大数据-[案例]Reduce端实现JOIN

select a.id,a.date,b.name,b.category_id,b.price from t_order a left join t_product b on a.pid = b.id

public class JobMain extends Configured implements Tool {
    @Override
    public int run(String[] strings) throws Exception {
        //创建一个任务对象
        Job job = Job.getInstance(super.getConf(), "mapreduce_reduce_join");
        //打包放在集群运行时，需要做一个配置
        job.setJarByClass(JobMain.class);
        //第一步:设置读取文件的类: K1 和V1
        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job, new Path("hdfs://node01:8020/input/reduce_join"));
        //第二步：设置Mapper类
        job.setMapperClass(ReduceJoinMapper.class);
        //设置Map阶段的输出类型: k2 和V2的类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);
        //第三,四，五，六步采用默认方式(分区，排序，规约，分组)
        // 第七步 ：设置文的Reducer类
        job.setReducerClass(ReduceJoinReducer.class);
        //设置Reduce阶段的输出类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        //第八步:设置输出类
        job.setOutputFormatClass(TextOutputFormat.class);
        //设置输出的路径
        TextOutputFormat.setOutputPath(job, new Path("hdfs://node01:8020/out/reduce_join_out"));
        boolean b = job.waitForCompletion(true);
        return b ? 0 : 1;
    }

    public static void main(String[] args) throws Exception {
        Configuration configuration = new Configuration();
        //启动一个任务
        int run = ToolRunner.run(configuration, new JobMain(), args);
        System.exit(run);
    }
}