Add logging functionality and configuration to app.py; update file handling and supported formats

.gitignore

@@ -195,3 +195,5 @@ cython_debug/
 
 ./temp
 .gradio
+.claude
+CLAUDE.md

src/app.py

@@ -1,6 +1,7 @@
 import os
+import logging
 from pathlib import Path
-from typing import *
+from typing import Optional
 from urllib.parse import urlparse
 
 import convertapi
@@ -8,8 +9,46 @@ import gradio as gr
 from dotenv import load_dotenv
 
 load_dotenv()
+
+# Setup logging
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+)
+logger = logging.getLogger(__name__)
+
 convertapi.api_credentials = os.getenv("CONVERTAPI_TOKEN")
 
+if not convertapi.api_credentials:
+    logger.error("CONVERTAPI_TOKEN not found in environment variables")
+    raise ValueError("CONVERTAPI_TOKEN is required")
+
+# Configuration constants
+MAX_FILE_SIZE = int(os.getenv("MAX_FILE_SIZE", 10 * 1024 * 1024))  # 10MB default
+TEMP_DIR = os.getenv("TEMP_DIR", "temp")
+LOG_LEVEL = os.getenv("LOG_LEVEL", "INFO")
+
+# Update logging level from config
+logger.setLevel(getattr(logging, LOG_LEVEL.upper()))
+
+# Get all supported formats from ConvertAPI
+def get_supported_formats():
+    try:
+        # Common formats that ConvertAPI supports
+        return [
+            "pdf", "docx", "doc", "txt", "rtf", "odt", "html", "epub",
+            "png", "jpg", "jpeg", "gif", "bmp", "tiff", "webp", "svg",
+            "xlsx", "xls", "csv", "ods", 
+            "pptx", "ppt", "odp",
+            "mp4", "avi", "mov", "wmv", "flv", "webm",
+            "mp3", "wav", "flac", "aac", "ogg"
+        ]
+    except Exception:
+        # Fallback to basic formats
+        return ["pdf", "docx", "txt", "png", "jpg", "xlsx", "pptx"]
+
+SUPPORTED_FORMATS = get_supported_formats()
+
 
 # Function to convert a local file
 def convert_local_file(local_file_path: str, output_format: str) -> str:
@@ -24,10 +63,28 @@ def convert_local_file(local_file_path: str, output_format: str) -> str:
         str: The path to the converted file or an error message.
     """
     try:
+        logger.info(f"Starting conversion of {local_file_path} to {output_format}")
+        
+        # Input validation
         if not local_file_path or not os.path.exists(local_file_path):
-            return "Invalid or non-existent local file path."
+            error_msg = "Invalid or non-existent local file path."
+            logger.error(error_msg)
+            return error_msg
+
+        if output_format not in SUPPORTED_FORMATS:
+            error_msg = f"Unsupported output format: {output_format}"
+            logger.error(error_msg)
+            return error_msg
+
+        # Check file size
+        file_size = os.path.getsize(local_file_path)
+        if file_size > MAX_FILE_SIZE:
+            error_msg = f"File too large: {file_size / (1024*1024):.1f}MB (max {MAX_FILE_SIZE / (1024*1024):.0f}MB)"
+            logger.error(error_msg)
+            return error_msg
 
         # Convert the local file
+        logger.info(f"Converting file: {local_file_path}")
         result = convertapi.convert(output_format, {"File": local_file_path})
 
         # Derive filename from local path
@@ -35,16 +92,19 @@ def convert_local_file(local_file_path: str, output_format: str) -> str:
 
         # Save the converted file to a temporary location
         output_filename = f"{input_filename}.{output_format}"
-        output_path = Path("temp") / output_filename
+        output_path = Path(TEMP_DIR) / output_filename
         output_path.parent.mkdir(exist_ok=True)
 
         result.file.save(str(output_path))
+        logger.info(f"Conversion successful: {output_path}")
 
         # Return the file path string on success
         return str(output_path)
 
     except Exception as e:
-        return f"Error converting file: {str(e)}"
+        error_msg = f"Error converting file: {str(e)}"
+        logger.error(error_msg)
+        return error_msg
 
 
 # Function to convert a file from a URL
@@ -60,13 +120,24 @@ def convert_from_url(document_url: str, output_format: str) -> str:
         str: The path to the converted file or an error message.
     """
     try:
+        logger.info(f"Starting URL conversion of {document_url} to {output_format}")
+        
+        # Input validation
         if not document_url or not (
             document_url.lower().startswith("http://")
             or document_url.lower().startswith("https://")
         ):
-            return "Invalid or unsupported URL format."
+            error_msg = "Invalid or unsupported URL format."
+            logger.error(error_msg)
+            return error_msg
+
+        if output_format not in SUPPORTED_FORMATS:
+            error_msg = f"Unsupported output format: {output_format}"
+            logger.error(error_msg)
+            return error_msg
 
         # Convert the file from a URL
+        logger.info(f"Converting file from URL: {document_url}")
         result = convertapi.convert(output_format, {"File": document_url})
 
         # Attempt to derive a filename from the URL for saving
@@ -80,16 +151,19 @@ def convert_from_url(document_url: str, output_format: str) -> str:
 
         # Save the converted file to a temporary location
         output_filename = f"{input_filename}.{output_format}"
-        output_path = Path("temp") / output_filename
+        output_path = Path(TEMP_DIR) / output_filename
         output_path.parent.mkdir(exist_ok=True)
 
         result.file.save(str(output_path))
+        logger.info(f"URL conversion successful: {output_path}")
 
         # Return the file path string on success
         return str(output_path)
 
     except Exception as e:
-        return f"Error converting file from URL: {str(e)}"
+        error_msg = f"Error converting file from URL: {str(e)}"
+        logger.error(error_msg)
+        return error_msg
 
 
 # Create Gradio interfaces
@@ -98,18 +172,7 @@ local_file_demo = gr.Interface(
     inputs=[
         gr.File(label="Upload File"),
         gr.Dropdown(
-            choices=[
-                "docx",
-                "pdf",
-                "txt",
-                "png",
-                "jpg",
-                "jpeg",
-                "xlsx",
-                "pptx",
-                "html",
-                "rtf",
-            ],
+            choices=SUPPORTED_FORMATS,
             label="Output Format",
             value="pdf",
         ),
@@ -127,18 +190,7 @@ url_demo = gr.Interface(
             value="",
         ),
         gr.Dropdown(
-            choices=[
-                "docx",
-                "pdf",
-                "txt",
-                "png",
-                "jpg",
-                "jpeg",
-                "xlsx",
-                "pptx",
-                "html",
-                "rtf",
-            ],
+            choices=SUPPORTED_FORMATS,
             label="Output Format",
             value="pdf",
         ),