224 lines
11 KiB
Python
224 lines
11 KiB
Python
# 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
|
||
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.")
|