Delete built-in cfgrib backend (#7670)

dcherian · web-flow · commit 0159e4571735 · 2023-03-29T09:19:50.000-06:00
* Delete built-in cfgrib  backend

* More deletes

* readd cfgrib to mypy ignores

* Fix docstring
diff --git a/ci/requirements/all-but-dask.yml b/ci/requirements/all-but-dask.yml
@@ -10,7 +10,6 @@ dependencies:
   - bottleneck
   - cartopy
   - cdms2
-  - cfgrib
   - cftime
   - coveralls
   - flox
diff --git a/ci/requirements/doc.yml b/ci/requirements/doc.yml
@@ -7,7 +7,6 @@ dependencies:
   - python=3.10
   - bottleneck
   - cartopy
-  - cfgrib>=0.9
   - dask-core>=2022.1
   - h5netcdf>=0.13
   - ipykernel
diff --git a/ci/requirements/environment-py311.yml b/ci/requirements/environment-py311.yml
@@ -8,7 +8,6 @@ dependencies:
   - bottleneck
   - cartopy
   # - cdms2
-  - cfgrib
   - cftime
   - dask-core
   - distributed
diff --git a/ci/requirements/environment-windows-py311.yml b/ci/requirements/environment-windows-py311.yml
@@ -6,7 +6,6 @@ dependencies:
   - bottleneck
   - cartopy
   # - cdms2  # Not available on Windows
-  # - cfgrib  # Causes Python interpreter crash on Windows: https://github.com/pydata/xarray/pull/3340
   - cftime
   - dask-core
   - distributed
diff --git a/ci/requirements/environment-windows.yml b/ci/requirements/environment-windows.yml
@@ -6,7 +6,6 @@ dependencies:
   - bottleneck
   - cartopy
   # - cdms2  # Not available on Windows
-  # - cfgrib  # Causes Python interpreter crash on Windows: https://github.com/pydata/xarray/pull/3340
   - cftime
   - dask-core
   - distributed
diff --git a/ci/requirements/environment.yml b/ci/requirements/environment.yml
@@ -8,7 +8,6 @@ dependencies:
   - bottleneck
   - cartopy
   - cdms2
-  - cfgrib
   - cftime
   - dask-core
   - distributed
diff --git a/ci/requirements/min-all-deps.yml b/ci/requirements/min-all-deps.yml
@@ -12,7 +12,6 @@ dependencies:
   - bottleneck=1.3
   - cartopy=0.20
   - cdms2=3.1
-  - cfgrib=0.9
   - cftime=1.5
   - coveralls
   - dask-core=2022.1
diff --git a/doc/getting-started-guide/installing.rst b/doc/getting-started-guide/installing.rst
@@ -45,8 +45,6 @@ For netCDF and IO
   other gridded raster datasets.
 - `iris <https://github.com/scitools/iris>`__: for conversion to and from iris'
   Cube objects
-- `cfgrib <https://github.com/ecmwf/cfgrib>`__: for reading GRIB files via the
-  *ECMWF ecCodes* library.
 
 For accelerating xarray
 ~~~~~~~~~~~~~~~~~~~~~~~
diff --git a/doc/user-guide/io.rst b/doc/user-guide/io.rst
@@ -1257,7 +1257,7 @@ GRIB format via cfgrib
 
 Xarray supports reading GRIB files via ECMWF cfgrib_ python driver,
 if it is installed. To open a GRIB file supply ``engine='cfgrib'``
-to :py:func:`open_dataset`:
+to :py:func:`open_dataset` after installing cfgrib_:
 
 .. ipython::
     :verbatim:
diff --git a/doc/whats-new.rst b/doc/whats-new.rst
@@ -51,6 +51,10 @@ Documentation
 Internal Changes
 ~~~~~~~~~~~~~~~~
 
+- Remove internal support for reading GRIB files through the ``cfgrib`` backend. ``cfgrib`` now uses the external
+  backend interface, so no existing code should break.
+  By `Deepak Cherian <https://github.com/dcherian>`_.
+
 .. _whats-new.2023.03.0:
 
 v2023.03.0 (March 22, 2023)
diff --git a/setup.cfg b/setup.cfg
@@ -89,7 +89,6 @@ io =
     fsspec
     cftime
     rasterio
-    cfgrib
     pooch
     ## Scitools packages & dependencies (e.g: cartopy, cf-units) can be hard to install
     # scitools-iris
diff --git a/xarray/backends/__init__.py b/xarray/backends/__init__.py
@@ -3,7 +3,6 @@
 DataStores provide a uniform interface for saving and loading data in different
 formats. They should not be used directly, but rather through Dataset objects.
 """
-from xarray.backends.cfgrib_ import CfGribDataStore
 from xarray.backends.common import AbstractDataStore, BackendArray, BackendEntrypoint
 from xarray.backends.file_manager import (
     CachingFileManager,
@@ -30,7 +29,6 @@
     "BackendEntrypoint",
     "FileManager",
     "CachingFileManager",
-    "CfGribDataStore",
     "DummyFileManager",
     "InMemoryDataStore",
     "NetCDF4DataStore",
diff --git a/xarray/backends/api.py b/xarray/backends/api.py
@@ -43,7 +43,7 @@
     T_NetcdfEngine = Literal["netcdf4", "scipy", "h5netcdf"]
     T_Engine = Union[
         T_NetcdfEngine,
-        Literal["pydap", "pynio", "pseudonetcdf", "cfgrib", "zarr"],
+        Literal["pydap", "pynio", "pseudonetcdf", "zarr"],
         type[BackendEntrypoint],
         str,  # no nice typing support for custom backends
         None,
@@ -64,7 +64,6 @@
     "h5netcdf": backends.H5NetCDFStore.open,
     "pynio": backends.NioDataStore,
     "pseudonetcdf": backends.PseudoNetCDFDataStore.open,
-    "cfgrib": backends.CfGribDataStore,
     "zarr": backends.ZarrStore.open_group,
 }
 
@@ -387,7 +386,7 @@ def open_dataset(
         ends with .gz, in which case the file is gunzipped and opened with
         scipy.io.netcdf (only netCDF3 supported). Byte-strings or file-like
         objects are opened by scipy.io.netcdf (netCDF3) or h5py (netCDF4/HDF).
-    engine : {"netcdf4", "scipy", "pydap", "h5netcdf", "pynio", "cfgrib", \
+    engine : {"netcdf4", "scipy", "pydap", "h5netcdf", "pynio", \
         "pseudonetcdf", "zarr", None}, installed backend \
         or subclass of xarray.backends.BackendEntrypoint, optional
         Engine to use when reading files. If not provided, the default engine
@@ -479,7 +478,7 @@ def open_dataset(
           relevant when using dask or another form of parallelism. By default,
           appropriate locks are chosen to safely read and write files with the
           currently active dask scheduler. Supported by "netcdf4", "h5netcdf",
-          "scipy", "pynio", "pseudonetcdf", "cfgrib".
+          "scipy", "pynio", "pseudonetcdf".
 
         See engine open function for kwargs accepted by each specific engine.
 
@@ -576,7 +575,7 @@ def open_dataarray(
         ends with .gz, in which case the file is gunzipped and opened with
         scipy.io.netcdf (only netCDF3 supported). Byte-strings or file-like
         objects are opened by scipy.io.netcdf (netCDF3) or h5py (netCDF4/HDF).
-    engine : {"netcdf4", "scipy", "pydap", "h5netcdf", "pynio", "cfgrib", \
+    engine : {"netcdf4", "scipy", "pydap", "h5netcdf", "pynio", \
         "pseudonetcdf", "zarr", None}, installed backend \
         or subclass of xarray.backends.BackendEntrypoint, optional
         Engine to use when reading files. If not provided, the default engine
@@ -666,7 +665,7 @@ def open_dataarray(
           relevant when using dask or another form of parallelism. By default,
           appropriate locks are chosen to safely read and write files with the
           currently active dask scheduler. Supported by "netcdf4", "h5netcdf",
-          "scipy", "pynio", "pseudonetcdf", "cfgrib".
+          "scipy", "pynio", "pseudonetcdf".
 
         See engine open function for kwargs accepted by each specific engine.
 
@@ -803,7 +802,7 @@ def open_mfdataset(
         If provided, call this function on each dataset prior to concatenation.
         You can find the file-name from which each dataset was loaded in
         ``ds.encoding["source"]``.
-    engine : {"netcdf4", "scipy", "pydap", "h5netcdf", "pynio", "cfgrib", \
+    engine : {"netcdf4", "scipy", "pydap", "h5netcdf", "pynio", \
         "pseudonetcdf", "zarr", None}, installed backend \
         or subclass of xarray.backends.BackendEntrypoint, optional
         Engine to use when reading files. If not provided, the default engine
diff --git a/xarray/backends/cfgrib_.py b/xarray/backends/cfgrib_.py
diff --git a/xarray/tests/__init__.py b/xarray/tests/__init__.py
@@ -75,7 +75,6 @@ def _importorskip(
 has_zarr, requires_zarr = _importorskip("zarr")
 has_fsspec, requires_fsspec = _importorskip("fsspec")
 has_iris, requires_iris = _importorskip("iris")
-has_cfgrib, requires_cfgrib = _importorskip("cfgrib")
 has_numbagg, requires_numbagg = _importorskip("numbagg")
 has_seaborn, requires_seaborn = _importorskip("seaborn")
 has_sparse, requires_sparse = _importorskip("sparse")
diff --git a/xarray/tests/test_backends.py b/xarray/tests/test_backends.py
@@ -63,7 +63,6 @@
     has_scipy,
     mock,
     network,
-    requires_cfgrib,
     requires_cftime,
     requires_dask,
     requires_fsspec,
@@ -4186,51 +4185,6 @@ def test_weakrefs(self) -> None:
             assert_identical(actual, expected)
 
 
-@requires_cfgrib
-class TestCfGrib:
-    def test_read(self) -> None:
-        expected = {
-            "number": 2,
-            "time": 3,
-            "isobaricInhPa": 2,
-            "latitude": 3,
-            "longitude": 4,
-        }
-        with open_example_dataset("example.grib", engine="cfgrib") as ds:
-            assert ds.dims == expected
-            assert list(ds.data_vars) == ["z", "t"]
-            assert ds["z"].min() == 12660.0
-
-    def test_read_filter_by_keys(self) -> None:
-        kwargs = {"filter_by_keys": {"shortName": "t"}}
-        expected = {
-            "number": 2,
-            "time": 3,
-            "isobaricInhPa": 2,
-            "latitude": 3,
-            "longitude": 4,
-        }
-        with open_example_dataset(
-            "example.grib", engine="cfgrib", backend_kwargs=kwargs
-        ) as ds:
-            assert ds.dims == expected
-            assert list(ds.data_vars) == ["t"]
-            assert ds["t"].min() == 231.0
-
-    def test_read_outer(self) -> None:
-        expected = {
-            "number": 2,
-            "time": 3,
-            "isobaricInhPa": 2,
-            "latitude": 2,
-            "longitude": 3,
-        }
-        with open_example_dataset("example.grib", engine="cfgrib") as ds:
-            res = ds.isel(latitude=[0, 2], longitude=[0, 1, 2])
-            assert res.dims == expected
-            assert res["t"].min() == 231.0
-
-
 @requires_pseudonetcdf
 @pytest.mark.filterwarnings("ignore:IOAPI_ISPH is assumed to be 6370000")
 class TestPseudoNetCDFFormat:
diff --git a/xarray/tests/test_distributed.py b/xarray/tests/test_distributed.py
diff --git a/xarray/tests/test_plugins.py b/xarray/tests/test_plugins.py
diff --git a/xarray/tutorial.py b/xarray/tutorial.py
diff --git a/xarray/util/print_versions.py b/xarray/util/print_versions.py
