import nltk
import sys
import random
import os

def main():
    try:
        num_pseudonyms = int(sys.argv[1]) if len(sys.argv) == 2 else 100
    except ValueError:
        print("The argument must be an integer.")
        return

    # Load the corpora
    nltk.download('wordnet')
    nltk.download('averaged_perceptron_tagger')
    nltk.download('universal_tagset')

    # Get all the adjectives and nouns
    adjectives = set()
    nouns = set()
    for synset in nltk.corpus.wordnet.all_synsets():
        for lemma in synset.lemmas():
            if lemma.name().isalpha():
                if synset.pos() == 'a':
                    adjectives.add(lemma.name())
                elif synset.pos() == 'n':
                    nouns.add(lemma.name())
    
    # Create the output directory if it doesn't exist
    os.makedirs('out', exist_ok=True)

    # Write the pseudonyms to a file
    with open('out/pseudonyms.txt', 'w+') as file:
        for _ in range(num_pseudonyms):
            adjective = list(adjectives)[random.randint(0, len(adjectives) - 1)].capitalize()
            noun = list(nouns)[random.randint(0, len(nouns) - 1)].capitalize()
            number = random.randint(1, 999)
            pseudonym = f'{adjective}-{noun}-{number}'
            file.write(pseudonym + '\n')

if __name__ == '__main__':
    main()