zbparse/flask_app/货物标/基础信息解析main.py

# -*- encoding:utf-8 -*-
import json
import threading
import time
import concurrent.futures
from flask_app.general.json_utils import clean_json_string, rename_outer_key
from flask_app.general.通用功能函数 import judge_consortium_bidding, process_judge_questions
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.main.判断是否分包等 import merge_json_to_list, read_questions_from_judge
from flask_app.货物标.投标人须知正文提取指定内容货物标版 import extract_from_notice
from flask_app.货物标.提取采购需求main import fetch_procurement_reqs


def aggregate_basic_info_goods(baseinfo_list):
    # for i in baseinfo_list:
    #     print(json.dumps(i,ensure_ascii=False,indent=4))
    """
    将基础信息列表中的数据进行合并和分类。

    参数：
    - baseinfo_list (list): 包含多个基础信息的列表。

    返回：
    - dict: 合并和分类后的基础信息字典。
    """
    key_groups = {
        "招标人/代理信息": ["招标人", "招标人联系方式", "招标代理机构", "招标代理机构联系方式","项目联系方式"],
        "项目信息": ["项目名称", "项目编号", "项目概况", "项目基本情况", "招标控制价", "投标竞争下浮率"],
        "采购要求": ["采购需求","技术要求","服务要求","商务要求","其他要求"],
        "关键时间/内容": [
            "投标文件递交截止日期",
            "开标时间",
            "开标地点",
            "澄清招标文件的截止时间",
            "投标有效期",
            "信息公示媒介"
        ],
        "保证金相关": ["质量保证金"],
        "其他信息": [
            "重新招标、不再招标和终止招标",
            "投标费用承担",
            "招标代理服务费",
            "是否退还投标文件"
        ]
    }

    combined_data = {}
    relevant_keys_detected = set()

    # 合并所有基础信息并收集相关键
    for baseinfo in baseinfo_list:
        combined_data.update(baseinfo)
        relevant_keys_detected.update(baseinfo.keys())

    # 动态调整键组
    dynamic_key_handling(key_groups, relevant_keys_detected)

    # 创建一个副本以存储未分类的项目
    unclassified_items = {k: v for k, v in combined_data.items() if
                          k not in [item for sublist in key_groups.values() for item in sublist]}

    # 按键组分类并嵌套
    for group_name, keys in key_groups.items():
        group_data = {key: combined_data.get(key, "未提供") for key in keys}
        combined_data[group_name] = group_data
        # 从 unclassified_items 中移除已分类的键
        for key in keys:
            unclassified_items.pop(key, None)

    # 将剩余未分类的键值对添加到 "其他信息" 组中
    combined_data["其他信息"].update(unclassified_items)

    # 移除顶层的未分类键值对
    for key in list(combined_data.keys()):
        if key not in key_groups:
            del combined_data[key]

    return combined_data

def dynamic_key_handling(key_groups, detected_keys):
    # 检查和调整键组配置
    for key in detected_keys:
        if "技术、服务要求" in detected_keys:
            # 如果检测到“技术、服务要求”，则移除“技术要求”和“服务要求”
            if "技术要求" in key_groups["采购要求"]:
                key_groups["采购要求"].remove("技术要求")
            if "服务要求" in key_groups["采购要求"]:
                key_groups["采购要求"].remove("服务要求")
            # 确保"技术、服务要求"存在于"采购要求"组中
            if "技术、服务要求" not in key_groups["采购要求"]:
                key_groups["采购要求"].insert(1, "技术、服务要求")
        else:
            # 如果不存在“技术、服务要求”，确保“技术要求”和“服务要求”都在"采购要求"组中
            if "技术要求" not in key_groups["采购要求"]:
                key_groups["采购要求"].insert(1, "技术要求")
            if "服务要求" not in key_groups["采购要求"]:
                key_groups["采购要求"].insert(2, "服务要求")
            # 移除"技术、服务要求"以保持互斥
            if "技术、服务要求" in key_groups["采购要求"]:
                key_groups["采购要求"].remove("技术、服务要求")
        # 处理“保证金相关”组
        if "保证金" in key:
            group = key_groups["保证金相关"]
            insert_before = "质量保证金"
            if insert_before in group:
                index = group.index(insert_before)
                if key not in group:  # 避免重复插入
                    group.insert(index, key)
            else:
                group.append(key)  # 如果没有找到特定键，则追加到末尾
        elif "联合体" in key:
            key_groups["项目信息"].append(key)
        elif "分包" in key:
            key_groups["项目信息"].append(key)
        elif "踏勘现场" in key:
            key_groups["其他信息"].append(key)
        elif "投标预备会" in key or "投标答疑会" in key:
            key_groups["其他信息"].append(key)
        elif "偏离" in key:
            key_groups["其他信息"].append(key)
        elif "递交方式" in key or "递交地点" in key:
            group = key_groups["关键时间/内容"]
            insert_after = "投标文件递交截止日期"
            if insert_after in group:
                index = group.index(insert_after)
                # 确保新键不重复
                if key not in group:
                    group.insert(index + 1, key)
            else:
                # 如果“投标文件递交截止日期”不存在，则追加到末尾
                if key not in group:
                    group.append(key)

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 = '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/是否相关问题货物标.txt'
    # judge_file_path ='D:\\flask_project\\flask_app\\static\\提示词\\是否相关问题货物标.txt'
    with concurrent.futures.ThreadPoolExecutor(max_workers=3) as executor:
        # 提交两个任务
        future1 = executor.submit(process_judge_questions, judge_file_path, chosen_numbers, merged_baseinfo_path,
                                  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 = rename_outer_key(rebidding_situation, "重新招标、不再招标和终止招标")
    baseinfo_list.append(update_json)

    # # judge_file_path = 'D:\\flask_project\\flask_app\\static\\提示词\\是否相关问题货物标.txt'
    # judge_questions = read_questions_from_judge(judge_file_path, chosen_numbers)
    # # print(judge_questions)
    # judge_consortium = judge_consortium_bidding(baseinfo_list)  # 通过招标公告判断是否接受联合体投标
    #
    # if judge_consortium:
    #     judge_consortium_question = (
    #         "该招标文件对于联合体投标的要求是怎样的，请按json格式给我提供信息，"
    #         "外层键名为'联合体投标要求'，其中有一个嵌套键值对为：\"是否接受联合体投标\":\"是\""
    #     )
    #     judge_questions.append(judge_consortium_question)
    # res2 = multi_threading(judge_questions, "", file_id, 2)  # 调用千问-long
    # if not res2:
    #     print("基础信息整合： multi_threading error!")
    # else:
    #     for question, response in res2:
    #         baseinfo_list.append(clean_json_string(response))
    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_goods(baseinfo_list)

    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="D:\\flask_project\\flask_app\\static\\output\\output1\\bf225a5e-16d0-45c8-8c19-54a1a94cf3e2\\ztbfile_merged_baseinfo.pdf"
    # procurement_file_path = "C:\\Users\\Administrator\\Desktop\\fsdownload\\b4601ea1-f087-4fa2-88ae-336ad4d8e1e9\\tmp\\ztbfile_procurement.pdf"
    procurement_file_path = "D:\\flask_project\\flask_app\\static\\output\\output1\\bf225a5e-16d0-45c8-8c19-54a1a94cf3e2\\ztbfile_procurement.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)
    print("------------------------------------")
    print(json.dumps(res, ensure_ascii=False, indent=4))
    end_time=time.time()
    print("elasped time:"+str(end_time-start_time))