CalcPackageDictMR.java

package mobvista.dmp.datasource.age.mapreduce;

import mobvista.dmp.util.MRUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

import java.io.IOException;

/**
 * Created by liushaui on 2017/2/17 0017.
 */
public class CalcPackageDictMR {
    public static void main(String[] args) throws ClassNotFoundException, IOException, InterruptedException {

        Configuration conf = new Configuration();
        conf.set("mapreduce.map.speculative", "true");
        conf.set("mapreduce.reduce.speculative", "true");
        conf.set("mapreduce.task.io.sort.mb", "500");
        conf.set("mapreduce.reduce.java.opts", "-Xmx1536m");
        conf.set("mapreduce.reduce.memory.mb", "2048");
        conf.set("mapreduce.reduce.shuffle.parallelcopies", "50");
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

        conf.set("low", otherArgs[2]);
        conf.set("high", otherArgs[3]);
        conf.set("unbelievable", otherArgs[4]);

        Job job = Job.getInstance(conf, "CalcPackageDictMR");
        job.setJarByClass(CalcPackageDictMR.class);
        job.setMapperClass(CalcPackageDictMapper.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);

        FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

        System.exit(job.waitForCompletion(true) ? 0 : 1);

    }

    public static class CalcPackageDictMapper extends Mapper<LongWritable, Text, Text, NullWritable> {
        Text outKey = new Text();
        int low;
        int high;
        float unbelievable;

        public void setup(Context context) throws IOException, InterruptedException {
            low = Integer.parseInt(context.getConfiguration().get("low"));
            high = Integer.parseInt(context.getConfiguration().get("high"));
            unbelievable = Float.parseFloat(context.getConfiguration().get("unbelievable"));
        }

        public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String line = value.toString();
            String[] fields = MRUtils.SPLITTER.split(line, -1);
            String tag = "";
            if (fields[4].equals("0.0") || Integer.parseInt(fields[2]) < low) {
                return;
            }
            if (Float.parseFloat(fields[3]) >= unbelievable) {
                tag = "unbelievable";
                outKey.set(MRUtils.JOINER.join(fields[0], fields[4], tag));
                context.write(outKey, NullWritable.get());
            }
            if (Integer.parseInt(fields[2]) >= high) {
                tag = "confirm";
            } else {
                tag = "calc";
            }
            outKey.set(MRUtils.JOINER.join(fields[0], fields[4], tag));
            context.write(outKey, NullWritable.get());
        }
    }
}