wordcount

gistfile1.txt

import sys
import itertools
from collections import Counter
from operator import itemgetter


def file_to_string_list(filename) -> list:
    try:
        with open(filename, 'r') as f:
            some_strs = [x.split() for x in f.readlines()]

        # opções pra devolver uma flat list de some_strs (nested list) acima
        # https://stackoverflow.com/questions/952914/how-to-make-a-flat-list-out-of-list-of-lists

        # from django.contrib.admin.utils import flatten
        # flatten(some_strs)

        # x = reduce(lambda x, y: x+y, some_strs)
        # reduce(lambda x, y: x + y, [1, 2, 3, 4, 5]) calcula ((((1 + 2) + 3) + 4) + 5)

        # O mesmo que a + b, para sequências a e b
        # import operator
        # x = reduce(operator.concat, some_strs)

        # Usando o itertools é o mais rápido

        return list(itertools.chain.from_iterable(some_strs))

    except FileNotFoundError as e:
        raise FileNotFoundError("Arquivo nao encontrado") from e


def print_words(filename):

    x = file_to_string_list(filename)
    items = sorted(Counter(c.lower() for c in x).items(), key=itemgetter(0))

    for letter, count in items:
        print(f"letra: '{letter}' ocorrencia: {count}x")


def print_top(filename):
    x = file_to_string_list(filename)
    items = Counter(c.lower() for c in x).most_common()[:20]

    for index, (letter, count) in enumerate(items, start=1):
        print(f"{index}º letra: '{letter}' ocorrencia: {count}x")

# A função abaixo chama print_words() ou print_top() de acordo com os
# parêtros do programa.


def main():
    if len(sys.argv) != 3:
        print('Utilização: ./13_wordcount.py {--count | --topcount} file')
        sys.exit(1)

    option = sys.argv[1]
    filename = sys.argv[2]
    if option == '--count':
        print_words(filename)
    elif option == '--topcount':
        print_top(filename)
    else:
        print('opção desconhecida: ' + option)
        sys.exit(1)


if __name__ == '__main__':
    main()