import argparse
import os

from inference.models.utils import get_roboflow_model
from tqdm import tqdm

import supervision as sv


def process_video(
    roboflow_api_key: str,
    model_id: str,
    source_video_path: str,
    target_video_path: str,
    confidence_threshold: float = 0.3,
    iou_threshold: float = 0.7,
) -> None:
    model = get_roboflow_model(model_id=model_id, api_key=roboflow_api_key)

    tracker = sv.ByteTrack()
    box_annotator = sv.BoundingBoxAnnotator()
    label_annotator = sv.LabelAnnotator()
    frame_generator = sv.get_video_frames_generator(source_path=source_video_path)
    video_info = sv.VideoInfo.from_video_path(video_path=source_video_path)

    with sv.VideoSink(target_path=target_video_path, video_info=video_info) as sink:
        for frame in tqdm(frame_generator, total=video_info.total_frames):
            results = model.infer(
                frame, confidence=confidence_threshold, iou_threshold=iou_threshold
            )[0]
            detections = sv.Detections.from_inference(results)
            detections = tracker.update_with_detections(detections)

            annotated_frame = box_annotator.annotate(
                scene=frame.copy(), detections=detections
            )

            annotated_labeled_frame = label_annotator.annotate(
                scene=annotated_frame, detections=detections
            )

            sink.write_frame(frame=annotated_labeled_frame)


if __name__ == "__main__":
    parser = argparse.ArgumentParser(
        description="Video Processing with Inference and ByteTrack"
    )
    parser.add_argument(
        "--model_id",
        default="yolov8x-1280",
        help="Roboflow model ID",
        type=str,
    )
    parser.add_argument(
        "--source_video_path",
        required=True,
        help="Path to the source video file",
        type=str,
    )
    parser.add_argument(
        "--target_video_path",
        required=True,
        help="Path to the target video file (output)",
        type=str,
    )
    parser.add_argument(
        "--confidence_threshold",
        default=0.3,
        help="Confidence threshold for the model",
        type=float,
    )
    parser.add_argument(
        "--iou_threshold", default=0.7, help="IOU threshold for the model", type=float
    )
    parser.add_argument(
        "--roboflow_api_key",
        default=None,
        help="Roboflow API key",
        type=str,
    )

    args = parser.parse_args()

    api_key = args.roboflow_api_key
    api_key = os.environ.get("ROBOFLOW_API_KEY", api_key)
    if api_key is None:
        raise ValueError(
            "Roboflow API key is missing. Please provide it as an argument or set the "
            "ROBOFLOW_API_KEY environment variable."
        )
    args.roboflow_api_key = api_key

    process_video(
        roboflow_api_key=args.roboflow_api_key,
        model_id=args.model_id,
        source_video_path=args.source_video_path,
        target_video_path=args.target_video_path,
        confidence_threshold=args.confidence_threshold,
        iou_threshold=args.iou_threshold,
    )