Repository: spark Updated Branches: refs/heads/master 9e7725c86 -> 78d18fdba
[SPARK-2658][SQL] Add rule for true = 1. Author: Michael Armbrust <mich...@databricks.com> Closes #1556 from marmbrus/fixBooleanEqualsOne and squashes the following commits: ad8edd4 [Michael Armbrust] Add rule for true = 1 and false = 0. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/78d18fdb Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/78d18fdb Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/78d18fdb Branch: refs/heads/master Commit: 78d18fdbaa62d8ed235c29b2e37fd6607263c639 Parents: 9e7725c Author: Michael Armbrust <mich...@databricks.com> Authored: Wed Jul 23 22:52:49 2014 -0700 Committer: Reynold Xin <r...@apache.org> Committed: Wed Jul 23 22:52:49 2014 -0700 ---------------------------------------------------------------------- .../spark/sql/catalyst/analysis/HiveTypeCoercion.scala | 12 +++++++++++- .../boolean = number-0-6b6975fa1892cc48edd87dc0df48a7c0 | 1 + .../spark/sql/hive/execution/HiveQuerySuite.scala | 12 ++++++++++++ 3 files changed, 24 insertions(+), 1 deletion(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/78d18fdb/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/HiveTypeCoercion.scala ---------------------------------------------------------------------- diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/HiveTypeCoercion.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/HiveTypeCoercion.scala index 76ddeba..9887856 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/HiveTypeCoercion.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/HiveTypeCoercion.scala @@ -231,10 +231,20 @@ trait HiveTypeCoercion { * Changes Boolean values to Bytes so that expressions like true < false can be Evaluated. */ object BooleanComparisons extends Rule[LogicalPlan] { + val trueValues = Seq(1, 1L, 1.toByte, 1.toShort, BigDecimal(1)).map(Literal(_)) + val falseValues = Seq(0, 0L, 0.toByte, 0.toShort, BigDecimal(0)).map(Literal(_)) + def apply(plan: LogicalPlan): LogicalPlan = plan transformAllExpressions { // Skip nodes who's children have not been resolved yet. case e if !e.childrenResolved => e - // No need to change EqualTo operators as that actually makes sense for boolean types. + + // Hive treats (true = 1) as true and (false = 0) as true. + case EqualTo(l @ BooleanType(), r) if trueValues.contains(r) => l + case EqualTo(l, r @ BooleanType()) if trueValues.contains(l) => r + case EqualTo(l @ BooleanType(), r) if falseValues.contains(r) => Not(l) + case EqualTo(l, r @ BooleanType()) if falseValues.contains(l) => Not(r) + + // No need to change other EqualTo operators as that actually makes sense for boolean types. case e: EqualTo => e // Otherwise turn them to Byte types so that there exists and ordering. case p: BinaryComparison http://git-wip-us.apache.org/repos/asf/spark/blob/78d18fdb/sql/hive/src/test/resources/golden/boolean = number-0-6b6975fa1892cc48edd87dc0df48a7c0 ---------------------------------------------------------------------- diff --git a/sql/hive/src/test/resources/golden/boolean = number-0-6b6975fa1892cc48edd87dc0df48a7c0 b/sql/hive/src/test/resources/golden/boolean = number-0-6b6975fa1892cc48edd87dc0df48a7c0 new file mode 100644 index 0000000..4d1ebdc --- /dev/null +++ b/sql/hive/src/test/resources/golden/boolean = number-0-6b6975fa1892cc48edd87dc0df48a7c0 @@ -0,0 +1 @@ +true true true true true true false false false false false false false false false false false false true true true true true true false false false false false false false false false false false false http://git-wip-us.apache.org/repos/asf/spark/blob/78d18fdb/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala ---------------------------------------------------------------------- diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala index eb7df71..6f36a4f 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala @@ -30,6 +30,18 @@ case class TestData(a: Int, b: String) */ class HiveQuerySuite extends HiveComparisonTest { + createQueryTest("boolean = number", + """ + |SELECT + | 1 = true, 1L = true, 1Y = true, true = 1, true = 1L, true = 1Y, + | 0 = true, 0L = true, 0Y = true, true = 0, true = 0L, true = 0Y, + | 1 = false, 1L = false, 1Y = false, false = 1, false = 1L, false = 1Y, + | 0 = false, 0L = false, 0Y = false, false = 0, false = 0L, false = 0Y, + | 2 = true, 2L = true, 2Y = true, true = 2, true = 2L, true = 2Y, + | 2 = false, 2L = false, 2Y = false, false = 2, false = 2L, false = 2Y + |FROM src LIMIT 1 + """.stripMargin) + test("CREATE TABLE AS runs once") { hql("CREATE TABLE foo AS SELECT 1 FROM src LIMIT 1").collect() assert(hql("SELECT COUNT(*) FROM foo").collect().head.getLong(0) === 1,