org.hedera.pig.load

Class WikiRevisionFullTextFilter

java.lang.Object

org.apache.pig.LoadFunc

org.hedera.pig.load.WikiRevisionFullTextFilter

All Implemented Interfaces:

org.apache.pig.LoadMetadata

public class WikiRevisionFullTextFilter
extends org.apache.pig.LoadFunc
implements org.apache.pig.LoadMetadata

A Pig UDF loader that filters wiki revision text by keywords

Author:

tuan

Field Summary

Fields

Modifier and Type	Field and Description
protected org.apache.pig.data.BagFactory	bags
protected org.apache.pig.ResourceSchema	schema
protected org.apache.pig.data.TupleFactory	tuples

Constructor Summary

Constructors

Constructor and Description
WikiRevisionFullTextFilter(String optString)

Method Summary

Methods

Modifier and Type	Method and Description
org.apache.hadoop.mapreduce.InputFormat	getInputFormat()
org.apache.pig.data.Tuple	getNext()
String[]	getPartitionKeys(String loc, org.apache.hadoop.mapreduce.Job job)
org.apache.pig.ResourceSchema	getSchema(String arg0, org.apache.hadoop.mapreduce.Job arg1)
org.apache.pig.ResourceStatistics	getStatistics(String arg0, org.apache.hadoop.mapreduce.Job arg1)
void	prepareToRead(org.apache.hadoop.mapreduce.RecordReader reader, org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigSplit split)
void	setLocation(String loc, org.apache.hadoop.mapreduce.Job job)
void	setPartitionFilter(org.apache.pig.Expression arg0)

Methods inherited from class org.apache.pig.LoadFunc

getAbsolutePath, getLoadCaster, getPathStrings, join, relativeToAbsolutePath, setUDFContextSignature, warn

Methods inherited from class java.lang.Object

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

Field Detail

schema

protected volatile org.apache.pig.ResourceSchema schema

tuples

protected org.apache.pig.data.TupleFactory tuples

bags

protected org.apache.pig.data.BagFactory bags

Constructor Detail

WikiRevisionFullTextFilter

public WikiRevisionFullTextFilter(String optString)

Method Detail

setLocation

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

Specified by:

setLocation in class org.apache.pig.LoadFunc

Throws:

IOException

getPartitionKeys

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

Specified by:

getPartitionKeys in interface org.apache.pig.LoadMetadata

Throws:

IOException

getSchema

public org.apache.pig.ResourceSchema getSchema(String arg0,
                                      org.apache.hadoop.mapreduce.Job arg1)
                                        throws IOException

Specified by:

getSchema in interface org.apache.pig.LoadMetadata

Throws:

IOException

getStatistics

public org.apache.pig.ResourceStatistics getStatistics(String arg0,
                                              org.apache.hadoop.mapreduce.Job arg1)
                                                throws IOException

Specified by:

getStatistics in interface org.apache.pig.LoadMetadata

Throws:

IOException

setPartitionFilter

public void setPartitionFilter(org.apache.pig.Expression arg0)
                        throws IOException

Specified by:

setPartitionFilter in interface org.apache.pig.LoadMetadata

Throws:

IOException

getInputFormat

public org.apache.hadoop.mapreduce.InputFormat getInputFormat()
                                                       throws IOException

Specified by:

getInputFormat in class org.apache.pig.LoadFunc

Throws:

IOException

prepareToRead

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

Specified by:

prepareToRead in class org.apache.pig.LoadFunc

Throws:

IOException

getNext

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

Specified by:

getNext in class org.apache.pig.LoadFunc

Throws:

IOException