[Cursor] Simplify serverless handler

api/index.py

@@ -1,10 +1,8 @@
-from http.server import BaseHTTPRequestHandler
 import json
 import os
 import tempfile
 import magic
 import requests
-from werkzeug.utils import secure_filename
 import datetime
 
 def is_valid_file(file_data):
@@ -60,102 +58,164 @@ def download_file(url):
     except Exception as e:
         raise ValueError(f"Failed to download file: {str(e)}")
 
-class Handler(BaseHTTPRequestHandler):
-    def do_GET(self):
-        if self.path == '/' or self.path == '':
-            self.send_response(200)
-            self.send_header('Content-type', 'application/json')
-            self.end_headers()
-            response = {
-                "status": "ok",
-                "message": "Document Processing API",
-                "version": "1.0.0"
-            }
-            self.wfile.write(json.dumps(response).encode())
-        elif self.path == '/health':
-            self.send_response(200)
-            self.send_header('Content-type', 'application/json')
-            self.end_headers()
-            response = {
-                "status": "healthy",
-                "timestamp": str(datetime.datetime.now(datetime.UTC))
+def handler(event, context):
+    """Serverless handler for Vercel"""
+    
+    # Add CORS headers to all responses
+    cors_headers = {
+        "Access-Control-Allow-Origin": "*",
+        "Access-Control-Allow-Headers": "Content-Type, Authorization",
+        "Access-Control-Allow-Methods": "GET, POST, OPTIONS",
+        "Content-Type": "application/json"
+    }
+    
+    # Handle OPTIONS request for CORS
+    if event.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:
+        # Route request
+        if path == '' or path == '/':
+            return {
+                "statusCode": 200,
+                "headers": cors_headers,
+                "body": json.dumps({
+                    "status": "ok",
+                    "message": "Document Processing API",
+                    "version": "1.0.0"
+                })
             }
-            self.wfile.write(json.dumps(response).encode())
-        else:
-            self.send_response(404)
-            self.send_header('Content-type', 'application/json')
-            self.end_headers()
-            response = {
-                "error": "Not Found",
-                "details": f"Path {self.path} not found"
+            
+        elif path == '/health':
+            return {
+                "statusCode": 200,
+                "headers": cors_headers,
+                "body": json.dumps({
+                    "status": "healthy",
+                    "timestamp": str(datetime.datetime.now(datetime.UTC))
+                })
             }
-            self.wfile.write(json.dumps(response).encode())
-
-    def do_POST(self):
-        content_length = int(self.headers.get('Content-Length', 0))
-        post_data = self.rfile.read(content_length)
-
-        if self.path == '/parse/file':
+            
+        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):
+                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:
-                if not post_data:
-                    self.send_error(400, "No file provided")
-                    return
-
-                if not is_valid_file(post_data):
-                    self.send_error(400, "Invalid file type")
-                    return
-
-                fd, temp_path = tempfile.mkstemp()
-                os.close(fd)
-
-                try:
-                    with open(temp_path, 'wb') as f:
-                        f.write(post_data)
-
-                    self.send_response(200)
-                    self.send_header('Content-type', 'application/json')
-                    self.end_headers()
-                    response = {
+                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)
                         }
-                    }
-                    self.wfile.write(json.dumps(response).encode())
-                finally:
-                    try:
-                        os.unlink(temp_path)
-                    except:
-                        pass
-
-            except Exception as e:
-                self.send_error(500, str(e))
-
-        elif self.path == '/parse/url':
-            try:
+                    })
+                }
+            finally:
+                # Clean up temp file
                 try:
-                    body = json.loads(post_data)
+                    os.unlink(temp_path)
                 except:
-                    self.send_error(400, "Invalid JSON")
-                    return
-
-                url = body.get('url')
-                if not url:
-                    self.send_error(400, "No URL provided")
-                    return
-
-                if not url.startswith(('http://', 'https://')):
-                    self.send_error(400, "Invalid URL")
-                    return
-
-                temp_path, content_type = download_file(url)
-                try:
-                    self.send_response(200)
-                    self.send_header('Content-type', 'application/json')
-                    self.end_headers()
-                    response = {
+                    pass
+                    
+        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'])
+            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": {
@@ -163,29 +223,31 @@ class Handler(BaseHTTPRequestHandler):
                             "content_type": content_type,
                             "size": os.path.getsize(temp_path)
                         }
-                    }
-                    self.wfile.write(json.dumps(response).encode())
-                finally:
-                    try:
-                        os.unlink(temp_path)
-                    except:
-                        pass
-
-            except ValueError as e:
-                self.send_error(400, str(e))
-            except Exception as e:
-                self.send_error(500, str(e))
-
+                    })
+                }
+            finally:
+                # Clean up temp file
+                try:
+                    os.unlink(temp_path)
+                except:
+                    pass
+                    
         else:
-            self.send_error(404, f"Path {self.path} not found")
-
-    def do_OPTIONS(self):
-        self.send_response(204)
-        self.send_header('Access-Control-Allow-Origin', '*')
-        self.send_header('Access-Control-Allow-Methods', 'GET, POST, OPTIONS')
-        self.send_header('Access-Control-Allow-Headers', 'Content-Type, Authorization')
-        self.end_headers()
-
-def handler(request, context):
-    """Vercel serverless handler"""
-    return Handler(request, None, None).handle_request() 
+            return {
+                "statusCode": 404,
+                "headers": cors_headers,
+                "body": json.dumps({
+                    "error": "Not Found",
+                    "details": f"Path {path} not found"
+                })
+            }
+            
+    except Exception as e:
+        return {
+            "statusCode": 500,
+            "headers": cors_headers,
+            "body": json.dumps({
+                "error": "Internal Server Error",
+                "details": str(e)
+            })
+        }