hadoop集群---计算手机流量上传下载

1.创建本地文件,需要注意的是,创建文件时尽量不要到有多余的字符或者换行,否则会报数组越界异常,解决方法是在map中分割文件时添加if判断语句

13726230501 200 1100
13396230502 300 1200
13897230503 400 1300
13897230503 100 300
13597230534 500 1400
13597230534 300 1200

2.上传至HDFS文件系统中

hadoop fs -put /phone.txt /data/phone/input

3.编写代码,代码如下

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.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class FlowSumWritable {
	
	public static void main(String[] args) throws Exception{
		Configuration conf = new Configuration();
		Job job = Job.getInstance(conf);
		Path inputPath = new Path(args[0]);
		Path outputPath = new Path(args[1]);
		
		job.setJarByClass(FlowSumWritable.class);
		job.setJobName("Flow");
		
		job.setMapperClass(Map.class);
		job.setReducerClass(Red.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(FlowWritable.class);
		
		FileInputFormat.setInputPaths(job, inputPath);
		FileOutputFormat.setOutputPath(job, outputPath);
		
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(FlowWritable.class);
		
		job.waitForCompletion(true);
	}

	public static class Map extends Mapper<LongWritable,Text,Text,FlowWritable>{
		public void map(LongWritable key,Text value,Context context) throws IOException, InterruptedException{
			String[] line = value.toString().split(" ");
			if(line.length>2){
				
				FlowWritable fwValue = new FlowWritable(Integer.parseInt(line[1]),Integer.parseInt(line[2]));
				
				context.write(new Text(line[0]), fwValue);
				
			}
		}
		
	}
	
	public static class Red extends Reducer<Text, FlowWritable, Text, Text>{
		
		public void reduce(Text key,Iterable<FlowWritable> value,Context context)throws IOException, InterruptedException{
			
			@SuppressWarnings("unused")
			String[] str;
			int upSum = 0;
			int downSum = 0;
			int totSum = 0;
			
			for (FlowWritable val : value) {
				
				//str = val.toString().split(" ");
				//upSum+=Integer.parseInt(str[0]);
				upSum+=val.getUpFlow();
				//downSum+=Integer.parseInt(str[1]);
				downSum+=val.getDownFlow();
				
			}
			totSum = upSum + downSum;
			//FlowWritable fw = new FlowWritable(upSum, downSum);
			
			context.write(key, new Text(upSum+":"+downSum+":"+totSum));
			
		}
		
	}
	
}

4.导出jar包并运行

hadoop jar /home/cloudera/jarfile/Flow.jar /data/phone/input /data/phone/output

5.查看运行结果

hadoop fs -cat /data/phone/output/part-r-00000