hgext/lfs/pointer.py
author Gregory Szorc <gregory.szorc@gmail.com>
Sun, 06 Oct 2019 19:25:18 -0400
changeset 43105 649d3ac37a12
parent 43077 687b865b95ad
child 48875 6000f5b25c9b
permissions -rw-r--r--
py3: define and use pycompat.iteritems() for hgext/ .iteritems() -> .items() is the last source transform being performed. But it is also the most widely used. This commit adds a pycompat.iteritems symbol and imports it in place of .iteritems() for usage in hgext/. I chose to stop at just hgext/ because the patch will be large and it is an easy boundary to stop at since we can disable source transformation on a per-package basis. There are places where the type does implement items() and we could call items() directly. However, this would require critical thought and I thought it would be easier to just blindly change the code. We know which call sites need to be audited in the future because they have "pycompat.iteritems." With this change, we no longer perform source transformation on hgext! Differential Revision: https://phab.mercurial-scm.org/D7014

# 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