view mercurial/pushkey.py @ 43658:0796e266d26b

dirs: resolve fuzzer OOM situation by disallowing deep directory hierarchies

It seems like 2048 directories ought to be enough for any reasonable
use of Mercurial?

A previous version of this patch scanned for slashes before any allocations
occurred. That approach is slower than this in the happy path, but much faster
than this in the case that too many slashes are encountered. We may want to
revisit it in the future using memchr() so it'll be well-optimized by the libc
we're using.

.. bc:

    Mercurial will now defend against OOMs by refusing to operate on
    paths with 2048 or more components. This means that _extremely_
    deep path hierarchies will be rejected, but we anticipate nobody
    is using hierarchies this deep.

Differential Revision: https://phab.mercurial-scm.org/D7411

# pushkey.py - dispatching for pushing and pulling keys
#
# Copyright 2010 Matt Mackall <[e-mail]>
#
# 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

from . import (
    bookmarks,
    encoding,
    obsolete,
    phases,
)


def _nslist(repo):
    n = {}
    for k in _namespaces:
        n[k] = b""
    if not obsolete.isenabled(repo, obsolete.exchangeopt):
        n.pop(b'obsolete')
    return n


_namespaces = {
    b"namespaces": (lambda *x: False, _nslist),
    b"bookmarks": (bookmarks.pushbookmark, bookmarks.listbookmarks),
    b"phases": (phases.pushphase, phases.listphases),
    b"obsolete": (obsolete.pushmarker, obsolete.listmarkers),
}


def register(namespace, pushkey, listkeys):
    _namespaces[namespace] = (pushkey, listkeys)


def _get(namespace):
    return _namespaces.get(namespace, (lambda *x: False, lambda *x: {}))


def push(repo, namespace, key, old, new):
    '''should succeed iff value was old'''
    pk = _get(namespace)[0]
    return pk(repo, key, old, new)


def list(repo, namespace):
    '''return a dict'''
    lk = _get(namespace)[1]
    return lk(repo)


encode = encoding.fromlocal

decode = encoding.tolocal


def encodekeys(keys):
    """encode the content of a pushkey namespace for exchange over the wire"""
    return b'\n'.join([b'%s\t%s' % (encode(k), encode(v)) for k, v in keys])


def decodekeys(data):
    """decode the content of a pushkey namespace from exchange over the wire"""
    result = {}
    for l in data.splitlines():
        k, v = l.split(b'\t')
        result[decode(k)] = decode(v)
    return result