From ef0ccbcb07252db0ead8509e70d1a9a670d41616 Mon Sep 17 00:00:00 2001
From: petermaxlee <petermaxlee@gmail.com>
Date: Wed, 27 Jul 2016 16:04:43 +0800
Subject: [SPARK-16729][SQL] Throw analysis exception for invalid date casts

## What changes were proposed in this pull request?
Spark currently throws exceptions for invalid casts for all other data types except date type. Somehow date type returns null. It should be consistent and throws analysis exception as well.

## How was this patch tested?
Added a unit test case in CastSuite.

Author: petermaxlee <petermaxlee@gmail.com>

Closes #14358 from petermaxlee/SPARK-16729.
---
 .../org/apache/spark/sql/catalyst/expressions/Cast.scala |  9 ++-------
 .../spark/sql/catalyst/expressions/CastSuite.scala       | 16 ++++++++++++++--
 2 files changed, 16 insertions(+), 9 deletions(-)

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala
index b1e89b5de8..a12fba047b 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala
@@ -52,7 +52,8 @@ object Cast {
     case (DateType, TimestampType) => true
     case (_: NumericType, TimestampType) => true
 
-    case (_, DateType) => true
+    case (StringType, DateType) => true
+    case (TimestampType, DateType) => true
 
     case (StringType, CalendarIntervalType) => true
 
@@ -228,18 +229,12 @@ case class Cast(child: Expression, dataType: DataType) extends UnaryExpression w
       // throw valid precision more than seconds, according to Hive.
       // Timestamp.nanos is in 0 to 999,999,999, no more than a second.
       buildCast[Long](_, t => DateTimeUtils.millisToDays(t / 1000L))
-    // Hive throws this exception as a Semantic Exception
-    // It is never possible to compare result when hive return with exception,
-    // so we can return null
-    // NULL is more reasonable here, since the query itself obeys the grammar.
-    case _ => _ => null
   }
 
   // IntervalConverter
   private[this] def castToInterval(from: DataType): Any => Any = from match {
     case StringType =>
       buildCast[UTF8String](_, s => CalendarInterval.fromString(s.toString))
-    case _ => _ => null
   }
 
   // LongConverter
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/CastSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/CastSuite.scala
index dfda7c50f2..5ae0527a9c 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/CastSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/CastSuite.scala
@@ -70,7 +70,8 @@ class CastSuite extends SparkFunSuite with ExpressionEvalHelper {
     checkNullCast(DateType, TimestampType)
     numericTypes.foreach(dt => checkNullCast(dt, TimestampType))
 
-    atomicTypes.foreach(dt => checkNullCast(dt, DateType))
+    checkNullCast(StringType, DateType)
+    checkNullCast(TimestampType, DateType)
 
     checkNullCast(StringType, CalendarIntervalType)
     numericTypes.foreach(dt => checkNullCast(StringType, dt))
@@ -366,7 +367,6 @@ class CastSuite extends SparkFunSuite with ExpressionEvalHelper {
     checkEvaluation(cast("2012-12-11", DoubleType), null)
     checkEvaluation(cast(123, IntegerType), 123)
 
-
     checkEvaluation(cast(Literal.create(null, IntegerType), ShortType), null)
   }
 
@@ -783,4 +783,16 @@ class CastSuite extends SparkFunSuite with ExpressionEvalHelper {
     checkEvaluation(cast("abc", BooleanType), null)
     checkEvaluation(cast("", BooleanType), null)
   }
+
+  test("SPARK-16729 type checking for casting to date type") {
+    assert(cast("1234", DateType).checkInputDataTypes().isSuccess)
+    assert(cast(new Timestamp(1), DateType).checkInputDataTypes().isSuccess)
+    assert(cast(false, DateType).checkInputDataTypes().isFailure)
+    assert(cast(1.toByte, DateType).checkInputDataTypes().isFailure)
+    assert(cast(1.toShort, DateType).checkInputDataTypes().isFailure)
+    assert(cast(1, DateType).checkInputDataTypes().isFailure)
+    assert(cast(1L, DateType).checkInputDataTypes().isFailure)
+    assert(cast(1.0.toFloat, DateType).checkInputDataTypes().isFailure)
+    assert(cast(1.0, DateType).checkInputDataTypes().isFailure)
+  }
 }
-- 
cgit v1.2.3