Files
@ d727e81e0097
Branch filter:
Location: kallithea/scripts/logformat.py - annotation
d727e81e0097
1.8 KiB
text/x-python
vcs: fix cloning remote repository with HTTP authentication (Issue #379)
Using a remote clone URI of
http://user:pass@host/...
triggered an exception:
...
E File ".../kallithea/lib/utils.py", line 256, in is_valid_repo_uri
E GitRepository._check_url(url)
E File ".../kallithea/lib/vcs/backends/git/repository.py", line 183, in _check_url
E passmgr.add_password(*authinfo)
E File "/usr/lib/python3.7/urllib/request.py", line 848, in add_password
E self.reduce_uri(u, default_port) for u in uri)
E File "/usr/lib/python3.7/urllib/request.py", line 848, in <genexpr>
E self.reduce_uri(u, default_port) for u in uri)
E File "/usr/lib/python3.7/urllib/request.py", line 875, in reduce_uri
E host, port = splitport(authority)
E File "/usr/lib/python3.7/urllib/parse.py", line 1022, in splitport
E match = _portprog.fullmatch(host)
E TypeError: cannot use a string pattern on a bytes-like object
The authinfo tuple is obtained via mercurial.util.url, which unfortunately
returns a tuple of bytes whereas urllib expects strings.
It seems that mercurial internally has some more hacking around urllib as
urllibcompat.py, which we don't use.
Therefore, transform the bytes into strings before passing authinfo to
urllib. As the realm can be None, we need to check it specifically otherwise
safe_str would return a string 'None'.
A basic test that catches the mentioned problem is added, even though it
does not actually test that cloning with auth info will actually work (it
only tests that it fails cleanly if the URI is not reachable).
Additionally, one use of 'test_uri' in hg/repository.py still needed to be
transformed from bytes to string. For git this was already ok.
Using a remote clone URI of
http://user:pass@host/...
triggered an exception:
...
E File ".../kallithea/lib/utils.py", line 256, in is_valid_repo_uri
E GitRepository._check_url(url)
E File ".../kallithea/lib/vcs/backends/git/repository.py", line 183, in _check_url
E passmgr.add_password(*authinfo)
E File "/usr/lib/python3.7/urllib/request.py", line 848, in add_password
E self.reduce_uri(u, default_port) for u in uri)
E File "/usr/lib/python3.7/urllib/request.py", line 848, in <genexpr>
E self.reduce_uri(u, default_port) for u in uri)
E File "/usr/lib/python3.7/urllib/request.py", line 875, in reduce_uri
E host, port = splitport(authority)
E File "/usr/lib/python3.7/urllib/parse.py", line 1022, in splitport
E match = _portprog.fullmatch(host)
E TypeError: cannot use a string pattern on a bytes-like object
The authinfo tuple is obtained via mercurial.util.url, which unfortunately
returns a tuple of bytes whereas urllib expects strings.
It seems that mercurial internally has some more hacking around urllib as
urllibcompat.py, which we don't use.
Therefore, transform the bytes into strings before passing authinfo to
urllib. As the realm can be None, we need to check it specifically otherwise
safe_str would return a string 'None'.
A basic test that catches the mentioned problem is added, even though it
does not actually test that cloning with auth info will actually work (it
only tests that it fails cleanly if the URI is not reachable).
Additionally, one use of 'test_uri' in hg/repository.py still needed to be
transformed from bytes to string. For git this was already ok.
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 a8e6bb9ee9ea 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 loc '*.py'|grep -v logformat.py` && scripts/logformat.py `hg loc '*.py'` && hg diff''')
raise SystemExit(1)
for f in sys.argv[1:]:
rewrite(f)
|