org.apache.cassandra.hadoop.pig
Class CassandraStorage

java.lang.Object
  org.apache.pig.LoadFunc
      org.apache.cassandra.hadoop.pig.CassandraStorage

All Implemented Interfaces:

org.apache.pig.LoadMetadata, org.apache.pig.StoreFuncInterface

public class CassandraStorage
extends org.apache.pig.LoadFunc
implements org.apache.pig.StoreFuncInterface, org.apache.pig.LoadMetadata

A LoadStoreFunc for retrieving data from and storing data to Cassandra A row from a standard CF will be returned as nested tuples: (key, ((name1, val1), (name2, val2))).

Field Summary

static java.lang.String	PIG_ALLOW_DELETES
static java.lang.String	PIG_INITIAL_ADDRESS
static java.lang.String	PIG_INPUT_FORMAT
static java.lang.String	PIG_INPUT_INITIAL_ADDRESS
static java.lang.String	PIG_INPUT_PARTITIONER
static java.lang.String	PIG_INPUT_RPC_PORT
static java.lang.String	PIG_OUTPUT_FORMAT
static java.lang.String	PIG_OUTPUT_INITIAL_ADDRESS
static java.lang.String	PIG_OUTPUT_PARTITIONER
static java.lang.String	PIG_OUTPUT_RPC_PORT
static java.lang.String	PIG_PARTITIONER
static java.lang.String	PIG_RPC_PORT
static java.lang.String	PIG_USE_SECONDARY
static java.lang.String	PIG_WIDEROW_INPUT

Constructor Summary

CassandraStorage()

CassandraStorage(int limit)

Method Summary

void	checkSchema(org.apache.pig.ResourceSchema schema)
void	cleanupOnFailure(java.lang.String failure, org.apache.hadoop.mapreduce.Job job)
org.apache.hadoop.mapreduce.InputFormat	getInputFormat()
int	getLimit()
org.apache.pig.data.Tuple	getNext()
org.apache.pig.data.Tuple	getNextWide()
org.apache.hadoop.mapreduce.OutputFormat	getOutputFormat()
java.lang.String[]	getPartitionKeys(java.lang.String location, org.apache.hadoop.mapreduce.Job job)
static java.util.Map<java.lang.String,java.lang.String>	getQueryMap(java.lang.String query)
org.apache.pig.ResourceSchema	getSchema(java.lang.String location, org.apache.hadoop.mapreduce.Job job)
org.apache.pig.ResourceStatistics	getStatistics(java.lang.String location, org.apache.hadoop.mapreduce.Job job)
void	prepareToRead(org.apache.hadoop.mapreduce.RecordReader reader, org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigSplit split)
void	prepareToWrite(org.apache.hadoop.mapreduce.RecordWriter writer)
void	putNext(org.apache.pig.data.Tuple t)
java.lang.String	relativeToAbsolutePath(java.lang.String location, org.apache.hadoop.fs.Path curDir)
java.lang.String	relToAbsPathForStoreLocation(java.lang.String location, org.apache.hadoop.fs.Path curDir)
void	setLocation(java.lang.String location, org.apache.hadoop.mapreduce.Job job)
void	setPartitionFilter(org.apache.pig.Expression partitionFilter)
void	setStoreFuncUDFContextSignature(java.lang.String signature)
void	setStoreLocation(java.lang.String location, org.apache.hadoop.mapreduce.Job job)
void	setUDFContextSignature(java.lang.String signature)

Methods inherited from class org.apache.pig.LoadFunc

getAbsolutePath, getLoadCaster, getPathStrings, join, warn

Methods inherited from class java.lang.Object

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

Field Detail

PIG_INPUT_RPC_PORT

public static final java.lang.String PIG_INPUT_RPC_PORT

See Also:

Constant Field Values

PIG_INPUT_INITIAL_ADDRESS

public static final java.lang.String PIG_INPUT_INITIAL_ADDRESS

See Also:

Constant Field Values

PIG_INPUT_PARTITIONER

public static final java.lang.String PIG_INPUT_PARTITIONER

See Also:

Constant Field Values

PIG_OUTPUT_RPC_PORT

public static final java.lang.String PIG_OUTPUT_RPC_PORT

See Also:

Constant Field Values

PIG_OUTPUT_INITIAL_ADDRESS

public static final java.lang.String PIG_OUTPUT_INITIAL_ADDRESS

See Also:

Constant Field Values

PIG_OUTPUT_PARTITIONER

public static final java.lang.String PIG_OUTPUT_PARTITIONER

See Also:

Constant Field Values

PIG_RPC_PORT

public static final java.lang.String PIG_RPC_PORT

See Also:

Constant Field Values

PIG_INITIAL_ADDRESS

public static final java.lang.String PIG_INITIAL_ADDRESS

See Also:

Constant Field Values

PIG_PARTITIONER

public static final java.lang.String PIG_PARTITIONER

See Also:

Constant Field Values

PIG_INPUT_FORMAT

public static final java.lang.String PIG_INPUT_FORMAT

See Also:

Constant Field Values

PIG_OUTPUT_FORMAT

public static final java.lang.String PIG_OUTPUT_FORMAT

See Also:

Constant Field Values

PIG_ALLOW_DELETES

public static final java.lang.String PIG_ALLOW_DELETES

See Also:

Constant Field Values

PIG_WIDEROW_INPUT

public static final java.lang.String PIG_WIDEROW_INPUT

See Also:

Constant Field Values

PIG_USE_SECONDARY

public static final java.lang.String PIG_USE_SECONDARY

See Also:

Constant Field Values

Constructor Detail

CassandraStorage

public CassandraStorage()

CassandraStorage

public CassandraStorage(int limit)

Parameters:

limit - number of columns to fetch in a slice

Method Detail

getLimit

public int getLimit()

getNextWide

public org.apache.pig.data.Tuple getNextWide()
                                      throws java.io.IOException

Throws:

java.io.IOException

getNext

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

Specified by:

getNext in class org.apache.pig.LoadFunc

Throws:

java.io.IOException

getInputFormat

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

Specified by:

getInputFormat in class org.apache.pig.LoadFunc

prepareToRead

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

Specified by:

prepareToRead in class org.apache.pig.LoadFunc

getQueryMap

public static java.util.Map<java.lang.String,java.lang.String> getQueryMap(java.lang.String query)

setLocation

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

Specified by:

setLocation in class org.apache.pig.LoadFunc

Throws:

java.io.IOException

getSchema

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

Specified by:

getSchema in interface org.apache.pig.LoadMetadata

Throws:

java.io.IOException

getStatistics

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

Specified by:

getStatistics in interface org.apache.pig.LoadMetadata

getPartitionKeys

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

Specified by:

getPartitionKeys in interface org.apache.pig.LoadMetadata

setPartitionFilter

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

Specified by:

setPartitionFilter in interface org.apache.pig.LoadMetadata

relativeToAbsolutePath

public java.lang.String relativeToAbsolutePath(java.lang.String location,
                                               org.apache.hadoop.fs.Path curDir)
                                        throws java.io.IOException

Overrides:

relativeToAbsolutePath in class org.apache.pig.LoadFunc

Throws:

java.io.IOException

setUDFContextSignature

public void setUDFContextSignature(java.lang.String signature)

Overrides:

setUDFContextSignature in class org.apache.pig.LoadFunc

setStoreFuncUDFContextSignature

public void setStoreFuncUDFContextSignature(java.lang.String signature)

Specified by:

setStoreFuncUDFContextSignature in interface org.apache.pig.StoreFuncInterface

relToAbsPathForStoreLocation

public java.lang.String relToAbsPathForStoreLocation(java.lang.String location,
                                                     org.apache.hadoop.fs.Path curDir)
                                              throws java.io.IOException

Specified by:

relToAbsPathForStoreLocation in interface org.apache.pig.StoreFuncInterface

Throws:

java.io.IOException

setStoreLocation

public void setStoreLocation(java.lang.String location,
                             org.apache.hadoop.mapreduce.Job job)
                      throws java.io.IOException

Specified by:

setStoreLocation in interface org.apache.pig.StoreFuncInterface

Throws:

java.io.IOException

getOutputFormat

public org.apache.hadoop.mapreduce.OutputFormat getOutputFormat()

Specified by:

getOutputFormat in interface org.apache.pig.StoreFuncInterface

checkSchema

public void checkSchema(org.apache.pig.ResourceSchema schema)
                 throws java.io.IOException

Specified by:

checkSchema in interface org.apache.pig.StoreFuncInterface

Throws:

java.io.IOException

prepareToWrite

public void prepareToWrite(org.apache.hadoop.mapreduce.RecordWriter writer)

Specified by:

prepareToWrite in interface org.apache.pig.StoreFuncInterface

putNext

public void putNext(org.apache.pig.data.Tuple t)
             throws java.io.IOException

Specified by:

putNext in interface org.apache.pig.StoreFuncInterface

Throws:

java.io.IOException

cleanupOnFailure

public void cleanupOnFailure(java.lang.String failure,
                             org.apache.hadoop.mapreduce.Job job)

Specified by:

cleanupOnFailure in interface org.apache.pig.StoreFuncInterface