chore(ci): switch from flake8 to ruff

Switch from using [flake8](https://pypi.org/project/flake8) to [ruff](https://pypi.org/project/ruff) as the primary linter for the project. Ruff is orders of magnitude faster than alternative tools while integrating more functionality behind a single, common interface. This should help speed up linting for the project considerably and allow for much more sophisticated linting options and configurations. As a consequence of that, the following changes are included as part of this migration: - Removal of flake8 from the project’s dependencies and pre-commit hooks. - Activation of additional linting rules supported by `ruff` and the accompanying changes on the source code to conform to these rules. - Upgrading of existing dependencies. - Removal of `tox.ini`. Tox configuration is now included in the `pyproject.toml` file. All the project configuration is now housed in one file. This is in line with [PEP 621](https://peps.python.org/pep-0621) guidelines. - Minor fixes and improvements.
savannahghi · Apr 12, 2023 · 6b407dd · 6b407dd
1 parent 0a8a200
commit 6b407dd
Show file tree

Hide file tree

Showing 57 changed files with 890 additions and 586 deletions.
diff --git a/.gitignore b/.gitignore
@@ -291,6 +291,9 @@ GitHub.sublime-settings
 # Session
 Session.vim
 
+# Ruff cache
+.ruff_cache
+
 # Temporary
 .netrwhist
 .~lock.*

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -9,6 +9,12 @@ repos:
       - id: check-yaml
       - id: check-added-large-files
 
+  - repo: https://github.com/charliermarsh/ruff-pre-commit
+    rev: "v0.0.261"
+    hooks:
+      - id: ruff
+        args: [ --fix, --exit-non-zero-on-fix ]
+
   - repo: https://github.com/psf/black
     rev: 23.3.0
     hooks:
@@ -24,14 +30,7 @@ repos:
     rev: v3.3.1
     hooks:
       - id: pyupgrade
-        args: [--py310-plus]
-
-  - repo: https://github.com/pycqa/flake8
-    rev: 6.0.0
-    hooks:
-      - id: flake8
-        args: ["--config=tox.ini"]
-        additional_dependencies: [flake8-isort]
+        args: ["--py310-plus"]
 
 # sets up .pre-commit-ci.yaml to ensure pre-commit dependencies stay up to date
 ci:

diff --git a/app/__init__.py b/app/__init__.py
@@ -3,7 +3,6 @@
 from typing import Any, Final, cast
 
 import yaml
-from yaml import Loader
 
 from app.core import DataSourceType
 from app.lib import (
@@ -28,7 +27,7 @@
 
 _SUPPORTED_DATA_SOURCE_TYPES_CONFIG_KEY: Final[
     str
-] = "SUPPORTED_DATA_SOURCE_TYPES"  # noqa
+] = "SUPPORTED_DATA_SOURCE_TYPES"
 
 _DEFAULT_CONFIG: Final[dict[str, Any]] = {
     _LOGGING_CONFIG_KEY: {
@@ -39,15 +38,15 @@
                 "format": (
                     "%(levelname)s: %(asctime)s %(module)s "
                     "%(process)d %(thread)d %(message)s"
-                )
-            }
+                ),
+            },
         },
         "handlers": {
             "console": {
                 "level": "DEBUG",
                 "class": "logging.StreamHandler",
                 "formatter": "verbose",
-            }
+            },
         },
         "root": {"level": "INFO", "handlers": ["console"]},
     },
@@ -86,32 +85,33 @@ def _load_config_file(
     # TODO: Ensure that a valid config file path was given and if not raise an
     #  appropriate Exception.
     with open(config_file_path, "rb") as config_file:
-        return yaml.load(config_file, Loader=Loader)
+        return yaml.safe_load(config_file)
 
 
 def _load_settings_initializers(
     initializers_dotted_paths: Sequence[str],
 ) -> Sequence[SettingInitializer]:
-    initializers: list[SettingInitializer] = list()
+    initializers: list[SettingInitializer] = []
     for _initializer_dotted_path in initializers_dotted_paths:
         try:
             initializer_klass: type[SettingInitializer]
             initializer_klass = import_string_as_klass(
-                _initializer_dotted_path, SettingInitializer
+                _initializer_dotted_path,
+                SettingInitializer,
             )
             initializers.append(initializer_klass())  # type: ignore
         except ImportError as exp:
             raise ImproperlyConfiguredError(
                 message='"%s" does not seem to be a valid path.'
-                % _initializer_dotted_path
+                % _initializer_dotted_path,
             ) from exp
         except TypeError as exp:
             raise ImproperlyConfiguredError(
                 message=(
                     'Invalid value, "%s" is either not class or is not a '
                     'subclass of "app.lib.SettingInitializer".'
                     % _initializer_dotted_path
-                )
+                ),
             ) from exp
 
     return initializers
@@ -127,7 +127,7 @@ class _DefaultTransportFactoryInitializer(SettingInitializer):
     def setting(self) -> str:
         return _DEFAULT_TRANSPORT_FACTORY_CONFIG_KEY
 
-    def execute(self, an_input: str | None) -> Any:
+    def execute(self, an_input: str | None) -> str | None:
         # If the default transport setting has not been provided or is empty,
         # do nothing.
         if not an_input:
@@ -136,20 +136,21 @@ def execute(self, an_input: str | None) -> Any:
         if type(an_input) is not str:
             raise ImproperlyConfiguredError(
                 message='The value of the "%s" setting must be a string'
-                % _DEFAULT_TRANSPORT_FACTORY_CONFIG_KEY
+                % _DEFAULT_TRANSPORT_FACTORY_CONFIG_KEY,
             )
 
         default_transport_factory: DefaultTransportFactory
         try:
             default_transport_factory = cast(
-                DefaultTransportFactory, import_string(an_input)
+                DefaultTransportFactory,
+                import_string(an_input),
             )
             global registry
             registry.default_transport_factory = default_transport_factory
         except (ImportError, TypeError) as exp:
             raise ImproperlyConfiguredError(
                 message="Unable to import the default transport factory at "
-                '"%s". Ensure a valid path was given.' % an_input
+                '"%s". Ensure a valid path was given.' % an_input,
             ) from exp
 
         return an_input
@@ -162,9 +163,9 @@ class _LoggingInitializer(SettingInitializer):
     def setting(self) -> str:
         return _LOGGING_CONFIG_KEY
 
-    def execute(self, an_input: Mapping[str, Any] | None) -> Any:
+    def execute(self, an_input: Mapping[str, Any] | None) -> Mapping[str, Any]:
         logging_config: dict[str, Any] = dict(
-            an_input or _DEFAULT_CONFIG[self.setting]
+            an_input or _DEFAULT_CONFIG[self.setting],
         )
         dictConfig(logging_config)
         return logging_config
@@ -180,17 +181,17 @@ class _SupportedDataSourceTypesInitializer(SettingInitializer):
     def setting(self) -> str:
         return _SUPPORTED_DATA_SOURCE_TYPES_CONFIG_KEY
 
-    def execute(self, an_input: Sequence[str] | None) -> Any:
+    def execute(self, an_input: Sequence[str] | None) -> Sequence[str]:
         supported_dst: Sequence[str] = (
             an_input or _DEFAULT_CONFIG[self.setting]
         )
         global registry
-        _dst: DataSourceType  # noqa: F842
+        _dst: DataSourceType
         registry.data_source_types = {
             _dst.code: _dst
-            for _dst in map(
-                lambda _s: self._dotted_path_to_data_source_type_klass(_s)(),
-                supported_dst,
+            for _dst in (
+                self._dotted_path_to_data_source_type_klass(_s)()
+                for _s in supported_dst
             )
         }
         return supported_dst
@@ -202,19 +203,20 @@ def _dotted_path_to_data_source_type_klass(
         try:
             data_source_type_klass: type[DataSourceType]
             data_source_type_klass = import_string_as_klass(
-                dotted_path, DataSourceType
+                dotted_path,
+                DataSourceType,
             )
             return data_source_type_klass
         except ImportError as exp:
             raise ImproperlyConfiguredError(
-                message='"%s" does not seem to be a valid path.' % dotted_path
+                message='"%s" does not seem to be a valid path.' % dotted_path,
             ) from exp
         except TypeError as exp:
             raise ImproperlyConfiguredError(
                 message=(
                     'Invalid value, "%s" is either not class or is not a '
                     'subclass of "app.core.DataSourceType".' % dotted_path
-                )
+                ),
             ) from exp
 
 
@@ -252,14 +254,15 @@ def setup(
     _initializers: list[Any] = list(settings_initializers or [])
     _initializers.extend(
         _load_settings_initializers(
-            _settings_dict.get(_SETTINGS_INITIALIZERS_CONFIG_KEY, tuple())
-        )
+            _settings_dict.get(_SETTINGS_INITIALIZERS_CONFIG_KEY, ()),
+        ),
     )
     _initializers.insert(0, _LoggingInitializer())
     _initializers.insert(1, _SupportedDataSourceTypesInitializer())
     _initializers.insert(2, _DefaultTransportFactoryInitializer())
 
     global settings
     settings = Config(  # type: ignore
-        settings=_settings_dict, settings_initializers=_initializers
+        settings=_settings_dict,
+        settings_initializers=_initializers,
     )
diff --git a/app/__main__.py b/app/__main__.py
@@ -68,7 +68,9 @@ def argparse_factory(prog_name: str = __title__) -> ArgumentParser:
         ),
     )
     parser.add_argument(
-        "--version", action="version", version="%(prog)s " + __version__
+        "--version",
+        action="version",
+        version="%(prog)s " + __version__,
     )
 
     return parser
@@ -94,9 +96,9 @@ def main_pipeline_factory(
     _transport: Transport
     _transport = (
         transport
-        or app.registry.get_default_transport_factory_or_raise(  # noqa
+        or app.registry.get_default_transport_factory_or_raise(
             error_message="The default transport factory is required by the "
-            "main application pipeline."
+            "main application pipeline.",
         )()
     )
     return Pipeline(
@@ -125,10 +127,11 @@ def main() -> None:  # pragma: no cover
     transport_factory = app.registry.get_default_transport_factory_or_raise()
     with transport_factory() as transport:
         main_pipeline: Pipeline[
-            Sequence[DataSourceType], Sequence[UploadExtractResult]
+            Sequence[DataSourceType],
+            Sequence[UploadExtractResult],
         ] = main_pipeline_factory(transport=transport)
         main_pipeline.execute(tuple(app.registry.data_source_types.values()))
-    print("Done ...")
+    print("Done ...")  # noqa: T201
 
 
 if __name__ == "__main__":  # pragma: no cover