Merge pull request #3359 from danswer-ai/conf-logging-filter

Added filter to slim connector and logging for space permissions

backend/danswer/connectors/confluence/connector.py

@@ -15,6 +15,7 @@ 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 datetime_from_string
 from danswer.connectors.confluence.utils import extract_text_from_confluence_html
+from danswer.connectors.confluence.utils import validate_attachment_filetype
 from danswer.connectors.interfaces import GenerateDocumentsOutput
 from danswer.connectors.interfaces import GenerateSlimDocumentOutput
 from danswer.connectors.interfaces import LoadConnector
@@ -276,9 +277,11 @@ class ConfluenceConnector(LoadConnector, PollConnector, SlimConnector):
         ):
             # If the page has restrictions, add them to the perm_sync_data
             # These will be used by doc_sync.py to sync permissions
-            perm_sync_data = {
-                "restrictions": page.get("restrictions", {}),
-                "space_key": page.get("space", {}).get("key"),
+            page_restrictions = page.get("restrictions")
+            page_space_key = page.get("space", {}).get("key")
+            page_perm_sync_data = {
+                "restrictions": page_restrictions or {},
+                "space_key": page_space_key,
             }
 
             doc_metadata_list.append(
@@ -288,7 +291,7 @@ class ConfluenceConnector(LoadConnector, PollConnector, SlimConnector):
                         page["_links"]["webui"],
                         self.is_cloud,
                     ),
-                    perm_sync_data=perm_sync_data,
+                    perm_sync_data=page_perm_sync_data,
                 )
             )
             attachment_cql = f"type=attachment and container='{page['id']}'"
@@ -298,6 +301,21 @@ class ConfluenceConnector(LoadConnector, PollConnector, SlimConnector):
                 expand=restrictions_expand,
                 limit=_SLIM_DOC_BATCH_SIZE,
             ):
+                if not validate_attachment_filetype(attachment):
+                    continue
+                attachment_restrictions = attachment.get("restrictions")
+                if not attachment_restrictions:
+                    attachment_restrictions = page_restrictions
+
+                attachment_space_key = attachment.get("space", {}).get("key")
+                if not attachment_space_key:
+                    attachment_space_key = page_space_key
+
+                attachment_perm_sync_data = {
+                    "restrictions": attachment_restrictions or {},
+                    "space_key": attachment_space_key,
+                }
+
                 doc_metadata_list.append(
                     SlimDocument(
                         id=build_confluence_document_id(
@@ -305,7 +323,7 @@ class ConfluenceConnector(LoadConnector, PollConnector, SlimConnector):
                             attachment["_links"]["webui"],
                             self.is_cloud,
                         ),
-                        perm_sync_data=perm_sync_data,
+                        perm_sync_data=attachment_perm_sync_data,
                     )
                 )
             if len(doc_metadata_list) > _SLIM_DOC_BATCH_SIZE:

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(
-    confluence_client: OnyxConfluence,
-    attachment: dict[str, Any],
-) -> str | None:
-    """If it returns None, assume that we should skip this attachment."""
-    if attachment["metadata"]["mediaType"] in [
+def validate_attachment_filetype(attachment: dict[str, Any]) -> bool:
+    return attachment["metadata"]["mediaType"] not 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 validate_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

@@ -242,7 +242,9 @@ 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

backend/tests/daily/connectors/confluence/test_confluence_permissions_basic.py

@@ -9,6 +9,7 @@ from danswer.connectors.confluence.connector import ConfluenceConnector
 def confluence_connector() -> ConfluenceConnector:
     connector = ConfluenceConnector(
         wiki_base="https://danswerai.atlassian.net",
+        is_cloud=True,
     )
     connector.load_credentials(
         {