kallithea Files · scripts/logformat.py

Files @ 6fb68819e58e

Branch filter:

Location: kallithea/scripts/logformat.py

6fb68819e58e 1.7 KiB text/x-python Show Annotation Show as Raw Download as Raw

Eivind Tagseth

git: improve performance working with git changesets

GitRepository._repo instantiates a new dulwich.repo.Repo on every usage,
rather than once at initialization time of GitRepository. As this involves a
lot of filesystem access, this is a costly operation.

Instead, let GitRepository.__init__ instantiate a dulwich.repo.Repo once,
and let GitRepository._repo just return it.

This improves performance significantly.
On test_graphmod_git, performance improves from 6.29 seconds median to 3.06
seconds median.

[Thomas De Schampheleire: extend improvement to _all_ usage of
GitRepository._repo instead of only some. To limit the delta, retain the
_repo property but simply return self.repo.]

#!/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)