TheAlgorithms-Python

1
import os
2
from string import ascii_letters
3

4
LETTERS_AND_SPACE = ascii_letters + " \t\n"
5

6

7
def load_dictionary() -> dict[str, None]:
8
    path = os.path.split(os.path.realpath(__file__))
9
    english_words: dict[str, None] = {}
10
    with open(path[0] + "/dictionary.txt") as dictionary_file:
11
        for word in dictionary_file.read().split("\n"):
12
            english_words[word] = None
13
    return english_words
14

15

16
ENGLISH_WORDS = load_dictionary()
17

18

19
def get_english_count(message: str) -> float:
20
    message = message.upper()
21
    message = remove_non_letters(message)
22
    possible_words = message.split()
23
    matches = len([word for word in possible_words if word in ENGLISH_WORDS])
24
    return float(matches) / len(possible_words)
25

26

27
def remove_non_letters(message: str) -> str:
28
    """
29
    >>> remove_non_letters("Hi! how are you?")
30
    'Hi how are you'
31
    >>> remove_non_letters("P^y%t)h@o*n")
32
    'Python'
33
    >>> remove_non_letters("1+1=2")
34
    ''
35
    >>> remove_non_letters("www.google.com/")
36
    'wwwgooglecom'
37
    >>> remove_non_letters("")
38
    ''
39
    """
40
    return "".join(symbol for symbol in message if symbol in LETTERS_AND_SPACE)
41

42

43
def is_english(
44
    message: str, word_percentage: int = 20, letter_percentage: int = 85
45
) -> bool:
46
    """
47
    >>> is_english('Hello World')
48
    True
49
    >>> is_english('llold HorWd')
50
    False
51
    """
52
    words_match = get_english_count(message) * 100 >= word_percentage
53
    num_letters = len(remove_non_letters(message))
54
    message_letters_percentage = (float(num_letters) / len(message)) * 100
55
    letters_match = message_letters_percentage >= letter_percentage
56
    return words_match and letters_match
57

58

59
if __name__ == "__main__":
60
    import doctest
61

62
    doctest.testmod()
63