cloud-fan commented on code in PR #47403:
URL: https://github.com/apache/spark/pull/47403#discussion_r1688094627
##########
sql/core/src/main/scala/org/apache/spark/sql/SparkSession.scala:
##########
@@ -650,14 +657,27 @@ class SparkSession private(
private[sql] def sql(sqlText: String, args: Array[_], tracker:
QueryPlanningTracker): DataFrame =
withActive {
val plan = tracker.measurePhase(QueryPlanningTracker.PARSING) {
- val parsedPlan = sessionState.sqlParser.parsePlan(sqlText)
- if (args.nonEmpty) {
- PosParameterizedQuery(parsedPlan,
args.map(lit(_).expr).toImmutableArraySeq)
- } else {
- parsedPlan
+ val parsedPlan = sessionState.sqlParser.parseScript(sqlText)
+ parsedPlan match {
+ case CompoundBody(Seq(singleStmtPlan: SingleStatement), label) if
args.nonEmpty =>
+ CompoundBody(Seq(SingleStatement(
+ PosParameterizedQuery(
+ singleStmtPlan.parsedPlan,
args.map(lit(_).expr).toImmutableArraySeq))), label)
+ case p =>
+ assert(args.isEmpty, "Named parameters are not supported for batch
queries")
+ p
}
}
- Dataset.ofRows(self, plan, tracker)
+
+ plan match {
+ case CompoundBody(Seq(singleStmtPlan: SingleStatement), _) =>
+ Dataset.ofRows(self, singleStmtPlan.parsedPlan, tracker)
+ case _ =>
+ // execute the plan directly if it is not a single statement
+ val lastRow = executeScript(plan).foldLeft(Array.empty[Row])((_,
next) => next)
+ val attributes = DataTypeUtils.toAttributes(lastRow.head.schema)
+ Dataset.ofRows(self, LocalRelation.fromExternalRows(attributes,
lastRow.toIndexedSeq))
Review Comment:
> all statements (including SELECTs) need to be executed eagerly
We need to materialize the query result but we don't need to collect the
result at the driver side (except for the last statement). E.g. we can write
the query result to a noop sink.
--
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: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
