12.17 无效投标、废标

flask_app/routes/偏离表main.py

@@ -5,7 +5,8 @@ import string
 import time
 
 from flask_app.general.doubao import doubao_model
-from flask_app.general.format_change import pdf2docx, docx2pdf
+from flask_app.general.format_change import pdf2docx, docx2pdf,doc2docx
+from flask_app.general.insert_del_pagemark import insert_mark
 from flask_app.general.json_utils import clean_json_string
 from flask_app.general.通义千问long import upload_file
 from flask_app.货物标.截取pdf货物标版 import truncate_pdf_specific_goods
@@ -353,10 +354,14 @@ def get_tech_and_business_deviation(file_path,file_type,unique_id,output_folder)
     global logger
     logger = get_global_logger(unique_id)
     if file_type == 1:  # docx
+        docx_path=file_path
         pdf_path = docx2pdf(file_path)  # 将docx转换为pdf以供后续处理
     elif file_type == 2:  # pdf
+        # docx_path=pdf2docx(file_path)
+        docx_path=""
         pdf_path = file_path
     elif file_type == 3:  # doc
+        docx_path=doc2docx(file_path)
         pdf_path = docx2pdf(file_path)
     else:
         logger.error("Unsupported file type provided. Preprocessing halted.")
@@ -366,14 +371,17 @@ def get_tech_and_business_deviation(file_path,file_type,unique_id,output_folder)
     notice_path=files[0]
     qualification_file=files[1]
     procurement_file=files[2]
+    # invalid_path=docx_path
+    invalid_path=docx_path if docx_path != "" else pdf_path  #可能是pdf docx
     if not procurement_file:
-        procurement_file=pdf_path    #直接传整份文件
+        procurement_file=invalid_path
+
     tech_deviation={}
     with concurrent.futures.ThreadPoolExecutor() as executor:
         # 提交任务到线程池
-        future_procurement = executor.submit(fetch_procurement_reqs, procurement_file, pdf_path)
+        future_procurement = executor.submit(fetch_procurement_reqs, procurement_file, invalid_path)
         time.sleep(1)
-        future_review = executor.submit(combine_qualification_review, pdf_path, qualification_file, notice_path)
+        future_review = executor.submit(combine_qualification_review, invalid_path, qualification_file, notice_path)
 
         try:
             # 获取函数执行结果

flask_app/routes/小解析main.py

@@ -77,8 +77,7 @@ def little_parse_engineering(output_folder, pdf_path):
     # 假设最后一个文件是需要处理的基础信息文件
     baseinfo_file_path = files[-1]
     if not baseinfo_file_path:
-        baseinfo_file_path=truncate_pdf_main(pdf_path,output_folder,5)[0]
+        baseinfo_file_path=truncate_pdf_main(pdf_path,output_folder,5)[0]  #invalid_path
-        # baseinfo_file_path=pdf_path    #截取失败就传整份文件
     # 上传文件并获取文件 ID
     file_id = upload_file(baseinfo_file_path)
     # 注意：以下路径被硬编码，确保该路径存在并且正确

flask_app/货物标/商务服务其他要求提取.py

@@ -7,6 +7,7 @@ from flask_app.general.doubao import read_txt_to_string, pdf2txt
 from flask_app.general.json_utils import combine_json_results, clean_json_string
 from flask_app.general.通义千问long import upload_file, qianwen_long_stream
 from flask_app.货物标.截取pdf货物标版 import extract_common_header, clean_page_content
+from flask_app.general.format_change import docx2pdf
 import concurrent.futures
 from flask_app.general.doubao import doubao_model
 
@@ -256,7 +257,10 @@ def generate_template(required_keys,full_text, type=1):
 
 def get_business_requirements(procurement_path,processed_filepath):
     required_keys = ["技\s*术\s*要\s*求", "商\s*务\s*要\s*求", "服\s*务\s*要\s*求", "其\s*他\s*要\s*求","总\s*体\s*要\s*求","建\s*设\s*要\s*求","进\s*度\s*要\s*求","工\s*期\s*要\s*求","质\s*保\s*要\s*求","培\s*训\s*要\s*求","售\s*后\s*要\s*求"]
-    contained_keys = find_exists(procurement_path, required_keys)
+    procurement_pdf_path=procurement_path
+    if procurement_path.lower().endswith('.doc', '.docx'):
+        procurement_pdf_path=docx2pdf(procurement_path)
+    contained_keys = find_exists(procurement_pdf_path, required_keys)
     print(contained_keys)
     if not contained_keys:
         return {}

flask_app/货物标/技术参数要求提取.py

@@ -373,6 +373,8 @@ def get_technical_requirements(invalid_path,processed_filepath):
     if '否' in judge_res:
         model_type = 0  # 使用qianwen-long+invalid_path
         print("no!调用invalid_path")
+        if invalid_path.lower().endswith('.pdf'):           #确保上传的是docx
+            invalid_path = pdf2docx(invalid_path)
         file_id=upload_file(invalid_path)
         user_query = generate_prompt(judge_res)
         model_res=qianwen_long(file_id,user_query)

flask_app/货物标/提取采购需求main.py

@@ -12,6 +12,7 @@ from flask_app.货物标.商务服务其他要求提取 import get_business_requ
 
 # 获取采购清单
 def fetch_procurement_reqs(procurement_path, invalid_path):
+    #procurement_path可能是pdf\docx
     # 定义默认的 procurement_reqs 字典
     DEFAULT_PROCUREMENT_REQS = {
         "采购需求": "",