def update_header_list(self, dataset_id, header_list):
if isinstance(header_list, list):
header_list = st.make_list_to_str(header_list)
if isinstance(header_list, str):
header_list = header_list.split(',')
header_list_tmp = dm.DataManager.get_dataset_table_headers(
dm.DataManager, dataset_id=dataset_id, local=False)
if not st.check_list_identical(header_list, header_list_tmp):
if header_list[0] == '' and len(header_list) == 1:
header_list = header_list_tmp
elif not all(x in header_list for x in header_list_tmp):
[
header_list.append(val) for val in header_list_tmp
if not val in header_list
]
header_list = st.make_list_to_str(header_list)
return header_list
def get_all_suitable_cleansers_by_header(self, user_id):
suitable_cleaners = []
cleansers = self.get_all_cleansers(DataCleanser)
datasets = dm.DataManager.get_all_datasets_only_id(
dm.DataManager, user_id)
for cleanser in cleansers:
for dataset_id in datasets:
dataset_header = dm.DataManager.get_dataset_table_headers(
dm.DataManager, dataset_id=dataset_id, local=False)
if cleanser.get_header_list() == st.make_list_to_str(
dataset_header):
suitable_cleaners.append(cleanser)
elif all(x in cleanser.get_header_list()
for x in dataset_header):
suitable_cleaners.append(cleanser)
return list(set(suitable_cleaners))
