def external_repo(url,
rev=None,
for_write=False,
cache_dir=None,
cache_types=None,
**kwargs):
from dvc.config import NoRemoteError
from dvc.scm.git import Git
logger.debug("Creating external repo %s@%s", url, rev)
path = _cached_clone(url, rev, for_write=for_write)
# Local HEAD points to the tip of whatever branch we first cloned from
# (which may not be the default branch), use origin/HEAD here to get
# the tip of the default branch
rev = rev or "refs/remotes/origin/HEAD"
cache_config = {
"cache": {
"dir": cache_dir or _get_cache_dir(url),
"type": cache_types,
}
}
config = _get_remote_config(url) if os.path.isdir(url) else {}
config.update(cache_config)
def make_repo(path, **_kwargs):
_config = cache_config.copy()
if os.path.isdir(url):
rel = os.path.relpath(path, _kwargs["scm"].root_dir)
repo_path = os.path.join(url, rel)
_config.update(_get_remote_config(repo_path))
return Repo(path, config=_config, **_kwargs)
root_dir = path if for_write else os.path.realpath(path)
repo_kwargs = dict(
root_dir=root_dir,
url=url,
scm=None if for_write else Git(root_dir),
rev=None if for_write else rev,
config=config,
repo_factory=make_repo,
**kwargs,
)
if "subrepos" not in repo_kwargs:
repo_kwargs["subrepos"] = True
if "uninitialized" not in repo_kwargs:
repo_kwargs["uninitialized"] = True
repo = Repo(**repo_kwargs)
try:
yield repo
except NoRemoteError as exc:
raise NoRemoteInExternalRepoError(url) from exc
except OutputNotFoundError as exc:
if exc.repo is repo:
raise NoOutputInExternalRepoError(exc.output, repo.root_dir,
url) from exc
raise
except FileMissingError as exc:
raise PathMissingError(exc.path, url) from exc
finally:
repo.close()
if for_write:
_remove(path)
def external_repo(url,
rev=None,
for_write=False,
cache_dir=None,
cache_types=None,
**kwargs):
from scmrepo.git import Git
from dvc.config import NoRemoteError
from dvc.fs import GitFileSystem
logger.debug("Creating external repo %s@%s", url, rev)
path = _cached_clone(url, rev, for_write=for_write)
# Local HEAD points to the tip of whatever branch we first cloned from
# (which may not be the default branch), use origin/HEAD here to get
# the tip of the default branch
rev = rev or "refs/remotes/origin/HEAD"
cache_config = {
"cache": {
"dir": cache_dir or _get_cache_dir(url),
"type": cache_types
}
}
config = _get_remote_config(url) if os.path.isdir(url) else {}
config.update(cache_config)
if for_write:
scm = None
root_dir = path
fs = None
else:
scm = Git(path)
fs = GitFileSystem(scm=scm, rev=rev)
root_dir = "/"
repo_kwargs = dict(
root_dir=root_dir,
url=url,
fs=fs,
config=config,
repo_factory=erepo_factory(url, root_dir, cache_config),
scm=scm,
**kwargs,
)
if "subrepos" not in repo_kwargs:
repo_kwargs["subrepos"] = True
if "uninitialized" not in repo_kwargs:
repo_kwargs["uninitialized"] = True
repo = Repo(**repo_kwargs)
try:
yield repo
except NoRemoteError as exc:
raise NoRemoteInExternalRepoError(url) from exc
except OutputNotFoundError as exc:
if exc.repo is repo:
raise NoOutputInExternalRepoError(exc.output, repo.root_dir,
url) from exc
raise
except FileMissingError as exc:
raise PathMissingError(exc.path, url) from exc
finally:
repo.close()
if for_write:
_remove(path)