feat: remove !h and make the bot have an in-memory dict of greeted users instead of using the backoff service

Dockerfile

@@ -29,9 +29,10 @@ WORKDIR "$APP_PATH"
 
 COPY --chown=$USERNAME pyproject.toml uv.lock Makefile README.md ./
 
+COPY --chown=$USERNAME src/ src/
+
 RUN uv sync
 
-COPY --chown=$USERNAME src/ src/
 COPY --chown=$USERNAME migrations/ migrations/
 
 

Makefile

@@ -16,7 +16,7 @@ tests:
 	uv run coverage xml
 
 serve:
-	uv run python -m src.huesoporro.main
+	uv run python -m src.apps.httpapi.litestar.main
 
 build:
 	docker build . -t git.roboces.dev/catalin/$(PROJECT_NAME):$(PROJECT_TAG) --target $(PROJECT_TARGET)

charts/huesoporro/Chart.yaml

@@ -15,10 +15,10 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.2.9
+version: 0.3.0
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to
 # follow Semantic Versioning. They should reflect the version the application is using.
 # It is recommended to use it with quotes.
-appVersion: "0.2.9"
+appVersion: "0.3.0"

charts/huesoporro/values.yaml

@@ -11,7 +11,7 @@ image:
   # This sets the pull policy for images.
   pullPolicy: Always
   # Overrides the image tag whose default is the chart appVersion.
-  tag: "0.2.9"
+  tag: "0.3.0"
 
 # This is for the secretes for pulling an image from a private repository more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
 imagePullSecrets: []

devenv.nix

@@ -10,7 +10,6 @@
   languages.python.version = "3.12.8";
 
   enterShell = ''
-    uv sync
   '';
 
   dotenv.enable = true;

pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "huesoporro"
-version = "0.2.9"
-description = "Misc Twitch bots"
+version = "0.3.0"
+description = "Misc Twitch bot"
 readme = "README.md"
 authors = [
     { name = "185504a9", email = "catalin@roboces.dev" }
@@ -25,6 +25,13 @@ dependencies = [
     "discord-py>=2.4.0",
 ]
 
+[project.scripts]
+huesoporro = "apps.cli.typer.main:app"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
 [tool.uv]
 dev-dependencies = [
     "mypy>=1.13.0",
@@ -46,7 +53,8 @@ module = [
     "caribou.migrate",
     "twitchio",
     "twitchio.ext",
-    "gtts"
+    "gtts",
+    "yt_dlp"
 ]
 ignore_missing_imports = true
 
@@ -60,3 +68,9 @@ extend-ignore = ["S101", "ISC002", "COM812", "ISC001", "EM101", "EM102"]
 [tool.pytest.ini_options]
 asyncio_mode = "auto"
 asyncio_default_fixture_loop_scope = "function"
+
+[dependency-groups]
+cli = [
+    "typer>=0.15.1",
+    "yt-dlp>=2025.1.26",
+]

src/apps/cli/typer/main.py

@@ -0,0 +1,24 @@
+from pathlib import Path
+
+from loguru import logger
+from typer import Typer
+
+from huesoporro.actions.import_from_vod import ImportFromVODAction
+from huesoporro.settings import Settings
+from huesoporro.svc.clean_cc_svc import CleanCCSvc
+from huesoporro.svc.download_closed_captions import DownloadClosedCaptionsSvc
+
+app = Typer()
+
+
+@app.command()
+def import_vod_cc(channel_name: str, youtube_url: str, db_path: Path | None = None):
+    logger.info(f"Importing VOD closed captions for {channel_name} from {youtube_url}")
+    s = Settings.get(db_filepath=db_path)
+    import_from_vod_action = ImportFromVODAction(
+        download_closed_captions_svc=DownloadClosedCaptionsSvc(),
+        clean_cc_svc=CleanCCSvc(),
+        s=s,
+    )
+    for cc_filepath in import_from_vod_action.run(channel_name, youtube_url):
+        logger.info(f"Closed captions imported from {cc_filepath}")

src/apps/httpapi/litestar/dependencies.py

@@ -1,16 +1,17 @@
 from litestar import Request
 from litestar.exceptions import HTTPException
 
-from src.huesoporro.actions.authenticate import AuthenticateAction
-from src.huesoporro.actions.get_user_by_jwt import GetUserByJWTAction
-from src.huesoporro.infra.authenticator import TwitchAuthenticator
-from src.huesoporro.infra.db import Database
-from src.huesoporro.infra.repos import UserRepo
-from src.huesoporro.models import User
-from src.huesoporro.settings import Settings
-from src.huesoporro.svc.get_chatbot_settings import ChatbotSettingsGetterSvc
-from src.huesoporro.svc.get_sentences_svc import SentencesGetterSvc
-from src.huesoporro.svc.store_settings import ChatbotSettingsStorerSvc
+from huesoporro.actions.authenticate import AuthenticateAction
+from huesoporro.actions.get_user_by_jwt import GetUserByJWTAction
+from huesoporro.infra.authenticator import TwitchAuthenticator
+from huesoporro.infra.db import Database
+from huesoporro.infra.repos import UserRepo
+from huesoporro.libs.db import MarkovDatabase
+from huesoporro.models import User
+from huesoporro.settings import Settings
+from huesoporro.svc.get_chatbot_settings import ChatbotSettingsGetterSvc
+from huesoporro.svc.store import SentenceStorerSvc
+from huesoporro.svc.store_settings import ChatbotSettingsStorerSvc
 
 
 def get_settings() -> Settings:
@@ -53,8 +54,8 @@ async def store_chatbot_settings_svc(db: Database):
     return ChatbotSettingsStorerSvc(db=db)
 
 
-async def get_sentences_svc(db: Database):
-    return SentencesGetterSvc(db=db)
+async def get_sentences_storer_svc(db: MarkovDatabase):
+    return SentenceStorerSvc(db=db)
 
 
 async def get_user_repo(s: Settings):

src/apps/httpapi/litestar/main.py

@@ -6,37 +6,35 @@ from litestar.exceptions import HTTPException
 from litestar.static_files import StaticFilesConfig
 from litestar.template import TemplateConfig
 
-from src.huesoporro.api.dependencies import (
+from apps.httpapi.litestar.dependencies import (
     authenticate,
     get_authenticate_action,
     get_authenticator,
     get_chatbot_settings_svc,
     get_db,
     get_get_user_by_jwt_action,
-    get_sentences_svc,
+    get_sentences_storer_svc,
     get_settings,
     get_user_repo,
     store_chatbot_settings_svc,
 )
-from src.huesoporro.api.errors import (
+from apps.httpapi.litestar.errors import (
     after_exception_handler,
     http_exception_handler,
     httpx_status_error_handler,
 )
-from src.huesoporro.api.routes.api import (
+from apps.httpapi.litestar.routes.api import (
     get_bot_settings,
     get_bot_status,
     get_index,
-    get_sentences,
     get_tts_overlay,
     get_tts_permalink,
     manage_bot,
     save_bot_settings,
-    save_new_sentence,
 )
-from src.huesoporro.api.routes.auth import get_code, login
-from src.huesoporro.bot import BotsManager
-from src.huesoporro.settings import Settings
+from apps.httpapi.litestar.routes.auth import get_code, login
+from huesoporro.bot import BotsManager
+from huesoporro.settings import Settings
 
 
 @get("/healthz")
@@ -57,8 +55,6 @@ def create_app():
             get_bot_status,
             save_bot_settings,
             get_bot_settings,
-            get_sentences,
-            save_new_sentence,
         ],
         static_files_config=(
             StaticFilesConfig(
@@ -87,7 +83,7 @@ def create_app():
             "bm": Provide(BotsManager, use_cache=True),
             "gbs": Provide(get_chatbot_settings_svc),
             "sbs": Provide(store_chatbot_settings_svc),
-            "sgs": Provide(get_sentences_svc),
+            "sss": Provide(get_sentences_storer_svc),
             "authenticator": Provide(get_authenticator),
             "authenticate_action": Provide(get_authenticate_action),
             "user_repo": Provide(get_user_repo),

src/apps/httpapi/litestar/routes/api.py

@@ -1,14 +1,14 @@
 from typing import Literal
 
-from litestar import MediaType, Response, get, post, put
+from litestar import MediaType, Response, get, put
+from litestar.datastructures import UploadFile
 from litestar.response import Template
-from pydantic import BaseModel
+from pydantic import BaseModel, ConfigDict
 
-from src.huesoporro.bot import BotsManager
-from src.huesoporro.models import ChatbotSettings, User
-from src.huesoporro.svc.get_chatbot_settings import ChatbotSettingsGetterSvc
-from src.huesoporro.svc.get_sentences_svc import SentencesGetterSvc
-from src.huesoporro.svc.store_settings import ChatbotSettingsStorerSvc
+from huesoporro.bot import BotsManager
+from huesoporro.models import ChatbotSettings, User
+from huesoporro.svc.get_chatbot_settings import ChatbotSettingsGetterSvc
+from huesoporro.svc.store_settings import ChatbotSettingsStorerSvc
 
 
 class ManageBotDTO(BaseModel):
@@ -16,6 +16,13 @@ class ManageBotDTO(BaseModel):
     channel_name: str | None = None
 
 
+class ImportTextFileDTO(BaseModel):
+    file: UploadFile
+    channel_name: str
+
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+
+
 @get(
     "/tts",
     media_type=MediaType.HTML,
@@ -97,17 +104,3 @@ async def save_bot_settings(
 ) -> dict:
     await sbs.run(user=user, bot_settings=data)
     return {"status": "ok"}
-
-
-@get("/sentences")
-async def get_sentences(user: User, sgs: SentencesGetterSvc) -> Template:
-    sentences = await sgs.run(user=user)
-    return Template(
-        template_name="sentences.html",
-        context={"sentences": [sentence.model_dump() for sentence in sentences]},
-    )
-
-
-@post("/api/v1/sentences")
-async def save_new_sentence(user: User, data: dict) -> dict:
-    return {"id": 54, "sentence": data["sentence"]}

src/apps/httpapi/litestar/routes/auth.py

@@ -4,8 +4,8 @@ from litestar import MediaType, get
 from litestar.datastructures.cookie import Cookie
 from litestar.response import Redirect, Template
 
-from src.huesoporro.actions.authenticate import AuthenticateAction
-from src.huesoporro.settings import Settings
+from huesoporro.actions.authenticate import AuthenticateAction
+from huesoporro.settings import Settings
 
 
 @get(path="/o/code")

src/huesoporro/actions/authenticate.py

@@ -1,9 +1,9 @@
 from pydantic import BaseModel
 
-from src.huesoporro.infra.authenticator import TwitchAuthenticator
-from src.huesoporro.infra.repos import UserRepo
-from src.huesoporro.models import User
-from src.huesoporro.settings import Settings
+from huesoporro.infra.authenticator import TwitchAuthenticator
+from huesoporro.infra.repos import UserRepo
+from huesoporro.models import User
+from huesoporro.settings import Settings
 
 
 class AuthenticateAction(BaseModel):

src/huesoporro/actions/get_random_quote.py

@@ -1,7 +1,7 @@
 from pydantic import BaseModel
 
-from src.huesoporro.models import Quote
-from src.huesoporro.svc.get_random_quote import RandomQuoteGetterSvc
+from huesoporro.models import Quote
+from huesoporro.svc.get_random_quote import RandomQuoteGetterSvc
 
 
 class GetRandomQuoteAction(BaseModel):

src/huesoporro/actions/get_user_by_jwt.py

@@ -1,10 +1,10 @@
 from loguru import logger
 from pydantic import BaseModel
 
-from src.huesoporro.infra.authenticator import TwitchAuthenticator
-from src.huesoporro.infra.repos import UserRepo
-from src.huesoporro.models import User
-from src.huesoporro.settings import Settings
+from huesoporro.infra.authenticator import TwitchAuthenticator
+from huesoporro.infra.repos import UserRepo
+from huesoporro.models import User
+from huesoporro.settings import Settings
 
 
 class GetUserByJWTAction(BaseModel):

src/huesoporro/actions/import_from_vod.py

@@ -0,0 +1,34 @@
+from collections.abc import Generator
+from pathlib import Path
+
+from pydantic import BaseModel, Field
+
+from huesoporro.libs.db import MarkovDatabase
+from huesoporro.settings import Settings
+from huesoporro.svc.clean_cc_svc import CleanCCSvc
+from huesoporro.svc.download_closed_captions import DownloadClosedCaptionsSvc
+from huesoporro.svc.store import SentenceStorerSvc
+
+
+class ImportFromVODAction(BaseModel):
+    download_closed_captions_svc: DownloadClosedCaptionsSvc
+
+    clean_cc_svc: CleanCCSvc
+    s: Settings = Field(default_factory=Settings.get)
+
+    ignore_lines: set[str] = {
+        "WEBVTT",
+        "Kind: captions",
+        "Language: en",
+        "Language: es",
+    }
+
+    def run(self, channel_name: str, youtube_url: str) -> Generator[Path, None, None]:
+        for cc_filepath in self.download_closed_captions_svc.run(youtube_url):
+            storer_svc = SentenceStorerSvc(
+                db=MarkovDatabase(channel=channel_name, settings=self.s)
+            )
+            for line in self.clean_cc_svc.run(cc_filepath):
+                if line and line not in self.ignore_lines:
+                    storer_svc.store_sentence(line.strip())
+            yield cc_filepath

src/huesoporro/actions/refresh.py

@@ -1,9 +1,9 @@
 from pydantic import BaseModel
 
-from src.huesoporro.infra.authenticator import TwitchAuthenticator
-from src.huesoporro.infra.repos import UserRepo
-from src.huesoporro.models import User
-from src.huesoporro.settings import Settings
+from huesoporro.infra.authenticator import TwitchAuthenticator
+from huesoporro.infra.repos import UserRepo
+from huesoporro.models import User
+from huesoporro.settings import Settings
 
 
 class RefreshAction(BaseModel):

src/huesoporro/actions/store_quote.py

@@ -2,9 +2,9 @@ import datetime
 
 from pydantic import BaseModel
 
-from src.huesoporro.models import Quote, User
-from src.huesoporro.svc.is_mod import IsModSvc
-from src.huesoporro.svc.quote_storer_svc import QuoteStorerSvc
+from huesoporro.models import Quote, User
+from huesoporro.svc.is_mod import IsModSvc
+from huesoporro.svc.quote_storer_svc import QuoteStorerSvc
 
 
 class StoreQuoteAction(BaseModel):

src/huesoporro/bot.py

@@ -2,25 +2,26 @@ import asyncio
 import random
 from collections.abc import Callable
 from enum import StrEnum
+from typing import ClassVar
 
 from loguru import logger
 from twitchio import Channel
 from twitchio.ext import commands, routines
 
-from src.huesoporro.actions.get_random_quote import GetRandomQuoteAction
-from src.huesoporro.actions.store_quote import StoreQuoteAction
-from src.huesoporro.api.dependencies import get_settings
-from src.huesoporro.infra.db import Database
-from src.huesoporro.infra.repos import QuoteRepo
-from src.huesoporro.libs.db import Database as MarkovDB
-from src.huesoporro.models import ChatbotSettings, User
-from src.huesoporro.svc.backoff_service import BackoffService
-from src.huesoporro.svc.generate import SentenceGeneratorSvc
-from src.huesoporro.svc.get_random_quote import RandomQuoteGetterSvc
-from src.huesoporro.svc.hello import HelloGeneratorSvc
-from src.huesoporro.svc.is_mod import IsModSvc
-from src.huesoporro.svc.quote_storer_svc import QuoteStorerSvc
-from src.huesoporro.svc.store import SentenceStorerSvc
+from huesoporro.actions.get_random_quote import GetRandomQuoteAction
+from huesoporro.actions.store_quote import StoreQuoteAction
+from huesoporro.infra.db import Database
+from huesoporro.infra.repos import QuoteRepo
+from huesoporro.libs.db import MarkovDatabase
+from huesoporro.models import ChatbotSettings, User
+from huesoporro.settings import Settings
+from huesoporro.svc.backoff_service import BackoffService
+from huesoporro.svc.generate import SentenceGeneratorSvc
+from huesoporro.svc.get_random_quote import RandomQuoteGetterSvc
+from huesoporro.svc.hello import get_hello_generator_svc
+from huesoporro.svc.is_mod import IsModSvc
+from huesoporro.svc.quote_storer_svc import QuoteStorerSvc
+from huesoporro.svc.store import SentenceStorerSvc
 
 
 class Bot(commands.Bot):
@@ -30,10 +31,10 @@ class Bot(commands.Bot):
         )
         self.channel = channel
         self.user = user
-        self.generate_svc = SentenceGeneratorSvc(db=MarkovDB(channel=channel))
-        self.hello_svc = HelloGeneratorSvc()
+        self.generate_svc = SentenceGeneratorSvc(db=MarkovDatabase(channel=channel))
+        self.hello_svc = get_hello_generator_svc()
         db = Database()
-        self.quote_repo = QuoteRepo(s=get_settings())
+        self.quote_repo = QuoteRepo(s=Settings.get())
         self.get_random_quote_svc = RandomQuoteGetterSvc(quote_repo=self.quote_repo)
         self.get_random_quote_action = GetRandomQuoteAction(
             quote_getter_svc=self.get_random_quote_svc
@@ -54,11 +55,6 @@ class Bot(commands.Bot):
         logger.info(f"Logged in as {self.nick}")
         logger.info(f"User id is {self.user_id}")
 
-    @commands.command(aliases=["h"])
-    async def hello(self, ctx: commands.Context, username: str | None = None):
-        username = username or ctx.author.name
-        await ctx.send(self.hello_svc.run(username))
-
     @commands.command(aliases=["g"])
     async def generate(self, ctx: commands.Context, *, words: str | None = None):
         sentence = await self.generate_svc.run(words)
@@ -98,6 +94,7 @@ class Bot(commands.Bot):
         quote = await self.get_random_quote_action.run(channel_name=self.channel)
         if quote:
             channel = self.get_channel_conn()
+            if channel:
                 logger.info(f"Sending random quote {quote.quote}")
                 await channel.send(quote.quote)
 
@@ -123,6 +120,23 @@ class Bot(commands.Bot):
         self.generation_routine.cancel()
 
 
+class HelloMessagesCog(commands.Cog):
+    hello_patterns: ClassVar[list[str]] = ["hola", "HOLA", "hiii", "ayo"]
+
+    def __init__(self, bot):
+        self.bot = bot
+        self.hello_svc = get_hello_generator_svc()
+
+    @commands.Cog.event()
+    async def event_message(self, message):
+        if not message.author:
+            return
+        if message.content in self.hello_patterns:
+            hello = self.hello_svc.run(message.author.name)
+            if hello:
+                await message.channel.send(hello)
+
+
 class MessageType(StrEnum):
     COMMAND = "COMMAND"
     HELLO = "HELLO"
@@ -136,7 +150,6 @@ class MessageHandler:
     """Handles different types of messages with their corresponding responses"""
 
     def __init__(self, channel_send_func: Callable):
-        self.hello_patterns = ["hola", "HOLA", "hiii", "ayo"]
         self.laugh_patterns = [
             "om",
             "KEK",
@@ -154,8 +167,6 @@ class MessageHandler:
         """Determines the type of message based on its content"""
         if content.startswith("!"):
             return MessageType.COMMAND
-        if content in self.hello_patterns:
-            return MessageType.HELLO
         if content == "Yes":
             return MessageType.YES
         if content.startswith("WHAT"):
@@ -164,10 +175,6 @@ class MessageHandler:
             return MessageType.LAUGH
         return MessageType.OTHER
 
-    async def handle_hello(self, author_name: str, hello_svc) -> str:
-        """Handles hello messages"""
-        return hello_svc.run(author_name)
-
     async def handle_laugh(self) -> str:
         """Handles laugh messages"""
         return random.choice(self.laugh_patterns)  # noqa: S311
@@ -176,20 +183,17 @@ class MessageHandler:
 class SaveMessagesCog(commands.Cog):
     def __init__(self, bot):
         self.bot = bot
-        self.store_svc = SentenceStorerSvc(db=MarkovDB(channel=bot.channel))
-        self.hello_svc = HelloGeneratorSvc()
+        self.store_svc = SentenceStorerSvc(db=MarkovDatabase(channel=bot.channel))
+        self.generate_svc = SentenceGeneratorSvc(db=MarkovDatabase(channel=bot.channel))
         self.backoff_svc = BackoffService()
         self.message_handler = MessageHandler(self._send_message)
 
-        # Register a separate send function for each message type
         self.send_functions = {
-            MessageType.HELLO: self._create_typed_send("hello"),
             MessageType.YES: self._create_typed_send("yes"),
             MessageType.WHAT: self._create_typed_send("what"),
             MessageType.LAUGH: self._create_typed_send("laugh"),
         }
 
-        # Register each send function with its own backoff
         for func in self.send_functions.values():
             self.backoff_svc.add_callable(func, backoff_seconds=10)
 
@@ -229,10 +233,6 @@ class SaveMessagesCog(commands.Cog):
         match msg_type:
             case MessageType.COMMAND:
                 return
-            case MessageType.HELLO:
-                response = await self.message_handler.handle_hello(
-                    message.author.name, self.hello_svc
-                )
             case MessageType.YES:
                 response = "Indeed"
             case MessageType.WHAT:
@@ -258,6 +258,7 @@ class BotsManager:
         logger.info(f"Adding bot for {user.user}")
         bot = Bot(user=user, channel=channel, chatbot_settings=chatbot_settings)
         bot.add_cog(SaveMessagesCog(bot))
+        bot.add_cog(HelloMessagesCog(bot))
         self.bots[user.user] = bot
 
     async def run_user_bot(self, user: User):

src/huesoporro/infra/authenticator.py

@@ -2,8 +2,8 @@ import httpx
 from litestar.exceptions import HTTPException
 from pydantic import BaseModel, ConfigDict, Field
 
-from src.huesoporro.models import TwitchAuth
-from src.huesoporro.settings import Settings
+from huesoporro.models import TwitchAuth
+from huesoporro.settings import Settings
 
 
 class TwitchAuthenticator(BaseModel):

src/huesoporro/infra/db.py

@@ -5,8 +5,8 @@ import aiosqlite
 from loguru import logger
 from pydantic import BaseModel, Field
 
-from src.huesoporro.models import ChatbotSettings, Sentence, User
-from src.huesoporro.settings import Settings
+from huesoporro.models import ChatbotSettings, User
+from huesoporro.settings import Settings
 
 
 class Database(BaseModel):
@@ -78,22 +78,3 @@ class Database(BaseModel):
         if not result:
             return None
         return ChatbotSettings(**dict(result))
-
-    async def save_sentence(self, sentence: str, auto_commit=True):
-        async with self.get_client(auto_commit=auto_commit) as db:
-            await db.execute(
-                "INSERT INTO sentences (sentence) VALUES (?)",
-                (sentence,),
-            )
-            await db.commit()
-
-    async def get_sentences(self, user: User) -> list[Sentence]:
-        async with self.get_client() as db:
-            db.row_factory = aiosqlite.Row
-            async with db.execute(
-                "SELECT * FROM sentences WHERE user_id = ?", (user.user,)
-            ) as cursor:
-                result = await cursor.fetchall()
-            if not result:
-                return []
-            return [Sentence(user=user, **dict(value)) for value in result]

src/huesoporro/infra/gtts.py

@@ -6,7 +6,7 @@ from gtts import gTTS
 from loguru import logger
 from pydantic import BaseModel
 
-from src.huesoporro.settings import Settings
+from huesoporro.settings import Settings
 
 
 class GTTS(BaseModel):

src/huesoporro/infra/repos.py

@@ -6,8 +6,8 @@ from typing import Generic, TypeVar
 import aiosqlite
 from pydantic import BaseModel, Field
 
-from src.huesoporro.models import Quote, User
-from src.huesoporro.settings import Settings
+from huesoporro.models import Quote, User
+from huesoporro.settings import Settings
 
 T = TypeVar("T", bound=BaseModel)
 

src/huesoporro/libs/db.py

@@ -4,11 +4,12 @@ import sqlite3
 import string
 from typing import Any
 
-import platformdirs
 from loguru import logger
 
+from huesoporro.settings import Settings
 
-class Database:
+
+class MarkovDatabase:
     """
     The database created is called `MarkovChain_{channel}.db`,
     and populated with 27 + 27^2 = 756 tables. Firstly, 27 tables with the structure of
@@ -86,14 +87,11 @@ class Database:
       to both get results from "hello" and "hello,".
     """
 
-    def __init__(self, channel: str):
-        self.user_data_path = platformdirs.user_data_path(
-            "huesoporro",
-            ensure_exists=True,
-        )
-        self.db_path = (
-            self.user_data_path / f"MarkovChain_{channel.replace('#', '').lower()}.db"
-        )
+    def __init__(self, channel: str, settings: Settings | None = None):
+        settings = settings or Settings.get()
+
+        self.db_path = settings.default_data_path / f"MarkovChain_{channel}.db"
+        self.user_data_path = self.db_path.parent
         self._execute_queue: list = []
 
         if self.db_path.is_file():
@@ -357,7 +355,7 @@ class Database:
 
             from nltk import ngrams
 
-            from src.huesoporro.libs.tokenizer import tokenize
+            from huesoporro.libs.tokenizer import tokenize
 
             channel = channel.replace("#", "").lower()
             copyfile(

src/huesoporro/main.py

@@ -1,6 +1,6 @@
 import uvicorn
 
-from src.huesoporro.settings import Settings
+from huesoporro.settings import Settings
 
 if __name__ == "__main__":
     settings = Settings.get()

src/huesoporro/models.py

@@ -4,7 +4,7 @@ from typing import Literal
 import jwt
 from pydantic import BaseModel, Field, field_validator
 
-from src.huesoporro.settings import Settings
+from huesoporro.settings import Settings
 
 
 class TwitchAuth(BaseModel):

src/huesoporro/settings.py

@@ -1,6 +1,7 @@
 from functools import lru_cache
 from pathlib import Path
 
+import platformdirs
 from pydantic import Field, HttpUrl, SecretStr, field_validator
 from pydantic_settings import BaseSettings
 
@@ -8,18 +9,19 @@ from pydantic_settings import BaseSettings
 class Settings(BaseSettings):
     port: int = 8000
     host: str = "0.0.0.0"  # noqa: S104
+
+    default_data_path: Path = platformdirs.user_data_path(
+        "huesoporro",
+        ensure_exists=True,
+    )
     static_files_path: Path = Field(
         default_factory=lambda: Path(__file__).parent / "static"
     )
     templates_files_path: Path = Field(
         default_factory=lambda: Path(__file__).parent / "templates"
     )
-    tts_cache_path: Path = Field(
-        default_factory=lambda: Path(__file__).parent / "tts_files"
-    )
-    db_filepath: Path = Field(
-        default_factory=lambda: Path(__file__).parent / "huesoporro.db"
-    )
+    tts_cache_path: Path = default_data_path / "tts_files"
+    db_filepath: Path = default_data_path / "huesoporro.db"
     twitch_client_id: str
     twitch_client_secret: SecretStr
     jwt_secret: SecretStr
@@ -31,8 +33,8 @@ class Settings(BaseSettings):
 
     @staticmethod
     @lru_cache(maxsize=1)
-    def get():
-        return Settings()  # type: ignore[call-arg] # pydantic-setting magic
+    def get(**data):
+        return Settings(**data)  # type: ignore[call-arg] # pydantic-setting magic
 
     @field_validator("allowed_users")
     @classmethod

src/huesoporro/svc/clean_cc_svc.py

@@ -0,0 +1,57 @@
+import re
+from collections.abc import Generator
+from pathlib import Path
+
+from pydantic import BaseModel
+
+
+class CleanCCSvc(BaseModel):
+    @classmethod
+    def clean_vtt_line(cls, line):
+        """
+        Clean a single line of VTT text by removing timestamps and HTML tags.
+
+        Args:
+            line (str): Single line from VTT file
+
+        Returns:
+            str: Cleaned line or None if line should be skipped
+        """
+        # Skip empty lines
+        if not line.strip():
+            return None
+        # Skip WEBVTT header
+        if line.strip().startswith("WEBVTT"):
+            return None
+
+        # Skip timestamp lines (e.g., "00:00:00.000 --> 00:00:02.000")
+        if re.match(
+            r"\d{2}:\d{2}:\d{2}\.\d{3}\s+-{2}>\s+\d{2}:\d{2}:\d{2}\.\d{3}", line
+        ):
+            return None
+
+        # Skip numeric identifiers
+        if line.strip().isdigit():
+            return None
+
+        # Remove HTML-style tags
+        line = re.sub(r"<[^>]+>", "", line)
+
+        # Remove multiple spaces
+        line = " ".join(line.split())
+
+        return line.strip()
+
+    @classmethod
+    def process_vtt_file(cls, file_path: Path):
+        seen_lines = set()
+
+        with file_path.open("r", encoding="utf-8") as f:
+            for line in f:
+                cleaned = cls.clean_vtt_line(line)
+                if line not in seen_lines:
+                    seen_lines.add(line)
+                    yield cleaned
+
+    def run(self, cc_file_path: Path) -> Generator[str, None, None]:
+        return self.process_vtt_file(cc_file_path)

src/huesoporro/svc/download_closed_captions.py

@@ -0,0 +1,44 @@
+import tempfile
+from collections.abc import Generator
+from pathlib import Path
+
+import yt_dlp
+from loguru import logger
+from pydantic import BaseModel
+
+
+class DownloadClosedCaptionsSvc(BaseModel):
+    @staticmethod
+    def run(youtube_url: str, sub_lang: str = "es") -> Generator[Path, None, None]:
+        """Download closed captions from a yt video and save it to a temp file
+
+        Args:
+            youtube_url: URL of the YouTube video
+            sub_lang: Language code for the subtitles (default: "es" for Spanish)
+
+        Returns:
+            Path: Path to the downloaded subtitles file
+
+        Raises:
+            ValueError: If subtitles are not available in the requested language
+        """
+        temp_dir = Path(tempfile.mkdtemp())
+        logger.info(f"Downloading subtitles for {youtube_url} to {temp_dir}")
+        ydl_opts = {
+            "skip_download": True,
+            "writesubtitles": True,
+            "writeautomaticsub": True,
+            "subtitleslangs": [sub_lang],
+            "subtitlesformat": "vtt",
+            "cookiesfrombrowser": ("firefox",),
+            "paths": {"home": str(temp_dir)},
+            "quiet": True,
+        }
+
+        try:
+            with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+                ydl.download([youtube_url])
+                return temp_dir.glob(f"*.{sub_lang}.vtt")
+
+        except yt_dlp.utils.DownloadError as exc:
+            raise ValueError(f"Failed to download subtitles: {exc!s}") from exc

src/huesoporro/svc/generate.py

@@ -3,8 +3,8 @@ import string
 from loguru import logger
 from pydantic import BaseModel, ConfigDict
 
-from src.huesoporro.libs.db import Database as MarkovDB
-from src.huesoporro.libs.tokenizer import detokenize, tokenize
+from huesoporro.libs.db import MarkovDatabase as MarkovDB
+from huesoporro.libs.tokenizer import detokenize, tokenize
 
 
 class SentenceGeneratorSvc(BaseModel):

src/huesoporro/svc/get_chatbot_settings.py

@@ -1,7 +1,7 @@
 from pydantic import BaseModel
 
-from src.huesoporro.infra.db import Database
-from src.huesoporro.models import ChatbotSettings, User
+from huesoporro.infra.db import Database
+from huesoporro.models import ChatbotSettings, User
 
 
 class ChatbotSettingsGetterSvc(BaseModel):

src/huesoporro/svc/get_random_quote.py

@@ -1,7 +1,7 @@
 from pydantic import BaseModel
 
-from src.huesoporro.infra.repos import QuoteRepo
-from src.huesoporro.models import Quote
+from huesoporro.infra.repos import QuoteRepo
+from huesoporro.models import Quote
 
 
 class RandomQuoteGetterSvc(BaseModel):

src/huesoporro/svc/get_sentences_svc.py

@@ -1,11 +0,0 @@
-from pydantic import BaseModel
-
-from src.huesoporro.infra.db import Database
-from src.huesoporro.models import Sentence, User
-
-
-class SentencesGetterSvc(BaseModel):
-    db: Database
-
-    async def run(self, user: User) -> list[Sentence]:
-        return await self.db.get_sentences(user=user)

src/huesoporro/svc/hello.py

@@ -1,11 +1,12 @@
 import random
+from functools import lru_cache
 
+from loguru import logger
 from pydantic import BaseModel, Field
 
 
 class HelloGeneratorSvc(BaseModel):
-    hellos: list[str] = Field(
-        default_factory=lambda: [
+    hellos: list[str] = [
         "Hola",
         "Ayo",
         "Hi",
@@ -14,7 +15,21 @@ class HelloGeneratorSvc(BaseModel):
         "HOLA",
         "hiii",
     ]
-    )
 
-    def run(self, username: str):
-        return f"{random.choice(self.hellos)} @{username}"  # noqa: S311
+    greeted_users: dict[str, str] = Field(default_factory=dict)
+
+    def run(self, username: str) -> str | None:
+        if username in self.greeted_users:
+            logger.info(f"User {username} already greeted")
+            return None
+
+        greeting = f"{random.choice(self.hellos)} @{username}"  # noqa: S311
+
+        self.greeted_users[username] = greeting
+
+        return greeting
+
+
+@lru_cache(maxsize=1)
+def get_hello_generator_svc() -> HelloGeneratorSvc:
+    return HelloGeneratorSvc()

src/huesoporro/svc/is_mod.py

@@ -1,7 +1,7 @@
 from pydantic import BaseModel
 
-from src.huesoporro.infra.db import Database
-from src.huesoporro.models import User
+from huesoporro.infra.db import Database
+from huesoporro.models import User
 
 
 class IsModSvc(BaseModel):

src/huesoporro/svc/quote_storer_svc.py

@@ -1,7 +1,7 @@
 from pydantic import BaseModel
 
-from src.huesoporro.infra.repos import QuoteRepo
-from src.huesoporro.models import Quote
+from huesoporro.infra.repos import QuoteRepo
+from huesoporro.models import Quote
 
 
 class QuoteStorerSvc(BaseModel):

src/huesoporro/svc/store.py

@@ -2,12 +2,12 @@ from loguru import logger
 from nltk.tokenize import sent_tokenize
 from pydantic import BaseModel, ConfigDict
 
-from src.huesoporro.libs.db import Database as MarkovDB
-from src.huesoporro.libs.tokenizer import tokenize
+from huesoporro.libs.db import MarkovDatabase
+from huesoporro.libs.tokenizer import tokenize
 
 
 class SentenceStorerSvc(BaseModel):
-    db: MarkovDB
+    db: MarkovDatabase
     key_length: int = 2
     end_tag: str = "<END>"
 

src/huesoporro/svc/store_settings.py

@@ -1,7 +1,7 @@
 from pydantic import BaseModel
 
-from src.huesoporro.infra.db import Database
-from src.huesoporro.models import ChatbotSettings, User
+from huesoporro.infra.db import Database
+from huesoporro.models import ChatbotSettings, User
 
 
 class ChatbotSettingsStorerSvc(BaseModel):

src/huesoporro/templates/index.html

@@ -185,7 +185,6 @@
         const chatbotManager = new ChatbotManager();
         chatbotManager.setEvents();
 
-
     });
 </script>
 </body>

src/huesoporro/templates/le_funny_dropdown.html

@@ -2,9 +2,8 @@
     <details class="dropdown">
         <summary>Le Funny</summary>
         <ul dir="rtl">
-            <li><a href="/sentences" >Sentences</a></li>
-            <li><a href="#" disabled>Quotes</a></li>
-            <li><a href="#" disabled>Copypastas</a></li>
+            <li><a href="/quotes" disabled>Quotes</a></li>
+            <li><a href="/copypastas" disabled>Copypastas</a></li>
         </ul>
     </details>
 </li>

src/huesoporro/templates/sentences.html

@@ -1,137 +0,0 @@
-{% include 'header.html' %}
-
-<body>
-<header>
-    <nav class="container">
-        <ul>
-            <li><a href="/">Chatbot</a></li>
-            <li><a href="/tts">TTS</a></li>
-            {% include 'le_funny_dropdown.html' %}
-        </ul>
-        {% include 'logout.html' %}
-    </nav>
-    <script>
-        function timestampToAwareDatetime(timestamp) {
-            const awareDatetime = new Date(timestamp);
-            awareDatetime.setMinutes(awareDatetime.getMinutes() - awareDatetime.getTimezoneOffset());
-            return awareDatetime;
-        }
-
-        function prettifyTimestamp(timestamp) {
-            const awareDatetime = timestampToAwareDatetime(timestamp);
-            return awareDatetime.toLocaleString();
-        }
-
-        function saveNewSentence(shortHash) {
-            /*
-            Save a newly-added sentence by POST'ing against /api/v1/sentences.
-
-            - if response is not 200, return nothing (validation logic to be added later
-            - if response is 200, retrieve save-new-${shortHash} and delete-new-${shortHas} and change their ids
-            to save-${newSentenceIdRetrievedFromResponse} and delete-${newSentenceIdRetrievedFromResponse}
-            assume a body like: {"id": 1, "sentence": "New sentence"}
-
-             */
-            const sentenceTextInput = document.getElementById(`newSentence${shortHash}`);
-            const sentence = sentenceTextInput.value;
-            // if sentence is empty, return
-            if (!sentence) {
-                return;
-            }
-            const sentenceData = {
-                "sentence": sentence
-            }
-            fetch(`/api/v1/sentences`, {
-                method: 'POST',
-                headers: {
-                    'Content-Type': 'application/json',
-                },
-                body: JSON.stringify(sentenceData)
-            }).then(response => {
-                response.json().then(data => {
-                    console.log(data);
-                    const saveButton = document.getElementById(`saveNew${shortHash}`);
-                    const deleteButton = document.getElementById(`deleteNew${shortHash}`);
-                    saveButton.id = `save-${data.id}`;
-                    deleteButton.id = `delete-${data.id}`;
-                });
-            });
-
-        }
-
-        function saveExistingSentence(id) {
-            // get sentence value by
-        }
-
-        document.addEventListener('DOMContentLoaded', function () {
-            const timestampCells = document.querySelectorAll('.timestamp-cell');
-            console.log(timestampCells);
-            timestampCells.forEach(cell => {
-                const timestampStr = cell.textContent.trim();
-                const timestamp = parseFloat(timestampStr) * 1000;
-                cell.textContent = prettifyTimestamp(timestamp);
-            });
-
-            const addButton = document.getElementById('add-sentence');
-            addButton.addEventListener('click', () => {
-                // add a new empty row at the top of the tbody
-                const sentencesTable = document.getElementById('sentencesTable');
-                const newRow = sentencesTable.insertRow();
-                const nowPrettyDate = prettifyTimestamp(Date.now());
-                const shortHash = Math.random().toString(36).substring(2, 10);
-                newRow.innerHTML = `
-                <td><textarea placeholder="Enter new sentence" id="newSentence${shortHash}"></textarea></td>
-                    <td class="timestamp-cell">${nowPrettyDate}</td>
-                    <td>
-                        <div class="container">
-                            <button id="saveNew${shortHash}" style="background-color: #00c482; border-color: #00c482" onclick="saveNewSentence('${shortHash}')">
-                                Save
-                            </button>
-                            <button id="deleteNew${shortHash}" style="border-color: #aa0000; background-color: #aa0000" onclick="this.parentElement.parentElement.parentElement.remove()">
-                                Delete
-                            </button>
-                        </div>
-                    </td>
-                `;
-            });
-        });
-    </script>
-</header>
-<main class="container">
-    <section>
-        <form role="search">
-            <input name="search" type="search" placeholder="Search sentence"/>
-            <input type="submit" value="Search"/>
-            <button id="add-sentence" class="secondary" type="button">Add</button>
-        </form>
-        <table id="sentencesTable">
-            <thead style="background-color: white; color: black">
-            <tr>
-                <th scope="col">Sentence</th>
-                <th scope="col">Last modified</th>
-                <th scope="col">Action</th>
-            </tr>
-            </thead>
-            <tbody id="sentencesTableBody">
-            {% for sentence in sentences %}
-            <tr>
-                <td><textarea>{{ sentence.sentence }}</textarea></td>
-                <td class="timestamp-cell">{{ sentence.last_updated_at }}</td>
-                <td>
-                    <div class="container">
-                        <button id="save-{{ sentence.id }}" style="background-color: #00c482; border-color: #00c482">
-                            Save
-                        </button>
-                        <button id="delete-{{ sentence.id }}" style="border-color: #aa0000; background-color: #aa0000">
-                            Delete
-                        </button>
-                    </div>
-                </td>
-            </tr>
-            {% endfor %}
-            </tbody>
-        </table>
-    </section>
-</main>
-</body>
-</html>

src/huesoporro/tts.py

@@ -7,7 +7,7 @@ from gtts import gTTS
 from litestar import WebSocket
 from loguru import logger
 
-from src.huesoporro.settings import Settings
+from huesoporro.settings import Settings
 
 
 class TTSManager:

tests/conftest.py

@@ -6,11 +6,11 @@ from caribou.migrate import load_migrations
 from polyfactory.factories.pydantic_factory import ModelFactory
 from polyfactory.pytest_plugin import register_fixture
 
-from src.huesoporro.infra.db import Database
-from src.huesoporro.models import ChatbotSettings, Quote, User
-from src.huesoporro.settings import Settings
-from src.huesoporro.svc.backoff_service import BackoffService
-from src.huesoporro.svc.is_mod import IsModSvc
+from huesoporro.infra.db import Database
+from huesoporro.models import ChatbotSettings, Quote, User
+from huesoporro.settings import Settings
+from huesoporro.svc.backoff_service import BackoffService
+from huesoporro.svc.is_mod import IsModSvc
 
 
 @pytest.fixture

tests/test_repos.py

@@ -2,8 +2,8 @@ import json
 
 import pytest
 
-from src.huesoporro.infra.repos import QuoteRepo, UserRepo
-from src.huesoporro.models import User
+from huesoporro.infra.repos import QuoteRepo, UserRepo
+from huesoporro.models import User
 
 
 @pytest.fixture

tests/test_svc.py

@@ -3,8 +3,8 @@ import time
 
 import pytest
 
-from src.huesoporro.models import ChatbotSettings, User
-from src.huesoporro.svc.is_mod import IsModSvc
+from huesoporro.models import ChatbotSettings, User
+from huesoporro.svc.is_mod import IsModSvc
 
 
 async def test_is_mod_svc_returns_true_for_channel(is_mod_svc: IsModSvc, user: User):

uv.lock

@@ -517,8 +517,8 @@ wheels = [
 
 [[package]]
 name = "huesoporro"
-version = "0.2.9"
-source = { virtual = "." }
+version = "0.3.0"
+source = { editable = "." }
 dependencies = [
     { name = "aiosqlite" },
     { name = "caribou" },
@@ -538,6 +538,10 @@ dependencies = [
 ]
 
 [package.dev-dependencies]
+cli = [
+    { name = "typer" },
+    { name = "yt-dlp" },
+]
 dev = [
     { name = "mypy" },
     { name = "polyfactory" },
@@ -567,6 +571,10 @@ requires-dist = [
 ]
 
 [package.metadata.requires-dev]
+cli = [
+    { name = "typer", specifier = ">=0.15.1" },
+    { name = "yt-dlp", specifier = ">=2025.1.26" },
+]
 dev = [
     { name = "mypy", specifier = ">=1.13.0" },
     { name = "polyfactory", specifier = ">=2.18.1" },
@@ -1367,6 +1375,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/63/6a/aca01554949f3a401991dc32fe22837baeaccb8a0d868256cbb26a029778/ruff-0.9.7-py3-none-win_arm64.whl", hash = "sha256:b075a700b2533feb7a01130ff656a4ec0d5f340bb540ad98759b8401c32c2037", size = 10177763 },
 ]
 
+[[package]]
+name = "shellingham"
+version = "1.5.4"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/58/15/8b3609fd3830ef7b27b655beb4b4e9c62313a4e8da8c676e142cc210d58e/shellingham-1.5.4.tar.gz", hash = "sha256:8dbca0739d487e5bd35ab3ca4b36e11c4078f3a234bfce294b0a0291363404de", size = 10310 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e0/f9/0595336914c5619e5f28a1fb793285925a8cd4b432c9da0a987836c7f822/shellingham-1.5.4-py2.py3-none-any.whl", hash = "sha256:7ecfff8f2fd72616f7481040475a65b2bf8af90a56c89140852d1120324e8686", size = 9755 },
+]
+
 [[package]]
 name = "six"
 version = "1.17.0"
@@ -1450,6 +1467,21 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/4b/be/49d93b0e13dad69a636e550a7b96a5208af9a91100f9b142a363882e0c4c/twitchio-2.10.0-py3-none-any.whl", hash = "sha256:7aa0b6950dad90feeb04b03fd10d3e4292fa8a7c2e7aea6b2fd6686bc5425fb2", size = 143761 },
 ]
 
+[[package]]
+name = "typer"
+version = "0.15.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "click" },
+    { name = "rich" },
+    { name = "shellingham" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/cb/ce/dca7b219718afd37a0068f4f2530a727c2b74a8b6e8e0c0080a4c0de4fcd/typer-0.15.1.tar.gz", hash = "sha256:a0588c0a7fa68a1978a069818657778f86abe6ff5ea6abf472f940a08bfe4f0a", size = 99789 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/d0/cc/0a838ba5ca64dc832aa43f727bd586309846b0ffb2ce52422543e6075e8a/typer-0.15.1-py3-none-any.whl", hash = "sha256:7994fb7b8155b64d3402518560648446072864beefd44aa2dc36972a5972e847", size = 44908 },
+]
+
 [[package]]
 name = "typing-extensions"
 version = "4.12.2"
@@ -1688,3 +1720,12 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/f5/d5/688db678e987c3e0fb17867970700b92603cadf36c56e5fb08f23e822a0c/yarl-1.18.3-cp313-cp313-win_amd64.whl", hash = "sha256:578e281c393af575879990861823ef19d66e2b1d0098414855dd367e234f5b3c", size = 315723 },
     { url = "https://files.pythonhosted.org/packages/f5/4b/a06e0ec3d155924f77835ed2d167ebd3b211a7b0853da1cf8d8414d784ef/yarl-1.18.3-py3-none-any.whl", hash = "sha256:b57f4f58099328dfb26c6a771d09fb20dbbae81d20cfb66141251ea063bd101b", size = 45109 },
 ]
+
+[[package]]
+name = "yt-dlp"
+version = "2025.2.19"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/53/36/ef300ba4a228b74612d4013b43ed303a0d6d2de17a71fc37e0b821577e0a/yt_dlp-2025.2.19.tar.gz", hash = "sha256:f33ca76df2e4db31880f2fe408d44f5058d9f135015b13e50610dfbe78245bea", size = 2929199 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/9e/45/6d1b759e68f5363b919828fb0e0c167a1cd5003b5b7c74cc0f0c2096be4f/yt_dlp-2025.2.19-py3-none-any.whl", hash = "sha256:3ed218eaeece55e9d715afd41abc450dc406ee63bf79355169dfde312d38fdb8", size = 3186543 },
+]