zbparse/flask_app/货物标/货物标解析main.py

# 竞磋 竞谈 磋商 询价 邀请 单一来源
import json
import time

from flask_app.main.format_change import docx2pdf, pdf2docx
from flask_app.main.json_utils import transform_json_values
from flask_app.货物标.基础信息解析main import combine_basic_info
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.货物标截取pdf import truncate_pdf_multiple
from concurrent.futures import ThreadPoolExecutor
import concurrent.futures
from flask_app.货物标.投标人须知正文条款提取成json文件货物标版 import convert_clause_to_json
from flask_app.货物标.无效标和废标和禁止投标整合main import combine_find_invalid
from flask_app.货物标.资格审查main import combine_qualification_review
from flask_app.货物标.评分标准提取main import combine_evaluation_standards
import logging


def get_global_logger(unique_id):
    if unique_id is None:
        return logging.getLogger()  # 获取默认的日志器
    logger = logging.getLogger(unique_id)
    return logger


logger = None

# 创建全局线程池
executor = ThreadPoolExecutor()


def preprocess_files(output_folder, file_path, file_type, unique_id):
    logger.info("starting 文件预处理...")
    logger.info("output_folder..." + output_folder)

    # 根据文件类型处理文件路径
    if file_type == 1:  # docx
        docx_path = file_path
        pdf_path = docx2pdf(docx_path)  # 将docx转换为pdf以供后续处理
    elif file_type == 2:  # pdf
        pdf_path = file_path
        docx_path = pdf2docx(pdf_path)  # 将pdf转换为docx以供上传到知识库
    elif file_type == 3:  # doc
        pdf_path = docx2pdf(file_path)
        docx_path = pdf2docx(pdf_path)
    else:
        logger.error("Unsupported file type provided. Preprocessing halted.")
        return None

    # # 异步上传知识库
    # future_knowledge = executor.submit(addfileToKnowledge, docx_path, "招标解析" + unique_id)
    # 调用截取PDF多次
    truncate_files = truncate_pdf_multiple(pdf_path,
                                           output_folder)  # index: 0->商务技术服务要求 1->评标办法 2->资格审查 3->投标人须知前附表 4->投标人须知正文

    # 处理各个部分
    invalid_docpath = docx_path  # docx截取无效标部分
    procurement_path = truncate_files[0]  # 商务技术服务要求
    evaluation_method_path = truncate_files[1]  # 评标办法
    qualification_path = truncate_files[2]  # 资格审查
    tobidders_notice_path = truncate_files[4]  # 投标人须知正文
    notice_path = truncate_files[5]
    merged_baseinfo_path = truncate_files[6]  # 合并封面+招标公告+投标人须知前附表+须知正文
    clause_path = convert_clause_to_json(tobidders_notice_path, output_folder)  # 投标人须知正文条款pdf->json

    logger.info("文件预处理done")

    # 提前返回，不等待 future_knowledge 完成，返回包含 Future 对象
    return {
        'file_path': file_path,
        'output_folder': output_folder,
        'procurement_path': procurement_path,
        'evaluation_method_path': evaluation_method_path,
        'qualification_path': qualification_path,
        'notice_path': notice_path,
        # 'knowledge_future': future_knowledge,  # 返回 Future 对象
        'clause_path': clause_path,
        'invalid_docpath': invalid_docpath,
        'merged_baseinfo_path': merged_baseinfo_path
    }

def fetch_project_basic_info(merged_baseinfo_path, procurement_file_path):  # 投标人须知前附表
    logger.info("starting基础信息...")
    basic_res = combine_basic_info(merged_baseinfo_path, procurement_file_path)
    logger.info("基础信息done")
    return basic_res


def fetch_qualification_review(output_folder, qualification_path, notice_path,merged_baseinfo_path):  # 资格审查
    logger.info("starting资格审查...")
    review_standards_res = combine_qualification_review(output_folder, qualification_path, notice_path,merged_baseinfo_path)
    logger.info("资格审查done")
    return review_standards_res


def fetch_evaluation_standards(evaluation_method_path):  # 评标细则
    logger.info("starting 商务评分和技术评分...")
    # 获取评标办法前附表的字典结果
    evaluation_standards_res = combine_evaluation_standards(evaluation_method_path)
    # 获取技术标和商务标
    technical_standards = {"技术评分": evaluation_standards_res.get("技术评分", {})}
    commercial_standards = {"商务评分": evaluation_standards_res.get("商务评分", {})}
    logger.info("商务评分和技术评分done")

    # 返回将 "技术标" 和 "商务标" 包含在新的键中
    return {
        "technical_standards": technical_standards,
        "commercial_standards": commercial_standards
    }


# TODO:doc文档转换
def fetch_invalid_requirements(invalid_docpath, output_folder):
    # 废标项要求：千问
    logger.info("starting无效标与废标...")
    find_invalid_res = combine_find_invalid(invalid_docpath, output_folder)
    logger.info("无效标与废标done...")
    return find_invalid_res

# 投标文件要求
def fetch_bidding_documents_requirements(clause_path):
    logger.info("starting投标文件要求...")
    fetch_bidding_documents_requirements_json = extract_from_notice(clause_path, 1)
    logger.info("投标文件要求done...")
    return {"投标文件要求": fetch_bidding_documents_requirements_json}


# 开评定标流程
def fetch_bid_opening(clause_path):
    logger.info("starting开评定标流程...")
    fetch_bid_opening_json = extract_from_notice(clause_path, 2)
    logger.info("开评定标流程done...")
    return {"开评定标流程": fetch_bid_opening_json}


def goods_bid_main(output_folder, file_path, file_type, unique_id):
    global logger
    logger = get_global_logger(unique_id)

    # 预处理文件，获取处理后的数据
    processed_data = preprocess_files(output_folder, file_path, file_type, unique_id)
    if not processed_data:
        yield json.dumps({})  # 如果处理数据失败，返回空的 JSON

    with concurrent.futures.ThreadPoolExecutor() as executor:
        # 立即启动不依赖 knowledge_name 和 index 的任务
        futures = {
            'evaluation_standards': executor.submit(fetch_evaluation_standards,
                                                    processed_data['evaluation_method_path']),
            'invalid_requirements': executor.submit(fetch_invalid_requirements, processed_data['invalid_docpath'],
                                                    output_folder),
            'bidding_documents_requirements': executor.submit(fetch_bidding_documents_requirements,
                                                              processed_data['clause_path']),
            'opening_bid': executor.submit(fetch_bid_opening, processed_data['clause_path']),
            'base_info': executor.submit(fetch_project_basic_info, processed_data['merged_baseinfo_path'],
                                         processed_data['procurement_path']),
            'qualification_review': executor.submit(fetch_qualification_review, output_folder,
                                                    processed_data['qualification_path'],
                                                    processed_data['notice_path'],
                                                    processed_data['merged_baseinfo_path']),
        }

        # 提前处理这些不依赖的任务，按完成顺序返回
        for future in concurrent.futures.as_completed(futures.values()):
            key = next(k for k, v in futures.items() if v == future)
            try:
                result = future.result()
                # 如果是 evaluation_standards，拆分技术标和商务标
                if key == 'evaluation_standards':
                    technical_standards = result["technical_standards"]
                    commercial_standards = result["commercial_standards"]
                    # 分别返回技术标和商务标
                    yield json.dumps({'technical_standards': transform_json_values(technical_standards)},
                                     ensure_ascii=False)
                    yield json.dumps({'commercial_standards': transform_json_values(commercial_standards)},
                                     ensure_ascii=False)
                else:
                    # 处理其他任务的结果
                    yield json.dumps({key: transform_json_values(result)}, ensure_ascii=False)
            except Exception as exc:
                logger.error(f"Error processing {key}: {exc}")
                yield json.dumps({'error': f'Error processing {key}: {str(exc)}'}, ensure_ascii=False)

        # # 只有在需要 knowledge_name 和 index 时才等待 future_knowledge 完成
        # try:
        #     knowledge_name = "招标解析" + unique_id
        #     index = processed_data['knowledge_future'].result()  # 阻塞等待知识库上传任务完成
        #
        #     # 提交依赖 knowledge_name 和 index 的任务
        #     future_dependencies = {
        #         'base_info': executor.submit(fetch_project_basic_info,processed_data['merged_baseinfo_path'], processed_data['procurement_path']),
        #         'qualification_review': executor.submit(fetch_qualification_review, output_folder,
        #                                                 processed_data['qualification_path'],
        #                                                 processed_data['notice_path'], processed_data['merged_baseinfo_path']),
        #     }
        #     # 按完成顺序返回依赖任务的结果
        #     for future in concurrent.futures.as_completed(future_dependencies.values()):
        #         key = next(k for k, v in future_dependencies.items() if v == future)
        #         try:
        #             result = future.result()
        #             yield json.dumps({key: transform_json_values(result)}, ensure_ascii=False)
        #         except Exception as exc:
        #             logger.error(f"Error processing {key}: {exc}")
        #             yield json.dumps({'error': f'Error processing {key}: {str(exc)}'}, ensure_ascii=False)
        #
        # except Exception as e:
        #     logger.error(f"Error uploading to knowledge base: {e}")
        #     yield json.dumps({'error': f'Knowledge upload failed: {str(e)}'}, ensure_ascii=False)

    # 删除知识索引
    # deleteKnowledge(index)

#TODO:目前的无效标这块的键值都删去空格了，所有的键名都删去空格
#广水市 2022 年义务教育学校多媒体补充采购项目 资格审查有问题
if __name__ == "__main__":
    output_folder = "flask_app/static/output/zytest1"

    start_time = time.time()
    file_type = 1  # 1:docx 2:pdf 3:其他
    input_file = "C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles\\6.2定版视频会议磋商文件.pdf"
    goods_bid_main(output_folder, input_file, file_type, "uuidzyzy11")
    end_time = time.time()
    elapsed_time = end_time - start_time  # 计算耗时
    print(f"Function execution took {elapsed_time} seconds.")