zzc created SPARK-6430:
--------------------------
Summary: Cannot resolve column correctlly when using left semi join
Key: SPARK-6430
URL: https://issues.apache.org/jira/browse/SPARK-6430
Project: Spark
Issue Type: Bug
Components: SQL
Affects Versions: 1.3.0
Environment: Spark 1.3.0 on yarn mode
Reporter: zzc
My code:
{quote}
case class TestData(key: Int, value: String)
case class TestData2(a: Int, b: Int)
import org.apache.spark.sql.execution.joins._
import sqlContext.implicits._
val testData = sc.parallelize(
(1 to 100).map(i => TestData(i, i.toString))).toDF()
testData.registerTempTable("testData")
val testData2 = sc.parallelize(
TestData2(1, 1) ::
TestData2(1, 2) ::
TestData2(2, 1) ::
TestData2(2, 2) ::
TestData2(3, 1) ::
TestData2(3, 2) :: Nil, 2).toDF()
testData2.registerTempTable("testData2")
//val tmp = sqlContext.sql("SELECT * FROM testData *LEFT SEMI JOIN* testData2
ON key = a ")
val tmp = sqlContext.sql("SELECT testData2.b, count(testData2.b) FROM testData
*LEFT SEMI JOIN* testData2 ON key = testData2.a group by testData2.b")
tmp.explain()
{quote}
Error log:
{quote}
org.apache.spark.sql.AnalysisException: cannot resolve 'testData2.b' given
input columns key, value; line 1 pos 108
at
org.apache.spark.sql.catalyst.analysis.package$AnalysisErrorAt.failAnalysis(package.scala:42)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$apply$3$$anonfun$apply$1.applyOrElse(CheckAnalysis.scala:48)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$apply$3$$anonfun$apply$1.applyOrElse(CheckAnalysis.scala:45)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:250)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:250)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:50)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:249)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$transformExpressionUp$1(QueryPlan.scala:103)
at
org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$2$$anonfun$apply$2.apply(QueryPlan.scala:117)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at scala.collection.immutable.List.foreach(List.scala:318)
{quote}
{quote}SELECT * FROM testData LEFT SEMI JOIN testData2 ON key = a{quote} is
correct,
{quote}
SELECT a FROM testData LEFT SEMI JOIN testData2 ON key = a
SELECT max(value) FROM testData LEFT SEMI JOIN testData2 ON key = a group by b
SELECT max(value) FROM testData LEFT SEMI JOIN testData2 ON key = testData2.a
group by testData2.b
SELECT testData2.b, count(testData2.b) FROM testData LEFT SEMI JOIN testData2
ON key = testData2.a group by testData2.b
{quote} are incorrect.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
