Update app.py

app.py

@@ -50,25 +50,33 @@ def process_file(uploaded_file):
         return {"type": "text", "content": "".join(page.extract_text() for page in reader.pages if page.extract_text())}
     
     if file_type == "zip":
-        with zipfile.ZipFile(uploaded_file) as z:
-            newline = "\n"
-            content = f"ZIP Contents:{newline}"
-            
-            # Jede Datei im ZIP lesen
-            for file_info in z.infolist():
-                if not file_info.is_dir():  # Ignoriere Ordner
-                    try:
-                        with z.open(file_info.filename) as file:
-                            # Nur Textdateien lesen (erweiterbare Whitelist)
-                            if file_info.filename.lower().endswith(('.txt', '.csv', '.py', '.html', '.js', '.css', '.pdf')):
-                                file_content = file.read().decode('utf-8')
-                                content += f"{newline}📁 Datei: {file_info.filename}{newline}{file_content}{newline}"
-                            else:
+    with zipfile.ZipFile(uploaded_file) as z:
+        newline = "\n"
+        content = f"ZIP Contents:{newline}"
+        
+        # Whitelist für Textdateien erweitern
+        text_extensions = ('.txt', '.csv', '.py', '.html', '.js', '.css', '.php', '.json', '.xml')
+        
+        for file_info in z.infolist():
+            if not file_info.is_dir():
+                try:
+                    with z.open(file_info.filename) as file:
+                        # Check 1: Erlaubte Dateiendung
+                        if file_info.filename.lower().endswith(text_extensions):
+                            file_content = file.read().decode('utf-8')
+                            content += f"{newline}📄 {file_info.filename}:{newline}{file_content}{newline}"
+                        # Check 2: Ist es trotzdem Text? (Magische Bytes prüfen)
+                        else:
+                            raw_content = file.read()
+                            try:
+                                decoded_content = raw_content.decode('utf-8')
+                                content += f"{newline}📄 {file_info.filename} (unbekannte Erweiterung):{newline}{decoded_content}{newline}"
+                            except UnicodeDecodeError:
                                 content += f"{newline}⚠️ Binärdatei ignoriert: {file_info.filename}{newline}"
-                    except Exception as e:
-                        content += f"{newline}❌ Fehler beim Lesen von {file_info.filename}: {str(e)}{newline}"
-            
-            return {"type": "text", "content": content}
+                except Exception as e:
+                    content += f"{newline}❌ Fehler bei {file_info.filename}: {str(e)}{newline}"
+        
+        return {"type": "text", "content": content}
     
     return {"type": "error", "content": "Unsupported file format"}
 # Sidebar für Einstellungen