分区编程:
1.根据业务需要,产生多个输出文件
2.多个reduce任务在运行,提高整体job的运行效率
package partition;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Mapper.Context;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.mapreduce.lib.partition.HashPartitioner;
/**
* 分区的例子必须打成jar运行
* 用处: 1.根据业务需要,产生多个输出文件
* 2.多个reduce任务在运行,提高整体job的运行效率
*/
public class KpiApp {
private static final String INPUT_PATH = "hdfs://hadoop:9000/wlan";
private static final String OUT_PATH = "hdfs://hadoop:9000/out";
public static void main(String[] args) throws Exception {
Job job = new Job(new Configuration(), KpiApp.class.getSimpleName());
//1.1 指定输入文件路径
FileInputFormat.setInputPaths(job, INPUT_PATH);
//指定哪个类用来格式化输入文件
job.setInputFormatClass(TextInputFormat.class);
//1.2 指定自定义的Mapper类
job.setMapperClass(MyMapper.class);
//指定输入<k2,v2>的类型
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(KpiWritable.class);
//1.3 指定分区类
job.setPartitionerClass(KpiPartitioner.class);
job.setNumReduceTasks(2);
//1.4 排序、分区
//1.5 合并
//2.2 指定自定义的reduce类
job.setReducerClass(MyReducer.class);
//指定输出<k3,v3>的类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(KpiWritable.class);
//2.3 指定输出到哪里
FileOutputFormat.setOutputPath(job, new Path(OUT_PATH));
//设定输出文件的格式化类
job.setOutputFormatClass(TextOutputFormat.class);
//把代码嫁给JobTracker执行
job.waitForCompletion(true);
}
static class MyMapper extends Mapper<LongWritable, Text, Text, KpiWritable>{
@Override
protected void map(LongWritable key, Text value,
org.apache.hadoop.mapreduce.Mapper<LongWritable, Text, Text, KpiWritable>.Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
String[] splited = value.toString().split("\t");
String msisdn = splited[1];
Text k2 = new Text(msisdn);
KpiWritable v2 = new KpiWritable(splited[6],splited[7],splited[8],splited[9]);
context.write(k2,v2);
}
}
static class MyReducer extends Reducer<Text, KpiWritable, Text, KpiWritable>{
@Override
protected void reduce(Text k2, Iterable<KpiWritable> v2s,
org.apache.hadoop.mapreduce.Reducer<Text, KpiWritable, Text, KpiWritable>.Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
long upPackNum = 0L;
long downPackNum = 0L;
long upPayLoad = 0L;
long downPayLoad = 0L;
for (KpiWritable kpiWritable : v2s) {
upPackNum += kpiWritable.upPackNum;
downPackNum += kpiWritable.downPackNum;
upPayLoad += kpiWritable.upPayLoad;
downPayLoad += kpiWritable.downPayLoad;
}
KpiWritable v3 = new KpiWritable(upPackNum+"",downPackNum+"", upPayLoad+"", downPayLoad+"");
context.write(k2,v3);
}
}
static class KpiPartitioner extends HashPartitioner<Text, LongWritable>{
@Override
public int getPartition(Text key, LongWritable value, int numReduceTasks) {
// TODO Auto-generated method stub
return (key.toString().length()==11)?0:1;
}
}
}
class KpiWritable implements Writable{
long upPackNum;
long downPackNum;
long upPayLoad;
long downPayLoad;
public KpiWritable(){}
public KpiWritable(String upPackNum, String downPackNum, String upPayLoad, String downPayLoad){
this.upPackNum = Long.parseLong(upPackNum);
this.downPackNum = Long.parseLong(downPackNum);
this.upPayLoad = Long.parseLong(upPayLoad);
this.downPayLoad = Long.parseLong(downPayLoad);
}
@Override
public void readFields(DataInput in) throws IOException {
// TODO Auto-generated method stub
this.upPackNum = in.readLong();
this.downPackNum = in.readLong();
this.upPayLoad = in.readLong();
this.downPayLoad = in.readLong();
}
@Override
public void write(DataOutput out) throws IOException {
// TODO Auto-generated method stub
out.writeLong(upPackNum);
out.writeLong(downPackNum);
out.writeLong(upPayLoad);
out.writeLong(downPayLoad);
}
@Override
public String toString() {
// TODO Auto-generated method stub
return upPackNum + "\t" + downPackNum + "\t" + upPayLoad + "\t" + downPayLoad;
}
}