"""YOLO 数据集格式的共用定义。

工作流里只用到"写出"这一侧：scripts/generate_boxes.py 产出的
`labels/<类别>/<图名>.txt` 与 `data.yaml` 是给外部检测训练用的交换格式。

标注文件每行一个目标，坐标相对图像宽高归一化到 [0, 1]，中心点格式：

```
<class_id> <cx> <cy> <w> <h>
```
"""

from __future__ import annotations

from collections.abc import Sequence
from pathlib import Path

IMAGE_SUFFIXES = (".png", ".jpg", ".jpeg", ".bmp", ".tif", ".tiff", ".webp")


def write_data_yaml(
    path: str | Path,
    classes: Sequence[str],
    root: str | Path = ".",
    train: str = "images/train",
    val: str = "images/val",
) -> Path:
    """写一个 YOLO 风格的 data.yaml，字段与 ultralytics 通用。"""
    import yaml

    path = Path(path)
    path.parent.mkdir(parents=True, exist_ok=True)
    path.write_text(
        yaml.safe_dump(
            {
                "path": str(root),
                "train": train,
                "val": val,
                "nc": len(classes),
                "names": dict(enumerate(classes)),
            },
            allow_unicode=True,
            sort_keys=False,
        ),
        encoding="utf-8",
    )
    return path