/**
* 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.
*/
package org.apache.mahout.analysis;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.CharArraySet;
import org.apache.lucene.analysis.LowerCaseFilter;
import org.apache.lucene.analysis.StopAnalyzer;
import org.apache.lucene.analysis.StopFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.standard.StandardFilter;
import org.apache.lucene.wikipedia.analysis.WikipediaTokenizer;
import java.io.Reader;
public class WikipediaAnalyzer extends Analyzer {
private final CharArraySet stopSet;
public WikipediaAnalyzer() {
stopSet = (CharArraySet) StopFilter.makeStopSet(StopAnalyzer.ENGLISH_STOP_WORDS);
}
public WikipediaAnalyzer(CharArraySet stopSet) {
this.stopSet = stopSet;
}
@Override
public TokenStream tokenStream(String fieldName, Reader reader) {
TokenStream result = new WikipediaTokenizer(reader);
result = new StandardFilter(result);
result = new LowerCaseFilter(result);
result = new StopFilter(true, result, stopSet);
return result;
}
}