import tkinter as tk
from tkinter import filedialog
import re
from typing import Dict
import sys

# Создаем корневое окно
root = tk.Tk()
root.title("Decoder")
# root.geometry('600x500')
# root.resizable(width=False, height=False)

text1 = tk.Text(root)
text1.pack(side=tk.TOP, fill=tk.BOTH, expand=True)

# Создаем полосу прокрутки
scrollbar = tk.Scrollbar(root)
scrollbar.pack(side=tk.RIGHT, fill=tk.Y)

# Привязываем полосу прокрутки к текстовому виджету
text1.config(yscrollcommand=scrollbar.set)
scrollbar.config(command=text1.yview)


def create_symbols(s: str) -> list:
    s = s.lower()
    d = {}
    tot = 0
    for c in s:
        if c.isalpha() and c not in "quote":
            d[c] = d.get(c, 0) + 1
            tot += 1

    for k in d:
        d[k] /= tot * 0.01

    si = list(d.items())
    si.sort(key=lambda x: -x[1])

    return si


def check_word(word):
    return ''.join(i for i in word if i.isalpha())


def match_word(match: str, word: str) -> bool:
    return all(
        (match[i] == match[j]) == (word[i] == word[j]) for i in range(len(word) - 1) for j in range(i, len(word)))


def count_words(text: str) -> tuple:
    words = [check_word(w) for w in text.lower().split()]
    word_dict = {}
    tot = 0
    for word in words:
        words_same_size = word_dict.setdefault(len(word), {})
        words_same_size[word] = words_same_size.get(word, 0) + 1
        tot += 1

        word_dict[len(word)] = words_same_size

    for k in word_dict:
        for j in word_dict[k]:
            word_dict[k][j] /= tot * 0.01

    for k in word_dict:
        si = list(word_dict[k].items())
        si.sort(key=lambda x: -x[1])
        word_dict[k] = si

    return word_dict, set(words)


def find_words(words: list, reg: str) -> list:
    return [w for w in words if re.match(reg, w)]


def check(word: str, key: Dict) -> bool:
    return any(key[k] is not None and k in word for k in key)


def get_keys(key: Dict) -> str:
    return ''.join(c for c in key if key[c] is None)


def get_chars(key: Dict):
    alph = 'абвгдеёжзийклмнопрстуфчцчшщъыьэюяңөү'
    return ''.join((c for c in alph if c not in key.values()))


def create_pattern_signs(word, key, counted_encoding_chars):
    reg = ''
    for s in word:
        if s in key.values():
            reg += list(key.keys())[list(key.values()).index(s)]
        elif s in 'нкы':
            reg += f'[{"".join(c[0] for c in counted_encoding_chars[1:4])}]'
        else:
            reg += f'[{get_keys(key)}]'
    return reg + '$'


def my_func():
    file_path = filedialog.askopenfilename(
        filetypes=[("Text Files", "*.txt"), ("All Files", "*.*")]
    )
    if file_path:
        with open(file_path, "r", encoding='utf-8') as file:
            content = file.read()
            # Добавляем содержимое файла в текстовый виджет
            text1.delete("1.0", tk.END)
            text1.insert(tk.END, content)
    encoded_text = open(file_path, 'r', encoding='UTF-8').read()
    sample_text = open('D:/Codes/hwPy/teory/Manas-eposu-2010-S-Karalaev.txt', 'r', encoding='UTF-8').read().replace(
        'www.el-sozduk.kg', '')

    counted_chars = create_symbols(sample_text)
    counted_encoding_chars = create_symbols(encoded_text)

    _, encoded_words = count_words(encoded_text)
    _, sample_words = count_words(sample_text)

    # инициализация словаря ключей
    key = {char[0]: None for char in counted_encoding_chars}
    key[counted_encoding_chars[0][0]] = 'а'

    counted_encoding_chars_dict = dict(counted_encoding_chars)
    counted_chars_dict = dict(counted_chars)

    # обновление словаря ключей на основе обязательных слов
    must_words = ["каныкей", 'деп', 'бейбак']
    for word in must_words:
        pattern = create_pattern_signs(word, key, counted_encoding_chars)
        matches = find_words(encoded_words, pattern)
        if len(matches) == 1:
            for i, char in enumerate(matches[0]):
                if key[char] is None:
                    key[char] = word[i]

    # обновление словаря ключей на основе анализа закодированного текста
    while None in key.values():
        examples = []
        for word in encoded_words:
            if not check(word, key):
                continue
            pattern = ''.join([f'[{get_chars(key)}]' if key.get(s) is None else key[s] for s in word]) + '$'
            matches = [match for match in (find_words(sample_words, pattern)) if match_word(match, word)]
            matches = [match for match in matches if any([s not in key.values() for s in match])]
            if len(matches) == 1:
                err = sum(
                    [abs(counted_encoding_chars_dict[word[i]] * 1.0 / counted_chars_dict[matches[0][i]] - 1) for i in
                     range(len(matches[0])) if key[word[i]] is None]) / len(word)
                examples.append((word, matches[0], err))

        if not examples:
            break
        examples.sort(key=lambda x: x[2])
        for i, char in enumerate(examples[0][0]):
            if key[char] is None and examples[0][1][i] not in key.values():
                key[char] = examples[0][1][i]

    text = ''
    for w in encoded_text:
        w = w.lower()
        if w.isalpha():
            text += key[w] if key.get(w, None) is not None else 'X'
        else:
            text += w
    output_text.insert('end', f'{text}')


def display_func():
    output = tk.Text(root, height=40, width=80)
    output.pack()
    my_func(output)

    # перенаправляем стандартный вывод в текстовый виджет
    sys.stdout = output

    # вызываем функцию my_func
    my_func()

    # возвращаем стандартный вывод на место
    sys.stdout = sys.__stdout__

# текстовое поле для вывода
output_text = tk.Text(root, height=20, width=80)
output_text.pack()

# добавляем кнопку для дешифровки
decrypt_button = tk.Button(root, text="Choose your file", command=my_func)
decrypt_button.pack(pady=10)

# Запускаем главный цикл окна
root.mainloop()