Package org.apache.hadoop.zebra.pig

Source Code of org.apache.hadoop.zebra.pig.TestTableLoader

/**
* 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.pig;

import java.io.File;
import java.io.IOException;
import java.util.Iterator;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
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.types.Schema;
import org.apache.hadoop.zebra.types.TypesUtils;
import org.apache.pig.ExecType;
import org.apache.pig.PigServer;
import org.apache.pig.backend.executionengine.ExecException;
import org.apache.pig.data.Tuple;
import org.apache.pig.test.MiniCluster;
import org.junit.Test;
import org.junit.BeforeClass;
import org.junit.AfterClass;
import junit.framework.Assert;

/**
* Note:
*
* Make sure you add the build/pig-0.1.0-dev-core.jar to the Classpath of the
* app/debug configuration, when run this from inside the Eclipse.
*
*/
public class TestTableLoader {
  static protected ExecType execType = ExecType.MAPREDUCE;
  static private MiniCluster cluster;
  static protected PigServer pigServer;
  static private Path pathTable;

  @BeforeClass
  public static void setUp() throws Exception {
    if (System.getProperty("hadoop.log.dir") == null) {
      String base = new File(".").getPath(); // getAbsolutePath();
      System
          .setProperty("hadoop.log.dir", new Path(base).toString() + "./logs");
    }

    if (execType == ExecType.MAPREDUCE) {
      cluster = MiniCluster.buildCluster();
      pigServer = new PigServer(ExecType.MAPREDUCE, cluster.getProperties());
    } else {
      pigServer = new PigServer(ExecType.LOCAL);
    }

    Configuration conf = new Configuration();
    FileSystem fs = cluster.getFileSystem();
    Path pathWorking = fs.getWorkingDirectory();
    // pathTable = new Path(pathWorking, this.getClass().getSimpleName());
    pathTable = new Path(pathWorking, "TestTableLoader");
    System.out.println("pathTable =" + pathTable);

    BasicTable.Writer writer = new BasicTable.Writer(pathTable,
        "a:string,b,c:string,d,e,f,g", "[a,b,c];[d,e,f,g]", false, conf);
    Schema schema = writer.getSchema();
    Tuple tuple = TypesUtils.createTuple(schema);

    final int numsBatch = 10;
    final int numsInserters = 2;
    TableInserter[] inserters = new TableInserter[numsInserters];
    for (int i = 0; i < numsInserters; i++) {
      inserters[i] = writer.getInserter("ins" + i, false);
    }

    for (int b = 0; b < numsBatch; b++) {
      for (int i = 0; i < numsInserters; i++) {
        TypesUtils.resetTuple(tuple);
        for (int k = 0; k < tuple.size(); ++k) {
          try {
            tuple.set(k, b + "_" + i + "" + k);
          } catch (ExecException e) {
            e.printStackTrace();
          }
        }
        inserters[i].insert(new BytesWritable(("key" + i).getBytes()), tuple);
      }
    }
    for (int i = 0; i < numsInserters; i++) {
      inserters[i].close();
    }
  }

  @AfterClass
  static public void tearDown() throws Exception {
    pigServer.shutdown();
  }

  @Test
  public void testReader1() throws ExecException, IOException {
    String query = "records = LOAD '" + pathTable.toString()
        + "' USING org.apache.hadoop.zebra.pig.TableLoader('c, a');";
    System.out.println(query);
    pigServer.registerQuery(query);
    Iterator<Tuple> it = pigServer.openIterator("records");
    while (it.hasNext()) {
      Tuple cur = it.next();
      System.out.println(cur);
    }
  }

  @Test
  public void testReader2() throws ExecException, IOException {
    String query = "records = LOAD '" + pathTable.toString()
        + "' USING org.apache.hadoop.zebra.pig.TableLoader('a, aa, b, c');";
    System.out.println(query);
    pigServer.registerQuery(query);
    Iterator<Tuple> it = pigServer.openIterator("records");
    int cnt = 0;
    while (it.hasNext()) {
      Tuple cur = it.next();
      cnt++;
      if (cnt == 1) {
        Assert.assertEquals(4, cur.size());
        Assert.assertEquals("0_00", cur.get(0));
        Assert.assertEquals(null, cur.get(1));
        Assert.assertEquals("0_01", cur.get(2));
        Assert.assertEquals("0_02", cur.get(3));
      }
      System.out.println(cur);
    }
  }
}
TOP

Related Classes of org.apache.hadoop.zebra.pig.TestTableLoader

TOP
Copyright © 2018 www.massapi.com. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.