Error Using InverseMapper and IdentityReducer while Executing MapReduce - hadoop

Question

So I have a huge Access Log file and I am trying to find the Path on the Server which is hit the Most. It is a Traditional Word Count Problem to find the No. of times a path is hit.
But, as the output values are not Sorted in a MR job(only the keys are sorted) I am executing another MR job where the mapper takes the Output of Previous job as input and I use InverseMapper.java to invert the keys and values and use Identity Reducer(Reducer.java) because no aggregation is need and I just need to sort the keys(i.e., values of the first Job). Here is my Code :
package edu.pitt.cloud.CloudProject;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable.DecreasingComparator;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.KeyValueTextInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.map.InverseMapper;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
public class AccessLogMostHitPath {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
String configPath = "/usr/local/hadoop-2.7.3/etc/hadoop/";
Path inputPath = new Path(args[0]);
Path outputPath = new Path(args[1]);
Path finalOutputPath = new Path(args[2]);
Configuration config = new Configuration(true);
config.addResource(new Path(configPath+"hdfs-site.xml"));
config.addResource(new Path(configPath+"core-site.xml"));
config.addResource(new Path(configPath+"yarn-site.xml"));
config.addResource(new Path(configPath+"mapred-site.xml"));
Job job = Job.getInstance(config, "AccessLogMostHitPath");
job.setJarByClass(AccessLogMostHitPath.class);
job.setMapperClass(AccessLogMostHitPathMapper.class);
job.setReducerClass(AccessLogMostHitPathReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
config.set("mapreduce.job.running.map.limit", "2");
FileInputFormat.addInputPath(job, inputPath);
job.setInputFormatClass(TextInputFormat.class);
FileOutputFormat.setOutputPath(job, outputPath);
job.setOutputFormatClass(TextOutputFormat.class);
job.setNumReduceTasks(1);
System.out.println("Starting Job Execution ::: AccessLogMostHitPath");
int code = job.waitForCompletion(true) ? 0 : 1;
System.out.println("Job Execution Finished ::: AccessLogMostHitPath");
if(code != 0){
System.out.println("First Job Failed");
System.exit(code);
}
FileSystem hdfs = FileSystem.get(config);
Path successPath = new Path(outputPath+"/_SUCCESS");
if (hdfs.exists(successPath))
hdfs.delete(successPath, true);
Job job2 = Job.getInstance(config, "AccessLogMostHitPathSort");
job2.setJarByClass(AccessLogMostHitPath.class);
job2.setMapperClass(InverseMapper.class);
job2.setReducerClass(Reducer.class);
//config.set("mapreduce.input.keyvaluelinerecordreader.key.value.separator", "\\t");
KeyValueTextInputFormat.addInputPath(job2, outputPath);
job2.setInputFormatClass(KeyValueTextInputFormat.class);
FileOutputFormat.setOutputPath(job2, finalOutputPath);
job2.setOutputFormatClass(TextOutputFormat.class);
job2.setNumReduceTasks(1);
job2.setMapOutputKeyClass(IntWritable.class);
job2.setMapOutputValueClass(Text.class);
job2.setSortComparatorClass(DecreasingComparator.class);
job2.setOutputKeyClass(IntWritable.class);
job2.setOutputValueClass(Text.class);
config.set("mapreduce.job.running.map.limit", "2");
System.out.println("Starting Job Execution ::: AccessLogMostHitPathSort");
int code2 = job2.waitForCompletion(true) ? 0 : 1;
System.out.println("Job Execution Finished ::: AccessLogMostHitPathSort");
System.exit(code2);
}
}
I get the Below Exception When I execute this :
Error: java.io.IOException: Type mismatch in key from map: expected org.apache.hadoop.io.IntWritable, received org.apache.hadoop.io.Text
at org.apache.hadoop.mapred.MapTask$MapOutputBuffer.collect(MapTask.java:1072)
at org.apache.hadoop.mapred.MapTask$NewOutputCollector.write(MapTask.java:715)
at org.apache.hadoop.mapreduce.task.TaskInputOutputContextImpl.write(TaskInputOutputContextImpl.java:89)
at org.apache.hadoop.mapreduce.lib.map.WrappedMapper$Context.write(WrappedMapper.java:112)
at org.apache.hadoop.mapreduce.lib.map.InverseMapper.map(InverseMapper.java:36)
at org.apache.hadoop.mapreduce.Mapper.run(Mapper.java:146)
at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:787)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:341)
at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:164)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1698)
at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:158)
Where is this going wrong?. I can see that somewhere there is a mismatchin the Key or Value Type but I have crosschecked Everything. Please Help.

Answer 1

The problem is KeyValueTextInputFormat. This is text input format, it reads key as Text and value as Text. But you declared that job2 output mapper types are IntWritable and Text:
job2.setMapOutputKeyClass(IntWritable.class);
job2.setMapOutputValueClass(Text.class);
So you have to provide your own input format that will read input correctly.