package org.apache.lucene.analysis;
/**
* 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.
*/
import java.io.IOException;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
/**
* Removes words that are too long or too short from the stream.
* <p>
* Note: Length is calculated as the number of UTF-16 code units.
* </p>
*/
public final class LengthFilter extends FilteringTokenFilter {
private final int min;
private final int max;
private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
/**
* Build a filter that removes words that are too long or too
* short from the text.
*/
public LengthFilter(boolean enablePositionIncrements, TokenStream in, int min, int max) {
super(enablePositionIncrements, in);
this.min = min;
this.max = max;
}
/**
* Build a filter that removes words that are too long or too
* short from the text.
* @deprecated Use {@link #LengthFilter(boolean, TokenStream, int, int)} instead.
*/
@Deprecated
public LengthFilter(TokenStream in, int min, int max) {
this(false, in, min, max);
}
@Override
public boolean accept() throws IOException {
final int len = termAtt.length();
return (len >= min && len <= max);
}
}