Files
@ 2ac4499b25eb
Branch filter:
Location: kallithea/scripts/logformat.py - annotation
2ac4499b25eb
1.7 KiB
text/x-python
lib: sanitize HTML for all types of README rendering, not only markdown
The repository summary page will display a rendered version of the
repository 'readme' based on its file extension. In commit 5746cc3b3fa5,
the rendered output was already sanitized when the input was markdown.
However, also readmes written in other formats, like ReStructuredText (RST)
or plain text could have content that we want sanitized.
Therefore, move the sanitizing one level up so it covers all renderers, for
now and the future.
This fixes an XSS issue when a repository readme contains javascript code,
which would be executed when the repository summary page is visited by a
user.
Reported by Bob Hogg <wombat@rwhogg.site> (thanks!).
The repository summary page will display a rendered version of the
repository 'readme' based on its file extension. In commit 5746cc3b3fa5,
the rendered output was already sanitized when the input was markdown.
However, also readmes written in other formats, like ReStructuredText (RST)
or plain text could have content that we want sanitized.
Therefore, move the sanitizing one level up so it covers all renderers, for
now and the future.
This fixes an XSS issue when a repository readme contains javascript code,
which would be executed when the repository summary page is visited by a
user.
Reported by Bob Hogg <wombat@rwhogg.site> (thanks!).
8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 8bc8366a6874 665dfa112f2c 8bc8366a6874 8bc8366a6874 665dfa112f2c | #!/usr/bin/env python2
import re
import sys
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)
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'),
]
for f in sys.argv[1:]:
s = open(f).read()
for r, t in res:
s = r.sub(t, s)
open(f, 'w').write(s)
|