import cv2
import numpy as np

class_names = [
    "person",
    "bicycle",
    "car",
    "motorcycle",
    "airplane",
    "bus",
    "train",
    "truck",
    "boat",
    "traffic light",
    "fire hydrant",
    "stop sign",
    "parking meter",
    "bench",
    "bird",
    "cat",
    "dog",
    "horse",
    "sheep",
    "cow",
    "elephant",
    "bear",
    "zebra",
    "giraffe",
    "backpack",
    "umbrella",
    "handbag",
    "tie",
    "suitcase",
    "frisbee",
    "skis",
    "snowboard",
    "sports ball",
    "kite",
    "baseball bat",
    "baseball glove",
    "skateboard",
    "surfboard",
    "tennis racket",
    "bottle",
    "wine glass",
    "cup",
    "fork",
    "knife",
    "spoon",
    "bowl",
    "banana",
    "apple",
    "sandwich",
    "orange",
    "broccoli",
    "carrot",
    "hot dog",
    "pizza",
    "donut",
    "cake",
    "chair",
    "couch",
    "potted plant",
    "bed",
    "dining table",
    "toilet",
    "tv",
    "laptop",
    "mouse",
    "remote",
    "keyboard",
    "cell phone",
    "microwave",
    "oven",
    "toaster",
    "sink",
    "refrigerator",
    "book",
    "clock",
    "vase",
    "scissors",
    "teddy bear",
    "hair drier",
    "toothbrush",
]

# Create a list of colors for each class where each color is a tuple of 3 integer values
rng = np.random.default_rng(3)
colors = rng.uniform(0, 255, size=(len(class_names), 3))


def nms(boxes, scores, iou_threshold):
    # Sort by score
    sorted_indices = np.argsort(scores)[::-1]

    keep_boxes = []
    while sorted_indices.size > 0:
        # Pick the last box
        box_id = sorted_indices[0]
        keep_boxes.append(box_id)

        # Compute IoU of the picked box with the rest
        ious = compute_iou(boxes[box_id, :], boxes[sorted_indices[1:], :])

        # Remove boxes with IoU over the threshold
        keep_indices = np.where(ious < iou_threshold)[0]

        # print(keep_indices.shape, sorted_indices.shape)
        sorted_indices = sorted_indices[keep_indices + 1]

    return keep_boxes


def multiclass_nms(boxes, scores, class_ids, iou_threshold):
    unique_class_ids = np.unique(class_ids)

    keep_boxes = []
    for class_id in unique_class_ids:
        class_indices = np.where(class_ids == class_id)[0]
        class_boxes = boxes[class_indices, :]
        class_scores = scores[class_indices]

        class_keep_boxes = nms(class_boxes, class_scores, iou_threshold)
        keep_boxes.extend(class_indices[class_keep_boxes])

    return keep_boxes


def compute_iou(box, boxes):
    # Compute xmin, ymin, xmax, ymax for both boxes
    xmin = np.maximum(box[0], boxes[:, 0])
    ymin = np.maximum(box[1], boxes[:, 1])
    xmax = np.minimum(box[2], boxes[:, 2])
    ymax = np.minimum(box[3], boxes[:, 3])

    # Compute intersection area
    intersection_area = np.maximum(0, xmax - xmin) * np.maximum(0, ymax - ymin)

    # Compute union area
    box_area = (box[2] - box[0]) * (box[3] - box[1])
    boxes_area = (boxes[:, 2] - boxes[:, 0]) * (boxes[:, 3] - boxes[:, 1])
    union_area = box_area + boxes_area - intersection_area

    # Compute IoU
    iou = intersection_area / union_area

    return iou


def xywh2xyxy(x):
    # Convert bounding box (x, y, w, h) to bounding box (x1, y1, x2, y2)
    y = np.copy(x)
    y[..., 0] = x[..., 0] - x[..., 2] / 2
    y[..., 1] = x[..., 1] - x[..., 3] / 2
    y[..., 2] = x[..., 0] + x[..., 2] / 2
    y[..., 3] = x[..., 1] + x[..., 3] / 2
    return y


def draw_seg_masks(image, masks, class_ids, mask_alpha=0.3):
    """Overlay pixel-level segmentation masks on *image* using per-class colours.

    Parameters
    ----------
    image : np.ndarray  BGR frame (H, W, 3)
    masks : np.ndarray  Float mask array of shape (N, Hm, Wm).  Each slice is
                        a soft mask (0-1) at the model's internal resolution.
    class_ids : array-like  Integer class index for each of the N masks.
    mask_alpha : float  Blend weight for the mask layer (0 = invisible, 1 = opaque).
    """
    if masks is None or len(masks) == 0:
        return image

    img_h, img_w = image.shape[:2]
    mask_layer = image.copy()

    for mask, class_id in zip(masks, class_ids):
        color = colors[int(class_id) % len(colors)]
        # Resize soft mask to frame resolution and threshold to binary.
        mask_resized = cv2.resize(mask, (img_w, img_h), interpolation=cv2.INTER_LINEAR)
        binary = (mask_resized > 0.5).astype(np.uint8)

        # Paint the masked pixels with the class colour.
        for ch, c_val in enumerate(color):
            mask_layer[:, :, ch] = np.where(binary, c_val, mask_layer[:, :, ch])

    return cv2.addWeighted(mask_layer, mask_alpha, image, 1 - mask_alpha, 0)


def draw_detections(image, boxes, scores, class_ids, masks=None, mask_alpha=0.3, class_names_list=None):
    """Draw segmentation masks (if any), bounding boxes, and labels on *image*.

    Parameters
    ----------
    image     : np.ndarray  BGR frame.
    boxes     : np.ndarray  Bounding boxes in xyxy format, shape (N, 4).
    scores    : np.ndarray  Confidence scores, shape (N,).
    class_ids : np.ndarray  Integer class indices, shape (N,).
    masks     : np.ndarray | None  Soft masks (N, Hm, Wm).  When provided the
                masks are blended onto the frame before boxes/labels are drawn.
    mask_alpha: float  Opacity of the mask layer.
    class_names_list: list[str] | None  List of active class names corresponding to class_ids.
    """
    if class_names_list is None:
        class_names_list = class_names

    det_img = image.copy()

    img_height, img_width = image.shape[:2]
    font_size = min([img_height, img_width]) * 0.0006
    text_thickness = int(min([img_height, img_width]) * 0.001)

    # 1. Draw segmentation masks first so boxes/labels render on top.
    if masks is not None and len(masks) > 0:
        det_img = draw_seg_masks(det_img, masks, class_ids, mask_alpha)

    # 2. Draw bounding boxes and labels of detections.
    for class_id, box, score in zip(class_ids, boxes, scores):
        color = colors[int(class_id) % len(colors)]

        draw_box(det_img, box, color)  # type: ignore

        label = class_names_list[int(class_id)] if int(class_id) < len(class_names_list) else str(class_id)
        caption = f"{label} {int(score * 100)}%"
        draw_text(det_img, caption, box, color, font_size, text_thickness)  # type: ignore

    return det_img




def draw_box(
    image: np.ndarray,
    box: np.ndarray,
    color: tuple[int, int, int] = (0, 0, 255),
    thickness: int = 2,
) -> np.ndarray:
    x1, y1, x2, y2 = box.astype(int)
    return cv2.rectangle(image, (x1, y1), (x2, y2), color, thickness)


def draw_text(
    image: np.ndarray,
    text: str,
    box: np.ndarray,
    color: tuple[int, int, int] = (0, 0, 255),
    font_size: float = 0.001,
    text_thickness: int = 2,
) -> np.ndarray:
    x1, y1, x2, y2 = box.astype(int)
    (tw, th), _ = cv2.getTextSize(
        text=text,
        fontFace=cv2.FONT_HERSHEY_SIMPLEX,
        fontScale=font_size,
        thickness=text_thickness,
    )
    th = int(th * 1.2)

    cv2.rectangle(image, (x1, y1), (x1 + tw, y1 - th), color, -1)

    return cv2.putText(
        image,
        text,
        (x1, y1),
        cv2.FONT_HERSHEY_SIMPLEX,
        font_size,
        (255, 255, 255),
        text_thickness,
        cv2.LINE_AA,
    )


def draw_masks(
    image: np.ndarray, boxes: np.ndarray, classes: np.ndarray, mask_alpha: float = 0.3
) -> np.ndarray:
    mask_img = image.copy()

    # Draw bounding boxes and labels of detections
    for box, class_id in zip(boxes, classes):
        color = colors[class_id]

        x1, y1, x2, y2 = box.astype(int)

        # Draw fill rectangle in mask image
        cv2.rectangle(mask_img, (x1, y1), (x2, y2), color, -1)  # type: ignore

    return cv2.addWeighted(mask_img, mask_alpha, image, 1 - mask_alpha, 0)