Github user anabranch commented on a diff in the pull request:
https://github.com/apache/spark/pull/16138#discussion_r91172169
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala
---
@@ -1047,6 +1047,53 @@ 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, ToDate(new ParseToTimestamp(left, format)))
+ }
+
+ override def inputTypes: Seq[AbstractDataType] = Seq(StringType,
StringType)
+ override def dataType: DataType = DateType
+ override def flatArguments: Iterator[Any] = Iterator(left, right)
+ override def sql: String = s"$prettyName(${left.sql}, ${right.sql})"
+}
+
+/**
+ * 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))
--- End diff --
Now if I remove the cast call and turn this function into:
```scala
def this(left: Expression, format: Expression) = {
this(left, format, UnixTimestamp(left, format))
}
```
I will end up with
```scala
scala> import org.apache.spark.sql.functions._
import org.apache.spark.sql.functions._
scala>
scala> //////////// TIME INFO
scala> spark.range(1).select(to_timestamp(lit("2016-12-31"),
"yyyy-MM-dd")).collect()
res0: Array[org.apache.spark.sql.Row] = Array([1970-01-01 11:05:19.476746])
scala> // expected is what the output of the below command
scala> spark.range(1).select(to_timestamp(lit("2016-12-31"),
"yyyy-MM-dd").cast("timestamp")).collect()
res1: Array[org.apache.spark.sql.Row] = Array([null])
scala>
scala>
scala> //////////// DATE INFO
scala> spark.range(1).select(to_date(lit("2016-12-31"),
"yyyy-MM-dd")).collect()
res2: Array[org.apache.spark.sql.Row] = Array([null])
scala> // expected is the output of the below command
scala> spark.range(1).select(to_date(to_timestamp(lit("2016-12-31"),
"yyyy-MM-dd"))).collect()
res3: Array[org.apache.spark.sql.Row] = Array([null])
```
---
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]
