blob: bc14cb8a690d684f009ca68bfd6133839ccb7468 [file] [log] [blame]
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.lucene.index;
import java.io.IOException;
import java.util.concurrent.atomic.AtomicInteger;
import org.apache.lucene.analysis.*;
import org.apache.lucene.analysis.tokenattributes.PayloadAttribute;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.IOContext;
import org.apache.lucene.store.IndexInput;
import org.apache.lucene.store.MockDirectoryWrapper;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.BytesRef;
import org.apache.lucene.util.LuceneTestCase;
import org.apache.lucene.util.TestUtil;
import org.junit.Before;
/**
* This testcase tests whether multi-level skipping is being used
* to reduce I/O while skipping through posting lists.
*
* Skipping in general is already covered by several other
* testcases.
*
*/
public class TestMultiLevelSkipList extends LuceneTestCase {
class CountingRAMDirectory extends MockDirectoryWrapper {
public CountingRAMDirectory(Directory delegate) {
super(random(), delegate);
}
@Override
public IndexInput openInput(String fileName, IOContext context) throws IOException {
IndexInput in = super.openInput(fileName, context);
if (fileName.endsWith(".frq"))
in = new CountingStream(in);
return in;
}
}
@Override
@Before
public void setUp() throws Exception {
super.setUp();
counter = 0;
}
public void testSimpleSkip() throws IOException {
Directory dir = new CountingRAMDirectory(new RAMDirectory());
IndexWriter writer = new IndexWriter(dir, newIndexWriterConfig(new PayloadAnalyzer())
.setCodec(TestUtil.alwaysPostingsFormat(TestUtil.getDefaultPostingsFormat()))
.setMergePolicy(newLogMergePolicy()));
Term term = new Term("test", "a");
for (int i = 0; i < 5000; i++) {
Document d1 = new Document();
d1.add(newTextField(term.field(), term.text(), Field.Store.NO));
writer.addDocument(d1);
}
writer.commit();
writer.forceMerge(1);
writer.close();
LeafReader reader = getOnlyLeafReader(DirectoryReader.open(dir));
for (int i = 0; i < 2; i++) {
counter = 0;
PostingsEnum tp = reader.postings(term, PostingsEnum.ALL);
checkSkipTo(tp, 14, 185); // no skips
checkSkipTo(tp, 17, 190); // one skip on level 0
checkSkipTo(tp, 287, 200); // one skip on level 1, two on level 0
// this test would fail if we had only one skip level,
// because than more bytes would be read from the freqStream
checkSkipTo(tp, 4800, 250);// one skip on level 2
}
}
public void checkSkipTo(PostingsEnum tp, int target, int maxCounter) throws IOException {
tp.advance(target);
if (maxCounter < counter) {
fail("Too many bytes read: " + counter + " vs " + maxCounter);
}
assertEquals("Wrong document " + tp.docID() + " after skipTo target " + target, target, tp.docID());
assertEquals("Frequency is not 1: " + tp.freq(), 1,tp.freq());
tp.nextPosition();
BytesRef b = tp.getPayload();
assertEquals(1, b.length);
assertEquals("Wrong payload for the target " + target + ": " + b.bytes[b.offset], (byte) target, b.bytes[b.offset]);
}
private static class PayloadAnalyzer extends Analyzer {
private final AtomicInteger payloadCount = new AtomicInteger(-1);
@Override
public TokenStreamComponents createComponents(String fieldName) {
Tokenizer tokenizer = new MockTokenizer(MockTokenizer.WHITESPACE, true);
return new TokenStreamComponents(tokenizer, new PayloadFilter(payloadCount, tokenizer));
}
}
private static class PayloadFilter extends TokenFilter {
PayloadAttribute payloadAtt;
private AtomicInteger payloadCount;
protected PayloadFilter(AtomicInteger payloadCount , TokenStream input) {
super(input);
this.payloadCount = payloadCount;
payloadAtt = addAttribute(PayloadAttribute.class);
}
@Override
public boolean incrementToken() throws IOException {
boolean hasNext = input.incrementToken();
if (hasNext) {
payloadAtt.setPayload(new BytesRef(new byte[] { (byte) payloadCount.incrementAndGet() }));
}
return hasNext;
}
}
private int counter = 0;
// Simply extends IndexInput in a way that we are able to count the number
// of bytes read
class CountingStream extends IndexInput {
private IndexInput input;
CountingStream(IndexInput input) {
super("CountingStream(" + input + ")");
this.input = input;
}
@Override
public byte readByte() throws IOException {
TestMultiLevelSkipList.this.counter++;
return this.input.readByte();
}
@Override
public void readBytes(byte[] b, int offset, int len) throws IOException {
TestMultiLevelSkipList.this.counter += len;
this.input.readBytes(b, offset, len);
}
@Override
public void close() throws IOException {
this.input.close();
}
@Override
public long getFilePointer() {
return this.input.getFilePointer();
}
@Override
public void seek(long pos) throws IOException {
this.input.seek(pos);
}
@Override
public long length() {
return this.input.length();
}
@Override
public CountingStream clone() {
return new CountingStream(this.input.clone());
}
@Override
public IndexInput slice(String sliceDescription, long offset, long length) throws IOException {
return new CountingStream(this.input.slice(sliceDescription, offset, length));
}
}
}