerCaseTokenizer(reader), stopWords);
}
}
}