public class MergeFileWork extends MapWork
MapWork.MapExplainVectorization
BaseWork.BaseExplainVectorization
SAMPLING_ON_PREV_MR, SAMPLING_ON_START
llapMode, uberMode, useVectorizedInputFileFormat, vectorizationEnabled, vectorizationExamined, vectorizedRowBatchCtx, vectorizedVertexNum
memAvailable, memNeeded, opProps, opTraits, runtimeStatsTmpDir, statistics, vectorDesc, vectorMode
Constructor and Description |
---|
MergeFileWork(List<org.apache.hadoop.fs.Path> inputPaths,
org.apache.hadoop.fs.Path outputDir,
boolean hasDynamicPartitions,
String srcTblInputFormat) |
MergeFileWork(List<org.apache.hadoop.fs.Path> inputPaths,
org.apache.hadoop.fs.Path outputDir,
String srcTblInputFormat) |
addIndexIntermediateFile, addMapWork, addPathToAlias, addPathToAlias, addPathToPartitionInfo, configureJobConf, deriveExplainAttributes, deriveLlap, getAliases, getAliasToPartnInfo, getAliasToWork, getAllRootOperators, getAnyRootOperator, getBaseSrc, getBucketedColsByDirectory, getDoSplitsGrouping, getDummyTableScan, getEventSourceColumnNameMap, getEventSourceColumnTypeMap, getEventSourcePartKeyExprMap, getEventSourceTableDescMap, getExecutionMode, getIncludedBuckets, getIndexIntermediateFile, getLlapIoDesc, getMapAliases, getMapExplainVectorization, getMaxSplitSize, getMinSplitSizePerNode, getMinSplitSizePerRack, getNameToSplitSample, getNotEnabledInputFileFormatReason, getNumMapTasks, getPartitionDescs, getPaths, getPathToAliases, getPathToPartitionInfo, getSamplingType, getSamplingTypeString, getSortedColsByDirectory, getTmpHDFSPath, getTmpPathForPartitionPruning, getTruncatedPathToAliases, getUseVectorizedInputFileFormat, getVectorizationEnabledConditionsMet, getVectorizationEnabledConditionsNotMet, getVectorizationInputFileFormatClassNameSet, getVectorizedRowBatch, getWorks, initialize, internTable, isInputFormatSorted, isLeftInputJoin, isMapperCannotSpanPartns, isUseBucketizedHiveInputFormat, mergeAliasedInput, mergingInto, removePathToAlias, removePathToPartitionInfo, replaceRoots, setAliasToPartnInfo, setAliasToWork, setBaseSrc, setDoSplitsGrouping, setDummyTableScan, setEventSourceColumnNameMap, setEventSourcePartKeyExprMap, setEventSourceTableDescMap, setIncludedBuckets, setInputformat, setInputFormatSorted, setLeftInputJoin, setMapAliases, setMapperCannotSpanPartns, setMaxSplitSize, setMinSplitSize, setMinSplitSizePerNode, setMinSplitSizePerRack, setNameToSplitSample, setNotEnabledInputFileFormatReason, setNumMapTasks, setPathToAliases, setPathToPartitionInfo, setSamplingType, setTmpHDFSPath, setTmpPathForPartitionPruning, setUseBucketizedHiveInputFormat, setUseVectorizedInputFileFormat, setVectorizationEnabledConditionsMet, setVectorizationEnabledConditionsNotMet, setVectorizationInputFileFormatClassNameSet, setVectorizedRowBatch
addDummyOp, addSortCols, getAllLeafOperators, getAllNative, getAllOperators, getDummyOps, getGroupByVectorOutput, getInputSourceToRuntimeValuesInfo, getLlapMode, getMapRedLocalWork, getName, getNotVectorizedReason, getReservedMemoryMB, getSortCols, getTag, getUberMode, getUsesVectorUDFAdaptor, getVectorizationEnabled, getVectorizationExamined, getVectorizedRowBatchCtx, getVectorizedVertexNum, setAllNative, setDummyOps, setGatheringStats, setGroupByVectorOutput, setInputSourceToRuntimeValuesInfo, setLlapMode, setMapRedLocalWork, setName, setNotVectorizedReason, setReservedMemoryMB, setTag, setUberMode, setUsesVectorUDFAdaptor, setVectorizationEnabled, setVectorizationExamined, setVectorizedRowBatchCtx, setVectorizedVertexNum
clone, getMaxMemoryAvailable, getMemoryNeeded, getOpProps, getRuntimeStatsTmpDir, getStatistics, getTraits, getUserLevelStatistics, getVectorDesc, getVectorMode, setMaxMemoryAvailable, setMemoryNeeded, setOpProps, setRuntimeStatsTmpDir, setStatistics, setTraits, setVectorDesc, setVectorMode
public MergeFileWork(List<org.apache.hadoop.fs.Path> inputPaths, org.apache.hadoop.fs.Path outputDir, String srcTblInputFormat)
public List<org.apache.hadoop.fs.Path> getInputPaths()
public void setInputPaths(List<org.apache.hadoop.fs.Path> inputPaths)
public org.apache.hadoop.fs.Path getOutputDir()
public void setOutputDir(org.apache.hadoop.fs.Path outputDir)
public Long getMinSplitSize()
getMinSplitSize
in class MapWork
public String getInputformat()
getInputformat
in class MapWork
public Class<? extends org.apache.hadoop.mapred.InputFormat> getInputformatClass()
public boolean isGatheringStats()
isGatheringStats
in class BaseWork
public boolean hasDynamicPartitions()
public void setHasDynamicPartitions(boolean hasDynamicPartitions)
public void resolveDynamicPartitionStoredAsSubDirsMerge(HiveConf conf, org.apache.hadoop.fs.Path path, TableDesc tblDesc, ArrayList<String> aliases, PartitionDesc partDesc)
resolveDynamicPartitionStoredAsSubDirsMerge
in class MapWork
public void resolveConcatenateMerge(HiveConf conf)
public ListBucketingCtx getListBucketingCtx()
public void setListBucketingCtx(ListBucketingCtx listBucketingCtx)
listBucketingCtx
- the listBucketingCtx to setpublic boolean isListBucketingAlterTableConcatenate()
public String getSourceTableInputFormat()
public void setSourceTableInputFormat(String srcTblInputFormat)
public String getMergeLevel()
Copyright © 2021 The Apache Software Foundation. All rights reserved.