MapReduce实验——统计拨打公共服务号码的电话信息

统计拨打公共服务号码的电话信息

Map类

package PhoneCollect;

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

import java.io.IOException;

public class MyMap extends Mapper<LongWritable,Text,Text,Text> {
   protected void map(LongWritable key,Text value,Context context) throws IOException, InterruptedException {
       String line = value.toString();
       String[] lineArr = line.split(" ");
       String anum = lineArr[0];
       String bnum = lineArr[1];
       context.write(new Text(bnum),new Text(anum));
   }
}

Reduce类

package PhoneCollect;

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

import java.io.IOException;

public class MyReduce extends Reducer<Text, Text,Text,Text> {
    protected void reduce(Text key,Iterable<Text> it,Context context) throws IOException, InterruptedException {
        String valueString;
        String out = "";
        for(Text value:it){
            valueString = value.toString();
            out += valueString+"|";
        }
        context.write(new Text(key),new Text(out));
    }
}

Job类

package PhoneCollect;
import org.apache.hadoop.conf.Configuration;
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.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class TestJob {
    public static void main(String[] args) throws IOException {
        //
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        //
        job.setJarByClass(TestJob.class);
        job.setMapperClass(MyMap.class);
        job.setReducerClass(MyReduce.class);
        //
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        //
        FileInputFormat.setInputPaths(job,new Path("file:///simple/source.txt"));
        FileOutputFormat.setOutputPath(job,new Path("file:///simple/output"));
    }
}

标签：拨打,org,hadoop,MapReduce,job,公共服务,Text,apache,import
来源： https://blog.csdn.net/weixin_45740510/article/details/122240909