nl.basjes.pig.input.apachehttpdlog

Class Loader

java.lang.Object

org.apache.pig.LoadFunc

nl.basjes.pig.input.apachehttpdlog.Loader

All Implemented Interfaces:

org.apache.pig.LoadMetadata, org.apache.pig.LoadPushDown

public class Loader
extends org.apache.pig.LoadFunc
implements org.apache.pig.LoadMetadata, org.apache.pig.LoadPushDown

Nested Class Summary

Nested classes/interfaces inherited from interface org.apache.pig.LoadPushDown

org.apache.pig.LoadPushDown.OperatorSet, org.apache.pig.LoadPushDown.RequiredField, org.apache.pig.LoadPushDown.RequiredFieldList, org.apache.pig.LoadPushDown.RequiredFieldResponse

Constructor Summary

Constructors

Constructor and Description
Loader(String... parameters) Pig Loaders only take string parameters.

Method Summary

Modifier and Type	Method and Description
List<nl.basjes.parse.core.Dissector>	getAdditionalDissectors()
List<org.apache.pig.LoadPushDown.OperatorSet>	getFeatures()
org.apache.hadoop.mapreduce.InputFormat<?,?>	getInputFormat()
String	getLogformat()
org.apache.pig.data.Tuple	getNext()
String[]	getPartitionKeys(String location, org.apache.hadoop.mapreduce.Job job)
List<String>	getRequestedFields()
org.apache.pig.ResourceSchema	getSchema(String location, org.apache.hadoop.mapreduce.Job job)
org.apache.pig.ResourceStatistics	getStatistics(String location, org.apache.hadoop.mapreduce.Job job)
Map<String,Set<String>>	getTypeRemappings()
void	prepareToRead(org.apache.hadoop.mapreduce.RecordReader newReader, org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigSplit pigSplit)
org.apache.pig.LoadPushDown.RequiredFieldResponse	pushProjection(org.apache.pig.LoadPushDown.RequiredFieldList pRequiredFieldList)
void	setLocation(String location, org.apache.hadoop.mapreduce.Job job)
void	setPartitionFilter(org.apache.pig.Expression partitionFilter)
void	setUDFContextSignature(String signature)

Methods inherited from class org.apache.pig.LoadFunc

getAbsolutePath, getLoadCaster, getPathStrings, join, relativeToAbsolutePath, warn

Methods inherited from class java.lang.Object

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

Constructor Detail

Loader

public Loader(String... parameters)

Pig Loaders only take string parameters. The CTOR is really the only interaction the user has with the Loader from the script.

Parameters:

parameters - specified from the call within the pig code

Method Detail

getInputFormat

public org.apache.hadoop.mapreduce.InputFormat<?,?> getInputFormat()
                                                            throws IOException

Specified by:

getInputFormat in class org.apache.pig.LoadFunc

Throws:

IOException

getLogformat

public final String getLogformat()

getRequestedFields

public final List<String> getRequestedFields()

getNext

public org.apache.pig.data.Tuple getNext()
                                  throws IOException

Specified by:

getNext in class org.apache.pig.LoadFunc

Throws:

IOException

prepareToRead

public void prepareToRead(org.apache.hadoop.mapreduce.RecordReader newReader,
                          org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigSplit pigSplit)
                   throws IOException

Specified by:

prepareToRead in class org.apache.pig.LoadFunc

Throws:

IOException

setLocation

public void setLocation(String location,
                        org.apache.hadoop.mapreduce.Job job)
                 throws IOException

Specified by:

setLocation in class org.apache.pig.LoadFunc

Throws:

IOException

getSchema

public org.apache.pig.ResourceSchema getSchema(String location,
                                               org.apache.hadoop.mapreduce.Job job)
                                        throws IOException

Specified by:

getSchema in interface org.apache.pig.LoadMetadata

Throws:

IOException

getStatistics

public org.apache.pig.ResourceStatistics getStatistics(String location,
                                                       org.apache.hadoop.mapreduce.Job job)
                                                throws IOException

Specified by:

getStatistics in interface org.apache.pig.LoadMetadata

Throws:

IOException

getPartitionKeys

public String[] getPartitionKeys(String location,
                                 org.apache.hadoop.mapreduce.Job job)
                          throws IOException

Specified by:

getPartitionKeys in interface org.apache.pig.LoadMetadata

Throws:

IOException

setPartitionFilter

public void setPartitionFilter(org.apache.pig.Expression partitionFilter)
                        throws IOException

Specified by:

setPartitionFilter in interface org.apache.pig.LoadMetadata

Throws:

IOException

getTypeRemappings

public final Map<String,Set<String>> getTypeRemappings()

getAdditionalDissectors

public List<nl.basjes.parse.core.Dissector> getAdditionalDissectors()

getFeatures

public List<org.apache.pig.LoadPushDown.OperatorSet> getFeatures()

Specified by:

getFeatures in interface org.apache.pig.LoadPushDown

pushProjection

public org.apache.pig.LoadPushDown.RequiredFieldResponse pushProjection(org.apache.pig.LoadPushDown.RequiredFieldList pRequiredFieldList)
                                                                 throws org.apache.pig.impl.logicalLayer.FrontendException

Specified by:

pushProjection in interface org.apache.pig.LoadPushDown

Throws:

org.apache.pig.impl.logicalLayer.FrontendException

setUDFContextSignature

public void setUDFContextSignature(String signature)

Overrides:

setUDFContextSignature in class org.apache.pig.LoadFunc