view hgext/lfs/pointer.py @ 43913:4b7d5d10c45d

exchange: ensure all outgoing subrepo references are present before pushing

We've run into occasional problems with people committing a repo, and then
amending or rebasing in the subrepo.  That makes it so that the revision in the
parent can't be checked out, and the problem gets propagated on push.  Mercurial
already tries to defend against this sort of dangling reference by pushing *all*
subrepo revisions first.  This reuses the checks that trigger warnings in
`hg verify` to bail on the push unless using `--force`.

I thought about putting this on the server side, but at that point, all of the
data has been transferred, only to bail out.  Additionally, SCM Manager hosts
subrepos in a location that isn't nested in the parent, so normal subrepo code
would complain that the subrepo is missing when run on the server.

Because the push command pushes subrepos before calling this exchange code, a
subrepo will be pushed before the parent is verified.  Not great, but no
dangling references are exchanged, so it solves the problem.  This code isn't in
the loop that pushes the subrepos because:

  1) the list of outgoing revisions is needed to limit the scope of the check
  2) the loop only accesses the current revision, and therefore can miss
     subrepos that were dropped in previous commits
  3) this code is called when pushing a subrepo, so the protection is recursive

I'm not sure if there's a cheap check for the list of files in the outgoing
bundle.  If there is, that would provide a fast path to bypass this check for
people not using subrepos (or if no subrepo changes were made).  There's
probably also room for verifying other references like tags.  But since that
doesn't break checkouts, it's much less of a problem.

Differential Revision: https://phab.mercurial-scm.org/D7616

# 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