Refactored Google Drive Connector + Permission Syncing (#2945)

* refactoring changes

* everything working for service account

* works with service account

* combined scopes

* copy change

* oauth prep

* Works for oauth and service account credentials

* mypy

* merge fixes

* Refactor Google Drive connector

* finished backend

* auth changes

* if its stupid but it works, its not stupid

* npm run dev fixes

* addressed change requests

* string fix

* minor fixes and cleanup

* spacing cleanup

* Update connector.py

* everything done

* testing!

* Delete backend/tests/daily/connectors/google_drive/file_generator.py

* cleaned up

---------

Co-authored-by: Chris Weaver <25087905+Weves@users.noreply.github.com>

.github/workflows/pr-python-connector-tests.yml

@@ -18,6 +18,9 @@ env:
   # Jira
   JIRA_USER_EMAIL: ${{ secrets.JIRA_USER_EMAIL }}
   JIRA_API_TOKEN: ${{ secrets.JIRA_API_TOKEN }}
+  # Google
+  GOOGLE_DRIVE_SERVICE_ACCOUNT_JSON_STR: ${{ secrets.GOOGLE_DRIVE_SERVICE_ACCOUNT_JSON_STR }}
+  GOOGLE_DRIVE_OAUTH_CREDENTIALS_JSON_STR: ${{ secrets.GOOGLE_DRIVE_OAUTH_CREDENTIALS_JSON_STR }}
 
 jobs:
   connectors-check:

backend/danswer/configs/app_configs.py

@@ -251,9 +251,6 @@
 # for some connectors
 ENABLE_EXPENSIVE_EXPERT_CALLS = False
 
-GOOGLE_DRIVE_INCLUDE_SHARED = False
-GOOGLE_DRIVE_FOLLOW_SHORTCUTS = False
-GOOGLE_DRIVE_ONLY_ORG_PUBLIC = False
 
 # TODO these should be available for frontend configuration, via advanced options expandable
 WEB_CONNECTOR_IGNORED_CLASSES = os.environ.get(

backend/danswer/connectors/confluence/connector.py

@@ -17,6 +17,7 @@
 from danswer.connectors.interfaces import GenerateSlimDocumentOutput
 from danswer.connectors.interfaces import LoadConnector
 from danswer.connectors.interfaces import PollConnector
+from danswer.connectors.interfaces import SecondsSinceUnixEpoch
 from danswer.connectors.interfaces import SlimConnector
 from danswer.connectors.models import BasicExpertInfo
 from danswer.connectors.models import ConnectorMissingCredentialError
@@ -249,7 +250,11 @@ def poll_source(self, start: float, end: float) -> GenerateDocumentsOutput:
         self.cql_time_filter += f" and lastmodified <= '{formatted_end_time}'"
         return self._fetch_document_batches()
 
-    def retrieve_all_slim_documents(self) -> GenerateSlimDocumentOutput:
+    def retrieve_all_slim_documents(
+        self,
+        start: SecondsSinceUnixEpoch | None = None,
+        end: SecondsSinceUnixEpoch | None = None,
+    ) -> GenerateSlimDocumentOutput:
         if self.confluence_client is None:
             raise ConnectorMissingCredentialError("Confluence")