feature/configure ruff for faster linting

.gitignore

@@ -97,6 +97,9 @@ venv.bak/
 .dmypy.json
 dmypy.json
 
+# ruff
+.ruff_cache
+
 # PyCharm
 .idea/
 .idea_modules/

.pre-commit-config.yaml

@@ -2,45 +2,28 @@ fail_fast: false
 default_language_version:
   python: python3.11
 repos:
-  - repo: https://github.com/pycqa/isort
-    rev: 5.12.0
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.0.292
     hooks:
-      - id: isort
-  - repo: https://github.com/myint/autoflake
-    rev: v2.2.1
-    hooks:
-      - id: autoflake
-        args: [--in-place, --remove-all-unused-imports]
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix]
   - repo: https://github.com/psf/black
-    rev: 23.7.0
+    rev: 23.9.1
     hooks:
       - id: black
-  - repo: https://github.com/PyCQA/bandit
-    rev: 1.7.5
-    hooks:
-      - id: bandit
-        args: [--silent, --ini=.bandit]
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.4.0
+    rev: v4.5.0
     hooks:
       - id: pretty-format-json
+        name: json
         args: [--autofix]
-      - id: end-of-file-fixer
-      - id: debug-statements
-        exclude: "cli\\.py$"
-  - repo: https://github.com/PyCQA/pydocstyle
-    rev: 6.3.0
-    hooks:
-      - id: pydocstyle
-        pass_filenames: true
-        additional_dependencies: [".[toml]"]
-        exclude: "test_"
   - repo: https://github.com/python-poetry/poetry
-    rev: 1.6.1
+    rev: 1.6.0
     hooks:
       - id: poetry-check
+        name: poetry
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.5.1
+    rev: v1.6.0
     hooks:
       - id: mypy
         name: mypy
@@ -50,6 +33,6 @@ repos:
           - "click>=8.1.7,<9"
           - "pydantic[dotenv,email]>=1.10.12,<2"
           - "pytest>=7.4.2,<8"
-          - "types-pytz>=2023.3.0.1,<2024"
-          - "types-requests>=2.31.0.2,<3"
+          - "types-pytz>=2023.3.1.1,<2024"
+          - "types-requests>=2.31.0.8,<3"
           - "types-setuptools>=68.2.0.0,<69"

mex/common/cli.py

@@ -1,5 +1,5 @@
 import json
-import pdb
+import pdb  # noqa: T100
 import sys
 from bdb import BdbQuit
 from enum import Enum
@@ -76,7 +76,7 @@ def field_to_option(field: ModelField) -> Option:
     return Option(
         field_to_parameters(field),
         default=default,
-        envvar=list(field.field_info.extra["env_names"])[0].upper(),
+        envvar=next(iter(field.field_info.extra["env_names"])).upper(),
         help=field.field_info.description,
         is_flag=field.type_ is bool and field.default is False,
         show_default=True,

mex/common/connector/http.py

@@ -60,6 +60,7 @@ def request(
             method: HTTP method to use
             endpoint: Path to API endpoint to be prefixed with host and version
             payload: Data to be serialized as JSON using the `MExEncoder`
+            params: Dictionary to be sent in the query string of the request
             kwargs: Further keyword arguments passed to `requests`
 
         Raises:

mex/common/extract.py

@@ -44,7 +44,7 @@ def parse_csv(
     Args:
         path_or_buffer: Location of CSV file or read buffer with CSV content
         into: Type of model to parse
-        chunkssize: Buffer size for chunked reading
+        chunksize: Buffer size for chunked reading
         kwargs: Additional keywords arguments for pandas
 
     Returns:

mex/common/ldap/connector.py

@@ -89,7 +89,7 @@ def _paged_ldap_search(
         return list(entries)
 
     def get_functional_accounts(
-        self, mail: str = "*", sAMAccountName: str = "*", **filters: str
+        self, mail: str = "*", sAMAccountName: str = "*", **filters: str  # noqa: N803
     ) -> Generator[LDAPActor, None, None]:
         """Get LDAP functional accounts that match provided filters.
 
@@ -145,7 +145,7 @@ def get_persons(
         )
 
     def get_units(
-        self, sAMAccountName: str = "*", mail: str = "*", **filters: str
+        self, sAMAccountName: str = "*", mail: str = "*", **filters: str  # noqa: N803
     ) -> Generator[LDAPUnit, None, None]:
         """Get LDAP units that match the provided filters.
 
@@ -166,7 +166,7 @@ def get_units(
         )
 
     def get_functional_account(
-        self, objectGUID: str = "*", **filters: str
+        self, objectGUID: str = "*", **filters: str  # noqa: N803
     ) -> LDAPActor:
         """Get a single LDAP functional account for the given filters.
 
@@ -188,16 +188,18 @@ def get_functional_account(
         )
         if not functional_accounts:
             raise EmptySearchResultError(
-                f"Cannot find AD functional account for filters 'objectGUID: {objectGUID}, {filters}'"
+                "Cannot find AD functional account for filters "
+                f"'objectGUID: {objectGUID}, {filters}'"
             )
         if len(functional_accounts) > 1:
             raise FoundMoreThanOneError(
-                f"Found multiple AD functional accounts for filters 'objectGUID: {objectGUID}, {filters}'"
+                "Found multiple AD functional accounts for filters "
+                f"'objectGUID: {objectGUID}, {filters}'"
             )
         return functional_accounts[0]
 
     def get_person(
-        self, objectGUID: str = "*", employeeID: str = "*", **filters: str
+        self, objectGUID: str = "*", employeeID: str = "*", **filters: str  # noqa: N803
     ) -> LDAPPerson:
         """Get a single LDAP person for the given filters.
 

mex/common/models/base.py

@@ -40,7 +40,7 @@ def transform(value: Any) -> str:
 
         try:
             value = super().__getitem__(key)
-        except:
+        except:  # noqa: E722
             value = None
         return transform(value)
 
@@ -145,7 +145,7 @@ def fix_listyness(cls, values: ModelValuesT) -> ModelValuesT:
 
     def checksum(self) -> str:
         """Calculate md5 checksum for this model."""
-        return hashlib.md5(pickle.dumps(self)).hexdigest()  # nosec
+        return hashlib.md5(pickle.dumps(self)).hexdigest()  # noqa: S324
 
     def __str__(self) -> str:
         """Format this model as a string for logging."""

mex/common/organigram/transform.py

@@ -40,7 +40,7 @@ def transform_organigram_units_to_organizational_units(
 
     for extracted_unit in extracted_unit_by_id_in_primary_source.values():
         identifier_in_primary_source = extracted_unit.identifierInPrimarySource
-        if parent_identifier_in_primary_source := parent_id_in_primary_source_by_id_in_primary_source.get(
+        if parent_identifier_in_primary_source := parent_id_in_primary_source_by_id_in_primary_source.get(  # noqa: E501
             identifier_in_primary_source
         ):
             if parent_unit := extracted_unit_by_id_in_primary_source.get(

mex/common/public_api/connector.py

@@ -97,7 +97,7 @@ def echo_job_logs(self, job_id: str) -> None:
     def wait_for_job(self, job_id: str) -> str:
         """Poll the status for this `job_id` until it is no longer 'RUNNING'."""
         response = self.request("GET", f"jobs/{job_id}")
-        return response.get("status", "NONE")
+        return str(response.get("status", "NONE"))
 
     def get_job_items(self, job_id: str) -> Generator[Identifier, None, None]:
         """Get the identifiers of the items created, updated or deleted during a job.
@@ -217,8 +217,7 @@ def get_item(self, identifier: Identifier | UUID) -> PublicApiItem | None:
             ) or error.response.status_code == 404:
                 return None
             # Re-raise any unexpected errors
-            else:
-                raise error
+            raise error
         else:
             return PublicApiItem.parse_obj(response)
 

mex/common/public_api/models.py

@@ -71,7 +71,7 @@ class PublicApiItem(PublicApiBaseModel):
     values: list[PublicApiField] = Field(..., include=True)
 
     @property
-    def stableTargetId(self) -> Identifier:
+    def stableTargetId(self) -> Identifier:  # noqa: N802
         """Return the stableTargetId of this item."""
         return Identifier(self.businessId.removesuffix("#"))
 
@@ -100,7 +100,7 @@ class PublicApiItemWithoutValues(PublicApiBaseModel):
     businessId: str
 
     @property
-    def stableTargetId(self) -> Identifier:
+    def stableTargetId(self) -> Identifier:  # noqa: N802
         """Return the stableTargetId of this item."""
         return Identifier(self.businessId.removesuffix("#"))
 

mex/common/settings.py

@@ -4,9 +4,8 @@
 from pathlib import Path
 from typing import Any, Optional, TypeVar, Union
 
-from pydantic import AnyUrl
+from pydantic import AnyUrl, Extra, Field, SecretStr
 from pydantic import BaseSettings as PydanticBaseSettings
-from pydantic import Extra, Field, SecretStr
 from pydantic.env_settings import DotenvType, env_file_sentinel
 from pydantic.typing import StrPath
 
@@ -191,8 +190,8 @@ def text(self) -> str:
         return "\n".join(
             [
                 f"{key.ljust(indent)} "
-                f"{', '.join(str(v) for v in value) if isinstance(value, list) else value}"
-                for key, value in dict_.items()
+                f"{', '.join(str(v) for v in val) if isinstance(val, list) else val}"
+                for key, val in dict_.items()
             ]
         )
 

mex/common/types/link.py

@@ -75,5 +75,4 @@ def __str__(self) -> str:
             title = markdown_escape(title)
             url = markdown_escape(self.url)
             return f"[{title}]({url})"
-        else:
-            return self.url
+        return self.url

mex/common/types/resolved_path.py

@@ -54,7 +54,7 @@ def resolve(self) -> Path:
         decide what it is relative to. We read the settings from the current
         `SettingsContext` and pick a base path from there.
         """
-        from mex.common.settings import SettingsContext  # noqa
+        from mex.common.settings import SettingsContext
 
         if self._path.is_absolute():
             return self._path

mex/common/types/timestamp.py

@@ -71,15 +71,15 @@ def __init__(
         self,
         *args: Union[str, date, datetime, "Timestamp"],
         tzinfo: Literal[None] = None,
-    ) -> None:  # noqa: D107
+    ) -> None:
         ...  # pragma: no cover
 
     @overload
     def __init__(
         self,
         *args: int,
         tzinfo: Optional[tzinfo] = None,
-    ) -> None:  # noqa: D107
+    ) -> None:
         ...  # pragma: no cover
 
     def __init__(

mex/common/utils.py

@@ -49,4 +49,4 @@ def jitter_sleep(min_seconds: float, jitter_seconds: float) -> None:
         min_seconds: The minimum time to sleep
         jitter_seconds: The variable sleep time added to the minimum
     """
-    sleep(min_seconds + random() * jitter_seconds)  # nosec
+    sleep(min_seconds + random() * jitter_seconds)  # noqa: S311

mex/common/wikidata/connector.py

@@ -61,7 +61,18 @@ def get_wikidata_item_details_by_id(self, item_id: str) -> dict[str, str]:
             "action": "wbgetentities",
             "format": "json",
             "ids": item_id,
-            "props": "info|aliases|labels|descriptions|datatype|claims|sitelinks|sitelinks/urls",
+            "props": "|".join(
+                [
+                    "info",
+                    "aliases",
+                    "labels",
+                    "descriptions",
+                    "datatype",
+                    "claims",
+                    "sitelinks",
+                    "sitelinks/urls",
+                ]
+            ),
             "formatversion": "2",
         }
 

mex/common/wikidata/extract.py

@@ -43,7 +43,7 @@ def search_organization_by_label(
             ) from exc
         except requests.exceptions.RetryError as exc:
             raise MExError(
-                f"RetryError: Max retries exceeded while processing results for {item_label}"
+                f"RetryError: Max retries exceeded processing results for {item_label}"
             ) from exc
         except KeyError as exc:
             raise MExError(