hadoop实现数据的二次排序
作者：互联网
需求：对业务数据根据上行流量和上行总流量做一个排序处理，上行流量升序，上行流量相同的上行总流量升序
数据说明：7，8，9，10位置的数据类型分别为upFlow，dowFlow，upCountFlow，downCountFlow
1363157985066 13726230503 00-FD-07-A4-72-B8:CMCC 120.196.100.82 i02.c.aliimg.com 游戏娱乐 24 27 2481 24681 200
1363157995052 13826544101 5C-0E-8B-C7-F1-E0:CMCC 120.197.40.4 jd.com 京东购物 4 0 264 0 200
1363157991076 13926435656 20-10-7A-28-CC-0A:CMCC 120.196.100.99 taobao.com 淘宝购物 2 4 132 1512 200
1363154400022 13926251106 5C-0E-8B-8B-B1-50:CMCC 120.197.40.4 cnblogs.com 技术门户 4 0 240 0 200
1363157993044 18211575961 94-71-AC-CD-E6-18:CMCC-EASY 120.196.100.99 iface.qiyi.com 视频网站 15 12 1527 2106 200
1363157995074 84138413 5C-0E-8B-8C-E8-20:7DaysInn 120.197.40.4 122.72.52.12 未知 20 16 4116 1432 200
1363157993055 13560439658 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 sougou.com 综合门户 18 15 1116 954 200
1363157992093 13560439658 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 zhilian.com 招聘门户 15 9 918 4938 200
1363157995033 15920133257 5C-0E-8B-C7-BA-20:CMCC 120.197.40.4 sug.so.360.cn 信息安全 20 20 3156 2936 200
1363157983019 13719199419 68-A1-B7-03-07-B1:CMCC-EASY 120.196.100.82 baidu.com 综合搜索 4 0 240 0 200
1363157984041 13660577991 5C-0E-8B-92-5C-20:CMCC-EASY 120.197.40.4 s19.cnzz.com 站点统计 24 9 6960 690 200
1363157973098 15013685858 5C-0E-8B-C7-F7-90:CMCC 120.197.40.4 rank.ie.sogou.com 搜索引擎 28 27 3659 3538 200
1363157986029 15989002119 E8-99-C4-4E-93-E0:CMCC-EASY 120.196.100.99 www.umeng.com 站点统计 3 3 1938 180 200
1363157986041 13480253104 5C-0E-8B-C7-FC-80:CMCC-EASY 120.197.40.4 csdn.net 技术门户 3 3 180 180 200
1363157984040 13602846565 5C-0E-8B-8B-B6-00:CMCC 120.197.40.4 2052.flash2-http.qq.com 综合门户 15 12 1938 2910 200
1363157995093 13922314466 00-FD-07-A2-EC-BA:CMCC 120.196.100.82 img.qfc.cn 图片大全 12 12 3008 3720 200
1363157982040 13502468823 5C-0A-5B-6A-0B-D4:CMCC-EASY 120.196.100.99 y0.ifengimg.com 综合门户 57 102 7335 110349 200
1363157986072 18320173382 84-25-DB-4F-10-1A:CMCC-EASY 120.196.100.99 input.shouji.sogou.com 搜索引擎 21 18 9531 2412 200
1363157990043 13925057413 00-1F-64-E1-E6-9A:CMCC 120.196.100.55 t3.baidu.com 搜索引擎 69 63 11058 48243 200
1363157988072 13760778710 00-FD-07-A4-7B-08:CMCC 120.196.100.82 http://youku.com/ 视频网站 2 2 120 120 200
1363157985079 13823070001 20-7C-8F-70-68-1F:CMCC 120.196.100.99 img.qfc.cn 图片浏览 6 3 360 180 200
1363157985069 13600217502 00-1F-64-E2-E8-B1:CMCC 120.196.100.55 www.baidu.com 综合门户 18 138 1080 186852 200
1、编写bean类，继承WritableComparable，用于比较逻辑的实现
package com.xiaofei.mr.sort;
import org.apache.hadoop.io.WritableComparable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
/**
* @author yangquan
* @date 2021.07.13
*/
public class FlowBeanCompare implements WritableComparable<FlowBeanCompare> {
private Integer upFlow;
private Integer downFlow;
private Integer upCountFlow;
private Integer downCountFlow;
public FlowBeanCompare() {
}
public FlowBeanCompare(Integer upFlow, Integer downFlow, Integer upCountFlow, Integer downCountFlow) {
this.upFlow = upFlow;
this.downFlow = downFlow;
this.upCountFlow = upCountFlow;
this.downCountFlow = downCountFlow;
}
@Override
public int compareTo(FlowBeanCompare o) {
int result = this.upFlow.compareTo(o.upFlow);
if(result==0){
return this.downFlow.compareTo(o.downFlow);
}else {
return result;
}
}
@Override
public void write(DataOutput out) throws IOException {
out.writeInt(upFlow);
out.writeInt(downFlow);
out.writeInt(upCountFlow);
out.writeInt(downCountFlow);
}
@Override
public void readFields(DataInput in) throws IOException {
this.upFlow = in.readInt();
this.downFlow=in.readInt();
this.upCountFlow=in.readInt();
this.downCountFlow=in.readInt();
}
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;
}
@Override
public String toString() {
return "FlowBean{" +
"upFlow=" + upFlow +
", downFlow=" + downFlow +
", upCountFlow=" + upCountFlow +
", downCountFlow=" + downCountFlow +
'}';
}
}
2、编写程序运行的主类
package com.xiaofei.mr.sort;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
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;
import java.io.IOException;
/**
* @author yangquan
* @date 2021.07.13
*/
public class FlowBeanSort extends Configured implements Tool {
@Override
public int run(String[] args) throws Exception {
Job job=Job.getInstance(super.getConf(),FlowBeanSort.class.getSimpleName());
job.setJarByClass(FlowBeanSort.class);
job.setInputFormatClass(TextInputFormat.class);
Path inpath = new Path("D:\\数据资料\\hadoop数据资料\\SortFlow\\intput");
TextInputFormat.addInputPath(job,inpath);
job.setMapperClass(FlowMapper.class);
job.setMapOutputKeyClass(FlowBeanCompare.class);
job.setMapOutputValueClass(NullWritable.class);
job.setOutputFormatClass(TextOutputFormat.class);
Path outpath=new Path("D:\\数据资料\\hadoop数据资料\\SortFlow\\out");
FileSystem fileSystem = FileSystem.get(super.getConf());
if(fileSystem.exists(outpath)){
fileSystem.delete(outpath,true);
}
TextOutputFormat.setOutputPath(job,outpath);
return (job.waitForCompletion(true)?0:1);
}
public static void main(String[] args) throws Exception {
int run = ToolRunner.run(new Configuration(), new FlowBeanSort(), args);
System.exit(run);
}
public static class FlowMapper extends Mapper<LongWritable, Text,FlowBeanCompare, NullWritable>{
private FlowBeanCompare flowBeanCompare;
@Override
protected void setup(Context context) throws IOException, InterruptedException {
flowBeanCompare=new FlowBeanCompare();
}
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String[] splits = value.toString().split("\t");
int upLow =Integer.parseInt( splits[6]);
int downFlow = Integer.parseInt(splits[7]);
int upCountFlow = Integer.parseInt(splits[8]);
int downCountFlow = Integer.parseInt(splits[9]);
flowBeanCompare.setUpFlow(upLow);
flowBeanCompare.setDownFlow(downFlow);
flowBeanCompare.setUpCountFlow(upCountFlow);
flowBeanCompare.setDownCountFlow(downCountFlow);
context.write(flowBeanCompare,NullWritable.get());
//说明：mapper中必须使用bean对象这个才会进行比对，如果使用Text类型的输出时无法进行比对的这点要注意
/*String line= splits[6]+","+splits[7]+","+splits[8]+","+splits[9];
context.write(new Text(line),NullWritable.get());*/
}
}
}
标签：二次,CMCC,hadoop,import,Integer,排序,com,public 来源： https://www.cnblogs.com/blogxiaochong/p/15007737.html