extension fix and logs

backend/onyx/connectors/google_drive/connector.py

@@ -590,6 +590,7 @@ class GoogleDriveConnector(SlimConnector, CheckpointedConnector[GoogleDriveCheck
                 logger.info(f"Getting files in folder '{folder_id}' as '{user_email}'")
                 yield from _yield_from_folder_crawl(folder_id, start)
 
+        logger.info(f"Done retrieving files for user {user_email}")
         curr_stage.stage = DriveRetrievalStage.DONE
 
     def _manage_service_account_retrieval(
@@ -652,6 +653,7 @@ class GoogleDriveConnector(SlimConnector, CheckpointedConnector[GoogleDriveCheck
             for user_email, stage_completion in checkpoint.completion_map.items()
             if stage_completion.stage != DriveRetrievalStage.DONE
         ]
+        logger.info(f"{len(non_completed_org_emails)} users left to retrieve")
 
         # don't process too many emails before returning a checkpoint. This is
         # to resolve the case where there are a ton of emails that don't have access

backend/onyx/connectors/google_drive/doc_conversion.py

@@ -59,6 +59,10 @@ GOOGLE_MIME_TYPES = {
     GDriveMimeType.PPT.value: "text/plain",
 }
 
+DRIVE_IGNORE_EXTENSIONS = {
+    "dll",
+}
+
 
 def _summarize_drive_image(
     image_data: bytes, image_name: str, image_analysis_llm: LLM | None
@@ -422,6 +426,10 @@ def _convert_drive_item_to_document(
                     )
                     return None
 
+        if file.get("name", "").split(".")[-1] in DRIVE_IGNORE_EXTENSIONS:
+            logger.warning(f"Skipping file {file.get('name')} due to extension.")
+            return None
+
         # If we don't have sections yet, use the basic extraction method
         if not sections:
             sections = _download_and_extract_sections_basic(