1
package org.apache.lucene.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.StringReader;
22
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
23
import org.apache.lucene.document.Document;
24
import org.apache.lucene.document.Field;
25
import org.apache.lucene.index.IndexReader;
26
import org.apache.lucene.index.IndexWriter;
27
import org.apache.lucene.index.IndexWriterConfig;
28
import org.apache.lucene.index.Term;
29
import org.apache.lucene.index.TermDocs;
30
import org.apache.lucene.queryParser.QueryParser;
31
import org.apache.lucene.search.IndexSearcher;
32
import org.apache.lucene.search.Query;
33
import org.apache.lucene.search.ScoreDoc;
34
import org.apache.lucene.store.RAMDirectory;
36
public class TestKeywordAnalyzer extends BaseTokenStreamTestCase {
38
private RAMDirectory directory;
39
private IndexSearcher searcher;
42
public void setUp() throws Exception {
44
directory = new RAMDirectory();
45
IndexWriter writer = new IndexWriter(directory, new IndexWriterConfig(
46
TEST_VERSION_CURRENT, new SimpleAnalyzer(
47
TEST_VERSION_CURRENT)));
49
Document doc = new Document();
50
doc.add(new Field("partnum", "Q36", Field.Store.YES, Field.Index.NOT_ANALYZED));
51
doc.add(new Field("description", "Illidium Space Modulator", Field.Store.YES, Field.Index.ANALYZED));
52
writer.addDocument(doc);
56
searcher = new IndexSearcher(directory, true);
59
public void testPerFieldAnalyzer() throws Exception {
60
PerFieldAnalyzerWrapper analyzer = new PerFieldAnalyzerWrapper(new SimpleAnalyzer(TEST_VERSION_CURRENT));
61
analyzer.addAnalyzer("partnum", new KeywordAnalyzer());
63
QueryParser queryParser = new QueryParser(TEST_VERSION_CURRENT, "description", analyzer);
64
Query query = queryParser.parse("partnum:Q36 AND SPACE");
66
ScoreDoc[] hits = searcher.search(query, null, 1000).scoreDocs;
67
assertEquals("Q36 kept as-is",
68
"+partnum:Q36 +space", query.toString("description"));
69
assertEquals("doc found!", 1, hits.length);
72
public void testMutipleDocument() throws Exception {
73
RAMDirectory dir = new RAMDirectory();
74
IndexWriter writer = new IndexWriter(dir, new IndexWriterConfig(TEST_VERSION_CURRENT, new KeywordAnalyzer()));
75
Document doc = new Document();
76
doc.add(new Field("partnum", "Q36", Field.Store.YES, Field.Index.ANALYZED));
77
writer.addDocument(doc);
79
doc.add(new Field("partnum", "Q37", Field.Store.YES, Field.Index.ANALYZED));
80
writer.addDocument(doc);
83
IndexReader reader = IndexReader.open(dir, true);
84
TermDocs td = reader.termDocs(new Term("partnum", "Q36"));
85
assertTrue(td.next());
86
td = reader.termDocs(new Term("partnum", "Q37"));
87
assertTrue(td.next());
91
public void testOffsets() throws Exception {
92
TokenStream stream = new KeywordAnalyzer().tokenStream("field", new StringReader("abcd"));
93
OffsetAttribute offsetAtt = stream.addAttribute(OffsetAttribute.class);
94
assertTrue(stream.incrementToken());
95
assertEquals(0, offsetAtt.startOffset());
96
assertEquals(4, offsetAtt.endOffset());
99
/** blast some random strings through the analyzer */
100
public void testRandomStrings() throws Exception {
101
checkRandomData(random, new KeywordAnalyzer(), 10000*RANDOM_MULTIPLIER);