gh-132390: Apply Ruff linting to Tools/build (#132391)

---------

Co-authored-by: Adam Turner <[email protected]>

Author: picnixz

.pre-commit-config.yaml

@@ -11,9 +11,9 @@ repos:
         args: [--exit-non-zero-on-fix]
         files: ^Lib/test/
       - id: ruff
-        name: Run Ruff (lint) on Tools/build/check_warnings.py
+        name: Run Ruff (lint) on Tools/build/
         args: [--exit-non-zero-on-fix, --config=Tools/build/.ruff.toml]
-        files: ^Tools/build/check_warnings.py
+        files: ^Tools/build/
       - id: ruff
         name: Run Ruff (lint) on Argument Clinic
         args: [--exit-non-zero-on-fix, --config=Tools/clinic/.ruff.toml]

Tools/build/.ruff.toml

@@ -18,3 +18,22 @@ select = [
     "W",       # pycodestyle
     "YTT",     # flake8-2020
 ]
+ignore = [
+    "E501",    # Line too long
+    "F541",    # f-string without any placeholders
+    "PYI024",  # Use `typing.NamedTuple` instead of `collections.namedtuple`
+    "PYI025",  # Use `from collections.abc import Set as AbstractSet`
+    "UP038",   # Use `X | Y` in `isinstance` call instead of `(X, Y)`
+]
+
+[per-file-target-version]
+"deepfreeze.py" = "py310"
+"stable_abi.py" = "py311"  # requires 'tomllib'
+
+[lint.per-file-ignores]
+"{check_extension_modules,freeze_modules}.py" = [
+    "UP031",  # Use format specifiers instead of percent format
+]
+"generate_{re_casefix,sre_constants,token}.py" = [
+    "UP031",  # Use format specifiers instead of percent format
+]

Tools/build/check_extension_modules.py

@@ -17,6 +17,7 @@
 
 See --help for more information
 """
+import _imp
 import argparse
 import collections
 import enum
@@ -27,12 +28,14 @@
 import sys
 import sysconfig
 import warnings
-import _imp
-
+from collections.abc import Iterable
 from importlib._bootstrap import _load as bootstrap_load
-from importlib.machinery import BuiltinImporter, ExtensionFileLoader, ModuleSpec
+from importlib.machinery import (
+    BuiltinImporter,
+    ExtensionFileLoader,
+    ModuleSpec,
+)
 from importlib.util import spec_from_file_location, spec_from_loader
-from typing import Iterable
 
 SRC_DIR = pathlib.Path(__file__).parent.parent.parent
 
@@ -195,7 +198,7 @@ def print_three_column(modinfos: list[ModuleInfo]):
             # guarantee zip() doesn't drop anything
             while len(names) % 3:
                 names.append("")
-            for l, m, r in zip(names[::3], names[1::3], names[2::3]):
+            for l, m, r in zip(names[::3], names[1::3], names[2::3]):  # noqa: E741
                 print("%-*s   %-*s   %-*s" % (longest, l, longest, m, longest, r))
 
         if verbose and self.builtin_ok:
@@ -420,7 +423,7 @@ def check_module_import(self, modinfo: ModuleInfo):
         except ImportError as e:
             logger.error("%s failed to import: %s", modinfo.name, e)
             raise
-        except Exception as e:
+        except Exception:
             if not hasattr(_imp, 'create_dynamic'):
                 logger.warning("Dynamic extension '%s' ignored", modinfo.name)
                 return

Tools/build/deepfreeze.py

@@ -13,7 +13,7 @@
 import re
 import time
 import types
-from typing import Dict, FrozenSet, TextIO, Tuple
+from typing import TextIO
 
 import umarshal
 
@@ -57,8 +57,8 @@ def get_localsplus(code: types.CodeType):
 
 
 def get_localsplus_counts(code: types.CodeType,
-                          names: Tuple[str, ...],
-                          kinds: bytes) -> Tuple[int, int, int, int]:
+                          names: tuple[str, ...],
+                          kinds: bytes) -> tuple[int, int, int]:
     nlocals = 0
     ncellvars = 0
     nfreevars = 0
@@ -84,7 +84,7 @@ def get_localsplus_counts(code: types.CodeType,
 PyUnicode_4BYTE_KIND = 4
 
 
-def analyze_character_width(s: str) -> Tuple[int, bool]:
+def analyze_character_width(s: str) -> tuple[int, bool]:
     maxchar = ' '
     for c in s:
         maxchar = max(maxchar, c)
@@ -109,7 +109,7 @@ class Printer:
     def __init__(self, file: TextIO) -> None:
         self.level = 0
         self.file = file
-        self.cache: Dict[tuple[type, object, str], str] = {}
+        self.cache: dict[tuple[type, object, str], str] = {}
         self.hits, self.misses = 0, 0
         self.finis: list[str] = []
         self.inits: list[str] = []
@@ -305,7 +305,7 @@ def generate_code(self, name: str, code: types.CodeType) -> str:
         self.inits.append(f"_PyStaticCode_Init({name_as_code})")
         return f"& {name}.ob_base.ob_base"
 
-    def generate_tuple(self, name: str, t: Tuple[object, ...]) -> str:
+    def generate_tuple(self, name: str, t: tuple[object, ...]) -> str:
         if len(t) == 0:
             return f"(PyObject *)& _Py_SINGLETON(tuple_empty)"
         items = [self.generate(f"{name}_{i}", it) for i, it in enumerate(t)]
@@ -379,7 +379,7 @@ def generate_complex(self, name: str, z: complex) -> str:
             self.write(f".cval = {{ {z.real}, {z.imag} }},")
         return f"&{name}.ob_base"
 
-    def generate_frozenset(self, name: str, fs: FrozenSet[object]) -> str:
+    def generate_frozenset(self, name: str, fs: frozenset[object]) -> str:
         try:
             fs = sorted(fs)
         except TypeError:
@@ -465,7 +465,7 @@ def generate(args: list[str], output: TextIO) -> None:
     printer = Printer(output)
     for arg in args:
         file, modname = arg.rsplit(':', 1)
-        with open(file, "r", encoding="utf8") as fd:
+        with open(file, encoding="utf8") as fd:
             source = fd.read()
             if is_frozen_header(source):
                 code = decode_frozen_data(source)
@@ -513,7 +513,7 @@ def main() -> None:
     if args.file:
         if verbose:
             print(f"Reading targets from {args.file}")
-        with open(args.file, "rt", encoding="utf-8-sig") as fin:
+        with open(args.file, encoding="utf-8-sig") as fin:
             rules = [x.strip() for x in fin]
     else:
         rules = args.args

Tools/build/freeze_modules.py

@@ -3,15 +3,14 @@
 See the notes at the top of Python/frozen.c for more info.
 """
 
-from collections import namedtuple
 import hashlib
 import ntpath
 import os
 import posixpath
+from collections import namedtuple
 
 from update_file import updating_file_with_tmpfile
 
-
 ROOT_DIR = os.path.dirname(os.path.dirname(os.path.dirname(__file__)))
 ROOT_DIR = os.path.abspath(ROOT_DIR)
 FROZEN_ONLY = os.path.join(ROOT_DIR, 'Tools', 'freeze', 'flag.py')
@@ -482,7 +481,6 @@ def regen_frozen(modules):
         header = relpath_for_posix_display(src.frozenfile, parentdir)
         headerlines.append(f'#include "{header}"')
 
-    externlines = UniqueList()
     bootstraplines = []
     stdliblines = []
     testlines = []
@@ -625,7 +623,6 @@ def regen_makefile(modules):
 def regen_pcbuild(modules):
     projlines = []
     filterlines = []
-    corelines = []
     for src in _iter_sources(modules):
         pyfile = relpath_for_windows_display(src.pyfile, ROOT_DIR)
         header = relpath_for_windows_display(src.frozenfile, ROOT_DIR)

Tools/build/generate_global_objects.py

@@ -286,7 +286,8 @@ def generate_runtime_init(identifiers, strings):
                 break
         else:
             raise NotImplementedError
-    assert nsmallposints and nsmallnegints
+    assert nsmallposints
+    assert nsmallnegints
 
     # Then target the runtime initializer.
     filename = os.path.join(INTERNAL, 'pycore_runtime_init_generated.h')
@@ -434,7 +435,7 @@ def get_identifiers_and_strings() -> 'tuple[set[str], dict[str, str]]':
                 # To cover tricky cases (like "\n") we also generate C asserts.
                 raise ValueError(
                     'do not use &_Py_ID or &_Py_STR for one-character latin-1 '
-                    + f'strings, use _Py_LATIN1_CHR instead: {string!r}')
+                    f'strings, use _Py_LATIN1_CHR instead: {string!r}')
             if string not in strings:
                 strings[string] = name
             elif name != strings[string]:

Tools/build/generate_levenshtein_examples.py

@@ -1,12 +1,11 @@
 """Generate 10,000 unique examples for the Levenshtein short-circuit tests."""
 
 import argparse
-from functools import lru_cache
 import json
 import os.path
+from functools import lru_cache
 from random import choices, randrange
 
-
 # This should be in sync with Lib/traceback.py.  It's not importing those values
 # because this script is being executed by PYTHON_FOR_REGEN and not by the in-tree
 # build of Python.

Tools/build/generate_re_casefix.py

@@ -9,7 +9,7 @@
 
 def update_file(file, content):
     try:
-        with open(file, 'r', encoding='utf-8') as fobj:
+        with open(file, encoding='utf-8') as fobj:
             if fobj.read() == content:
                 return False
     except (OSError, ValueError):
@@ -50,7 +50,7 @@ def main(outfile='Lib/re/_casefix.py'):
     # List of codes of lowercased characters which have the same uppercase.
     equivalent_lower_codes = [sorted(t)
                               for s in equivalent_chars
-                              for t in [set(ord(c.lower()) for c in s)]
+                              for t in [{ord(c.lower()) for c in s}]
                               if len(t) > 1]
 
     bad_codes = []

Tools/build/generate_sbom.py

@@ -1,14 +1,15 @@
 """Tool for generating Software Bill of Materials (SBOM) for Python's dependencies"""
-import os
-import re
+
+import glob
 import hashlib
 import json
-import glob
-from pathlib import Path, PurePosixPath, PureWindowsPath
+import os
+import re
 import subprocess
 import sys
-import urllib.request
 import typing
+import urllib.request
+from pathlib import Path, PurePosixPath, PureWindowsPath
 
 CPYTHON_ROOT_DIR = Path(__file__).parent.parent.parent
 
@@ -250,7 +251,7 @@ def check_sbom_packages(sbom_data: dict[str, typing.Any]) -> None:
         license_concluded = package["licenseConcluded"]
         error_if(
             license_concluded != "NOASSERTION",
-            f"License identifier must be 'NOASSERTION'"
+            "License identifier must be 'NOASSERTION'"
         )
 
 

Tools/build/generate_sre_constants.py

@@ -6,7 +6,7 @@
 
 def update_file(file, content):
     try:
-        with open(file, 'r') as fobj:
+        with open(file) as fobj:
             if fobj.read() == content:
                 return False
     except (OSError, ValueError):