简单的计算最值的MapReduce程序

import java.io.IOException;
import java.util.StringTokenizer;
import java.util.*;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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 max_number {

  public static class TokenizerMapper
       extends Mapper<Object, Text, Text, IntWritable>{

    private final static IntWritable one = new IntWritable(1);
 
    public void map(Object key, Text value, Context context
                    ) throws IOException, InterruptedException {
    String line=value.toString();
      StringTokenizer itr = new StringTokenizer(line,"\n");
      while (itr.hasMoreTokens()) {
    StringTokenizer tkl=new StringTokenizer(itr.nextToken());
    String sKey=tkl.nextToken();
    String sNum=tkl.nextToken();
    Text key=new Text(sKey);
    int numInt=Integer.parseInt(sScore);
        context.write(key, new IntWritable(numInt));
      }
    }
  }

  public static class IntSumReducer
       extends Reducer<Text,IntWritable,Text,IntWritable> {
    private IntWritable result = new IntWritable();

    public void reduce(Text key, Iterable<IntWritable> values,
                       Context context
                       ) throws IOException, InterruptedException {
      int max = -219876543;
  Iterator<IntWritable>iterator=values.iterator();
      while(iterator.hasNext())
      {
        int max1= iterator.next().get();
    if(max1>=max){max=max1;}

    
}  context.write(key, new IntWritable(max));
    }
  }

  public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    Job job = Job.getInstance(conf, "max number");
    job.setJarByClass(max_number.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

运行需要的设置

导入hadoop的class和java_home路径
export JAVA_HOME=/usr/java/default
export PATH=${JAVA_HOME}/bin:${PATH}
export HADOOP_CLASSPATH=${JAVA_HOME}/lib/tools.jar

--编译写好的MapReduce java程序
$ $Hadoop_Home/bin/hadoop com.sun.tools.javac.Main max_number.java
$ jar cf maxnumber.jar max_number*.class
--上传文件到hdfs
$Hadoop_Home/bin/hadoop fs --copyFromLocal /home/hadoop/hadoop/random.txt /test/random
--执行
 $Hadoop_Home/bin/hadoop jar maxnumber.jar max_number /test/random /output11/minnumber2 //练习执行的脚本

查询输出Output:

$ $Hadoop_Home/bin/hadoop fs -cat /output11/minnumber2/part-r-00000`