viirya commented on a change in pull request #30245:
URL: https://github.com/apache/spark/pull/30245#discussion_r520289276
##########
File path:
sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/SubexpressionEliminationSuite.scala
##########
@@ -146,20 +146,111 @@ class SubexpressionEliminationSuite extends
SparkFunSuite {
equivalence.addExprTree(add)
// the `two` inside `fallback` should not be added
assert(equivalence.getAllEquivalentExprs.count(_.size > 1) == 0)
- assert(equivalence.getAllEquivalentExprs.count(_.size == 1) == 3) // add,
two, explode
+ assert(equivalence.getAllEquivalentExprs.count(_.size == 1) == 3) // add,
two, explode
}
- test("Children of conditional expressions") {
- val condition = And(Literal(true), Literal(false))
+ test("Children of conditional expressions: If") {
val add = Add(Literal(1), Literal(2))
- val ifExpr = If(condition, add, add)
+ val condition = GreaterThan(add, Literal(3))
- val equivalence = new EquivalentExpressions
- equivalence.addExprTree(ifExpr)
- // the `add` inside `If` should not be added
- assert(equivalence.getAllEquivalentExprs.count(_.size > 1) == 0)
- // only ifExpr and its predicate expression
- assert(equivalence.getAllEquivalentExprs.count(_.size == 1) == 2)
+ val ifExpr1 = If(condition, add, add)
+ val equivalence1 = new EquivalentExpressions
+ equivalence1.addExprTree(ifExpr1)
+
+ // `add` is in both two branches of `If` and predicate.
+ assert(equivalence1.getAllEquivalentExprs.count(_.size == 2) == 1)
+ assert(equivalence1.getAllEquivalentExprs.filter(_.size == 2).head ==
Seq(add, add))
+ // one-time expressions: only ifExpr and its predicate expression
+ assert(equivalence1.getAllEquivalentExprs.count(_.size == 1) == 2)
+ assert(equivalence1.getAllEquivalentExprs.filter(_.size == 1).head ==
Seq(ifExpr1))
+ assert(equivalence1.getAllEquivalentExprs.filter(_.size == 1).last ==
Seq(condition))
+
+ // Repeated `add` is only in one branch, so we don't count it.
+ val ifExpr2 = If(condition, Add(Literal(1), Literal(3)), Add(add, add))
+ val equivalence2 = new EquivalentExpressions
+ equivalence2.addExprTree(ifExpr2)
+
+ assert(equivalence2.getAllEquivalentExprs.count(_.size > 1) == 0)
+ assert(equivalence2.getAllEquivalentExprs.count(_.size == 1) == 3)
+
+ val ifExpr3 = If(condition, ifExpr1, ifExpr1)
+ val equivalence3 = new EquivalentExpressions
+ equivalence3.addExprTree(ifExpr3)
+
+ // `add`: 2, `condition`: 2
+ assert(equivalence3.getAllEquivalentExprs.count(_.size == 2) == 2)
+ assert(equivalence3.getAllEquivalentExprs.filter(_.size == 2).head ==
Seq(add, add))
+ assert(equivalence3.getAllEquivalentExprs.filter(_.size == 2).last ==
Seq(condition, condition))
+
+ // `ifExpr1`, `ifExpr3`
+ assert(equivalence3.getAllEquivalentExprs.count(_.size == 1) == 2)
+ assert(equivalence3.getAllEquivalentExprs.filter(_.size == 1).head ==
Seq(ifExpr1))
+ assert(equivalence3.getAllEquivalentExprs.filter(_.size == 1).last ==
Seq(ifExpr3))
+ }
+
+ test("Children of conditional expressions: CaseWhen") {
+ val add1 = Add(Literal(1), Literal(2))
+ val add2 = Add(Literal(2), Literal(3))
+ val conditions1 = (GreaterThan(add2, Literal(3)), add1) ::
+ (GreaterThan(add2, Literal(4)), add1) ::
+ (GreaterThan(add2, Literal(5)), add1) :: Nil
+
+ val caseWhenExpr1 = CaseWhen(conditions1, None)
+ val equivalence1 = new EquivalentExpressions
+ equivalence1.addExprTree(caseWhenExpr1)
+
+ // `add2` is repeatedly in all conditions.
Review comment:
We treat the first condition specially because it is definitely run. So
it counts one for `add2`. Other conditions all contain `add2` so it counts for
one. That is where the count 2 comes from for `add2`.
For `add1`, although all values contain it, it is definitely run, so we
count it one. If no other expression contains `add1`, we don't extract
subexpression for `add1` as it will run just once (we only run one value of
`CaseWhen`).
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
