Merge pull request #1026 from ocefpaf/pre-commit_fixes

Enable bugbear...

cchecker.py

@@ -34,7 +34,7 @@ def parse_options(opts):
         try:
             checker_type, checker_opt = opt_str.split(":", 1)
         except ValueError:
-            warnings.warn(f"Could not split option {opt_str}, ignoring")
+            warnings.warn(f"Could not split option {opt_str}, ignoring", stacklevel=2)
         else:
             options_dict[checker_type].add(checker_opt)
     return options_dict

compliance_checker/acdd.py

@@ -188,7 +188,7 @@ def check_var_units(self, ds):
             msgs = []
             # Check units and dims for variable
             unit_check = hasattr(ds.variables[variable], "units")
-            no_dim_check = getattr(ds.variables[variable], "dimensions") == ()
+            no_dim_check = ds.variables[variable].dimensions == ()
             # Check if we have no dimensions.  If no dims, skip test
             if no_dim_check:
                 continue
@@ -256,7 +256,7 @@ def check_lat_extents(self, ds):
 
         # identify lat var(s) as per CF 4.1
         lat_vars = {}  # var -> number of criteria passed
-        for name, var in ds.variables.items():
+        for _name, var in ds.variables.items():
             # must have units
             if not hasattr(var, "units"):
                 continue
@@ -354,7 +354,7 @@ def check_lon_extents(self, ds):
 
         # identify lon var(s) as per CF 4.2
         lon_vars = {}  # var -> number of criteria passed
-        for name, var in ds.variables.items():
+        for _name, var in ds.variables.items():
             # must have units
             if not hasattr(var, "units"):
                 continue
@@ -779,7 +779,7 @@ def check_metadata_link(self, ds):
         if not hasattr(ds, "metadata_link"):
             return
         msgs = []
-        meta_link = getattr(ds, "metadata_link")
+        meta_link = ds.metadata_link
         if "http" not in meta_link:
             msgs.append("Metadata URL should include http:// or https://")
         valid_link = len(msgs) == 0
@@ -793,7 +793,7 @@ def check_id_has_no_blanks(self, ds):
         """
         if not hasattr(ds, "id"):
             return
-        if " " in getattr(ds, "id"):
+        if " " in ds.id:
             return Result(
                 BaseCheck.MEDIUM,
                 False,

compliance_checker/base.py

@@ -549,7 +549,7 @@ def attr_check(kvp, ds, priority, ret_val, gname=None, var_name=None):
     # starting with "check".  Avoid naming check functions
     # starting with check if you want to pass them in with
     # a tuple to avoid them being checked more than once
-    elif hasattr(other, "__call__"):
+    elif callable(other):
         # check that the attribute is actually present.
         # This reduces boilerplate in functions by not needing
         # to check whether the attribute is present every time
@@ -629,7 +629,10 @@ def score_group(group_name=None):
     Please do not using scoring groups and update your plugins
     if necessary
     """
-    warnings.warn("Score_group is deprecated as of Compliance Checker v3.2.")
+    warnings.warn(
+        "Score_group is deprecated as of Compliance Checker v3.2.",
+        stacklevel=2,
+    )
 
     def _inner(func):
         def _dec(s, ds):

compliance_checker/cf/cf_1_6.py

@@ -126,7 +126,7 @@ def check_child_attr_data_types(self, ds):
             "_FillValue",
         }
 
-        for var_name, var in ds.variables.items():
+        for _var_name, var in ds.variables.items():
             for att_name in special_attrs.intersection(var.ncattrs()):
                 self._parent_var_attr_type_check(att_name, var, ctx)
         return ctx.to_result()
@@ -416,7 +416,7 @@ def check_fill_value_equal_missing_value(self, ds):
         fails = []
         total = 0
 
-        for name, variable in ds.variables.items():
+        for _name, variable in ds.variables.items():
             # If the variable have a defined _FillValue a defined missing_value check it.
 
             if hasattr(variable, "_FillValue") and hasattr(variable, "missing_value"):
@@ -447,7 +447,7 @@ def check_valid_range_or_valid_min_max_present(self, ds):
         fails = []
         total = 0
 
-        for name, variable in ds.variables.items():
+        for _name, variable in ds.variables.items():
             if hasattr(variable, "valid_max") and (
                 hasattr(variable, "valid_min") or hasattr(variable, "valid_range")
             ):

compliance_checker/cf/cf_1_7.py

@@ -794,7 +794,8 @@ def _evaluate_towgs84(self, val):
             return (True, msg)
 
     def check_grid_mapping(self, ds):
-        super().check_grid_mapping.__doc__
+        # FIXME: Looks like this is not needed.
+        # super().check_grid_mapping.__doc__
         prev_return = super().check_grid_mapping(ds)
         grid_mapping_variables = cfutil.get_grid_mapping_variables(ds)
         for var_name in sorted(grid_mapping_variables):
@@ -876,6 +877,7 @@ def check_grid_mapping(self, ds):
                     warn(
                         "Error occurred while trying to query "
                         "Proj4 SQLite database at {}: {}".format(proj_db_path, str(e)),
+                        stacklevel=2,
                     )
             prev_return[var.name] = test_ctx.to_result()
 
@@ -891,6 +893,7 @@ def check_standard_name_deprecated_modifiers(self, ds):
         if deprecated_var_names:
             warn(
                 f"Deprecated standard_name modifiers found on variables {deprecated_var_names}",
+                stacklevel=2,
             )
 
     def _process_v_datum_str(self, v_datum_str, conn):
@@ -926,7 +929,8 @@ def _check_dimensionless_vertical_coordinate_1_7(
         formula_terms = getattr(variable, "formula_terms", None)
         # Skip the variable if it's dimensional
         correct_computed_std_name_ctx = TestCtx(
-            BaseCheck.MEDIUM, self.section_titles["4.3"]
+            BaseCheck.MEDIUM,
+            self.section_titles["4.3"],
         )
         # IMPLEMENTATION CONFORMANCE 4.3.3 REQUIRED
         correct_computed_std_name_ctx.assert_true(

compliance_checker/cf/cf_1_8.py

@@ -134,7 +134,7 @@ def check_geometry(self, ds: Dataset):
             else:
                 geometry_var = ds.variables[geometry_var_name]
 
-            geometry_type = getattr(geometry_var, "geometry_type")
+            geometry_type = geometry_var.geometry_type
             try:
                 node_coord_var_names = geometry_var.node_coordinates
             except AttributeError:
@@ -471,6 +471,7 @@ def handle_lsid(self, taxon_lsid_variable, taxon_name_variable):
                     "'urn:lsid:marinespecies.org:taxname:<AphiaID>' or "
                     "'urn:lsid:itis.gov:itis_tsn:<TSN>'.  Assuming "
                     "pass condition",
+                    stacklevel=1,
                 )
 
         return messages
@@ -597,8 +598,8 @@ def check_polygon_orientation(self, transposed_coords, interior=False):
 
         try:
             polygon = Polygon(transposed_coords.tolist())
-        except ValueError:
-            raise ValueError(
+        except ValueError as err:
+            raise ValueError from err(
                 "Polygon contains too few points to perform orientation test",
             )
 

compliance_checker/cf/cf_1_9.py

@@ -76,7 +76,8 @@ def check_time_coordinate_variable_has_calendar(self, ds):
         return ret_val
 
     def check_time_coordinate(self, ds):
-        super().check_calendar.__doc__
+        # FIXME: Looks like this is not needed.
+        # super().check_calendar.__doc__
         prev_return = super().check_time_coordinate(ds)
         seconds_regex = regex.compile(
             r"\w+ since \d{1,4}-\d{1,2}-\d{1,2}[ T]"

compliance_checker/cf/cf_base.py

@@ -400,20 +400,20 @@ def _check_formula_terms(self, ds, coord, dimless_coords_dict):
         # the regex grouping always has component names in even positions and
         # the corresponding variable name in odd positions.
         poorly_formed_formula_terms = ("Attribute formula_terms is not well-formed",)
-        matches = [
-            match
-            for match in regex.finditer(
-                r"(\w+):\s+(\w+)(?:\s+(?!$)|$)", variable.formula_terms
-            )
-        ]
+        matches = list(
+            regex.finditer(
+                r"(\w+):\s+(\w+)(?:\s+(?!$)|$)",
+                variable.formula_terms,
+            ),
+        )
         if not matches:
             valid_formula_terms.add_failure(poorly_formed_formula_terms)
             return valid_formula_terms.to_result()
 
-        terms = set(m.group(1) for m in matches)
+        terms = {m.group(1) for m in matches}
         # get the variables named in the formula terms and check if any
         # are not present in the dataset
-        missing_vars = sorted(set(m.group(2) for m in matches) - set(ds.variables))
+        missing_vars = sorted({m.group(2) for m in matches} - set(ds.variables))
         missing_fmt = "The following variable(s) referenced in {}:formula_terms are not present in the dataset: {}"
         valid_formula_terms.assert_true(
             len(missing_vars) == 0,
@@ -567,7 +567,7 @@ def _find_ancillary_vars(self, ds, refresh=False):
         # Invalidate the cache at all costs
         self._ancillary_vars[ds] = []
 
-        for name, var in ds.variables.items():
+        for _name, var in ds.variables.items():
             if hasattr(var, "ancillary_variables"):
                 for anc_name in var.ancillary_variables.split(" "):
                     if anc_name in ds.variables:
@@ -638,6 +638,7 @@ def _find_cf_standard_name_table(self, ds):
                         warn(
                             "Cannot extract CF standard name version number "
                             "from standard_name_vocabulary string",
+                            stacklevel=2,
                         )
                         return False
             else:
@@ -650,6 +651,7 @@ def _find_cf_standard_name_table(self, ds):
                 "Cannot convert standard name table to lowercase.  This can "
                 "occur if a non-string standard_name_vocabulary global "
                 "attribute is supplied",
+                stacklevel=2,
             )
             return False
 
@@ -694,6 +696,7 @@ def _find_cf_standard_name_table(self, ds):
             warn(
                 f"Problem fetching standard name table:\n{e}\n"
                 f"Using packaged v{self._std_names._version}",
+                stacklevel=2,
             )
             return False
 

compliance_checker/cfutil.py

@@ -67,8 +67,8 @@ def attr_membership(attr_val, value_set, attr_type=str, modifier_fn=lambda x: x)
 
     if not isinstance(attr_val, attr_type):
         warnings.warn(
-            "Attribute is of type {}, {} expected. "
-            "Attempting to cast to expected type.".format(type(attr_val), attr_type),
+            f"Attribute is of type {type(attr_val)!r}, {attr_type!r} expected. Attempting to cast to expected type.",
+            stacklevel=2,
         )
         try:
             # if the expected type is str, try casting to unicode type
@@ -79,7 +79,7 @@ def attr_membership(attr_val, value_set, attr_type=str, modifier_fn=lambda x: x)
                 new_attr_val = attr_type(attr_val)
         # catch casting errors
         except (ValueError, UnicodeEncodeError):
-            warnings.warn(f"Could not cast to type {attr_type}")
+            warnings.warn(f"Could not cast to type {attr_type}", stacklevel=2)
             return False
     else:
         new_attr_val = attr_val
@@ -88,8 +88,8 @@ def attr_membership(attr_val, value_set, attr_type=str, modifier_fn=lambda x: x)
         is_in_set = modifier_fn(new_attr_val) in value_set
     except Exception as e:
         warnings.warn(
-            "Could not apply modifier function {} to value: "
-            " {}".format(modifier_fn, e.msg),
+            f"Could not apply modifier function {modifier_fn} to value: {e.msg}",
+            stacklevel=2,
         )
         return False
 
@@ -172,15 +172,15 @@ def is_geophysical(ds, variable):
 
     if not isinstance(standard_name_test, str):
         warnings.warn(
-            "Variable {} has non string standard name, "
-            "Attempting cast to string".format(variable),
+            f"Variable {variable} has non string standard name, Attempting cast to string",
+            stacklevel=2,
         )
         try:
             standard_name = str(standard_name_test)
         except ValueError:
             warnings.warn(
-                "Unable to cast standard name to string, excluding "
-                "from geophysical variables",
+                "Unable to cast standard name to string, excluding from geophysical variables",
+                stacklevel=2,
             )
     else:
         standard_name = standard_name_test

compliance_checker/protocols/netcdf.py

@@ -84,6 +84,7 @@ def is_remote_netcdf(ds_str):
     except requests.exceptions.RequestException as e:
         warnings.warn(
             f"Received exception when making HEAD request to {ds_str}: {e}",
+            stacklevel=2,
         )
         content_type = None
     else:

compliance_checker/runner.py

@@ -40,7 +40,7 @@ def run_checker(
         skip_checks=None,
         include_checks=None,
         output_filename="-",
-        output_format=["text"],
+        output_format="text",
         options=None,
     ):
         """
@@ -184,7 +184,7 @@ def html_output(cls, cs, score_dict, output_filename, ds_loc, limit):
         """
         checkers_html = []
         for ds, score_groups in score_dict.items():
-            for checker, (groups, errors) in score_groups.items():
+            for checker, (groups, _errors) in score_groups.items():
                 checkers_html.append(cs.checker_html_output(checker, groups, ds, limit))
 
         html = cs.html_output(checkers_html)

compliance_checker/suite.py

@@ -172,6 +172,7 @@ def _load_checkers(cls, checkers):
                         'attributes. "name" attribute is deprecated. '
                         "Assuming checker is latest version.",
                         DeprecationWarning,
+                        stacklevel=2,
                     )
                     # append "unknown" to version string since no versioning
                     # info was provided
@@ -350,6 +351,7 @@ def _process_skip_checks(cls, skip_checks):
                             split_check_spec[1],
                             check_name,
                         ),
+                        stacklevel=2,
                     )
                     check_max_level = BaseCheck.HIGH
 
@@ -358,7 +360,10 @@ def _process_skip_checks(cls, skip_checks):
         return check_dict
 
     def run(self, ds, skip_checks, *checker_names):
-        warnings.warn("suite.run is deprecated, use suite.run_all in calls " "instead")
+        warnings.warn(
+            "suite.run is deprecated, use suite.run_all in calls instead",
+            stacklevel=2,
+        )
         return self.run_all(ds, checker_names, skip_checks=skip_checks)
 
     def run_all(self, ds, checker_names, include_checks=None, skip_checks=None):

pyproject.toml

@@ -15,7 +15,7 @@ markers = [
 [tool.ruff]
 select = [
     "A", # flake8-builtins
-    # "B", # flake8-bugbear
+    "B", # flake8-bugbear
     "C4", # flake8-comprehensions
     "E", # pycodecstyle
     "F", # flakes
@@ -39,3 +39,5 @@ ignore = [
   "E402",
   "A001",
 ]
+"compliance_checker/__init__.py" = ["B019"]
+"compliance_checker/cfutil.py" = ["B028"]