Update app.py

app.py

@@ -24,10 +24,10 @@ def anonymize_text_including_proper_nouns_and_addresses(text):
     lookup_table = {}
     counters = Counter()
     pii_config = {
-    'phone_number': (r'\b\d{3}[-.\s]?\d{3}[-.\s]?\d{4}\b', '__PHONE__'),
-    'text_address': (r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b', '__EMAIL]__'),
-    'social_security_number': (r'\b\d{3}-\d{2}-\d{4}\b', '__SSN]__'),
-    'website': (r'\b(?:http://|https://)?(?:www\.)?[a-zA-Z0-9./]+\.[a-z]{2,}\b', '__WEBSITE]__')
+    'phone_number': (r'\b\d{3}[-.\s]?\d{3}[-.\s]?\d{4}\b', 'PHONE__'),
+    'text_address': (r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b', 'EMAIL__'),
+    'social_security_number': (r'\b\d{3}-\d{2}-\d{4}\b', 'SSN__'),
+    'website': (r'\b(?:http://|https://)?(?:www\.)?[a-zA-Z0-9./]+\.[a-z]{2,}\b', 'WEBSITE__')
     }
     
     # First, handle regex-based PII detection and anonymization
@@ -55,7 +55,7 @@ def anonymize_text_including_proper_nouns_and_addresses(text):
         if label in ['ORG', 'PERSON', 'GPE', 'LOC', 'FAC']: # Optionally include'PROPN' for more restriction
             original = ent_or_token.text
             counters[label] += 1
-            placeholder_with_counter = f"[__{label}__{counters[label]}"
+            placeholder_with_counter = f"{label}__{counters[label]}"
             if original in anonymized_text:  # Check if the text still contains the original
                 anonymized_text = anonymized_text.replace(original, placeholder_with_counter, 1)
                 lookup_table[placeholder_with_counter] = original