2.17 新增子进程处理文件切割，貌似可以解决内存泄漏问题

flask_app/routes/test_preprocess.py

@@ -7,8 +7,7 @@ import time
 from flask_app.ConnectionLimiter import require_execution_timeout
 from flask_app.general.format_change import download_file
 from flask_app.routes.utils import validate_and_setup_logger
-from flask_app.routes.货物标解析main import preprocess_files
-
+from flask_app.routes.货物标解析main import preprocess_files, preprocess_file_main
 
 test_process_bp = Blueprint('test_process', __name__)
 @test_process_bp.route('/test_process', methods=['POST'])
@@ -31,9 +30,7 @@ def process_file():
         # print(file_path)
         # 调用预处理函数
         start_time = time.time()
-        with multiprocessing.Pool(processes=1) as pool:
-            # 调用 apply 或 apply_async 执行子进程任务
-            result = pool.apply(preprocess_files, args=(output_folder, file_path, 2, logger,))
+        result=preprocess_file_main(output_folder, file_path, file_type,logger)
 
         # 处理结果
         if not result:

flask_app/routes/工程标解析main.py

@@ -1,5 +1,6 @@
 # -*- encoding:utf-8 -*-
 import json
+import multiprocessing
 import os
 import time
 from concurrent.futures import ThreadPoolExecutor
@@ -21,8 +22,15 @@ from flask_app.工程标.资格审查模块main import combine_review_standards
 from flask_app.general.商务技术评分提取 import combine_evaluation_standards
 from flask_app.general.format_change import pdf2docx, docx2pdf
 
-# 创建全局线程池
-executor = ThreadPoolExecutor()
+
+def preprocess_file_main(output_folder, file_path, file_type,logger):
+    # 这里是你原本处理请求的地方
+    with multiprocessing.Pool(processes=1) as pool:
+        result = pool.apply(
+            preprocess_files,  # 你的实际执行函数
+            args=(output_folder, file_path, file_type, logger)
+        )
+    return result
 def preprocess_files(output_folder, file_path, file_type,logger):
     logger.info("starting 文件预处理...")
     start_time=time.time()
@@ -221,12 +229,10 @@ def fetch_bid_opening(invalid_deleted_docx, merged_baseinfo_path_more, clause_pa
         result = {"开评定标流程": {}}
     return result
 
-#分段返回
-
 def engineering_bid_main(output_folder, file_path, file_type, unique_id):
     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,logger)
+    processed_data = preprocess_file_main(output_folder, file_path, file_type,logger)
     if not processed_data:
         error_response = {
             'error': '文件预处理失败。请检查文件类型并重试。'

flask_app/routes/货物标解析main.py

@@ -1,4 +1,5 @@
 import json
+import multiprocessing
 import time
 from docx import Document
 from flask_app.general.format_change import docx2pdf, pdf2docx
@@ -15,6 +16,15 @@ from flask_app.general.投标人须知正文条款提取成json文件 import con
 from flask_app.general.无效标和废标公共代码 import combine_find_invalid
 from flask_app.货物标.资格审查main import combine_qualification_review
 from flask_app.general.商务技术评分提取 import combine_evaluation_standards
+
+def preprocess_file_main(output_folder, file_path, file_type,logger):
+    # 这里是你原本处理请求的地方
+    with multiprocessing.Pool(processes=1) as pool:
+        result = pool.apply(
+            preprocess_files,  # 你的实际执行函数
+            args=(output_folder, file_path, file_type, logger)
+        )
+    return result
 def preprocess_files(output_folder, file_path, file_type,logger):
     logger.info("starting 文件预处理...")
     start_time = time.time()
@@ -225,7 +235,7 @@ def post_process_baseinfo(base_info,logger):
 def goods_bid_main(output_folder, file_path, file_type, unique_id):
     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,logger)
+    processed_data = preprocess_file_main(output_folder, file_path, file_type,logger)
     if not processed_data:
         error_response = {
             'error': '文件预处理失败。请检查文件类型并重试。'