# -*- coding:utf-8 -*-
# 開發(fā)人員 : csu·攀-_-||
# 開發(fā)時間 : 2021/9/7 0007 10:30
# 文件名稱 : pplable2json.py
# 開發(fā)工具 : PyCharm
# 功能描述 : PPOCRLabel標注的txt格式轉換成labelme能修改的json格式

import os
import cv2
import json
import base64

#轉base64
def image_to_base64(image_np):
    image = cv2.imencode('.jpg', image_np)[1]
    image_code = str(base64.b64encode(image))[2:-1]
    return image_code

def pp2json(path,savepath):
    with open(os.path.join(path,'Label.txt'),'r',encoding='utf-8') as f:
        for line in f.readlines():
            line = line.strip('\n')  # 去掉列表中每一個元素的換行符
            imgname = line.split('\t')[0].split('/')[1]
            img = cv2.imread(os.path.join(path,imgname))
            H,W,C = img.shape
            items = json.loads(line.split('\t')[1])
            item_shapes = []
            for item in items:
                item_shapes.append({
                    "label":item['transcription'],
                    "points":item['points'],
                    "group_id": 0,
                    "shape_type": "polygon",
                    "flags": {}
                })
            new_dict = {
                "version": "4.5.9",
                "flags": {},
                "shapes": item_shapes,
                "imagePath": imgname,
                "imageData": image_to_base64(img),
                "imageHeight": H,
                "imageWidth": W
            }
            with open(os.path.join(savepath,imgname.split('.')[0] + '.json'), "w",encoding='utf-8') as fw:
                print(imgname,' succeed!')
                json.dump(new_dict, fw)


if __name__ == '__main__':
    path = r'E:\Projects\OCR-release-2.1\tools\infer\imgs\train_data'
    savepath = r'json1'
    pp2json(path,savepath)