Reapply "整理项目结构，优化配置项"

This reverts commit 2f650dd880.

util/data_util.py

@@ -0,0 +1,158 @@
+import re
+from datetime import datetime
+
+
+# 处理金额类数据
+def handle_decimal(string):
+    if not string:
+        return ""
+    string = re.sub(r'[^0-9.]', '', string)
+    if "." not in string:
+        front = string
+        back = ""
+    else:
+        front, back = string.rsplit('.', 1)
+        front = front.replace(".", "")
+
+    front = front[-16:]
+    if back:
+        back = "." + back
+    return front + back
+
+
+# 处理日期类数据
+def handle_date(string):
+    if not string:
+        return ""
+
+    string = string.replace("年", "-").replace("月", "-").replace("日", "").replace("/", "-").replace(".", "-")
+    string = re.sub(r'[^0-9-]', '', string)
+    string = string.strip("-")
+    if "-" in string:
+        dash_count = string.count("-")
+        if dash_count > 2:
+            third_dash_index = string.find("-", string.find("-", string.find("-") + 1) + 1)
+            string = string[:third_dash_index]
+        day = string[string.rindex("-") + 1:]
+        if len(day) > 2:
+            string = string[:2 - len(day)]
+    else:
+        if len(string) > 8:
+            string = string[:8]
+
+    if len(string) < 6:
+        return ""
+
+    # 定义可能的日期格式
+    formats = [
+        # yyyy-MM-dd
+        '%Y-%m-%d',
+        # yy-MM-dd
+        '%y-%m-%d',
+        # yyyyMMdd
+        '%Y%m%d',
+        # yyMMdd
+        '%y%m%d',
+    ]
+
+    # 遍历所有格式，尝试解析日期
+    for fmt in formats:
+        try:
+            date = datetime.strptime(string, fmt)
+            # 限定日期的年份范围
+            if 2000 < date.year < 2100:
+                return date.strftime("%Y-%m-%d")
+            continue
+        except ValueError:
+            continue
+
+    return ""
+
+
+def handle_hospital(string):
+    if not string:
+        return ""
+    return string[:255]
+
+
+def handle_department(string):
+    if not string:
+        return ""
+    return string[:255]
+
+
+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
+
+
+# 处理姓名类数据
+def handle_name(string):
+    if not string:
+        return ""
+    return re.sub(r'[^⺀-鿿·]', '', string)[:30]
+
+
+# 处理医保类型数据
+def handle_insurance_type(string):
+    if not string:
+        return ""
+    worker_insurance_keys = ["社保", "城保", "职", "退休"]
+    villager_insurance_keys = ["农保", "居民"]
+    migrant_worker_insurance_keys = ["农民工"]
+    no_insurance_keys = ["自费", "全费"]
+    if any(key in string for key in worker_insurance_keys):
+        return "职工医保"
+    if any(key in string for key in villager_insurance_keys):
+        return "居民医保"
+    if any(key in string for key in migrant_worker_insurance_keys):
+        return "农民工医保"
+    if any(key in string for key in no_insurance_keys):
+        return "无医保"
+    return "其他"
+
+
+# 处理原始数据
+def handle_original_data(string):
+    if not string:
+        return ""
+    # 防止过长存入数据库失败
+    return string[:255]
+
+
+# 处理id类数据
+def handle_id(string):
+    if not string:
+        return ""
+    # 防止过长存入数据库失败
+    return string[:50]
+
+
+# 处理年龄类数据
+def handle_age(string):
+    if not string:
+        return ""
+    string = string.split("岁")[0]
+    num = re.sub(r'\D', '', string)
+    return num[-3:]