view hgext/lfs/pointer.py @ 46314:95a615dd77bf

clone: make sure we warm the cache after a clone

This work around any deviciency/limitation of the clone process. In our case
this ensure the persistent nodemap exist with valid content.

Ideally, the cloning process would also do "the right thing". However since
older server will never be able to do "the right thing". The local workaround
will be necessary anyway.

I am not worried by the performance impact of this as `hg clone` is non-instant
on large repositories where is could matters. Warming the cache if they are
already correct is very fast. And if they are not already warm, this seems like
a good time to do so.

This impact various test as more cache are now warmed sooner, all the change
should be harmless.

Differential Revision: https://phab.mercurial-scm.org/D9789

# 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.StorageError):
    pass


class gitlfspointer(dict):
    VERSION = b'https://git-lfs.github.com/spec/v1'

    def __init__(self, *args, **kwargs):
        self[b'version'] = self.VERSION
        super(gitlfspointer, self).__init__(*args)
        self.update(pycompat.byteskwargs(kwargs))

    @classmethod
    def deserialize(cls, text):
        try:
            return cls(l.split(b' ', 1) for l in text.splitlines()).validate()
        except ValueError:  # l.split returns 1 item instead of 2
            raise InvalidPointer(
                _(b'cannot parse git-lfs text: %s') % stringutil.pprint(text)
            )

    def serialize(self):
        sortkeyfunc = lambda x: (x[0] != b'version', x)
        items = sorted(pycompat.iteritems(self.validate()), key=sortkeyfunc)
        return b''.join(b'%s %s\n' % (k, v) for k, v in items)

    def oid(self):
        return self[b'oid'].split(b':')[-1]

    def size(self):
        return int(self[b'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 = {
        b'size': re.compile(br'\A[0-9]+\Z'),
        b'oid': re.compile(br'\Asha256:[0-9a-f]{64}\Z'),
        b'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 pycompat.iteritems(self):
            if k in self._requiredre:
                if not self._requiredre[k].match(v):
                    raise InvalidPointer(
                        _(b'unexpected lfs pointer value: %s=%s')
                        % (k, stringutil.pprint(v))
                    )
                requiredcount += 1
            elif not self._keyre.match(k):
                raise InvalidPointer(_(b'unexpected lfs pointer key: %s') % k)
            if not self._valuere.match(v):
                raise InvalidPointer(
                    _(b'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(
                _(b'missing lfs pointer keys: %s') % b', '.join(miss)
            )
        return self


deserialize = gitlfspointer.deserialize