ideas for improvements

.gitignore

@@ -24,9 +24,6 @@ build/
 # Jupyter Notebooks
 .ipynb_checkpoints/
 
-# VS Code
-.vscode/
-
 # PyCharm
 .idea/
 

.vscode/extensions.json

@@ -0,0 +1,6 @@
+{
+  "recommendations": [
+    "ms-python.python",
+    "charliermarsh.ruff",
+  ]
+}

.vscode/settings.json

@@ -0,0 +1,14 @@
+{
+  "python.analysis.typeCheckingMode": "standard",
+  "flake8.enabled": false,
+  "ruff.enable": true,
+  "ruff.lint.enable": true,
+  "[python]": {
+    "editor.formatOnSave": true,
+    "editor.defaultFormatter": "charliermarsh.ruff",
+    "editor.codeActionsOnSave": {
+      "source.fixAll": "explicit",
+      "source.organizeImports": "explicit"
+    }
+  },
+}

pyproject.toml

@@ -32,6 +32,7 @@ tpcds_datagen = ["duckdb==1.3.1", "pyarrow>=15.0.0"]
 tpch_datagen = ["duckdb==1.3.1", "pyarrow>=15.0.0"]
 sparkmeasure = ["sparkmeasure==0.24.0"]
 sail = ["pysail==0.3.3", "pyspark[connect]==4.0.0", "deltalake>=1.0.2", "pyarrow>=15.0.0"]
+dev = ["ruff>=0.12.9"]
 
 [project.urls]
 github = "https://github.com/mwc360/LakeBench"
@@ -47,3 +48,40 @@ include-package-data = true
 
 [tool.setuptools.packages.find]
 where = ["src"]
+
+[tool.ruff]
+line-length = 120
+indent-width = 4
+extend-include = ["*.ipynb"]
+extend-exclude = ["build", "dist", ".venv", ".github", ".vscode"]
+
+[tool.ruff.format]
+quote-style = "double"
+indent-style = "space"
+skip-magic-trailing-comma = false
+
+[tool.ruff.lint]
+select = ["ALL"]
+ignore = [  # https://docs.astral.sh/ruff/rules/
+    "COM812", # Trailing comma missing
+    "D100",   # Missing docstring in public module
+    "D200",   # One-line docstring should fit on one line
+    "D203",   # 1 blank line required before class docstring
+    "D212",   #	Multi-line docstring summary should start at the first line
+    "EM101",  # Exception must not use a string literal, assign to variable first
+    "EM102",  # Exception must not use an f-string literal, assign to variable first
+    "FBT001", # Boolean-typed positional argument in function definition
+    "FBT002", # Boolean default positional argument in function definition
+    "Q003",   # Change outer quotes to avoid escaping inner quotes
+    "SLF001", # Private member accessed: {access}
+    "TRY003", # Avoid specifying long messages outside the exception class
+]
+unfixable = [
+    "C405",   # Unnecessary list literal (rewrite as a set literal)
+    "D400",   # First line should end with a period
+    "D415",   # First line should end with a period, question mark, or exclamation point
+    "PT027",  # Use `pytest.raises` instead of unittest-style `assertRaises`
+    "RET504", # Unnecessary assignment to `query` before `return` statement
+    "SIM118", # Use `key in dict` instead of `key in dict.keys()` - VERY DANGEROUS!
+    "T201",   # `print` found
+]

src/lakebench/engines/duckdb.py

@@ -22,7 +22,19 @@ def __init__(
             cost_per_vcore_hour: Optional[float] = None,
             ):
         """
-        Initialize the DuckDB Engine Configs
+        Initialize the DuckDB Engine Configs.
+
+        Parameters
+        ----------
+        delta_abfss_schema_path : str
+            TODO: what does it do?
+            Benchmark input data are converted from parque files to delta tables.
+            This path is the destination where those delta tables are saved to during benchmark execution.
+        cost_per_vcore_hour : Optional[float]
+            TODO: what does it mean; what is it good for?
+            In order to compare costs of benchmark execution of different engines, this parameter allows specifying the cost per vCore-hour.
+            Benchmark result table contains the cost per query.
+
         """
         super().__init__()
         import duckdb
@@ -32,7 +44,7 @@ def __init__(
         self.catalog_name = None
         self.schema_name = None
         if self.delta_abfss_schema_path.startswith("abfss://"):
-            if self.is_fabric:
+            if self.is_fabric:  # this could be moved to BaseEngine
                 os.environ["AZURE_STORAGE_TOKEN"] = (
                     self.notebookutils.credentials.getToken("storage")
                 )