view hgext/lfs/pointer.py @ 39141:c89e2fb207a1 stable

remotephase: fast path newheads computation in simple case (issue5964)

Changeset 88efb7d6bcb6 fixed the logic of `phases.newheads` but greatly
regressed its performance (up to many order of magnitude). The first step to
fix the regression is to exit early when there is no work to do. If there are
no heads to filter or not roots to filter them, we don't have to do any work.

This fixes the regression when talking to an all public changeset. The
performance is even better than before.

pypy, compared to an all public repo
------------------------------------

8eeed92475d5: 0.005758 seconds
88efb7d6bcb6: 0.602517 seconds (x104)
this code:    0.001508 seconds (-74% from base)

mercurial compared to an all public repo
----------------------------------------

8eeed92475d5: 0.000577 seconds
88efb7d6bcb6: 0.185316 seconds (x321)
this code:    0.000150 seconds (-74% from base)

The performance of newheads, when actual computations are required, is fixed
in the next changeset.

# 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