AWS EMR运行MAPREDUCE程序-WORDCOUNT

1、首先在ECLIPSE上开发WordCount程序

      包名：test_mapreduce

      JAVA文件名：WordCount.java

      

      WordCount.java程序：

      

package test_mapreduce;

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, 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,IntWritable,Text,IntWritable> {
    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> [<in>...] <out>");
      System.exit(2);
    }

    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);
    for (int i = 0; i < otherArgs.length - 1; ++i) {
      FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
    }
    FileOutputFormat.setOutputPath(job,
      new Path(otherArgs[otherArgs.length - 1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

2、把程序打包为test.jar

3、在AWS S3控制台创建BUCKET：balinanews，并创建test文件夹

4、上传test.jar文件到test目录下

5、在test文件夹下上传一个test.sql文件，作为WORDCOUNT程序的输入

6、在AWS EMR控制台，点击进入EMR STEP选项

7、点击 添加步骤按钮，填写如下：

       步骤类型：自定义JAR

       名称：wordcount test

       JAR位置：s3://balinanews/test/test.jar

       自变量：s3://balinanews/test/input  s3://balinanews/test/output  （前一个参数是输入路径，后一个是输出路径）

       

   点击添加后，任务进入运行状态。

     最后进入已完成状态：

      

8、查看执行结果：

       

        打开part-r-00000查看内容如下：（前面是字符，后面是统计量）

        

到此运行一个mapreduce任务结束。