1 package org.apache.lucene.queryParser.complexPhrase;
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.util.HashSet;
22 import org.apache.lucene.analysis.Analyzer;
23 import org.apache.lucene.analysis.MockAnalyzer;
24 import org.apache.lucene.document.Document;
25 import org.apache.lucene.document.Field;
26 import org.apache.lucene.index.IndexWriter;
27 import org.apache.lucene.queryParser.QueryParser;
28 import org.apache.lucene.search.IndexSearcher;
29 import org.apache.lucene.search.Query;
30 import org.apache.lucene.search.ScoreDoc;
31 import org.apache.lucene.search.TopDocs;
32 import org.apache.lucene.store.Directory;
33 import org.apache.lucene.util.LuceneTestCase;
35 public class TestComplexPhraseQuery extends LuceneTestCase {
37 Analyzer analyzer = new MockAnalyzer(random);
39 DocData docsContent[] = { new DocData("john smith", "1"),
40 new DocData("johathon smith", "2"),
41 new DocData("john percival smith", "3"),
42 new DocData("jackson waits tom", "4") };
44 private IndexSearcher searcher;
46 String defaultFieldName = "name";
48 public void testComplexPhrases() throws Exception {
49 checkMatches("\"john smith\"", "1"); // Simple multi-term still works
50 checkMatches("\"j* smyth~\"", "1,2"); // wildcards and fuzzies are OK in
52 checkMatches("\"(jo* -john) smith\"", "2"); // boolean logic works
53 checkMatches("\"jo* smith\"~2", "1,2,3"); // position logic works.
54 checkMatches("\"jo* [sma TO smZ]\" ", "1,2"); // range queries supported
55 checkMatches("\"john\"", "1,3"); // Simple single-term still works
56 checkMatches("\"(john OR johathon) smith\"", "1,2"); // boolean logic with
58 checkMatches("\"(jo* -john) smyth~\"", "2"); // boolean logic with
61 // checkMatches("\"john -percival\"", "1"); // not logic doesn't work
64 checkMatches("\"john nosuchword*\"", ""); // phrases with clauses producing
67 checkBadQuery("\"jo* id:1 smith\""); // mixing fields in a phrase is bad
68 checkBadQuery("\"jo* \"smith\" \""); // phrases inside phrases is bad
71 private void checkBadQuery(String qString) {
72 QueryParser qp = new ComplexPhraseQueryParser(TEST_VERSION_CURRENT, defaultFieldName, analyzer);
73 Throwable expected = null;
76 } catch (Throwable e) {
79 assertNotNull("Expected parse error in " + qString, expected);
83 private void checkMatches(String qString, String expectedVals)
85 QueryParser qp = new ComplexPhraseQueryParser(TEST_VERSION_CURRENT, defaultFieldName, analyzer);
86 qp.setFuzzyPrefixLength(1); // usually a good idea
88 Query q = qp.parse(qString);
90 HashSet<String> expecteds = new HashSet<String>();
91 String[] vals = expectedVals.split(",");
92 for (int i = 0; i < vals.length; i++) {
93 if (vals[i].length() > 0)
94 expecteds.add(vals[i]);
97 TopDocs td = searcher.search(q, 10);
98 ScoreDoc[] sd = td.scoreDocs;
99 for (int i = 0; i < sd.length; i++) {
100 Document doc = searcher.doc(sd[i].doc);
101 String id = doc.get("id");
102 assertTrue(qString + "matched doc#" + id + " not expected", expecteds
104 expecteds.remove(id);
107 assertEquals(qString + " missing some matches ", 0, expecteds.size());
112 public void setUp() throws Exception {
115 IndexWriter w = new IndexWriter(rd, newIndexWriterConfig(TEST_VERSION_CURRENT, analyzer));
116 for (int i = 0; i < docsContent.length; i++) {
117 Document doc = new Document();
118 doc.add(newField("name", docsContent[i].name, Field.Store.YES,
119 Field.Index.ANALYZED));
120 doc.add(newField("id", docsContent[i].id, Field.Store.YES,
121 Field.Index.ANALYZED));
125 searcher = new IndexSearcher(rd, true);
129 public void tearDown() throws Exception {
135 static class DocData {
140 public DocData(String name, String id) {