don't yield expected auth errors (#4494)

* don't yield expected auth errors

* only catch 403s

backend/onyx/connectors/google_drive/file_retrieval.py

@@ -4,6 +4,7 @@ from datetime import datetime
 from datetime import timezone
 
 from googleapiclient.discovery import Resource  # type: ignore
+from googleapiclient.errors import HttpError  # type: ignore
 
 from onyx.connectors.google_drive.constants import DRIVE_FOLDER_TYPE
 from onyx.connectors.google_drive.constants import DRIVE_SHORTCUT_TYPE
@@ -131,17 +132,26 @@ def crawl_folders_for_files(
                     completion_stage=DriveRetrievalStage.FOLDER_FILES,
                 )
             # Only mark a folder as done if it was fully traversed without errors
+            # This usually indicates that the owner of the folder was impersonated.
+            # In cases where this never happens, most likely the folder owner is
+            # not part of the google workspace in question (or for oauth, the authenticated
+            # user doesn't own the folder)
             if found_files:
                 update_traversed_ids_func(parent_id)
         except Exception as e:
-            logger.error(f"Error getting files in parent {parent_id}: {e}")
-            yield RetrievedDriveFile(
-                drive_file=file,
-                user_email=user_email,
-                parent_id=parent_id,
-                completion_stage=DriveRetrievalStage.FOLDER_FILES,
-                error=e,
-            )
+            if isinstance(e, HttpError) and e.status_code == 403:
+                # don't yield an error here because this is expected behavior
+                # when a user doesn't have access to a folder
+                logger.debug(f"Error getting files in parent {parent_id}: {e}")
+            else:
+                logger.error(f"Error getting files in parent {parent_id}: {e}")
+                yield RetrievedDriveFile(
+                    drive_file=file,
+                    user_email=user_email,
+                    parent_id=parent_id,
+                    completion_stage=DriveRetrievalStage.FOLDER_FILES,
+                    error=e,
+                )
     else:
         logger.info(f"Skipping subfolder files since already traversed: {parent_id}")