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);
}
}
執行需要的設定
匯入hadoop的class和java_home路徑
export JAVA_HOME=/usr/java/default
export PATH=${JAVA_HOME}/bin:${PATH}
export HADOOP_CLASSPATH=${JAVA_HOME}/lib/tools.jar
--編譯寫好的MapReduce java程式
$ $Hadoop_Home/bin/hadoop com.sun.tools.javac.Main max_number.java
$ jar cf maxnumber.jar max_number*.class
--上傳檔案到hdfs
$Hadoop_Home/bin/hadoop fs --copyFromLocal /home/hadoop/hadoop/random.txt /test/random
--執行
$Hadoop_Home/bin/hadoop jar maxnumber.jar max_number /test/random /output11/minnumber2 //練習執行的指令碼
查詢輸出Output:
$ $Hadoop_Home/bin/hadoop fs -cat /output11/minnumber2/part-r-00000`