trait ParquetPartitionReaderBase extends Logging with Arm with ScanWithMetrics with MultiFileReaderFunctions
- Alphabetic
- By Inheritance
- ParquetPartitionReaderBase
- MultiFileReaderFunctions
- ScanWithMetrics
- Arm
- Logging
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Abstract Value Members
Concrete 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
-
def
addPartitionValues(batch: Option[ColumnarBatch], inPartitionValues: InternalRow, partitionSchema: StructType): Option[ColumnarBatch]
- Attributes
- protected
- Definition Classes
- MultiFileReaderFunctions
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
-
def
calculateParquetFooterSize(currentChunkedBlocks: Seq[BlockMetaData], schema: MessageType): Long
- Attributes
- protected
- Annotations
- @nowarn()
-
def
calculateParquetOutputSize(currentChunkedBlocks: Seq[BlockMetaData], schema: MessageType, handleCoalesceFiles: Boolean): Long
- Attributes
- protected
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native() @HotSpotIntrinsicCandidate()
-
def
closeOnExcept[T <: AutoCloseable, V](r: Option[T])(block: (Option[T]) ⇒ V): V
Executes the provided code block, closing the resources only if an exception occurs
Executes the provided code block, closing the resources only if an exception occurs
- Definition Classes
- Arm
-
def
closeOnExcept[T <: AutoCloseable, V](r: ArrayBuffer[T])(block: (ArrayBuffer[T]) ⇒ V): V
Executes the provided code block, closing the resources only if an exception occurs
Executes the provided code block, closing the resources only if an exception occurs
- Definition Classes
- Arm
-
def
closeOnExcept[T <: AutoCloseable, V](r: Array[T])(block: (Array[T]) ⇒ V): V
Executes the provided code block, closing the resources only if an exception occurs
Executes the provided code block, closing the resources only if an exception occurs
- Definition Classes
- Arm
-
def
closeOnExcept[T <: AutoCloseable, V](r: Seq[T])(block: (Seq[T]) ⇒ V): V
Executes the provided code block, closing the resources only if an exception occurs
Executes the provided code block, closing the resources only if an exception occurs
- Definition Classes
- Arm
-
def
closeOnExcept[T <: AutoCloseable, V](r: T)(block: (T) ⇒ V): V
Executes the provided code block, closing the resource only if an exception occurs
Executes the provided code block, closing the resource only if an exception occurs
- Definition Classes
- Arm
-
def
computeBlockMetaData(blocks: Seq[BlockMetaData], realStartOffset: Long, copyRangesToUpdate: Option[ArrayBuffer[CopyRange]] = None): Seq[BlockMetaData]
Computes new block metadata to reflect where the blocks and columns will appear in the computed Parquet file.
Computes new block metadata to reflect where the blocks and columns will appear in the computed Parquet file.
- blocks
block metadata from the original file(s) that will appear in the computed file
- realStartOffset
starting file offset of the first block
- copyRangesToUpdate
optional buffer to update with ranges of column data to copy
- returns
updated block metadata
- Attributes
- protected
- Annotations
- @nowarn()
-
def
copyBlocksData(in: FSDataInputStream, out: HostMemoryOutputStream, blocks: Seq[BlockMetaData], realStartOffset: Long): Seq[BlockMetaData]
Copies the data corresponding to the clipped blocks in the original file and compute the block metadata for the output.
Copies the data corresponding to the clipped blocks in the original file and compute the block metadata for the output. The output blocks will contain the same column chunk metadata but with the file offsets updated to reflect the new position of the column data as written to the output.
- in
the input stream for the original Parquet file
- out
the output stream to receive the data
- blocks
block metadata from the original file that will appear in the computed file
- realStartOffset
starting file offset of the first block
- returns
updated block metadata corresponding to the output
- Attributes
- protected
- val copyBufferSize: Int
-
def
copyDataRange(range: CopyRange, in: FSDataInputStream, out: OutputStream, copyBuffer: Array[Byte]): Unit
- Attributes
- protected
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
def
equals(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
def
fileSystemBytesRead(): Long
- Attributes
- protected
- Definition Classes
- MultiFileReaderFunctions
- Annotations
- @nowarn()
-
def
freeOnExcept[T <: RapidsBuffer, V](r: T)(block: (T) ⇒ V): V
Executes the provided code block, freeing the RapidsBuffer only if an exception occurs
Executes the provided code block, freeing the RapidsBuffer only if an exception occurs
- Definition Classes
- Arm
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native() @HotSpotIntrinsicCandidate()
- def getParquetOptions(clippedSchema: MessageType, useFieldId: Boolean): ParquetOptions
-
def
hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @native() @HotSpotIntrinsicCandidate()
-
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
-
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() @HotSpotIntrinsicCandidate()
-
final
def
notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native() @HotSpotIntrinsicCandidate()
-
def
populateCurrentBlockChunk(blockIter: BufferedIterator[BlockMetaData], maxReadBatchSizeRows: Int, maxReadBatchSizeBytes: Long): Seq[BlockMetaData]
- Attributes
- protected
-
def
readPartFile(blocks: Seq[BlockMetaData], clippedSchema: MessageType, filePath: Path): (HostMemoryBuffer, Long)
- Attributes
- protected
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
-
def
toCudfColumnNames(readDataSchema: StructType, fileSchema: MessageType, isCaseSensitive: Boolean, useFieldId: Boolean): Seq[String]
Take case-sensitive into consideration when getting the data reading column names before sending parquet-formatted buffer to cudf.
Take case-sensitive into consideration when getting the data reading column names before sending parquet-formatted buffer to cudf. Also clips the column names if
useFieldIdis true.- readDataSchema
Spark schema to read
- fileSchema
the schema of the dumped parquet-formatted buffer, already removed unmatched
- isCaseSensitive
if it is case sensitive
- useFieldId
if enabled
spark.sql.parquet.fieldId.read.enabled- returns
a sequence of tuple of column names following the order of readDataSchema
- Attributes
- protected
-
def
toString(): String
- Definition Classes
- AnyRef → Any
-
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
withResource[T <: AutoCloseable, V](h: CloseableHolder[T])(block: (CloseableHolder[T]) ⇒ V): V
Executes the provided code block and then closes the resource
Executes the provided code block and then closes the resource
- Definition Classes
- Arm
-
def
withResource[T <: AutoCloseable, V](r: ArrayBuffer[T])(block: (ArrayBuffer[T]) ⇒ V): V
Executes the provided code block and then closes the array buffer of resources
Executes the provided code block and then closes the array buffer of resources
- Definition Classes
- Arm
-
def
withResource[T <: AutoCloseable, V](r: Array[T])(block: (Array[T]) ⇒ V): V
Executes the provided code block and then closes the array of resources
Executes the provided code block and then closes the array of resources
- Definition Classes
- Arm
-
def
withResource[T <: AutoCloseable, V](r: Seq[T])(block: (Seq[T]) ⇒ V): V
Executes the provided code block and then closes the sequence of resources
Executes the provided code block and then closes the sequence of resources
- Definition Classes
- Arm
-
def
withResource[T <: AutoCloseable, V](r: Option[T])(block: (Option[T]) ⇒ V): V
Executes the provided code block and then closes the Option[resource]
Executes the provided code block and then closes the Option[resource]
- Definition Classes
- Arm
-
def
withResource[T <: AutoCloseable, V](r: T)(block: (T) ⇒ V): V
Executes the provided code block and then closes the resource
Executes the provided code block and then closes the resource
- Definition Classes
- Arm
-
def
withResourceIfAllowed[T, V](r: T)(block: (T) ⇒ V): V
Executes the provided code block and then closes the value if it is AutoCloseable
Executes the provided code block and then closes the value if it is AutoCloseable
- Definition Classes
- Arm
-
def
writeFooter(out: OutputStream, blocks: Seq[BlockMetaData], schema: MessageType): Unit
- Attributes
- protected