structure_assignment/scripts/process.py

import argparse

from structure_assignment.pipeline import Runner

classla_directory = '../resources/classla'
wani_file_name = '../resources/wani.py'  # TODO: remove once luscenje_struktur incorporates wani in package

if (__name__ == '__main__'):

    arg_parser = argparse.ArgumentParser(description='Run part or all of structure pipeline.')
    arg_parser.add_argument('-mode', type=str, help='Mode')
    arg_parser.add_argument('-infile', type=str, help='Input file')
    arg_parser.add_argument('-outfile', type=str, help='Output file')
    arg_parser.add_argument('-instructs', type=str, help='Input structure file')
    arg_parser.add_argument('-outstructs', type=str, help='Output structure file')
    arguments = arg_parser.parse_args()

    mode = arguments.mode
    input_file_name = arguments.infile
    output_file_name = arguments.outfile
    input_structure_file_name = arguments.instructs
    output_structure_file_name = arguments.outstructs

    nlp_needed = mode in {'strings_to_parse', 'strings_to_dictionary', 'all'}
    runner = Runner(nlp_needed, classla_directory, wani_file_name)
    if (mode == 'strings_to_parse'):
        runner.strings_to_parse(input_file_name, output_file_name)
    elif (mode == 'strings_to_dictionary'):
        runner.strings_to_dictionary(input_file_name, output_file_name, input_structure_file_name, output_structure_file_name)
    elif (mode == 'parse_to_dictionary'):
        runner.parse_to_dictionary(input_file_name, output_file_name, input_structure_file_name, output_structure_file_name)
    elif (mode == 'validate_structures'):
        runner.validate_structures(input_file_name)
    elif (mode == 'validate_dictionary'):
        runner.validate_dictionary(input_file_name)
    elif (mode == 'all'):
        runner.run_all(input_file_name, output_file_name, input_structure_file_name, output_structure_file_name)