1 package org.apache.lucene.analysis;
4 * Licensed to the Apache Software Foundation (ASF) under one or more
5 * contributor license agreements. See the NOTICE file distributed with
6 * this work for additional information regarding copyright ownership.
7 * The ASF licenses this file to You under the Apache License, Version 2.0
8 * (the "License"); you may not use this file except in compliance with
9 * the License. You may obtain a copy of the License at
11 * http://www.apache.org/licenses/LICENSE-2.0
13 * Unless required by applicable law or agreed to in writing, software
14 * distributed under the License is distributed on an "AS IS" BASIS,
15 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16 * See the License for the specific language governing permissions and
17 * limitations under the License.
20 import java.io.IOException;
22 import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
25 * Removes words that are too long or too short from the stream.
27 * Note: Length is calculated as the number of UTF-16 code units.
30 public final class LengthFilter extends FilteringTokenFilter {
32 private final int min;
33 private final int max;
35 private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
38 * Build a filter that removes words that are too long or too
39 * short from the text.
41 public LengthFilter(boolean enablePositionIncrements, TokenStream in, int min, int max) {
42 super(enablePositionIncrements, in);
48 * Build a filter that removes words that are too long or too
49 * short from the text.
50 * @deprecated Use {@link #LengthFilter(boolean, TokenStream, int, int)} instead.
53 public LengthFilter(TokenStream in, int min, int max) {
54 this(false, in, min, max);
58 public boolean accept() throws IOException {
59 final int len = termAtt.length();
60 return (len >= min && len <= max);