Package org.apache.drill.exec.store.delta

Class DeltaGroupScan

java.lang.Object

org.apache.drill.exec.physical.base.AbstractBase

org.apache.drill.exec.physical.base.AbstractGroupScan

org.apache.drill.exec.physical.base.AbstractFileGroupScan

org.apache.drill.exec.physical.base.AbstractGroupScanWithMetadata<ParquetMetadataProvider>

org.apache.drill.exec.store.parquet.AbstractParquetGroupScan

org.apache.drill.exec.store.delta.DeltaGroupScan

All Implemented Interfaces:

Iterable<PhysicalOperator>, GraphValue<PhysicalOperator>, FileGroupScan, FragmentLeaf, GroupScan, HasAffinity, Leaf, PhysicalOperator, Scan

public class DeltaGroupScan
extends AbstractParquetGroupScan

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	DeltaGroupScan.DeltaGroupScanBuilder

Nested classes/interfaces inherited from class org.apache.drill.exec.store.parquet.AbstractParquetGroupScan

AbstractParquetGroupScan.RowGroupScanFilterer<B extends AbstractParquetGroupScan.RowGroupScanFilterer<B>>

Nested classes/interfaces inherited from class org.apache.drill.exec.physical.base.AbstractGroupScanWithMetadata

AbstractGroupScanWithMetadata.GroupScanWithMetadataFilterer<B extends AbstractGroupScanWithMetadata.GroupScanWithMetadataFilterer<B>>

Field Summary

Fields inherited from class org.apache.drill.exec.store.parquet.AbstractParquetGroupScan

entries, mappings, readerConfig, rowGroups

Fields inherited from class org.apache.drill.exec.physical.base.AbstractGroupScanWithMetadata

columns, files, fileSet, filter, limit, matchAllMetadata, metadataProvider, nonInterestingColumnsMetadata, partitionColumns, partitions, segments, tableMetadata, usedMetastore

Fields inherited from class org.apache.drill.exec.physical.base.AbstractBase

INIT_ALLOCATION, initialAllocation, MAX_ALLOCATION, maxAllocation, userName

Fields inherited from interface org.apache.drill.exec.physical.base.GroupScan

ALL_COLUMNS

Constructor Summary

Constructors

Constructor	Description
DeltaGroupScan(String userName, List<ReadEntryWithPath> entries, StoragePluginConfig storageConfig, FormatPluginConfig formatConfig, List<SchemaPath> columns, TupleMetadata schema, String path, ParquetReaderConfig readerConfig, LogicalExpression condition, Integer limit, Map<org.apache.hadoop.fs.Path,Map<String,String>> partitionHolder, StoragePluginRegistry pluginRegistry)

Method Summary

Modifier and Type	Method	Description
DeltaGroupScan	applyLimit(int maxRecords)	By default, return null to indicate row count based prune is not supported.
static DeltaGroupScan.DeltaGroupScanBuilder	builder()
DeltaGroupScan	clone(List<SchemaPath> columns)	Returns a clone of GroupScan instance, except that the new GroupScan will use the provided list of columns .
DeltaGroupScan	clone(FileSelection selection)
protected AbstractParquetGroupScan	cloneWithFileSelection(Collection<org.apache.hadoop.fs.Path> filePaths)
protected DeltaParquetTableMetadataProvider.Builder	defaultTableMetadataProviderBuilder(MetadataProviderManager source)	Returns TableMetadataProviderBuilder instance which may provide metadata without using Drill Metastore.
LogicalExpression	getCondition()
protected Collection<CoordinationProtos.DrillbitEndpoint>	getDrillbits()
protected AbstractParquetGroupScan.RowGroupScanFilterer<?>	getFilterer()	Returns holder for metadata values which provides API to filter metadata and build new group scan instance using filtered metadata.
FormatPluginConfig	getFormatConfig()
PhysicalOperator	getNewWithChildren(List<PhysicalOperator> children)	Regenerate with this node with a new set of children.
Map<org.apache.hadoop.fs.Path,Map<String,String>>	getPartitionHolder()
protected List<String>	getPartitionValues(LocationProvider locationProvider)
String	getPath()
TupleMetadata	getSchema()
SubScan	getSpecificScan(int minorFragmentId)
StoragePluginConfig	getStorageConfig()
protected boolean	supportsFileImplicitColumns()
boolean	supportsLimitPushdown()	Default is not to support limit pushdown.
protected DeltaParquetTableMetadataProvider.Builder	tableMetadataProviderBuilder(MetadataProviderManager source)	Returns TableMetadataProviderBuilder instance based on specified MetadataProviderManager source.
String	toString()

Methods inherited from class org.apache.drill.exec.store.parquet.AbstractParquetGroupScan

applyAssignments, applyFilter, canPushdownProjects, getEntries, getFiles, getMaxParallelizationWidth, getOperatorAffinity, getReadEntries, getReaderConfig, getReaderConfigForSerialization, getRowGroupsMetadata, modifyFileSelection, pruneForPartitions, pruneRowGroupsForFiles, supportsFilterPushDown

Methods inherited from class org.apache.drill.exec.physical.base.AbstractGroupScanWithMetadata

checkMetadataConsistency, getColumns, getColumnValueCount, getDigest, getFileSet, getFilesMetadata, getFilter, getFilterPredicate, getFilterPredicate, getFilterString, getLimit, getMetadataProvider, getNextOrEmpty, getNonInterestingColumnsMetadata, getPartitionColumns, getPartitionsMetadata, getPartitionValue, getScanStats, getSegmentsMetadata, getTableMetadata, getTypeForColumn, hasFiles, init, isAllDataPruned, isGroupScanFullyMatchesFilter, isImplicitOrPartCol, isMatchAllMetadata, limitMetadata, pruneForPartitions, setFilter, setFilterForRuntime, usedMetastore

Methods inherited from class org.apache.drill.exec.physical.base.AbstractFileGroupScan

supportsPartitionFilterPushdown

Methods inherited from class org.apache.drill.exec.physical.base.AbstractGroupScan

accept, enforceWidth, getAnalyzeInfoProvider, getDistributionAffinity, getInitialAllocation, getMaxAllocation, getMinParallelizationWidth, getOperatorType, getScanStats, getScanStats, getSelectionRoot, isDistributed, isExecutable, iterator

Methods inherited from class org.apache.drill.exec.physical.base.AbstractBase

accept, getCost, getOperatorId, getSVMode, getUserName, isBufferedOperator, setCost, setMaxAllocation, setOperatorId

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.apache.drill.common.graph.GraphValue

accept

Methods inherited from interface org.apache.drill.exec.physical.base.GroupScan

enforceWidth, getAnalyzeInfoProvider, getMinParallelizationWidth, getScanStats, getScanStats, getSelectionRoot, isDistributed

Methods inherited from interface org.apache.drill.exec.physical.base.HasAffinity

getDistributionAffinity

Methods inherited from interface java.lang.Iterable

forEach, iterator, spliterator

Methods inherited from interface org.apache.drill.exec.physical.base.PhysicalOperator

accept, getCost, getInitialAllocation, getMaxAllocation, getOperatorId, getOperatorType, getSVMode, getUserName, isBufferedOperator, isExecutable, setCost, setMaxAllocation, setOperatorId

Constructor Details

DeltaGroupScan

public DeltaGroupScan(String userName,
 List<ReadEntryWithPath> entries,
 StoragePluginConfig storageConfig,
 FormatPluginConfig formatConfig,
 List<SchemaPath> columns,
 TupleMetadata schema,
 String path,
 ParquetReaderConfig readerConfig,
 LogicalExpression condition,
 Integer limit,
 Map<org.apache.hadoop.fs.Path,Map<String,String>> partitionHolder,
 StoragePluginRegistry pluginRegistry)
               throws IOException

Throws:

IOException

Method Details

tableMetadataProviderBuilder

protected DeltaParquetTableMetadataProvider.Builder tableMetadataProviderBuilder(MetadataProviderManager source)

Description copied from class: AbstractGroupScanWithMetadata

Returns TableMetadataProviderBuilder instance based on specified MetadataProviderManager source.

Specified by:

tableMetadataProviderBuilder in class AbstractGroupScanWithMetadata<ParquetMetadataProvider>

Parameters:

source - metadata provider manager

Returns:

TableMetadataProviderBuilder instance

defaultTableMetadataProviderBuilder

protected DeltaParquetTableMetadataProvider.Builder defaultTableMetadataProviderBuilder(MetadataProviderManager source)

Description copied from class: AbstractGroupScanWithMetadata

Returns TableMetadataProviderBuilder instance which may provide metadata without using Drill Metastore.

Specified by:

defaultTableMetadataProviderBuilder in class AbstractParquetGroupScan

Parameters:

source - metadata provider manager

Returns:

TableMetadataProviderBuilder instance

builder

public static DeltaGroupScan.DeltaGroupScanBuilder builder()

clone

public DeltaGroupScan clone(List<SchemaPath> columns)

Description copied from interface: GroupScan

Returns a clone of GroupScan instance, except that the new GroupScan will use the provided list of columns .

Specified by:

clone in interface GroupScan

Overrides:

clone in class AbstractGroupScan

applyLimit

public DeltaGroupScan applyLimit(int maxRecords)

Description copied from class: AbstractGroupScan

By default, return null to indicate row count based prune is not supported. Each group scan subclass should override, if it supports row count based prune.

Specified by:

applyLimit in interface GroupScan

Overrides:

applyLimit in class AbstractParquetGroupScan

Parameters:

maxRecords - : the number of rows requested from group scan.

Returns:

a new instance of group scan if the prune is successful. null when either if row-based prune is not supported, or if prune is not successful.

getSpecificScan

public SubScan getSpecificScan(int minorFragmentId)

clone

public DeltaGroupScan clone(FileSelection selection)
                     throws IOException

Specified by:

clone in interface FileGroupScan

Overrides:

clone in class AbstractFileGroupScan

Throws:

IOException

getFilterer

protected AbstractParquetGroupScan.RowGroupScanFilterer<?> getFilterer()

Description copied from class: AbstractGroupScanWithMetadata

Returns holder for metadata values which provides API to filter metadata and build new group scan instance using filtered metadata.

Specified by:

getFilterer in class AbstractParquetGroupScan

getDrillbits

protected Collection<CoordinationProtos.DrillbitEndpoint> getDrillbits()

Specified by:

getDrillbits in class AbstractParquetGroupScan

cloneWithFileSelection

protected AbstractParquetGroupScan cloneWithFileSelection(Collection<org.apache.hadoop.fs.Path> filePaths)
                                                   throws IOException

Specified by:

cloneWithFileSelection in class AbstractParquetGroupScan

Throws:

IOException

supportsFileImplicitColumns

protected boolean supportsFileImplicitColumns()

Specified by:

supportsFileImplicitColumns in class AbstractGroupScanWithMetadata<ParquetMetadataProvider>

getPartitionValues

protected List<String> getPartitionValues(LocationProvider locationProvider)

Specified by:

getPartitionValues in class AbstractGroupScanWithMetadata<ParquetMetadataProvider>

getNewWithChildren

public PhysicalOperator getNewWithChildren(List<PhysicalOperator> children)

Description copied from interface: PhysicalOperator

Regenerate with this node with a new set of children. This is used in the case of materialization or optimization.

Parameters:

children -

supportsLimitPushdown

public boolean supportsLimitPushdown()

Description copied from class: AbstractGroupScan

Default is not to support limit pushdown.

Specified by:

supportsLimitPushdown in interface GroupScan

Overrides:

supportsLimitPushdown in class AbstractGroupScanWithMetadata<ParquetMetadataProvider>

getSchema

public TupleMetadata getSchema()

Overrides:

getSchema in class AbstractGroupScanWithMetadata<ParquetMetadataProvider>

getStorageConfig

public StoragePluginConfig getStorageConfig()

getFormatConfig

public FormatPluginConfig getFormatConfig()

getPath

public String getPath()

getCondition

public LogicalExpression getCondition()

getPartitionHolder

public Map<org.apache.hadoop.fs.Path,Map<String,String>> getPartitionHolder()

toString

public String toString()

Overrides:

toString in class Object