mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2026-09-05 09:25:03 +00:00
Change: skip documents with empty content in apply AI suggestions WF
This commit is contained in:
+2
-1
@@ -684,7 +684,8 @@ It requires [AI features](configuration.md#ai) to be enabled. You can specify:
|
||||
never replace the document's existing tags.
|
||||
|
||||
The action works with every trigger **except Consumption Started**, because suggestions are made from
|
||||
the document's text, which does not exist until after the document has been processed.
|
||||
the document's text, which does not exist until after the document has been processed. Documents whose
|
||||
processed text is empty or contains only whitespace are skipped.
|
||||
|
||||
Because the query to the AI service is slow, the action is queued and runs in the background rather
|
||||
than as part of the workflow run itself. The document is updated once the suggestions come back.
|
||||
|
||||
@@ -5711,6 +5711,39 @@ class TestApplyAISuggestionsWorkflowAction(
|
||||
self.assertEqual(changed, [])
|
||||
self.assertIn("AI is not enabled", "".join(cm.output))
|
||||
|
||||
def test_document_without_content_does_nothing(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- A document whose OCR content is empty or whitespace-only
|
||||
WHEN:
|
||||
- AI suggestions are applied by a workflow
|
||||
THEN:
|
||||
- The classifier is not called and the document is left unchanged
|
||||
"""
|
||||
action = self.make_action(ai_overwrite_existing=True)
|
||||
|
||||
for content in ("", " \n\t"):
|
||||
with self.subTest(content=content):
|
||||
self.doc.content = content
|
||||
self.doc.save(update_fields=["content"])
|
||||
|
||||
with (
|
||||
mock.patch(
|
||||
"documents.workflows.ai.get_ai_document_classification",
|
||||
) as get_classification,
|
||||
self.assertLogs(
|
||||
"paperless.workflows.ai",
|
||||
level="WARNING",
|
||||
) as cm,
|
||||
):
|
||||
changed = apply_ai_suggestions_to_document(action, self.doc)
|
||||
|
||||
self.assertEqual(changed, [])
|
||||
get_classification.assert_not_called()
|
||||
self.assertIn("has no content", "".join(cm.output))
|
||||
self.doc.refresh_from_db()
|
||||
self.assertEqual(self.doc.title, "original.pdf")
|
||||
|
||||
def test_invalid_configuration_leaves_document_untouched(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
|
||||
@@ -138,6 +138,16 @@ def apply_ai_suggestions_to_document(
|
||||
)
|
||||
return []
|
||||
|
||||
if not document.content.strip():
|
||||
logger.warning(
|
||||
"Document %s has no content, skipping AI suggestions for workflow "
|
||||
"action %s",
|
||||
document.pk,
|
||||
action.pk,
|
||||
extra={"group": logging_group},
|
||||
)
|
||||
return []
|
||||
|
||||
# Workflows run without a user, so we use the document owner
|
||||
owner = document.owner
|
||||
|
||||
|
||||
Reference in New Issue
Block a user