优化科室的匹配

util/data_util.py

@@ -102,26 +102,16 @@ def parse_department(string):
     result = []
     if not string:
         return result
-    string = re.sub(r'\([^()]*\)|\[[^\[\]]*]|\{[^{}]*}|（[^（）]*）|[^⺀-鿿]', '', string)[:255]
-    if string == "科":
-        return result
-    result.append(string)
-    string_without_num = re.sub(r'\d|一|二|三|四|五|六|七|八|九|十', '', string)
-    if string == "科":
-        return result
-    if string_without_num != string:
-        result.append(string_without_num)
-    pure_string = string_without_num.split("科")[0] + "科"
-    if string == "科":
-        return result
-    if pure_string != string_without_num:
-        result.append(pure_string)
-    pure_string_without_io = pure_string.replace("内", "").replace("外", "")
-    if string == "科":
-        return result
-    if pure_string_without_io != pure_string:
-        result.append(pure_string)
-    return result
+
+    string = string.replace(")", "").replace("）", "").replace("(", " ").replace("（", " ")  # 去除括号
+    string = re.sub(r'[^⺀-鿿 ]', '', string)  # 去除非汉字字符，除了空格
+    string = re.sub(r'[一二三四五六七八九十]', '', string)  # 去除中文数字
+    string = string.replace("科", " ")  # 分离科室
+    departments = string.strip().split(" ")
+    for department in departments:
+        if department:
+            result.append(department)
+    return set(result)
 
 
 # 处理姓名类数据