public class VectorGroupByOperator extends Operator<GroupByDesc> implements VectorizationOperator, VectorizationContextRegion, IConfigureJobConf
Operator.Counter, Operator.OperatorFunc, Operator.State
abortOp, alias, asyncInitOperations, cContext, childOperators, childOperatorsArray, childOperatorsTag, conf, CONTEXT_NAME_KEY, done, groupKeyObject, HIVE_COUNTER_CREATED_DYNAMIC_PARTITIONS, HIVE_COUNTER_CREATED_FILES, HIVE_COUNTER_FATAL, id, inputObjInspectors, numRows, operatorId, out, outputObjInspector, parentOperators, reporter, runTimeNumRows, state, statsMap
Constructor and Description |
---|
VectorGroupByOperator()
Kryo ctor.
|
VectorGroupByOperator(CompilationOpContext ctx) |
VectorGroupByOperator(CompilationOpContext ctx,
OperatorDesc conf,
VectorizationContext vContext,
VectorDesc vectorDesc) |
Modifier and Type | Method and Description |
---|---|
boolean |
batchNeedsClone()
There are aggregate implementations where the contents of the batch are processed in an async way,
(e.g.
|
void |
closeOp(boolean aborted)
Operator specific close routine.
|
void |
configureJobConf(org.apache.hadoop.mapred.JobConf job) |
void |
endGroup() |
VectorAggregateExpression[] |
getAggregators() |
VectorizationContext |
getInputVectorizationContext() |
VectorExpression[] |
getKeyExpressions() |
long |
getMaxMemory() |
String |
getName()
Gets the name of the node.
|
static String |
getOperatorName() |
VectorizationContext |
getOutputVectorizationContext() |
OperatorType |
getType()
Return the type of the specific operator among the
types in OperatorType.
|
VectorDesc |
getVectorDesc() |
protected void |
initializeOp(org.apache.hadoop.conf.Configuration hconf)
Operator specific initialization.
|
void |
process(Object row,
int tag)
Process the row.
|
void |
setAggregators(VectorAggregateExpression[] aggregators) |
void |
setKeyExpressions(VectorExpression[] keyExpressions) |
void |
setNextVectorBatchGroupStatus(boolean isLastGroupBatch) |
void |
startGroup() |
abort, acceptLimitPushdown, allInitializedParentsAreClosed, areAllParentsInitialized, augmentPlan, cleanUpInputFileChanged, cleanUpInputFileChangedOp, clone, cloneOp, cloneRecursiveChildren, close, columnNamesRowResolvedCanBeObtained, completeInitializationOp, createDummy, defaultEndGroup, defaultStartGroup, dump, dump, flush, flushRecursive, forward, getAdditionalCounters, getChildOperators, getChildren, getColumnExprMap, getCompilationOpContext, getConf, getConfiguration, getCounterName, getDone, getExecContext, getGroupKeyObject, getIdentifier, getInputObjInspectors, getIsReduceSink, getMarker, getNextCntr, getNumChild, getNumParent, getOperatorId, getOpTraits, getOutputObjInspector, getParentOperators, getReduceOutputName, getSchema, getStatistics, getStats, initEvaluators, initEvaluators, initEvaluatorsAndReturnStruct, initialize, initialize, initializeChildren, initializeLocalWork, initOperatorId, isUseBucketizedHiveInputFormat, jobClose, jobCloseOp, logicalEquals, logicalEqualsTree, logStats, opAllowedAfterMapJoin, opAllowedBeforeMapJoin, opAllowedBeforeSortMergeJoin, opAllowedConvertMapJoin, passExecContext, preorderMap, processGroup, removeChild, removeChildAndAdoptItsChildren, removeParent, removeParents, replaceChild, replaceParent, replaceTabAlias, reset, setAlias, setChildOperators, setColumnExprMap, setCompilationOpContext, setConf, setDone, setExecContext, setGroupKeyObject, setInputContext, setInputObjInspectors, setMarker, setOpTraits, setOutputCollector, setParentOperators, setReporter, setSchema, setStatistics, setUseBucketizedHiveInputFormat, supportAutomaticSortMergeJoin, supportSkewJoinOptimization, supportUnionRemoveOptimization, toString, toString, toString, vectorForward
public VectorGroupByOperator(CompilationOpContext ctx, OperatorDesc conf, VectorizationContext vContext, VectorDesc vectorDesc) throws HiveException
HiveException
public VectorGroupByOperator()
public VectorGroupByOperator(CompilationOpContext ctx)
public VectorizationContext getInputVectorizationContext()
getInputVectorizationContext
in interface VectorizationOperator
protected void initializeOp(org.apache.hadoop.conf.Configuration hconf) throws HiveException
Operator
initializeOp
in class Operator<GroupByDesc>
HiveException
public void setNextVectorBatchGroupStatus(boolean isLastGroupBatch) throws HiveException
setNextVectorBatchGroupStatus
in class Operator<GroupByDesc>
HiveException
public void startGroup() throws HiveException
startGroup
in class Operator<GroupByDesc>
HiveException
public void endGroup() throws HiveException
endGroup
in class Operator<GroupByDesc>
HiveException
public void process(Object row, int tag) throws HiveException
Operator
process
in class Operator<GroupByDesc>
row
- The object representing the row.tag
- The tag of the row usually means which parent this row comes from.
Rows with the same tag should have exactly the same rowInspector
all the time.HiveException
public void closeOp(boolean aborted) throws HiveException
Operator
closeOp
in class Operator<GroupByDesc>
HiveException
public VectorExpression[] getKeyExpressions()
public void setKeyExpressions(VectorExpression[] keyExpressions)
public VectorAggregateExpression[] getAggregators()
public void setAggregators(VectorAggregateExpression[] aggregators)
public VectorizationContext getOutputVectorizationContext()
getOutputVectorizationContext
in interface VectorizationContextRegion
public OperatorType getType()
Operator
getType
in class Operator<GroupByDesc>
public String getName()
Node
getName
in interface Node
getName
in class Operator<GroupByDesc>
public static String getOperatorName()
public VectorDesc getVectorDesc()
getVectorDesc
in interface VectorizationOperator
public void configureJobConf(org.apache.hadoop.mapred.JobConf job)
configureJobConf
in interface IConfigureJobConf
public long getMaxMemory()
public boolean batchNeedsClone()
Operator
batchNeedsClone
in class Operator<GroupByDesc>
Copyright © 2023 The Apache Software Foundation. All rights reserved.