mapreduce/src/contrib/streaming/src/test/org/apache/hadoop/streaming/TestStreamAggregate.java

/**
 * 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.streaming;

import junit.framework.TestCase;
import java.io.*;

import org.apache.hadoop.mapreduce.JobContext;

/**
 * This class tests hadoopStreaming in MapReduce local mode.
 * It uses Hadoop Aggregate to count the numbers of word occurrences 
 * in the input.
 */
public class TestStreamAggregate extends TestCase
{
  protected File INPUT_FILE = new File("stream_aggregate_input.txt");
  protected File OUTPUT_DIR = new File("stream_aggregate_out");
  protected String input = "roses are red\nviolets are blue\nbunnies are pink\n";
  // map parses input lines and generates count entries for each word.
  protected String map = StreamUtil.makeJavaCommand(StreamAggregate.class, new String[]{".", "\\n"});
  // Use the aggregate combine, reducei to aggregate the counts
  protected String outputExpect = "are\t3\nblue\t1\nbunnies\t1\npink\t1\nred\t1\nroses\t1\nviolets\t1\n";

  private StreamJob job;

  public TestStreamAggregate() throws IOException
  {
    UtilTest utilTest = new UtilTest(getClass().getName());
    utilTest.checkUserDir();
    utilTest.redirectIfAntJunit();
  }

  protected void createInput() throws IOException
  {
    DataOutputStream out = new DataOutputStream(
                                                new FileOutputStream(INPUT_FILE.getAbsoluteFile()));
    out.write(input.getBytes("UTF-8"));
    out.close();
  }

  protected String[] genArgs() {
    return new String[] {
      "-input", INPUT_FILE.getAbsolutePath(),
      "-output", OUTPUT_DIR.getAbsolutePath(),
      "-mapper", map,
      "-reducer", "aggregate",
      //"-verbose",
      //"-jobconf", "stream.debug=set"
      "-jobconf", JobContext.PRESERVE_FAILED_TASK_FILES + "=true",
      "-jobconf", "stream.tmpdir="+System.getProperty("test.build.data","/tmp")
    };
  }
  
  public void testCommandLine()
  {
    try {
      try {
        OUTPUT_DIR.getAbsoluteFile().delete();
      } catch (Exception e) {
      }

      createInput();
      boolean mayExit = false;

      // During tests, the default Configuration will use a local mapred
      // So don't specify -config or -cluster
      job = new StreamJob(genArgs(), mayExit);      
      job.go();
      File outFile = new File(OUTPUT_DIR, "part-00000").getAbsoluteFile();
      String output = StreamUtil.slurp(outFile);
      outFile.delete();
      System.err.println("outEx1=" + outputExpect);
      System.err.println("  out1=" + output);
      assertEquals(outputExpect, output);
    } catch(Exception e) {
      failTrace(e);
    } finally {
      File outFileCRC = new File(OUTPUT_DIR, ".part-00000.crc").getAbsoluteFile();
      INPUT_FILE.delete();
      outFileCRC.delete();
      OUTPUT_DIR.getAbsoluteFile().delete();
    }
  }

  private void failTrace(Exception e)
  {
    StringWriter sw = new StringWriter();
    e.printStackTrace(new PrintWriter(sw));
    fail(sw.toString());
  }

  public static void main(String[]args) throws Exception
  {
    new TestStreaming().testCommandLine();
  }

}