/**
* 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.hadoop.mapreduce.lib.input;
import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertNotNull;
import static org.junit.Assert.assertTrue;
import java.io.File;
import java.io.IOException;
import java.net.URL;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.TaskAttemptID;
import org.apache.hadoop.mapreduce.task.TaskAttemptContextImpl;
import org.junit.Test;
public class TestLineRecordReader {
private void testSplitRecords(String testFileName, long firstSplitLength)
throws IOException {
URL testFileUrl = getClass().getClassLoader().getResource(testFileName);
assertNotNull("Cannot find " + testFileName, testFileUrl);
File testFile = new File(testFileUrl.getFile());
long testFileSize = testFile.length();
Path testFilePath = new Path(testFile.getAbsolutePath());
Configuration conf = new Configuration();
conf.setInt(org.apache.hadoop.mapreduce.lib.input.
LineRecordReader.MAX_LINE_LENGTH, Integer.MAX_VALUE);
assertTrue("unexpected test data at " + testFile,
testFileSize > firstSplitLength);
TaskAttemptContext context = new TaskAttemptContextImpl(conf, new TaskAttemptID());
// read the data without splitting to count the records
FileSplit split = new FileSplit(testFilePath, 0, testFileSize,
(String[])null);
LineRecordReader reader = new LineRecordReader();
reader.initialize(split, context);
int numRecordsNoSplits = 0;
while (reader.nextKeyValue()) {
++numRecordsNoSplits;
}
reader.close();
// count the records in the first split
split = new FileSplit(testFilePath, 0, firstSplitLength, (String[])null);
reader = new LineRecordReader();
reader.initialize(split, context);
int numRecordsFirstSplit = 0;
while (reader.nextKeyValue()) {
++numRecordsFirstSplit;
}
reader.close();
// count the records in the second split
split = new FileSplit(testFilePath, firstSplitLength,
testFileSize - firstSplitLength, (String[])null);
reader = new LineRecordReader();
reader.initialize(split, context);
int numRecordsRemainingSplits = 0;
while (reader.nextKeyValue()) {
++numRecordsRemainingSplits;
}
reader.close();
assertEquals("Unexpected number of records in bzip2 compressed split",
numRecordsNoSplits, numRecordsFirstSplit + numRecordsRemainingSplits);
}
@Test
public void testBzip2SplitEndsAtCR() throws IOException {
// the test data contains a carriage-return at the end of the first
// split which ends at compressed offset 136498 and the next
// character is not a linefeed
testSplitRecords("blockEndingInCR.txt.bz2", 136498);
}
@Test
public void testBzip2SplitEndsAtCRThenLF() throws IOException {
// the test data contains a carriage-return at the end of the first
// split which ends at compressed offset 136498 and the next
// character is a linefeed
testSplitRecords("blockEndingInCRThenLF.txt.bz2", 136498);
}
}