diff options
author | Yin Huai <yhuai@databricks.com> | 2015-08-12 21:24:15 -0700 |
---|---|---|
committer | Reynold Xin <rxin@databricks.com> | 2015-08-12 21:24:15 -0700 |
commit | 2278219054314f1d31ffc358a59aa5067f9f5de9 (patch) | |
tree | dbc8355c5f048b556f5e9cb688ef7081af90a61d | |
parent | 2fb4901b71cee65d40a43e61e3f4411c30cdefc3 (diff) | |
download | spark-2278219054314f1d31ffc358a59aa5067f9f5de9.tar.gz spark-2278219054314f1d31ffc358a59aa5067f9f5de9.tar.bz2 spark-2278219054314f1d31ffc358a59aa5067f9f5de9.zip |
[SPARK-9920] [SQL] The simpleString of TungstenAggregate does not show its output
https://issues.apache.org/jira/browse/SPARK-9920
Taking `sqlContext.sql("select i, sum(j1) as sum from testAgg group by i").explain()` as an example, the output of our current master is
```
== Physical Plan ==
TungstenAggregate(key=[i#0], value=[(sum(cast(j1#1 as bigint)),mode=Final,isDistinct=false)]
TungstenExchange hashpartitioning(i#0)
TungstenAggregate(key=[i#0], value=[(sum(cast(j1#1 as bigint)),mode=Partial,isDistinct=false)]
Scan ParquetRelation[file:/user/hive/warehouse/testagg][i#0,j1#1]
```
With this PR, the output will be
```
== Physical Plan ==
TungstenAggregate(key=[i#0], functions=[(sum(cast(j1#1 as bigint)),mode=Final,isDistinct=false)], output=[i#0,sum#18L])
TungstenExchange hashpartitioning(i#0)
TungstenAggregate(key=[i#0], functions=[(sum(cast(j1#1 as bigint)),mode=Partial,isDistinct=false)], output=[i#0,currentSum#22L])
Scan ParquetRelation[file:/user/hive/warehouse/testagg][i#0,j1#1]
```
Author: Yin Huai <yhuai@databricks.com>
Closes #8150 from yhuai/SPARK-9920.
2 files changed, 9 insertions, 4 deletions
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/SortBasedAggregate.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/SortBasedAggregate.scala index ab26f9c58a..f4c14a9b35 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/SortBasedAggregate.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/SortBasedAggregate.scala @@ -108,6 +108,10 @@ case class SortBasedAggregate( override def simpleString: String = { val allAggregateExpressions = nonCompleteAggregateExpressions ++ completeAggregateExpressions - s"""SortBasedAggregate ${groupingExpressions} ${allAggregateExpressions}""" + + val keyString = groupingExpressions.mkString("[", ",", "]") + val functionString = allAggregateExpressions.mkString("[", ",", "]") + val outputString = output.mkString("[", ",", "]") + s"SortBasedAggregate(key=$keyString, functions=$functionString, output=$outputString)" } } diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/TungstenAggregate.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/TungstenAggregate.scala index c40ca97379..99f51ba5b6 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/TungstenAggregate.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/TungstenAggregate.scala @@ -127,11 +127,12 @@ case class TungstenAggregate( testFallbackStartsAt match { case None => val keyString = groupingExpressions.mkString("[", ",", "]") - val valueString = allAggregateExpressions.mkString("[", ",", "]") - s"TungstenAggregate(key=$keyString, value=$valueString" + val functionString = allAggregateExpressions.mkString("[", ",", "]") + val outputString = output.mkString("[", ",", "]") + s"TungstenAggregate(key=$keyString, functions=$functionString, output=$outputString)" case Some(fallbackStartsAt) => s"TungstenAggregateWithControlledFallback $groupingExpressions " + - s"$allAggregateExpressions fallbackStartsAt=$fallbackStartsAt" + s"$allAggregateExpressions $resultExpressions fallbackStartsAt=$fallbackStartsAt" } } } |