Update app.py

app.py

@@ -97,6 +97,21 @@ def mask_department(text):
     text = re.sub(r"([가-힣]{2,20}학과)", lambda m: to_chosung(m.group(1)[:-2]) + "학과", text)
     return text
 
+
+def postprocess_sensitive_patterns(text):
+    # IP 주소: 192.168.35.201 → 192.168.*.*
+    text = re.sub(r"\b(\d{1,3})\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})\b", r"\1.\2.*.*", text)
+
+    # 전화번호: 031-987-6543 → 031-***-6543
+    text = re.sub(r"\b(\d{2,4})-(\d{3,4})-(\d{4})\b", r"\1-***-\3", text)
+
+    # 카드번호: 1234-5678-9012-3456 → 1234-****-****-3456
+    text = re.sub(r"\b(\d{4})[- ]?(\d{4})[- ]?(\d{4})[- ]?(\d{4})\b", r"\1-****-****-\4", text)
+
+    return text
+
+
+
 def sanitize_sensitive_info(text, keyword_string, replace_word):
     text = mask_school_names(text)
     text = mask_department(text)
@@ -120,6 +135,9 @@ def sanitize_sensitive_info(text, keyword_string, replace_word):
     text = re.sub(r"([가-힣]+(대로|로|길))\s?(\d+)(호|번길|가)?", r"\1 ***", text)
     text = re.sub(r"(\d{4})[- ]?(\d{4})[- ]?(\d{4})[- ]?(\d{4})",
                   lambda m: f"{m.group(1)}-****-****-{m.group(4)}", text)
+    # 📌 후처리 추가
+    text = postprocess_sensitive_patterns(text)
+    
     return text
 
 def final_name_remask_exact_only(text, mapping_dict):