org.apache.hadoop.hive.ql.io.rcfile.merge
Class MergeWork

java.lang.Object
  org.apache.hadoop.hive.ql.plan.AbstractOperatorDesc
      org.apache.hadoop.hive.ql.plan.BaseWork
          org.apache.hadoop.hive.ql.plan.MapWork
              org.apache.hadoop.hive.ql.io.rcfile.merge.MergeWork

All Implemented Interfaces:

Serializable, Cloneable, OperatorDesc

public class MergeWork
extends MapWork
implements Serializable

See Also:

Serialized Form

Field Summary

Fields inherited from class org.apache.hadoop.hive.ql.plan.MapWork

SAMPLING_ON_PREV_MR, SAMPLING_ON_START

Constructor Summary

MergeWork()

MergeWork(List<org.apache.hadoop.fs.Path> inputPaths, org.apache.hadoop.fs.Path outputDir)

MergeWork(List<org.apache.hadoop.fs.Path> inputPaths, org.apache.hadoop.fs.Path outputDir, boolean hasDynamicPartitions, DynamicPartitionCtx dynPartCtx)

Method Summary

DynamicPartitionCtx	getDynPartCtx()
String	getInputformat()
List<org.apache.hadoop.fs.Path>	getInputPaths()
ListBucketingCtx	getListBucketingCtx()
Class<? extends org.apache.hadoop.mapred.Mapper>	getMapperClass()
Long	getMinSplitSize()
org.apache.hadoop.fs.Path	getOutputDir()
boolean	hasDynamicPartitions()
boolean	isGatheringStats()
boolean	isListBucketingAlterTableConcatenate()
void	resolveConcatenateMerge(HiveConf conf) alter table ...
void	resolveDynamicPartitionStoredAsSubDirsMerge(HiveConf conf, org.apache.hadoop.fs.Path path, TableDesc tblDesc, ArrayList<String> aliases, PartitionDesc partDesc)
void	setDynPartCtx(DynamicPartitionCtx dynPartCtx)
void	setHasDynamicPartitions(boolean hasDynamicPartitions)
void	setInputPaths(List<org.apache.hadoop.fs.Path> inputPaths)
void	setListBucketingCtx(ListBucketingCtx listBucketingCtx)
void	setOutputDir(org.apache.hadoop.fs.Path outputDir)

Methods inherited from class org.apache.hadoop.hive.ql.plan.MapWork

addIndexIntermediateFile, addMapWork, configureJobConf, deriveExplainAttributes, getAliases, getAliasToPartnInfo, getAliasToWork, getAllRootOperators, getBucketedColsByDirectory, getHadoopSupportsSplittable, getIndexIntermediateFile, getJoinTree, getMapLocalWork, getMaxSplitSize, getMinSplitSizePerNode, getMinSplitSizePerRack, getNameToSplitSample, getNumMapTasks, getOpParseCtxMap, getPartitionDescs, getPaths, getPathToAliases, getPathToPartitionInfo, getSamplingType, getSamplingTypeString, getScratchColumnMap, getScratchColumnVectorTypes, getSortedColsByDirectory, getTmpHDFSPath, getTruncatedPathToAliases, getVectorMode, getVectorModeOn, getWorks, initialize, isInputFormatSorted, isMapperCannotSpanPartns, isUseBucketizedHiveInputFormat, mergeAliasedInput, mergingInto, replaceRoots, setAliasToPartnInfo, setAliasToWork, setHadoopSupportsSplittable, setInputformat, setInputFormatSorted, setJoinTree, setMapLocalWork, setMapperCannotSpanPartns, setMaxSplitSize, setMinSplitSize, setMinSplitSizePerNode, setMinSplitSizePerRack, setNameToSplitSample, setNumMapTasks, setOpParseCtxMap, setPathToAliases, setPathToPartitionInfo, setSamplingType, setScratchColumnMap, setScratchColumnVectorTypes, setTmpHDFSPath, setUseBucketizedHiveInputFormat, setVectorMode

Methods inherited from class org.apache.hadoop.hive.ql.plan.BaseWork

addDummyOp, getAllOperators, getDummyOps, getName, setDummyOps, setGatheringStats, setName

Methods inherited from class org.apache.hadoop.hive.ql.plan.AbstractOperatorDesc

clone, getOpTraits, getStatistics, setOpTraits, setStatistics

Methods inherited from class java.lang.Object

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

Constructor Detail

MergeWork

public MergeWork()

MergeWork

public MergeWork(List<org.apache.hadoop.fs.Path> inputPaths,
                 org.apache.hadoop.fs.Path outputDir)

MergeWork

public MergeWork(List<org.apache.hadoop.fs.Path> inputPaths,
                 org.apache.hadoop.fs.Path outputDir,
                 boolean hasDynamicPartitions,
                 DynamicPartitionCtx dynPartCtx)

Method Detail

getInputPaths

public List<org.apache.hadoop.fs.Path> getInputPaths()

setInputPaths

public void setInputPaths(List<org.apache.hadoop.fs.Path> inputPaths)

getOutputDir

public org.apache.hadoop.fs.Path getOutputDir()

setOutputDir

public void setOutputDir(org.apache.hadoop.fs.Path outputDir)

getMapperClass

public Class<? extends org.apache.hadoop.mapred.Mapper> getMapperClass()

getMinSplitSize

public Long getMinSplitSize()

Overrides:

getMinSplitSize in class MapWork

getInputformat

public String getInputformat()

Overrides:

getInputformat in class MapWork

isGatheringStats

public boolean isGatheringStats()

Overrides:

isGatheringStats in class BaseWork

hasDynamicPartitions

public boolean hasDynamicPartitions()

setHasDynamicPartitions

public void setHasDynamicPartitions(boolean hasDynamicPartitions)

resolveDynamicPartitionStoredAsSubDirsMerge

public void resolveDynamicPartitionStoredAsSubDirsMerge(HiveConf conf,
                                                        org.apache.hadoop.fs.Path path,
                                                        TableDesc tblDesc,
                                                        ArrayList<String> aliases,
                                                        PartitionDesc partDesc)

Overrides:

resolveDynamicPartitionStoredAsSubDirsMerge in class MapWork

resolveConcatenateMerge

public void resolveConcatenateMerge(HiveConf conf)

alter table ... concatenate If it is skewed table, use subdirectories in inputpaths.

getDynPartCtx

public DynamicPartitionCtx getDynPartCtx()

setDynPartCtx

public void setDynPartCtx(DynamicPartitionCtx dynPartCtx)

getListBucketingCtx

public ListBucketingCtx getListBucketingCtx()

Returns:

the listBucketingCtx

setListBucketingCtx

public void setListBucketingCtx(ListBucketingCtx listBucketingCtx)

Parameters:

listBucketingCtx - the listBucketingCtx to set

isListBucketingAlterTableConcatenate

public boolean isListBucketingAlterTableConcatenate()

Returns:

the isListBucketingAlterTableConcatenate