Merge pull request #1089 from PowerGridModel/feature/ruff-checks

mgovers · web-flow · commit 070b81bcb810 · 2025-08-19T07:59:27.000Z
Linting and Formatting: S, FBT, PT, TRY checks
diff --git a/code_generation/code_gen.py b/code_generation/code_gen.py
@@ -12,7 +12,7 @@
 TEMPLATE_DIR = Path(__file__).parent / "templates"
 OUTPUT_PATH = Path(__file__).parents[1]
 
-JINJA_ENV = Environment(loader=FileSystemLoader(TEMPLATE_DIR))
+JINJA_ENV = Environment(loader=FileSystemLoader(TEMPLATE_DIR), autoescape=True)
 
 
 def _data_type_nan(data_type: str):
diff --git a/code_generation/templates/power_grid_model_c/power_grid_model/include/power_grid_model/auxiliary/attribute_classes.hpp.jinja b/code_generation/templates/power_grid_model_c/power_grid_model/include/power_grid_model/auxiliary/attribute_classes.hpp.jinja
@@ -12,7 +12,7 @@
 #include "../common/common.hpp"
 #include "../common/enum.hpp"
 #include "../common/three_phase_tensor.hpp"
-
+{% autoescape false %}
 namespace power_grid_model {
 
 {% for attribute_class in classes -%}
@@ -42,5 +42,5 @@ using Asym{{ attribute_class.name }} = {{ attribute_class.name }}<asymmetric_t>;
 {% endfor %}
 
 } // namespace power_grid_model
-
+{% endautoescape %}
 // clang-format on
diff --git a/code_generation/templates/power_grid_model_c/power_grid_model/include/power_grid_model/auxiliary/meta_gen/attribute_classes.hpp.jinja b/code_generation/templates/power_grid_model_c/power_grid_model/include/power_grid_model/auxiliary/meta_gen/attribute_classes.hpp.jinja
@@ -16,7 +16,7 @@
 
 #include "../{{ name }}.hpp" // NOLINT
 
-
+{% autoescape false %}
 namespace power_grid_model::meta_data {
 
 // template specialization to get list of attributes in the value field
@@ -43,5 +43,5 @@ struct get_attributes_list<{{ attribute_class.name }}> {
 
 
 } // namespace power_grid_model::meta_data
-
+{% endautoescape %}
 // clang-format on
diff --git a/code_generation/templates/power_grid_model_c/power_grid_model/include/power_grid_model/auxiliary/static_asserts/attribute_classes.hpp.jinja b/code_generation/templates/power_grid_model_c/power_grid_model/include/power_grid_model/auxiliary/static_asserts/attribute_classes.hpp.jinja
@@ -10,7 +10,7 @@
 #include "../{{ name }}.hpp" // NOLINT
 
 #include <cstddef>
-
+{% autoescape false %}
 namespace power_grid_model::test {
 
 {% for attribute_class in classes -%}
@@ -32,5 +32,5 @@ static_assert(offsetof({{ specification }}, {{ attribute.names }}) == offsetof({
 {% endfor %}
 
 } // namespace power_grid_model::test
-
+{% endautoescape %}
 // clang-format on
diff --git a/code_generation/templates/power_grid_model_c/power_grid_model_c/include/power_grid_model_c/dataset_class_maps.h.jinja b/code_generation/templates/power_grid_model_c/power_grid_model_c/include/power_grid_model_c/dataset_class_maps.h.jinja
@@ -17,7 +17,7 @@
 #define POWER_GRID_MODEL_C_DATASET_DEFINITIONS_H
 
 #include "basics.h"
-
+{% autoescape false %}
 #ifdef __cplusplus
 extern "C" {
 #endif
@@ -44,4 +44,4 @@ PGM_API extern PGM_MetaAttribute const* const PGM_def_{{ dataset }}_{{ component
 
 #endif
 // clang-format on
-
+{% endautoescape %}
diff --git a/code_generation/templates/power_grid_model_c/power_grid_model_c/src/dataset_class_maps.cpp.jinja b/code_generation/templates/power_grid_model_c/power_grid_model_c/src/dataset_class_maps.cpp.jinja
@@ -10,7 +10,7 @@
 #include "forward_declarations.hpp"
 #include "power_grid_model_c/dataset_definitions.h"
 #include "power_grid_model_c/meta_data.h"
-
+{% autoescape false %}
 {% for dataset, components in all_map.items() -%}
 // dataset {{ dataset }}
 PGM_MetaDataset const* const PGM_def_{{ dataset }} = PGM_meta_get_dataset_by_name(nullptr, "{{ dataset }}");
@@ -26,6 +26,6 @@ PGM_MetaAttribute const* const PGM_def_{{ dataset }}_{{ component }}_{{ attribut
 {% endfor -%}
 
 //
-
+{% endautoescape %}
 // clang-format on
 
diff --git a/docs/examples/Generic Branch Example.ipynb b/docs/examples/Generic Branch Example.ipynb
@@ -632,11 +632,10 @@
     ")\n",
     "\n",
     "\n",
-    "pd.set_option(\"display.max_columns\", None)\n",
-    "pd.set_option(\"display.max_rows\", None)\n",
-    "pd.set_option(\"display.expand_frame_repr\", False)\n",
-    "pd.set_option(\"display.max_columns\", None)\n",
-    "pd.set_option(\"display.max_colwidth\", None)\n",
+    "pd.options.display.max_columns = None\n",
+    "pd.options.display.max_rows = None\n",
+    "pd.options.display.expand_frame_repr = False\n",
+    "pd.options.display.max_colwidth = None\n",
     "\n",
     "\n",
     "def e3(x):\n",
diff --git a/pyproject.toml b/pyproject.toml
@@ -110,7 +110,8 @@ show-fixes = true
 # Assume Python 3.11
 target-version = "py311"
 
-extend-exclude = ["setup.py"]
+[tool.ruff.lint.pydocstyle]
+convention = "google"
 
 [tool.ruff.lint]
 select = [
@@ -145,10 +146,17 @@ select = [
     "SLF",
     "UP",
     "RSE",
-    "RUF"
+    "RUF",
+    "S",
+    "FBT003",
+    "TRY002",
+    "PT"
+]
+
+ignore = [
+    "UP038", # deprecated, https://docs.astral.sh/ruff/rules/non-pep604-isinstance/#deprecation
+    "PT019" # flags false positives
 ]
-# the rule is deprecated, https://docs.astral.sh/ruff/rules/non-pep604-isinstance/#deprecation
-ignore = ["UP038"]
 
 [tool.ruff.lint.isort]
 # Imports that are imported using keyword "as" and are from the same source - are combined.
@@ -158,11 +166,10 @@ combine-as-imports = true
 # Ignore `F811` (redefinition violations) in all examples notebooks since we use redefinition.
 "docs/examples/*.ipynb" = ["F811", "E402"]
 # Pylint was only run in src directory before moving to Ruff
-"tests/*" = ["PLR0915", "PLR0912", "PLR0913"]
+"tests/*" = ["PLR0915", "PLR0912", "PLR0913", "S"]
 # Ignore private member access: _model_ptr, _all_component_count...
 "src/power_grid_model/_core/*.py" = ["SLF001"]
 "tests/unit/test_error_handling.py" = ["SLF001"]
-"setup.py" = ["PL"]
 
 [tool.mypy]
 follow_imports = "silent"
diff --git a/src/power_grid_model/utils.py b/src/power_grid_model/utils.py
@@ -282,7 +282,7 @@ def _compatibility_deprecated_export_json_data(
         file_pointer.write(old_format_serialized_data)
 
 
-def import_input_data(json_file: Path) -> SingleDataset:
+def import_input_data(json_file: Path) -> SingleDataset:  # pragma: no cover
     """
     [deprecated] Import input json data.
 
@@ -299,8 +299,10 @@ def import_input_data(json_file: Path) -> SingleDataset:
     warnings.warn(_DEPRECATED_JSON_DESERIALIZATION_MSG, DeprecationWarning)
 
     data = _compatibility_deprecated_import_json_data(json_file=json_file, data_type=DatasetType.input)
-    assert isinstance(data, dict)
-    assert all(isinstance(component, np.ndarray) and component.ndim == 1 for component in data.values())
+    if not isinstance(data, dict):
+        raise TypeError(f"Expected data to be dict, got {type(data)}")
+    if not all(isinstance(component, np.ndarray) and component.ndim == 1 for component in data.values()):
+        raise TypeError("All components must be 1D numpy arrays")
     return cast_type(SingleDataset, data)
 
 
@@ -398,12 +400,14 @@ def self_test():
             with Path(output_file_path).open("r", encoding="utf-8") as output_file:
                 output_data = json.load(output_file)
 
-            assert output_data is not None
-            assert math.isclose(
+            if output_data is None:  # pragma: no cover
+                raise ValueError("Output data should not be None")
+            if not math.isclose(
                 output_data["data"][ComponentType.node][0]["u"],
                 input_data["data"][ComponentType.node][0]["u_rated"],
                 abs_tol=1e-9,
-            )
+            ):  # pragma: no cover
+                raise ValueError("The difference between the input and output data is too big.")
 
             print("Self test finished.")
         except Exception as e:
diff --git a/src/power_grid_model/validation/_rules.py b/src/power_grid_model/validation/_rules.py
@@ -794,8 +794,8 @@ def no_strict_subset_missing(data: SingleDataset, fields: list[str], component_t
     errors = []
     if component_type in data:
         component_data = data[component_type]
-        instances_with_nan_data = np.full_like([], False, shape=(len(component_data),), dtype=bool)
-        instances_with_non_nan_data = np.full_like([], False, shape=(len(component_data),), dtype=bool)
+        instances_with_nan_data = np.full_like([], fill_value=False, shape=(len(component_data),), dtype=bool)
+        instances_with_non_nan_data = np.full_like([], fill_value=False, shape=(len(component_data),), dtype=bool)
         for field in fields:
             nan_value = _nan_type(component_type, field)
             asym_axes = tuple(range(component_data.ndim, component_data[field].ndim))
@@ -850,7 +850,7 @@ def not_all_missing(data: SingleDataset, fields: list[str], component_type: Comp
     errors = []
     if component_type in data:
         component_data = data[component_type]
-        instances_with_all_nan_data = np.full_like([], True, shape=(len(component_data),), dtype=bool)
+        instances_with_all_nan_data = np.full_like([], fill_value=True, shape=(len(component_data),), dtype=bool)
 
         for field in fields:
             nan_value = _nan_type(component_type, field)
diff --git a/src/power_grid_model/validation/utils.py b/src/power_grid_model/validation/utils.py
@@ -81,7 +81,8 @@ def _eval_field_expression(data: np.ndarray, expression: str) -> np.ndarray:
         return data[fields[0]]
 
     max_num_fields = 2
-    assert len(fields) == max_num_fields
+    if len(fields) != max_num_fields:
+        raise ValueError(f"There should be exactly {max_num_fields} fields, got {len(fields)} fields")
     zero_div = np.logical_or(np.equal(data[fields[1]], 0.0), np.logical_not(np.isfinite(data[fields[1]])))
     if np.any(zero_div):
         result = np.full_like(data[fields[0]], np.nan)
@@ -188,9 +189,7 @@ def errors_to_string(
 
 
 def _nan_type(component: ComponentType, field: str, data_type: DatasetType = DatasetType.input):
-    """
-    Helper function to retrieve the nan value for a certain field as defined in the power_grid_meta_data.
-    """
+    """Helper function to retrieve the nan value for a certain field as defined in the power_grid_meta_data."""
     return power_grid_meta_data[data_type][component].nans[field]
 
 
@@ -264,7 +263,7 @@ def _set_default_value(
 
 def _get_valid_ids(data: SingleDataset, ref_components: ComponentType | list[ComponentType]) -> list[int]:
     """
-    This function returns the valid IDs specified by all ref_components
+    This function returns the valid IDs specified by all ref_components.
 
     Args:
         data: The input/update data set for all components
diff --git a/tests/unit/deprecated/test_end_to_end.py b/tests/unit/deprecated/test_end_to_end.py
@@ -12,7 +12,7 @@
 from tests.unit.utils import compare_result
 
 
-@pytest.fixture()
+@pytest.fixture
 def deprecated_format_test_case():
     return Path(__file__).parent / "data/dummy-test-batch-dependent-not-cacheable"
 
diff --git a/tests/unit/test_0Z_model_validation.py b/tests/unit/test_0Z_model_validation.py
@@ -110,7 +110,7 @@ def __exit__(self, exc_type, exc_value, traceback):
 
 
 @pytest.mark.parametrize(
-    ["case_id", "case_path", "sym", "calculation_type", "calculation_method", "rtol", "atol", "params"],
+    ("case_id", "case_path", "sym", "calculation_type", "calculation_method", "rtol", "atol", "params"),
     pytest_cases(get_batch_cases=False),
 )
 def test_single_validation(
@@ -163,7 +163,7 @@ def test_single_validation(
 
 
 @pytest.mark.parametrize(
-    ["case_id", "case_path", "sym", "calculation_type", "calculation_method", "rtol", "atol", "params"],
+    ("case_id", "case_path", "sym", "calculation_type", "calculation_method", "rtol", "atol", "params"),
     pytest_cases(get_batch_cases=True),
 )
 def test_batch_validation(
diff --git a/tests/unit/test_buffer_handling.py b/tests/unit/test_buffer_handling.py
@@ -40,7 +40,7 @@ def load_data(component_type, is_batch, is_sparse, is_columnar):
 
 
 @pytest.mark.parametrize(
-    "component_type, is_batch, is_columnar",
+    ("component_type", "is_batch", "is_columnar"),
     [
         pytest.param(ComponentType.sym_load, True, True, id="sym_load-batch-columnar"),
         pytest.param(ComponentType.sym_load, True, False, id="sym_load-batch-row_based"),
@@ -70,7 +70,7 @@ def test__get_dense_buffer_properties(component_type, is_batch, is_columnar):
 
 
 @pytest.mark.parametrize(
-    "component_type, is_columnar",
+    ("component_type", "is_columnar"),
     [
         pytest.param(ComponentType.sym_load, True, id="sym_load-columnar"),
         pytest.param(ComponentType.sym_load, False, id="sym_load-row_based"),
@@ -96,7 +96,7 @@ def test__get_sparse_buffer_properties(component_type, is_columnar):
 
 
 @pytest.mark.parametrize(
-    "component, is_batch, is_columnar, is_sparse",
+    ("component", "is_batch", "is_columnar", "is_sparse"),
     [
         pytest.param(ComponentType.sym_load, True, True, False, id="sym_load-columnar"),
         pytest.param(ComponentType.asym_load, True, True, False, id="asym_load-columnar"),
@@ -127,7 +127,7 @@ def test__get_raw_attribute_data_view(component, is_batch, is_columnar, is_spars
 
 
 @pytest.mark.parametrize(
-    "component, attribute",
+    ("component", "attribute"),
     [
         pytest.param(ComponentType.asym_load, "p_specified", id="asym_load-shape_missmatch"),
     ],
@@ -160,7 +160,7 @@ def test__get_raw_attribute_data_view_fail(component, attribute):
 
 
 @pytest.mark.parametrize(
-    "component, is_batch, is_columnar, is_sparse",
+    ("component", "is_batch", "is_columnar", "is_sparse"),
     [
         pytest.param(ComponentType.sym_load, True, True, False, id="sym_load"),
         pytest.param(ComponentType.asym_load, True, True, False, id="asym_load-columnar"),
@@ -183,7 +183,7 @@ def test__get_raw_attribute_data_view_direct(component, is_batch, is_columnar, i
 
 
 @pytest.mark.parametrize(
-    "component, attr_data_shape, attribute",
+    ("component", "attr_data_shape", "attribute"),
     [
         pytest.param(ComponentType.asym_load, (2, 4, 3), "p_specified", id="asym_load-columnar"),
         pytest.param(ComponentType.asym_load, (1, 4, 3), "p_specified", id="asym_load-columnar"),
@@ -219,7 +219,7 @@ def test__get_raw_attribute_data_view_directly(component, attr_data_shape, attri
 
 
 @pytest.mark.parametrize(
-    "component, attr_data_shape, attribute",
+    ("component", "attr_data_shape", "attribute"),
     [
         pytest.param(ComponentType.asym_load, (2, 4, 4), "p_specified", id="asym_load-columnar"),
         pytest.param(ComponentType.asym_load, (2, 6, 4), "p_specified", id="asym_load-columnar"),
diff --git a/tests/unit/test_data_handling.py b/tests/unit/test_data_handling.py
@@ -168,5 +168,5 @@ def test_dtype_compatibility_check_compatible():
 def test_dtype_compatibility_check__error():
     nodes = initialize_array(DT.sym_output, CT.node, (1, 2))
     data = {CT.node: nodes.astype(nodes.dtype.newbyteorder("S"))}
-    with pytest.raises(ValueError):
+    with pytest.raises(ValueError, match="Data type does not match schema."):
         CMutableDataset(data, DT.sym_output)
diff --git a/tests/unit/test_dataset.py b/tests/unit/test_dataset.py
@@ -48,7 +48,7 @@ def test_const_dataset__empty_dataset(dataset_type):
     assert info.elements_per_scenario() == {}
     assert info.total_elements() == {}
 
-    with pytest.raises(ValueError):
+    with pytest.raises(ValueError, match="The dataset type could not be deduced."):
         CConstDataset(data={})
 
 
@@ -85,7 +85,7 @@ def test_const_dataset__single_data(dataset_type):
     assert info.total_elements() == components
 
 
-@pytest.mark.parametrize("batch_size", (0, 1, 3))
+@pytest.mark.parametrize("batch_size", [0, 1, 3])
 def test_const_dataset__uniform_batch_data(dataset_type, batch_size):
     components = {ComponentType.node: 3, ComponentType.sym_load: 2, ComponentType.asym_load: 4}
     data = {
@@ -157,11 +157,11 @@ def test_const_dataset__mixed_batch_size(dataset_type):
         ComponentType.node: np.zeros(shape=(2, 3), dtype=power_grid_meta_data[dataset_type][ComponentType.node]),
         ComponentType.line: np.zeros(shape=(3, 3), dtype=power_grid_meta_data[dataset_type][ComponentType.line]),
     }
-    with pytest.raises(ValueError):
+    with pytest.raises(ValueError, match="Provided 'batch size' is incorrect for the provided data."):
         CConstDataset(data, dataset_type)
 
 
-@pytest.mark.parametrize("bad_indptr", (np.ndarray([0, 1]), np.ndarray([0, 3, 2]), np.ndarray([0, 1, 2, 3, 4])))
+@pytest.mark.parametrize("bad_indptr", [np.ndarray([0, 1]), np.ndarray([0, 3, 2]), np.ndarray([0, 1, 2, 3, 4])])
 def test_const_dataset__bad_sparse_data(dataset_type, bad_indptr):
     data = {
         ComponentType.node: {
@@ -193,5 +193,5 @@ def test_const_dataset__different_dtype(dataset_type, dtype, supported):
         result = CConstDataset(data, dataset_type)
         assert result.get_info().total_elements() == {ComponentType.node: 3}
     else:
-        with pytest.raises(ValueError):
+        with pytest.raises(ValueError, match="Data type does not match schema."):
             CConstDataset(data, dataset_type)
diff --git a/tests/unit/test_internal_utils.py b/tests/unit/test_internal_utils.py
@@ -789,7 +789,7 @@ def test_get_dataset_type(dataset_type):
 
 
 def test_get_dataset_type__empty_data():
-    with pytest.raises(ValueError):
+    with pytest.raises(ValueError, match="At least one component should have row based data."):
         get_dataset_type(data={})
 
 
diff --git a/tests/unit/test_serialization.py b/tests/unit/test_serialization.py
diff --git a/tests/unit/test_utils.py b/tests/unit/test_utils.py
diff --git a/tests/unit/utils.py b/tests/unit/utils.py
diff --git a/tests/unit/validation/test_rules.py b/tests/unit/validation/test_rules.py
diff --git a/tests/unit/validation/test_utils.py b/tests/unit/validation/test_utils.py
diff --git a/tests/unit/validation/test_validation_functions.py b/tests/unit/validation/test_validation_functions.py
