Substring_finder/main.py at main · lastmart/Substring_finder · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
from report import Reporter
import substring_finder
import os
import re

if __name__ == '__main__':
    substring_finders = [
        substring_finder.brute_force,
        substring_finder.KMP_algorithm,
        substring_finder.z_function_finder,
        substring_finder.BMH_algorithm,
        substring_finder.AC_algorithm,
    ]
    comparing_parameters = [
        (
            r"BigDataWithoutRepeating.txt",
            "ними",
            "Big data without repeating (len(substring) == 4)",
        ),
        (
            r"BigDataWithoutRepeating.txt",
            "Сонский",
            "Big data without repeating (len(substring) == 7)",
        ),
        (
            r"BigDataWithoutRepeating.txt",
            "Мы предлагаем вам",
            "Big data without repeating (len(substring) == 17)",
        ),
        (
            r"BigDataWithoutRepeating.txt",
            "%D0%9A%D0%BE%D0%BB%D1%8C%D1%86%D0%B0",
            "Big data without repeating (len(substring) == 36)",
        ),
        (
            r"SmallDataWithoutRepeating.txt",
            "них",
            "Small data without repeating (len(substring) == 3)",
        ),
        (
            r"SmallDataWithoutRepeating.txt",
            "Mon Dieu",
            "Small data without repeating (len(substring) == 8)",
        ),
        (
            r"SmallDataWithoutRepeating.txt",
            "Доктор посмотрел",
            "Small data without repeating (len(substring) == 16)",
        ),
        (
            r"SmallDataWithoutRepeating.txt",
            "Зала ресторации превратилась",
            "Small data without repeating (len(substring) == 28)",
        ),
        (
            r"BeginningAndEndingOfSubstringRepeatManyTimes.txt",
            "the same part finish the same part",
            "Beginning and ending of substring repeat many times",
        ),
        (
            r"BeginningOfSubstringRepeatManyTimes.txt",
            "Hello my dear Sun",
            "Beginning of substring repeat many times",
        ),
        (
            r"SubstringContainsFewDifferentLetters.txt",
            "aaaaaaaaff",
            "Substring contains few different letters",
        ),
    ]
    texts_path = os.path.dirname(__file__) + "\\texts\\"
    comparing_parameters = list(map(lambda x: (texts_path + x[0], x[1], x[2]),
                                    comparing_parameters))
    groups_patterns = [re.compile(r'(Big data without repeating)(.*)'),
                       re.compile(r'(Small data without repeating)(.*)'),
                       re.compile(
                           r'(.*\brepeat\b.*)|(Substring contains few different letters)')]
    reporter = Reporter(substring_finders, comparing_parameters, 51, groups_patterns)
    reporter.generate_statistics()