hadoop之MapReduce上网流量统计（2）

需求二：上行流量倒序排序（递减排序）

FlowBeanSort :
import org.apache.hadoop.io.WritableComparable;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

public class FlowBeanSort implements WritableComparable<FlowBeanSort> {


    //上行流量
    private Integer  upFlow;
    //下行流量
    private Integer  downFlow;
    //上行总流量
    private Integer  upCountFlow;
    //下行总流量
    private Integer  downCountFlow;

    @Override
    public String toString() {
        return upFlow+"\t"+downFlow+"\t"+upCountFlow+"\t"+downCountFlow;
    }

    public Integer getUpFlow() {
        return upFlow;
    }

    public void setUpFlow(Integer upFlow) {
        this.upFlow = upFlow;
    }

    public Integer getDownFlow() {
        return downFlow;
    }

    public void setDownFlow(Integer downFlow) {
        this.downFlow = downFlow;
    }

    public Integer getUpCountFlow() {
        return upCountFlow;
    }

    public void setUpCountFlow(Integer upCountFlow) {
        this.upCountFlow = upCountFlow;
    }

    public Integer getDownCountFlow() {
        return downCountFlow;
    }

    public void setDownCountFlow(Integer downCountFlow) {
        this.downCountFlow = downCountFlow;
    }


    /**
     * 比较器，以上行流量进行比较
     * @param o
     * @return
     */
    @Override
    public int compareTo(FlowBeanSort o) {
        int i = this.upFlow.compareTo(o.upFlow);
        return -i;
    }

    /**
     * 序列化的方法
     * @param out
     * @throws IOException
     */
    @Override
    public void write(DataOutput out) throws IOException {
        out.writeInt(upFlow);
        out.writeInt(downFlow);
        out.writeInt(upCountFlow);
        out.writeInt(downCountFlow);
    }

    /**
     * 反序列的方法
     * @param in
     * @throws IOException
     */
    @Override
    public void readFields(DataInput in) throws IOException {
        this.upFlow = in.readInt();
        this.downFlow = in.readInt();
        this.upCountFlow = in.readInt();
        this.downCountFlow = in.readInt();
    }
}





FlowSortMapper:
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

public class FlowSortMapper extends Mapper<LongWritable,Text,FlowBeanSort,Text> {


    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
       //13480253104	3	3	180	180
        String[] split = value.toString().split("\t");
        FlowBeanSort flowBeanSort = new FlowBeanSort();
        flowBeanSort.setUpFlow(Integer.parseInt(split[1]));
        flowBeanSort.setDownFlow(Integer.parseInt(split[2]));
        flowBeanSort.setUpCountFlow(Integer.parseInt(split[3]));
        flowBeanSort.setDownCountFlow(Integer.parseInt(split[4]));
        context.write(flowBeanSort,new Text(split[0]));

    }
}



FlowSortReducer:
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class FlowSortReducer extends Reducer<FlowBeanSort,Text,FlowBeanSort,Text> {

    @Override
    protected void reduce(FlowBeanSort key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
        for (Text value : values) {
            context.write(key,value);
        }
    }
}


FlowSortMain:
import cn.itcast.demo3.flowCount.FlowBean;
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.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class FlowSortMain extends Configured implements Tool {
    @Override
    public int run(String[] args) throws Exception {
        Job job = Job.getInstance(super.getConf(), "flowSort");

        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job,new Path("file:///F:\\流量统计\\out_sort_flow"));

        job.setMapperClass(FlowSortMapper.class);
        job.setMapOutputKeyClass(FlowBeanSort.class);
        job.setMapOutputValueClass(Text.class);


        job.setReducerClass(FlowSortReducer.class);
        job.setOutputKeyClass(FlowBeanSort.class);
        job.setOutputValueClass(Text.class);

        job.setOutputFormatClass(TextOutputFormat.class);
        TextOutputFormat.setOutputPath(job,new Path("file:///F:\\upflow_sort_output"));

        boolean b = job.waitForCompletion(true);


        return b?0:1;
    }

    public static void main(String[] args) throws Exception {
        int run = ToolRunner.run(new Configuration(), new FlowSortMain(), args);
        System.exit(run);
    }

}



数据输入：
13480253104	3	3	180	180
13502468823	57	102	7335	110349
13560439658	33	24	2034	5892
13600217502	18	138	1080	186852
13602846565	15	12	1938	2910
13660577991	24	9	6960	690
13719199419	4	0	240	0
13726230503	24	27	2481	24681
13760778710	2	2	120	120
13823070001	6	3	360	180
13826544101	4	0	264	0
13922314466	12	12	3008	3720
13925057413	69	63	11058	48243
13926251106	4	0	240	0
13926435656	2	4	132	1512
15013685858	28	27	3659	3538
15920133257	20	20	3156	2936
15989002119	3	3	1938	180
18211575961	15	12	1527	2106
18320173382	21	18	9531	2412
84138413	20	16	4116	1432

数据输出：
13925057413	69	63	11058	48243
13502468823	57	102	7335	110349
13560439658	33	24	2034	5892
15013685858	28	27	3659	3538
13726230503	24	27	2481	24681
13660577991	24	9	6960	690
18320173382	21	18	9531	2412
84138413	20	16	4116	1432
15920133257	20	20	3156	2936
13600217502	18	138	1080	186852
13602846565	15	12	1938	2910
18211575961	15	12	1527	2106
13922314466	12	12	3008	3720
13823070001	6	3	360	180
13826544101	4	0	264	0
13719199419	4	0	240	0
13926251106	4	0	240	0
15989002119	3	3	1938	180
13480253104	3	3	180	180
13926435656	2	4	132	1512
13760778710	2	2	120	120