hadoop 透過cachefile來避免資料傾斜

package hello_hadoop;
import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileReader;
import java.io.FileWriter;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.URI;
import java.net.URISyntaxException;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.filecache.DistributedCache;
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.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class GetFileName {
	//得到處理的檔名，以及將需要的檔案快取到相應的節點
	private final static  Log LOG = LogFactory.getLog(GetFileName.class);
	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException, URISyntaxException {
		LOG.info("Go into the main method ......");
		Configuration conf = new Configuration();
		Job job = Job.getInstance(conf);
		
		job.setJarByClass(GetFileName.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(Text.class);
		job.setMapperClass(GetFileNameMapper.class);
		job.setNumReduceTasks(0);
		//叢集上新增DistributedCache data134:9000namenode的描述   #thelinkofthefile改檔案的連結，下面讀取的時候需要使用
		job.addCacheFile(new URI("hdfs://data134:9000/home/tmp.txt#thelinkofthefile"));
		FileInputFormat.addInputPath(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		boolean test = job.waitForCompletion(true);
		LOG.info("End  the main method ......");
		System.exit(test?0:1);		
	}
}
class GetFileNameMapper extends Mapper<LongWritable, Text, Text, Text>{
	private final Log LOG = LogFactory.getLog(GetFileNameMapper.class);
	
	@Override
	protected void setup(Mapper<LongWritable, Text, Text, Text>.Context context)
			throws IOException, InterruptedException {
		if(context.getCacheFiles().length>0);
		URI u = context.getCacheFiles()[0];
		//這裡使用連結來訪問檔案
		BufferedReader br = new BufferedReader( new FileReader(new File("./thelinkofthefile")));
		String line = br.readLine();
		context.write(new Text(line), new Text());
		System.out.println("Here I read Line :"+line);
	}
	@Override
	protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, Text>.Context context)
			throws IOException, InterruptedException {
	}
}