程式設計題1:編寫一個WordCount程式
Mapper
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
public class WcountMapper extends Mapper<LongWritable,Text,Text,IntWritable> {
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String s = value.toString();
String[] split = s.split(" ");
for (String s1 : split) {
context.write(new Text(s1), new IntWritable(1));
}
}
}
Reducer
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
public class WcountReducer 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 value : values) {
sum += value.get();
}
context.write(key,new IntWritable(sum));
}
}
driver
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 java.io.IOException;
public class WcountDriver {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration entries = new Configuration();
Job job = Job.getInstance(entries);
job.setJarByClass(WcountDriver.class);
job.setMapperClass(WcountMapper.class);
job.setReducerClass(WcountReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.setInputPaths(job,new Path("F:\\data\\input\\KvText.txt"));
FileOutputFormat.setOutputPath(job,new Path("F:\\data\\outputdata\\output1"));
job.waitForCompletion(true);
}
}