116 lines
3.5 KiB
Python
116 lines
3.5 KiB
Python
#!/usr/bin/env python
|
||
# -*- coding: utf-8 -*-
|
||
# @Time : 2025/3/15 19:52
|
||
# @Author : AngesZhu
|
||
# @File : province_rules.py
|
||
# @Desc : 省份相关规则
|
||
import random
|
||
import re
|
||
from typing import Dict, List, Optional, Tuple
|
||
from functools import lru_cache
|
||
|
||
# 不可变的基础数据
|
||
PROVINCE_DATA = (
|
||
("北京", "京", "北京", "010", "华北"),
|
||
("天津", "津", "天津", "022", "华北"),
|
||
("河北", "冀", "石家庄", "0311", "华北"),
|
||
# ... 其他省份数据
|
||
("台湾", "台", "台北", "00886", "华东"),
|
||
("香港", "港", "香港", "00852", "华南"),
|
||
("澳门", "澳", "澳门", "00853", "华南")
|
||
)
|
||
|
||
# 类型别名
|
||
Province = Tuple[str, str, str, str, str]
|
||
ProvinceDict = Dict[str, str]
|
||
|
||
|
||
# 纯函数：数据转换
|
||
def create_mappings(data: Tuple[Province, ...]) -> Tuple[Dict[str, Province], Dict[str, Province]]:
|
||
"""创建名称和简称的映射"""
|
||
name_map = {p[0]: p for p in data}
|
||
abbr_map = {p[1]: p for p in data}
|
||
return name_map, abbr_map
|
||
|
||
|
||
# 初始化映射
|
||
NAME_MAP, ABBR_MAP = create_mappings(PROVINCE_DATA)
|
||
ALL_VALID_NAMES = frozenset(NAME_MAP.keys()) | frozenset(ABBR_MAP.keys())
|
||
|
||
|
||
# 纯函数：输入清理
|
||
def clean_input(input_str: str) -> str:
|
||
"""清理和标准化输入字符串"""
|
||
if not input_str or not isinstance(input_str, str):
|
||
return ""
|
||
cleaned = input_str.strip().translate(str.maketrans('（）', '()'))
|
||
return re.sub(r'\s+', '', cleaned)
|
||
|
||
|
||
# 带缓存的函数：省份验证
|
||
@lru_cache(maxsize=128)
|
||
def validate_province(input_str: str) -> Optional[Province]:
|
||
"""验证并返回省份信息"""
|
||
cleaned = clean_input(input_str)
|
||
if not cleaned:
|
||
return None
|
||
|
||
# 处理带后缀的情况
|
||
def remove_suffix(text: str, suffix: str) -> Optional[Province]:
|
||
if text.endswith(suffix) and len(text) > len(suffix):
|
||
base = text[:-len(suffix)]
|
||
return NAME_MAP.get(base)
|
||
return None
|
||
|
||
# 尝试各种匹配方式
|
||
return (NAME_MAP.get(cleaned) or
|
||
ABBR_MAP.get(cleaned) or
|
||
remove_suffix(cleaned, '省') or
|
||
remove_suffix(cleaned, '自治区') or
|
||
remove_suffix(cleaned, '特别行政区'))
|
||
|
||
|
||
# 纯函数：随机选择
|
||
def get_random_province(region: Optional[str] = None) -> Province:
|
||
"""随机获取一个省份"""
|
||
pool = [p for p in PROVINCE_DATA if not region or p[4] == region]
|
||
if not pool:
|
||
raise ValueError(f"无效的地区：{region}")
|
||
return random.choice(pool)
|
||
|
||
|
||
# 纯函数：信息转换
|
||
def province_to_dict(province: Province) -> ProvinceDict:
|
||
"""将省份元组转换为字典"""
|
||
keys = ("name", "abbr", "capital", "area_code", "region")
|
||
return dict(zip(keys, province))
|
||
|
||
|
||
# 组合函数：获取完整信息
|
||
def get_province_info(input_str: str) -> ProvinceDict:
|
||
"""获取省份的完整信息"""
|
||
province = validate_province(input_str)
|
||
if not province:
|
||
raise ValueError(f"无效的省份输入：{input_str}")
|
||
return province_to_dict(province)
|
||
|
||
|
||
# 使用示例
|
||
if __name__ == "__main__":
|
||
# 随机获取一个省份
|
||
random_prov = get_random_province()
|
||
print(f"随机省份：{random_prov}")
|
||
|
||
# 验证省份
|
||
test_cases = ["北京", "上海市", " 浙 ", "黑", "台湾省", "invalid"]
|
||
for case in test_cases:
|
||
result = validate_province(case)
|
||
print(f"验证 '{case}': {'有效' if result else '无效'}")
|
||
|
||
# 获取省份信息
|
||
try:
|
||
info = get_province_info("广东")
|
||
print("\n广东省信息：")
|
||
print(info)
|
||
except ValueError as e:
|
||
print(e) |