class
FileStreamSink extends Sink with Logging
Instance Constructors
-
new
FileStreamSink(sparkSession: SparkSession, path: String, fileFormat: FileFormat, partitionColumnNames: Seq[String], options: Map[String, String])
Value Members
-
final
def
!=(arg0: AnyRef): Boolean
-
final
def
!=(arg0: Any): Boolean
-
final
def
##(): Int
-
final
def
==(arg0: AnyRef): Boolean
-
final
def
==(arg0: Any): Boolean
-
def
addBatch(batchId: Long, data: DataFrame): Unit
-
final
def
asInstanceOf[T0]: T0
-
def
clone(): AnyRef
-
final
def
eq(arg0: AnyRef): Boolean
-
def
equals(arg0: Any): Boolean
-
def
finalize(): Unit
-
final
def
getClass(): Class[_]
-
def
hashCode(): Int
-
def
initializeLogIfNecessary(isInterpreter: Boolean): Unit
-
final
def
isInstanceOf[T0]: Boolean
-
def
isTraceEnabled(): Boolean
-
def
log: Logger
-
def
logDebug(msg: ⇒ String, throwable: Throwable): Unit
-
def
logDebug(msg: ⇒ String): Unit
-
def
logError(msg: ⇒ String, throwable: Throwable): Unit
-
def
logError(msg: ⇒ String): Unit
-
def
logInfo(msg: ⇒ String, throwable: Throwable): Unit
-
def
logInfo(msg: ⇒ String): Unit
-
def
logName: String
-
def
logTrace(msg: ⇒ String, throwable: Throwable): Unit
-
def
logTrace(msg: ⇒ String): Unit
-
def
logWarning(msg: ⇒ String, throwable: Throwable): Unit
-
def
logWarning(msg: ⇒ String): Unit
-
final
def
ne(arg0: AnyRef): Boolean
-
final
def
notify(): Unit
-
final
def
notifyAll(): Unit
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
-
def
toString(): String
-
final
def
wait(): Unit
-
final
def
wait(arg0: Long, arg1: Int): Unit
-
final
def
wait(arg0: Long): Unit
Inherited from Logging
Inherited from AnyRef
Inherited from Any
A sink that writes out results to parquet files. Each batch is written out to a unique directory. After all of the files in a batch have been successfully written, the list of file paths is appended to the log atomically. In the case of partial failures, some duplicate data may be present in the target directory, but only one copy of each file will be present in the log.