cloud-fan commented on a change in pull request #34053:
URL: https://github.com/apache/spark/pull/34053#discussion_r716520340
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicLogicalOperators.scala
##########
@@ -1597,3 +1597,119 @@ case class LateralJoin(
copy(left = newChild)
}
}
+
+/**
+ * A logical plan for as-of join.
+ */
+case class AsOfJoin(
+ left: LogicalPlan,
+ right: LogicalPlan,
+ asOfCondition: Expression,
+ condition: Option[Expression],
+ joinType: JoinType,
+ orderExpression: Expression,
+ toleranceAssertion: Option[Expression]) extends BinaryNode {
+
+ require(Seq(Inner, LeftOuter).contains(joinType),
+ s"Unsupported as-of join type $joinType")
+
+ override protected def stringArgs: Iterator[Any] = super.stringArgs.take(5)
+
+ override def output: Seq[Attribute] = {
+ joinType match {
+ case LeftOuter =>
+ left.output ++ right.output.map(_.withNullability(true))
+ case _ =>
+ left.output ++ right.output
+ }
+ }
+
+ def duplicateResolved: Boolean =
left.outputSet.intersect(right.outputSet).isEmpty
+
+ override lazy val resolved: Boolean = {
+ childrenResolved &&
+ expressions.forall(_.resolved) &&
+ duplicateResolved &&
+ asOfCondition.dataType == BooleanType &&
+ condition.forall(_.dataType == BooleanType) &&
+ toleranceAssertion.forall { assertion =>
+ assertion.foldable && assertion.eval().asInstanceOf[Boolean]
+ }
+ }
+
+ final override val nodePatterns: Seq[TreePattern] = Seq(AS_OF_JOIN)
+
+ override protected def withNewChildrenInternal(
+ newLeft: LogicalPlan, newRight: LogicalPlan): AsOfJoin = {
+ copy(left = newLeft, right = newRight)
+ }
+}
+
+object AsOfJoin {
+
+ def apply(
+ left: LogicalPlan,
+ right: LogicalPlan,
+ leftAsOf: Expression,
+ rightAsOf: Expression,
+ condition: Option[Expression],
+ joinType: JoinType,
+ tolerance: Option[Expression],
+ allowExactMatches: Boolean,
+ direction: AsOfJoinDirection): AsOfJoin = {
+ val asOfCond = makeAsOfCond(leftAsOf, rightAsOf, tolerance,
allowExactMatches, direction)
+ val orderingExpr = makeOrderingExpr(leftAsOf, rightAsOf, direction)
+ AsOfJoin(left, right, asOfCond, condition, joinType,
+ orderingExpr, tolerance.map(t => GreaterThanOrEqual(t,
Literal.default(t.dataType))))
+ }
+
+ private def makeAsOfCond(
+ leftAsOf: Expression,
+ rightAsOf: Expression,
+ tolerance: Option[Expression],
+ allowExactMatches: Boolean,
+ direction: AsOfJoinDirection): Expression = {
+ val base = (allowExactMatches, direction) match {
+ case (true, Backward) => GreaterThanOrEqual(leftAsOf, rightAsOf)
+ case (false, Backward) => GreaterThan(leftAsOf, rightAsOf)
+ case (true, Forward) => LessThanOrEqual(leftAsOf, rightAsOf)
+ case (false, Forward) => LessThan(leftAsOf, rightAsOf)
+ case (true, Nearest) => Literal.TrueLiteral
+ case (false, Nearest) => Not(EqualTo(leftAsOf, rightAsOf))
+ }
+ tolerance match {
+ case Some(tolerance) =>
+ (allowExactMatches, direction) match {
+ case (true, Backward) =>
+ And(base, GreaterThanOrEqual(rightAsOf, Subtract(leftAsOf,
tolerance)))
+ case (false, Backward) =>
+ And(base, GreaterThan(rightAsOf, Subtract(leftAsOf, tolerance)))
+ case (true, Forward) =>
+ And(base, LessThanOrEqual(rightAsOf, Add(leftAsOf, tolerance)))
Review comment:
shall we use `TimeAdd` expression in case the `tolerance` is interval
type?
--
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]
