CLock

,

.gitignore

@@ -197,3 +197,7 @@ node_modules/prettier/esm/parser-postcss.mjs
 node_modules/prettier/esm/parser-typescript.mjs
 node_modules/prettier/esm/parser-yaml.mjs
 node_modules/prettier/esm/standalone.mjs
+cr_results.json
+not_in_db.json
+rr_results.json
+s_results.json

.trunk/configs/.shellcheckrc

@@ -0,0 +1,7 @@
+enable=all
+source-path=SCRIPTDIR
+disable=SC2154
+
+# If you're having issues with shellcheck following source, disable the errors via:
+# disable=SC1090
+# disable=SC1091

.trunk/trunk.yaml

@@ -2,34 +2,38 @@
 # To learn more about the format of this file, see https://docs.trunk.io/reference/trunk-yaml
 version: 0.1
 cli:
-  version: 1.20.1
+  version: 1.22.2
 # Trunk provides extensibility via plugins. (https://docs.trunk.io/plugins)
 plugins:
   sources:
     - id: trunk
-      ref: v1.4.5
+      ref: v1.6.0
       uri: https://github.com/trunk-io/plugins
 # Many linters and tools depend on runtimes - configure them here. (https://docs.trunk.io/runtimes)
 runtimes:
   enabled:
+    - go@1.21.0
     - node@18.12.1
     - python@3.10.8
 # This is the section where you manage your linters. (https://docs.trunk.io/check/configuration)
 lint:
   enabled:
-    - actionlint@1.6.27
-    - bandit@1.7.8
-    - black@24.3.0
+    - shellcheck@0.10.0
+    - shfmt@3.6.0
+    - taplo@0.8.1
+    - actionlint@1.7.1
+    - bandit@1.7.9
+    - black@24.4.2
     - codespell
-    - checkov@3.2.48
+    - checkov@3.2.139
     - git-diff-check
     - isort@5.13.2
     - pylint
-    - markdownlint@0.39.0
-    - prettier@3.2.5
-    - ruff@0.3.4
-    - trivy@0.50.1
-    - trufflehog@3.71.0
+    - markdownlint@0.41.0
+    - prettier@3.3.2
+    - ruff@0.4.9
+    - trivy@0.52.2
+    - trufflehog@3.78.1
     - yamllint@1.35.1
 actions:
   disabled:

bot.py

@@ -16,6 +16,7 @@ import os
 import random
 import re
 import shutil
+import subprocess
 import sys
 import threading
 import uuid
@@ -41,11 +42,16 @@ from discord.ext import commands, tasks
 from spotipy.oauth2 import SpotifyClientCredentials
 
 import yt_dlp
+from communication_subroutine import (
+    IN_COMM_Q,
+    OUT_COMM_Q,
+    QueryControl,
+    comm_subroutine,
+    PREPPED_TRACKS,
+)
 from spotify_dl import spotify
 from spotify_dl import youtube as youtube_download
 
-from communication_subroutine import comm_subroutine, IN_COMM_Q, OUT_COMM_Q
-
 # *=========================== Classes definition
 
 # The above code is defining a TypedDict called `Music_Config` in Python. This TypedDict has three
@@ -62,23 +68,6 @@ Music_Config = TypedDict(
 )
 
 
-class QueryControl:
-    """
-    This class `QueryControl` is used to manage queries with information about the author, UUID,
-    content, logger, context, and replies.
-    """
-    def __init__(self, query_author, query_uuid, query_content, uplogger, ctx) -> None:
-        self.author = query_author
-        self.uuid = query_uuid
-        self.content = query_content
-        self.logger = uplogger
-        self.stop = False
-        self.ctx = ctx
-        self.logger.info(
-            f"Created Query control for {self.author}, {self.uuid}: {self.content}"
-        )
-        self.replies = []
-
 class MusicFileList(object):
     """
     The `MusicFileList` class manages a list of music files, with the ability to refresh the list from a
@@ -131,46 +120,8 @@ class MusicFileList(object):
         post_data = {"item": str(item)}
         requests.post(f"{FILE_SERVICE_ADDRESS}{SEND_MP3}", json=post_data, timeout=360)
 
-class DoSearchView(discord.ui.View):
-    def __init__(self, _uuid, result_list, *args, **kwargs) -> None:
-        super().__init__(*args, **kwargs)
-        self.uuid = _uuid
-        self.result_list = result_list
-
-    @discord.ui.button(
-        label="Nastepna strona", style=discord.ButtonStyle.primary, row=0
-    )
-    async def next_callback(self, interaction, button):
-        # emoji = await ctx.guild.fetch_emoji(id)
-        # button.emoji=1102174413887111189
-        logger.info("Pressed")
-        await interaction.response.edit_message(
-            content="You clicked the button!"
-        )  # Send a message when the button is clicked
-
-    @discord.ui.button(label="Wyszukaj wiecej", style=discord.ButtonStyle.danger, row=0)
-    async def reset_callback(self, interaction, button):
-        # emoji = await ctx.guild.fetch_emoji(id)
-        # button.emoji=1102174413887111189
-        logger.info("Pressed")
-        await interaction.response.edit_message(
-            content="You clicked the button!"
-        )  # Send a message when the button is clicked
-
-    @discord.ui.button(
-        label="Poprzednia Strona", style=discord.ButtonStyle.primary, row=0
-    )
-    async def perv_callback(self, interaction, button):
-        # emoji = await ctx.guild.fetch_emoji(id)
-        # button.emoji=1102174413887111189
-        logger.info("Pressed")
-        await interaction.response.edit_message(
-            content="You clicked the button!"
-        )  # Send a message when the button is clicked
-
 
 # *=========================================== Predefines
-formatter = logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s")
 MASTER_TIMEOUT = datetime.now()
 INITIAL_TIME_WAIT = 500
 MUZYKA: Music_Config = {"ctx": None, "queue": [], "requester": []}
@@ -188,10 +139,16 @@ MUZYKA_MOJEGO_LUDU_SLOWA_KLUCZOWE = 15
 MUZYKA_MOJEGO_LUDU_PLAJLISTA = 30
 
 FILE_SERVICE_ADDRESS = "http://192.168.1.15:5000"
+RADIO_HARBOR_ADDRESS = "http://192.168.1.15:54321"
+SKIP_TRACK = "/skip"
+
 GET_MP3 = "/mp3"
 SEND_MP3 = "/update_mp3"
 GET_PLAYLIST = "/get_music"
 ADD_TO_PRIO_PLAYLIST = "/add_to_priority"
+CREATE_PRIO_PLAYLIST = "/create_priority_playlist"
+
+REQUEST_MUSIC = "/request_radio_file"
 CLEAR_PRIO = "/clear_pr_pls"
 LIBRARIAN_SERVICE_ADDRESS = "http://192.168.1.192:5001"
 SEND_QUERY = "/query"
@@ -285,6 +242,7 @@ handler = handlers.RotatingFileHandler(
     maxBytes=6 * 1024 * 1024,
     backupCount=6,
 )
+formatter = logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s")
 handler.setFormatter(formatter)
 logger.addHandler(handler)
 random.seed()
@@ -330,7 +288,6 @@ for key in word_reactions:
 logger.info("Done")
 
 
-
 # *=========================================== Create Client
 logger.info("Creating discord bot")
 client = commands.Bot(intents=intents, command_prefix="$")
@@ -344,16 +301,18 @@ logger.info("Done")
 async def on_ready():
     """Metoda wywoływana przy połączeniu do serwera."""
     logger.debug("%s has connected to Discord!", client.user)
+    await client.load_extension("voice_recognition")
+    logger.info("Cogs")
+    logger.info(client.cogs)
     await client.change_presence(activity=discord.Game(name="Axe Throwing Darts"))
     await client.tree.sync()
+    for com in client.commands:
+        logger.info(com.qualified_name)
     check_self.start()
     check_data_q.start()
 
 
 @client.event
-# trunk-ignore(pylint/R0915)
-# trunk-ignore(pylint/R0914)
-# trunk-ignore(pylint/R0912)
 async def on_message(message):
     """
     Handle incoming messages in a Discord server, perform various
@@ -453,7 +412,13 @@ async def on_message(message):
             result, MESSAGE_TABLE = await handle_response(
                 prompt, vykidailo, bartender, MESSAGE_TABLE, username, "CONVERSATION"
             )
-        await message.reply(result)
+
+            if len(result) < 1500:
+                await message.reply(result)
+            else:
+                while len(result) > 1500:
+                    await message.reply(result[:1500])
+                    result = result[1500:]
     if "imaginuje sobie:" in message.content:
         async with channel.typing():
             logger.info("Poczatek procedury obrazkowej")
@@ -577,16 +542,20 @@ async def connect(ctx, arg=None):
     """
     if ctx and arg:
         logger.info("Ctx and arg defined for connect")
-    voice_channel = client.get_channel(1060349757349974066)
 
     if client.voice_clients:
-        voice_client = client.voice_clients[0]
-        if voice_client.is_connected():
+        logger.info("Already connected with other client")
+    else:
+        vc = None
+        if ctx.author.voice.channel:
+            vc = await ctx.author.voice.channel.connect()
+        else:
+            voice_channel = client.get_channel(1060349757349974066)
+            vc = await voice_channel.connect()
+        if not vc:
+            logger.error("Not possible to connect to voice")
             return
-    voice_channel_connection = await voice_channel.connect()
-    if not voice_channel_connection:
-        logger.error("Not possible to connect to voice")
-    logger.info("Connecting to voice")
+        logger.info("Connected to voice")
 
 
 async def disconnect(ctx):
@@ -607,8 +576,6 @@ async def disconnect(ctx):
             await voice_client.disconnect()
 
 
-# trunk-ignore(pylint/R0915)
-# trunk-ignore(pylint/R0912)
 async def play(ctx, zamawial=None, arg=None):
     """
     Play a music file, retrieve metadata about the file, and send a
@@ -688,7 +655,12 @@ async def play(ctx, zamawial=None, arg=None):
             query, vykidailo, bartender, message_table_muzyka, username, "MUSIC"
         )
         logger.debug("Obecna historia czatu: %s", message_table_muzyka)
-        await ctx.send(result)
+        if len(result) < 1500:
+            await ctx.send(result)
+        else:
+            while len(result) > 1500:
+                await ctx.send(result[:1500])
+                result = result[1500:]
 
 
 async def archive_channel(channel_no):
@@ -727,54 +699,64 @@ async def check_music():
             await play(MUZYKA["ctx"], MUZYKA["requester"])
             await asyncio.sleep(2)
 
+
 @tasks.loop(seconds=3)
-# trunk-ignore(pylint/R0915)
 async def check_data_q():
+    """
+    This function checks the data queue for any new entries and processes them accordingly.
+    """
     try:
-        data = IN_COMM_Q.get(block=False)
+        fresh_data = IN_COMM_Q.get(block=False)
         entries = []
-        if data.stop:
-            searcher = data.author
-            ctx = data.ctx
-            query = data.content
+        if fresh_data.stop:
+            searcher = fresh_data.author
+            query = fresh_data.content
             l_p = 1
-            for doi in data.entries:
+            for doi in fresh_data.entries:
                 logger.info(doi)
-                desc = data.entries[doi]
-                title = desc['Title'][0]
-                entries.append(f"{l_p}. {title} pod linkiem https://www.sci-hub.se/{doi} i jest to {desc['type']}\n")
-                l_p+=1
-            message = '*Z podłogi wysuwa się winda na książki*'
-            message += f' Dzielny poszukiwaczu @{searcher} w odpowiedzi na twoje zapytanie {query}'
-            message += 'nasza biblioteka służy Ci odpowiedzią. Przy dźwięku fanfar winda się otwiera a w środku '
-            if len(entries)<1:
+                desc = fresh_data.entries[doi]
+                title = desc["Title"][0]
+                entries.append(
+                    f"{l_p}. {title} pod linkiem https://www.sci-hub.se/{doi} i jest to {desc['type']}\n"
+                )
+                l_p += 1
+            message = "*Z podłogi wysuwa się winda na książki*"
+            if fresh_data.ctx is not None:
+                ctx = fresh_data.ctx
+                message += f" Dzielny poszukiwaczu @{searcher} w odpowiedzi na twoje zapytanie {query} nr {fresh_data.uuid}"
+            else:
+                ctx = client.get_channel(1062047571557744721)
+                message += f" Mam wynik dla zapytania {fresh_data.uuid} ale że Hammer coś grzebał nie pamiętam kto to chciał i co chciał"
+
+            message += "nasza biblioteka służy Ci odpowiedzią. Przy dźwięku fanfar winda się otwiera a w środku "
+            if len(entries) < 1:
                 message += "niestety nie ma nic"
-            elif len(entries)>=1 and len(entries)<5:
+                await ctx.send(message)
+            elif len(entries) >= 1 and len(entries) < 5:
                 message += " znajduje się coś:\n"
                 for item in entries:
-                    message+=item
+                    message += item
+                await ctx.send(message)
             else:
-                message+= " znajduje się cholernie dużo:\n"
+                message += " znajduje się cholernie dużo:\n"
                 for item in entries:
-                    message+=item
+                    message += item
                     if len(message) > 1500:
                         await ctx.send(message)
                         message = ""
 
-            await ctx.send(message)
-            #Kept for sentimental reasons
-            #await ctx.send(f"O. A tak będzie wyglądało coś ciekawego w przyszłości: {data}")
+            # Kept for sentimental reasons
+            # await ctx.send(f"O. A tak będzie wyglądało coś ciekawego w przyszłości: {data}")
     except Empty:
         pass
 
+
 @tasks.loop(seconds=120)
-# trunk-ignore(pylint/R0915)
 async def check_self():
     """
     The function `check_data` periodically checks for conditions to send messages and manage log files
     in a Discord channel.
     """
-    # trunk-ignore(codespell/misspelled)
     # logger.info("Heartbeat of cleanup proc")
     channel = client.get_channel(1062047367337095268)
     messages = [message async for message in channel.history(limit=1)]
@@ -837,9 +819,7 @@ async def check_self():
                 await channel.send(
                     "*Przeciąga się za barem* No dobra - porobione to można dalej pi... *Zauważa spojrzenie Hammera* eprzyć o głupotach z klientami... Szefie... *Bierze 'ukradkowy' łyk z piersiówki*"
                 )
-    # trunk-ignore(pylint/W0603)
     global LAST_SPONTANEOUS_CALL
-    # trunk-ignore(pylint/W0603)
     global TIME_BETWEEN_CALLS
     tdelta = datetime.now() - LAST_SPONTANEOUS_CALL
     tdelta = tdelta.total_seconds()
@@ -875,7 +855,6 @@ async def get_random_cyclic_message():
         mess_key = list(cyclic_words.keys())[messnum]
         return cyclic_words[mess_key][0]
     ai_check2 = random.randint(0, 10)
-    # trunk-ignore(pylint/W0603)
     global MESSAGE_TABLE
     if ai_check2 < 6:
         logger.info("Dykteryjka")
@@ -909,10 +888,6 @@ async def get_random_cyclic_message():
     return result
 
 
-# trunk-ignore(pylint/R0912)
-# trunk-ignore(pylint/R0913)
-# trunk-ignore(pylint/R0914)
-# trunk-ignore(pylint/R0915)
 async def handle_response(
     prompt, vykidailo, bartender, history, username, request_type
 ):
@@ -986,17 +961,17 @@ async def handle_response(
         "Rozmiar zapytania przed dodaniem historii %s", chat_gpt_config_request_size
     )
     if request_type == "MUSIC":
-        algorithm = "gpt-3.5-turbo-0125"
+        algorithm = "gpt-4o"
         table = message_table_muzyka
         token_amount = 10700
     elif request_type == "RANDOM":
-        algorithm = "gpt-3.5-turbo-0125"
+        algorithm = "gpt-4o"
         table = MESSAGE_TABLE
         token_amount = 10700
     else:
         table = MESSAGE_TABLE
-        algorithm = "gpt-4"
-        token_amount = 7000
+        algorithm = "gpt-4o"
+        token_amount = 10700
 
     prompt_gpt_request_size = num_tokens_from_string(
         {"role": "user", "content": final_prompt}, "gpt-4"
@@ -1078,31 +1053,36 @@ async def handle_response(
     logger.info(result)
     temp = {"role": "assistant", "content": result}
     history.append(temp)
-    if request_type:
-        with open(MEMORY_FIVE_MUZYKA, "r+", encoding=ENCODING) as file:
+    if request_type == "MUSIC":
+        with open(MEMORY_FIVE_MUZYKA, "r+", encoding=ENCODING) as file_music_memory:
             # First we load existing data into a dict.
-            file_data = json.load(file)
+            file_data = json.load(file_music_memory)
             # Join new_data with file_data inside emp_details
             file_data.append(temp)
-            # Sets file's current position at offset.
-            file.seek(0)
+            file_music_memory.seek(0)
             # convert back to json.
-            json.dump(file_data, file, indent=4)
+            json.dump(file_data, file_music_memory, indent=4)
+    elif request_type == "RANDOM":
+        with open(MEMORY_FIVE_SIARA, "r+", encoding=ENCODING) as file_memory:
+            # First we load existing data into a dict.
+            file_data = json.load(file_memory)
+            # Join new_data with file_data inside emp_details
+            file_data.append(temp)
+            file_memory.seek(0)
+            # convert back to json.
+            json.dump(file_data, file_memory, indent=4)
     else:
-        with open(MEMORY_FIVE_SIARA, "r+", encoding=ENCODING) as file:
+        with open(MEMORY_FIVE_SIARA, "r+", encoding=ENCODING) as file_memory:
             # First we load existing data into a dict.
-            file_data = json.load(file)
+            file_data = json.load(file_memory)
             # Join new_data with file_data inside emp_details
             file_data.append(temp)
-            # Sets file's current position at offset.
-            file.seek(0)
+            file_memory.seek(0)
             # convert back to json.
-            json.dump(file_data, file, indent=4)
+            json.dump(file_data, file_memory, indent=4)
     return result, MESSAGE_TABLE
 
 
-# trunk-ignore(pylint/R0915)
-# trunk-ignore(pylint/R0914)
 async def get_file(ctx, source, link):
     """
     Take in three parameters: "ctx" (context),
@@ -1124,11 +1104,19 @@ async def get_file(ctx, source, link):
     if source == "Spotify":
         dir_path = None
         item_type, item_id = spotify.parse_spotify_url(link)
-        if item_id:
-            coro = asyncio.to_thread(spotify.fetch_tracks, args=(spotify_ctrl, item_type, link))
-            file_list = await coro
-            coro = asyncio.to_thread(spotify.get_item_name, args=(spotify_ctrl, item_type, item_id))
-            directory_name = await coro
+        if item_type in ["album", "track", "playlist"] and item_id:
+            logger.info(item_type)
+            logger.info(item_id)
+            logger.info("Spotify link provided")
+            file_list = await asyncio.to_thread(
+                spotify.fetch_tracks, spotify_ctrl, item_type, link
+            )
+            logger.info(file_list)
+            directory_name = await asyncio.to_thread(
+                spotify.get_item_name, spotify_ctrl, item_type, item_id
+            )
+            logger.info(directory_name)
+            logger.info("Spotify scrape done")
             url_data = {"urls": []}
             url_dict = {}
             url_dict["save_path"] = Path(
@@ -1138,6 +1126,7 @@ async def get_file(ctx, source, link):
             url_dict["songs"] = file_list
             url_data["urls"].append(url_dict.copy())
             file_name_f = youtube_download.default_filename
+            logger.info("YT-DL")
             coro = asyncio.to_thread(
                 youtube_download.download_songs,
                 songs=url_data,
@@ -1153,6 +1142,7 @@ async def get_file(ctx, source, link):
                 proxy="",
             )
             _ = await coro
+            logger.info("YT-DL done")
             dir_path = (url_dict["save_path"].resolve()).as_posix()
             if platform == "win32":
                 dir_path = dir_path.replace("/", "\\")
@@ -1323,9 +1313,6 @@ async def get_stats(ctx, history_limit):
             yield name, how_many
 
 
-# trunk-ignore(pylint/R0915)
-# trunk-ignore(pylint/R0912)
-# trunk-ignore(pylint/R0914)
 async def wyszukaj(ctx, how_many=0, slowa_kluczowe=None):
     """
     Take in a context object and an optional integer parameter "how_many" and perform search
@@ -1395,6 +1382,53 @@ async def max_weight(lista):
 # *=========================================== Define Commands
 
 
+@client.hybrid_command(
+    name="skip_track",
+    description="Przeskocz kawałek w radiu",
+    guild=discord.Object(id=664789470779932693),
+)
+async def skip_track(ctx):
+    async with ctx.typing():
+        allowed = False
+        for role in ctx.author.roles:
+            if role.name in ("Thane", "Jarl"):
+                allowed = True
+        if not allowed:
+            await ctx.send("Łapy precz od radia")
+        else:
+            coroutine = asyncio.to_thread(
+                requests.get,
+                f"{RADIO_HARBOR_ADDRESS}{SKIP_TRACK}",
+                timeout=360,
+            )
+            result = await coroutine
+            logger.info("Done %s", result)
+            await ctx.send("Zrobione szefie!")
+
+
+@client.hybrid_command(
+    name="zrestartuj_radio",
+    description="Komenda ktora uruchamia radio ponownie jakby się zawiesiło",
+    guild=discord.Object(id=664789470779932693),
+)
+async def zrestartuj_radio(ctx):
+    async with ctx.typing():
+        allowed = False
+        for role in ctx.author.roles:
+            if role.name in ("Thane", "Jarl"):
+                allowed = True
+        if not allowed:
+            await ctx.send("Łapy precz od radia")
+        else:
+            retcode = subprocess.run(
+                "/home/pi/Conjurer/restart_radio.sh",
+                shell=False,
+                check=False,
+                capture_output=True,
+            )
+            logger.info("Wynik: %s", retcode)
+
+
 @client.hybrid_command(
     name="dej_co_ze_spotifaja",
     description="Podaj link do spotify - sciagnie i doda muzyke",
@@ -1485,8 +1519,6 @@ async def dej_co_z_jutuba(ctx):
     description="Jeśli nie wiesz jak użyć tej komendy to nawet nie próbuj",
     guild=discord.Object(id=664789470779932693),
 )
-# trunk-ignore(pylint/R0914)
-# trunk-ignore(pylint/R0912)
 async def update_banlist(ctx):
     """
     Update a banlist in a Discord guild from preprovided list in channel.
@@ -1639,6 +1671,41 @@ async def graj_muzyko(ctx):
         check_music.start()
 
 
+@client.hybrid_command(
+    name="radio_hardkor",
+    description="Włącza radio Conjurer na kanale #nocna-zmiana.",
+    guild=discord.Object(id=664789470779932693),
+)
+async def radio_hardkor(ctx):
+    """
+    Plays the radio hardkor stream in the voice channel.
+
+    Args:
+        ctx: The context object representing the invocation context.
+
+    Returns:
+        None
+    """
+    logger.info("Press play on radio hardkor")
+    async with ctx.typing():
+        global MUZYKA  # pylint: disable=global-variable-not-assigned
+        MUZYKA["ctx"] = ctx
+        if not client.voice_clients:
+            await connect(ctx=ctx)
+            voice_client = client.voice_clients[0]
+            voice_client.play(
+                discord.PCMVolumeTransformer(
+                    discord.FFmpegPCMAudio("http://95.175.16.246:666/mp3-stream"),
+                    volume=0.3,
+                )
+            )
+            logger.info("Press play on radio completed")
+        else:
+            logger.error("Already playing")
+        await asyncio.sleep(12)
+        check_music.start()
+
+
 @client.hybrid_command(
     name="cisza",
     description="Wyłącza muzykę i czyści plejliste.",
@@ -1781,6 +1848,7 @@ async def zagraj_mi_kawalek(ctx):
                 "Obawiam się że nie mogę nic znaleźć u siebie. Spróbuj komendy '$dej_co_ze_spotifaja' jeśli masz link"
             )
 
+
 @client.hybrid_command(
     name="dodaj_do_ulubionych",
     description="Dodaje do listy ulubionych w radiu",
@@ -1812,7 +1880,80 @@ async def dodaj_do_ulubionych(ctx):
             json=jrequest,
             timeout=360,
         )
-        _ = await coroutine
+        result = await coroutine
+        logger.info("Done %s", result)
+        await ctx.send("Zrobione szefie!")
+
+
+@client.hybrid_command(
+    name="ja_chciol",
+    description="Dodaje do listy ulubionych w radiu",
+    guild=discord.Object(id=664789470779932693),
+)
+async def request_radio(ctx):
+    """
+    Generate a playlist in queue. First word in this command shall be int defining length of the playlist.
+    Rest of the line are search terms.
+
+    :param ctx: ctx stands for "context" and is a parameter commonly used in Discord.py commands. It
+    represents the context in which the command was invoked, including information such as the message,
+    the channel, the server, and the user who invoked the command. This parameter is required in all
+    Discord.py commands
+    """
+    async with ctx.typing():
+        logger.info("Zaczynam szukać timestamp %s", datetime.now())
+
+        word_list = ctx.message.content.split()
+        jrequest = {
+            "lista_slow": word_list,
+            "UUID": str(uuid.uuid4()),
+        }
+        coroutine = asyncio.to_thread(
+            requests.post,
+            f"{FILE_SERVICE_ADDRESS}{REQUEST_MUSIC}",
+            json=jrequest,
+            timeout=360,
+        )
+        result = await coroutine
+        logger.info("Done %s", result)
+        await ctx.send("Zrobione szefie!")
+
+
+@client.hybrid_command(
+    name="stworz_audycje",
+    description="Dodaje do listy ulubionych w radiu",
+    guild=discord.Object(id=664789470779932693),
+)
+async def stworz_audycje(ctx):
+    """
+    Generate a playlist in queue. First word in this command shall be int defining length of the playlist.
+    Rest of the line are search terms.
+
+    :param ctx: ctx stands for "context" and is a parameter commonly used in Discord.py commands. It
+    represents the context in which the command was invoked, including information such as the message,
+    the channel, the server, and the user who invoked the command. This parameter is required in all
+    Discord.py commands
+    """
+    async with ctx.typing():
+        logger.info("Zaczynam szukać timestamp %s", datetime.now())
+
+        dlugosc_playlisty = ctx.message.content.split()[1]
+        word_list = ctx.message.content.split()
+        jrequest = {
+            "lista_slow": word_list,
+            "dlugosc_plejlisty": dlugosc_playlisty,
+            "UUID": str(uuid.uuid4()),
+        }
+        coroutine = asyncio.to_thread(
+            requests.post,
+            f"{FILE_SERVICE_ADDRESS}{CREATE_PRIO_PLAYLIST}",
+            json=jrequest,
+            timeout=360,
+        )
+        result = await coroutine
+        logger.info("Done %s", result)
+        await ctx.send("Zrobione szefie!")
+
 
 @client.hybrid_command(
     name="wyczysc_ulubione",
@@ -1831,12 +1972,13 @@ async def wyczysc_ulubione(ctx):
     """
     async with ctx.typing():
         coroutine = asyncio.to_thread(
-            requests.post,
+            requests.get,
             f"{FILE_SERVICE_ADDRESS}{CLEAR_PRIO}",
-            json={},
             timeout=360,
         )
-        _ = await coroutine
+        result = await coroutine
+        logger.info("Done %s", result)
+        await ctx.send("Zrobione szefie!")
 
 
 @client.hybrid_command(
@@ -2058,8 +2200,6 @@ async def get_image_stable_diffusion(ctx):
     description="Gra muzyke wyszukana na bazie tematow konwersacji na kanale NZ",
     guild=discord.Object(id=664789470779932693),
 )
-# trunk-ignore(pylint/R0912)
-# trunk-ignore(pylint/R0915)
 async def zagraj_muzyke_mego_ludu(ctx):
     """
     Play completeley random playlist based on messaging history.
@@ -2209,11 +2349,27 @@ async def parametry_muzyki_mego_ludu(
     guild=discord.Object(id=664789470779932693),
 )
 async def wyszukaj_linki_do_dokumentow(ctx):
+    """
+    The function `wyszukaj_linki_do_dokumentow` searches for links to documents in a crossref database and provides links to scihub.
+
+    :param ctx: The `ctx` parameter is typically used in Discord.py, a Python library for creating Discord bots.
+    It represents the context of the command being executed, including information about the message, the server,
+    and the user who invoked the command.
+    """
     query = ctx.message.content
     query_uuid = uuid.uuid4()
-    #TODO: TESTING ONLY!!
-    #query_uuid = uuid.UUID('{12345678-1234-5678-1234-567812345678}')
-    json_query = {"UUID": str(query_uuid), "query": str(query)[30:], "page": 1}
+    # TODO: TESTING ONLY!!
+    # query_uuid = uuid.UUID('{12345678-1234-5678-1234-567812345678}')
+    ctx.message.content = ctx.message.content.replace(
+        "$wyszukaj_linki_do_dokumentow", ""
+    )
+
+    json_query = {
+        "UUID": str(query_uuid),
+        "query": str(query),
+        "page": 1,
+        "deep_search": False,
+    }
     coroutine = asyncio.to_thread(
         requests.post,
         f"{LIBRARIAN_SERVICE_ADDRESS}{SEND_QUERY}",
@@ -2221,14 +2377,16 @@ async def wyszukaj_linki_do_dokumentow(ctx):
         timeout=360,
     )
     await ctx.send(
-        "*Conjurer powoli notuje podane przez Ciebie. Podchodzi do sprytnie ukrytej przy barze rury od poczty pneumatycznej i" +
-        " wrzuca twój liścik do środka* To teraz trza poczekać kilka godzin. Biblioteka to te 3/4 stacji."+
-        " A przecież pół stacji to browar, motelik dla zabaw cielesnych i ten Bar. Więc te 12/8 stacji teraz będzie ciężko pracować"
+        "*Conjurer powoli notuje podane przez Ciebie. Podchodzi do sprytnie ukrytej przy barze rury od poczty pneumatycznej i"
+        + " wrzuca twój liścik do środka* To teraz trza poczekać kilka godzin. Biblioteka to 3/4 stacji."
+        + " A przecież pół stacji to browar, motelik dla zabaw cielesnych i ten Bar. Więc 12/8 stacji teraz będzie ciężko pracować"
     )
     query_response = await coroutine
     if not query_response.status_code == 200:
-        await ctx.send("*Z rury wydobywa się dym. Conjurer łapie pierwszą ciecz pod ręką i pryska na rurę. Następuje drobna eksplozja i wszystko zaczyna się palić."+
-        " Conjurer jest skonfundowany..* Wołaj szefa - mam nieodparte wrażenie że się coś wyjebało")
+        await ctx.send(
+            "*Z rury wydobywa się dym. Conjurer łapie pierwszą ciecz pod ręką i pryska na rurę. Następuje drobna eksplozja i wszystko zaczyna się palić."
+            + " Conjurer jest skonfundowany..* Wołaj szefa - mam nieodparte wrażenie że się coś wyjebało"
+        )
         return
 
     query, query_uuid, queue_size = (
@@ -2240,10 +2398,107 @@ async def wyszukaj_linki_do_dokumentow(ctx):
         username = ctx.message.author.nick
     else:
         username = ctx.message.author.name
-    query_object = QueryControl(username, query_uuid, query, logger, ctx)
+    query_object = QueryControl(username, query_uuid, query, ctx)
     OUT_COMM_Q.put(query_object)
-    await ctx.send(f"No dobra poszło. Zapamiętaj proszę {query_uuid} - to identyfikator twojego zapytania. Jesteś {queue_size} w kolejce."+
-    " Zapytania obsługuje algorytm zasilany czterema chomikami zapierdalającymi w kołowrotku - więc wyniki najwcześniej za kilka godzi - ale mogą być też dni.")
+    await ctx.send(
+        f"No dobra poszło. Zapamiętaj proszę {query_uuid} - to identyfikator twojego zapytania. Jesteś {queue_size} w kolejce."
+        + " Zapytania obsługuje algorytm zasilany czterema chomikami zapierdalającymi w kołowrotku - więc wyniki najwcześniej za kilka godzi - ale mogą być też dni."
+    )
+
+
+@client.hybrid_command(
+    name="glebokie_gardlo",
+    description="Przygotowuje drinka o nazwie głębokie gardło",
+    guild=discord.Object(id=664789470779932693),
+)
+async def wyszukaj_linki_do_dokumentow_deep(ctx):
+    """
+    The function `wyszukaj_linki_do_dokumentow_deep` performs a deep search for links to documents in
+    a crossref database and provides links to scihub.
+
+    :param ctx: The `ctx` parameter is typically used in Discord.py, a Python library for creating Discord bots.
+    It represents the context of the command being executed, including information about the message, the server,
+    and the user who invoked the command.
+    """
+    # TODO: Implement deep search logic here
+    query = ctx.message.content.replace("$glebokie_gardlo", "")
+    allowed = False
+    for role in ctx.message.author.roles:
+        if role.name == "Bartender":
+            allowed = True
+        if role.name == "Scribe":
+            allowed = True
+        if role.name == "Thane":
+            allowed = True
+    if not allowed:
+        if ctx.message.author.nick:
+            username = ctx.message.author.nick
+        else:
+            username = ctx.message.author.name
+        vykidailo = False
+        bartender = False
+        prompt = "Przygotuj mi drinka o nazwie Głębokie Gardło, inspirowanego tym sławnym filmem oraz skandalem Watergate"
+        for role in ctx.message.author.roles:
+            if role.name == "Vykidailo":
+                vykidailo = True
+            if role.name == "Bartender":
+                bartender = True
+        global MESSAGE_TABLE  # pylint: disable=global-statement
+
+        result, MESSAGE_TABLE = await handle_response(
+            prompt, vykidailo, bartender, MESSAGE_TABLE, username, "CONVERSATION"
+        )
+        if len(result) < 1500:
+            await ctx.send(result)
+        else:
+            while len(result) > 1500:
+                await ctx.send(result[:1500])
+                result = result[1500:]
+        return
+
+    query_uuid = uuid.uuid4()
+    # TODO: TESTING ONLY!!
+    # query_uuid = uuid.UUID('{12345678-1234-5678-1234-567812345678}')
+    json_query = {
+        "UUID": str(query_uuid),
+        "query": str(query),
+        "page": 1,
+        "deep_search": True,
+    }
+    coroutine = asyncio.to_thread(
+        requests.post,
+        f"{LIBRARIAN_SERVICE_ADDRESS}{SEND_QUERY}",
+        json=json_query,
+        timeout=360,
+    )
+    await ctx.send(
+        "*Conjurer mruga okiem i zamiast drinka wyjmuje dysk usb z terminala. Podchodzi do sprytnie ukrytej przy barze rury od poczty pneumatycznej i"
+        + " wrzuca ten dysk do środk* To teraz trza poczekać kilka godzin. TO będzie głębokie wyszukanie"
+        + " Rozgląda się dookoła i stawia przed tobą mętnego drinka o zapachu mięty, gwiezdnego pyłu i oleju silnikowego"
+    )
+    query_response = await coroutine
+    if not query_response.status_code == 200:
+        await ctx.send(
+            "*Z rury wydobywa się dym. Conjurer łapie pierwszą ciecz pod ręką i pryska na rurę. Następuje drobna eksplozja i wszystko zaczyna się palić."
+            + " Conjurer jest skonfundowany..* Wołaj szefa - mam nieodparte wrażenie że się coś wyjebało"
+        )
+        return
+
+    query, query_uuid, queue_size = (
+        query_response.json()["data"][0],
+        query_response.json()["data"][1],
+        query_response.json()["data"][2],
+    )
+    if ctx.message.author.nick:
+        username = ctx.message.author.nick
+    else:
+        username = ctx.message.author.name
+    query_object = QueryControl(username, query_uuid, query, ctx)
+    OUT_COMM_Q.put(query_object)
+    await ctx.send(
+        f"Wypij wypi {query_uuid} - to identyfikator twojego zapytania. Jesteś {queue_size} w kolejce niestety kolejka obowiazuje zawsze."
+        + " Zapytania obsługuje algorytm zasilany czterema chomikami zapierdalającymi w kołowrotku - więc wyniki najwcześniej za kilka godzin - ale mogą być też dni. Głębokie zabawy trwają dłużej. *Znowu mruga*"
+    )
 
 
 @client.hybrid_command(
@@ -2275,11 +2530,29 @@ async def krecimy_pornola(ctx):
                     sciezka, files = await get_file(ctx, "Pornol", item_yt)
                     if files:
                         logger.info("Pornol udany")
-                        ctx.reply(f"Jest w tajnym archiwum pod adresem{sciezka})")
+                        await ctx.send(f"Jest w tajnym archiwum pod adresem{sciezka})")
     else:
-        ctx.reply("Jak ładnie szefa poprosisz.")
+        await ctx.reply("Jak ładnie szefa poprosisz.")
 
+@client.hybrid_command(
+    name="co_na_plejliscie_wariacie",
+    description="Wyswietl kawalki ktore sa na pocztku list radia",
+    guild=discord.Object(id=664789470779932693),
+)
+async def co_na_plejliscie_wariacie(ctx):
+    """
+    Download a music number from youtube.
 
+    :param ctx: ctx stands for "context" and is a parameter commonly used in Discord.py commands. It
+    represents the context in which the command was invoked, including information such as the message,
+    the channel, the server, and the user who invoked the command. It allows the command to interact
+    with the Discord API and
+    """
+    await ctx.send("Dej mnie chwilkę")
+    async with ctx.typing():
+        logger.info("plejlista")
+        logger.info(PREPPED_TRACKS)
+        await ctx.send(f"Didżej Hammer i jego sztuczna inteligencja (||he he||) prezentują: \n- obecnie grany jest {(PREPPED_TRACKS['now_playing']).rstrip()} (wg metadanych: {PREPPED_TRACKS['meta']}) \n- następny będzie{(PREPPED_TRACKS['next']).rstrip()} \n- na liście priorytetowej {(PREPPED_TRACKS['priority']).rstrip()} \n- na liście hitów obecnie czeka kawałek {(PREPPED_TRACKS['hit']).rstrip()} \n- na liście wszystkich kawałków {(PREPPED_TRACKS['all']).rstrip()} \n- najświeższym zamówieniem od słuchaczy jest {(PREPPED_TRACKS['requests']).rstrip()} \nZ kolei jingiel to: {(PREPPED_TRACKS['jingles']).rstrip()}")
 
 # *================================== Run
 if __name__ == "__main__":
@@ -2287,23 +2560,16 @@ if __name__ == "__main__":
     threads = []
     logger.info("Starting discord bot: Creating threads")
     threads.append(threading.Thread(target=client.run, args=(TOKEN,)))
-    threads.append(threading.Thread(target=comm_subroutine, args=(logger,)))
+    threads.append(threading.Thread(target=comm_subroutine))
     logger.info("Starting discord bot: Starting threads")
-    i = 0
+    WRK_CNT = 0
     for worker in threads:
-        i+=1
-        logger.info("Starting discord bot: Starting thread {i}")
+        WRK_CNT += 1
+        logger.info("Starting discord bot: Starting thread %s", WRK_CNT)
         worker.start()
     logger.info("Starting discord bot: Joining threads")
-    i=0
+    WRK_CNT = 0
     for worker in threads:
-        i+=1
-        logger.info("Starting discord bot: Joining thread {i}")
+        WRK_CNT += 1
+        logger.info("Starting discord bot: Joining thread %s", WRK_CNT)
         worker.join()
-
-# widok - generuje się 5 stron po 4 linki
-# odśwież - zamienić na "dalej" - zaciąga kolejne 20 rezultatów
-# po wyslaniu czekamy na odbior i dodajemy UUID oraz nick poszukiwacza do queue ktora jest sprawdzana
-# flask sobie chodzi i jak dostaje posta z wynikami to wyciaga z queue UUID i odpowiada że znalazła
-# po samym wyszukaniu dajemy info że "Zaczynam szukać ale pare godzin to potrwa."
-# OPCJONALNIE: Dosyłamy znalezione wyniki na bieżąco - wtedy wkładamy do queue dla UUID wyniki

cogs/music.py

@@ -0,0 +1,46 @@
+import discord
+from discord.ext import commands
+from typing import  Optional
+
+class Music(commands.Cog):
+    def __init__(self, bot):
+        self.bot = bot # This is so you can access Bot instance in your cog
+
+# You must have this function for `bot.load_extension` to call
+def setup(bot):
+    bot.add_cog(Music(bot))
+
+@commands.hybrid_command(
+    name="przytul", description="Przytul kogoś - daj mention po komendzie :)"
+)
+async def przytul(ctx, arg: Optional[discord.Member] = None):
+    """
+    Generate a text about hugging mentioned user.
+
+    :param ctx: ctx stands for "context" and is a required parameter in Discord.py commands. It
+    represents the context in which the command was invoked, including information such as the message,
+    the channel, the server, and the user who invoked the command
+    :param arg: arg is a parameter of the function "przytul" that expects a Discord member object. The
+    parameter is optional, meaning that if no member object is provided, it will default to None
+    :type arg: Optional[discord.Member]
+    """
+    async with ctx.typing():
+        nieprzytulac = False
+        for mention in ctx.message.mentions:
+            for role in mention.roles:
+                if role.name == "NIEPRZYTULAĆ!":
+                    nieprzytulac = True
+
+        if arg and nieprzytulac:
+            await ctx.send(
+                f"Żebym ja Ciebie nie przytulił {ctx.message.author.mention}"
+            )
+        elif arg:
+            await ctx.send(
+                # trunk-ignore(codespell/misspelled)
+                f"Już dobrze.... Już dobrze... Ojej.. Biedactwo... :( *W ułamku sekundy {arg.mention} znajduje sie w duszącym uścisku. Żebra trzeszczą - kilka pęka. Pacnięcia po plecach grożą odbiciem nerek, a głaskanie po głowie powoduje wstrząs mózgu*"
+            )
+        else:
+            await ctx.send(
+                "Kogo mam przytulić? *Wyłamuje kostki i przeciąga się - jego 200 kilowa sylwetka złożona z samych mięśni świadczy o tym że jest gotowy*"
+            )

communication_subroutine.py

@@ -2,17 +2,70 @@ import logging
 import threading
 import json
 import time
+import re
+from urllib import request as urequest
+
 from queue import Queue, Empty
 from flask import Flask, jsonify, request
 from waitress import serve
 
 HOST_ADDRESS = "192.168.1.191"
 PORT_ADDRESS = 5000
+ICECAST_ADDRESS = "http://192.168.1.15:8000"
 OUT_COMM_Q = Queue()
 IN_COMM_Q = Queue()
+SRCHTITLE = re.compile(br'StreamTitle=\\*(?P<title>[^;]*);').search
+
 awaiting_q = []
 incoming_q = Queue()
 app = Flask(__name__)
+PREPPED_TRACKS = {
+    "requests" : "",
+    "hit" : "",
+    "all": "",
+    "priority":"",
+    "jingles":"",
+    "now_playing":"",
+    "next": "",
+    "meta" : ""
+}
+logger = logging.getLogger("discord")
+
+class QueryControl:
+    """
+    This class `QueryControl` is used to manage queries with information about the author, UUID,
+    content, logger, context, and replies.
+    """
+    def __init__(self, query_author, query_uuid, query_content, ctx) -> None:
+        self.author = query_author
+        self.uuid = query_uuid
+        self.content = query_content
+        self.logger = logging.getLogger("discord")
+        self.stop = False
+        self.ctx = ctx
+        self.logger.info(
+            f"Created Query control for {self.author}, {self.uuid}: {self.content}"
+        )
+        self.replies = []
+
+@app.route("/prepped_tracks", methods=["POST"])
+def log_radio_tracks():
+    app.logger = logging.getLogger("discord")
+
+    app.logger.info(request)
+    record = json.loads(request.data)
+    app.logger.info(record)
+    if "next" in record[0]:
+        metadata = id3(ICECAST_ADDRESS)
+        PREPPED_TRACKS["now_playing"] = PREPPED_TRACKS["next"]
+        if metadata:
+            PREPPED_TRACKS["meta"] = metadata["name"] + " - " + metadata["title"] + "(" + metadata["genre"] + ")"
+        else:
+            PREPPED_TRACKS["meta"] = "Nie znaju"
+    PREPPED_TRACKS[record[0]] = record[1]
+    app.logger.info("DATA RECEIVED")
+    return jsonify("SUCCESS")
+
 
 @app.route("/conjurer", methods=["POST"])
 def answer_external_command():
@@ -22,10 +75,11 @@ def answer_external_command():
     :return: The function `answer_external_command()` is returning a JSON response with the message
     "SUCCESS".
     """
-    app.logger.info(request)
+    logger = logging.getLogger("discord")
+    logger.info(request)
     record = json.loads(request.data)
-    app.logger.info(record)
-    app.logger.info("DATA RECEIVED")
+    logger.info(record)
+    logger.info("DATA RECEIVED")
     incoming_q.put(record)
     return jsonify("SUCCESS")
 
@@ -40,25 +94,29 @@ def check_alive():
     """
     return jsonify("ALIVE")
 
-def flask_debug(_logger):
+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.
     """
-    _logger.info("Attempt debug")
+    logger = logging.getLogger("discord")
+
+    logger.info("Attempt debug")
     # trunk-ignore(bandit/B201)
     app.run(debug=True, use_reloader=False, host=HOST_ADDRESS, port=PORT_ADDRESS)
 
 
-def waitress_run(_logger):
+def waitress_run():
     """
     The `waitress_run` function serves the `app` on host "0.0.0.0"
     and port 5000 using the Waitress WSGI server.
     """
-    _logger.info("Attempt waitress")
+    logger = logging.getLogger("discord")
+
+    logger.info("Attempt waitress")
     serve(app, host=HOST_ADDRESS, port=PORT_ADDRESS)
 
-def scan_queue(_logger):
+def scan_queue():
     """
     The function `scan_queue` reads data from a queue, logs it, and appends it to another queue.
 
@@ -67,12 +125,13 @@ def scan_queue(_logger):
     and provide information for debugging purposes. In this code snippet, the `_logger` object is used
     to log the
     """
+    logger = logging.getLogger("discord")
     while True:
         data = OUT_COMM_Q.get()
-        _logger.info(data)
+        logger.info(data)
         awaiting_q.append(data)
 
-def scan_incoming(_logger):
+def scan_incoming():
     """
     The `scan_incoming` function continuously checks for incoming data, processes it, and logs when data
     is found.
@@ -82,20 +141,51 @@ def scan_incoming(_logger):
     debugging, monitoring, or tracking the flow of the program. In this case, the `_logger` is being
     used
     """
+    logger = logging.getLogger("discord")
     while True:
         try:
             answer = incoming_q.get(block=False)
-            _logger.info("DATA FOUND")
+            logger.info("DATA FOUND")
+            record_stored = False
             for record in awaiting_q:
                 if record.uuid in answer.keys():
+                    record_stored = True
+                    record.stop = True
+                    record.entries = answer[record.uuid]
+                    IN_COMM_Q.put(record)
+            if not record_stored:
+                for key in answer.keys():
+                    record = QueryControl("Orphaned", key, "Orphan", None)
                     record.stop = True
                     record.entries = answer[record.uuid]
                     IN_COMM_Q.put(record)
         except Empty:
             time.sleep(1)
 
+def get_stream_title(tag:bytes) -> str:
+    title = ''
+    if m := SRCHTITLE(tag):
+        #decode, strip, unescape and remove surrounding quotes (may not even be the same type of quote)
+        title = m.group('title').decode('utf-8').strip().replace('\\', '')[1:-1]
+    return title
 
-def comm_subroutine(logger):
+def id3(url:str) -> dict:
+    request = urequest.Request(url, headers={'Icy-MetaData': 1})
+
+    with urequest.urlopen(request) as resp:
+        metaint = int(resp.headers.get('icy-metaint', '-1'))
+        if metaint<0:
+            return False
+        resp.read(metaint) #this isn't seekable so, arbitrarily read to the point we want
+        tagdata = dict(
+            site_url = resp.headers.get('icy-url'  )        ,
+            name     = resp.headers.get('icy-name' ).title(),
+            genre    = resp.headers.get('icy-genre').title(),
+            title    = get_stream_title(resp.read(255))     )
+        return tagdata
+
+
+def comm_subroutine():
     """
     The `comm_subroutine` function starts multiple threads to run different tasks concurrently.
 
@@ -104,12 +194,13 @@ def comm_subroutine(logger):
     the provided code snippet, the logger is used to log messages at the "info" level
     """
     #logger.setLevel(logging.DEBUG)
-    logger.info("Started")
+    logger = logging.getLogger("discord")
+    logger.info("Started comms")
     threads = []
-    #threads.append(threading.Thread(target=flask_debug, args=(logger,)))
-    threads.append(threading.Thread(target=waitress_run, args=(logger,)))
-    threads.append(threading.Thread(target=scan_queue,args=(logger,)))
-    threads.append(threading.Thread(target=scan_incoming,args=(logger,)))
+    #threads.append(threading.Thread(target=flask_debug))
+    threads.append(threading.Thread(target=waitress_run))
+    threads.append(threading.Thread(target=scan_queue))
+    threads.append(threading.Thread(target=scan_incoming))
 
 
     for worker in threads:
@@ -118,5 +209,4 @@ def comm_subroutine(logger):
         worker.join()
 
 if __name__ == "__main__":
-    logging_client = logging.getLogger(__name__)
-    comm_subroutine(logging_client)
+    comm_subroutine()

conjurer_librarian/conjurer_librarian.py

@@ -1,243 +1,383 @@
-import re
+"""
+This module contains the implementation of the Librarian class and
+related functions for searching and refining queries.
+
+Classes:
+-   Librarian: Represents a librarian object that performs search and
+    refinement operations on queries
+
+Functions:
+-   flask_debug: Starts a Flask application in debug mode without using the reloader.
+-   waitress_run: Serves the Flask application using the Waitress WSGI server.
+-   BackgroundTaskSearch: Represents a background task for running the
+    Librarian object asynchronously
+"""
+
+import asyncio
+import json
 import logging
+import netrc
 import threading
 import time
-from flask import Flask, jsonify, request
-import netrc
-import json
-import asyncio
 from json.decoder import JSONDecodeError
-from urllib.request import urlopen
+from logging import handlers
+from queue import Queue
+
+import requests
+import scrape_bot
+import search_bot
+#import search_bot2 as search_bot
+from flask import Flask, jsonify, request
 from habanero import Crossref
 from waitress import serve
-from queue import Queue
-import search_bot
-import scrape_bot
-import requests
-NETRC_FILE = r"C:\Users\Activcom.pl\.netrc"
 
+# Constants
+NETRC_FILE = r"C:\Users\Activcom.pl\.netrc"
 HOST_ADDRESS = "192.168.1.192"
 PORT_ADDRESS = 5001
 MAIN_BOT_ADDRESS = "http://192.168.1.191:5000"
 SEND_RESULTS = "/conjurer"
-BDSM_UUID_TEST = '96b7f85a-1142-4908-8986-62a2ea25a147'
-MAX_CR_RESULTS = 150000
+BDSM_UUID_TEST = "96b7f85a-1142-4908-8986-62a2ea25a147"
+
+MAX_CR_RESULTS = 1000
+#TEST PURPOSES ONLY!
+#MAX_CR_RESULTS = 5
+
 ENCODING = "utf-8"
+
 app = Flask(__name__)
 
 librarian_queue = Queue()
 librarian_list = []
 
-class Librarian(object):
 
-    def __init__(self, app, query, uuid) -> None:
+# trunk-ignore(pylint/R0902)
+class Librarian(object):
+    """
+    Represents a librarian object that performs search and refinement operations on queries.
+    """
+
+    def __init__(self, _app, query, uuid, _deep_search) -> None:
+        """
+        Initializes a Librarian object.
+
+        Args:
+        - _app: The Flask application object.
+        - query: The query to be searched.
+        - uuid: The unique identifier for the search.
+
+        Attributes:
+        - cr: The Crossref object for performing the search.
+        - query: The query to be searched.
+        - uuid: The unique identifier for the search.
+        - limit: The maximum number of search results to fetch.
+        - fetched: The number of search results fetched so far.
+        - hit: The number of search results that match the refinement criteria.
+        - total: The total number of search results.
+        - app: The Flask application object.
+        - live_results: A list to store live search results.
+        - final_result: A list to store the final refined search results.
+        - not_in_db: A list to store search results that are not in the local database.
+        - search_result_from_cr: A dictionary to store the search results from Crossref.
+        - done: A flag indicating if the search is done.
+        """
         netrc_mod = netrc.netrc(NETRC_FILE)
-        authTokens = netrc_mod.authenticators("crossref")
-        self.cr = Crossref(mailto=authTokens[0])
+        auth_tokens = netrc_mod.authenticators("crossref")
+        self.cr = Crossref(
+            mailto=auth_tokens[0],
+            ua_string=f"Conjurer project. mailto:{auth_tokens[0]}"
+        )
         self.query = query
         self.uuid = str(uuid)
         self.limit = MAX_CR_RESULTS
         self.fetched = 0
         self.hit = 0
         self.total = 0
-        self.app = app
-        self.logger = app.logger
+        self.app = _app
         self.live_results = []
-        self.final_result = []
-        self.not_in_db = []
+        self.final_result = {}
+        self.not_in_db = {}
         self.search_result_from_cr = {}
         self.done = False
+        self.deep_search = _deep_search
+
+    async def search_crossref(self, query, deep_search=False):
+        """
+        Performs a search on Crossref for the given query.
+
+        Args:
+        - query: The query to be searched.
+
+        Returns:
+        - result: The search result from Crossref.
+
+        Raises:
+        - None.
+        """
 
-    async def search_crossref(self, query):
         self.app.logger.info("STARTED SEARCH")
-        result = self.cr.works(query = query, limit = 1000)
-        self.search_result_from_cr.update(result)
-        self.total = result['message']['total-results']
-        self.fetched += len(result['message']['items'])
-        self.logger.info (self.total)
-        self.logger.info(self.fetched)
-        while self.total > self.fetched and self.limit > self.fetched:
-            result = self.cr.works(query = query, limit = 1000)
-            self.search_result_from_cr.update(result)
-            self.total = result['message']['total-results']
-            self.fetched += len(result['message']['items'])
-            self.logger.info (self.total)
-            self.logger.info(self.fetched)
-            time.sleep(0.1)
-        self.app.logger.info("CROSSREF DONE")
-        #TODO: add to sql with UUID
-        #sql row - title, doi, author, uuid, last retrieved, is_available
         
+        if not deep_search:
+            query_limit = MAX_CR_RESULTS if MAX_CR_RESULTS < 1000 else 1000
+            cr_result = self.cr.works(query=query, limit=query_limit)
+            self.search_result_from_cr.update(cr_result)
+            self.total = cr_result["message"]["total-results"]
+            self.fetched += len(cr_result["message"]["items"])
+            self.app.logger.info(self.total)
+            self.app.logger.info(self.fetched)
+            while self.total > self.fetched and self.limit > self.fetched:
+                tmp_result = self.cr.works(query=query, limit=query_limit, offset=self.fetched)
+                cr_result["message"]["items"].extend(tmp_result["message"]["items"])
+                self.total = tmp_result["message"]["total-results"]
+                self.fetched = len(cr_result["message"]["items"])
+                self.app.logger.info(self.total)
+                self.app.logger.info(self.fetched)
+                time.sleep(0.1)
+
+        else:
+            cr_result = self.cr.works(query=query, cursor_max=15000, cursor='*', progress_bar = True)
+            result = cr_result[0]
+            for item in cr_result[1:]:
+                result["message"]["items"].extend(item["message"]["items"])
+                self.total = item["message"]["total-results"]
+                self.fetched = len(result["message"]["items"])
+                self.app.logger.info(self.total)
+                self.app.logger.info(self.fetched)
+            cr_result = result
+            self.app.logger.info("Total, fetched:")
+            self.app.logger.info(self.total)
+            self.app.logger.info(self.fetched)
+            self.search_result_from_cr.update(cr_result)
+            self.total = cr_result["message"]["total-results"]
+            self.app.logger.info("CROSSREF DONE")
+
+            self.app.logger.info("CROSSREF DONE")
+        with open("cr_results.json", "r+", encoding="utf-8") as data_file:
+            # First we load existing data into a dict.
+            try:
+                file_data = json.load(data_file)
+            except JSONDecodeError:
+                file_data = {}
+            data_file.truncate(0)
+            data_file.seek(0)
+            tmp = {self.uuid : self.search_result_from_cr}
+            if file_data:
+                file_data.update(tmp)
+            else:
+                file_data = tmp
+            json.dump(file_data, data_file, indent=4)
+        return cr_result
+
+
+    async def refine_search(self, unrefined_result):
+        """
+        Refines the search query based on the unrefined search result.
+
+        Args:
+        - unrefined_result: The unrefined search result.
+
+        Returns:
+        - refined_result: The refined search result.
+
+        Raises:
+        - None.
+        """
+        summarized_results = []
+        self.app.logger.info("REFINE: Removing all derived works from the list")
+        for item in unrefined_result["message"]["items"]:
+            summarized_results.append(
+                {
+                    "DOI": item["DOI"],
+                    "title": item["title"] if "title" in item else None,
+                    "type": item["type"] if "type" in item else None,
+                }
+            )
+
+        partial_result = {
+            self.uuid: {
+                "total_results": self.search_result_from_cr["message"][
+                    "total-results"
+                ],
+                "on_page": 1,
+                "summary": summarized_results,
+                "results": self.search_result_from_cr["message"]["items"],
+            }
+        }
+        self.app.logger.info("REFINE: Dumping to file")
+        temp = []
+        refined_result = {}
+        for key in partial_result:
+            self.app.logger.info("KEY:")
+            self.app.logger.info(key)
+
+        for item in partial_result[self.uuid]["summary"]:
+            if item["title"]:
+                temp.append(item)
+
+        for item in temp:
+            refined_result[item["DOI"]]=  item
         with open("rr_results.json", "r+", encoding="utf-8") as data_file:
             # First we load existing data into a dict.
             try:
                 file_data = json.load(data_file)
             except JSONDecodeError:
                 file_data = {}
-            summarized_results = []
-            self.app.logger.info("REFINE: Removing all derived works from the list")
-            for item in self.search_result_from_cr['message']['items']:
-                container = "NO"
-                if "container-title" in item:
-                    container = "YES"
-                else:
-                    summarized_results.append({"DOI" : item['DOI'], "title": item['title'] if 'title' in item else None,"type": item['type'] if 'type' in item else None, "container": container})
-            result = {self.uuid : {"total_results": self.search_result_from_cr['message']['total-results'], "on_page" : 1, "summary":summarized_results, "results":self.search_result_from_cr['message']['items']}}
-            if file_data:
-                file_data.update(result)
-            else:
-                file_data = result
-            
-            self.app.logger.info("REFINE: Dumping to file")
             data_file.truncate(0)
             data_file.seek(0)
+            tmp = {self.uuid: refined_result}
+            if file_data:
+                file_data.update(tmp)
+            else:
+                file_data = tmp
             json.dump(file_data, data_file, indent=4)
-            return result
+        return refined_result
 
-    async def check_dois_in_local_db(self, doi):
-        self.app.logger.info("REFINE: Running search in the backend app")
-        coro = asyncio.to_thread(search_bot.search_for_doi, doi, self.live_results, self.app.logger)
-        result = await coro
-        return result
+    async def check_if_exists(self, refined_result):
+        """
+        Checks if the given DOI exists.
 
-    async def check_if_exists_brute_force(self, page_url):
-        self.app.logger.error("REFINE: Brute force search!")
-        if not page_url.startswith(("http:", "https:")):
-            raise ValueError("URL must start with 'http:' or 'https:'")
-        # trunk-ignore(bandit/B310)
-        with urlopen(page_url) as response:
-            data = response.read()
-            text = data.decode("utf-8")
-            for line in text.splitlines():
-                if re.match(r".*Unfortunately, Sci-Hub doesn't have the requested document.*", line):
-                    return False
-                if m := re.match(r".*<embed type=\"application.pdf\"\s*src=\"(.*\.pdf)",line):
-                    direct_download_link = "https:" + str(m.group(1))
-                    self.app.logger.info (direct_download_link)
-                    return True
-        return False
+        Args:
+        - doi: The DOI to be checked.
+        - brute_force: A flag indicating if brute force method should be used.
 
-    async def check_if_exists(self, doi, brute_force = False):
+        Returns:
+        - result: The search result.
+
+        Raises:
+        - None.
+        """
         result = {}
-        result = await self.check_dois_in_local_db(doi)
-        if brute_force and not result:
-            for item in doi:
-                item_link = "https://sci-hub.se/" + item[0]
-                tmp = {"DOI" : item["DOI"], "exists" : await self.check_if_exists_brute_force(item_link), "data": item}
-                result.update(tmp)
-        return result
-
-    async def refine_query(self, unrefined_reqult, brute_force = False):
-        temp = []
-        refined_result = []
-        for key in unrefined_reqult:
-            self.logger.info("KEY:")
-            self.logger.info(key)
-
-        for item in unrefined_reqult[self.uuid]["summary"]:
-            if item["container"] == "NO" and item["title"]:                
-                refined_result.append(item)
-
-        for item in refined_result:
-            temp.append([item["DOI"], item])
-
-        refined_result = await self.check_if_exists(temp)
-
-        for item in refined_result:
+        self.app.logger.info("REFINE: Running search in the backend app")
+        dois = []
+        for item, value in refined_result.items():
+            dois.append([item, value])
+        coro = asyncio.to_thread(
+            search_bot.search_for_doi, dois, self.live_results, self.app.logger
+        )
+        result = await coro
+        result_list = []
+        result_no_db = []
+        for item in result:
             if item["exists"]:
-                self.final_result.append(item["data"])
+                result_list.append(item)
             else:
-                self.not_in_db.append(item["data"])
-        self.hit = len(self.final_result)
-        return self.final_result
-    #TODO: DOłożyć sprawdzenie czy w rafinowanym pliku już nie mamy częściowego wyniku
-    async def answer_query(self):
-        #TODO: DOłożyć sprawdzenie czy w rafinowanym pliku już nie mamy częściowego wyniku tutaj bo zanim w ogóle otworzymy nierafinowany
-        #Search sql for UUID
-        #SQL SELECT * FROM RESULTS WHERE UUID = uuid
-        self.logger.info(f"Search started {self.uuid}")
-        database = None
-        query = self.query
-        with open("cr_results.json", "r+", encoding="utf-8") as cr_file:
-            #tu logika komunikacji z SQL i cała logika związana z wyszukaniem
-            #ale tymczasowo plik
-            try:
-                database =  json.load(cr_file)
-            except JSONDecodeError:
-                pass
-            #TODO: Zwracać i final_result i not_in_db. Not in db_do pliku - i do ręcznego przeglądania potem.
-            if database:
-                for item in database.keys():
-                    if item in self.uuid:
-                        self.result = await self.refine_query(database)
-                        temp = {}
-                        for item in self.result:
-                            temp[item['DOI']] = {"Title" : item['title'], "type": item['type']}
-                        self.result = temp
-                        temp2 = {}
-                        for item in self.not_in_db:
-                            temp2[item['DOI']] = {"Title" : item['title'], "type": item['type']}
-                        self.not_in_db = temp2
-                        return self.result
-                answer = await self.search_crossref(query=query)
-                database.update(answer)
-                cr_file.truncate(0)
-                cr_file.seek(0)
-                json.dump(database,cr_file)
-                self.result = await self.refine_query(answer)
-            else:
-                answer = await self.search_crossref(query=query)
-                database = answer
-                cr_file.truncate(0)
-                cr_file.seek(0)
-                json.dump(database,cr_file)
-                self.result = await self.refine_query(answer)
-                self.app.logger.info("Refined")
-                self.done = True
-            temp = {}
-            for item in self.result:
-                temp[item['DOI']] = {"Title" : item['title'], "type": item['type']}
-            self.result = temp
-            temp2 = {}
-            for item in self.not_in_db:
-                temp2[item['DOI']] = {"Title" : item['title'], "type": item['type']}
-                self.not_in_db = temp2
-            return self.result
+                result_no_db.append(item)
+        self.hit = len(result)
+        return result_list, result_no_db
+
+
+    async def answer_query(self, deep_search=False):
+        """
+        Answers the search query.
+
+        Args:
+        - None.
+
+        Returns:
+        - result: The search result.
+
+        Raises:
+        - None.
+        """
+        self.app.logger.info(f"Search started {self.uuid}")
+        cr_result = await self.search_crossref(query=self.query, deep_search=deep_search)
+        refined_result = await self.refine_search(cr_result)
+        answer, negative_answer = await self.check_if_exists(refined_result)
+
+        self.app.logger.info("Returning result")
+        self.app.logger.info(answer)
+        self.app.logger.info(negative_answer)
+
+        for item in answer:
+            self.final_result[item["DOI"]] = {"Title": item["data"]["title"], "type": item["data"]["type"]}
+        for item in negative_answer:
+            self.not_in_db[item["DOI"]] = {"Title": item["data"]["title"], "type": item["data"]["type"]}
+        self.app.logger.info("Returning result case2")
+        self.app.logger.info(self.final_result)
+        return self.final_result
+
+# ============================= FLASK INTERNALS===============================
+
 
-#============================= FLASK INTERNALS===============================
 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.
+    Starts a Flask application in debug mode without using the reloader.
+
+    Args:
+    - None.
+
+    Returns:
+    - None.
+
+    Raises:
+    - None.
     """
     # 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 "0.0.0.0"
-    and port 5000 using the Waitress WSGI server.
+    Serves the Flask application using the Waitress WSGI server.
+
+    Args:
+    - None.
+
+    Returns:
+    - None.
+
+    Raises:
+    - None.
     """
     serve(app, host=HOST_ADDRESS, port=PORT_ADDRESS)
 
+
 class BackgroundTaskSearch(threading.Thread):
+    """
+    A background task for searching and saving results to files.
+
+    This class extends the `threading.Thread` class and is responsible for running
+    the search task in the background. It retrieves queries from a queue, performs
+    the search, and saves the results to files.
+
+    Attributes:
+        app (App): The application instance.
+    """
+
     def run(self):
-        loop = asyncio.new_event_loop()  # loop = asyncio.get_event_loop()
+        """
+        Run the background task.
+
+        This method is called when the thread is started. It creates a new event loop,
+        runs the `_run` method, and closes the event loop.
+        """
+        loop = asyncio.new_event_loop()
         loop.run_until_complete(self._run())
         loop.close()
 
     async def _run(self):
+        """
+        Perform the search task.
+
+        This method is an asynchronous coroutine that runs in a loop. It retrieves a
+        librarian from the queue, answers the query, and saves the results to files.
+        It also sends the results to a remote server.
+
+        The search task continues running indefinitely until the thread is stopped.
+        """
         while True:
             database = None
             ndb_database = None
             librarian = librarian_queue.get()
             self.app.logger.info("STARTED")
-            result = await librarian.answer_query()
+            result = await librarian.answer_query(librarian.deep_search)
             result = {librarian.uuid: result}
             self.app.logger.info("Saving to file")
+
+            # Save results to "not_in_db.json" file
             with open("not_in_db.json", "r+", encoding="utf-8") as ndb_file:
                 try:
-                    ndb_database =  json.load(ndb_file)
+                    ndb_database = json.load(ndb_file)
                 except JSONDecodeError:
                     pass
                 if ndb_database:
@@ -248,9 +388,10 @@ class BackgroundTaskSearch(threading.Thread):
                 ndb_file.seek(0)
                 json.dump(ndb_database, ndb_file)
 
+            # Save results to "s_results.json" file
             with open("s_results.json", "r+", encoding="utf-8") as s_file:
                 try:
-                    database =  json.load(s_file)
+                    database = json.load(s_file)
                 except JSONDecodeError:
                     pass
                 if database:
@@ -267,26 +408,41 @@ class BackgroundTaskSearch(threading.Thread):
 
             self.app.logger.info(result)
             coroutine = asyncio.to_thread(
-            requests.post,
-            f"{MAIN_BOT_ADDRESS}{SEND_RESULTS}",
-            json=result,
-            timeout=360,
-    )       
+                requests.post,
+                f"{MAIN_BOT_ADDRESS}{SEND_RESULTS}",
+                json=result,
+                timeout=360,
+            )
             self.app.logger.info("SENT")
             result = await coroutine
             self.app.logger.info(result.status_code)
             self.app.logger.info("SEND CONFIRMED")
             time.sleep(1)
-            
-#==================================SERVER ROUTES==========================================
+
+
+# ==================================SERVER ROUTES==========================================
 @app.route("/query", methods=["POST"])
 async def query_database():
+    """
+    Endpoint for querying the database.
+
+    This function receives a POST request containing a JSON payload with a query and a UUID.
+    It creates a Librarian object with the query and UUID,
+    and adds it to the librarian_queue and librarian_list.
+    Finally, it returns a JSON response indicating the success
+    of the operation, along with the query, UUID,
+    and the current size of the librarian_queue.
+
+    Returns:
+        tuple: A tuple containing a JSON response and a status code.
+    """
     record = json.loads(request.data)
     app.logger.info(record)
     app.logger.info(record["query"])
     app.logger.info(record["UUID"])
     uuid = record["UUID"]
-    cl = Librarian(app, record["query"], uuid)
+    deep_search = record["deep_search"]
+    cl = Librarian(app, record["query"], uuid, deep_search)
     librarian_queue.put(cl)
     librarian_list.append(cl)
     answer_data = (record["query"], record["UUID"], librarian_queue.qsize())
@@ -296,8 +452,15 @@ async def query_database():
     )
     return return_data
 
+
 @app.route("/get_partial_result", methods=["POST"])
 async def get_partial():
+    """
+    Retrieves the partial result for a given UUID.
+
+    Returns:
+        A JSON response containing the partial result.
+    """
     record = json.loads(request.data)
     app.logger.info(record)
     app.logger.info(record["UUID"])
@@ -311,25 +474,34 @@ async def get_partial():
     )
     return return_data
 
-#=======================================MAIN===================================================
+
+# =======================================MAIN===================================================
 if __name__ == "__main__":
-    logger = app.logger
-    logger.setLevel(logging.DEBUG)
+    app.logger.setLevel(logging.DEBUG)
+    h1 = handlers.RotatingFileHandler(
+        filename="D:\\logs\\librarian.log",
+        encoding="utf-8",
+        mode="a",
+        maxBytes=6 * 1024 * 1024,
+        backupCount=6,
+    )
+
+    app.logger.addHandler(h1)
     threads = []
     threads.append(threading.Thread(target=waitress_run))
-    #threads.append(threading.Thread(target=flask_debug))
+    # threads.append(threading.Thread(target=flask_debug))
     bgtask = BackgroundTaskSearch()
     bgtask.app = app
     threads.append(bgtask)
-    threads.append(threading.Thread(target = scrape_bot.scraper, args=(logger,)))
+    threads.append(threading.Thread(target=scrape_bot.scraper, args=(app.logger,)))
     i = 0
     for worker in threads:
         try:
-            logger.info(f"App number: {i}")
-            i+=1
+            app.logger.info("App number: %s", i)
+            i += 1
             worker.start()
         except RuntimeError as e:
-            logger.error("Exploded")
+            app.logger.error("Exploded")
             print(str(e))
     for worker in threads:
         worker.join()

conjurer_librarian/count_lines.py

@@ -0,0 +1,8 @@
+
+FILEPTH = r"C:\Database\chunks\4_chunk.txt"
+
+with open(FILEPTH, "r", encoding="utf-8") as file:
+    tab = file.readlines()
+    print(len(tab))
+
+    #1842295

conjurer_librarian/install_librarian_service.sh

@@ -1,11 +1,33 @@
 #!/bin/bash
-python3 -m venv /home/pi/Conjurer_librarian/env
-cp  /home/pi/conjurer/conjurer_librarian/conjurer_librarian.py ./Conjurer_librarian/
-cp  /home/pi/conjurer/conjurer_librarian/requirements_librarian.txt ./Conjurer_librarian/
-cd /home/pi/Conjurer_librarian
-source /home/pi/Conjurer_librarian/env/bin/activate
-./env/bin/python3 -m pip install --upgrade pip
-./env/bin/python3 -m pip install -r requirements_librarian.txt
-deactivate
+# This script sets up a virtual environment for the Conjurer Librarian service and installs the required dependencies.
 
-cp  /home/pi/conjurer/conjurer_librarian/conjurer_librarian.py ./Conjurer_librarian/
+
+# Create a virtual environment at /home/pi/Conjurer_librarian/env
+python3 -m venv /home/pi/Conjurer_librarian/env
+
+# Copy the Conjurer Librarian Python script to the appropriate directory
+cp /home/pi/conjurer/conjurer_librarian/conjurer_librarian.py ./Conjurer_librarian/
+
+# Copy the requirements file to the appropriate directory
+cp /home/pi/conjurer/conjurer_librarian/requirements_librarian.txt ./Conjurer_librarian/
+
+# Change directory to /home/pi/Conjurer_librarian
+cd /home/pi/Conjurer_librarian
+
+touch /home/pi/Conjurer/rr_results.json
+touch /home/pi/Conjurer/cr_results.json
+touch /home/pi/Conjurer/s_results.json
+touch /home/pi/Conjurer/rr_results.json
+touch /home/pi/Conjurer/not_in_db.json
+
+# Activate the virtual environment
+source /home/pi/Conjurer_librarian/env/bin/activate
+
+# Upgrade pip
+./env/bin/python3 -m pip install --upgrade pip
+
+# Install the required dependencies
+./env/bin/python3 -m pip install -r requirements_librarian.txt
+
+# Deactivate the virtual environment
+deactivate

conjurer_librarian/requirements_librarian.txt

@@ -1,3 +1,3 @@
 habanero
 waitress
-flask
+flask[async]

conjurer_librarian/scrape_bot.py

@@ -1,46 +1,69 @@
+"""
+This module contains the code for the scrape bot.
+"""
+
 import json
-from json.decoder import JSONDecodeError
-from urllib.request import urlopen
-from requests import Timeout,ConnectTimeout, ConnectionError
-from queue import Queue
+import logging
+import random
 import re
 import time
-import random
-import logging
+from json import JSONDecodeError
+from queue import Queue
 from threading import Thread
-SCR_DATABASE_PATH = r'C:\\Database\\chunks\\'
+from urllib.request import urlopen
+
+from requests import ConnectionError as RequestsConnectionError
+from requests import ConnectTimeout, Timeout
+
+SCR_DATABASE_PATH = r"C:\\Database\\chunks\\"
 SCR_FILENAME = "40_chunk.txt"
 SCR_ENCODING = "utf-8"
 
 WORK_Q = Queue()
 random.seed()
+
+
 def load_ndb_to_q(logger):
+    """
+    This function loads items from the not_in_db.json file into the work queue.
+    """
     logger.info("Loader started")
-    while True:    
+    while True:
         with open("not_in_db.json", "r+", encoding="utf-8") as ndb_file:
             try:
-                ndb_database =  json.load(ndb_file)
-                for item in ndb_database.keys():
-                    logger.info(item)
-                    url = f"https://sci-hub.se/{item}"
-                    WORK_Q.put([item, url, False])
+                ndb_database = json.load(ndb_file)
+                for _ in range (1,10):
+                    try:
+                        key = next(iter(ndb_database))
+                        _ = ndb_database.pop(key)
+                        logger.info(key)
+                        url = f"https://sci-hub.se/{key}"
+                        WORK_Q.put([key, url, False])
+                    except StopIteration:
+                        break
                 ndb_file.truncate(0)
+                ndb_file.seek(0)
+                json.dump(ndb_database, ndb_file, indent=4)
             except JSONDecodeError:
-                time.sleep(60*60*2)
-                pass
-        time.sleep(180)
+                time.sleep(60 * 60 * 3)
+        time.sleep(60*60*3)
+
 
 def check_if_exists_brute_force(logger):
+    """
+    This function checks if a document exists using brute force search.
+    """
+    # Function code here
     while True:
         logger.info("Scraper tick")
         item = WORK_Q.get()
-        page_url =item[1] 
+        page_url = item[1]
         logger.error("REFINE: Brute force search!")
         if not page_url.startswith(("http:", "https:")):
             raise ValueError("URL must start with 'http:' or 'https:'")
         blocked = True
         try:
-        # trunk-ignore(bandit/B310)
+            # trunk-ignore(bandit/B310)
             with urlopen(page_url) as response:
                 data = response.read()
                 text = data.decode("utf-8")
@@ -50,44 +73,64 @@ def check_if_exists_brute_force(logger):
                     blocked = False
                 else:
                     for line in text.splitlines():
-                        if re.match(r".*Unfortunately, Sci-Hub doesn't have the requested document.*", line):
+                        if re.match(
+                            r".*Unfortunately, Sci-Hub doesn't have the requested document.*",
+                            line,
+                        ):
                             blocked = False
                             logger.info("Not found")
                             item[2] = False
-                        if m := re.match(r".*<embed type=\"application.pdf\"\s*src=\"(.*\.pdf)",line):
+                        if m := re.match(
+                            r".*<embed type=\"application.pdf\"\s*src=\"(.*\.pdf)", line
+                        ):
                             blocked = False
                             direct_download_link = "https:" + str(m.group(1))
-                            logger.info (direct_download_link)
-                            with open(SCR_DATABASE_PATH + SCR_FILENAME, "a", encoding=SCR_ENCODING) as operated_file:
+                            logger.info(direct_download_link)
+                            with open(
+                                SCR_DATABASE_PATH + SCR_FILENAME,
+                                "a",
+                                encoding=SCR_ENCODING,
+                            ) as operated_file:
                                 operated_file.write("\n")
                                 operated_file.write(item[0])
                                 item[2] = True
-        except (Timeout,ConnectTimeout, ConnectionRefusedError, ConnectionError):
+        except (
+            Timeout,
+            ConnectTimeout,
+            ConnectionRefusedError,
+            ConnectionError,
+            RequestsConnectionError,
+        ):
             pass
         if blocked:
             logger.info(item)
             logger.info(text)
             logger.error("Got blocked. Fuck.")
-            time.sleep(60*60*72)
+            time.sleep(60 * 60 * 72)
         # trunk-ignore(bandit/B311)
-        rand = random.randint(1,100)
-        logger.info(f"Sleeping for {3*rand} minutes")
-        time.sleep(180*rand)
+        rand = random.randint(1, 60)
+        logger.info(f"Sleeping for {2*rand} minutes")
+        time.sleep(120 * rand)
 
-def scraper(logger = None):
+
+def scraper(logger=None):
+    """
+    This function is responsible for scraping data.
+    """
     if not logger:
         logger = logging.getLogger()
         logger.setLevel("DEBUG")
         h1 = logging.StreamHandler()
         logger.addHandler(h1)
         logger.info("No logger set. Test run")
-  
-    loader = Thread(target = load_ndb_to_q, args = (logger,))
-    scraper = Thread(target = check_if_exists_brute_force, args = (logger,))
+
+    loader = Thread(target=load_ndb_to_q, args=(logger,))
+    _scraper = Thread(target=check_if_exists_brute_force, args=(logger,))
     loader.start()
-    scraper.start()
+    _scraper.start()
     loader.join()
-    scraper.join()
+    _scraper.join()
+
 
 if __name__ == "__main__":
-    scraper()
+    scraper()

conjurer_librarian/search_bot.py

@@ -1,28 +1,66 @@
-#TODO: Wpiemdolić to wszystko w klasę z loggerem przysłanym z góry
+"""
+This module contains functions for searching for DOI (Digital Object Identifier)
+in a list of live results.
+It includes a producer-consumer pattern implementation using threads and queues.
 
-from queue import Queue, Empty
+Functions:
+- producer: Reads lines from a file and puts them into an output queue.
+- consumer: Consumes items from an input queue and checks if DOI exists in the live results list.
+- search_for_doi: Searches for DOI in live results using the producer-consumer pattern.
+
+Global Variables:
+- MAXTHREADS: Maximum number of worker threads.
+- DATABASE_PATH: Path to the database files.
+- ENCODING: Encoding of the database files.
+- CHUNK: File name pattern for the database files.
+- _sentinel: Sentinel object used to signal termination.
+- result_list: List to store the search results.
+- WORK_Q_SIZE: Maximum size of the work queue.
+"""
+
+# TODO: Wpiemdolić to wszystko w klasę z loggerem przysłanym z góry
+from queue import Empty, Queue
 from threading import Thread
+import time
 q = Queue()
+#TODO: Count number of lines in files and print to approximate on which part of the file search is
 
-#TODO: DATA FOR TEST ONLY
-#MAXTHREADS = 5
-#DATABASE_PATH = r'C:\\Database\\chunks_1\\'
+# DATA FOR TEST ONLY
+# MAXTHREADS = 5
+# DATABASE_PATH = r'C:\\Database\\chunks_1\\'
 
-#TODO: DEPLOYMENT DATA
+# DEPLOYMENT DATA
 MAXTHREADS = 41
-DATABASE_PATH = r'C:\\Database\\chunks\\'
+DATABASE_PATH = r"C:\\Database\\chunks\\"
 
 ENCODING = "utf-8"
-CHUNk = "_chunk.txt"
+CHUNK = "_chunk.txt"
 _sentinel = object()
-result_list = []
-WORK_Q_SIZE = 15500000
+WORK_Q_SIZE = 35500000
 
-def producer(out_q, control_q, filename, logger):
+
+def producer(out_q, control_q, filename, _logger):
+    """
+    Produces items from the output queue and puts them into the control queue.
+
+    Args:
+        out_q (Queue): Output queue.
+        control_q (Queue): Control queue.
+        filename (str): Name of the file.
+        _logger: Logger object for logging.
+    """
     with open(DATABASE_PATH + filename, "r+", encoding=ENCODING) as operated_file:
-        logger.info(f"Worker {filename} ")
+        print(f"Worker {filename} ")
+        line_no = 0
         while True:
             line = operated_file.readline()
+            line_no += 1
+            print(f"\t \t \t \t \t \t W{filename}{line_no}\r", end="")
+
+            if not line:
+                print(f"EOF {filename}")
+                break
+
             if not line:
                 break
             out_q.put(line)
@@ -30,77 +68,133 @@ def producer(out_q, control_q, filename, logger):
                 check = control_q.get(block=False)
             except Empty:
                 check = False
-                pass
+
             if check is _sentinel:
-                logger.info("TERM signal received")
+                print("TERM signal received")
                 control_q.put(check)
                 break
-        logger.info(f"Worker finished: {filename}")
+        print(f"Worker finished: {filename}")
         out_q.put(_sentinel)
- 
-#IMPORTANT!!! ONLY ONE CONSUMER THREAD AS WE ARE NOT PUTTING SENTINELS BACK
-#TODO: Change doi to tuple list and only put term when all doi are found => (doi, True)
-def consumer(in_q, control_q, doi, live_results, logger):
-    sentinels = 0
-    for item in doi:
-        result_list.append({"DOI" : item[0], "exists" : False, "data" : item[1]})
+
+
+# IMPORTANT!!! ONLY ONE CONSUMER THREAD AS WE ARE NOT PUTTING SENTINELS BACK
+def consumer(in_q, control_q, doi, live_results, result_list, control_dict, no, _logger):
+    """
+    Consumes items from an input queue and checks if DOI exists in the live results list.
+
+    Args:
+        in_q (Queue): Input queue.
+        control_q (Queue): Control queue.
+        doi (list): List of DOI to search for.
+        live_results (list): List to store the search results.
+        _logger: Logger object for logging.
+    """
+    print(f"Consumer thread started: {no} no")
+    empty_counter = 0
+    alive_no = 0
     while True:
         done_check = True
-        data = in_q.get()
-        if data is _sentinel:
-            logger.info("Worker finished")
-            sentinels += 1
-        else:
-            for item in result_list:
-                if item["DOI"] in data and not item["exists"]:
-                    logger.info(data)
-                    logger.info("HIT")
-                    item["exists"] = True
-                    live_results.append(item)
-                done_check = done_check and item["exists"]
-            if done_check:
-                control_q.put(_sentinel)
-        if sentinels >= MAXTHREADS:
-            logger.info("All workers finished")
+        try:
+            data = in_q.get(block=True, timeout = 1)
+            if data is _sentinel:
+                control_dict["sentinels"] += 1
+                print(f"Workers finished: {control_dict['sentinels']} reported by consumer {no}")
+
+            else:
+                empty_counter = 0
+                alive_no += 1
+                print(f"C{no}__{alive_no}\r", end="")
+
+                for item in result_list:
+                    if item["DOI"] in data and not item["exists"]:
+                        print(f"HIT in {no} content {data[0]} line {data[1]} file {data[2]} {item["exists"]}")
+                        _logger.info(data)
+                        _logger.info("HIT")
+                        item["exists"] = True
+                        live_results.append(item)
+                    done_check = done_check and item["exists"]
+                if done_check:
+                    control_q.put(_sentinel)
+        except Empty:
+            empty_counter += 1
+            time.sleep(1)
+            print(f"Consumer {no} empty")
+            if empty_counter > 5:
+                print("Consumer %s empty lvl 2", no)
+                time.sleep(2)
+            elif empty_counter > 10:
+                print(f"Consumer thread finished {no}")
+                break
+
+        if control_dict["sentinels"] >= MAXTHREADS:
+            _logger.info(f"All workers finished {no}")
             break
 
 
-def search_for_doi(doi, live_results, logger):
+
+def search_for_doi(doi, live_results, _logger):
+    """
+    Search for DOI in live_results using _logger for logging.
+
+    Args:
+        doi (list): List of DOI to search for.
+        live_results (list): List to store the search results.
+        _logger: Logger object for logging.
+    """
+    control_dict = {"sentinels":0}
+    result_list = []
     threads = []
     work_q = Queue(maxsize=WORK_Q_SIZE)
     control_q = Queue()
-    t_cons = Thread(target = consumer, args = (work_q, control_q, doi, live_results, logger))
-    logger.info("Consumer thread created")
-    threads.append(t_cons)
-    for i in range(0,MAXTHREADS):
-        #TODO: TEST DATA
-        #filename = "test" + str(i) + CHUNk
-        #TODO: DEPLOYMENT DATA
-        filename = str(i) + CHUNk
-        logger.info(f"Creating worker thread no: {i}")
-        threads.append(Thread(target = producer, args = (work_q, control_q, filename,logger)))
+
+    for item in doi:
+        result_list.append({"DOI": item[0], "exists": False, "data": item[1]})
+
+    for i in range (0, (len(doi)//1000)+2):
+        t_cons = Thread(
+            target=consumer, args=(work_q, control_q, doi, live_results, result_list, control_dict, i, _logger)
+        )
+        _logger.info("Consumer thread created")
+        threads.append(t_cons)
+    for i in range(0, MAXTHREADS):
+        # TEST DATA
+        # filename = "test" + str(i) + CHUNk
+        # DEPLOYMENT DATA
+        filename = str(i) + CHUNK
+        _logger.info(f"Creating worker thread no: {i}")
+        threads.append(
+            Thread(target=producer, args=(work_q, control_q, filename, _logger))
+        )
     for worker in threads:
         worker.start()
     for worker in threads:
         worker.join()
     return result_list
 
+
 if __name__ == "__main__":
     import logging
+
     logger = logging.getLogger()
     logger.setLevel("DEBUG")
     h1 = logging.StreamHandler()
     logger.addHandler(h1)
     logger.info("TEST RUN")
     live_result = []
-    logger.info(search_for_doi([
-        ("10.1002/9781118786352.wbieg0998.pub2","DATA"),
-        ("10.1002/j.2050-0416.2002.tb00563.x","DATA"),
-        ("10.1111/j.1365-2958.1994.tb00448.x","DATA"),
-        ("10.2165/00128415-200309690-00017","DATA"),
-        ("10.5772/48313","DATA"),
-        ("10.15803/ijnc.7.2_419","DATA"),
-        ("10.1051/0004-6361/201321596e","DATA"),
-        ("10.2307/40835941","DATA"),
-        ], live_result, logger))
+    logger.info(
+        search_for_doi(
+            [
+                ("10.1002/9781118786352.wbieg0998.pub2", "DATA"),
+                ("10.1002/j.2050-0416.2002.tb00563.x", "DATA"),
+                ("10.1111/j.1365-2958.1994.tb00448.x", "DATA"),
+                ("10.2165/00128415-200309690-00017", "DATA"),
+                ("10.5772/48313", "DATA"),
+                ("10.15803/ijnc.7.2_419", "DATA"),
+                ("10.1051/0004-6361/201321596e", "DATA"),
+                ("10.2307/40835941", "DATA"),
+            ],
+            live_result,
+            logger,
+        )
+    )
     logger.info(live_result)

conjurer_librarian/search_bot2.py

@@ -0,0 +1,206 @@
+"""
+This module contains functions for searching for DOI (Digital Object Identifier)
+in a list of live results.
+It includes a producer-consumer pattern implementation using threads and queues.
+
+Functions:
+- producer: Reads lines from a file and puts them into an output queue.
+- consumer: Consumes items from an input queue and checks if DOI exists in the live results list.
+- search_for_doi: Searches for DOI in live results using the producer-consumer pattern.
+
+Global Variables:
+- MAXTHREADS: Maximum number of worker threads.
+- DATABASE_PATH: Path to the database files.
+- ENCODING: Encoding of the database files.
+- CHUNK: File name pattern for the database files.
+- _sentinel: Sentinel object used to signal termination.
+- result_list: List to store the search results.
+- WORK_Q_SIZE: Maximum size of the work queue.
+"""
+
+# TODO: Wpiemdolić to wszystko w klasę z loggerem przysłanym z góry
+from multiprocessing import Manager, Process, Queue
+from queue import Empty, Full
+import time
+
+# DATA FOR TEST ONLY
+#MAXTHREADS = 6
+#DATABASE_PATH = r'C:\\Database\\chunks_1\\'
+
+# DEPLOYMENT DATA
+MAXTHREADS = 41
+DATABASE_PATH = r"C:\\Database\\chunks\\"
+
+ENCODING = "utf-8"
+CHUNK = "_chunk.txt"
+_sentinel = None
+WORK_Q_SIZE = 355000
+
+
+def producer(out_q, control_q, filename, _logger):
+    """
+    Produces items from the output queue and puts them into the control queue.
+
+    Args:
+        out_q (Queue): Output queue.
+        control_q (Queue): Control queue.
+        filename (str): Name of the file.
+        _logger: Logger object for logging.
+    """
+    with open(DATABASE_PATH + filename, "r+", encoding=ENCODING) as operated_file:
+        print(f"Worker {filename} ")
+        line_no = 0
+        while True:
+            line = operated_file.readline()
+            line_no += 1
+            print(f"\t \t \t W{filename}{line_no}\r", end="")
+
+            if not line:
+                print(f"EOF {filename}")
+                break
+            try:
+                out_q.put([line, line_no, filename], block = True, timeout = 60)
+            except Full:
+                print("queue fulll")
+            try:
+                check = control_q.get(block=False)
+            except Empty:
+                check = False
+            if check is None:
+                print(f"TERM signal received {filename}")
+                control_q.put(check)
+                control_q.close()
+                break
+        print(f"Worker finished: {filename}")
+        out_q.put(_sentinel)
+        out_q.close()
+
+
+
+# IMPORTANT!!! ONLY ONE CONSUMER THREAD AS WE ARE NOT PUTTING SENTINELS BACK
+def consumer(in_q, control_q, doi, live_results, result_list, control_dict, no, _logger):
+    """
+    Consumes items from an input queue and checks if DOI exists in the live results list.
+
+    Args:
+        in_q (Queue): Input queue.
+        control_q (Queue): Control queue.
+        doi (list): List of DOI to search for.
+        live_results (list): List to store the search results.
+        _logger: Logger object for logging.
+    """
+    print(f"Consumer thread started: {no} no")
+    empty_counter = 0
+    alive_no = 0
+    while True:
+        done_check = True
+        try:
+            data = in_q.get(block=True, timeout = 1)
+            empty_counter = 0
+            if data is None:
+                control_dict["sentinels"] += 1
+                print(f"Workers finished: {control_dict['sentinels']} reported by consumer {no}")
+            else:
+                empty_counter = 0
+                if alive_no > 9:
+                    alive_no = 0
+                alive_no += 1
+                print(f"C{no}{alive_no}\r", end="")
+                for item in result_list:
+                    if item["DOI"] in data[0] and not item["exists"]:
+                        print(f"HIT in {no} content {data[0]} line {data[1]} file {data[2]} {item["exists"]}")
+                        item["exists"] = True
+                        live_results.append(item)
+                    done_check = done_check and item["exists"]
+                if done_check:
+                    control_q.put(_sentinel)
+        except Empty:
+            empty_counter += 1
+            time.sleep(1)
+            print(f"Consumer {no} empty")
+            if empty_counter > 5:
+                print("Consumer %s empty lvl 2", no)
+                time.sleep(2)
+            elif empty_counter > 10:
+                print(f"Consumer thread finished {no}")
+                break
+        if control_dict["sentinels"] >= MAXTHREADS:
+            print(f"All workers finished killing {no}")
+            break
+    print("Consumer thread finished %s",no )
+    control_q.close()
+
+
+def search_for_doi(doi, live_results, _logger):
+    """
+    Search for DOI in live_results using _logger for logging.
+
+    Args:
+        doi (list): List of DOI to search for.
+        live_results (list): List to store the search results.
+        _logger: Logger object for logging.
+    """
+    with Manager() as manager:
+        control_dict = manager.dict()
+        control_dict["sentinels"] = 0
+        result_list = []
+        for item in doi:
+            result_list.append({"DOI": item[0], "exists": False, "data": item[1]})
+        result_list_proxy = manager.list(result_list)
+
+        threads = []
+        work_q = Queue(maxsize=WORK_Q_SIZE)
+        control_q = Queue()
+        for i in range(0, MAXTHREADS):
+            # TEST DATA
+            #filename = "test" + str(i) + CHUNK
+            # DEPLOYMENT DATA
+            filename = str(i) + CHUNK
+            print(f"Creating worker thread no: {i}")
+            threads.append(
+                Process(target=producer, args=(work_q, control_q, filename, _logger))
+            )
+        for i in range (0, (len(doi)//1000)+5):
+            t_cons = Process(
+                target=consumer, args=(work_q, control_q, doi, live_results, result_list_proxy, control_dict, i, _logger)
+            )
+            print("Consumer thread created")
+            threads.append(t_cons)
+
+        for worker in threads:
+            worker.start()
+        for worker in threads:
+            worker.join()
+        result_list = list(result_list_proxy)
+        for worker in threads:
+            worker.close()
+        return result_list
+
+
+if __name__ == "__main__":
+    import logging
+
+    logger = logging.getLogger()
+    logger.setLevel("DEBUG")
+    h1 = logging.StreamHandler()
+    logger.addHandler(h1)
+    print("TEST RUN")
+    live_result = []
+    print(
+        search_for_doi(
+            [
+                ("10.1002/9781118786352.wbieg0998.pub2", "DATA"),
+                ("10.1002/j.2050-0416.2002.tb00563.x", "DATA"),
+                ("10.1111/j.1365-2958.1994.tb00448.x", "DATA"),
+                ("10.2165/00128415-200309690-00017", "DATA"),
+                ("10.5772/48313", "DATA"),
+                ("10.15803/ijnc.7.2_419", "DATA"),
+                ("10.1051/0004-6361/201321596e", "DATA"),
+                ("10.2307/40835941", "DATA"),
+                ("NOT_ON_LIST", "DATA"),
+            ],
+            live_result,
+            logger,
+        )
+    )
+    print(live_result)

conjurer_librarian/test_send.py

@@ -0,0 +1,45 @@
+import asyncio
+import json
+import logging
+from json.decoder import JSONDecodeError
+from logging import handlers
+import requests
+
+MAIN_BOT_ADDRESS = "http://192.168.1.191:5000"
+SEND_RESULTS = "/conjurer"
+
+async def send_results():
+    logger = logging.getLogger()
+    logger.setLevel(logging.DEBUG)
+    h1 = handlers.RotatingFileHandler(
+        filename="D:\\logs\\librarian.log",
+        encoding="utf-8",
+        mode="a",
+        maxBytes=6 * 1024 * 1024,
+        backupCount=6,
+    )
+
+    logger.addHandler(h1)
+
+    with open("s_results.json", "r+", encoding="utf-8") as s_file:
+        try:
+            database = json.load(s_file)
+        except JSONDecodeError:
+            pass
+    result = database["4bacbca0-ce3b-45c6-90a1-05c70b46b740"]
+    result = {"4bacbca0-ce3b-45c6-90a1-05c70b46b740":result}
+
+    coroutine = asyncio.to_thread(
+        requests.post,
+        f"{MAIN_BOT_ADDRESS}{SEND_RESULTS}",
+        json=result,
+        timeout=360,
+    )
+    logger.info("SENT")
+    result = await coroutine
+    logger.info(result.status_code)
+    logger.info("SEND CONFIRMED")
+async def main():
+    await send_results()
+if __name__ == "__main__":
+    asyncio.run(main())

conjurer_musician/conjurer_musician.py

@@ -6,7 +6,9 @@ API endpoints.
 """
 import json
 import logging
+import os
 import re
+import requests
 import threading
 import time
 from datetime import datetime
@@ -14,10 +16,11 @@ from logging import handlers
 from pathlib import Path
 from platform import uname
 from sys import platform
-
-from flask import Flask, jsonify, redirect, request, send_from_directory
+from flask import Flask, jsonify, redirect, request, send_from_directory, render_template
 from waitress import serve
 
+MAIN_BOT_ADDRESS = "http://192.168.1.191:5000"
+MUSIC_TRACKER = "/prepped_tracks"
 HOST_ADDRESS = "192.168.1.15"
 PORT_ADDRESS = 5000
 if platform in ("linux", "linux2"):
@@ -28,6 +31,8 @@ if platform in ("linux", "linux2"):
         NETRC_FILE = "/home/mtuszowski/.netrc"
         LOGSTORE = "/home/mtuszowski/conjurer/logs/"
         ENCODING = "utf-8"
+        RADIOLOG_PATH = '/home/pi/Conjurer/radio_log.log'
+        PERSISTENCE_PATH = '/home/pi/Conjurer/persistence.log'
 
     else:
         LOGFILE = "/home/pi/Conjurer/discord_mus_service.log"
@@ -35,53 +40,50 @@ if platform in ("linux", "linux2"):
         LOGSTORE = "/home/pi/RetroPie/logs/"
         ENCODING = "utf-8"
         MUSIC_FOLDER = "/home/pi/RetroPie/mp3/"
+        PRIORITY_FOLDER = "/home/pi/RetroPie/mp3/Magiczne i chuj/"
+        RADIOLOG_PATH = '/home/pi/Conjurer/radio_log.log'
+        PERSISTENCE_PATH = '/home/pi/Conjurer/persistence.log'
 
 
 music_file_list = []
-
-
-def create_playlist():
-    """
-    Reads a JSON file containing a playlist and writes the playlist items to a text file.
-
-    The JSON file path is '/home/pi/Conjurer/playlist.json',
-    and the text file path is '/home/pi/Conjurer/all_playlist.playlist'.
-
-    Raises:
-        JSONDecodeError: If the JSON file cannot be decoded.
-
-    """
-    with open("/home/pi/Conjurer/playlist.json", "r+", encoding="utf-8") as r_file:
-        with open(
-            "/home/pi/Conjurer/all_playlist.playlist", "w", encoding="utf-8"
-        ) as w_file:
-            try:
-                playlist = json.load(r_file)
-                for item in playlist:
-                    w_file.write(item)
-                    w_file.write("\n")
-            except json.JSONDecodeError:
-                pass
-
+priority_list = []
 
 def rescan():
     """
     The `rescan` function logs a message, scans for mp3 files in a specified folder,
     and adds them to a list of music files.
     """
-    logging.info("Rescan triggered")
+    logger = logging.getLogger("conjurer_musician")
+    logger.info("Rescan triggered")
+
     for mp3_item in Path.glob(Path(MUSIC_FOLDER), "**/*.mp3"):
         temp_music_file = mp3_item.as_posix()
         if platform == "win32":
             temp_music_file = temp_music_file.replace("/", "\\")
         music_file_list.append(temp_music_file)
-    with open("/home/pi/Conjurer/playlist.json", "r+", encoding="utf-8") as s_file:
-        database = music_file_list
-        # self.app.logger.info("DUMPING DATA")
-        s_file.truncate(0)
-        s_file.seek(0)
-        json.dump(database, s_file)
-    create_playlist()
+
+    for mp3_item in Path.glob(Path(PRIORITY_FOLDER), "**/*.mp3"):
+        temp_music_file = mp3_item.as_posix()
+        if platform == "win32":
+            temp_music_file = temp_music_file.replace("/", "\\")
+        priority_list.append(temp_music_file)
+
+    with open(
+            "/home/pi/Conjurer/all_playlist.playlist", "w", encoding="utf-8"
+        ) as w_file:
+        try:
+            for item in music_file_list:
+                w_file.write(item)
+                w_file.write("\n")
+        except json.JSONDecodeError:
+            pass
+    with open("/home/pi/Conjurer/hit.playlist", "w", encoding="utf-8") as w_file:
+        try:
+            for item in priority_list:
+                w_file.write(item)
+                w_file.write("\n")
+        except json.JSONDecodeError:
+            pass
 
 
 def thread_rescan():
@@ -89,13 +91,87 @@ def thread_rescan():
     The `thread_rescan` function periodically triggers a rescan operation after a specified time
     interval.
     """
-    logging.info("Starting filesystemupdater")
+    logger = logging.getLogger("conjurer_musician")
+    logger.info("Starting filesystemupdater")
     while True:
         time.sleep(60 * 60 * 24)
-        logging.info("Rescan triggered")
+        logger.info("Rescan triggered")
         rescan()
 
 
+def scan_tracks():
+    #Set the filename and open the file
+    logger = logging.getLogger("conjurer_musician")
+
+    file = open(RADIOLOG_PATH,'r')
+    #Find the size of the file and move to the end
+    st_results = os.stat(RADIOLOG_PATH)
+    st_size = st_results[6]
+    file.seek(st_size)
+    st_results1 = os.stat(PERSISTENCE_PATH)
+    prev_st_size1 = st_results[6]
+
+    while 1:
+
+        st_results1 = os.stat(PERSISTENCE_PATH)
+        st_size1 = st_results1[6]
+        if prev_st_size1 != st_size1:
+            while prev_st_size1 != st_size1:
+                prev_st_size1 = st_size1
+                st_results1 = os.stat(PERSISTENCE_PATH)
+                st_size1 = st_results1[6]
+                time.sleep(0.1)
+            file1 = open(PERSISTENCE_PATH, 'r')
+            lines = file1.readlines()
+            result = ["next", lines[2]]
+            file1.close()
+            returned = requests.post(
+                    f"{MAIN_BOT_ADDRESS}{MUSIC_TRACKER}",
+                    json=result,
+                    timeout=360)
+            logger.info("SENT")
+            logger.info(returned.status_code)
+            logger.info("SEND CONFIRMED")
+
+        where = file.tell()
+        line = file.readline()
+        if not line:
+            time.sleep(1)
+            file.seek(where)
+        else:
+            if re.match(".*Prepared.*",line):
+                result = None
+                if re.match(".*jingles.*", line):
+                    logger.info("jingles")
+                    logger.info(line) # already has newline
+                    result = ["jingles", line]
+                elif re.match(".*priority.*", line):
+                    logger.info("priority")
+                    logger.info(line) # already has newline
+                    result = ["priority", line]
+                elif re.match(".*hit.*", line):
+                    logger.info("hit")
+                    logger.info(line) # already has newline
+                    result = ["hit", line]
+                elif re.match(".*all_playlist.*", line):
+                    logger.info("all")
+                    logger.info(line) # already has newline
+                    result = ["all", line]
+                elif re.match(".*request.*", line):
+                    logger.info("requests")
+                    logger.info(line) # already has newline
+                    result = ["requests", line]
+                if result:
+                    returned = requests.post(
+                    f"{MAIN_BOT_ADDRESS}{MUSIC_TRACKER}",
+                    json=result,
+                    timeout=360)
+                    logger.info("SENT")
+                    logger.info(returned.status_code)
+                    logger.info("SEND CONFIRMED")
+        time.sleep(0.1)
+
+
 app = Flask(__name__)
 
 
@@ -202,7 +278,9 @@ def wyszukaj(word_list, how_many, _logger=None, return_to_bot=True):
                 return_list.append(search_weight[itr])
                 if not return_to_bot:
                     with open(
-                        "/home/pi/Conjurer/priority_queue.playlist", "r+", encoding="utf-8"
+                        "/home/pi/Conjurer/priority_queue.playlist",
+                        "r+",
+                        encoding="utf-8",
                     ) as s_file:
                         s_file.write(search_weight[itr][1])
                 break
@@ -211,14 +289,7 @@ def wyszukaj(word_list, how_many, _logger=None, return_to_bot=True):
         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)])
-        if not return_to_bot:
-
-            with open(
-               "/home/pi/Conjurer/priority_queue.playlist", "r+", encoding="utf-8"
-            ) as s_file:
-                s_file.truncate(0)
-                for item in return_list:
-                    s_file.write(item[1] + "\n")
+    fun_logger.info("Done: %s", return_list)
     return return_list
 
 
@@ -253,24 +324,37 @@ def remove_characters(string, character):
 @app.route("/stream", methods=["GET"])
 def stream_music():
     """
-    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`.
+    The function `stream_music` is a route handler for the "/stream" endpoint.
+    It returns a JSON response containing a key "music_file_list" with the value of the variable `music_file_list`.
+
+    :return: A JSON response containing a key "music_file_list" with the value of the variable `music_file_list`.
     """
-    return send_from_directory("/tmp/hls", "stream.m3u8")
 
-@app.route('/<string:file_name>')
+    #return send_from_directory("/tmp/hls", "stream.m3u8")
+    return render_template("/home/pi/Conjurer/stream.html")
+
+@app.route("/<string:file_name>")
 def stream(file_name):
-    video_dir = '/tmp/hls'
-    return send_from_directory(video_dir, file_name)
+    """
+    Stream the specified file from the video directory.
 
+    Args:
+        file_name (str): The name of the file to be streamed.
+
+    Returns:
+        Response: The response containing the streamed file.
+    """
+    # trunk-ignore(bandit/B108)
+    video_dir = "/tmp/hls"
+    return send_from_directory(video_dir, file_name)
 
 @app.route("/stream_mp3", methods=["GET"])
 def stream_music_mp3():
     """
-    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`.
+    The function `stream_music_mp3` is a route handler for the "/stream_mp3" endpoint.
+    It redirects the user to the URL "http://www.example.com" with a status code of 302.
+
+    :return: A redirect response to "http://www.example.com" with a status code of 302.
     """
     return redirect("http://www.example.com", code=302)
 
@@ -278,19 +362,18 @@ def stream_music_mp3():
 @app.route("/clear_pr_pls", methods=["GET"])
 def clear_pr_pls():
     """
-    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`.
+    The function `clear_pr_pls` clears the contents of the priority queue playlist file.
+
+    :return: A JSON response indicating the success of the operation.
     """
-    with open(
-        "/home/pi/Conjurer/priority_queue.playlist", "w", encoding="utf-8"
-        ) as s_file:
-        s_file.truncate(0)
+    app.logger.info("CLEARING PLAYLIST")
+    with open('/home/pi/Conjurer/priority_queue.playlist', 'w', encoding='utf-8') as cleared_pl:
+        cleared_pl.write('')
+
     return_data = jsonify(isError=False, message="Success", statusCode=200, data=[])
     return return_data, 200
 
 
-
 @app.route("/mp3", methods=["GET"])
 def get_music_list():
     """
@@ -325,20 +408,22 @@ def update_music_list():
 @app.route("/get_music", methods=["POST"])
 def look_for_playlist():
     """
-    The function `update_music_list` receives a POST request with a JSON payload, logs the received
+    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: 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.
+
+    :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.
     """
     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 = wyszukaj(
+        record["lista_slow"], record["dlugosc_plejlisty"], app.logger, True
+    )
 
     return_data = (
         jsonify(isError=False, message="Success", statusCode=200, data=return_data),
@@ -346,26 +431,89 @@ def look_for_playlist():
     )
     return return_data
 
-@app.route("/add_to_priority", methods=["POST"])
-def add_to_priority():
+
+@app.route("/request_radio_file", methods=["POST"])
+def add_request():
+    record = json.loads(request.data)
+    app.logger.info(record)
+    app.logger.info(record["lista_slow"])
+    app.logger.info(record["UUID"])
+    return_data = wyszukaj(
+        record["lista_slow"], 0, app.logger, False
+    )
+
+    with open(
+        "/home/pi/Conjurer/request.playlist", "a", encoding="utf-8"
+    ) as s_file:
+        for item in return_data:
+            s_file.write(item[1] + "\n")
+    return_data = (
+        jsonify(isError=False, message="Success", statusCode=200, data={"status": "OK"}),
+        200,
+    )
+    return return_data
+
+@app.route("/create_priority_playlist", methods=["POST"])
+def create_priority_playlist():
     """
-    The function `update_music_list` receives a POST request with a JSON payload, logs the received
+    The function `create_priority_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: 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.
+
+    :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.
     """
     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, False)
-
+    return_data = wyszukaj(
+        record["lista_slow"], record["dlugosc_plejlisty"], app.logger, False
+    )
+    with open(
+        "/home/pi/Conjurer/request.playlist", "a", encoding="utf-8"
+    ) as s_file:
+        for item in return_data:
+            s_file.write(item[1] + "\n")
     return_data = (
-        jsonify(isError=False, message="Success", statusCode=200, data=return_data),
+        jsonify(isError=False, message="Success", statusCode=200, data={"status": "OK"}),
+        200,
+    )
+    return return_data
+
+
+@app.route("/add_to_priority", methods=["POST"])
+def add_to_priority():
+    """
+    The function `add_to_priority` 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.
+    """
+    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, False
+    )
+    with open(
+        "/home/pi/Conjurer/priority_queue.playlist", "a", encoding="utf-8"
+    ) as s_file:
+        for item in return_data:
+            s_file.write(item[1] + "\n")
+    return_data = (
+        jsonify(isError=False, message="Success", statusCode=200, data={"status": "OK"}),
         200,
     )
     return return_data
@@ -382,8 +530,18 @@ def flask_debug():
 
 def waitress_run():
     """
-    The `waitress_run` function serves the `app` on host "0.0.0.0"
+    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)
 
@@ -407,12 +565,16 @@ if __name__ == "__main__":
     rescan()
     logger.info("Started")
     threads = []
-    #threads.append(threading.Thread(target=flask_debug))
+    # threads.append(threading.Thread(target=flask_debug))
     threads.append(threading.Thread(target=waitress_run))
     threads.append(threading.Thread(target=thread_rescan))
 
     for worker in threads:
         worker.start()
 
+    time.sleep(60)
+    threads.append(threading.Thread(target=scan_tracks))
+    threads[2].start()
+
     for worker in threads:
         worker.join()

conjurer_musician/music_utils.py

@@ -0,0 +1,26 @@
+# This Python file uses the following encoding: utf-8
+"""This module contains utility scripts used by musi radiostation Conjurer"""
+import time
+import re
+
+NAME = "/home/pi/Conjurer/persistence.log"
+
+def print_top():
+    """
+    Prints the top 65 lines from a file specified by the NAME variable.
+    """
+    while True:
+        line = ""
+        buffer = ""
+        with open(NAME, "r", encoding="utf-8") as f:
+            for _ in range (45):
+                line = f.readline()
+                if re.match(".*mp3", line):
+                    buffer += line
+            print("=====================================")
+            print(buffer)
+            print("=====================================")
+        time.sleep(180)
+
+if __name__ == "__main__":
+    print_top()

conjurer_musician/pl.config

@@ -0,0 +1,14 @@
+$dodaj_do_ulubionych 100 nightwish
+$dodaj_do_ulubionych 100 amon amarth
+$dodaj_do_ulubionych 100 tactical sekt
+$dodaj_do_ulubionych 100 lacuna coil
+$dodaj_do_ulubionych 100 sefa
+$dodaj_do_ulubionych 100 frenchcore
+$dodaj_do_ulubionych 100 peacock
+$dodaj_do_ulubionych 100 vavamuffin
+$dodaj_do_ulubionych 100 abradab
+$dodaj_do_ulubionych 100 eluveitie
+$dodaj_do_ulubionych 100 youtube
+
+$dodaj_do_ulubionych 100 elyose
+$dodaj_do_ulubionych 1 artisans du chaos

conjurer_musician/radio_conjurer.liq

@@ -1,48 +1,169 @@
+# FILEPATH: /home/mtuszowski/conjurer/conjurer_musician/radio_conjurer.liq
+
+# This script sets up a Liquidsoap radio stream with various features and configurations.
+
+# Load icecast credentials from a JSON file
 let json.parse credentials  = file.contents("/home/pi/Conjurer/icecast_credentials.json")
+
+# Enable replaygain metadata processing
 enable_replaygain_metadata()
 
-s1 = replaygain(playlist(reload_mode="watch", "/home/pi/Conjurer/all_playlist.playlist"))
-s2 = replaygain(playlist(reload_mode="watch", "/home/pi/Conjurer/priority_queue.playlist"))
+# Set up a playlog for tracking played tracks
 
-s = random(id="randomizer", weights=[7000, 100], [s2, s1])
+l = playlog(duration = 72000.0, persistency="/home/pi/Conjurer/persistence.log")
 
+# Function to check if a track can be played based on its metadata
+def check(r)
+    m = request.metadata(r)
+    if l.last(m) < 36000. then
+        log.info("Rejecting #{m['filename']} (played #{l.last(m)}s ago).")
+        false
+    else
+        l.add(m)
+        true
+    end
+end
+
+# Define playlists to be used in the stream
+s1 = replaygain(playlist(reload_mode="watch", check_next=check, "/home/pi/Conjurer/all_playlist.playlist"))
+s2 = replaygain(playlist(reload_mode="watch", check_next=check, "/home/pi/Conjurer/priority_queue.playlist"))
+s3 = replaygain(playlist(reload_mode="watch", check_next=check, "/home/pi/Conjurer/hit.playlist"))
+
+# Create a request queue for user-generated requests
+requests_queue = request.queue()
+
+# Function to process the request queue and add new requests
+def queue_processing()
+    text=file.lines("/home/pi/Conjurer/request.playlist")
+    if text != [] then
+        list.iter(fun(item) -> requests_queue.push.uri(item), text)
+        file.remove("/home/pi/Conjurer/request.playlist")
+        f = file.open("/home/pi/Conjurer/request.playlist", create=true)
+        f.close()
+    end
+end
+
+# Randomly select a playlist with weights
+s4 = random(id="randomizer", weights=[2, 3, 5], [s1, s2, s3])
+
+# Load jingles playlist
+jingles = (playlist(reload_mode="watch", "/home/pi/Conjurer/jingles.playlist"))
+
+# Create the main stream with random playlist and jingles
+s = rotate(id="randomizer", weights=[10, 1], [s4, jingles])
+
+s = crossfade(fade_out=2., fade_in=2., duration=4., fallback(id="switcher", track_sensitive=false, [requests_queue, s]))
+
+# Set up an interactive harbor for controlling the stream
 interactive.harbor(port = 9999)
-f = interactive.float("f", description="Frequency", min=0., max=1000.,unit="Hz", 200.)
-g = interactive.float("g", description="Gain", min=0., max=20.,unit="dB", 8.)
+
+# Set up interactive controls for bass boost
+f = interactive.float("f", description="Frequency", min=0., max=1000., unit="Hz", 200.)
+g = interactive.float("g", description="Gain", min=0., max=20., unit="dB", 8.)
 b = bass_boost(frequency=f, gain=g, s)
 s = add([s, b])
-a = interactive.float("main_volume", min=0., max=20., 1.)
-s = compress.multiband.interactive(bands=3, s)
 
-s = nrj(normalize (s))
-s = crossfade(fade_out=3., fade_in=3., duration=5., s)
-s = amplify(a,s)
+# Set up interactive control for main volume
+a = interactive.float("main_volume", min=0., max=20., 0.4)
+s = compress.multiband.interactive(bands=7, s)
 
-s = blank.skip(max_blank=2., s)
+mic_gain = interactive.float("mic_volume", min=0., max=20., 6.)
+# Apply audio processing effects
+tmic = buffer(input.pulseaudio()) # Microphone
+mic = amplify(mic_gain, tmic)
+mic = gate(threshold=-80., range=-120., mic)
+mic = compress(threshold=0., ratio=2.,mic)
+mic = blank.strip(max_blank=10., min_noise=.1, threshold=-20., mic)
 
-emergency = single("/home/pi/RetroPie/mp3/Youtube/Dr. Peacock - Trip to Ireland [GvrvQTUbUcA].mp3")
-radio = fallback(id="switcher",track_sensitive = false, [s, emergency]) 
+s = add([s, mic])
 
-handle_metadata = fun (m) -> begin
-    print(m["title"])
-    print(m["artist"])
-    print(m["filename"])
-end
-radio.on_metadata(handle_metadata)
-interactive.persistent("script.params")
+# Apply audio processing effects
+s = nrj(normalize(s))
+s = amplify(a, s)
 
+
+# Skip blank sections in the stream
+s = blank.skip(max_blank=10., s)
+
+# Configure logging settings
 log_to_stdout = true
 log_to_file = true
 logpath = "/home/pi/Conjurer/radio_log.log"
 loglevel = 3
+set("log.stdout", log_to_stdout)
+set("log.level", loglevel)
 
-# Enable logging on Standard Output and set logging level.
-set("log.stdout",log_to_stdout)
-set("log.level",loglevel)
+# Enable logging to file
+set("log.file", log_to_file)
+set("log.file.path", logpath)
 
-# Enable logging to file. See variable: logpath
-set("log.file",log_to_file)
-set("log.file.path",logpath)
+# Set up emergency fallback track
+emergency = single("/home/pi/RetroPie/mp3/Youtube/Dr. Peacock - Trip to Ireland [GvrvQTUbUcA].mp3")
+radio =  fallback(id="switcher2", track_sensitive=false, [s, emergency])
+# Set up an interactive control for skipping tracks
+p = interactive.bool("Skip track", false)
 
-output.file.hls("/tmp/hls",[("mp3-low", %mp3(bitrate=96)), ("mp3-hi", %mp3(bitrate=160))],radio)
-output.icecast(%mp3, host="retropie", port=8000,password=credentials.password, icy_metadata="true", mount="mp3-stream", radio)
+def http_skip(~protocol, ~data, ~headers, uri)=
+    radio.skip()
+    http.response(code=200,data="Skipped")
+end
+harbor.http.register(port=54321,method="GET","/skip", http_skip)
+
+
+# Function to process the request queue and skip the current track if requested
+def check_skip()
+    if p() then
+        log.info("Skipping current track.")
+        radio.skip()
+        p.set(false)
+    end
+end
+
+# Run the queue processing function every 60 seconds
+thread.run(every=60., queue_processing)
+
+
+# Run the check_skip function every 5 seconds
+thread.run(every=15., check_skip)
+
+
+# Enable persistent script parameters
+interactive.persistent("script.params")
+
+# Configure output formats and destinations
+
+output.icecast(%mp3, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="mp3-stream", radio)
+output.pulseaudio(radio)
+#output.file.hls("/tmp/hls", [("mp3-low", %mp3(bitrate=96)), ("mp3-hi", %mp3(bitrate=160))], radio)
+# Uncomment the following lines to enable additional output formats
+# output.icecast(%opus, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="opus-stream", radio)
+# output.icecast(%ogg, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="ogg-stream", radio)
+# output.icecast(%aac, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="aac-stream", radio)
+# output.icecast(%flac, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="flac-stream", radio)
+# output.icecast(%vorbis, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="vorbis-stream", radio)
+# output.icecast(%speex, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="speex-stream", radio)
+# output.icecast(%wav, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="wav-stream", radio)
+# output.icecast(%pcm, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="pcm-stream", radio)
+# output.icecast(%raw, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="raw-stream", radio)
+# output.icecast(%s16l, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="s16l-stream", radio)
+# output.icecast(%s16b, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="s16b-stream", radio)
+# output.icecast(%s24l, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="s24l-stream", radio)
+# output.icecast(%s24b, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="s24b-stream", radio)
+# output.icecast(%s32l, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="s32l-stream", radio)
+# output.icecast(%s32b, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="s32b-stream", radio)
+# output.icecast(%s64l, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="s64l-stream", radio)
+# output.icecast(%s64b, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="s64b-stream", radio)
+# output.icecast(%s128l, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="s128l-stream", radio)
+# output.icecast(%s128b, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="s128b-stream", radio)
+# output.icecast(%s256l, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="s256l-stream", radio)
+# output.icecast(%s256b, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="s256b-stream", radio)
+# output.icecast(%s512l, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="s512l-stream", radio)
+# output.icecast(%s512b, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="s512b-stream", radio)
+# output.icecast(%s1024l, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="s1024l-stream", radio)
+# output.icecast(%s1024b, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="s1024b-stream", radio)
+# output.icecast(%s2048l, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="s2048l-stream", radio)
+# output.icecast(%s2048b, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="s2048b-stream", radio)
+# output.icecast(%s4096l, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="s4096l-stream", radio)
+# output.icecast(%s4096b, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="s4096b-stream", radio)
+# output.icecast(%s8192l, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="s8192l-stream", radio)
+# output.icecast(%s8192b, host="retropie", port=8000, password=credentials.password, icy_metadata="true", mount="s8192b-stream", radio)

conjurer_musician/requirements_musician.txt

@@ -1,2 +1,3 @@
 flask
-waitress
+waitress
+sshtunnel

conjurer_musician/stream.html

@@ -0,0 +1,9 @@
+    <html>
+        <head>
+            <title>HTTP Live Streaming Example</title>
+        </head>
+        <body>
+            <video src="/tmp/hls/stream.m3u8" height="300" width="400">
+            </video>
+        </body>
+    </html>

install_main_bot.sh

@@ -1,4 +1,5 @@
 #!/bin/bash
+sudo apt-get install python3-dev
 cd /home/pi
 mdkir Conjurer
 cd Conjurer
@@ -9,6 +10,11 @@ source ./env/bin/activate
 ./env/bin/python3 -m pip install -r requirements_bot.txt
 sed -i -e 's/os.rename/shutil.copy/g' ./env/lib/python3.11/site-packages/spotify_dl/youtube.py
 sed -i '1i\import shutil' ./env/lib/python3.11/site-packages/spotify_dl/youtube.py
+sed -i '1i\import logging' ./env/lib/python3.11/site-packages/spotify_dl/spotify.py
+
+sed -i '21i\         logger = logging.getLogger("discord")' ./env/lib/python3.11/site-packages/spotify_dl/spotify.py
+sed -i '22i\         logger.info("Playlist")' ./env/lib/python3.11/site-packages/spotify_dl/spotify.py
+
 deactivate
 sudo cp ./conjurer.service /etc/systemd/system/
 sudo systemctl daemon-reload

install_music_bot.sh

@@ -8,9 +8,17 @@ cp /home/pi/conjurer/conjurer_musician/requirements_musician.txt /home/pi/Conjur
 cp /home/pi/conjurer/conjurer_musician/conjurer_musician.py /home/pi/Conjurer/
 cp /home/pi/conjurer/conjurer_musician/radio_conjurer.liq /home/pi/Conjurer/
 touch /home/pi/Conjurer/discord_mus_service.log
-touch /home/pi/Conjurer/all_playlist.txt
+
 touch /home/pi/Conjurer/playlist.json
+touch /home/pi/Conjurer/prio_playlist.json
+
+touch /home/pi/Conjurer/all_playlist.playlist
 touch /home/pi/Conjurer/priority_queue.playlist
+touch /home/pi/Conjurer/hit.playlist
+touch /home/pi/Conjurer/request.playlist
+touch /home/pi/Conjurer/persistence.log
+echo "[]" > /home/pi/Conjurer/persistence.log
+
 touch /home/pi/Conjurer/radio_log.log
 ./env/bin/python3 -m pip install --upgrade pip
 ./env/bin/python3 -m pip install -r requirements_musician.txt
@@ -24,3 +32,7 @@ sudo cp /home/pi/conjurer/conjurer_musician/radio_service.service /etc/systemd/s
 sudo systemctl daemon-reload
 sudo systemctl start radio_service.service
 sudo systemctl enable radio_service.service
+
+
+sed -i -e 's/os.rename/shutil.copy/g' ./env/lib/python3.11/site-packages/spotify_dl/youtube.py
+sed -i '1i\import shutil' ./env/lib/python3.11/site-packages/spotify_dl/youtube.py

requirements_bot.txt

@@ -12,4 +12,8 @@ spotipy
 tiktoken
 PyNaCl
 flask
-waitress
+waitress
+clickupython
+assemblyai[extras]
+SpeechRecognition
+git+https://github.com/imayhaveborkedit/discord-ext-voice-recv

restart_radio.sh

@@ -0,0 +1,3 @@
+sshpass -p raspberry ssh pi@192.168.1.15 << 'ENDSSH'
+sudo reboot
+ENDSSH

settings.json

@@ -204,6 +204,13 @@
             false,
             false
         ],
+        "same plusy\\b": [
+            "Jak na cmentarzu Szefie. Jak na cmentarzu",
+            15.0,
+            0,
+            false,
+            false
+        ],
         "kld\\b": [
             "KLD? Mieli tam burdel większy niż u Hammera. Ale o ile Hammer sprzątnął już nawet całkiem nieźle - to tam śmieci wyniosły się same. Uczcijmy ich minutą śmiechu.",
             15.0,

spotify_dl/spotify.py

@@ -239,6 +239,8 @@ def get_item_name(sp, item_type, item_id):
         name = sp.album(album_id=item_id).get("name")
     elif item_type == "track":
         name = sp.track(track_id=item_id).get("name")
+    elif item_type == "artist_top_tracks":
+        name = sp.artist_top_tracks(artist_id=item_id).get("name")
     return sanitize(name)
 
 

sr_example.py

@@ -0,0 +1,229 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import annotations
+
+import logging
+
+from discord.ext.voice_recv.sinks import AudioSink
+
+log = logging.getLogger(__name__)
+
+__all__ = [
+    'SpeechRecognitionSink',
+]
+
+try:
+    import discord.ext.speech_recognition as sr  # type: ignore
+except ImportError:
+
+    def SpeechRecognitionSink(**kwargs) -> AudioSink:
+        """A stub for when the SpeechRecognition module isn't found."""
+        raise RuntimeError('The SpeechRecognition module is required to use this sink.')
+
+else:
+    import time
+    import array
+    import asyncio
+    import audioop
+
+    from collections import defaultdict
+
+    from discord.ext.voice_recv.sinks  import SilencePacket
+
+    from typing import TYPE_CHECKING, TypedDict
+
+    if TYPE_CHECKING:
+        from concurrent.futures import Future as CFuture
+        from typing import Literal, Callable, Optional, Any, Final, Protocol, Awaitable, TypeVar
+
+        from discord import Member
+
+        from ..opus import VoiceData
+        from ..types import MemberOrUser as User
+
+        T = TypeVar('T')
+
+        SRRecognizerMethod = Literal[
+            'sphinx',
+            'google',
+            'google_cloud',
+            'wit',
+            'azure',
+            'bing',
+            'lex',
+            'houndify',
+            'amazon',
+            'assemblyai',
+            'ibm',
+            'tensorflow',
+            'whisper',
+            'vosk',
+        ]
+
+        class SRStopper(Protocol):
+            def __call__(self, wait: bool = True, /) -> None:
+                ...
+
+        SRProcessDataCB = Callable[[sr.Recognizer, sr.AudioData, User], Optional[str]]
+        SRTextCB = Callable[[User, str], Any]
+
+    class _StreamData(TypedDict):
+        stopper: Optional[SRStopper]
+        recognizer: sr.Recognizer
+        buffer: array.array[int]
+
+    class SpeechRecognitionSink(AudioSink):  # type: ignore
+        def __init__(
+            self,
+            *,
+            process_cb: Optional[SRProcessDataCB] = None,
+            text_cb: Optional[SRTextCB] = None,
+            default_recognizer: SRRecognizerMethod = 'assemblyai',
+            phrase_time_limit: int = 10,
+            ignore_silence_packets: bool = True,
+        ):
+            super().__init__(None)
+            self.process_cb: Optional[SRProcessDataCB] = process_cb
+            self.text_cb: Optional[SRTextCB] = text_cb
+            self.phrase_time_limmit: int = phrase_time_limit
+            self.ignore_silence_packets: bool = ignore_silence_packets
+
+            self.default_recognizer: SRRecognizerMethod = default_recognizer
+            self._stream_data: defaultdict[int, _StreamData] = defaultdict(
+                lambda: _StreamData(stopper=None, recognizer=sr.Recognizer(), buffer=array.array('B'))
+            )
+
+        def _await(self, coro: Awaitable[T]) -> CFuture[T]:
+            assert self.client is not None
+            return asyncio.run_coroutine_threadsafe(coro, self.client.loop)
+
+        def wants_opus(self) -> bool:
+            return False
+
+        def write(self, user: Optional[User], data: VoiceData) -> None:
+            if self.ignore_silence_packets and isinstance(data.packet, SilencePacket):
+                return
+
+            if user is None:
+                return
+
+            sdata = self._stream_data[user.id]
+            sdata['buffer'].extend(data.pcm)
+
+            if not sdata['stopper']:
+                sdata['stopper'] = sdata['recognizer'].listen_in_background(
+                    DiscordSRAudioSource(sdata['buffer']), self.background_listener(user), self.phrase_time_limmit
+                )
+
+        def background_listener(self, user: User):
+            process_cb = self.process_cb or self.get_default_process_callback()
+            text_cb = self.text_cb or self.get_default_text_callback()
+
+            def callback(_recognizer: sr.Recognizer, _audio: sr.AudioData):
+                output = process_cb(_recognizer, _audio, user)
+                if output is not None:
+                    text_cb(user, output)
+
+            return callback
+
+        def get_default_process_callback(self) -> SRProcessDataCB:
+            def cb(recognizer: sr.Recognizer, audio: sr.AudioData, user: Optional[User]) -> Optional[str]:
+                log.debug("Got %s, %s, %s", audio, audio.sample_rate, audio.sample_width)
+                text: Optional[str] = None
+                try:
+                    # they changed recognize_google to be optionally assigned at runtime...
+                    func = getattr(recognizer, 'recognize_' + self.default_recognizer, recognizer.recognize_google) # type: ignore
+                    text = func(audio)  # type: ignore
+                except sr.UnknownValueError:
+                    log.debug("Bad speech chunk")
+                    # self._debug_audio_chunk(audio)
+
+                return text
+
+            return cb
+
+        def get_default_text_callback(self) -> SRTextCB:
+            def cb(user: Optional[User], text: Optional[str]) -> Any:
+                log.info("%s said: %s", user.display_name if user else 'Someone', text)
+
+            return cb
+
+        @AudioSink.listener()
+        def on_voice_member_disconnect(self, member: Member, ssrc: Optional[int]) -> None:
+            self._drop(member.id)
+
+        def cleanup(self) -> None:
+            for user_id in tuple(self._stream_data.keys()):
+                self._drop(user_id)
+
+        def _drop(self, user_id: int) -> None:
+            data = self._stream_data.pop(user_id)
+
+            stopper = data.get('stopper')
+            if stopper:
+                stopper()
+
+            buffer = data.get('buffer')
+            if buffer:
+                # arrays don't have a clear function
+                del buffer[:]
+
+        def _debug_audio_chunk(self, audio: sr.AudioData, filename: str = 'sound.wav') -> None:
+            import io, wave, discord
+
+            with io.BytesIO() as b:
+                with wave.open(b, 'wb') as writer:
+                    writer.setframerate(48000)
+                    writer.setsampwidth(2)
+                    writer.setnchannels(2)
+                    writer.writeframes(audio.get_wav_data())
+
+                b.seek(0)
+                f = discord.File(b, filename)
+                self._await(self.voice_client.channel.send(file=f))  # type: ignore
+
+    class DiscordSRAudioSource(sr.AudioSource):
+        little_endian: Final[bool] = True
+        SAMPLE_RATE: Final[int] = 48_000
+        SAMPLE_WIDTH: Final[int] = 2
+        CHANNELS: Final[int] = 2
+        CHUNK: Final[int] = 960
+
+        def __init__(self, buffer: array.array[int]):
+            self.buffer = buffer
+            self._entered: bool = False
+
+        @property
+        def stream(self):
+            return self
+
+        def __enter__(self):
+            if self._entered:
+                log.warning('Already entered sr audio source')
+            self._entered = True
+            return self
+
+        def __exit__(self, *exc) -> None:
+            self._entered = False
+            if any(exc):
+                log.exception('Error closing sr audio source')
+
+        def read(self, size: int) -> bytes:
+            # TODO: make this timeout configurable
+            for _ in range(10):
+                if len(self.buffer) < size * self.CHANNELS:
+                    time.sleep(0.1)
+                else:
+                    break
+            else:
+                if len(self.buffer) == 0:
+                    return b''
+
+            chunksize = size * self.CHANNELS
+            audiochunk = self.buffer[:chunksize].tobytes()
+            del self.buffer[: min(chunksize, len(audiochunk))]
+            audiochunk = audioop.tomono(audiochunk, 2, 1, 1)
+            return audiochunk
+
+        def close(self) -> None:
+            self.buffer.clear()

stream_test.py

@@ -0,0 +1,62 @@
+# Start by making sure the `assemblyai` package is installed.
+# If not, you can install it by running the following command:
+# pip install -U assemblyai
+#
+# Then, make sure you have PyAudio installed: https://pypi.org/project/PyAudio/
+#
+# Note: Some macOS users might need to use `pip3` instead of `pip`.
+
+import pyaudio
+import assemblyai as aai
+
+aai.settings.api_key = "aa9962f0088a449a9c4ab2361e96cc08"
+
+def on_open(session_opened: aai.RealtimeSessionOpened):
+  "This function is called when the connection has been established."
+
+  print("Session ID:", session_opened.session_id)
+
+def on_data(transcript: aai.RealtimeTranscript):
+  "This function is called when a new transcript has been received."
+
+  if not transcript.text:
+    return
+
+  if isinstance(transcript, aai.RealtimeFinalTranscript):
+    print(transcript.text, end="\r\n")
+  else:
+    print(transcript.text, end="\r")
+
+def on_error(error: aai.RealtimeError):
+  "This function is called when the connection has been closed."
+
+  print("An error occured:", error)
+
+def on_close():
+  "This function is called when the connection has been closed."
+
+  print("Closing Session")
+
+transcriber = aai.RealtimeTranscriber(
+  on_data=on_data,
+  on_error=on_error,
+  sample_rate=44_100,
+  on_open=on_open, # optional
+  on_close=on_close, # optional
+)
+
+
+pa = pyaudio.PyAudio()
+for i in range(pa.get_device_count()):
+  print (pa.get_device_info_by_index(i))
+
+# Start the connection
+#transcriber.connect()
+
+# Open a microphone stream
+#microphone_stream = aai.extras.MicrophoneStream()
+
+# Press CTRL+C to abort
+#transcriber.stream(microphone_stream)
+
+#transcriber.close()

test_time.py

@@ -0,0 +1,7 @@
+import time
+first_time = time.time_ns()
+
+time.sleep(1)
+time_diff = time.time_ns() - first_time
+print(time_diff)
+#2000149433

utils/update_memory.py

@@ -0,0 +1,33 @@
+import json
+MEMORY_FIVE_SIARA = "/home/pi/Conjurer/pamiec.json"
+ENCODING = "utf-8"
+
+messages = [
+    {"role": "user", "content" : "Hammer: All systems operational"},
+    {"role": "assistant", "content": "Aye, Szefie! Wszystkie systemy działają sprawnie. Gotów do dalszej służby! Co podać?"},
+    {"role": "user", "content" : "Hammer: Podaj coś na orzeźwienie i przebudzenie. COś co rozgrzeje moje stare kości po ciężkiej pracy!"},
+    {"role": "assistant", "content": "Z przyjemnością Szefie! Dla Ciebie przygotuję Midzynarodówkę Interstelarną Wolf's Dragoon - wysoce energetyczny koktajl rozgrzewający i pobudzający jednocześnie."+
+                                    "Do przygotowania potrzebuję:"+
+                                    "\n"+
+                                    "60 ml mocnego rumu z Wolfa (lub innego, jeśli wolisz)"+
+                                    "30 ml soku z cytryny"+
+                                    "35 ml domowego syropu z mięty"+
+                                    "15 ml świeżo zmielonej kawy"+
+                                    "\n"+
+                                    "Mieszam wszystko w shakerze z lodem, a potem przelewam przez sitko do kieliszka koktajlowego. W górę serwuję z bigoskiem z miętą i zestem z cytryny. Rozgrzewa, orzeźwia i daje kopa na resztę nocy."+
+                                    "\n"+
+                                    "Co powiesz Szefie, podać Ci taki?"},
+    {"role": "user", "content" : "Hammer: Brzmi jak coś co zrobi robotę! Skal!"},
+]
+
+
+for temp in messages:
+
+    with open(MEMORY_FIVE_SIARA, "r+", encoding=ENCODING) as file_memory:
+        # First we load existing data into a dict.
+        file_data = json.load(file_memory)
+        # Join new_data with file_data inside emp_details
+        file_data.append(temp)
+        file_memory.seek(0)
+        # convert back to json.
+        json.dump(file_data, file_memory, indent=4)

voice_example.py

@@ -0,0 +1,47 @@
+# -*- coding: utf-8 -*-
+
+import discord
+from discord.ext import commands, voice_recv
+
+discord.opus._load_default()
+
+bot = commands.Bot(command_prefix=commands.when_mentioned, intents=discord.Intents.all())
+
+class Testing(commands.Cog):
+    def __init__(self, bot):
+        self.bot = bot
+
+    @commands.command()
+    async def test(self, ctx):
+        def callback(user, data: voice_recv.VoiceData):
+            print(f"Got packet from {user}")
+
+            ## voice power level, how loud the user is speaking
+            # ext_data = packet.extension_data.get(voice_recv.ExtensionID.audio_power)
+            # value = int.from_bytes(ext_data, 'big')
+            # power = 127-(value & 127)
+            # print('#' * int(power * (79/128)))
+            ## instead of 79 you can use shutil.get_terminal_size().columns-1
+
+        vc = await ctx.author.voice.channel.connect(cls=voice_recv.VoiceRecvClient)
+        vc.listen(voice_recv.BasicSink(callback))
+
+    @commands.command()
+    async def stop(self, ctx):
+        await ctx.voice_client.disconnect()
+
+    @commands.command()
+    async def die(self, ctx):
+        ctx.voice_client.stop()
+        await ctx.bot.close()
+
+@bot.event
+async def on_ready():
+    print('Logged in as {0.id}/{0}'.format(bot.user))
+    print('------')
+    await bot.add_cog(Testing(bot))
+
+REMOTE_HOST_NAME = "discord"
+
+
+bot.run("NzUxNDQxODgzNDA2MDA4NDEw.Go--wb.Nr28Oo4eYAP1p2XFVHF5uIQfcPD7s_jO2NfMCQ")

voice_recognition.py

@@ -0,0 +1,233 @@
+import logging
+import wave
+import asyncio
+import assemblyai as aai
+import discord
+from discord.ext import commands, voice_recv, tasks
+from discord.opus import Decoder as OpusDecoder
+import time
+# Replace with your API key
+aai.settings.api_key = "aa9962f0088a449a9c4ab2361e96cc08"
+discord.opus._load_default()
+CHANNELS = OpusDecoder.CHANNELS
+SAMPLE_WIDTH = OpusDecoder.SAMPLE_SIZE // OpusDecoder.CHANNELS
+SAMPLING_RATE = OpusDecoder.SAMPLING_RATE
+
+#rotate file after there is 0.5s between last received pcm for user.
+#delete messsages after user disconnect
+
+logger = logging.getLogger("discord")
+location = "/home/pi/Conjurer/transcripts/"
+
+class CommunicationObject:
+    def __init__(self, msg_type, user, data):
+        self.type = msg_type
+        self.user = user
+        self.data = data
+    def __repr__(self):
+        return f"{self.type} : {self.user} : {self.data}"
+
+class WaveWriter:
+    def __init__(self, user_id, queue):
+        self.queue = queue
+        self.user = user_id
+        self.username = str(user_id.id)
+        #here we can add hashing function to make transcription files not possible to be connected with discord id
+        self.present_file_id = 0
+        self.file_name_past = None
+        self.file_name_present = location + self.username + "_" + str(self.present_file_id) + ".mp3"
+        self.transcript_file_present : wave.Wave_write = wave.open(
+            self.file_name_present, "wb"
+        )
+        self.transcript_file_present.setnchannels(CHANNELS)
+        self.transcript_file_present.setsampwidth(SAMPLE_WIDTH)
+        self.transcript_file_present.setframerate(SAMPLING_RATE)
+        self.file_name_future = location + self.username + "_" + str(self.present_file_id + 1) + ".mp3"
+        self.transcript_file_future : wave.Wave_write = wave.open(
+            self.file_name_future, "wb"
+        )
+        self.transcript_file_future.setnchannels(CHANNELS)
+        self.transcript_file_future.setsampwidth(SAMPLE_WIDTH)
+        self.transcript_file_future.setframerate(SAMPLING_RATE)
+
+    async def rotate(self):
+
+        self.transcript_file_present.close()
+        self.file_name_past = self.file_name_present
+        if self.present_file_id > 10:
+            self.present_file_id = 0
+        else:
+            self.present_file_id += 1
+        self.file_name_present = self.file_name_future
+        self.transcript_file_present = self.transcript_file_future
+        self.file_name_future = location + self.username + "_" + str(self.present_file_id + 1) + ".mp3"
+        self.transcript_file_future : wave.Wave_write = wave.open(
+            self.file_name_future, "wb"
+        )
+        self.transcript_file_future.setnchannels(CHANNELS)
+        self.transcript_file_future.setsampwidth(SAMPLE_WIDTH)
+        self.transcript_file_future.setframerate(SAMPLING_RATE)
+        operation = CommunicationObject(msg_type="send_file",user=self.user,data=[self.file_name_past])
+
+        await self.queue.put(operation)
+
+    def writeframes(self, pcmdata):
+        self.transcript_file_present.writeframes(pcmdata)
+
+    def cleanup(self):
+        logger.info("Cleanup for user %s", self.username)
+        self.transcript_file_present.close()
+        self.transcript_file_future.close()
+
+
+class SRBuffer(voice_recv.AudioSink):
+    """Endpoint AudioSink that generates a wav file.
+    Best used in conjunction with a silence generating sink. (TBD)
+    """
+    # on member join dodajemytypa do listy
+    # on member disconnect - dropujemy go
+    def __init__(self, queue):
+        super().__init__()
+        self.queue = queue
+        self.wavewriter = {}
+
+    def on_user_connect(self, username):
+        self.wavewriter[str(username.id)] = [WaveWriter(username, self.queue), time.time_ns(), time.time_ns(), False, False]
+
+    def on_user_disconnect(self,username):
+        self.wavewriter[str(username.id)].cleanup()
+        self.wavewriter.pop(str(username.id))
+
+    def wants_opus(self) -> bool:
+        return False
+
+    def write(self, user, data) -> None:
+        #logger.info("DAta write")
+        if user:
+            self.wavewriter[str(user.id)][0].writeframes(data.pcm)
+            self.wavewriter[str(user.id)][1] = time.time_ns() #time from last write
+            self.wavewriter[str(user.id)][3] = True #data written in last iter
+            self.wavewriter[str(user.id)][4] = True #data in buff
+            time.sleep(0.001)
+
+    def cleanup(self) -> None:
+        try:
+            logger.info("Cleanup for SRBuffer")
+            for item in self.wavewriter.values():
+                item[0].cleanup()
+        except Exception:
+            logger.warning("WaveSink got error closing file on cleanup", exc_info=True)
+
+
+class Transcriber(commands.Cog):
+    def __init__(self, bot):
+        self.bot = bot
+        self.threads = []
+        self.comm_queue = asyncio.Queue()
+        self.wsink = SRBuffer(self.comm_queue)
+        self.worker = None
+        self.mc = None
+        self.vc = None
+
+    @commands.hybrid_command(name="transcribe")
+    async def test(self, ctx):
+        if self.vc:
+            vc = self.vc #to juz powinien byc voice channel z funkcja conenct
+        else:
+            vc = None
+        self.mc = ctx.message.channel
+        if self.bot.voice_clients:
+            if  isinstance(self.bot.voice_clients[0], voice_recv.VoiceRecvClient):
+                logger.debug("Already transcribing")
+            else:
+                logger.debug("Already connected with other client")
+        else:
+            logger.debug("Connected")
+            vc = await ctx.author.voice.channel.connect(cls=voice_recv.VoiceRecvClient)
+            logger.info(self.bot.voice_clients)
+            self.check_data.start()
+            self.worker = asyncio.create_task(self.transcribe_output_queue())
+            vc.listen(self.wsink)
+
+
+    @tasks.loop(seconds=0.5)
+    async def check_data(self):
+        for item in self.wsink.wavewriter.values():
+            if not item[3]:
+                timediff_rotation = time.time_ns() - item[2]
+                timediff_write = time.time_ns() -item[1]
+                if  timediff_rotation > 13000149433 and timediff_write > 500014943 and item[4]:
+                    logger.info("File rotation time since last write %s %s", timediff_write, timediff_write/1e9)
+                    logger.info("File rotation time since last rotation %s %s",timediff_rotation, timediff_rotation/1e9)
+                    item[2] = time.time_ns()
+                    item[4] = False
+                    await item[0].rotate()
+            item[3] = False
+
+    @commands.Cog.listener()
+    async def on_voice_state_update(self, user, before, after):
+        if user == self.bot.user:
+            logger.debug("Ignoring self")
+            return
+
+        if before.channel is None:
+            logger.info("User %s connected to channel %s", user, after.channel.name)
+            self.wsink.on_user_connect(user)
+        elif after.channel is  None:
+            logger.info("User %s disconnected from channel %s", user, before.channel.name)
+            operation = CommunicationObject(msg_type="user_cleanup", user=user, data=None)
+            await self.comm_queue.put(operation)
+        else:
+            logger.debug("User VC status changed %s", user.id)
+            logger.debug("Before %s", before)
+            logger.debug("After %s", after)
+
+
+    @commands.command(name="stop_transcribe")
+    async def stop(self, ctx):
+        self.check_data.stop()
+        stop_token = CommunicationObject("STOP",None,None)
+
+        await self.comm_queue.put(stop_token)
+        await ctx.voice_client.disconnect()
+
+    async def transcribe_output_queue(self):
+        logger.info("Transcript uploader start")
+        config = aai.TranscriptionConfig(language_code="pl")
+        transcriber = aai.Transcriber()
+        logger.debug("Transcriber queue id: %s",id(self.comm_queue))
+
+        while True:
+            logger.debug("waiting for tasks")
+            item = await self.comm_queue.get()
+            logger.debug("Got %s", item)
+            if "STOP" in item.type:
+                logger.debug("Queue ended")
+                break
+            elif "send_file" in item.type:
+                logger.debug("Sending file for transcription")
+                transcript = None
+                for iter in item.data:
+                    try:
+                        coro = asyncio.to_thread(
+                            transcriber.transcribe,
+                            iter,
+                            config=config
+                        )
+                        transcript = await coro
+                    except Exception as e:
+                        logger.warn("Exceptiom occured %s", e)
+                    await self.mc.send(f"{item.user} : {transcript.text}")
+                    if transcript.error:
+                        logger.error(transcript.error)
+                        raise AssertionError
+            elif "user_cleanup" in item.type:
+                logger.info("User %s disconnected - cleanup action")
+            else:
+                logger.warn("Something went wrong with object %s", item)
+        logger.info("Transcript uploader stoped")
+
+async def setup(bot):
+    logger = logging.getLogger("discord")
+    await bot.add_cog(Transcriber(bot))
+    logger.info("Loading voice transcribed module done")