Performance: resolve index-write permissions and effective content in bulk (#13869)

* fix(search): resolve index-write permissions and effective content in bulk

Add WriteBatch.add_or_update_ids() and use it in bulk_update_documents
and trash restore, cutting index writes from ~8 queries per document
to a constant handful per batch

* Always these new ones with xdist, try a better condition
This commit is contained in:
Trenton H
2026-09-07 14:43:13 -07:00
committed by GitHub
parent d52cc1b609
commit f5ff18326d
4 changed files with 233 additions and 5 deletions
+40
View File
@@ -284,6 +284,46 @@ class WriteBatch:
tantivy.Query.term_query(self._backend._schema, "id", doc_id),
)
def add_or_update_ids(self, ids: Sequence[int]) -> None:
"""
Add or update multiple documents in the batch by primary key.
Unlike calling ``add_or_update()`` once per document, this resolves
viewer permissions and effective (versioned) content in bulk against
the ids as a whole, instead of once per document -- see
``_DocumentViewerStream`` and ``annotate_effective_content``. Use
this whenever more than one document is being written in the same
batch.
An id with no matching document (e.g. deleted between the caller
collecting ids and the batch running) is silently skipped, matching
``add_or_update()``'s existing single-document deferred-task behavior
rather than erroring or leaving a stale index entry.
Args:
ids: Primary keys of Document instances to index
"""
from documents.models import Document
from documents.versioning import annotate_effective_content
ids = list(ids)
if not ids:
return
queryset = annotate_effective_content(
Document.objects.filter(pk__in=ids)
.select_related("correspondent", "document_type", "storage_path", "owner")
.prefetch_related("tags", "notes__user", "custom_fields__field"),
)
for document, grant in _DocumentViewerStream(queryset, chunk_size=1000):
self.remove(document.pk)
doc = self._backend._build_tantivy_doc(
document,
viewer_ids=grant.viewer_ids,
viewer_group_ids=grant.viewer_group_ids,
)
self._writer.add_document(doc)
class TantivyBackend:
"""