def find_outs_by_path(self, path, outs=None, recursive=False, strict=True):
if not outs:
outs = [out for stage in self.stages for out in stage.outs]
abs_path = os.path.abspath(path)
path_info = PathInfo(abs_path)
match = path_info.__eq__ if strict else path_info.isin_or_eq
def func(out):
if out.scheme == "local" and match(out.path_info):
return True
if recursive and out.path_info.isin(path_info):
return True
return False
matched = list(filter(func, outs))
if not matched:
raise OutputNotFoundError(path, self)
return matched
def find_outs_by_path(self, path, outs=None, recursive=False, strict=True):
# using `outs_graph` to ensure graph checks are run
outs = outs or self.outs_graph
abs_path = os.path.abspath(path)
path_info = PathInfo(abs_path)
match = path_info.__eq__ if strict else path_info.isin_or_eq
def func(out):
if out.scheme == "local" and match(out.path_info):
return True
if recursive and out.path_info.isin(path_info):
return True
return False
matched = list(filter(func, outs))
if not matched:
raise OutputNotFoundError(path, self)
return matched
def get_url(path, repo=None, rev=None, remote=None):
"""
Returns the URL to the storage location of a data file or directory tracked
in a DVC repo. For Git repos, HEAD is used unless a rev argument is
supplied. The default remote is tried unless a remote argument is supplied.
Raises OutputNotFoundError if the file is not tracked by DVC.
NOTE: This function does not check for the actual existence of the file or
directory in the remote storage.
"""
with _make_repo(repo, rev=rev) as _repo:
path_info = PathInfo(_repo.root_dir) / path
with reraise(FileNotFoundError, PathMissingError(path, repo)):
metadata = _repo.repo_tree.metadata(path_info)
if not metadata.is_dvc:
raise OutputNotFoundError(path, repo)
cloud = metadata.repo.cloud
hash_info = _repo.repo_tree.get_hash(path_info)
return cloud.get_url_for(remote, checksum=hash_info.value)
def get_url(path, repo=None, rev=None, remote=None):
"""
Returns the URL to the storage location of a data file or directory tracked
in a DVC repo. For Git repos, HEAD is used unless a rev argument is
supplied. The default remote is tried unless a remote argument is supplied.
Raises OutputNotFoundError if the file is not tracked by DVC.
NOTE: This function does not check for the actual existence of the file or
directory in the remote storage.
"""
with Repo.open(repo, rev=rev, subrepos=True, uninitialized=True) as _repo:
fs_path = _repo.fs.path.join(_repo.root_dir, path)
with reraise(FileNotFoundError, PathMissingError(path, repo)):
metadata = _repo.repo_fs.metadata(fs_path)
if not metadata.is_dvc:
raise OutputNotFoundError(path, repo)
cloud = metadata.repo.cloud
md5 = metadata.repo.dvcfs.info(fs_path)["md5"]
return cloud.get_url_for(remote, checksum=md5)
def get_url(path, repo=None, rev=None, remote=None):
"""
Returns the URL to the storage location of a data file or directory tracked
in a DVC repo. For Git repos, HEAD is used unless a rev argument is
supplied. The default remote is tried unless a remote argument is supplied.
Raises OutputNotFoundError if the file is not tracked by DVC.
NOTE: This function does not check for the actual existence of the file or
directory in the remote storage.
"""
with Repo.open(repo, rev=rev, subrepos=True, uninitialized=True) as _repo:
with reraise(FileNotFoundError, PathMissingError(path, repo)):
info = _repo.repo_fs.info(path)
dvc_info = info.get("dvc_info")
if not dvc_info:
raise OutputNotFoundError(path, repo)
dvc_repo = info["repo"]
md5 = dvc_info["md5"]
return dvc_repo.cloud.get_url_for(remote, checksum=md5)
def find_out_by_relpath(self, path):
raise OutputNotFoundError(path, self)
