Merge pull request #336 from ocefpaf/move_more_lints_to_ruff

Move more lints to ruff
ioos · Feb 27, 2024 · 3012d18 · 3012d18
2 parents 9bbb705 + d209851
commit 3012d18
Show file tree

Hide file tree

Showing 20 changed files with 163 additions and 90 deletions.
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -13,12 +13,6 @@ repos:
     - id: file-contents-sorter
       files: requirements-dev.txt
 
-- repo: https://github.com/psf/black
-  rev: 24.2.0
-  hooks:
-  - id: black
-    language_version: python3
-
 - repo: https://github.com/pre-commit/mirrors-mypy
   rev: v1.8.0
   hooks:
@@ -59,6 +53,24 @@ repos:
   rev: v0.2.2
   hooks:
     - id: ruff
+      args: ["--fix", "--show-fixes"]
+    - id: ruff-format
+
+- repo: https://github.com/nbQA-dev/nbQA
+  rev: 1.7.1
+  hooks:
+    - id: nbqa-check-ast
+    - id: nbqa-black
+    - id: nbqa-ruff
+      args: [
+        --fix,
+        --config=ruff.toml,
+        ]
+
+- repo: https://github.com/bdice/nb-strip-paths
+  rev: v0.1.0
+  hooks:
+    - id: nb-strip-paths
 
 - repo: https://github.com/tox-dev/pyproject-fmt
   rev: 1.7.0

diff --git a/MANIFEST.in b/MANIFEST.in
@@ -11,6 +11,7 @@ prune notebooks
 prune tests
 
 exclude .coveragerc
+exclude ruff.toml
 exclude .gitignore
 exclude .isort.cfg
 exclude .pre-commit-config.yaml

diff --git a/erddapy/core/griddap.py b/erddapy/core/griddap.py
@@ -32,7 +32,9 @@ def _griddap_get_constraints(
         phrase, *__ = var.split("[")
         var_name = phrase.split(" ")[-1]
         variable_names.append(var_name)
-    table = pd.DataFrame({"dimension name": [], "min": [], "max": [], "length": []})
+    table = pd.DataFrame(
+        {"dimension name": [], "min": [], "max": [], "length": []},
+    )
     for dim in dim_names:
         url = f"{dataset_url}.csvp?{dim}"
         data = pd.read_csv(url).values
@@ -62,15 +64,21 @@ def _griddap_get_constraints(
     return constraints_dict, dim_names, variable_names
 
 
-def _griddap_check_constraints(user_constraints: dict, original_constraints: dict):
+def _griddap_check_constraints(
+    user_constraints: dict,
+    original_constraints: dict,
+):
     """Check that constraints changed by user match those expected by dataset."""
     if user_constraints.keys() != original_constraints.keys():
         raise ValueError(
             "keys in e.constraints have changed. Re-run e.griddap_initialize",
         )
 
 
-def _griddap_check_variables(user_variables: ListLike, original_variables: ListLike):
+def _griddap_check_variables(
+    user_variables: ListLike,
+    original_variables: ListLike,
+):
     """Check user has not requested variables that do not exist in dataset."""
     invalid_variables = []
     for variable in user_variables:

diff --git a/erddapy/core/interfaces.py b/erddapy/core/interfaces.py
@@ -33,7 +33,9 @@ def to_pandas(
     try:
         return pd.read_csv(data, **(pandas_kwargs or {}))
     except Exception as e:
-        raise ValueError(f"Could not read url {url} with Pandas.read_csv.") from e
+        raise ValueError(
+            f"Could not read url {url} with Pandas.read_csv.",
+        ) from e
 
 
 def to_ncCF(

diff --git a/erddapy/core/netcdf.py b/erddapy/core/netcdf.py
@@ -36,7 +36,11 @@ def _tempnc(data: BinaryIO) -> Generator[str, None, None]:
 
     tmp = None
     try:
-        tmp = NamedTemporaryFile(suffix=".nc", prefix="erddapy_", delete=delete)
+        tmp = NamedTemporaryFile(
+            suffix=".nc",
+            prefix="erddapy_",
+            delete=delete,
+        )
         tmp.write(data.read())
         tmp.flush()
         yield tmp.name

diff --git a/erddapy/core/url.py b/erddapy/core/url.py
@@ -30,7 +30,9 @@ def _sort_url(url):
         else:
             variables, constraints = parts.query.split("&", maxsplit=1)
         sorted_variables = ",".join(sorted(variables.split(",")))
-        sorted_query = OrderedDict(sorted(dict(parse.parse_qsl(constraints)).items()))
+        sorted_query = OrderedDict(
+            sorted(dict(parse.parse_qsl(constraints)).items()),
+        )
         sorted_query_str = parse.unquote(parse.urlencode(sorted_query))
         sorted_url = f"{parts.scheme}://{parts.netloc}{parts.path}?{parts.params}{sorted_variables}&{sorted_query_str}{parts.fragment}"
     else:
@@ -134,7 +136,9 @@ def _format_constraints_url(kwargs: dict) -> str:
 def _check_substrings(constraint):
     """Extend the OPeNDAP with extra strings."""
     substrings = ["now", "min", "max"]
-    return any(True for substring in substrings if substring in str(constraint))
+    return any(
+        True for substring in substrings if substring in str(constraint)
+    )
 
 
 def parse_dates(
@@ -326,7 +330,9 @@ def get_info_url(
 
     """
     if not dataset_id:
-        raise ValueError(f"You must specify a valid dataset_id, got {dataset_id}")
+        raise ValueError(
+            f"You must specify a valid dataset_id, got {dataset_id}",
+        )
 
     url = f"{server}/info/{dataset_id}/index.{response}"
     return url
@@ -393,7 +399,9 @@ def get_download_url(
 
     """
     if not dataset_id:
-        raise ValueError(f"Please specify a valid `dataset_id`, got {dataset_id}")
+        raise ValueError(
+            f"Please specify a valid `dataset_id`, got {dataset_id}",
+        )
 
     if not protocol:
         raise ValueError(f"Please specify a valid `protocol`, got {protocol}")

diff --git a/erddapy/erddapy.py b/erddapy/erddapy.py
@@ -161,7 +161,9 @@ def griddap_initialize(
                 f"Method only valid using griddap protocol, got {self.protocol}",
             )
         if dataset_id is None:
-            raise ValueError(f"Must set a valid dataset_id, got {self.dataset_id}")
+            raise ValueError(
+                f"Must set a valid dataset_id, got {self.dataset_id}",
+            )
         # Return the opendap URL without any slicing so the user can do it later.
         if self.response == "opendap":
             return
@@ -315,10 +317,14 @@ def get_download_url(
         constraints = constraints if constraints else self.constraints
 
         if not dataset_id:
-            raise ValueError(f"Please specify a valid `dataset_id`, got {dataset_id}")
+            raise ValueError(
+                f"Please specify a valid `dataset_id`, got {dataset_id}",
+            )
 
         if not protocol:
-            raise ValueError(f"Please specify a valid `protocol`, got {protocol}")
+            raise ValueError(
+                f"Please specify a valid `protocol`, got {protocol}",
+            )
 
         if (
             protocol == "griddap"
@@ -362,7 +368,11 @@ def to_pandas(
         response = kw.pop("response", "csvp")
         distinct = kw.pop("distinct", False)
         url = self.get_download_url(response=response, distinct=distinct)
-        return to_pandas(url, requests_kwargs=requests_kwargs, pandas_kwargs=dict(**kw))
+        return to_pandas(
+            url,
+            requests_kwargs=requests_kwargs,
+            pandas_kwargs=dict(**kw),
+        )
 
     def to_ncCF(self, protocol: str = None, **kw):
         """Load the data request into a Climate and Forecast compliant netCDF4-python object."""
@@ -392,7 +402,12 @@ def to_xarray(
             requests_kwargs = {**{"auth": self.auth}, **requests_kwargs}
         else:
             requests_kwargs = {"auth": self.auth}
-        return to_xarray(url, response, requests_kwargs, xarray_kwargs=dict(**kw))
+        return to_xarray(
+            url,
+            response,
+            requests_kwargs,
+            xarray_kwargs=dict(**kw),
+        )
 
     def to_iris(self, **kw):
         """Load the data request into an iris.CubeList.
@@ -409,7 +424,9 @@ def _get_variables_uncached(self, dataset_id: OptionalStr = None) -> dict:
             dataset_id = self.dataset_id
 
         if dataset_id is None:
-            raise ValueError(f"You must specify a valid dataset_id, got {dataset_id}")
+            raise ValueError(
+                f"You must specify a valid dataset_id, got {dataset_id}",
+            )
 
         url = self.get_info_url(dataset_id=dataset_id, response="csv")
 
@@ -419,14 +436,21 @@ def _get_variables_uncached(self, dataset_id: OptionalStr = None) -> dict:
         self._dataset_id = dataset_id
         for variable in set(_df["Variable Name"]):
             attributes = (
-                _df.loc[_df["Variable Name"] == variable, ["Attribute Name", "Value"]]
+                _df.loc[
+                    _df["Variable Name"] == variable,
+                    ["Attribute Name", "Value"],
+                ]
                 .set_index("Attribute Name")
                 .to_dict()["Value"]
             )
             variables.update({variable: attributes})
         return variables
 
-    def get_var_by_attr(self, dataset_id: OptionalStr = None, **kwargs) -> list[str]:
+    def get_var_by_attr(
+        self,
+        dataset_id: OptionalStr = None,
+        **kwargs,
+    ) -> list[str]:
         """
         Return a variable based on its attributes.
 

diff --git a/erddapy/multiple_server_search.py b/erddapy/multiple_server_search.py
@@ -74,7 +74,10 @@ def search_servers(
             f"Protocol must be tabledap or griddap, got {protocol}",
         )
     if servers_list:
-        urls = {server: _format_search_string(server, query) for server in servers_list}
+        urls = {
+            server: _format_search_string(server, query)
+            for server in servers_list
+        }
     else:
         urls = {
             key: _format_search_string(server.url, query)

diff --git a/notebooks/00-quick_intro.ipynb b/notebooks/00-quick_intro.ipynb
@@ -32,7 +32,6 @@
    "source": [
     "from erddapy import ERDDAP\n",
     "\n",
-    "\n",
     "server = \"https://standards.sensors.ioos.us/erddap\"\n",
     "e = ERDDAP(\n",
     "    server=server,\n",
@@ -63,7 +62,7 @@
     "    \"latitude\",\n",
     "    \"longitude\",\n",
     "    \"sea_water_temperature\",\n",
-    "    \"air_temperature\"\n",
+    "    \"air_temperature\",\n",
     "]\n",
     "\n",
     "e.constraints = {\n",

diff --git a/notebooks/01a-griddap.ipynb b/notebooks/01a-griddap.ipynb
@@ -24,7 +24,6 @@
     "import geopandas\n",
     "import pooch\n",
     "\n",
-    "\n",
     "url = \"https://naturalearth.s3.amazonaws.com/4.1.1/50m_physical/ne_50m_geography_marine_polys.zip\"\n",
     "fname = pooch.retrieve(\n",
     "    url,\n",
@@ -87,9 +86,7 @@
     "e.griddap_initialize()\n",
     "\n",
     "print(f\"variables in this dataset:\\n\\n{e.variables}\")\n",
-    "print(\n",
-    "    f\"\\nconstraints of this dataset:\\n\\n{json.dumps(e.constraints, indent=1)}\"\n",
-    ")"
+    "print(f\"\\nconstraints of this dataset:\\n\\n{json.dumps(e.constraints, indent=1)}\")"
    ]
   },
   {
@@ -188,7 +185,6 @@
     "import cartopy.crs as ccrs\n",
     "import matplotlib.pyplot as plt\n",
     "\n",
-    "\n",
     "fig, ax = plt.subplots(subplot_kw={\"projection\": ccrs.PlateCarree()})\n",
     "ds[\"ROSE\"].plot(ax=ax)\n",
     "ax.coastlines();"
@@ -210,7 +206,6 @@
    "source": [
     "import regionmask\n",
     "\n",
-    "\n",
     "region = regionmask.from_geopandas(SA, name=name)\n",
     "region.plot();"
    ]
@@ -340,7 +335,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.1"
+   "version": "3.10.13"
   }
  },
  "nbformat": 4,