refactor: update ruff rules and fix some type issues

pyproject.toml

@@ -47,27 +47,67 @@ select = [
   "C4", # flake8-comprehensions
   "C90", # mccabe
   "COM", # flake8-commas
+  "D", # pydocstyle
   "DTZ", # flake8-datetimez
   "E", "W", # pycodestyle
+  "ERA", # eradicate
   "F", # Pyflakes
+  "FA",
+  "FBT", # boolean trap
+  "FIX", # fix me
   "FLY", # flynt
   "FURB", # refurb
+  "G", # flake8-logging-format
   "I", # isort
+  "ICN", # import conventions
+  "INP", # no pep420
+  "INT", # gettext
+  "ISC", # implicit str concat
+  "LOG",  # flake8-logging
   "N", # pep8-nameing
   "NPY", # numpy specific rules
+  "PD", # pandas vet
   "PERF", # Perflint
+  "PGH",
   "PIE", # flake8-pie
+  "PL", # pylint
+  "PT", # pytest style
+  "PTH", # Pathlib
+  "Q", # quotes
+  "RET", # Return
+  "RSE", # raise
   "RUF", # Ruff specific rules
   "S", # flake8-bandit
   "SIM", # flake8-simplify
+  "SLF", # Self
+  "SLOT",
+  "T10", # debug statements
   "T20", # flake8-print
+  "TC", # Type checking
   "TCH", # flake8-type-checking
+  "TID", # tidy import
   "TRY", # tryceratops
   "UP", # pyupgrade
   "YTT", # flake8-2020
 ]
 
-ignore = ['S101', 'COM812', 'ANN101', 'ANN102', 'ANN401', 'TRY003']
+ignore = [
+  'ANN401',
+  'COM812',
+  'D101',
+  'D102',
+  'D103',
+  'D105',
+  'D107',
+  'D203',
+  'D213',
+  'D413',
+  'FBT001',
+  'FBT002',
+  'FIX002',
+  'S101',
+  'TRY003'
+]
 
 # Allow autofix for all enabled rules (when `--fix`) is provided.
 fixable = ["A", "B", "C", "D", "E", "F", "G", "I", "N", "Q", "S", "T", "W", "ANN", "ARG", "BLE", "COM", "DJ", "DTZ", "EM", "ERA", "EXE", "FBT", "ICN", "INP", "ISC", "NPY", "PD", "PGH", "PIE", "PL", "PT", "PTH", "PYI", "RET", "RSE", "RUF", "SIM", "SLF", "TCH", "TID", "TRY", "UP", "YTT"]
@@ -101,11 +141,15 @@ exclude = [
 # Allow unused variables when underscore-prefixed.
 dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
 
-
 [tool.ruff.lint.per-file-ignores]
-"cimsparql/data_models.py" = ["N815"]
-"docs/conf.py" = ["A001"]
+"docs/conf.py" = ["A001", "INP001", "D100"]
+"src/cimsparql/data_models.py" = ["N815"]
+"src/cimsparql/graphdb.py" = ["PD901"]
+"src/cimsparql/model.py" = ["PD901"]
+"src/cimsparql/type_mapper.py" = ["PD901"]
+"tests/**/*.py" = [ "D100", "D101", "D103", "D104", "PLR2004"]
 "tests/test*.py" = ["ANN201"]
+"tests/test_type_mapper.py" = ["PD901"]
 
 [tool.ruff.lint.pep8-naming]
 # Allow Pydantic's `@validator` decorator to trigger class method treatment.

src/cimsparql/graphdb.py

@@ -94,7 +94,7 @@ def __post_init__(self) -> None:
     def url(self) -> str:
         if self.rest_api == RestApi.BLAZEGRAPH:
             return service_blazegraph(self.server, self.repo, self.protocol)
-        elif self.rest_api == RestApi.DIRECT_SPARQL_ENDPOINT:
+        if self.rest_api == RestApi.DIRECT_SPARQL_ENDPOINT:
             return self.server
         return service(self.repo, self.server, self.protocol, self.path)
 

src/cimsparql/url.py

@@ -5,8 +5,6 @@
 
 """
 
-from __future__ import annotations
-
 
 def service(repo: str | None = None, server: str = "127.0.0.1:7200", protocol: str = "https", path: str = "") -> str:
     """Service url for GraphdDBClient.

src/cimsparql/value_mapper.py

@@ -6,7 +6,7 @@
 class ValueMapper:
     """Base value mapper."""
 
-    def map(self, df: pd.DataFrame) -> pd.DataFrame:  # A003
+    def map(self, df: pd.DataFrame) -> pd.DataFrame:
         return df
 
 

tests/test_graphdb.py

@@ -36,7 +36,7 @@
 
 
 def exception_logging(func: Callable[[Any], pd.DataFrame], *args: Any):
-    logger.debug(f"Starting {func.__name__}")
+    logger.debug("Starting %s", func.__name__)
     try:
         return func(*args)
     except Exception:

tests/test_model_properties.py

@@ -80,7 +80,7 @@ async def get_node_consistency_test_data(
     )
 
 
-async def collect_node_consistency_data() -> list[NodeConsistencyData]:
+async def collect_node_consistency_data() -> list[NodeConsistencyData | None]:
     test_models = [t_custom.federated_model(), t_entsoe.micro_t1_nl()]
     if any(m.model is None and m.must_run_in_ci and os.getenv("CI") for m in test_models):
         pytest.fail("Model that must run in CI is None")

tests/test_type_mapper.py

@@ -91,7 +91,7 @@ def test_map_data_types(httpserver: HTTPServer):
         ("date", ("2021-12-14", pd.Timestamp("2021-12-14 00:00:00"))),
         (
             "dateTime",
-            ("2002-10-14T12:00:00", datetime.datetime(2002, 10, 14, 12, 0, 0)),  # noqa DTZ001
+            ("2002-10-14T12:00:00", datetime.datetime(2002, 10, 14, 12, 0, 0)),  # noqa: DTZ001
         ),
         ("dateTime", ("2002-10-14T12:00:00Z", pd.Timestamp("2002-10-14 12:00:00+0000", tz="UTC"))),
         ("duration", ("P365D", datetime.timedelta(365))),
@@ -105,7 +105,7 @@ def test_map_data_types(httpserver: HTTPServer):
         ("time", ("21:32:52Z", pd.Timestamp("21:32:52", tz="UTC"))),
     ],
 )
-def test_xsd_types(dtype: str, test: tuple):
+def test_xsd_types(dtype: str, test: tuple[str, Any]):
     value, expect = test
     assert type_mapper.XSD_TYPE_MAP[dtype](value) == expect
 
@@ -135,7 +135,7 @@ class FloatSchema(CoercingSchema):
         ({"float_col": ["1.0", None]}, {"float_col": [1.0, np.nan]}),
     ],
 )
-def test_coerce_missing_type(httpserver: HTTPServer, in_data: dict, out_data: dict):
+def test_coerce_missing_type(httpserver: HTTPServer, in_data: dict[str, Any], out_data: dict[str, Any]):
     client = init_triple_store_server(httpserver)
     in_df, out_df = pd.DataFrame(in_data), pd.DataFrame(out_data)
     mapper = type_mapper.TypeMapper(client)

tests/test_xml_adaptor.py

@@ -7,7 +7,7 @@
 
 @pytest.fixture
 def xml_adaptor():
-    folder = Path(__file__).parent / "data/micro"
+    folder = Path(__file__).parent / "data" / "micro"
     return XmlModelAdaptor.from_folder(folder)