KickJava   Java API By Example, From Geeks To Geeks.

Java > Open Source Codes > org > apache > lucene > index > TestSegmentTermEnum


1 package org.apache.lucene.index;
2
3 import java.io.IOException JavaDoc;
4
5 import junit.framework.TestCase;
6
7 import org.apache.lucene.analysis.WhitespaceAnalyzer;
8 import org.apache.lucene.document.Document;
9 import org.apache.lucene.document.Field;
10 import org.apache.lucene.index.IndexReader;
11 import org.apache.lucene.index.IndexWriter;
12 import org.apache.lucene.index.Term;
13 import org.apache.lucene.index.TermEnum;
14 import org.apache.lucene.store.Directory;
15 import org.apache.lucene.store.RAMDirectory;
16
17 /**
18  * @author goller
19  */
20 public class TestSegmentTermEnum extends TestCase
21 {
22   Directory dir = new RAMDirectory();
23
24   public void testTermEnum()
25   {
26     IndexWriter writer = null;
27
28     try {
29       writer = new IndexWriter(dir, new WhitespaceAnalyzer(), true);
30
31       // add 100 documents with term : aaa
32 // add 100 documents with terms: aaa bbb
33 // Therefore, term 'aaa' has document frequency of 200 and term 'bbb' 100
34 for (int i = 0; i < 100; i++) {
35         addDoc(writer, "aaa");
36         addDoc(writer, "aaa bbb");
37       }
38
39       writer.close();
40     }
41     catch (IOException JavaDoc e) {
42       e.printStackTrace();
43     }
44
45     try {
46       // verify document frequency of terms in an unoptimized index
47 verifyDocFreq();
48
49       // merge segments by optimizing the index
50 writer = new IndexWriter(dir, new WhitespaceAnalyzer(), false);
51       writer.optimize();
52       writer.close();
53
54       // verify document frequency of terms in an optimized index
55 verifyDocFreq();
56     }
57     catch (IOException JavaDoc e2) {
58       e2.printStackTrace();
59     }
60   }
61
62   private void verifyDocFreq()
63       throws IOException JavaDoc
64   {
65       IndexReader reader = IndexReader.open(dir);
66       TermEnum termEnum = null;
67
68     // create enumeration of all terms
69 termEnum = reader.terms();
70     // go to the first term (aaa)
71 termEnum.next();
72     // assert that term is 'aaa'
73 assertEquals("aaa", termEnum.term().text());
74     assertEquals(200, termEnum.docFreq());
75     // go to the second term (bbb)
76 termEnum.next();
77     // assert that term is 'bbb'
78 assertEquals("bbb", termEnum.term().text());
79     assertEquals(100, termEnum.docFreq());
80
81     termEnum.close();
82
83
84     // create enumeration of terms after term 'aaa', including 'aaa'
85 termEnum = reader.terms(new Term("content", "aaa"));
86     // assert that term is 'aaa'
87 assertEquals("aaa", termEnum.term().text());
88     assertEquals(200, termEnum.docFreq());
89     // go to term 'bbb'
90 termEnum.next();
91     // assert that term is 'bbb'
92 assertEquals("bbb", termEnum.term().text());
93     assertEquals(100, termEnum.docFreq());
94
95     termEnum.close();
96   }
97
98   private void addDoc(IndexWriter writer, String JavaDoc value)
99   {
100     Document doc = new Document();
101     doc.add(Field.UnStored("content", value));
102
103     try {
104       writer.addDocument(doc);
105     }
106     catch (IOException JavaDoc e) {
107       e.printStackTrace();
108     }
109   }
110 }
111
Popular Tags