日志、监控与错误处理体系

# 用 python-json-logger 输出 JSON
from pythonjsonlogger import jsonlogger

handler = logging.StreamHandler()
handler.setFormatter(jsonlogger.JsonFormatter(
    "%(asctime)s %(levelname)s %(name)s %(message)s"
))
logging.getLogger().addHandler(handler)

# 输出：{"asctime": "...", "levelname": "ERROR", "name": "payment", ...}

# 更简单：用 structlog 或 loguru
# loguru 示例：
from loguru import logger
logger.add("app.json", serialize=True)  # 自动 JSON
logger.add("app.log", rotation="10 MB", retention="30 days")
logger.bind(user_id=123, order_id=456, amount=99.9).error("支付失败")

# 1. 自定义异常层次
class AppError(Exception):
    """应用异常基类"""
    code = "APP_ERROR"

class PaymentError(AppError):
    code = "PAYMENT_ERROR"

class InsufficientBalanceError(PaymentError):
    code = "INSUFFICIENT_BALANCE"

# 2. 精确捕获，不要裸 except
try:
    process_payment(order)
except InsufficientBalanceError:
    return {"error": "余额不足"}, 400
except PaymentError as e:
    logger.error(f"支付失败: {e}")
    return {"error": "支付服务暂时不可用"}, 502
except Exception:
    logger.exception("未预期的错误")  # 记录完整堆栈
    raise  # 重新抛出，不要吞掉

# 3. 永远不要这样写：
try:
    risky_operation()
except:  # 裸 except 会捕获 KeyboardInterrupt 和 SystemExit！
    pass   # 吞掉所有错误，问题被隐藏，调试噩梦

# 4. finally 确保资源释放
try:
    f = open("data.txt")
    process(f)
finally:
    f.close()  # 即使出错也会关闭

# 更好：用上下文管理器
with open("data.txt") as f:
    process(f)  # 自动关闭

# 重试：网络请求可能因临时故障失败，重试可以解决
import tenacity

@tenacity.retry(
    stop=tenacity.stop_after_attempt(3),       # 最多重试3次
    wait=tenacity.wait_exponential(min=1, max=10),  # 指数退避1s,2s,4s
    retry=tenacity.retry_if_exception_type(NetworkError),
)
def call_external_api():
    return requests.get("https://api.example.com/data", timeout=5)

# 熔断：当依赖服务持续失败时，快速失败而不是一直等待
# 用 circuitbreaker 库或手动实现
class CircuitBreaker:
    def __init__(self, threshold=5, reset_timeout=30):
        self.failures = 0
        self.threshold = threshold
        self.reset_timeout = reset_timeout
        self.opened = False

    def call(self, func, *args):
        if self.opened:
            raise Exception("熔断器开启，快速失败")
        try:
            result = func(*args)
            self.failures = 0  # 成功则重置
            return result
        except Exception:
            self.failures += 1
            if self.failures >= self.threshold:
                self.opened = True
            raise

# 降级：主服务不可用时提供备用方案
def get_user_recommendations(user_id):
    try:
        return ai_service.get_recommendations(user_id)
    except Exception:
        logger.warning("AI推荐不可用，降级为热门推荐")
        return get_popular_items()  # 降级方案