Update app.py

app.py

@@ -19,7 +19,7 @@ model = joblib.load("model.joblib")
 class EmailInput(BaseModel):
     input_email_body: str
 
-# PII Masking Function
+# Updated PII Masking Function (fixes Aadhaar vs Card and name misclassifications)
 def mask_and_store_all_pii(text):
     text = str(text)
     pii_map = {}
@@ -27,20 +27,22 @@ def mask_and_store_all_pii(text):
 
     patterns = {
         "email": r"\b[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+\b",
-        "phone_number": r"\b\d{10}\b",
-        "dob": r"\b\d{2}[/-]\d{2}[/-]\d{4}\b",
-        "aadhar_num": r"\b\d{4}[- ]?\d{4}[- ]?\d{4}\b",
-        "credit_debit_no": r"\b(?:\d[ -]*?){13,16}\b",
-        "cvv_no": r"\b\d{3}\b",
-        "expiry_no": r"\b(0[1-9]|1[0-2])\/\d{2,4}\b",
-        "full_name": r"\b([A-Z][a-z]+(?:\s[A-Z][a-z]+)+)\b"
+        "phone_number": r"\+?\d[\d\s\-]{7,14}\d",
+        "dob": r"\b\d{1,2}[\/\-\.\s]\d{1,2}[\/\-\.\s]\d{2,4}\b",
+        "aadhar_num": r"\b\d{4}[ -]?\d{4}[ -]?\d{4}\b(?!\d)",
+        "credit_debit_no": r"\b(?:\d[ -]*?){13,19}\b",
+        "cvv_no": r"(?i)\b(?:cvv[:\s\-]*)?(\d{3,4})\b",
+        "expiry_no": r"\b(0[1-9]|1[0-2])[\/\-]\d{2,4}\b",
+        # Avoid naive full name pattern to prevent false positives like 'Dear Sir'
     }
 
     for label, pattern in patterns.items():
         for match in re.finditer(pattern, text):
             original = match.group()
             start, end = match.start(), match.end()
-            placeholder = f"[{label}_{len(pii_map)}]"
+            placeholder = f"[{label}_{len(pii_map):03d}]"
+            if original not in text:
+                continue
             pii_map[placeholder] = original
             entity_list.append({
                 "position": [start, end],
@@ -81,4 +83,3 @@ def classify_email(data: EmailInput):
 @app.get("/")
 def root():
     return {"message": "Email Classification API is running."}
-