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

src/documents/consumer.py

@@ -53,6 +53,7 @@ from documents.utils import copy_basic_file_stats
 from documents.utils import copy_file_with_basic_stats
 from documents.utils import run_subprocess
 from paperless.config import OcrConfig
+from paperless.config import RemoteOCRConfig
 from paperless.models import ArchiveFileGenerationChoices
 from paperless.parsers import ParserContext
 from paperless.parsers import ParserProtocol
@@ -451,12 +452,19 @@ class ConsumerPlugin(
                 except Exception as e:
                     self.log.error(f"Error attempting to clean PDF: {e}")
 
+            # Workflows have already run at this point, so the metadata knows
+            # whether this document was singled out for remote OCR
+            allow_remote = (
+                self.metadata.remote_ocr or RemoteOCRConfig().remote_ocr_by_default
+            )
+
             # Based on the mime type, get the parser for that type
             parser_class: type[ParserProtocol] | None = (
                 get_parser_registry().get_parser_for_file(
                     mime_type,
                     self.filename,
                     self.working_copy,
+                    allow_remote=allow_remote,
                 )
             )
             if not parser_class:

src/documents/data_models.py

@@ -34,6 +34,7 @@ class DocumentMetadataOverrides:
     skip_asn_if_exists: bool = False
     version_label: str | None = None
     actor_id: int | None = None
+    remote_ocr: bool = False
 
     def update(self, other: "DocumentMetadataOverrides") -> "DocumentMetadataOverrides":
         """
@@ -57,6 +58,8 @@ class DocumentMetadataOverrides:
             self.actor_id = other.actor_id
         if other.skip_asn_if_exists:
             self.skip_asn_if_exists = True
+        if other.remote_ocr:
+            self.remote_ocr = True
         if other.version_label is not None:
             self.version_label = other.version_label
 

src/documents/tasks.py

@@ -67,6 +67,7 @@ from documents.utils import identity
 from documents.versioning import annotate_effective_content
 from documents.workflows.utils import get_workflows_for_trigger
 from paperless.config import AIConfig
+from paperless.config import RemoteOCRConfig
 from paperless.logging import consume_task_id
 from paperless.parsers import ParserContext
 from paperless.parsers.registry import get_parser_registry
@@ -338,10 +339,17 @@ def bulk_update_documents(document_ids) -> None:
 
 
 @shared_task
-def update_document_content_maybe_archive_file(document_id) -> None:
+def update_document_content_maybe_archive_file(
+    document_id,
+    *,
+    remote_ocr: bool = False,
+) -> None:
     """
     Re-creates OCR content and thumbnail for a document, and archive file if
     it exists.
+
+    Remote OCR is used only when the engine is configured to handle everything
+    or if explicitly asked for via ``remote_ocr``.
     """
     document = Document.objects.get(id=document_id)
 
@@ -351,6 +359,7 @@ def update_document_content_maybe_archive_file(document_id) -> None:
         mime_type,
         document.original_filename or "",
         document.source_path,
+        allow_remote=remote_ocr or RemoteOCRConfig().remote_ocr_by_default,
     )
 
     if not parser_class:

src/documents/tests/test_api_app_config.py

@@ -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,

src/documents/tests/test_consumer.py

@@ -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,

src/documents/tests/test_tasks.py

@@ -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,