[Cursor] Simplify serverless handler

api/index.py

@@ -58,8 +58,73 @@ def download_file(url):
     except Exception as e:
         raise ValueError(f"Failed to download file: {str(e)}")
 
-def handler(event, context):
-    """Serverless handler for Vercel"""
+def handle_root():
+    return {
+        "status": "ok",
+        "message": "Document Processing API",
+        "version": "1.0.0"
+    }
+
+def handle_health():
+    return {
+        "status": "healthy",
+        "timestamp": str(datetime.datetime.now(datetime.UTC))
+    }
+
+def handle_parse_file(file_data):
+    if not file_data:
+        raise ValueError("No file provided")
+        
+    if not is_valid_file(file_data):
+        raise ValueError("Invalid file type")
+        
+    fd, temp_path = tempfile.mkstemp()
+    os.close(fd)
+    
+    try:
+        with open(temp_path, 'wb') as f:
+            f.write(file_data)
+        
+        return {
+            "status": "success",
+            "message": "File processed successfully",
+            "metadata": {
+                "size": os.path.getsize(temp_path),
+                "mime_type": magic.from_file(temp_path, mime=True)
+            }
+        }
+    finally:
+        try:
+            os.unlink(temp_path)
+        except:
+            pass
+
+def handle_parse_url(url):
+    if not url:
+        raise ValueError("No URL provided")
+        
+    if not url.startswith(('http://', 'https://')):
+        raise ValueError("Invalid URL")
+        
+    temp_path, content_type = download_file(url)
+    try:
+        return {
+            "status": "success",
+            "message": "URL processed successfully",
+            "metadata": {
+                "url": url,
+                "content_type": content_type,
+                "size": os.path.getsize(temp_path)
+            }
+        }
+    finally:
+        try:
+            os.unlink(temp_path)
+        except:
+            pass
+
+def handler(request, context):
+    """Vercel serverless handler"""
     
     # Add CORS headers to all responses
     cors_headers = {
@@ -70,168 +135,36 @@ def handler(event, context):
     }
     
     # Handle OPTIONS request for CORS
-    if event.get('httpMethod') == 'OPTIONS':
+    if request.get('httpMethod') == 'OPTIONS':
         return {
             "statusCode": 204,
             "headers": cors_headers,
             "body": ""
         }
     
-    # Get path and method
-    path = event.get('path', '/').rstrip('/')
-    method = event.get('httpMethod', 'GET')
-    
     try:
+        # Get path and method
+        path = request.get('path', '/').rstrip('/')
+        method = request.get('httpMethod', 'GET')
+        
         # Route request
+        response_data = None
         if path == '' or path == '/':
-            return {
-                "statusCode": 200,
-                "headers": cors_headers,
-                "body": json.dumps({
-                    "status": "ok",
-                    "message": "Document Processing API",
-                    "version": "1.0.0"
-                })
-            }
-            
+            response_data = handle_root()
         elif path == '/health':
-            return {
-                "statusCode": 200,
-                "headers": cors_headers,
-                "body": json.dumps({
-                    "status": "healthy",
-                    "timestamp": str(datetime.datetime.now(datetime.UTC))
-                })
-            }
-            
+            response_data = handle_health()
         elif path == '/parse/file' and method == 'POST':
-            # Check if there's a file in the request
-            if 'body' not in event or not event['body']:
-                return {
-                    "statusCode": 400,
-                    "headers": cors_headers,
-                    "body": json.dumps({
-                        "error": "No file provided",
-                        "details": "Please provide a file in the request body"
-                    })
-                }
-                
-            # Get file data
-            file_data = event['body']
-            if event.get('isBase64Encoded', False):
+            file_data = request.get('body', '')
+            if request.get('isBase64Encoded', False):
                 import base64
                 file_data = base64.b64decode(file_data)
-                
-            # Validate file type
-            if not is_valid_file(file_data):
-                return {
-                    "statusCode": 400,
-                    "headers": cors_headers,
-                    "body": json.dumps({
-                        "error": "Invalid file type",
-                        "details": "Supported formats: PDF, TXT, HTML, MD, DOCX"
-                    })
-                }
-                
-            # Save to temp file
-            fd, temp_path = tempfile.mkstemp()
-            os.close(fd)
-            
-            try:
-                with open(temp_path, 'wb') as f:
-                    f.write(file_data)
-                
-                # Process file here
-                return {
-                    "statusCode": 200,
-                    "headers": cors_headers,
-                    "body": json.dumps({
-                        "status": "success",
-                        "message": "File processed successfully",
-                        "metadata": {
-                            "size": os.path.getsize(temp_path),
-                            "mime_type": magic.from_file(temp_path, mime=True)
-                        }
-                    })
-                }
-            finally:
-                # Clean up temp file
-                try:
-                    os.unlink(temp_path)
-                except:
-                    pass
-                    
+            response_data = handle_parse_file(file_data)
         elif path == '/parse/url' and method == 'POST':
-            # Get request body
-            if 'body' not in event or not event['body']:
-                return {
-                    "statusCode": 400,
-                    "headers": cors_headers,
-                    "body": json.dumps({
-                        "error": "No request body",
-                        "details": "Please provide a URL in the request body"
-                    })
-                }
-                
-            # Parse JSON body
             try:
-                body = json.loads(event['body'])
+                body = json.loads(request.get('body', '{}'))
             except:
-                return {
-                    "statusCode": 400,
-                    "headers": cors_headers,
-                    "body": json.dumps({
-                        "error": "Invalid JSON",
-                        "details": "Request body must be valid JSON"
-                    })
-                }
-                
-            # Get URL from body
-            url = body.get('url')
-            if not url:
-                return {
-                    "statusCode": 400,
-                    "headers": cors_headers,
-                    "body": json.dumps({
-                        "error": "No URL provided",
-                        "details": "Please provide a URL in the request body"
-                    })
-                }
-                
-            if not url.startswith(('http://', 'https://')):
-                return {
-                    "statusCode": 400,
-                    "headers": cors_headers,
-                    "body": json.dumps({
-                        "error": "Invalid URL",
-                        "details": "URL must start with http:// or https://"
-                    })
-                }
-                
-            # Download and process file
-            temp_path, content_type = download_file(url)
-            try:
-                # Process file here
-                return {
-                    "statusCode": 200,
-                    "headers": cors_headers,
-                    "body": json.dumps({
-                        "status": "success",
-                        "message": "URL processed successfully",
-                        "metadata": {
-                            "url": url,
-                            "content_type": content_type,
-                            "size": os.path.getsize(temp_path)
-                        }
-                    })
-                }
-            finally:
-                # Clean up temp file
-                try:
-                    os.unlink(temp_path)
-                except:
-                    pass
-                    
+                raise ValueError("Invalid JSON")
+            response_data = handle_parse_url(body.get('url'))
         else:
             return {
                 "statusCode": 404,
@@ -242,6 +175,21 @@ def handler(event, context):
                 })
             }
             
+        return {
+            "statusCode": 200,
+            "headers": cors_headers,
+            "body": json.dumps(response_data)
+        }
+        
+    except ValueError as e:
+        return {
+            "statusCode": 400,
+            "headers": cors_headers,
+            "body": json.dumps({
+                "error": "Bad Request",
+                "details": str(e)
+            })
+        }
     except Exception as e:
         return {
             "statusCode": 500,