##// END OF EJS Templates
narrow: use diffmatcher to send only new filelogs in non-ellipses widening...
narrow: use diffmatcher to send only new filelogs in non-ellipses widening Before this patch, when we widen a non-ellipses narrow clone, we downloads all the filelogs matching the resulting new matcher. This is same as the ellipses case but can be improved because, we don't pull new csets in non-ellipses cases, we can only download the new added files instead of downloading all the files which matches the new matcher. So, we only download files which matches the new matcher but does not matches the old matcher. There exists a match.differencematcher() which is used here. This will lead to significant amount of speedup in extending a non-ellipses narrow copy on large repos because we will download and process only the new required filelogs. The tests changes demonstrate that we are downloading now less files. Thanks to Augie for pointing that functionality of differencematcher exists in core. Differential Revision: https://phab.mercurial-scm.org/D4614

File last commit:

r38494:67dc32d4 @56 default
r39701:c73c7653 default
Show More
pointer.py
83 lines | 2.8 KiB | text/x-python | PythonLexer
# pointer.py - Git-LFS pointer serialization
#
# Copyright 2017 Facebook, Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from __future__ import absolute_import
import re
from mercurial.i18n import _
from mercurial import (
error,
pycompat,
)
from mercurial.utils import (
stringutil,
)
class InvalidPointer(error.RevlogError):
pass
class gitlfspointer(dict):
VERSION = 'https://git-lfs.github.com/spec/v1'
def __init__(self, *args, **kwargs):
self['version'] = self.VERSION
super(gitlfspointer, self).__init__(*args)
self.update(pycompat.byteskwargs(kwargs))
@classmethod
def deserialize(cls, text):
try:
return cls(l.split(' ', 1) for l in text.splitlines()).validate()
except ValueError: # l.split returns 1 item instead of 2
raise InvalidPointer(_('cannot parse git-lfs text: %s')
% stringutil.pprint(text))
def serialize(self):
sortkeyfunc = lambda x: (x[0] != 'version', x)
items = sorted(self.validate().iteritems(), key=sortkeyfunc)
return ''.join('%s %s\n' % (k, v) for k, v in items)
def oid(self):
return self['oid'].split(':')[-1]
def size(self):
return int(self['size'])
# regular expressions used by _validate
# see https://github.com/git-lfs/git-lfs/blob/master/docs/spec.md
_keyre = re.compile(br'\A[a-z0-9.-]+\Z')
_valuere = re.compile(br'\A[^\n]*\Z')
_requiredre = {
'size': re.compile(br'\A[0-9]+\Z'),
'oid': re.compile(br'\Asha256:[0-9a-f]{64}\Z'),
'version': re.compile(br'\A%s\Z' % stringutil.reescape(VERSION)),
}
def validate(self):
"""raise InvalidPointer on error. return self if there is no error"""
requiredcount = 0
for k, v in self.iteritems():
if k in self._requiredre:
if not self._requiredre[k].match(v):
raise InvalidPointer(
_('unexpected lfs pointer value: %s=%s')
% (k, stringutil.pprint(v)))
requiredcount += 1
elif not self._keyre.match(k):
raise InvalidPointer(_('unexpected lfs pointer key: %s') % k)
if not self._valuere.match(v):
raise InvalidPointer(_('unexpected lfs pointer value: %s=%s')
% (k, stringutil.pprint(v)))
if len(self._requiredre) != requiredcount:
miss = sorted(set(self._requiredre.keys()).difference(self.keys()))
raise InvalidPointer(_('missing lfs pointer keys: %s')
% ', '.join(miss))
return self
deserialize = gitlfspointer.deserialize