Update app.py

app.py

@@ -108,3 +108,87 @@ def refactored_mask_names(original_text, names, start_counter=100):
 
 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_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)
+
+    text = re.sub(r"(\d)학년(\s?(\d)반)?", lambda m: "*학년" + (" *반" if m.group(3) else ""), text)
+    text = re.sub(r"(\d)학년\s?(\d)반", r"*학년 *반", text)
+
+    keywords = [k.strip() for k in keyword_string.split(",") if k.strip()]
+    for kw in keywords:
+        pattern = rf"\b{re.escape(kw)}\b"
+        text = re.sub(pattern, replace_word, text, flags=re.IGNORECASE)
+    text = re.sub(r"(\d{3})-(\d{4})-(\d{4})", r"\1-****-\3", text)
+    text = re.sub(r"(\d{4})년 (\d{1,2})월 (\d{1,2})일", r"19**년 \2월 *일", text)
+    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)
+    text = re.sub(r"[\w\.-]+@[\w\.-]+", r"******@****", text)
+    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)
+    text = re.sub(r"(\d{2,6})[-]?(\d{2,6})[-]?(\d{2,6})",
+                  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)
+    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
+
+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)
+⚠️ *완벽하지 않을 수 있습니다. 반드시 직접 최종 점검하세요.*
+""")
+    input_text = gr.Textbox(lines=15, label="📥 원본 텍스트 입력")
+    keyword_input = gr.Textbox(lines=1, label="기관 키워드 (쉼표로 구분)", value="굿네이버스, good neighbors, gn, 사회복지법인 굿네이버스")
+    replace_input = gr.Textbox(lines=1, label="치환할 텍스트", value="우리기관")
+    run_button = gr.Button("🚀 마스킹 실행")
+    masked_output = gr.Textbox(lines=15, label="🔐 마스킹된 텍스트")
+    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()