Finally, the remote ocr workflow (#13637)

* Ok! Backend stuff for the remote ocr workflow

* Frotnend workflow stuff

* And docs

* Fix dynamic action fields thing

* Actually, fix the action dropdown thing

* Fix this validation thing, and we have to check existing actions

* Fix migration

src/documents/tests/test_api_workflows.py

@@ -506,6 +506,141 @@ class TestApiWorkflows(DirectoriesMixin, APITestCase):
 
         self.assertEqual(Workflow.objects.count(), 1)
 
+    def test_api_create_remote_ocr_action_requires_consumption_trigger(
+        self,
+    ) -> None:
+        """
+        GIVEN:
+            - API request to create a workflow with a remote OCR action
+            - No consumption started trigger, so the action could never run
+        WHEN:
+            - API is called
+        THEN:
+            - Correct HTTP 400 response
+            - No objects are created
+        """
+        existing_count = Workflow.objects.count()
+
+        response = self.client.post(
+            self.ENDPOINT,
+            json.dumps(
+                {
+                    "name": "Remote OCR too late",
+                    "order": 1,
+                    "triggers": [
+                        {
+                            "type": WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED,
+                        },
+                    ],
+                    "actions": [
+                        {
+                            "type": WorkflowAction.WorkflowActionType.REMOTE_OCR,
+                        },
+                    ],
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertEqual(Workflow.objects.count(), existing_count)
+
+    def test_api_create_remote_ocr_action_with_consumption_trigger(self) -> None:
+        """
+        GIVEN:
+            - API request to create a workflow with a remote OCR action
+            - A consumption started trigger alongside another trigger type
+        WHEN:
+            - API is called
+        THEN:
+            - The workflow is created, the action applies to consumption only
+        """
+        response = self.client.post(
+            self.ENDPOINT,
+            json.dumps(
+                {
+                    "name": "Remote OCR on consume",
+                    "order": 1,
+                    "triggers": [
+                        {
+                            "type": WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
+                            "filter_filename": "*.pdf",
+                        },
+                        {
+                            "type": WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED,
+                        },
+                    ],
+                    "actions": [
+                        {
+                            "type": WorkflowAction.WorkflowActionType.REMOTE_OCR,
+                        },
+                    ],
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_201_CREATED)
+
+    def test_api_partial_update_adds_remote_ocr_action(self) -> None:
+        """
+        GIVEN:
+            - An existing workflow with a consumption started trigger
+        WHEN:
+            - A partial update adds a remote OCR action without resubmitting triggers
+        THEN:
+            - The existing trigger is considered and the update succeeds
+        """
+        response = self.client.patch(
+            f"{self.ENDPOINT}{self.workflow.id}/",
+            json.dumps(
+                {
+                    "actions": [
+                        {
+                            "type": WorkflowAction.WorkflowActionType.REMOTE_OCR,
+                        },
+                    ],
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        self.assertEqual(
+            self.workflow.actions.get().type,
+            WorkflowAction.WorkflowActionType.REMOTE_OCR,
+        )
+
+    def test_api_partial_update_cannot_remove_remote_ocr_trigger(self) -> None:
+        """
+        GIVEN:
+            - An existing workflow with a remote OCR action
+            - An existing consumption started trigger
+        WHEN:
+            - A partial update replaces the trigger without resubmitting actions
+        THEN:
+            - The existing action is considered and the update is rejected
+        """
+        self.action.type = WorkflowAction.WorkflowActionType.REMOTE_OCR
+        self.action.save()
+
+        response = self.client.patch(
+            f"{self.ENDPOINT}{self.workflow.id}/",
+            json.dumps(
+                {
+                    "triggers": [
+                        {
+                            "type": WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
+                        },
+                    ],
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertEqual(self.workflow.triggers.get(), self.trigger)
+
     def test_api_create_workflow_trigger_action_empty_fields(self) -> None:
         """
         GIVEN:

src/documents/tests/test_workflows.py

@@ -5409,3 +5409,82 @@ class TestDateWorkflowLocalization(
             document = Document.objects.first()
             assert document is not None
             assert document.title == expected_title
+
+
+class TestRemoteOCRWorkflowAction(DirectoriesMixin, SampleDirMixin, APITestCase):
+    def _make_workflow(self, trigger_type) -> None:
+        trigger = WorkflowTrigger.objects.create(type=trigger_type)
+        action = WorkflowAction.objects.create(
+            type=WorkflowAction.WorkflowActionType.REMOTE_OCR,
+        )
+        w = Workflow.objects.create(name="Remote OCR", order=0)
+        w.triggers.add(trigger)
+        w.actions.add(action)
+        w.save()
+
+    def test_consumption_trigger_requests_remote_ocr(self) -> None:
+        """
+        GIVEN:
+            - A consumption workflow with a remote OCR action
+        WHEN:
+            - A matching document is consumed
+        THEN:
+            - The overrides ask for remote OCR, which is what the consumer
+              reads when choosing a parser
+        """
+        self._make_workflow(WorkflowTrigger.WorkflowTriggerType.CONSUMPTION)
+
+        test_file = shutil.copy(
+            self.SAMPLE_DIR / "simple.pdf",
+            self.dirs.scratch_dir / "simple.pdf",
+        )
+        overrides = DocumentMetadataOverrides()
+
+        run_workflows(
+            WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
+            ConsumableDocument(
+                source=DocumentSource.ConsumeFolder,
+                original_file=test_file,
+            ),
+            overrides=overrides,
+        )
+
+        self.assertTrue(overrides.remote_ocr)
+
+    def test_other_trigger_types_are_ignored(self) -> None:
+        """
+        GIVEN:
+            - A workflow with a remote OCR action that also has a
+              non-consumption trigger, which is a valid combination
+        WHEN:
+            - The non-consumption trigger fires
+        THEN:
+            - The action is skipped, since the document has already been
+              parsed by this point
+        """
+        trigger = WorkflowTrigger.objects.create(
+            type=WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
+        )
+        updated_trigger = WorkflowTrigger.objects.create(
+            type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
+        )
+        action = WorkflowAction.objects.create(
+            type=WorkflowAction.WorkflowActionType.REMOTE_OCR,
+        )
+        w = Workflow.objects.create(name="Remote OCR", order=0)
+        w.triggers.add(trigger, updated_trigger)
+        w.actions.add(action)
+        w.save()
+
+        doc = Document.objects.create(
+            title="sample test",
+            original_filename="sample.pdf",
+        )
+
+        with self.assertLogs("paperless.handlers", level="DEBUG") as cm:
+            run_workflows(
+                WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
+                doc,
+            )
+
+        self.assertIn("only applies to consumption triggers", "".join(cm.output))