ai提取优化医疗产品判断条件,保留公告的优先级规则优化循环去重的问题

BaseDataMaintenance/maintenance/dataflow.py

@@ -1288,7 +1288,7 @@ class Dataflow():
             base_list.sort(key=lambda x:x["bondId_num"],reverse=True)
             return base_list[0]["docid"]
         if len(base_list)>0:
-            base_list.sort(key=lambda x:x["docid"],reverse=to_reverse)
+            base_list.sort(key=lambda x:x["docid"],reverse=False)
             base_list.sort(key=lambda x:x.get(document_attachment_extract_status,0),reverse=True)
             base_list.sort(key=lambda x:x["extract_count"],reverse=True)
             return base_list[0]["docid"]
@@ -4919,7 +4919,7 @@ class Dataflow_dumplicate(Dataflow):
 
         if item:
             log("start dumplicate_comsumer_handle")
-            self.dumplicate_comsumer_handle(item,None,self.ots_client,get_all=False,upgrade=False)
+            self.dumplicate_comsumer_handle(item,None,self.ots_client,get_all=True,upgrade=False)
             return
 
     def test_merge(self,list_docid_less,list_docid_greater):
@@ -5158,7 +5158,7 @@ if __name__ == '__main__':
     # test_attachment_interface()
     df_dump = Dataflow_dumplicate(start_delete_listener=False)
     # df_dump.start_flow_dumplicate()
-    df_dump.test_dumplicate(626076001
+    df_dump.test_dumplicate(628170641
                             )
     # df_dump.dumplicate_comsumer_handle_interface(603504420,document_table="document_0000",document_table_index="document_0000_index",project_table="project_0000",project_table_index="project_0000_index_formerge")
     # compare_dumplicate_check()

BaseDataMaintenance/maintenance/product/medical_product.py

@@ -22,7 +22,6 @@ class MedicalProduct():
     def is_medical_product(self,content):
         _search = self.medical_pattern.search(content)
         if _search:
-            print(_search.group())
             return True
         else:
             return False