io.prestosql.plugin.hive.parquet

Class ParquetPageSourceFactory

java.lang.Object

io.prestosql.plugin.hive.parquet.ParquetPageSourceFactory

All Implemented Interfaces:

HivePageSourceFactory

public class ParquetPageSourceFactory
extends Object
implements HivePageSourceFactory

Constructor Summary

Constructors

Constructor and Description
ParquetPageSourceFactory(TypeManager typeManager, HdfsEnvironment hdfsEnvironment, FileFormatDataSourceStats stats)

Method Summary

Modifier and Type	Method and Description
Optional<? extends ConnectorPageSource>	createPageSource(org.apache.hadoop.conf.Configuration configuration, ConnectorSession session, org.apache.hadoop.fs.Path path, long start, long length, long fileSize, Properties schema, List<HiveColumnHandle> columns, TupleDomain<HiveColumnHandle> effectivePredicate, org.joda.time.DateTimeZone hiveStorageTimeZone)
static ParquetPageSource	createParquetPageSource(HdfsEnvironment hdfsEnvironment, String user, org.apache.hadoop.conf.Configuration configuration, org.apache.hadoop.fs.Path path, long start, long length, long fileSize, Properties schema, List<HiveColumnHandle> columns, boolean useParquetColumnNames, boolean failOnCorruptedParquetStatistics, io.airlift.units.DataSize maxReadBlockSize, TypeManager typeManager, TupleDomain<HiveColumnHandle> effectivePredicate, FileFormatDataSourceStats stats)
static TupleDomain<org.apache.parquet.column.ColumnDescriptor>	getParquetTupleDomain(Map<List<String>,RichColumnDescriptor> descriptorsByPath, TupleDomain<HiveColumnHandle> effectivePredicate)
static org.apache.parquet.schema.Type	getParquetType(HiveColumnHandle column, org.apache.parquet.schema.MessageType messageType, boolean useParquetColumnNames)

Methods inherited from class java.lang.Object

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

Constructor Detail

ParquetPageSourceFactory

@Inject
public ParquetPageSourceFactory(TypeManager typeManager,
                                        HdfsEnvironment hdfsEnvironment,
                                        FileFormatDataSourceStats stats)

Method Detail

createPageSource

public Optional<? extends ConnectorPageSource> createPageSource(org.apache.hadoop.conf.Configuration configuration,
                                                                ConnectorSession session,
                                                                org.apache.hadoop.fs.Path path,
                                                                long start,
                                                                long length,
                                                                long fileSize,
                                                                Properties schema,
                                                                List<HiveColumnHandle> columns,
                                                                TupleDomain<HiveColumnHandle> effectivePredicate,
                                                                org.joda.time.DateTimeZone hiveStorageTimeZone)

Specified by:

createPageSource in interface HivePageSourceFactory

createParquetPageSource

public static ParquetPageSource createParquetPageSource(HdfsEnvironment hdfsEnvironment,
                                                        String user,
                                                        org.apache.hadoop.conf.Configuration configuration,
                                                        org.apache.hadoop.fs.Path path,
                                                        long start,
                                                        long length,
                                                        long fileSize,
                                                        Properties schema,
                                                        List<HiveColumnHandle> columns,
                                                        boolean useParquetColumnNames,
                                                        boolean failOnCorruptedParquetStatistics,
                                                        io.airlift.units.DataSize maxReadBlockSize,
                                                        TypeManager typeManager,
                                                        TupleDomain<HiveColumnHandle> effectivePredicate,
                                                        FileFormatDataSourceStats stats)

getParquetTupleDomain

public static TupleDomain<org.apache.parquet.column.ColumnDescriptor> getParquetTupleDomain(Map<List<String>,RichColumnDescriptor> descriptorsByPath,
                                                                                            TupleDomain<HiveColumnHandle> effectivePredicate)

getParquetType

public static org.apache.parquet.schema.Type getParquetType(HiveColumnHandle column,
                                                            org.apache.parquet.schema.MessageType messageType,
                                                            boolean useParquetColumnNames)