pdf_title_image/busi_instance.py

# -*- coding: utf-8 -*-
# @Author: privacy
# @Date:   2024-08-30 11:17:21
# @Last Modified by:   privacy
# @Last Modified time: 2024-09-26 14:32:39

"""
商务部分
"""
import re
from typing import List, Optional

from celery_tasks.LLMAgent import get_proj
from celery_tasks.project_loc import extract_project
from celery_tasks.text_extractor import similar_match
from celery_tasks.extract_financial_report import extract_financial_report


def get_score(comment: str, standard: str):
    if re.findall(r'A~D|A～D|A、B、C', standard):
        try:
            return re.findall('([A-D])级', comment).pop()
        except Exception:
            return 'B'
    elif re.findall(r'\d+\s?分', standard):
        try:
            return re.findall(r'(\d+)\s?分', comment).pop()
        except Exception:
            return "60"


def busi_loc(scrutinize_dict: dict, outline_dict: List[dict], title_list: List[dict], table_list: List[dict], image_list: List[dict], supplier: str, project: str = None, file_name: str = None) -> Optional[List[dict]]:
    """
    投标商务部分定位

    Args:
        scrutinize_dict:   详细评审
        tender_file:    投标文件
    Returns:
        result: 商务部分详审结果
    """
    part = None
    # 从详审大纲中获取商务评分方法
    for key in scrutinize_dict.keys():
        if '商务' in key:
            part = key
            break

    # 没有找到商务评审方法则直接返回
    if not part:
        return None

    result = {
        'scoringCriteria': []
    }

    for item in scrutinize_dict[key]:
        if '信用' in item['评分因素']:
            result['scoringCriteria'].append({
                'scoringFactors': item['评分因素'],
                'scoringStandard': item['评分标准'],
                'percentage': item['权重'],
                'suppliers': [{
                    'name': supplier,
                    'grade': get_score(comment="B级（70分）", standard=item['评分标准']),
                    'pages': []
                }]
            })
        elif '业绩' in item['评分因素']:
            # 项目业绩表查询
            proj_list = extract_project(table_list, instances=['合同金额', '合同价格', '发包人名称', '项目规模', '合同时间'])
            # 定位信息格式化
            title_sims = [{'fileName': file_name, 'pageKey': '', 'pageStart': str(proj['page_numbers'][-1]), 'pageEnd': str(proj['page_numbers'][-1])} for proj in proj_list]
            # # 打分
            comment = get_proj(input_json=proj_list, standard=item['评分标准'])
            # 结果回传
            result['scoringCriteria'].append({
                'scoringFactors': item['评分因素'],
                'scoringStandard': item['评分标准'],
                'percentage': item['权重'],
                'suppliers': [{
                    'name': supplier,
                    'grade': get_score(comment=comment, standard=item['评分标准']),
                    'pages': title_sims
                }]
            })
        elif '财务' in item['评分因素']:
            financial_list = extract_financial_report(
                title_list=title_list,
                table_list=table_list,
                image_list=image_list,
                year=2022
            )

            title_sims = []
            starts = []

            for _ in financial_list:
                for page in _['pages']:
                    starts.append(page[0])

            for page in set(starts):
                title_sims.append({
                    "fileName": file_name,
                    "pageKey": "",
                    "pageEnd": page,
                    "pageStart": page,
                })

            result['scoringCriteria'].append({
                'scoringFactors': item['评分因素'],
                'scoringStandard': item['评分标准'],
                'percentage': item['权重'],
                'suppliers': [{
                    'name': supplier,
                    'grade': 'B',
                    'supplier': '3个关键的财务指标',
                    'pages': title_sims
                }]
            })
        elif '报价' in item['评分因素']:
            result['scoringCriteria'].append({
                'scoringFactors': item['评分因素'],
                'scoringStandard': item['评分标准'],
                'percentage': item['权重'],
                'suppliers': [{
                    'name': supplier,
                    'grade': 'B',
                    'pages': []
                }]
            })
        elif '完整性' in item['评分因素']:
            result['scoringCriteria'].append({
                'scoringFactors': item['评分因素'],
                'scoringStandard': item['评分标准'],
                'percentage': item['权重'],
                'suppliers': [{
                    'name': supplier,
                    'grade': 'B',
                    'pages': []
                }]
            })
        elif '涉密' in item['评分因素']:
            result['scoringCriteria'].append({
                'scoringFactors': item['评分因素'],
                'scoringStandard': item['评分标准'],
                'percentage': item['权重'],
                'suppliers': [{
                    'name': supplier,
                    'grade': get_score(comment="A级（100分）", standard=item['评分标准']),
                    'pages': []
                }]
            })
        else:
            title_sims = similar_match(outline_dict, [item['评分因素']], key='title')

            pages = [{'fileName': file_name, 'pageStart': str(sim['page_number']), 'pageEnd': str(sim['page_number']), 'pageKey': '', 'text': sim['title'], 'score': sim['相似度']} for sim in title_sims]

            result['scoringCriteria'].append({
                'scoringFactors': item['评分因素'],
                'scoringStandard': item['评分标准'],
                'percentage': item['权重'],
                'suppliers': [{
                    'name': supplier,
                    'grade': get_score(comment="B级（70分）", standard=item['评分标准']),
                    'pages': pages,
                }]
            })

    return result


if __name__ == '__main__':
    import os
    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)
            if outline_dict == []:
                os.remove(file)
                continue
            with open(file.replace('outline.json', 'title.json'), 'r', encoding='utf-8') as fp:
                title_list = json.load(fp)
            with open(file.replace('outline.json', 'table.json'), 'r', encoding='utf-8') as fp:
                table_list = json.load(fp)
            with open(file.replace('outline.json', 'image.json'), 'r', encoding='utf-8') as fp:
                image_list = json.load(fp)

            supplier = file.split('\\')[-2]

            pprint(
                busi_loc(
                    scrutinize_dict=scrutinize_dict,
                    outline_dict=outline_dict,
                    title_list=title_list,
                    table_list=table_list,
                    image_list=image_list,
                    supplier=supplier,
                    project=project,
                    file_name=file
                )
            )
            exit(0)