def __generate_length_dependent_key(self, command_line_args):
num_records = command_line_args.pop('num_records', None)
peptide_length = command_line_args.pop('peptide_length', None)
if num_records is None:
return r.Key(r.WholeRange(), peptide_length=peptide_length)
return r.Key(r.DiscreteDataChunk(list(range(num_records))),
peptide_length=peptide_length)
def test_hdf5_array_repository_remove_records(array_repository_w_saved_data):
_, repo, _, ids = array_repository_w_saved_data
prev_indices = {}
for index in repo.indices:
prev_indices[index] = repo.get_index(index)
removed_ids = ranges.Key([ids[0]])
repo.remove_records(removed_ids)
removed_locations = repo.find(removed_ids)
locations = repo.find(ids)
found_ids = []
for path, indices in locations.items():
with hdf5.HDF5File() as file:
dataset = file[path]
for _id, idx in dataset.attrs.items():
if idx in indices:
found_ids.append(_id)
assert repo.get_num_records() == len(ids) - 1
assert len(removed_locations) == 0
assert len(found_ids) == len(ids) - 1
assert sorted(found_ids) != ids
for index in repo.indices:
assert prev_indices[index] != repo.get_index(index)
def test_hdf5_obj_repository_load_from_whole_range(obj_repository_w_saved_data,
dict_sort_key):
dicts, repo, _, ids = obj_repository_w_saved_data
key = ranges.Key(ranges.WholeRange())
loaded_ids, loaded_data = zip(*list(repo.load(key)))
loaded_ids = list(loaded_ids)
loaded_data = list(loaded_data)
loaded_ids.sort()
loaded_data.sort(key=dict_sort_key)
dicts.sort(key=dict_sort_key)
assert loaded_data == dicts
assert ids == loaded_ids
def test_hdf5_array_repository_load_from_whole_range(
array_repository_w_saved_data):
arrays, repo, _, ids = array_repository_w_saved_data
arrays = [list(record) for record in arrays.reg_combos + arrays.cap_combos]
key = ranges.Key(ranges.WholeRange())
loaded_ids, loaded_data = zip(*list(repo.load(key)))
loaded_ids = list(loaded_ids)
loaded_data = [list(record) for record in loaded_data]
loaded_ids.sort()
loaded_data.sort()
arrays.sort()
assert loaded_data == arrays
assert ids == loaded_ids
def test_hdf5_obj_repository_load_from_index_vals(obj_repository_w_saved_data,
extract_attr_from_dicts,
dict_sort_key):
dicts, repo, _, ids = obj_repository_w_saved_data
for index in repo.DEFAULT_INDICES:
key = ranges.Key(extract_attr_from_dicts(dicts, index), index=index)
loaded_ids, loaded_data = zip(*list(repo.load(key)))
loaded_ids = list(loaded_ids)
loaded_data = list(loaded_data)
loaded_ids.sort()
loaded_data.sort(key=dict_sort_key)
dicts.sort(key=dict_sort_key)
assert loaded_data == dicts
assert ids == loaded_ids
def __extract_operation_parameters(self, command_line_args):
if self.operation == g.SidechainModifier.STRING:
operation_parameters = {
'sidechain_key': r.Key(r.WholeRange()),
'connection_key': r.Key(r.WholeRange())
}
elif self.operation == g.MonomerGenerator.STRING:
operation_parameters = {
'sidechain_key': r.Key(r.WholeRange()),
'backbone_key': r.Key(r.WholeRange())
}
elif self.operation == g.PeptidePlanGenerator.STRING:
operation_parameters = {'monomer_key': r.Key(r.WholeRange())}
elif self.operation == g.PeptideGenerator.STRING:
operation_parameters = {
'peptide_plan_key':
self.__generate_length_dependent_key(command_line_args),
'monomer_key':
r.Key(r.WholeRange())
}
elif self.operation == g.TemplatePeptideGenerator.STRING:
operation_parameters = {
'peptide_key':
self.__generate_length_dependent_key(command_line_args),
'template_key':
r.Key(r.WholeRange())
}
elif self.operation == g.MacrocycleGenerator.STRING:
operation_parameters = {
'template_peptide_key':
self.__generate_length_dependent_key(command_line_args),
'reaction_key':
r.Key(r.WholeRange())
}
elif self.operation == g.InterMolecularReactionGenerator.STRING:
operation_parameters = {
'sidechain_key': r.Key(r.WholeRange()),
'monomer_key': r.Key(r.WholeRange()),
'template_key': r.Key(r.WholeRange())
}
elif self.operation == g.IntraMolecularReactionGenerator.STRING:
operation_parameters = {'template_key': r.Key(r.WholeRange())}
elif self.operation == g.ConformerGenerator.STRING:
operation_parameters = {
'macrocycle_key':
self.__generate_length_dependent_key(command_line_args)
}
operation_parameters.update(command_line_args)
return operation_parameters
def test_key_batched_data_chunk(total_num_data, total_num_jobs, job_num, static_range, expected_start, expected_end, expected_result):
data_chunk = ranges.Key(ranges.BatchedDataChunk(total_num_data, total_num_jobs, job_num))
assert(data_chunk.start == expected_start)
assert(data_chunk.end == expected_end)
assert((data_chunk in static_range) == expected_result)
assert((static_range in data_chunk) == expected_result)
def test_key_discrete_data_chunk(test_min, test_max, static_range, expected):
int_avg = int((test_min + test_max) / 2)
data_chunk = ranges.Key(ranges.DiscreteDataChunk([test_min, int_avg, test_max]))
assert((data_chunk in static_range) == expected)
assert(int_avg in data_chunk)
def test_key_whole_range(static_range):
whole_range = ranges.Key(ranges.WholeRange())
assert(static_range in whole_range)
assert(whole_range in static_range)
def test_key_range(test_min, test_max, static_range, expected):
dynamic_range = ranges.Key(ranges.Range(test_min, test_max))
assert((dynamic_range in static_range) == expected)
assert((static_range in dynamic_range) == expected)
