import re


def find_regexp(regexp, filename="slovnik.txt"):
    with open(filename, "r") as my_file:
        for line in my_file:
            if re.search(regexp, line):
                strip_line = line.rstrip()
                print(strip_line, end=", ")
    print("\n")


# Vypsat vsechny retezce, ktere obsahuji podretezec 'oo'
find_regexp(r'oo')
# Vypsat vsechny retezce, ktere zacinaji na 'e' a konci na 'le'
# Vypise pouze erteple, elle, emile,
find_regexp(r'^e.*le$')
# Vypsat vsechny retezce, ktere obsahuji 'a', 'e', 'i', 'o', 'u' v tomto
# poradi (ale ne nutne za sebou, napr. akademickou)
find_regexp(r'a.*e.*i.*o.*u')
# Vypsat vsechny retezce, ktere obsahuji podretezec delky 4
# tvoreny z pismen "rst" (napr. bratrstvi)
find_regexp(r'[rst]{4}')
# Vypsat vsechny retezce, dve 'u' vzdalena od sebe 8 pozic (napr. 'uhlovodiku')
find_regexp(r'u.{8}u')
# Obsahuji pismeno 'u' na druhe i predposledni pozici (napr. 'luxus')
find_regexp(r'^.u.*u.$')
# Kromě prvniho a posledniho pismene obsahuji pouze samohlasky a maji presne
# 5 pismen (napr. 'foyer')
find_regexp(r'^.[aeiouy]{3}.$')


def load_data():
    with open('sherlock.txt', 'r') as file:
        dct = {}

        # load data do dictionary
        for line in file:
            # clean text
            clear_line = cleanString = re.sub('\W+', ' ', line)

            for word in clear_line.split(' '):
                if len(word) > 0:
                    dct[word] = dct.get(word, 0) + 1

    return dct


def top_n(dct, n):
    i = 0
    result = reversed(sorted(dct, key=dct.get))  # creates iterator
    for i in range(n):
        el = next(result)  # next element form iterator
        print(str(i + 1) + ".", "\"" + el + "\"", "has", dct[el],
              "occurrences")


def word_average(dct):
    sum_key_length = 0
    for key, value in dct.items():
        sum_key_length += (len(key) * value)

    print("Average length of word is", sum_key_length / sum(dct.values()))


d = load_data()
top_n(d, 10)
print()
word_average(d)