# Ultralytics YOLO 🚀, AGPL-3.0 license

import itertools
import os
from glob import glob
from math import ceil
from pathlib import Path

import cv2
import numpy as np
from PIL import Image
from tqdm import tqdm

from ultralytics.data.utils import exif_size, img2label_paths
from ultralytics.utils.checks import check_requirements

check_requirements("shapely")
from shapely.geometry import Polygon


def bbox_iof(polygon1, bbox2, eps=1e-6):
    """
    Calculate iofs between bbox1 and bbox2.

    Args:
        polygon1 (np.ndarray): Polygon coordinates, (n, 8).
        bbox2 (np.ndarray): Bounding boxes, (n ,4).
    """
    polygon1 = polygon1.reshape(-1, 4, 2)
    lt_point = np.min(polygon1, axis=-2)
    rb_point = np.max(polygon1, axis=-2)
    bbox1 = np.concatenate([lt_point, rb_point], axis=-1)

    lt = np.maximum(bbox1[:, None, :2], bbox2[..., :2])
    rb = np.minimum(bbox1[:, None, 2:], bbox2[..., 2:])
    wh = np.clip(rb - lt, 0, np.inf)
    h_overlaps = wh[..., 0] * wh[..., 1]

    l, t, r, b = (bbox2[..., i] for i in range(4))
    polygon2 = np.stack([l, t, r, t, r, b, l, b], axis=-1).reshape(-1, 4, 2)

    sg_polys1 = [Polygon(p) for p in polygon1]
    sg_polys2 = [Polygon(p) for p in polygon2]
    overlaps = np.zeros(h_overlaps.shape)
    for p in zip(*np.nonzero(h_overlaps)):
        overlaps[p] = sg_polys1[p[0]].intersection(sg_polys2[p[-1]]).area
    unions = np.array([p.area for p in sg_polys1], dtype=np.float32)
    unions = unions[..., None]

    unions = np.clip(unions, eps, np.inf)
    outputs = overlaps / unions
    if outputs.ndim == 1:
        outputs = outputs[..., None]
    return outputs


def load_yolo_dota(data_root, split="train"):
    """
    Load DOTA dataset.

    Args:
        data_root (str): Data root.
        split (str): The split data set, could be train or val.

    Notes:
        The directory structure assumed for the DOTA dataset:
            - data_root
                - images
                    - train
                    - val
                - labels
                    - train
                    - val
    """
    assert split in ["train", "val"]
    im_dir = os.path.join(data_root, f"images/{split}")
    assert Path(im_dir).exists(), f"Can't find {im_dir}, please check your data root."
    im_files = glob(os.path.join(data_root, f"images/{split}/*"))
    lb_files = img2label_paths(im_files)
    annos = []
    for im_file, lb_file in zip(im_files, lb_files):
        w, h = exif_size(Image.open(im_file))
        with open(lb_file) as f:
            lb = [x.split() for x in f.read().strip().splitlines() if len(x)]
            lb = np.array(lb, dtype=np.float32)
        annos.append(dict(ori_size=(h, w), label=lb, filepath=im_file))
    return annos


def get_windows(im_size, crop_sizes=[1024], gaps=[200], im_rate_thr=0.6, eps=0.01):
    """
    Get the coordinates of windows.

    Args:
        im_size (tuple): Original image size, (h, w).
        crop_sizes (List(int)): Crop size of windows.
        gaps (List(int)): Gap between each crops.
        im_rate_thr (float): Threshold of windows areas divided by image ares.
    """
    h, w = im_size
    windows = []
    for crop_size, gap in zip(crop_sizes, gaps):
        assert crop_size > gap, f"invalid crop_size gap pair [{crop_size} {gap}]"
        step = crop_size - gap

        xn = 1 if w <= crop_size else ceil((w - crop_size) / step + 1)
        xs = [step * i for i in range(xn)]
        if len(xs) > 1 and xs[-1] + crop_size > w:
            xs[-1] = w - crop_size

        yn = 1 if h <= crop_size else ceil((h - crop_size) / step + 1)
        ys = [step * i for i in range(yn)]
        if len(ys) > 1 and ys[-1] + crop_size > h:
            ys[-1] = h - crop_size

        start = np.array(list(itertools.product(xs, ys)), dtype=np.int64)
        stop = start + crop_size
        windows.append(np.concatenate([start, stop], axis=1))
    windows = np.concatenate(windows, axis=0)

    im_in_wins = windows.copy()
    im_in_wins[:, 0::2] = np.clip(im_in_wins[:, 0::2], 0, w)
    im_in_wins[:, 1::2] = np.clip(im_in_wins[:, 1::2], 0, h)
    im_areas = (im_in_wins[:, 2] - im_in_wins[:, 0]) * (im_in_wins[:, 3] - im_in_wins[:, 1])
    win_areas = (windows[:, 2] - windows[:, 0]) * (windows[:, 3] - windows[:, 1])
    im_rates = im_areas / win_areas
    if not (im_rates > im_rate_thr).any():
        max_rate = im_rates.max()
        im_rates[abs(im_rates - max_rate) < eps] = 1
    return windows[im_rates > im_rate_thr]


def get_window_obj(anno, windows, iof_thr=0.7):
    """Get objects for each window."""
    h, w = anno["ori_size"]
    label = anno["label"]
    if len(label):
        label[:, 1::2] *= w
        label[:, 2::2] *= h
        iofs = bbox_iof(label[:, 1:], windows)
        # Unnormalized and misaligned coordinates
        window_anns = [(label[iofs[:, i] >= iof_thr]) for i in range(len(windows))]
    else:
        window_anns = [np.zeros((0, 9), dtype=np.float32) for _ in range(len(windows))]
    return window_anns


def crop_and_save(anno, windows, window_objs, im_dir, lb_dir):
    """
    Crop images and save new labels.

    Args:
        anno (dict): Annotation dict, including `filepath`, `label`, `ori_size` as its keys.
        windows (list): A list of windows coordinates.
        window_objs (list): A list of labels inside each window.
        im_dir (str): The output directory path of images.
        lb_dir (str): The output directory path of labels.

    Notes:
        The directory structure assumed for the DOTA dataset:
            - data_root
                - images
                    - train
                    - val
                - labels
                    - train
                    - val
    """
    im = cv2.imread(anno["filepath"])
    name = Path(anno["filepath"]).stem
    for i, window in enumerate(windows):
        x_start, y_start, x_stop, y_stop = window.tolist()
        new_name = name + "__" + str(x_stop - x_start) + "__" + str(x_start) + "___" + str(y_start)
        patch_im = im[y_start:y_stop, x_start:x_stop]
        ph, pw = patch_im.shape[:2]

        cv2.imwrite(os.path.join(im_dir, f"{new_name}.jpg"), patch_im)
        label = window_objs[i]
        if len(label) == 0:
            continue
        label[:, 1::2] -= x_start
        label[:, 2::2] -= y_start
        label[:, 1::2] /= pw
        label[:, 2::2] /= ph

        with open(os.path.join(lb_dir, f"{new_name}.txt"), "w") as f:
            for lb in label:
                formatted_coords = ["{:.6g}".format(coord) for coord in lb[1:]]
                f.write(f"{int(lb[0])} {' '.join(formatted_coords)}\n")


def split_images_and_labels(data_root, save_dir, split="train", crop_sizes=[1024], gaps=[200]):
    """
    Split both images and labels.

    Notes:
        The directory structure assumed for the DOTA dataset:
            - data_root
                - images
                    - split
                - labels
                    - split
        and the output directory structure is:
            - save_dir
                - images
                    - split
                - labels
                    - split
    """
    im_dir = Path(save_dir) / "images" / split
    im_dir.mkdir(parents=True, exist_ok=True)
    lb_dir = Path(save_dir) / "labels" / split
    lb_dir.mkdir(parents=True, exist_ok=True)

    annos = load_yolo_dota(data_root, split=split)
    for anno in tqdm(annos, total=len(annos), desc=split):
        windows = get_windows(anno["ori_size"], crop_sizes, gaps)
        window_objs = get_window_obj(anno, windows)
        crop_and_save(anno, windows, window_objs, str(im_dir), str(lb_dir))


def split_trainval(data_root, save_dir, crop_size=1024, gap=200, rates=[1.0]):
    """
    Split train and val set of DOTA.

    Notes:
        The directory structure assumed for the DOTA dataset:
            - data_root
                - images
                    - train
                    - val
                - labels
                    - train
                    - val
        and the output directory structure is:
            - save_dir
                - images
                    - train
                    - val
                - labels
                    - train
                    - val
    """
    crop_sizes, gaps = [], []
    for r in rates:
        crop_sizes.append(int(crop_size / r))
        gaps.append(int(gap / r))
    for split in ["train", "val"]:
        split_images_and_labels(data_root, save_dir, split, crop_sizes, gaps)


def split_test(data_root, save_dir, crop_size=1024, gap=200, rates=[1.0]):
    """
    Split test set of DOTA, labels are not included within this set.

    Notes:
        The directory structure assumed for the DOTA dataset:
            - data_root
                - images
                    - test
        and the output directory structure is:
            - save_dir
                - images
                    - test
    """
    crop_sizes, gaps = [], []
    for r in rates:
        crop_sizes.append(int(crop_size / r))
        gaps.append(int(gap / r))
    save_dir = Path(save_dir) / "images" / "test"
    save_dir.mkdir(parents=True, exist_ok=True)

    im_dir = Path(os.path.join(data_root, "images/test"))
    assert im_dir.exists(), f"Can't find {str(im_dir)}, please check your data root."
    im_files = glob(str(im_dir / "*"))
    for im_file in tqdm(im_files, total=len(im_files), desc="test"):
        w, h = exif_size(Image.open(im_file))
        windows = get_windows((h, w), crop_sizes=crop_sizes, gaps=gaps)
        im = cv2.imread(im_file)
        name = Path(im_file).stem
        for window in windows:
            x_start, y_start, x_stop, y_stop = window.tolist()
            new_name = name + "__" + str(x_stop - x_start) + "__" + str(x_start) + "___" + str(y_start)
            patch_im = im[y_start:y_stop, x_start:x_stop]
            cv2.imwrite(os.path.join(str(save_dir), f"{new_name}.jpg"), patch_im)


if __name__ == "__main__":
    split_trainval(
        data_root="DOTAv2",
        save_dir="DOTAv2-split",
    )
    split_test(
        data_root="DOTAv2",
        save_dir="DOTAv2-split",
    )