Flake8/Black => Ruff

.github/workflows/code-style-checks.yaml

@@ -29,8 +29,7 @@ jobs:
 #      - name: Run mypy
 #        run: mypy ./
 
-      - name: Run Flake8
-        run: flake8
-
-      - name: Run Black
-        run: black --check --diff .
+      # changed-python-files could be an empty string, which would cause `ruff check` to be run against the entire project.
+      - name: Run Ruff Linter
+        if: steps.changed-python-files.outputs.all_changed_files != ''
+        run: ruff check ${{ steps.changed-python-files.outputs.all_changed_files }}

brus_backend_common/helpers/uri.py

@@ -13,9 +13,7 @@
     Internet RFC on Relative Uniform Resource Locators
     Format: scheme://netloc/path;parameters?query#fragment
     List of supported schemes: {}
-    """.format(
-    supported_schemes
-)
+    """.format(supported_schemes)
 
 
 def parse_http_url(http_url: str) -> Tuple[Any, Any | None, Any]:

brus_backend_common/lookups.py

@@ -23,7 +23,7 @@
     LookupType("04", "project grant (B)"),
     LookupType("05", "cooperative agreement (B)"),
     LookupType(
-        "06", "direct payment for specified use, as a subsidy or other non-reimbursable direct financial aid " "(C)"
+        "06", "direct payment for specified use, as a subsidy or other non-reimbursable direct financial aid (C)"
     ),
     LookupType("07", "direct loan (E)"),
     LookupType("08", "guaranteed/insured loan (F)"),

brus_backend_common/models/lakehouse_model.py

@@ -464,7 +464,9 @@ def safe_literal_eval(val: Any) -> Any:
         }
         params.update(kwargs)
 
-        return pd.read_csv(io.BytesIO(self._s3_object), **params)[list(self.STRUCTURE.columns)] if self.exists() else None  # type: ignore
+        return (
+            pd.read_csv(io.BytesIO(self._s3_object), **params)[list(self.STRUCTURE.columns)] if self.exists() else None
+        )  # type: ignore
 
     def to_polars_df(self, **kwargs: Any) -> pl.DataFrame | pl.Series | None:
         return pl.read_csv(self.CSV_PATH, **kwargs) if self.exists() else None

brus_backend_common/models/migrations/add_test_column.py

@@ -1,5 +1,6 @@
 from brus_backend_common.models.lakehouse_model import DeltaModel
 
+
 def migrate(model: DeltaModel):
     if model.spark:
         sql_string = f"""
@@ -8,6 +9,7 @@ def migrate(model: DeltaModel):
         """
         model.spark.sql(sql_string)
 
+
 def reverse_migrate(model: DeltaModel):
     if model.spark:
         sql_string = f"""

brus_backend_common/models/migrations/drop_test_column.py

@@ -1,5 +1,6 @@
 from brus_backend_common.models.lakehouse_model import DeltaModel
 
+
 def migrate(model: DeltaModel):
     if model.spark:
         sql_string = f"""
@@ -16,6 +17,7 @@ def migrate(model: DeltaModel):
         """
         model.spark.sql(sql_string)
 
+
 def reverse_migrate(model: DeltaModel):
     if model.spark:
         sql_string = f"""

brus_backend_common/scripts/loaders/defc_gold.py

@@ -261,7 +261,6 @@ def main(local_file: str | None = None, force_reload: bool = False, metrics_json
         clean_df, gold_model.to_pandas_df(), ["defc_id"], ["code"], date_format="%Y-%m-%d"
     )
     if force_reload or diff_found:
-
         # The only diff should be whenever a new code is added. Noting it here
         if diff_found:
             incoming_defcs = list(clean_df["code"])

brus_backend_common/tests/integration/test_spark_app.py

@@ -101,7 +101,7 @@ def test_spark_write_csv_app_run(spark: SparkSession, s3_unittest_data_bucket):
 
     df = spark.createDataFrame([Row(**data_row) for data_row in data])
     # NOTE! NOTE! NOTE! MinIO locally does not support a TRAILING SLASH after object (folder) name
-    df.write.option("header", True).csv(f"s3a://{s3_unittest_data_bucket}" f"/write_to_s3")
+    df.write.option("header", True).csv(f"s3a://{s3_unittest_data_bucket}/write_to_s3")
 
     # Verify there are *.csv part files in the chosen bucket
     s3_client = _get_boto3("client", "s3")

pyproject.toml

@@ -76,15 +76,13 @@ dependencies = [
 
 [project.optional-dependencies]
 dev = [
-    "black==25.1.0",
     "docker==7.0.0",
-    "Flake8-pyproject==1.2.4",
-    "flake8==7.0.0",
     "pytest==8.2.0",
     "pytest-cov==4.1.0",
     "pytest-pretty==1.3.0",
     "pytest-xdist==3.7.0",
     "requests-mock==1.12.1",
+    "ruff==0.14.14",
 ]
 spark = [
     "delta-spark==2.4.0",
@@ -94,10 +92,25 @@ awscli = [
     "awscli==1.32.58",
 ]
 
-[tool.black]
+[tool.ruff]
 line-length = 120
-target-version = ['py312']
-exclude = '/(\.git|\.venv|venv|migrations)/'
+target-version = 'py312'
+
+[tool.ruff.format]
+line-ending = "lf"
+
+[tool.ruff.lint]
+preview = true  # enable new rules
+select = ['C','E','F','W','B']
+ignore = ['E203','E501','F541','W605']
+exclude = [
+    '.git',
+    '.venv',
+    'venv',
+    '**/migrations/**',
+    'build',
+    'brus-backend-common.egg-info'
+]
 
 
 [tool.coverage.run]
@@ -140,16 +153,3 @@ markers = [
 pythonpath = [
   "."
 ]
-
-[tool.flake8]
-select = ['C','E','F','W','B','B950']
-ignore = ['E501','W503','E203','F541','E704']
-extend-ignore = ['W605','W503','E203']
-exclude = [
-    '.venv',
-    'venv',
-    'build',
-    'brus_backend_common.egg-info',
-    'brus_backend_common/*/migrations/*'
-]
-max-line-length = 120