[SPARK-5454] More robust handling of self joins

Also I fix a bunch of bad output in test cases.

Author: Michael Armbrust <michael@databricks.com>

Closes #4520 from marmbrus/selfJoin and squashes the following commits:

4f4a85c [Michael Armbrust] comments
49c8e26 [Michael Armbrust] fix tests
6fc38de [Michael Armbrust] fix style
55d64b3 [Michael Armbrust] fix dataframe selfjoins

(cherry picked from commit a60d2b70adff3a8fb3bdfac226b1d86fdb443da4)
Signed-off-by: Michael Armbrust <michael@databricks.com>

1 files changed, 1 insertions, 3 deletions

diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/plans/PlanTest.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/plans/PlanTest.scala
index c4a1f899d8..7d609b9138 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/plans/PlanTest.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/plans/PlanTest.scala
@@ -33,11 +33,9 @@ class PlanTest extends FunSuite {
    * we must normalize them to check if two different queries are identical.
    */
   protected def normalizeExprIds(plan: LogicalPlan) = {
-    val list = plan.flatMap(_.expressions.flatMap(_.references).map(_.exprId.id))
-    val minId = if (list.isEmpty) 0 else list.min
     plan transformAllExpressions {
       case a: AttributeReference =>
-        AttributeReference(a.name, a.dataType, a.nullable)(exprId = ExprId(a.exprId.id - minId))
+        AttributeReference(a.name, a.dataType, a.nullable)(exprId = ExprId(0))
     }
   }