Performance: replace django-treenode with adjacency-list tags

Co-Authored-By: Codex <267193182+codex@users.noreply.github.com>

docker/rootfs/etc/s6-overlay/s6-rc.d/init-compile-bytecode/run

@@ -39,7 +39,6 @@ declare -a scope=(
 	"${site_packages}/allauth"
 	"${site_packages}/drf_spectacular"
 	"${site_packages}/drf_spectacular_sidecar"
-	"${site_packages}/treenode"
 	"${site_packages}/compression_middleware"
 )
 

pyproject.toml

@@ -38,7 +38,6 @@ dependencies = [
   "django-multiselectfield~=1.0.1",
   "django-rich~=2.2.0",
   "django-soft-delete~=1.0.18",
-  "django-treenode>=0.24",
   "djangorestframework~=3.16",
   "drf-spectacular~=0.30",
   "drf-spectacular-sidecar>=2026.7.1,<2026.10",

src-ui/src/app/components/common/custom-fields-dropdown/custom-fields-dropdown.component.scss

@@ -1,3 +1,10 @@
 .custom-fields-dropdown {
     min-width: 300px;
+
+    // correct position on mobile
+    @media (max-width: 575.98px) {
+        &.show {
+            margin-left: -245px !important;
+        }
+    }
 }

src-ui/src/app/components/document-detail/document-detail.component.html

@@ -308,7 +308,7 @@
                   </tr>
                   <tr class="align-middle">
                     <td i18n>Original SHA256 checksum</td>
-                    <td><span class="badge bg-light text-dark font-monospace text-wrap text-break text-start">{{metadata()?.original_checksum}}</span></td>
+                    <td><span class="badge bg-light font-monospace text-wrap text-break text-start">{{metadata()?.original_checksum}}</span></td>
                   </tr>
                   <tr>
                     <td i18n>Original file size</td>

src/conftest.py

@@ -77,30 +77,6 @@ def _clear_django_caches() -> None:
         cache.clear()
 
 
-@pytest.fixture(autouse=True)
-def _keep_connection_open_in_atomic(monkeypatch: pytest.MonkeyPatch) -> None:
-    """Make ``close_old_connections()`` a no-op inside the test's transaction.
-
-    The Celery signal handlers call it, as a worker would between tasks. Tests
-    run inside an open atomic block, where Postgres really closes the
-    connection, taking the test transaction and every later test on the
-    worker with it. SQLite in-memory ignores the close, which hid this.
-    """
-    from django.db.backends.base.base import BaseDatabaseWrapper
-
-    original = BaseDatabaseWrapper.close_if_unusable_or_obsolete
-
-    def close_unless_atomic(self: BaseDatabaseWrapper) -> None:
-        if not self.in_atomic_block:
-            original(self)
-
-    monkeypatch.setattr(
-        BaseDatabaseWrapper,
-        "close_if_unusable_or_obsolete",
-        close_unless_atomic,
-    )
-
-
 @pytest.fixture
 def paperless_dirs(
     tmp_path: Path,

src/documents/admin.py

@@ -1,7 +1,6 @@
 from django.conf import settings
 from django.contrib import admin
 from guardian.admin import GuardedModelAdmin
-from treenode.admin import TreeNodeModelAdmin
 
 from documents.models import Correspondent
 from documents.models import CustomField
@@ -29,7 +28,7 @@ class CorrespondentAdmin(GuardedModelAdmin):
     list_editable = ("match", "matching_algorithm")
 
 
-class TagAdmin(GuardedModelAdmin, TreeNodeModelAdmin):
+class TagAdmin(GuardedModelAdmin):
     list_display = ("name", "color", "match", "matching_algorithm")
     list_filter = ("matching_algorithm",)
     list_editable = ("color", "match", "matching_algorithm")

src/documents/bulk_edit.py

@@ -255,19 +255,13 @@ def modify_tags(
     affected_docs = list(qs.values_list("pk", flat=True))
     DocumentTagRelationship = Document.tags.through
 
-    # add with all ancestors
-    expanded_add_tags: set[int] = set()
-    add_tag_objects = Tag.objects.filter(pk__in=add_tags)
-    for t in add_tag_objects:
-        expanded_add_tags.add(int(t.id))
-        expanded_add_tags.update(int(pk) for pk in t.get_ancestors_pks())
-
-    # remove with all descendants
-    expanded_remove_tags: set[int] = set()
-    remove_tag_objects = Tag.objects.filter(pk__in=remove_tags)
-    for t in remove_tag_objects:
-        expanded_remove_tags.add(int(t.id))
-        expanded_remove_tags.update(int(pk) for pk in t.get_descendants_pks())
+    hierarchy = Tag.get_hierarchy()
+    expanded_add_tags = hierarchy.with_ancestors(
+        Tag.objects.filter(pk__in=add_tags).values_list("pk", flat=True),
+    )
+    expanded_remove_tags = hierarchy.with_descendants(
+        Tag.objects.filter(pk__in=remove_tags).values_list("pk", flat=True),
+    )
 
     with transaction.atomic():
         if expanded_remove_tags:

src/documents/management/commands/document_importer.py

@@ -108,6 +108,24 @@ def _deserialize_record(
         ) from e
 
     for field_name, field_value in record.get("fields", {}).items():
+        # Older exports include django-treenode's derived bookkeeping. The
+        # parent FK is authoritative; accept only these known removed fields.
+        if Model is Tag and field_name in {
+            "tn_ancestors_count",
+            "tn_ancestors_pks",
+            "tn_children_count",
+            "tn_children_pks",
+            "tn_depth",
+            "tn_descendants_count",
+            "tn_descendants_pks",
+            "tn_index",
+            "tn_level",
+            "tn_order",
+            "tn_priority",
+            "tn_siblings_count",
+            "tn_siblings_pks",
+        }:
+            continue
         field = Model._meta.get_field(field_name)
         remote = field.remote_field
 

src/documents/matching.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 import logging
 import re
 from fnmatch import fnmatch
+from fnmatch import translate as fnmatch_translate
 from typing import TYPE_CHECKING
 
 from rest_framework import serializers
@@ -547,48 +548,6 @@ def existing_document_matches_workflow(
     return (True, None)
 
 
-def glob_to_database_regex(pattern: str) -> str:
-    """
-    Translates an fnmatch style glob into a regular expression which the
-    database can evaluate, matching the whole value.
-
-    fnmatch.translate is not usable here: it emits syntax such as (?s:...),
-    atomic groups and named group backreferences, which PostgreSQL rejects.
-    Only constructs common to Python, PostgreSQL and MariaDB are produced.
-    """
-    parts: list[str] = []
-    i = 0
-    n = len(pattern)
-    while i < n:
-        char = pattern[i]
-        i += 1
-        if char == "*":
-            parts.append(".*")
-        elif char == "?":
-            parts.append(".")
-        elif char == "[":
-            j = i
-            if j < n and pattern[j] == "!":
-                j += 1
-            if j < n and pattern[j] == "]":
-                j += 1
-            while j < n and pattern[j] != "]":
-                j += 1
-            if j >= n:
-                parts.append(r"\[")
-            else:
-                stuff = pattern[i:j].replace("\\", r"\\").replace("[", r"\[")
-                i = j + 1
-                if stuff.startswith("!"):
-                    stuff = "^" + stuff[1:]
-                elif stuff.startswith("^"):
-                    stuff = "\\" + stuff
-                parts.append(f"[{stuff}]")
-        else:
-            parts.append(re.escape(char))
-    return "^" + "".join(parts) + "$"
-
-
 def prefilter_documents_by_workflowtrigger(
     documents: QuerySet[Document],
     trigger: WorkflowTrigger,
@@ -669,9 +628,8 @@ def prefilter_documents_by_workflowtrigger(
         documents = documents.annotate(**annotations).filter(custom_field_q)
 
     if trigger.filter_filename:
-        documents = documents.filter(
-            original_filename__iregex=glob_to_database_regex(trigger.filter_filename),
-        )
+        regex = fnmatch_translate(trigger.filter_filename).lstrip("^").rstrip("$")
+        documents = documents.filter(original_filename__iregex=regex)
 
     return documents
 

src/documents/migrations/0028_replace_tag_tree_fields.py

@@ -0,0 +1,64 @@
+# Generated by Django 5.2.17 on 2026-10-28 22:54
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0027_documentbarcode"),
+    ]
+
+    operations = [
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_ancestors_count",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_ancestors_pks",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_children_count",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_children_pks",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_depth",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_descendants_count",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_descendants_pks",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_index",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_level",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_order",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_priority",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_siblings_count",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="tn_siblings_pks",
+        ),
+    ]

src/documents/models.py

@@ -14,7 +14,6 @@ from django.db import models
 from django.utils import timezone
 from django.utils.translation import gettext_lazy as _
 from multiselectfield import MultiSelectField
-from treenode.models import TreeNodeModel
 
 if settings.AUDIT_LOG_ENABLED:
     from auditlog.registry import auditlog
@@ -100,7 +99,17 @@ class Correspondent(MatchingModel):
         verbose_name_plural = _("correspondents")
 
 
-class Tag(MatchingModel, TreeNodeModel):
+class Tag(MatchingModel):
+    # Keep the existing column and reverse relation during the transition.
+    tn_parent = models.ForeignKey(
+        "self",
+        blank=True,
+        null=True,
+        on_delete=models.CASCADE,
+        related_name="tn_children",
+        verbose_name=_("Parent"),
+    )
+
     color = models.CharField(_("color"), max_length=7, default="#a6cee3")
     # Maximum allowed nesting depth for tags (root = 1, max depth = 5)
     MAX_NESTING_DEPTH: Final[int] = 5
@@ -114,27 +123,51 @@ class Tag(MatchingModel, TreeNodeModel):
         ),
     )
 
-    class Meta(MatchingModel.Meta, TreeNodeModel.Meta):
+    class Meta(MatchingModel.Meta):
         verbose_name = _("tag")
         verbose_name_plural = _("tags")
 
+    @classmethod
+    def get_hierarchy(cls):
+        from documents.tag_hierarchy import TagHierarchy
+
+        return TagHierarchy(cls.objects.values_list("pk", "tn_parent_id"))
+
+    @property
+    def parent_pk(self):
+        return self.tn_parent_id
+
+    def get_parent(self):
+        return self.tn_parent
+
+    def get_ancestors_pks(self):
+        return self.get_hierarchy().ancestors(self.tn_parent_id)
+
+    def get_ancestors(self):
+        ids = self.get_ancestors_pks()
+        tags = self.__class__.objects.in_bulk(ids)
+        return [tags[pk] for pk in ids]
+
+    def get_descendants_pks(self):
+        return self.get_hierarchy().descendants([self.pk])
+
+    def get_descendants(self):
+        return self.__class__.objects.filter(pk__in=self.get_descendants_pks())
+
+    def get_children_queryset(self):
+        return self.__class__.objects.filter(tn_parent_id=self.pk)
+
     def clean(self) -> None:
-        # Prevent self-parenting and assigning a descendant as parent
-        parent = self.get_parent()
-        if parent == self:
-            raise ValidationError({"parent": _("Cannot set itself as parent.")})
-        if parent and self.pk is not None and self.is_ancestor_of(parent):
-            raise ValidationError({"parent": _("Cannot set parent to a descendant.")})
-
-        # Enforce maximum nesting depth
-        new_parent_depth = 0
-        if parent:
-            new_parent_depth = parent.get_ancestors_count() + 1
-
-        height = 0 if self.pk is None else self.get_depth()
-        deepest_new_depth = (new_parent_depth + 1) + height
-        if deepest_new_depth > self.MAX_NESTING_DEPTH:
-            raise ValidationError({"parent": _("Maximum nesting depth exceeded.")})
+        hierarchy = self.get_hierarchy()
+        if self.pk is not None and self.tn_parent_id == self.pk:
+            raise ValidationError({"tn_parent": _("Cannot set itself as parent.")})
+        ancestors = hierarchy.ancestors(self.tn_parent_id)
+        if self.pk is not None and self.pk in ancestors:
+            raise ValidationError(
+                {"tn_parent": _("Cannot set parent to a descendant.")},
+            )
+        if len(ancestors) + 1 + hierarchy.height(self.pk) > self.MAX_NESTING_DEPTH:
+            raise ValidationError({"tn_parent": _("Maximum nesting depth exceeded.")})
 
         return super().clean()
 
@@ -539,10 +572,7 @@ class Document(SoftDeleteModel, ModelWithOwner):  # type: ignore[django-manager-
         return self.created
 
     def add_nested_tags(self, tags) -> None:
-        tag_ids = set()
-        for tag in tags:
-            tag_ids.add(tag.id)
-            tag_ids.update(tag.get_ancestors_pks())
+        tag_ids = Tag.get_hierarchy().with_ancestors(tag.pk for tag in tags)
 
         tags_to_add = self.tags.model.objects.filter(id__in=tag_ids)
         self.tags.add(*tags_to_add)

src/documents/serialisers.py

@@ -589,7 +589,7 @@ class TagSerializer(MatchingModelSerializer, OwnedObjectSerializer):
 
     text_color = serializers.SerializerMethodField()
 
-    # map to treenode's tn_parent
+    # Preserve the public API parent field.
     parent = serializers.PrimaryKeyRelatedField(
         queryset=Tag.objects.all(),
         allow_null=True,
@@ -692,7 +692,9 @@ class TagSerializer(MatchingModelSerializer, OwnedObjectSerializer):
                 self.instance.clean()
             except ValidationError as e:
                 logger.debug("Tag parent validation failed: %s", e)
-                raise e
+                raise serializers.ValidationError(
+                    {"parent": e.message_dict["tn_parent"]},
+                ) from e
             finally:
                 self.instance.tn_parent = original_parent
         else:
@@ -702,7 +704,9 @@ class TagSerializer(MatchingModelSerializer, OwnedObjectSerializer):
                 temp.clean()
             except ValidationError as e:
                 logger.debug("Tag parent validation failed: %s", e)
-                raise e
+                raise serializers.ValidationError(
+                    {"parent": e.message_dict["tn_parent"]},
+                ) from e
 
         return super().validate(attrs)
 
@@ -1198,61 +1202,35 @@ class DocumentSerializer(
                             doc_id,
                         )
         if "tags" in validated_data:
-            # Respect tag hierarchy on updates:
-            # - Adding a child adds its ancestors
-            # - Removing a parent removes all its descendants
-            prev_tags = set(instance.tags.all())
-            requested_tags = set(validated_data["tags"])
+            hierarchy = Tag.get_hierarchy()
+            previous_ids = set(instance.tags.values_list("pk", flat=True))
+            requested_ids = {tag.pk for tag in validated_data["tags"]}
+            required_ids = hierarchy.with_ancestors(requested_ids - previous_ids)
+            blocked_ids = hierarchy.with_descendants(previous_ids - requested_ids)
+            blocked_ids.difference_update(required_ids)
+            final_ids = hierarchy.with_ancestors(requested_ids) - blocked_ids
+            validated_data["tags"] = list(Tag.objects.filter(pk__in=final_ids))
 
-            # Tags newly added in this update and the ancestors they require
-            added_tags = requested_tags - prev_tags
-            required_by_add_tags = set(added_tags)
-            for t in added_tags:
-                required_by_add_tags.update(t.get_ancestors())
-
-            # Tags being removed in this update and all descendants, except
-            # those required by a tag that is being added in this same update
-            removed_tags = prev_tags - requested_tags
-            blocked_tags = set(removed_tags)
-            for t in removed_tags:
-                blocked_tags.update(t.get_descendants())
-            blocked_tags.difference_update(required_by_add_tags)
-
-            # Add all parent tags
-            final_tags = set(requested_tags)
-            for t in requested_tags:
-                final_tags.update(t.get_ancestors())
-
-            # Drop removed parents and their descendants
-            final_tags.difference_update(blocked_tags)
-
-            validated_data["tags"] = list(final_tags)
         if validated_data.get("remove_inbox_tags"):
-            current_tag_ids = {t.pk for t in instance.tags.all()}
+            hierarchy = Tag.get_hierarchy()
             tags = (
                 validated_data["tags"]
                 if "tags" in validated_data
                 else list(instance.tags.all())
             )
-
-            # Tags newly added in this update, plus their ancestors, are kept
-            keep_ids: set[int] = set()
-            for tag in tags:
-                if tag.pk not in current_tag_ids:
-                    keep_ids.add(tag.pk)
-                    keep_ids.update(int(pk) for pk in tag.get_ancestors_pks())
-
-            # Remove inbox tags and their descendants, except those being kept
-            remove_ids: set[int] = set()
-            for inbox_tag in (
+            current_ids = set(instance.tags.values_list("pk", flat=True))
+            keep_ids = hierarchy.with_ancestors(
+                tag.pk for tag in tags if tag.pk not in current_ids
+            )
+            inbox_ids = (
                 Tag.objects.filter(is_inbox_tag=True)
-                .exclude(pk__in=keep_ids)
-                .only("pk", "tn_descendants_pks")
-            ):
-                remove_ids.add(inbox_tag.pk)
-                remove_ids.update(int(pk) for pk in inbox_tag.get_descendants_pks())
-
-            validated_data["tags"] = [t for t in tags if t.pk not in remove_ids]
+                .exclude(
+                    pk__in=keep_ids,
+                )
+                .values_list("pk", flat=True)
+            )
+            remove_ids = hierarchy.with_descendants(inbox_ids) - keep_ids
+            validated_data["tags"] = [tag for tag in tags if tag.pk not in remove_ids]
 
         if settings.AUDIT_LOG_ENABLED:
             with set_actor(self.user):

src/documents/tag_hierarchy.py

@@ -0,0 +1,61 @@
+"""An operation-local snapshot of tag edges, with no persistent derived fields.
+
+Never cache this globally: tasks, bulk updates and other processes can change
+parents. Callers traversing multiple tags should share one snapshot.
+"""
+
+from collections import defaultdict
+from collections.abc import Iterable
+
+
+class TagHierarchy:
+    def __init__(self, edges: Iterable[tuple[int, int | None]]) -> None:
+        self.parents = dict(edges)
+        self.children: dict[int | None, list[int]] = defaultdict(list)
+        for pk, parent in self.parents.items():
+            self.children[parent].append(pk)
+
+    def ancestors(self, parent_id: int | None) -> list[int]:
+        result = []
+        seen = set()
+        while parent_id is not None and parent_id not in seen:
+            seen.add(parent_id)
+            result.append(parent_id)
+            parent_id = self.parents.get(parent_id)
+        return result[::-1]
+
+    def with_ancestors(self, roots: Iterable[int]) -> set[int]:
+        result = set(roots)
+        for pk in list(result):
+            result.update(self.ancestors(self.parents.get(pk)))
+        return result
+
+    def with_descendants(self, roots: Iterable[int]) -> set[int]:
+        roots = set(roots)
+        return roots | self.descendants(roots)
+
+    def descendants(self, roots: Iterable[int]) -> set[int]:
+        roots = {pk for pk in roots if pk is not None}
+        seen = set(roots)
+        pending = list(roots)
+        while pending:
+            for child in self.children.get(pending.pop(), ()):
+                if child not in seen:
+                    seen.add(child)
+                    pending.append(child)
+        return seen - roots
+
+    def height(self, pk: int | None) -> int:
+        if pk is None:
+            return 0
+        seen = {pk}
+        pending = [(pk, 0)]
+        height = 0
+        while pending:
+            parent, depth = pending.pop()
+            height = max(height, depth)
+            for child in self.children.get(parent, ()):
+                if child not in seen:
+                    seen.add(child)
+                    pending.append((child, depth + 1))
+        return height

src/documents/tests/test_api_custom_fields.py

@@ -1062,7 +1062,7 @@ class TestCustomFieldsAPI(DirectoriesMixin, APITestCase):
                 "custom_fields": [
                     {
                         "field": custom_field_doclink.id,
-                        "value": [doc2.id, doc3.id, doc4.id],
+                        "value": [2, 3, 4],
                     },
                 ],
             },
@@ -1073,13 +1073,13 @@ class TestCustomFieldsAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(CustomFieldInstance.objects.count(), 4)
         _cf_5 = doc2.custom_fields.first()
         assert _cf_5 is not None
-        self.assertEqual(_cf_5.value, [doc1.id])
+        self.assertEqual(_cf_5.value, [1])
         _cf_6 = doc3.custom_fields.first()
         assert _cf_6 is not None
-        self.assertEqual(_cf_6.value, [doc1.id])
+        self.assertEqual(_cf_6.value, [1])
         _cf_7 = doc4.custom_fields.first()
         assert _cf_7 is not None
-        self.assertEqual(_cf_7.value, [doc1.id])
+        self.assertEqual(_cf_7.value, [1])
 
         # Add links appends if necessary
         resp = self.client.patch(
@@ -1088,7 +1088,7 @@ class TestCustomFieldsAPI(DirectoriesMixin, APITestCase):
                 "custom_fields": [
                     {
                         "field": custom_field_doclink.id,
-                        "value": [doc1.id, doc4.id],
+                        "value": [1, 4],
                     },
                 ],
             },
@@ -1098,7 +1098,7 @@ class TestCustomFieldsAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(resp.status_code, status.HTTP_200_OK)
         _cf_8 = doc4.custom_fields.first()
         assert _cf_8 is not None
-        self.assertEqual(_cf_8.value, [doc1.id, doc3.id])
+        self.assertEqual(_cf_8.value, [1, 3])
 
         # Remove one of the links, removed on other doc
         resp = self.client.patch(
@@ -1107,7 +1107,7 @@ class TestCustomFieldsAPI(DirectoriesMixin, APITestCase):
                 "custom_fields": [
                     {
                         "field": custom_field_doclink.id,
-                        "value": [doc2.id, doc3.id],
+                        "value": [2, 3],
                     },
                 ],
             },
@@ -1117,13 +1117,13 @@ class TestCustomFieldsAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(resp.status_code, status.HTTP_200_OK)
         _cf_9 = doc2.custom_fields.first()
         assert _cf_9 is not None
-        self.assertEqual(_cf_9.value, [doc1.id])
+        self.assertEqual(_cf_9.value, [1])
         _cf_10 = doc3.custom_fields.first()
         assert _cf_10 is not None
-        self.assertEqual(_cf_10.value, [doc1.id, doc4.id])
+        self.assertEqual(_cf_10.value, [1, 4])
         _cf_11 = doc4.custom_fields.first()
         assert _cf_11 is not None
-        self.assertEqual(_cf_11.value, [doc3.id])
+        self.assertEqual(_cf_11.value, [3])
 
         # Removes the field entirely
         resp = self.client.patch(
@@ -1140,10 +1140,10 @@ class TestCustomFieldsAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(_cf_12.value, [])
         _cf_13 = doc3.custom_fields.first()
         assert _cf_13 is not None
-        self.assertEqual(_cf_13.value, [doc4.id])
+        self.assertEqual(_cf_13.value, [4])
         _cf_14 = doc4.custom_fields.first()
         assert _cf_14 is not None
-        self.assertEqual(_cf_14.value, [doc3.id])
+        self.assertEqual(_cf_14.value, [3])
 
         # If field exists on target doc but value is None
         doc5 = Document.objects.create(
@@ -1170,7 +1170,7 @@ class TestCustomFieldsAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(resp.status_code, status.HTTP_200_OK)
         _cf_15 = doc5.custom_fields.first()
         assert _cf_15 is not None
-        self.assertEqual(_cf_15.value, [doc1.id])
+        self.assertEqual(_cf_15.value, [1])
 
     def test_documentlink_patch_requires_change_permission_on_target_documents(
         self,

src/documents/tests/test_api_filter_by_custom_fields.py

@@ -6,7 +6,6 @@ from unittest.mock import patch
 from urllib.parse import quote
 
 import time_machine
-from django.db import connection
 from django.test import override_settings
 from django.utils import timezone
 from rest_framework.test import APITestCase
@@ -21,13 +20,6 @@ from paperless_testing.dirs import DirectoriesMixin
 from paperless_testing.factories import UserFactory
 
 
-def _exact_equal(value: str | None, expected: str) -> bool:
-    """`exact` follows the column collation, which is case insensitive on MariaDB."""
-    if connection.vendor == "mysql" and value is not None:
-        return value.casefold() == expected.casefold()
-    return value == expected
-
-
 class DocumentWrapper:
     """
     Allows Pythonic access to the custom fields associated with the wrapped document.
@@ -295,8 +287,7 @@ class TestCustomFieldsSearch(DirectoriesMixin, APITestCase):
         self._assert_query_match_predicate(
             ["string_field", "exact", "paperless"],
             lambda document: (
-                "string_field" in document
-                and _exact_equal(document["string_field"], "paperless")
+                "string_field" in document and document["string_field"] == "paperless"
             ),
         )
 
@@ -305,10 +296,7 @@ class TestCustomFieldsSearch(DirectoriesMixin, APITestCase):
             ["string_field", "in", ["paperless", "Paperless"]],
             lambda document: (
                 "string_field" in document
-                and any(
-                    _exact_equal(document["string_field"], expected)
-                    for expected in ("paperless", "Paperless")
-                )
+                and document["string_field"] in ("paperless", "Paperless")
             ),
         )
 
@@ -640,23 +628,22 @@ class TestCustomFieldsSearch(DirectoriesMixin, APITestCase):
     # Subset check (document link field only)                   #
     # ==========================================================#
     def test_document_link_contains(self) -> None:
-        linked = {self.documents[1].id, self.documents[2].id}
         # Document link field "contains" performs a subset check.
         self._assert_query_match_predicate(
-            ["documentlink_field", "contains", sorted(linked)],
+            ["documentlink_field", "contains", [1, 2]],
             lambda document: (
                 "documentlink_field" in document
                 and document["documentlink_field"] is not None
-                and set(document["documentlink_field"]) >= linked
+                and set(document["documentlink_field"]) >= {1, 2}
             ),
         )
         # The order of IDs don't matter - this is the same as above.
         self._assert_query_match_predicate(
-            ["documentlink_field", "contains", sorted(linked, reverse=True)],
+            ["documentlink_field", "contains", [2, 1]],
             lambda document: (
                 "documentlink_field" in document
                 and document["documentlink_field"] is not None
-                and set(document["documentlink_field"]) >= linked
+                and set(document["documentlink_field"]) >= {1, 2}
             ),
         )
 
@@ -773,7 +760,7 @@ class TestCustomFieldsSearch(DirectoriesMixin, APITestCase):
             lambda document: (
                 not (
                     "string_field" in document
-                    and _exact_equal(document["string_field"], "paperless")
+                    and document["string_field"] == "paperless"
                 )
             ),
         )

src/documents/tests/test_api_search.py

@@ -944,7 +944,7 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_200_OK)
 
         results = response.data["results"]
-        self.assertEqual({r["id"] for r in results}, {d1.id, d2.id})
+        self.assertEqual({r["id"] for r in results}, {1, 2})
 
     @mock.patch("documents.search._backend.parse_user_query")
     def test_search_parser_bug_surfaces_as_500_not_400(self, m) -> None:
@@ -1801,7 +1801,6 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
     def test_search_sorting(self) -> None:
         u1 = UserFactory(username="user1")
         u2 = UserFactory(username="user2")
-        u3 = UserFactory(username="user3")
         c1 = Correspondent.objects.create(name="corres Ax")
         c2 = Correspondent.objects.create(name="corres Cx")
         c3 = Correspondent.objects.create(name="corres Bx")
@@ -1827,7 +1826,6 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
             content="test",
             archive_serial_number=1,
             title="1",
-            owner=u3,
         )
         Note.objects.create(
             note="This is a note.",
@@ -1880,14 +1878,14 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
             search_query("&ordering=-num_notes"),
             [d1.id, d3.id, d2.id],
         )
-        # owner sort: ORM orders by owner_id (integer)
+        # owner sort: ORM orders by owner_id (integer); NULLs first in SQLite ASC
         self.assertListEqual(
             search_query("&ordering=owner"),
-            [d1.id, d2.id, d3.id],
+            [d3.id, d1.id, d2.id],
         )
         self.assertListEqual(
             search_query("&ordering=-owner"),
-            [d3.id, d2.id, d1.id],
+            [d2.id, d1.id, d3.id],
         )
 
     def test_search_ordering_by_score(self) -> None:

src/documents/tests/test_api_status.py

@@ -5,7 +5,6 @@ from datetime import timedelta
 from pathlib import Path
 from unittest import mock
 
-from django.db import connection
 from django.test import override_settings
 from django.utils import timezone
 from rest_framework import status
@@ -69,7 +68,7 @@ class TestSystemStatus(APITestCase):
         self.assertEqual(response.data["install_type"], "bare-metal")
         self.assertIsNotNone(response.data["storage"]["total"])
         self.assertIsNotNone(response.data["storage"]["available"])
-        self.assertEqual(response.data["database"]["type"], connection.vendor)
+        self.assertEqual(response.data["database"]["type"], "sqlite")
         self.assertIsNotNone(response.data["database"]["url"])
         self.assertEqual(response.data["database"]["status"], "OK")
         self.assertIsNone(response.data["database"]["error"])

src/documents/tests/test_bulk_edit.py

@@ -1031,7 +1031,9 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         with self.assertLogs("paperless.bulk_edit", level="ERROR") as cm:
             bulk_edit.merge(doc_ids)
             error_str = cm.output[0]
-            expected_str = f"Error merging document {self.doc2.id}, it will not be included in the merge"
+            expected_str = (
+                "Error merging document 2, it will not be included in the merge"
+            )
             self.assertIn(expected_str, error_str)
 
         mock_consume_file.assert_not_called()
@@ -1191,7 +1193,7 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         with self.assertLogs("paperless.bulk_edit", level="ERROR") as cm:
             bulk_edit.split(doc_ids, pages)
             error_str = cm.output[0]
-            expected_str = f"Error splitting document {self.doc2.id}"
+            expected_str = "Error splitting document 2"
             self.assertIn(expected_str, error_str)
 
         mock_consume_file.assert_not_called()

src/documents/tests/test_consumer.py

@@ -248,8 +248,8 @@ class TestConsumer(
         )
         self.assertIsNone(document.correspondent)
         self.assertIsNone(document.document_type)
-        self.assertEqual(document.filename, f"{document.pk:07}.pdf")
-        self.assertEqual(document.archive_filename, f"{document.pk:07}.pdf")
+        self.assertEqual(document.filename, "0000001.pdf")
+        self.assertEqual(document.archive_filename, "0000001.pdf")
 
         self.assertIsFile(document.source_path)
 
@@ -1127,17 +1127,17 @@ class TestConsumer(
         with self.get_consumer(settings.CONSUMPTION_DIR / "simple.png") as consumer:
             consumer.run()
 
-            doc1 = Document.objects.latest("pk")
+            doc1 = Document.objects.filter(pk=1).first()
 
         with self.get_consumer(settings.CONSUMPTION_DIR / "simple.pdf") as consumer:
             consumer.run()
 
-            doc2 = Document.objects.latest("pk")
+            doc2 = Document.objects.filter(pk=2).first()
 
         with self.get_consumer(settings.CONSUMPTION_DIR / "simple.png.pdf") as consumer:
             consumer.run()
 
-            doc3 = Document.objects.latest("pk")
+            doc3 = Document.objects.filter(pk=3).first()
 
         self.assertEqual(doc1.filename, "simple.png")
         self.assertEqual(doc1.archive_filename, "simple.pdf")

src/documents/tests/test_document_list_effective_content_annotation.py

@@ -242,7 +242,9 @@ class TestDocumentListEffectiveContentAnnotation:
         # Only the list query itself reads a content column: no extra query
         # for the skipped prefetch, none for a per-instance fallback
         content_queries = [
-            query for query in ctx.captured_queries if _content_column() in query["sql"]
+            query
+            for query in ctx.captured_queries
+            if '"documents_document"."content"' in query["sql"]
         ]
         assert len(content_queries) == 1
 
@@ -363,11 +365,6 @@ def _get_document_queries(
     return [q for q in ctx.captured_queries if '"django_content_type"' not in q["sql"]]
 
 
-def _content_column() -> str:
-    quote = connection.ops.quote_name
-    return f"{quote('documents_document')}.{quote('content')}"
-
-
 def _get_effective_content_fallback_queries(
     ctx: CaptureQueriesContext,
 ) -> list[dict[str, str]]:
@@ -382,7 +379,7 @@ def _get_effective_content_fallback_queries(
     return [
         q
         for q in ctx.captured_queries
-        if q["sql"].startswith(f"SELECT {_content_column()} FROM")
+        if q["sql"].startswith('SELECT "documents_document"."content" FROM')
     ]
 
 

src/documents/tests/test_file_handling.py

@@ -760,9 +760,6 @@ class TestFileHandlingWithArchive(DirectoriesMixin, FileSystemAssertsMixin, Test
             archive_checksum="B",
         )
 
-        # Without a format the files are renamed to match the primary key
-        original = doc.source_path
-        archive = doc.archive_path
         self.assertIsFile(original)
         self.assertIsFile(archive)
         self.assertIsFile(doc.source_path)
@@ -981,9 +978,6 @@ class TestFileHandlingWithArchive(DirectoriesMixin, FileSystemAssertsMixin, Test
             archive_filename="0000001.pdf",
         )
 
-        # Without a format the files are renamed to match the primary key
-        original = doc.source_path
-        archive = doc.archive_path
         self.assertIsFile(original)
         self.assertIsFile(archive)
         self.assertIsFile(doc.source_path)

src/documents/tests/test_management_exporter.py

@@ -151,20 +151,6 @@ class TestExportImport(
 
         super().setUp()
 
-    def _install_sample_files(self) -> None:
-        documents_dir = Path(self.dirs.media_dir) / "documents"
-        shutil.rmtree(documents_dir)
-        install_document_samples(documents_dir)
-        # Thumbnails are located by primary key, which the database sequence
-        # does not reset between tests on PostgreSQL
-        for number, document in enumerate(
-            (self.d1, self.d2, self.d3, self.d4),
-            start=1,
-        ):
-            source = documents_dir / "thumbnails" / f"{number:07}.webp"
-            if source != document.thumbnail_path:
-                shutil.copy(source, document.thumbnail_path)
-
     def _get_document_from_manifest(self, manifest, id):
         f = list(
             filter(
@@ -218,7 +204,8 @@ class TestExportImport(
         return manifest
 
     def test_exporter(self, *, use_filename_format=False) -> None:
-        self._install_sample_files()
+        shutil.rmtree(Path(self.dirs.media_dir) / "documents")
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         num_permission_objects = Permission.objects.count()
 
@@ -321,7 +308,8 @@ class TestExportImport(
             self.assertEqual(messages.total_issue_count, 0)
 
     def test_exporter_with_filename_format(self) -> None:
-        self._install_sample_files()
+        shutil.rmtree(Path(self.dirs.media_dir) / "documents")
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         with override_settings(
             FILENAME_FORMAT="{created_year}/{correspondent}/{title}",
@@ -329,7 +317,8 @@ class TestExportImport(
             self.test_exporter(use_filename_format=True)
 
     def test_exporter_includes_share_links_and_bundles(self) -> None:
-        self._install_sample_files()
+        shutil.rmtree(Path(self.dirs.media_dir) / "documents")
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         share_link = ShareLink.objects.create(
             slug="share-link-slug",
@@ -427,7 +416,8 @@ class TestExportImport(
             )
 
     def test_update_export_changed_time(self) -> None:
-        self._install_sample_files()
+        shutil.rmtree(Path(self.dirs.media_dir) / "documents")
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         self._do_export()
         self.assertIsFile(self.target / "manifest.json")
@@ -462,7 +452,8 @@ class TestExportImport(
         self.assertEqual(st_mtime_3, st_mtime_4)
 
     def test_update_export_changed_checksum(self) -> None:
-        self._install_sample_files()
+        shutil.rmtree(Path(self.dirs.media_dir) / "documents")
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         self._do_export()
 
@@ -488,7 +479,8 @@ class TestExportImport(
         self.assertIsFile(self.target / "manifest.json")
 
     def test_update_export_deleted_document(self) -> None:
-        self._install_sample_files()
+        shutil.rmtree(Path(self.dirs.media_dir) / "documents")
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         manifest = self._do_export()
 
@@ -519,7 +511,8 @@ class TestExportImport(
 
     @override_settings(FILENAME_FORMAT="{title}/{correspondent}")
     def test_update_export_changed_location(self) -> None:
-        self._install_sample_files()
+        shutil.rmtree(Path(self.dirs.media_dir) / "documents")
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         self._do_export(use_filename_format=True)
         self.assertIsFile(self.target / "wow1" / "c.pdf")
@@ -560,7 +553,8 @@ class TestExportImport(
             - Zipfile is created
             - Zipfile contains exported files
         """
-        self._install_sample_files()
+        shutil.rmtree(Path(self.dirs.media_dir) / "documents")
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         args = ["document_exporter", self.target, "--zip"]
 
@@ -588,7 +582,8 @@ class TestExportImport(
             - Zipfile is created
             - Zipfile contains exported files
         """
-        self._install_sample_files()
+        shutil.rmtree(Path(self.dirs.media_dir) / "documents")
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         args = ["document_exporter", self.target, "--zip", "--use-filename-format"]
 
@@ -623,7 +618,8 @@ class TestExportImport(
             - Zipfile contains exported files
             - The existing file and directory in target are removed
         """
-        self._install_sample_files()
+        shutil.rmtree(Path(self.dirs.media_dir) / "documents")
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         # Create stuff in target directory
         existing_file = self.target / "test.txt"
@@ -718,7 +714,8 @@ class TestExportImport(
             - Manifest.json doesn't contain information about archive files
             - Documents can be imported again
         """
-        self._install_sample_files()
+        shutil.rmtree(Path(self.dirs.media_dir) / "documents")
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         manifest = self._do_export()
         has_archive = False
@@ -760,7 +757,8 @@ class TestExportImport(
             - Manifest.json doesn't contain information about thumbnails
             - Documents can be imported again
         """
-        self._install_sample_files()
+        shutil.rmtree(Path(self.dirs.media_dir) / "documents")
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         manifest = self._do_export()
         has_thumbnail = False
@@ -804,7 +802,8 @@ class TestExportImport(
             - Main manifest.json file doesn't contain information about documents
             - Documents can be imported again
         """
-        self._install_sample_files()
+        shutil.rmtree(Path(self.dirs.media_dir) / "documents")
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         manifest = self._do_export(split_manifest=True)
         has_document = False
@@ -828,7 +827,8 @@ class TestExportImport(
             self.assertEqual(CustomFieldInstance.objects.count(), 1)
 
     def _export_import_barcodes(self, *, split_manifest: bool) -> None:
-        self._install_sample_files()
+        shutil.rmtree(Path(self.dirs.media_dir) / "documents")
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
         DocumentBarcodeFactory(document=self.d1, value="https://example.com")
         DocumentBarcodeFactory(document=self.d2, page=2, value="DE8937")
 
@@ -863,7 +863,8 @@ class TestExportImport(
         THEN:
             - Documents can be imported again
         """
-        self._install_sample_files()
+        shutil.rmtree(Path(self.dirs.media_dir) / "documents")
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         self._do_export(use_folder_prefix=True)
 
@@ -889,7 +890,8 @@ class TestExportImport(
         THEN:
             - Documents can be imported again
         """
-        self._install_sample_files()
+        shutil.rmtree(Path(self.dirs.media_dir) / "documents")
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         self._do_export(use_folder_prefix=True, split_manifest=True)
 
@@ -915,7 +917,8 @@ class TestExportImport(
             - ContentType & Permission objects are not deleted, db transaction rolled back
         """
 
-        self._install_sample_files()
+        shutil.rmtree(Path(self.dirs.media_dir) / "documents")
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         num_content_type_objects = ContentType.objects.count()
         num_permission_objects = Permission.objects.count()
@@ -951,7 +954,8 @@ class TestExportImport(
             self.assertEqual(Permission.objects.count(), num_permission_objects + 1)
 
     def test_exporter_with_auditlog_disabled(self) -> None:
-        self._install_sample_files()
+        shutil.rmtree(Path(self.dirs.media_dir) / "documents")
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         with override_settings(
             AUDIT_LOG_ENABLED=False,
@@ -970,7 +974,8 @@ class TestExportImport(
             - The soft-deleted document, note, and custom field instance
               survive the round-trip with deleted_at preserved
         """
-        self._install_sample_files()
+        shutil.rmtree(Path(self.dirs.media_dir) / "documents")
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         # d1 has self.note and self.cfi1 attached via setUp
         self.d1.delete()

src/documents/tests/test_management_fuzzy.py

@@ -19,10 +19,6 @@ class TestFuzzyMatchCommand(TestCase):
         call_command(
             "document_fuzzy_match",
             "--no-progress-bar",
-            # The default scales with the CPU count and forks, which closes
-            # the test's database connection on PostgreSQL
-            "--processes",
-            "1",
             *args,
             stdout=stdout,
             stderr=stderr,

src/documents/tests/test_management_retagger.py

@@ -425,29 +425,26 @@ class TestRetaggerStoragePath(DirectoriesMixin):
 @pytest.mark.management
 @pytest.mark.django_db
 class TestRetaggerIdRange(DirectoriesMixin):
+    @pytest.mark.usefixtures("documents")
     @pytest.mark.parametrize(
-        ("range_end", "expected_count"),
+        ("id_range_args", "expected_count"),
         [
-            pytest.param("second", 1, id="narrow_range_limits_scope"),
-            pytest.param("extra", 2, id="wide_range_tags_all_matches"),
+            pytest.param(["1", "2"], 1, id="narrow_range_limits_scope"),
+            pytest.param(["1", "9999"], 2, id="wide_range_tags_all_matches"),
         ],
     )
     def test_id_range_limits_scope(
         self,
         tags: TagTuple,
-        documents: DocumentTuple,
-        range_end: str,
+        id_range_args: list[str],
         expected_count: int,
     ) -> None:
-        first, second, *_ = documents
-        extra = DocumentFactory(content="NOT the first document")
-        end = {"second": second, "extra": extra}[range_end]
+        DocumentFactory(content="NOT the first document")
         call_command(
             "document_retagger",
             "--tags",
             "--id-range",
-            str(first.pk),
-            str(end.pk),
+            *id_range_args,
             skip_checks=True,
         )
         tag_first, *_ = tags

src/documents/tests/test_matching_glob_regex.py

@@ -1,68 +0,0 @@
-import re
-from fnmatch import fnmatch
-
-import pytest
-
-from documents.matching import glob_to_database_regex
-from documents.models import Document
-from paperless_testing.factories import DocumentFactory
-
-NAMES = [
-    "invoice.pdf",
-    "Invoice.PDF",
-    "invoice_2024.pdf",
-    "a.b.c",
-    "a-b",
-    "sample [1].pdf",
-    "sample 1.pdf",
-    "x^y",
-    "back\\slash",
-    "dir/file.pdf",
-    "",
-]
-
-PATTERNS = [
-    "*",
-    "invoice.pdf",
-    "*.pdf",
-    "*invoice*pdf",
-    "*a*b*c*",
-    "invoice_????.pdf",
-    "sample [[]1].pdf",
-    "sample [1-2].pdf",
-    "sample [!2].pdf",
-    "sample [^2].pdf",
-    "sample [",
-    "a.b.c",
-    "x^y",
-    "back\\slash",
-    "[]]",
-]
-
-
-@pytest.mark.parametrize("pattern", PATTERNS)
-def test_regex_agrees_with_fnmatch(pattern: str) -> None:
-    regex = glob_to_database_regex(pattern)
-    for name in NAMES:
-        expected = fnmatch(name.lower(), pattern.lower())
-        actual = re.search(regex, name, re.IGNORECASE) is not None
-        assert actual is expected, f"{pattern!r} vs {name!r}"
-
-
-@pytest.mark.parametrize("pattern", ["*", "*a*b*c*", "a*b*c*d*e"])
-def test_regex_avoids_syntax_postgresql_rejects(pattern: str) -> None:
-    regex = glob_to_database_regex(pattern)
-    assert not any(marker in regex for marker in ("(?", "\\Z"))
-
-
-@pytest.mark.django_db
-def test_database_filter_matches_glob() -> None:
-    matching = DocumentFactory(original_filename="Invoice_2024.PDF")
-    DocumentFactory(original_filename="invoice_2024.txt")
-    DocumentFactory(original_filename="receipt.pdf")
-
-    found = Document.objects.filter(
-        original_filename__iregex=glob_to_database_regex("*invoice*.pdf"),
-    )
-
-    assert list(found) == [matching]

src/documents/tests/test_tag_adjacency.py

@@ -0,0 +1,104 @@
+from django.core.exceptions import FieldDoesNotExist
+from django.db import connection
+from django.test import TestCase
+from django.test.utils import CaptureQueriesContext
+
+from documents.management.commands.document_importer import _deserialize_record
+from documents.models import Tag
+from documents.tag_hierarchy import TagHierarchy
+from paperless_testing.migrations import TestMigrations
+
+
+class TestTagAdjacency(TestCase):
+    def test_held_instance_uses_current_parent_edges(self):
+        first = Tag.objects.create(name="First")
+        second = Tag.objects.create(name="Second")
+        child = Tag.objects.create(name="Child", tn_parent=first)
+        Tag.objects.filter(pk=child.pk).update(tn_parent=second)
+        assert first.get_descendants_pks() == set()
+        assert second.get_descendants_pks() == {child.pk}
+
+    def test_queryset_delete_preserves_cascade(self):
+        root = Tag.objects.create(name="Root")
+        child = Tag.objects.create(name="Child", tn_parent=root)
+        Tag.objects.create(name="Grandchild", tn_parent=child)
+        survivor = Tag.objects.create(name="Other root")
+        Tag.objects.filter(pk=root.pk).delete()
+        assert list(Tag.objects.values_list("pk", flat=True)) == [survivor.pk]
+
+    def test_flat_writes_do_not_update_other_tags(self):
+        Tag.objects.bulk_create([Tag(name=f"Tag {i}") for i in range(100)])
+        with CaptureQueriesContext(connection) as queries:
+            new = Tag.objects.create(name="New")
+        assert not any(q["sql"].startswith("UPDATE") for q in queries)
+        with CaptureQueriesContext(connection) as queries:
+            new.name = "Renamed"
+            new.save()
+        tag_updates = [
+            q["sql"] for q in queries if q["sql"].startswith('UPDATE "documents_tag"')
+        ]
+        assert len(tag_updates) == 1
+        assert 'WHERE "documents_tag"."id" =' in tag_updates[0]
+
+    def test_batch_snapshot_is_one_query_and_includes_overlapping_roots(self):
+        root = Tag.objects.create(name="Root")
+        child = Tag.objects.create(name="Child", tn_parent=root)
+        leaf = Tag.objects.create(name="Leaf", tn_parent=child)
+        with self.assertNumQueries(1):
+            hierarchy = Tag.get_hierarchy()
+            assert hierarchy.with_ancestors([leaf.pk]) == {root.pk, child.pk, leaf.pk}
+            assert hierarchy.with_descendants([root.pk, child.pk]) == {
+                root.pk,
+                child.pk,
+                leaf.pk,
+            }
+        assert hierarchy.height(None) == 0
+
+    def test_legacy_export_fields_are_ignored_but_parent_is_preserved(self):
+        model, tag, m2m = _deserialize_record(
+            {
+                "model": "documents.tag",
+                "pk": 2,
+                "fields": {
+                    "name": "Child",
+                    "tn_parent": 1,
+                    "tn_order": 3,
+                    "tn_siblings_pks": "4,5",
+                    "tn_descendants_pks": "6",
+                },
+            },
+        )
+        assert model is Tag
+        assert tag.tn_parent_id == 1
+        assert tag.name == "Child"
+        assert not m2m
+        with self.assertRaises(FieldDoesNotExist):
+            _deserialize_record(
+                {"model": "documents.tag", "pk": 3, "fields": {"tn_typo": "bad"}},
+            )
+
+    def test_malformed_cycles_terminate(self):
+        hierarchy = TagHierarchy([(1, 2), (2, 1)])
+        assert hierarchy.with_descendants([1]) == {1, 2}
+        assert set(hierarchy.ancestors(2)) == {1, 2}
+
+
+class TestTagAdjacencyMigration(TestMigrations):
+    migrate_from = "0027_documentbarcode"
+    migrate_to = "0028_replace_tag_tree_fields"
+
+    def setUpBeforeMigration(self, apps):
+        tag = apps.get_model("documents", "Tag")
+        root = tag.objects.create(name="Root")
+        child = tag.objects.create(name="Child", tn_parent=root)
+        self.edges = [(root.pk, None), (child.pk, root.pk)]
+
+    def test_parent_edges_survive(self):
+        tag = self.apps.get_model("documents", "Tag")
+        assert (
+            list(tag.objects.order_by("pk").values_list("pk", "tn_parent_id"))
+            == self.edges
+        )
+        assert {
+            field.name for field in tag._meta.fields if field.name.startswith("tn_")
+        } == {"tn_parent"}

src/documents/tests/test_workflows.py

@@ -174,8 +174,8 @@ class TestWorkflows(
         w.save()
 
         self.assertEqual(w.__str__(), "Workflow: Workflow 1")
-        self.assertEqual(trigger.__str__(), f"WorkflowTrigger {trigger.pk}")
-        self.assertEqual(action.__str__(), f"WorkflowAction {action.pk}")
+        self.assertEqual(trigger.__str__(), "WorkflowTrigger 1")
+        self.assertEqual(action.__str__(), "WorkflowAction 1")
 
         test_file = shutil.copy(
             self.SIMPLE_PDF,
@@ -433,7 +433,7 @@ class TestWorkflows(
                 list(document.tags.all()),
                 [self.t1, self.t2, self.t3],
             )
-            self.assertCountEqual(
+            self.assertEqual(
                 list(
                     get_users_with_perms(
                         document,

src/documents/views.py

@@ -627,7 +627,7 @@ class TagViewSet(PermissionsAwareDocumentCountMixin, ModelViewSet[Tag]):
         queryset = queryset.order_by(*ordering)
 
         all_tags = list(queryset)
-        descendant_pks = {pk for tag in all_tags for pk in tag.get_descendants_pks()}
+        descendant_pks = Tag.get_hierarchy().descendants(t.pk for t in all_tags)
 
         if descendant_pks:
             user = getattr(getattr(self, "request", None), "user", None)
@@ -5060,12 +5060,7 @@ class BulkEditObjectsView(PassUserMixin):
             if object_type == "tags":
                 editable_ids = set(user_permitted_objects.values_list("pk", flat=True))
                 all_ids = set(objs.values_list("pk", flat=True))
-                for tag in objs:
-                    all_ids.update(
-                        descendant.pk
-                        for descendant in tag.get_descendants()
-                        if descendant.pk in editable_ids
-                    )
+                all_ids.update(Tag.get_hierarchy().descendants(all_ids) & editable_ids)
                 objs = object_class.objects.filter(pk__in=all_ids)
             objs = objs.select_related("owner")
             object_ids = list(objs.values_list("pk", flat=True))

src/documents/workflows/mutations.py

@@ -6,6 +6,7 @@ from guardian.shortcuts import remove_perm
 from documents.data_models import DocumentMetadataOverrides
 from documents.models import CustomFieldInstance
 from documents.models import Document
+from documents.models import Tag
 from documents.models import WorkflowAction
 from documents.permissions import PermissionsSpec
 from documents.permissions import set_permissions_for_objects
@@ -134,10 +135,9 @@ def apply_assignment_to_overrides(
     if action.has_assign_tags:
         if overrides.tag_ids is None:
             overrides.tag_ids = []
-        tag_ids_to_add: set[int] = set()
-        for tag in action.assign_tags.all():
-            tag_ids_to_add.add(tag.pk)
-            tag_ids_to_add.update(int(pk) for pk in tag.get_ancestors_pks())
+        tag_ids_to_add = Tag.get_hierarchy().with_ancestors(
+            tag.pk for tag in action.assign_tags.all()
+        )
 
         overrides.tag_ids = list(set(overrides.tag_ids) | tag_ids_to_add)
 
@@ -216,10 +216,9 @@ def apply_removal_to_document(
     if action.remove_all_tags:
         Document.objects.get(pk=document.pk).tags.clear()
     else:
-        tag_ids_to_remove: set[int] = set()
-        for tag in action.remove_tags.all():
-            tag_ids_to_remove.add(tag.pk)
-            tag_ids_to_remove.update(int(pk) for pk in tag.get_descendants_pks())
+        tag_ids_to_remove = Tag.get_hierarchy().with_descendants(
+            tag.pk for tag in action.remove_tags.all()
+        )
 
         if tag_ids_to_remove:
             Document.objects.get(pk=document.pk).tags.remove(*tag_ids_to_remove)
@@ -297,10 +296,9 @@ def apply_removal_to_overrides(
     if action.remove_all_tags:
         overrides.tag_ids = None
     elif overrides.tag_ids:
-        tag_ids_to_remove: set[int] = set()
-        for tag in action.remove_tags.all():
-            tag_ids_to_remove.add(tag.pk)
-            tag_ids_to_remove.update(int(pk) for pk in tag.get_descendants_pks())
+        tag_ids_to_remove = Tag.get_hierarchy().with_descendants(
+            tag.pk for tag in action.remove_tags.all()
+        )
 
         overrides.tag_ids = [t for t in overrides.tag_ids if t not in tag_ids_to_remove]
 

src/paperless/settings/__init__.py

@@ -157,7 +157,6 @@ INSTALLED_APPS = [
     "allauth.headless",
     "drf_spectacular",
     "drf_spectacular_sidecar",
-    "treenode",
     *env_apps,
 ]
 

src/paperless_ai/tests/test_chat.py

@@ -1,7 +1,6 @@
 from __future__ import annotations
 
 import json
-from contextlib import nullcontext
 from typing import TYPE_CHECKING
 from typing import Any
 from unittest.mock import MagicMock
@@ -38,13 +37,6 @@ def patch_embed_model():
     llama_settings.Settings.embed_model = None
 
 
-@pytest.fixture(autouse=True)
-def keep_db_connection():
-    # Closing the connection would roll back the test's transaction on PostgreSQL
-    with patch("paperless_ai.chat.db_connection_released", nullcontext):
-        yield
-
-
 @pytest.fixture(autouse=True)
 def patch_embed_nodes():
     with patch(

uv.lock

@@ -1210,15 +1210,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/99/c3/305a9f7611c0dc96d2a638bc3a67bdcde5a7faa5f4669188db018b8af6fc/django_stubs_ext-6.1.1-py3-none-any.whl", hash = "sha256:64aebb7ce2c327a4a2b75207d67034e879fd7edf027c93487be69da363dc79fa", size = 10853, upload-time = "2026-09-14T08:45:51.289Z" },
 ]
 
-[[package]]
-name = "django-treenode"
-version = "0.25.0"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/cb/2b/09f04b44b3583a911ae4f5d0e3360a23d529704c9e9115fce2520b7d4420/django_treenode-0.25.0.tar.gz", hash = "sha256:d14d0eb3571c227ce11147210d62a8f87b568bbb30fa76a5be9b9e6d514157c3", size = 29951, upload-time = "2026-08-26T00:20:13.489Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/e1/ac/2140e8c20e2a47457ec23302273527d3430bf5c09edb8940d74c0725c138/django_treenode-0.25.0-py3-none-any.whl", hash = "sha256:f47caab5440420870b6287602b3ee401ca354416d44b24ab97579be5ea658927", size = 22343, upload-time = "2026-08-26T00:20:12.078Z" },
-]
-
 [[package]]
 name = "djangorestframework"
 version = "3.18.3"
@@ -3107,7 +3098,6 @@ dependencies = [
     { name = "django-multiselectfield" },
     { name = "django-rich" },
     { name = "django-soft-delete" },
-    { name = "django-treenode" },
     { name = "djangorestframework" },
     { name = "drf-spectacular" },
     { name = "drf-spectacular-sidecar" },
@@ -3258,7 +3248,6 @@ requires-dist = [
     { name = "django-multiselectfield", specifier = "~=1.0.1" },
     { name = "django-rich", specifier = "~=2.2.0" },
     { name = "django-soft-delete", specifier = "~=1.0.18" },
-    { name = "django-treenode", specifier = ">=0.24" },
     { name = "djangorestframework", specifier = "~=3.16" },
     { name = "drf-spectacular", specifier = "~=0.30" },
     { name = "drf-spectacular-sidecar", specifier = ">=2026.7.1,<2026.10" },