eclipse中开发Hadoop2.x的Map/Reduce项目

本文演示如何在Eclipse中开发一个Map/Reduce项目： 1、环境说明 Hadoop2.2.0 Eclipse?Juno SR2 Hadoop2.x-eclipse-plugin 插件的编译安装配置的过程参考：http://www.micmiu.com/bigdata/hadoop/hadoop2-x-eclipse-plugin-build-install/ 2、新建MR工程 依次

本文演示如何在Eclipse中开发一个Map/Reduce项目： 1、环境说明

• Hadoop2.2.0
• Eclipse?Juno SR2
• Hadoop2.x-eclipse-plugin 插件的编译安装配置的过程参考：http://www.micmiu.com/bigdata/hadoop/hadoop2-x-eclipse-plugin-build-install/

2、新建MR工程 依次点击 File →?New →?Ohter... ?选择 “Map/Reduce Project”，然后输入项目名称:micmiu_MRDemo，创建新项目: 3、创建Mapper和Reducer 依次点击?File →?New →?Ohter... 选择Mapper，自动继承Mapper 创建Reducer的过程同Mapper，具体的业务逻辑自己实现即可。 本文就以官方自带的WordCount为例进行测试：

package com.micmiu.mr;
/**
 * 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.
 */
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class WordCount {
  public static class TokenizerMapper 
       extends Mapper<object text intwritable>{
    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();
    public void map(Object key, Text value, Context context
                    ) throws IOException, InterruptedException {
      StringTokenizer itr = new StringTokenizer(value.toString());
      while (itr.hasMoreTokens()) {
        word.set(itr.nextToken());
        context.write(word, one);
      }
    }
  }
  public static class IntSumReducer 
       extends Reducer<text> {
    private IntWritable result = new IntWritable();
    public void reduce(Text key, Iterable<intwritable> values, 
                       Context context
                       ) throws IOException, InterruptedException {
      int sum = 0;
      for (IntWritable val : values) {
        sum += val.get();
      }
      result.set(sum);
      context.write(key, result);
    }
  }
  public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length != 2) {
      System.err.println("Usage: wordcount <in> <out>");
      System.exit(2);
    }
    //conf.set("fs.defaultFS", "hdfs://192.168.6.77:9000");
    Job job = new Job(conf, "word count");
    job.setJarByClass(WordCount.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}</out></in></intwritable></text></object>

4、准备测试数据 micmiu-01.txt：

Hi Michael welcome to Hadoop 
more see micmiu.com

micmiu-02.txt：

Hi Michael welcome to BigData
more see micmiu.com

micmiu-03.txt：

Hi Michael welcome to Spark 
more see micmiu.com

把 micmiu 打头的三个文件上传到hdfs：

micmiu-mbp:Downloads micmiu$ hdfs dfs -copyFromLocal micmiu-*.txt /user/micmiu/test/input
micmiu-mbp:Downloads micmiu$ hdfs dfs -ls /user/micmiu/test/input
Found 3 items
-rw-r--r--   1 micmiu supergroup         50 2014-04-15 14:53 /user/micmiu/test/input/micmiu-01.txt
-rw-r--r--   1 micmiu supergroup         50 2014-04-15 14:53 /user/micmiu/test/input/micmiu-02.txt
-rw-r--r--   1 micmiu supergroup         49 2014-04-15 14:53 /user/micmiu/test/input/micmiu-03.txt
micmiu-mbp:Downloads micmiu$

5、配置运行参数 Run As →?Run Configurations… ，在Arguments中配置运行参数，例如程序的输入参数： 6、运行 Run As -> Run on Hadoop ，执行完成后可以看到如下信息： 到此Eclipse中调用Hadoop2x本地伪分布式模式执行MR演示成功。 ps：调用集群环境MR运行一直失败，暂时没有找到原因。 —————– ?EOF?@Michael Sun?—————–

原文地址：eclipse中开发Hadoop2.x的Map/Reduce项目, 感谢原作者分享。