import re2 as re
import csv
import time

def format_surnames(surname_file):
    with open(surname_file, 'r', encoding='utf-8') as csvfile:
        reader = csv.reader(csvfile)
        surnames = {row[0].lower() for row in reader}
    return surnames 

def find_matching_lines(input_file, output_file, female_surname_file, male_surname_file):
    start_time = time.time()  

    female_surnames = format_surnames(female_surname_file)
    male_surnames = format_surnames(male_surname_file)
    all_surnames = female_surnames.union(male_surnames)

    pattern = re.compile("|".join(all_surnames).lower(), setting)

    with open(input_file, 'r', encoding='utf-8') as infile, \
         open(output_file, 'w', encoding='utf-8') as outfile:
        for line in infile:
            if pattern.search(line):
                outfile.write(line)

    end_time = time.time()
    elapsed_time = end_time - start_time
    print(f"Czas wykonania programu: {elapsed_time} sekundy")

setting = re.Options()
setting.max_mem = (1 << 30) * 3
find_matching_lines('polish_wiki_excerpt.in', 'output.txt', 'nazwiska_kobiet.csv', 'nazwiska_męskie.csv')