conjurer/conjurer_musician/conjurer_musician.py

"""Musician - the Discord music player service.

Serves the music library index and keyword search the bot uses for Discord
playback (/mp3, /update_mp3, /get_music) plus the file-share endpoints.

Radio playlist management and the radio-log tailer moved to
conjurer_betoniarka/betoniarka.py, which runs INSIDE the radio container as
the same user as Liquidsoap - the musician no longer writes any radio files,
so the old root-owned-network-share permission mess is gone.
"""

import json
import logging
import os
import random
import re
import threading
import time
from datetime import datetime
from logging import handlers
from pathlib import Path
from typing import List

from flask import Flask, abort, jsonify, request
from waitress import serve

import media_search_functions


def _env(name: str, default: str) -> str:
    return os.getenv(name, default)


def _env_path(name: str, default: str) -> Path:
    value = os.getenv(name, default)
    return Path(value).expanduser().resolve()


API_KEY = os.getenv("CONJURER_API_KEY")
HOST_ADDRESS = _env("CONJURER_MUSICIAN_HOST", "0.0.0.0")
PORT_ADDRESS = int(_env("CONJURER_MUSICIAN_PORT", "5000"))

BASE_DIR = Path(
    os.getenv("CONJURER_MUSICIAN_BASE", str(Path(__file__).resolve().parent))
)
LOGFILE = _env_path(
    "CONJURER_MUSICIAN_LOG", str(BASE_DIR / "discord_mus_service.log")
)
LOGSTORE = _env_path("CONJURER_LOGSTORE", str(BASE_DIR / "logs"))
MUSIC_FOLDER = _env_path(
    "CONJURER_MUSIC_FOLDER", str(BASE_DIR / "music")
)

ENCODING = _env("CONJURER_ENCODING", "utf-8")
SEPARATOR_FILE_PATH = os.sep

random.seed()
music_file_list: List[str] = []


def _authorize_request() -> None:
    if API_KEY and request.headers.get("X-Conjurer-Api-Key") != API_KEY:
        abort(401)


def rescan():
    """Refresh the in-memory library index used by /mp3 and /get_music.

    Radio playlist files are NOT written here anymore - that is the
    betoniarka's job, colocated with Liquidsoap.
    """
    logger = logging.getLogger("conjurer_musician")
    logger.info("Rescan triggered")

    music_file_list.clear()

    for mp3_item in MUSIC_FOLDER.glob("**/*.mp3"):
        temp_music_file = mp3_item.as_posix()
        if os.name == "nt":
            temp_music_file = temp_music_file.replace("/", "\\")
        music_file_list.append(temp_music_file)


def thread_rescan():
    """
    The `thread_rescan` function periodically triggers a rescan operation after a specified time
    interval.
    """
    logger = logging.getLogger("conjurer_musician")
    logger.info("Starting filesystemupdater")
    while True:
        time.sleep(60 * 60 * 24)
        logger.info("Rescan triggered")
        rescan()


app = Flask(__name__)
# AutoIndex(app, browse_root="/")


# TODO: Odpalić wyszukiwarki w wątkach i dopiero po wszystkim zsumować wyszukiwanie.
def wyszukaj(word_list, how_many, _logger=None, return_to_bot=True):
    """
    Searches for music files based on a list of keywords and returns a list of matching files.

    Args:
        word_list (list): A list of keywords to search for.
        how_many (int): The maximum number of matching files to return.

    Returns:
        list: A list of matching files, sorted by their search weight.

    """
    if _logger is None:
        fun_logger = logging.getLogger()
    else:
        fun_logger = _logger
    return_list = []
    search_weight = []

    for _ in range(len(music_file_list)):
        search_weight.append((0, ""))

    time_start = datetime.now()
    if int(how_many) > 0:
        skip_start = 2
    else:
        skip_start = 1
    for word in word_list[skip_start:]:
        token_weight = len(word)
        fun_logger.info("Słowo kluczowe: %s", word)
        itr = 0
        for file in music_file_list:
            file = file.split(SEPARATOR_FILE_PATH)

            char_remove = [
                ".",
                "^",
                "$",
                "*",
                "+",
                "?",
                "{",
                "}",
                "[",
                "]",
                "\\",
                "/",
                "|",
                "(",
                ")",
                "!",
                ",",
                "-",
                ":",
                "mp3",
            ]
            all_words = []
            for f_iter in file:
                for char in char_remove:
                    f_iter = remove_characters(f_iter, char)
                tmp = f_iter.split()
                all_words.extend(tmp)
            pingu = 1
            pattern_len = len(all_words)
            if platform == "win32":
                skip = 2
            else:
                skip = 4
            matched_times = 1
            # TODO: To do wątków albo for asynchroniczny
            for itm in all_words[skip:]:
                pingu += 1
                pattern = ".*" + word + ".*"
                if re.match(pattern, itm, re.IGNORECASE):
                    temp_weight = (
                        search_weight[itr][0]
                        + (token_weight + (pingu**1.5) / pattern_len) / matched_times
                    )
                    search_weight[itr] = (
                        temp_weight,
                        music_file_list[itr],
                    )
                    matched_times += 1
            itr += 1

    fun_logger.info(
        "Stworzylem tablice wag zajęło mi to %s", datetime.now() - time_start
    )
    time_start = datetime.now()
    item_to_search = max_weight(search_weight)
    itr = 0
    if item_to_search == 0:
        return []
    not_found = True
    return_list = []
    if int(how_many) <= 0:
        fun_logger.info("Jeden plik do zagrania")
        while not_found:
            if search_weight[itr][0] == item_to_search:
                return_list.append(search_weight[itr])
                break
            itr += 1
    else:
        fun_logger.info("Wiele plików do zagrania")
        search_weight.sort(key=lambda x: x[0], reverse=True)
        return_list.extend(search_weight[: int(how_many)])
    fun_logger.info("Done: %s", return_list)
    return return_list


def max_weight(lista):
    """
    Take a list of weights and return the maximum weight.

    :param lista: It seems like the parameter `lista` is a list of items, possibly representing weights.
    The function name `max_weight` suggests that the function is intended to find the maximum weight
    from the list. However, without more context or information about the problem, it's difficult to say
    for sure what the
    """
    maximum_weight = 0
    for iterator in lista:
        if iterator[0] > maximum_weight:
            maximum_weight = iterator[0]
    return maximum_weight


def remove_characters(string, character):
    """
    The `remove_characters` function removes all occurrences of a specified character from a given
    string.

    :param string: The string parameter is the input string from which characters will be removed
    :param character: The character parameter is the character that you want to remove from the string
    :return: a new string where all occurrences of the specified character have been removed.
    """
    return string.replace(character, "")


@app.route('/get_share_list', methods=['POST'])
def get_share_list():
    _authorize_request()
    data = request.get_json()
    entries = data.get('entries')
    keywords = data.get('keywords')
    # Validate entries
    if not isinstance(entries, int) or not (1 <= entries <= 10):
        return jsonify({'error': '"entries" must be an integer between 1 and 10.'}), 400
    # Validate keywords list
    if not isinstance(keywords, list) or not all(isinstance(k, str) for k in keywords):
        return jsonify({'error': '"keywords" must be a list of strings.'}), 400
    # Call external search
    files = media_search_functions.find_matches(entries, keywords)
    # Return each file path as a JSON list
    return jsonify({'files': files}), 200

@app.route('/get_share_links', methods=['POST'])
def get_share_links():
    _authorize_request()
    data = request.get_json()
    file_paths = data.get('file_paths')
    # Validate file_paths list
    if not isinstance(file_paths, list) or not all(isinstance(p, str) for p in file_paths):
        return jsonify({'error': '"file_paths" must be a list of strings.'}), 400
    # Call external publish
    links = media_search_functions.publish(file_paths)
    # Return list of published links
    return jsonify({'links': links}), 200



@app.route("/mp3", methods=["GET"])
def get_music_list():
    """
    The function `get_music_list` returns a JSON object containing a list of music files.
    :return: A JSON response containing a key "music_file_list" with the value of the variable
    `music_file_list`.
    """
    return jsonify({"music_file_list": music_file_list})


@app.route("/update_mp3", methods=["POST"])
def update_music_list():
    """
    The function `update_music_list` receives a POST request with a JSON payload, logs the received
    item, adds it to a music file list, and returns a success message along with the updated record.
    :return: The function `update_music_list` is returning a tuple containing a JSON response and a
    status code. The JSON response includes keys `isError`, `message`, `statusCode`, and `data`,
    with values indicating the success of the operation and the data that was
    received and added to the `music_file_list`.
    The status code returned is 200, indicating a successful response.
    """
    _authorize_request()
    record = json.loads(request.data)
    app.logger.info(record["item"])
    music_file_list.append(record["item"])
    return_data = (
        jsonify(isError=False, message="Success", statusCode=200, data=record),
        200,
    )
    return return_data


@app.route("/get_music", methods=["POST"])
def look_for_playlist():
    """
    The function `look_for_playlist` receives a POST request with a JSON payload, logs the received
    item, adds it to a music file list, and returns a success message along with the updated record.

    :return: A tuple containing a JSON response and a status code. The JSON response includes keys `isError`,
             `message`, `statusCode`, and `data`, with values indicating the success of the operation and the
             data that was received and added to the `music_file_list`. The status code returned is 200,
             indicating a successful response.
    """
    _authorize_request()
    record = json.loads(request.data)
    app.logger.info(record)
    app.logger.info(record["lista_slow"])
    app.logger.info(record["UUID"])
    app.logger.info(record["dlugosc_plejlisty"])
    return_data = wyszukaj(
        record["lista_slow"], record["dlugosc_plejlisty"], app.logger, True
    )

    return_data = (
        jsonify(isError=False, message="Success", statusCode=200, data=return_data),
        200,
    )
    return return_data


def flask_debug():
    """
    The `flask_debug` function starts a Flask application in debug mode without using the reloader.
    Do not use for production for fucks sake.
    """
    # trunk-ignore(bandit/B201)
    app.run(debug=True, use_reloader=False, host=HOST_ADDRESS, port=PORT_ADDRESS)


def waitress_run():
    """
    The `waitress_run` function serves the `app` on host HOST_ADDRESS
    and port 5000 using the Waitress WSGI server.

    This function starts the Waitress server and listens for incoming requests
    on the specified host and port. It uses the `serve` function from the Waitress
    library to handle the serving process.

    Parameters:
        None

    Returns:
        None
    """
    serve(app, host=HOST_ADDRESS, port=PORT_ADDRESS)


if __name__ == "__main__":
    logger = logging.getLogger("conjurer_musician")
    logger.setLevel(logging.DEBUG)
    formatter = logging.Formatter(
        "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
    )
    handler = handlers.RotatingFileHandler(
        filename=LOGFILE,
        encoding=ENCODING,
        mode="a",
        maxBytes=6 * 1024 * 1024,
        backupCount=6,
    )
    handler.setFormatter(formatter)
    logger.addHandler(handler)

    rescan()
    logger.info("Started")
    threads = []
    # threads.append(threading.Thread(target=flask_debug))
    threads.append(threading.Thread(target=waitress_run, daemon=True))
    threads.append(threading.Thread(target=thread_rescan, daemon=True))

    for worker in threads:
        worker.start()

    try:
        for worker in threads:
            worker.join()
    except KeyboardInterrupt:
        logger.info("Shutdown requested - exiting musician service")