pre-commit: Add codespell and ruff (TheAlgorithms#189)

Author: cclauss

.flake8

@@ -7,17 +7,19 @@ repos:
         types: [python]
       - id: trailing-whitespace
 
-  - repo: https://github.com/psf/black
-    rev: 23.1.0
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.2.5
     hooks:
-      - id: black
+      - id: codespell
+        additional_dependencies:
+          - tomli
 
-  - repo: https://github.com/PyCQA/isort
-    rev: 5.12.0
+  - repo: https://github.com/psf/black
+    rev: 23.7.0
     hooks:
-      - id: isort
+      - id: black
 
-  - repo: https://github.com/PyCQA/flake8
-    rev: 6.0.0
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.0.285
     hooks:
-      - id: flake8
+      - id: ruff

.pre-commit-config.yaml

@@ -30,13 +30,14 @@ def _get_private_key() -> str:
     if private_key is None:
         private_key_path = os.getenv("GITHUB_PRIVATE_KEY_PATH")
         if private_key_path is None:
-            raise RuntimeError(
+            msg = (
                 "Provide the private key using the GITHUB_PRIVATE_KEY environment "
-                + "variable or in a file using the GITHUB_PRIVATE_KEY_PATH "
-                + "environment variable. The path should either be absolute or "
-                + "relative to the repository root."
+                "variable or in a file using the GITHUB_PRIVATE_KEY_PATH environment "
+                "variable. The path should either be absolute or relative to the "
+                "repository root."
             )
-        with open(private_key_path, "r") as f:
+            raise RuntimeError(msg)
+        with open(private_key_path) as f:  # noqa: PTH123
             private_key = f.read()
     return private_key
 
@@ -93,10 +94,11 @@ def log(response: ClientResponse, body: bytes) -> None:  # pragma: no cover
         if response.status in STATUS_OK:
             loggerlevel = logger.info
             # Comments and reviews are too long to be logged for INFO level
-            if response.url.name in ("comments", "reviews"):
-                data = response.url.name.upper()
-            else:
-                data = body.decode(UTF_8_CHARSET)
+            data = (
+                response.url.name.upper()
+                if response.url.name in ("comments", "reviews")
+                else body.decode(UTF_8_CHARSET)
+            )
         else:
             loggerlevel = logger.error
             data = body.decode(UTF_8_CHARSET)

algorithms_keeper/api.py

@@ -53,7 +53,7 @@ def validate_extension(self) -> str:
             filepath = file.path
             if not filepath.suffix:
                 if ".github" not in filepath.parts:
-                    if filepath.parent.name:
+                    if filepath.parent.name:  # noqa: SIM114
                         invalid_filepath.append(file.name)
                     # Dotfiles are not considered as invalid if they are present in the
                     # root of the repository

algorithms_keeper/parser/files_parser.py

@@ -74,7 +74,8 @@ class PythonParser(BaseFilesParser):
         ".txt",
         # Good old Python file
         ".py",
-    ) + DOCS_EXTENSIONS
+        *DOCS_EXTENSIONS,
+    )
 
     def __init__(
         self,

algorithms_keeper/parser/python_parser.py

@@ -83,12 +83,12 @@ def add_error(
         # It seems that ``ParserSyntaxError`` is not a subclass of ``SyntaxError``,
         # the same information is stored under a different attribute. There is no
         # filename information in ``ParserSyntaxError``, thus the parameter `filepath`.
-        if isinstance(exc, SyntaxError):  # pragma: no cover
+        if isinstance(exc, SyntaxError):  # noqa: SIM108, pragma: no cover
             lineno = exc.lineno or 1
         else:
             lineno = exc.raw_line
         body = (
-            f"An error occured while parsing the file: `{filepath}`\n"
+            f"An error occurred while parsing the file: `{filepath}`\n"
             f"```python\n{message}\n```"
         )
         self._comments.append(ReviewComment(body, filepath, lineno))

algorithms_keeper/parser/record.py

@@ -10,14 +10,14 @@
 
 INVALID_CAMEL_CASE_NAME_COMMENT: str = (
     "Class names should follow the [`CamelCase`]"
-    + "(https://en.wikipedia.org/wiki/Camel_case) naming convention. "
-    + "Please update the following name accordingly: `{nodename}`"
+    "(https://en.wikipedia.org/wiki/Camel_case) naming convention. "
+    "Please update the following name accordingly: `{nodename}`"
 )
 
 INVALID_SNAKE_CASE_NAME_COMMENT: str = (
     "Variable and function names should follow the [`snake_case`]"
-    + "(https://en.wikipedia.org/wiki/Snake_case) naming convention. "
-    + "Please update the following name accordingly: `{nodename}`"
+    "(https://en.wikipedia.org/wiki/Snake_case) naming convention. "
+    "Please update the following name accordingly: `{nodename}`"
 )
 
 
@@ -35,9 +35,8 @@ def valid(self, name: str) -> bool:
             name = name.strip("_")
             if name[0].islower() or "_" in name:
                 return False
-        else:
-            if name.lower() != name and name.upper() != name:
-                return False
+        elif name.lower() != name and name.upper() != name:
+            return False
         return True
 
 
@@ -159,7 +158,7 @@ def visit_ClassDef(self, node: cst.ClassDef) -> None:
     def visit_Attribute(self, node: cst.Attribute) -> None:
         # The attribute node can come through other context as well but we only care
         # about the ones coming from assignments.
-        if self._assigntarget_counter > 0:
+        if self._assigntarget_counter > 0:  # noqa: SIM102
             # We only care about assignment attribute to *self*.
             if m.matches(node, m.Attribute(value=m.Name(value="self"))):
                 self._validate_nodename(
@@ -169,7 +168,7 @@ def visit_Attribute(self, node: cst.Attribute) -> None:
     def visit_Element(self, node: cst.Element) -> None:
         # We only care about elements in *List* or *Tuple* specifically coming from
         # inside the multiple assignments.
-        if self._assigntarget_counter > 0:
+        if self._assigntarget_counter > 0:  # noqa: SIM102
             if m.matches(node, m.Element(value=m.Name())):
                 nodename = cst.ensure_type(node.value, cst.Name).value
                 self._validate_nodename(node, nodename, NamingConvention.SNAKE_CASE)

algorithms_keeper/parser/rules/naming_convention.py

@@ -8,7 +8,7 @@
 
 MISSING_DOCTEST: str = (
     "As there is no test file in this pull request nor any test function or class in "
-    + "the file `{filepath}`, please provide doctest for the function `{nodename}`"
+    "the file `{filepath}`, please provide doctest for the function `{nodename}`"
 )
 
 INIT: str = "__init__"
@@ -184,7 +184,7 @@ def spam(self):
                     pass
             """
         ),
-        # Check that `_skip_doctest` attribute is reseted after leaving the class.
+        # Check that `_skip_doctest` attribute is reset after leaving the class.
         Invalid(
             """
             def bar():
@@ -221,7 +221,7 @@ def visit_ClassDef(self, node: cst.ClassDef) -> None:
         # Temporary storage of the ``skip_doctest`` value only during the class visit.
         # If the class-level docstring contains doctest, then the checks should only be
         # skipped for all its methods and not for other functions/class in the module.
-        # After leaving the class, ``skip_doctest`` should be resetted to whatever the
+        # After leaving the class, ``skip_doctest`` should be reset to whatever the
         # value was before.
         self._temporary = self._skip_doctest
         self._skip_doctest = self._has_doctest(node)

algorithms_keeper/parser/rules/require_doctest.py

@@ -7,8 +7,8 @@
 
 MISSING_RETURN_TYPE_HINT: str = (
     "Please provide return type hint for the function: `{nodename}`. "
-    + "**If the function does not return a value, please provide "
-    + "the type hint as:** `def function() -> None:`"
+    "**If the function does not return a value, please provide "
+    "the type hint as:** `def function() -> None:`"
 )
 
 IGNORE_PARAM: set[str] = {"self", "cls"}

algorithms_keeper/parser/rules/require_type_hint.py

@@ -8,10 +8,10 @@
 class UseFstringRule(CstLintRule):
     MESSAGE: str = (
         "As mentioned in the [Contributing Guidelines]"
-        + "(https://github.com/TheAlgorithms/Python/blob/master/CONTRIBUTING.md), "
-        + "please do not use printf style formatting or `str.format()`. "
-        + "Use [f-string](https://realpython.com/python-f-strings/) instead to be "
-        + "more readable and efficient."
+        "(https://github.com/TheAlgorithms/Python/blob/master/CONTRIBUTING.md), "
+        "please do not use printf style formatting or `str.format()`. "
+        "Use [f-string](https://realpython.com/python-f-strings/) instead to be "
+        "more readable and efficient."
     )
 
     VALID = [

algorithms_keeper/parser/rules/use_fstring.py

@@ -142,7 +142,7 @@ async def get_user_open_pr_numbers(
     )
     pr_numbers = []
     async for pull in gh.getiter(search_url, oauth_token=await gh.access_token):
-        pr_numbers.append(pull["number"])
+        pr_numbers.append(pull["number"])  # noqa: PERF401
     return pr_numbers
 
 
@@ -211,7 +211,7 @@ async def get_pr_files(gh: GitHubAPI, *, pull_request: Mapping[str, Any]) -> lis
     async for data in gh.getiter(
         pull_request["url"] + "/files", oauth_token=await gh.access_token
     ):
-        files.append(
+        files.append(  # noqa: PERF401
             File(
                 data["filename"],
                 Path(data["filename"]),

algorithms_keeper/utils.py

@@ -1,6 +1,3 @@
-[tool.isort]
-profile = "black"
-
 [tool.mypy]
 ignore_missing_imports = true
 warn_unused_configs = true
@@ -19,6 +16,81 @@ module = "tests.data.*"
 disallow_untyped_defs = false
 check_untyped_defs = false
 
+[tool.ruff]
+select = [
+  "A",      # flake8-builtins
+  "AIR",    # Airflow
+  "ASYNC",  # flake8-async
+  "B",      # flake8-bugbear
+  "BLE",    # flake8-blind-except
+  "C4",     # flake8-comprehensions
+  "C90",    # McCabe cyclomatic complexity
+  "CPY",    # flake8-copyright
+  "DJ",     # flake8-django
+  "DTZ",    # flake8-datetimez
+  "E",      # pycodestyle
+  "EM",     # flake8-errmsg
+  "EXE",    # flake8-executable
+  "F",      # Pyflakes
+  "FLY",    # flynt
+  "G",      # flake8-logging-format
+  "I",      # isort
+  "ICN",    # flake8-import-conventions
+  "INP",    # flake8-no-pep420
+  "INT",    # flake8-gettext
+  "ISC",    # flake8-implicit-str-concat
+  "N",      # pep8-naming
+  "NPY",    # NumPy-specific rules
+  "PD",     # pandas-vet
+  "PERF",   # Perflint
+  "PGH",    # pygrep-hooks
+  "PIE",    # flake8-pie
+  "PL",     # Pylint
+  "PT",     # flake8-pytest-style
+  "PTH",    # flake8-use-pathlib
+  "PYI",    # flake8-pyi
+  "RSE",    # flake8-raise
+  "RUF",    # Ruff-specific rules
+  "S",      # flake8-bandit
+  "SIM",    # flake8-simplify
+  "SLF",    # flake8-self
+  "SLOT",   # flake8-slots
+  "T10",    # flake8-debugger
+  "TCH",    # flake8-type-checking
+  "TID",    # flake8-tidy-imports
+  "UP",     # pyupgrade
+  "W",      # pycodestyle
+  "YTT",    # flake8-2020
+  # "ANN",  # flake8-annotations
+  # "ARG",  # flake8-unused-arguments
+  # "COM",  # flake8-commas
+  # "D",    # pydocstyle
+  # "ERA",  # eradicate
+  # "FA",   # flake8-future-annotations
+  # "FBT",  # flake8-boolean-trap
+  # "FIX",  # flake8-fixme
+  # "Q",    # flake8-quotes
+  # "RET",  # flake8-return
+  # "T20",  # flake8-print
+  # "TD",   # flake8-todos
+  # "TRY",  s# tryceratops
+]
+ignore = ["N802", "PGH003", "RUF012", "SLF001"]
+line-length = 88
+target-version = "py38"
+
+[tool.ruff.mccabe]
+max-complexity = 13
+
+[tool.ruff.per-file-ignores]
+"tests/*" = ["PT006", "PT007", "S101"]
+"tests/test_commands.py" = ["B008"]
+"tests/test_pull_requests.py" = ["B008"]
+
+[tool.ruff.pylint]
+allow-magic-value-types = ["bytes", "int", "str"]
+max-args = 6  # Recommended: 5
+
 [tool.pytest.ini_options]
 testpaths = "tests"
 addopts = """\

pyproject.toml

@@ -66,5 +66,3 @@ def c(self, a: int = 10) -> None:
 
 class C:
     """A class which requires descriptive names"""
-
-    pass

tests/data/descriptive_name.py

@@ -4,7 +4,6 @@
 import pytest
 import pytest_asyncio
 from gidgethub import apps, sansio
-from pytest import MonkeyPatch
 
 from algorithms_keeper.api import GitHubAPI, token_cache
 
@@ -23,7 +22,7 @@ async def github_api() -> AsyncGenerator[GitHubAPI, None]:
     assert session.closed is True
 
 
-@pytest.mark.asyncio
+@pytest.mark.asyncio()
 async def test_initialization() -> None:
     async with aiohttp.ClientSession() as session:
         github_api = GitHubAPI(number, session, "algorithms-keeper")
@@ -35,8 +34,10 @@ async def test_initialization() -> None:
     assert github_api.requester == "algorithms-keeper"
 
 
-@pytest.mark.asyncio
-async def test_access_token(github_api: GitHubAPI, monkeypatch: MonkeyPatch) -> None:
+@pytest.mark.asyncio()
+async def test_access_token(
+    github_api: GitHubAPI, monkeypatch: pytest.MonkeyPatch
+) -> None:
     monkeypatch.setattr(apps, "get_installation_access_token", mock_return)
     monkeypatch.setenv("GITHUB_APP_ID", "")
     monkeypatch.setenv("GITHUB_PRIVATE_KEY", "")
@@ -49,7 +50,7 @@ async def test_access_token(github_api: GitHubAPI, monkeypatch: MonkeyPatch) ->
     assert cached_token == token
 
 
-@pytest.mark.asyncio
+@pytest.mark.asyncio()
 async def test_headers_and_log(github_api: GitHubAPI) -> None:
     request_headers = sansio.create_headers("algorithms-keeper")
     resp = await github_api._request(

tests/test_api.py

@@ -20,7 +20,7 @@
 
 # Reminder: ``Event.delivery_id`` is used as a short description for the respective
 # test case and as a way to id the specific test case in the parametrized group.
-@pytest.mark.asyncio
+@pytest.mark.asyncio()
 @pytest.mark.parametrize(
     "event, gh, expected",
     (
@@ -187,7 +187,7 @@
                 post_data=[{"labels": [Label.FAILED_TEST]}],
             ),
         ),
-        # Check run complated and it's a failure, there is ``FAILED_TEST`` label on
+        # Check run completed and it's a failure, there is ``FAILED_TEST`` label on
         # the pull request, so don't do anything.
         (
             Event(