kallithea Files · scripts/logformat.py

Files @ e54ddaa52fee

Branch filter:

Location: kallithea/scripts/logformat.py

e54ddaa52fee 1.7 KiB text/x-python Show Annotation Show as Raw Download as Raw

Andrew Shadura

hooks: parse incoming git refs correctly

Hooks receive a line of the following format on standard input:

<old-value> SP <new-value> SP <ref-name> LF

where <old-value> is the old object name stored in the ref,
<new-value> is the new object name to be stored in the ref
and <ref-name> is the full name of the ref.

This means, we have to strip at least the LF in order to have a
correct version of the ref name after the split. Also, when
parsing the ref name itself, use all components but first instead
of just second, as a ref name may have slashes in it.

Previously, failure to parse ref name correctly would lead to the
following behaviour. A newly created repository with no commits pushed
has HEAD set to refs/heads/master by default, even though there's no
such ref in the repository yet. Upon first push, Kallithea rewrites
this symbolic reference with a reference to a real branch.

However, due to a bug in ref name parsing, if a ref name had a slash,
Kallithea would update HEAD to an invalid reference:

git push origin feature/branch

would rewrite HEAD to refs/heads/feature. All future attempts to work
with this repository would fail because dulwich would complain it can't
read HEAD as it is a directory.

#!/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 = file(f).read()
    for r, t in res:
        s = r.sub(t, s)
    file(f, 'w').write(s)