001/**
002 * Licensed to the Apache Software Foundation (ASF) under one
003 * or more contributor license agreements.  See the NOTICE file
004 * distributed with this work for additional information
005 * regarding copyright ownership.  The ASF licenses this file
006 * to you under the Apache License, Version 2.0 (the
007 * "License"); you may not use this file except in compliance
008 * with the License.  You may obtain a copy of the License at
009 *
010 *     http://www.apache.org/licenses/LICENSE-2.0
011 *
012 * Unless required by applicable law or agreed to in writing, software
013 * distributed under the License is distributed on an "AS IS" BASIS,
014 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
015 * See the License for the specific language governing permissions and
016 * limitations under the License.
017 */
018
019package org.apache.hadoop.mapreduce;
020
021import java.io.IOException;
022
023import org.apache.hadoop.classification.InterfaceAudience;
024import org.apache.hadoop.classification.InterfaceStability;
025import org.apache.hadoop.fs.FileSystem;
026
027/** 
028 * <code>OutputFormat</code> describes the output-specification for a 
029 * Map-Reduce job.
030 *
031 * <p>The Map-Reduce framework relies on the <code>OutputFormat</code> of the
032 * job to:<p>
033 * <ol>
034 *   <li>
035 *   Validate the output-specification of the job. For e.g. check that the 
036 *   output directory doesn't already exist. 
037 *   <li>
038 *   Provide the {@link RecordWriter} implementation to be used to write out
039 *   the output files of the job. Output files are stored in a 
040 *   {@link FileSystem}.
041 *   </li>
042 * </ol>
043 * 
044 * @see RecordWriter
045 */
046@InterfaceAudience.Public
047@InterfaceStability.Stable
048public abstract class OutputFormat<K, V> {
049
050  /** 
051   * Get the {@link RecordWriter} for the given task.
052   *
053   * @param context the information about the current task.
054   * @return a {@link RecordWriter} to write the output for the job.
055   * @throws IOException
056   */
057  public abstract RecordWriter<K, V> 
058    getRecordWriter(TaskAttemptContext context
059                    ) throws IOException, InterruptedException;
060
061  /** 
062   * Check for validity of the output-specification for the job.
063   *  
064   * <p>This is to validate the output specification for the job when it is
065   * a job is submitted.  Typically checks that it does not already exist,
066   * throwing an exception when it already exists, so that output is not
067   * overwritten.</p>
068   *
069   * @param context information about the job
070   * @throws IOException when output should not be attempted
071   */
072  public abstract void checkOutputSpecs(JobContext context
073                                        ) throws IOException, 
074                                                 InterruptedException;
075
076  /**
077   * Get the output committer for this output format. This is responsible
078   * for ensuring the output is committed correctly.
079   * @param context the task context
080   * @return an output committer
081   * @throws IOException
082   * @throws InterruptedException
083   */
084  public abstract 
085  OutputCommitter getOutputCommitter(TaskAttemptContext context
086                                     ) throws IOException, InterruptedException;
087}
088