1 package org.apache.lucene.analysis.pt;
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.KeywordMarkerFilter;
25 import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
26 import org.apache.lucene.analysis.tokenattributes.KeywordAttribute;
29 * A {@link TokenFilter} that applies {@link PortugueseStemmer} to stem
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}.
37 public final class PortugueseStemFilter extends TokenFilter {
38 private final PortugueseStemmer stemmer = new PortugueseStemmer();
39 private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
40 private final KeywordAttribute keywordAttr = addAttribute(KeywordAttribute.class);
42 public PortugueseStemFilter(TokenStream input) {
47 public boolean incrementToken() throws IOException {
48 if (input.incrementToken()) {
49 if (!keywordAttr.isKeyword()) {
50 // this stemmer increases word length by 1: worst case '*ã' -> '*ão'
51 final int len = termAtt.length();
52 final int newlen = stemmer.stem(termAtt.resizeBuffer(len+1), len);
53 termAtt.setLength(newlen);