def clean_wrapper(name_string, dict_list=regex_dicts): print name_string out = psCleanup.rem_diacritics(name_string) out = psCleanup.stdize_case(out) out = psCleanup.master_clean_regex([out], dict_list) out = out[0].strip() return(out)
def name_clean_wrapper(name_list, clean_regex=name_address_regex, legal_regex=legal_regex): name_string = psCleanup.decoder(name_list) name_string = psCleanup.remove_diacritics(name_string) name_string = psCleanup.stdize_case(name_string) name_string = psCleanup.master_clean_regex(name_string, clean_regex) names_ids = psCleanup.get_legal_ids(name_string, legal_regex) return names_ids
def clean_wrapper(name_string, dict_list=regex_dicts): print name_string out = psCleanup.rem_diacritics(name_string) out = psCleanup.stdize_case(out) out = psCleanup.master_clean_regex([out], dict_list) out = out[0].strip() return (out)
def address_clean_wrapper(address_list, clean_regex=name_address_regex): address_string = psCleanup.decoder(address_list) address_string = psCleanup.remove_diacritics(address_string) address_string = psCleanup.stdize_case(address_string) address_string = psCleanup.master_clean_regex(address_string, clean_regex) return address_string
def clean_wrapper(name_dict, dict_list=regex_dicts): name_string = psCleanup.decoder(name_dict["person_name"]) out = psCleanup.rem_diacritics(name_string) out = psCleanup.stdize_case(out) out = psCleanup.master_clean_regex([out], dict_list) out = out[0].strip() name_dict["person_name"] = psCleanup.encoder(out) return name_dict
def clean_wrapper(name_dict, dict_list=regex_dicts): name_string = psCleanup.decoder(name_dict['person_name']) out = psCleanup.rem_diacritics(name_string) out = psCleanup.stdize_case(out) out = psCleanup.master_clean_regex([out], dict_list) out = out[0].strip() name_dict['person_name'] = psCleanup.encoder(out) return (name_dict)