#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.main.知识库操作 import addfileToKnowledge, deleteKnowledge 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] 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 } def fetch_project_basic_info(knowledge_name, output_folder, clause_path): # 投标人须知前附表 logger.info("starting基础信息...") basic_res = combine_basic_info(knowledge_name,output_folder,clause_path) logger.info("基础信息done") return basic_res def fetch_qualification_review(output_folder,qualification_path,notice_path,knowledge_name): #资格审查 logger.info("starting资格审查...") review_standards_res = combine_qualification_review(output_folder,qualification_path,notice_path, knowledge_name) 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']) } # 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, knowledge_name, output_folder, processed_data['clause_path']), 'qualification_review': executor.submit(fetch_qualification_review,output_folder, processed_data['qualification_path'],processed_data['notice_path'],knowledge_name), } # 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) 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.")