1 package org.apache.lucene.analysis.ar;
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.TokenFilter;
23 import org.apache.lucene.analysis.TokenStream;
24 import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
27 * A {@link TokenFilter} that applies {@link ArabicNormalizer} to normalize the orthography.
31 public final class ArabicNormalizationFilter extends TokenFilter {
32 private final ArabicNormalizer normalizer = new ArabicNormalizer();
33 private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
35 public ArabicNormalizationFilter(TokenStream input) {
40 public boolean incrementToken() throws IOException {
41 if (input.incrementToken()) {
42 int newlen = normalizer.normalize(termAtt.buffer(), termAtt.length());
43 termAtt.setLength(newlen);