[SPARK-29838][SQL] PostgreSQL dialect: cast to timestamp

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/PostgreSQLDialect.scala

@@ -19,15 +19,15 @@ package org.apache.spark.sql.catalyst.analysis
 
 import org.apache.spark.internal.Logging
 import org.apache.spark.sql.catalyst.expressions.Cast
-import org.apache.spark.sql.catalyst.expressions.postgreSQL.PostgreCastToBoolean
+import org.apache.spark.sql.catalyst.expressions.postgreSQL.{PostgreCastToBoolean, PostgreCastToTimestamp}
 import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
 import org.apache.spark.sql.catalyst.rules.Rule
 import org.apache.spark.sql.internal.SQLConf
-import org.apache.spark.sql.types.{BooleanType, StringType}
+import org.apache.spark.sql.types.{BooleanType, TimestampType}
 
 object PostgreSQLDialect {
   val postgreSQLDialectRules: List[Rule[LogicalPlan]] =
-    CastToBoolean ::
+    CastToBoolean :: CastToTimestamp ::
       Nil
 
   object CastToBoolean extends Rule[LogicalPlan] with Logging {
@@ -46,4 +46,19 @@ object PostgreSQLDialect {
       }
     }
   }
+
+  object CastToTimestamp extends Rule[LogicalPlan] {
+    override def apply(plan: LogicalPlan): LogicalPlan = {
+      val conf = SQLConf.get
+      if (conf.usePostgreSQLDialect) {
+        plan.transformExpressions {
+          case Cast(child, dataType, timeZoneId)
+            if dataType == TimestampType =>
+            PostgreCastToTimestamp(child, timeZoneId)
+        }
+      } else {
+        plan
+      }
+    }
+  }
 }

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala

@@ -410,7 +410,7 @@ abstract class CastBase extends UnaryExpression with TimeZoneAwareExpression wit
   }
 
   // TimestampConverter
-  private[this] def castToTimestamp(from: DataType): Any => Any = from match {
+  protected[this] def castToTimestamp(from: DataType): Any => Any = from match {
     case StringType =>
       buildCast[UTF8String](_, utfs => DateTimeUtils.stringToTimestamp(utfs, zoneId).orNull)
     case BooleanType =>
@@ -1159,7 +1159,7 @@ abstract class CastBase extends UnaryExpression with TimeZoneAwareExpression wit
     }
   }
 
-  private[this] def castToTimestampCode(
+  protected[this] def castToTimestampCode(
       from: DataType,
       ctx: CodegenContext): CastFunction = from match {
     case StringType =>

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/postgreSQL/PostgreCastToBoolean.scala → sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/postgreSQL/PostgreCastBase.scala

@@ -16,19 +16,29 @@
  */
 package org.apache.spark.sql.catalyst.expressions.postgreSQL
 
+import java.time.ZoneId
+
+import org.apache.spark.sql.AnalysisException
 import org.apache.spark.sql.catalyst.analysis.TypeCheckResult
 import org.apache.spark.sql.catalyst.expressions.{CastBase, Expression, TimeZoneAwareExpression}
+import org.apache.spark.sql.catalyst.expressions.codegen.{CodegenContext, JavaCode}
 import org.apache.spark.sql.catalyst.expressions.codegen.Block._
+import org.apache.spark.sql.catalyst.util.DateTimeUtils
 import org.apache.spark.sql.catalyst.util.postgreSQL.StringUtils
-import org.apache.spark.sql.types._
+import org.apache.spark.sql.types.{BooleanType, DataType, DateType, IntegerType, NullType, StringType, TimestampType}
 import org.apache.spark.unsafe.types.UTF8String
 
-case class PostgreCastToBoolean(child: Expression, timeZoneId: Option[String])
-  extends CastBase {
+abstract class PostgreCastBase extends CastBase{
 
-  override protected def ansiEnabled =
+  override protected def ansiEnabled: Boolean =
     throw new UnsupportedOperationException("PostgreSQL dialect doesn't support ansi mode")
 
+  override def nullable: Boolean = child.nullable
+}
+
+case class PostgreCastToBoolean(child: Expression, timeZoneId: Option[String])
+  extends PostgreCastBase {
+
   override def withTimeZone(timeZoneId: String): TimeZoneAwareExpression =
     copy(timeZoneId = Option(timeZoneId))
 
@@ -75,9 +85,57 @@ case class PostgreCastToBoolean(child: Expression, timeZoneId: Option[String])
 
   override def dataType: DataType = BooleanType
 
-  override def nullable: Boolean = child.nullable
-
   override def toString: String = s"PostgreCastToBoolean($child as ${dataType.simpleString})"
 
   override def sql: String = s"CAST(${child.sql} AS ${dataType.sql})"
 }
+
+case class PostgreCastToTimestamp(child: Expression, timeZoneId: Option[String])
+  extends PostgreCastBase {
+  override def dataType: DataType = TimestampType
+
+  override def checkInputDataTypes(): TypeCheckResult = child.dataType match {
+    case StringType | DateType =>
+      TypeCheckResult.TypeCheckSuccess
+    case _ =>
+      TypeCheckResult.TypeCheckFailure(s"cannot cast type ${child.dataType} to timestamp")
+  }
+  /** Returns a copy of this expression with the specified timeZoneId. */
+  override def withTimeZone(timeZoneId: String): TimeZoneAwareExpression =
+    copy(timeZoneId = Option(timeZoneId))
+
+  override def castToTimestamp(from: DataType): Any => Any = from match {
+    case StringType =>
+      buildCast[UTF8String](_, utfs => DateTimeUtils.stringToTimestamp(utfs, zoneId)
+        .getOrElse(throw new AnalysisException(s"invalid input syntax for type timestamp:$utfs")))
+    case DateType =>
+      super.castToTimestamp(from)
+  }
+
+  override def castToTimestampCode(
+      from: DataType,
+      ctx: CodegenContext): CastFunction = from match {
+    case StringType =>
+      val zoneIdClass = classOf[ZoneId]
+      val zid = JavaCode.global(
+        ctx.addReferenceObj("zoneId", zoneId, zoneIdClass.getName),
+        zoneIdClass)
+      val longOpt = ctx.freshVariable("longOpt", classOf[Option[Long]])
+      (c, evPrim, evNull) =>
+        code"""
+          scala.Option<Long> $longOpt =
+            org.apache.spark.sql.catalyst.util.DateTimeUtils.stringToTimestamp($c, $zid);
+          if ($longOpt.isDefined()) {
+            $evPrim = ((Long) $longOpt.get()).longValue();
+          } else {
+            $evNull = throw new AnalysisException(s"invalid input syntax for type timestamp:$c");
+          }
+         """
+    case DateType =>
+      super.castToTimestampCode(from, ctx)
+  }
+
+  override def toString: String = s"PostgreCastToTimestamp($child as ${dataType.simpleString})"
+
+  override def sql: String = s"CAST(${child.sql} AS ${dataType.sql})"
+}

sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/postgreSQL/CastSuite.scala

@@ -70,4 +70,14 @@ class CastSuite extends SparkFunSuite with ExpressionEvalHelper {
     assert(PostgreCastToBoolean(Literal(1.toDouble), None).checkInputDataTypes().isFailure)
     assert(PostgreCastToBoolean(Literal(1.toFloat), None).checkInputDataTypes().isFailure)
   }
+
+  test("unsupported data types to cast to tiestamp") {
+    assert(PostgreCastToTimestamp(Literal(1), None).checkInputDataTypes().isFailure)
+    assert(PostgreCastToTimestamp(Literal(1.toByte), None).checkInputDataTypes().isFailure)
+    assert(PostgreCastToTimestamp(Literal(1.toDouble), None).checkInputDataTypes().isFailure)
+    assert(PostgreCastToTimestamp(Literal(1.toFloat), None).checkInputDataTypes().isFailure)
+    assert(PostgreCastToTimestamp(Literal(1.toLong), None).checkInputDataTypes().isFailure)
+    assert(PostgreCastToTimestamp(Literal(1.toShort), None).checkInputDataTypes().isFailure)
+    assert(PostgreCastToTimestamp(Literal(BigDecimal(1.0)), None).checkInputDataTypes().isFailure)
+  }
 }

sql/core/src/test/scala/org/apache/spark/sql/PostgreSQLDialectQuerySuite.scala

@@ -39,4 +39,14 @@ class PostgreSQLDialectQuerySuite extends QueryTest with SharedSparkSession {
       intercept[IllegalArgumentException](sql(s"select cast('$input' as boolean)").collect())
     }
   }
+
+  test("cast to timestamp") {
+    Seq(1, 0.1, 1.toDouble, 5.toFloat, true, 3.toByte, 4.toShort) foreach { value =>
+      val actualResult = intercept[AnalysisException](
+        sql(s"SELECT CAST(${value} AS timestamp)")
+      ).getMessage
+      val expectedResult = s"Cannot cast type ${value.getClass} to Timestamp."
+      assert(actualResult == expectedResult)
+    }
+  }
 }