Merge branch 'dev' into feature-remote-repect-archive-file-setting

docs/configuration.md

@@ -948,10 +948,11 @@ for display in the web interface.
 
     !!! note
 
-        The **remote OCR parser** (Azure AI) always produces a searchable
+        The **remote OCR parser** (Azure AI) also honors this setting: when
-        PDF and stores it as the archive copy, regardless of this setting.
+        no archive is requested (`never`, or `auto` with a born-digital PDF),
-        `ARCHIVE_FILE_GENERATION=never` has no effect when the remote
+        the remote engine is skipped entirely and locally-extracted text is
-        parser handles a document.
+        used instead, avoiding an unnecessary API call and a duplicate text
+        layer.
 
 #### [`PAPERLESS_OCR_CLEAN=<mode>`](#PAPERLESS_OCR_CLEAN) {#PAPERLESS_OCR_CLEAN}
 

docs/migration-v3.md

@@ -187,10 +187,11 @@ PAPERLESS_ARCHIVE_FILE_GENERATION=auto
 
 ### Remote OCR parser
 
-If you use the **remote OCR parser** (Azure AI), note that it always produces a
+If you use the **remote OCR parser** (Azure AI), `ARCHIVE_FILE_GENERATION` is
-searchable PDF and stores it as the archive copy. `ARCHIVE_FILE_GENERATION=never`
+honored the same way as for the local engine: when no archive is requested
-has no effect for documents handled by the remote parser - the archive is produced
+(`never`, or `auto` with a born-digital PDF), the remote engine is skipped
-unconditionally by the remote engine.
+entirely and locally-extracted text is used instead, avoiding an unnecessary
+API call and a duplicate text layer.
 
 ## Search Index (Whoosh -> Tantivy)
 

docs/usage.md

@@ -576,7 +576,9 @@ The following workflow action types are available:
 - Tags, correspondent, document type and storage path
 - Document owner
 - View and / or edit permissions to users or groups
-- Custom fields. Note that no value for the field will be set
+- Custom fields, optionally with a value. If no value is set, the field is only added to the
+  document and any value it may already have is left untouched. If a value is set, it will
+  overwrite an existing value of that field on the document.
 
 ##### Removal {#workflow-action-removal}
 

src-ui/src/app/components/common/input/custom-fields-values/custom-fields-values.component.spec.ts

@@ -52,10 +52,10 @@ describe('CustomFieldsValuesComponent', () => {
   })
 
   it('should set selectedFields and map values correctly', () => {
-    component.value = { 1: 'value1' }
+    component.value = { 1: 'value1', 3: 0, 4: false }
-    component.selectedFields = [1, 2]
+    component.selectedFields = [1, 2, 3, 4]
-    expect(component.selectedFields).toEqual([1, 2])
+    expect(component.selectedFields).toEqual([1, 2, 3, 4])
-    expect(component.value).toEqual({ 1: 'value1', 2: null })
+    expect(component.value).toEqual({ 1: 'value1', 2: null, 3: 0, 4: false })
   })
 
   it('should return the correct custom field by id', () => {

src-ui/src/app/components/common/input/custom-fields-values/custom-fields-values.component.ts

@@ -77,7 +77,7 @@ export class CustomFieldsValuesComponent extends AbstractInputComponent<Object>
     this._selectedFields = newFields
     // map the selected fields to an object with field_id as key and value as value
     this.value = newFields.reduce((acc, fieldId) => {
-      acc[fieldId] = this.value?.[fieldId] || null
+      acc[fieldId] = this.value?.[fieldId] ?? null
       return acc
     }, {})
     this.onChange(this.value)

src/documents/serialisers.py

@@ -3213,6 +3213,13 @@ class WorkflowActionSerializer(serializers.ModelSerializer[WorkflowAction]):
                         {"assign_title": f'Invalid f-string detected: "{e.args[0]}"'},
                     )
 
+        if attrs.get("assign_custom_fields_values"):
+            # Empty strings treated as None to avoid unexpected behavior
+            attrs["assign_custom_fields_values"] = {
+                field_id: (None if value == "" else value)
+                for field_id, value in attrs["assign_custom_fields_values"].items()
+            }
+
         if (
             "type" in attrs
             and attrs["type"] == WorkflowAction.WorkflowActionType.EMAIL

src/documents/tests/test_api_workflows.py

@@ -422,6 +422,11 @@ class TestApiWorkflows(DirectoriesMixin, APITestCase):
             json.dumps(
                 {
                     "assign_title": "",
+                    "assign_custom_fields": [self.cf1.id, self.cf2.id],
+                    "assign_custom_fields_values": {
+                        str(self.cf1.id): "",
+                        str(self.cf2.id): 0,
+                    },
                 },
             ),
             content_type="application/json",
@@ -429,6 +434,10 @@ class TestApiWorkflows(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_201_CREATED)
         action = WorkflowAction.objects.get(id=response.data["id"])
         self.assertIsNone(action.assign_title)
+        self.assertEqual(
+            action.assign_custom_fields_values,
+            {str(self.cf1.id): None, str(self.cf2.id): 0},
+        )
 
         response = self.client.post(
             self.ENDPOINT_TRIGGERS,

src/documents/tests/test_workflows.py

@@ -2000,6 +2000,55 @@ class TestWorkflows(
                 r"Doc added in \w{3,}",
             )  # Match any 3-letter month name
 
+    def test_document_updated_workflow_existing_custom_field_empty_value(self) -> None:
+        """
+        GIVEN:
+            - Existing workflow with UPDATED trigger and action that assigns a custom field
+              with an empty value
+        WHEN:
+            - Document is updated that already contains the field with a value
+        THEN:
+            - The existing value is left untouched, see GH #13627
+        """
+        trigger = WorkflowTrigger.objects.create(
+            type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
+            filter_has_document_type=self.dt,
+        )
+        action = WorkflowAction.objects.create()
+        action.assign_custom_fields.add(self.cf1)
+        action.assign_custom_fields_values = {self.cf1.pk: ""}
+        action.save()
+        w = Workflow.objects.create(
+            name="Workflow 1",
+            order=0,
+        )
+        w.triggers.add(trigger)
+        w.actions.add(action)
+        w.save()
+
+        doc = Document.objects.create(
+            title="sample test",
+            correspondent=self.c,
+            original_filename="sample.pdf",
+        )
+        CustomFieldInstance.objects.create(
+            document=doc,
+            field=self.cf1,
+            value_text="existing value",
+        )
+
+        superuser = User.objects.create_superuser("superuser")
+        self.client.force_authenticate(user=superuser)
+
+        self.client.patch(
+            f"/api/documents/{doc.id}/",
+            {"document_type": self.dt.id},
+            format="json",
+        )
+
+        doc.refresh_from_db()
+        self.assertEqual(doc.custom_fields.get(field=self.cf1).value, "existing value")
+
     def test_document_updated_workflow_existing_custom_field(self) -> None:
         """
         GIVEN:

src/documents/workflows/mutations.py

@@ -105,7 +105,8 @@ def apply_assignment_to_document(
                 field=field,
                 document=document,
             ).first()
-            if instance and args[value_field_name] is not None:
+            # empty string is indistinguishable from no value in the UI
+            if instance and args[value_field_name] not in (None, ""):
                 setattr(instance, value_field_name, args[value_field_name])
                 instance.save()
             elif not instance:

src/paperless/parsers/remote.py

@@ -3,7 +3,9 @@ Built-in remote-OCR document parser.
 
 Handles documents by sending them to a configured remote OCR engine
 (currently Azure AI Vision / Document Intelligence) and retrieving both
-the extracted text and a searchable PDF with an embedded text layer.
+the extracted text and a searchable PDF with an embedded text layer. For
+born-digital PDFs that need no archive copy, the remote call is skipped
+entirely in favor of locally-extracted text (see ``RemoteDocumentParser.parse``).
 
 When no engine is configured, ``score()`` returns ``None`` so the parser
 is effectively invisible to the registry — the tesseract parser handles
@@ -22,6 +24,8 @@ from typing import Self
 from django.conf import settings
 
 from documents.parsers import ParseError
+from paperless.parsers.utils import extract_pdf_text
+from paperless.parsers.utils import post_process_text
 from paperless.version import __full_version_str__
 
 if TYPE_CHECKING:
@@ -70,8 +74,11 @@ class RemoteDocumentParser:
     """Parse documents via a remote OCR API (currently Azure AI Vision).
 
     This parser sends documents to a remote engine that returns both
-    extracted text and a searchable PDF with an embedded text layer.
+    extracted text and a searchable PDF with an embedded text layer,
-    It does not depend on Tesseract or ocrmypdf.
+    except when ``parse()`` is called with ``produce_archive=False`` for
+    a PDF, in which case the remote call is skipped and only locally
+    extracted text is returned (no archive). It does not depend on
+    Tesseract or ocrmypdf.
 
     Class attributes
     ----------------
@@ -160,8 +167,11 @@ class RemoteDocumentParser:
         Returns
         -------
         bool
-            Always True — the remote engine always returns a PDF with an
+            Always True — the remote engine is capable of returning a PDF
-            embedded text layer that serves as the archive copy.
+            with an embedded text layer to serve as the archive copy.
+            Whether it actually does so for a given document depends on
+            ``produce_archive`` passed to :meth:`parse` (see there for when
+            the remote engine call, and thus archive generation, is skipped).
         """
         return True
 
@@ -218,6 +228,12 @@ class RemoteDocumentParser:
     ) -> None:
         """Send the document to the remote engine and store results.
 
+        When *produce_archive* is False for a PDF, the caller (via
+        ``documents.consumer.should_produce_archive``) has already determined
+        that the document is born-digital and needs no archive — skip the
+        remote engine entirely rather than re-OCRing it and creating a
+        duplicate text layer.
+
         Parameters
         ----------
         document_path:
@@ -225,8 +241,8 @@ class RemoteDocumentParser:
         mime_type:
             Detected MIME type of the document.
         produce_archive:
-            Ignored — the remote engine always returns a searchable PDF,
+            Whether an archive copy is wanted. For PDFs, False skips the
-            which is stored as the archive copy regardless of this flag.
+            remote engine and uses locally-extracted text instead.
         """
         config = RemoteEngineConfig(
             engine=settings.REMOTE_OCR_ENGINE,
@@ -241,6 +257,16 @@ class RemoteDocumentParser:
             self._text = ""
             return
 
+        if not produce_archive and mime_type == "application/pdf":
+            logger.debug(
+                "Remote OCR: skipped — no archive requested, "
+                "using locally-extracted text",
+            )
+            self._text = (
+                post_process_text(extract_pdf_text(document_path, log=logger)) or ""
+            )
+            return
+
         if config.engine == "azureai":
             self._text = self._azure_ai_vision_parse(document_path, config)
 

src/paperless/tests/parsers/test_remote_parser.py

@@ -337,6 +337,117 @@ class TestRemoteParserParse:
         assert remote_parser.get_date() is None
 
 
+# ---------------------------------------------------------------------------
+# parse() — produce_archive=False skips the remote engine (PDFs only)
+# ---------------------------------------------------------------------------
+
+
+class TestRemoteParserSkipsWhenNoArchiveWanted:
+    """When the caller has already decided no archive is needed for a PDF
+    (documents.consumer.should_produce_archive), the remote engine call is
+    skipped entirely in favor of locally-extracted text.
+    """
+
+    def test_pdf_skips_azure_when_no_archive_requested(
+        self,
+        remote_parser: RemoteDocumentParser,
+        simple_digital_pdf_file: Path,
+        azure_client: Mock,
+    ) -> None:
+        """
+        GIVEN: produce_archive=False for a PDF
+        WHEN:  parse() is called
+        THEN:  Azure is never invoked, no archive is produced, and text
+               comes from local pdftotext extraction
+        """
+        remote_parser.parse(
+            simple_digital_pdf_file,
+            "application/pdf",
+            produce_archive=False,
+        )
+
+        azure_client.begin_analyze_document.assert_not_called()
+        assert remote_parser.get_archive_path() is None
+        assert remote_parser.get_text() != ""
+
+    def test_pdf_no_archive_requested_text_matches_local_extraction(
+        self,
+        remote_parser: RemoteDocumentParser,
+        simple_digital_pdf_file: Path,
+        azure_client: Mock,
+        mocker: MockerFixture,
+    ) -> None:
+        """
+        GIVEN: produce_archive=False for a PDF
+        WHEN:  parse() is called
+        THEN:  the returned text is exactly the locally-extracted text,
+               not anything from the (unused) Azure mock
+        """
+        mocker.patch(
+            "paperless.parsers.remote.extract_pdf_text",
+            return_value="Local digital text.",
+        )
+
+        remote_parser.parse(
+            simple_digital_pdf_file,
+            "application/pdf",
+            produce_archive=False,
+        )
+
+        assert remote_parser.get_text() == "Local digital text."
+
+    def test_pdf_no_archive_requested_closes_no_client(
+        self,
+        remote_parser: RemoteDocumentParser,
+        simple_digital_pdf_file: Path,
+        azure_client: Mock,
+    ) -> None:
+        remote_parser.parse(
+            simple_digital_pdf_file,
+            "application/pdf",
+            produce_archive=False,
+        )
+
+        azure_client.close.assert_not_called()
+
+    def test_non_pdf_still_calls_azure_when_no_archive_requested(
+        self,
+        remote_parser: RemoteDocumentParser,
+        simple_digital_pdf_file: Path,
+        azure_client: Mock,
+    ) -> None:
+        """
+        Images have no local-text fallback, so produce_archive=False does
+        not skip the remote engine for non-PDF MIME types.
+        """
+        remote_parser.parse(
+            simple_digital_pdf_file,
+            "image/png",
+            produce_archive=False,
+        )
+
+        azure_client.begin_analyze_document.assert_called_once()
+        assert remote_parser.get_text() == _DEFAULT_TEXT
+
+    @pytest.mark.usefixtures("no_engine_settings")
+    def test_unconfigured_engine_takes_precedence_over_skip(
+        self,
+        remote_parser: RemoteDocumentParser,
+        simple_digital_pdf_file: Path,
+    ) -> None:
+        """An unconfigured engine still short-circuits before the
+        produce_archive check, returning empty text as before.
+        """
+        remote_parser.parse(
+            simple_digital_pdf_file,
+            "application/pdf",
+            produce_archive=False,
+        )
+
+        assert remote_parser.get_text() == ""
+        assert remote_parser.get_archive_path() is None
+
+
 # ---------------------------------------------------------------------------
 # parse() — Azure failure path
 # ---------------------------------------------------------------------------