【无标题】2222222

最新推荐文章于 2024-10-04 18:47:42 发布

lucky 999

最新推荐文章于 2024-10-04 18:47:42 发布

阅读量969

点赞数

文章标签： hadoop mapreduce hdfs

本文链接：https://blog.csdn.net/m0_46313431/article/details/122121436

版权

package bigdata;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.IOException;

public class PersonDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        // 获取配置文件和job对象
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);

        // 设置jar的路径
        job.setJarByClass(PersonDriver.class);

        // 设置mapper类和reducer类
        job.setMapperClass(PersonMapper.class);
        job.setReducerClass(PersonReduce.class);

        // 设置mapper输出的key和value的数据类型
        job.setMapOutputKeyClass(PersonBean.class);
        job.setMapOutputValueClass(NullWritable.class);

        // 设置reduce输出的key和value的数据类型
        job.setOutputKeyClass(PersonBean.class);
        job.setOutputValueClass(NullWritable.class);

        // 设置自定义分区的类
        job.setPartitionerClass(PersonPartition.class);
        // 设置ReduceTask的数量
        job.setNumReduceTasks(3);

        String INPUT_PATH = "./datas/data01.txt";
        String OUTPUT_PATH = "./dd";
        FileInputFormat.addInputPath(job, new Path(INPUT_PATH));
        FileOutputFormat.setOutputPath(job, new Path(OUTPUT_PATH));
        FileSystem fs = FileSystem.get(new Configuration());
        if (fs.exists(new Path(OUTPUT_PATH))) {
            fs.delete(new Path(OUTPUT_PATH), true);
        }
        // 提交计算任务(job)
        boolean result = job.waitForCompletion(true);

        System.exit(result ? 0:1);
    }
}