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    
019    package org.apache.hadoop.mapreduce;
020    
021    import java.io.IOException;
022    
023    import org.apache.hadoop.classification.InterfaceAudience;
024    import org.apache.hadoop.classification.InterfaceStability;
025    import org.apache.hadoop.mapreduce.InputFormat;
026    import org.apache.hadoop.mapreduce.Mapper;
027    import org.apache.hadoop.mapreduce.RecordReader;
028    
029    /**
030     * <code>InputSplit</code> represents the data to be processed by an 
031     * individual {@link Mapper}. 
032     *
033     * <p>Typically, it presents a byte-oriented view on the input and is the 
034     * responsibility of {@link RecordReader} of the job to process this and present
035     * a record-oriented view.
036     * 
037     * @see InputFormat
038     * @see RecordReader
039     */
040    @InterfaceAudience.Public
041    @InterfaceStability.Stable
042    public abstract class InputSplit {
043      /**
044       * Get the size of the split, so that the input splits can be sorted by size.
045       * @return the number of bytes in the split
046       * @throws IOException
047       * @throws InterruptedException
048       */
049      public abstract long getLength() throws IOException, InterruptedException;
050    
051      /**
052       * Get the list of nodes by name where the data for the split would be local.
053       * The locations do not need to be serialized.
054       * @return a new array of the node nodes.
055       * @throws IOException
056       * @throws InterruptedException
057       */
058      public abstract 
059        String[] getLocations() throws IOException, InterruptedException;
060    }