Packages

case class DeltaParquetFileFormat(protocol: Protocol, metadata: Metadata, isSplittable: Boolean = true, disablePushDowns: Boolean = false, tablePath: Option[String] = None, broadcastDvMap: Option[Broadcast[Map[URI, DeletionVectorDescriptorWithFilterType]]] = None, broadcastHadoopConf: Option[Broadcast[SerializableConfiguration]] = None) extends ParquetFileFormat with Product with Serializable

A thin wrapper over the Parquet file format to support

  • columns names without restrictions.
  • populated a column from the deletion vector of this file (if exists) to indicate whether the row is deleted or not according to the deletion vector. Consumers of this scan can use the column values to filter out the deleted rows.
Linear Supertypes
Product, Equals, ParquetFileFormat, Serializable, Logging, DataSourceRegister, FileFormat, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. DeltaParquetFileFormat
  2. Product
  3. Equals
  4. ParquetFileFormat
  5. Serializable
  6. Logging
  7. DataSourceRegister
  8. FileFormat
  9. AnyRef
  10. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. Protected

Instance Constructors

  1. new DeltaParquetFileFormat(protocol: Protocol, metadata: Metadata, isSplittable: Boolean = true, disablePushDowns: Boolean = false, tablePath: Option[String] = None, broadcastDvMap: Option[Broadcast[Map[URI, DeletionVectorDescriptorWithFilterType]]] = None, broadcastHadoopConf: Option[Broadcast[SerializableConfiguration]] = None)

Value Members

  1. final def !=(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  2. final def ##: Int
    Definition Classes
    AnyRef → Any
  3. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  4. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  5. val broadcastDvMap: Option[Broadcast[Map[URI, DeletionVectorDescriptorWithFilterType]]]
  6. val broadcastHadoopConf: Option[Broadcast[SerializableConfiguration]]
  7. def buildReader(sparkSession: SparkSession, dataSchema: StructType, partitionSchema: StructType, requiredSchema: StructType, filters: Seq[Filter], options: Map[String, String], hadoopConf: Configuration): (PartitionedFile) => Iterator[InternalRow]
    Attributes
    protected
    Definition Classes
    FileFormat
  8. def buildReaderWithPartitionValues(sparkSession: SparkSession, dataSchema: StructType, partitionSchema: StructType, requiredSchema: StructType, filters: Seq[Filter], options: Map[String, String], hadoopConf: Configuration): (PartitionedFile) => Iterator[InternalRow]
    Definition Classes
    DeltaParquetFileFormat → ParquetFileFormat → FileFormat
  9. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.CloneNotSupportedException]) @native()
  10. val columnMappingMode: DeltaColumnMappingMode
  11. def copyWithDVInfo(tablePath: String, broadcastDvMap: Broadcast[Map[URI, DeletionVectorDescriptorWithFilterType]], broadcastHadoopConf: Broadcast[SerializableConfiguration]): DeltaParquetFileFormat
  12. def createFileMetadataCol(): AttributeReference
    Definition Classes
    FileFormat
  13. val disablePushDowns: Boolean
  14. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  15. def equals(other: Any): Boolean

    We sometimes need to replace FileFormat within LogicalPlans, so we have to override equals to ensure file format changes are captured

    We sometimes need to replace FileFormat within LogicalPlans, so we have to override equals to ensure file format changes are captured

    Definition Classes
    DeltaParquetFileFormat → Equals → ParquetFileFormat → AnyRef → Any
  16. def fileConstantMetadataExtractors: Map[String, (PartitionedFile) => Any]
    Definition Classes
    FileFormat
  17. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.Throwable])
  18. final def getClass(): Class[_ <: AnyRef]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  19. def hasDeletionVectorMap(): Boolean
  20. def hashCode(): Int
    Definition Classes
    DeltaParquetFileFormat → ParquetFileFormat → AnyRef → Any
  21. def inferSchema(sparkSession: SparkSession, parameters: Map[String, String], files: Seq[FileStatus]): Option[StructType]
    Definition Classes
    ParquetFileFormat → FileFormat
  22. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  23. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  24. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  25. def isSplitable(sparkSession: SparkSession, options: Map[String, String], path: Path): Boolean
    Definition Classes
    DeltaParquetFileFormat → ParquetFileFormat → FileFormat
  26. val isSplittable: Boolean
  27. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  28. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  29. def logDebug(msg: => String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  30. def logDebug(msg: => String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  31. def logError(msg: => String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  32. def logError(msg: => String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  33. def logInfo(msg: => String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  34. def logInfo(msg: => String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  35. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  36. def logTrace(msg: => String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  37. def logTrace(msg: => String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  38. def logWarning(msg: => String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  39. def logWarning(msg: => String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  40. val metadata: Metadata
  41. def metadataSchemaFields: Seq[StructField]
    Definition Classes
    DeltaParquetFileFormat → ParquetFileFormat → FileFormat
  42. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  43. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  44. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  45. def prepareSchemaForRead(inputSchema: StructType): StructType

    prepareSchemaForRead must only be used for parquet read.

    prepareSchemaForRead must only be used for parquet read. It removes "PARQUET_FIELD_ID_METADATA_KEY" for name mapping mode which address columns by physical name instead of id.

  46. def prepareWrite(sparkSession: SparkSession, job: Job, options: Map[String, String], dataSchema: StructType): OutputWriterFactory
    Definition Classes
    ParquetFileFormat → FileFormat
  47. def productElementNames: Iterator[String]
    Definition Classes
    Product
  48. val protocol: Protocol
  49. val referenceSchema: StructType
  50. def shortName(): String
    Definition Classes
    ParquetFileFormat → DataSourceRegister
  51. def supportBatch(sparkSession: SparkSession, schema: StructType): Boolean
    Definition Classes
    ParquetFileFormat → FileFormat
  52. def supportDataType(dataType: DataType): Boolean
    Definition Classes
    ParquetFileFormat → FileFormat
  53. def supportFieldName(name: String): Boolean
    Definition Classes
    DeltaParquetFileFormat → FileFormat
  54. final def synchronized[T0](arg0: => T0): T0
    Definition Classes
    AnyRef
  55. val tablePath: Option[String]
  56. def toString(): String
    Definition Classes
    ParquetFileFormat → AnyRef → Any
  57. def vectorTypes(requiredSchema: StructType, partitionSchema: StructType, sqlConf: SQLConf): Option[Seq[String]]
    Definition Classes
    ParquetFileFormat → FileFormat
  58. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.InterruptedException])
  59. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.InterruptedException])
  60. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.InterruptedException]) @native()

Inherited from Product

Inherited from Equals

Inherited from ParquetFileFormat

Inherited from Serializable

Inherited from Logging

Inherited from DataSourceRegister

Inherited from FileFormat

Inherited from AnyRef

Inherited from Any

Ungrouped