import argparse import os from utils import read_local import preprocessing_funcs import ac_funcs def parse_arguments(): parser = argparse.ArgumentParser(description="Smart Chunking Tester") parser.add_argument( "--input_dir", help="Input directory (local path or S3 URI)", default="src/new/" ) return parser.parse_args() def main(): args = parse_arguments() input_dir = args.input_dir for file in os.listdir(input_dir): full_path = os.path.join(input_dir, file) print("--" * 20) print(file) contract_text = read_local(full_path) contract_text = preprocessing_funcs.clean_newlines(contract_text) contract_text = preprocessing_funcs.clean_law_symbols(contract_text) text_dict = preprocessing_funcs.split_text( contract_text ) # return a dictionary with keys - page_num (str), values as the page_text irs_answers = ac_funcs.tin_regex(filename=str(file), text_dict=text_dict) if irs_answers is None: irs_answers = {} irs_answers["PROV_GROUP_TIN"] = "N/A" irs_answers["PROV_TIN_OTHER"] = "N/A" print(irs_answers) if __name__ == "__main__": main()