JAVA程序实现mapreduce的wordcount
程序代码：
package hdfs.files;
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.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
public class WordCountDriver {
public static class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String line = value.toString();
String[] words=line.split(" ");
for(String w:words) {
context.write(new Text(w), new IntWritable(1));
}
}
}
public static class WordCountReducer extends Reducer <Text, IntWritable, Text, IntWritable>{
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));
}
}
public static void main(String[] args) throws IllegalArgumentException, IOException, ClassNotFoundException, InterruptedException {
System.setProperty("HADOOP_USER_NAME", "root");
Configuration conf=new Configuration();
Job job=Job.getInstance(conf);
job.setJarByClass(WordCountDriver.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("/usr/local/hdfs/input/cc.txt"));
FileOutputFormat.setOutputPath(job, new Path("/usr/local/hdfs/output"));
Boolean rs=job.waitForCompletion(true);
System.exit(rs?0:1);
}
}
