统一引号格式，优化架构排布

util/data_util.py

@@ -8,20 +8,20 @@ from util import common_util
 # 处理金额类数据
 def handle_decimal(string):
     if not string:
-        return ""
+        return ''
     string = re.sub(r'[^0-9.]', '', string)
     if not string:
-        return ""
-    if "." not in string:
+        return ''
+    if '.' not in string:
         if len(string) > 2:
-            result = string[:-2] + "." + string[-2:]
+            result = string[:-2] + '.' + string[-2:]
         else:
             result = string
     else:
         front, back = string.rsplit('.', 1)
-        front = front.replace(".", "")
+        front = front.replace('.', '')
         if back:
-            back = "." + back[:2]
+            back = '.' + back[:2]
         result = front + back
     return result[:16]
 
@@ -32,7 +32,7 @@ def parse_money(capital_num, num):
             money = common_util.chinese_money_to_number(capital_num)
             return capital_num, money
         except Exception as e:
-            logging.warning("大写金额解析失败", exc_info=e)
+            logging.warning('大写金额解析失败', exc_info=e)
 
     return num, handle_decimal(num)
 
@@ -40,17 +40,17 @@ def parse_money(capital_num, num):
 # 处理日期类数据
 def handle_date(string):
     if not string:
-        return ""
+        return ''
 
-    string = string.replace("年", "-").replace("月", "-").replace("日", "").replace("/", "-").replace(".", "-")
+    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("-")
+    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)
+            third_dash_index = string.find('-', string.find('-', string.find('-') + 1) + 1)
             string = string[:third_dash_index]
-        day = string[string.rindex("-") + 1:]
+        day = string[string.rindex('-') + 1:]
         if len(day) > 2:
             string = string[:2 - len(day)]
     else:
@@ -58,7 +58,7 @@ def handle_date(string):
             string = string[:8]
 
     if len(string) < 6:
-        return ""
+        return ''
 
     # 定义可能的日期格式
     formats = [
@@ -78,23 +78,23 @@ def handle_date(string):
             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")
+                return date.strftime('%Y-%m-%d')
             continue
         except ValueError:
             continue
 
-    return ""
+    return ''
 
 
 def handle_hospital(string):
     if not string:
-        return ""
+        return ''
     return string[:255]
 
 
 def handle_department(string):
     if not string:
-        return ""
+        return ''
     return string[:255]
 
 
@@ -103,12 +103,12 @@ def parse_department(string):
     if not string:
         return result
 
-    string = string.replace(")", "").replace("）", "").replace("(", " ").replace("（", " ")  # 去除括号
+    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("病区", "").replace("病", "")  # 去除常见的无意义词
-    string = string.replace("科", " ")  # 分离科室
-    departments = string.strip().split(" ")
+    string = string.replace('病区', '').replace('病', '')  # 去除常见的无意义词
+    string = string.replace('科', ' ')  # 分离科室
+    departments = string.strip().split(' ')
     for department in departments:
         if department:
             result.append(department)
@@ -118,33 +118,33 @@ def parse_department(string):
 # 处理姓名类数据
 def handle_name(string):
     if not string:
-        return ""
+        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"]
+        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"
+        return '职工医保'
     if any(key in string for key in villager_insurance_keys):
-        return "居民医保"
+        return '居民医保'
     if any(key in string for key in migrant_worker_insurance_keys):
-        return "农民工医保"
+        return '农民工医保'
     if any(key in string for key in no_insurance_keys):
-        return "无医保"
-    return "其他"
+        return '无医保'
+    return '其他'
 
 
 # 处理原始数据
 def handle_original_data(string):
     if not string:
-        return ""
+        return ''
     # 防止过长存入数据库失败
     return string[:255]
 
@@ -152,7 +152,7 @@ def handle_original_data(string):
 # 处理id类数据
 def handle_id(string):
     if not string:
-        return ""
+        return ''
     # 防止过长存入数据库失败
     return string[:50]
 
@@ -160,8 +160,8 @@ def handle_id(string):
 # 处理年龄类数据
 def handle_age(string):
     if not string:
-        return ""
-    string = string.split("岁")[0]
+        return ''
+    string = string.split('岁')[0]
     num = re.sub(r'\D', '', string)
     return num[-3:]
 
@@ -173,8 +173,8 @@ def parse_hospital(string):
         return result
 
     string = common_util.traditional_to_simple_chinese(string)
-    string_without_brackets = string.replace(")", "").replace("）", "").replace("(", " ").replace("（", " ")
-    string_without_company = string_without_brackets.replace("有限公司", "")
-    split_hospitals = string_without_company.replace("医院", "医院 ")
-    result += split_hospitals.strip().split(" ")
+    string_without_brackets = string.replace(')', '').replace('）', '').replace('(', ' ').replace('（', ' ')
+    string_without_company = string_without_brackets.replace('有限公司', '')
+    split_hospitals = string_without_company.replace('医院', '医院 ')
+    result += split_hospitals.strip().split(' ')
     return result