cjvt-srl-tagging/tools/main.py

from parser.parser import Parser
import os
from os.path import join
import re
import sys
import cProfile


def main():
    # make sure you sanitize every input into unicode

    SSJ500K_2_1 = 27829  # number of sentences
    par = Parser()

    print("parsing ssj")
    ssj_file = "../data/ssj500k-sl.sample.xml"
    ssj_dict = par.parse_tei(ssj_file)
    # assert (len(ssj_dict) == 27829), "Parsed wrong number of sentences."
    print("end parsing ssj")

    print("parsing kres")
    # kres_file = "../data/kres_example/F0019343.xml.parsed.xml"
    kres_dir = "../data/kres_example/"
    for kres_file in os.listdir(kres_dir):

        # since there will be processed files in the same folder
        if re.match("^F.+\.xml\.parsed\.xml$", kres_file) is None:
            continue

        print("Processing file: " + kres_file)
        out_file = ""
        res_dict = par.parse_tei(join(kres_dir, kres_file))
        for _, sentence in res_dict.items():
            out_file += par.to_conll_2009_SRL(sentence)
        with open(join(kres_dir, kres_file + ".tsv"), "wb+") as fp:
            fp.write(out_file.encode("utf-8"))
            fp.close()
    print("end parsing kres")


if __name__ == "__main__":
    cProfile.run("main()", sort="tottime")
    # main()