mlk

app.py

@@ -38,14 +38,15 @@ def extract_text(doc):
         return doc.read().decode('utf-8')
 
     if doc.name.endswith(".pdf"):
-        raw = doc.read()  
+        raw = doc.read()
+        
+        # Handle null bytes
+        raw = raw.replace(b'\x00', b'')  
 
-        # Remove null bytes without decoding 
-        raw = raw.replace(b'\x00', b'')
+        with pdfplumber.open(raw) as pdf:
+            pages = [page.extract_text() for page in pdf.pages]
 
-        pdf = pdfplumber.open(io.BytesIO(raw))
-        pages = [page.extract_text() for page in pdf.pages]      
-        return "\n".join(pages)
+            return "\n".join(pages)
     
     
     if doc.name.endswith('.docx'):