不使用JobConf运行Hadoop作业

我找不到提交不使用已弃用JobConf类的Hadoop作业的单个示例. JobClient,尚未弃用,仍然只支持带JobConf参数的方法.

有人可以指点我的Java代码提交Hadoop地图/减少作业只使用Configuration类(非JobConf),并使用mapreduce.lib.input包而不是mapred.input？

希望这有用

import java.io.File;

import org.apache.commons.io.FileUtils;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class MapReduceExample extends Configured implements Tool {

    static class MyMapper extends Mapper {
        public MyMapper(){

        }

        protected void map(
                LongWritable key,
                Text value,
                org.apache.hadoop.mapreduce.Mapper.Context context)
                throws java.io.IOException, InterruptedException {
            context.getCounter("mygroup", "jeff").increment(1);
            context.write(key, value);
        };
    }

    @Override
    public int run(String[] args) throws Exception {
        Job job = new Job();
        job.setMapperClass(MyMapper.class);
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        job.waitForCompletion(true);
        return 0;
    }

    public static void main(String[] args) throws Exception {
        FileUtils.deleteDirectory(new File("data/output"));
        args = new String[] { "data/input", "data/output" };
        ToolRunner.run(new MapReduceExample(), args);
    }
}

我相信本教程说明了使用Hadoop 0.20.1删除已弃用的JobConf类.