cloud-fan commented on code in PR #44375:
URL: https://github.com/apache/spark/pull/44375#discussion_r1429446785
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/python/UserDefinedPythonDataSource.scala:
##########
@@ -124,21 +128,78 @@ class PythonPartitionReaderFactory(
override def createReader(partition: InputPartition):
PartitionReader[InternalRow] = {
new PartitionReader[InternalRow] {
- private val outputIter = source.createPartitionReadIteratorInPython(
- partition.asInstanceOf[PythonInputPartition],
- pickledReadFunc,
- outputSchema,
- jobArtifactUUID)
+ // Dummy SQLMetrics. The result is manually reported via DSv2 interface
+ // via passing the value to `CustomTaskMetric`. Note that
`pythonOtherMetricsDesc`
+ // is not used when it is reported. It is to reuse existing Python
runner.
+ // See also `UserDefinedPythonDataSource.createPythonMetrics`.
+ private[this] val metrics: Map[String, SQLMetric] = {
+ PythonSQLMetrics.pythonSizeMetricsDesc.keys
+ .map(_ -> new SQLMetric("size", -1)).toMap ++
+ PythonSQLMetrics.pythonOtherMetricsDesc.keys
+ .map(_ -> new SQLMetric("sum", -1)).toMap
+ }
+
+ private val outputIter = {
+ val evaluatorFactory = source.createMapInBatchEvaluatorFactory(
+ pickledReadFunc,
+ outputSchema,
+ metrics,
+ jobArtifactUUID)
+
+ val part = partition.asInstanceOf[PythonInputPartition]
+ evaluatorFactory.createEvaluator().eval(
+ part.index, Iterator.single(InternalRow(part.pickedPartition)))
+ }
override def next(): Boolean = outputIter.hasNext
override def get(): InternalRow = outputIter.next()
override def close(): Unit = {}
+
+ override def currentMetricsValues(): Array[CustomTaskMetric] = {
+ source.createPythonTaskMetrics(metrics.map { case (k, v) => k ->
v.value})
+ }
}
}
}
+class PythonCustomMetric extends CustomMetric {
+ private var initName: String = _
+ private var initDescription: String = _
+ def initialize(n: String, d: String): Unit = {
Review Comment:
the caller side always call `initialize` right after instantiating
`PythonCustomMetric`, shall we just add constructor with parameters?
--
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]
