Performance fix: use subqueries to improve object retrieval in large installs (#11950)

Co-authored-by: github-actions <41898282+github-actions[bot]@users.noreply.github.com>

.github/workflows/ci.yml

@@ -617,7 +617,7 @@ jobs:
           version: ${{ steps.get_version.outputs.version }}
           prerelease: ${{ steps.get_version.outputs.prerelease }}
           publish: true # ensures release is not marked as draft
-          committish: ${{ github.sha }}
+          commitish: main
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       - name: Upload release archive

docker/management_script.sh

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py management_command "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py management_command "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py management_command "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/convert_mariadb_uuid

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py convert_mariadb_uuid "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py convert_mariadb_uuid "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py convert_mariadb_uuid "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/createsuperuser

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py createsuperuser "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py createsuperuser "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py createsuperuser "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/decrypt_documents

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py decrypt_documents "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py decrypt_documents "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py decrypt_documents "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/document_archiver

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py document_archiver "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py document_archiver "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py document_archiver "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/document_create_classifier

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py document_create_classifier "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py document_create_classifier "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py document_create_classifier "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/document_exporter

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py document_exporter "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py document_exporter "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py document_exporter "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/document_fuzzy_match

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py document_fuzzy_match "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py document_fuzzy_match "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py document_fuzzy_match "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/document_importer

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py document_importer "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py document_importer "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py document_importer "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/document_index

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py document_index "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py document_index "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py document_index "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/document_renamer

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py document_renamer "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py document_renamer "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py document_renamer "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/document_retagger

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py document_retagger "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py document_retagger "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py document_retagger "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/document_sanity_checker

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py document_sanity_checker "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py document_sanity_checker "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py document_sanity_checker "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/document_thumbnails

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py document_thumbnails "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py document_thumbnails "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py document_thumbnails "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/mail_fetcher

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py mail_fetcher "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py mail_fetcher "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py mail_fetcher "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/manage_superuser

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py manage_superuser "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py manage_superuser "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py manage_superuser "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/prune_audit_logs

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py prune_audit_logs "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py prune_audit_logs "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py prune_audit_logs "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docs/changelog.md

@@ -1,7 +1,79 @@
 # Changelog
 
+## paperless-ngx 2.20.6
+
+### Bug Fixes
+
+-   Fix: extract all ids for nested tags [@shamoon](https://github.com/shamoon) ([#11888](https://github.com/paperless-ngx/paperless-ngx/pull/11888))
+-   Fixhancement: change date calculation for 'this year' to include future documents [@shamoon](https://github.com/shamoon) ([#11884](https://github.com/paperless-ngx/paperless-ngx/pull/11884))
+-   Fix: Running management scripts under rootless could fail [@stumpylog](https://github.com/stumpylog) ([#11870](https://github.com/paperless-ngx/paperless-ngx/pull/11870))
+-   Fix: use correct field id for overrides [@shamoon](https://github.com/shamoon) ([#11869](https://github.com/paperless-ngx/paperless-ngx/pull/11869))
+
+### All App Changes
+
+<details>
+<summary>3 changes</summary>
+
+-   Fix: extract all ids for nested tags [@shamoon](https://github.com/shamoon) ([#11888](https://github.com/paperless-ngx/paperless-ngx/pull/11888))
+-   Fixhancement: change date calculation for 'this year' to include future documents [@shamoon](https://github.com/shamoon) ([#11884](https://github.com/paperless-ngx/paperless-ngx/pull/11884))
+-   Fix: use correct field id for overrides [@shamoon](https://github.com/shamoon) ([#11869](https://github.com/paperless-ngx/paperless-ngx/pull/11869))
+</details>
+
+## paperless-ngx 2.20.5
+
+### Bug Fixes
+
+-   Fix: ensure horizontal scroll for long tag names in list, wrap tags without parent [@shamoon](https://github.com/shamoon) ([#11811](https://github.com/paperless-ngx/paperless-ngx/pull/11811))
+-   Fix: use explicit order field for workflow actions [@shamoon](https://github.com/shamoon) [@stumpylog](https://github.com/stumpylog) ([#11781](https://github.com/paperless-ngx/paperless-ngx/pull/11781))
+
+### All App Changes
+
+<details>
+<summary>2 changes</summary>
+
+-   Fix: ensure horizontal scroll for long tag names in list, wrap tags without parent [@shamoon](https://github.com/shamoon) ([#11811](https://github.com/paperless-ngx/paperless-ngx/pull/11811))
+-   Fix: use explicit order field for workflow actions [@shamoon](https://github.com/shamoon) [@stumpylog](https://github.com/stumpylog) ([#11781](https://github.com/paperless-ngx/paperless-ngx/pull/11781))
+</details>
+
+## paperless-ngx 2.20.4
+
+### Security
+
+-   Resolve [GHSA-28cf-xvcf-hw6m](https://github.com/paperless-ngx/paperless-ngx/security/advisories/GHSA-28cf-xvcf-hw6m)
+
+### Bug Fixes
+
+-   Fix: propagate metadata override created value [@shamoon](https://github.com/shamoon) ([#11659](https://github.com/paperless-ngx/paperless-ngx/pull/11659))
+-   Fix: support ordering by storage path name [@shamoon](https://github.com/shamoon) ([#11661](https://github.com/paperless-ngx/paperless-ngx/pull/11661))
+-   Fix: validate cf integer values within PostgreSQL range [@shamoon](https://github.com/shamoon) ([#11666](https://github.com/paperless-ngx/paperless-ngx/pull/11666))
+-   Fixhancement: add error handling and retry when opening index [@shamoon](https://github.com/shamoon) ([#11731](https://github.com/paperless-ngx/paperless-ngx/pull/11731))
+-   Fix: fix recurring workflow to respect latest run time [@shamoon](https://github.com/shamoon) ([#11735](https://github.com/paperless-ngx/paperless-ngx/pull/11735))
+
+### All App Changes
+
+<details>
+<summary>5 changes</summary>
+
+-   Fix: propagate metadata override created value [@shamoon](https://github.com/shamoon) ([#11659](https://github.com/paperless-ngx/paperless-ngx/pull/11659))
+-   Fix: support ordering by storage path name [@shamoon](https://github.com/shamoon) ([#11661](https://github.com/paperless-ngx/paperless-ngx/pull/11661))
+-   Fix: validate cf integer values within PostgreSQL range [@shamoon](https://github.com/shamoon) ([#11666](https://github.com/paperless-ngx/paperless-ngx/pull/11666))
+-   Fixhancement: add error handling and retry when opening index [@shamoon](https://github.com/shamoon) ([#11731](https://github.com/paperless-ngx/paperless-ngx/pull/11731))
+-   Fix: fix recurring workflow to respect latest run time [@shamoon](https://github.com/shamoon) ([#11735](https://github.com/paperless-ngx/paperless-ngx/pull/11735))
+</details>
+
+## paperless-ngx 2.20.3
+
+### Security
+
+-   Resolve [GHSA-7cq3-mhxq-w946](https://github.com/paperless-ngx/paperless-ngx/security/advisories/GHSA-7cq3-mhxq-w946)
+
 ## paperless-ngx 2.20.2
 
+### Security
+
+-   Resolve [GHSA-6653-vcx4-69mc](https://github.com/paperless-ngx/paperless-ngx/security/advisories/GHSA-6653-vcx4-69mc)
+-   Resolve [GHSA-24x5-wp64-9fcc](https://github.com/paperless-ngx/paperless-ngx/security/advisories/GHSA-24x5-wp64-9fcc)
+
 ### Features / Enhancements
 
 -   Tweakhancement: dim inactive users in users-groups list [@shamoon](https://github.com/shamoon) ([#11537](https://github.com/paperless-ngx/paperless-ngx/pull/11537))

docs/configuration.md

@@ -170,11 +170,18 @@ Available options are `postgresql` and `mariadb`.
 
     !!! note
 
-        A small pool is typically sufficient — for example, a size of 4.
-        Make sure your PostgreSQL server's max_connections setting is large enough to handle:
-        ```(Paperless workers + Celery workers) × pool size + safety margin```
-        For example, with 4 Paperless workers and 2 Celery workers, and a pool size of 4:
-        (4 + 2) × 4 + 10 = 34 connections required.
+        A pool of 8-10 connections per worker is typically sufficient.
+        If you encounter error messages such as `couldn't get a connection`
+        or database connection timeouts, you probably need to increase the pool size.
+
+    !!! warning
+        Make sure your PostgreSQL `max_connections` setting is large enough to handle the connection pools:
+        `(NB_PAPERLESS_WORKERS + NB_CELERY_WORKERS) × POOL_SIZE + SAFETY_MARGIN`. For example, with
+        4 Paperless workers and 2 Celery workers, and a pool size of 8:``(4 + 2) × 8 + 10 = 58`,
+        so `max_connections = 60` (or even more) is appropriate.
+
+        This assumes only Paperless-ngx connects to your PostgreSQL instance. If you have other applications,
+        you should increase `max_connections` accordingly.
 
 #### [`PAPERLESS_DB_READ_CACHE_ENABLED=<bool>`](#PAPERLESS_DB_READ_CACHE_ENABLED) {#PAPERLESS_DB_READ_CACHE_ENABLED}
 
@@ -1007,7 +1014,7 @@ still perform some basic text pre-processing before matching.
 
 : See also `PAPERLESS_NLTK_DIR`.
 
-    Defaults to 1.
+    Defaults to true, enabling the feature.
 
 #### [`PAPERLESS_DATE_PARSER_LANGUAGES=<lang>`](#PAPERLESS_DATE_PARSER_LANGUAGES) {#PAPERLESS_DATE_PARSER_LANGUAGES}
 
@@ -1074,7 +1081,7 @@ valid crontab(5) expression describing when to run.
 
 : Enables compression of the responses from the webserver.
 
-: Defaults to 1, enabling compression.
+: Defaults to true, enabling compression.
 
     !!! note
 

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "paperless-ngx"
-version = "2.20.4"
+version = "2.20.6"
 description = "A community-supported supercharged document management system: scan, index and archive all your physical documents"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -238,7 +238,7 @@ lint.isort.force-single-line = true
 
 [tool.codespell]
 write-changes = true
-ignore-words-list = "criterias,afterall,valeu,ureue,equest,ure,assertIn,Oktober"
+ignore-words-list = "criterias,afterall,valeu,ureue,equest,ure,assertIn,Oktober,commitish"
 skip = "src-ui/src/locale/*,src-ui/pnpm-lock.yaml,src-ui/e2e/*,src/paperless_mail/tests/samples/*,src/documents/tests/samples/*,*.po,*.json"
 
 [tool.pytest.ini_options]

src-ui/package.json

@@ -1,6 +1,6 @@
 {
   "name": "paperless-ngx-ui",
-  "version": "2.20.4",
+  "version": "2.20.6",
   "scripts": {
     "preinstall": "npx only-allow pnpm",
     "ng": "ng",

src-ui/src/app/components/common/input/tags/tags.component.html

@@ -28,7 +28,7 @@
             </button>
           </ng-template>
           <ng-template ng-option-tmp let-item="item" let-index="index" let-search="searchTerm">
-            <div class="tag-option-row d-flex align-items-center">
+            <div class="tag-option-row d-flex align-items-center" [class.w-auto]="!getTag(item.id)?.parent">
               @if (item.id && tags) {
                 @if (getTag(item.id)?.parent) {
                   <i-bs name="list-nested" class="me-1"></i-bs>

src-ui/src/app/components/common/input/tags/tags.component.scss

@@ -22,8 +22,8 @@
 }
 
 // Dropdown hierarchy reveal for ng-select options
-::ng-deep .ng-dropdown-panel .ng-option {
-  overflow-x: scroll;
+:host ::ng-deep .ng-dropdown-panel .ng-option {
+  overflow-x: auto !important;
 
   .tag-option-row {
     font-size: 1rem;
@@ -41,12 +41,12 @@
   }
 }
 
-::ng-deep .ng-dropdown-panel .ng-option:hover .hierarchy-reveal,
-::ng-deep .ng-dropdown-panel .ng-option.ng-option-marked .hierarchy-reveal {
+:host ::ng-deep .ng-dropdown-panel .ng-option:hover .hierarchy-reveal,
+:host ::ng-deep .ng-dropdown-panel .ng-option.ng-option-marked .hierarchy-reveal {
   max-width: 1000px;
 }
 
 ::ng-deep .ng-dropdown-panel .ng-option:hover .hierarchy-indicator,
-::ng-deep .ng-dropdown-panel .ng-option.ng-option-marked .hierarchy-indicator {
+:host ::ng-deep .ng-dropdown-panel .ng-option.ng-option-marked .hierarchy-indicator {
   background: transparent;
 }

src-ui/src/app/components/manage/management-list/management-list.component.spec.ts

@@ -229,6 +229,21 @@ describe('ManagementListComponent', () => {
     expect(reloadSpy).toHaveBeenCalled()
   })
 
+  it('should use the all list length for collection size when provided', fakeAsync(() => {
+    jest.spyOn(tagService, 'listFiltered').mockReturnValueOnce(
+      of({
+        count: 1,
+        all: [1, 2, 3],
+        results: tags.slice(0, 1),
+      })
+    )
+
+    component.reloadData()
+    tick(100)
+
+    expect(component.collectionSize).toBe(3)
+  }))
+
   it('should support quick filter for objects', () => {
     const qfSpy = jest.spyOn(documentListViewService, 'quickFilter')
     const filterButton = fixture.debugElement.queryAll(By.css('button'))[9]

src-ui/src/app/components/manage/management-list/management-list.component.ts

@@ -171,7 +171,7 @@ export abstract class ManagementListComponent<T extends MatchingModel>
         tap((c) => {
           this.unfilteredData = c.results
           this.data = this.filterData(c.results)
-          this.collectionSize = c.count
+          this.collectionSize = c.all?.length ?? c.count
         }),
         delay(100)
       )
@@ -364,7 +364,7 @@ export abstract class ManagementListComponent<T extends MatchingModel>
       backdrop: 'static',
     })
     modal.componentInstance.title = $localize`Confirm delete`
-    modal.componentInstance.messageBold = $localize`This operation will permanently delete all objects.`
+    modal.componentInstance.messageBold = $localize`This operation will permanently delete the selected ${this.typeNamePlural}.`
     modal.componentInstance.message = $localize`This operation cannot be undone.`
     modal.componentInstance.btnClass = 'btn-danger'
     modal.componentInstance.btnCaption = $localize`Proceed`

src-ui/src/app/components/manage/saved-views/saved-views.component.html

@@ -51,6 +51,7 @@
             @if (displayFields) {
               <pngx-input-drag-drop-select i18n-title title="Show" i18n-emptyText emptyText="Default" [items]="displayFields" formControlName="display_fields"></pngx-input-drag-drop-select>
             }
+            <span class="small text-muted fst-italic" i18n>Note: ordering is not preserved</span>
           </div>
       </div>
       </li>

src-ui/src/environments/environment.prod.ts

@@ -6,7 +6,7 @@ export const environment = {
   apiVersion: '9', // match src/paperless/settings.py
   appTitle: 'Paperless-ngx',
   tag: 'prod',
-  version: '2.20.4',
+  version: '2.20.6',
   webSocketHost: window.location.host,
   webSocketProtocol: window.location.protocol == 'https:' ? 'wss:' : 'ws:',
   webSocketBaseUrl: base_url.pathname + 'ws/',

src/documents/data_models.py

@@ -115,7 +115,7 @@ class DocumentMetadataOverrides:
             ).values_list("id", flat=True),
         )
         overrides.custom_fields = {
-            custom_field.id: custom_field.value
+            custom_field.field.id: custom_field.value
             for custom_field in doc.custom_fields.all()
         }
 

src/documents/index.py

@@ -602,7 +602,7 @@ def rewrite_natural_date_keywords(query_string: str) -> str:
 
             case "this year":
                 start = datetime(local_now.year, 1, 1, 0, 0, 0, tzinfo=tz)
-                end = datetime.combine(today, time.max, tzinfo=tz)
+                end = datetime(local_now.year, 12, 31, 23, 59, 59, tzinfo=tz)
 
             case "previous week":
                 days_since_monday = local_now.weekday()

src/documents/migrations/1075_workflowaction_order.py

@@ -12,7 +12,7 @@ def populate_action_order(apps, schema_editor):
 
 class Migration(migrations.Migration):
     dependencies = [
-        ("documents", "1075_alter_paperlesstask_task_name"),
+        ("documents", "1074_workflowrun_deleted_at_workflowrun_restored_at_and_more"),
     ]
 
     operations = [

src/documents/permissions.py

@@ -2,10 +2,17 @@ from django.contrib.auth.models import Group
 from django.contrib.auth.models import Permission
 from django.contrib.auth.models import User
 from django.contrib.contenttypes.models import ContentType
+from django.db.models import Count
+from django.db.models import IntegerField
+from django.db.models import OuterRef
 from django.db.models import Q
 from django.db.models import QuerySet
+from django.db.models import Subquery
+from django.db.models.functions import Cast
+from django.db.models.functions import Coalesce
 from guardian.core import ObjectPermissionChecker
 from guardian.models import GroupObjectPermission
+from guardian.models import UserObjectPermission
 from guardian.shortcuts import assign_perm
 from guardian.shortcuts import get_objects_for_user
 from guardian.shortcuts import get_users_with_perms
@@ -129,23 +136,96 @@ def set_permissions_for_object(permissions: dict, object, *, merge: bool = False
                         )
 
 
+def _permitted_document_ids(user):
+    """
+    Return a queryset of document IDs the user may view, limited to non-deleted
+    documents. This intentionally avoids ``get_objects_for_user`` to keep the
+    subquery small and index-friendly.
+    """
+
+    base_docs = Document.objects.filter(deleted_at__isnull=True).only("id", "owner")
+
+    if user is None or not getattr(user, "is_authenticated", False):
+        # Just Anonymous user e.g. for drf-spectacular
+        return base_docs.filter(owner__isnull=True).values_list("id", flat=True)
+
+    if getattr(user, "is_superuser", False):
+        return base_docs.values_list("id", flat=True)
+
+    document_ct = ContentType.objects.get_for_model(Document)
+    perm_filter = {
+        "permission__codename": "view_document",
+        "permission__content_type": document_ct,
+    }
+
+    user_perm_docs = (
+        UserObjectPermission.objects.filter(user=user, **perm_filter)
+        .annotate(object_pk_int=Cast("object_pk", IntegerField()))
+        .values_list("object_pk_int", flat=True)
+    )
+
+    group_perm_docs = (
+        GroupObjectPermission.objects.filter(group__user=user, **perm_filter)
+        .annotate(object_pk_int=Cast("object_pk", IntegerField()))
+        .values_list("object_pk_int", flat=True)
+    )
+
+    permitted_documents = user_perm_docs.union(group_perm_docs)
+
+    return base_docs.filter(
+        Q(owner=user) | Q(owner__isnull=True) | Q(id__in=permitted_documents),
+    ).values_list("id", flat=True)
+
+
 def get_document_count_filter_for_user(user):
     """
     Return the Q object used to filter document counts for the given user.
+
+    The filter is expressed as an ``id__in`` against a small subquery of permitted
+    document IDs to keep the generated SQL simple and avoid large OR clauses.
     """
 
-    if user is None or not getattr(user, "is_authenticated", False):
-        return Q(documents__deleted_at__isnull=True, documents__owner__isnull=True)
     if getattr(user, "is_superuser", False):
+        # Superuser: no permission filtering needed
         return Q(documents__deleted_at__isnull=True)
-    return Q(
-        documents__deleted_at__isnull=True,
-        documents__id__in=get_objects_for_user_owner_aware(
-            user,
-            "documents.view_document",
-            Document,
-        ).values_list("id", flat=True),
+
+    permitted_ids = _permitted_document_ids(user)
+    return Q(documents__id__in=permitted_ids)
+
+
+def annotate_document_count_for_related_queryset(
+    queryset,
+    through_model,
+    related_object_field: str,
+    target_field: str = "document_id",
+    user=None,
+):
+    """
+    Annotate a queryset with permissions-aware document counts using a subquery
+    against a relation table.
+
+    Args:
+        queryset: base queryset to annotate (must contain pk)
+        through_model: model representing the relation (e.g., Document.tags.through
+                       or CustomFieldInstance)
+        source_field: field on the relation pointing back to queryset pk
+        target_field: field on the relation pointing to Document id
+        user: the user for whom to filter permitted document ids
+    """
+
+    permitted_ids = _permitted_document_ids(user)
+    counts = (
+        through_model.objects.filter(
+            **{
+                related_object_field: OuterRef("pk"),
+                f"{target_field}__in": permitted_ids,
+            },
+        )
+        .values(related_object_field)
+        .annotate(c=Count(target_field))
+        .values("c")
     )
+    return queryset.annotate(document_count=Coalesce(Subquery(counts[:1]), 0))
 
 
 def get_objects_for_user_owner_aware(user, perms, Model) -> QuerySet:

src/documents/serialisers.py

@@ -40,6 +40,7 @@ from guardian.utils import get_group_obj_perms_model
 from guardian.utils import get_user_obj_perms_model
 from rest_framework import fields
 from rest_framework import serializers
+from rest_framework.exceptions import PermissionDenied
 from rest_framework.fields import SerializerMethodField
 from rest_framework.filters import OrderingFilter
 
@@ -436,6 +437,19 @@ class OwnedObjectSerializer(
         return instance
 
     def update(self, instance, validated_data):
+        user = getattr(self, "user", None)
+        is_superuser = user.is_superuser if user is not None else False
+        is_owner = instance.owner == user if user is not None else False
+        is_unowned = instance.owner is None
+
+        if (
+            ("owner" in validated_data and validated_data["owner"] != instance.owner)
+            or "set_permissions" in validated_data
+        ) and not (is_superuser or is_owner or is_unowned):
+            raise PermissionDenied(
+                _("Insufficient permissions."),
+            )
+
         if "set_permissions" in validated_data:
             self._set_permissions(validated_data["set_permissions"], instance)
         self.validate_unique_together(validated_data, instance)
@@ -580,30 +594,34 @@ class TagSerializer(MatchingModelSerializer, OwnedObjectSerializer):
         ),
     )
     def get_children(self, obj):
-        filter_q = self.context.get("document_count_filter")
-        request = self.context.get("request")
-        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_map = self.context.get("children_map")
+        if children_map is not None:
+            children = children_map.get(obj.pk, [])
+        else:
+            filter_q = self.context.get("document_count_filter")
+            request = self.context.get("request")
+            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_queryset = (
-            obj.get_children_queryset()
-            .select_related("owner")
-            .annotate(document_count=Count("documents", filter=filter_q))
-        )
+            children = (
+                obj.get_children_queryset()
+                .select_related("owner")
+                .annotate(document_count=Count("documents", filter=filter_q))
+            )
 
-        view = self.context.get("view")
-        ordering = (
-            OrderingFilter().get_ordering(request, children_queryset, view)
-            if request and view
-            else None
-        )
-        ordering = ordering or (Lower("name"),)
-        children_queryset = children_queryset.order_by(*ordering)
+            view = self.context.get("view")
+            ordering = (
+                OrderingFilter().get_ordering(request, children, view)
+                if request and view
+                else None
+            )
+            ordering = ordering or (Lower("name"),)
+            children = children.order_by(*ordering)
 
         serializer = TagSerializer(
-            children_queryset,
+            children,
             many=True,
             user=self.user,
             full_perms=self.full_perms,
@@ -695,6 +713,9 @@ class StoragePathField(serializers.PrimaryKeyRelatedField):
 
 class CustomFieldSerializer(serializers.ModelSerializer):
     def __init__(self, *args, **kwargs):
+        # Ignore args passed by permissions mixin
+        kwargs.pop("user", None)
+        kwargs.pop("full_perms", None)
         context = kwargs.get("context")
         self.api_version = int(
             context.get("request").version

src/documents/tests/test_api_documents.py

@@ -1216,6 +1216,17 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
 
         self.assertEqual(response.status_code, status.HTTP_405_METHOD_NOT_ALLOWED)
 
+    def test_upload_insufficient_permissions(self):
+        self.client.force_authenticate(user=User.objects.create_user("testuser2"))
+
+        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
+            response = self.client.post(
+                "/api/documents/post_document/",
+                {"document": f},
+            )
+
+        self.assertEqual(response.status_code, status.HTTP_403_FORBIDDEN)
+
     def test_upload_empty_metadata(self):
         self.consume_file_mock.return_value = celery.result.AsyncResult(
             id=str(uuid.uuid4()),

src/documents/tests/test_api_permissions.py

@@ -441,6 +441,59 @@ class TestApiAuth(DirectoriesMixin, APITestCase):
         self.assertTrue(checker.has_perm("change_document", doc))
         self.assertIn("change_document", get_perms(group1, doc))
 
+    def test_document_permissions_change_requires_owner(self):
+        owner = User.objects.create_user(username="owner")
+        editor = User.objects.create_user(username="editor")
+        editor.user_permissions.add(
+            *Permission.objects.all(),
+        )
+
+        doc = Document.objects.create(
+            title="Ownered doc",
+            content="sensitive",
+            checksum="abc123",
+            mime_type="application/pdf",
+            owner=owner,
+        )
+
+        assign_perm("view_document", editor, doc)
+        assign_perm("change_document", editor, doc)
+
+        self.client.force_authenticate(editor)
+        response = self.client.patch(
+            f"/api/documents/{doc.pk}/",
+            json.dumps(
+                {
+                    "set_permissions": {
+                        "view": {
+                            "users": [editor.id],
+                            "groups": [],
+                        },
+                        "change": {
+                            "users": None,
+                            "groups": None,
+                        },
+                    },
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_403_FORBIDDEN)
+
+        self.client.force_authenticate(editor)
+        response = self.client.patch(
+            f"/api/documents/{doc.pk}/",
+            json.dumps(
+                {
+                    "owner": editor.id,
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_403_FORBIDDEN)
+
     def test_dynamic_permissions_fields(self):
         user1 = User.objects.create_user(username="user1")
         user1.user_permissions.add(*Permission.objects.filter(codename="view_document"))

src/documents/tests/test_index.py

@@ -180,7 +180,7 @@ class TestRewriteNaturalDateKeywords(SimpleTestCase):
             (
                 "added:this year",
                 datetime(2025, 7, 15, 12, 0, 0, tzinfo=timezone.utc),
-                ("added:[20250101", "TO 20250715"),
+                ("added:[20250101", "TO 20251231"),
             ),
             (
                 "added:previous year",

src/documents/views.py

@@ -32,7 +32,6 @@ from django.db.models import Count
 from django.db.models import IntegerField
 from django.db.models import Max
 from django.db.models import Model
-from django.db.models import Q
 from django.db.models import Sum
 from django.db.models import When
 from django.db.models.functions import Length
@@ -128,6 +127,7 @@ from documents.matching import match_storage_paths
 from documents.matching import match_tags
 from documents.models import Correspondent
 from documents.models import CustomField
+from documents.models import CustomFieldInstance
 from documents.models import Document
 from documents.models import DocumentType
 from documents.models import Note
@@ -147,6 +147,7 @@ from documents.permissions import PaperlessAdminPermissions
 from documents.permissions import PaperlessNotePermissions
 from documents.permissions import PaperlessObjectPermissions
 from documents.permissions import ViewDocumentsPermissions
+from documents.permissions import annotate_document_count_for_related_queryset
 from documents.permissions import get_document_count_filter_for_user
 from documents.permissions import get_objects_for_user_owner_aware
 from documents.permissions import has_perms_owner_aware
@@ -370,22 +371,37 @@ class PermissionsAwareDocumentCountMixin(BulkPermissionMixin, PassUserMixin):
     Mixin to add document count to queryset, permissions-aware if needed
     """
 
+    # Default is simple relation path, override for through-table/count specialization.
+    document_count_through = None
+    document_count_source_field = None
+
     def get_document_count_filter(self):
         request = getattr(self, "request", None)
         user = getattr(request, "user", None) if request else None
         return get_document_count_filter_for_user(user)
 
     def get_queryset(self):
+        base_qs = super().get_queryset()
+
+        # Use optimized through-table counting when configured.
+        if self.document_count_through:
+            user = getattr(getattr(self, "request", None), "user", None)
+            return annotate_document_count_for_related_queryset(
+                base_qs,
+                through_model=self.document_count_through,
+                related_object_field=self.document_count_source_field,
+                user=user,
+            )
+
+        # Fallback: simple Count on relation with permission filter.
         filter = self.get_document_count_filter()
-        return (
-            super()
-            .get_queryset()
-            .annotate(document_count=Count("documents", filter=filter))
+        return base_qs.annotate(
+            document_count=Count("documents", filter=filter),
         )
 
 
 @extend_schema_view(**generate_object_with_permissions_schema(CorrespondentSerializer))
-class CorrespondentViewSet(ModelViewSet, PermissionsAwareDocumentCountMixin):
+class CorrespondentViewSet(PermissionsAwareDocumentCountMixin, ModelViewSet):
     model = Correspondent
 
     queryset = Correspondent.objects.select_related("owner").order_by(Lower("name"))
@@ -422,8 +438,10 @@ class CorrespondentViewSet(ModelViewSet, PermissionsAwareDocumentCountMixin):
 
 
 @extend_schema_view(**generate_object_with_permissions_schema(TagSerializer))
-class TagViewSet(ModelViewSet, PermissionsAwareDocumentCountMixin):
+class TagViewSet(PermissionsAwareDocumentCountMixin, ModelViewSet):
     model = Tag
+    document_count_through = Document.tags.through
+    document_count_source_field = "tag_id"
 
     queryset = Tag.objects.select_related("owner").order_by(
         Lower("name"),
@@ -448,8 +466,51 @@ 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:
+            user = getattr(getattr(self, "request", None), "user", None)
+            children_source = list(
+                annotate_document_count_for_related_queryset(
+                    Tag.objects.filter(pk__in=descendant_pks | {t.pk for t in all_tags})
+                    .select_related("owner")
+                    .order_by(*ordering),
+                    through_model=self.document_count_through,
+                    related_object_field=self.document_count_source_field,
+                    user=user,
+                ),
+            )
+        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)
+        response = self.get_paginated_response(serializer.data)
+        if descendant_pks:
+            # Include children in the "all" field, if needed
+            response.data["all"] = [tag.pk for tag in children_source]
+        return response
+
     def perform_update(self, serializer):
         old_parent = self.get_object().get_parent()
         tag = serializer.save()
@@ -459,7 +520,7 @@ class TagViewSet(ModelViewSet, PermissionsAwareDocumentCountMixin):
 
 
 @extend_schema_view(**generate_object_with_permissions_schema(DocumentTypeSerializer))
-class DocumentTypeViewSet(ModelViewSet, PermissionsAwareDocumentCountMixin):
+class DocumentTypeViewSet(PermissionsAwareDocumentCountMixin, ModelViewSet):
     model = DocumentType
 
     queryset = DocumentType.objects.select_related("owner").order_by(Lower("name"))
@@ -1060,7 +1121,7 @@ class DocumentViewSet(
             ):
                 return HttpResponseForbidden("Insufficient permissions to delete notes")
 
-            note = Note.objects.get(id=int(request.GET.get("id")))
+            note = Note.objects.get(id=int(request.GET.get("id")), document=doc)
             if settings.AUDIT_LOG_ENABLED:
                 LogEntry.objects.log_create(
                     instance=doc,
@@ -1664,6 +1725,8 @@ class PostDocumentView(GenericAPIView):
     parser_classes = (parsers.MultiPartParser,)
 
     def post(self, request, *args, **kwargs):
+        if not request.user.has_perm("documents.add_document"):
+            return HttpResponseForbidden("Insufficient permissions")
         serializer = self.get_serializer(data=request.data)
         serializer.is_valid(raise_exception=True)
 
@@ -2303,7 +2366,7 @@ class BulkDownloadView(GenericAPIView):
 
 
 @extend_schema_view(**generate_object_with_permissions_schema(StoragePathSerializer))
-class StoragePathViewSet(ModelViewSet, PermissionsAwareDocumentCountMixin):
+class StoragePathViewSet(PermissionsAwareDocumentCountMixin, ModelViewSet):
     model = StoragePath
 
     queryset = StoragePath.objects.select_related("owner").order_by(
@@ -2820,7 +2883,7 @@ class WorkflowViewSet(ModelViewSet):
     )
 
 
-class CustomFieldViewSet(ModelViewSet):
+class CustomFieldViewSet(PermissionsAwareDocumentCountMixin, ModelViewSet):
     permission_classes = (IsAuthenticated, PaperlessObjectPermissions)
 
     serializer_class = CustomFieldSerializer
@@ -2832,35 +2895,11 @@ class CustomFieldViewSet(ModelViewSet):
     filterset_class = CustomFieldFilterSet
 
     model = CustomField
+    document_count_through = CustomFieldInstance
+    document_count_source_field = "field_id"
 
     queryset = CustomField.objects.all().order_by("-created")
 
-    def get_queryset(self):
-        filter = (
-            Q(fields__document__deleted_at__isnull=True)
-            if self.request.user is None or self.request.user.is_superuser
-            else (
-                Q(
-                    fields__document__deleted_at__isnull=True,
-                    fields__document__id__in=get_objects_for_user_owner_aware(
-                        self.request.user,
-                        "documents.view_document",
-                        Document,
-                    ).values_list("id", flat=True),
-                )
-            )
-        )
-        return (
-            super()
-            .get_queryset()
-            .annotate(
-                document_count=Count(
-                    "fields",
-                    filter=filter,
-                ),
-            )
-        )
-
 
 @extend_schema_view(
     get=extend_schema(

src/paperless/version.py

@@ -1,6 +1,6 @@
 from typing import Final
 
-__version__: Final[tuple[int, int, int]] = (2, 20, 4)
+__version__: Final[tuple[int, int, int]] = (2, 20, 6)
 # Version string like X.Y.Z
 __full_version_str__: Final[str] = ".".join(map(str, __version__))
 # Version string like X.Y

uv.lock

@@ -2115,7 +2115,7 @@ wheels = [
 
 [[package]]
 name = "paperless-ngx"
-version = "2.20.4"
+version = "2.20.6"
 source = { virtual = "." }
 dependencies = [
     { name = "babel", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },