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.classification.InterfaceStability.Evolving;
026    import org.apache.hadoop.mapred.SplitLocationInfo;
027    import org.apache.hadoop.mapreduce.InputFormat;
028    import org.apache.hadoop.mapreduce.Mapper;
029    import org.apache.hadoop.mapreduce.RecordReader;
030    
031    /**
032     * <code>InputSplit</code> represents the data to be processed by an 
033     * individual {@link Mapper}. 
034     *
035     * <p>Typically, it presents a byte-oriented view on the input and is the 
036     * responsibility of {@link RecordReader} of the job to process this and present
037     * a record-oriented view.
038     * 
039     * @see InputFormat
040     * @see RecordReader
041     */
042    @InterfaceAudience.Public
043    @InterfaceStability.Stable
044    public abstract class InputSplit {
045      /**
046       * Get the size of the split, so that the input splits can be sorted by size.
047       * @return the number of bytes in the split
048       * @throws IOException
049       * @throws InterruptedException
050       */
051      public abstract long getLength() throws IOException, InterruptedException;
052    
053      /**
054       * Get the list of nodes by name where the data for the split would be local.
055       * The locations do not need to be serialized.
056       * 
057       * @return a new array of the node nodes.
058       * @throws IOException
059       * @throws InterruptedException
060       */
061      public abstract 
062        String[] getLocations() throws IOException, InterruptedException;
063      
064      /**
065       * Gets info about which nodes the input split is stored on and how it is
066       * stored at each location.
067       * 
068       * @return list of <code>SplitLocationInfo</code>s describing how the split
069       *    data is stored at each location. A null value indicates that all the
070       *    locations have the data stored on disk.
071       * @throws IOException
072       */
073      @Evolving
074      public SplitLocationInfo[] getLocationInfo() throws IOException {
075        return null;
076      }
077    }