Update app.py

app.py

@@ -8,7 +8,7 @@ import tempfile
 from datetime import datetime
 from pathlib import Path
 from urllib.parse import urlparse
-from typing import List, Dict, Tuple, Union, Optional
+from typing import List, Dict, Tuple, Union
 import requests
 import validators
 import gradio as gr
@@ -199,15 +199,29 @@ class FileProcessor:
 
         return dataset
 
-    def process_zip_file(zip_path):
-        """Extract and process files within a ZIP archive."""
-        extraction_directory = tempfile.mkdtemp()
+    def _process_zip_file(self, zip_path: str, temp_dir: str) -> List[Dict]:
+        """Process ZIP file contents"""
+        results = []
         with zipfile.ZipFile(zip_path, 'r') as zip_ref:
-            zip_ref.extractall(extraction_directory)
-            for extracted_file in os.listdir(extraction_directory):
-                extracted_file_path = os.path.join(extraction_directory, extracted_file)
-                process_file(extracted_file_path)
-    
+            zip_ref.extractall(temp_dir)
+            for root, _, files in os.walk(temp_dir):
+                for filename in files:
+                    filepath = os.path.join(root, filename)
+                    if self.is_text_file(filepath):
+                        try:
+                            with open(filepath, 'r', encoding='utf-8', errors='ignore') as f:
+                                content = f.read()
+                            if content.strip():
+                                results.append({
+                                    "source": "file",
+                                    "filename": filename,
+                                    "content": content,
+                                    "timestamp": datetime.now().isoformat()
+                                })
+                        except Exception as e:
+                            logger.error(f"Error reading file {filename}: {str(e)}")
+        return results
+
 def _process_single_file(self, file) -> List[Dict]:
     try:
         file_stat = os.stat(file.name)
@@ -246,13 +260,6 @@ def _process_single_file(self, file) -> List[Dict]:
 
 def generate_qr_code(json_data):
     """Generate a QR code from JSON data."""
-    # Limit the size of json_data to avoid exceeding QR code version limits
-    max_length = 2953  # Maximum length for version 40 (the highest version)
-    
-    if len(json_data) > max_length:
-        logger.warning("JSON data is too large for QR code generation. Truncating data.")
-        json_data = json_data[:max_length]  # Truncate the data
-
     qr = qrcode.make(json_data)
     qr_path = "output/qr_code.png"
     qr.save(qr_path)