def __init__(
self,
type_name: str,
uuid: Hashable,
save_dir: str,
subdir_split: Optional[int] = None,
pickle_protocol: int = -1
):
super(FileClassificationElement, self).__init__(type_name, uuid)
# TODO: Remove absolute path conversion (allow relative)
self.save_dir = osp.abspath(osp.expanduser(save_dir))
self.pickle_protocol = pickle_protocol
# Saving components
self.subdir_split = subdir_split
if subdir_split and int(subdir_split) > 0:
self.subdir_split = subdir_split = int(subdir_split)
# Using all but the last split segment. This is so we don't create
# a whole bunch of directories with a single element in them.
save_dir = osp.join(self.save_dir,
*partition_string(str(uuid).replace('-', ''),
subdir_split)[:subdir_split-1]
)
else:
save_dir = self.save_dir
self.filepath = osp.join(save_dir,
"%s.%s.classification.pickle"
% (self.type_name, str(self.uuid)))
def __init__(self,
type_name,
uuid,
save_dir,
subdir_split=None,
pickle_protocol=-1):
"""
Initialize a file-base descriptor element.
:param type_name: Type of classification. This is usually the name of
the classifier that generated this result.
:type type_name: str
:param uuid: uuid for this classification
:type uuid: collections.abc.Hashable
:param save_dir: Directory to save this element's contents. If this path
is relative, we interpret as relative to the current working
directory.
:type save_dir: str | unicode
:param subdir_split: If a positive integer, this will cause us to store
the vector file in a subdirectory under the ``save_dir`` that was
specified. The integer value specifies the number of splits that we
will make in the stringification of this descriptor's UUID. If
there happen to be dashes in this stringification, we will
remove them (as would happen if given an uuid.UUID instance as
the uuid element).
:type subdir_split: None | int
:param pickle_protocol: Pickling protocol to use. We will use -1 by
default (latest version, probably binary).
:type pickle_protocol: int
"""
super(FileClassificationElement, self).__init__(type_name, uuid)
# TODO: Remove absolute path conversion (allow relative)
self.save_dir = osp.abspath(osp.expanduser(save_dir))
self.pickle_protocol = pickle_protocol
# Saving components
self.subdir_split = subdir_split
if subdir_split and int(subdir_split) > 0:
self.subdir_split = subdir_split = int(subdir_split)
# Using all but the last split segment. This is so we don't create
# a whole bunch of directories with a single element in them.
save_dir = osp.join(
self.save_dir,
*partition_string(str(uuid).replace('-', ''),
subdir_split)[:subdir_split - 1])
else:
save_dir = self.save_dir
self.filepath = osp.join(
save_dir,
"%s.%s.classification.pickle" % (self.type_name, str(self.uuid)))
def _containing_dir(self, uuid: Hashable) -> str:
"""
Return the containing directory for something with the given UUID value
"""
if not self._uuid_chunk:
# No sub-directory storage configured
return self._root_dir
str_uuid = str(uuid)
# TODO(paul.tunison): Modify uuid string if to short for set UUID chunk.
# e.g. if uuid is the integer 1 and chunk size is 10, we should
# convert strigified result to be at least length 10?
# Do this in _fp_for_uuid method?
leading_parts = partition_string(str_uuid, self._uuid_chunk)[:-1]
return osp.join(self._root_dir, *leading_parts)
def __init__(self,
type_str: str,
uuid: Hashable,
save_dir: str,
subdir_split: Optional[int] = None):
"""
Initialize a file-base descriptor element.
:param type_str: Type of descriptor. This is usually the name of the
content descriptor that generated this vector.
:param uuid: uuid for this descriptor
:param save_dir: Directory to save this element's contents. If this path
is relative, we interpret as relative to the current working
directory.
:param subdir_split: If a positive integer and greater than 1, this will
cause us to store the vector file in a subdirectory under the
``save_dir`` based on our ``uuid``. The integer value specifies the
number of splits that we will make in the stringification of this
descriptor's UUID. The last split component is left off when
determining the save directory (thus the >1 above).
Dashes are stripped from this string (as would happen if given an
uuid.UUID instance as the uuid element).
"""
super(DescriptorFileElement, self).__init__(type_str, uuid)
self._save_dir = osp.abspath(osp.expanduser(save_dir))
self._subdir_split = subdir_split
# Generate filepath from parameters
if self._subdir_split and int(self._subdir_split) > 1:
# TODO: If uuid is an integer, create string with left-padded 0's
# to expand out the "length" before partitioning.
save_dir = osp.join(
self._save_dir,
*partition_string(
str(self.uuid()).replace('-', ''),
int(self._subdir_split))[:-1])
else:
save_dir = self._save_dir
self._vec_filepath = osp.join(
save_dir, "%s.%s.vector.npy" % (self.type(), str(self.uuid())))