def _get_object_fields(self):
"""# fetch list of field names that compose the object list."""
object_fields = {}
for set_name in self._sets:
data = self.hdf5_file['/{}/object_fields'.format(set_name)].value
object_fields[set_name] = tuple(convert_ascii_to_str(data))
return object_fields
def get(self, index=None, convert_to_str=False):
"""Retrieves data of the field from the dataset's hdf5 metadata file.
This method retrieves the i'th data from the hdf5 file. Also, it is
possible to retrieve multiple values by inserting a list/tuple of
number values as indexes.
Parameters
----------
index : int/list/tuple, optional
Index number of he field. If it is a list, returns the data
for all the value indexes of that list.
convert_to_str : bool, optional
Convert the output data into a string.
Warning: output must be of type np.uint8
Returns
-------
np.ndarray/list/str
Numpy array containing the field's data.
If convert_to_str is set to True, it returns a string
or list of strings.
Note
----
When using lists/tuples of indexes, this method sorts the list
and removes duplicate values. This is because the h5py
api requires the indexing elements to be in increasing order when
retrieving data.
"""
if index is None:
data = self._get_all_idx()
else:
data = self._get_range_idx(index)
if convert_to_str:
data = convert_ascii_to_str(data)
return data
def test_convert_ascii_to_str__raises_error__empty_input():
with pytest.raises(AssertionError):
convert_ascii_to_str([])
def _get_object_fields(self):
object_fields_data = self.hdf5_group['object_fields'].value
output = convert_ascii_to_str(object_fields_data)
if type(output) == 'string':
output = (output, )
return output
def test_convert_ascii_to_str_multiple_strings(sample, output):
res = convert_ascii_to_str(np.array(sample, dtype=np.uint8))
assert(output == res)