1 package org.apache.lucene.analysis.br;
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;
23 import org.apache.lucene.analysis.KeywordMarkerFilter; // for javadoc
24 import org.apache.lucene.analysis.TokenFilter;
25 import org.apache.lucene.analysis.TokenStream;
26 import org.apache.lucene.analysis.tokenattributes.KeywordAttribute;
27 import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
30 * A {@link TokenFilter} that applies {@link BrazilianStemmer}.
32 * To prevent terms from being stemmed use an instance of
33 * {@link KeywordMarkerFilter} or a custom {@link TokenFilter} that sets
34 * the {@link KeywordAttribute} before this {@link TokenStream}.
36 * @see KeywordMarkerFilter
39 public final class BrazilianStemFilter extends TokenFilter {
42 * {@link BrazilianStemmer} in use by this filter.
44 private BrazilianStemmer stemmer = new BrazilianStemmer();
45 private Set<?> exclusions = null;
46 private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
47 private final KeywordAttribute keywordAttr = addAttribute(KeywordAttribute.class);
50 * Creates a new BrazilianStemFilter
52 * @param in the source {@link TokenStream}
54 public BrazilianStemFilter(TokenStream in) {
59 * Creates a new BrazilianStemFilter
61 * @param in the source {@link TokenStream}
62 * @param exclusiontable a set of terms that should be prevented from being stemmed.
63 * @deprecated use {@link KeywordAttribute} with {@link KeywordMarkerFilter} instead.
66 public BrazilianStemFilter(TokenStream in, Set<?> exclusiontable) {
68 this.exclusions = exclusiontable;
72 public boolean incrementToken() throws IOException {
73 if (input.incrementToken()) {
74 final String term = termAtt.toString();
75 // Check the exclusion table.
76 if (!keywordAttr.isKeyword() && (exclusions == null || !exclusions.contains(term))) {
77 final String s = stemmer.stem(term);
78 // If not stemmed, don't waste the time adjusting the token.
79 if ((s != null) && !s.equals(term))
80 termAtt.setEmpty().append(s);