# sanguo_data/config.py
from dataclasses import dataclass
import os
import yaml

@dataclass(frozen=True)
class DataConfig:
    data_paths: dict
    data_sources: dict
    validation: dict
    performance: dict

def load_config(path: str) -> DataConfig:
    try:
        with open(path, "r", encoding="utf-8") as f:
            raw = yaml.safe_load(f)
    except FileNotFoundError:
        raise FileNotFoundError(f"配置文件不存在: {path}")
    except yaml.YAMLError as e:
        raise ValueError(f"YAML解析失败: {e}")

    if not raw:
        raise ValueError(f"配置文件为空: {path}")

    return DataConfig(
        data_paths=raw.get("data_paths", {}),
        data_sources=raw.get("data_sources", {}),
        validation=raw.get("validation", {}),
        performance=raw.get("performance", {}),
    )


def find_config_path() -> str:
    """Locate data_platform.yaml: container /app/config first, then repo config/."""
    candidates = [
        "/app/config/data_platform.yaml",
        os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "config", "data_platform.yaml"),
        "config/data_platform.yaml",
    ]
    for p in candidates:
        if os.path.exists(p):
            return p
    return candidates[0]