(1)WordDistinctMappper
package s27;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
public class WordDistinctMapper extends Mapper<LongWritable,Text,Text,NullWritable>{
public void map(LongWritable key, Text value, Context context) throws IOException,InterruptedException {
context.write(value,NullWritable.get());
}
}
(2)WordDistinctReduce
package s27;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
public class WordDistinctReducer extends Reducer<Text,NullWritable,Text,NullWritable> {
public void reduce(Text key,Iterable
context.write(key,NullWritable.get());
}
}
(3)WordDistinctJob
package s27;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
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 WordDistinctJob {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf=new Configuration();
conf.set("fs.defaultFS","hdfs://master:9000");
Job job= Job.getInstance(conf);
job.setJarByClass(WordDistinctJob.class);
job.setMapperClass(WordDistinctMapper.class);
job.setReducerClass(WordDistinctReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(NullWritable.class);
Path pin=new Path("/sw");
Path pout=new Path("/out");
FileSystem fs=FileSystem.get(conf);
if(fs.exists(pout)){
fs.delete(pout,true);
}
FileInputFormat.setInputPaths(job,pin);
FileOutputFormat.setOutputPath(job,pout);
job.waitForCompletion(true);
}
}
原文:https://www.cnblogs.com/Song-wei/p/13902086.html