ianmcook commented on code in PR #46529:
URL: https://github.com/apache/spark/pull/46529#discussion_r1610524728
##########
python/pyspark/sql/pandas/types.py:
##########
@@ -232,6 +312,124 @@ def _get_local_timezone() -> str:
return os.environ.get("TZ", "dateutil/:")
+def _check_arrow_array_timestamps_localize(
+ a: Union["pa.Array", "pa.ChunkedArray"],
+ dt: DataType,
+ truncate: bool = True,
+ timezone: Optional[str] = None,
+) -> Union["pa.Array", "pa.ChunkedArray"]:
+ """
+ Convert Arrow timestamps to timezone-naive in the specified timezone if
the specified Spark
+ data type is TimestampType, and optionally truncate nanosecond timestamps
to microseconds.
+
+ This function works on Arrow Arrays and ChunkedArrays, and it recurses to
convert nested
+ timestamps.
+
+ Parameters
+ ----------
+ a : :class:`pyarrow.Array` or :class:`pyarrow.ChunkedArray`
+ dt : :class:`DataType`
+ The Spark data type corresponding to the Arrow Array to be converted.
+ truncate : bool, default True
+ Whether to truncate nanosecond timestamps to microseconds. (default
``True``)
+ timezone : str, optional
+ The timezone to convert from. If there is a timestamp type, it's
required.
+
+ Returns
+ -------
+ :class:`pyarrow.Array` or :class:`pyarrow.ChunkedArray`
+ """
+ import pyarrow.types as types
+ import pyarrow as pa
+ import pyarrow.compute as pc
+
+ if isinstance(a, pa.ChunkedArray) and (types.is_nested(a.type) or
types.is_dictionary(a.type)):
+ return pa.chunked_array(
+ [
+ _check_arrow_array_timestamps_localize(chunk, dt, truncate,
timezone)
+ for chunk in a.iterchunks()
+ ]
+ )
+
+ if types.is_timestamp(a.type) and truncate and a.type.unit == "ns":
+ a = pc.floor_temporal(a, unit="microsecond")
+
+ if types.is_timestamp(a.type) and a.type.tz is None and type(dt) ==
TimestampType:
+ assert timezone is not None
+
+ # Only localize timestamps that will become Spark TimestampType
columns.
+ # Do not localize timestamps that will become Spark TimestampNTZType
columns.
+ return pc.assume_timezone(a, timezone)
+ if types.is_list(a.type):
+ at: ArrayType = cast(ArrayType, dt)
+ return pa.ListArray.from_arrays(
+ a.offsets,
+ _check_arrow_array_timestamps_localize(a.values, at.elementType,
truncate, timezone),
+ )
Review Comment:
Thanks for catching this. Fixed in 5db5e4b. Added tests in fc758e6 to fail
if nulls are not preserved here.
##########
python/pyspark/sql/pandas/types.py:
##########
@@ -232,6 +312,124 @@ def _get_local_timezone() -> str:
return os.environ.get("TZ", "dateutil/:")
+def _check_arrow_array_timestamps_localize(
+ a: Union["pa.Array", "pa.ChunkedArray"],
+ dt: DataType,
+ truncate: bool = True,
+ timezone: Optional[str] = None,
+) -> Union["pa.Array", "pa.ChunkedArray"]:
+ """
+ Convert Arrow timestamps to timezone-naive in the specified timezone if
the specified Spark
+ data type is TimestampType, and optionally truncate nanosecond timestamps
to microseconds.
+
+ This function works on Arrow Arrays and ChunkedArrays, and it recurses to
convert nested
+ timestamps.
+
+ Parameters
+ ----------
+ a : :class:`pyarrow.Array` or :class:`pyarrow.ChunkedArray`
+ dt : :class:`DataType`
+ The Spark data type corresponding to the Arrow Array to be converted.
+ truncate : bool, default True
+ Whether to truncate nanosecond timestamps to microseconds. (default
``True``)
+ timezone : str, optional
+ The timezone to convert from. If there is a timestamp type, it's
required.
+
+ Returns
+ -------
+ :class:`pyarrow.Array` or :class:`pyarrow.ChunkedArray`
+ """
+ import pyarrow.types as types
+ import pyarrow as pa
+ import pyarrow.compute as pc
+
+ if isinstance(a, pa.ChunkedArray) and (types.is_nested(a.type) or
types.is_dictionary(a.type)):
+ return pa.chunked_array(
+ [
+ _check_arrow_array_timestamps_localize(chunk, dt, truncate,
timezone)
+ for chunk in a.iterchunks()
+ ]
+ )
+
+ if types.is_timestamp(a.type) and truncate and a.type.unit == "ns":
+ a = pc.floor_temporal(a, unit="microsecond")
+
+ if types.is_timestamp(a.type) and a.type.tz is None and type(dt) ==
TimestampType:
+ assert timezone is not None
+
+ # Only localize timestamps that will become Spark TimestampType
columns.
+ # Do not localize timestamps that will become Spark TimestampNTZType
columns.
+ return pc.assume_timezone(a, timezone)
+ if types.is_list(a.type):
+ at: ArrayType = cast(ArrayType, dt)
+ return pa.ListArray.from_arrays(
+ a.offsets,
+ _check_arrow_array_timestamps_localize(a.values, at.elementType,
truncate, timezone),
+ )
+ if types.is_map(a.type):
+ mt: MapType = cast(MapType, dt)
+ # TODO(SPARK-48302): Do not replace nulls in MapArray with empty lists
+ return pa.MapArray.from_arrays(
+ a.offsets,
+ _check_arrow_array_timestamps_localize(a.keys, mt.keyType,
truncate, timezone),
+ _check_arrow_array_timestamps_localize(a.items, mt.valueType,
truncate, timezone),
+ )
+ if types.is_struct(a.type):
Review Comment:
Fixed in 5db5e4b. Added tests in fc758e6 to fail if nulls are not preserved
here.
--
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]
