pdf_title_image/tech_instance.py

# -*- coding: utf-8 -*-
# @Author: privacy
# @Date:   2024-06-11 13:43:14
# @Last Modified by:   privacy
# @Last Modified time: 2024-09-05 16:29:06
# 技术部分定位
from typing import List
from celery_tasks.text_extractor import similar_match


def tech_loc(scrutinize_dict: dict, outline_dict: List[dict], supplier: str):
    """
    投标技术部分定位
    Args:
        scrutinize_dict: 详细评审
        outline_dict:   投标文件大纲
    """
    targets = []
    part = None
    for key in scrutinize_dict.keys():
        if '技术' in key:
            part = key
            break

    if not part:
        return None

    for ins in scrutinize_dict[key]:
        inst = ins['评分因素']
        text = ins['评分标准']
        weig = ins['权重']
        t = []
        for i in text.split('。'):
            for j in i.split('；'):
                for k in j.split('，'):
                    t.append(k)
        targets.append({
            'title': inst,
            'text': t,
            'weight': weig
        })

    result = {
        'scoringCriteria': [],
        '标准': []
    }
    for i in targets:
        try:
            title_sims = similar_match(outline_dict, [i['title']], key='title')
        except Exception as e:
            print(supplier)
            raise(e)
        result['scoringCriteria'].append({
            'scoringFactors': i['title'],
            'scoringStandard': i['text'],
            'percentage': i['weight'],
            'suppliers': [{
                'name': supplier,
                'grade': 'B',
                'supplier': '总体服务方案的概括文字(200字以内)',
                'pages': title_sims
            }]
        })

        # text_sims = similar_match(outline_dict, i['text'], key='title')
        # for j in range(len(text_sims)):
        #     result['标准'].append({
        #         '评分标准': i['text'][j],
        #         '定位结果': text_sims[j]
        #     })

    return result


if __name__ == '__main__':
    import json
    from glob import glob
    from pprint import pprint
    with open('bidding_dataset.json', 'r', encoding='utf-8') as fp:
        scrutinizes = json.load(fp)
    for project in scrutinizes.keys():
        scrutinize_dict = scrutinizes[project]
        for file in glob(f'./data/0预审查初审详审测试数据/{project}/*/*-outline.json'):
            with open(file, 'r', encoding='utf-8') as fp:
                outline_dict = json.load(fp)
            supplier = file.split('\\')[-2]
            pprint(
                tech_loc(scrutinize_dict=scrutinize_dict, outline_dict=outline_dict, supplier=supplier)
            )