I am sending all the files in a directory to distributed cache. So what i have done so far is
import java.net.URI;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.filecache.DistributedCache;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
public class dc_driver extends Configured implements Tool {
@SuppressWarnings("deprecation")
@Override
public int run(String[] args) throws Exception {
Configuration conf = new Configuration();
DistributedCache.createSymlink(conf);
URI archiveuri = new URI("/user/cloudera/dc_archive_input/dc.zip#dczip");
DistributedCache.addCacheArchive(archiveuri, conf);
Job job = new Job(conf);
job.setJobName(this.getClass().getName());
job.setJarByClass(dc_driver.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
job.setMapperClass(dc_mapper.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
job.setNumReduceTasks(0);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
return job.waitForCompletion(true) ? 0 : 1;
}
public static void main(String[] args) throws Exception {
int res = ToolRunner.run(new Configuration(), new dc_driver(), args);
System.exit(res);
}
}
import java.io.BufferedReader;
import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.filecache.DistributedCache;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Mapper.Context;
import org.apache.hadoop.util.StringUtils;
public class dc_mapper extends Mapper<LongWritable, Text, Text,Text> {
String s1;
public void setup(Context context) throws IOException,InterruptedException {
Configuration conf = context.getConfiguration();
URL resource = conf.getResource("dczip");
s1 = resource.toString();
}
public void map(LongWritable key, Text value,Context context)
throws IOException, InterruptedException {
String line = value.toString();
context.write(new Text(s1), new Text(line));
}
}
I got the output as
file:/mapred/local/taskTracker/cloudera/jobcache/job_201402240544_0011/attempt_201402240544_0011_m_000000_0/work/dczip 10,pooja,bnglr file:/mapred/local/taskTracker/cloudera/jobcache/job_201402240544_0011/attempt_201402240544_0011_m_000000_0/work/dczip 40,rahul,hyb
How to read the contents to the file inside dc.zip
