AnishMahto commented on code in PR #56124:
URL: https://github.com/apache/spark/pull/56124#discussion_r3307732017
##########
sql/connect/server/src/main/scala/org/apache/spark/sql/connect/pipelines/PipelinesHandler.scala:
##########
@@ -388,13 +400,107 @@ private[connect] object PipelinesHandler extends Logging
{
objectName = Option(flowIdentifier.unquotedString),
language = Some(Python()))))
case proto.PipelineCommand.DefineFlow.DetailsCase.AUTO_CDC_FLOW_DETAILS
=>
- throw new UnsupportedOperationException("AutoCdcFlowDetails is not yet
implemented.")
+ val autoCdcDetails = flow.getAutoCdcFlowDetails
+ graphElementRegistry.registerFlow(
+ buildAutoCdcFlow(
+ autoCdcDetails = autoCdcDetails,
+ flow = flow,
+ flowIdentifier = flowIdentifier,
+ destinationIdentifier = destinationIdentifier,
+ defaultCatalog = defaultCatalog,
+ defaultDatabase = defaultDatabase,
+ transformExpressionFunc = transformExpressionFunc))
case other =>
throw new UnsupportedOperationException(s"Unsupported DefineFlow
details case: $other")
}
flowIdentifier
}
+ /**
+ * Build an [[AutoCdcFlow]] from the proto-supplied AutoCDC flow details.
+ *
+ * The flow's source expression is encoded by the Python client as a
streaming-table name; we
+ * model that on the server side as a streaming [[UnresolvedRelation]] so
that pipelines flow
+ * analysis (which already handles `STREAM(t)` references) can resolve it
against the rest of
+ * the dataflow graph.
+ */
+ private def buildAutoCdcFlow(
+ autoCdcDetails: proto.PipelineCommand.DefineFlow.AutoCdcFlowDetails,
+ flow: proto.PipelineCommand.DefineFlow,
+ flowIdentifier: TableIdentifier,
+ destinationIdentifier: TableIdentifier,
+ defaultCatalog: String,
+ defaultDatabase: String,
+ transformExpressionFunc: proto.Expression => Expression): AutoCdcFlow = {
+ val sourcePlan: LogicalPlan = UnresolvedRelation(
+ multipartIdentifier =
scala.collection.immutable.Seq(autoCdcDetails.getSource),
+ isStreaming = true
+ )
Review Comment:
Good catch. Multipart `source` _should_ be supported, this was a miss on my
part. Fixed the parsing so that it actually works for dotted identifiers, and
added `AutoCDC API: multi-part `source` resolves to the corresponding qualified
dataset` test to `PythonPipelineSuite`.
--
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]
