"""Utilities for loading OHLCV data for local backtesting."""
from __future__ import annotations

from dataclasses import dataclass
from pathlib import Path
from typing import Optional

import pandas as pd


@dataclass
class DataSlice:
    symbol: str
    timeframe: str
    data: pd.DataFrame


def load_csv(path: Path, symbol: str, timeframe: str, start: Optional[str] = None, end: Optional[str] = None) -> DataSlice:
    if not path.exists():
        raise FileNotFoundError(f"Missing data file: {path}")

    df = pd.read_csv(path, parse_dates=["timestamp"])
    df = df.sort_values("timestamp").reset_index(drop=True)
    if start:
        df = df[df["timestamp"] >= pd.Timestamp(start)]
    if end:
        df = df[df["timestamp"] <= pd.Timestamp(end)]
    if df.empty:
        raise ValueError("No rows remain after applying date filters")

    expected_cols = {"timestamp", "open", "high", "low", "close", "volume"}
    missing = expected_cols.difference(df.columns)
    if missing:
        raise ValueError(f"Missing columns in {path}: {sorted(missing)}")

    df = df.set_index("timestamp")

    return DataSlice(symbol=symbol.upper(), timeframe=timeframe, data=df)