diff options
author | Keuntae Park <sirpkt@apache.org> | 2015-07-08 14:29:52 -0700 |
---|---|---|
committer | Michael Armbrust <michael@databricks.com> | 2015-07-08 14:29:52 -0700 |
commit | f031543782e8f0f5b6a4471ba1c1d5c53efbe5cd (patch) | |
tree | 3253ee6cb9cd58387fae6e5cf794ba993c6146cb /sql | |
parent | 2b40365d76b7d9d382ad5077cdf979906bca17f2 (diff) | |
download | spark-f031543782e8f0f5b6a4471ba1c1d5c53efbe5cd.tar.gz spark-f031543782e8f0f5b6a4471ba1c1d5c53efbe5cd.tar.bz2 spark-f031543782e8f0f5b6a4471ba1c1d5c53efbe5cd.zip |
[SPARK-8783] [SQL] CTAS with WITH clause does not work
Currently, CTESubstitution only handles the case that WITH is on the top of the plan.
I think it SHOULD handle the case that WITH is child of CTAS.
This patch simply changes 'match' to 'transform' for recursive search of WITH in the plan.
Author: Keuntae Park <sirpkt@apache.org>
Closes #7180 from sirpkt/SPARK-8783 and squashes the following commits:
e4428f0 [Keuntae Park] Merge remote-tracking branch 'upstream/master' into CTASwithWITH
1671c77 [Keuntae Park] WITH clause can be inside CTAS
Diffstat (limited to 'sql')
-rw-r--r-- | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala | 2 | ||||
-rw-r--r-- | sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala | 18 |
2 files changed, 19 insertions, 1 deletions
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala index 15e84e68b9..3fdc6d62bc 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala @@ -85,7 +85,7 @@ class Analyzer( */ object CTESubstitution extends Rule[LogicalPlan] { // TODO allow subquery to define CTE - def apply(plan: LogicalPlan): LogicalPlan = plan match { + def apply(plan: LogicalPlan): LogicalPlan = plan transform { case With(child, relations) => substituteCTE(child, relations) case other => other } diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala index bf9f2ecd51..05a1f0094e 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala @@ -159,6 +159,24 @@ class SQLQuerySuite extends QueryTest { checkAnswer(query, Row(1, 1) :: Nil) } + test("CTAS with WITH clause") { + val df = Seq((1, 1)).toDF("c1", "c2") + df.registerTempTable("table1") + + sql( + """ + |CREATE TABLE with_table1 AS + |WITH T AS ( + | SELECT * + | FROM table1 + |) + |SELECT * + |FROM T + """.stripMargin) + val query = sql("SELECT * FROM with_table1") + checkAnswer(query, Row(1, 1) :: Nil) + } + test("explode nested Field") { Seq(NestedArray1(NestedArray2(Seq(1, 2, 3)))).toDF.registerTempTable("nestedArray") checkAnswer( |