1
package org.apache.solr.analysis;
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.Reader;
21
import java.io.StringReader;
22
import java.util.HashMap;
25
import org.apache.lucene.analysis.MockTokenizer;
26
import org.apache.lucene.analysis.TokenStream;
27
import org.apache.lucene.analysis.Tokenizer;
28
import org.apache.solr.common.ResourceLoader;
29
import org.apache.solr.core.SolrResourceLoader;
32
* Simple tests to ensure the Hyphenation compound filter factory is working.
34
public class TestHyphenationCompoundWordTokenFilterFactory extends BaseTokenTestCase {
36
* Ensure the factory works with hyphenation grammar+dictionary: using default options.
38
public void testHyphenationWithDictionary() throws Exception {
39
Reader reader = new StringReader("min veninde som er lidt af en læsehest");
40
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
41
HyphenationCompoundWordTokenFilterFactory factory = new HyphenationCompoundWordTokenFilterFactory();
42
ResourceLoader loader = new SolrResourceLoader(null, null);
43
Map<String,String> args = new HashMap<String,String>(DEFAULT_VERSION_PARAM);
44
args.put("hyphenator", "da_UTF8.xml");
45
args.put("dictionary", "da_compoundDictionary.txt");
47
factory.inform(loader);
48
TokenStream stream = factory.create(tokenizer);
50
assertTokenStreamContents(stream,
51
new String[] { "min", "veninde", "som", "er", "lidt", "af", "en", "læsehest", "læse", "hest" },
52
new int[] { 1, 1, 1, 1, 1, 1, 1, 1, 0, 0 }
57
* Ensure the factory works with no dictionary: using hyphenation grammar only.
58
* Also change the min/max subword sizes from the default. When using no dictionary,
59
* its generally necessary to tweak these, or you get lots of expansions.
61
public void testHyphenationOnly() throws Exception {
62
Reader reader = new StringReader("basketballkurv");
63
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
64
HyphenationCompoundWordTokenFilterFactory factory = new HyphenationCompoundWordTokenFilterFactory();
65
ResourceLoader loader = new SolrResourceLoader(null, null);
66
Map<String,String> args = new HashMap<String,String>(DEFAULT_VERSION_PARAM);
67
args.put("hyphenator", "da_UTF8.xml");
68
args.put("minSubwordSize", "2");
69
args.put("maxSubwordSize", "4");
71
factory.inform(loader);
72
TokenStream stream = factory.create(tokenizer);
74
assertTokenStreamContents(stream,
75
new String[] { "basketballkurv", "ba", "sket", "bal", "ball", "kurv" }