Breaking: Decouple OCR control from archive file control (#12448)

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: shamoon <4887959+shamoon@users.noreply.github.com>
This commit is contained in:
Trenton H
2026-04-06 15:50:21 -07:00
committed by GitHub
co-authored by Claude Sonnet 4.6 shamoon
parent a945cd9379
commit c232d443fa
31 changed files with 1933 additions and 233 deletions
+11 -1
View File
@@ -30,6 +30,7 @@ from documents.consumer import AsnCheckPlugin
from documents.consumer import ConsumerPlugin
from documents.consumer import ConsumerPreflightPlugin
from documents.consumer import WorkflowTriggerPlugin
from documents.consumer import should_produce_archive
from documents.data_models import ConsumableDocument
from documents.data_models import DocumentMetadataOverrides
from documents.double_sided import CollatePlugin
@@ -311,7 +312,16 @@ def update_document_content_maybe_archive_file(document_id) -> None:
parser.configure(ParserContext())
try:
parser.parse(document.source_path, mime_type)
produce_archive = should_produce_archive(
parser,
mime_type,
document.source_path,
)
parser.parse(
document.source_path,
mime_type,
produce_archive=produce_archive,
)
thumbnail = parser.get_thumbnail(document.source_path, mime_type)