cloud-fan commented on code in PR #46143:
URL: https://github.com/apache/spark/pull/46143#discussion_r2838239392
##########
sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/FilterPushdownSuite.scala:
##########
@@ -152,17 +156,125 @@ class FilterPushdownSuite extends PlanTest {
test("can't push without rewrite") {
val originalQuery =
testRelation
- .select($"a" + $"b" as "e")
+ .select($"a" + $"b" as "e", $"a" - $"b" as "f")
.where($"e" === 1)
.analyze
val optimized = Optimize.execute(originalQuery.analyze)
val correctAnswer =
testRelation
.where($"a" + $"b" === 1)
- .select($"a" + $"b" as "e")
+ .select($"a" + $"b" as "e", $"a" - $"b" as "f")
+ .analyze
+
+ comparePlans(optimized, correctAnswer)
+ }
+
+ test("SPARK-47672: Do double evaluation when configured") {
+ withSQLConf(SQLConf.AVOID_DOUBLE_FILTER_EVAL.key -> "false") {
+ val originalQuery = testStringRelation
+ .select($"a", $"e".rlike("magic") as "f", $"e".rlike("notmagic") as
"j", $"b")
+ .where($"a" > 5 && $"f")
+ .analyze
+
+ val optimized = Optimize.execute(originalQuery)
+
+ val correctAnswer = testStringRelation
+ .where($"a" > 5 && $"e".rlike("magic"))
+ .select($"a", $"e".rlike("magic") as "f", $"e".rlike("notmagic") as
"j", $"b")
.analyze
+ comparePlans(optimized, correctAnswer)
+ }
+ }
+
+ test("SPARK-47672: Make sure that we handle the case where everything is
expensive") {
+ val originalQuery = testStringRelation
+ .select($"e".rlike("magic") as "f")
+ .where($"f")
+ .analyze
+
+ val optimized = Optimize.execute(originalQuery)
+
+ val correctAnswer = testStringRelation
+ .select($"e".rlike("magic") as "f")
+ .where($"f")
+ .analyze
+
+ comparePlans(optimized, correctAnswer)
+ }
+
+ // Case 3: Filter references expensive to compute references.
+ test("SPARK-47672: Avoid double evaluation with projections can't push past
certain items") {
+ val originalQuery = testStringRelation
+ .select($"a", $"e".rlike("magic") as "f")
+ .where($"a" > 5 || $"f")
+ .analyze
+
+ val optimized = Optimize.execute(originalQuery)
+
+ val correctAnswer = testStringRelation
+ .select($"a", $"e".rlike("magic") as "f")
+ .where($"a" > 5 || $"f")
+ .analyze
+
+ comparePlans(optimized, correctAnswer)
+ }
+
+ // Case 1: Multiple filters that don't reference any projection aliases -
all should be pushed
+ test("SPARK-47672: Case 1 - multiple filters not referencing projection
aliases") {
+ val originalQuery = testStringRelation
+ .select($"a" as "c", $"e".rlike("magic") as "f", $"b" as "d")
+ .where($"a" > 5 && $"b" < 10)
Review Comment:
The analyzer can add missing columns into `Project`, but for test shall we
explicitly select column `a` and `b` for clarity?
--
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]
