in parquet_flask/io_logic/sanitize_record.py [0:0]
def start(self, json_file_path):
if not FileUtils.file_exist(json_file_path):
raise ValueError('json file does not exist: {}'.format(json_file_path))
json_obj = FileUtils.read_json(json_file_path)
is_valid, json_errors = GeneralUtils.is_json_valid(json_obj, basic_schema)
if not is_valid:
raise ValueError(f'input file has invalid high level schema: {json_file_path}. errors; {json_errors}')
LOGGER.warning('disabling validation of individual observation record. it is taking a long time')
is_valid, json_errors = self.__validate_json(json_obj)
if not is_valid:
raise ValueError(f'json has some error. Not validating: {json_errors}')
for each in json_obj[CDMSConstants.observations_key]:
self.__sanitize_record(each)
return json_obj