1.
package com.zhangchengqi;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
@Override
protected void map(LongWritable key, Text value,Context context)throws IOException, InterruptedException {
String line = value.toString();
String[] words = line.split(" ");
for(String w : words) {
word.set(w);
context.write(word, one);
}
}
}
2.
package com.zhangchengqi;
import java.io.IOException;
import java.util.Iterator;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class WordCountReducer extends Reducer<Text, IntWritable,Text, IntWritable>{
@Override
protected void reduce(Text key, Iterable<IntWritable> values,Context context)throws IOException, InterruptedException {
int sum = 0;
for(IntWritable v:values) {
sum+=v.get();
}
context.write(key, new IntWritable(sum));
}
}
3.
package com.zhangchengqi;
import java.io.IOException;
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;
public class WordCountMain {
public static void main(String[] args)throws IOException,ClassNotFoundException, InterruptedException {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(WordCountMapper.class);
job.setMapperClass(WordCountMapper.class);
job.setReducerClass(WordCountReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
boolean rs = job.waitForCompletion(true);
System.exit(rs?0:1);
}
}