From 77cc25fb7473d8a06b727d2ba5ee62db1c651cf8 Mon Sep 17 00:00:00 2001
From: Zhongshuai Pei <799203320@qq.com>
Date: Thu, 30 Apr 2015 15:22:13 -0700
Subject: [PATCH] [SPARK-7267][SQL]Push down Project when it's child is Limit
SQL
```
select key from (select key,value from t1 limit 100) t2 limit 10
```
Optimized Logical Plan before modifying
```
== Optimized Logical Plan ==
Limit 10
Project key#228
Limit 100
MetastoreRelation default, t1, None
```
Optimized Logical Plan after modifying
```
== Optimized Logical Plan ==
Limit 10
Limit 100
Project key#228
MetastoreRelation default, t1, None
```
After this, we can combine limits
Author: Zhongshuai Pei <799203320@qq.com>
Author: DoingDone9 <799203320@qq.com>
Closes #5797 from DoingDone9/ProjectLimit and squashes the following commits:
70d0fca [Zhongshuai Pei] Update FilterPushdownSuite.scala
dc83ae9 [Zhongshuai Pei] Update FilterPushdownSuite.scala
485c61c [Zhongshuai Pei] Update Optimizer.scala
f03fe7f [Zhongshuai Pei] Merge pull request #12 from apache/master
f12fa50 [Zhongshuai Pei] Merge pull request #10 from apache/master
f61210c [Zhongshuai Pei] Merge pull request #9 from apache/master
34b1a9a [Zhongshuai Pei] Merge pull request #8 from apache/master
802261c [DoingDone9] Merge pull request #7 from apache/master
d00303b [DoingDone9] Merge pull request #6 from apache/master
98b134f [DoingDone9] Merge pull request #5 from apache/master
161cae3 [DoingDone9] Merge pull request #4 from apache/master
c87e8b6 [DoingDone9] Merge pull request #3 from apache/master
cb1852d [DoingDone9] Merge pull request #2 from apache/master
c3f046f [DoingDone9] Merge pull request #1 from apache/master
---
.../spark/sql/catalyst/optimizer/Optimizer.scala | 3 +++
.../catalyst/optimizer/FilterPushdownSuite.scala | 16 ++++++++++++++++
2 files changed, 19 insertions(+)
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
index 485761dd85..63669e970b 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
@@ -170,6 +170,9 @@ object ColumnPruning extends Rule[LogicalPlan] {
Project(substitutedProjection, child)
+ case Project(projectList, Limit(exp, child)) =>
+ Limit(exp, Project(projectList, child))
+
// Eliminate no-op Projects
case Project(projectList, child) if child.output == projectList => child
}
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/FilterPushdownSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/FilterPushdownSuite.scala
index aa9708b164..2ad73941ab 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/FilterPushdownSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/FilterPushdownSuite.scala
@@ -90,7 +90,23 @@ class FilterPushdownSuite extends PlanTest {
comparePlans(optimized, correctAnswer)
}
+
+ test("column pruning for Project(ne, Limit)") {
+ val originalQuery =
+ testRelation
+ .select('a,'b)
+ .limit(2)
+ .select('a)
+
+ val optimized = Optimize.execute(originalQuery.analyze)
+ val correctAnswer =
+ testRelation
+ .select('a)
+ .limit(2).analyze
+ comparePlans(optimized, correctAnswer)
+ }
+
// After this line is unimplemented.
test("simple push down") {
val originalQuery =
--
GitLab