import json
import scraper
import re

def flatten(xss):
    return [x for xs in xss for x in xs]

def readUtf8(files: list[str]) -> list[str]:
    data = []
    for file in files:
         f = open(file, "rb")
         b = f.read()
         f.close()
         data.append(str(b, "utf-8"))

    return data

keywords = re.compile(r'(?i)(?:(edge|spank|dildo|pee|special\s*spank|bondage\s*dildo|clothespins)\s*x?(\d+)?)x?|(?:x?(\d+)?x?\s*(edge|spank|dildo|pee|special\s*spank|bondage\s*dildo|clothespins))')

tripleHour = re.compile(r'(?i)t{1,}r{1,}i{1,}p{1,}l{1,}e{1,} keyword')

def fit_into_numbers(x: int, numbers: list[int]):
    window_size = 2
    numbers.reverse()
    for i in range(len(numbers) - window_size + 1):
        items = numbers[i: i + window_size]
        if x >= items[1] and x < items[0]:
            return items[1]

keywordValues = {
    0: {
        "edge": 2,
        "spank": 10,
        "dildo": 5,
        "-keywords": 3,
    },
    100: {
        "edge": 4,
        "spank": 10,
        "dildo": 5,
        "-keywords": 3,
    },
    250: {
        "edge": 4,
        "spank": 20,
        "dildo": 5,
        "-keywords": 3,
    },
    500: {
        "edge": 8,
        "spank": 20,
        "dildo": 10,
        "-keywords": 3,
    },
    750: {
        "edge": 8,
        "spank": 20,
        "dildo": 10,
        "-keywords": 6,
    },
    1000: {
        "edge": 8,
        "spank": 20,
        "dildo": 10,
        "-keywords": 6,
    },
    1250: {
        "edge": 8,
        "spank": 20,
        "dildo": 10,
        "-keywords": 6,
    },
    1500: {
        "edge": 8,
        "spank": 20,
        "dildo": 10,
        "-keywords": 6,
    },
    2000: {
        "edge": 8,
        "spank": 20,
        "dildo": 10,
        "-keywords": 6,
    },
    2500: {
        "edge": 8,
        "spank": 20,
        "dildo": 10,
        "pee": 1,
        "-keywords": 6,
    },
    3000: {
        "edge": 16,
        "spank": 40,
        "dildo": 20,
        "pee": 2,
        "-keywords": 6,
    },
    3500: {
        "edge": 16,
        "spank": 40,
        "dildo": 20,
        "pee": 2,
        "special spank": 10,
        "-keywords": 6,
    },
    4000: {
        "edge": 16,
        "spank": 40,
        "dildo": 20,
        "pee": 2,
        "special spank": 10,
        "bondage dildo": 10,
        "-keywords": 6,
    },
    4500: {
        "edge": 16,
        "spank": 40,
        "dildo": 20,
        "pee": 2,
        "special spank": 10,
        "bondage dildo": 10,
        "-keywords": 6,
    },
    5000: {
        "edge": 16,
        "spank": 40,
        "dildo": 20,
        "pee": 2,
        "special spank": 10,
        "bondage dildo": 10,
        "-keywords": 6,
    },
    6000: {
        "edge": 16,
        "spank": 40,
        "dildo": 20,
        "pee": 2,
        "special spank": 10,
        "bondage dildo": 10,
        "clothespins": 5,
        "-keywords": 6,
    },
    7000: {
        "edge": 16,
        "spank": 40,
        "dildo": 20,
        "pee": 2,
        "special spank": 10,
        "bondage dildo": 10,
        "clothespins": 5,
        "-keywords": 8,
    },
    8000: {
        "edge": 16,
        "spank": 40,
        "dildo": 20,
        "pee": 2,
        "special spank": 10,
        "bondage dildo": 10,
        "clothespins": 5,
        "-keywords": 6,
    },
    9000: {
        "edge": 32,
        "spank": 80,
        "dildo": 40,
        "pee": 4,
        "special spank": 20,
        "bondage dildo": 20,
        "clothespins": 10,
        "-keywords": 6,
    },
    10000: {
        "edge": 32,
        "spank": 80,
        "dildo": 40,
        "pee": 4,
        "special spank": 20,
        "bondage dildo": 20,
        "clothespins": 10,
        "-keywords": 6,
    },
}

if __name__ == "__main__":
    pages = readUtf8([str(x) + ".html" for x in range(477, 478)])
    posts = flatten([scraper.get_posts(x) for x in pages])
    first = min([post.post_number for post in posts])
    last = max([post.post_number for post in posts])
    print(f"Going from post #{first} to #{last}")

    total = {
        "edge": 0,
        "spank": 0,
        "dildo": 0,
        "pee": 0,
        "special spank": 0,
        "bondage dildo": 0,
        "clothespins": 0,
    }

    # tkh = [post for post in posts if post.post_number == 7179][0]
    # print(tkh)
    # print(tkh.author == "Snoek")
    # print()
    triple_hours = [post.time for post in posts if post.author == "Snoek" and len(tripleHour.findall(post.content)) > 0]
    print(triple_hours)

    for post in posts:
        rules = keywordValues[fit_into_numbers(post.post_number, list(keywordValues.keys()))]
        # print("Current rules " + str(rules))
        inpost = {
            "edge": 0,
            "spank": 0,
            "dildo": 0,
            "pee": 0,
            "special spank": 0,
            "bondage dildo": 0,
            "clothespins": 0,
        }
        for match in keywords.finditer(post.content):
            groups = match.groups()
            word = [group for group in groups if group is not None and not group.isdigit()][0]
            count = [group for group in groups if group is not None and group.isdigit()]
            if word.lower() not in inpost:
                raise "Unknown word " + word.lower()
            if len(count) > 1:
                # print(f"Adding {count} to '{word.lower()}'")
                inpost[word.lower()] += count * rules[word.lower()]
            else:
                # print(f"Adding 1 to '{word.lower()}'")
                inpost[word.lower()] += 1 * rules[word.lower()]

        keywordsUsed = sum(inpost.values())

        if len([x for x in triple_hours if (post.time - x).total_seconds() > 0]) > 0:
            for key in inpost.keys():
                inpost[key] *= 3

        inpost["edge"] += rules["edge"] * 2

        for key in inpost.keys():
            total[key] += inpost[key]

    print(total)