1 package org.apache.lucene.analysis.en;
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;
25 import org.apache.lucene.analysis.tokenattributes.KeywordAttribute;
27 /** A high-performance kstem filter for english.
29 * See <a href="http://ciir.cs.umass.edu/pubfiles/ir-35.pdf">
30 * "Viewing Morphology as an Inference Process"</a>
31 * (Krovetz, R., Proceedings of the Sixteenth Annual International ACM SIGIR
32 * Conference on Research and Development in Information Retrieval, 191-203, 1993).
34 * All terms must already be lowercased for this filter to work correctly.
37 public final class KStemFilter extends TokenFilter {
38 private final KStemmer stemmer = new KStemmer();
39 private final CharTermAttribute termAttribute = addAttribute(CharTermAttribute.class);
40 private final KeywordAttribute keywordAtt = addAttribute(KeywordAttribute.class);
42 public KStemFilter(TokenStream in) {
46 /** Returns the next, stemmed, input Token.
47 * @return The stemed form of a token.
51 public boolean incrementToken() throws IOException {
52 if (!input.incrementToken())
55 char[] term = termAttribute.buffer();
56 int len = termAttribute.length();
57 if ((!keywordAtt.isKeyword()) && stemmer.stem(term, len)) {
58 termAttribute.setEmpty().append(stemmer.asCharSequence());