Added filter to slim connector and logging for space permissions

backend/danswer/connectors/confluence/connector.py

@@ -13,6 +13,7 @@ from danswer.connectors.confluence.onyx_confluence import build_confluence_clien
 from danswer.connectors.confluence.onyx_confluence import OnyxConfluence
 from danswer.connectors.confluence.utils import attachment_to_content
 from danswer.connectors.confluence.utils import build_confluence_document_id
+from danswer.connectors.confluence.utils import check_attachment_filetype
 from danswer.connectors.confluence.utils import datetime_from_string
 from danswer.connectors.confluence.utils import extract_text_from_confluence_html
 from danswer.connectors.interfaces import GenerateDocumentsOutput
@@ -298,6 +299,8 @@ class ConfluenceConnector(LoadConnector, PollConnector, SlimConnector):
                 expand=restrictions_expand,
                 limit=_SLIM_DOC_BATCH_SIZE,
             ):
+                if not check_attachment_filetype(attachment):
+                    continue
                 doc_metadata_list.append(
                     SlimDocument(
                         id=build_confluence_document_id(

backend/danswer/connectors/confluence/utils.py

@@ -177,19 +177,23 @@ def extract_text_from_confluence_html(
     return format_document_soup(soup)
 
 
-def attachment_to_content(
+def check_attachment_filetype(attachment: dict[str, Any]) -> bool:
-    confluence_client: OnyxConfluence,
+    return attachment["metadata"]["mediaType"] in [
-    attachment: dict[str, Any],
-) -> str | None:
-    """If it returns None, assume that we should skip this attachment."""
-    if attachment["metadata"]["mediaType"] in [
         "image/jpeg",
         "image/png",
         "image/gif",
         "image/svg+xml",
         "video/mp4",
         "video/quicktime",
-    ]:
+    ]
+
+
+def attachment_to_content(
+    confluence_client: OnyxConfluence,
+    attachment: dict[str, Any],
+) -> str | None:
+    """If it returns None, assume that we should skip this attachment."""
+    if not check_attachment_filetype(attachment):
         return None
 
     download_link = confluence_client.url + attachment["_links"]["download"]
@@ -245,7 +249,7 @@ def build_confluence_document_id(
     return f"{base_url}{content_url}"
 
 
-def extract_referenced_attachment_names(page_text: str) -> list[str]:
+def _extract_referenced_attachment_names(page_text: str) -> list[str]:
     """Parse a Confluence html page to generate a list of current
         attachments in use
 

backend/ee/danswer/external_permissions/confluence/doc_sync.py

@@ -95,7 +95,6 @@ def _get_cloud_space_permissions(
 
 def _get_space_permissions(
     confluence_client: OnyxConfluence,
-    is_cloud: bool,
 ) -> dict[str, ExternalAccess]:
     logger.debug("Getting space permissions")
     # Gets all the spaces in the Confluence instance
@@ -117,7 +116,7 @@ def _get_space_permissions(
     logger.debug(f"Got {len(all_space_keys)} spaces from confluence")
     space_permissions_by_space_key: dict[str, ExternalAccess] = {}
     for space_key in all_space_keys:
-        if is_cloud:
+        if confluence_client.cloud:
             space_permissions = _get_cloud_space_permissions(
                 confluence_client=confluence_client, space_key=space_key
             )
@@ -242,7 +241,9 @@ def _fetch_all_page_restrictions_for_space(
                 )
             continue
 
-        logger.warning(f"No permissions found for document {slim_doc.id}")
+        logger.warning(
+            f"No permissions found for document {slim_doc.id} in space {space_key}"
+        )
 
     logger.debug("Finished fetching all page restrictions for space")
     return document_restrictions
@@ -263,11 +264,8 @@ def confluence_doc_sync(
     )
     confluence_connector.load_credentials(cc_pair.credential.credential_json)
 
-    is_cloud = cc_pair.connector.connector_specific_config.get("is_cloud", False)
-
     space_permissions_by_space_key = _get_space_permissions(
-        confluence_client=confluence_connector.confluence_client,
+        confluence_client=confluence_connector.confluence_client
-        is_cloud=is_cloud,
     )
 
     slim_docs = []