org.apache.mahout.text

Class SequenceFilesFromMailArchivesMapper

java.lang.Object

org.apache.hadoop.mapreduce.Mapper<org.apache.hadoop.io.IntWritable,org.apache.hadoop.io.BytesWritable,org.apache.hadoop.io.Text,org.apache.hadoop.io.Text>

org.apache.mahout.text.SequenceFilesFromMailArchivesMapper

public class SequenceFilesFromMailArchivesMapper
extends org.apache.hadoop.mapreduce.Mapper<org.apache.hadoop.io.IntWritable,org.apache.hadoop.io.BytesWritable,org.apache.hadoop.io.Text,org.apache.hadoop.io.Text>

Map Class for the SequenceFilesFromMailArchives job

Nested Class Summary

Nested classes/interfaces inherited from class org.apache.hadoop.mapreduce.Mapper

org.apache.hadoop.mapreduce.Mapper.Context

Constructor Summary

Constructors

Constructor and Description
SequenceFilesFromMailArchivesMapper()

Method Summary

Methods

Modifier and Type	Method and Description
protected static String	generateKey(String mboxFilename, String prefix, String messageId)
void	map(org.apache.hadoop.io.IntWritable key, org.apache.hadoop.io.BytesWritable value, org.apache.hadoop.mapreduce.Mapper.Context context)
long	parseMailboxLineByLine(String filename, InputStream mailBoxInputStream, org.apache.hadoop.mapreduce.Mapper.Context context)
void	setup(org.apache.hadoop.mapreduce.Mapper.Context context)

Methods inherited from class org.apache.hadoop.mapreduce.Mapper

cleanup, run

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

SequenceFilesFromMailArchivesMapper

public SequenceFilesFromMailArchivesMapper()

Method Detail

setup

public void setup(org.apache.hadoop.mapreduce.Mapper.Context context)
           throws IOException,
                  InterruptedException

Overrides:

setup in class org.apache.hadoop.mapreduce.Mapper<org.apache.hadoop.io.IntWritable,org.apache.hadoop.io.BytesWritable,org.apache.hadoop.io.Text,org.apache.hadoop.io.Text>

Throws:

IOException

InterruptedException

parseMailboxLineByLine

public long parseMailboxLineByLine(String filename,
                          InputStream mailBoxInputStream,
                          org.apache.hadoop.mapreduce.Mapper.Context context)
                            throws IOException,
                                   InterruptedException

Throws:

IOException

InterruptedException

generateKey

protected static String generateKey(String mboxFilename,
                 String prefix,
                 String messageId)

map

public void map(org.apache.hadoop.io.IntWritable key,
       org.apache.hadoop.io.BytesWritable value,
       org.apache.hadoop.mapreduce.Mapper.Context context)
         throws IOException,
                InterruptedException

Overrides:

map in class org.apache.hadoop.mapreduce.Mapper<org.apache.hadoop.io.IntWritable,org.apache.hadoop.io.BytesWritable,org.apache.hadoop.io.Text,org.apache.hadoop.io.Text>

Throws:

IOException

InterruptedException