MapReduce提交作业

java代码

package com.test.Job;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;

public class jobSubmit {
    public static void main(String[] args) throws Exception{
        Configuration entries = new Configuration();
        Job job = Job.getInstance(entries, "JobSubmit");
        job.setJarByClass(jobSubmit.class);
        
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        
        job.setMapperClass(MyMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);

        job.setReducerClass(MyReduce.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);

        FileSystem fileSystem = FileSystem.newInstance(entries);
        Path outFilePath = new Path(args[1]);
        if (fileSystem.exists(outFilePath)) {
            fileSystem.delete(outFilePath, true);
        }
        FileOutputFormat.setOutputPath(job, outFilePath);
        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);
    }
    
    public static class MyMapper extends Mapper<LongWritable, Text, Text, LongWritable>{
        private final LongWritable one = new LongWritable(1);
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException,InterruptedException{
            String[] split = value.toString().split(" ");
            for(String sp : split){
                context.write(new Text(sp), one);
            }
        }
    }

    public static class MyReduce extends Reducer<Text,LongWritable,Text,LongWritable>{
        protected void reduce(Text key,Iterable<LongWritable> values,Context context) throws IOException,InterruptedException{
            int sum = 0;
            for(LongWritable writable : values){
                sum += writable.get();
            }
            context.write(key, new LongWritable(sum));
        }
    }
}

把java代码编译jar包（IDEA）

• clean
  
  
• install
  
  

上传HDFS

• 上传Linux服务器

rz

• 拷贝到/home/hdfs 目录下
  
• 上传到HDFS
  
  
• 执行命令运行程序

hadoop jar 
/home/hdfs/XXXX-1.0-SNAPSHOT-jar-with-dependencies.jar（本地jar包路径）
com.test.Job.jobSubmit（main函数） 
hdfs://192.168.1.37:8020/user/tgm/hello.txt（输入文件）
hdfs://192.168.1.37:8020/user/tgm/hello_result.txt（结果保存文件）

• 程序执行完毕，查看结果文件，从HDFS文件系统下载hello_result.txt文件，查看内容。