Untitled

mail@pastecode.io avatar
unknown
plain_text
a year ago
2.1 kB
3
Indexable
Never
import java.io.IOException;
import java.util.StringTokenizer;
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.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class ItemCountMapReduce {

  public static class ItemCountMapper extends Mapper<Object, Text, Text, IntWritable> {

    private final static IntWritable one = new IntWritable(1);
    private Text item = new Text();

    public void map(Object key, Text value, Context context)
        throws IOException, InterruptedException {
      StringTokenizer tokenizer = new StringTokenizer(value.toString());
      while (tokenizer.hasMoreTokens()) {
        item.set(tokenizer.nextToken());
        context.write(item, one);
      }
    }
  }

  public static class ItemCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {

    private IntWritable result = new IntWritable();

    public void reduce(Text key, Iterable<IntWritable> values, Context context)
        throws IOException, InterruptedException {
      int sum = 0;
      for (IntWritable val : values) {
        sum += val.get();
      }
      result.set(sum);
      context.write(key, result);
    }
  }

  public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    Job job = Job.getInstance(conf, "Item Count");
    job.setJarByClass(ItemCountMapReduce.class);
    job.setMapperClass(ItemCountMapper.class);
    job.setCombinerClass(ItemCountReducer.class);
    job.setReducerClass(ItemCountReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}