/*
* Copyright 2004 The Apache Software Foundation
*
* Licensed 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;
using Lucene.Net.Analysis;
namespace Lucene.Net.Analysis.Standard
{
/// Filters {@link StandardTokenizer} with {@link StandardFilter}, {@link
/// LowerCaseFilter} and {@link StopFilter}, using a list of English stop words.
///
///
/// $Id: StandardAnalyzer.cs,v 1.3 2005/10/06 19:29:55 dsd Exp $
///
public class StandardAnalyzer : Analyzer
{
private System.Collections.Hashtable stopSet;
/// An array containing some common English words that are usually not
/// useful for searching.
///
public static readonly System.String[] STOP_WORDS;
/// Builds an analyzer with the default stop words ({@link #STOP_WORDS}).
public StandardAnalyzer() : this(STOP_WORDS)
{
}
/// Builds an analyzer with the given stop words.
public StandardAnalyzer(System.String[] stopWords)
{
stopSet = StopFilter.MakeStopSet(stopWords);
}
/// Constructs a {@link StandardTokenizer} filtered by a {@link
/// StandardFilter}, a {@link LowerCaseFilter} and a {@link StopFilter}.
///
public override TokenStream TokenStream(System.String fieldName, System.IO.TextReader reader)
{
TokenStream result = new StandardTokenizer(reader);
result = new StandardFilter(result);
result = new LowerCaseFilter(result);
result = new StopFilter(result, stopSet);
return result;
}
static StandardAnalyzer()
{
STOP_WORDS = StopAnalyzer.ENGLISH_STOP_WORDS;
}
}
}