hadoop - 在reudcer类中使用全局变量

我需要在我的mapreduce程序中使用全局变量，如何在以下代码中进行设置并在reducer中使用全局变量。

public class tfidf
{
  public static tfidfMap..............
  {
  }
  public static tfidfReduce.............
  {
  }
  public static void main(String args[])
  {
       Configuration conf=new Configuration();
       conf.set("","");
  }

}

最佳答案

模板代码可能看起来像这样(Reducer未显示，但是相同的主体)

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Mapper.Context;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class ToolExample extends Configured implements Tool {

    @Override
    public int run(String[] args) throws Exception {
        Job job = new Job(getConf());
        Configuration conf = job.getConfiguration();

        conf.set("strProp", "value");
        conf.setInt("intProp", 123);
        conf.setBoolean("boolProp", true);

        // rest of your config here
        // ..

        return job.waitForCompletion(true) ? 0 : 1;
    }

    public static class MyMapper extends
            Mapper<LongWritable, Text, LongWritable, Text> {
        private String strProp;
        private int intProp;
        private boolean boolProp;

        @Override
        protected void setup(Context context) throws IOException,
                InterruptedException {
            Configuration conf = context.getConfiguration();

            strProp = conf.get("strProp");
            intProp = conf.getInt("intProp", -1);
            boolProp = conf.getBoolean("boolProp", false);
        }
    }

    public static void main(String args[]) throws Exception {
        System.exit(ToolRunner.run(new ToolExample(), args));
    }
}