hadoop mapreduce计算实例

hadoop中使用mapreduce计算框架进行计算任务，场景：统计日志文件data02.log的数据中一共包含多少部电影。

Mapreduce代码实例

//Mapper过程

package sss;

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


public class SMapper extends Mapper <LongWritable, Text, Text, LongWritable>{

@Override
protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, LongWritable>.Context context)
throws IOException, InterruptedException {


String line = value.toString();
String s[] = line.split(";");

int num = 0;

for(String str : s) {
   if(s.equals("")) {
      continue;
    }
   num ++;
}

context.write(new Text("movie"), new LongWritable(num));
}

}


//Reduce过程
package sss;

import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;


public class Submitter {

public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

  Configuration conf = new Configuration();

  FileSystem fs = FileSystem.get(conf);
  if(fs.exists(new Path(args[1]))) {
     fs.delete(new Path(args[1]), true);
  }

Job job = Job.getInstance();
job.setJarByClass(Submitter.class);
job.setMapperClass(SMapper.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
boolean b = job.waitForCompletion(true);
System.out.println(b);

}
}

运行结果：