com.facebook.presto.hive.parquet

Class ParquetPageSourceFactory

java.lang.Object

com.facebook.presto.hive.parquet.ParquetPageSourceFactory

All Implemented Interfaces:

HiveBatchPageSourceFactory

public class ParquetPageSourceFactory
extends Object
implements HiveBatchPageSourceFactory

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, Path path, long start, long length, long fileSize, Storage storage, SchemaTableName tableName, Map<String,String> tableParameters, List<HiveColumnHandle> columns, TupleDomain<HiveColumnHandle> effectivePredicate, org.joda.time.DateTimeZone hiveStorageTimeZone, HiveFileContext hiveFileContext, Optional<EncryptionInformation> encryptionInformation)
static ParquetPageSource	createParquetPageSource(HdfsEnvironment hdfsEnvironment, String user, org.apache.hadoop.conf.Configuration configuration, Path path, long start, long length, long fileSize, List<HiveColumnHandle> columns, SchemaTableName tableName, boolean useParquetColumnNames, boolean failOnCorruptedParquetStatistics, io.airlift.units.DataSize maxReadBlockSize, boolean batchReaderEnabled, boolean verificationEnabled, TypeManager typeManager, TupleDomain<HiveColumnHandle> effectivePredicate, FileFormatDataSourceStats stats, HiveFileContext hiveFileContext)
static Optional<org.apache.parquet.schema.Type>	getColumnType(Type prestoType, org.apache.parquet.schema.MessageType messageType, boolean useParquetColumnNames, HiveColumnHandle column, SchemaTableName tableName, Path path)
static TupleDomain<org.apache.parquet.column.ColumnDescriptor>	getParquetTupleDomain(Map<List<String>,RichColumnDescriptor> descriptorsByPath, TupleDomain<HiveColumnHandle> effectivePredicate)
static Optional<org.apache.parquet.schema.Type>	getParquetType(Type prestoType, org.apache.parquet.schema.MessageType messageType, boolean useParquetColumnNames, HiveColumnHandle column, SchemaTableName tableName, Path path)

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,
                                                                Path path,
                                                                long start,
                                                                long length,
                                                                long fileSize,
                                                                Storage storage,
                                                                SchemaTableName tableName,
                                                                Map<String,String> tableParameters,
                                                                List<HiveColumnHandle> columns,
                                                                TupleDomain<HiveColumnHandle> effectivePredicate,
                                                                org.joda.time.DateTimeZone hiveStorageTimeZone,
                                                                HiveFileContext hiveFileContext,
                                                                Optional<EncryptionInformation> encryptionInformation)

Specified by:

createPageSource in interface HiveBatchPageSourceFactory

createParquetPageSource

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

getParquetTupleDomain

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

getParquetType

public static Optional<org.apache.parquet.schema.Type> getParquetType(Type prestoType,
                                                                      org.apache.parquet.schema.MessageType messageType,
                                                                      boolean useParquetColumnNames,
                                                                      HiveColumnHandle column,
                                                                      SchemaTableName tableName,
                                                                      Path path)

getColumnType

public static Optional<org.apache.parquet.schema.Type> getColumnType(Type prestoType,
                                                                     org.apache.parquet.schema.MessageType messageType,
                                                                     boolean useParquetColumnNames,
                                                                     HiveColumnHandle column,
                                                                     SchemaTableName tableName,
                                                                     Path path)