/**
* 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.zebra.io;
import java.io.IOException;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import junit.framework.Assert;
import junit.framework.TestCase;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.LocalFileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.fs.RawLocalFileSystem;
import org.apache.hadoop.io.BytesWritable;
import org.apache.hadoop.zebra.io.BasicTable;
import org.apache.hadoop.zebra.io.TableInserter;
import org.apache.hadoop.zebra.io.TableScanner;
import org.apache.hadoop.zebra.io.BasicTable.Reader.RangeSplit;
import org.apache.hadoop.zebra.types.ParseException;
import org.apache.hadoop.zebra.types.Schema;
import org.apache.hadoop.zebra.types.TypesUtils;
import org.apache.pig.data.DataBag;
import org.apache.pig.data.DataByteArray;
import org.apache.pig.data.Tuple;
import org.junit.AfterClass;
import org.junit.BeforeClass;
import org.junit.Test;
/**
*
* Test projections on complicated column types.
*
*/
public class TestBasicTableSplits {
final static String STR_SCHEMA = "f1:bool, r:record(f11:int, f12:long), m:map(string), c:collection(f13:double, f14:float, f15:bytes)";
// TODO: try map hash split later
final static String STR_STORAGE = "[r.f12, f1]; [m]";
private static Configuration conf;
private static Path path;
private static FileSystem fs;
@BeforeClass
public static void setUpOnce() throws IOException {
conf = new Configuration();
conf.setInt("table.output.tfile.minBlock.size", 64 * 1024);
conf.setInt("table.input.split.minSize", 64 * 1024);
conf.set("table.output.tfile.compression", "none");
RawLocalFileSystem rawLFS = new RawLocalFileSystem();
fs = new LocalFileSystem(rawLFS);
path = new Path(fs.getWorkingDirectory(), "TestBasicTableSplits");
fs = path.getFileSystem(conf);
// drop any previous tables
BasicTable.drop(path, conf);
BasicTable.Writer writer = new BasicTable.Writer(path, STR_SCHEMA,
STR_STORAGE, false, conf);
writer.finish();
Schema schema = writer.getSchema();
Tuple tuple = TypesUtils.createTuple(schema);
BasicTable.Writer writer1 = new BasicTable.Writer(path, conf);
int part = 0;
TableInserter inserter = writer1.getInserter("part" + part, true);
TypesUtils.resetTuple(tuple);
tuple.set(0, true);
Tuple tupRecord;
try {
tupRecord = TypesUtils.createTuple(schema.getColumnSchema("r")
.getSchema());
} catch (ParseException e) {
e.printStackTrace();
throw new IOException(e);
}
// row 1
tupRecord.set(0, 1);
tupRecord.set(1, 1001L);
tuple.set(1, tupRecord);
Map<String, String> map = new HashMap<String, String>();
map.put("a", "x");
map.put("b", "y");
map.put("c", "z");
tuple.set(2, map);
DataBag bagColl = TypesUtils.createBag();
Schema schColl = schema.getColumn(3).getSchema();
Tuple tupColl1 = TypesUtils.createTuple(schColl);
Tuple tupColl2 = TypesUtils.createTuple(schColl);
byte[] abs1 = new byte[3];
byte[] abs2 = new byte[4];
tupColl1.set(0, 3.1415926);
tupColl1.set(1, 1.6);
abs1[0] = 11;
abs1[1] = 12;
abs1[2] = 13;
tupColl1.set(2, new DataByteArray(abs1));
bagColl.add(tupColl1);
tupColl2.set(0, 123.456789);
tupColl2.set(1, 100);
abs2[0] = 21;
abs2[1] = 22;
abs2[2] = 23;
abs2[3] = 24;
tupColl2.set(2, new DataByteArray(abs2));
bagColl.add(tupColl2);
tuple.set(3, bagColl);
int row = 0;
inserter.insert(new BytesWritable(String.format("k%d%d", part + 1, row + 1)
.getBytes()), tuple);
// row 2
row++;
TypesUtils.resetTuple(tuple);
TypesUtils.resetTuple(tupRecord);
map.clear();
tuple.set(0, false);
tupRecord.set(0, 2);
tupRecord.set(1, 1002L);
tuple.set(1, tupRecord);
map.put("boy", "girl");
map.put("adam", "amy");
map.put("bob", "becky");
map.put("carl", "cathy");
tuple.set(2, map);
bagColl.clear();
TypesUtils.resetTuple(tupColl1);
TypesUtils.resetTuple(tupColl2);
tupColl1.set(0, 7654.321);
tupColl1.set(1, 0.0001);
abs1[0] = 31;
abs1[1] = 32;
abs1[2] = 33;
tupColl1.set(2, new DataByteArray(abs1));
bagColl.add(tupColl1);
tupColl2.set(0, 0.123456789);
tupColl2.set(1, 0.3333);
abs2[0] = 41;
abs2[1] = 42;
abs2[2] = 43;
abs2[3] = 44;
tupColl2.set(2, new DataByteArray(abs2));
bagColl.add(tupColl2);
tuple.set(3, bagColl);
inserter.insert(new BytesWritable(String.format("k%d%d", part + 1, row + 1)
.getBytes()), tuple);
inserter.close();
writer1.finish();
writer.close();
}
@AfterClass
public static void tearDownOnce() throws IOException {
}
@Test
public void test1() throws IOException, ParseException {
String projection = new String("r.f12, f1");
BasicTable.Reader reader = new BasicTable.Reader(path, conf);
reader.setProjection(projection);
// long totalBytes = reader.getStatus().getSize();
List<RangeSplit> splits = reader.rangeSplit(1);
reader.close();
reader = new BasicTable.Reader(path, conf);
reader.setProjection(projection);
TableScanner scanner = reader.getScanner(splits.get(0), true);
BytesWritable key = new BytesWritable();
Tuple value = TypesUtils.createTuple(scanner.getSchema());
scanner.getKey(key);
Assert.assertEquals(key, new BytesWritable("k11".getBytes()));
scanner.getValue(value);
Assert.assertEquals(1001L, value.get(0));
Assert.assertEquals(true, value.get(1));
scanner.advance();
scanner.getKey(key);
Assert.assertEquals(key, new BytesWritable("k12".getBytes()));
scanner.getValue(value);
Assert.assertEquals(1002L, value.get(0));
Assert.assertEquals(false, value.get(1));
reader.close();
}
@Test
public void testStitch() throws IOException, ParseException {
String projection = new String("f1, r");
BasicTable.Reader reader = new BasicTable.Reader(path, conf);
reader.setProjection(projection);
// long totalBytes = reader.getStatus().getSize();
List<RangeSplit> splits = reader.rangeSplit(1);
reader.close();
reader = new BasicTable.Reader(path, conf);
reader.setProjection(projection);
TableScanner scanner = reader.getScanner(splits.get(0), true);
BytesWritable key = new BytesWritable();
Tuple value = TypesUtils.createTuple(scanner.getSchema());
scanner.getKey(key);
Assert.assertEquals(key, new BytesWritable("k11".getBytes()));
scanner.getValue(value);
Tuple recordTuple = (Tuple) value.get(1);
Assert.assertEquals(1, recordTuple.get(0));
Assert.assertEquals(1001L, recordTuple.get(1));
Assert.assertEquals(true, value.get(0));
reader.close();
}
}