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 java.io.IOException;
22
import org.apache.lucene.analysis.MockAnalyzer;
23
import org.apache.lucene.analysis.TokenStream;
24
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
25
import org.apache.lucene.document.Document;
26
import org.apache.lucene.document.Field;
27
import org.apache.lucene.index.FieldInfo.IndexOptions;
28
import org.apache.lucene.store.MockDirectoryWrapper;
29
import org.apache.lucene.util.LuceneTestCase;
30
import org.apache.lucene.util._TestUtil;
31
import org.junit.Ignore;
34
* Test indexes ~82M docs with 26 terms each, so you get > Integer.MAX_VALUE terms/docs pairs
35
* @lucene.experimental
37
public class Test2BPostings extends LuceneTestCase {
40
public void test() throws Exception {
42
MockDirectoryWrapper dir = newFSDirectory(_TestUtil.getTempDir("2BPostings"));
43
dir.setThrottling(MockDirectoryWrapper.Throttling.NEVER);
44
dir.setCheckIndexOnClose(false); // don't double-checkindex
46
IndexWriter w = new IndexWriter(dir,
47
new IndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(random))
48
.setMaxBufferedDocs(IndexWriterConfig.DISABLE_AUTO_FLUSH)
49
.setRAMBufferSizeMB(256.0)
50
.setMergeScheduler(new ConcurrentMergeScheduler())
51
.setMergePolicy(newLogMergePolicy(false, 10))
52
.setOpenMode(IndexWriterConfig.OpenMode.CREATE));
54
MergePolicy mp = w.getConfig().getMergePolicy();
55
if (mp instanceof LogByteSizeMergePolicy) {
57
((LogByteSizeMergePolicy) mp).setMaxMergeMB(1024*1024*1024);
60
Document doc = new Document();
61
Field field = new Field("field", new MyTokenStream());
62
field.setIndexOptions(IndexOptions.DOCS_ONLY);
63
field.setOmitNorms(true);
66
final int numDocs = (Integer.MAX_VALUE / 26) + 1;
67
for (int i = 0; i < numDocs; i++) {
69
if (VERBOSE && i % 100000 == 0) {
70
System.out.println(i + " of " + numDocs + "...");
75
CheckIndex ci = new CheckIndex(dir);
77
ci.setInfoStream(System.out);
83
public static final class MyTokenStream extends TokenStream {
84
private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
85
private final char buffer[];
88
public MyTokenStream() {
90
buffer = termAtt.buffer();
94
public boolean incrementToken() throws IOException {
96
buffer[0] = (char) index++;
103
public void reset() throws IOException {