import re


words = []

with open("censored.txt", encoding="UTF-8") as f:
    for line in f:
        words.append(line.strip())


WORDS = re.compile(r"\w+")
PATTERN = re.compile(
    f"^({"|".join(words + [word + "s" for word in words])})$",
    re.IGNORECASE,
)
URL_PATTERN = re.compile(r"https?://[^\s]+", re.IGNORECASE)
INVITES_PATTERN = re.compile(r"(discord)?.gg/[^\s]+", re.IGNORECASE)


def censor(message: str, is_gif_allowed: bool = False) -> str:
    """Returns the first censored word or pattern found.

    Args:
        message (str): The message to moderate.
        is_gif_allowed (bool, optional): If GIFs are allowed. Defaults to False.

    Returns:
        str | None: The blocked pattern found as it was found.
    """

    for word in WORDS.finditer(message):
        word = message[word.start() : word.end()]
        if PATTERN.match(word):
            return word

    for match in URL_PATTERN.finditer(message):
        string = message[match.start() : match.end()]

        if is_gif_allowed and string.startswith("https://tenor.com/view/"):
            continue

        return string

    match = next(INVITES_PATTERN.finditer(message), None)

    if match is not None:
        return message[match.start() : match.end()]

    return None