annotate hgext/largefiles/storefactory.py @ 40053:8c692a6b5ad1

fuzz: new fuzzer for cext/manifest.c

This is a bit messy, because lazymanifest is tightly coupled to the
cpython API for performance reasons. As a result, we have to build a
whole Python without pymalloc (so ASAN can help us out) and link
against that. Then we have to use an embedded Python interpreter. We
could manually drive the lazymanifest in C from that point, but
experimentally just using PyEval_EvalCode isn't really any slower so
we may as well do that and write the innermost guts of the fuzzer in
Python.

Leak detection is currently disabled for this fuzzer because there are
a few global-lifetime things in our extensions that we more or less
intentionally leak and I didn't want to take the detour to work around
that for now.

This should not be pushed to our repo until
https://github.com/google/oss-fuzz/pull/1853 is merged, as this
depends on having the Python tarball around.

Differential Revision: https://phab.mercurial-scm.org/D4879

# 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,
    hg,
    util,
)

from . import (
    lfutil,
    localstore,
    wirestore,
)

# During clone this function is passed the src's ui object
# but it needs the dest's ui object so it can read out of
# the config file. Use repo.ui instead.
def openstore(repo=None, remote=None, put=False, ui=None):
    if ui is None:
        ui = repo.ui

    if not remote:
        lfpullsource = getattr(repo, 'lfpullsource', None)
        if lfpullsource:
            path = ui.expandpath(lfpullsource)
        elif put:
            path = ui.expandpath('default-push', 'default')
        else:
            path = ui.expandpath('default')

        # ui.expandpath() leaves 'default-push' and 'default' alone if
        # they cannot be expanded: fallback to the empty string,
        # meaning the current directory.
        if repo is None:
            path = ui.expandpath('default')
            path, _branches = hg.parseurl(path)
            remote = hg.peer(repo or ui, {}, path)
        elif path == 'default-push' or path == 'default':
            path = ''
            remote = repo
        else:
            path, _branches = hg.parseurl(path)
            remote = hg.peer(repo or ui, {}, path)

    # The path could be a scheme so use Mercurial's normal functionality
    # to resolve the scheme to a repository and use its path
    path = util.safehasattr(remote, 'url') and remote.url() or remote.path

    match = _scheme_re.match(path)
    if not match:                       # regular filesystem path
        scheme = 'file'
    else:
        scheme = match.group(1)

    try:
        storeproviders = _storeprovider[scheme]
    except KeyError:
        raise error.Abort(_('unsupported URL scheme %r') % scheme)

    for classobj in storeproviders:
        try:
            return classobj(ui, repo, remote)
        except lfutil.storeprotonotcapable:
            pass

    raise error.Abort(_('%s does not appear to be a largefile store') %
                     util.hidepassword(path))

_storeprovider = {
    'file':  [localstore.localstore],
    'http':  [wirestore.wirestore],
    'https': [wirestore.wirestore],
    'ssh': [wirestore.wirestore],
    }

_scheme_re = re.compile(br'^([a-zA-Z0-9+-.]+)://')

def getlfile(ui, hash):
    return util.chunkbuffer(openstore(ui=ui)._get(hash))