fix doc number miss-match issue (#822)

### What problem does this PR solve?

#620 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

api/apps/document_app.py

@@ -250,13 +250,9 @@ def rm():
             if not tenant_id:
                 return get_data_error_result(retmsg="Tenant not found!")
 
-            ELASTICSEARCH.deleteByQuery(
-                Q("match", doc_id=doc.id), idxnm=search.index_name(tenant_id))
-
-            DocumentService.clear_chunk_num(doc_id)
             b, n = File2DocumentService.get_minio_address(doc_id=doc_id)
 
-            if not DocumentService.delete(doc):
+            if not DocumentService.remove_document(doc, tenant_id):
                 return get_data_error_result(
                     retmsg="Database error (Document removal)!")
 

api/apps/file2document_app.py

@@ -58,11 +58,7 @@ def convert():
                     tenant_id = DocumentService.get_tenant_id(doc_id)
                     if not tenant_id:
                         return get_data_error_result(retmsg="Tenant not found!")
-                    ELASTICSEARCH.deleteByQuery(
+                    if not DocumentService.remove_document(doc, tenant_id):
-                        Q("match", doc_id=doc.id), idxnm=search.index_name(tenant_id))
-                    DocumentService.increment_chunk_num(
-                        doc.id, doc.kb_id, doc.token_num * -1, doc.chunk_num * -1, 0)
-                    if not DocumentService.delete(doc):
                         return get_data_error_result(
                             retmsg="Database error (Document removal)!")
                 File2DocumentService.delete_by_file_id(id)
@@ -125,11 +121,7 @@ def rm():
                 tenant_id = DocumentService.get_tenant_id(doc_id)
                 if not tenant_id:
                     return get_data_error_result(retmsg="Tenant not found!")
-                ELASTICSEARCH.deleteByQuery(
+                if not DocumentService.remove_document(doc, tenant_id):
-                    Q("match", doc_id=doc.id), idxnm=search.index_name(tenant_id))
-                DocumentService.increment_chunk_num(
-                    doc.id, doc.kb_id, doc.token_num * -1, doc.chunk_num * -1, 0)
-                if not DocumentService.delete(doc):
                     return get_data_error_result(
                         retmsg="Database error (Document removal)!")
         return get_json_result(data=True)

api/apps/file_app.py

@@ -277,11 +277,7 @@ def rm():
                 tenant_id = DocumentService.get_tenant_id(doc_id)
                 if not tenant_id:
                     return get_data_error_result(retmsg="Tenant not found!")
-                ELASTICSEARCH.deleteByQuery(
+                if not DocumentService.remove_document(doc, tenant_id):
-                    Q("match", doc_id=doc.id), idxnm=search.index_name(tenant_id))
-                DocumentService.increment_chunk_num(
-                    doc.id, doc.kb_id, doc.token_num * -1, doc.chunk_num * -1, 0)
-                if not DocumentService.delete(doc):
                     return get_data_error_result(
                         retmsg="Database error (Document removal)!")
             File2DocumentService.delete_by_file_id(file_id)

api/apps/kb_app.py

@@ -136,12 +136,7 @@ def rm():
                 data=False, retmsg=f'Only owner of knowledgebase authorized for this operation.', retcode=RetCode.OPERATING_ERROR)
 
         for doc in DocumentService.query(kb_id=req["kb_id"]):
-            ELASTICSEARCH.deleteByQuery(
+            if not DocumentService.remove_document(doc, kbs[0].tenant_id):
-                Q("match", doc_id=doc.id), idxnm=search.index_name(kbs[0].tenant_id))
-
-            DocumentService.increment_chunk_num(
-                doc.id, doc.kb_id, doc.token_num * -1, doc.chunk_num * -1, 0)
-            if not DocumentService.delete(doc):
                 return get_data_error_result(
                     retmsg="Database error (Document removal)!")
 

api/db/services/document_service.py

@@ -70,27 +70,12 @@ class DocumentService(CommonService):
             raise RuntimeError("Database error (Knowledgebase)!")
         return doc
 
-    @classmethod
-    @DB.connection_context()
-    def delete(cls, doc):
-        e, kb = KnowledgebaseService.get_by_id(doc.kb_id)
-        if not KnowledgebaseService.update_by_id(
-                kb.id, {"doc_num": max(0, kb.doc_num - 1)}):
-            raise RuntimeError("Database error (Knowledgebase)!")
-        return cls.delete_by_id(doc.id)
-
     @classmethod
     @DB.connection_context()
     def remove_document(cls, doc, tenant_id):
         ELASTICSEARCH.deleteByQuery(
                 Q("match", doc_id=doc.id), idxnm=search.index_name(tenant_id))
-
+        cls.clear_chunk_num(doc.id)
-        cls.increment_chunk_num(
-            doc.id, doc.kb_id, doc.token_num * -1, doc.chunk_num * -1, 0)
-        if not cls.delete(doc):
-            raise RuntimeError("Database error (Document removal)!")
-
-        MINIO.rm(doc.kb_id, doc.location)
         return cls.delete_by_id(doc.id)
 
     @classmethod