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.mapred;
020
021import java.io.IOException;
022
023import org.apache.hadoop.classification.InterfaceAudience;
024import org.apache.hadoop.classification.InterfaceStability;
025
026/**
027 * <code>RecordReader</code> reads &lt;key, value&gt; pairs from an 
028 * {@link InputSplit}.
029 *   
030 * <p><code>RecordReader</code>, typically, converts the byte-oriented view of 
031 * the input, provided by the <code>InputSplit</code>, and presents a 
032 * record-oriented view for the {@link Mapper} and {@link Reducer} tasks for
033 * processing. It thus assumes the responsibility of processing record 
034 * boundaries and presenting the tasks with keys and values.</p>
035 * 
036 * @see InputSplit
037 * @see InputFormat
038 */
039@InterfaceAudience.Public
040@InterfaceStability.Stable
041public interface RecordReader<K, V> {
042  /** 
043   * Reads the next key/value pair from the input for processing.
044   *
045   * @param key the key to read data into
046   * @param value the value to read data into
047   * @return true iff a key/value was read, false if at EOF
048   */      
049  boolean next(K key, V value) throws IOException;
050  
051  /**
052   * Create an object of the appropriate type to be used as a key.
053   * 
054   * @return a new key object.
055   */
056  K createKey();
057  
058  /**
059   * Create an object of the appropriate type to be used as a value.
060   * 
061   * @return a new value object.
062   */
063  V createValue();
064
065  /** 
066   * Returns the current position in the input.
067   * 
068   * @return the current position in the input.
069   * @throws IOException
070   */
071  long getPos() throws IOException;
072
073  /** 
074   * Close this {@link InputSplit} to future operations.
075   * 
076   * @throws IOException
077   */ 
078  public void close() throws IOException;
079
080  /**
081   * How much of the input has the {@link RecordReader} consumed i.e.
082   * has been processed by?
083   * 
084   * @return progress from <code>0.0</code> to <code>1.0</code>.
085   * @throws IOException
086   */
087  float getProgress() throws IOException;
088}