Code clean-up: removal of dead code and shortening expressions

notebooks/google_drive_web_vtt_vectorizer_and_storer.ipynb

@@ -86,7 +86,16 @@
    "outputs": [],
    "source": [
     "web_vtt_parser = container.mime_type_handler_factory(MIME_TYPE)\n",
-    "display_html(f\"<p>{escape(str(type(web_vtt_parser)))}</p>\")"
+    "display_html(f\"<p>{escape(str(type(web_vtt_parser)))}</p><code>{id(web_vtt_parser)}</code>\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "display_html(f\"<code>{id(container.mime_type_handler_factory(MIME_TYPE))}</code>\")"
    ]
   },
   {

src/ctp_slack_bot/containers.py

@@ -8,7 +8,7 @@ from slack_bolt.async_app import AsyncApp
 from ctp_slack_bot.core.config import Settings
 from ctp_slack_bot.db.mongo_db import MongoDBResource
 from ctp_slack_bot.db.repositories.mongo_db_vectorized_chunk_repository import MongoVectorizedChunkRepositoryResource
-from ctp_slack_bot.mime_type_handlers.base import MimeTypeHandlerMeta
+from ctp_slack_bot.mime_type_handlers.base import MimeTypeHandler
 from ctp_slack_bot.services.answer_retrieval_service import AnswerRetrievalService
 from ctp_slack_bot.services.content_ingestion_service import ContentIngestionService
 from ctp_slack_bot.services.context_retrieval_service import ContextRetrievalService
@@ -78,7 +78,7 @@ class Container(DeclarativeContainer): # TODO: audit for potential async-related
                                             slack_service,
                                             slack_bolt_app,
                                             settings)
-    mime_type_handler_factory   = Callable (lambda mime_type: MimeTypeHandlerMeta._registry[mime_type]())
+    mime_type_handler_factory   = Callable (MimeTypeHandler.for_mime_type)
     google_drive_service        = Singleton(GoogleDriveService,
                                             settings=settings)
     # file_monitor_service        = Singleton(FileMonitorService,

src/ctp_slack_bot/mime_type_handlers/__init__.py

@@ -1,2 +1,2 @@
-from ctp_slack_bot.mime_type_handlers.base import BaseMimeTypeHandler, MimeTypeHandlerMeta
+from ctp_slack_bot.mime_type_handlers.base import MimeTypeHandler, MimeTypeHandlerMeta
 from ctp_slack_bot.mime_type_handlers.text.vtt import WebVTTMimeTypeHandler

src/ctp_slack_bot/mime_type_handlers/base.py

@@ -1,4 +1,5 @@
 from abc import ABCMeta, abstractmethod
+from functools import lru_cache
 from typing import Any, ClassVar, Dict, Mapping, Optional
 
 from ctp_slack_bot.models import Content
@@ -18,11 +19,12 @@ class MimeTypeHandlerABCMeta(MimeTypeHandlerMeta, ABCMeta):
     pass
 
 
-class BaseMimeTypeHandler(metaclass=MimeTypeHandlerABCMeta):
+class MimeTypeHandler(metaclass=MimeTypeHandlerABCMeta):
 
     @classmethod
-    def for_mime_type(cls, mime_type: str) -> Optional[type["BaseMimeHandler"]]:
-        return cls._registry.get(mime_type)
+    @lru_cache
+    def for_mime_type(cls, mime_type: str) -> Optional[type["MimeTypeHandler"]]:
+        return cls._registry.get(mime_type)()
 
     @abstractmethod
     def from_bytes(cls, id: str, metadata: Mapping[str, Any], buffer: bytes) -> Content:

src/ctp_slack_bot/mime_type_handlers/text/vtt.py

@@ -5,23 +5,16 @@ from types import MappingProxyType
 from typing import Any, Mapping, Optional, Self
 from webvtt import WebVTT
 
-from ctp_slack_bot.mime_type_handlers import BaseMimeTypeHandler
+from ctp_slack_bot.mime_type_handlers import MimeTypeHandler
 from ctp_slack_bot.models import Content, WebVTTContent, WebVTTFrame
 
 
 ISO_DATE_TIME_PATTERN = compile_re(r"Start time: (\d{4}-\d{2}-\d{2}(?: \d{2}:\d{2}:\d{2}(?:Z|[+-]\d{2}:\d{2})?)?)")
 
-class WebVTTMimeTypeHandler(BaseMimeTypeHandler):
+class WebVTTMimeTypeHandler(MimeTypeHandler):
 
     MIME_TYPE = "text/vtt"
 
-    def from_buffer(self: Self, id: str, metadata: Mapping[str, Any], buffer: bytes) -> WebVTTContent:
-        web_vtt = WebVTT.from_buffer(BytesIO(buffer))
-        frames = tuple(WebVTTFrame.from_webvtt_caption(caption, index)
-                       for index, caption
-                       in enumerate(web_vtt.captions, 1))
-        return WebVTTContent(id=id, metadata=MappingProxyType(metadata), start_time=cls.__get_start_time(web_vtt), frames=frames)
-
     @classmethod
     def __get_start_time(cls, web_vtt: WebVTT) -> Optional[datetime]:
         try: