CI check comments of cheanged Python files

This commit is contained in:
Zhichang Yu
2025-11-14 10:53:09 +08:00
parent 63131ec9b2
commit 6b52f7df5a
2 changed files with 68 additions and 0 deletions

36
check_comment_ascii.py Normal file
View File

@ -0,0 +1,36 @@
#!/usr/bin/env python3
import sys
import tokenize
import ast
import pathlib
import re
ASCII = re.compile(r"^[ -~]*\Z") # Only printable ASCII
def check(src: str, name: str) -> int:
"""
I'm a docstring
"""
ok = 1
# A common comment begins with `#`
with tokenize.open(src) as fp:
for tk in tokenize.generate_tokens(fp.readline):
if tk.type == tokenize.COMMENT and not ASCII.fullmatch(tk.string):
print(f"{name}:{tk.start[0]}: non-ASCII comment: {tk.string}")
ok = 0
# A docstring begins and ends with `'''`
for node in ast.walk(ast.parse(pathlib.Path(src).read_text(), filename=name)):
if isinstance(node, (ast.FunctionDef, ast.ClassDef, ast.Module)):
if (doc := ast.get_docstring(node)) and not ASCII.fullmatch(doc):
print(f"{name}:{node.lineno}: non-ASCII docstring: {doc}")
ok = 0
return ok
if __name__ == "__main__":
status = 0
for file in sys.argv[1:]:
if not check(file, file):
status = 1
sys.exit(status)