Reformat with ruff format

README.md

@@ -79,36 +79,38 @@ There are three "environments" set up for pixi:
 - `dev`
 - `examples`
 
-And two "tasks": 
+And three "tasks":
 
 - `lint`
-- `test`
+- `test` : run most of the tests
+- `test_all` : run the tests that access AWS -- i.e. download data directly.
 
 To run the tests in an isolated environment:
 
 ```bash
 pixi run -e dev test
 ```
 
-To run a shell to do dev work:
-
+Or with a specific python version:
 ```bash
-pixi shell -e dev
+pixi run -e test312 test
 ```
 
-If you want to run the examples (notebooks and al that):
+Options are: `test310` `test311` `test312` `test313`
+
+
+To run a shell to do dev work:
 
 ```bash
-pixi shell -e all
+pixi shell -e dev
 ```
 
-That will set up a conda environment with all the develop dependencies.
-
-To run a shell in which you can run the examples:
+To run a shell in which you can run the examples (notebooks and al that):
 
 ```bash
 pixi shell -e examples
 ```
+
 To run a shell with everything (dev and example deps:
 
 ```bash

profiling/STOFS_benchmarks.py

@@ -6,8 +6,8 @@
 import xarray as xr
 import xugrid as xu
 
-bucket_name = 'noaa-gestofs-pds'
-key = '_para2/stofs_2d_glo.20230819/stofs_2d_glo.t00z.fields.cwl.nc'
+bucket_name = "noaa-gestofs-pds"
+key = "_para2/stofs_2d_glo.20230819/stofs_2d_glo.t00z.fields.cwl.nc"
 url = f"s3://{bucket_name}/{key}"
 
 fs = fsspec.filesystem("s3", anon=True)
@@ -16,30 +16,31 @@
     fs.open(url),
     chunks={},
     drop_variables=["neta", "nvel", "max_nvdll", "max_nvell"],
-    engine='h5netcdf'
+    engine="h5netcdf",
 )
 
 bbox = (-70, 40, -60, 50)
 
+
 def info(ds):
-    print(f'Data Variables: {ds.data_vars}')
-    print(f'Coordinates: {ds.coords}')
-    print(f'Dimensions: {ds.dims}')
-    print(f'Attributes: {ds.attrs}\n')
+    print(f"Data Variables: {ds.data_vars}")
+    print(f"Coordinates: {ds.coords}")
+    print(f"Dimensions: {ds.dims}")
+    print(f"Attributes: {ds.attrs}\n")
 
 
 print("Subsetting methods comparison")
 start = time.time()
 ads = ds.xsg.grid.subset_bbox(ds, bbox)
-print(f"Xarray-subset-grid - {time.time-start} sec")
+print(f"Xarray-subset-grid - {time.time - start} sec")
 
 start = time.time()
 tds = thalassa.normalize(ds)
 tds = thalassa.crop(tds, shapely.box(*bbox))
-print(f"Thalassa - {time.time-start} sec")
+print(f"Thalassa - {time.time - start} sec")
 
 # Checking time only for subsetting operation
 uds = xu.UgridDataset(ds)
 start = time.time()
 uds = uds.ugrid.sel(y=slice(bbox[2], bbox[3]), x=slice(bbox[0], bbox[1]))
-print(f"UGrid - {time.time-start} sec")
+print(f"UGrid - {time.time - start} sec")

pyproject.toml

@@ -63,11 +63,19 @@ write_to = "xarray_subset_grid/_version.py"
 
 [tool.ruff]
 builtins = ["ellipsis"]
-extend-exclude = ["xarray_subset_grid/_version.py"]
+extend-exclude = ["xarray_subset_grid/_version.py", "docs"]
 target-version = "py310"
 # Use a longer line length.
 line-length = 100
 
+[tool.ruff.format]
+# Prefer single quotes over double quotes.
+quote-style = "double"
+# Use `\n` line endings for all files
+line-ending = "lf"
+exclude = ["*.ipynb"]
+
+
 [tool.ruff.lint]
 ignore = [
   "E402", # module level import not at top of file
@@ -138,7 +146,8 @@ python-build = "*"
 
 [tool.pixi.feature.dev.tasks]
 lint = "ruff check tests xarray_subset_grid"
-test = "pytest --online tests/"
+test = "pytest tests/"
+test_all = "pytest --online tests/"
 
 [tool.pixi.feature.examples.dependencies]
 matplotlib = "*"

tests/conftest.py

@@ -16,8 +16,7 @@ def pytest_addoption(parser):
 def pytest_configure(config):
     # register an additional marker
     config.addinivalue_line(
-        "markers",
-        "online: mark test to run only when online (using AWS resources)"
+        "markers", "online: mark test to run only when online (using AWS resources)"
     )
 
 

tests/test_grids/test_regular_grid.py

@@ -12,7 +12,7 @@
 
 from xarray_subset_grid.grids.regular_grid import RegularGrid
 
-TEST_DATA = Path(__file__).parent.parent / 'example_data'
+TEST_DATA = Path(__file__).parent.parent / "example_data"
 
 TEST_FILE1 = TEST_DATA / "AMSEAS-subset.nc"
 
@@ -23,6 +23,7 @@
 
 """
 
+
 def test_recognise():
     """
     works for at least one file ...
@@ -31,6 +32,7 @@ def test_recognise():
 
     assert RegularGrid.recognize(ds)
 
+
 def test_recognise_not():
     """
     should not recognise an SGrid
@@ -40,8 +42,6 @@ def test_recognise_not():
     assert not RegularGrid.recognize(ds)
 
 
-
-
 #######
 # These from teh ugrid tests -- need to be adapted
 #######

tests/test_grids/test_sgrid.py

@@ -11,44 +11,55 @@
 try:
     import fsspec
     import zarr
+
     zarr__version__ = int(zarr.__version__.split(".")[0])
 except ImportError:
     fsspec = None
 
 
-test_dir = Path(__file__).parent.parent / 'example_data'
+test_dir = Path(__file__).parent.parent / "example_data"
+
+sample_sgrid_file = test_dir / "arakawa_c_test_grid.nc"
 
-sample_sgrid_file = test_dir / 'arakawa_c_test_grid.nc'
 
 def test_grid_topology_location_parse():
     ds = xr.open_dataset(sample_sgrid_file, decode_times=False)
-    node_info = _get_location_info_from_topology(ds['grid'], 'node')
-    edge1_info  = _get_location_info_from_topology(ds['grid'], 'edge1')
-    edge2_info = _get_location_info_from_topology(ds['grid'], 'edge2')
-    face_info = _get_location_info_from_topology(ds['grid'], 'face')
-
-    assert node_info == {'dims': ['xi_psi', 'eta_psi'],
-                         'coords': ['lon_psi', 'lat_psi'],
-                         'padding': {'xi_psi': 'none', 'eta_psi': 'none'}}
-    assert edge1_info == {'dims': ['xi_u', 'eta_u'],
-                          'coords': ['lon_u', 'lat_u'],
-                          'padding': {'eta_u': 'both', 'xi_u': 'none'}}
-    assert edge2_info == {'dims': ['xi_v', 'eta_v'],
-                          'coords': ['lon_v', 'lat_v'],
-                          'padding': {'xi_v': 'both', 'eta_v': 'none'}}
-    assert face_info == {'dims': ['xi_rho', 'eta_rho'],
-                         'coords': ['lon_rho', 'lat_rho'],
-                         'padding': {'xi_rho': 'both', 'eta_rho': 'both'}}
-
-
-@pytest.mark.skipif(zarr__version__>=3,
-                    reason="zarr3.0.8 doesn't support FSpec AWS (it might soon)")
+    node_info = _get_location_info_from_topology(ds["grid"], "node")
+    edge1_info = _get_location_info_from_topology(ds["grid"], "edge1")
+    edge2_info = _get_location_info_from_topology(ds["grid"], "edge2")
+    face_info = _get_location_info_from_topology(ds["grid"], "face")
+
+    assert node_info == {
+        "dims": ["xi_psi", "eta_psi"],
+        "coords": ["lon_psi", "lat_psi"],
+        "padding": {"xi_psi": "none", "eta_psi": "none"},
+    }
+    assert edge1_info == {
+        "dims": ["xi_u", "eta_u"],
+        "coords": ["lon_u", "lat_u"],
+        "padding": {"eta_u": "both", "xi_u": "none"},
+    }
+    assert edge2_info == {
+        "dims": ["xi_v", "eta_v"],
+        "coords": ["lon_v", "lat_v"],
+        "padding": {"xi_v": "both", "eta_v": "none"},
+    }
+    assert face_info == {
+        "dims": ["xi_rho", "eta_rho"],
+        "coords": ["lon_rho", "lat_rho"],
+        "padding": {"xi_rho": "both", "eta_rho": "both"},
+    }
+
+
+@pytest.mark.skipif(
+    zarr__version__ >= 3, reason="zarr3.0.8 doesn't support FSpec AWS (it might soon)"
+)
 @pytest.mark.online
 def test_polygon_subset():
-    '''
+    """
     This is a basic integration test for the subsetting of a ROMS sgrid dataset using
     a polygon.
-    '''
+    """
     if fsspec is None:
         raise ImportError("Must have fsspec installed to run --online tests")
     fs = fsspec.filesystem(
@@ -61,9 +72,7 @@ def test_polygon_subset():
     )
     m = fs.get_mapper("")
 
-    ds = xr.open_dataset(
-        m, engine="zarr", backend_kwargs=dict(consolidated=False), chunks={}
-    )
+    ds = xr.open_dataset(m, engine="zarr", backend_kwargs=dict(consolidated=False), chunks={})
 
     polygon = np.array(
         [
@@ -77,46 +86,43 @@ def test_polygon_subset():
             [-122.38488806417945, 34.98888604471138],
         ]
     )
-    ds_temp = ds.xsg.subset_vars(['temp','u', 'v'])
+    ds_temp = ds.xsg.subset_vars(["temp", "u", "v"])
     ds_subset = ds_temp.xsg.subset_polygon(polygon)
 
     # Check that the subset dataset has the correct dimensions given the original padding
-    assert ds_subset.sizes['eta_rho'] == ds_subset.sizes['eta_psi'] + 1
-    assert ds_subset.sizes['eta_u'] == ds_subset.sizes['eta_psi'] + 1
-    assert ds_subset.sizes['eta_v'] == ds_subset.sizes['eta_psi']
-    assert ds_subset.sizes['xi_rho'] == ds_subset.sizes['xi_psi'] + 1
-    assert ds_subset.sizes['xi_u'] == ds_subset.sizes['xi_psi']
-    assert ds_subset.sizes['xi_v'] == ds_subset.sizes['xi_psi'] + 1
+    assert ds_subset.sizes["eta_rho"] == ds_subset.sizes["eta_psi"] + 1
+    assert ds_subset.sizes["eta_u"] == ds_subset.sizes["eta_psi"] + 1
+    assert ds_subset.sizes["eta_v"] == ds_subset.sizes["eta_psi"]
+    assert ds_subset.sizes["xi_rho"] == ds_subset.sizes["xi_psi"] + 1
+    assert ds_subset.sizes["xi_u"] == ds_subset.sizes["xi_psi"]
+    assert ds_subset.sizes["xi_v"] == ds_subset.sizes["xi_psi"] + 1
 
     # Check that the subset rho/psi/u/v positional relationship makes sense aka psi point is
     # 'between' it's neighbor rho points
     # Note that this needs to be better generalized; it's not trivial to write a test that
     # works in all potential cases.
-    assert (ds_subset['lon_rho'][0,0] < ds_subset['lon_psi'][0,0]
-            and ds_subset['lon_rho'][0,1] > ds_subset['lon_psi'][0,0])
+    assert (
+        ds_subset["lon_rho"][0, 0] < ds_subset["lon_psi"][0, 0]
+        and ds_subset["lon_rho"][0, 1] > ds_subset["lon_psi"][0, 0]
+    )
 
     # ds_subset.temp_sur.isel(ocean_time=0).plot(x="lon_rho", y="lat_rho")
 
+
 def test_polygon_subset_2():
     ds = xr.open_dataset(sample_sgrid_file, decode_times=False)
-    polygon = np.array([
-        [6.5, 37.5],
-        [6.5, 39.5],
-        [9.5, 40.5],
-        [8.5, 37.5],
-        [6.5, 37.5]
-    ])
+    polygon = np.array([[6.5, 37.5], [6.5, 39.5], [9.5, 40.5], [8.5, 37.5], [6.5, 37.5]])
     ds_subset = ds.xsg.subset_polygon(polygon)
 
-    #Check that the subset dataset has the correct dimensions given the original padding
-    assert ds_subset.sizes['eta_rho'] == ds_subset.sizes['eta_psi'] + 1
-    assert ds_subset.sizes['eta_u'] == ds_subset.sizes['eta_psi'] + 1
-    assert ds_subset.sizes['eta_v'] == ds_subset.sizes['eta_psi']
-    assert ds_subset.sizes['xi_rho'] == ds_subset.sizes['xi_psi'] + 1
-    assert ds_subset.sizes['xi_u'] == ds_subset.sizes['xi_psi']
-    assert ds_subset.sizes['xi_v'] == ds_subset.sizes['xi_psi'] + 1
+    # Check that the subset dataset has the correct dimensions given the original padding
+    assert ds_subset.sizes["eta_rho"] == ds_subset.sizes["eta_psi"] + 1
+    assert ds_subset.sizes["eta_u"] == ds_subset.sizes["eta_psi"] + 1
+    assert ds_subset.sizes["eta_v"] == ds_subset.sizes["eta_psi"]
+    assert ds_subset.sizes["xi_rho"] == ds_subset.sizes["xi_psi"] + 1
+    assert ds_subset.sizes["xi_u"] == ds_subset.sizes["xi_psi"]
+    assert ds_subset.sizes["xi_v"] == ds_subset.sizes["xi_psi"] + 1
 
     assert ds_subset.lon_psi.min() <= 6.5 and ds_subset.lon_psi.max() >= 9.5
     assert ds_subset.lat_psi.min() <= 37.5 and ds_subset.lat_psi.max() >= 40.5
 
-    assert 'u' in ds_subset.variables.keys()
+    assert "u" in ds_subset.variables.keys()