Add 'ERA5-Land' dataset to predefined datasets

README.md

@@ -74,13 +74,13 @@ and produce a hydrograph.
 In condensed code:
 
 ```python
-forcing = ewatercycle.forcing.sources['MarrmotForcing'].generate(...)
-model = ewatercycle.models.sources['MarrmotM14'](forcing)
+forcing = ewatercycle.forcing.sources["MarrmotForcing"].generate(...)
+model = ewatercycle.models.sources["MarrmotM14"](forcing)
 model.setup(...)
 model.initialize()
-while (model.time < model.end_time):
+while model.time < model.end_time:
     model.update()
-    value = model.get_value_as_xarray('flux_out_Q')
+    value = model.get_value_as_xarray("flux_out_Q")
 model.finalize()
 ewatercycle.analysis.hydrograph(...)
 ```
@@ -98,14 +98,14 @@ from ewatercycle.testing.fixtures import rhine_shape
 import shapefile
 import xarray as xr
 
-forcing = ewatercycle.forcing.sources['MarrmotForcing'].generate(
-    dataset='ERA5',
-    start_time='2010-01-01T00:00:00Z',
-    end_time='2010-12-31T00:00:00Z',
-    shape=rhine_shape()
+forcing = ewatercycle.forcing.sources["MarrmotForcing"].generate(
+    dataset="ERA5",
+    start_time="2010-01-01T00:00:00Z",
+    end_time="2010-12-31T00:00:00Z",
+    shape=rhine_shape(),
 )
 
-model = ewatercycle.models.sources['MarrmotM14'](version='2020.11', forcing=forcing)
+model = ewatercycle.models.sources["MarrmotM14"](version="2020.11", forcing=forcing)
 
 cfg_file, cfg_dir = model.setup(
     threshold_flow_generation_evap_change=0.1,
@@ -115,31 +115,29 @@ model.initialize(cfg_file)
 
 # flux_out_Q unit conversion factor from mm/day to m3/s
 sf = shapefile.Reader(rhine_shape())
-area = sf.record(0)['SUB_AREA'] * 1e6 # from shapefile in m2
+area = sf.record(0)["SUB_AREA"] * 1e6  # from shapefile in m2
 conversion_mmday2m3s = 1 / (1000 * 24 * 60 * 60)
 conversion = conversion_mmday2m3s * area
 
 simulated_discharge = []
-while (model.time < model.end_time):
+while model.time < model.end_time:
     model.update()
-    simulated_discharge.append(
-        model.get_value_as_xarray('flux_out_Q')
-    )
+    simulated_discharge.append(model.get_value_as_xarray("flux_out_Q"))
 
 observations_ds = ewatercycle.observation.grdc.get_grdc_data(
     station_id=6335020,  # Rees, Germany
     start_time=model.start_time_as_isostr,
     end_time=model.end_time_as_isostr,
-    column='observation',
+    column="observation",
 )
 
 # Combine the simulated discharge with the observations
-sim_da = xr.concat(simulated_discharge, dim='time') * conversion
-sim_da.name = 'simulated'
+sim_da = xr.concat(simulated_discharge, dim="time") * conversion
+sim_da.name = "simulated"
 discharge = xr.merge([sim_da, observations_ds["observation"]]).to_dataframe()
 discharge = discharge[["observation", "simulated"]].dropna()
 
-ewatercycle.analysis.hydrograph(discharge, reference='observation')
+ewatercycle.analysis.hydrograph(discharge, reference="observation")
 
 model.finalize()
 ```

src/ewatercycle/_forcings/caravan.py

@@ -199,7 +199,7 @@ def generate(  # type: ignore[override]
             raise ValueError(msg)
         basin_id = str(kwargs["basin_id"])
 
-        dataset: str = basin_id.split("_")[0]
+        dataset: str = basin_id.split("_", maxsplit=1)[0]
         ds = cls.get_dataset(dataset)
         ds_basin = ds.sel(basin_id=basin_id.encode())
         ds_basin_time = crop_ds(ds_basin, start_time, end_time)

src/ewatercycle/base/parameter_set.py

@@ -40,7 +40,7 @@ def download_github_repo(
     """
     zip_url = f"https://github.com/{org}/{repo}/archive/refs/heads/{branch}.zip"
 
-    https_response = urlopen(zip_url)  # noqa: S310
+    https_response = urlopen(zip_url)
     if https_response.status != 200:
         msg = (
             f"HTTP error {https_response.status}\n"

src/ewatercycle/esmvaltool/builder.py

@@ -290,8 +290,8 @@ def add_variable(
         units: str | None = None,
         stats: ClimateStatistics | None = None,
         short_name: str | None = None,
-        start_year: int | None | Literal[False] = None,
-        end_year: int | None | Literal[False] = None,
+        start_year: int | Literal[False] | None = None,
+        end_year: int | Literal[False] | None = None,
     ):
         """Add a variable to the recipe.
 

src/ewatercycle/esmvaltool/datasets.py

@@ -17,6 +17,13 @@
         type="reanaly",
         version=1,
     ),
+    "ERA5-Land": Dataset(
+        dataset="ERA5-Land",
+        project="OBS6",
+        tier=3,
+        type="reanaly",
+        version=1,
+    ),
 }
 """Dictionary of predefined forcing datasets.
 
@@ -28,7 +35,7 @@
 
     >> from ewatercycle.forcing import DATASETS
     >> list(DATASETS.keys())
-    ['ERA5', 'ERA-Interim']
+    ['ERA5', 'ERA-Interim', 'ERA5-Land']
 
 """
 

src/ewatercycle/observation/caravan.py

@@ -60,7 +60,7 @@ def get_caravan_data(
             NCO:            netCDF Operators version 5.0.6 (Homepage = http://nco.sf....
             _NCProperties:  version=2,netcdf=4.8.1,hdf5=1.10.7
     """  # noqa: D214,D410,D411
-    dataset: str = basin_id.split("_")[0]
+    dataset: str = basin_id.split("_", maxsplit=1)[0]
     ds = CaravanForcing.get_dataset(dataset)
     ds_basin = ds.sel(basin_id=basin_id.encode())
     ds_basin_time = crop_ds(ds_basin, start_time, end_time)

src/ewatercycle/observation/grdc.py

@@ -90,7 +90,7 @@ def get_grdc_data(
                 institution:    GRDC
                 history:        Download from GRDC Database, 21/06/2024
                 missing_value:  -999.000
-    """  # noqa: D214,D410,D411
+    """
     if data_home:
         data_path = to_absolute_path(data_home)
     elif CFG.grdc_location:

src/ewatercycle/util.py

@@ -339,7 +339,7 @@ def extract_package_name(value: str) -> str:
     E.g. "ewatercycle_HBV.model:HBV" will return
     "ewatercycle_HBV".
     """
-    source = value.split(":")[0]
+    source = value.split(":", maxsplit=1)[0]
     return source.split(".")[0]
 
 

tests/src/base/test_forcing.py

@@ -369,7 +369,7 @@ def test_retrieve_caravan_forcing(tmp_path: Path, mock_retrieve: mock.MagicMock)
     content = list(ds.data_vars.keys())
     expected = ["Q", "evspsblpot", "pr", "tas", "tasmax", "tasmin"]
     assert content == expected
-    mock_retrieve.assert_called_once_with(basin_id.split("_")[0])
+    mock_retrieve.assert_called_once_with(basin_id.split("_", maxsplit=1)[0])
 
     assert caravan_forcing.to_xarray()["evspsblpot"].attrs["unit"] == "kg m-2 s-1"
     assert caravan_forcing.to_xarray()["pr"].attrs["unit"] == "kg m-2 s-1"
@@ -394,7 +394,7 @@ def test_retrieve_caravan_forcing_empty_vars(
     content = list(ds.data_vars.keys())
     expected = ["Q", "evspsblpot", "pr", "tas", "tasmax", "tasmin"]
     assert content == expected
-    mock_retrieve.assert_called_once_with(basin_id.split("_")[0])
+    mock_retrieve.assert_called_once_with(basin_id.split("_", maxsplit=1)[0])
 
 
 def test_retrieve_caravan_forcing_no_basin_id(