Hadoop的word co-occurrence实现
package wco;import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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.conf.Configured;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
public class WCo extends Configured implements Tool {
@Override
public int run(String[] args) throws Exception {
if (args.length != 2) {
System.out.printf("Usage: hadoop jar wco.WCo\n");
return -1;
}
Job job = new Job(getConf());
job.setJarByClass(WCo.class);
job.setJobName("Word Co Occurrence");
FileInputFormat.setInputPaths(job, new Path(args));
FileOutputFormat.setOutputPath(job, new Path(args));
job.setMapperClass(WCoMapper.class);
job.setReducerClass(WCoReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
boolean success = job.waitForCompletion(true);
return success ? 0 : 1;
}
public static void main(String[] args) throws Exception {
int exitCode = ToolRunner.run(new Configuration(), new WCo(), args);
System.exit(exitCode);
}
}
页:
[1]