Enhancement: duplicates filter (#13994)

src/documents/filters.py

@@ -25,6 +25,7 @@ from django.db.models import Sum
 from django.db.models import Value
 from django.db.models import When
 from django.db.models.functions import Cast
+from django.db.models.functions import NullIf
 from django.utils.translation import gettext_lazy as _
 from django_filters import DateFilter
 from django_filters.rest_framework import BooleanFilter
@@ -50,6 +51,7 @@ from documents.models import ShareLink
 from documents.models import ShareLinkBundle
 from documents.models import StoragePath
 from documents.models import Tag
+from documents.permissions import permitted_document_ids
 from documents.permissions import permitted_object_ids
 
 if TYPE_CHECKING:
@@ -793,6 +795,12 @@ class CustomFieldQueryFilter(Filter):
 
 
 class DocumentFilterSet(FilterSet):
+    has_duplicates = BooleanFilter(method="filter_has_duplicates")
+
+    def __init__(self, *args: Any, user: Any = None, **kwargs: Any) -> None:
+        super().__init__(*args, **kwargs)
+        self._user = user
+
     is_tagged = BooleanFilter(
         label="Is tagged",
         field_name="tags",
@@ -852,6 +860,38 @@ class DocumentFilterSet(FilterSet):
 
     mime_type = MimeTypeFilter()
 
+    def filter_has_duplicates(self, queryset, name, value):
+        if value is None:
+            return queryset
+
+        user = (
+            self._user
+            if self._user is not None
+            else getattr(self.request, "user", None)
+        )
+        queryset = queryset.alias(
+            nonempty_archive_checksum=NullIf("archive_checksum", Value("")),
+        )
+
+        visible_root_documents = Document.global_objects.filter(
+            root_document__isnull=True,
+            pk__in=permitted_document_ids(
+                user,
+                include_deleted=True,
+            ),
+        ).exclude(pk=OuterRef("pk"))
+        # see serialisers._get_viewable_duplicates().
+        matching_duplicates = visible_root_documents.filter(
+            Q(checksum=OuterRef("checksum"))
+            | Q(checksum=OuterRef("nonempty_archive_checksum"))
+            | Q(archive_checksum=OuterRef("checksum"))
+            | Q(archive_checksum=OuterRef("nonempty_archive_checksum")),
+        )
+
+        return queryset.alias(
+            has_visible_duplicates=Exists(matching_duplicates),
+        ).filter(has_visible_duplicates=value)
+
     # Backwards compatibility
     created__date__gt = DateFilter(field_name="created", lookup_expr="gt")
     created__date__gte = DateFilter(field_name="created", lookup_expr="gte")

src/documents/migrations/0026_alter_document_archive_checksum_and_more.py

@@ -0,0 +1,86 @@
+# Generated by Django 5.2.16 on 2026-09-05 16:29
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0025_workflowaction_apply_ai_suggestions"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="document",
+            name="archive_checksum",
+            field=models.CharField(
+                blank=True,
+                db_index=True,
+                editable=False,
+                help_text="The checksum of the archived document.",
+                max_length=64,
+                null=True,
+                verbose_name="archive checksum",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="savedviewfilterrule",
+            name="rule_type",
+            field=models.PositiveSmallIntegerField(
+                choices=[
+                    (0, "title contains"),
+                    (1, "content contains"),
+                    (2, "ASN is"),
+                    (3, "correspondent is"),
+                    (4, "document type is"),
+                    (5, "is in inbox"),
+                    (6, "has tag"),
+                    (7, "has any tag"),
+                    (8, "created before"),
+                    (9, "created after"),
+                    (10, "created year is"),
+                    (11, "created month is"),
+                    (12, "created day is"),
+                    (13, "added before"),
+                    (14, "added after"),
+                    (15, "modified before"),
+                    (16, "modified after"),
+                    (17, "does not have tag"),
+                    (18, "does not have ASN"),
+                    (19, "title or content contains"),
+                    (20, "fulltext query"),
+                    (21, "more like this"),
+                    (22, "has tags in"),
+                    (23, "ASN greater than"),
+                    (24, "ASN less than"),
+                    (25, "storage path is"),
+                    (26, "has correspondent in"),
+                    (27, "does not have correspondent in"),
+                    (28, "has document type in"),
+                    (29, "does not have document type in"),
+                    (30, "has storage path in"),
+                    (31, "does not have storage path in"),
+                    (32, "owner is"),
+                    (33, "has owner in"),
+                    (34, "does not have owner"),
+                    (35, "does not have owner in"),
+                    (36, "has custom field value"),
+                    (37, "is shared by me"),
+                    (38, "has custom fields"),
+                    (39, "has custom field in"),
+                    (40, "does not have custom field in"),
+                    (41, "does not have custom field"),
+                    (42, "custom fields query"),
+                    (43, "created to"),
+                    (44, "created from"),
+                    (45, "added to"),
+                    (46, "added from"),
+                    (47, "mime type is"),
+                    (48, "simple title search"),
+                    (49, "simple text search"),
+                    (50, "has duplicates"),
+                ],
+                verbose_name="rule type",
+            ),
+        ),
+    ]

src/documents/models.py

@@ -227,6 +227,7 @@ class Document(SoftDeleteModel, ModelWithOwner):  # type: ignore[django-manager-
         editable=False,
         blank=True,
         null=True,
+        db_index=True,
         help_text=_("The checksum of the archived document."),
     )
 
@@ -706,6 +707,7 @@ class SavedViewFilterRule(models.Model):
         (47, _("mime type is")),
         (48, _("simple title search")),
         (49, _("simple text search")),
+        (50, _("has duplicates")),
     ]
 
     saved_view = models.ForeignKey(

src/documents/tests/test_api_bulk_edit.py

@@ -717,6 +717,44 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(args[0], [self.doc2.id])
         self.assertEqual(kwargs["storage_path"], self.sp1.id)
 
+    @mock.patch("documents.serialisers.bulk_edit.set_storage_path")
+    def test_api_bulk_edit_with_all_true_resolves_owned_duplicates(self, m) -> None:
+        self.setup_mock(m, "set_storage_path")
+        user = User.objects.create_user(username="duplicate-owner")
+        user.user_permissions.add(
+            Permission.objects.get(codename="change_document"),
+        )
+        first_duplicate = Document.objects.create(
+            checksum="owned-duplicate",
+            title="First duplicate",
+            owner=user,
+        )
+        second_duplicate = Document.objects.create(
+            checksum="owned-duplicate",
+            title="Second duplicate",
+            owner=user,
+        )
+        self.client.force_authenticate(user=user)
+
+        response = self.client.post(
+            "/api/documents/bulk_edit/",
+            json.dumps(
+                {
+                    "all": True,
+                    "filters": {"has_duplicates": True},
+                    "method": "set_storage_path",
+                    "parameters": {"storage_path": self.sp1.id},
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        m.assert_called_once()
+        args, kwargs = m.call_args
+        self.assertCountEqual(args[0], [first_duplicate.id, second_duplicate.id])
+        self.assertEqual(kwargs["storage_path"], self.sp1.id)
+
     @mock.patch("documents.search.get_backend")
     @mock.patch("documents.serialisers.bulk_edit.set_storage_path")
     def test_api_bulk_edit_with_all_true_resolves_documents_from_search_filters(

src/documents/tests/test_api_documents.py

@@ -981,6 +981,128 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
         self.assertEqual(len(results), 1)
         self.assertEqual(results[0]["id"], doc.id)
 
+    def test_has_duplicates_filter(self) -> None:
+        original_match = Document.objects.create(
+            title="original match",
+            checksum="same-original",
+        )
+        second_original_match = Document.objects.create(
+            title="second original match",
+            checksum="same-original",
+        )
+        archive_match = Document.objects.create(
+            title="archive match",
+            checksum="archive-source",
+            archive_checksum="same-archive",
+        )
+        original_to_archive_match = Document.objects.create(
+            title="original to archive match",
+            checksum="same-archive",
+        )
+        first_archive_match = Document.objects.create(
+            title="first archive match",
+            checksum="first-archive-source",
+            archive_checksum="same-archive-only",
+        )
+        second_archive_match = Document.objects.create(
+            title="second archive match",
+            checksum="second-archive-source",
+            archive_checksum="same-archive-only",
+        )
+        first_empty_archive = Document.objects.create(
+            title="first empty archive",
+            checksum="first-empty-archive",
+            archive_checksum="",
+        )
+        second_empty_archive = Document.objects.create(
+            title="second empty archive",
+            checksum="second-empty-archive",
+            archive_checksum="",
+        )
+        unique = Document.objects.create(title="unique", checksum="unique")
+        version_root = Document.objects.create(
+            title="version root",
+            checksum="version-root",
+        )
+        Document.objects.create(
+            title="version",
+            checksum=unique.checksum,
+            root_document=version_root,
+            version_index=1,
+        )
+        trash_match = Document.objects.create(
+            title="trash match",
+            checksum="trash-match",
+        )
+        trashed_duplicate = Document.objects.create(
+            title="trashed duplicate",
+            checksum="trash-match",
+        )
+        trashed_duplicate.delete()
+
+        response = self.client.get("/api/documents/?has_duplicates=true")
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        self.assertCountEqual(
+            [document["id"] for document in response.data["results"]],
+            [
+                original_match.id,
+                second_original_match.id,
+                archive_match.id,
+                original_to_archive_match.id,
+                first_archive_match.id,
+                second_archive_match.id,
+                trash_match.id,
+            ],
+        )
+
+        response = self.client.get("/api/documents/?has_duplicates=false")
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        self.assertCountEqual(
+            [document["id"] for document in response.data["results"]],
+            [
+                unique.id,
+                version_root.id,
+                first_empty_archive.id,
+                second_empty_archive.id,
+            ],
+        )
+
+        response = self.client.get(f"/api/documents/{first_empty_archive.id}/")
+        self.assertEqual(response.data["duplicate_documents"], [])
+
+    def test_has_duplicates_filter_respects_document_permissions(self) -> None:
+        owner = User.objects.create_user(username="duplicate-owner")
+        requester = User.objects.create_user(username="duplicate-requester")
+        requester.user_permissions.add(
+            Permission.objects.get(codename="view_document"),
+        )
+        visible_document = Document.objects.create(
+            title="visible document",
+            checksum="permission-match",
+            owner=requester,
+        )
+        hidden_duplicate = Document.objects.create(
+            title="hidden duplicate",
+            checksum="permission-match",
+            owner=owner,
+        )
+        self.client.force_authenticate(user=requester)
+
+        response = self.client.get("/api/documents/?has_duplicates=true")
+        self.assertNotIn(
+            visible_document.id,
+            [document["id"] for document in response.data["results"]],
+        )
+
+        assign_perm("view_document", requester, hidden_duplicate)
+        response = self.client.get("/api/documents/?has_duplicates=true")
+        self.assertIn(
+            visible_document.id,
+            [document["id"] for document in response.data["results"]],
+        )
+
     def test_custom_fields_icontains_filter_no_duplicates(self) -> None:
         """
         GIVEN:

src/documents/views.py

@@ -2816,6 +2816,7 @@ class DocumentSelectionMixin:
         filtered_documents = DocumentFilterSet(
             data=orm_filters,
             queryset=permitted_documents,
+            user=user,
         ).qs.distinct()
         # tantivy-filtered docs (if search params provided)
         search_filtered_ids = self._get_search_document_ids(