Github user anabranch commented on a diff in the pull request:
https://github.com/apache/spark/pull/16138#discussion_r91403382
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala
---
@@ -1047,6 +1047,57 @@ case class ToDate(child: Expression) extends
UnaryExpression with ImplicitCastIn
}
/**
+ * Parses a column with a format to a timestamp.
+ */
+@ExpressionDescription(
+ usage = "_FUNC_(timestamp_str, fmt) - Parses the `timestamp` expression
" +
+ "with the `fmt` expression.",
+ extended = """
+ Examples:
+ > SELECT _FUNC_('2016-12-31', 'yyyy-MM-dd');
+ 2016-12-31
+ """)
+case class ParseToDate(left: Expression, right: Expression, child:
Expression)
+ extends RuntimeReplaceable with ImplicitCastInputTypes {
+
+ def this(left: Expression, format: Expression) = {
+ this(left, format, Cast(new ParseToTimestamp(left, format), DateType))
+ }
+
+ override def inputTypes: Seq[AbstractDataType] = Seq(StringType,
StringType)
+ override def flatArguments: Iterator[Any] = Iterator(left, right)
+ override def sql: String = s"$prettyName(${left.sql}, ${right.sql})"
+
+ override def prettyName: String = "to_date"
+ override def dataType: DataType = DateType
+}
+
+/**
+ * Parses a column with a format to a timestamp.
+ */
+@ExpressionDescription(
+ usage = "_FUNC_(timestamp, fmt) - Parses the `timestamp` expression with
the `fmt` expression.",
+ extended = """
+ Examples:
+ > SELECT _FUNC_('2016-12-31', 'yyyy-MM-dd');
+ 2016-12-31 00:00:00.0
+ """)
+case class ParseToTimestamp(left: Expression, right: Expression, child:
Expression)
+ extends RuntimeReplaceable with ImplicitCastInputTypes {
+
+ def this(left: Expression, format: Expression) = {
+ this(left, format, Cast(UnixTimestamp(left, format), TimestampType))
+}
+
+ override def inputTypes: Seq[AbstractDataType] = Seq(StringType,
StringType)
+ override def flatArguments: Iterator[Any] = Iterator(left, right)
+ override def sql: String = s"$prettyName(${left.sql}, ${right.sql})"
+
+ override def prettyName: String = "to_timestamp"
+ override def dataType: DataType = TimestampType
--- End diff --
If I remove this `DataType` override I will end up with the right answer
but the wrong type (string).
If I have this `DataType` override I will end up with the wrong answer but
the right type.
If I cast to the expected type by either having the `dataType` override or
removing it, I will get the expected output. But I have to cast after
performing `to_timestamp` or `to_date`. The cast within the expression does not
seem to be respected.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
