"""
算子系统：基础数学算子和技术指标算子的注册与管理
支持算子的注册、查询、反射调用
"""

import numpy as np
import pandas as pd
from typing import Dict, Callable, List, Optional, Any
from abc import ABC, abstractmethod
import inspect


class Operator(ABC):
    """算子基类"""

    def __init__(self, name: str, func: Callable, description: str = ""):
        """
        Parameters:
        -----------
        name : str
            算子名称（唯一标识）
        func : Callable
            算子函数
        description : str
            算子描述
        """
        self.name = name
        self.func = func
        self.description = description
        self._signature = inspect.signature(func)

    def __call__(self, *args, **kwargs):
        """调用算子函数"""
        return self.func(*args, **kwargs)

    def get_signature(self):
        """获取函数签名"""
        return self._signature

    def __repr__(self):
        return f"Operator(name='{self.name}', description='{self.description}')"


class OperatorRegistry:
    """算子注册表"""

    def __init__(self):
        self._operators: Dict[str, Operator] = {}

    def register(self, operator: Operator):
        """注册算子"""
        if operator.name in self._operators:
            raise ValueError(f"算子 '{operator.name}' 已存在")
        self._operators[operator.name] = operator

    def register_function(self, name: str, func: Callable, description: str = ""):
        """直接注册函数为算子"""
        operator = Operator(name, func, description)
        self.register(operator)

    def get(self, name: str) -> Optional[Operator]:
        """获取算子"""
        return self._operators.get(name)

    def has(self, name: str) -> bool:
        """检查算子是否存在"""
        return name in self._operators

    def list_all(self) -> List[str]:
        """列出所有算子名称"""
        return list(self._operators.keys())

    def get_all(self) -> Dict[str, Operator]:
        """获取所有算子"""
        return self._operators.copy()


# 全局算子注册表
_registry = OperatorRegistry()


def register_operator(name: str, description: str = ""):
    """装饰器：注册算子"""

    def decorator(func: Callable):
        _registry.register_function(name, func, description)
        return func

    return decorator


def get_operator(name: str) -> Optional[Operator]:
    """获取算子"""
    return _registry.get(name)


def get_registry() -> OperatorRegistry:
    """获取全局注册表"""
    return _registry


# ==================== 基础数学算子 ====================


@register_operator("add", "加法: x + y")
def _add(x: np.ndarray, y: np.ndarray) -> np.ndarray:
    return x + y


@register_operator("sub", "减法: x - y")
def _sub(x: np.ndarray, y: np.ndarray) -> np.ndarray:
    return x - y


@register_operator("mul", "乘法: x * y")
def _mul(x: np.ndarray, y: np.ndarray) -> np.ndarray:
    return x * y


@register_operator("div", "除法: x / y (安全除法)")
def _div(x: np.ndarray, y: np.ndarray) -> np.ndarray:
    denom = np.where(np.abs(y) < 1e-12, np.nan, y)
    return x / denom


@register_operator("neg", "取负: -x")
def _neg(x: np.ndarray) -> np.ndarray:
    return np.negative(x)


@register_operator("abs", "绝对值: |x|")
def _abs(x: np.ndarray) -> np.ndarray:
    return np.abs(x)


@register_operator("log", "对数: log(|x|)")
def _log(x: np.ndarray) -> np.ndarray:
    return np.log(np.clip(np.abs(x), 1e-12, None))


@register_operator("sqrt", "平方根: sqrt(x)")
def _sqrt(x: np.ndarray) -> np.ndarray:
    return np.sqrt(np.clip(x, 0.0, None))


@register_operator("pow", "幂运算: x^y (限制范围)")
def _pow(x: np.ndarray, y: np.ndarray) -> np.ndarray:
    y_clip = np.clip(y, -3.0, 3.0)
    with np.errstate(over="ignore", invalid="ignore"):
        out = np.power(np.clip(x, -1e6, 1e6), y_clip)
    out[~np.isfinite(out)] = np.nan
    return out


# ==================== 时间序列算子 ====================


def _rolling_mean(x: np.ndarray, window: int) -> np.ndarray:
    s = pd.Series(x)
    return s.rolling(window, min_periods=max(2, window // 2)).mean().to_numpy()


def _rolling_std(x: np.ndarray, window: int) -> np.ndarray:
    s = pd.Series(x)
    return s.rolling(window, min_periods=max(2, window // 2)).std().to_numpy()


def _ts_delta(x: np.ndarray, period: int) -> np.ndarray:
    s = pd.Series(x)
    return s.diff(period).to_numpy()


def _ts_rank(x: np.ndarray, window: int) -> np.ndarray:
    s = pd.Series(x)
    return (
        s.rolling(window, min_periods=max(2, window // 2))
        .apply(lambda a: pd.Series(a).rank(pct=True).iloc[-1], raw=False)
        .to_numpy()
    )


def _delay(x: np.ndarray, period: int) -> np.ndarray:
    s = pd.Series(x)
    return s.shift(period).to_numpy()


# 注册时间序列算子（带不同窗口）
for w in (3, 6, 12, 24, 48, 96):
    _registry.register_function(
        f"sma{w}", lambda x, w=w: _rolling_mean(x, w), f"简单移动平均: SMA(x, {w})"
    )
    _registry.register_function(
        f"std{w}", lambda x, w=w: _rolling_std(x, w), f"滚动标准差: STD(x, {w})"
    )
    _registry.register_function(
        f"rank{w}", lambda x, w=w: _ts_rank(x, w), f"滚动排名: RANK(x, {w})"
    )
    _registry.register_function(
        f"delta{w}", lambda x, w=w: _ts_delta(x, w), f"差分: DELTA(x, {w})"
    )
    _registry.register_function(
        f"delay{w}", lambda x, w=w: _delay(x, w), f"延迟: DELAY(x, {w})"
    )


# ==================== 因子公式解析与计算 ====================


class FactorFormula:
    """因子公式：支持序列化和反序列化"""

    def __init__(self, expression: str, feature_names: List[str]):
        """
        Parameters:
        -----------
        expression : str
            因子表达式（使用算子名称）
        feature_names : List[str]
            特征名称列表
        """
        self.expression = expression
        self.feature_names = feature_names

    def compute(self, features: Dict[str, np.ndarray]) -> np.ndarray:
        """
        计算因子值

        Parameters:
        -----------
        features : Dict[str, np.ndarray]
            特征字典，key为特征名称

        Returns:
        --------
        np.ndarray: 因子值
        """
        # 构建计算环境
        env = {}

        # 添加特征
        for name in self.feature_names:
            if name not in features:
                raise KeyError(f"特征 '{name}' 不存在")
            env[name] = features[name]

        # 添加算子
        for op_name in _registry.list_all():
            op = _registry.get(op_name)
            if op:
                env[op_name] = op.func

        # 添加numpy和pandas（用于某些表达式）
        env["np"] = np
        env["pd"] = pd

        # 执行表达式
        try:
            # 限制可用的内置函数
            safe_builtins = {
                "abs": abs,
                "min": min,
                "max": max,
                "sum": sum,
                "len": len,
            }
            result = eval(self.expression, {"__builtins__": safe_builtins}, env)

            # 确保结果是numpy数组
            if not isinstance(result, np.ndarray):
                if isinstance(result, (int, float)):
                    # 标量转换为数组（广播）
                    result = np.full(len(features[self.feature_names[0]]), result)
                else:
                    result = np.array(result)

            # 确保长度一致
            expected_len = len(features[self.feature_names[0]])
            if len(result) != expected_len:
                raise ValueError(
                    f"表达式结果长度 {len(result)} 与特征长度 {expected_len} 不匹配"
                )

            return result
        except Exception as e:
            raise RuntimeError(f"计算因子表达式失败: {e}\n表达式: {self.expression}")

    def to_dict(self) -> Dict:
        """序列化为字典"""
        return {"expression": self.expression, "feature_names": self.feature_names}

    @classmethod
    def from_dict(cls, data: Dict) -> "FactorFormula":
        """从字典反序列化"""
        return cls(data["expression"], data["feature_names"])

    def __repr__(self):
        return f"FactorFormula(expression='{self.expression}', features={self.feature_names})"