Skip to content

[SPARK-57402][SQL][FOLLOWUP] Allow pipeline definitions in batch operation checks #57345

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
cloud-fan wants to merge 2 commits into
base: master
Choose a base branch
from
+51 −0
Open

[SPARK-57402][SQL][FOLLOWUP] Allow pipeline definitions in batch operation checks #57345

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3f989bb
[SPARK-57402][SQL][FOLLOWUP] Allow pipeline definitions in batch oper…
cloud-fan Jul 18, 2026
f8ecc01
✅ test(sql): Cover AUTO CDC batch validation
cloud-fan Jul 20, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 12 additions & 0 deletions ...t/src/main/scala/org/apache/spark/sql/catalyst/analysis/UnsupportedOperationChecker.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,7 +37,19 @@ import org.apache.spark.sql.streaming.{GroupStateTimeout, OutputMode}
*/
object UnsupportedOperationChecker extends Logging {

// Pipeline definition commands are always root plans and must reach SparkStrategies.Pipelines
// for their dedicated errors. Materialized views are intentionally excluded because their
// queries are batch queries and must continue to reject streaming sources here.
private def isPipelineDefinition(plan: LogicalPlan): Boolean = plan match {
case _: CreateStreamingTableAsSelect | _: CreateStreamingTableAutoCdc |
_: CreateFlowCommand => true
case _ => false
}

def checkForBatch(plan: LogicalPlan): Unit = {
if (isPipelineDefinition(plan)) {
return
}
plan.foreachUp {
case p if p.isStreaming =>
throwError("Queries with streaming sources must be executed with writeStream.start(), or " +
Expand Down
39 changes: 39 additions & 0 deletions ...st/src/test/scala/org/apache/spark/sql/catalyst/analysis/UnsupportedOperationsSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,6 +65,45 @@ class UnsupportedOperationsSuite extends SparkFunSuite with SQLHelper {
streamRelation.select($"`count(*)`"),
Seq("with streaming source", "start"))

private val emptyTableSpec = TableSpec(
properties = Map.empty,
provider = None,
options = Map.empty,
location = None,
comment = None,
collation = None,
serde = None,
external = false)

assertSupportedInBatchPlan(
"streaming table definition with streaming source",
CreateStreamingTableAsSelect(
name = batchRelation,
columns = Nil,
partitioning = Nil,
tableSpec = emptyTableSpec,
query = streamRelation,
originalText = "",
ifNotExists = false))

assertSupportedInBatchPlan(
"flow definition with streaming source",
CreateFlowCommand(batchRelation, streamRelation, comment = None))

assertSupportedInBatchPlan(
"AUTO CDC streaming table definition with streaming source",
CreateStreamingTableAutoCdc(
name = batchRelation,
columns = Nil,
partitioning = Nil,
tableSpec = emptyTableSpec,
ifNotExists = false,
source = streamRelation,
keys = Nil,
deleteCondition = None,
sequenceByExpr = attribute,
includeColumns = None,
excludeColumns = None))

/*
=======================================================================================
Expand Down