test_script/YQ_OCR/to_md/convert_MD.py

import copy
import re
from itertools import chain
from pathlib import Path

import numpy as np
import pandas as pd
import json
from mdutils.mdutils import MdUtils
import requests

from YQ_OCR.config import keyDict

url = 'http://192.168.199.107:18087'
url_path = '/ocr_system/identify'
imgs_path = '/Users/zeke/work/sx/OCR/HROCR/to_md/YQ_OCR/img'


# 1. xlsx -> 正确json文件(写入厂家信息)
# 2. 发送图片(带正确json文件)
# 3. 把返回的json 和正确的json 进行对比(有key--用返回结果与正确结果比对,无key--用正确结果与返回结果比对)

# 编辑距离
def Levenshtein_Distance(str1, str2):
    matrix = [[i + j for j in range(len(str2) + 1)] for i in range(len(str1) + 1)]
    for i in range(1, len(str1) + 1):
        for j in range(1, len(str2) + 1):
            d = 0 if (str1[i - 1] == str2[j - 1]) else 1
            matrix[i][j] = min(matrix[i - 1][j] + 1, matrix[i][j - 1] + 1, matrix[i - 1][j - 1] + d)
    return matrix[len(str1)][len(str2)]


# 发送请求 带正确答案参数
def send_request(img_path: Path, img_json: str):
    file = {'file': (img_path.name, open(img_path, 'rb'), img_path)}
    payload = {'docDataStr': img_json}
    r = requests.post(url + url_path, files=file, data=payload)
    return r.json()


# 处理返回结果
def _parse_result(r):  # sourcery skip: dict-comprehension
    if r['status'] == '000':
        result = r['result']
        res = {}
        for field in keyDict:
            if field in result:
                res[field] = result[field]
        res['noKeyList'] = result['noKeyList']
        res['logoList'] = result['logoList']
        logoFileName = [log['logoFileName'] for log in res['logoList']]
        res['logoList'] = logoFileName
        return res
    elif r['status'] == '101':
        return "101"


# 比较两个json文件 并在md文件中写入对比结果
def evaluate_one(xlsx_dict, res_dict):
    true_num = 0
    xlsx_dict_no_space = copy.deepcopy(xlsx_dict)
    for index, text in enumerate(xlsx_dict_no_space):
        xlsx_dict_no_space[index] = text.replace(' ', '')
    for key_yes in res_dict:
        if type(res_dict[key_yes]) is str:
            if Levenshtein_Distance(res_dict[key_yes], xlsx_dict_no_space[key_yes]) == 0:
                table_result.extend([key_yes, xlsx_dict[key_yes], res_dict[key_yes], '✅'])
                true_num += 1
            else:
                table_result.extend([key_yes, xlsx_dict[key_yes], res_dict[key_yes], '❌'])

    key_no_dict = {}
    for key_no_xlsx in xlsx_dict_no_space['noKeyList']:
        key_no_dict[key_no_xlsx] = []
        for key_no_res in res_dict['noKeyList']:
            key_no_dict[key_no_xlsx].append((Levenshtein_Distance(key_no_xlsx, key_no_res), key_no_res))
        sort_NoKey = sorted(key_no_dict[key_no_xlsx], key=lambda x: x[0])
        NoKey_min_distance = sort_NoKey[0][0]
        if NoKey_min_distance == 0:
            table_result.extend(['无key值', key_no_xlsx, sort_NoKey[0][1], '✅'])
            true_num += 1
        else:
            table_result.extend(['无key值', key_no_xlsx, sort_NoKey[0][1], '❌'])
    rate = true_num / (len(table_result) / 4)
    all_rate.append(rate)
    statistics = f'共{len(table_result) // 4}个字段,正确{true_num}个,错误{len(table_result) // 4 - true_num}个'

    return "{:.2f}%".format(rate * 100), statistics


# 打开正确的json文件
def open_true_json(j_path):
    with j_path.open('r') as f:
        j_dict = json.load(f)
        j_json_str = json.dumps(j_dict, ensure_ascii=False)
        return j_dict, j_json_str


if __name__ == '__main__':
    img_paths = chain(*[Path(imgs_path).rglob(f'*.{ext}') for ext in ['jpg', 'png', 'jpeg', 'PNG', 'JPG', 'JPEG']])
    all_rate = []
    for img_path in img_paths:
        print(img_path)
        # json result
        true_d, true_json = open_true_json(img_path.with_suffix('.json'))
        result = send_request(img_path, true_json)
        res_d = _parse_result(result)
        # md
        md_file_path = img_path.parent / (img_path.with_suffix('.md'))
        MD = MdUtils(file_name=str(md_file_path))
        table_result = ['key值', '正确答案', 'ocr返回答案', '是否正确']
        rate, statistics = evaluate_one(true_d, res_d)
        MD.new_header(level=1, title='测试结果')
        MD.new_header(level=2, title=f'正确率：{rate}')
        MD.new_header(level=3, title=statistics)
        print(f'正确率：{rate}')
        MD.new_table(columns=4, rows=len(table_result) // 4, text=table_result, text_align='center')
        MD.create_md_file()

    print('-------------------------------')
    all_rate = "{:.2f}%".format(np.mean(all_rate) * 100)
    print(f'总体正确率：{all_rate}')