From 985d532812cf176d0e12b799c723f917282b6813 Mon Sep 17 00:00:00 2001
From: Sean Zhong <seanzhong@databricks.com>
Date: Thu, 2 Jun 2016 16:21:33 -0700
Subject: [PATCH] [SPARK-15734][SQL] Avoids printing internal row in explain
output
## What changes were proposed in this pull request?
This PR avoids printing internal rows in explain output for some operators.
**Before change:**
```
scala> (1 to 10).toSeq.map(_ => (1,2,3)).toDF().createTempView("df3")
scala> spark.sql("select * from df3 where 1=2").explain(true)
...
== Analyzed Logical Plan ==
_1: int, _2: int, _3: int
Project [_1#37,_2#38,_3#39]
+- Filter (1 = 2)
+- SubqueryAlias df3
+- LocalRelation [_1#37,_2#38,_3#39], [[0,1,2,3],[0,1,2,3],[0,1,2,3],[0,1,2,3],[0,1,2,3],[0,1,2,3],[0,1,2,3],[0,1,2,3],[0,1,2,3],[0,1,2,3]]
...
== Physical Plan ==
LocalTableScan [_1#37,_2#38,_3#39]
```
**After change:**
```
scala> spark.sql("select * from df3 where 1=2").explain(true)
...
== Analyzed Logical Plan ==
_1: int, _2: int, _3: int
Project [_1#58,_2#59,_3#60]
+- Filter (1 = 2)
+- SubqueryAlias df3
+- LocalRelation [_1#58,_2#59,_3#60]
...
== Physical Plan ==
LocalTableScan <empty>, [_1#58,_2#59,_3#60]
```
## How was this patch tested?
Manual test.
Author: Sean Zhong <seanzhong@databricks.com>
Closes #13471 from clockfly/verbose_breakdown_5.
---
.../spark/sql/catalyst/plans/logical/LocalRelation.scala | 8 +++++++-
.../org/apache/spark/sql/execution/ExistingRDD.scala | 2 ++
.../apache/spark/sql/execution/LocalTableScanExec.scala | 8 ++++++++
3 files changed, 17 insertions(+), 1 deletion(-)
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/LocalRelation.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/LocalRelation.scala
index 5813b74c77..87b8647655 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/LocalRelation.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/LocalRelation.scala
@@ -57,7 +57,13 @@ case class LocalRelation(output: Seq[Attribute], data: Seq[InternalRow] = Nil)
LocalRelation(output.map(_.newInstance()), data).asInstanceOf[this.type]
}
- override protected def stringArgs = Iterator(output)
+ override protected def stringArgs: Iterator[Any] = {
+ if (data.isEmpty) {
+ Iterator("<empty>", output)
+ } else {
+ Iterator(output)
+ }
+ }
override def sameResult(plan: LogicalPlan): Boolean = plan match {
case LocalRelation(otherOutput, otherData) =>
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/ExistingRDD.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/ExistingRDD.scala
index fef3255c73..b8b392608d 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/ExistingRDD.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/ExistingRDD.scala
@@ -91,6 +91,8 @@ private[sql] case class LogicalRDD(
case _ => false
}
+ override protected def stringArgs: Iterator[Any] = Iterator(output)
+
override def producedAttributes: AttributeSet = outputSet
@transient override lazy val statistics: Statistics = Statistics(
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/LocalTableScanExec.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/LocalTableScanExec.scala
index c5e78b0333..df2f238d8c 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/LocalTableScanExec.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/LocalTableScanExec.scala
@@ -48,6 +48,14 @@ private[sql] case class LocalTableScanExec(
}
}
+ override protected def stringArgs: Iterator[Any] = {
+ if (rows.isEmpty) {
+ Iterator("<empty>", output)
+ } else {
+ Iterator(output)
+ }
+ }
+
override def executeCollect(): Array[InternalRow] = {
unsafeRows
}
--
GitLab