ADD：批量接口

@@ -10,4 +10,7 @@ urlpatterns = [
     path(r'invoice/downloadExcel', views.InvoiceExcelView.as_view()),
     path(r'invoice/queryInfo', views.InvoiceQueryInfoView.as_view()),
     path(r'contract/v1', views.SEContractView.as_view()),
+    path(r'reocr', views.DocReOcrView.as_view()),
+    path(r'batch/reocr', views.BatchReOcrView.as_view()),
+    
 ]

@@ -591,7 +591,11 @@ invoice_download_args = {
 
 doc_reocr_args = {
     'doc_id': fields.Int(required=True),
-    'application_entity': fields.Int(required=True),
+    'application_entity': fields.Str(required=True),
+}
+
+batch_reocr_args = {
+    'application_entity': fields.Str(required=True),
 }
 
 
@@ -2123,4 +2127,59 @@ class DocReOcrView(GenericView, DocHandler):
                               '[is_priority={3}] [enqueue_res={4}] [classify_1={5}]'.format(args, prefix, doc.id,
                                                                            is_priority, enqueue_res, classify_1))
 
+        return response.ok()
+
+class BatchReOcrView(GenericView, DocHandler):
+    permission_classes = [IsAuthenticated]
+    authentication_classes = [OAuth2AuthenticationWithUser]
+
+    # 现有文件批量重新识别接口
+    @use_args(batch_reocr_args, location='data')
+    def post(self, request, args): 
+        start_time = time.time()
+
+        application_entity = args.get('application_entity')
+
+        today = timezone.now().date()
+        start_of_day = timezone.make_aware(timezone.datetime.combine(today, timezone.datetime.min.time()))
+        end_of_day = timezone.make_aware(timezone.datetime.combine(today, timezone.datetime.max.time()))
+
+
+        doc_class, prefix = self.get_doc_class(application_entity)
+        docs = doc_class.objects.filter(status=2, create_time__range=(start_of_day, end_of_day))
+
+        # 遍历
+        for doc in docs.iterator(): 
+
+        # 3. 选择队列进入
+            is_priority = PriorityApplication.objects.filter(application_id=doc.application_id, on_off=True).exists()
+            is_zip = False
+    
+            classify_1 = 0
+            # 电子合同 Econtract or OVP(FSM)
+            if doc.data_source == consts.DATA_SOURCE_LIST[2] or doc.data_source == consts.DATA_SOURCE_LIST[3]:  
+                if doc.document_scheme == consts.DOC_SCHEME_LIST[1]:
+                    for keyword, classify_1_tmp in consts.ECONTRACT_KEYWORDS_MAP.get(prefix):
+                        if keyword in doc.document_name:
+                            classify_1 = classify_1_tmp
+                            break
+            # FSM合同：WEP/MSI/SC/SC2
+            elif doc.data_source == consts.DATA_SOURCE_LIST[0] and doc.document_scheme == consts.DOC_SCHEME_LIST[0]:
+                for keyword, classify_1_tmp in consts.FSM_ECONTRACT_KEYWORDS_MAP.get(prefix):
+                    if keyword in doc.document_name:
+                        classify_1 = classify_1_tmp
+                        break 
+                    
+                    
+            if doc.document_name.endswith('.zip') or doc.document_name.endswith('.rar') or doc.document_name.endswith('.ZIP') \
+                    or doc.document_name.endswith('.RAR'):
+                is_zip = True
+    
+            # task = 'AFC_11001_0_Y' 'AFC_11001_0_N' 最后的Y,N表示是否是reocr，N否，Y是
+            task = consts.SPLIT_STR.join([prefix, str(doc.id), str(classify_1), 'Y'])
+            enqueue_res = rh.enqueue([task], is_priority, is_zip)
+            self.running_log.info('[doc upload success] [args={0}] [business_type={1}] [doc_id={2}] '
+                                  '[is_priority={3}] [enqueue_res={4}] [classify_1={5}]'.format(args, prefix, doc.id,
+                                                                               is_priority, enqueue_res, classify_1))
+    
         return response.ok()
\ No newline at end of file