hadoop分区

package demo04.flow;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Partitioner;


public class FlowPartion extends Partitioner {

    @Override
    public int getPartition(Text text, FlowNum flowNum, int i) {
        String line = text.toString();
        if (line.startsWith("135")) {
            return 0;
        }else if(line.startsWith("135")){
            return 1;
        }else if(line.startsWith("135")){
            return 2;
        }else if(line.startsWith("135")){
            return 3;
        }else if(line.startsWith("135")){
            return 4;
        }else{
            return 5;
        }
    }
}

主程序里run方法里加入

//分区,分区个数,分区个数最好与上面方法的分区个数相等，多了冗余，少了一个reduce处理多份工作
job.setPartitionerClass(FlowPartion.class);
job.setNumReduceTasks(6);