1
package org.apache.lucene.index;
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 org.apache.lucene.analysis.Analyzer;
21
import org.apache.lucene.analysis.MockAnalyzer;
22
import org.apache.lucene.document.Document;
23
import org.apache.lucene.document.Field;
24
import org.apache.lucene.index.FieldInfo.IndexOptions;
25
import org.apache.lucene.store.Directory;
26
import org.apache.lucene.util.LuceneTestCase;
30
* @lucene.experimental
32
public class TestOmitPositions extends LuceneTestCase {
34
public void testBasic() throws Exception {
35
Directory dir = newDirectory();
36
RandomIndexWriter w = new RandomIndexWriter(random, dir);
37
Document doc = new Document();
38
Field f = newField("foo", "this is a test test", Field.Index.ANALYZED);
39
f.setIndexOptions(IndexOptions.DOCS_AND_FREQS);
41
for (int i = 0; i < 100; i++) {
45
IndexReader reader = w.getReader();
48
TermPositions tp = reader.termPositions(new Term("foo", "test"));
50
assertEquals(2, tp.freq());
51
assertEquals(0, tp.nextPosition());
52
assertEquals(0, tp.nextPosition());
55
TermDocs te = reader.termDocs(new Term("foo", "test"));
57
assertEquals(2, te.freq());
64
// Tests whether the DocumentWriter correctly enable the
65
// omitTermFreqAndPositions bit in the FieldInfo
66
public void testPositions() throws Exception {
67
Directory ram = newDirectory();
68
Analyzer analyzer = new MockAnalyzer(random);
69
IndexWriter writer = new IndexWriter(ram, newIndexWriterConfig( TEST_VERSION_CURRENT, analyzer));
70
Document d = new Document();
72
// f1,f2,f3: docs only
73
Field f1 = newField("f1", "This field has docs only", Field.Store.NO, Field.Index.ANALYZED);
74
f1.setIndexOptions(IndexOptions.DOCS_ONLY);
77
Field f2 = newField("f2", "This field has docs only", Field.Store.NO, Field.Index.ANALYZED);
78
f2.setIndexOptions(IndexOptions.DOCS_ONLY);
81
Field f3 = newField("f3", "This field has docs only", Field.Store.NO, Field.Index.ANALYZED);
82
f3.setIndexOptions(IndexOptions.DOCS_ONLY);
85
// f4,f5,f6 docs and freqs
86
Field f4 = newField("f4", "This field has docs and freqs", Field.Store.NO, Field.Index.ANALYZED);
87
f4.setIndexOptions(IndexOptions.DOCS_AND_FREQS);
90
Field f5 = newField("f5", "This field has docs and freqs", Field.Store.NO, Field.Index.ANALYZED);
91
f5.setIndexOptions(IndexOptions.DOCS_AND_FREQS);
94
Field f6 = newField("f6", "This field has docs and freqs", Field.Store.NO, Field.Index.ANALYZED);
95
f6.setIndexOptions(IndexOptions.DOCS_AND_FREQS);
98
// f7,f8,f9 docs/freqs/positions
99
Field f7 = newField("f7", "This field has docs and freqs and positions", Field.Store.NO, Field.Index.ANALYZED);
100
f7.setIndexOptions(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS);
103
Field f8 = newField("f8", "This field has docs and freqs and positions", Field.Store.NO, Field.Index.ANALYZED);
104
f8.setIndexOptions(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS);
107
Field f9 = newField("f9", "This field has docs and freqs and positions", Field.Store.NO, Field.Index.ANALYZED);
108
f9.setIndexOptions(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS);
111
writer.addDocument(d);
112
writer.forceMerge(1);
114
// now we add another document which has docs-only for f1, f4, f7, docs/freqs for f2, f5, f8,
115
// and docs/freqs/positions for f3, f6, f9
118
// f1,f4,f7: docs only
119
f1 = newField("f1", "This field has docs only", Field.Store.NO, Field.Index.ANALYZED);
120
f1.setIndexOptions(IndexOptions.DOCS_ONLY);
123
f4 = newField("f4", "This field has docs only", Field.Store.NO, Field.Index.ANALYZED);
124
f4.setIndexOptions(IndexOptions.DOCS_ONLY);
127
f7 = newField("f7", "This field has docs only", Field.Store.NO, Field.Index.ANALYZED);
128
f7.setIndexOptions(IndexOptions.DOCS_ONLY);
131
// f2, f5, f8: docs and freqs
132
f2 = newField("f2", "This field has docs and freqs", Field.Store.NO, Field.Index.ANALYZED);
133
f2.setIndexOptions(IndexOptions.DOCS_AND_FREQS);
136
f5 = newField("f5", "This field has docs and freqs", Field.Store.NO, Field.Index.ANALYZED);
137
f5.setIndexOptions(IndexOptions.DOCS_AND_FREQS);
140
f8 = newField("f8", "This field has docs and freqs", Field.Store.NO, Field.Index.ANALYZED);
141
f8.setIndexOptions(IndexOptions.DOCS_AND_FREQS);
144
// f3, f6, f9: docs and freqs and positions
145
f3 = newField("f3", "This field has docs and freqs and positions", Field.Store.NO, Field.Index.ANALYZED);
146
f3.setIndexOptions(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS);
149
f6 = newField("f6", "This field has docs and freqs and positions", Field.Store.NO, Field.Index.ANALYZED);
150
f6.setIndexOptions(IndexOptions.DOCS_AND_FREQS);
153
f9 = newField("f9", "This field has docs and freqs and positions", Field.Store.NO, Field.Index.ANALYZED);
154
f9.setIndexOptions(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS);
157
writer.addDocument(d);
160
writer.forceMerge(1);
164
SegmentReader reader = SegmentReader.getOnlySegmentReader(ram);
165
FieldInfos fi = reader.fieldInfos();
166
// docs + docs = docs
167
assertEquals(IndexOptions.DOCS_ONLY, fi.fieldInfo("f1").indexOptions);
168
// docs + docs/freqs = docs
169
assertEquals(IndexOptions.DOCS_ONLY, fi.fieldInfo("f2").indexOptions);
170
// docs + docs/freqs/pos = docs
171
assertEquals(IndexOptions.DOCS_ONLY, fi.fieldInfo("f3").indexOptions);
172
// docs/freqs + docs = docs
173
assertEquals(IndexOptions.DOCS_ONLY, fi.fieldInfo("f4").indexOptions);
174
// docs/freqs + docs/freqs = docs/freqs
175
assertEquals(IndexOptions.DOCS_AND_FREQS, fi.fieldInfo("f5").indexOptions);
176
// docs/freqs + docs/freqs/pos = docs/freqs
177
assertEquals(IndexOptions.DOCS_AND_FREQS, fi.fieldInfo("f6").indexOptions);
178
// docs/freqs/pos + docs = docs
179
assertEquals(IndexOptions.DOCS_ONLY, fi.fieldInfo("f7").indexOptions);
180
// docs/freqs/pos + docs/freqs = docs/freqs
181
assertEquals(IndexOptions.DOCS_AND_FREQS, fi.fieldInfo("f8").indexOptions);
182
// docs/freqs/pos + docs/freqs/pos = docs/freqs/pos
183
assertEquals(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS, fi.fieldInfo("f9").indexOptions);
189
private void assertNoPrx(Directory dir) throws Throwable {
190
final String[] files = dir.listAll();
191
for(int i=0;i<files.length;i++) {
192
assertFalse(files[i].endsWith(".prx"));
193
assertFalse(files[i].endsWith(".pos"));
197
// Verifies no *.prx exists when all fields omit term positions:
198
public void testNoPrxFile() throws Throwable {
199
Directory ram = newDirectory();
200
Analyzer analyzer = new MockAnalyzer(random);
201
IndexWriter writer = new IndexWriter(ram, newIndexWriterConfig(
202
TEST_VERSION_CURRENT, analyzer).setMaxBufferedDocs(3).setMergePolicy(newLogMergePolicy()));
203
LogMergePolicy lmp = (LogMergePolicy) writer.getConfig().getMergePolicy();
204
lmp.setMergeFactor(2);
205
lmp.setUseCompoundFile(false);
206
Document d = new Document();
208
Field f1 = newField("f1", "This field has term freqs", Field.Store.NO, Field.Index.ANALYZED);
209
f1.setIndexOptions(IndexOptions.DOCS_AND_FREQS);
212
for(int i=0;i<30;i++)
213
writer.addDocument(d);
219
// now add some documents with positions, and check there is no prox after optimization
221
f1 = newField("f1", "This field has positions", Field.Store.NO, Field.Index.ANALYZED);
224
for(int i=0;i<30;i++)
225
writer.addDocument(d);
228
writer.forceMerge(1);