view hgext/lfs/pointer.py @ 37047:fddcb51b5084

wireproto: define permissions-based routing of HTTPv2 wire protocol

Now that we have a scaffolding for serving version 2 of the HTTP
protocol, let's start implementing it.

A good place to start is URL routing and basic request processing
semantics. We can focus on content types, capabilities detect, etc
later.

Version 2 of the HTTP wire protocol encodes the needed permissions
of the request in the URL path. The reasons for this are documented
in the added documentation. In short, a) it makes it really easy and
fail proof for server administrators to implement path-based
authentication and b) it will enable clients to realize very early in
a server exchange that authentication will be required to complete
the operation. This latter point avoids all kinds of complexity and
problems, like dealing with Expect: 100-continue and clients finding
out later during `hg push` that they need to provide authentication.
This will avoid the current badness where clients send a full bundle,
get an HTTP 403, provide authentication, then retransmit the bundle.

In order to implement command checking, we needed to implement a
protocol handler for the new wire protocol. Our handler is just
small enough to run the code we've implemented.

Tests for the defined functionality have been added.

I very much want to refactor the permissions checking code and define
a better response format. But this can be done later. Nothing is
covered by backwards compatibility at this point.

Differential Revision: https://phab.mercurial-scm.org/D2836

# 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,
)

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: %r') % 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' % re.escape(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 value: %s=%r') % (k, v))
                requiredcount += 1
            elif not self._keyre.match(k):
                raise InvalidPointer(_('unexpected key: %s') % k)
            if not self._valuere.match(v):
                raise InvalidPointer(_('unexpected value: %s=%r') % (k, v))
        if len(self._requiredre) != requiredcount:
            miss = sorted(set(self._requiredre.keys()).difference(self.keys()))
            raise InvalidPointer(_('missed keys: %s') % ', '.join(miss))
        return self

deserialize = gitlfspointer.deserialize