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

FIX: Add fixes to allow reading kerchunk catalog #485

Merged
merged 5 commits into from
Jun 26, 2022
Merged

FIX: Add fixes to allow reading kerchunk catalog #485

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
c4d45d6
add fixes to allow reading kerchunk catalog
mgrover1 Jun 24, 2022
c47b9a5
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Jun 24, 2022
e84ffb7
Update intake_esm/source.py
mgrover1 Jun 24, 2022
87c4621
fix tests
andersy005 Jun 25, 2022
d262de0
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Jun 25, 2022
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
1 change: 1 addition & 0 deletions intake_esm/cat.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@ class Config:
class DataFormat(str, enum.Enum):
netcdf = 'netcdf'
zarr = 'zarr'
reference = 'reference'

class Config:
validate_all = True
Expand Down
23 changes: 11 additions & 12 deletions intake_esm/source.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,14 +18,16 @@ class ESMDataSourceError(Exception):
def _get_xarray_open_kwargs(data_format, xarray_open_kwargs=None, storage_options=None):
xarray_open_kwargs = (xarray_open_kwargs or {}).copy()
_default_open_kwargs = {
'engine': 'zarr' if data_format == 'zarr' else 'netcdf4',
'engine': 'zarr' if data_format in {'zarr', 'reference'} else 'netcdf4',
'chunks': {},
'backend_kwargs': {},
}
if not xarray_open_kwargs:
xarray_open_kwargs = _default_open_kwargs
else:
xarray_open_kwargs = {**_default_open_kwargs, **xarray_open_kwargs}
xarray_open_kwargs = (
{**_default_open_kwargs, **xarray_open_kwargs}
if xarray_open_kwargs
else _default_open_kwargs
)

if (
xarray_open_kwargs['engine'] == 'zarr'
and 'storage_options' not in xarray_open_kwargs['backend_kwargs']
Expand All @@ -47,19 +49,16 @@ def _open_dataset(
data_format=None,
):

_can_be_local = fsspec.utils.can_be_local(urlpath)
storage_options = xarray_open_kwargs.get('backend_kwargs', {}).get('storage_options', {})

# Support kerchunk datasets, setting the file object (fo) and urlpath
if data_format == 'reference':
if 'storage_options' not in xarray_open_kwargs.keys():
xarray_open_kwargs['storage_options'] = {}
xarray_open_kwargs['storage_options']['fo'] = urlpath
xarray_open_kwargs['backend_kwargs']['storage_options']['fo'] = urlpath
xarray_open_kwargs['backend_kwargs']['consolidated'] = False
urlpath = 'reference://'

if xarray_open_kwargs['engine'] == 'zarr':
url = urlpath
elif _can_be_local:
elif fsspec.utils.can_be_local(urlpath):
url = fsspec.open_local(urlpath, **storage_options)
else:
url = fsspec.open(urlpath, **storage_options).open()
Expand All @@ -77,6 +76,7 @@ def _open_dataset(

if varname and isinstance(varname, str):
varname = [varname]

if requested_variables:
if isinstance(requested_variables, str):
requested_variables = [requested_variables]
Expand Down Expand Up @@ -214,7 +214,6 @@ def _open_dataset(self):
"""Open dataset with xarray"""

try:

datasets = [
_open_dataset(
record[self.path_column_name],
Expand Down
7 changes: 5 additions & 2 deletions tests/test_source.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@
'sample_data/kerchunk-files/noaa-nwm-test-reference.json',
)

multi_path = os.path.dirname(f1) + '/*.nc'
multi_path = f'{os.path.dirname(f1)}/*.nc'


def _common_open(fpath, varname='tasmax'):
Expand All @@ -44,10 +44,13 @@ def test_get_xarray_open_kwargs(storage_options):


def test_open_dataset_kerchunk(kerchunk_file=kerchunk_file):
xarray_open_kwargs = _get_xarray_open_kwargs(
'reference', dict(engine='zarr', consolidated=False), storage_options={}
)
ds = _open_dataset(
data_format='reference',
urlpath=kerchunk_file,
varname=None,
xarray_open_kwargs=dict(engine='zarr', consolidated=False),
xarray_open_kwargs=xarray_open_kwargs,
).compute()
assert isinstance(ds, xarray.Dataset)