1 package org.apache.lucene.analysis.hi;
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.KeywordMarkerFilter;
23 import org.apache.lucene.analysis.TokenFilter;
24 import org.apache.lucene.analysis.TokenStream;
25 import org.apache.lucene.analysis.tokenattributes.KeywordAttribute;
26 import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
29 * A {@link TokenFilter} that applies {@link HindiNormalizer} to normalize the
32 * In some cases the normalization may cause unrelated terms to conflate, so
33 * to prevent terms from being normalized use an instance of
34 * {@link KeywordMarkerFilter} or a custom {@link TokenFilter} that sets
35 * the {@link KeywordAttribute} before this {@link TokenStream}.
37 * @see HindiNormalizer
39 public final class HindiNormalizationFilter extends TokenFilter {
41 private final HindiNormalizer normalizer = new HindiNormalizer();
42 private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
43 private final KeywordAttribute keywordAtt = addAttribute(KeywordAttribute.class);
45 public HindiNormalizationFilter(TokenStream input) {
50 public boolean incrementToken() throws IOException {
51 if (input.incrementToken()) {
52 if (!keywordAtt.isKeyword())
53 termAtt.setLength(normalizer.normalize(termAtt.buffer(),