hadoop InputSplit 源码

  • 2022-10-20
  • 浏览 (107)

haddop InputSplit 代码

文件路径:/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/InputSplit.java

/**
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package org.apache.hadoop.mapreduce;

import java.io.IOException;

import org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.classification.InterfaceStability.Evolving;
import org.apache.hadoop.mapred.SplitLocationInfo;
import org.apache.hadoop.mapreduce.InputFormat;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.RecordReader;

/**
 * <code>InputSplit</code> represents the data to be processed by an 
 * individual {@link Mapper}. 
 *
 * <p>Typically, it presents a byte-oriented view on the input and is the 
 * responsibility of {@link RecordReader} of the job to process this and present
 * a record-oriented view.
 * 
 * @see InputFormat
 * @see RecordReader
 */
@InterfaceAudience.Public
@InterfaceStability.Stable
public abstract class InputSplit {
  /**
   * Get the size of the split, so that the input splits can be sorted by size.
   * @return the number of bytes in the split
   * @throws IOException
   * @throws InterruptedException
   */
  public abstract long getLength() throws IOException, InterruptedException;

  /**
   * Get the list of nodes by name where the data for the split would be local.
   * The locations do not need to be serialized.
   * 
   * @return a new array of the node nodes.
   * @throws IOException
   * @throws InterruptedException
   */
  public abstract 
    String[] getLocations() throws IOException, InterruptedException;
  
  /**
   * Gets info about which nodes the input split is stored on and how it is
   * stored at each location.
   * 
   * @return list of <code>SplitLocationInfo</code>s describing how the split
   *    data is stored at each location. A null value indicates that all the
   *    locations have the data stored on disk.
   * @throws IOException
   */
  @Evolving
  public SplitLocationInfo[] getLocationInfo() throws IOException {
    return null;
  }
}

相关信息

hadoop 源码目录

相关文章

hadoop Cluster 源码

hadoop ClusterMetrics 源码

hadoop ContextFactory 源码

hadoop Counter 源码

hadoop CounterGroup 源码

hadoop Counters 源码

hadoop CryptoUtils 源码

hadoop CustomJobEndNotifier 源码

hadoop FileSystemCounter 源码

hadoop ID 源码

0  赞