Hadoop模板（新API）

最新推荐文章于 2023-03-19 19:56:53 发布

u010660276

最新推荐文章于 2023-03-19 19:56:53 发布

阅读量350

点赞数

分类专栏： Hadoop

本文链接：https://blog.csdn.net/u010660276/article/details/50956605

版权

Hadoop 专栏收录该内容

10 篇文章 0 订阅

订阅专栏

本文提供了一个使用Hadoop新API的示例程序，通过一个简单的MapReduce作业展示了如何读取键值对输入并进行处理。该程序继承了Configured类，并实现了Tool接口，能够从文本文件中读取数据，通过Map阶段将键值对位置互换，再通过Reduce阶段聚合相同的键。

摘要由CSDN通过智能技术生成

跟原来的API稍有不同，其实也差不多

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
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.input.KeyValueTextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

import sun.launcher.resources.launcher;

public class NewAPIMyJob extends Configured implements Tool {

    public static class MapClass extends Mapper<Text, Text, Text, Text>{
        public void map(Text key,Text value,Context context)throws IOException,InterruptedException{
             context.write(value, key);
        }
    }
    public static class Reduce  extends Reducer<Text, Text, Text, Text>{

        public void reduce(Text key,Iterable<Text> value,Context context)throws IOException,InterruptedException{

            String reString="";
            for(Text val:value){
                if(reString.length()>0)reString+=",";
                reString+=val.toString();
            }
            context.write(key, new Text(reString));
        }
    }
    @Override
    public int run(String[] arg0) throws Exception,InterruptedException {
        // TODO Auto-generated method stub

        Configuration configuration=getConf();
        Job job=new Job(configuration,"MyJob");

        job.setJarByClass(MyJob.class);

        FileInputFormat.setInputPaths(job, new Path(arg0[0]));
        FileOutputFormat.setOutputPath(job, new Path(arg0[1]));

        job.setMapperClass(MapClass.class);
        job.setReducerClass(Reduce.class);
        job.setInputFormatClass(KeyValueTextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        System.exit(job.waitForCompletion(true)?0:1);

        return 0;
    }

    public static void main(String[] args)throws Exception {
        // TODO Auto-generated method stub

        int res=ToolRunner.run(new Configuration(),new NewAPIMyJob(),args);
        System.exit(res);

    }

}