chaoqin-li1123 commented on code in PR #45977:
URL: https://github.com/apache/spark/pull/45977#discussion_r1563028108
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonStreamingSourceRunner.scala:
##########
@@ -199,4 +223,30 @@ class PythonStreamingSourceRunner(
logError("Exception when trying to kill worker", e)
}
}
+
+ private val allocator = ArrowUtils.rootAllocator.newChildAllocator(
+ s"stream reader for $pythonExec", 0, Long.MaxValue)
+
+ def readArrowRecordBatches(): Iterator[InternalRow] = {
+ assert(dataIn.readInt() == SpecialLengths.START_ARROW_STREAM)
+ val reader = new ArrowStreamReader(dataIn, allocator)
+ val root = reader.getVectorSchemaRoot()
+ // When input is empty schema can't be read.
+ val schema = ArrowUtils.fromArrowSchema(root.getSchema())
+ assert(schema == outputSchema)
+
+ val vectors = root.getFieldVectors().asScala.map { vector =>
+ new ArrowColumnVector(vector)
+ }.toArray[ColumnVector]
+ val rows = ArrayBuffer[InternalRow]()
Review Comment:
We can't do lazy initialization here because we need to send the data from
python process to JVM, the communication is synchronous.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
