org.apache.carbondata.hadoop

Class CarbonInputSplit

java.lang.Object

org.apache.hadoop.mapreduce.InputSplit

org.apache.hadoop.mapreduce.lib.input.FileSplit

org.apache.carbondata.hadoop.CarbonInputSplit

All Implemented Interfaces:

Serializable, Comparable<org.apache.carbondata.core.datastore.block.Distributable>, org.apache.carbondata.core.datastore.block.Distributable, Block, org.apache.hadoop.io.Writable

public class CarbonInputSplit
extends org.apache.hadoop.mapreduce.lib.input.FileSplit
implements org.apache.carbondata.core.datastore.block.Distributable, Serializable, org.apache.hadoop.io.Writable, Block

Carbon input split to allow distributed read of CarbonTableInputFormat.

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
String	taskId

Constructor Summary

Constructors

Constructor and Description
CarbonInputSplit()
CarbonInputSplit(String segmentId, org.apache.hadoop.fs.Path path, long start, long length, String[] locations, org.apache.carbondata.core.statusmanager.FileFormat fileFormat)
CarbonInputSplit(String segmentId, org.apache.hadoop.fs.Path path, long start, long length, String[] locations, String[] inMemoryHosts, org.apache.carbondata.core.statusmanager.FileFormat fileFormat)
CarbonInputSplit(String segmentId, String blockletId, org.apache.hadoop.fs.Path path, long start, long length, String[] locations, int numberOfBlocklets, org.apache.carbondata.core.metadata.ColumnarFormatVersion version, Map<String,String> blockStorageIdMap, String[] deleteDeltaFiles) Constructor to initialize the CarbonInputSplit with blockStorageIdMap
CarbonInputSplit(String segmentId, String blockletId, org.apache.hadoop.fs.Path path, long start, long length, String[] locations, int numberOfBlocklets, org.apache.carbondata.core.metadata.ColumnarFormatVersion version, String[] deleteDeltaFiles)

Method Summary

Modifier and Type	Method and Description
int	compareTo(org.apache.carbondata.core.datastore.block.Distributable o)
static List<org.apache.carbondata.core.datastore.block.TableBlockInfo>	createBlocks(List<CarbonInputSplit> splitList)
boolean	equals(Object obj)
static CarbonInputSplit	from(String segmentId, String blockletId, org.apache.hadoop.mapreduce.lib.input.FileSplit split, org.apache.carbondata.core.metadata.ColumnarFormatVersion version, String dataMapWritePath)
boolean	fullScan()
String	getBlockletId()
String	getBlockPath()
Map<String,String>	getBlockStorageIdMap() returns map of blocklocation and storage id
String	getBucketId()
String[]	getDeleteDeltaFiles()
org.apache.carbondata.core.indexstore.BlockletDetailInfo	getDetailInfo()
org.apache.carbondata.core.statusmanager.FileFormat	getFileFormat()
List<String>	getInvalidSegments()
List<org.apache.carbondata.core.mutate.UpdateVO>	getInvalidTimestampRange()
List<Long>	getMatchedBlocklets() return all matched blocklets for scanning
int	getNumberOfBlocklets() returns the number of blocklets
org.apache.carbondata.core.datamap.Segment	getSegment()
String	getSegmentId()
static org.apache.carbondata.core.datastore.block.TableBlockInfo	getTableBlockInfo(CarbonInputSplit inputSplit)
org.apache.carbondata.core.metadata.ColumnarFormatVersion	getVersion()
int	hashCode()
org.apache.carbondata.core.indexstore.Blocklet	makeBlocklet()
void	readFields(DataInput in)
void	setDeleteDeltaFiles(String[] deleteDeltaFiles)
void	setDetailInfo(org.apache.carbondata.core.indexstore.BlockletDetailInfo detailInfo)
void	setFormat(org.apache.carbondata.core.statusmanager.FileFormat fileFormat)
void	setInvalidSegments(List<org.apache.carbondata.core.datamap.Segment> invalidSegments)
void	setInvalidTimestampRange(List<org.apache.carbondata.core.mutate.UpdateVO> invalidTimestamps)
void	setVersion(org.apache.carbondata.core.metadata.ColumnarFormatVersion version)
void	write(DataOutput out)

Methods inherited from class org.apache.hadoop.mapreduce.lib.input.FileSplit

getLength, getLocationInfo, getLocations, getPath, getStart, toString

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Methods inherited from interface org.apache.carbondata.core.datastore.block.Distributable

getLocations

Field Detail

taskId

public String taskId

Constructor Detail

CarbonInputSplit

public CarbonInputSplit()

CarbonInputSplit

public CarbonInputSplit(String segmentId,
                        String blockletId,
                        org.apache.hadoop.fs.Path path,
                        long start,
                        long length,
                        String[] locations,
                        int numberOfBlocklets,
                        org.apache.carbondata.core.metadata.ColumnarFormatVersion version,
                        String[] deleteDeltaFiles)

CarbonInputSplit

public CarbonInputSplit(String segmentId,
                        org.apache.hadoop.fs.Path path,
                        long start,
                        long length,
                        String[] locations,
                        org.apache.carbondata.core.statusmanager.FileFormat fileFormat)

CarbonInputSplit

public CarbonInputSplit(String segmentId,
                        org.apache.hadoop.fs.Path path,
                        long start,
                        long length,
                        String[] locations,
                        String[] inMemoryHosts,
                        org.apache.carbondata.core.statusmanager.FileFormat fileFormat)

CarbonInputSplit

public CarbonInputSplit(String segmentId,
                        String blockletId,
                        org.apache.hadoop.fs.Path path,
                        long start,
                        long length,
                        String[] locations,
                        int numberOfBlocklets,
                        org.apache.carbondata.core.metadata.ColumnarFormatVersion version,
                        Map<String,String> blockStorageIdMap,
                        String[] deleteDeltaFiles)

Constructor to initialize the CarbonInputSplit with blockStorageIdMap

Parameters:

segmentId -

path -

start -

length -

locations -

numberOfBlocklets -

version -

blockStorageIdMap -

Method Detail

from

public static CarbonInputSplit from(String segmentId,
                                    String blockletId,
                                    org.apache.hadoop.mapreduce.lib.input.FileSplit split,
                                    org.apache.carbondata.core.metadata.ColumnarFormatVersion version,
                                    String dataMapWritePath)
                             throws IOException

Throws:

IOException

createBlocks

public static List<org.apache.carbondata.core.datastore.block.TableBlockInfo> createBlocks(List<CarbonInputSplit> splitList)

getTableBlockInfo

public static org.apache.carbondata.core.datastore.block.TableBlockInfo getTableBlockInfo(CarbonInputSplit inputSplit)

getSegmentId

public String getSegmentId()

getSegment

public org.apache.carbondata.core.datamap.Segment getSegment()

readFields

public void readFields(DataInput in)
                throws IOException

Specified by:

readFields in interface org.apache.hadoop.io.Writable

Overrides:

readFields in class org.apache.hadoop.mapreduce.lib.input.FileSplit

Throws:

IOException

write

public void write(DataOutput out)
           throws IOException

Specified by:

write in interface org.apache.hadoop.io.Writable

Overrides:

write in class org.apache.hadoop.mapreduce.lib.input.FileSplit

Throws:

IOException

getInvalidSegments

public List<String> getInvalidSegments()

setInvalidSegments

public void setInvalidSegments(List<org.apache.carbondata.core.datamap.Segment> invalidSegments)

setInvalidTimestampRange

public void setInvalidTimestampRange(List<org.apache.carbondata.core.mutate.UpdateVO> invalidTimestamps)

getInvalidTimestampRange

public List<org.apache.carbondata.core.mutate.UpdateVO> getInvalidTimestampRange()

getNumberOfBlocklets

public int getNumberOfBlocklets()

returns the number of blocklets

Returns:

getVersion

public org.apache.carbondata.core.metadata.ColumnarFormatVersion getVersion()

setVersion

public void setVersion(org.apache.carbondata.core.metadata.ColumnarFormatVersion version)

getBucketId

public String getBucketId()

getBlockletId

public String getBlockletId()

compareTo

public int compareTo(org.apache.carbondata.core.datastore.block.Distributable o)

Specified by:

compareTo in interface Comparable<org.apache.carbondata.core.datastore.block.Distributable>

equals

public boolean equals(Object obj)

Overrides:

equals in class Object

hashCode

public int hashCode()

Overrides:

hashCode in class Object

getBlockPath

public String getBlockPath()

Specified by:

getBlockPath in interface Block

Returns:

the path of this block

getMatchedBlocklets

public List<Long> getMatchedBlocklets()

Description copied from interface: Block

return all matched blocklets for scanning

Specified by:

getMatchedBlocklets in interface Block

Returns:

list of blocklet offset in the block

fullScan

public boolean fullScan()

Specified by:

fullScan in interface Block

Returns:

true if need to do full scan of this block

getBlockStorageIdMap

public Map<String,String> getBlockStorageIdMap()

returns map of blocklocation and storage id

Returns:

getDeleteDeltaFiles

public String[] getDeleteDeltaFiles()

setDeleteDeltaFiles

public void setDeleteDeltaFiles(String[] deleteDeltaFiles)

getDetailInfo

public org.apache.carbondata.core.indexstore.BlockletDetailInfo getDetailInfo()

setDetailInfo

public void setDetailInfo(org.apache.carbondata.core.indexstore.BlockletDetailInfo detailInfo)

getFileFormat

public org.apache.carbondata.core.statusmanager.FileFormat getFileFormat()

setFormat

public void setFormat(org.apache.carbondata.core.statusmanager.FileFormat fileFormat)

makeBlocklet

public org.apache.carbondata.core.indexstore.Blocklet makeBlocklet()