case class GpuParquetScan(sparkSession: SparkSession, hadoopConf: Configuration, fileIndex: PartitioningAwareFileIndex, dataSchema: StructType, readDataSchema: StructType, readPartitionSchema: StructType, pushedFilters: Array[Filter], options: CaseInsensitiveStringMap, partitionFilters: Seq[Expression], dataFilters: Seq[Expression], rapidsConf: RapidsConf, queryUsesInputFile: Boolean = false) extends FileScan with GpuScan with Logging with Product with Serializable
Base GpuParquetScan used for common code across Spark versions. Gpu version of Spark's 'ParquetScan'.
- sparkSession
SparkSession.
- hadoopConf
Hadoop configuration.
- fileIndex
File index of the relation.
- dataSchema
Schema of the data.
- readDataSchema
Schema to read.
- readPartitionSchema
Partition schema.
- pushedFilters
Filters on non-partition columns.
- options
Parquet option settings.
- partitionFilters
Filters on partition columns.
- dataFilters
File source metadata filters.
- rapidsConf
Rapids configuration.
- queryUsesInputFile
This is a parameter to easily allow turning it off in GpuTransitionOverrides if InputFileName, InputFileBlockStart, or InputFileBlockLength are used
Linear Supertypes
Ordering
- Alphabetic
- By Inheritance
Inherited
- GpuParquetScan
- Serializable
- Serializable
- Product
- Equals
- GpuScan
- ScanWithMetrics
- FileScan
- Logging
- SupportsMetadata
- SupportsReportStatistics
- Batch
- Scan
- AnyRef
- Any
- Hide All
- Show All
Visibility
- Public
- All
Instance Constructors
-
new
GpuParquetScan(sparkSession: SparkSession, hadoopConf: Configuration, fileIndex: PartitioningAwareFileIndex, dataSchema: StructType, readDataSchema: StructType, readPartitionSchema: StructType, pushedFilters: Array[Filter], options: CaseInsensitiveStringMap, partitionFilters: Seq[Expression], dataFilters: Seq[Expression], rapidsConf: RapidsConf, queryUsesInputFile: Boolean = false)
- sparkSession
SparkSession.
- hadoopConf
Hadoop configuration.
- fileIndex
File index of the relation.
- dataSchema
Schema of the data.
- readDataSchema
Schema to read.
- readPartitionSchema
Partition schema.
- pushedFilters
Filters on non-partition columns.
- options
Parquet option settings.
- partitionFilters
Filters on partition columns.
- dataFilters
File source metadata filters.
- rapidsConf
Rapids configuration.
- queryUsesInputFile
This is a parameter to easily allow turning it off in GpuTransitionOverrides if InputFileName, InputFileBlockStart, or InputFileBlockLength are used
Value Members
-
final
def
!=(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
##(): Int
- Definition Classes
- AnyRef → Any
-
final
def
==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
-
def
createReaderFactory(): PartitionReaderFactory
- Definition Classes
- GpuParquetScan → Batch
-
val
dataFilters: Seq[Expression]
- Definition Classes
- GpuParquetScan → FileScan
- val dataSchema: StructType
-
def
description(): String
- Definition Classes
- GpuParquetScan → FileScan → Scan
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
def
equals(obj: Any): Boolean
- Definition Classes
- GpuParquetScan → Equals → FileScan → AnyRef → Any
-
def
equivalentFilters(a: Array[Filter], b: Array[Filter]): Boolean
- Attributes
- protected
- Definition Classes
- FileScan
-
def
estimateStatistics(): Statistics
- Definition Classes
- FileScan → SupportsReportStatistics
-
val
fileIndex: PartitioningAwareFileIndex
- Definition Classes
- GpuParquetScan → FileScan
-
def
finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( classOf[java.lang.Throwable] )
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
def
getFileUnSplittableReason(path: Path): String
- Definition Classes
- FileScan
-
def
getMetaData(): Map[String, String]
- Definition Classes
- FileScan → SupportsMetadata
- val hadoopConf: Configuration
-
def
hashCode(): Int
- Definition Classes
- GpuParquetScan → FileScan → AnyRef → Any
-
def
initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
- Attributes
- protected
- Definition Classes
- Logging
-
def
initializeLogIfNecessary(isInterpreter: Boolean): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
-
def
isSplitable(path: Path): Boolean
- Definition Classes
- GpuParquetScan → FileScan
-
def
isTraceEnabled(): Boolean
- Attributes
- protected
- Definition Classes
- Logging
-
def
log: Logger
- Attributes
- protected
- Definition Classes
- Logging
-
def
logDebug(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logDebug(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logError(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logError(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logInfo(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logInfo(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logName: String
- Attributes
- protected
- Definition Classes
- Logging
-
def
logTrace(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logTrace(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logWarning(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logWarning(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
val
maxMetadataValueLength: Int
- Definition Classes
- FileScan
-
val
metrics: Map[String, GpuMetric]
- Definition Classes
- ScanWithMetrics
-
final
def
ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
final
def
notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
final
def
notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
- val options: CaseInsensitiveStringMap
-
val
partitionFilters: Seq[Expression]
- Definition Classes
- GpuParquetScan → FileScan
-
def
partitions: Seq[FilePartition]
- Attributes
- protected
- Definition Classes
- FileScan
-
def
planInputPartitions(): Array[InputPartition]
- Definition Classes
- FileScan → Batch
- val pushedFilters: Array[Filter]
- val queryUsesInputFile: Boolean
- val rapidsConf: RapidsConf
-
val
readDataSchema: StructType
- Definition Classes
- GpuParquetScan → FileScan
-
val
readPartitionSchema: StructType
- Definition Classes
- GpuParquetScan → FileScan
-
def
readSchema(): StructType
- Definition Classes
- FileScan → Scan
-
def
seqToString(seq: Seq[Any]): String
- Attributes
- protected
- Definition Classes
- FileScan
-
val
sparkSession: SparkSession
- Definition Classes
- GpuParquetScan → FileScan
-
def
supportedCustomMetrics(): Array[CustomMetric]
- Definition Classes
- Scan
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
-
def
toBatch(): Batch
- Definition Classes
- FileScan → Scan
-
def
toContinuousStream(arg0: String): ContinuousStream
- Definition Classes
- Scan
-
def
toMicroBatchStream(arg0: String): MicroBatchStream
- Definition Classes
- Scan
-
final
def
wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
-
def
withFilters(partitionFilters: Seq[Expression], dataFilters: Seq[Expression]): FileScan
- Definition Classes
- GpuParquetScan → FileScan
-
def
withInputFile(): GpuScan
Create a version of this scan with input file name support
Create a version of this scan with input file name support
- Definition Classes
- GpuParquetScan → GpuScan