#!/usr/bin/env python3
# This code from https://github.com/lllyasviel/ControlNet

import os
import argparse
import cv2
import numpy as np
import math
import glob
from scipy.ndimage import gaussian_filter
import matplotlib.pyplot as plt
import torch

import urllib
import openpose.util as util
from openpose.model import bodypose_model
import json


class Body(object):
    def __init__(self, the_model_path):
        self.model = bodypose_model()
        if torch.cuda.is_available():
            self.model = self.model.cuda()
        model_dict = util.transfer(self.model, torch.load(the_model_path))
        self.model.load_state_dict(model_dict)
        self.model.eval()

    def __call__(self, ori_img):
        # scale_search = [0.5, 1.0, 1.5, 2.0]
        scale_search = [0.5]
        boxsize = 368
        stride = 8
        padValue = 128
        threshold1 = 0.1
        threshold2 = 0.05
        multiplier = [x * boxsize / ori_img.shape[0] for x in scale_search]
        heatmap_avg = np.zeros((ori_img.shape[0], ori_img.shape[1], 19))
        paf_avg = np.zeros((ori_img.shape[0], ori_img.shape[1], 38))

        for m in range(len(multiplier)):
            scale = multiplier[m]
            imageToTest = cv2.resize(ori_img, (0, 0), fx=scale, fy=scale, interpolation=cv2.INTER_CUBIC)
            imageToTest_padded, pad = util.padRightDownCorner(imageToTest, stride, padValue)
            im = np.transpose(np.float32(imageToTest_padded[:, :, :, np.newaxis]), (3, 2, 0, 1)) / 256 - 0.5
            im = np.ascontiguousarray(im)

            data = torch.from_numpy(im).float()
            if torch.cuda.is_available():
                data = data.cuda()
            # data = data.permute([2, 0, 1]).unsqueeze(0).float()
            with torch.no_grad():
                Mconv7_stage6_L1, Mconv7_stage6_L2 = self.model(data)
            Mconv7_stage6_L1 = Mconv7_stage6_L1.cpu().numpy()
            Mconv7_stage6_L2 = Mconv7_stage6_L2.cpu().numpy()

            # extract outputs, resize, and remove padding
            # output 1 is heatmaps
            # heatmap = np.transpose(np.squeeze(net.blobs[output_blobs.keys()[1]].data), (1, 2, 0))
            heatmap = np.transpose(np.squeeze(Mconv7_stage6_L2), (1, 2, 0))
            heatmap = cv2.resize(heatmap, (0, 0), fx=stride, fy=stride, interpolation=cv2.INTER_CUBIC)
            heatmap = heatmap[:imageToTest_padded.shape[0] - pad[2], :imageToTest_padded.shape[1] - pad[3], :]
            heatmap = cv2.resize(heatmap, (ori_img.shape[1], ori_img.shape[0]), interpolation=cv2.INTER_CUBIC)

            # paf = np.transpose(np.squeeze(net.blobs[output_blobs.keys()[0]].data), (1, 2, 0))  # output 0 is PAFs
            paf = np.transpose(np.squeeze(Mconv7_stage6_L1), (1, 2, 0))  # output 0 is PAFs
            paf = cv2.resize(paf, (0, 0), fx=stride, fy=stride, interpolation=cv2.INTER_CUBIC)
            paf = paf[:imageToTest_padded.shape[0] - pad[2], :imageToTest_padded.shape[1] - pad[3], :]
            paf = cv2.resize(paf, (ori_img.shape[1], ori_img.shape[0]), interpolation=cv2.INTER_CUBIC)

            heatmap_avg += heatmap_avg + heatmap / len(multiplier)
            paf_avg += + paf / len(multiplier)

        all_peaks = []
        peak_counter = 0

        for part in range(18):
            map_ori = heatmap_avg[:, :, part]
            one_heatmap = gaussian_filter(map_ori, sigma=3)

            map_left = np.zeros(one_heatmap.shape)
            map_left[1:, :] = one_heatmap[:-1, :]
            map_right = np.zeros(one_heatmap.shape)
            map_right[:-1, :] = one_heatmap[1:, :]
            map_up = np.zeros(one_heatmap.shape)
            map_up[:, 1:] = one_heatmap[:, :-1]
            map_down = np.zeros(one_heatmap.shape)
            map_down[:, :-1] = one_heatmap[:, 1:]

            peaks_binary = np.logical_and.reduce(
                (one_heatmap >= map_left, one_heatmap >= map_right, one_heatmap >= map_up,
                 one_heatmap >= map_down, one_heatmap > threshold1))
            peaks = list(zip(np.nonzero(peaks_binary)[1], np.nonzero(peaks_binary)[0]))  # note reverse
            peaks_with_score = [x + (map_ori[x[1], x[0]],) for x in peaks]
            peak_id = range(peak_counter, peak_counter + len(peaks))
            peaks_with_score_and_id = [peaks_with_score[i] + (peak_id[i],) for i in range(len(peak_id))]

            all_peaks.append(peaks_with_score_and_id)
            peak_counter += len(peaks)

        # find connection in the specified sequence, center 29 is in the position 15
        limbSeq = [[2, 3], [2, 6], [3, 4], [4, 5], [6, 7], [7, 8], [2, 9], [9, 10],
                   [10, 11], [2, 12], [12, 13], [13, 14], [2, 1], [1, 15], [15, 17],
                   [1, 16], [16, 18], [3, 17], [6, 18]]
        # the middle joints heatmap correspondence
        mapIdx = [[31, 32], [39, 40], [33, 34], [35, 36], [41, 42], [43, 44], [19, 20], [21, 22],
                  [23, 24], [25, 26], [27, 28], [29, 30], [47, 48], [49, 50], [53, 54], [51, 52],
                  [55, 56], [37, 38], [45, 46]]

        connection_all = []
        special_k = []
        mid_num = 10

        for k in range(len(mapIdx)):
            score_mid = paf_avg[:, :, [x - 19 for x in mapIdx[k]]]
            candA = all_peaks[limbSeq[k][0] - 1]
            candB = all_peaks[limbSeq[k][1] - 1]
            nA = len(candA)
            nB = len(candB)
            # indexA, indexB = limbSeq[k]
            if nA != 0 and nB != 0:
                connection_candidate = []
                for i in range(nA):
                    for j in range(nB):
                        vec = np.subtract(candB[j][:2], candA[i][:2])
                        norm = math.sqrt(vec[0] * vec[0] + vec[1] * vec[1])
                        norm = max(0.001, norm)
                        vec = np.divide(vec, norm)

                        startend = list(zip(np.linspace(candA[i][0], candB[j][0], num=mid_num),
                                            np.linspace(candA[i][1], candB[j][1], num=mid_num)))

                        vec_x = np.array([score_mid[int(round(startend[index][1])), int(round(startend[index][0])), 0]
                                          for index in range(len(startend))])
                        vec_y = np.array([score_mid[int(round(startend[index][1])), int(round(startend[index][0])), 1]
                                          for index in range(len(startend))])

                        score_midpts = np.multiply(vec_x, vec[0]) + np.multiply(vec_y, vec[1])
                        score_with_dist_prior = sum(score_midpts) / len(score_midpts) + min(
                            0.5 * ori_img.shape[0] / norm - 1, 0)
                        criterion1 = len(np.nonzero(score_midpts > threshold2)[0]) > 0.8 * len(score_midpts)
                        criterion2 = score_with_dist_prior > 0
                        if criterion1 and criterion2:
                            connection_candidate.append(
                                [i, j, score_with_dist_prior, score_with_dist_prior + candA[i][2] + candB[j][2]])

                connection_candidate = sorted(connection_candidate, key=lambda x: x[2], reverse=True)
                connection = np.zeros((0, 5))
                for c in range(len(connection_candidate)):
                    i, j, s = connection_candidate[c][0:3]
                    if i not in connection[:, 3] and j not in connection[:, 4]:
                        connection = np.vstack([connection, [candA[i][3], candB[j][3], s, i, j]])
                        if len(connection) >= min(nA, nB):
                            break

                connection_all.append(connection)
            else:
                special_k.append(k)
                connection_all.append([])

        # last number in each row is the total parts number of that person
        # the second last number in each row is the score of the overall configuration
        subset = -1 * np.ones((0, 20))
        candidate = np.array([item for sublist in all_peaks for item in sublist])

        for k in range(len(mapIdx)):
            if k not in special_k:
                partAs = connection_all[k][:, 0]
                partBs = connection_all[k][:, 1]
                indexA, indexB = np.array(limbSeq[k]) - 1

                for i in range(len(connection_all[k])):  # = 1:size(temp,1)
                    found = 0
                    subset_idx = [-1, -1]
                    for j in range(len(subset)):  # 1:size(subset,1):
                        if subset[j][indexA] == partAs[i] or subset[j][indexB] == partBs[i]:
                            subset_idx[found] = j
                            found += 1

                    if found == 1:
                        j = subset_idx[0]
                        if subset[j][indexB] != partBs[i]:
                            subset[j][indexB] = partBs[i]
                            subset[j][-1] += 1
                            subset[j][-2] += candidate[partBs[i].astype(int), 2] + connection_all[k][i][2]
                    elif found == 2:  # if found 2 and disjoint, merge them
                        j1, j2 = subset_idx
                        membership = ((subset[j1] >= 0).astype(int) + (subset[j2] >= 0).astype(int))[:-2]
                        if len(np.nonzero(membership == 2)[0]) == 0:  # merge
                            subset[j1][:-2] += (subset[j2][:-2] + 1)
                            subset[j1][-2:] += subset[j2][-2:]
                            subset[j1][-2] += connection_all[k][i][2]
                            subset = np.delete(subset, j2, 0)
                        else:  # as like found == 1
                            subset[j1][indexB] = partBs[i]
                            subset[j1][-1] += 1
                            subset[j1][-2] += candidate[partBs[i].astype(int), 2] + connection_all[k][i][2]

                    # if no partA is found in the subset, create a new subset
                    elif not found and k < 17:
                        row = -1 * np.ones(20)
                        row[indexA] = partAs[i]
                        row[indexB] = partBs[i]
                        row[-1] = 2
                        row[-2] = sum(candidate[connection_all[k][i, :2].astype(int), 2]) + connection_all[k][i][2]
                        subset = np.vstack([subset, row])
        # delete some rows of subset which has few parts occur
        deleteIdx = []
        for i in range(len(subset)):
            if subset[i][-1] < 4 or subset[i][-2] / subset[i][-1] < 0.4:
                deleteIdx.append(i)
        subset = np.delete(subset, deleteIdx, axis=0)

        # subset: n*20 array, 0-17 is the index in candidate, 18 is the total score, 19 is the total parts
        # candidate: x, y, score, id
        return candidate, subset


def get_pose_json(ori_img):
    height, width, channels = ori_img.shape

    candidate, subset = body_estimation(ori_img)

    if len(candidate) == 0 or len(subset) == 0:
        print("No poses found in the input image.")
        return None

    candidate_int = candidate.astype(int)
    candidate_list = candidate_int[:, :2].tolist()

    data = {
        "width": width,
        "height": height,
        "keypoints": candidate_list
    }
    candidate_json = json.dumps(data)

    return candidate_json


def process_image(this_input_image, the_body_estimation, these_args):
    output_filename = '.'.join(this_input_image.split('.')[:-1]) + '.openpose.png'
    if os.path.isfile(output_filename) and not args.force:
        print(f"Output file {output_filename} already exists, skipping {this_input_image}")
        return

    ori_img = cv2.imread(this_input_image)  # B,G,R order
    # height, width, channels = ori_img.shape

    try:
        candidate, subset = the_body_estimation(ori_img)
    except Exception as e:
        print(f"Error processing image {input_image}: {e}")
        return

    if len(candidate) == 0 or len(subset) == 0:
        print(f"No poses found in the input image {input_image}.")
        return

    if these_args.json_output:
        candidate_json = get_pose_json(ori_img)
        output_filename = '.'.join(input_image.split('.')[:-1]) + '.openpose.json'
        with open(output_filename, 'w') as f:
            f.write(candidate_json)

    canvas = np.zeros_like(ori_img)
    canvas.fill(0)
    canvas = util.draw_bodypose(canvas, candidate, subset)

    cv2.imwrite(output_filename, canvas)

    if these_args.show_image:
        plt.imshow(canvas[:, :, [2, 1, 0]])
        plt.show()


if __name__ == "__main__":

    parser = argparse.ArgumentParser(description='Body Pose Estimation using OpenPose', add_help=True)
    group = parser.add_mutually_exclusive_group(required=True)
    group.add_argument("-i", "--input_image", help="Path to the input image", type=str)
    group.add_argument("-d", "--directory", help="Directory to search for images", type=str)
    parser.add_argument("-p", "--patterns", help="Pattern to match for images in directory", type=str)
    parser.add_argument("-r", "--recursive", help="Search for files in subdirectories recursively",
                        action="store_true")
    parser.add_argument("-s", "--show_image", help="Display the output image", action="store_true")
    parser.add_argument("-j", "--json_output", help="Save JSON output to file", action="store_true")
    parser.add_argument("-f", "--force", help="Force processing of images even if output file already exists",
                        action="store_true")
    args = parser.parse_args()

    script_path = os.path.abspath(__file__)
    script_dir = os.path.dirname(script_path)

    model_dir = os.path.join(script_dir, "model")
    os.makedirs(model_dir, exist_ok=True)

    model_path = os.path.join(model_dir, "body_pose_model.pth")

    if not os.path.isfile(model_path):
        body_model_path = \
            "https://huggingface.co/lllyasviel/ControlNet/resolve/main/annotator/ckpts/body_pose_model.pth"
        urllib.request.urlretrieve(body_model_path, model_path)

    body_estimation = Body(model_path)

    if args.input_image:
        images = [args.input_image]
    else:
        patterns = args.patterns.split(',')
        for pattern in patterns:
            for input_image in glob.iglob(os.path.join(args.directory, '**', pattern)
                                          if args.recursive else os.path.join(args.directory, pattern),
                                          recursive=args.recursive):
                print(f"Processing {input_image}")
                process_image(input_image, body_estimation, args)