import gradio as gr
import torch
from sahi.prediction import ObjectPrediction
from sahi.utils.cv import visualize_object_predictions, read_image
from ultralyticsplus import YOLO

# Images
torch.hub.download_url_to_file('https://huggingface.co/spaces/foduucom/table-extraction-yolov8/resolve/main/test/table1.jpg', 'document1.jpg')
torch.hub.download_url_to_file('https://huggingface.co/spaces/foduucom/table-extraction-yolov8/resolve/main/test/table2.jpg', 'document2.jpg')
torch.hub.download_url_to_file('https://huggingface.co/spaces/foduucom/table-extraction-yolov8/resolve/main/test/table3.jpg', 'document3.jpg')

def yolov8_inference(
    image: gr.inputs.Image = None,
    model_path: gr.inputs.Dropdown = None,
    image_size: gr.inputs.Slider = 640,
    conf_threshold: gr.inputs.Slider = 0.25,
    iou_threshold: gr.inputs.Slider = 0.45,
):
    """
    YOLOv8 inference function
    Args:
        image: Input image
        model_path: Path to the model
        image_size: Image size
        conf_threshold: Confidence threshold
        iou_threshold: IOU threshold
    Returns:
        Rendered image
    """
    model = YOLO(model_path)
    model.conf = conf_threshold
    model.iou = iou_threshold
    results = model.predict(image, imgsz=image_size)
    object_prediction_list = []
    for _, image_results in enumerate(results):
        if len(image_results)!=0:
            image_predictions_in_xyxy_format = image_results['det']
            for pred in image_predictions_in_xyxy_format:
                x1, y1, x2, y2 = (
                    int(pred[0]),
                    int(pred[1]),
                    int(pred[2]),
                    int(pred[3]),
                )
                bbox = [x1, y1, x2, y2]
                score = pred[4]
                category_name = model.model.names[int(pred[5])]
                category_id = pred[5]
                object_prediction = ObjectPrediction(
                    bbox=bbox,
                    category_id=int(category_id),
                    score=score,
                    category_name=category_name,
                )
                object_prediction_list.append(object_prediction)

    image = read_image(image)
    output_image = visualize_object_predictions(image=image, object_prediction_list=object_prediction_list)
    return output_image['image']
        

inputs = [
    gr.inputs.Image(type="filepath", label="Input Image"),
    gr.inputs.Dropdown(["foduucom/table-detection-and-extraction"], 
                       default="foduucom/table-detection-and-extraction", label="Model"),
    gr.inputs.Slider(minimum=320, maximum=1280, default=640, step=32, label="Image Size"),
    gr.inputs.Slider(minimum=0.0, maximum=1.0, default=0.25, step=0.05, label="Confidence Threshold"),
    gr.inputs.Slider(minimum=0.0, maximum=1.0, default=0.45, step=0.05, label="IOU Threshold"),
]

outputs = gr.outputs.Image(type="filepath", label="Output Image")
title = "YoloTableExtract: Efficient Table Detection"

description = "🔍 YoloTableExtract is a powerful space that utilizes YOLOv8s for accurate table detection and extraction. Whether tables are bordered or borderless, this space can effectively identify and extract them from images. For further assistance and support related to documentation or data-related issues, feel free to contact info@foduu.com. If you find this space helpful, please show your appreciation by liking it. ❤️👍🏼"
examples = [['document1.jpg', 'foduucom/table-detection-and-extraction', 640, 0.25, 0.45], ['document2.jpg', 'foduucom/table-detection-and-extraction', 640, 0.25, 0.45], ['document3.jpg', 'foduucom/table-detection-and-extraction', 1280, 0.25, 0.45]]
demo_app = gr.Interface(
    fn=yolov8_inference,
    inputs=inputs,
    outputs=outputs,
    title=title,
    description=description,
    examples=examples,
    cache_examples=True,
    theme='huggingface',
)
demo_app.launch(debug=True, enable_queue=True)