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.Closeable;
022    import java.io.IOException;
023    
024    import org.apache.hadoop.classification.InterfaceAudience;
025    import org.apache.hadoop.classification.InterfaceStability;
026    
027    /**
028     * The record reader breaks the data into key/value pairs for input to the
029     * {@link Mapper}.
030     * @param <KEYIN>
031     * @param <VALUEIN>
032     */
033    @InterfaceAudience.Public
034    @InterfaceStability.Stable
035    public abstract class RecordReader<KEYIN, VALUEIN> implements Closeable {
036    
037      /**
038       * Called once at initialization.
039       * @param split the split that defines the range of records to read
040       * @param context the information about the task
041       * @throws IOException
042       * @throws InterruptedException
043       */
044      public abstract void initialize(InputSplit split,
045                                      TaskAttemptContext context
046                                      ) throws IOException, InterruptedException;
047    
048      /**
049       * Read the next key, value pair.
050       * @return true if a key/value pair was read
051       * @throws IOException
052       * @throws InterruptedException
053       */
054      public abstract 
055      boolean nextKeyValue() throws IOException, InterruptedException;
056    
057      /**
058       * Get the current key
059       * @return the current key or null if there is no current key
060       * @throws IOException
061       * @throws InterruptedException
062       */
063      public abstract
064      KEYIN getCurrentKey() throws IOException, InterruptedException;
065      
066      /**
067       * Get the current value.
068       * @return the object that was read
069       * @throws IOException
070       * @throws InterruptedException
071       */
072      public abstract 
073      VALUEIN getCurrentValue() throws IOException, InterruptedException;
074      
075      /**
076       * The current progress of the record reader through its data.
077       * @return a number between 0.0 and 1.0 that is the fraction of the data read
078       * @throws IOException
079       * @throws InterruptedException
080       */
081      public abstract float getProgress() throws IOException, InterruptedException;
082      
083      /**
084       * Close the record reader.
085       */
086      public abstract void close() throws IOException;
087    }