1
package org.apache.lucene.analysis.cz;
3
import java.io.IOException;
5
import org.apache.lucene.analysis.KeywordMarkerFilter;// for javadoc
6
import org.apache.lucene.analysis.TokenFilter;
7
import org.apache.lucene.analysis.TokenStream;
8
import org.apache.lucene.analysis.tokenattributes.KeywordAttribute;
9
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
12
* Licensed to the Apache Software Foundation (ASF) under one or more
13
* contributor license agreements. See the NOTICE file distributed with
14
* this work for additional information regarding copyright ownership.
15
* The ASF licenses this file to You under the Apache License, Version 2.0
16
* (the "License"); you may not use this file except in compliance with
17
* the License. You may obtain a copy of the License at
19
* http://www.apache.org/licenses/LICENSE-2.0
21
* Unless required by applicable law or agreed to in writing, software
22
* distributed under the License is distributed on an "AS IS" BASIS,
23
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
24
* See the License for the specific language governing permissions and
25
* limitations under the License.
29
* A {@link TokenFilter} that applies {@link CzechStemmer} to stem Czech words.
31
* To prevent terms from being stemmed use an instance of
32
* {@link KeywordMarkerFilter} or a custom {@link TokenFilter} that sets
33
* the {@link KeywordAttribute} before this {@link TokenStream}.
35
* <p><b>NOTE</b>: Input is expected to be in lowercase,
36
* but with diacritical marks</p>
37
* @see KeywordMarkerFilter
39
public final class CzechStemFilter extends TokenFilter {
40
private final CzechStemmer stemmer = new CzechStemmer();
41
private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
42
private final KeywordAttribute keywordAttr = addAttribute(KeywordAttribute.class);
44
public CzechStemFilter(TokenStream input) {
49
public boolean incrementToken() throws IOException {
50
if (input.incrementToken()) {
51
if(!keywordAttr.isKeyword()) {
52
final int newlen = stemmer.stem(termAtt.buffer(), termAtt.length());
53
termAtt.setLength(newlen);