case class GpuDataSource(sparkSession: SparkSession, className: String, paths: Seq[String] = Nil, userSpecifiedSchema: Option[StructType] = None, partitionColumns: Seq[String] = Seq.empty, bucketSpec: Option[BucketSpec] = None, options: Map[String, String] = Map.empty, catalogTable: Option[CatalogTable] = None, origProvider: Class[_], gpuFileFormat: ColumnarFileFormat) extends Logging with Product with Serializable
A truncated version of Spark DataSource that converts to use the GPU version of InsertIntoHadoopFsRelationCommand for FileFormats we support. This does not support DataSource V2 writing at this point because at the time of copying, it did not.
- Alphabetic
- By Inheritance
- GpuDataSource
- Serializable
- Serializable
- Product
- Equals
- Logging
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Instance Constructors
- new GpuDataSource(sparkSession: SparkSession, className: String, paths: Seq[String] = Nil, userSpecifiedSchema: Option[StructType] = None, partitionColumns: Seq[String] = Seq.empty, bucketSpec: Option[BucketSpec] = None, options: Map[String, String] = Map.empty, catalogTable: Option[CatalogTable] = None, origProvider: Class[_], gpuFileFormat: ColumnarFileFormat)
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
- val bucketSpec: Option[BucketSpec]
- val catalogTable: Option[CatalogTable]
- val className: String
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native() @HotSpotIntrinsicCandidate()
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native() @HotSpotIntrinsicCandidate()
-
def
globPaths: Boolean
Whether or not paths should be globbed before being used to access files.
- val gpuFileFormat: ColumnarFileFormat
-
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
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
-
final
def
ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
final
def
notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native() @HotSpotIntrinsicCandidate()
-
final
def
notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native() @HotSpotIntrinsicCandidate()
- val options: Map[String, String]
- val origProvider: Class[_]
- val partitionColumns: Seq[String]
- val paths: Seq[String]
-
def
resolveRelation(checkFilesExist: Boolean = true): BaseRelation
Create a resolved
BaseRelationthat can be used to read data from or write data into thisDataSourceCreate a resolved
BaseRelationthat can be used to read data from or write data into thisDataSource- checkFilesExist
Whether to confirm that the files exist when generating the non-streaming file based datasource. StructuredStreaming jobs already list file existence, and when generating incremental jobs, the batch is considered as a non-streaming file based data source. Since we know that files already exist, we don't need to check them again.
- val sparkSession: SparkSession
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
- val userSpecifiedSchema: Option[StructType]
-
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()
-
final
def
wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
def
writeAndRead(mode: SaveMode, data: LogicalPlan, outputColumnNames: Seq[String], physicalPlan: SparkPlan, useStableSort: Boolean): BaseRelation
Writes the given
LogicalPlanout to thisDataSourceand returns aBaseRelationfor the following reading.Writes the given
LogicalPlanout to thisDataSourceand returns aBaseRelationfor the following reading.- mode
The save mode for this writing.
- data
The input query plan that produces the data to be written. Note that this plan is analyzed and optimized.
- outputColumnNames
The original output column names of the input query plan. The optimizer may not preserve the output column's names' case, so we need this parameter instead of
data.output.- physicalPlan
The physical plan of the input query plan. We should run the writing command with this physical plan instead of creating a new physical plan, so that the metrics can be correctly linked to the given physical plan and shown in the web UI.