package com.wordcount;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class wordreducer extends Reducer<Text, IntWritable, Text, IntWritable> {
private IntWritable res = new IntWritable();
public void reduce(Text key, Iterable<IntWritable> values, Context context)
throws IOException, InterruptedException {
int sum = 0;
for (IntWritable val : values) {
sum += val.get();
}
res.set(sum);
context.write(key, res);
}
}
package com.wordcount;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.*;
import java.util.*;
public class wordmapper extends Mapper<Object, Text, Text, IntWritable> {
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
StringTokenizer itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
context.write(word, one);
}
}
}
package com.wordcount;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class entry {
@SuppressWarnings("deprecation")
public static void main(String arg[]) throws Exception {
Configuration conf = new Configuration();
String[] otherarg = new GenericOptionsParser(conf, arg)
.getRemainingArgs();
if (otherarg.length != 2) {
System.out.println("error!");
System.exit(2);
}
Job job = new Job(conf, "worcount");
job.setJarByClass(entry.class);
job.setMapperClass(wordmapper.class);
job.setReducerClass(wordreducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job, new Path(arg[0]));
FileOutputFormat.setOutputPath(job, new Path(arg[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
HadoopMapReduceWordcount示例程序
最新推荐文章于 2018-05-17 13:39:19 发布