MapReduce编程实例之数据去重

任务描述：

让原始数据中出现次数超过一次的数据在输出文件中只出现一次。

example data：

2015-3-1 a
2015-3-2 b
2015-3-3 c
2015-3-4 d
2015-3-5 e
2015-3-6 f
2015-3-7 g
2015-3-1 a
2015-3-2 b
2015-3-3 c
2015-3-4 d
2015-3-5 e
2015-3-6 f
2015-3-7 g
2015-3-1 a
2015-3-2 b
2015-3-3 c
2015-3-4 d
2015-3-5 e
2015-3-6 f
2015-3-7 g

code：

package mrTest;

import java.io.IOException;
import java.util.Date;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
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 com.ibm.icu.text.SimpleDateFormat;

public class shujuquchong {

public static class Map extends Mapper{

public void map(Object key,Text value,Context context) throws IOException, InterruptedException{
context.write(value, NullWritable.get());
}
}

public static class Reduce extends Reducer{
public void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException{
context.write(key,  NullWritable.get());
}
}
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
// TODO Auto-generated method stub

Job job = new Job(new Configuration(), " 数据去重");
job.setJarByClass(shujuquchong.class);

job.setNumReduceTasks(1);

job.setOutputKeyClass(Text.class);
job.setOutputValueClass(NullWritable.class);

job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);

FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
//记录时间
SimpleDateFormat  sdf = new SimpleDateFormat();
    Date start = new Date();        //开始时间
    
int result = job.waitForCompletion(true)? 0 : 1;    //任务开始

Date end = new Date();     //结束时间
float time = (float)((end.getTime() - start.getTime()) / 60000.0);  //任务开始到结束经历的时间

System.out.println("Job 开始的时间为：" + start);
System.out.println("Job 结束的时间为：" + end);
System.out.println("Job 经历的时间为：" + time + "分钟");

System.out.println("Job 的名字：" + job.getJobName());
System.out.println("Job 是否成功：" + job.isSuccessful() );
System.out.println("Job 输入的行数：" + job.getCounters().findCounter("org.apache.hadoop.mapred.Task$Counter",  "MAP_INPUT_RECORDS").getValue());
System.out.println("Job 输出的行数：" + job.getCounters().findCounter("org.apache.hadoop.mapred.Task$Counter",  "MAP_OUTPUT_RECORDS").getValue());
System.out.println("Job 输入的行数：" + job.getCounters().findCounter("org.apache.hadoop.mapred.Task$Counter",  "REDUCE_INPUT_RECORDS").getValue());
System.out.println("Job 输出的行数：" + job.getCounters().findCounter("org.apache.hadoop.mapred.Task$Counter",  "REDUCE_OUTPUT_RECORDS").getValue());

System.exit(result); //判断是否结束
}

}