Merge branch 'dev' into feature-better-asn-operations

pyproject.toml

@@ -46,14 +46,14 @@ dependencies = [
   "drf-writable-nested~=0.7.1",
   "filelock~=3.20.0",
   "flower~=2.0.1",
-  "gotenberg-client~=0.13.1",
+  "gotenberg-client~=0.12.0",
   "httpx-oauth~=0.16",
   "imap-tools~=1.11.0",
   "inotifyrecursive~=0.3",
   "jinja2~=3.1.5",
   "langdetect~=1.0.9",
   "nltk~=3.9.1",
-  "ocrmypdf~=16.13.0",
+  "ocrmypdf~=16.12.0",
   "pathvalidate~=3.3.1",
   "pdf2image~=1.17.0",
   "python-dateutil~=2.9.0",

src/documents/barcodes.py

@@ -16,6 +16,7 @@ from pikepdf import Pdf
 from documents.converters import convert_from_tiff_to_pdf
 from documents.data_models import ConsumableDocument
 from documents.data_models import DocumentMetadataOverrides
+from documents.models import Document
 from documents.models import Tag
 from documents.plugins.base import ConsumeTaskPlugin
 from documents.plugins.base import StopConsumeTaskError
@@ -115,6 +116,24 @@ class BarcodePlugin(ConsumeTaskPlugin):
         self._tiff_conversion_done = False
         self.barcodes: list[Barcode] = []
 
+    def _apply_detected_asn(self, detected_asn: int) -> None:
+        """
+        Apply a detected ASN to metadata if allowed.
+        """
+        if (
+            self.metadata.skip_asn_if_exists
+            and Document.global_objects.filter(
+                archive_serial_number=detected_asn,
+            ).exists()
+        ):
+            logger.info(
+                f"Found ASN in barcode {detected_asn} but skipping because it already exists.",
+            )
+            return
+
+        logger.info(f"Found ASN in barcode: {detected_asn}")
+        self.metadata.asn = detected_asn
+
     def run(self) -> None:
         # Some operations may use PIL, override pixel setting if needed
         maybe_override_pixel_limit()
@@ -186,13 +205,8 @@ class BarcodePlugin(ConsumeTaskPlugin):
 
         # Update/overwrite an ASN if possible
         # After splitting, as otherwise each split document gets the same ASN
-        if (
+        if self.settings.barcode_enable_asn and (located_asn := self.asn) is not None:
-            self.settings.barcode_enable_asn
+            self._apply_detected_asn(located_asn)
-            and not self.metadata.skip_asn
-            and (located_asn := self.asn) is not None
-        ):
-            logger.info(f"Found ASN in barcode: {located_asn}")
-            self.metadata.asn = located_asn
 
     def cleanup(self) -> None:
         self.temp_dir.cleanup()

src/documents/bulk_edit.py

@@ -7,7 +7,6 @@ from pathlib import Path
 from typing import TYPE_CHECKING
 from typing import Literal
 
-from celery import chain
 from celery import chord
 from celery import group
 from celery import shared_task
@@ -38,6 +37,42 @@ if TYPE_CHECKING:
 logger: logging.Logger = logging.getLogger("paperless.bulk_edit")
 
 
+@shared_task(bind=True)
+def restore_archive_serial_numbers_task(
+    self,
+    backup: dict[int, int],
+    *args,
+    **kwargs,
+) -> None:
+    restore_archive_serial_numbers(backup)
+
+
+def release_archive_serial_numbers(doc_ids: list[int]) -> dict[int, int]:
+    """
+    Clears ASNs on documents that are about to be replaced so new documents
+    can be assigned ASNs without uniqueness collisions. Returns a backup map
+    of doc_id -> previous ASN for potential restoration.
+    """
+    qs = Document.objects.filter(
+        id__in=doc_ids,
+        archive_serial_number__isnull=False,
+    ).only("pk", "archive_serial_number")
+    backup = dict(qs.values_list("pk", "archive_serial_number"))
+    qs.update(archive_serial_number=None)
+    logger.info(f"Released archive serial numbers for documents {list(backup.keys())}")
+    return backup
+
+
+def restore_archive_serial_numbers(backup: dict[int, int]) -> None:
+    """
+    Restores ASNs using the provided backup map, intended for
+    rollback when replacement consumption fails.
+    """
+    for doc_id, asn in backup.items():
+        Document.objects.filter(pk=doc_id).update(archive_serial_number=asn)
+    logger.info(f"Restored archive serial numbers for documents {list(backup.keys())}")
+
+
 def set_correspondent(
     doc_ids: list[int],
     correspondent: Correspondent,
@@ -386,6 +421,7 @@ def merge(
 
     merged_pdf = pikepdf.new()
     version: str = merged_pdf.pdf_version
+    handoff_asn: int | None = None
     # use doc_ids to preserve order
     for doc_id in doc_ids:
         doc = qs.get(id=doc_id)
@@ -401,6 +437,8 @@ def merge(
                 version = max(version, pdf.pdf_version)
                 merged_pdf.pages.extend(pdf.pages)
             affected_docs.append(doc.id)
+            if handoff_asn is None and doc.archive_serial_number is not None:
+                handoff_asn = doc.archive_serial_number
         except Exception as e:
             logger.exception(
                 f"Error merging document {doc.id}, it will not be included in the merge: {e}",
@@ -426,6 +464,8 @@ def merge(
                 DocumentMetadataOverrides.from_document(metadata_document)
             )
             overrides.title = metadata_document.title + " (merged)"
+            if metadata_document.archive_serial_number is not None:
+                handoff_asn = metadata_document.archive_serial_number
         else:
             overrides = DocumentMetadataOverrides()
     else:
@@ -433,8 +473,11 @@ def merge(
 
     if user is not None:
         overrides.owner_id = user.id
-    # Avoid copying or detecting ASN from merged PDFs to prevent collision
+    if not delete_originals:
-    overrides.skip_asn = True
+        overrides.skip_asn_if_exists = True
+
+    if delete_originals and handoff_asn is not None:
+        overrides.asn = handoff_asn
 
     logger.info("Adding merged document to the task queue.")
 
@@ -447,12 +490,20 @@ def merge(
     )
 
     if delete_originals:
+        backup = release_archive_serial_numbers(affected_docs)
         logger.info(
             "Queueing removal of original documents after consumption of merged document",
         )
-        chain(consume_task, delete.si(affected_docs)).delay()
+        try:
-    else:
+            consume_task.apply_async(
-        consume_task.delay()
+                link=[delete.si(affected_docs)],
+                link_error=[restore_archive_serial_numbers_task.s(backup)],
+            )
+        except Exception:
+            restore_archive_serial_numbers(backup)
+            raise
+        else:
+            consume_task.delay()
 
     return "OK"
 
@@ -494,6 +545,8 @@ def split(
                 overrides.title = f"{doc.title} (split {idx + 1})"
                 if user is not None:
                     overrides.owner_id = user.id
+                if not delete_originals:
+                    overrides.skip_asn_if_exists = True
                 logger.info(
                     f"Adding split document with pages {split_doc} to the task queue.",
                 )
@@ -508,10 +561,20 @@ def split(
                 )
 
             if delete_originals:
+                backup = release_archive_serial_numbers([doc.id])
                 logger.info(
                     "Queueing removal of original document after consumption of the split documents",
                 )
-                chord(header=consume_tasks, body=delete.si([doc.id])).delay()
+                try:
+                    chord(
+                        header=consume_tasks,
+                        body=delete.si([doc.id]),
+                    ).apply_async(
+                        link_error=[restore_archive_serial_numbers_task.s(backup)],
+                    )
+                except Exception:
+                    restore_archive_serial_numbers(backup)
+                    raise
             else:
                 group(consume_tasks).delay()
 
@@ -614,7 +677,10 @@ def edit_pdf(
             )
             if user is not None:
                 overrides.owner_id = user.id
-
+            if not delete_original:
+                overrides.skip_asn_if_exists = True
+            if delete_original and len(pdf_docs) == 1:
+                overrides.asn = doc.archive_serial_number
             for idx, pdf in enumerate(pdf_docs, start=1):
                 filepath: Path = (
                     Path(tempfile.mkdtemp(dir=settings.SCRATCH_DIR))
@@ -633,7 +699,17 @@ def edit_pdf(
                 )
 
             if delete_original:
-                chord(header=consume_tasks, body=delete.si([doc.id])).delay()
+                backup = release_archive_serial_numbers([doc.id])
+                try:
+                    chord(
+                        header=consume_tasks,
+                        body=delete.si([doc.id]),
+                    ).apply_async(
+                        link_error=[restore_archive_serial_numbers_task.s(backup)],
+                    )
+                except Exception:
+                    restore_archive_serial_numbers(backup)
+                    raise
             else:
                 group(consume_tasks).delay()
 

src/documents/consumer.py

@@ -696,7 +696,7 @@ class ConsumerPlugin(
                 pk=self.metadata.storage_path_id,
             )
 
-        if self.metadata.asn is not None and not self.metadata.skip_asn:
+        if self.metadata.asn is not None:
             document.archive_serial_number = self.metadata.asn
 
         if self.metadata.owner_id:
@@ -812,8 +812,8 @@ class ConsumerPreflightPlugin(
         """
         Check that if override_asn is given, it is unique and within a valid range
         """
-        if self.metadata.skip_asn or self.metadata.asn is None:
+        if self.metadata.asn is None:
-            # if skip is set or ASN is None
+            # if ASN is None
             return
         # Validate the range is above zero and less than uint32_t max
         # otherwise, Whoosh can't handle it in the index

src/documents/data_models.py

@@ -30,7 +30,7 @@ class DocumentMetadataOverrides:
     change_users: list[int] | None = None
     change_groups: list[int] | None = None
     custom_fields: dict | None = None
-    skip_asn: bool = False
+    skip_asn_if_exists: bool = False
 
     def update(self, other: "DocumentMetadataOverrides") -> "DocumentMetadataOverrides":
         """
@@ -50,8 +50,8 @@ class DocumentMetadataOverrides:
             self.storage_path_id = other.storage_path_id
         if other.owner_id is not None:
             self.owner_id = other.owner_id
-        if other.skip_asn:
+        if other.skip_asn_if_exists:
-            self.skip_asn = True
+            self.skip_asn_if_exists = True
 
         # merge
         if self.tag_ids is None:

src/documents/serialisers.py

@@ -580,34 +580,30 @@ class TagSerializer(MatchingModelSerializer, OwnedObjectSerializer):
         ),
     )
     def get_children(self, obj):
-        children_map = self.context.get("children_map")
+        filter_q = self.context.get("document_count_filter")
-        if children_map is not None:
+        request = self.context.get("request")
-            children = children_map.get(obj.pk, [])
+        if filter_q is None:
-        else:
+            user = getattr(request, "user", None) if request else None
-            filter_q = self.context.get("document_count_filter")
+            filter_q = get_document_count_filter_for_user(user)
-            request = self.context.get("request")
+            self.context["document_count_filter"] = filter_q
-            if filter_q is None:
-                user = getattr(request, "user", None) if request else None
-                filter_q = get_document_count_filter_for_user(user)
-                self.context["document_count_filter"] = filter_q
 
-            children = (
+        children_queryset = (
-                obj.get_children_queryset()
+            obj.get_children_queryset()
-                .select_related("owner")
+            .select_related("owner")
-                .annotate(document_count=Count("documents", filter=filter_q))
+            .annotate(document_count=Count("documents", filter=filter_q))
-            )
+        )
 
-            view = self.context.get("view")
+        view = self.context.get("view")
-            ordering = (
+        ordering = (
-                OrderingFilter().get_ordering(request, children, view)
+            OrderingFilter().get_ordering(request, children_queryset, view)
-                if request and view
+            if request and view
-                else None
+            else None
-            )
+        )
-            ordering = ordering or (Lower("name"),)
+        ordering = ordering or (Lower("name"),)
-            children = children.order_by(*ordering)
+        children_queryset = children_queryset.order_by(*ordering)
 
         serializer = TagSerializer(
-            children,
+            children_queryset,
             many=True,
             user=self.user,
             full_perms=self.full_perms,

src/documents/tests/test_bulk_edit.py

@@ -603,23 +603,21 @@ class TestPDFActions(DirectoriesMixin, TestCase):
             expected_filename,
         )
         self.assertEqual(consume_file_args[1].title, None)
-        self.assertTrue(consume_file_args[1].skip_asn)
+        # No metadata_document_id, delete_originals False, so ASN should be None
+        self.assertIsNone(consume_file_args[1].asn)
 
         # With metadata_document_id overrides
         result = bulk_edit.merge(doc_ids, metadata_document_id=metadata_document_id)
         consume_file_args, _ = mock_consume_file.call_args
         self.assertEqual(consume_file_args[1].title, "B (merged)")
         self.assertEqual(consume_file_args[1].created, self.doc2.created)
-        self.assertTrue(consume_file_args[1].skip_asn)
 
         self.assertEqual(result, "OK")
 
     @mock.patch("documents.bulk_edit.delete.si")
     @mock.patch("documents.tasks.consume_file.s")
-    @mock.patch("documents.bulk_edit.chain")
     def test_merge_and_delete_originals(
         self,
-        mock_chain,
         mock_consume_file,
         mock_delete_documents,
     ):
@@ -633,6 +631,12 @@ class TestPDFActions(DirectoriesMixin, TestCase):
             - Document deletion task should be called
         """
         doc_ids = [self.doc1.id, self.doc2.id, self.doc3.id]
+        self.doc1.archive_serial_number = 101
+        self.doc2.archive_serial_number = 102
+        self.doc3.archive_serial_number = 103
+        self.doc1.save()
+        self.doc2.save()
+        self.doc3.save()
 
         result = bulk_edit.merge(doc_ids, delete_originals=True)
         self.assertEqual(result, "OK")
@@ -643,7 +647,8 @@ class TestPDFActions(DirectoriesMixin, TestCase):
 
         mock_consume_file.assert_called()
         mock_delete_documents.assert_called()
-        mock_chain.assert_called_once()
+        consume_sig = mock_consume_file.return_value
+        consume_sig.apply_async.assert_called_once()
 
         consume_file_args, _ = mock_consume_file.call_args
         self.assertEqual(
@@ -651,7 +656,7 @@ class TestPDFActions(DirectoriesMixin, TestCase):
             expected_filename,
         )
         self.assertEqual(consume_file_args[1].title, None)
-        self.assertTrue(consume_file_args[1].skip_asn)
+        self.assertEqual(consume_file_args[1].asn, 101)
 
         delete_documents_args, _ = mock_delete_documents.call_args
         self.assertEqual(
@@ -659,6 +664,92 @@ class TestPDFActions(DirectoriesMixin, TestCase):
             doc_ids,
         )
 
+        self.doc1.refresh_from_db()
+        self.doc2.refresh_from_db()
+        self.doc3.refresh_from_db()
+        self.assertIsNone(self.doc1.archive_serial_number)
+        self.assertIsNone(self.doc2.archive_serial_number)
+        self.assertIsNone(self.doc3.archive_serial_number)
+
+    @mock.patch("documents.bulk_edit.delete.si")
+    @mock.patch("documents.tasks.consume_file.s")
+    def test_merge_and_delete_originals_restore_on_failure(
+        self,
+        mock_consume_file,
+        mock_delete_documents,
+    ):
+        """
+        GIVEN:
+            - Existing documents
+        WHEN:
+            - Merge action with deleting documents is called with 1 document
+            - Error occurs when queuing consume file task
+        THEN:
+            - Archive serial numbers are restored
+        """
+        doc_ids = [self.doc1.id]
+        self.doc1.archive_serial_number = 111
+        self.doc1.save()
+        sig = mock.Mock()
+        sig.apply_async.side_effect = Exception("boom")
+        mock_consume_file.return_value = sig
+
+        with self.assertRaises(Exception):
+            bulk_edit.merge(doc_ids, delete_originals=True)
+
+        self.doc1.refresh_from_db()
+        self.assertEqual(self.doc1.archive_serial_number, 111)
+
+    @mock.patch("documents.bulk_edit.delete.si")
+    @mock.patch("documents.tasks.consume_file.s")
+    def test_merge_and_delete_originals_metadata_handoff(
+        self,
+        mock_consume_file,
+        mock_delete_documents,
+    ):
+        """
+        GIVEN:
+            - Existing documents with ASNs
+        WHEN:
+            - Merge with delete_originals=True and metadata_document_id set
+        THEN:
+            - Handoff ASN uses metadata document ASN
+        """
+        doc_ids = [self.doc1.id, self.doc2.id]
+        self.doc1.archive_serial_number = 101
+        self.doc2.archive_serial_number = 202
+        self.doc1.save()
+        self.doc2.save()
+
+        result = bulk_edit.merge(
+            doc_ids,
+            metadata_document_id=self.doc2.id,
+            delete_originals=True,
+        )
+        self.assertEqual(result, "OK")
+
+        consume_file_args, _ = mock_consume_file.call_args
+        self.assertEqual(consume_file_args[1].asn, 202)
+
+    def test_restore_archive_serial_numbers_task(self):
+        """
+        GIVEN:
+            - Existing document with no archive serial number
+        WHEN:
+            - Restore archive serial number task is called with backup data
+        THEN:
+            - Document archive serial number is restored
+        """
+        self.doc1.archive_serial_number = 444
+        self.doc1.save()
+        Document.objects.filter(pk=self.doc1.id).update(archive_serial_number=None)
+
+        backup = {self.doc1.id: 444}
+        bulk_edit.restore_archive_serial_numbers_task(backup)
+
+        self.doc1.refresh_from_db()
+        self.assertEqual(self.doc1.archive_serial_number, 444)
+
     @mock.patch("documents.tasks.consume_file.s")
     def test_merge_with_archive_fallback(self, mock_consume_file):
         """
@@ -727,6 +818,7 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         self.assertEqual(mock_consume_file.call_count, 2)
         consume_file_args, _ = mock_consume_file.call_args
         self.assertEqual(consume_file_args[1].title, "B (split 2)")
+        self.assertIsNone(consume_file_args[1].asn)
 
         self.assertEqual(result, "OK")
 
@@ -751,6 +843,8 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         """
         doc_ids = [self.doc2.id]
         pages = [[1, 2], [3]]
+        self.doc2.archive_serial_number = 200
+        self.doc2.save()
 
         result = bulk_edit.split(doc_ids, pages, delete_originals=True)
         self.assertEqual(result, "OK")
@@ -768,6 +862,42 @@ class TestPDFActions(DirectoriesMixin, TestCase):
             doc_ids,
         )
 
+        self.doc2.refresh_from_db()
+        self.assertIsNone(self.doc2.archive_serial_number)
+
+    @mock.patch("documents.bulk_edit.delete.si")
+    @mock.patch("documents.tasks.consume_file.s")
+    @mock.patch("documents.bulk_edit.chord")
+    def test_split_restore_on_failure(
+        self,
+        mock_chord,
+        mock_consume_file,
+        mock_delete_documents,
+    ):
+        """
+        GIVEN:
+            - Existing documents
+        WHEN:
+            - Split action with deleting documents is called with 1 document and 2 page groups
+            - Error occurs when queuing chord task
+        THEN:
+            - Archive serial numbers are restored
+        """
+        doc_ids = [self.doc2.id]
+        pages = [[1, 2]]
+        self.doc2.archive_serial_number = 222
+        self.doc2.save()
+
+        sig = mock.Mock()
+        sig.apply_async.side_effect = Exception("boom")
+        mock_chord.return_value = sig
+
+        result = bulk_edit.split(doc_ids, pages, delete_originals=True)
+        self.assertEqual(result, "OK")
+
+        self.doc2.refresh_from_db()
+        self.assertEqual(self.doc2.archive_serial_number, 222)
+
     @mock.patch("documents.tasks.consume_file.delay")
     @mock.patch("pikepdf.Pdf.save")
     def test_split_with_errors(self, mock_save_pdf, mock_consume_file):
@@ -968,10 +1098,49 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         mock_chord.return_value.delay.return_value = None
         doc_ids = [self.doc2.id]
         operations = [{"page": 1}, {"page": 2}]
+        self.doc2.archive_serial_number = 250
+        self.doc2.save()
 
         result = bulk_edit.edit_pdf(doc_ids, operations, delete_original=True)
         self.assertEqual(result, "OK")
         mock_chord.assert_called_once()
+        consume_file_args, _ = mock_consume_file.call_args
+        self.assertEqual(consume_file_args[1].asn, 250)
+        self.doc2.refresh_from_db()
+        self.assertIsNone(self.doc2.archive_serial_number)
+
+    @mock.patch("documents.bulk_edit.delete.si")
+    @mock.patch("documents.tasks.consume_file.s")
+    @mock.patch("documents.bulk_edit.chord")
+    def test_edit_pdf_restore_on_failure(
+        self,
+        mock_chord,
+        mock_consume_file,
+        mock_delete_documents,
+    ):
+        """
+        GIVEN:
+            - Existing document
+        WHEN:
+            - edit_pdf is called with delete_original=True
+            - Error occurs when queuing chord task
+        THEN:
+            - Archive serial numbers are restored
+        """
+        doc_ids = [self.doc2.id]
+        operations = [{"page": 1}]
+        self.doc2.archive_serial_number = 333
+        self.doc2.save()
+
+        sig = mock.Mock()
+        sig.apply_async.side_effect = Exception("boom")
+        mock_chord.return_value = sig
+
+        with self.assertRaises(Exception):
+            bulk_edit.edit_pdf(doc_ids, operations, delete_original=True)
+
+        self.doc2.refresh_from_db()
+        self.assertEqual(self.doc2.archive_serial_number, 333)
 
     @mock.patch("documents.tasks.update_document_content_maybe_archive_file.delay")
     def test_edit_pdf_with_update_document(self, mock_update_document):

src/documents/tests/test_consumer.py

@@ -14,6 +14,7 @@ from django.test import override_settings
 from django.utils import timezone
 from guardian.core import ObjectPermissionChecker
 
+from documents.barcodes import BarcodePlugin
 from documents.consumer import ConsumerError
 from documents.data_models import DocumentMetadataOverrides
 from documents.data_models import DocumentSource
@@ -412,14 +413,6 @@ class TestConsumer(
         self.assertEqual(document.archive_serial_number, 123)
         self._assert_first_last_send_progress()
 
-    def testMetadataOverridesSkipAsnPropagation(self):
-        overrides = DocumentMetadataOverrides()
-        incoming = DocumentMetadataOverrides(skip_asn=True)
-
-        overrides.update(incoming)
-
-        self.assertTrue(overrides.skip_asn)
-
     def testOverrideTitlePlaceholders(self):
         c = Correspondent.objects.create(name="Correspondent Name")
         dt = DocumentType.objects.create(name="DocType Name")
@@ -1240,3 +1233,46 @@ class PostConsumeTestCase(DirectoriesMixin, GetConsumerMixin, TestCase):
                         r"sample\.pdf: Error while executing post-consume script: Command '\[.*\]' returned non-zero exit status \d+\.",
                     ):
                         consumer.run_post_consume_script(doc)
+
+
+class TestMetadataOverrides(TestCase):
+    def test_update_skip_asn_if_exists(self):
+        base = DocumentMetadataOverrides()
+        incoming = DocumentMetadataOverrides(skip_asn_if_exists=True)
+        base.update(incoming)
+        self.assertTrue(base.skip_asn_if_exists)
+
+
+class TestBarcodeApplyDetectedASN(TestCase):
+    """
+    GIVEN:
+        - Existing Documents with ASN 123
+    WHEN:
+        - A BarcodePlugin which detected an ASN
+    THEN:
+        - If skip_asn_if_exists is set, and ASN exists, do not set ASN
+        - If skip_asn_if_exists is set, and ASN does not exist, set ASN
+    """
+
+    def test_apply_detected_asn_skips_existing_when_flag_set(self):
+        doc = Document.objects.create(
+            checksum="X1",
+            title="D1",
+            archive_serial_number=123,
+        )
+        metadata = DocumentMetadataOverrides(skip_asn_if_exists=True)
+        plugin = BarcodePlugin(
+            input_doc=mock.Mock(),
+            metadata=metadata,
+            status_mgr=mock.Mock(),
+            base_tmp_dir=tempfile.gettempdir(),
+            task_id="test-task",
+        )
+
+        plugin._apply_detected_asn(123)
+        self.assertIsNone(plugin.metadata.asn)
+
+        doc.hard_delete()
+
+        plugin._apply_detected_asn(123)
+        self.assertEqual(plugin.metadata.asn, 123)

src/documents/views.py

@@ -448,43 +448,8 @@ class TagViewSet(ModelViewSet, PermissionsAwareDocumentCountMixin):
     def get_serializer_context(self):
         context = super().get_serializer_context()
         context["document_count_filter"] = self.get_document_count_filter()
-        if hasattr(self, "_children_map"):
-            context["children_map"] = self._children_map
         return context
 
-    def list(self, request, *args, **kwargs):
-        """
-        Build a children map once to avoid per-parent queries in the serializer.
-        """
-        queryset = self.filter_queryset(self.get_queryset())
-        ordering = OrderingFilter().get_ordering(request, queryset, self) or (
-            Lower("name"),
-        )
-        queryset = queryset.order_by(*ordering)
-
-        all_tags = list(queryset)
-        descendant_pks = {pk for tag in all_tags for pk in tag.get_descendants_pks()}
-
-        if descendant_pks:
-            filter_q = self.get_document_count_filter()
-            children_source = (
-                Tag.objects.filter(pk__in=descendant_pks | {t.pk for t in all_tags})
-                .select_related("owner")
-                .annotate(document_count=Count("documents", filter=filter_q))
-                .order_by(*ordering)
-            )
-        else:
-            children_source = all_tags
-
-        children_map = {}
-        for tag in children_source:
-            children_map.setdefault(tag.tn_parent_id, []).append(tag)
-        self._children_map = children_map
-
-        page = self.paginate_queryset(queryset)
-        serializer = self.get_serializer(page, many=True)
-        return self.get_paginated_response(serializer.data)
-
     def perform_update(self, serializer):
         old_parent = self.get_object().get_parent()
         tag = serializer.save()

src/locale/en_US/LC_MESSAGES/django.po

@@ -2,7 +2,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: paperless-ngx\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2026-01-12 21:04+0000\n"
+"POT-Creation-Date: 2026-01-08 21:50+0000\n"
 "PO-Revision-Date: 2022-02-17 04:17\n"
 "Last-Translator: \n"
 "Language-Team: English\n"
@@ -1219,35 +1219,35 @@ msgstr ""
 msgid "workflow runs"
 msgstr ""
 
-#: documents/serialisers.py:646
+#: documents/serialisers.py:642
 msgid "Invalid color."
 msgstr ""
 
-#: documents/serialisers.py:1850
+#: documents/serialisers.py:1846
 #, python-format
 msgid "File type %(type)s not supported"
 msgstr ""
 
-#: documents/serialisers.py:1894
+#: documents/serialisers.py:1890
 #, python-format
 msgid "Custom field id must be an integer: %(id)s"
 msgstr ""
 
-#: documents/serialisers.py:1901
+#: documents/serialisers.py:1897
 #, python-format
 msgid "Custom field with id %(id)s does not exist"
 msgstr ""
 
-#: documents/serialisers.py:1918 documents/serialisers.py:1928
+#: documents/serialisers.py:1914 documents/serialisers.py:1924
 msgid ""
 "Custom fields must be a list of integers or an object mapping ids to values."
 msgstr ""
 
-#: documents/serialisers.py:1923
+#: documents/serialisers.py:1919
 msgid "Some custom fields don't exist or were specified twice."
 msgstr ""
 
-#: documents/serialisers.py:2038
+#: documents/serialisers.py:2034
 msgid "Invalid variable detected."
 msgstr ""
 

uv.lock

@@ -104,9 +104,9 @@ dependencies = [
     { name = "isodate", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "typing-extensions", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/44/7b/8115cd713e2caa5e44def85f2b7ebd02a74ae74d7113ba20bdd41fd6dd80/azure_ai_documentintelligence-1.0.2.tar.gz", hash = "sha256:4d75a2513f2839365ebabc0e0e1772f5601b3a8c9a71e75da12440da13b63484", size = 170940, upload-time = "2025-03-27T02:46:20.606Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/44/7b/8115cd713e2caa5e44def85f2b7ebd02a74ae74d7113ba20bdd41fd6dd80/azure_ai_documentintelligence-1.0.2.tar.gz", hash = "sha256:4d75a2513f2839365ebabc0e0e1772f5601b3a8c9a71e75da12440da13b63484", size = 170940 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/d9/75/c9ec040f23082f54ffb1977ff8f364c2d21c79a640a13d1c1809e7fd6b1a/azure_ai_documentintelligence-1.0.2-py3-none-any.whl", hash = "sha256:e1fb446abbdeccc9759d897898a0fe13141ed29f9ad11fc705f951925822ed59", size = 106005, upload-time = "2025-03-27T02:46:22.356Z" },
+    { url = "https://files.pythonhosted.org/packages/d9/75/c9ec040f23082f54ffb1977ff8f364c2d21c79a640a13d1c1809e7fd6b1a/azure_ai_documentintelligence-1.0.2-py3-none-any.whl", hash = "sha256:e1fb446abbdeccc9759d897898a0fe13141ed29f9ad11fc705f951925822ed59", size = 106005 },
 ]
 
 [[package]]
@@ -118,9 +118,9 @@ dependencies = [
     { name = "six", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "typing-extensions", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/75/aa/7c9db8edd626f1a7d99d09ef7926f6f4fb34d5f9fa00dc394afdfe8e2a80/azure_core-1.33.0.tar.gz", hash = "sha256:f367aa07b5e3005fec2c1e184b882b0b039910733907d001c20fb08ebb8c0eb9", size = 295633, upload-time = "2025-04-03T23:51:02.058Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/75/aa/7c9db8edd626f1a7d99d09ef7926f6f4fb34d5f9fa00dc394afdfe8e2a80/azure_core-1.33.0.tar.gz", hash = "sha256:f367aa07b5e3005fec2c1e184b882b0b039910733907d001c20fb08ebb8c0eb9", size = 295633 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/07/b7/76b7e144aa53bd206bf1ce34fa75350472c3f69bf30e5c8c18bc9881035d/azure_core-1.33.0-py3-none-any.whl", hash = "sha256:9b5b6d0223a1d38c37500e6971118c1e0f13f54951e6893968b38910bc9cda8f", size = 207071, upload-time = "2025-04-03T23:51:03.806Z" },
+    { url = "https://files.pythonhosted.org/packages/07/b7/76b7e144aa53bd206bf1ce34fa75350472c3f69bf30e5c8c18bc9881035d/azure_core-1.33.0-py3-none-any.whl", hash = "sha256:9b5b6d0223a1d38c37500e6971118c1e0f13f54951e6893968b38910bc9cda8f", size = 207071 },
 ]
 
 [[package]]
@@ -1101,15 +1101,15 @@ wheels = [
 
 [[package]]
 name = "gotenberg-client"
-version = "0.13.1"
+version = "0.12.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "httpx", extra = ["http2"], marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "typing-extensions", marker = "(python_full_version < '3.11' and sys_platform == 'darwin') or (python_full_version < '3.11' and sys_platform == 'linux')" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/e4/6c/aaadd6657ca42fbd148b1c00604b98c1ead5a22552f4e5365ce5f0632430/gotenberg_client-0.13.1.tar.gz", hash = "sha256:cdd6bbb535cd739b87446cd1b4f6347ed7f9af6a0d4b19baf7c064b75528ee54", size = 1211143, upload-time = "2025-12-04T20:45:24.151Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/61/6d/07ea213c146bbe91dffebff2d8f4dc61e7076d3dd34d4fd1467f9163e752/gotenberg_client-0.12.0.tar.gz", hash = "sha256:1ab50878024469fc003c414ee9810ceeb00d4d7d7c36bd2fb75318fbff139e9b", size = 1210884, upload-time = "2025-10-15T15:32:37.669Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/79/f6/7a6e6785295332d2538f729ae19516cef712273a5ab8b90d015f08e37a45/gotenberg_client-0.13.1-py3-none-any.whl", hash = "sha256:613f7083a5e8a81699dd8d715c97e5806a424ac48920aad25d7c11b600cdfaf3", size = 51058, upload-time = "2025-12-04T20:45:22.603Z" },
+    { url = "https://files.pythonhosted.org/packages/12/39/fcb24ff053b1be7e5124f56c3d358706a23a328f685c6db33bc9dbc5472d/gotenberg_client-0.12.0-py3-none-any.whl", hash = "sha256:a540b35ac518e902c2860a88fbe448c15fe5a56fe8ec8604e6a2c8c2228fd0cb", size = 51051, upload-time = "2025-10-15T15:32:36.32Z" },
 ]
 
 [[package]]
@@ -1483,9 +1483,9 @@ wheels = [
 name = "isodate"
 version = "0.7.2"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/54/4d/e940025e2ce31a8ce1202635910747e5a87cc3a6a6bb2d00973375014749/isodate-0.7.2.tar.gz", hash = "sha256:4cd1aa0f43ca76f4a6c6c0292a85f40b35ec2e43e315b59f06e6d32171a953e6", size = 29705, upload-time = "2024-10-08T23:04:11.5Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/54/4d/e940025e2ce31a8ce1202635910747e5a87cc3a6a6bb2d00973375014749/isodate-0.7.2.tar.gz", hash = "sha256:4cd1aa0f43ca76f4a6c6c0292a85f40b35ec2e43e315b59f06e6d32171a953e6", size = 29705 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/15/aa/0aca39a37d3c7eb941ba736ede56d689e7be91cab5d9ca846bde3999eba6/isodate-0.7.2-py3-none-any.whl", hash = "sha256:28009937d8031054830160fce6d409ed342816b543597cece116d966c6d99e15", size = 22320, upload-time = "2024-10-08T23:04:09.501Z" },
+    { url = "https://files.pythonhosted.org/packages/15/aa/0aca39a37d3c7eb941ba736ede56d689e7be91cab5d9ca846bde3999eba6/isodate-0.7.2-py3-none-any.whl", hash = "sha256:28009937d8031054830160fce6d409ed342816b543597cece116d966c6d99e15", size = 22320 },
 ]
 
 [[package]]
@@ -2114,7 +2114,7 @@ wheels = [
 
 [[package]]
 name = "ocrmypdf"
-version = "16.13.0"
+version = "16.12.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "deprecation", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -2127,9 +2127,9 @@ dependencies = [
     { name = "pluggy", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "rich", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/8c/52/be1aaece0703a736757d8957c0d4f19c37561054169b501eb0e7132f15e5/ocrmypdf-16.13.0.tar.gz", hash = "sha256:29d37e915234ce717374863a9cc5dd32d29e063dfe60c51380dda71254c88248", size = 7042247, upload-time = "2025-12-24T07:58:35.86Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/2b/ed/dacc0f189e4fcefc52d709e9961929e3f622a85efa5ae47c9d9663d75cab/ocrmypdf-16.12.0.tar.gz", hash = "sha256:a0f6509e7780b286391f8847fae1811d2b157b14283ad74a2431d6755c5c0ed0", size = 7037326, upload-time = "2025-11-11T22:30:14.223Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/41/b1/e2e7ad98de0d3ee05b44dbc3f78ccb158a620f3add82d00c85490120e7f2/ocrmypdf-16.13.0-py3-none-any.whl", hash = "sha256:fad8a6f7cc52cdc6225095c401a1766c778c47efe9f1e854ae4dc64a550a3d37", size = 165377, upload-time = "2025-12-24T07:58:33.925Z" },
+    { url = "https://files.pythonhosted.org/packages/ce/34/d9d04420e6f7a71e2135b41599dae273e4ef36e2ce79b065b65fb2471636/ocrmypdf-16.12.0-py3-none-any.whl", hash = "sha256:0ea5c42027db9cf3bd12b0d0b4190689027ef813fdad3377106ea66bba0012c3", size = 163415, upload-time = "2025-11-11T22:30:11.56Z" },
 ]
 
 [[package]]
@@ -2321,7 +2321,7 @@ requires-dist = [
     { name = "drf-writable-nested", specifier = "~=0.7.1" },
     { name = "filelock", specifier = "~=3.20.0" },
     { name = "flower", specifier = "~=2.0.1" },
-    { name = "gotenberg-client", specifier = "~=0.13.1" },
+    { name = "gotenberg-client", specifier = "~=0.12.0" },
     { name = "granian", extras = ["uvloop"], marker = "extra == 'webserver'", specifier = "~=2.5.1" },
     { name = "httpx-oauth", specifier = "~=0.16" },
     { name = "imap-tools", specifier = "~=1.11.0" },
@@ -2330,7 +2330,7 @@ requires-dist = [
     { name = "langdetect", specifier = "~=1.0.9" },
     { name = "mysqlclient", marker = "extra == 'mariadb'", specifier = "~=2.2.7" },
     { name = "nltk", specifier = "~=3.9.1" },
-    { name = "ocrmypdf", specifier = "~=16.13.0" },
+    { name = "ocrmypdf", specifier = "~=16.12.0" },
     { name = "pathvalidate", specifier = "~=3.3.1" },
     { name = "pdf2image", specifier = "~=1.17.0" },
     { name = "psycopg", extras = ["c", "pool"], marker = "extra == 'postgres'", specifier = "==3.2.12" },
@@ -3004,11 +3004,11 @@ wheels = [
 
 [[package]]
 name = "python-gnupg"
-version = "0.5.6"
+version = "0.5.5"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/98/2c/6cd2c7cff4bdbb434be5429ef6b8e96ee6b50155551361f30a1bb2ea3c1d/python_gnupg-0.5.6.tar.gz", hash = "sha256:5743e96212d38923fc19083812dc127907e44dbd3bcf0db4d657e291d3c21eac", size = 66825, upload-time = "2025-12-31T17:19:33.19Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/42/d0/72a14a79f26c6119b281f6ccc475a787432ef155560278e60df97ce68a86/python-gnupg-0.5.5.tar.gz", hash = "sha256:3fdcaf76f60a1b948ff8e37dc398d03cf9ce7427065d583082b92da7a4ff5a63", size = 66467, upload-time = "2025-08-04T19:26:55.778Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/d2/ab/0ea9de971caf3cd2e268d2b05dfe9883b21cfe686a59249bd2dccb4bae33/python_gnupg-0.5.6-py2.py3-none-any.whl", hash = "sha256:b5050a55663d8ab9fcc8d97556d229af337a87a3ebebd7054cbd8b7e2043394a", size = 22082, upload-time = "2025-12-31T17:16:22.743Z" },
+    { url = "https://files.pythonhosted.org/packages/aa/19/c147f78cc18c8788f54d4a16a22f6c05deba85ead5672d3ddf6dcba5a5fe/python_gnupg-0.5.5-py2.py3-none-any.whl", hash = "sha256:51fa7b8831ff0914bc73d74c59b99c613de7247b91294323c39733bb85ac3fc1", size = 21916, upload-time = "2025-08-04T19:26:54.307Z" },
 ]
 
 [[package]]