org.apache.drill.exec.store.parquet

Class ParquetFormatPlugin

java.lang.Object

org.apache.drill.exec.store.parquet.ParquetFormatPlugin

All Implemented Interfaces:

FormatPlugin

public class ParquetFormatPlugin
extends Object
implements FormatPlugin

Field Summary

Fields

Modifier and Type	Field and Description
static String[]	PARQUET_FORMAT_VERSIONS ParquetProperties.WriterVersion
static org.apache.parquet.format.converter.ParquetMetadataConverter	parquetMetadataConverter

Constructor Summary

Constructors

Constructor and Description
ParquetFormatPlugin(String name, DrillbitContext context, org.apache.hadoop.conf.Configuration fsConf, StoragePluginConfig storageConfig)
ParquetFormatPlugin(String name, DrillbitContext context, org.apache.hadoop.conf.Configuration fsConf, StoragePluginConfig storageConfig, ParquetFormatConfig formatConfig)

Method Summary

Modifier and Type	Method and Description
ParquetFormatConfig	getConfig()
DrillbitContext	getContext()
org.apache.hadoop.conf.Configuration	getFsConf()
AbstractFileGroupScan	getGroupScan(String userName, FileSelection selection, List<SchemaPath> columns)
AbstractFileGroupScan	getGroupScan(String userName, FileSelection selection, List<SchemaPath> columns, OptionManager options)
AbstractFileGroupScan	getGroupScan(String userName, FileSelection selection, List<SchemaPath> columns, OptionManager options, MetadataProviderManager metadataProviderManager)
FormatMatcher	getMatcher()
String	getName()
Set<StoragePluginOptimizerRule>	getOptimizerRules()
RecordWriter	getRecordWriter(FragmentContext context, ParquetWriter writer)
StoragePluginConfig	getStorageConfig()
AbstractWriter	getWriter(PhysicalOperator child, String location, List<String> partitionColumns)
WriterRecordBatch	getWriterBatch(FragmentContext context, RecordBatch incoming, ParquetWriter writer)
DrillStatsTable.TableStatistics	readStatistics(org.apache.hadoop.fs.FileSystem fs, org.apache.hadoop.fs.Path statsTablePath)
boolean	supportsAutoPartitioning() Indicates whether this FormatPlugin supports auto-partitioning for CTAS statements
boolean	supportsRead()
boolean	supportsStatistics()
boolean	supportsWrite()
void	writeStatistics(DrillStatsTable.TableStatistics statistics, org.apache.hadoop.fs.FileSystem fs, org.apache.hadoop.fs.Path statsTablePath)

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.apache.drill.exec.store.dfs.FormatPlugin

getGroupScan, getOptimizerRules

Field Detail

PARQUET_FORMAT_VERSIONS

public static final String[] PARQUET_FORMAT_VERSIONS

ParquetProperties.WriterVersion

parquetMetadataConverter

public static final org.apache.parquet.format.converter.ParquetMetadataConverter parquetMetadataConverter

Constructor Detail

ParquetFormatPlugin

public ParquetFormatPlugin(String name,
                           DrillbitContext context,
                           org.apache.hadoop.conf.Configuration fsConf,
                           StoragePluginConfig storageConfig)

ParquetFormatPlugin

public ParquetFormatPlugin(String name,
                           DrillbitContext context,
                           org.apache.hadoop.conf.Configuration fsConf,
                           StoragePluginConfig storageConfig,
                           ParquetFormatConfig formatConfig)

Method Detail

getFsConf

public org.apache.hadoop.conf.Configuration getFsConf()

Specified by:

getFsConf in interface FormatPlugin

getConfig

public ParquetFormatConfig getConfig()

Specified by:

getConfig in interface FormatPlugin

getContext

public DrillbitContext getContext()

Specified by:

getContext in interface FormatPlugin

supportsRead

public boolean supportsRead()

Specified by:

supportsRead in interface FormatPlugin

getOptimizerRules

public Set<StoragePluginOptimizerRule> getOptimizerRules()

Specified by:

getOptimizerRules in interface FormatPlugin

getWriter

public AbstractWriter getWriter(PhysicalOperator child,
                                String location,
                                List<String> partitionColumns)
                         throws IOException

Specified by:

getWriter in interface FormatPlugin

Throws:

IOException

getRecordWriter

public RecordWriter getRecordWriter(FragmentContext context,
                                    ParquetWriter writer)
                             throws IOException,
                                    OutOfMemoryException

Throws:

IOException

OutOfMemoryException

getWriterBatch

public WriterRecordBatch getWriterBatch(FragmentContext context,
                                        RecordBatch incoming,
                                        ParquetWriter writer)
                                 throws ExecutionSetupException

Throws:

ExecutionSetupException

getGroupScan

public AbstractFileGroupScan getGroupScan(String userName,
                                          FileSelection selection,
                                          List<SchemaPath> columns)
                                   throws IOException

Specified by:

getGroupScan in interface FormatPlugin

Throws:

IOException

getGroupScan

public AbstractFileGroupScan getGroupScan(String userName,
                                          FileSelection selection,
                                          List<SchemaPath> columns,
                                          OptionManager options)
                                   throws IOException

Specified by:

getGroupScan in interface FormatPlugin

Throws:

IOException

getGroupScan

public AbstractFileGroupScan getGroupScan(String userName,
                                          FileSelection selection,
                                          List<SchemaPath> columns,
                                          OptionManager options,
                                          MetadataProviderManager metadataProviderManager)
                                   throws IOException

Specified by:

getGroupScan in interface FormatPlugin

Throws:

IOException

supportsStatistics

public boolean supportsStatistics()

Specified by:

supportsStatistics in interface FormatPlugin

readStatistics

public DrillStatsTable.TableStatistics readStatistics(org.apache.hadoop.fs.FileSystem fs,
                                                      org.apache.hadoop.fs.Path statsTablePath)
                                               throws IOException

Specified by:

readStatistics in interface FormatPlugin

Throws:

IOException

writeStatistics

public void writeStatistics(DrillStatsTable.TableStatistics statistics,
                            org.apache.hadoop.fs.FileSystem fs,
                            org.apache.hadoop.fs.Path statsTablePath)
                     throws IOException

Specified by:

writeStatistics in interface FormatPlugin

Throws:

IOException

getStorageConfig

public StoragePluginConfig getStorageConfig()

Specified by:

getStorageConfig in interface FormatPlugin

getName

public String getName()

Specified by:

getName in interface FormatPlugin

supportsWrite

public boolean supportsWrite()

Specified by:

supportsWrite in interface FormatPlugin

supportsAutoPartitioning

public boolean supportsAutoPartitioning()

Description copied from interface: FormatPlugin

Indicates whether this FormatPlugin supports auto-partitioning for CTAS statements

Specified by:

supportsAutoPartitioning in interface FormatPlugin

Returns:

true if auto-partitioning is supported

getMatcher

public FormatMatcher getMatcher()

Specified by:

getMatcher in interface FormatPlugin