Merge pull request #237 from scrapy/ruff

Migrate to ruff.

Author: wRAR

.bandit.yml

@@ -1,23 +1,7 @@
 repos:
-- repo: https://github.com/PyCQA/bandit
-  rev: 1.8.2
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  rev: v0.9.3
   hooks:
-  - id: bandit
-    args: [-r, -c, .bandit.yml]
-- repo: https://github.com/PyCQA/flake8
-  rev: 7.1.1
-  hooks:
-  - id: flake8
-- repo: https://github.com/psf/black.git
-  rev: 24.10.0
-  hooks:
-  - id: black
-- repo: https://github.com/pycqa/isort
-  rev: 5.13.2
-  hooks:
-  - id: isort
-- repo: https://github.com/asottile/pyupgrade
-  rev: v3.19.1
-  hooks:
-  - id: pyupgrade
-    args: [--py39-plus]
+    - id: ruff
+      args: [ --fix ]
+    - id: ruff-format

.bumpversion.cfg

@@ -9,13 +9,13 @@
 # All configuration values have a default; values that are commented out
 # serve to show the default.
 
-import os
 import sys
+from pathlib import Path
 
 # If extensions (or modules to document with autodoc) are in another directory,
 # add these directories to sys.path here. If the directory is relative to the
 # documentation root, use os.path.abspath to make it absolute, like shown here.
-sys.path.insert(0, os.path.abspath(".."))
+sys.path.insert(0, str(Path(__file__).parent.parent))
 
 # -- General configuration -----------------------------------------------------
 

.coveragerc

@@ -0,0 +1,183 @@
+[tool.bumpversion]
+current_version = "2.3.1"
+commit = true
+tag = true
+tag_name = "v{new_version}"
+
+[[tool.bumpversion.files]]
+filename = "setup.py"
+
+[[tool.bumpversion.files]]
+filename = "w3lib/__init__.py"
+
+[[tool.bumpversion.files]]
+filename = "docs/conf.py"
+
+[tool.coverage.run]
+branch = true
+include = ["w3lib/*"]
+
+[tool.coverage.report]
+exclude_also = [
+    "if TYPE_CHECKING:",
+]
+
+[tool.mypy]
+check_untyped_defs = true
+
+[[tool.mypy.overrides]]
+# All non-tests functions must be typed.
+module = "w3lib.*"
+disallow_untyped_defs = true
+
+[[tool.mypy.overrides]]
+# Allow test functions to be untyped
+module = "tests.*"
+disallow_untyped_defs = false
+
+[tool.pylint.MASTER]
+persistent = "no"
+
+[tool.pylint."MESSAGES CONTROL"]
+enable = [
+    "useless-suppression",
+]
+disable = [
+    "fixme",
+    "import-error",
+    "import-outside-toplevel",
+    "invalid-name",
+    "line-too-long",
+    "missing-class-docstring",
+    "missing-function-docstring",
+    "missing-module-docstring",
+    "raise-missing-from",
+    "redefined-builtin",
+    "redefined-outer-name",
+    "too-many-arguments",
+    "too-many-branches",
+    "too-many-lines",
+    "too-many-positional-arguments",
+    "too-many-public-methods",
+    "unused-argument",
+    "unused-variable",
+]
+
+[tool.ruff.lint]
+extend-select = [
+    # flake8-bugbear
+    "B",
+    # flake8-comprehensions
+    "C4",
+    # pydocstyle
+    "D",
+    # flake8-future-annotations
+    "FA",
+    # flynt
+    "FLY",
+    # refurb
+    "FURB",
+    # isort
+    "I",
+    # flake8-implicit-str-concat
+    "ISC",
+    # flake8-logging
+    "LOG",
+    # Perflint
+    "PERF",
+    # pygrep-hooks
+    "PGH",
+    # flake8-pie
+    "PIE",
+    # pylint
+    "PL",
+    # flake8-use-pathlib
+    "PTH",
+    # flake8-pyi
+    "PYI",
+    # flake8-quotes
+    "Q",
+    # flake8-return
+    "RET",
+    # flake8-raise
+    "RSE",
+    # Ruff-specific rules
+    "RUF",
+    # flake8-bandit
+    "S",
+    # flake8-simplify
+    "SIM",
+    # flake8-slots
+    "SLOT",
+    # flake8-debugger
+    "T10",
+    # flake8-type-checking
+    "TC",
+    # pyupgrade
+    "UP",
+    # pycodestyle warnings
+    "W",
+    # flake8-2020
+    "YTT",
+]
+ignore = [
+    # Within an `except` clause, raise exceptions with `raise ... from`
+    "B904",
+    # Missing docstring in public module
+    "D100",
+    # Missing docstring in public class
+    "D101",
+    # Missing docstring in public method
+    "D102",
+    # Missing docstring in public function
+    "D103",
+    # Missing docstring in public package
+    "D104",
+    # Missing docstring in magic method
+    "D105",
+    # Missing docstring in public nested class
+    "D106",
+    # Missing docstring in __init__
+    "D107",
+    # One-line docstring should fit on one line with quotes
+    "D200",
+    # No blank lines allowed after function docstring
+    "D202",
+    # 1 blank line required between summary line and description
+    "D205",
+    # Multi-line docstring closing quotes should be on a separate line
+    "D209",
+    # First line should end with a period
+    "D400",
+    # First line should be in imperative mood; try rephrasing
+    "D401",
+    # First line should not be the function's "signature"
+    "D402",
+    # First word of the first line should be properly capitalized
+    "D403",
+    # No blank lines allowed between a section header and its content
+    "D412",
+    # Too many return statements
+    "PLR0911",
+    # Too many branches
+    "PLR0912",
+    # Too many arguments in function definition
+    "PLR0913",
+    # Too many statements
+    "PLR0915",
+    # Magic value used in comparison
+    "PLR2004",
+    # String contains ambiguous {}.
+    "RUF001",
+    # Docstring contains ambiguous {}.
+    "RUF002",
+    # Comment contains ambiguous {}.
+    "RUF003",
+    # Mutable class attributes should be annotated with `typing.ClassVar`
+    "RUF012",
+    # Use of `assert` detected
+    "S101",
+]
+
+[tool.ruff.lint.pydocstyle]
+convention = "pep257"

.flake8

@@ -1,14 +1,13 @@
-from setuptools import find_packages, setup
+from pathlib import Path
 
-with open("README.rst", encoding="utf-8") as f:
-    long_description = f.read()
+from setuptools import find_packages, setup
 
 setup(
     name="w3lib",
     version="2.3.1",
     license="BSD",
     description="Library of web-related functions",
-    long_description=long_description,
+    long_description=Path("README.rst").read_text(encoding="utf-8"),
     long_description_content_type="text/x-rst",
     author="Scrapy project",
     author_email="info@scrapy.org",

.isort.cfg

@@ -33,7 +33,7 @@ class RequestEncodingTests(unittest.TestCase):
 
     def test_bom(self):
         # cjk water character in unicode
-        water_unicode = "\u6C34"
+        water_unicode = "\u6c34"
         # BOM + water character encoded
         utf16be = b"\xfe\xff\x6c\x34"
         utf16le = b"\xff\xfe\x34\x6c"
@@ -273,8 +273,8 @@ def test_python_crash(self):
 
         random.seed(42)
         buf = BytesIO()
-        for i in range(150000):
-            buf.write(bytes([random.randint(0, 255)]))
+        for _ in range(150000):
+            buf.write(bytes([random.randint(0, 255)]))  # noqa: S311
         to_unicode(buf.getvalue(), "utf-16-le")
         to_unicode(buf.getvalue(), "utf-16-be")
         to_unicode(buf.getvalue(), "utf-32-le")

.pre-commit-config.yaml

@@ -84,8 +84,8 @@ def test_missing_semicolon(self):
             ("&#x41h", "Ah"),
             ("&#65!", "A!"),
             ("&#65x", "Ax"),
-            ("&sup3!", "\u00B3!"),
-            ("&Aacute!", "\u00C1!"),
+            ("&sup3!", "\u00b3!"),
+            ("&Aacute!", "\u00c1!"),
             ("&#9731!", "\u2603!"),
             ("&#153", "\u2122"),
             ("&#x99", "\u2122"),
@@ -325,7 +325,6 @@ def test_with_escape_chars(self):
 
 
 class UnquoteMarkupTest(unittest.TestCase):
-
     sample_txt1 = """<node1>hi, this is sample text with entities: &amp; &copy;
 <![CDATA[although this is inside a cdata! &amp; &quot;]]></node1>"""
     sample_txt2 = (