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.mapred;
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.io.Writable;
026    
027    /**
028     * <code>InputSplit</code> represents the data to be processed by an 
029     * individual {@link Mapper}. 
030     *
031     * <p>Typically, it presents a byte-oriented view on the input and is the 
032     * responsibility of {@link RecordReader} of the job to process this and present
033     * a record-oriented view.
034     * 
035     * @see InputFormat
036     * @see RecordReader
037     */
038    @InterfaceAudience.Public
039    @InterfaceStability.Stable
040    public interface InputSplit extends Writable {
041    
042      /**
043       * Get the total number of bytes in the data of the <code>InputSplit</code>.
044       * 
045       * @return the number of bytes in the input split.
046       * @throws IOException
047       */
048      long getLength() throws IOException;
049      
050      /**
051       * Get the list of hostnames where the input split is located.
052       * 
053       * @return list of hostnames where data of the <code>InputSplit</code> is
054       *         located as an array of <code>String</code>s.
055       * @throws IOException
056       */
057      String[] getLocations() throws IOException;
058    }