import xml.etree.ElementTree as ET

import pickle
import os
from os import listdir, getcwd
from os.path import join
import glob

classes = ['crazing', 'inclusion', 'patches', 'pitted_surface', 'rolled-in_scale', 'scratches']  # xml文件中标记的种类


def convert(size, box):
    dw = 1.0 / size[0]
    dh = 1.0 / size[1]
    x = (box[0] + box[1]) / 2.0
    y = (box[2] + box[3]) / 2.0
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x * dw
    w = w * dw
    y = y * dh
    h = h * dh
    return (x, y, w, h)


def convert_annotation(image_name):
    try:
        in_file = open('../dataset/annotations/val/' + image_name[:-3] + 'xml', encoding='utf-8')  # 原来的xml文件路径
    except FileNotFoundError:
        print(f"Warning: XML file for {image_name} not found, skipping.")
        return

    out_file = open('../dataset/labels/val/' + image_name[:-3] + 'txt', 'w', encoding='utf-8')  # 转换后的txt文件存放路径
    tree = ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)

    for obj in root.iter('object'):
        difficult = obj.find('difficult').text
        cls = obj.find('name').text
        if cls not in classes or int(difficult) == 1:
            continue
        cls_id = classes.index(cls)
        xmlbox = obj.find('bndbox')
        b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),
             float(xmlbox.find('ymax').text))
        bb = convert((w, h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
    in_file.close()
    out_file.close()


wd = getcwd()

if __name__ == '__main__':

    for image_path in glob.glob("../dataset/images/val/*.jpg"):  # xml对应的图片的路径
        image_name = image_path.split('\\')[-1]
        convert_annotation(image_name)