from scipy.io import loadmat
import  glob,os
import  xml.dom.minidom
from tqdm import tqdm
from creat_xml_fordetection import make_xml_iccv
den_path = "../data_MPKFNet/data/VOC/VOCdevkit/VOCiccvtrain/ground_truth/"
voc_path = "../data_MPKFNet/data/VOC/VOCdevkit/VOCiccvtrain/Annotations/"
save_path = "../data_MPKFNet/data/VOC/VOCdevkit/VOCiccvtrain/Bird_detection/"
def get_mat_point (path):
    mat_data = loadmat(path)
    positions = mat_data['image_info'][0, 0][0, 0][0]
    count = mat_data['image_info'][0][0][0][0][1][0][0]
    return  positions
def get_xml_box (path):
    dom = xml.dom.minidom.parse(path)
    objects = dom.getElementsByTagName("object")
    all_boxes = []
    for object in objects:
        bndbox = object.getElementsByTagName('bndbox')[0]
        xmin = bndbox.getElementsByTagName('xmin')[0]
        ymin = bndbox.getElementsByTagName('ymin')[0]
        xmax = bndbox.getElementsByTagName('xmax')[0]
        ymax = bndbox.getElementsByTagName('ymax')[0]

        xmin_data = int(xmin.childNodes[0].data)
        ymin_data = int(ymin.childNodes[0].data)
        xmax_data = int(xmax.childNodes[0].data)
        ymax_data = int(ymax.childNodes[0].data)
        all_boxes.append((xmin_data,ymin_data,xmax_data,ymax_data))
    sizes = dom.getElementsByTagName("size")
    for size in sizes:
        w = size.getElementsByTagName('width')[0]
        w_data = int(w.childNodes[0].data)
        h = size.getElementsByTagName('height')[0]
        h_data = int(h.childNodes[0].data)

    return all_boxes ,w_data,h_data

def point_in_box (site,box):
    flag = False
    if (site[0]>=box[0]) and (site[0]<=box[2]) and (site[1]>=box[1]) and (site[1]<=box[3]):
        flag = True
    return flag

def ifsame_box(site1,site2,box):
    centerx = (box[0]+box[2])/2
    centery = (box[1]+box[3])/2
    dis1 =  ((site1[0]-centerx)*(site1[0]-centerx) +(site1[1]-centery)*(site1[1]-centery))**0.5
    dis2 = ((site2[0] - centerx) * (site2[0] - centerx) + (site2[1] - centery) * (site2[1] - centery))**0.5
    if dis1>dis2:
        flag = True
    else:
        flag = False
    return flag
def get_new(site,boxes,img_w,img_h):
    min_dis = 10e10
    min_index = 0
    for i in range(len(boxes)):
        centerx = (boxes[i][0] + boxes[i][2]) / 2
        centery = (boxes[i][1] + boxes[i][3]) / 2
        dis = ((site[0]-centerx)*(site[0]-centerx) +(site[1]-centery)*(site[1]-centery))**0.5
        if dis < min_dis:
            min_dis = dis
            min_index = i
    w = (boxes[min_index][2]-boxes[min_index][0])/2
    h = (boxes[min_index][3]-boxes[min_index][1])/2
    xmin = site[0]-w
    if xmin <0:
        xmin =0
    xmax = site[0]+w
    if xmax >img_w:
        xmax = img_w-1
    ymin = site[1]-h
    if ymin<0:
        ymin = 0
    ymax = site[1]+h
    if ymax >img_h:
        ymax = img_h-1
    return ((xmin,ymin,xmax,ymax))





if __name__ == '__main__':
    xml_lists = os.listdir(voc_path)
    for xml_path in tqdm(xml_lists) :
        print(xml_path+"is doing")
        mat_path = xml_path.replace(".xml",".mat").replace("HatIMG","GT_HatIMG")
        ALL_points = get_mat_point(den_path+mat_path)
        ALl_boxes, image_W,image_H = get_xml_box (voc_path+xml_path)
        ALL_point_box = []   #点对应的边框的编号
        No_Label_point = []
        Yes_Label_point = []
        Yes_Box_index = []
        ###############步1  完成对ALL_point的所有点的遍历，寻找每个点对应的box在ALL_boxes中的索引，最终得到一个list ALL_point_box 代表每个点对应的box的索引，没有的是100000
        for i in range(len(ALL_points)):
            ALL_point_box.append(100000)
            for j in range(len(ALl_boxes)):
                if point_in_box(ALL_points[i],ALl_boxes[j]): #判断是否在边框里面，是的话就将边框的编号放到点对应边框的数组里面，否则该点对应的边框为100000
                    ALL_point_box[i]=j
                    break
        #########################################步2.1 筛选出来准标注的和未标注的
        for i in range(len(ALL_point_box)):
            if ALL_point_box[i]==100000:
                No_Label_point.append(ALL_points[i])

            else:
                 Yes_Label_point.append(ALL_points[i])
                 Yes_Box_index.append(ALL_point_box[i])
        ###################步2.2对已标记的点进行遍历，去除掉具有重复边框的点
        for i in range(5):
            for i in range(len(Yes_Label_point)):
                if i >= len(Yes_Label_point):
                    break
                else:
                    for j in range(i+1,len(Yes_Label_point)):
                        #print(len(Yes_Label_point))
                        if j >= len(Yes_Label_point):
                            break
                        else:
                            if Yes_Box_index[i] == Yes_Box_index[j]:    #当前点和遍历点是一样的

                                if ifsame_box(Yes_Label_point[i],Yes_Label_point[j],ALl_boxes[Yes_Box_index[i]]):
                                    No_Label_point.append(Yes_Label_point[j])
                                    del Yes_Label_point[j]
                                    Yes_Box_index.remove(Yes_Box_index[j])
                                else:
                                    No_Label_point.append(Yes_Label_point[i])
                                    del Yes_Label_point[i]
                                    Yes_Box_index.remove(Yes_Box_index[i])
                                    break
        ##########步3推理未标记的点的边框信息 对No_Laber_point进行遍历
        final_boxes = ALl_boxes
        for i in range(len(No_Label_point)):
            final_boxes.append(get_new(No_Label_point[i],ALl_boxes,image_W,image_H))
        #########步4存储为xml
        make_xml_iccv(xml_path.replace(".xml",".jpg"),image_H,image_W,final_boxes,save_path+xml_path)

    print(final_boxes)