1
package org.apache.lucene.analysis.bg;
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;
21
import java.util.Collections;
23
import org.apache.lucene.analysis.Analyzer;
24
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
25
import org.apache.lucene.analysis.CharArraySet;
26
import org.apache.lucene.util.Version;
29
* Test the Bulgarian analyzer
31
public class TestBulgarianAnalyzer extends BaseTokenStreamTestCase {
34
* This test fails with NPE when the stopwords file is missing in classpath
36
public void testResourcesAvailable() {
37
new BulgarianAnalyzer(TEST_VERSION_CURRENT);
40
public void testStopwords() throws IOException {
41
Analyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT);
42
assertAnalyzesTo(a, "Как се казваш?", new String[] {"казваш"});
45
public void testCustomStopwords() throws IOException {
46
Analyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT, Collections
48
assertAnalyzesTo(a, "Как се казваш?",
49
new String[] {"как", "се", "казваш"});
52
public void testReusableTokenStream() throws IOException {
53
Analyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT);
54
assertAnalyzesToReuse(a, "документи", new String[] {"документ"});
55
assertAnalyzesToReuse(a, "документ", new String[] {"документ"});
59
* Test some examples from the paper
61
public void testBasicExamples() throws IOException {
62
Analyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT);
63
assertAnalyzesTo(a, "енергийни кризи", new String[] {"енергийн", "криз"});
64
assertAnalyzesTo(a, "Атомната енергия", new String[] {"атомн", "енерг"});
66
assertAnalyzesTo(a, "компютри", new String[] {"компютр"});
67
assertAnalyzesTo(a, "компютър", new String[] {"компютр"});
69
assertAnalyzesTo(a, "градове", new String[] {"град"});
72
public void testWithStemExclusionSet() throws IOException {
73
CharArraySet set = new CharArraySet(Version.LUCENE_31, 1, true);
75
Analyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT, CharArraySet.EMPTY_SET, set);
76
assertAnalyzesTo(a, "строевете строеве", new String[] { "строй", "строеве" });
79
/** blast some random strings through the analyzer */
80
public void testRandomStrings() throws Exception {
81
checkRandomData(random, new BulgarianAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);