// original code from Apache Solr - ported to work with Lucene 3.x and reformatted to Search coding style
/**
* 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.solr.analysis;
import java.io.IOException;
import java.util.Set;
import org.apache.lucene.analysis.CharArraySet;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.TermAttribute;
/**
* A TokenFilter that only keeps tokens with text contained in the
* required words. This filter behaves like the inverse of StopFilter.
*
* @version $Id: KeepWordFilter.java 940806 2010-05-04 11:18:46Z uschindler $
* @since solr 1.3
*/
public final class KeepWordFilter extends TokenFilter {
private final CharArraySet words;
private final TermAttribute termAtt = addAttribute( TermAttribute.class );
/**
* @deprecated Use {@link #KeepWordFilter(TokenStream, Set, boolean)} instead
*/
@Deprecated
public KeepWordFilter(TokenStream in, Set<String> words, boolean ignoreCase) {
this( in, new CharArraySet( words, ignoreCase ) );
}
/**
* The words set passed to this constructor will be directly used by this filter
* and should not be modified,
*/
public KeepWordFilter(TokenStream in, CharArraySet words) {
super( in );
this.words = words;
}
@Override
public boolean incrementToken() throws IOException {
while ( input.incrementToken() ) {
if ( words.contains( termAtt.termBuffer(), 0, termAtt.termLength() ) ) {
return true;
}
}
return false;
}
}