Skip to main content

Posts

Showing posts with the label Map-Reduce

Hadoop Simple Indexer source code with Map reduce

/*  * To change this template, choose Tools | Templates  * and open the template in the editor.  */ package lineindexer; /**  *  * @author masteruser  */ import java.io.IOException; import java.util.ArrayList; import java.util.Iterator; import java.util.List; import java.util.StringTokenizer; 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.LongWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapred.FileInputFormat; import org.apache.hadoop.mapred.FileOutputFormat; import org.apache.hadoop.mapred.FileSplit; import org.apache.hadoop.mapred.JobClient; import org.apache.hadoop.mapred.JobConf; import org.apache.hadoop.mapred.MapReduceBase; import org.apache.hadoop.mapred.Mapper; import org.apache.hadoop.mapred.OutputCollector; import org.apache.hadoop.mapred.Reducer; import org.apache.had...