Skip to content

[SPARK-20636] Add the rule TransposeWindow to the optimization batch #23222

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

Closed
gatorsmile wants to merge 5 commits into from
Closed

[SPARK-20636] Add the rule TransposeWindow to the optimization batch #23222

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
1270e89
add the rule TransposeWindow to the batch
gatorsmile Dec 5, 2018
dc39b2a
fix.
gatorsmile Dec 6, 2018
d540120
fix
gatorsmile Dec 17, 2018
7fa8643
Merge remote-tracking branch 'upstream/master' into followupSPARK-20636
gatorsmile Dec 17, 2018
083c726
fix
gatorsmile Dec 17, 2018
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
1 change: 1 addition & 0 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,6 +73,7 @@ abstract class Optimizer(sessionCatalog: SessionCatalog)
CombineLimits,
CombineUnions,
// Constant folding and strength reduction
TransposeWindow,
NullPropagation,
ConstantPropagation,
FoldablePropagation,
Expand Down
38 changes: 26 additions & 12 deletions sql/core/src/test/scala/org/apache/spark/sql/DataFrameWindowFunctionsSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,8 @@ package org.apache.spark.sql
import org.scalatest.Matchers.the

import org.apache.spark.TestUtils.{assertNotSpilled, assertSpilled}
import org.apache.spark.sql.catalyst.optimizer.TransposeWindow
import org.apache.spark.sql.execution.exchange.Exchange
import org.apache.spark.sql.expressions.{MutableAggregationBuffer, UserDefinedAggregateFunction, Window}
import org.apache.spark.sql.functions._
import org.apache.spark.sql.internal.SQLConf
Expand Down Expand Up @@ -668,18 +670,30 @@ class DataFrameWindowFunctionsSuite extends QueryTest with SharedSQLContext {
("S2", "P2", 300)
).toDF("sno", "pno", "qty")

val w1 = Window.partitionBy("sno")
val w2 = Window.partitionBy("sno", "pno")

checkAnswer(
df.select($"sno", $"pno", $"qty", sum($"qty").over(w2).alias("sum_qty_2"))
.select($"sno", $"pno", $"qty", col("sum_qty_2"), sum("qty").over(w1).alias("sum_qty_1")),
Seq(
Row("S1", "P1", 100, 800, 800),
Row("S1", "P1", 700, 800, 800),
Row("S2", "P1", 200, 200, 500),
Row("S2", "P2", 300, 300, 500)))

Seq(true, false).foreach { transposeWindowEnabled =>
val excludedRules = if (transposeWindowEnabled) "" else TransposeWindow.ruleName
withSQLConf(SQLConf.OPTIMIZER_EXCLUDED_RULES.key -> excludedRules) {
val w1 = Window.partitionBy("sno")
val w2 = Window.partitionBy("sno", "pno")

val select = df.select($"sno", $"pno", $"qty", sum($"qty").over(w2).alias("sum_qty_2"))
.select($"sno", $"pno", $"qty", col("sum_qty_2"), sum("qty").over(w1).alias("sum_qty_1"))

val expectedNumExchanges = if (transposeWindowEnabled) 1 else 2
val actualNumExchanges = select.queryExecution.executedPlan.collect {
case e: Exchange => e
}.length
assert(actualNumExchanges == expectedNumExchanges)

checkAnswer(
select,
Seq(
Row("S1", "P1", 100, 800, 800),
Row("S1", "P1", 700, 800, 800),
Row("S2", "P1", 200, 200, 500),
Row("S2", "P2", 300, 300, 500)))
}
}
}

test("NaN and -0.0 in window partition keys") {
Expand Down