zbparse/flask_app/货物标/基础信息解析货物标版.py

# -*- encoding:utf-8 -*-
import json
import threading
import time
import concurrent.futures
from flask_app.general.json_utils import clean_json_string, add_outer_key
from flask_app.general.通用功能函数 import process_judge_questions, aggregate_basic_info
from flask_app.general.多线程提问 import read_questions_from_file, multi_threading
from flask_app.general.通义千问long import upload_file
from flask_app.工程标.判断是否分包等 import merge_json_to_list
from flask_app.general.投标人须知正文提取指定内容 import extract_from_notice
from flask_app.货物标.提取采购需求main import fetch_procurement_reqs


def get_base_info(merged_baseinfo_path,clause_path):
    file_id = upload_file(merged_baseinfo_path)
    baseinfo_file_path='flask_app/static/提示词/基本信息货物标.txt'
    # baseinfo_file_path = r'D:\flask_project\flask_app\static\提示词\基本信息货物标.txt'
    questions = read_questions_from_file(baseinfo_file_path)
    more_query = "请你根据招标文件信息，回答以下问题：是否组织踏勘现场？是否召开投标预备会（或投标答疑会）？是否退还投标文件？是否允许分包? 是否需要递交投标保证金（或磋商保证金）？是否需要提交履约保证金（或履约担保）？是否有招标代理服务费（或中标、成交服务费或采购代理服务费）？请按json格式给我提供信息，键名分别为'是否组织踏勘现场','是否召开投标预备会'（或'是否召开投标答疑会'）,'是否退还投标文件',是否允许分包','是否递交投标保证金'（或'是否递交磋商保证金'）,'是否提交履约保证金','是否有招标代理服务费',键值仅限于'是','否','未知',若存在矛盾信息，请回答'未知'。"
    questions.append(more_query)
    baseinfo_results = multi_threading(questions, "", file_id, 2)  # 1代表使用百炼rag 2代表使用qianwen-long
    baseinfo_list = [clean_json_string(res) for _, res in baseinfo_results] if baseinfo_results else []
    chosen_numbers, merged = merge_json_to_list(baseinfo_list.pop())
    baseinfo_list.append(merged)
    judge_file_path = 'flask_app/static/提示词/是否相关问题.txt'
    # judge_file_path =r'D:\flask_project\flask_app\static\提示词\是否相关问题.txt'
    with concurrent.futures.ThreadPoolExecutor(max_workers=2) as executor:
        # 提交两个任务
        future1 = executor.submit(process_judge_questions, judge_file_path, chosen_numbers, file_id,
                                  baseinfo_list)
        future2 = executor.submit(extract_from_notice, merged_baseinfo_path, clause_path, 3)  # 新增的多线程任务

        # 等待两个任务完成并获取结果
        future1.result()  # process_judge_questions 直接修改 baseinfo_list，不需要返回值
        rebidding_situation = future2.result()
    update_json = add_outer_key(rebidding_situation, "重新招标、不再招标和终止招标")
    baseinfo_list.append(update_json)
    return baseinfo_list

def combine_basic_info(merged_baseinfo_path, procurement_path,clause_path,invalid_path):
    baseinfo_list = []
    temp_list = []
    procurement_reqs = {}
    # 定义一个线程函数来获取基础信息
    def get_base_info_thread():
        nonlocal temp_list
        temp_list = get_base_info(merged_baseinfo_path,clause_path)
    # 定义一个线程函数来获取采购需求
    def fetch_procurement_reqs_thread():
        nonlocal procurement_reqs
        procurement_reqs = fetch_procurement_reqs(procurement_path,invalid_path)
    # 创建并启动获取基础信息的线程
    thread1 = threading.Thread(target=get_base_info_thread)
    thread1.start()
    # 等待一秒后启动获取采购需求的线程
    time.sleep(1)
    thread2 = threading.Thread(target=fetch_procurement_reqs_thread)
    thread2.start()
    # 等待两个线程都完成
    thread1.join()
    thread2.join()
    # 合并结果
    baseinfo_list += temp_list  # temp_list 是一个列表
    baseinfo_list.append(procurement_reqs)  # procurement_reqs 是一个字典
    aggregated_baseinfo = aggregate_basic_info(baseinfo_list,'goods')

    return {"基础信息": aggregated_baseinfo}


if __name__ == "__main__":
    start_time=time.time()
    # baseinfo_file_path = "C:\\Users\\Administrator\\Desktop\\货物标\\truncate_all\\ztbfile_merged_baseinfo\\ztbfile_merged_baseinfo_3-31.pdf"
    merged_baseinfo_path=r"D:\flask_project\flask_app\static\output\output1\eabefc28-142f-4bb5-b1be-e86e43bb87b5\invalid_del.docx"
    # procurement_file_path = "C:\\Users\\Administrator\\Desktop\\fsdownload\\b4601ea1-f087-4fa2-88ae-336ad4d8e1e9\\tmp\\ztbfile_procurement.pdf"
    procurement_file_path = r"D:\flask_project\flask_app\static\output\output1\83ae3e35-9136-4402-a74f-01d7adfcbb73\invalid_added.docx"
    clause_path='D:\\flask_project\\flask_app\\static\\output\\output1\\bf225a5e-16d0-45c8-8c19-54a1a94cf3e2\\clause1.json'
    # res = combine_basic_info(merged_baseinfo_path, procurement_file_path,clause_path)
    res=get_base_info(merged_baseinfo_path,"")
    print("------------------------------------")
    print(json.dumps(res, ensure_ascii=False, indent=4))
    end_time=time.time()
    print("elasped time:"+str(end_time-start_time))