import difflib
import os
import re
import numpy as np

from Generator.LogGenerator import LogGenerator
from Processor.StreamingLogCluster import StreamingLogCluster
from Tester.RegressionMetricsCalculator import RegressionMetricsCalculator

if __name__ == '__main__':
    gen = LogGenerator()

    MODEL_PATH = '../Resources/model'
    DB_FILE = "../Resources/logs.db"

    if os.path.exists(DB_FILE):
        os.remove(DB_FILE)

    print("--- ЗАПУСК: Delta Mode ---")
    clusterer = StreamingLogCluster(MODEL_PATH, db_path=DB_FILE)

    sm = 0

    for j in range(1000):

        data = []

        count = 500

        sm += count

        # Генерируем 10 примеров
        for i in range(count):
            # 1. Получаем объект Term
            term = gen.generate()

            # 3. Используем данные (например, сохраняем в JSON для обучения)
            template = term.structure().text
            log = term.render(0.5)

            measure = clusterer.process_time_measure(log.text)

            data.append(measure)

        arr = np.array(data)
        means = arr.mean(axis=0) * 1000

        print(f"{sm}|{"|".join(map(str,means))}")