kallithea Files · scripts/logformat.py

Files @ f08fbf424898

Branch filter:

Location: kallithea/scripts/logformat.py

f08fbf424898 1.8 KiB text/x-python Show Annotation Show as Raw Download as Raw

mads

auth: don't trust clients too much - only trust the *last* IP in the X-Forwarded-For header

The X-Forwarded-For header contains a list of IP addresses, where each
proxy server appends the IP they see their request coming from.
See https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/X-Forwarded-For .

Trusting the *first* IP in HTTP_X_FORWARDED_FOR would allow clients to claim
any IP, which could be used to bypass IP restrictions configured in Kallithea.

Instead, only trust the last proxy in the chain, and thus only use the *last*
IP in HTTP_X_FORWARDED_FOR. (In setups where more than last IP should be
trusted, the last proxy server in the chain must be configured rewrite the
header accordingly.)

#!/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)