Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Handle datetimes correctly for dataframe + multivalue #512

Merged
merged 2 commits into from
Aug 1, 2024
Merged

Handle datetimes correctly for dataframe + multivalue #512

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
36db2b3
Handle datetimes correctly for dataframe + multivalue
kbolashev Aug 1, 2024
c05ccee
Send timezone too
kbolashev Aug 1, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 20 additions & 1 deletion dagshub/data_engine/model/datasource.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -584,6 +584,7 @@ def _df_to_metadata(
update_entry.allowMultiple = True
for sub_val in val:
value_type = field_value_types.get(key)
time_zone = None
if value_type is None:
value_type = metadataTypeLookup[type(sub_val)]
field_value_types[key] = value_type
Expand All @@ -598,9 +599,17 @@ def _df_to_metadata(
sub_val = sub_val.encode("utf-8")
if isinstance(sub_val, bytes):
sub_val = wrap_bytes(sub_val)
if isinstance(sub_val, datetime.datetime):
time_zone = _get_datetime_utc_offset(sub_val)
sub_val = int(sub_val.timestamp() * 1000)
res.append(
DatapointMetadataUpdateEntry(
url=datapoint, key=key, value=str(sub_val), valueType=value_type, allowMultiple=True
url=datapoint,
key=key,
value=str(sub_val),
valueType=value_type,
allowMultiple=True,
timeZone=time_zone,
)
)
else:
Expand All @@ -612,20 +621,25 @@ def _df_to_metadata(
if value_type == MetadataFieldType.BLOB and not isinstance(val, bytes):
if key not in document_fields:
continue
time_zone = None
# Pandas quirk - integers are floats on the backend
if value_type == MetadataFieldType.INTEGER:
val = int(val)
if isinstance(val, str) and key in document_fields:
val = val.encode("utf-8")
if isinstance(val, bytes):
val = wrap_bytes(val)
if isinstance(val, datetime.datetime):
time_zone = _get_datetime_utc_offset(val)
val = int(val.timestamp() * 1000)
res.append(
DatapointMetadataUpdateEntry(
url=datapoint,
key=key,
value=str(val),
valueType=value_type,
allowMultiple=key in multivalue_fields,
timeZone=time_zone,
)
)
return res
Expand Down Expand Up @@ -1438,6 +1452,7 @@ def update_metadata(self, datapoints: Union[List[str], str], metadata: Dict[str,
if e.key == k:
e.allowMultiple = True
for sub_val in v:
time_zone = None
value_type = field_value_types.get(k)
if value_type is None:
value_type = metadataTypeLookup[type(sub_val)]
Expand All @@ -1449,6 +1464,9 @@ def update_metadata(self, datapoints: Union[List[str], str], metadata: Dict[str,
continue
if isinstance(v, str) and k in document_fields:
v = v.encode("utf-8")
if isinstance(v, datetime.datetime):
time_zone = _get_datetime_utc_offset(v)
v = int(v.timestamp() * 1000)
if isinstance(v, bytes):
sub_val = wrap_bytes(sub_val)
self._metadata_entries.append(
Expand All @@ -1459,6 +1477,7 @@ def update_metadata(self, datapoints: Union[List[str], str], metadata: Dict[str,
# todo: preliminary type check
valueType=value_type,
allowMultiple=k in self._multivalue_fields,
timeZone=time_zone,
)
)

Expand Down
8 changes: 6 additions & 2 deletions tests/data_engine/test_datasource.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -149,8 +149,12 @@ def test_pandas_timestamp(ds):
actual = Datasource._df_to_metadata(ds, df)

expected = [
DatapointMetadataUpdateEntry("test1", "key1", "2020-10-10 10:10:00", MetadataFieldType.DATETIME),
DatapointMetadataUpdateEntry("test2", "key1", "2030-10-10 10:20:20", MetadataFieldType.DATETIME),
DatapointMetadataUpdateEntry(
"test1", "key1", f"{int(data_dict['key1'][0].timestamp()) * 1000}", MetadataFieldType.DATETIME
),
DatapointMetadataUpdateEntry(
"test2", "key1", f"{int(data_dict['key1'][1].timestamp()) * 1000}", MetadataFieldType.DATETIME
),
]

assert expected == actual
Loading