Add Ruff lint to github actions

.github/workflows/test.yaml

@@ -16,5 +16,7 @@ jobs:
           cache: true
           # auth-host: prefix.dev
           # auth-token: ${{ secrets.PREFIX_DEV_TOKEN }}
+      - run: pixi run --environment ${{ matrix.environment }} lint
       - run: pixi run --environment ${{ matrix.environment }} test
 
+

.gitignore

@@ -164,3 +164,4 @@ xarray_subset_grid/_version.py
 .pixi
 *.egg-info
 
+.ruff_cache/

examples/subset_file.py

@@ -2,7 +2,6 @@
 import numpy as np
 import xarray as xr
 
-import xarray_subset_grid.accessor
 from xarray_subset_grid.grids import ugrid
 from xarray_subset_grid.utils import format_bytes
 from xarray_subset_grid.visualization.mpl_plotting import plot_ugrid

profiling/STOFS_benchmarks.py

@@ -1,15 +1,11 @@
 import time
 
-import cf_xarray
 import fsspec
-import s3fs
 import shapely
 import thalassa
 import xarray as xr
 import xugrid as xu
 
-import xarray_subset_grid as xrsg
-
 bucket_name = 'noaa-gestofs-pds'
 key = '_para2/stofs_2d_glo.20230819/stofs_2d_glo.t00z.fields.cwl.nc'
 url = f"s3://{bucket_name}/{key}"

profiling/p_in_p_perf.py

@@ -44,30 +44,32 @@ def ray_tracing_numpy(x, y, poly):
 
 import numpy as np
 
-# Using a 20 vertex polygon -- arbitrary decision as common max for 
+# Using a 20 vertex polygon -- arbitrary decision as common max for
 # bounding poly used for subsetting.
-test_poly = np.array([
-    [-69.0842494, 41.8576263],
-    [-69.3834133, 41.6994390],
-    [-69.4844079, 41.5818408],
-    [-69.7009389, 41.5498641],
-    [-70.0628678, 41.5884718],
-    [-70.3054548, 41.6810850],
-    [-70.6109682, 41.7607248],
-    [-70.8657576, 41.9553727],
-    [-71.1089099, 42.1369069],
-    [-71.1294295, 42.4274792],
-    [-70.8877302, 42.6500898],
-    [-70.7118900, 42.7635708],
-    [-70.4645152, 42.8363260],
-    [-70.1066827, 42.8113145],
-    [-69.9021696, 42.7796958],
-    [-69.7686684, 42.7210923],
-    [-69.4055325, 42.5535379],
-    [-69.1527168, 42.3072355],
-    [-68.9597074, 42.0243090],
-    [-68.9939291, 41.9264228],
-])
+test_poly = np.array(
+    [
+        [-69.0842494, 41.8576263],
+        [-69.3834133, 41.6994390],
+        [-69.4844079, 41.5818408],
+        [-69.7009389, 41.5498641],
+        [-70.0628678, 41.5884718],
+        [-70.3054548, 41.6810850],
+        [-70.6109682, 41.7607248],
+        [-70.8657576, 41.9553727],
+        [-71.1089099, 42.1369069],
+        [-71.1294295, 42.4274792],
+        [-70.8877302, 42.6500898],
+        [-70.7118900, 42.7635708],
+        [-70.4645152, 42.8363260],
+        [-70.1066827, 42.8113145],
+        [-69.9021696, 42.7796958],
+        [-69.7686684, 42.7210923],
+        [-69.4055325, 42.5535379],
+        [-69.1527168, 42.3072355],
+        [-68.9597074, 42.0243090],
+        [-68.9939291, 41.9264228],
+    ]
+)
 
 min_lon, min_lat = test_poly.min(axis=0)
 max_lon, max_lat = test_poly.max(axis=0)
@@ -88,8 +90,8 @@ def ray_tracing_numpy(x, y, poly):
 # 9.03 ms ± 303 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)
 
 
-
 from geometry_utils import polygon_inside
+
 geom = polygon_inside(test_poly, test_points)
 # 1000 pts
 # In [11]: %timeit polygon_inside(test_poly, test_points)
@@ -101,7 +103,7 @@ def ray_tracing_numpy(x, y, poly):
 # Do they give the same answer?
 assert np.array_equal(rtn_inside, geom)
 
-from shapely import contains_xy, Polygon
+from shapely import Polygon, contains_xy
 
 sh_poly = Polygon(test_poly)
 
@@ -114,7 +116,4 @@ def ray_tracing_numpy(x, y, poly):
 # 54.7 ms ± 1.4 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)
 
 
-
 assert np.array_equal(rtn_inside, shapely)
-
-

pyproject.toml

@@ -4,36 +4,38 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "xarray_subset_grid"
-authors = [{ name = "Matthew Iannucci", email = "[email protected]" },
-           { name = "Christopher H. Barker", email = "[email protected]" }]
+authors = [
+  { name = "Matthew Iannucci", email = "[email protected]" },
+  { name = "Christopher H. Barker", email = "[email protected]" },
+]
 description = "Subset Xarray datasets in space"
 readme = "README.md"
 requires-python = ">=3.10"
 keywords = ["xarray"]
 license = { file = "LICENSE" }
 
 classifiers = [
-    "Development Status :: 5 - Production/Stable",
-    "Intended Audience :: Science/Research",
-    "Operating System :: OS Independent",
-    "License :: OSI Approved :: BSD License",
-    "Programming Language :: Python",
-    "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.10",
-    "Programming Language :: Python :: 3.11",
-    "Programming Language :: Python :: 3.12",
-    "Topic :: Scientific/Engineering",
+  "Development Status :: 5 - Production/Stable",
+  "Intended Audience :: Science/Research",
+  "Operating System :: OS Independent",
+  "License :: OSI Approved :: BSD License",
+  "Programming Language :: Python",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Topic :: Scientific/Engineering",
 ]
 
 dynamic = ["version"]
 
 dependencies = [
-  "numpy", 
-  "xarray>=2023.10.0", 
-  "cf_xarray", 
+  "numpy",
+  "xarray>=2023.10.0",
+  "cf_xarray",
   "dask[complete]",
   "netcdf4",
-  ]
+]
 
 [project.optional-dependencies]
 dev = [
@@ -45,13 +47,7 @@ dev = [
   "sphinx",
   "sphinx-rtd-theme",
 ]
-examples = [
-  "fsspec",
-  "s3fs",
-  "zarr",
-  "matplotlib",
-  "h5netcdf"
-]
+examples = ["fsspec", "s3fs", "zarr", "matplotlib", "h5netcdf"]
 
 [project.urls]
 "Homepage" = "https://github.com/asascience-open/xarray-subset-grid"
@@ -64,25 +60,23 @@ 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"]
 target-version = "py310"
 # Use a longer line length.
-line-length = 95
+line-length = 100
 
 [tool.ruff.lint]
 ignore = [
   "E402", # module level import not at top of file
   "E731", # do not assign a lambda expression, use a def
 ]
 select = [
-  "F", # Pyflakes
-  "E", # Pycodestyle
+  "F",   # Pyflakes
+  "E",   # Pycodestyle
   "W",
   "TID", # flake8-tidy-imports (absolute imports)
-  "I", # isort
-  "UP", # Pyupgrade
+  "I",   # isort
+  "UP",  # Pyupgrade
 ]
 extend-safe-fixes = [
   "TID252", # absolute imports
@@ -104,7 +98,7 @@ default = { solve-group = "default" }
 dev = { features = ["dev"], solve-group = "default" }
 examples = { features = ["examples"], solve-group = "default" }
 all = { features = ["dev", "examples"], solve-group = "default" }
-test310 = ["dev", "py310"] # implicit: test310 = ["dev", "py310", "default"]
+test310 = ["dev", "py310"]                                        # implicit: test310 = ["dev", "py310", "default"]
 test311 = ["dev", "py311"]
 test312 = ["dev", "py312"]
 
@@ -134,7 +128,9 @@ pytest-cov = "*"
 sphinx = "*"
 sphinx-rtd-theme = "*"
 
+
 [tool.pixi.feature.dev.tasks]
+lint = "ruff check"
 test = "pytest tests/"
 
 [tool.pixi.feature.examples.dependencies]

tests/test_grids/test_ugrid.py

@@ -2,10 +2,11 @@
 tests for ugrid code
 """
 from pathlib import Path
-import xarray as xr
-from xarray_subset_grid.grids import ugrid
 
 import pytest
+import xarray as xr
+
+from xarray_subset_grid.grids import ugrid
 
 EXAMPLE_DATA = Path(__file__).parent.parent.parent / "examples" / "example_data"
 
@@ -220,7 +221,6 @@
 # topology for TEST_FILE1
 grid_topology = {'node_coordinates': ('lon', 'lat'),
                  'face_node_connectivity': 'nv',
-                 'node_coordinates': ('lon', 'lat'),
                  'face_coordinates': ('lonc', 'latc'),
                  'face_face_connectivity': 'nbe'
                  }

xarray_subset_grid/accessor.py

@@ -1,7 +1,6 @@
-from typing import Optional
 import warnings
-#from typing import Optional, Union
 
+#from typing import Optional, Union
 import numpy as np
 import xarray as xr
 
@@ -20,7 +19,7 @@ def register_grid_impl(grid_impl: Grid, priority: int = 0):
     _grid_impls.insert(priority, grid_impl)
 
 
-def grid_factory(ds: xr.Dataset) -> Optional[Grid]:
+def grid_factory(ds: xr.Dataset) -> Grid | None:
     """
     Get the grid implementation for the given dataset.
     :param ds: The dataset to get the grid implementation for
@@ -37,7 +36,7 @@ class GridDatasetAccessor:
     """Accessor for grid operations on datasets"""
 
     _ds: xr.Dataset
-    _grid: Optional[Grid]
+    _grid: Grid | None
 
     def __init__(self, ds: xr.Dataset):
         """
@@ -48,7 +47,7 @@ def __init__(self, ds: xr.Dataset):
         self._grid = grid_factory(ds)
 
     @property
-    def grid(self) -> Optional[Grid]:
+    def grid(self) -> Grid | None:
         """The recognized grid implementation for the given dataset
         :return: The grid implementation or None if no implementation is found
         """
@@ -100,7 +99,7 @@ def subset_vars(self, vars: list[str]) -> xr.Dataset:
         return self._ds
 
     def subset_polygon(self, polygon: list[tuple[float, float]] | np.ndarray
-                       ) -> Optional[xr.Dataset]:
+                       ) -> xr.Dataset | None:
         """
         Subset the dataset to the grid.
 
@@ -116,7 +115,7 @@ def subset_polygon(self, polygon: list[tuple[float, float]] | np.ndarray
 
     def subset_bbox(
         self, bbox: tuple[float, float, float, float]
-    ) -> Optional[xr.Dataset]:
+    ) -> xr.Dataset | None:
         """Subset the dataset to the bounding box
 
         This call is forwarded to the grid implementation with the loaded dataset.

xarray_subset_grid/grid.py

@@ -1,6 +1,5 @@
 from abc import ABC, abstractmethod
 from collections.abc import Iterable
-from typing import Union
 
 import numpy as np
 import xarray as xr
@@ -55,7 +54,7 @@ def subset_vars(self, ds: xr.Dataset, vars: Iterable[str]) -> xr.Dataset:
 
     @abstractmethod
     def subset_polygon(
-        self, ds: xr.Dataset, polygon: Union[list[tuple[float, float]], np.ndarray]
+        self, ds: xr.Dataset, polygon: list[tuple[float, float]] | np.ndarray
     ) -> xr.Dataset:
         """Subset the dataset to the grid
         :param ds: The dataset to subset

xarray_subset_grid/grids/sgrid.py

@@ -1,5 +1,3 @@
-from typing import Union
-
 import numpy as np
 import xarray as xr
 
@@ -18,7 +16,8 @@ def recognize(ds: xr.Dataset) -> bool:
         except KeyError:
             return False
 
-        # For now, if the dataset has a grid topology and not a mesh topology, we assume it's a SGRID
+        # For now, if the dataset has a grid topology and not a mesh topology,
+        # we assume it's a SGRID
         return len(_grid_topology_keys) > 0 and _grid_topology_keys[0] in ds
 
     @property
@@ -56,7 +55,7 @@ def data_vars(self, ds: xr.Dataset) -> set[str]:
         return {var for var in ds.data_vars if not set(ds[var].dims).isdisjoint(dims)}
 
     def subset_polygon(
-        self, ds: xr.Dataset, polygon: Union[list[tuple[float, float]], np.ndarray]
+        self, ds: xr.Dataset, polygon: list[tuple[float, float]] | np.ndarray
     ) -> xr.Dataset:
         """Subset the dataset to the grid
         :param ds: The dataset to subset
@@ -111,14 +110,10 @@ def subset_polygon(
             # so that we can use it to mask and drop via xr.where, which requires that
             # the mask and data have the same shape and both are DataArrays with matching
             # dimensions
-            ds_subset = ds.assign(
-                subset_mask=xr.DataArray(polygon_mask, dims=mask_dims)
-            )
+            ds_subset = ds.assign(subset_mask=xr.DataArray(polygon_mask, dims=mask_dims))
 
             # Now we can use the mask to subset the data
-            ds_subset = (
-                ds_subset[vars].where(ds_subset.subset_mask, drop=True).drop_encoding()
-            )
+            ds_subset = ds_subset[vars].where(ds_subset.subset_mask, drop=True).drop_encoding()
 
             # Add the subsetted dataset to the list for merging
             ds_out.append(ds_subset)