org.apache.hadoop.mapreduce.OutputFormat Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of hadoop-client-api
Apache Hadoop Client
There is a newer version: 3.4.1
/**
 * 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 org.apache.hadoop.shaded.com.liance
 * with the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org.apache.hadoop.shaded.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.shaded.org.apache.hadoop.mapreduce;

import java.org.apache.hadoop.shaded.io.IOException;

import org.apache.hadoop.shaded.org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.shaded.org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.shaded.org.apache.hadoop.fs.FileSystem;

/** 
 * OutputFormat describes the output-specification for a 
 * Map-Reduce job.
 *
 * The Map-Reduce framework relies on the OutputFormat of the
 * job to:

 * 

 *   
 *   Validate the output-specification of the job. For e.g. check that the 
 *   output directory doesn't already exist. 
 *   

 *   Provide the {@link RecordWriter} implementation to be used to write out
 *   the output files of the job. Output files are stored in a 
 *   {@link FileSystem}.
 *   
 * 
 * 
 * @see RecordWriter
 */
@InterfaceAudience.Public
@InterfaceStability.Stable
public abstract class OutputFormat {

  /** 
   * Get the {@link RecordWriter} for the given task.
   *
   * @param context the information about the current task.
   * @return a {@link RecordWriter} to write the output for the job.
   * @throws IOException
   */
  public abstract RecordWriter 
    getRecordWriter(TaskAttemptContext context
                    ) throws IOException, InterruptedException;

  /** 
   * Check for validity of the output-specification for the job.
   *  
   * This is to validate the output specification for the job when it is
   * a job is submitted.  Typically checks that it does not already exist,
   * throwing an exception when it already exists, so that output is not
   * overwritten.
   *
   * Implementations which write to filesystems which support delegation
   * tokens usually collect the tokens for the destination path(s)
   * and attach them to the job context's JobConf.
   * @param context information about the job
   * @throws IOException when output should not be attempted
   */
  public abstract void checkOutputSpecs(JobContext context
                                        ) throws IOException, 
                                                 InterruptedException;

  /**
   * Get the output org.apache.hadoop.shaded.com.itter for this output format. This is responsible
   * for ensuring the output is org.apache.hadoop.shaded.com.itted correctly.
   * @param context the task context
   * @return an output org.apache.hadoop.shaded.com.itter
   * @throws IOException
   * @throws InterruptedException
   */
  public abstract 
  OutputCommitter getOutputCommitter(TaskAttemptContext context
                                     ) throws IOException, InterruptedException;
}