Update app.py

app.py

@@ -37,84 +37,52 @@ def extract_names(text):
         return []
 
     names = []
+
+    NAME_FILTER_EXCEPTIONS = set([
+        '법적', '군의', '사회적', '심리적', '행정적', '의료적', '법률적',
+        '개인정보', '본인', '직통번호', '이메일', '전화번호', '연락처', '주소',
+        '해당', '현재', '상담', '예약', '센터', '아래', '위치', '소속', '보호자',
+    ])
+
     for entity in results:
         if entity.get("entity_group") == "PS":
             name = entity["word"].replace("##", "").strip()
-            if len(name) >= 2 and name not in names:
+            if len(name) >= 2 and name not in names and name not in NAME_FILTER_EXCEPTIONS:
                 names.append(name)
 
     COMMON_SUFFIXES = [
-        # 직함/직책
         '대표', '이사', '전무', '상무', '부장', '차장', '과장', '대리', '사원',
         '실장', '팀장', '소장', '국장', '본부장', '주임', '총무', '회장', '부회장', '사무장',
         '직원', '매니저', '지점장',
-        # 교육/전문가
         '선생님', '선생', '교사', '교장', '교감', '부교장', '조교수', '교수', '연구원', '강사',
         '박사', '석사', '학사', '의사', '간호사', '간병인',
-        # 학생 관련
         '학생', '수험생', '초등학생', '중학생', '고등학생', '학부모',
-        # 가족/친척
         '어머니', '아버지', '엄마', '아빠', '형', '누나', '언니', '오빠', '동생',
         '아들', '딸', '할머니', '할아버지', '외할머니', '외할아버지',
         '이모', '고모', '삼촌', '숙모', '외삼촌', '고모부', '이모부', '조카', '사촌',
         '남편', '아내', '부인', '와이프', '신랑', '장모', '장인', '사위', '며느리',
         '올케', '형수', '제수씨', '매형', '처제', '시누이',
-        # 그 외 지칭
         '보호자', '피해자', '당사자', '대상자', '주민', '어르신', '기사님'
     ]
 
-    # 조사 포함 패턴
     KOREAN_JOSA = r'(이[가]|은|는|을|를|과|와|의|도|만|께서|에서|으로|에게|한테|보다|까지|부터)?'
 
-    # 붙여쓰기: 이민지선생님, 김대리와
     attached_pattern = r'([가-힣]{2,4})(' + '|'.join(COMMON_SUFFIXES) + r')' + KOREAN_JOSA
     attached_matches = re.findall(attached_pattern, text)
     for match in attached_matches:
         name = match[0]
-        if name not in names:
+        if name not in names and name not in NAME_FILTER_EXCEPTIONS:
             names.append(name)
 
-    # 띄어쓰기: 이민지 선생님, 김대리 와
     spaced_pattern = r'([가-힣]{2,4})\s+(' + '|'.join(COMMON_SUFFIXES) + r')' + KOREAN_JOSA
     spaced_matches = re.findall(spaced_pattern, text)
     for match in spaced_matches:
         name = match[0]
-        if name not in names:
+        if name not in names and name not in NAME_FILTER_EXCEPTIONS:
             names.append(name)
 
     return names
 
-
-def refactored_mask_names(original_text, names, start_counter=100):
-    korean_josa = ['이가','를','은','는','을','도','만','과','와','에게','에서','으로',
-                   '까지','조차','마저','이며','이다','이나','이나마','밖에','이든','이라도',
-                   '이','가','의']
-    masked = original_text
-    mapping = {}
-    counter = start_counter
-    used_names = set()
-    for name in names:
-        for josa in korean_josa:
-            full = name + josa
-            pattern = rf'(?<![\w가-힣]){re.escape(full)}(?![\w가-힣])'
-            if re.search(pattern, masked):
-                tag = f"N{counter:03d}"
-                mapping[tag] = name
-                masked = re.sub(pattern, tag + josa, masked)
-                counter += 1
-                used_names.add(name)
-                break
-    for name in names:
-        if name in used_names:
-            continue
-        pattern = rf'(?<![\w가-힣]){re.escape(name)}(?![\w가-힣])'
-        if re.search(pattern, masked):
-            tag = f"N{counter:03d}"
-            mapping[tag] = name
-            masked = re.sub(pattern, tag, masked)
-            counter += 1
-    return masked, mapping
-
 def to_chosung(text):
     CHOSUNG_LIST = [chr(i) for i in range(0x1100, 0x1113)]
     result = ""
@@ -127,10 +95,13 @@ def to_chosung(text):
             result += ch
     return result
 
+
+
 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 sanitize_sensitive_info(text, keyword_string, replace_word):
     text = mask_school_names(text)
     text = mask_department(text)
@@ -154,18 +125,16 @@ def sanitize_sensitive_info(text, keyword_string, replace_word):
                   lambda m: f"{m.group(1)[:2]}{'*'*(len(m.group(1))-2)}{'*'*len(m.group(2))}{m.group(3)[-4:]}", text)
     text = re.sub(r"(\d{4})[- ]?(\d{4})[- ]?(\d{4})[- ]?(\d{4})",
                   lambda m: f"{m.group(1)}-****-****-{m.group(4)}", 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)
-    text = re.sub(r"([가-힣]{1,10})(은행|동|로|길)\s?([\d\-]{4,})",
-                  lambda m: m.group(1) + m.group(2) + " " + re.sub(r"\d", "*", m.group(3)), text)
     return text
 
+
 def final_name_remask_exact_only(text, mapping_dict):
     for tag, name in mapping_dict.items():
         pattern = rf'(?<![\w가-힣]){re.escape(name)}(?![\w가-힣])'
         text = re.sub(pattern, tag, text)
     return text
 
+
 def apply_masking(text, keywords, replace_word):
     names = extract_names(text)
     masked, mapping = refactored_mask_names(text, names)
@@ -174,21 +143,11 @@ def apply_masking(text, keywords, replace_word):
     mapping_table = "\n".join([f"{k} → {v}" for k, v in mapping.items()])
     return sanitized, mapping_table
 
-def remask_with_mapping(text, mapping_string):
-    mapping = {}
-    for line in mapping_string.strip().split("\n"):
-        if "→" in line:
-            tag, name = line.split("→")
-            mapping[tag.strip()] = name.strip()
-    for tag, name in mapping.items():
-        pattern = rf'(?<![\w가-힣]){re.escape(name)}(?![\w가-힣])'
-        text = re.sub(pattern, tag, text)
-    return text
 
 with gr.Blocks() as demo:
     gr.Markdown("""
 🛡️ **민감정보 마스킹 [땡땡이 마스킹]**  
-이름 + 민감정보 + 초/중/고 마스킹기 (초성 기반)
+이름 + 민감정보 + 초/중/고 마스킹기 (초성 기반)  
 ⚠️ *완벽하지 않을 수 있습니다. 반드시 직접 최종 점검하세요.*
 """)
     input_text = gr.Textbox(lines=15, label="📥 원본 텍스트 입력")