Allow parsers to declare uses remote, and remote ocr_mode (#13634)

* uses_remote_service + allow_remote to allow opt-in / out of remote OCR

* Add to parser dev docs

* remote_ocr_mode config setting

* Checks for remote_ocr_mode and fix import

* Update config.component.spec.ts

* More tests for remote_ocr_mode

* Docs for remote_ocr_mode

* Ok, wire up the remote_ocr_mode with allow_remote for consumer

* Update consumer.py

* Format remote OCR mode check tests

* Use get_choice_from_env
This commit is contained in:
shamoon
2026-08-24 14:43:04 -07:00
committed by GitHub
parent a1f20c9fe7
commit 7f1609332a
20 changed files with 425 additions and 1 deletions
@@ -75,6 +75,7 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
"remote_ocr_engine": None,
"remote_ocr_api_key": None,
"remote_ocr_endpoint": None,
"remote_ocr_mode": None,
"ai_enabled": False,
"llm_embedding_backend": None,
"llm_embedding_model": None,
+80
View File
@@ -1559,6 +1559,72 @@ class PostConsumeTestCase(DirectoriesMixin, GetConsumerMixin, TestCase):
consumer.run_post_consume_script(doc)
class TestConsumerRemoteOCR(
DirectoriesMixin,
FileSystemAssertsMixin,
GetConsumerMixin,
TestCase,
):
"""
The consumer resolves the remote OCR mode and the per-document request from
workflows into the allow_remote flag it hands to the parser registry.
"""
def setUp(self) -> None:
super().setUp()
patcher = mock.patch("documents.consumer.get_parser_registry")
self.mock_registry = patcher.start()
self.mock_registry.return_value.get_parser_for_file.return_value = DummyParser
self.addCleanup(patcher.stop)
def _consume(self, *, overrides: DocumentMetadataOverrides | None = None) -> bool:
src = (
Path(__file__).parent
/ "samples"
/ "documents"
/ "originals"
/ "0000001.pdf"
)
dst = self.dirs.scratch_dir / "sample.pdf"
shutil.copy(src, dst)
with self.get_consumer(dst, overrides=overrides) as consumer:
consumer.run()
_, kwargs = self.mock_registry.return_value.get_parser_for_file.call_args
return kwargs["allow_remote"]
@override_settings(REMOTE_OCR_MODE="always")
def test_always_mode_allows_remote(self) -> None:
"""
GIVEN: Remote OCR mode is 'always'.
WHEN: A document is consumed without any workflow asking for it.
THEN: The registry is allowed to pick the remote parser.
"""
self.assertTrue(self._consume())
@override_settings(REMOTE_OCR_MODE="workflow_only")
def test_workflow_only_mode_denies_remote_by_default(self) -> None:
"""
GIVEN: Remote OCR mode is 'workflow_only'.
WHEN: A document is consumed and nothing asked for remote OCR.
THEN: The remote parser is excluded.
"""
self.assertFalse(self._consume())
@override_settings(REMOTE_OCR_MODE="workflow_only")
def test_workflow_only_mode_allows_remote_when_requested(self) -> None:
"""
GIVEN: Remote OCR mode is 'workflow_only'.
WHEN: A workflow set remote_ocr on the metadata overrides.
THEN: The registry is allowed to pick the remote parser.
"""
self.assertTrue(
self._consume(overrides=DocumentMetadataOverrides(remote_ocr=True)),
)
class TestMetadataOverrides(TestCase):
def test_update_skip_asn_if_exists(self) -> None:
base = DocumentMetadataOverrides()
@@ -1566,6 +1632,20 @@ class TestMetadataOverrides(TestCase):
base.update(incoming)
self.assertTrue(base.skip_asn_if_exists)
def test_update_remote_ocr(self) -> None:
base = DocumentMetadataOverrides()
base.update(DocumentMetadataOverrides(remote_ocr=True))
self.assertTrue(base.remote_ocr)
def test_update_remote_ocr_is_not_unset(self) -> None:
"""
A later workflow that says nothing must not undo an earlier one that
asked for remote OCR.
"""
base = DocumentMetadataOverrides(remote_ocr=True)
base.update(DocumentMetadataOverrides())
self.assertTrue(base.remote_ocr)
def test_update_actor_and_version_label(self) -> None:
base = DocumentMetadataOverrides(
actor_id=1,
+39
View File
@@ -287,6 +287,45 @@ class TestUpdateContent(DirectoriesMixin, TestCase):
self.assertNotEqual(Document.objects.get(pk=doc.pk).content, "test")
class TestUpdateContentRemoteOCR(DirectoriesMixin, TestCase):
"""
Consumption workflows do not run on reprocess, so the remote parser is
used only in 'always' mode or when the caller explicitly asks for it.
"""
def setUp(self) -> None:
super().setUp()
patcher = mock.patch("documents.tasks.get_parser_registry")
self.mock_registry = patcher.start()
self.mock_registry.return_value.get_parser_for_file.return_value = None
self.addCleanup(patcher.stop)
self.doc = Document.objects.create(
title="test",
content="my document",
checksum="wow",
mime_type="application/pdf",
)
def _allow_remote(self, **kwargs) -> bool:
tasks.update_document_content_maybe_archive_file(self.doc.pk, **kwargs)
_, call_kwargs = self.mock_registry.return_value.get_parser_for_file.call_args
return call_kwargs["allow_remote"]
@override_settings(REMOTE_OCR_MODE="always")
def test_always_mode_allows_remote(self) -> None:
self.assertTrue(self._allow_remote())
@override_settings(REMOTE_OCR_MODE="workflow_only")
def test_workflow_only_mode_denies_remote_by_default(self) -> None:
self.assertFalse(self._allow_remote())
@override_settings(REMOTE_OCR_MODE="workflow_only")
def test_workflow_only_mode_allows_remote_when_requested(self) -> None:
self.assertTrue(self._allow_remote(remote_ocr=True))
class TestAIIndex(DirectoriesMixin, TestCase):
@override_settings(
AI_ENABLED=True,