Update app.py

app.py

@@ -97,16 +97,26 @@ def mask_department(text):
     return text
 
 def mask_sensitive_numbers(text):
-    text = re.sub(r"(\d{3})-(\d{4})-(\d{4})", r"\1-****-\3", text)
+    # 일반 전화번호: 000-0000-0000
+    text = re.sub(r"(\d{2,3})-(\d{3,4})-(\d{4})", r"\1-****-\3", text)
+    # 주민등록번호
     text = re.sub(r"(\d{6})[-](\d)\d{6}", r"*******-\2*****", text)
-    text = re.sub(r"(\d{4})[- ]?(\d{4})[- ]?(\d{4})[- ]?(\d{4})", lambda m: f"{m.group(1)}-****-****-{m.group(4)}", text)
+    # 카드 번호: 0000-0000-0000-0000 또는 공백 또는 없음
+    text = re.sub(r"(\d{4})[- ]?(\d{4})[- ]?(\d{4})[- ]?(\d{4})", r"\1-****-****-\4", text)
+    # 번지/동/호
     text = re.sub(r"(\d{1,3})번지", r"***번지", text)
     text = re.sub(r"(\d{1,3})동", r"***동", text)
     text = re.sub(r"(\d{1,4})호", r"****호", text)
+    # 이메일
     text = re.sub(r"[\w\.-]+@[\w\.-]+", r"******@****", text)
-    text = re.sub(r"(\d{1,3})\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})", lambda m: f"{m.group(1)}.{m.group(2)}.*.*", text)
-    return text
+    # IP 주소
+    text = re.sub(r"(\d{1,3})\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})", r"\1.\2.*.*", text)
+    
+    # 👇 추가된 부분: 마침표나 하이픈으로 구분된 3~4세트 숫자들
+    text = re.sub(r"(?<!\d)(\d{2,4}[-\.]){2,3}\d{2,4}(?!\d)", lambda m: re.sub(r"\d{2,4}", '***', m.group(0)), text)
 
+    return text
+    
 def sanitize_sensitive_info(text, keyword_string, replace_word):
     text = mask_school_names(text)
     text = mask_department(text)