Files
@ f0fbb0fe4462
Branch filter:
Location: kallithea/scripts/logformat.py - annotation
f0fbb0fe4462
1.8 KiB
text/x-python
git: update check for invalid URL characters to work with Python versions that include an attempt at fixing the very same problem
With changes like
https://github.com/python/cpython/commit/76cd81d60310d65d01f9d7b48a8985d8ab89c8b4
making it to Python 3.10 and being backported to previous Python versions, the
approach in a8a51a3bdb61 no longer works when combined with
urllib.parse.urlparse in d2f59de17bef: path will never contain the invalid
characters.
To catch this case anyway, add a new check to verify that the parsed URL can
roundtrip back to the original representation with urllib.parse.urlunparse .
The actual exception might vary, but one of them should always fire.
There is a risk that the new check will reject some URLs that somehow isn't
normalized. No such cases have been found yet.
With changes like
https://github.com/python/cpython/commit/76cd81d60310d65d01f9d7b48a8985d8ab89c8b4
making it to Python 3.10 and being backported to previous Python versions, the
approach in a8a51a3bdb61 no longer works when combined with
urllib.parse.urlparse in d2f59de17bef: path will never contain the invalid
characters.
To catch this case anyway, add a new check to verify that the parsed URL can
roundtrip back to the original representation with urllib.parse.urlunparse .
The actual exception might vary, but one of them should always fire.
There is a risk that the new check will reject some URLs that somehow isn't
normalized. No such cases have been found yet.
aa6f17a53b49 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 0a277465fddf 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 4473f1094d3d 4473f1094d3d 8bc8366a6874 8bc8366a6874 63b548dd5ef3 8bc8366a6874 63b548dd5ef3 8bc8366a6874 63b548dd5ef3 8bc8366a6874 63b548dd5ef3 8bc8366a6874 63b548dd5ef3 8bc8366a6874 8bc8366a6874 4473f1094d3d 4473f1094d3d 665dfa112f2c 8bc8366a6874 8bc8366a6874 665dfa112f2c 4473f1094d3d 4473f1094d3d 4473f1094d3d 4473f1094d3d a8e6bb9ee9ea a8e6bb9ee9ea 0a84ef075575 4473f1094d3d 4473f1094d3d 4473f1094d3d 4473f1094d3d | #!/usr/bin/env python3
import re
import sys
logre = r'''
(log\.(?:error|info|warning|debug)
[(][ \n]*
)
%s
(
[ \n]*[)]
)
'''
res = [
# handle % () - keeping spaces around the old %
(re.compile(logre % r'''("[^"]*"|'[^']*') ([\n ]*) % ([\n ]*) \( ( (?:[^()]|\n)* (?: \( (?:[^()]|\n)* \) (?:[^()]|\n)* )* ) \) ''', flags=re.MULTILINE | re.VERBOSE), r'\1\2,\3\4\5\6'),
# handle % without () - keeping spaces around the old %
(re.compile(logre % r'''("[^"]*"|'[^']*') ([\n ]*) % ([\n ]*) ( (?:[^()]|\n)* (?: \( (?:[^()]|\n)* \) (?:[^()]|\n)* )* ) ''', flags=re.MULTILINE | re.VERBOSE), r'\1\2,\3\4\5\6'),
# remove extra space if it is on next line
(re.compile(logre % r'''("[^"]*"|'[^']*') , (\n [ ]) ([ ][\n ]*) ( (?:[^()]|\n)* (?: \( (?:[^()]|\n)* \) (?:[^()]|\n)* )* ) ''', flags=re.MULTILINE | re.VERBOSE), r'\1\2,\3\4\5\6'),
# remove extra space if it is on same line
(re.compile(logre % r'''("[^"]*"|'[^']*') , [ ]+ () ( [\n ]+) ( (?:[^()]|\n)* (?: \( (?:[^()]|\n)* \) (?:[^()]|\n)* )* ) ''', flags=re.MULTILINE | re.VERBOSE), r'\1\2,\3\4\5\6'),
# remove trailing , and space
(re.compile(logre % r'''("[^"]*"|'[^']*') , () ( [\n ]*) ( (?:[^()]|\n)* (?: \( (?:[^()]|\n)* \) (?:[^()]|\n)* )* [^(), \n] ) [ ,]*''', flags=re.MULTILINE | re.VERBOSE), r'\1\2,\3\4\5\6'),
]
def rewrite(f):
s = open(f).read()
for r, t in res:
s = r.sub(t, s)
open(f, 'w').write(s)
if __name__ == '__main__':
if len(sys.argv) < 2:
print('Cleanup of superfluous % formatting of log statements.')
print('Usage:')
print(''' hg revert `hg files 'set:**.py'|grep -v logformat.py` && scripts/logformat.py `hg files 'set:**.py'` && hg diff''')
raise SystemExit(1)
for f in sys.argv[1:]:
rewrite(f)
|