HyukjinKwon commented on code in PR #38462:
URL: https://github.com/apache/spark/pull/38462#discussion_r1013933320
##########
python/pyspark/sql/connect/column.py:
##########
@@ -99,11 +101,59 @@ def to_plan(self, session: Optional["RemoteSparkSession"])
-> "proto.Expression"
value_type = type(self._value)
exp = proto.Expression()
if value_type is int:
- exp.literal.i32 = cast(int, self._value)
+ exp.literal.i64 = cast(int, self._value)
+ elif value_type is bool:
+ exp.literal.boolean = cast(bool, self._value)
elif value_type is str:
exp.literal.string = cast(str, self._value)
elif value_type is float:
exp.literal.fp64 = cast(float, self._value)
+ elif value_type is decimal.Decimal:
+ d_v = cast(decimal.Decimal, self._value)
+ v_tuple = d_v.as_tuple()
+ exp.literal.decimal.scale = abs(v_tuple.exponent)
+ exp.literal.decimal.precision = len(v_tuple.digits) -
abs(v_tuple.exponent)
+ # Two complement yeah...
+ raise ValueError("Python Decimal not supported.")
+ elif value_type is bytes:
+ exp.literal.binary = self._value
+ elif value_type is datetime.datetime:
+ # Microseconds since epoch.
+ dt = cast(datetime.datetime, self._value)
+ v = dt - datetime.datetime(1970, 1, 1, 0, 0, 0, 0)
+ exp.literal.timestamp = int(v / datetime.timedelta(microseconds=1))
Review Comment:
Can we maybe match the implementation in PySpark's:
https://github.com/apache/spark/blob/master/python/pyspark/sql/types.py#L254-L260
?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
