Update app.py

app.py

@@ -1,144 +1,216 @@
-
-# ▶️ Part 1: 이름 태깅 + 파생 표현 후처리 + 우리기관 강화치환
-
+# masking_ver2.py
 import re
 import gradio as gr
-import threading
 from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
 
+# =============================================
+# Configurable Constants
+# =============================================
 TAG_PREFIX = "N"
-COMMON_SUFFIXES = ['학생', '선생님', '씨', '님']
-COMMON_JOSA = ['이', '가', '은', '는', '을', '를', '께서', '에게', '에서']
 
+NAME_ENTITY_EXCEPTIONS = set([
+    '법적', '군의', '사회적', '심리적', '행정적', '의료적', '법률적',
+    '개인정보', '본인', '해당', '현재', '아래', '위치', '소속',
+    '상담', '그래도'
+])
+
+REGEX_KEYWORDS_TO_MASK = set([
+    '이메일', '전화번호', '연락처', '주소', '센터', '카드번호', '주민등록번호', 'IP', 'IP주소', '계좌번호'
+])
+
+# 분리된 suffix 그룹
+FAMILY_TITLES = ['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']
+
+ACADEMIC_TITLES = ['학생', '초등학생', '중학생', '고등학생', '수험생', '학부모']
+
+OCCUPATIONAL_TITLES = ['대표', '이사', '전무', '상무', '부장', '차장', '과장', '대리', '사원',
+                        '실장', '팀장', '소장', '국장', '본부장', '주임', '총무', '회장', '부회장',
+                        '사무장', '직원', '매니저', '지점장', '선생님', '선생', '교사', '교장',
+                        '교감', '부교장', '조교수', '교수', '연구원', '강사', '박사', '석사', '학사',
+                        '의사', '간호사', '간병인', '보호자', '피해자', '당사자', '대상자', '주민', '어르신', '기사님']
+
+COMMON_SUFFIXES = FAMILY_TITLES + ACADEMIC_TITLES + OCCUPATIONAL_TITLES
+
+# =============================================
+# Preload Model
+# =============================================
 model_name = "Leo97/KoELECTRA-small-v3-modu-ner"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForTokenClassification.from_pretrained(model_name)
 ner_pipeline = pipeline("ner", model=model, tokenizer=tokenizer, aggregation_strategy="simple")
 
+# =============================================
+# Utility Functions
+# =============================================
+def to_chosung(text):
+    CHOSUNG_LIST = [chr(i) for i in range(0x1100, 0x1113)]
+    result = ""
+    for ch in text:
+        if '가' <= ch <= '힣':
+            code = ord(ch) - ord('가')
+            cho = code // 588
+            result += CHOSUNG_LIST[cho]
+        else:
+            result += ch
+    return result
+
+def postprocess_sensitive_patterns(text):
+    text = re.sub(r"\b[\w\.-]+@", r"******@", text)  # 이메일: 골뱅이 앞만 가리기
+
+    def mask_sequence(match):
+        parts = re.split(r'[.-]', match.group())
+        masked = []
+        for i, part in enumerate(parts):
+            if part.isdigit():
+                if i % 2 == 0:
+                    masked.append(part)
+                else:
+                    masked.append('*' * len(part))
+            else:
+                masked.append(part)
+        return '.'.join(masked) if '.' in match.group() else '-'.join(masked)
+
+    text = re.sub(r"(?<![\\$\\\\])(?<!\d,)(?:\d{2,4}[.-]){1,3}\d{2,4}(?!\d)", mask_sequence, text)
+    text = re.sub(r"(\d{1,3})동", r"***동", text)  # 동 정보
+    text = re.sub(r"(\d{1,4})호", r"****호", text)  # 호수 정보
+    return text
+
+# =============================================
+# Masking Core Functions
+# =============================================
 def extract_names(text):
-    results = ner_pipeline(text)
+    try:
+        results = ner_pipeline(text)
+    except Exception as e:
+        print("NER 오류 발생:", e)
+        return []
+
     names = []
+    base_names = set()
     for entity in results:
         if entity.get("entity_group") == "PS":
             name = entity["word"].replace("##", "").strip()
-            if len(name) >= 2:
+            if len(name) >= 2 and name not in NAME_ENTITY_EXCEPTIONS:
                 names.append(name)
-    return list(set(names))
+                base_names.add(name)
 
-def apply_name_tags(text, names, start=100):
+    KOREAN_JOSA = r'(이[가]|은|는|을|를|과|와|의|도|만|께서|에서|으로|에게|한테|보다|까지|부터)?'
+    attached = r'([가-힣]{2,4})(?:' + '|'.join(COMMON_SUFFIXES) + r')' + KOREAN_JOSA
+    spaced = r'([가-힣]{2,4})\s+(?:' + '|'.join(COMMON_SUFFIXES) + r')' + KOREAN_JOSA
+
+    for pattern in [attached, spaced]:
+        for match in re.findall(pattern, text):
+            name = match[0]
+            if name not in names and name not in NAME_ENTITY_EXCEPTIONS:
+                names.append(name)
+
+    # 🧠 후처리: 이름+조사 붙은 경우로도 다시 추출
+    for name in base_names:
+        for suffix in COMMON_SUFFIXES:
+            for josa in ["", "은", "는", "이", "가", "을", "를", "도", "과", "와", "께서", "에서", "으로"]:
+                pattern = rf'{re.escape(name)}\s?{suffix}{josa}'
+                if re.search(pattern, text):
+                    if name not in names:
+                        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 = {}
-    tagged = text
-    counter = start
+    counter = start_counter
+    used_names = set()
+
     for name in names:
-        tag = f"{TAG_PREFIX}{counter:03d}"
-        pattern = re.compile(rf'(?<![\w가-힣]){re.escape(name)}(?![\w가-힣])')
-        tagged, n = pattern.subn(tag, tagged)
-        if n > 0:
+        for josa in korean_josa:
+            full = name + josa
+            pattern = rf'(?<![\w가-힣]){re.escape(full)}(?![\w가-힣])'
+            if re.search(pattern, masked):
+                tag = f"{TAG_PREFIX}{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"{TAG_PREFIX}{counter:03d}"
             mapping[tag] = name
+            masked = re.sub(pattern, tag, masked)
             counter += 1
-    return tagged, mapping
+    return masked, mapping
 
-def expand_variation_patterns(tagged_text, mapping):
-    for tag, base in mapping.items():
-        suffix_pattern = re.compile(rf'([\(\["'‘“\s]*){re.escape(base)}(?:{"|".join(COMMON_SUFFIXES)})?(?:{"|".join(COMMON_JOSA)})?', re.IGNORECASE)
-        tagged_text = suffix_pattern.sub(lambda m: m.group(0).replace(base, tag), tagged_text)
-    return tagged_text
-
-def replace_institution_keywords(text, keywords, replace_word):
-    for kw in keywords:
-        pattern = re.compile(rf'([\s\(\["'‘“]*){re.escape(kw)}([가-힣\s.,;:!?()"'”’]*)', re.IGNORECASE)
-        text = pattern.sub(lambda m: m.group(1) + replace_word + m.group(2), 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 postprocess_sensitive_patterns(text):
-    text = re.sub(r"[\w\.-]+@[\w\.-]+", "******@***.***", text)
-    text = re.sub(r"(\d{6})[- ]?(\d{7})", "******-*******", text)
-    text = re.sub(r"(\d{3})[- ]?(\d{4})[- ]?(\d{4})", "***-****-****", text)
-    text = re.sub(r"(\d{1,3})동", "***동", text)
-    text = re.sub(r"(\d{1,4})호", "****호", text)
+def mask_department(text):
+    return re.sub(r"([가-힣]{2,20}학과)", lambda m: to_chosung(m.group(1)[:-2]) + "학과", text)
+
+def mask_school_names(text):
+    global school_name_candidates
+    school_name_candidates = []
+
+    def replacer(match):
+        name = match.group(1)
+        if 2 <= len(name) <= 20:
+            school_name_candidates.append(name)
+            return to_chosung(name) + match.group(2)
+        return match.group(0)
+
+    text = re.sub(r"(\b[가-힣]{2,20})(초등학교|중학교|고등학교)", replacer, text)
+    for name in school_name_candidates:
+        pattern = rf"{re.escape(name)}\s?(초등학교|중학교|고등학교)"
+        text = re.sub(pattern, to_chosung(name) + " " + r"\1", text)
     return text
 
-def apply_masking(text, keyword_string, replace_word):
-    keywords = [k.strip() for k in keyword_string.split(",") if k.strip()]
-    text = replace_institution_keywords(text, keywords, replace_word)
-    text = postprocess_sensitive_patterns(text)
-    names = extract_names(text)
-    tagged, mapping = apply_name_tags(text, names)
+def sanitize_sensitive_info(text, keyword_string, replace_word):
+    text = postprocess_sensitive_patterns(text)  # 먼저 처리
+    text = mask_school_names(text)
+    text = mask_department(text)
+    text = re.sub(r"(\d)학년(\s?(\d)반)?", lambda m: "*학년" + (" *반" if m.group(3) else ""), text)
 
-    def finalize():
-        final_tagged = expand_variation_patterns(tagged, mapping)
-        mapping_str = "\n".join([f"{k} → {v}" for k, v in mapping.items()])
-        masked_output.update(value=final_tagged)
-        mapping_output.update(value=mapping_str)
+    keywords = [k.strip() for k in keyword_string.split(",") if k.strip()] + list(REGEX_KEYWORDS_TO_MASK)
+    for kw in keywords:
+        pattern = rf"\b{re.escape(kw)}\b"
+        text = re.sub(pattern, replace_word, text, flags=re.IGNORECASE)
 
-    threading.Timer(0.2, finalize).start()
-    return tagged, "\n".join([f"{k} → {v}" for k, v in mapping.items()])
+    text = re.sub(r"(\d{6})[-](\d)\d{6}", r"*******-\2*****", text)
+    text = re.sub(r"([가-힣]+(대로|로|길))\s?(\d+)(호|번길|가)?", r"\1 ***", text)
+    return text
 
-# Part 1 UI
+def apply_masking(text, keywords, replace_word):
+    names = extract_names(text)
+    masked, mapping = refactored_mask_names(text, names)
+    sanitized = sanitize_sensitive_info(masked, keywords, replace_word)
+    sanitized = final_name_remask_exact_only(sanitized, mapping)
+    mapping_table = "\n".join([f"{k} → {v}" for k, v in mapping.items()])
+    return sanitized, mapping_table
+
+# UI
 with gr.Blocks() as demo:
-    gr.Markdown("🧠 **v4.3A: 이름 + 파생 표현 + 기관 치환 (1단계)**")
-    input_text = gr.Textbox(lines=15, label="📄 원문 텍스트")
-    keyword_input = gr.Textbox(lines=1, label="기관 키워드 (쉼표로 구분)", value="굿네이버스, 사회복지법인 굿네이버스")
+    gr.Markdown("""
+    🛡️ **민감정보 마스킹 [ver2]**  
+    이름 + 민감정보 + 초/중/고 마스킹기 (초성 기반 + 예외 필터 + 후처리 강화)
+    """)
+    input_text = gr.Textbox(lines=15, label="📅 원본 텍스트 입력")
+    keyword_input = gr.Textbox(lines=1, label="기관 키워드 (쉼표 구분)", value="굿네이버스, 사회복지법인 굿네이버스")
     replace_input = gr.Textbox(lines=1, label="치환할 텍스트", value="우리기관")
-    run_button = gr.Button("🚀 실행")
+    run_button = gr.Button("🚀 마스킹 실행")
     masked_output = gr.Textbox(lines=15, label="🔐 마스킹 결과")
-    mapping_output = gr.Textbox(lines=10, label="🏷️ 태그 매핑", interactive=False)
-    run_button.click(fn=apply_masking, inputs=[input_text, keyword_input, replace_input], outputs=[masked_output, mapping_output])
-
-
-# ▶️ Part 2: 학과/학교 초성 변환 + 학년/반 마스킹 + mapping 보정
-# - 이 부분은 이어서 별도 실행 환경 or 연동 코드로 붙일 수 있습니다.
-# - 필요 시 한 파일로 통합 가능
-
-
-# ▶️ Part 2: 학과/학교 초성 변환 + 학년/반 마스킹 + mapping 보정
-
-def to_chosung(text):
-    CHOSUNG_LIST = [chr(i) for i in range(0x1100, 0x1113)]
-    result = ""
-    for ch in text:
-        if '가' <= ch <= '힣':
-            code = ord(ch) - ord('가')
-            cho = code // 588
-            result += CHOSUNG_LIST[cho]
-        else:
-            result += ch
-    return result
-
-def mask_school_names(text):
-    def replace_school(m):
-        return to_chosung(m.group(1)) + m.group(2)
-    return re.sub(r"([가-힣]{2,20})(초등학교|중학교|고등학교)", replace_school, text)
-
-def mask_department_names(text):
-    return re.sub(r"([가-힣]{2,20})학과", lambda m: to_chosung(m.group(1)) + "학과", text)
-
-def mask_grade_class(text):
-    return re.sub(r"(\d)학년(\s?(\d)반)?", "*학년 *반", text)
-
-def mapping_boost_context(text, mapping_dict):
-    COMMON_SUFFIXES = ['학생', '선생님', '씨', '님']
-    COMMON_JOSA = ['이', '가', '은', '는', '을', '를', '께서', '에게', '에서']
-    updated = {}
-    for tag, base in mapping_dict.items():
-        idx = text.find(tag)
-        if idx == -1:
-            updated[tag] = base
-            continue
-        window = text[max(0, idx - 100): idx + 100]
-        pattern = re.compile(rf"([가-힣])?{re.escape(base)}(?:{'|'.join(COMMON_SUFFIXES)})?(?:{'|'.join(COMMON_JOSA)})?")
-        match = pattern.search(window)
-        if match:
-            updated[tag] = match.group(0)
-        else:
-            updated[tag] = base
-    return updated
-
-# 👇 예시: 후처리 최종 적용
-# final_output = mask_school_names(tagged_text)
-# final_output = mask_department_names(final_output)
-# final_output = mask_grade_class(final_output)
-# mapping = mapping_boost_context(final_output, mapping)
+    mapping_output = gr.Textbox(lines=10, label="🏷️ 이름 태그 매핑", interactive=False)
 
+    run_button.click(fn=apply_masking, inputs=[input_text, keyword_input, replace_input], outputs=[masked_output, mapping_output])
 
 demo.launch()