Merge pull request #54 from marcogll/feature/sprint-updates-20240112-15660961988964187929

Complete Sprint Tasks and Restore Google Calendar

bot/main.py

@@ -42,7 +42,8 @@ from bot.modules.vikunja import vikunja_conv_handler, get_projects_list, get_tas
 from bot.modules.printer import send_file_to_printer, check_print_status
 from bot.db import setup_database
 from bot.modules.flow_engine import FlowEngine
-from bot.modules.llm_engine import transcribe_audio
+from bot.modules.transcription import transcribe_audio
+from bot.modules.file_validation import validate_document
 
 from bot.scheduler import schedule_daily_summary
 
@@ -169,6 +170,13 @@ async def handle_document(update: Update, context: ContextTypes.DEFAULT_TYPE) ->
     """Handles documents sent to the bot for printing."""
     document = update.message.document
     user_id = update.effective_user.id
+
+    # Validate the document before processing
+    is_valid, message = validate_document(document)
+    if not is_valid:
+        await update.message.reply_text(message)
+        return
+
     file = await context.bot.get_file(document.file_id)
 
     # Create a directory for temporary files if it doesn't exist

bot/modules/file_validation.py

@@ -0,0 +1,91 @@
+# bot/modules/file_validation.py
+# This module provides functions for validating files before processing.
+
+import logging
+from telegram import Document
+
+# Set up logging
+logger = logging.getLogger(__name__)
+
+# --- Configuration ---
+# Whitelist of allowed MIME types. Prevents processing of potentially harmful files.
+# Examples: 'application/pdf', 'image/jpeg', 'application/msword',
+# 'application/vnd.openxmlformats-officedocument.wordprocessingml.document'
+ALLOWED_MIME_TYPES = {
+    'application/pdf',
+    'application/msword',
+    'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
+    'text/plain',
+    'image/jpeg',
+    'image/png'
+}
+
+# Maximum file size in bytes (e.g., 10 * 1024 * 1024 for 10 MB)
+MAX_FILE_SIZE_BYTES = 10 * 1024 * 1024  # 10 MB
+
+# --- Validation Functions ---
+
+def is_file_type_allowed(document: Document) -> bool:
+    """
+    Checks if the document's MIME type is in the allowed whitelist.
+
+    Args:
+        document: The Telegram Document object to check.
+
+    Returns:
+        True if the MIME type is allowed, False otherwise.
+    """
+    if not document or not document.mime_type:
+        logger.warning("Document or its MIME type is missing.")
+        return False
+
+    logger.info(f"Validating file type: {document.mime_type}")
+
+    if document.mime_type in ALLOWED_MIME_TYPES:
+        logger.info("File type is allowed.")
+        return True
+    else:
+        logger.warning(f"File type '{document.mime_type}' is not in the allowed list.")
+        return False
+
+def is_file_size_acceptable(document: Document) -> bool:
+    """
+    Checks if the document's file size is within the acceptable limit.
+
+    Args:
+        document: The Telegram Document object to check.
+
+    Returns:
+        True if the file size is acceptable, False otherwise.
+    """
+    if not document or document.file_size is None:
+        logger.warning("Document or its file size is missing.")
+        return False
+
+    logger.info(f"Validating file size: {document.file_size} bytes.")
+
+    if document.file_size <= MAX_FILE_SIZE_BYTES:
+        logger.info("File size is acceptable.")
+        return True
+    else:
+        logger.warning(f"File size {document.file_size} exceeds the limit of {MAX_FILE_SIZE_BYTES} bytes.")
+        return False
+
+def validate_document(document: Document) -> (bool, str):
+    """
+    Performs all validation checks on a document.
+
+    Args:
+        document: The Telegram Document object to validate.
+
+    Returns:
+        A tuple containing a boolean indicating if the document is valid,
+        and a string message explaining the result.
+    """
+    if not is_file_type_allowed(document):
+        return False, f"Unsupported file type: {document.mime_type}. Please upload a supported document."
+
+    if not is_file_size_acceptable(document):
+        return False, f"File is too large. The maximum allowed size is {MAX_FILE_SIZE_BYTES // 1024 // 1024} MB."
+
+    return True, "File is valid and can be processed."

bot/modules/llm_engine.py

@@ -33,24 +33,3 @@ def get_smart_response(prompt):
         # Si algo sale mal, devolvemos el error
         return f"Ocurrió un error al comunicarse con OpenAI: {e}"
 
-def transcribe_audio(audio_file_path):
-    """
-    Transcribes an audio file using OpenAI's Whisper model.
-
-    Parameters:
-    - audio_file_path: The path to the audio file.
-    """
-    if not OPENAI_API_KEY:
-        return "Error: OPENAI_API_KEY is not configured."
-
-    try:
-        client = openai.OpenAI(api_key=OPENAI_API_KEY)
-
-        with open(audio_file_path, "rb") as audio_file:
-            transcript = client.audio.transcriptions.create(
-                model="whisper-1",
-                file=audio_file
-            )
-        return transcript.text
-    except Exception as e:
-        return f"Error during audio transcription: {e}"

bot/modules/transcription.py

@@ -0,0 +1,47 @@
+# bot/modules/transcription.py
+# This module handles audio transcription using the Whisper API.
+
+import logging
+import os
+from openai import OpenAI
+from bot.config import OPENAI_API_KEY
+
+# Set up logging
+logger = logging.getLogger(__name__)
+
+# Initialize the OpenAI client
+if not OPENAI_API_KEY:
+    logger.error("OPENAI_API_KEY is not configured in environment variables.")
+    client = None
+else:
+    client = OpenAI(api_key=OPENAI_API_KEY)
+
+def transcribe_audio(file_path: str) -> str:
+    """
+    Transcribes an audio file using the Whisper API.
+
+    Args:
+        file_path: The path to the audio file to transcribe.
+
+    Returns:
+        The transcribed text, or an error message if transcription fails.
+    """
+    if not client:
+        return "Error: OpenAI API key is not configured."
+
+    if not os.path.exists(file_path):
+        logger.error(f"Audio file not found at: {file_path}")
+        return "Error: Audio file not found."
+
+    try:
+        logger.info(f"Transcribing audio from: {file_path}")
+        with open(file_path, "rb") as audio_file:
+            transcript = client.audio.transcriptions.create(
+                model="whisper-1",
+                file=audio_file
+            )
+        logger.info("Transcription successful.")
+        return transcript.text
+    except Exception as e:
+        logger.error(f"Error during audio transcription: {e}")
+        return "Error: Could not transcribe audio."

requirements.txt

@@ -1,4 +1,4 @@
-python-telegram-bot[job-queue]<22
+python-telegram-bot[job-queue]==21.1.1
 requests
 schedule
 google-api-python-client
@@ -7,3 +7,4 @@ google-auth-oauthlib
 openai
 pytz
 python-dotenv
+ffmpeg-python