Chore(deps): Bump the document-processing group with 3 updates

Bumps the document-processing group with 3 updates: [gotenberg-client](https://github.com/stumpylog/gotenberg-client), [ocrmypdf](https://github.com/ocrmypdf/OCRmyPDF) and [tika-client](https://github.com/stumpylog/tika-client).


Updates `gotenberg-client` from 0.13.1 to 0.14.0
- [Release notes](https://github.com/stumpylog/gotenberg-client/releases)
- [Changelog](https://github.com/stumpylog/gotenberg-client/blob/main/CHANGELOG.md)
- [Commits](https://github.com/stumpylog/gotenberg-client/compare/0.13.1...0.14.0)

Updates `ocrmypdf` from 17.3.0 to 17.4.0
- [Release notes](https://github.com/ocrmypdf/OCRmyPDF/releases)
- [Commits](https://github.com/ocrmypdf/OCRmyPDF/compare/v17.3.0...v17.4.0)

Updates `tika-client` from 0.10.0 to 0.11.0
- [Release notes](https://github.com/stumpylog/tika-client/releases)
- [Changelog](https://github.com/stumpylog/tika-client/blob/main/CHANGELOG.md)
- [Commits](https://github.com/stumpylog/tika-client/compare/0.10.0...0.11.0)

---
updated-dependencies:
- dependency-name: gotenberg-client
  dependency-version: 0.14.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: document-processing
- dependency-name: ocrmypdf
  dependency-version: 17.4.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: document-processing
- dependency-name: tika-client
  dependency-version: 0.11.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: document-processing
...

Signed-off-by: dependabot[bot] <support@github.com>

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -21,6 +21,7 @@ body:
         - [The installation instructions](https://docs.paperless-ngx.com/setup/#installation).
         - [Existing issues and discussions](https://github.com/paperless-ngx/paperless-ngx/search?q=&type=issues).
         - Disable any custom container initialization scripts, if using
+        - Remove any third-party parser plugins — issues caused by or requiring changes to a third-party plugin will be closed without investigation.
 
         If you encounter issues while installing or configuring Paperless-ngx, please post in the ["Support" section of the discussions](https://github.com/paperless-ngx/paperless-ngx/discussions/new?category=support).
   - type: textarea

.github/workflows/ci-backend.yml

@@ -24,7 +24,6 @@ jobs:
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           fetch-depth: 0
-          persist-credentials: false
       - name: Decide run mode
         id: force
         run: |
@@ -50,7 +49,7 @@ jobs:
       - name: Detect changes
         id: filter
         if: steps.force.outputs.run_all != 'true'
-        uses: dorny/paths-filter@de90cc6fb38fc0963ad72b210f1f284cd68cea36 # v3.0.2
+        uses: dorny/paths-filter@fbd0ab8f3e69293af611ebaee6363fc25e6d187d # v4.0.1
         with:
           base: ${{ steps.range.outputs.base }}
           ref: ${{ steps.range.outputs.ref }}
@@ -73,8 +72,6 @@ jobs:
     steps:
       - name: Checkout
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-        with:
-          persist-credentials: false
       - name: Start containers
         run: |
           docker compose --file docker/compose/docker-compose.ci-test.yml pull --quiet
@@ -148,8 +145,6 @@ jobs:
     steps:
       - name: Checkout
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-        with:
-          persist-credentials: false
       - name: Set up Python
         id: setup-python
         uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
@@ -178,7 +173,7 @@ jobs:
             check \
             src/
       - name: Cache Mypy
-        uses: actions/cache@cdf6c1fa76f9f475f3d7449005a359c84ca0f306 # v5.0.3
+        uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
         with:
           path: .mypy_cache
           # Keyed by OS, Python version, and dependency hashes

.github/workflows/ci-docker.yml

@@ -42,8 +42,6 @@ jobs:
     steps:
       - name: Checkout
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-        with:
-          persist-credentials: false
       - name: Determine ref name
         id: ref
         run: |
@@ -171,7 +169,7 @@ jobs:
       packages: write
     steps:
       - name: Download digests
-        uses: actions/download-artifact@70fc10c6e5e1ce46ad2ea6f2b72d43f7d47b13c3 # v8.0.0
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
         with:
           path: /tmp/digests
           pattern: digest-*.txt

.github/workflows/ci-docs.yml

@@ -26,7 +26,6 @@ jobs:
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           fetch-depth: 0
-          persist-credentials: false
       - name: Decide run mode
         id: force
         run: |
@@ -52,7 +51,7 @@ jobs:
       - name: Detect changes
         id: filter
         if: steps.force.outputs.run_all != 'true'
-        uses: dorny/paths-filter@de90cc6fb38fc0963ad72b210f1f284cd68cea36 # v3.0.2
+        uses: dorny/paths-filter@fbd0ab8f3e69293af611ebaee6363fc25e6d187d # v4.0.1
         with:
           base: ${{ steps.range.outputs.base }}
           ref: ${{ steps.range.outputs.ref }}
@@ -69,11 +68,9 @@ jobs:
     name: Build Documentation
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/configure-pages@983d7736d9b0ae728b81ab479565c72886d7745b # v5.0.0
+      - uses: actions/configure-pages@45bfe0192ca1faeb007ade9deae92b16b8254a0d # v6.0.0
       - name: Checkout
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-        with:
-          persist-credentials: false
       - name: Set up Python
         id: setup-python
         uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
@@ -110,7 +107,7 @@ jobs:
       url: ${{ steps.deployment.outputs.page_url }}
     steps:
       - name: Deploy GitHub Pages
-        uses: actions/deploy-pages@d6db90164ac5ed86f2b6aed7e0febac5b3c0c03e # v4.0.5
+        uses: actions/deploy-pages@cd2ce8fcbc39b97be8ca5fce6e763baed58fa128 # v5.0.0
         id: deployment
         with:
           artifact_name: github-pages-${{ github.run_id }}-${{ github.run_attempt }}

.github/workflows/ci-frontend.yml

@@ -46,7 +46,7 @@ jobs:
       - name: Detect changes
         id: filter
         if: steps.force.outputs.run_all != 'true'
-        uses: dorny/paths-filter@de90cc6fb38fc0963ad72b210f1f284cd68cea36 # v3.0.2
+        uses: dorny/paths-filter@fbd0ab8f3e69293af611ebaee6363fc25e6d187d # v4.0.1
         with:
           base: ${{ steps.range.outputs.base }}
           ref: ${{ steps.range.outputs.ref }}
@@ -62,10 +62,8 @@ jobs:
     steps:
       - name: Checkout
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-        with:
-          persist-credentials: false
       - name: Install pnpm
-        uses: pnpm/action-setup@41ff72655975bd51cab0327fa583b6e92b6d3061 # v4.2.0
+        uses: pnpm/action-setup@fc06bc1257f339d1d5d8b3a19a8cae5388b55320 # v5.0.0
         with:
           version: 10
       - name: Use Node.js 24
@@ -76,7 +74,7 @@ jobs:
           cache-dependency-path: 'src-ui/pnpm-lock.yaml'
       - name: Cache frontend dependencies
         id: cache-frontend-deps
-        uses: actions/cache@cdf6c1fa76f9f475f3d7449005a359c84ca0f306 # v5.0.3
+        uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
         with:
           path: |
             ~/.pnpm-store
@@ -92,10 +90,8 @@ jobs:
     steps:
       - name: Checkout
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-        with:
-          persist-credentials: false
       - name: Install pnpm
-        uses: pnpm/action-setup@41ff72655975bd51cab0327fa583b6e92b6d3061 # v4.2.0
+        uses: pnpm/action-setup@fc06bc1257f339d1d5d8b3a19a8cae5388b55320 # v5.0.0
         with:
           version: 10
       - name: Use Node.js 24
@@ -105,7 +101,7 @@ jobs:
           cache: 'pnpm'
           cache-dependency-path: 'src-ui/pnpm-lock.yaml'
       - name: Cache frontend dependencies
-        uses: actions/cache@cdf6c1fa76f9f475f3d7449005a359c84ca0f306 # v5.0.3
+        uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
         with:
           path: |
             ~/.pnpm-store
@@ -129,10 +125,8 @@ jobs:
     steps:
       - name: Checkout
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-        with:
-          persist-credentials: false
       - name: Install pnpm
-        uses: pnpm/action-setup@41ff72655975bd51cab0327fa583b6e92b6d3061 # v4.2.0
+        uses: pnpm/action-setup@fc06bc1257f339d1d5d8b3a19a8cae5388b55320 # v5.0.0
         with:
           version: 10
       - name: Use Node.js 24
@@ -142,7 +136,7 @@ jobs:
           cache: 'pnpm'
           cache-dependency-path: 'src-ui/pnpm-lock.yaml'
       - name: Cache frontend dependencies
-        uses: actions/cache@cdf6c1fa76f9f475f3d7449005a359c84ca0f306 # v5.0.3
+        uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
         with:
           path: |
             ~/.pnpm-store
@@ -182,10 +176,8 @@ jobs:
     steps:
       - name: Checkout
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-        with:
-          persist-credentials: false
       - name: Install pnpm
-        uses: pnpm/action-setup@41ff72655975bd51cab0327fa583b6e92b6d3061 # v4.2.0
+        uses: pnpm/action-setup@fc06bc1257f339d1d5d8b3a19a8cae5388b55320 # v5.0.0
         with:
           version: 10
       - name: Use Node.js 24
@@ -195,7 +187,7 @@ jobs:
           cache: 'pnpm'
           cache-dependency-path: 'src-ui/pnpm-lock.yaml'
       - name: Cache frontend dependencies
-        uses: actions/cache@cdf6c1fa76f9f475f3d7449005a359c84ca0f306 # v5.0.3
+        uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
         with:
           path: |
             ~/.pnpm-store
@@ -217,9 +209,8 @@ jobs:
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           fetch-depth: 2
-          persist-credentials: false
       - name: Install pnpm
-        uses: pnpm/action-setup@41ff72655975bd51cab0327fa583b6e92b6d3061 # v4.2.0
+        uses: pnpm/action-setup@fc06bc1257f339d1d5d8b3a19a8cae5388b55320 # v5.0.0
         with:
           version: 10
       - name: Use Node.js 24
@@ -229,7 +220,7 @@ jobs:
           cache: 'pnpm'
           cache-dependency-path: 'src-ui/pnpm-lock.yaml'
       - name: Cache frontend dependencies
-        uses: actions/cache@cdf6c1fa76f9f475f3d7449005a359c84ca0f306 # v5.0.3
+        uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
         with:
           path: |
             ~/.pnpm-store

.github/workflows/ci-lint.yml

@@ -16,11 +16,9 @@ jobs:
     steps:
       - name: Checkout
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-        with:
-          persist-credentials: false
       - name: Install Python
         uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
         with:
           python-version: "3.14"
       - name: Run prek
-        uses: j178/prek-action@0bb87d7f00b0c99306c8bcb8b8beba1eb581c037 # v1.1.1
+        uses: j178/prek-action@53276d8b0d10f8b6672aa85b4588c6921d0370cc # v2.0.1

.github/workflows/ci-release.yml

@@ -29,11 +29,9 @@ jobs:
     steps:
       - name: Checkout
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-        with:
-          persist-credentials: false
       # ---- Frontend Build ----
       - name: Install pnpm
-        uses: pnpm/action-setup@41ff72655975bd51cab0327fa583b6e92b6d3061 # v4.2.0
+        uses: pnpm/action-setup@fc06bc1257f339d1d5d8b3a19a8cae5388b55320 # v5.0.0
         with:
           version: 10
       - name: Use Node.js 24
@@ -135,7 +133,7 @@ jobs:
       version: ${{ steps.get-version.outputs.version }}
     steps:
       - name: Download release artifact
-        uses: actions/download-artifact@70fc10c6e5e1ce46ad2ea6f2b72d43f7d47b13c3 # v8.0.0
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
         with:
           name: release
           path: ./
@@ -150,7 +148,7 @@ jobs:
           fi
       - name: Create release and changelog
         id: create-release
-        uses: release-drafter/release-drafter@6db134d15f3909ccc9eefd369f02bd1e9cffdf97 # v6.2.0
+        uses: release-drafter/release-drafter@139054aeaa9adc52ab36ddf67437541f039b88e2 # v7.1.1
         with:
           name: Paperless-ngx ${{ steps.get-version.outputs.version }}
           tag: ${{ steps.get-version.outputs.version }}
@@ -161,7 +159,7 @@ jobs:
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       - name: Upload release archive
-        uses: shogo82148/actions-upload-release-asset@8f6863c6c894ba46f9e676ef5cccec4752723c1e # v1.9.2
+        uses: shogo82148/actions-upload-release-asset@96bc1f0cb850b65efd58a6b5eaa0a69f88d38077 # v1.10.0
         with:
           github_token: ${{ secrets.GITHUB_TOKEN }}
           upload_url: ${{ steps.create-release.outputs.upload_url }}
@@ -181,7 +179,6 @@ jobs:
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           ref: main
-          persist-credentials: true # for pushing changelog branch
       - name: Set up Python
         id: setup-python
         uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0

.github/workflows/ci-static-analysis.yml

@@ -1,42 +0,0 @@
-name: Static Analysis
-on:
-  push:
-    branches-ignore:
-      - 'translations**'
-  pull_request:
-    branches-ignore:
-      - 'translations**'
-  workflow_dispatch:
-concurrency:
-  group: static-analysis-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-permissions:
-  contents: read
-jobs:
-  zizmor:
-    name: Run zizmor
-    runs-on: ubuntu-24.04
-    permissions:
-      contents: read
-      actions: read
-      security-events: write
-    steps:
-      - name: Checkout
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-        with:
-          persist-credentials: false
-      - name: Run zizmor
-        uses: zizmorcore/zizmor-action@71321a20a9ded102f6e9ce5718a2fcec2c4f70d8 # v0.5.2
-  semgrep:
-    name: Semgrep CE
-    runs-on: ubuntu-24.04
-    container:
-      image: semgrep/semgrep:1.155.0@sha256:cc869c685dcc0fe497c86258da9f205397d8108e56d21a86082ea4886e52784d
-    if: github.actor != 'dependabot[bot]'
-    steps:
-      - name: Checkout
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-        with:
-          persist-credentials: false
-      - name: Run Semgrep
-        run: semgrep scan --config auto

.github/workflows/codeql-analysis.yml

@@ -35,8 +35,6 @@ jobs:
     steps:
       - name: Checkout repository
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-        with:
-          persist-credentials: false
       # Initializes the CodeQL tools for scanning.
       - name: Initialize CodeQL
         uses: github/codeql-action/init@c793b717bc78562f491db7b0e93a3a178b099162 # v4.32.5

.github/workflows/crowdin.yml

@@ -16,7 +16,6 @@ jobs:
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           token: ${{ secrets.PNGX_BOT_PAT }}
-          persist-credentials: false
       - name: crowdin action
         uses: crowdin/github-action@8818ff65bfc4322384f983ea37e3926948c11745 # v2.15.0
         with:

.github/workflows/project-actions.yml

@@ -19,6 +19,6 @@ jobs:
     if: github.event_name == 'pull_request_target' && (github.event.action == 'opened' || github.event.action == 'reopened') && github.event.pull_request.user.login != 'dependabot'
     steps:
       - name: Label PR with release-drafter
-        uses: release-drafter/release-drafter@6db134d15f3909ccc9eefd369f02bd1e9cffdf97 # v6.2.0
+        uses: release-drafter/release-drafter@139054aeaa9adc52ab36ddf67437541f039b88e2 # v7.1.1
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/translate-strings.yml

@@ -17,7 +17,6 @@ jobs:
         with:
           token: ${{ secrets.PNGX_BOT_PAT }}
           ref: ${{ env.GH_REF }}
-          persist-credentials: true # for pushing translation branch
       - name: Set up Python
         id: setup-python
         uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
@@ -37,7 +36,7 @@ jobs:
       - name: Generate backend translation strings
         run: cd src/ && uv run manage.py makemessages -l en_US -i "samples*"
       - name: Install pnpm
-        uses: pnpm/action-setup@41ff72655975bd51cab0327fa583b6e92b6d3061 # v4.2.0
+        uses: pnpm/action-setup@fc06bc1257f339d1d5d8b3a19a8cae5388b55320 # v5.0.0
         with:
           version: 10
       - name: Use Node.js 24
@@ -48,7 +47,7 @@ jobs:
           cache-dependency-path: 'src-ui/pnpm-lock.yaml'
       - name: Cache frontend dependencies
         id: cache-frontend-deps
-        uses: actions/cache@cdf6c1fa76f9f475f3d7449005a359c84ca0f306 # v5.0.3
+        uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
         with:
           path: |
             ~/.pnpm-store

.pre-commit-config.yaml

@@ -50,12 +50,12 @@ repos:
           - 'prettier-plugin-organize-imports@4.3.0'
   # Python hooks
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.15.6
+    rev: v0.15.8
     hooks:
       - id: ruff-check
       - id: ruff-format
   - repo: https://github.com/tox-dev/pyproject-fmt
-    rev: "v2.12.1"
+    rev: "v2.21.0"
     hooks:
       - id: pyproject-fmt
   # Dockerfile hooks

docker/rootfs/etc/s6-overlay/s6-rc.d/init-search-index/run

@@ -3,26 +3,10 @@
 
 declare -r log_prefix="[init-index]"
 
-declare -r index_version=9
+echo "${log_prefix} Checking search index..."
-declare -r data_dir="${PAPERLESS_DATA_DIR:-/usr/src/paperless/data}"
+cd "${PAPERLESS_SRC_DIR}"
-declare -r index_version_file="${data_dir}/.index_version"
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
-
+	python3 manage.py document_index reindex --if-needed --no-progress-bar
-update_index () {
+else
-	echo "${log_prefix} Search index out of date. Updating..."
+	s6-setuidgid paperless python3 manage.py document_index reindex --if-needed --no-progress-bar
-	cd "${PAPERLESS_SRC_DIR}"
-	if [[ -n "${USER_IS_NON_ROOT}" ]]; then
-		python3 manage.py document_index reindex --no-progress-bar
-		echo ${index_version} | tee "${index_version_file}" > /dev/null
-	else
-		s6-setuidgid paperless python3 manage.py document_index reindex --no-progress-bar
-		echo ${index_version} | s6-setuidgid paperless tee "${index_version_file}" > /dev/null
-	fi
-}
-
-if [[ (! -f "${index_version_file}") ]]; then
-	echo "${log_prefix} No index version file found"
-	update_index
-elif [[ $(<"${index_version_file}") != "$index_version" ]]; then
-	echo "${log_prefix} index version updated"
-	update_index
 fi

docs/administration.md

@@ -180,6 +180,16 @@ following:
     This might not actually do anything. Not every new paperless version
     comes with new database migrations.
 
+4.  Rebuild the search index if needed.
+
+    ```shell-session
+    cd src
+    python3 manage.py document_index reindex --if-needed
+    ```
+
+    This is a no-op if the index is already up to date, so it is safe to
+    run on every upgrade.
+
 ### Database Upgrades
 
 Paperless-ngx is compatible with Django-supported versions of PostgreSQL and MariaDB and it is generally
@@ -453,17 +463,42 @@ the search yields non-existing documents or won't find anything, you
 may need to recreate the index manually.
 
 ```
-document_index {reindex,optimize}
+document_index {reindex,optimize} [--recreate] [--if-needed]
 ```
 
-Specify `reindex` to have the index created from scratch. This may take
+Specify `reindex` to rebuild the index from all documents in the database. This
-some time.
+may take some time.
 
-Specify `optimize` to optimize the index. This updates certain aspects
+Pass `--recreate` to wipe the existing index before rebuilding. Use this when the
-of the index and usually makes queries faster and also ensures that the
+index is corrupted or you want a fully clean rebuild.
-autocompletion works properly. This command is regularly invoked by the
+
+Pass `--if-needed` to skip the rebuild if the index is already up to date (schema
+version and search language match). Safe to run on every startup or upgrade.
+
+Specify `optimize` to optimize the index. This command is regularly invoked by the
 task scheduler.
 
+!!! note
+
+    The `optimize` subcommand is deprecated and is now a no-op. Tantivy manages
+    segment merging automatically; no manual optimization step is needed.
+
+!!! note
+
+    **Docker users:** On every startup, the container runs
+    `document_index reindex --if-needed` automatically. Schema changes, language
+    changes, and missing indexes are all detected and rebuilt before the webserver
+    starts. No manual step is required.
+
+    **Bare metal users:** Run the following command after each upgrade (and after
+    changing `PAPERLESS_SEARCH_LANGUAGE`). It is a no-op if the index is already
+    up to date:
+
+    ```shell-session
+    cd src
+    python3 manage.py document_index reindex --if-needed
+    ```
+
 ### Clearing the database read cache
 
 If the database read cache is enabled, **you must run this command** after making any changes to the database outside the application context.

docs/advanced_usage.md

@@ -723,6 +723,81 @@ services:
 
 1. Note the `:ro` tag means the folder will be mounted as read only. This is for extra security against changes
 
+## Installing third-party parser plugins {#parser-plugins}
+
+Third-party parser plugins extend Paperless-ngx to support additional file
+formats. A plugin is a Python package that advertises itself under the
+`paperless_ngx.parsers` entry point group. Refer to the
+[developer documentation](development.md#making-custom-parsers) for how to
+create one.
+
+!!! warning "Third-party plugins are not officially supported"
+
+    The Paperless-ngx maintainers do not provide support for third-party
+    plugins. Issues caused by or requiring changes to a third-party plugin
+    will be closed without further investigation. Always reproduce problems
+    with all plugins removed before filing a bug report.
+
+### Docker
+
+Use a [custom container initialization script](#custom-container-initialization)
+to install the package before the webserver starts. Create a shell script and
+mount it into `/custom-cont-init.d`:
+
+```bash
+#!/bin/bash
+# /path/to/my/scripts/install-parsers.sh
+
+pip install my-paperless-parser-package
+```
+
+Mount it in your `docker-compose.yml`:
+
+```yaml
+services:
+  webserver:
+    # ...
+    volumes:
+      - /path/to/my/scripts:/custom-cont-init.d:ro
+```
+
+The script runs as `root` before the webserver starts, so the package will be
+available when Paperless-ngx discovers plugins at startup.
+
+### Bare metal
+
+Install the package into the same Python environment that runs Paperless-ngx.
+If you followed the standard bare-metal install guide, that is the `paperless`
+user's environment:
+
+```bash
+sudo -Hu paperless pip3 install my-paperless-parser-package
+```
+
+If you are using `uv` or a virtual environment, activate it first and then run:
+
+```bash
+uv pip install my-paperless-parser-package
+# or
+pip install my-paperless-parser-package
+```
+
+Restart all Paperless-ngx services after installation so the new plugin is
+discovered.
+
+### Verifying installation
+
+On the next startup, check the application logs for a line confirming
+discovery:
+
+```
+Loaded third-party parser 'My Parser' v1.0.0 by Acme Corp (entrypoint: 'my_parser').
+```
+
+If this line does not appear, verify that the package is installed in the
+correct environment and that its `pyproject.toml` declares the
+`paperless_ngx.parsers` entry point.
+
 ## MySQL Caveats {#mysql-caveats}
 
 ### Case Sensitivity

docs/api.md

@@ -167,9 +167,8 @@ Query parameters:
 - `term`: The incomplete term.
 - `limit`: Amount of results. Defaults to 10.
 
-Results returned by the endpoint are ordered by importance of the term
+Results are ordered by how many of the user's visible documents contain
-in the document index. The first result is the term that has the highest
+each matching word. The first result is the word that appears in the most documents.
-[Tf/Idf](https://en.wikipedia.org/wiki/Tf%E2%80%93idf) score in the index.
 
 ```json
 ["term1", "term3", "term6", "term4"]
@@ -437,3 +436,6 @@ Initial API version.
   moved from the bulk edit endpoint to their own individual endpoints. Using these methods via
   the bulk edit endpoint is still supported for compatibility with versions < 10 until support
   for API v9 is dropped.
+- The `all` parameter of list endpoints is now deprecated and will be removed in a future version.
+- The bulk edit objects endpoint now supports `all` and `filters` parameters to avoid having to send
+  large lists of object IDs for operations affecting many objects.

docs/configuration.md

@@ -1103,6 +1103,32 @@ should be a valid crontab(5) expression describing when to run.
 
     Defaults to `0 0 * * *` or daily at midnight.
 
+#### [`PAPERLESS_SEARCH_LANGUAGE=<language>`](#PAPERLESS_SEARCH_LANGUAGE) {#PAPERLESS_SEARCH_LANGUAGE}
+
+: Sets the stemmer language for the full-text search index.
+Stemming improves recall by matching word variants (e.g. "running" matches "run").
+Changing this setting causes the index to be rebuilt automatically on next startup.
+An invalid value raises an error at startup.
+
+: Use the ISO 639-1 two-letter code (e.g. `en`, `de`, `fr`). Lowercase full names
+(e.g. `english`, `german`, `french`) are also accepted. The capitalized names shown
+in the [Tantivy Language enum](https://docs.rs/tantivy/latest/tantivy/tokenizer/enum.Language.html)
+documentation are **not** valid — use the lowercase equivalent.
+
+: If not set, paperless infers the language from
+[`PAPERLESS_OCR_LANGUAGE`](#PAPERLESS_OCR_LANGUAGE). If the OCR language has no
+Tantivy stemmer equivalent, stemming is disabled.
+
+    Defaults to unset (inferred from `PAPERLESS_OCR_LANGUAGE`).
+
+#### [`PAPERLESS_ADVANCED_FUZZY_SEARCH_THRESHOLD=<float>`](#PAPERLESS_ADVANCED_FUZZY_SEARCH_THRESHOLD) {#PAPERLESS_ADVANCED_FUZZY_SEARCH_THRESHOLD}
+
+: When set to a float value, approximate/fuzzy matching is applied alongside exact
+matching. Fuzzy results rank below exact matches. A value of `0.5` is a reasonable
+starting point. Leave unset to disable fuzzy matching entirely.
+
+    Defaults to unset (disabled).
+
 #### [`PAPERLESS_SANITY_TASK_CRON=<cron expression>`](#PAPERLESS_SANITY_TASK_CRON) {#PAPERLESS_SANITY_TASK_CRON}
 
 : Configures the scheduled sanity checker frequency. The value should be a

docs/development.md

@@ -370,121 +370,367 @@ docker build --file Dockerfile --tag paperless:local .
 
 ## Extending Paperless-ngx
 
-Paperless-ngx does not have any fancy plugin systems and will probably never
+Paperless-ngx supports third-party document parsers via a Python entry point
-have. However, some parts of the application have been designed to allow
+plugin system. Plugins are distributed as ordinary Python packages and
-easy integration of additional features without any modification to the
+discovered automatically at startup — no changes to the Paperless-ngx source
-base code.
+are required.
+
+!!! warning "Third-party plugins are not officially supported"
+
+    The Paperless-ngx maintainers do not provide support for third-party
+    plugins. Issues that are caused by or require changes to a third-party
+    plugin will be closed without further investigation. If you believe you
+    have found a bug in Paperless-ngx itself (not in a plugin), please
+    reproduce it with all third-party plugins removed before filing an issue.
 
 ### Making custom parsers
 
-Paperless-ngx uses parsers to add documents. A parser is
+Paperless-ngx uses parsers to add documents. A parser is responsible for:
-responsible for:
 
-- Retrieving the content from the original
+- Extracting plain-text content from the document
-- Creating a thumbnail
+- Generating a thumbnail image
-- _optional:_ Retrieving a created date from the original
+- _optional:_ Detecting the document's creation date
-- _optional:_ Creating an archived document from the original
+- _optional:_ Producing a searchable PDF archive copy
 
-Custom parsers can be added to Paperless-ngx to support more file types. In
+Custom parsers are distributed as ordinary Python packages and registered
-order to do that, you need to write the parser itself and announce its
+via a [setuptools entry point](https://setuptools.pypa.io/en/latest/userguide/entry_point.html).
-existence to Paperless-ngx.
+No changes to the Paperless-ngx source are required.
 
-The parser itself must extend `documents.parsers.DocumentParser` and
+#### 1. Implementing the parser class
-must implement the methods `parse` and `get_thumbnail`. You can provide
+
-your own implementation to `get_date` if you don't want to rely on
+Your parser must satisfy the `ParserProtocol` structural interface defined in
-Paperless-ngx' default date guessing mechanisms.
+`paperless.parsers`. The simplest approach is to write a plain class — no base
+class is required, only the right attributes and methods.
+
+**Class-level identity attributes**
+
+The registry reads these before instantiating the parser, so they must be
+plain class attributes (not instance attributes or properties):
 
 ```python
-class MyCustomParser(DocumentParser):
+class MyCustomParser:
-
+    name    = "My Format Parser"   # human-readable name shown in logs
-    def parse(self, document_path, mime_type):
+    version = "1.0.0"              # semantic version string
-        # This method does not return anything. Rather, you should assign
+    author  = "Acme Corp"          # author / organisation
-        # whatever you got from the document to the following fields:
+    url     = "https://example.com/my-parser"  # docs or issue tracker
-
-        # The content of the document.
-        self.text = "content"
-
-        # Optional: path to a PDF document that you created from the original.
-        self.archive_path = os.path.join(self.tempdir, "archived.pdf")
-
-        # Optional: "created" date of the document.
-        self.date = get_created_from_metadata(document_path)
-
-    def get_thumbnail(self, document_path, mime_type):
-        # This should return the path to a thumbnail you created for this
-        # document.
-        return os.path.join(self.tempdir, "thumb.webp")
 ```
 
-If you encounter any issues during parsing, raise a
+**Declaring supported MIME types**
-`documents.parsers.ParseError`.
 
-The `self.tempdir` directory is a temporary directory that is guaranteed
+Return a `dict` mapping MIME type strings to preferred file extensions
-to be empty and removed after consumption finished. You can use that
+(including the leading dot). Paperless-ngx uses the extension when storing
-directory to store any intermediate files and also use it to store the
+archive copies and serving files for download.
-thumbnail / archived document.
-
-After that, you need to announce your parser to Paperless-ngx. You need to
-connect a handler to the `document_consumer_declaration` signal. Have a
-look in the file `src/paperless_tesseract/apps.py` on how that's done.
-The handler is a method that returns information about your parser:
 
 ```python
-def myparser_consumer_declaration(sender, **kwargs):
+@classmethod
+def supported_mime_types(cls) -> dict[str, str]:
     return {
-        "parser": MyCustomParser,
+        "application/x-my-format": ".myf",
-        "weight": 0,
+        "application/x-my-format-alt": ".myf",
-        "mime_types": {
-            "application/pdf": ".pdf",
-            "image/jpeg": ".jpg",
-        }
     }
 ```
 
-- `parser` is a reference to a class that extends `DocumentParser`.
+**Scoring**
-- `weight` is used whenever two or more parsers are able to parse a
-  file: The parser with the higher weight wins. This can be used to
-  override the parsers provided by Paperless-ngx.
-- `mime_types` is a dictionary. The keys are the mime types your
-  parser supports and the value is the default file extension that
-  Paperless-ngx should use when storing files and serving them for
-  download. We could guess that from the file extensions, but some
-  mime types have many extensions associated with them and the Python
-  methods responsible for guessing the extension do not always return
-  the same value.
 
-## Using Visual Studio Code devcontainer
+When more than one parser can handle a file, the registry calls `score()` on
+each candidate and picks the one with the highest result and equal scores favor third-party parsers over built-ins. Return `None` to
+decline handling a file even though the MIME type is listed as supported (for
+example, when a required external service is not configured).
 
-Another easy way to get started with development is to use Visual Studio
+| Score  | Meaning                                                                           |
-Code devcontainers. This approach will create a preconfigured development
+| ------ | --------------------------------------------------------------------------------- |
-environment with all of the required tools and dependencies.
+| `None` | Decline — do not handle this file                                                 |
-[Learn more about devcontainers](https://code.visualstudio.com/docs/devcontainers/containers).
+| `10`   | Default priority used by all built-in parsers                                     |
-The .devcontainer/vscode/tasks.json and .devcontainer/vscode/launch.json files
+| `20`   | Priority used by the remote OCR built-in parser, allowing it to replace Tesseract |
-contain more information about the specific tasks and launch configurations (see the
+| `> 10` | Override a built-in parser for the same MIME type                                 |
-non-standard "description" field).
 
-To get started:
+```python
+@classmethod
+def score(
+    cls,
+    mime_type: str,
+    filename: str,
+    path: "Path | None" = None,
+) -> int | None:
+    # Inspect filename or file bytes here if needed.
+    return 10
+```
 
-1. Clone the repository on your machine and open the Paperless-ngx folder in VS Code.
+**Archive and rendition flags**
 
-2. VS Code will prompt you with "Reopen in container". Do so and wait for the environment to start.
+```python
+@property
+def can_produce_archive(self) -> bool:
+    """True if parse() can produce a searchable PDF archive copy."""
+    return True   # or False if your parser doesn't produce PDFs
 
-3. In case your host operating system is Windows:
+@property
-   - The Source Control view in Visual Studio Code might show: "The detected Git repository is potentially unsafe as the folder is owned by someone other than the current user." Use "Manage Unsafe Repositories" to fix this.
+def requires_pdf_rendition(self) -> bool:
-   - Git might have detecteded modifications for all files, because Windows is using CRLF line endings. Run `git checkout .` in the containers terminal to fix this issue.
+    """True if the original format cannot be displayed by a browser
+    (e.g. DOCX, ODT) and the PDF output must always be kept."""
+    return False
+```
 
-4. Initialize the project by running the task **Project Setup: Run all Init Tasks**. This
+**Context manager — temp directory lifecycle**
-   will initialize the database tables and create a superuser. Then you can compile the front end
-   for production or run the frontend in debug mode.
 
-5. The project is ready for debugging, start either run the fullstack debug or individual debug
+Paperless-ngx always uses parsers as context managers. Create a temporary
-   processes. Yo spin up the project without debugging run the task **Project Start: Run all Services**
+working directory in `__enter__` (or `__init__`) and remove it in `__exit__`
+regardless of whether an exception occurred. Store intermediate files,
+thumbnails, and archive PDFs inside this directory.
 
-## Developing Date Parser Plugins
+```python
+import shutil
+import tempfile
+from pathlib import Path
+from typing import Self
+from types import TracebackType
+
+from django.conf import settings
+
+class MyCustomParser:
+    ...
+
+    def __init__(self, logging_group: object = None) -> None:
+        settings.SCRATCH_DIR.mkdir(parents=True, exist_ok=True)
+        self._tempdir = Path(
+            tempfile.mkdtemp(prefix="paperless-", dir=settings.SCRATCH_DIR)
+        )
+        self._text: str | None = None
+        self._archive_path: Path | None = None
+
+    def __enter__(self) -> Self:
+        return self
+
+    def __exit__(
+        self,
+        exc_type: type[BaseException] | None,
+        exc_val: BaseException | None,
+        exc_tb: TracebackType | None,
+    ) -> None:
+        shutil.rmtree(self._tempdir, ignore_errors=True)
+```
+
+**Optional context — `configure()`**
+
+The consumer calls `configure()` with a `ParserContext` after instantiation
+and before `parse()`. If your parser doesn't need context, a no-op
+implementation is fine:
+
+```python
+from paperless.parsers import ParserContext
+
+def configure(self, context: ParserContext) -> None:
+    pass   # override if you need context.mailrule_id, etc.
+```
+
+**Parsing**
+
+`parse()` is the core method. It must not return a value; instead, store
+results in instance attributes and expose them via the accessor methods below.
+Raise `documents.parsers.ParseError` on any unrecoverable failure.
+
+```python
+from documents.parsers import ParseError
+
+def parse(
+    self,
+    document_path: Path,
+    mime_type: str,
+    *,
+    produce_archive: bool = True,
+) -> None:
+    try:
+        self._text = extract_text_from_my_format(document_path)
+    except Exception as e:
+        raise ParseError(f"Failed to parse {document_path}: {e}") from e
+
+    if produce_archive and self.can_produce_archive:
+        archive = self._tempdir / "archived.pdf"
+        convert_to_pdf(document_path, archive)
+        self._archive_path = archive
+```
+
+**Result accessors**
+
+```python
+def get_text(self) -> str | None:
+    return self._text
+
+def get_date(self) -> "datetime.datetime | None":
+    # Return a datetime extracted from the document, or None to let
+    # Paperless-ngx use its default date-guessing logic.
+    return None
+
+def get_archive_path(self) -> Path | None:
+    return self._archive_path
+
+def get_page_count(self, document_path: Path, mime_type: str) -> int | None:
+    # If the format doesn't have the concept of pages, return None
+    return count_pages(document_path)
+
+```
+
+**Thumbnail**
+
+`get_thumbnail()` may be called independently of `parse()`. Return the path
+to a WebP image inside `self._tempdir`. The image should be roughly 500 × 700
+pixels.
+
+```python
+def get_thumbnail(self, document_path: Path, mime_type: str) -> Path:
+    thumb = self._tempdir / "thumb.webp"
+    render_thumbnail(document_path, thumb)
+    return thumb
+```
+
+**Optional methods**
+
+These are called by the API on demand, not during the consumption pipeline.
+Implement them if your format supports the information; otherwise return
+`None` / `[]`.
+
+```python
+
+def extract_metadata(
+    self,
+    document_path: Path,
+    mime_type: str,
+) -> "list[MetadataEntry]":
+    # Must never raise. Return [] if metadata cannot be read.
+    from paperless.parsers import MetadataEntry
+    return [
+        MetadataEntry(
+            namespace="https://example.com/ns/",
+            prefix="ex",
+            key="Author",
+            value="Alice",
+        )
+    ]
+```
+
+#### 2. Registering via entry point
+
+Add the following to your package's `pyproject.toml`. The key (left of `=`)
+is an arbitrary name used only in log output; the value is the
+`module:ClassName` import path.
+
+```toml
+[project.entry-points."paperless_ngx.parsers"]
+my_parser = "my_package.parsers:MyCustomParser"
+```
+
+Install your package into the same Python environment as Paperless-ngx (or
+add it to the Docker image), and the parser will be discovered automatically
+on the next startup. No configuration changes are needed.
+
+To verify discovery, check the application logs at startup for a line like:
+
+```
+Loaded third-party parser 'My Format Parser' v1.0.0 by Acme Corp (entrypoint: 'my_parser').
+```
+
+#### 3. Utilities
+
+`paperless.parsers.utils` provides helpers you can import directly:
+
+| Function                                | Description                                                      |
+| --------------------------------------- | ---------------------------------------------------------------- |
+| `read_file_handle_unicode_errors(path)` | Read a file as UTF-8, replacing invalid bytes instead of raising |
+| `get_page_count_for_pdf(path)`          | Count pages in a PDF using pikepdf                               |
+| `extract_pdf_metadata(path)`            | Extract XMP metadata from a PDF as a `list[MetadataEntry]`       |
+
+#### Minimal example
+
+A complete, working parser for a hypothetical plain-XML format:
+
+```python
+from __future__ import annotations
+
+import shutil
+import tempfile
+from pathlib import Path
+from typing import Self
+from types import TracebackType
+import xml.etree.ElementTree as ET
+
+from django.conf import settings
+
+from documents.parsers import ParseError
+from paperless.parsers import ParserContext
+
+
+class XmlDocumentParser:
+    name    = "XML Parser"
+    version = "1.0.0"
+    author  = "Acme Corp"
+    url     = "https://example.com/xml-parser"
+
+    @classmethod
+    def supported_mime_types(cls) -> dict[str, str]:
+        return {"application/xml": ".xml", "text/xml": ".xml"}
+
+    @classmethod
+    def score(cls, mime_type: str, filename: str, path: Path | None = None) -> int | None:
+        return 10
+
+    @property
+    def can_produce_archive(self) -> bool:
+        return False
+
+    @property
+    def requires_pdf_rendition(self) -> bool:
+        return False
+
+    def __init__(self, logging_group: object = None) -> None:
+        settings.SCRATCH_DIR.mkdir(parents=True, exist_ok=True)
+        self._tempdir = Path(tempfile.mkdtemp(prefix="paperless-", dir=settings.SCRATCH_DIR))
+        self._text: str | None = None
+
+    def __enter__(self) -> Self:
+        return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb) -> None:
+        shutil.rmtree(self._tempdir, ignore_errors=True)
+
+    def configure(self, context: ParserContext) -> None:
+        pass
+
+    def parse(self, document_path: Path, mime_type: str, *, produce_archive: bool = True) -> None:
+        try:
+            tree = ET.parse(document_path)
+            self._text = " ".join(tree.getroot().itertext())
+        except ET.ParseError as e:
+            raise ParseError(f"XML parse error: {e}") from e
+
+    def get_text(self) -> str | None:
+        return self._text
+
+    def get_date(self):
+        return None
+
+    def get_archive_path(self) -> Path | None:
+        return None
+
+    def get_thumbnail(self, document_path: Path, mime_type: str) -> Path:
+        from PIL import Image, ImageDraw
+        img = Image.new("RGB", (500, 700), color="white")
+        ImageDraw.Draw(img).text((10, 10), "XML Document", fill="black")
+        out = self._tempdir / "thumb.webp"
+        img.save(out, format="WEBP")
+        return out
+
+    def get_page_count(self, document_path: Path, mime_type: str) -> int | None:
+        return None
+
+    def extract_metadata(self, document_path: Path, mime_type: str) -> list:
+        return []
+```
+
+### Developing date parser plugins
 
 Paperless-ngx uses a plugin system for date parsing, allowing you to extend or replace the default date parsing behavior. Plugins are discovered using [Python entry points](https://setuptools.pypa.io/en/latest/userguide/entry_point.html).
 
-### Creating a Date Parser Plugin
+#### Creating a Date Parser Plugin
 
 To create a custom date parser plugin, you need to:
 
@@ -492,7 +738,7 @@ To create a custom date parser plugin, you need to:
 2. Implement the required abstract method
 3. Register your plugin via an entry point
 
-#### 1. Implementing the Parser Class
+##### 1. Implementing the Parser Class
 
 Your parser must extend `documents.plugins.date_parsing.DateParserPluginBase` and implement the `parse` method:
 
@@ -532,7 +778,7 @@ class MyDateParserPlugin(DateParserPluginBase):
         yield another_datetime
 ```
 
-#### 2. Configuration and Helper Methods
+##### 2. Configuration and Helper Methods
 
 Your parser instance is initialized with a `DateParserConfig` object accessible via `self.config`. This provides:
 
@@ -565,11 +811,11 @@ def _filter_date(
     """
 ```
 
-#### 3. Resource Management (Optional)
+##### 3. Resource Management (Optional)
 
 If your plugin needs to acquire or release resources (database connections, API clients, etc.), override the context manager methods. Paperless-ngx will always use plugins as context managers, ensuring resources can be released even in the event of errors.
 
-#### 4. Registering Your Plugin
+##### 4. Registering Your Plugin
 
 Register your plugin using a setuptools entry point in your package's `pyproject.toml`:
 
@@ -580,7 +826,7 @@ my_parser = "my_package.parsers:MyDateParserPlugin"
 
 The entry point name (e.g., `"my_parser"`) is used for sorting when multiple plugins are found. Paperless-ngx will use the first plugin alphabetically by name if multiple plugins are discovered.
 
-### Plugin Discovery
+#### Plugin Discovery
 
 Paperless-ngx automatically discovers and loads date parser plugins at runtime. The discovery process:
 
@@ -591,7 +837,7 @@ Paperless-ngx automatically discovers and loads date parser plugins at runtime.
 
 If multiple plugins are installed, a warning is logged indicating which plugin was selected.
 
-### Example: Simple Date Parser
+#### Example: Simple Date Parser
 
 Here's a minimal example that only looks for ISO 8601 dates:
 
@@ -623,3 +869,30 @@ class ISODateParserPlugin(DateParserPluginBase):
             if filtered_date is not None:
                 yield filtered_date
 ```
+
+## Using Visual Studio Code devcontainer
+
+Another easy way to get started with development is to use Visual Studio
+Code devcontainers. This approach will create a preconfigured development
+environment with all of the required tools and dependencies.
+[Learn more about devcontainers](https://code.visualstudio.com/docs/devcontainers/containers).
+The .devcontainer/vscode/tasks.json and .devcontainer/vscode/launch.json files
+contain more information about the specific tasks and launch configurations (see the
+non-standard "description" field).
+
+To get started:
+
+1. Clone the repository on your machine and open the Paperless-ngx folder in VS Code.
+
+2. VS Code will prompt you with "Reopen in container". Do so and wait for the environment to start.
+
+3. In case your host operating system is Windows:
+   - The Source Control view in Visual Studio Code might show: "The detected Git repository is potentially unsafe as the folder is owned by someone other than the current user." Use "Manage Unsafe Repositories" to fix this.
+   - Git might have detecteded modifications for all files, because Windows is using CRLF line endings. Run `git checkout .` in the containers terminal to fix this issue.
+
+4. Initialize the project by running the task **Project Setup: Run all Init Tasks**. This
+   will initialize the database tables and create a superuser. Then you can compile the front end
+   for production or run the frontend in debug mode.
+
+5. The project is ready for debugging, start either run the fullstack debug or individual debug
+   processes. Yo spin up the project without debugging run the task **Project Start: Run all Services**

docs/migration-v3.md

@@ -104,6 +104,37 @@ Multiple options are combined in a single value:
 PAPERLESS_DB_OPTIONS="sslmode=require;sslrootcert=/certs/ca.pem;pool.max_size=10"
 ```
 
+## Search Index (Whoosh -> Tantivy)
+
+The full-text search backend has been replaced with [Tantivy](https://github.com/quickwit-oss/tantivy).
+The index format is incompatible with Whoosh, so **the search index is automatically rebuilt from
+scratch on first startup after upgrading**. No manual action is required for the rebuild itself.
+
+### Note and custom field search syntax
+
+The old Whoosh index exposed `note` and `custom_field` as flat text fields that were included in
+unqualified searches (e.g. just typing `invoice` would match note content). With Tantivy these are
+now structured JSON fields accessed via dotted paths:
+
+| Old syntax           | New syntax                  |
+| -------------------- | --------------------------- |
+| `note:query`         | `notes.note:query`          |
+| `custom_field:query` | `custom_fields.value:query` |
+
+**Saved views are migrated automatically.** Any saved view filter rule that used an explicit
+`note:` or `custom_field:` field prefix in a fulltext query is rewritten to the new syntax by a
+data migration that runs on upgrade.
+
+**Unqualified queries are not migrated.** If you had a saved view with a plain search term (e.g.
+`invoice`) that happened to match note content or custom field values, it will no longer return
+those matches. Update those queries to use the explicit prefix, for example:
+
+```
+invoice OR notes.note:invoice OR custom_fields.value:invoice
+```
+
+Custom field names can also be searched with `custom_fields.name:fieldname`.
+
 ## OpenID Connect Token Endpoint Authentication
 
 Some existing OpenID Connect setups may require an explicit token endpoint authentication method after upgrading to v3.

docs/usage.md

@@ -804,13 +804,20 @@ contract you signed 8 years ago).
 
 When you search paperless for a document, it tries to match this query
 against your documents. Paperless will look for matching documents by
-inspecting their content, title, correspondent, type and tags. Paperless
+inspecting their content, title, correspondent, type, tags, notes, and
-returns a scored list of results, so that documents matching your query
+custom field values. Paperless returns a scored list of results, so that
-better will appear further up in the search results.
+documents matching your query better will appear further up in the search
+results.
 
 By default, paperless returns only documents which contain all words
-typed in the search bar. However, paperless also offers advanced search
+typed in the search bar. A few things to know about how matching works:
-syntax if you want to drill down the results further.
+
+- **Word-order-independent**: "invoice unpaid" and "unpaid invoice" return the same results.
+- **Accent-insensitive**: searching `resume` also finds `résumé`, `cafe` finds `café`.
+- **Separator-agnostic**: punctuation and separators are stripped during indexing, so
+  searching a partial number like `1312` finds documents containing `A-1312/B`.
+
+Paperless also offers advanced search syntax if you want to drill down further.
 
 Matching documents with logical expressions:
 
@@ -839,18 +846,69 @@ Matching inexact words:
 produ*name
 ```
 
+Matching natural date keywords:
+
+```
+added:today
+modified:yesterday
+created:this_week
+added:last_month
+modified:this_year
+```
+
+Supported date keywords: `today`, `yesterday`, `this_week`, `last_week`,
+`this_month`, `last_month`, `this_year`, `last_year`.
+
+#### Searching custom fields
+
+Custom field values are included in the full-text index, so a plain search
+already matches documents whose custom field values contain your search terms.
+To narrow by field name or value specifically:
+
+```
+custom_fields.value:policy
+custom_fields.name:"Contract Number"
+custom_fields.name:Insurance custom_fields.value:policy
+```
+
+- `custom_fields.value` matches against the value of any custom field.
+- `custom_fields.name` matches the name of the field (use quotes for multi-word names).
+- Combine both to find documents where a specific named field contains a specific value.
+
+Because separators are stripped during indexing, individual parts of formatted
+codes are searchable on their own. A value stored as `A-1312/99.50` produces the
+tokens `a`, `1312`, `99`, `50` — each searchable independently:
+
+```
+custom_fields.value:1312
+custom_fields.name:"Contract Number" custom_fields.value:1312
+```
+
 !!! note
 
-    Inexact terms are hard for search indexes. These queries might take a
+    Custom date fields do not support relative date syntax (e.g. `[now to 2 weeks]`).
-    while to execute. That's why paperless offers auto complete and query
+    For date ranges on custom date fields, use the document list filters in the web UI.
-    correction.
+
+#### Searching notes
+
+Notes content is included in full-text search automatically. To search
+by note author or content specifically:
+
+```
+notes.user:alice
+notes.note:reminder
+notes.user:alice notes.note:insurance
+```
 
 All of these constructs can be combined as you see fit. If you want to
-learn more about the query language used by paperless, paperless uses
+learn more about the query language used by paperless, see the
-Whoosh's default query language. Head over to [Whoosh query
+[Tantivy query language documentation](https://docs.rs/tantivy/latest/tantivy/query/struct.QueryParser.html).
-language](https://whoosh.readthedocs.io/en/latest/querylang.html). For
+
-details on what date parsing utilities are available, see [Date
+!!! note
-parsing](https://whoosh.readthedocs.io/en/latest/dates.html#parsing-date-queries).
+
+    Fuzzy (approximate) matching can be enabled by setting
+    [`PAPERLESS_ADVANCED_FUZZY_SEARCH_THRESHOLD`](configuration.md#PAPERLESS_ADVANCED_FUZZY_SEARCH_THRESHOLD).
+    When enabled, paperless will include near-miss results ranked below exact matches.
 
 ## Keyboard shortcuts / hotkeys
 

pyproject.toml

@@ -13,7 +13,6 @@ classifiers = [
 ]
 # TODO: Move certain things to groups and then utilize that further
 # This will allow testing to not install a webserver, mysql, etc
-
 dependencies = [
   "azure-ai-documentintelligence>=1.0.2",
   "babel>=2.17",
@@ -47,7 +46,7 @@ dependencies = [
   "faiss-cpu>=1.10",
   "filelock~=3.25.2",
   "flower~=2.0.1",
-  "gotenberg-client~=0.13.1",
+  "gotenberg-client~=0.14.0",
   "httpx-oauth~=0.16",
   "ijson>=3.2",
   "imap-tools~=1.11.0",
@@ -60,7 +59,7 @@ dependencies = [
   "llama-index-llms-openai>=0.6.13",
   "llama-index-vector-stores-faiss>=0.5.2",
   "nltk~=3.9.1",
-  "ocrmypdf~=17.3.0",
+  "ocrmypdf~=17.4.0",
   "openai>=1.76",
   "pathvalidate~=3.3.1",
   "pdf2image~=1.17.0",
@@ -75,39 +74,40 @@ dependencies = [
   "scikit-learn~=1.8.0",
   "sentence-transformers>=4.1",
   "setproctitle~=1.3.4",
-  "tika-client~=0.10.0",
+  "tantivy>=0.25.1",
+  "tika-client~=0.11.0",
   "torch~=2.10.0",
   "watchfiles>=1.1.1",
   "whitenoise~=6.11",
-  "whoosh-reloaded>=2.7.5",
   "zxing-cpp~=3.0.0",
 ]
-
+[project.optional-dependencies]
-optional-dependencies.mariadb = [
+mariadb = [
   "mysqlclient~=2.2.7",
 ]
-optional-dependencies.postgres = [
+postgres = [
   "psycopg[c,pool]==3.3",
   # Direct dependency for proper resolution of the pre-built wheels
   "psycopg-c==3.3",
   "psycopg-pool==3.3",
 ]
-optional-dependencies.webserver = [
+webserver = [
   "granian[uvloop]~=2.7.0",
 ]
 
 [dependency-groups]
-
 dev = [
-  { "include-group" = "docs" },
+  { include-group = "docs" },
-  { "include-group" = "testing" },
+  { include-group = "lint" },
-  { "include-group" = "lint" },
+  { include-group = "testing" },
 ]
-
 docs = [
   "zensical>=0.0.21",
 ]
-
+lint = [
+  "prek~=0.3.0",
+  "ruff~=0.15.0",
+]
 testing = [
   "daphne",
   "factory-boy~=3.3.1",
@@ -119,17 +119,12 @@ testing = [
   "pytest-env~=1.5.0",
   "pytest-httpx",
   "pytest-mock~=3.15.1",
-  #"pytest-randomly~=4.0.1",
+  # "pytest-randomly~=4.0.1",
   "pytest-rerunfailures~=16.1",
   "pytest-sugar",
   "pytest-xdist~=3.8.0",
+  "time-machine>=2.13",
 ]
-
-lint = [
-  "prek~=0.3.0",
-  "ruff~=0.15.0",
-]
-
 typing = [
   "celery-types",
   "django-filter-stubs",
@@ -154,24 +149,21 @@ typing = [
 
 [tool.uv]
 required-version = ">=0.9.0"
-package = false
 environments = [
   "sys_platform == 'darwin'",
   "sys_platform == 'linux'",
 ]
-
+package = false
 [[tool.uv.index]]
 name = "pytorch-cpu"
 url = "https://download.pytorch.org/whl/cpu"
 explicit = true
-
 [tool.uv.sources]
 # Markers are chosen to select these almost exclusively when building the Docker image
 psycopg-c = [
   { url = "https://github.com/paperless-ngx/builder/releases/download/psycopg-trixie-3.3.0/psycopg_c-3.3.0-cp312-cp312-linux_x86_64.whl", marker = "sys_platform == 'linux' and platform_machine == 'x86_64' and python_version == '3.12'" },
   { url = "https://github.com/paperless-ngx/builder/releases/download/psycopg-trixie-3.3.0/psycopg_c-3.3.0-cp312-cp312-linux_aarch64.whl", marker = "sys_platform == 'linux' and platform_machine == 'aarch64' and python_version == '3.12'" },
 ]
-
 torch = [
   { index = "pytorch-cpu" },
 ]
@@ -186,10 +178,10 @@ respect-gitignore = true
 # https://docs.astral.sh/ruff/settings/
 fix = true
 show-fixes = true
-
 output-format = "grouped"
+[tool.ruff.lint]
 # https://docs.astral.sh/ruff/rules/
-lint.extend-select = [
+extend-select = [
   "COM",  # https://docs.astral.sh/ruff/rules/#flake8-commas-com
   "DJ",   # https://docs.astral.sh/ruff/rules/#flake8-django-dj
   "EXE",  # https://docs.astral.sh/ruff/rules/#flake8-executable-exe
@@ -214,115 +206,52 @@ lint.extend-select = [
   "UP",   # https://docs.astral.sh/ruff/rules/#pyupgrade-up
   "W",    # https://docs.astral.sh/ruff/rules/#pycodestyle-e-w
 ]
-lint.ignore = [
+ignore = [
   "DJ001",
   "PLC0415",
   "RUF012",
   "SIM105",
 ]
 # Migrations
-lint.per-file-ignores."*/migrations/*.py" = [
+per-file-ignores."*/migrations/*.py" = [
   "E501",
   "SIM",
   "T201",
 ]
 # Testing
-lint.per-file-ignores."*/tests/*.py" = [
+per-file-ignores."*/tests/*.py" = [
   "E501",
   "SIM117",
 ]
-lint.per-file-ignores.".github/scripts/*.py" = [
+per-file-ignores.".github/scripts/*.py" = [
   "E501",
   "INP001",
   "SIM117",
 ]
 # Docker specific
-lint.per-file-ignores."docker/rootfs/usr/local/bin/wait-for-redis.py" = [
+per-file-ignores."docker/rootfs/usr/local/bin/wait-for-redis.py" = [
   "INP001",
   "T201",
 ]
-lint.per-file-ignores."docker/wait-for-redis.py" = [
+per-file-ignores."docker/wait-for-redis.py" = [
   "INP001",
   "T201",
 ]
-lint.per-file-ignores."src/documents/models.py" = [
+per-file-ignores."src/documents/models.py" = [
   "SIM115",
 ]
-
+isort.force-single-line = true
-lint.isort.force-single-line = true
 
 [tool.codespell]
 write-changes = true
 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/paperless/tests/samples/mail/*,src/documents/tests/samples/*,*.po,*.json"
+skip = """\
+  src-ui/src/locale/*,src-ui/pnpm-lock.yaml,src-ui/e2e/*,src/paperless_mail/tests/samples/*,src/paperless/tests/samples\
+  /mail/*,src/documents/tests/samples/*,*.po,*.json\
+  """
 
-[tool.pytest]
+[tool.pyproject-fmt]
-minversion = "9.0"
+table_format = "long"
-pythonpath = [ "src" ]
-
-strict_config = true
-strict_markers = true
-strict_parametrization_ids = true
-strict_xfail = true
-
-testpaths = [
-  "src/documents/tests/",
-  "src/paperless/tests/",
-  "src/paperless_mail/tests/",
-  "src/paperless_ai/tests",
-]
-
-addopts = [
-  "--pythonwarnings=all",
-  "--cov",
-  "--cov-report=html",
-  "--cov-report=xml",
-  "--numprocesses=auto",
-  "--maxprocesses=16",
-  "--dist=loadscope",
-  "--durations=50",
-  "--durations-min=0.5",
-  "--junitxml=junit.xml",
-  "-o",
-  "junit_family=legacy",
-]
-
-norecursedirs = [ "src/locale/", ".venv/", "src-ui/" ]
-
-DJANGO_SETTINGS_MODULE = "paperless.settings"
-
-markers = [
-  "live: Integration tests requiring external services (Gotenberg, Tika, nginx, etc)",
-  "nginx: Tests that make HTTP requests to the local nginx service",
-  "gotenberg: Tests requiring Gotenberg service",
-  "tika: Tests requiring Tika service",
-  "greenmail: Tests requiring Greenmail service",
-  "date_parsing: Tests which cover date parsing from content or filename",
-  "management: Tests which cover management commands/functionality",
-]
-
-[tool.pytest_env]
-PAPERLESS_DISABLE_DBHANDLER = "true"
-PAPERLESS_CACHE_BACKEND = "django.core.cache.backends.locmem.LocMemCache"
-PAPERLESS_CHANNELS_BACKEND = "channels.layers.InMemoryChannelLayer"
-
-[tool.coverage.report]
-exclude_also = [
-  "if settings.AUDIT_LOG_ENABLED:",
-  "if AUDIT_LOG_ENABLED:",
-  "if TYPE_CHECKING:",
-]
-
-[tool.coverage.run]
-source = [
-  "src/",
-]
-omit = [
-  "*/tests/*",
-  "manage.py",
-  "paperless/wsgi.py",
-  "paperless/auth.py",
-]
 
 [tool.mypy]
 mypy_path = "src"
@@ -345,6 +274,68 @@ python-platform = "linux"
 [tool.django-stubs]
 django_settings_module = "paperless.settings"
 
+[tool.pytest]
+minversion = "9.0"
+pythonpath = [ "src" ]
+strict_config = true
+strict_markers = true
+strict_parametrization_ids = true
+strict_xfail = true
+testpaths = [
+  "src/documents/tests/",
+  "src/paperless/tests/",
+  "src/paperless_mail/tests/",
+  "src/paperless_ai/tests",
+]
+addopts = [
+  "--pythonwarnings=all",
+  "--cov",
+  "--cov-report=html",
+  "--cov-report=xml",
+  "--numprocesses=auto",
+  "--maxprocesses=16",
+  "--dist=loadscope",
+  "--durations=50",
+  "--durations-min=0.5",
+  "--junitxml=junit.xml",
+  "-o",
+  "junit_family=legacy",
+]
+norecursedirs = [ "src/locale/", ".venv/", "src-ui/" ]
+DJANGO_SETTINGS_MODULE = "paperless.settings"
+markers = [
+  "live: Integration tests requiring external services (Gotenberg, Tika, nginx, etc)",
+  "nginx: Tests that make HTTP requests to the local nginx service",
+  "gotenberg: Tests requiring Gotenberg service",
+  "tika: Tests requiring Tika service",
+  "greenmail: Tests requiring Greenmail service",
+  "date_parsing: Tests which cover date parsing from content or filename",
+  "management: Tests which cover management commands/functionality",
+  "search: Tests for the Tantivy search backend",
+]
+
+[tool.pytest_env]
+PAPERLESS_DISABLE_DBHANDLER = "true"
+PAPERLESS_CACHE_BACKEND = "django.core.cache.backends.locmem.LocMemCache"
+PAPERLESS_CHANNELS_BACKEND = "channels.layers.InMemoryChannelLayer"
+
+[tool.coverage.report]
+exclude_also = [
+  "if settings.AUDIT_LOG_ENABLED:",
+  "if AUDIT_LOG_ENABLED:",
+  "if TYPE_CHECKING:",
+]
+[tool.coverage.run]
+source = [
+  "src/",
+]
+omit = [
+  "*/tests/*",
+  "manage.py",
+  "paperless/wsgi.py",
+  "paperless/auth.py",
+]
+
 [tool.mypy-baseline]
 baseline_path = ".mypy-baseline.txt"
 sort_baseline = true

src-ui/e2e/dashboard/requests/api-dashboard1.har

@@ -468,7 +468,7 @@
         "time": 0.951,
         "request": {
           "method": "GET",
-          "url": "http://localhost:8000/api/documents/?page=1&page_size=50&ordering=-created&truncate_content=true&tags__id__in=9",
+          "url": "http://localhost:8000/api/documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__in=9",
           "httpVersion": "HTTP/1.1",
           "cookies": [],
           "headers": [

src-ui/e2e/dashboard/requests/api-dashboard3.har

@@ -534,7 +534,7 @@
         "time": 0.653,
         "request": {
           "method": "GET",
-          "url": "http://localhost:8000/api/documents/?page=1&page_size=50&ordering=-created&truncate_content=true&tags__id__all=9",
+          "url": "http://localhost:8000/api/documents/?page=1&page_size=10&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__all=9",
           "httpVersion": "HTTP/1.1",
           "cookies": [],
           "headers": [

src-ui/e2e/document-detail/requests/api-document-detail2.har

@@ -883,7 +883,7 @@
         "time": 0.93,
         "request": {
           "method": "GET",
-          "url": "http://localhost:8000/api/documents/?page=1&page_size=50&ordering=-created&truncate_content=true&tags__id__all=4",
+          "url": "http://localhost:8000/api/documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__all=4",
           "httpVersion": "HTTP/1.1",
           "cookies": [],
           "headers": [
@@ -961,7 +961,7 @@
         "time": -1,
         "request": {
           "method": "GET",
-          "url": "http://localhost:8000/api/documents/?page=1&page_size=50&ordering=-created&truncate_content=true&tags__id__all=4",
+          "url": "http://localhost:8000/api/documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__all=4",
           "httpVersion": "HTTP/1.1",
           "cookies": [],
           "headers": [

src-ui/e2e/document-list/document-list.spec.ts

@@ -16,7 +16,7 @@ test('basic filtering', async ({ page }) => {
   await expect(page).toHaveURL(/tags__id__all=9/)
   await expect(page.locator('pngx-document-list')).toHaveText(/8 documents/)
   await page.getByRole('button', { name: 'Document type' }).click()
-  await page.getByRole('menuitem', { name: 'Invoice Test 3' }).click()
+  await page.getByRole('menuitem', { name: /^Invoice Test/ }).click()
   await expect(page).toHaveURL(/document_type__id__in=1/)
   await expect(page.locator('pngx-document-list')).toHaveText(/3 documents/)
   await page.getByRole('button', { name: 'Reset filters' }).first().click()

src-ui/package.json

@@ -11,15 +11,15 @@
   },
   "private": true,
   "dependencies": {
-    "@angular/cdk": "^21.2.2",
+    "@angular/cdk": "^21.2.4",
-    "@angular/common": "~21.2.4",
+    "@angular/common": "~21.2.6",
-    "@angular/compiler": "~21.2.4",
+    "@angular/compiler": "~21.2.6",
-    "@angular/core": "~21.2.4",
+    "@angular/core": "~21.2.6",
-    "@angular/forms": "~21.2.4",
+    "@angular/forms": "~21.2.6",
-    "@angular/localize": "~21.2.4",
+    "@angular/localize": "~21.2.6",
-    "@angular/platform-browser": "~21.2.4",
+    "@angular/platform-browser": "~21.2.6",
-    "@angular/platform-browser-dynamic": "~21.2.4",
+    "@angular/platform-browser-dynamic": "~21.2.6",
-    "@angular/router": "~21.2.4",
+    "@angular/router": "~21.2.6",
     "@ng-bootstrap/ng-bootstrap": "^20.0.0",
     "@ng-select/ng-select": "^21.5.2",
     "@ngneat/dirty-check-forms": "^3.0.3",
@@ -29,7 +29,7 @@
     "mime-names": "^1.0.0",
     "ngx-bootstrap-icons": "^1.9.3",
     "ngx-color": "^10.1.0",
-    "ngx-cookie-service": "^21.1.0",
+    "ngx-cookie-service": "^21.3.1",
     "ngx-device-detector": "^11.0.0",
     "ngx-ui-tour-ng-bootstrap": "^18.0.0",
     "pdfjs-dist": "^5.4.624",
@@ -42,24 +42,24 @@
   "devDependencies": {
     "@angular-builders/custom-webpack": "^21.0.3",
     "@angular-builders/jest": "^21.0.3",
-    "@angular-devkit/core": "^21.2.2",
+    "@angular-devkit/core": "^21.2.3",
-    "@angular-devkit/schematics": "^21.2.2",
+    "@angular-devkit/schematics": "^21.2.3",
-    "@angular-eslint/builder": "21.3.0",
+    "@angular-eslint/builder": "21.3.1",
-    "@angular-eslint/eslint-plugin": "21.3.0",
+    "@angular-eslint/eslint-plugin": "21.3.1",
-    "@angular-eslint/eslint-plugin-template": "21.3.0",
+    "@angular-eslint/eslint-plugin-template": "21.3.1",
-    "@angular-eslint/schematics": "21.3.0",
+    "@angular-eslint/schematics": "21.3.1",
-    "@angular-eslint/template-parser": "21.3.0",
+    "@angular-eslint/template-parser": "21.3.1",
-    "@angular/build": "^21.2.2",
+    "@angular/build": "^21.2.3",
-    "@angular/cli": "~21.2.2",
+    "@angular/cli": "~21.2.3",
-    "@angular/compiler-cli": "~21.2.4",
+    "@angular/compiler-cli": "~21.2.6",
     "@codecov/webpack-plugin": "^1.9.1",
     "@playwright/test": "^1.58.2",
     "@types/jest": "^30.0.0",
-    "@types/node": "^25.4.0",
+    "@types/node": "^25.5.0",
-    "@typescript-eslint/eslint-plugin": "^8.57.0",
+    "@typescript-eslint/eslint-plugin": "^8.57.2",
-    "@typescript-eslint/parser": "^8.57.0",
+    "@typescript-eslint/parser": "^8.57.2",
-    "@typescript-eslint/utils": "^8.57.0",
+    "@typescript-eslint/utils": "^8.57.2",
-    "eslint": "^10.0.3",
+    "eslint": "^10.1.0",
     "jest": "30.3.0",
     "jest-environment-jsdom": "^30.3.0",
     "jest-junit": "^16.0.0",

src-ui/src/app/components/common/filterable-dropdown/filterable-dropdown.component.ts

@@ -20,9 +20,9 @@ import { Subject, filter, takeUntil } from 'rxjs'
 import { NEGATIVE_NULL_FILTER_VALUE } from 'src/app/data/filter-rule-type'
 import { MatchingModel } from 'src/app/data/matching-model'
 import { ObjectWithPermissions } from 'src/app/data/object-with-permissions'
+import { SelectionDataItem } from 'src/app/data/results'
 import { FilterPipe } from 'src/app/pipes/filter.pipe'
 import { HotKeyService } from 'src/app/services/hot-key.service'
-import { SelectionDataItem } from 'src/app/services/rest/document.service'
 import { pngxPopperOptions } from 'src/app/utils/popper-options'
 import { LoadingComponentWithPermissions } from '../../loading-component/loading.component'
 import { ClearableBadgeComponent } from '../clearable-badge/clearable-badge.component'

src-ui/src/app/components/document-detail/document-detail.component.spec.ts

@@ -959,7 +959,7 @@ describe('DocumentDetailComponent', () => {
     component.reprocess()
     const modalCloseSpy = jest.spyOn(openModal, 'close')
     openModal.componentInstance.confirmClicked.next()
-    expect(reprocessSpy).toHaveBeenCalledWith([doc.id])
+    expect(reprocessSpy).toHaveBeenCalledWith({ documents: [doc.id] })
     expect(modalSpy).toHaveBeenCalled()
     expect(toastSpy).toHaveBeenCalled()
     expect(modalCloseSpy).toHaveBeenCalled()

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

@@ -1379,25 +1379,27 @@ export class DocumentDetailComponent
     modal.componentInstance.btnCaption = $localize`Proceed`
     modal.componentInstance.confirmClicked.subscribe(() => {
       modal.componentInstance.buttonsEnabled = false
-      this.documentsService.reprocessDocuments([this.document.id]).subscribe({
+      this.documentsService
-        next: () => {
+        .reprocessDocuments({ documents: [this.document.id] })
-          this.toastService.showInfo(
+        .subscribe({
-            $localize`Reprocess operation for "${this.document.title}" will begin in the background.`
+          next: () => {
-          )
+            this.toastService.showInfo(
-          if (modal) {
+              $localize`Reprocess operation for "${this.document.title}" will begin in the background.`
-            modal.close()
+            )
-          }
+            if (modal) {
-        },
+              modal.close()
-        error: (error) => {
+            }
-          if (modal) {
+          },
-            modal.componentInstance.buttonsEnabled = true
+          error: (error) => {
-          }
+            if (modal) {
-          this.toastService.showError(
+              modal.componentInstance.buttonsEnabled = true
-            $localize`Error executing operation`,
+            }
-            error
+            this.toastService.showError(
-          )
+              $localize`Error executing operation`,
-        },
+              error
-      })
+            )
+          },
+        })
     })
   }
 

src-ui/src/app/components/document-list/bulk-editor/bulk-editor.component.html

@@ -92,7 +92,7 @@
           <button ngbDropdownItem (click)="rotateSelected()" [disabled]="!userOwnsAll && !userCanEditAll">
             <i-bs name="arrow-clockwise" class="me-1"></i-bs><ng-container i18n>Rotate</ng-container>
           </button>
-          <button ngbDropdownItem (click)="mergeSelected()" [disabled]="!userCanAdd || list.selected.size < 2">
+          <button ngbDropdownItem (click)="mergeSelected()" [disabled]="!userCanAdd || list.allSelected || list.selectedCount < 2">
             <i-bs name="journals" class="me-1"></i-bs><ng-container i18n>Merge</ng-container>
           </button>
         </div>
@@ -103,13 +103,13 @@
         class="btn btn-sm btn-outline-primary"
         id="dropdownSend"
         ngbDropdownToggle
-        [disabled]="disabled || list.selected.size === 0"
+        [disabled]="disabled || !list.hasSelection || list.allSelected"
       >
         <i-bs name="send"></i-bs><div class="d-none d-sm-inline ms-1"><ng-container i18n>Send</ng-container>
         </div>
       </button>
       <div ngbDropdownMenu aria-labelledby="dropdownSend" class="shadow">
-        <button ngbDropdownItem (click)="createShareLinkBundle()">
+        <button ngbDropdownItem (click)="createShareLinkBundle()" [disabled]="list.allSelected">
           <i-bs name="link" class="me-1"></i-bs><ng-container i18n>Create a share link bundle</ng-container>
         </button>
         <button ngbDropdownItem (click)="manageShareLinkBundles()">
@@ -117,7 +117,7 @@
         </button>
         <div class="dropdown-divider"></div>
         @if (emailEnabled) {
-          <button ngbDropdownItem (click)="emailSelected()">
+          <button ngbDropdownItem (click)="emailSelected()" [disabled]="list.allSelected">
             <i-bs name="envelope" class="me-1"></i-bs><ng-container i18n>Email</ng-container>
           </button>
         }

src-ui/src/app/components/document-list/bulk-editor/bulk-editor.component.spec.ts

@@ -13,6 +13,7 @@ import { of, throwError } from 'rxjs'
 import { Correspondent } from 'src/app/data/correspondent'
 import { CustomField, CustomFieldDataType } from 'src/app/data/custom-field'
 import { DocumentType } from 'src/app/data/document-type'
+import { FILTER_TITLE } from 'src/app/data/filter-rule-type'
 import { Results } from 'src/app/data/results'
 import { StoragePath } from 'src/app/data/storage-path'
 import { Tag } from 'src/app/data/tag'
@@ -273,6 +274,92 @@ describe('BulkEditorComponent', () => {
     expect(component.customFieldsSelectionModel.selectionSize()).toEqual(1)
   })
 
+  it('should apply list selection data to tags menu when all filtered documents are selected', () => {
+    jest.spyOn(permissionsService, 'currentUserCan').mockReturnValue(true)
+    fixture.detectChanges()
+    jest
+      .spyOn(documentListViewService, 'allSelected', 'get')
+      .mockReturnValue(true)
+    jest
+      .spyOn(documentListViewService, 'selectedCount', 'get')
+      .mockReturnValue(3)
+    documentListViewService.selectionData = selectionData
+    const getSelectionDataSpy = jest.spyOn(documentService, 'getSelectionData')
+
+    component.openTagsDropdown()
+
+    expect(getSelectionDataSpy).not.toHaveBeenCalled()
+    expect(component.tagSelectionModel.selectionSize()).toEqual(1)
+  })
+
+  it('should apply list selection data to document types menu when all filtered documents are selected', () => {
+    jest.spyOn(permissionsService, 'currentUserCan').mockReturnValue(true)
+    fixture.detectChanges()
+    jest
+      .spyOn(documentListViewService, 'allSelected', 'get')
+      .mockReturnValue(true)
+    documentListViewService.selectionData = selectionData
+    const getSelectionDataSpy = jest.spyOn(documentService, 'getSelectionData')
+
+    component.openDocumentTypeDropdown()
+
+    expect(getSelectionDataSpy).not.toHaveBeenCalled()
+    expect(component.documentTypeDocumentCounts).toEqual(
+      selectionData.selected_document_types
+    )
+  })
+
+  it('should apply list selection data to correspondents menu when all filtered documents are selected', () => {
+    jest.spyOn(permissionsService, 'currentUserCan').mockReturnValue(true)
+    fixture.detectChanges()
+    jest
+      .spyOn(documentListViewService, 'allSelected', 'get')
+      .mockReturnValue(true)
+    documentListViewService.selectionData = selectionData
+    const getSelectionDataSpy = jest.spyOn(documentService, 'getSelectionData')
+
+    component.openCorrespondentDropdown()
+
+    expect(getSelectionDataSpy).not.toHaveBeenCalled()
+    expect(component.correspondentDocumentCounts).toEqual(
+      selectionData.selected_correspondents
+    )
+  })
+
+  it('should apply list selection data to storage paths menu when all filtered documents are selected', () => {
+    jest.spyOn(permissionsService, 'currentUserCan').mockReturnValue(true)
+    fixture.detectChanges()
+    jest
+      .spyOn(documentListViewService, 'allSelected', 'get')
+      .mockReturnValue(true)
+    documentListViewService.selectionData = selectionData
+    const getSelectionDataSpy = jest.spyOn(documentService, 'getSelectionData')
+
+    component.openStoragePathDropdown()
+
+    expect(getSelectionDataSpy).not.toHaveBeenCalled()
+    expect(component.storagePathDocumentCounts).toEqual(
+      selectionData.selected_storage_paths
+    )
+  })
+
+  it('should apply list selection data to custom fields menu when all filtered documents are selected', () => {
+    jest.spyOn(permissionsService, 'currentUserCan').mockReturnValue(true)
+    fixture.detectChanges()
+    jest
+      .spyOn(documentListViewService, 'allSelected', 'get')
+      .mockReturnValue(true)
+    documentListViewService.selectionData = selectionData
+    const getSelectionDataSpy = jest.spyOn(documentService, 'getSelectionData')
+
+    component.openCustomFieldsDropdown()
+
+    expect(getSelectionDataSpy).not.toHaveBeenCalled()
+    expect(component.customFieldDocumentCounts).toEqual(
+      selectionData.selected_custom_fields
+    )
+  })
+
   it('should execute modify tags bulk operation', () => {
     jest.spyOn(permissionsService, 'currentUserCan').mockReturnValue(true)
     jest
@@ -300,13 +387,56 @@ describe('BulkEditorComponent', () => {
       parameters: { add_tags: [101], remove_tags: [] },
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
     ) // listAllFilteredIds
   })
 
+  it('should execute modify tags bulk operation for all filtered documents', () => {
+    jest.spyOn(permissionsService, 'currentUserCan').mockReturnValue(true)
+    jest
+      .spyOn(documentListViewService, 'documents', 'get')
+      .mockReturnValue([{ id: 3 }, { id: 4 }])
+    jest
+      .spyOn(documentListViewService, 'selected', 'get')
+      .mockReturnValue(new Set([3, 4]))
+    jest
+      .spyOn(documentListViewService, 'allSelected', 'get')
+      .mockReturnValue(true)
+    jest
+      .spyOn(documentListViewService, 'filterRules', 'get')
+      .mockReturnValue([{ rule_type: FILTER_TITLE, value: 'apple' }])
+    jest
+      .spyOn(documentListViewService, 'selectedCount', 'get')
+      .mockReturnValue(25)
+    jest
+      .spyOn(permissionsService, 'currentUserHasObjectPermissions')
+      .mockReturnValue(true)
+    component.showConfirmationDialogs = false
+    fixture.detectChanges()
+
+    component.setTags({
+      itemsToAdd: [{ id: 101 }],
+      itemsToRemove: [],
+    })
+
+    const req = httpTestingController.expectOne(
+      `${environment.apiBaseUrl}documents/bulk_edit/`
+    )
+    req.flush(true)
+    expect(req.request.body).toEqual({
+      all: true,
+      filters: { title__icontains: 'apple' },
+      method: 'modify_tags',
+      parameters: { add_tags: [101], remove_tags: [] },
+    })
+    httpTestingController.match(
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+    ) // list reload
+  })
+
   it('should execute modify tags bulk operation with confirmation dialog if enabled', () => {
     let modal: NgbModalRef
     modalService.activeInstances.subscribe((m) => (modal = m[0]))
@@ -332,7 +462,7 @@ describe('BulkEditorComponent', () => {
       .expectOne(`${environment.apiBaseUrl}documents/bulk_edit/`)
       .flush(true)
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -423,7 +553,7 @@ describe('BulkEditorComponent', () => {
       parameters: { correspondent: 101 },
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -455,7 +585,7 @@ describe('BulkEditorComponent', () => {
       .expectOne(`${environment.apiBaseUrl}documents/bulk_edit/`)
       .flush(true)
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -521,7 +651,7 @@ describe('BulkEditorComponent', () => {
       parameters: { document_type: 101 },
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -553,7 +683,7 @@ describe('BulkEditorComponent', () => {
       .expectOne(`${environment.apiBaseUrl}documents/bulk_edit/`)
       .flush(true)
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -619,7 +749,7 @@ describe('BulkEditorComponent', () => {
       parameters: { storage_path: 101 },
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -651,7 +781,7 @@ describe('BulkEditorComponent', () => {
       .expectOne(`${environment.apiBaseUrl}documents/bulk_edit/`)
       .flush(true)
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -717,7 +847,7 @@ describe('BulkEditorComponent', () => {
       parameters: { add_custom_fields: [101], remove_custom_fields: [102] },
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -749,7 +879,7 @@ describe('BulkEditorComponent', () => {
       .expectOne(`${environment.apiBaseUrl}documents/bulk_edit/`)
       .flush(true)
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -858,7 +988,7 @@ describe('BulkEditorComponent', () => {
       documents: [3, 4],
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -951,7 +1081,7 @@ describe('BulkEditorComponent', () => {
       documents: [3, 4],
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -986,7 +1116,7 @@ describe('BulkEditorComponent', () => {
       source_mode: 'latest_version',
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -1027,7 +1157,7 @@ describe('BulkEditorComponent', () => {
       metadata_document_id: 3,
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -1046,7 +1176,7 @@ describe('BulkEditorComponent', () => {
       delete_originals: true,
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -1067,7 +1197,7 @@ describe('BulkEditorComponent', () => {
       archive_fallback: true,
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -1089,22 +1219,39 @@ describe('BulkEditorComponent', () => {
     component.downloadForm.get('downloadFileTypeArchive').patchValue(true)
     fixture.detectChanges()
     let downloadSpy = jest.spyOn(documentService, 'bulkDownload')
+    downloadSpy.mockReturnValue(of(new Blob()))
     //archive
     component.downloadSelected()
-    expect(downloadSpy).toHaveBeenCalledWith([3, 4], 'archive', false)
+    expect(downloadSpy).toHaveBeenCalledWith(
+      { documents: [3, 4] },
+      'archive',
+      false
+    )
     //originals
     component.downloadForm.get('downloadFileTypeArchive').patchValue(false)
     component.downloadForm.get('downloadFileTypeOriginals').patchValue(true)
     component.downloadSelected()
-    expect(downloadSpy).toHaveBeenCalledWith([3, 4], 'originals', false)
+    expect(downloadSpy).toHaveBeenCalledWith(
+      { documents: [3, 4] },
+      'originals',
+      false
+    )
     //both
     component.downloadForm.get('downloadFileTypeArchive').patchValue(true)
     component.downloadSelected()
-    expect(downloadSpy).toHaveBeenCalledWith([3, 4], 'both', false)
+    expect(downloadSpy).toHaveBeenCalledWith(
+      { documents: [3, 4] },
+      'both',
+      false
+    )
     //formatting
     component.downloadForm.get('downloadUseFormatting').patchValue(true)
     component.downloadSelected()
-    expect(downloadSpy).toHaveBeenCalledWith([3, 4], 'both', true)
+    expect(downloadSpy).toHaveBeenCalledWith(
+      { documents: [3, 4] },
+      'both',
+      true
+    )
 
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/bulk_download/`
@@ -1153,7 +1300,7 @@ describe('BulkEditorComponent', () => {
       },
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -1450,6 +1597,7 @@ describe('BulkEditorComponent', () => {
 
     expect(modal.componentInstance.customFields.length).toEqual(2)
     expect(modal.componentInstance.fieldsToAddIds).toEqual([1, 2])
+    expect(modal.componentInstance.selection).toEqual({ documents: [3, 4] })
     expect(modal.componentInstance.documents).toEqual([3, 4])
 
     modal.componentInstance.failed.emit()
@@ -1460,7 +1608,7 @@ describe('BulkEditorComponent', () => {
     expect(toastServiceShowInfoSpy).toHaveBeenCalled()
     expect(listReloadSpy).toHaveBeenCalled()
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`

src-ui/src/app/components/document-list/bulk-editor/bulk-editor.component.ts

@@ -16,6 +16,7 @@ import { first, map, Observable, Subject, switchMap, takeUntil } from 'rxjs'
 import { ConfirmDialogComponent } from 'src/app/components/common/confirm-dialog/confirm-dialog.component'
 import { CustomField } from 'src/app/data/custom-field'
 import { MatchingModel } from 'src/app/data/matching-model'
+import { SelectionDataItem } from 'src/app/data/results'
 import { SETTINGS_KEYS } from 'src/app/data/ui-settings'
 import { IfPermissionsDirective } from 'src/app/directives/if-permissions.directive'
 import { DocumentListViewService } from 'src/app/services/document-list-view.service'
@@ -30,9 +31,9 @@ import { CustomFieldsService } from 'src/app/services/rest/custom-fields.service
 import { DocumentTypeService } from 'src/app/services/rest/document-type.service'
 import {
   DocumentBulkEditMethod,
+  DocumentSelectionQuery,
   DocumentService,
   MergeDocumentsRequest,
-  SelectionDataItem,
 } from 'src/app/services/rest/document.service'
 import { SavedViewService } from 'src/app/services/rest/saved-view.service'
 import { ShareLinkBundleService } from 'src/app/services/rest/share-link-bundle.service'
@@ -41,6 +42,7 @@ import { TagService } from 'src/app/services/rest/tag.service'
 import { SettingsService } from 'src/app/services/settings.service'
 import { ToastService } from 'src/app/services/toast.service'
 import { flattenTags } from 'src/app/utils/flatten-tags'
+import { queryParamsFromFilterRules } from 'src/app/utils/query-params'
 import { MergeConfirmDialogComponent } from '../../common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component'
 import { RotateConfirmDialogComponent } from '../../common/confirm-dialog/rotate-confirm-dialog/rotate-confirm-dialog.component'
 import { CorrespondentEditDialogComponent } from '../../common/edit-dialog/correspondent-edit-dialog/correspondent-edit-dialog.component'
@@ -261,17 +263,13 @@ export class BulkEditorComponent
     modal: NgbModalRef,
     method: DocumentBulkEditMethod,
     args: any,
-    overrideDocumentIDs?: number[]
+    overrideSelection?: DocumentSelectionQuery
   ) {
     if (modal) {
       modal.componentInstance.buttonsEnabled = false
     }
     this.documentService
-      .bulkEdit(
+      .bulkEdit(overrideSelection ?? this.getSelectionQuery(), method, args)
-        overrideDocumentIDs ?? Array.from(this.list.selected),
-        method,
-        args
-      )
       .pipe(first())
       .subscribe({
         next: () => this.handleOperationSuccess(modal),
@@ -329,7 +327,7 @@ export class BulkEditorComponent
   ) {
     let selectionData = new Map<number, ToggleableItemState>()
     items.forEach((i) => {
-      if (i.document_count == this.list.selected.size) {
+      if (i.document_count == this.list.selectedCount) {
         selectionData.set(i.id, ToggleableItemState.Selected)
       } else if (i.document_count > 0) {
         selectionData.set(i.id, ToggleableItemState.PartiallySelected)
@@ -338,7 +336,31 @@ export class BulkEditorComponent
     selectionModel.init(selectionData)
   }
 
+  private getSelectionQuery(): DocumentSelectionQuery {
+    if (this.list.allSelected) {
+      return {
+        all: true,
+        filters: queryParamsFromFilterRules(this.list.filterRules),
+      }
+    }
+
+    return {
+      documents: Array.from(this.list.selected),
+    }
+  }
+
+  private getSelectionSize(): number {
+    return this.list.selectedCount
+  }
+
   openTagsDropdown() {
+    if (this.list.allSelected) {
+      const selectionData = this.list.selectionData
+      this.tagDocumentCounts = selectionData?.selected_tags ?? []
+      this.applySelectionData(this.tagDocumentCounts, this.tagSelectionModel)
+      return
+    }
+
     this.documentService
       .getSelectionData(Array.from(this.list.selected))
       .pipe(first())
@@ -349,6 +371,17 @@ export class BulkEditorComponent
   }
 
   openDocumentTypeDropdown() {
+    if (this.list.allSelected) {
+      const selectionData = this.list.selectionData
+      this.documentTypeDocumentCounts =
+        selectionData?.selected_document_types ?? []
+      this.applySelectionData(
+        this.documentTypeDocumentCounts,
+        this.documentTypeSelectionModel
+      )
+      return
+    }
+
     this.documentService
       .getSelectionData(Array.from(this.list.selected))
       .pipe(first())
@@ -362,6 +395,17 @@ export class BulkEditorComponent
   }
 
   openCorrespondentDropdown() {
+    if (this.list.allSelected) {
+      const selectionData = this.list.selectionData
+      this.correspondentDocumentCounts =
+        selectionData?.selected_correspondents ?? []
+      this.applySelectionData(
+        this.correspondentDocumentCounts,
+        this.correspondentSelectionModel
+      )
+      return
+    }
+
     this.documentService
       .getSelectionData(Array.from(this.list.selected))
       .pipe(first())
@@ -375,6 +419,17 @@ export class BulkEditorComponent
   }
 
   openStoragePathDropdown() {
+    if (this.list.allSelected) {
+      const selectionData = this.list.selectionData
+      this.storagePathDocumentCounts =
+        selectionData?.selected_storage_paths ?? []
+      this.applySelectionData(
+        this.storagePathDocumentCounts,
+        this.storagePathsSelectionModel
+      )
+      return
+    }
+
     this.documentService
       .getSelectionData(Array.from(this.list.selected))
       .pipe(first())
@@ -388,6 +443,17 @@ export class BulkEditorComponent
   }
 
   openCustomFieldsDropdown() {
+    if (this.list.allSelected) {
+      const selectionData = this.list.selectionData
+      this.customFieldDocumentCounts =
+        selectionData?.selected_custom_fields ?? []
+      this.applySelectionData(
+        this.customFieldDocumentCounts,
+        this.customFieldsSelectionModel
+      )
+      return
+    }
+
     this.documentService
       .getSelectionData(Array.from(this.list.selected))
       .pipe(first())
@@ -437,33 +503,33 @@ export class BulkEditorComponent
         changedTags.itemsToRemove.length == 0
       ) {
         let tag = changedTags.itemsToAdd[0]
-        modal.componentInstance.message = $localize`This operation will add the tag "${tag.name}" to ${this.list.selected.size} selected document(s).`
+        modal.componentInstance.message = $localize`This operation will add the tag "${tag.name}" to ${this.getSelectionSize()} selected document(s).`
       } else if (
         changedTags.itemsToAdd.length > 1 &&
         changedTags.itemsToRemove.length == 0
       ) {
         modal.componentInstance.message = $localize`This operation will add the tags ${this._localizeList(
           changedTags.itemsToAdd
-        )} to ${this.list.selected.size} selected document(s).`
+        )} to ${this.getSelectionSize()} selected document(s).`
       } else if (
         changedTags.itemsToAdd.length == 0 &&
         changedTags.itemsToRemove.length == 1
       ) {
         let tag = changedTags.itemsToRemove[0]
-        modal.componentInstance.message = $localize`This operation will remove the tag "${tag.name}" from ${this.list.selected.size} selected document(s).`
+        modal.componentInstance.message = $localize`This operation will remove the tag "${tag.name}" from ${this.getSelectionSize()} selected document(s).`
       } else if (
         changedTags.itemsToAdd.length == 0 &&
         changedTags.itemsToRemove.length > 1
       ) {
         modal.componentInstance.message = $localize`This operation will remove the tags ${this._localizeList(
           changedTags.itemsToRemove
-        )} from ${this.list.selected.size} selected document(s).`
+        )} from ${this.getSelectionSize()} selected document(s).`
       } else {
         modal.componentInstance.message = $localize`This operation will add the tags ${this._localizeList(
           changedTags.itemsToAdd
         )} and remove the tags ${this._localizeList(
           changedTags.itemsToRemove
-        )} on ${this.list.selected.size} selected document(s).`
+        )} on ${this.getSelectionSize()} selected document(s).`
       }
 
       modal.componentInstance.btnClass = 'btn-warning'
@@ -502,9 +568,9 @@ export class BulkEditorComponent
       })
       modal.componentInstance.title = $localize`Confirm correspondent assignment`
       if (correspondent) {
-        modal.componentInstance.message = $localize`This operation will assign the correspondent "${correspondent.name}" to ${this.list.selected.size} selected document(s).`
+        modal.componentInstance.message = $localize`This operation will assign the correspondent "${correspondent.name}" to ${this.getSelectionSize()} selected document(s).`
       } else {
-        modal.componentInstance.message = $localize`This operation will remove the correspondent from ${this.list.selected.size} selected document(s).`
+        modal.componentInstance.message = $localize`This operation will remove the correspondent from ${this.getSelectionSize()} selected document(s).`
       }
       modal.componentInstance.btnClass = 'btn-warning'
       modal.componentInstance.btnCaption = $localize`Confirm`
@@ -540,9 +606,9 @@ export class BulkEditorComponent
       })
       modal.componentInstance.title = $localize`Confirm document type assignment`
       if (documentType) {
-        modal.componentInstance.message = $localize`This operation will assign the document type "${documentType.name}" to ${this.list.selected.size} selected document(s).`
+        modal.componentInstance.message = $localize`This operation will assign the document type "${documentType.name}" to ${this.getSelectionSize()} selected document(s).`
       } else {
-        modal.componentInstance.message = $localize`This operation will remove the document type from ${this.list.selected.size} selected document(s).`
+        modal.componentInstance.message = $localize`This operation will remove the document type from ${this.getSelectionSize()} selected document(s).`
       }
       modal.componentInstance.btnClass = 'btn-warning'
       modal.componentInstance.btnCaption = $localize`Confirm`
@@ -578,9 +644,9 @@ export class BulkEditorComponent
       })
       modal.componentInstance.title = $localize`Confirm storage path assignment`
       if (storagePath) {
-        modal.componentInstance.message = $localize`This operation will assign the storage path "${storagePath.name}" to ${this.list.selected.size} selected document(s).`
+        modal.componentInstance.message = $localize`This operation will assign the storage path "${storagePath.name}" to ${this.getSelectionSize()} selected document(s).`
       } else {
-        modal.componentInstance.message = $localize`This operation will remove the storage path from ${this.list.selected.size} selected document(s).`
+        modal.componentInstance.message = $localize`This operation will remove the storage path from ${this.getSelectionSize()} selected document(s).`
       }
       modal.componentInstance.btnClass = 'btn-warning'
       modal.componentInstance.btnCaption = $localize`Confirm`
@@ -615,33 +681,33 @@ export class BulkEditorComponent
         changedCustomFields.itemsToRemove.length == 0
       ) {
         let customField = changedCustomFields.itemsToAdd[0]
-        modal.componentInstance.message = $localize`This operation will assign the custom field "${customField.name}" to ${this.list.selected.size} selected document(s).`
+        modal.componentInstance.message = $localize`This operation will assign the custom field "${customField.name}" to ${this.getSelectionSize()} selected document(s).`
       } else if (
         changedCustomFields.itemsToAdd.length > 1 &&
         changedCustomFields.itemsToRemove.length == 0
       ) {
         modal.componentInstance.message = $localize`This operation will assign the custom fields ${this._localizeList(
           changedCustomFields.itemsToAdd
-        )} to ${this.list.selected.size} selected document(s).`
+        )} to ${this.getSelectionSize()} selected document(s).`
       } else if (
         changedCustomFields.itemsToAdd.length == 0 &&
         changedCustomFields.itemsToRemove.length == 1
       ) {
         let customField = changedCustomFields.itemsToRemove[0]
-        modal.componentInstance.message = $localize`This operation will remove the custom field "${customField.name}" from ${this.list.selected.size} selected document(s).`
+        modal.componentInstance.message = $localize`This operation will remove the custom field "${customField.name}" from ${this.getSelectionSize()} selected document(s).`
       } else if (
         changedCustomFields.itemsToAdd.length == 0 &&
         changedCustomFields.itemsToRemove.length > 1
       ) {
         modal.componentInstance.message = $localize`This operation will remove the custom fields ${this._localizeList(
           changedCustomFields.itemsToRemove
-        )} from ${this.list.selected.size} selected document(s).`
+        )} from ${this.getSelectionSize()} selected document(s).`
       } else {
         modal.componentInstance.message = $localize`This operation will assign the custom fields ${this._localizeList(
           changedCustomFields.itemsToAdd
         )} and remove the custom fields ${this._localizeList(
           changedCustomFields.itemsToRemove
-        )} on ${this.list.selected.size} selected document(s).`
+        )} on ${this.getSelectionSize()} selected document(s).`
       }
 
       modal.componentInstance.btnClass = 'btn-warning'
@@ -779,7 +845,7 @@ export class BulkEditorComponent
         backdrop: 'static',
       })
       modal.componentInstance.title = $localize`Confirm`
-      modal.componentInstance.messageBold = $localize`Move ${this.list.selected.size} selected document(s) to the trash?`
+      modal.componentInstance.messageBold = $localize`Move ${this.getSelectionSize()} selected document(s) to the trash?`
       modal.componentInstance.message = $localize`Documents can be restored prior to permanent deletion.`
       modal.componentInstance.btnClass = 'btn-danger'
       modal.componentInstance.btnCaption = $localize`Move to trash`
@@ -789,13 +855,13 @@ export class BulkEditorComponent
           modal.componentInstance.buttonsEnabled = false
           this.executeDocumentAction(
             modal,
-            this.documentService.deleteDocuments(Array.from(this.list.selected))
+            this.documentService.deleteDocuments(this.getSelectionQuery())
           )
         })
     } else {
       this.executeDocumentAction(
         null,
-        this.documentService.deleteDocuments(Array.from(this.list.selected))
+        this.documentService.deleteDocuments(this.getSelectionQuery())
       )
     }
   }
@@ -811,7 +877,7 @@ export class BulkEditorComponent
           : 'originals'
     this.documentService
       .bulkDownload(
-        Array.from(this.list.selected),
+        this.getSelectionQuery(),
         downloadFileType,
         this.downloadForm.get('downloadUseFormatting').value
       )
@@ -827,7 +893,7 @@ export class BulkEditorComponent
       backdrop: 'static',
     })
     modal.componentInstance.title = $localize`Reprocess confirm`
-    modal.componentInstance.messageBold = $localize`This operation will permanently recreate the archive files for ${this.list.selected.size} selected document(s).`
+    modal.componentInstance.messageBold = $localize`This operation will permanently recreate the archive files for ${this.getSelectionSize()} selected document(s).`
     modal.componentInstance.message = $localize`The archive files will be re-generated with the current settings.`
     modal.componentInstance.btnClass = 'btn-danger'
     modal.componentInstance.btnCaption = $localize`Proceed`
@@ -837,9 +903,7 @@ export class BulkEditorComponent
         modal.componentInstance.buttonsEnabled = false
         this.executeDocumentAction(
           modal,
-          this.documentService.reprocessDocuments(
+          this.documentService.reprocessDocuments(this.getSelectionQuery())
-            Array.from(this.list.selected)
-          )
         )
       })
   }
@@ -866,7 +930,7 @@ export class BulkEditorComponent
     })
     const rotateDialog = modal.componentInstance as RotateConfirmDialogComponent
     rotateDialog.title = $localize`Rotate confirm`
-    rotateDialog.messageBold = $localize`This operation will add rotated versions of the ${this.list.selected.size} document(s).`
+    rotateDialog.messageBold = $localize`This operation will add rotated versions of the ${this.getSelectionSize()} document(s).`
     rotateDialog.btnClass = 'btn-danger'
     rotateDialog.btnCaption = $localize`Proceed`
     rotateDialog.documentID = Array.from(this.list.selected)[0]
@@ -877,7 +941,7 @@ export class BulkEditorComponent
         this.executeDocumentAction(
           modal,
           this.documentService.rotateDocuments(
-            Array.from(this.list.selected),
+            this.getSelectionQuery(),
             rotateDialog.degrees
           )
         )
@@ -890,7 +954,7 @@ export class BulkEditorComponent
     })
     const mergeDialog = modal.componentInstance as MergeConfirmDialogComponent
     mergeDialog.title = $localize`Merge confirm`
-    mergeDialog.messageBold = $localize`This operation will merge ${this.list.selected.size} selected documents into a new document.`
+    mergeDialog.messageBold = $localize`This operation will merge ${this.getSelectionSize()} selected documents into a new document.`
     mergeDialog.btnCaption = $localize`Proceed`
     mergeDialog.documentIDs = Array.from(this.list.selected)
     mergeDialog.confirmClicked
@@ -935,7 +999,7 @@ export class BulkEditorComponent
       (item) => item.id
     )
 
-    dialog.documents = Array.from(this.list.selected)
+    dialog.selection = this.getSelectionQuery()
     dialog.succeeded.subscribe((result) => {
       this.toastService.showInfo($localize`Custom fields updated.`)
       this.list.reload()

src-ui/src/app/components/document-list/bulk-editor/custom-fields-bulk-edit-dialog/custom-fields-bulk-edit-dialog.component.spec.ts

@@ -48,7 +48,7 @@ describe('CustomFieldsBulkEditDialogComponent', () => {
       .mockReturnValue(of('Success'))
     const successSpy = jest.spyOn(component.succeeded, 'emit')
 
-    component.documents = [1, 2]
+    component.selection = [1, 2]
     component.fieldsToAddIds = [1]
     component.form.controls['1'].setValue('Value 1')
     component.save()
@@ -63,7 +63,7 @@ describe('CustomFieldsBulkEditDialogComponent', () => {
       .mockReturnValue(throwError(new Error('Error')))
     const failSpy = jest.spyOn(component.failed, 'emit')
 
-    component.documents = [1, 2]
+    component.selection = [1, 2]
     component.fieldsToAddIds = [1]
     component.form.controls['1'].setValue('Value 1')
     component.save()

src-ui/src/app/components/document-list/bulk-editor/custom-fields-bulk-edit-dialog/custom-fields-bulk-edit-dialog.component.ts

@@ -17,7 +17,10 @@ import { SelectComponent } from 'src/app/components/common/input/select/select.c
 import { TextComponent } from 'src/app/components/common/input/text/text.component'
 import { UrlComponent } from 'src/app/components/common/input/url/url.component'
 import { CustomField, CustomFieldDataType } from 'src/app/data/custom-field'
-import { DocumentService } from 'src/app/services/rest/document.service'
+import {
+  DocumentSelectionQuery,
+  DocumentService,
+} from 'src/app/services/rest/document.service'
 import { TextAreaComponent } from '../../../common/input/textarea/textarea.component'
 
 @Component({
@@ -76,7 +79,11 @@ export class CustomFieldsBulkEditDialogComponent {
 
   public form: FormGroup = new FormGroup({})
 
-  public documents: number[] = []
+  public selection: DocumentSelectionQuery = { documents: [] }
+
+  public get documents(): number[] {
+    return this.selection.documents
+  }
 
   initForm() {
     Object.keys(this.form.controls).forEach((key) => {
@@ -91,7 +98,7 @@ export class CustomFieldsBulkEditDialogComponent {
 
   public save() {
     this.documentService
-      .bulkEdit(this.documents, 'modify_custom_fields', {
+      .bulkEdit(this.selection, 'modify_custom_fields', {
         add_custom_fields: this.form.value,
         remove_custom_fields: this.fieldsToRemoveIds,
       })

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

@@ -2,8 +2,8 @@
   <div ngbDropdown class="btn-group flex-fill d-sm-none">
     <button class="btn btn-sm btn-outline-primary" id="dropdownSelectMobile" ngbDropdownToggle>
       <i-bs name="text-indent-left"></i-bs><div class="d-none d-sm-inline ms-1"><ng-container i18n>Select</ng-container></div>
-      @if (list.selected.size > 0) {
+      @if (list.hasSelection) {
-        <pngx-clearable-badge [selected]="list.selected.size > 0" [number]="list.selected.size" (cleared)="list.selectNone()"></pngx-clearable-badge><span class="visually-hidden">selected</span>
+        <pngx-clearable-badge [selected]="list.hasSelection" [number]="list.selectedCount" (cleared)="list.selectNone()"></pngx-clearable-badge><span class="visually-hidden">selected</span>
       }
     </button>
     <div ngbDropdownMenu aria-labelledby="dropdownSelectMobile" class="shadow">
@@ -17,7 +17,7 @@
       <span class="input-group-text border-0" i18n>Select:</span>
     </div>
     <div class="btn-group btn-group-sm flex-nowrap">
-      @if (list.selected.size > 0) {
+      @if (list.hasSelection) {
         <button class="btn btn-sm btn-outline-secondary" (click)="list.selectNone()">
           <i-bs name="slash-circle" class="me-1"></i-bs><ng-container i18n>None</ng-container>
         </button>
@@ -127,11 +127,11 @@
         <div class="spinner-border spinner-border-sm me-2" role="status"></div>
         <ng-container i18n>Loading...</ng-container>
       }
-      @if (list.selected.size > 0) {
+      @if (list.hasSelection) {
-        <span i18n>{list.collectionSize, plural, =1 {Selected {{list.selected.size}} of one document} other {Selected {{list.selected.size}} of {{list.collectionSize || 0}} documents}}</span>
+        <span i18n>{list.collectionSize, plural, =1 {Selected {{list.selectedCount}} of one document} other {Selected {{list.selectedCount}} of {{list.collectionSize || 0}} documents}}</span>
       }
       @if (!list.isReloading) {
-        @if (list.selected.size === 0) {
+        @if (!list.hasSelection) {
           <span i18n>{list.collectionSize, plural, =1 {One document} other {{{list.collectionSize || 0}} documents}}</span>
           }&nbsp;@if (isFiltered) {
             &nbsp;<span i18n>(filtered)</span>
@@ -142,7 +142,7 @@
           <i-bs width="1em" height="1em" name="x"></i-bs><small i18n>Reset filters</small>
         </button>
       }
-      @if (!list.isReloading && list.selected.size > 0) {
+      @if (!list.isReloading && list.hasSelection) {
         <button class="btn btn-link py-0" (click)="list.selectNone()">
           <i-bs width="1em" height="1em" name="slash-circle" class="me-1"></i-bs><small i18n>Clear selection</small>
         </button>

src-ui/src/app/components/document-list/document-list.component.spec.ts

@@ -388,8 +388,8 @@ describe('DocumentListComponent', () => {
   it('should support select all, none, page & range', () => {
     jest.spyOn(documentListService, 'documents', 'get').mockReturnValue(docs)
     jest
-      .spyOn(documentService, 'listAllFilteredIds')
+      .spyOn(documentListService, 'collectionSize', 'get')
-      .mockReturnValue(of(docs.map((d) => d.id)))
+      .mockReturnValue(docs.length)
     fixture.detectChanges()
     expect(documentListService.selected.size).toEqual(0)
     const docCards = fixture.debugElement.queryAll(
@@ -403,7 +403,8 @@ describe('DocumentListComponent', () => {
     displayModeButtons[2].triggerEventHandler('click')
     expect(selectAllSpy).toHaveBeenCalled()
     fixture.detectChanges()
-    expect(documentListService.selected.size).toEqual(3)
+    expect(documentListService.allSelected).toBeTruthy()
+    expect(documentListService.selectedCount).toEqual(3)
     docCards.forEach((card) => {
       expect(card.context.selected).toBeTruthy()
     })

src-ui/src/app/components/document-list/document-list.component.ts

@@ -240,7 +240,7 @@ export class DocumentListComponent
   }
 
   get isBulkEditing(): boolean {
-    return this.list.selected.size > 0
+    return this.list.hasSelection
   }
 
   toggleDisplayField(field: DisplayField) {
@@ -327,7 +327,7 @@ export class DocumentListComponent
       })
       .pipe(takeUntil(this.unsubscribeNotifier))
       .subscribe(() => {
-        if (this.list.selected.size > 0) {
+        if (this.list.hasSelection) {
           this.list.selectNone()
         } else if (this.isFiltered) {
           this.resetFilters()
@@ -356,7 +356,7 @@ export class DocumentListComponent
       .pipe(takeUntil(this.unsubscribeNotifier))
       .subscribe(() => {
         if (this.list.documents.length > 0) {
-          if (this.list.selected.size > 0) {
+          if (this.list.hasSelection) {
             this.openDocumentDetail(Array.from(this.list.selected)[0])
           } else {
             this.openDocumentDetail(this.list.documents[0])

src-ui/src/app/components/document-list/filter-editor/filter-editor.component.ts

@@ -76,6 +76,7 @@ import {
   FILTER_TITLE_CONTENT,
   NEGATIVE_NULL_FILTER_VALUE,
 } from 'src/app/data/filter-rule-type'
+import { SelectionData, SelectionDataItem } from 'src/app/data/results'
 import {
   PermissionAction,
   PermissionType,
@@ -84,11 +85,7 @@ import {
 import { CorrespondentService } from 'src/app/services/rest/correspondent.service'
 import { CustomFieldsService } from 'src/app/services/rest/custom-fields.service'
 import { DocumentTypeService } from 'src/app/services/rest/document-type.service'
-import {
+import { DocumentService } from 'src/app/services/rest/document.service'
-  DocumentService,
-  SelectionData,
-  SelectionDataItem,
-} from 'src/app/services/rest/document.service'
 import { SearchService } from 'src/app/services/rest/search.service'
 import { StoragePathService } from 'src/app/services/rest/storage-path.service'
 import { TagService } from 'src/app/services/rest/tag.service'

src-ui/src/app/components/manage/document-attributes/document-attributes.component.html

@@ -9,8 +9,8 @@
     <div ngbDropdown class="btn-group flex-fill d-sm-none">
       <button class="btn btn-sm btn-outline-primary" id="dropdownSelectMobile" ngbDropdownToggle>
         <i-bs name="text-indent-left"></i-bs><div class="d-none d-sm-inline ms-1"><ng-container i18n>Select</ng-container></div>
-        @if (activeManagementList.selectedObjects.size > 0) {
+        @if (activeManagementList.hasSelection) {
-          <pngx-clearable-badge [selected]="activeManagementList.selectedObjects.size > 0" [number]="activeManagementList.selectedObjects.size" (cleared)="activeManagementList.selectNone()"></pngx-clearable-badge><span class="visually-hidden">selected</span>
+          <pngx-clearable-badge [selected]="activeManagementList.hasSelection" [number]="activeManagementList.selectedCount" (cleared)="activeManagementList.selectNone()"></pngx-clearable-badge><span class="visually-hidden">selected</span>
         }
       </button>
       <div ngbDropdownMenu aria-labelledby="dropdownSelectMobile" class="shadow">
@@ -25,7 +25,7 @@
         <span class="input-group-text border-0" i18n>Select:</span>
       </div>
       <div class="btn-group btn-group-sm flex-nowrap">
-        @if (activeManagementList.selectedObjects.size > 0) {
+        @if (activeManagementList.hasSelection) {
           <button class="btn btn-sm btn-outline-secondary" (click)="activeManagementList.selectNone()">
             <i-bs name="slash-circle" class="me-1"></i-bs><ng-container i18n>None</ng-container>
           </button>
@@ -40,11 +40,11 @@
     </div>
 
     <button type="button" class="btn btn-sm btn-outline-primary" (click)="activeManagementList.setPermissions()"
-      [disabled]="!activeManagementList.userCanBulkEdit(PermissionAction.Change) || activeManagementList.selectedObjects.size === 0">
+      [disabled]="!activeManagementList.userCanBulkEdit(PermissionAction.Change) || !activeManagementList.hasSelection">
       <i-bs name="person-fill-lock" class="me-1"></i-bs><ng-container i18n>Permissions</ng-container>
     </button>
     <button type="button" class="btn btn-sm btn-outline-danger" (click)="activeManagementList.delete()"
-      [disabled]="!activeManagementList.userCanBulkEdit(PermissionAction.Delete) || activeManagementList.selectedObjects.size === 0">
+      [disabled]="!activeManagementList.userCanBulkEdit(PermissionAction.Delete) || !activeManagementList.hasSelection">
       <i-bs name="trash" class="me-1"></i-bs><ng-container i18n>Delete</ng-container>
     </button>
     <button type="button" class="btn btn-sm btn-outline-primary ms-md-5" (click)="activeManagementList.openCreateDialog()"

src-ui/src/app/components/manage/document-attributes/management-list/management-list.component.html

@@ -65,8 +65,8 @@
     @if (displayCollectionSize > 0) {
       <div>
         <ng-container i18n>{displayCollectionSize, plural, =1 {One {{typeName}}} other {{{displayCollectionSize || 0}} total {{typeNamePlural}}}}</ng-container>
-        @if (selectedObjects.size > 0) {
+        @if (hasSelection) {
-          &nbsp;({{selectedObjects.size}} selected)
+          &nbsp;({{selectedCount}} selected)
         }
       </div>
     }

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

@@ -117,7 +117,6 @@ describe('ManagementListComponent', () => {
             : tags
           return of({
             count: results.length,
-            all: results.map((o) => o.id),
             results,
           })
         }
@@ -231,11 +230,11 @@ describe('ManagementListComponent', () => {
     expect(reloadSpy).toHaveBeenCalled()
   })
 
-  it('should use API count for pagination and all ids for displayed total', fakeAsync(() => {
+  it('should use API count for pagination and nested ids for displayed total', fakeAsync(() => {
     jest.spyOn(tagService, 'listFiltered').mockReturnValueOnce(
       of({
         count: 1,
-        all: [1, 2, 3],
+        display_count: 3,
         results: tags.slice(0, 1),
       })
     )
@@ -315,13 +314,17 @@ describe('ManagementListComponent', () => {
     expect(component.togggleAll).toBe(false)
   })
 
-  it('selectAll should use all IDs when collection size exists', () => {
+  it('selectAll should activate all-selection mode', () => {
-    ;(component as any).allIDs = [1, 2, 3, 4]
+    ;(tagService.listFiltered as jest.Mock).mockClear()
-    component.collectionSize = 4
+    component.collectionSize = tags.length
 
     component.selectAll()
 
-    expect(component.selectedObjects).toEqual(new Set([1, 2, 3, 4]))
+    expect(tagService.listFiltered).not.toHaveBeenCalled()
+    expect(component.selectedObjects).toEqual(new Set(tags.map((t) => t.id)))
+    expect((component as any).allSelectionActive).toBe(true)
+    expect(component.hasSelection).toBe(true)
+    expect(component.selectedCount).toBe(tags.length)
     expect(component.togggleAll).toBe(true)
   })
 
@@ -395,6 +398,33 @@ describe('ManagementListComponent', () => {
     expect(successToastSpy).toHaveBeenCalled()
   })
 
+  it('should support bulk edit permissions for all filtered items', () => {
+    const bulkEditPermsSpy = jest
+      .spyOn(tagService, 'bulk_edit_objects')
+      .mockReturnValue(of('OK'))
+    component.selectAll()
+
+    let modal: NgbModalRef
+    modalService.activeInstances.subscribe((m) => (modal = m[m.length - 1]))
+    fixture.detectChanges()
+    component.setPermissions()
+    expect(modal).not.toBeUndefined()
+
+    modal.componentInstance.confirmClicked.emit({
+      permissions: {},
+      merge: true,
+    })
+
+    expect(bulkEditPermsSpy).toHaveBeenCalledWith(
+      [],
+      BulkEditObjectOperation.SetPermissions,
+      {},
+      true,
+      true,
+      { is_root: true }
+    )
+  })
+
   it('should support bulk delete objects', () => {
     const bulkEditSpy = jest.spyOn(tagService, 'bulk_edit_objects')
     component.toggleSelected(tags[0])
@@ -415,7 +445,11 @@ describe('ManagementListComponent', () => {
     modal.componentInstance.confirmClicked.emit(null)
     expect(bulkEditSpy).toHaveBeenCalledWith(
       Array.from(selected),
-      BulkEditObjectOperation.Delete
+      BulkEditObjectOperation.Delete,
+      null,
+      null,
+      false,
+      null
     )
     expect(errorToastSpy).toHaveBeenCalled()
 
@@ -426,6 +460,29 @@ describe('ManagementListComponent', () => {
     expect(successToastSpy).toHaveBeenCalled()
   })
 
+  it('should support bulk delete for all filtered items', () => {
+    const bulkEditSpy = jest
+      .spyOn(tagService, 'bulk_edit_objects')
+      .mockReturnValue(of('OK'))
+
+    component.selectAll()
+    let modal: NgbModalRef
+    modalService.activeInstances.subscribe((m) => (modal = m[m.length - 1]))
+    fixture.detectChanges()
+    component.delete()
+    expect(modal).not.toBeUndefined()
+
+    modal.componentInstance.confirmClicked.emit(null)
+    expect(bulkEditSpy).toHaveBeenCalledWith(
+      [],
+      BulkEditObjectOperation.Delete,
+      null,
+      null,
+      true,
+      { is_root: true }
+    )
+  })
+
   it('should disallow bulk permissions or delete objects if no global perms', () => {
     jest.spyOn(permissionsService, 'currentUserCan').mockReturnValue(false)
     expect(component.userCanBulkEdit(PermissionAction.Delete)).toBeFalsy()

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

@@ -90,7 +90,8 @@ export abstract class ManagementListComponent<T extends MatchingModel>
 
   public data: T[] = []
   private unfilteredData: T[] = []
-  private allIDs: number[] = []
+  private currentExtraParams: { [key: string]: any } = null
+  private allSelectionActive = false
 
   public page = 1
 
@@ -107,6 +108,16 @@ export abstract class ManagementListComponent<T extends MatchingModel>
   public selectedObjects: Set<number> = new Set()
   public togggleAll: boolean = false
 
+  public get hasSelection(): boolean {
+    return this.selectedObjects.size > 0 || this.allSelectionActive
+  }
+
+  public get selectedCount(): number {
+    return this.allSelectionActive
+      ? this.displayCollectionSize
+      : this.selectedObjects.size
+  }
+
   ngOnInit(): void {
     this.reloadData()
 
@@ -150,11 +161,11 @@ export abstract class ManagementListComponent<T extends MatchingModel>
   }
 
   protected getCollectionSize(results: Results<T>): number {
-    return results.all?.length ?? results.count
+    return results.count
   }
 
   protected getDisplayCollectionSize(results: Results<T>): number {
-    return this.getCollectionSize(results)
+    return results.display_count ?? this.getCollectionSize(results)
   }
 
   getDocumentCount(object: MatchingModel): number {
@@ -171,6 +182,7 @@ export abstract class ManagementListComponent<T extends MatchingModel>
 
   reloadData(extraParams: { [key: string]: any } = null) {
     this.loading = true
+    this.currentExtraParams = extraParams
     this.clearSelection()
     this.service
       .listFiltered(
@@ -189,7 +201,6 @@ export abstract class ManagementListComponent<T extends MatchingModel>
           this.data = this.filterData(c.results)
           this.collectionSize = this.getCollectionSize(c)
           this.displayCollectionSize = this.getDisplayCollectionSize(c)
-          this.allIDs = c.all
         }),
         delay(100)
       )
@@ -346,7 +357,16 @@ export abstract class ManagementListComponent<T extends MatchingModel>
     return objects.map((o) => o.id)
   }
 
+  private getBulkEditFilters(): { [key: string]: any } {
+    const filters = { ...this.currentExtraParams }
+    if (this._nameFilter?.length) {
+      filters['name__icontains'] = this._nameFilter
+    }
+    return filters
+  }
+
   clearSelection() {
+    this.allSelectionActive = false
     this.togggleAll = false
     this.selectedObjects.clear()
   }
@@ -356,6 +376,7 @@ export abstract class ManagementListComponent<T extends MatchingModel>
   }
 
   selectPage() {
+    this.allSelectionActive = false
     this.selectedObjects = new Set(this.getSelectableIDs(this.data))
     this.togggleAll = this.areAllPageItemsSelected()
   }
@@ -365,11 +386,16 @@ export abstract class ManagementListComponent<T extends MatchingModel>
       this.clearSelection()
       return
     }
-    this.selectedObjects = new Set(this.allIDs)
+
+    this.allSelectionActive = true
+    this.selectedObjects = new Set(this.getSelectableIDs(this.data))
     this.togggleAll = this.areAllPageItemsSelected()
   }
 
   toggleSelected(object) {
+    if (this.allSelectionActive) {
+      this.allSelectionActive = false
+    }
     this.selectedObjects.has(object.id)
       ? this.selectedObjects.delete(object.id)
       : this.selectedObjects.add(object.id)
@@ -377,6 +403,9 @@ export abstract class ManagementListComponent<T extends MatchingModel>
   }
 
   protected areAllPageItemsSelected(): boolean {
+    if (this.allSelectionActive) {
+      return this.data.length > 0
+    }
     const ids = this.getSelectableIDs(this.data)
     return ids.length > 0 && ids.every((id) => this.selectedObjects.has(id))
   }
@@ -390,10 +419,12 @@ export abstract class ManagementListComponent<T extends MatchingModel>
         modal.componentInstance.buttonsEnabled = false
         this.service
           .bulk_edit_objects(
-            Array.from(this.selectedObjects),
+            this.allSelectionActive ? [] : Array.from(this.selectedObjects),
             BulkEditObjectOperation.SetPermissions,
             permissions,
-            merge
+            merge,
+            this.allSelectionActive,
+            this.allSelectionActive ? this.getBulkEditFilters() : null
           )
           .subscribe({
             next: () => {
@@ -428,8 +459,12 @@ export abstract class ManagementListComponent<T extends MatchingModel>
       modal.componentInstance.buttonsEnabled = false
       this.service
         .bulk_edit_objects(
-          Array.from(this.selectedObjects),
+          this.allSelectionActive ? [] : Array.from(this.selectedObjects),
-          BulkEditObjectOperation.Delete
+          BulkEditObjectOperation.Delete,
+          null,
+          null,
+          this.allSelectionActive,
+          this.allSelectionActive ? this.getBulkEditFilters() : null
         )
         .subscribe({
           next: () => {

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

@@ -41,7 +41,6 @@ describe('TagListComponent', () => {
     listFilteredSpy = jest.spyOn(tagService, 'listFiltered').mockReturnValue(
       of({
         count: 3,
-        all: [1, 2, 3],
         results: [
           {
             id: 1,

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

@@ -9,7 +9,6 @@ import {
 import { NgxBootstrapIconsModule } from 'ngx-bootstrap-icons'
 import { TagEditDialogComponent } from 'src/app/components/common/edit-dialog/tag-edit-dialog/tag-edit-dialog.component'
 import { FILTER_HAS_TAGS_ALL } from 'src/app/data/filter-rule-type'
-import { Results } from 'src/app/data/results'
 import { Tag } from 'src/app/data/tag'
 import { IfPermissionsDirective } from 'src/app/directives/if-permissions.directive'
 import { SortableDirective } from 'src/app/directives/sortable.directive'
@@ -77,16 +76,6 @@ export class TagListComponent extends ManagementListComponent<Tag> {
     return data.filter((tag) => !tag.parent || !availableIds.has(tag.parent))
   }
 
-  protected override getCollectionSize(results: Results<Tag>): number {
-    // Tag list pages are requested with is_root=true (when unfiltered), so
-    // pagination must follow root count even though `all` includes descendants
-    return results.count
-  }
-
-  protected override getDisplayCollectionSize(results: Results<Tag>): number {
-    return super.getCollectionSize(results)
-  }
-
   protected override getSelectableIDs(tags: Tag[]): number[] {
     const ids: number[] = []
     for (const tag of tags.filter(Boolean)) {

src-ui/src/app/data/results.ts

@@ -1,7 +1,26 @@
+import { Document } from './document'
+
 export interface Results<T> {
   count: number
 
-  results: T[]
+  display_count?: number
 
-  all: number[]
+  results: T[]
+}
+
+export interface SelectionDataItem {
+  id: number
+  document_count: number
+}
+
+export interface SelectionData {
+  selected_storage_paths: SelectionDataItem[]
+  selected_correspondents: SelectionDataItem[]
+  selected_tags: SelectionDataItem[]
+  selected_document_types: SelectionDataItem[]
+  selected_custom_fields: SelectionDataItem[]
+}
+
+export interface DocumentResults extends Results<Document> {
+  selection_data?: SelectionData
 }

src-ui/src/app/services/document-list-view.service.spec.ts

@@ -127,13 +127,10 @@ describe('DocumentListViewService', () => {
     expect(documentListViewService.currentPage).toEqual(1)
     documentListViewService.reload()
     const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     req.flush(full_results)
-    httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/selection_data/`
-    )
     expect(req.request.method).toEqual('GET')
     expect(documentListViewService.isReloading).toBeFalsy()
     expect(documentListViewService.activeSavedViewId).toBeNull()
@@ -145,12 +142,12 @@ describe('DocumentListViewService', () => {
   it('should handle error on page request out of range', () => {
     documentListViewService.currentPage = 50
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=50&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=50&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     req.flush([], { status: 404, statusText: 'Unexpected error' })
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     expect(documentListViewService.currentPage).toEqual(1)
@@ -167,7 +164,7 @@ describe('DocumentListViewService', () => {
     ]
     documentListViewService.setFilterRules(filterRulesAny)
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&tags__id__in=${tags__id__in}`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__in=${tags__id__in}`
     )
     expect(req.request.method).toEqual('GET')
     req.flush(
@@ -175,13 +172,13 @@ describe('DocumentListViewService', () => {
       { status: 404, statusText: 'Unexpected error' }
     )
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     // reset the list
     documentListViewService.setFilterRules([])
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
   })
 
@@ -189,7 +186,7 @@ describe('DocumentListViewService', () => {
     documentListViewService.currentPage = 1
     documentListViewService.sortField = 'custom_field_999'
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-custom_field_999&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-custom_field_999&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     req.flush(
@@ -198,7 +195,7 @@ describe('DocumentListViewService', () => {
     )
     // resets itself
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
   })
 
@@ -213,7 +210,7 @@ describe('DocumentListViewService', () => {
     ]
     documentListViewService.setFilterRules(filterRulesAny)
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&tags__id__in=${tags__id__in}`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__in=${tags__id__in}`
     )
     expect(req.request.method).toEqual('GET')
     req.flush('Generic error', { status: 404, statusText: 'Unexpected error' })
@@ -221,7 +218,7 @@ describe('DocumentListViewService', () => {
     // reset the list
     documentListViewService.setFilterRules([])
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
   })
 
@@ -230,7 +227,7 @@ describe('DocumentListViewService', () => {
     expect(documentListViewService.sortReverse).toBeTruthy()
     documentListViewService.setSort('added', false)
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=added&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=added&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     expect(documentListViewService.sortField).toEqual('added')
@@ -238,12 +235,12 @@ describe('DocumentListViewService', () => {
 
     documentListViewService.sortField = 'created'
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=created&truncate_content=true&include_selection_data=true`
     )
     expect(documentListViewService.sortField).toEqual('created')
     documentListViewService.sortReverse = true
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     expect(documentListViewService.sortReverse).toBeTruthy()
@@ -286,7 +283,7 @@ describe('DocumentListViewService', () => {
     const req = httpTestingController.expectOne(
       `${environment.apiBaseUrl}documents/?page=${page}&page_size=${
         documentListViewService.pageSize
-      }&ordering=${reverse ? '-' : ''}${sort}&truncate_content=true`
+      }&ordering=${reverse ? '-' : ''}${sort}&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     expect(documentListViewService.currentPage).toEqual(page)
@@ -303,7 +300,7 @@ describe('DocumentListViewService', () => {
     }
     documentListViewService.loadFromQueryParams(convertToParamMap(params))
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=${documentListViewService.currentPage}&page_size=${documentListViewService.pageSize}&ordering=-added&truncate_content=true&tags__id__all=${tags__id__all}`
+      `${environment.apiBaseUrl}documents/?page=${documentListViewService.currentPage}&page_size=${documentListViewService.pageSize}&ordering=-added&truncate_content=true&include_selection_data=true&tags__id__all=${tags__id__all}`
     )
     expect(req.request.method).toEqual('GET')
     expect(documentListViewService.filterRules).toEqual([
@@ -313,15 +310,12 @@ describe('DocumentListViewService', () => {
       },
     ])
     req.flush(full_results)
-    httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/selection_data/`
-    )
   })
 
   it('should use filter rules to update query params', () => {
     documentListViewService.setFilterRules(filterRules)
     const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=${documentListViewService.currentPage}&page_size=${documentListViewService.pageSize}&ordering=-created&truncate_content=true&tags__id__all=${tags__id__all}`
+      `${environment.apiBaseUrl}documents/?page=${documentListViewService.currentPage}&page_size=${documentListViewService.pageSize}&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__all=${tags__id__all}`
     )
     expect(req.request.method).toEqual('GET')
   })
@@ -330,34 +324,26 @@ describe('DocumentListViewService', () => {
     documentListViewService.currentPage = 2
     let req = httpTestingController.expectOne((request) =>
       request.urlWithParams.startsWith(
-        `${environment.apiBaseUrl}documents/?page=2&page_size=50&ordering=-created&truncate_content=true`
+        `${environment.apiBaseUrl}documents/?page=2&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
       )
     )
     expect(req.request.method).toEqual('GET')
     req.flush(full_results)
-    req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/selection_data/`
-    )
-    req.flush([])
 
     documentListViewService.setFilterRules(filterRules, true)
 
     const filteredReqs = httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&tags__id__all=${tags__id__all}`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__all=${tags__id__all}`
     )
     expect(filteredReqs).toHaveLength(1)
     filteredReqs[0].flush(full_results)
-    req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/selection_data/`
-    )
-    req.flush([])
     expect(documentListViewService.currentPage).toEqual(1)
   })
 
   it('should support quick filter', () => {
     documentListViewService.quickFilter(filterRules)
     const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=${documentListViewService.currentPage}&page_size=${documentListViewService.pageSize}&ordering=-created&truncate_content=true&tags__id__all=${tags__id__all}`
+      `${environment.apiBaseUrl}documents/?page=${documentListViewService.currentPage}&page_size=${documentListViewService.pageSize}&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__all=${tags__id__all}`
     )
     expect(req.request.method).toEqual('GET')
   })
@@ -380,21 +366,21 @@ describe('DocumentListViewService', () => {
       convertToParamMap(params)
     )
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=${page}&page_size=${documentListViewService.pageSize}&ordering=-added&truncate_content=true&tags__id__all=${tags__id__all}`
+      `${environment.apiBaseUrl}documents/?page=${page}&page_size=${documentListViewService.pageSize}&ordering=-added&truncate_content=true&include_selection_data=true&tags__id__all=${tags__id__all}`
     )
     expect(req.request.method).toEqual('GET')
     // reset the list
     documentListViewService.currentPage = 1
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-added&truncate_content=true&tags__id__all=9`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-added&truncate_content=true&include_selection_data=true&tags__id__all=9`
     )
     documentListViewService.setFilterRules([])
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-added&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-added&truncate_content=true&include_selection_data=true`
     )
     documentListViewService.sortField = 'created'
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     documentListViewService.activateSavedView(null)
   })
@@ -402,21 +388,18 @@ describe('DocumentListViewService', () => {
   it('should support navigating next / previous', () => {
     documentListViewService.setFilterRules([])
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(documentListViewService.currentPage).toEqual(1)
     documentListViewService.pageSize = 3
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=3&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=3&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     req.flush({
       count: 3,
       results: documents.slice(0, 3),
     })
-    httpTestingController
-      .expectOne(`${environment.apiBaseUrl}documents/selection_data/`)
-      .flush([])
     expect(documentListViewService.hasNext(documents[0].id)).toBeTruthy()
     expect(documentListViewService.hasPrevious(documents[0].id)).toBeFalsy()
     documentListViewService.getNext(documents[0].id).subscribe((docId) => {
@@ -463,7 +446,7 @@ describe('DocumentListViewService', () => {
     expect(documentListViewService.currentPage).toEqual(1)
     documentListViewService.pageSize = 3
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=3&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=3&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     jest
       .spyOn(documentListViewService, 'getLastPage')
@@ -478,7 +461,7 @@ describe('DocumentListViewService', () => {
     expect(reloadSpy).toHaveBeenCalled()
     expect(documentListViewService.currentPage).toEqual(2)
     const reqs = httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=2&page_size=3&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=2&page_size=3&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(reqs.length).toBeGreaterThan(0)
   })
@@ -513,11 +496,11 @@ describe('DocumentListViewService', () => {
       .mockReturnValue(documents)
     documentListViewService.currentPage = 2
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=2&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=2&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     documentListViewService.pageSize = 3
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=2&page_size=3&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=2&page_size=3&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     const reloadSpy = jest.spyOn(documentListViewService, 'reload')
     documentListViewService.getPrevious(1).subscribe({
@@ -527,7 +510,7 @@ describe('DocumentListViewService', () => {
     expect(reloadSpy).toHaveBeenCalled()
     expect(documentListViewService.currentPage).toEqual(1)
     const reqs = httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=3&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=3&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(reqs.length).toBeGreaterThan(0)
   })
@@ -540,13 +523,10 @@ describe('DocumentListViewService', () => {
   it('should support select a document', () => {
     documentListViewService.reload()
     const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     req.flush(full_results)
-    httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/selection_data/`
-    )
     documentListViewService.toggleSelected(documents[0])
     expect(documentListViewService.isSelected(documents[0])).toBeTruthy()
     documentListViewService.toggleSelected(documents[0])
@@ -554,12 +534,16 @@ describe('DocumentListViewService', () => {
   })
 
   it('should support select all', () => {
-    documentListViewService.selectAll()
+    documentListViewService.reload()
-    const req = httpTestingController.expectOne(
+    const reloadReq = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
-    expect(req.request.method).toEqual('GET')
+    expect(reloadReq.request.method).toEqual('GET')
-    req.flush(full_results)
+    reloadReq.flush(full_results)
+
+    documentListViewService.selectAll()
+    expect(documentListViewService.allSelected).toBeTruthy()
+    expect(documentListViewService.selectedCount).toEqual(documents.length)
     expect(documentListViewService.selected.size).toEqual(documents.length)
     expect(documentListViewService.isSelected(documents[0])).toBeTruthy()
     documentListViewService.selectNone()
@@ -568,16 +552,13 @@ describe('DocumentListViewService', () => {
   it('should support select page', () => {
     documentListViewService.pageSize = 3
     const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=3&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=3&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     req.flush({
       count: 3,
       results: documents.slice(0, 3),
     })
-    httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/selection_data/`
-    )
     documentListViewService.selectPage()
     expect(documentListViewService.selected.size).toEqual(3)
     expect(documentListViewService.isSelected(documents[5])).toBeFalsy()
@@ -586,13 +567,10 @@ describe('DocumentListViewService', () => {
   it('should support select range', () => {
     documentListViewService.reload()
     const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     req.flush(full_results)
-    httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/selection_data/`
-    )
     documentListViewService.toggleSelected(documents[0])
     expect(documentListViewService.isSelected(documents[0])).toBeTruthy()
     documentListViewService.selectRangeTo(documents[2])
@@ -601,26 +579,62 @@ describe('DocumentListViewService', () => {
     expect(documentListViewService.isSelected(documents[3])).toBeTruthy()
   })
 
-  it('should support selection range reduction', () => {
+  it('should clear all-selected mode when toggling a single document', () => {
+    documentListViewService.reload()
+    const req = httpTestingController.expectOne(
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+    )
+    req.flush(full_results)
+
     documentListViewService.selectAll()
+    expect(documentListViewService.allSelected).toBeTruthy()
+
+    documentListViewService.toggleSelected(documents[0])
+
+    expect(documentListViewService.allSelected).toBeFalsy()
+    expect(documentListViewService.isSelected(documents[0])).toBeFalsy()
+  })
+
+  it('should clear all-selected mode when selecting a range', () => {
+    documentListViewService.reload()
+    const req = httpTestingController.expectOne(
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+    )
+    req.flush(full_results)
+
+    documentListViewService.selectAll()
+    documentListViewService.toggleSelected(documents[1])
+    documentListViewService.selectAll()
+    expect(documentListViewService.allSelected).toBeTruthy()
+
+    documentListViewService.selectRangeTo(documents[3])
+
+    expect(documentListViewService.allSelected).toBeFalsy()
+    expect(documentListViewService.isSelected(documents[1])).toBeTruthy()
+    expect(documentListViewService.isSelected(documents[2])).toBeTruthy()
+    expect(documentListViewService.isSelected(documents[3])).toBeTruthy()
+  })
+
+  it('should support selection range reduction', () => {
+    documentListViewService.reload()
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(req.request.method).toEqual('GET')
     req.flush(full_results)
+
+    documentListViewService.selectAll()
     expect(documentListViewService.selected.size).toEqual(6)
 
     documentListViewService.setFilterRules(filterRules)
-    httpTestingController.expectOne(
+    req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&tags__id__all=9`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__all=9`
     )
-    const reqs = httpTestingController.match(
+    req.flush({
-      `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id&tags__id__all=9`
-    )
-    reqs[0].flush({
       count: 3,
       results: documents.slice(0, 3),
     })
+    expect(documentListViewService.allSelected).toBeTruthy()
     expect(documentListViewService.selected.size).toEqual(3)
   })
 
@@ -628,7 +642,7 @@ describe('DocumentListViewService', () => {
     const cancelSpy = jest.spyOn(documentListViewService, 'cancelPending')
     documentListViewService.reload()
     httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&tags__id__all=9`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__all=9`
     )
     expect(cancelSpy).toHaveBeenCalled()
   })
@@ -647,7 +661,7 @@ describe('DocumentListViewService', () => {
     documentListViewService.setFilterRules([])
     expect(documentListViewService.sortField).toEqual('created')
     httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
   })
 
@@ -674,11 +688,11 @@ describe('DocumentListViewService', () => {
     expect(localStorageSpy).toHaveBeenCalled()
     // reload triggered
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     documentListViewService.displayFields = null
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     expect(documentListViewService.displayFields).toEqual(
       DEFAULT_DISPLAY_FIELDS.filter((f) => f.id !== DisplayField.ADDED).map(
@@ -718,7 +732,7 @@ describe('DocumentListViewService', () => {
   it('should generate quick filter URL preserving default state', () => {
     documentListViewService.reload()
     httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
     )
     const urlTree = documentListViewService.getQuickFilterUrl(filterRules)
     expect(urlTree).toBeDefined()

src-ui/src/app/services/document-list-view.service.ts

@@ -1,6 +1,6 @@
 import { Injectable, inject } from '@angular/core'
 import { ParamMap, Router, UrlTree } from '@angular/router'
-import { Observable, Subject, first, takeUntil } from 'rxjs'
+import { Observable, Subject, takeUntil } from 'rxjs'
 import {
   DEFAULT_DISPLAY_FIELDS,
   DisplayField,
@@ -8,6 +8,7 @@ import {
   Document,
 } from '../data/document'
 import { FilterRule } from '../data/filter-rule'
+import { DocumentResults, SelectionData } from '../data/results'
 import { SavedView } from '../data/saved-view'
 import { DOCUMENT_LIST_SERVICE } from '../data/storage-keys'
 import { SETTINGS_KEYS } from '../data/ui-settings'
@@ -17,7 +18,7 @@ import {
   isFullTextFilterRule,
 } from '../utils/filter-rules'
 import { paramsFromViewState, paramsToViewState } from '../utils/query-params'
-import { DocumentService, SelectionData } from './rest/document.service'
+import { DocumentService } from './rest/document.service'
 import { SettingsService } from './settings.service'
 
 const LIST_DEFAULT_DISPLAY_FIELDS: DisplayField[] = DEFAULT_DISPLAY_FIELDS.map(
@@ -79,6 +80,11 @@ export interface ListViewState {
    */
   selected?: Set<number>
 
+  /**
+   * True if the full filtered result set is selected.
+   */
+  allSelected?: boolean
+
   /**
    * The page size of the list view.
    */
@@ -198,6 +204,20 @@ export class DocumentListViewService {
       sortReverse: true,
       filterRules: [],
       selected: new Set<number>(),
+      allSelected: false,
+    }
+  }
+
+  private syncSelectedToCurrentPage() {
+    if (!this.allSelected) {
+      return
+    }
+
+    this.selected.clear()
+    this.documents?.forEach((doc) => this.selected.add(doc.id))
+
+    if (!this.collectionSize) {
+      this.selectNone()
     }
   }
 
@@ -293,27 +313,18 @@ export class DocumentListViewService {
         activeListViewState.sortField,
         activeListViewState.sortReverse,
         activeListViewState.filterRules,
-        { truncate_content: true }
+        { truncate_content: true, include_selection_data: true }
       )
       .pipe(takeUntil(this.unsubscribeNotifier))
       .subscribe({
         next: (result) => {
+          const resultWithSelectionData = result as DocumentResults
           this.initialized = true
           this.isReloading = false
           activeListViewState.collectionSize = result.count
           activeListViewState.documents = result.results
-
+          this.selectionData = resultWithSelectionData.selection_data ?? null
-          this.documentService
+          this.syncSelectedToCurrentPage()
-            .getSelectionData(result.all)
-            .pipe(first())
-            .subscribe({
-              next: (selectionData) => {
-                this.selectionData = selectionData
-              },
-              error: () => {
-                this.selectionData = null
-              },
-            })
 
           if (updateQueryParams && !this._activeSavedViewId) {
             let base = ['/documents']
@@ -446,6 +457,20 @@ export class DocumentListViewService {
     return this.activeListViewState.selected
   }
 
+  get allSelected(): boolean {
+    return this.activeListViewState.allSelected ?? false
+  }
+
+  get selectedCount(): number {
+    return this.allSelected
+      ? (this.collectionSize ?? this.selected.size)
+      : this.selected.size
+  }
+
+  get hasSelection(): boolean {
+    return this.allSelected || this.selected.size > 0
+  }
+
   setSort(field: string, reverse: boolean) {
     this.activeListViewState.sortField = field
     this.activeListViewState.sortReverse = reverse
@@ -600,11 +625,16 @@ export class DocumentListViewService {
   }
 
   selectNone() {
+    this.activeListViewState.allSelected = false
     this.selected.clear()
     this.rangeSelectionAnchorIndex = this.lastRangeSelectionToIndex = null
   }
 
   reduceSelectionToFilter() {
+    if (this.allSelected) {
+      return
+    }
+
     if (this.selected.size > 0) {
       this.documentService
         .listAllFilteredIds(this.filterRules)
@@ -619,12 +649,12 @@ export class DocumentListViewService {
   }
 
   selectAll() {
-    this.documentService
+    this.activeListViewState.allSelected = true
-      .listAllFilteredIds(this.filterRules)
+    this.syncSelectedToCurrentPage()
-      .subscribe((ids) => ids.forEach((id) => this.selected.add(id)))
   }
 
   selectPage() {
+    this.activeListViewState.allSelected = false
     this.selected.clear()
     this.documents.forEach((doc) => {
       this.selected.add(doc.id)
@@ -632,10 +662,13 @@ export class DocumentListViewService {
   }
 
   isSelected(d: Document) {
-    return this.selected.has(d.id)
+    return this.allSelected || this.selected.has(d.id)
   }
 
   toggleSelected(d: Document): void {
+    if (this.allSelected) {
+      this.activeListViewState.allSelected = false
+    }
     if (this.selected.has(d.id)) this.selected.delete(d.id)
     else this.selected.add(d.id)
     this.rangeSelectionAnchorIndex = this.documentIndexInCurrentView(d.id)
@@ -643,6 +676,10 @@ export class DocumentListViewService {
   }
 
   selectRangeTo(d: Document) {
+    if (this.allSelected) {
+      this.activeListViewState.allSelected = false
+    }
+
     if (this.rangeSelectionAnchorIndex !== null) {
       const documentToIndex = this.documentIndexInCurrentView(d.id)
       const fromIndex = Math.min(

src-ui/src/app/services/rest/abstract-name-filter-service.spec.ts

@@ -96,6 +96,30 @@ export const commonAbstractNameFilterPaperlessServiceTests = (
       })
       req.flush([])
     })
+
+    test('should call appropriate api endpoint for bulk delete on all filtered objects', () => {
+      subscription = service
+        .bulk_edit_objects(
+          [],
+          BulkEditObjectOperation.Delete,
+          null,
+          null,
+          true,
+          { name__icontains: 'hello' }
+        )
+        .subscribe()
+      const req = httpTestingController.expectOne(
+        `${environment.apiBaseUrl}bulk_edit_objects/`
+      )
+      expect(req.request.method).toEqual('POST')
+      expect(req.request.body).toEqual({
+        object_type: endpoint,
+        operation: BulkEditObjectOperation.Delete,
+        all: true,
+        filters: { name__icontains: 'hello' },
+      })
+      req.flush([])
+    })
   })
 
   beforeEach(() => {

src-ui/src/app/services/rest/abstract-name-filter-service.ts

@@ -37,13 +37,22 @@ export abstract class AbstractNameFilterService<
     objects: Array<number>,
     operation: BulkEditObjectOperation,
     permissions: { owner: number; set_permissions: PermissionsObject } = null,
-    merge: boolean = null
+    merge: boolean = null,
+    all: boolean = false,
+    filters: { [key: string]: any } = null
   ): Observable<string> {
-    const params = {
+    const params: any = {
-      objects,
       object_type: this.resourceName,
       operation,
     }
+    if (all) {
+      params['all'] = true
+      if (filters) {
+        params['filters'] = filters
+      }
+    } else {
+      params['objects'] = objects
+    }
     if (operation === BulkEditObjectOperation.SetPermissions) {
       params['owner'] = permissions?.owner
       params['permissions'] = permissions?.set_permissions

src-ui/src/app/services/rest/document.service.spec.ts

@@ -198,7 +198,7 @@ describe(`DocumentService`, () => {
     const content = 'both'
     const useFilenameFormatting = false
     subscription = service
-      .bulkDownload(ids, content, useFilenameFormatting)
+      .bulkDownload({ documents: ids }, content, useFilenameFormatting)
       .subscribe()
     const req = httpTestingController.expectOne(
       `${environment.apiBaseUrl}${endpoint}/bulk_download/`
@@ -218,7 +218,9 @@ describe(`DocumentService`, () => {
       add_tags: [15],
       remove_tags: [6],
     }
-    subscription = service.bulkEdit(ids, method, parameters).subscribe()
+    subscription = service
+      .bulkEdit({ documents: ids }, method, parameters)
+      .subscribe()
     const req = httpTestingController.expectOne(
       `${environment.apiBaseUrl}${endpoint}/bulk_edit/`
     )
@@ -230,9 +232,32 @@ describe(`DocumentService`, () => {
     })
   })
 
+  it('should call appropriate api endpoint for bulk edit with all and filters', () => {
+    const method = 'modify_tags'
+    const parameters = {
+      add_tags: [15],
+      remove_tags: [6],
+    }
+    const selection = {
+      all: true,
+      filters: { title__icontains: 'apple' },
+    }
+    subscription = service.bulkEdit(selection, method, parameters).subscribe()
+    const req = httpTestingController.expectOne(
+      `${environment.apiBaseUrl}${endpoint}/bulk_edit/`
+    )
+    expect(req.request.method).toEqual('POST')
+    expect(req.request.body).toEqual({
+      all: true,
+      filters: { title__icontains: 'apple' },
+      method,
+      parameters,
+    })
+  })
+
   it('should call appropriate api endpoint for delete documents', () => {
     const ids = [1, 2, 3]
-    subscription = service.deleteDocuments(ids).subscribe()
+    subscription = service.deleteDocuments({ documents: ids }).subscribe()
     const req = httpTestingController.expectOne(
       `${environment.apiBaseUrl}${endpoint}/delete/`
     )
@@ -244,7 +269,7 @@ describe(`DocumentService`, () => {
 
   it('should call appropriate api endpoint for reprocess documents', () => {
     const ids = [1, 2, 3]
-    subscription = service.reprocessDocuments(ids).subscribe()
+    subscription = service.reprocessDocuments({ documents: ids }).subscribe()
     const req = httpTestingController.expectOne(
       `${environment.apiBaseUrl}${endpoint}/reprocess/`
     )
@@ -256,7 +281,7 @@ describe(`DocumentService`, () => {
 
   it('should call appropriate api endpoint for rotate documents', () => {
     const ids = [1, 2, 3]
-    subscription = service.rotateDocuments(ids, 90).subscribe()
+    subscription = service.rotateDocuments({ documents: ids }, 90).subscribe()
     const req = httpTestingController.expectOne(
       `${environment.apiBaseUrl}${endpoint}/rotate/`
     )

src-ui/src/app/services/rest/document.service.ts

@@ -12,7 +12,7 @@ import {
 import { DocumentMetadata } from 'src/app/data/document-metadata'
 import { DocumentSuggestions } from 'src/app/data/document-suggestions'
 import { FilterRule } from 'src/app/data/filter-rule'
-import { Results } from 'src/app/data/results'
+import { Results, SelectionData } from 'src/app/data/results'
 import { SETTINGS_KEYS } from 'src/app/data/ui-settings'
 import { queryParamsFromFilterRules } from '../../utils/query-params'
 import {
@@ -24,19 +24,6 @@ import { SettingsService } from '../settings.service'
 import { AbstractPaperlessService } from './abstract-paperless-service'
 import { CustomFieldsService } from './custom-fields.service'
 
-export interface SelectionDataItem {
-  id: number
-  document_count: number
-}
-
-export interface SelectionData {
-  selected_storage_paths: SelectionDataItem[]
-  selected_correspondents: SelectionDataItem[]
-  selected_tags: SelectionDataItem[]
-  selected_document_types: SelectionDataItem[]
-  selected_custom_fields: SelectionDataItem[]
-}
-
 export enum BulkEditSourceMode {
   LATEST_VERSION = 'latest_version',
   EXPLICIT_SELECTION = 'explicit_selection',
@@ -81,6 +68,12 @@ export interface RemovePasswordDocumentsRequest {
   source_mode?: BulkEditSourceMode
 }
 
+export interface DocumentSelectionQuery {
+  documents?: number[]
+  all?: boolean
+  filters?: { [key: string]: any }
+}
+
 @Injectable({
   providedIn: 'root',
 })
@@ -338,33 +331,37 @@ export class DocumentService extends AbstractPaperlessService<Document> {
     return this.http.get<DocumentMetadata>(url.toString())
   }
 
-  bulkEdit(ids: number[], method: DocumentBulkEditMethod, args: any) {
+  bulkEdit(
+    selection: DocumentSelectionQuery,
+    method: DocumentBulkEditMethod,
+    args: any
+  ) {
     return this.http.post(this.getResourceUrl(null, 'bulk_edit'), {
-      documents: ids,
+      ...selection,
       method: method,
       parameters: args,
     })
   }
 
-  deleteDocuments(ids: number[]) {
+  deleteDocuments(selection: DocumentSelectionQuery) {
     return this.http.post(this.getResourceUrl(null, 'delete'), {
-      documents: ids,
+      ...selection,
     })
   }
 
-  reprocessDocuments(ids: number[]) {
+  reprocessDocuments(selection: DocumentSelectionQuery) {
     return this.http.post(this.getResourceUrl(null, 'reprocess'), {
-      documents: ids,
+      ...selection,
     })
   }
 
   rotateDocuments(
-    ids: number[],
+    selection: DocumentSelectionQuery,
     degrees: number,
     sourceMode: BulkEditSourceMode = BulkEditSourceMode.LATEST_VERSION
   ) {
     return this.http.post(this.getResourceUrl(null, 'rotate'), {
-      documents: ids,
+      ...selection,
       degrees,
       source_mode: sourceMode,
     })
@@ -412,14 +409,14 @@ export class DocumentService extends AbstractPaperlessService<Document> {
   }
 
   bulkDownload(
-    ids: number[],
+    selection: DocumentSelectionQuery,
     content = 'both',
     useFilenameFormatting: boolean = false
   ) {
     return this.http.post(
       this.getResourceUrl(null, 'bulk_download'),
       {
-        documents: ids,
+        ...selection,
         content: content,
         follow_formatting: useFilenameFormatting,
       },

src/documents/admin.py

@@ -100,24 +100,23 @@ class DocumentAdmin(GuardedModelAdmin):
         return Document.global_objects.all()
 
     def delete_queryset(self, request, queryset):
-        from documents import index
+        from documents.search import get_backend
 
-        with index.open_index_writer() as writer:
+        with get_backend().batch_update() as batch:
             for o in queryset:
-                index.remove_document(writer, o)
+                batch.remove(o.pk)
-
         super().delete_queryset(request, queryset)
 
     def delete_model(self, request, obj):
-        from documents import index
+        from documents.search import get_backend
 
-        index.remove_document_from_index(obj)
+        get_backend().remove(obj.pk)
         super().delete_model(request, obj)
 
     def save_model(self, request, obj, form, change):
-        from documents import index
+        from documents.search import get_backend
 
-        index.add_or_update_document(obj)
+        get_backend().add_or_update(obj)
         super().save_model(request, obj, form, change)
 
 

src/documents/bulk_edit.py

@@ -349,11 +349,11 @@ def delete(doc_ids: list[int]) -> Literal["OK"]:
 
         Document.objects.filter(id__in=delete_ids).delete()
 
-        from documents import index
+        from documents.search import get_backend
 
-        with index.open_index_writer() as writer:
+        with get_backend().batch_update() as batch:
             for id in delete_ids:
-                index.remove_document_by_id(writer, id)
+                batch.remove(id)
 
         status_mgr = DocumentsStatusManager()
         status_mgr.send_documents_deleted(delete_ids)

src/documents/index.py

@@ -1,655 +0,0 @@
-from __future__ import annotations
-
-import logging
-import math
-import re
-from collections import Counter
-from contextlib import contextmanager
-from datetime import UTC
-from datetime import datetime
-from datetime import time
-from datetime import timedelta
-from shutil import rmtree
-from time import sleep
-from typing import TYPE_CHECKING
-from typing import Literal
-
-from dateutil.relativedelta import relativedelta
-from django.conf import settings
-from django.utils import timezone as django_timezone
-from django.utils.timezone import get_current_timezone
-from django.utils.timezone import now
-from guardian.shortcuts import get_users_with_perms
-from whoosh import classify
-from whoosh import highlight
-from whoosh import query
-from whoosh.fields import BOOLEAN
-from whoosh.fields import DATETIME
-from whoosh.fields import KEYWORD
-from whoosh.fields import NUMERIC
-from whoosh.fields import TEXT
-from whoosh.fields import Schema
-from whoosh.highlight import HtmlFormatter
-from whoosh.idsets import BitSet
-from whoosh.idsets import DocIdSet
-from whoosh.index import FileIndex
-from whoosh.index import LockError
-from whoosh.index import create_in
-from whoosh.index import exists_in
-from whoosh.index import open_dir
-from whoosh.qparser import MultifieldParser
-from whoosh.qparser import QueryParser
-from whoosh.qparser.dateparse import DateParserPlugin
-from whoosh.qparser.dateparse import English
-from whoosh.qparser.plugins import FieldsPlugin
-from whoosh.scoring import TF_IDF
-from whoosh.util.times import timespan
-from whoosh.writing import AsyncWriter
-
-from documents.models import CustomFieldInstance
-from documents.models import Document
-from documents.models import Note
-from documents.models import User
-
-if TYPE_CHECKING:
-    from django.db.models import QuerySet
-    from whoosh.reading import IndexReader
-    from whoosh.searching import ResultsPage
-    from whoosh.searching import Searcher
-
-logger = logging.getLogger("paperless.index")
-
-
-def get_schema() -> Schema:
-    return Schema(
-        id=NUMERIC(stored=True, unique=True),
-        title=TEXT(sortable=True),
-        content=TEXT(),
-        asn=NUMERIC(sortable=True, signed=False),
-        correspondent=TEXT(sortable=True),
-        correspondent_id=NUMERIC(),
-        has_correspondent=BOOLEAN(),
-        tag=KEYWORD(commas=True, scorable=True, lowercase=True),
-        tag_id=KEYWORD(commas=True, scorable=True),
-        has_tag=BOOLEAN(),
-        type=TEXT(sortable=True),
-        type_id=NUMERIC(),
-        has_type=BOOLEAN(),
-        created=DATETIME(sortable=True),
-        modified=DATETIME(sortable=True),
-        added=DATETIME(sortable=True),
-        path=TEXT(sortable=True),
-        path_id=NUMERIC(),
-        has_path=BOOLEAN(),
-        notes=TEXT(),
-        num_notes=NUMERIC(sortable=True, signed=False),
-        custom_fields=TEXT(),
-        custom_field_count=NUMERIC(sortable=True, signed=False),
-        has_custom_fields=BOOLEAN(),
-        custom_fields_id=KEYWORD(commas=True),
-        owner=TEXT(),
-        owner_id=NUMERIC(),
-        has_owner=BOOLEAN(),
-        viewer_id=KEYWORD(commas=True),
-        checksum=TEXT(),
-        page_count=NUMERIC(sortable=True),
-        original_filename=TEXT(sortable=True),
-        is_shared=BOOLEAN(),
-    )
-
-
-def open_index(*, recreate=False) -> FileIndex:
-    transient_exceptions = (FileNotFoundError, LockError)
-    max_retries = 3
-    retry_delay = 0.1
-
-    for attempt in range(max_retries + 1):
-        try:
-            if exists_in(settings.INDEX_DIR) and not recreate:
-                return open_dir(settings.INDEX_DIR, schema=get_schema())
-            break
-        except transient_exceptions as exc:
-            is_last_attempt = attempt == max_retries or recreate
-            if is_last_attempt:
-                logger.exception(
-                    "Error while opening the index after retries, recreating.",
-                )
-                break
-
-            logger.warning(
-                "Transient error while opening the index (attempt %s/%s): %s. Retrying.",
-                attempt + 1,
-                max_retries + 1,
-                exc,
-            )
-            sleep(retry_delay)
-        except Exception:
-            logger.exception("Error while opening the index, recreating.")
-            break
-
-    # create_in doesn't handle corrupted indexes very well, remove the directory entirely first
-    if settings.INDEX_DIR.is_dir():
-        rmtree(settings.INDEX_DIR)
-    settings.INDEX_DIR.mkdir(parents=True, exist_ok=True)
-
-    return create_in(settings.INDEX_DIR, get_schema())
-
-
-@contextmanager
-def open_index_writer(*, optimize=False) -> AsyncWriter:
-    writer = AsyncWriter(open_index())
-
-    try:
-        yield writer
-    except Exception as e:
-        logger.exception(str(e))
-        writer.cancel()
-    finally:
-        writer.commit(optimize=optimize)
-
-
-@contextmanager
-def open_index_searcher() -> Searcher:
-    searcher = open_index().searcher()
-
-    try:
-        yield searcher
-    finally:
-        searcher.close()
-
-
-def update_document(
-    writer: AsyncWriter,
-    doc: Document,
-    effective_content: str | None = None,
-) -> None:
-    tags = ",".join([t.name for t in doc.tags.all()])
-    tags_ids = ",".join([str(t.id) for t in doc.tags.all()])
-    notes = ",".join([str(c.note) for c in Note.objects.filter(document=doc)])
-    custom_fields = ",".join(
-        [str(c) for c in CustomFieldInstance.objects.filter(document=doc)],
-    )
-    custom_fields_ids = ",".join(
-        [str(f.field.id) for f in CustomFieldInstance.objects.filter(document=doc)],
-    )
-    asn: int | None = doc.archive_serial_number
-    if asn is not None and (
-        asn < Document.ARCHIVE_SERIAL_NUMBER_MIN
-        or asn > Document.ARCHIVE_SERIAL_NUMBER_MAX
-    ):
-        logger.error(
-            f"Not indexing Archive Serial Number {asn} of document {doc.pk}. "
-            f"ASN is out of range "
-            f"[{Document.ARCHIVE_SERIAL_NUMBER_MIN:,}, "
-            f"{Document.ARCHIVE_SERIAL_NUMBER_MAX:,}.",
-        )
-        asn = 0
-    users_with_perms = get_users_with_perms(
-        doc,
-        only_with_perms_in=["view_document"],
-    )
-    viewer_ids: str = ",".join([str(u.id) for u in users_with_perms])
-    writer.update_document(
-        id=doc.pk,
-        title=doc.title,
-        content=effective_content or doc.content,
-        correspondent=doc.correspondent.name if doc.correspondent else None,
-        correspondent_id=doc.correspondent.id if doc.correspondent else None,
-        has_correspondent=doc.correspondent is not None,
-        tag=tags if tags else None,
-        tag_id=tags_ids if tags_ids else None,
-        has_tag=len(tags) > 0,
-        type=doc.document_type.name if doc.document_type else None,
-        type_id=doc.document_type.id if doc.document_type else None,
-        has_type=doc.document_type is not None,
-        created=datetime.combine(doc.created, time.min),
-        added=doc.added,
-        asn=asn,
-        modified=doc.modified,
-        path=doc.storage_path.name if doc.storage_path else None,
-        path_id=doc.storage_path.id if doc.storage_path else None,
-        has_path=doc.storage_path is not None,
-        notes=notes,
-        num_notes=len(notes),
-        custom_fields=custom_fields,
-        custom_field_count=len(doc.custom_fields.all()),
-        has_custom_fields=len(custom_fields) > 0,
-        custom_fields_id=custom_fields_ids if custom_fields_ids else None,
-        owner=doc.owner.username if doc.owner else None,
-        owner_id=doc.owner.id if doc.owner else None,
-        has_owner=doc.owner is not None,
-        viewer_id=viewer_ids if viewer_ids else None,
-        checksum=doc.checksum,
-        page_count=doc.page_count,
-        original_filename=doc.original_filename,
-        is_shared=len(viewer_ids) > 0,
-    )
-    logger.debug(f"Index updated for document {doc.pk}.")
-
-
-def remove_document(writer: AsyncWriter, doc: Document) -> None:
-    remove_document_by_id(writer, doc.pk)
-
-
-def remove_document_by_id(writer: AsyncWriter, doc_id) -> None:
-    writer.delete_by_term("id", doc_id)
-
-
-def add_or_update_document(
-    document: Document,
-    effective_content: str | None = None,
-) -> None:
-    with open_index_writer() as writer:
-        update_document(writer, document, effective_content=effective_content)
-
-
-def remove_document_from_index(document: Document) -> None:
-    with open_index_writer() as writer:
-        remove_document(writer, document)
-
-
-class MappedDocIdSet(DocIdSet):
-    """
-    A DocIdSet backed by a set of `Document` IDs.
-    Supports efficiently looking up if a whoosh docnum is in the provided `filter_queryset`.
-    """
-
-    def __init__(self, filter_queryset: QuerySet, ixreader: IndexReader) -> None:
-        super().__init__()
-        document_ids = filter_queryset.order_by("id").values_list("id", flat=True)
-        max_id = document_ids.last() or 0
-        self.document_ids = BitSet(document_ids, size=max_id)
-        self.ixreader = ixreader
-
-    def __contains__(self, docnum) -> bool:
-        document_id = self.ixreader.stored_fields(docnum)["id"]
-        return document_id in self.document_ids
-
-    def __bool__(self) -> Literal[True]:
-        # searcher.search ignores a filter if it's "falsy".
-        # We use this hack so this DocIdSet, when used as a filter, is never ignored.
-        return True
-
-
-class DelayedQuery:
-    def _get_query(self):
-        raise NotImplementedError  # pragma: no cover
-
-    def _get_query_sortedby(self) -> tuple[None, Literal[False]] | tuple[str, bool]:
-        if "ordering" not in self.query_params:
-            return None, False
-
-        field: str = self.query_params["ordering"]
-
-        sort_fields_map: dict[str, str] = {
-            "created": "created",
-            "modified": "modified",
-            "added": "added",
-            "title": "title",
-            "correspondent__name": "correspondent",
-            "document_type__name": "type",
-            "archive_serial_number": "asn",
-            "num_notes": "num_notes",
-            "owner": "owner",
-            "page_count": "page_count",
-        }
-
-        if field.startswith("-"):
-            field = field[1:]
-            reverse = True
-        else:
-            reverse = False
-
-        if field not in sort_fields_map:
-            return None, False
-        else:
-            return sort_fields_map[field], reverse
-
-    def __init__(
-        self,
-        searcher: Searcher,
-        query_params,
-        page_size,
-        filter_queryset: QuerySet,
-    ) -> None:
-        self.searcher = searcher
-        self.query_params = query_params
-        self.page_size = page_size
-        self.saved_results = dict()
-        self.first_score = None
-        self.filter_queryset = filter_queryset
-        self.suggested_correction = None
-        self._manual_hits_cache: list | None = None
-
-    def __len__(self) -> int:
-        if self._manual_sort_requested():
-            manual_hits = self._manual_hits()
-            return len(manual_hits)
-
-        page = self[0:1]
-        return len(page)
-
-    def _manual_sort_requested(self):
-        ordering = self.query_params.get("ordering", "")
-        return ordering.lstrip("-").startswith("custom_field_")
-
-    def _manual_hits(self):
-        if self._manual_hits_cache is None:
-            q, mask, suggested_correction = self._get_query()
-            self.suggested_correction = suggested_correction
-
-            results = self.searcher.search(
-                q,
-                mask=mask,
-                filter=MappedDocIdSet(self.filter_queryset, self.searcher.ixreader),
-                limit=None,
-            )
-            results.fragmenter = highlight.ContextFragmenter(surround=50)
-            results.formatter = HtmlFormatter(tagname="span", between=" ... ")
-
-            if not self.first_score and len(results) > 0:
-                self.first_score = results[0].score
-
-            if self.first_score:
-                results.top_n = [
-                    (
-                        (hit[0] / self.first_score) if self.first_score else None,
-                        hit[1],
-                    )
-                    for hit in results.top_n
-                ]
-
-            hits_by_id = {hit["id"]: hit for hit in results}
-            matching_ids = list(hits_by_id.keys())
-
-            ordered_ids = list(
-                self.filter_queryset.filter(id__in=matching_ids).values_list(
-                    "id",
-                    flat=True,
-                ),
-            )
-            ordered_ids = list(dict.fromkeys(ordered_ids))
-
-            self._manual_hits_cache = [
-                hits_by_id[_id] for _id in ordered_ids if _id in hits_by_id
-            ]
-        return self._manual_hits_cache
-
-    def __getitem__(self, item):
-        if item.start in self.saved_results:
-            return self.saved_results[item.start]
-
-        if self._manual_sort_requested():
-            manual_hits = self._manual_hits()
-            start = 0 if item.start is None else item.start
-            stop = item.stop
-            hits = manual_hits[start:stop] if stop is not None else manual_hits[start:]
-            page = ManualResultsPage(hits)
-            self.saved_results[start] = page
-            return page
-
-        q, mask, suggested_correction = self._get_query()
-        self.suggested_correction = suggested_correction
-        sortedby, reverse = self._get_query_sortedby()
-
-        page: ResultsPage = self.searcher.search_page(
-            q,
-            mask=mask,
-            filter=MappedDocIdSet(self.filter_queryset, self.searcher.ixreader),
-            pagenum=math.floor(item.start / self.page_size) + 1,
-            pagelen=self.page_size,
-            sortedby=sortedby,
-            reverse=reverse,
-        )
-        page.results.fragmenter = highlight.ContextFragmenter(surround=50)
-        page.results.formatter = HtmlFormatter(tagname="span", between=" ... ")
-
-        if not self.first_score and len(page.results) > 0 and sortedby is None:
-            self.first_score = page.results[0].score
-
-        page.results.top_n = [
-            (
-                (hit[0] / self.first_score) if self.first_score else None,
-                hit[1],
-            )
-            for hit in page.results.top_n
-        ]
-
-        self.saved_results[item.start] = page
-
-        return page
-
-
-class ManualResultsPage(list):
-    def __init__(self, hits) -> None:
-        super().__init__(hits)
-        self.results = ManualResults(hits)
-
-
-class ManualResults:
-    def __init__(self, hits) -> None:
-        self._docnums = [hit.docnum for hit in hits]
-
-    def docs(self):
-        return self._docnums
-
-
-class LocalDateParser(English):
-    def reverse_timezone_offset(self, d):
-        return (d.replace(tzinfo=django_timezone.get_current_timezone())).astimezone(
-            UTC,
-        )
-
-    def date_from(self, *args, **kwargs):
-        d = super().date_from(*args, **kwargs)
-        if isinstance(d, timespan):
-            d.start = self.reverse_timezone_offset(d.start)
-            d.end = self.reverse_timezone_offset(d.end)
-        elif isinstance(d, datetime):
-            d = self.reverse_timezone_offset(d)
-        return d
-
-
-class DelayedFullTextQuery(DelayedQuery):
-    def _get_query(self) -> tuple:
-        q_str = self.query_params["query"]
-        q_str = rewrite_natural_date_keywords(q_str)
-        qp = MultifieldParser(
-            [
-                "content",
-                "title",
-                "correspondent",
-                "tag",
-                "type",
-                "notes",
-                "custom_fields",
-            ],
-            self.searcher.ixreader.schema,
-        )
-        qp.add_plugin(
-            DateParserPlugin(
-                basedate=django_timezone.now(),
-                dateparser=LocalDateParser(),
-            ),
-        )
-        q = qp.parse(q_str)
-        suggested_correction = None
-        try:
-            corrected = self.searcher.correct_query(q, q_str)
-            if corrected.string != q_str:
-                corrected_results = self.searcher.search(
-                    corrected.query,
-                    limit=1,
-                    filter=MappedDocIdSet(self.filter_queryset, self.searcher.ixreader),
-                    scored=False,
-                )
-                if len(corrected_results) > 0:
-                    suggested_correction = corrected.string
-        except Exception as e:
-            logger.info(
-                "Error while correcting query %s: %s",
-                f"{q_str!r}",
-                e,
-            )
-
-        return q, None, suggested_correction
-
-
-class DelayedMoreLikeThisQuery(DelayedQuery):
-    def _get_query(self) -> tuple:
-        more_like_doc_id = int(self.query_params["more_like_id"])
-        content = Document.objects.get(id=more_like_doc_id).content
-
-        docnum = self.searcher.document_number(id=more_like_doc_id)
-        kts = self.searcher.key_terms_from_text(
-            "content",
-            content,
-            numterms=20,
-            model=classify.Bo1Model,
-            normalize=False,
-        )
-        q = query.Or(
-            [query.Term("content", word, boost=weight) for word, weight in kts],
-        )
-        mask: set = {docnum}
-
-        return q, mask, None
-
-
-def autocomplete(
-    ix: FileIndex,
-    term: str,
-    limit: int = 10,
-    user: User | None = None,
-) -> list:
-    """
-    Mimics whoosh.reading.IndexReader.most_distinctive_terms with permissions
-    and without scoring
-    """
-    terms = []
-
-    with ix.searcher(weighting=TF_IDF()) as s:
-        qp = QueryParser("content", schema=ix.schema)
-        # Don't let searches with a query that happen to match a field override the
-        # content field query instead and return bogus, not text data
-        qp.remove_plugin_class(FieldsPlugin)
-        q = qp.parse(f"{term.lower()}*")
-        user_criterias: list = get_permissions_criterias(user)
-
-        results = s.search(
-            q,
-            terms=True,
-            filter=query.Or(user_criterias) if user_criterias is not None else None,
-        )
-
-        termCounts = Counter()
-        if results.has_matched_terms():
-            for hit in results:
-                for _, match in hit.matched_terms():
-                    termCounts[match] += 1
-            terms = [t for t, _ in termCounts.most_common(limit)]
-
-        term_encoded: bytes = term.encode("UTF-8")
-        if term_encoded in terms:
-            terms.insert(0, terms.pop(terms.index(term_encoded)))
-
-    return terms
-
-
-def get_permissions_criterias(user: User | None = None) -> list:
-    user_criterias = [query.Term("has_owner", text=False)]
-    if user is not None:
-        if user.is_superuser:  # superusers see all docs
-            user_criterias = []
-        else:
-            user_criterias.append(query.Term("owner_id", user.id))
-            user_criterias.append(
-                query.Term("viewer_id", str(user.id)),
-            )
-    return user_criterias
-
-
-def rewrite_natural_date_keywords(query_string: str) -> str:
-    """
-    Rewrites natural date keywords (e.g. added:today or added:"yesterday") to UTC range syntax for Whoosh.
-    This resolves timezone issues with date parsing in Whoosh as well as adding support for more
-    natural date keywords.
-    """
-
-    tz = get_current_timezone()
-    local_now = now().astimezone(tz)
-    today = local_now.date()
-
-    # all supported Keywords
-    pattern = r"(\b(?:added|created|modified))\s*:\s*[\"']?(today|yesterday|this month|previous month|previous week|previous quarter|this year|previous year)[\"']?"
-
-    def repl(m):
-        field = m.group(1)
-        keyword = m.group(2).lower()
-
-        match keyword:
-            case "today":
-                start = datetime.combine(today, time.min, tzinfo=tz)
-                end = datetime.combine(today, time.max, tzinfo=tz)
-
-            case "yesterday":
-                yesterday = today - timedelta(days=1)
-                start = datetime.combine(yesterday, time.min, tzinfo=tz)
-                end = datetime.combine(yesterday, time.max, tzinfo=tz)
-
-            case "this month":
-                start = datetime(local_now.year, local_now.month, 1, 0, 0, 0, tzinfo=tz)
-                end = start + relativedelta(months=1) - timedelta(seconds=1)
-
-            case "previous month":
-                this_month_start = datetime(
-                    local_now.year,
-                    local_now.month,
-                    1,
-                    0,
-                    0,
-                    0,
-                    tzinfo=tz,
-                )
-                start = this_month_start - relativedelta(months=1)
-                end = this_month_start - timedelta(seconds=1)
-
-            case "this year":
-                start = datetime(local_now.year, 1, 1, 0, 0, 0, tzinfo=tz)
-                end = datetime(local_now.year, 12, 31, 23, 59, 59, tzinfo=tz)
-
-            case "previous week":
-                days_since_monday = local_now.weekday()
-                this_week_start = datetime.combine(
-                    today - timedelta(days=days_since_monday),
-                    time.min,
-                    tzinfo=tz,
-                )
-                start = this_week_start - timedelta(days=7)
-                end = this_week_start - timedelta(seconds=1)
-
-            case "previous quarter":
-                current_quarter = (local_now.month - 1) // 3 + 1
-                this_quarter_start_month = (current_quarter - 1) * 3 + 1
-                this_quarter_start = datetime(
-                    local_now.year,
-                    this_quarter_start_month,
-                    1,
-                    0,
-                    0,
-                    0,
-                    tzinfo=tz,
-                )
-                start = this_quarter_start - relativedelta(months=3)
-                end = this_quarter_start - timedelta(seconds=1)
-
-            case "previous year":
-                start = datetime(local_now.year - 1, 1, 1, 0, 0, 0, tzinfo=tz)
-                end = datetime(local_now.year - 1, 12, 31, 23, 59, 59, tzinfo=tz)
-
-        # Convert to UTC and format
-        start_str = start.astimezone(UTC).strftime("%Y%m%d%H%M%S")
-        end_str = end.astimezone(UTC).strftime("%Y%m%d%H%M%S")
-        return f"{field}:[{start_str} TO {end_str}]"
-
-    return re.sub(pattern, repl, query_string, flags=re.IGNORECASE)

src/documents/management/commands/document_exporter.py

@@ -385,10 +385,10 @@ class Command(CryptMixin, PaperlessCommand):
             "workflow_webhook_actions": WorkflowActionWebhook.objects.all(),
             "workflows": Workflow.objects.all(),
             "custom_fields": CustomField.objects.all(),
-            "custom_field_instances": CustomFieldInstance.objects.all(),
+            "custom_field_instances": CustomFieldInstance.global_objects.all(),
             "app_configs": ApplicationConfiguration.objects.all(),
-            "notes": Note.objects.all(),
+            "notes": Note.global_objects.all(),
-            "documents": Document.objects.order_by("id").all(),
+            "documents": Document.global_objects.order_by("id").all(),
             "social_accounts": SocialAccount.objects.all(),
             "social_apps": SocialApp.objects.all(),
             "social_tokens": SocialToken.objects.all(),
@@ -443,7 +443,7 @@ class Command(CryptMixin, PaperlessCommand):
                             writer.write_batch(batch)
 
             document_map: dict[int, Document] = {
-                d.pk: d for d in Document.objects.order_by("id")
+                d.pk: d for d in Document.global_objects.order_by("id")
             }
 
             # 3. Export files from each document
@@ -619,12 +619,15 @@ class Command(CryptMixin, PaperlessCommand):
         """Write per-document manifest file for --split-manifest mode."""
         content = [document_dict]
         content.extend(
-            serializers.serialize("python", Note.objects.filter(document=document)),
+            serializers.serialize(
+                "python",
+                Note.global_objects.filter(document=document),
+            ),
         )
         content.extend(
             serializers.serialize(
                 "python",
-                CustomFieldInstance.objects.filter(document=document),
+                CustomFieldInstance.global_objects.filter(document=document),
             ),
         )
         manifest_name = base_name.with_name(f"{base_name.stem}-manifest.json")

src/documents/management/commands/document_importer.py

@@ -125,7 +125,7 @@ class Command(CryptMixin, PaperlessCommand):
                         "Found existing user(s), this might indicate a non-empty installation",
                     ),
                 )
-            if Document.objects.count() != 0:
+            if Document.global_objects.count() != 0:
                 self.stdout.write(
                     self.style.WARNING(
                         "Found existing documents(s), this might indicate a non-empty installation",
@@ -376,7 +376,7 @@ class Command(CryptMixin, PaperlessCommand):
         ]
 
         for record in self.track(document_records, description="Copying files..."):
-            document = Document.objects.get(pk=record["pk"])
+            document = Document.global_objects.get(pk=record["pk"])
 
             doc_file = record[EXPORTER_FILE_NAME]
             document_path = self.source / doc_file

src/documents/management/commands/document_index.py

@@ -1,11 +1,26 @@
+import logging
+
+from django.conf import settings
 from django.db import transaction
 
 from documents.management.commands.base import PaperlessCommand
-from documents.tasks import index_optimize
+from documents.models import Document
-from documents.tasks import index_reindex
+from documents.search import get_backend
+from documents.search import needs_rebuild
+from documents.search import reset_backend
+from documents.search import wipe_index
+
+logger = logging.getLogger("paperless.management.document_index")
 
 
 class Command(PaperlessCommand):
+    """
+    Django management command for search index operations.
+
+    Provides subcommands for reindexing documents and optimizing the search index.
+    Supports conditional reindexing based on schema version and language changes.
+    """
+
     help = "Manages the document index."
 
     supports_progress_bar = True
@@ -14,15 +29,49 @@ class Command(PaperlessCommand):
     def add_arguments(self, parser):
         super().add_arguments(parser)
         parser.add_argument("command", choices=["reindex", "optimize"])
+        parser.add_argument(
+            "--recreate",
+            action="store_true",
+            default=False,
+            help="Wipe and recreate the index from scratch (only used with reindex).",
+        )
+        parser.add_argument(
+            "--if-needed",
+            action="store_true",
+            default=False,
+            help=(
+                "Skip reindex if the index is already up to date. "
+                "Checks schema version and search language sentinels. "
+                "Safe to run on every startup or upgrade."
+            ),
+        )
 
     def handle(self, *args, **options):
         with transaction.atomic():
             if options["command"] == "reindex":
-                index_reindex(
+                if options.get("if_needed") and not needs_rebuild(settings.INDEX_DIR):
+                    self.stdout.write("Search index is up to date.")
+                    return
+                if options.get("recreate"):
+                    wipe_index(settings.INDEX_DIR)
+
+                documents = Document.objects.select_related(
+                    "correspondent",
+                    "document_type",
+                    "storage_path",
+                    "owner",
+                ).prefetch_related("tags", "notes", "custom_fields", "versions")
+                get_backend().rebuild(
+                    documents,
                     iter_wrapper=lambda docs: self.track(
                         docs,
                         description="Indexing documents...",
                     ),
                 )
+                reset_backend()
+
             elif options["command"] == "optimize":
-                index_optimize()
+                logger.info(
+                    "document_index optimize is a no-op — Tantivy manages "
+                    "segment merging automatically.",
+                )

src/documents/migrations/0017_migrate_fulltext_query_field_prefixes.py

@@ -0,0 +1,39 @@
+import re
+
+from django.db import migrations
+
+# Matches "note:" when NOT preceded by a word character or dot.
+# This avoids false positives like "denote:" or already-migrated "notes.note:".
+# Handles start-of-string, whitespace, parentheses, +/- operators per Whoosh syntax.
+_NOTE_RE = re.compile(r"(?<![.\w])note:")
+
+# Same logic for "custom_field:" -> "custom_fields.value:"
+_CUSTOM_FIELD_RE = re.compile(r"(?<![.\w])custom_field:")
+
+
+def migrate_fulltext_query_field_prefixes(apps, schema_editor):
+    SavedViewFilterRule = apps.get_model("documents", "SavedViewFilterRule")
+
+    # rule_type 20 = "fulltext query" — value is a search query string
+    for rule in SavedViewFilterRule.objects.filter(rule_type=20).exclude(
+        value__isnull=True,
+    ):
+        new_value = _NOTE_RE.sub("notes.note:", rule.value)
+        new_value = _CUSTOM_FIELD_RE.sub("custom_fields.value:", new_value)
+
+        if new_value != rule.value:
+            rule.value = new_value
+            rule.save(update_fields=["value"])
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0016_sha256_checksums"),
+    ]
+
+    operations = [
+        migrations.RunPython(
+            migrate_fulltext_query_field_prefixes,
+            migrations.RunPython.noop,
+        ),
+    ]

src/documents/models.py

@@ -1114,19 +1114,7 @@ class CustomFieldInstance(SoftDeleteModel):
         ]
 
     def __str__(self) -> str:
-        value = (
+        return str(self.field.name) + f" : {self.value_for_search}"
-            next(
-                option.get("label")
-                for option in self.field.extra_data["select_options"]
-                if option.get("id") == self.value_select
-            )
-            if (
-                self.field.data_type == CustomField.FieldDataType.SELECT
-                and self.value_select is not None
-            )
-            else self.value
-        )
-        return str(self.field.name) + f" : {value}"
 
     @classmethod
     def get_value_field_name(cls, data_type: CustomField.FieldDataType):
@@ -1144,6 +1132,25 @@ class CustomFieldInstance(SoftDeleteModel):
         value_field_name = self.get_value_field_name(self.field.data_type)
         return getattr(self, value_field_name)
 
+    @property
+    def value_for_search(self) -> str | None:
+        """
+        Return the value suitable for full-text indexing and display, or None
+        if the value is unset.
+
+        For SELECT fields, resolves the human-readable label rather than the
+        opaque option ID stored in value_select.
+        """
+        if self.value is None:
+            return None
+        if self.field.data_type == CustomField.FieldDataType.SELECT:
+            options = (self.field.extra_data or {}).get("select_options", [])
+            return next(
+                (o["label"] for o in options if o.get("id") == self.value),
+                None,
+            )
+        return str(self.value)
+
 
 if settings.AUDIT_LOG_ENABLED:
     auditlog.register(

src/documents/sanity_checker.py

@@ -9,19 +9,14 @@ to wrap the document queryset (e.g., with a progress bar). The default
 is an identity function that adds no overhead.
 """
 
-from __future__ import annotations
-
 import logging
 import uuid
 from collections import defaultdict
-from collections.abc import Callable
-from collections.abc import Iterable
 from collections.abc import Iterator
 from pathlib import Path
 from typing import TYPE_CHECKING
 from typing import Final
 from typing import TypedDict
-from typing import TypeVar
 
 from celery import states
 from django.conf import settings
@@ -29,14 +24,13 @@ from django.utils import timezone
 
 from documents.models import Document
 from documents.models import PaperlessTask
+from documents.utils import IterWrapper
 from documents.utils import compute_checksum
+from documents.utils import identity
 from paperless.config import GeneralConfig
 
 logger = logging.getLogger("paperless.sanity_checker")
 
-_T = TypeVar("_T")
-IterWrapper = Callable[[Iterable[_T]], Iterable[_T]]
-
 
 class MessageEntry(TypedDict):
     """A single sanity check message with its severity level."""
@@ -45,11 +39,6 @@ class MessageEntry(TypedDict):
     message: str
 
 
-def _identity(iterable: Iterable[_T]) -> Iterable[_T]:
-    """Pass through an iterable unchanged (default iter_wrapper)."""
-    return iterable
-
-
 class SanityCheckMessages:
     """Collects sanity check messages grouped by document primary key.
 
@@ -296,7 +285,7 @@ def _check_document(
 def check_sanity(
     *,
     scheduled: bool = True,
-    iter_wrapper: IterWrapper[Document] = _identity,
+    iter_wrapper: IterWrapper[Document] = identity,
 ) -> SanityCheckMessages:
     """Run a full sanity check on the document archive.
 

src/documents/search/__init__.py

@@ -0,0 +1,21 @@
+from documents.search._backend import SearchIndexLockError
+from documents.search._backend import SearchResults
+from documents.search._backend import TantivyBackend
+from documents.search._backend import TantivyRelevanceList
+from documents.search._backend import WriteBatch
+from documents.search._backend import get_backend
+from documents.search._backend import reset_backend
+from documents.search._schema import needs_rebuild
+from documents.search._schema import wipe_index
+
+__all__ = [
+    "SearchIndexLockError",
+    "SearchResults",
+    "TantivyBackend",
+    "TantivyRelevanceList",
+    "WriteBatch",
+    "get_backend",
+    "needs_rebuild",
+    "reset_backend",
+    "wipe_index",
+]

src/documents/search/_backend.py

@@ -0,0 +1,858 @@
+from __future__ import annotations
+
+import logging
+import threading
+import unicodedata
+from collections import Counter
+from dataclasses import dataclass
+from datetime import UTC
+from datetime import datetime
+from typing import TYPE_CHECKING
+from typing import Self
+from typing import TypedDict
+from typing import TypeVar
+
+import filelock
+import regex
+import tantivy
+from django.conf import settings
+from django.utils.timezone import get_current_timezone
+from guardian.shortcuts import get_users_with_perms
+
+from documents.search._query import build_permission_filter
+from documents.search._query import parse_user_query
+from documents.search._schema import _write_sentinels
+from documents.search._schema import build_schema
+from documents.search._schema import open_or_rebuild_index
+from documents.search._schema import wipe_index
+from documents.search._tokenizer import register_tokenizers
+from documents.utils import IterWrapper
+from documents.utils import identity
+
+if TYPE_CHECKING:
+    from pathlib import Path
+
+    from django.contrib.auth.base_user import AbstractBaseUser
+    from django.db.models import QuerySet
+
+    from documents.models import Document
+
+logger = logging.getLogger("paperless.search")
+
+_WORD_RE = regex.compile(r"\w+")
+_AUTOCOMPLETE_REGEX_TIMEOUT = 1.0  # seconds; guards against ReDoS on untrusted content
+
+T = TypeVar("T")
+
+
+def _ascii_fold(s: str) -> str:
+    """
+    Normalize unicode to ASCII equivalent characters for search consistency.
+
+    Converts accented characters (e.g., "café") to their ASCII base forms ("cafe")
+    to enable cross-language searching without requiring exact diacritic matching.
+    """
+    return unicodedata.normalize("NFD", s).encode("ascii", "ignore").decode()
+
+
+def _extract_autocomplete_words(text_sources: list[str]) -> set[str]:
+    """Extract and normalize words for autocomplete.
+
+    Splits on non-word characters (matching Tantivy's simple tokenizer), lowercases,
+    and ascii-folds each token. Uses the regex library with a timeout to guard against
+    ReDoS on untrusted document content.
+    """
+    words = set()
+    for text in text_sources:
+        if not text:
+            continue
+        try:
+            tokens = _WORD_RE.findall(text, timeout=_AUTOCOMPLETE_REGEX_TIMEOUT)
+        except TimeoutError:  # pragma: no cover
+            logger.warning(
+                "Autocomplete word extraction timed out for a text source; skipping.",
+            )
+            continue
+        for token in tokens:
+            normalized = _ascii_fold(token.lower())
+            if normalized:
+                words.add(normalized)
+    return words
+
+
+class SearchHit(TypedDict):
+    """Type definition for search result hits."""
+
+    id: int
+    score: float
+    rank: int
+    highlights: dict[str, str]
+
+
+@dataclass(frozen=True, slots=True)
+class SearchResults:
+    """
+    Container for search results with pagination metadata.
+
+    Attributes:
+        hits: List of search results with scores and highlights
+        total: Total matching documents across all pages (for pagination)
+        query: Preprocessed query string after date/syntax rewriting
+    """
+
+    hits: list[SearchHit]
+    total: int  # total matching documents (for pagination)
+    query: str  # preprocessed query string
+
+
+class TantivyRelevanceList:
+    """
+    DRF-compatible list wrapper for Tantivy search hits.
+
+    Provides paginated access to search results while storing all hits in memory
+    for efficient ID retrieval. Used by Django REST framework for pagination.
+
+    Methods:
+        __len__: Returns total hit count for pagination calculations
+        __getitem__: Slices the hit list for page-specific results
+
+    Note: Stores ALL post-filter hits so get_all_result_ids() can return
+    every matching document ID without requiring a second search query.
+    """
+
+    def __init__(self, hits: list[SearchHit]) -> None:
+        self._hits = hits
+
+    def __len__(self) -> int:
+        return len(self._hits)
+
+    def __getitem__(self, key: slice) -> list[SearchHit]:
+        return self._hits[key]
+
+
+class SearchIndexLockError(Exception):
+    """Raised when the search index file lock cannot be acquired within the timeout."""
+
+
+class WriteBatch:
+    """
+    Context manager for bulk index operations with file locking.
+
+    Provides transactional batch updates to the search index with proper
+    concurrency control via file locking. All operations within the batch
+    are committed atomically or rolled back on exception.
+
+    Usage:
+        with backend.batch_update() as batch:
+            batch.add_or_update(document)
+            batch.remove(doc_id)
+    """
+
+    def __init__(self, backend: TantivyBackend, lock_timeout: float):
+        self._backend = backend
+        self._lock_timeout = lock_timeout
+        self._writer = None
+        self._lock = None
+
+    def __enter__(self) -> Self:
+        if self._backend._path is not None:
+            lock_path = self._backend._path / ".tantivy.lock"
+            self._lock = filelock.FileLock(str(lock_path))
+            try:
+                self._lock.acquire(timeout=self._lock_timeout)
+            except filelock.Timeout as e:  # pragma: no cover
+                raise SearchIndexLockError(
+                    f"Could not acquire index lock within {self._lock_timeout}s",
+                ) from e
+
+        self._writer = self._backend._index.writer()
+        return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        try:
+            if exc_type is None:
+                self._writer.commit()
+                self._backend._index.reload()
+            # Explicitly delete writer to release tantivy's internal lock.
+            # On exception the uncommitted writer is simply discarded.
+            if self._writer is not None:
+                del self._writer
+                self._writer = None
+        finally:
+            if self._lock is not None:
+                self._lock.release()
+
+    def add_or_update(
+        self,
+        document: Document,
+        effective_content: str | None = None,
+    ) -> None:
+        """
+        Add or update a document in the batch.
+
+        Implements upsert behavior by deleting any existing document with the same ID
+        and adding the new version. This ensures stale document data (e.g., after
+        permission changes) doesn't persist in the index.
+
+        Args:
+            document: Django Document instance to index
+            effective_content: Override document.content for indexing (used when
+                re-indexing with newer OCR text from document versions)
+        """
+        self.remove(document.pk)
+        doc = self._backend._build_tantivy_doc(document, effective_content)
+        self._writer.add_document(doc)
+
+    def remove(self, doc_id: int) -> None:
+        """
+        Remove a document from the batch by its primary key.
+
+        Uses range query instead of term query to work around unsigned integer
+        type detection bug in tantivy-py 0.25.
+        """
+        # Use range query to work around u64 deletion bug
+        self._writer.delete_documents_by_query(
+            tantivy.Query.range_query(
+                self._backend._schema,
+                "id",
+                tantivy.FieldType.Unsigned,
+                doc_id,
+                doc_id,
+            ),
+        )
+
+
+class TantivyBackend:
+    """
+    Tantivy search backend with explicit lifecycle management.
+
+    Provides full-text search capabilities using the Tantivy search engine.
+    Supports in-memory indexes (for testing) and persistent on-disk indexes
+    (for production use). Handles document indexing, search queries, autocompletion,
+    and "more like this" functionality.
+
+    The backend manages its own connection lifecycle and can be reset when
+    the underlying index directory changes (e.g., during test isolation).
+    """
+
+    def __init__(self, path: Path | None = None):
+        # path=None → in-memory index (for tests)
+        # path=some_dir → on-disk index (for production)
+        self._path = path
+        self._index = None
+        self._schema = None
+
+    def open(self) -> None:
+        """
+        Open or rebuild the index as needed.
+
+        For disk-based indexes, checks if rebuilding is needed due to schema
+        version or language changes. Registers custom tokenizers after opening.
+        Safe to call multiple times - subsequent calls are no-ops.
+        """
+        if self._index is not None:
+            return  # pragma: no cover
+        if self._path is not None:
+            self._index = open_or_rebuild_index(self._path)
+        else:
+            self._index = tantivy.Index(build_schema())
+        register_tokenizers(self._index, settings.SEARCH_LANGUAGE)
+        self._schema = self._index.schema
+
+    def close(self) -> None:
+        """
+        Close the index and release resources.
+
+        Safe to call multiple times - subsequent calls are no-ops.
+        """
+        self._index = None
+        self._schema = None
+
+    def _ensure_open(self) -> None:
+        """Ensure the index is open before operations."""
+        if self._index is None:
+            self.open()  # pragma: no cover
+
+    def _build_tantivy_doc(
+        self,
+        document: Document,
+        effective_content: str | None = None,
+    ) -> tantivy.Document:
+        """Build a tantivy Document from a Django Document instance.
+
+        ``effective_content`` overrides ``document.content`` for indexing —
+        used when re-indexing a root document with a newer version's OCR text.
+        """
+        content = (
+            effective_content if effective_content is not None else document.content
+        )
+
+        doc = tantivy.Document()
+
+        # Basic fields
+        doc.add_unsigned("id", document.pk)
+        doc.add_text("checksum", document.checksum)
+        doc.add_text("title", document.title)
+        doc.add_text("title_sort", document.title)
+        doc.add_text("content", content)
+        doc.add_text("bigram_content", content)
+
+        # Original filename - only add if not None/empty
+        if document.original_filename:
+            doc.add_text("original_filename", document.original_filename)
+
+        # Correspondent
+        if document.correspondent:
+            doc.add_text("correspondent", document.correspondent.name)
+            doc.add_text("correspondent_sort", document.correspondent.name)
+            doc.add_unsigned("correspondent_id", document.correspondent_id)
+
+        # Document type
+        if document.document_type:
+            doc.add_text("document_type", document.document_type.name)
+            doc.add_text("type_sort", document.document_type.name)
+            doc.add_unsigned("document_type_id", document.document_type_id)
+
+        # Storage path
+        if document.storage_path:
+            doc.add_text("storage_path", document.storage_path.name)
+            doc.add_unsigned("storage_path_id", document.storage_path_id)
+
+        # Tags — collect names for autocomplete in the same pass
+        tag_names: list[str] = []
+        for tag in document.tags.all():
+            doc.add_text("tag", tag.name)
+            doc.add_unsigned("tag_id", tag.pk)
+            tag_names.append(tag.name)
+
+        # Notes — JSON for structured queries (notes.user:alice, notes.note:text),
+        # companion text field for default full-text search.
+        num_notes = 0
+        for note in document.notes.all():
+            num_notes += 1
+            doc.add_json("notes", {"note": note.note, "user": note.user.username})
+
+        # Custom fields — JSON for structured queries (custom_fields.name:x, custom_fields.value:y),
+        # companion text field for default full-text search.
+        for cfi in document.custom_fields.all():
+            search_value = cfi.value_for_search
+            # Skip fields where there is no value yet
+            if search_value is None:
+                continue
+            doc.add_json(
+                "custom_fields",
+                {
+                    "name": cfi.field.name,
+                    "value": search_value,
+                },
+            )
+
+        # Dates
+        created_date = datetime(
+            document.created.year,
+            document.created.month,
+            document.created.day,
+            tzinfo=UTC,
+        )
+        doc.add_date("created", created_date)
+        doc.add_date("modified", document.modified)
+        doc.add_date("added", document.added)
+
+        if document.archive_serial_number is not None:
+            doc.add_unsigned("asn", document.archive_serial_number)
+
+        if document.page_count is not None:
+            doc.add_unsigned("page_count", document.page_count)
+
+        doc.add_unsigned("num_notes", num_notes)
+
+        # Owner
+        if document.owner_id:
+            doc.add_unsigned("owner_id", document.owner_id)
+
+        # Viewers with permission
+        users_with_perms = get_users_with_perms(
+            document,
+            only_with_perms_in=["view_document"],
+        )
+        for user in users_with_perms:
+            doc.add_unsigned("viewer_id", user.pk)
+
+        # Autocomplete words
+        text_sources = [document.title, content]
+        if document.correspondent:
+            text_sources.append(document.correspondent.name)
+        if document.document_type:
+            text_sources.append(document.document_type.name)
+        text_sources.extend(tag_names)
+
+        for word in sorted(_extract_autocomplete_words(text_sources)):
+            doc.add_text("autocomplete_word", word)
+
+        return doc
+
+    def add_or_update(
+        self,
+        document: Document,
+        effective_content: str | None = None,
+    ) -> None:
+        """
+        Add or update a single document with file locking.
+
+        Convenience method for single-document updates. For bulk operations,
+        use batch_update() context manager for better performance.
+
+        Args:
+            document: Django Document instance to index
+            effective_content: Override document.content for indexing
+        """
+        self._ensure_open()
+        with self.batch_update(lock_timeout=5.0) as batch:
+            batch.add_or_update(document, effective_content)
+
+    def remove(self, doc_id: int) -> None:
+        """
+        Remove a single document from the index with file locking.
+
+        Convenience method for single-document removal. For bulk operations,
+        use batch_update() context manager for better performance.
+
+        Args:
+            doc_id: Primary key of the document to remove
+        """
+        self._ensure_open()
+        with self.batch_update(lock_timeout=5.0) as batch:
+            batch.remove(doc_id)
+
+    def search(
+        self,
+        query: str,
+        user: AbstractBaseUser | None,
+        page: int,
+        page_size: int,
+        sort_field: str | None,
+        *,
+        sort_reverse: bool,
+    ) -> SearchResults:
+        """
+        Execute a search query against the document index.
+
+        Processes the user query through date rewriting, normalization, and
+        permission filtering before executing against Tantivy. Supports both
+        relevance-based and field-based sorting.
+
+        Args:
+            query: User's search query (supports natural date keywords, field filters)
+            user: User for permission filtering (None for superuser/no filtering)
+            page: Page number (1-indexed) for pagination
+            page_size: Number of results per page
+            sort_field: Field to sort by (None for relevance ranking)
+            sort_reverse: Whether to reverse the sort order
+
+        Returns:
+            SearchResults with hits, total count, and processed query
+        """
+        self._ensure_open()
+        tz = get_current_timezone()
+        user_query = parse_user_query(self._index, query, tz)
+
+        # Apply permission filter if user is not None (not superuser)
+        if user is not None:
+            permission_filter = build_permission_filter(self._schema, user)
+            final_query = tantivy.Query.boolean_query(
+                [
+                    (tantivy.Occur.Must, user_query),
+                    (tantivy.Occur.Must, permission_filter),
+                ],
+            )
+        else:
+            final_query = user_query
+
+        searcher = self._index.searcher()
+        offset = (page - 1) * page_size
+
+        # Map sort fields
+        sort_field_map = {
+            "title": "title_sort",
+            "correspondent__name": "correspondent_sort",
+            "document_type__name": "type_sort",
+            "created": "created",
+            "added": "added",
+            "modified": "modified",
+            "archive_serial_number": "asn",
+            "page_count": "page_count",
+            "num_notes": "num_notes",
+        }
+
+        # Perform search
+        if sort_field and sort_field in sort_field_map:
+            mapped_field = sort_field_map[sort_field]
+            results = searcher.search(
+                final_query,
+                limit=offset + page_size,
+                order_by_field=mapped_field,
+                order=tantivy.Order.Desc if sort_reverse else tantivy.Order.Asc,
+            )
+            # Field sorting: hits are still (score, DocAddress) tuples; score unused
+            all_hits = [(hit[1], 0.0) for hit in results.hits]
+        else:
+            # Score-based search: hits are (score, DocAddress) tuples
+            results = searcher.search(final_query, limit=offset + page_size)
+            all_hits = [(hit[1], hit[0]) for hit in results.hits]
+
+        total = results.count
+
+        # Normalize scores for score-based searches
+        if not sort_field and all_hits:
+            max_score = max(hit[1] for hit in all_hits) or 1.0
+            all_hits = [(hit[0], hit[1] / max_score) for hit in all_hits]
+
+        # Apply threshold filter if configured (score-based search only)
+        threshold = settings.ADVANCED_FUZZY_SEARCH_THRESHOLD
+        if threshold is not None and not sort_field:
+            all_hits = [hit for hit in all_hits if hit[1] >= threshold]
+
+        # Get the page's hits
+        page_hits = all_hits[offset : offset + page_size]
+
+        # Build result hits with highlights
+        hits: list[SearchHit] = []
+        snippet_generator = None
+
+        for rank, (doc_address, score) in enumerate(page_hits, start=offset + 1):
+            # Get the actual document from the searcher using the doc address
+            actual_doc = searcher.doc(doc_address)
+            doc_dict = actual_doc.to_dict()
+            doc_id = doc_dict["id"][0]
+
+            highlights: dict[str, str] = {}
+
+            # Generate highlights if score > 0
+            if score > 0:
+                try:
+                    if snippet_generator is None:
+                        snippet_generator = tantivy.SnippetGenerator.create(
+                            searcher,
+                            final_query,
+                            self._schema,
+                            "content",
+                        )
+
+                    content_snippet = snippet_generator.snippet_from_doc(actual_doc)
+                    if content_snippet:
+                        highlights["content"] = str(content_snippet)
+
+                    # Try notes highlights
+                    if "notes" in doc_dict:
+                        notes_generator = tantivy.SnippetGenerator.create(
+                            searcher,
+                            final_query,
+                            self._schema,
+                            "notes",
+                        )
+                        notes_snippet = notes_generator.snippet_from_doc(actual_doc)
+                        if notes_snippet:
+                            highlights["notes"] = str(notes_snippet)
+
+                except Exception:  # pragma: no cover
+                    logger.debug("Failed to generate highlights for doc %s", doc_id)
+
+            hits.append(
+                SearchHit(
+                    id=doc_id,
+                    score=score,
+                    rank=rank,
+                    highlights=highlights,
+                ),
+            )
+
+        return SearchResults(
+            hits=hits,
+            total=total,
+            query=query,
+        )
+
+    def autocomplete(
+        self,
+        term: str,
+        limit: int,
+        user: AbstractBaseUser | None = None,
+    ) -> list[str]:
+        """
+        Get autocomplete suggestions for search queries.
+
+        Returns words that start with the given term prefix, ranked by document
+        frequency (how many documents contain each word). Optionally filters
+        results to only words from documents visible to the specified user.
+
+        Args:
+            term: Prefix to match against autocomplete words
+            limit: Maximum number of suggestions to return
+            user: User for permission filtering (None for no filtering)
+
+        Returns:
+            List of word suggestions ordered by frequency, then alphabetically
+        """
+        self._ensure_open()
+        normalized_term = _ascii_fold(term.lower())
+
+        searcher = self._index.searcher()
+
+        # Apply permission filter for non-superusers so autocomplete words
+        # from invisible documents don't leak to other users.
+        if user is not None and not user.is_superuser:
+            base_query = build_permission_filter(self._schema, user)
+        else:
+            base_query = tantivy.Query.all_query()
+
+        results = searcher.search(base_query, limit=10000)
+
+        # Count how many visible documents each word appears in.
+        # Using Counter (not set) preserves per-word document frequency so
+        # we can rank suggestions by how commonly they occur — the same
+        # signal Whoosh used for Tf/Idf-based autocomplete ordering.
+        word_counts: Counter[str] = Counter()
+        for _score, doc_address in results.hits:
+            stored_doc = searcher.doc(doc_address)
+            doc_dict = stored_doc.to_dict()
+            if "autocomplete_word" in doc_dict:
+                word_counts.update(doc_dict["autocomplete_word"])
+
+        # Filter to prefix matches, sort by document frequency descending;
+        # break ties alphabetically for stable, deterministic output.
+        matches = sorted(
+            (w for w in word_counts if w.startswith(normalized_term)),
+            key=lambda w: (-word_counts[w], w),
+        )
+
+        return matches[:limit]
+
+    def more_like_this(
+        self,
+        doc_id: int,
+        user: AbstractBaseUser | None,
+        page: int,
+        page_size: int,
+    ) -> SearchResults:
+        """
+        Find documents similar to the given document using content analysis.
+
+        Uses Tantivy's "more like this" query to find documents with similar
+        content patterns. The original document is excluded from results.
+
+        Args:
+            doc_id: Primary key of the reference document
+            user: User for permission filtering (None for no filtering)
+            page: Page number (1-indexed) for pagination
+            page_size: Number of results per page
+
+        Returns:
+            SearchResults with similar documents (excluding the original)
+        """
+        self._ensure_open()
+        searcher = self._index.searcher()
+
+        # First find the document address
+        id_query = tantivy.Query.range_query(
+            self._schema,
+            "id",
+            tantivy.FieldType.Unsigned,
+            doc_id,
+            doc_id,
+        )
+        results = searcher.search(id_query, limit=1)
+
+        if not results.hits:
+            # Document not found
+            return SearchResults(hits=[], total=0, query=f"more_like:{doc_id}")
+
+        # Extract doc_address from (score, doc_address) tuple
+        doc_address = results.hits[0][1]
+
+        # Build more like this query
+        mlt_query = tantivy.Query.more_like_this_query(
+            doc_address,
+            min_doc_frequency=1,
+            max_doc_frequency=None,
+            min_term_frequency=1,
+            max_query_terms=12,
+            min_word_length=None,
+            max_word_length=None,
+            boost_factor=None,
+        )
+
+        # Apply permission filter
+        if user is not None:
+            permission_filter = build_permission_filter(self._schema, user)
+            final_query = tantivy.Query.boolean_query(
+                [
+                    (tantivy.Occur.Must, mlt_query),
+                    (tantivy.Occur.Must, permission_filter),
+                ],
+            )
+        else:
+            final_query = mlt_query
+
+        # Search
+        offset = (page - 1) * page_size
+        results = searcher.search(final_query, limit=offset + page_size)
+
+        total = results.count
+        # Convert from (score, doc_address) to (doc_address, score)
+        all_hits = [(hit[1], hit[0]) for hit in results.hits]
+
+        # Normalize scores
+        if all_hits:
+            max_score = max(hit[1] for hit in all_hits) or 1.0
+            all_hits = [(hit[0], hit[1] / max_score) for hit in all_hits]
+
+        # Get page hits
+        page_hits = all_hits[offset : offset + page_size]
+
+        # Build results
+        hits: list[SearchHit] = []
+        for rank, (doc_address, score) in enumerate(page_hits, start=offset + 1):
+            actual_doc = searcher.doc(doc_address)
+            doc_dict = actual_doc.to_dict()
+            result_doc_id = doc_dict["id"][0]
+
+            # Skip the original document
+            if result_doc_id == doc_id:
+                continue
+
+            hits.append(
+                SearchHit(
+                    id=result_doc_id,
+                    score=score,
+                    rank=rank,
+                    highlights={},  # MLT doesn't generate highlights
+                ),
+            )
+
+        return SearchResults(
+            hits=hits,
+            total=max(0, total - 1),  # Subtract 1 for the original document
+            query=f"more_like:{doc_id}",
+        )
+
+    def batch_update(self, lock_timeout: float = 30.0) -> WriteBatch:
+        """
+        Get a batch context manager for bulk index operations.
+
+        Use this for efficient bulk document updates/deletions. All operations
+        within the batch are committed atomically at the end of the context.
+
+        Args:
+            lock_timeout: Seconds to wait for file lock acquisition
+
+        Returns:
+            WriteBatch context manager
+
+        Raises:
+            SearchIndexLockError: If lock cannot be acquired within timeout
+        """
+        self._ensure_open()
+        return WriteBatch(self, lock_timeout)
+
+    def rebuild(
+        self,
+        documents: QuerySet[Document],
+        iter_wrapper: IterWrapper[Document] = identity,
+    ) -> None:
+        """
+        Rebuild the entire search index from scratch.
+
+        Wipes the existing index and re-indexes all provided documents.
+        On failure, restores the previous index state to keep the backend usable.
+
+        Args:
+            documents: QuerySet of Document instances to index
+            iter_wrapper: Optional wrapper function for progress tracking
+                (e.g., progress bar). Should yield each document unchanged.
+        """
+        # Create new index (on-disk or in-memory)
+        if self._path is not None:
+            wipe_index(self._path)
+            new_index = tantivy.Index(build_schema(), path=str(self._path))
+            _write_sentinels(self._path)
+        else:
+            new_index = tantivy.Index(build_schema())
+        register_tokenizers(new_index, settings.SEARCH_LANGUAGE)
+
+        # Point instance at the new index so _build_tantivy_doc uses it
+        old_index, old_schema = self._index, self._schema
+        self._index = new_index
+        self._schema = new_index.schema
+
+        try:
+            writer = new_index.writer()
+            for document in iter_wrapper(documents):
+                doc = self._build_tantivy_doc(
+                    document,
+                    document.get_effective_content(),
+                )
+                writer.add_document(doc)
+            writer.commit()
+            new_index.reload()
+        except BaseException:  # pragma: no cover
+            # Restore old index on failure so the backend remains usable
+            self._index = old_index
+            self._schema = old_schema
+            raise
+
+
+# Module-level singleton with proper thread safety
+_backend: TantivyBackend | None = None
+_backend_path: Path | None = None  # tracks which INDEX_DIR the singleton uses
+_backend_lock = threading.RLock()
+
+
+def get_backend() -> TantivyBackend:
+    """
+    Get the global backend instance with thread safety.
+
+    Returns a singleton TantivyBackend instance, automatically reinitializing
+    when settings.INDEX_DIR changes. This ensures proper test isolation when
+    using pytest-xdist or @override_settings that change the index directory.
+
+    Returns:
+        Thread-safe singleton TantivyBackend instance
+    """
+    global _backend, _backend_path
+
+    current_path: Path = settings.INDEX_DIR
+
+    # Fast path: backend is initialized and path hasn't changed (no lock needed)
+    if _backend is not None and _backend_path == current_path:
+        return _backend
+
+    # Slow path: first call, or INDEX_DIR changed between calls
+    with _backend_lock:
+        # Double-check after acquiring lock — another thread may have beaten us
+        if _backend is not None and _backend_path == current_path:
+            return _backend  # pragma: no cover
+
+        if _backend is not None:
+            _backend.close()
+
+        _backend = TantivyBackend(path=current_path)
+        _backend.open()
+        _backend_path = current_path
+
+        return _backend
+
+
+def reset_backend() -> None:
+    """
+    Reset the global backend instance with thread safety.
+
+    Forces creation of a new backend instance on the next get_backend() call.
+    Used for test isolation and when switching between different index directories.
+    """
+    global _backend, _backend_path
+
+    with _backend_lock:
+        if _backend is not None:
+            _backend.close()
+        _backend = None
+        _backend_path = None

src/documents/search/_query.py

@@ -0,0 +1,497 @@
+from __future__ import annotations
+
+from datetime import UTC
+from datetime import date
+from datetime import datetime
+from datetime import timedelta
+from typing import TYPE_CHECKING
+from typing import Final
+
+import regex
+import tantivy
+from dateutil.relativedelta import relativedelta
+from django.conf import settings
+
+if TYPE_CHECKING:
+    from datetime import tzinfo
+
+    from django.contrib.auth.base_user import AbstractBaseUser
+
+# Maximum seconds any single regex substitution may run.
+# Prevents ReDoS on adversarial user-supplied query strings.
+_REGEX_TIMEOUT: Final[float] = 1.0
+
+_DATE_ONLY_FIELDS = frozenset({"created"})
+
+_DATE_KEYWORDS = frozenset(
+    {
+        "today",
+        "yesterday",
+        "this_week",
+        "last_week",
+        "this_month",
+        "last_month",
+        "this_year",
+        "last_year",
+    },
+)
+
+_FIELD_DATE_RE = regex.compile(
+    r"(\w+):(" + "|".join(_DATE_KEYWORDS) + r")\b",
+)
+_COMPACT_DATE_RE = regex.compile(r"\b(\d{14})\b")
+_RELATIVE_RANGE_RE = regex.compile(
+    r"\[now([+-]\d+[dhm])?\s+TO\s+now([+-]\d+[dhm])?\]",
+    regex.IGNORECASE,
+)
+# Whoosh-style relative date range: e.g. [-1 week to now], [-7 days to now]
+_WHOOSH_REL_RANGE_RE = regex.compile(
+    r"\[-(?P<n>\d+)\s+(?P<unit>second|minute|hour|day|week|month|year)s?\s+to\s+now\]",
+    regex.IGNORECASE,
+)
+# Whoosh-style 8-digit date: field:YYYYMMDD — field-aware so timezone can be applied correctly
+_DATE8_RE = regex.compile(r"(?P<field>\w+):(?P<date8>\d{8})\b")
+
+
+def _fmt(dt: datetime) -> str:
+    """Format a datetime as an ISO 8601 UTC string for use in Tantivy range queries."""
+    return dt.astimezone(UTC).strftime("%Y-%m-%dT%H:%M:%SZ")
+
+
+def _iso_range(lo: datetime, hi: datetime) -> str:
+    """Format a [lo TO hi] range string in ISO 8601 for Tantivy query syntax."""
+    return f"[{_fmt(lo)} TO {_fmt(hi)}]"
+
+
+def _date_only_range(keyword: str, tz: tzinfo) -> str:
+    """
+    For `created` (DateField): use the local calendar date, converted to
+    midnight UTC boundaries. No offset arithmetic — date only.
+    """
+
+    today = datetime.now(tz).date()
+
+    if keyword == "today":
+        lo = datetime(today.year, today.month, today.day, tzinfo=UTC)
+        return _iso_range(lo, lo + timedelta(days=1))
+    if keyword == "yesterday":
+        y = today - timedelta(days=1)
+        lo = datetime(y.year, y.month, y.day, tzinfo=UTC)
+        hi = datetime(today.year, today.month, today.day, tzinfo=UTC)
+        return _iso_range(lo, hi)
+    if keyword == "this_week":
+        mon = today - timedelta(days=today.weekday())
+        lo = datetime(mon.year, mon.month, mon.day, tzinfo=UTC)
+        return _iso_range(lo, lo + timedelta(weeks=1))
+    if keyword == "last_week":
+        this_mon = today - timedelta(days=today.weekday())
+        last_mon = this_mon - timedelta(weeks=1)
+        lo = datetime(last_mon.year, last_mon.month, last_mon.day, tzinfo=UTC)
+        hi = datetime(this_mon.year, this_mon.month, this_mon.day, tzinfo=UTC)
+        return _iso_range(lo, hi)
+    if keyword == "this_month":
+        lo = datetime(today.year, today.month, 1, tzinfo=UTC)
+        if today.month == 12:
+            hi = datetime(today.year + 1, 1, 1, tzinfo=UTC)
+        else:
+            hi = datetime(today.year, today.month + 1, 1, tzinfo=UTC)
+        return _iso_range(lo, hi)
+    if keyword == "last_month":
+        if today.month == 1:
+            lo = datetime(today.year - 1, 12, 1, tzinfo=UTC)
+        else:
+            lo = datetime(today.year, today.month - 1, 1, tzinfo=UTC)
+        hi = datetime(today.year, today.month, 1, tzinfo=UTC)
+        return _iso_range(lo, hi)
+    if keyword == "this_year":
+        lo = datetime(today.year, 1, 1, tzinfo=UTC)
+        return _iso_range(lo, datetime(today.year + 1, 1, 1, tzinfo=UTC))
+    if keyword == "last_year":
+        lo = datetime(today.year - 1, 1, 1, tzinfo=UTC)
+        return _iso_range(lo, datetime(today.year, 1, 1, tzinfo=UTC))
+    raise ValueError(f"Unknown keyword: {keyword}")
+
+
+def _datetime_range(keyword: str, tz: tzinfo) -> str:
+    """
+    For `added` / `modified` (DateTimeField, stored as UTC): convert local day
+    boundaries to UTC — full offset arithmetic required.
+    """
+
+    now_local = datetime.now(tz)
+    today = now_local.date()
+
+    def _midnight(d: date) -> datetime:
+        return datetime(d.year, d.month, d.day, tzinfo=tz).astimezone(UTC)
+
+    if keyword == "today":
+        return _iso_range(_midnight(today), _midnight(today + timedelta(days=1)))
+    if keyword == "yesterday":
+        y = today - timedelta(days=1)
+        return _iso_range(_midnight(y), _midnight(today))
+    if keyword == "this_week":
+        mon = today - timedelta(days=today.weekday())
+        return _iso_range(_midnight(mon), _midnight(mon + timedelta(weeks=1)))
+    if keyword == "last_week":
+        this_mon = today - timedelta(days=today.weekday())
+        last_mon = this_mon - timedelta(weeks=1)
+        return _iso_range(_midnight(last_mon), _midnight(this_mon))
+    if keyword == "this_month":
+        first = today.replace(day=1)
+        if today.month == 12:
+            next_first = date(today.year + 1, 1, 1)
+        else:
+            next_first = date(today.year, today.month + 1, 1)
+        return _iso_range(_midnight(first), _midnight(next_first))
+    if keyword == "last_month":
+        this_first = today.replace(day=1)
+        if today.month == 1:
+            last_first = date(today.year - 1, 12, 1)
+        else:
+            last_first = date(today.year, today.month - 1, 1)
+        return _iso_range(_midnight(last_first), _midnight(this_first))
+    if keyword == "this_year":
+        return _iso_range(
+            _midnight(date(today.year, 1, 1)),
+            _midnight(date(today.year + 1, 1, 1)),
+        )
+    if keyword == "last_year":
+        return _iso_range(
+            _midnight(date(today.year - 1, 1, 1)),
+            _midnight(date(today.year, 1, 1)),
+        )
+    raise ValueError(f"Unknown keyword: {keyword}")
+
+
+def _rewrite_compact_date(query: str) -> str:
+    """Rewrite Whoosh compact date tokens (14-digit YYYYMMDDHHmmss) to ISO 8601."""
+
+    def _sub(m: regex.Match[str]) -> str:
+        raw = m.group(1)
+        try:
+            dt = datetime(
+                int(raw[0:4]),
+                int(raw[4:6]),
+                int(raw[6:8]),
+                int(raw[8:10]),
+                int(raw[10:12]),
+                int(raw[12:14]),
+                tzinfo=UTC,
+            )
+            return dt.strftime("%Y-%m-%dT%H:%M:%SZ")
+        except ValueError:
+            return str(m.group(0))
+
+    try:
+        return _COMPACT_DATE_RE.sub(_sub, query, timeout=_REGEX_TIMEOUT)
+    except TimeoutError:  # pragma: no cover
+        raise ValueError(
+            "Query too complex to process (compact date rewrite timed out)",
+        )
+
+
+def _rewrite_relative_range(query: str) -> str:
+    """Rewrite Whoosh relative ranges ([now-7d TO now]) to concrete ISO 8601 UTC boundaries."""
+
+    def _sub(m: regex.Match[str]) -> str:
+        now = datetime.now(UTC)
+
+        def _offset(s: str | None) -> timedelta:
+            if not s:
+                return timedelta(0)
+            sign = 1 if s[0] == "+" else -1
+            n, unit = int(s[1:-1]), s[-1]
+            return (
+                sign
+                * {
+                    "d": timedelta(days=n),
+                    "h": timedelta(hours=n),
+                    "m": timedelta(minutes=n),
+                }[unit]
+            )
+
+        lo, hi = now + _offset(m.group(1)), now + _offset(m.group(2))
+        if lo > hi:
+            lo, hi = hi, lo
+        return f"[{_fmt(lo)} TO {_fmt(hi)}]"
+
+    try:
+        return _RELATIVE_RANGE_RE.sub(_sub, query, timeout=_REGEX_TIMEOUT)
+    except TimeoutError:  # pragma: no cover
+        raise ValueError(
+            "Query too complex to process (relative range rewrite timed out)",
+        )
+
+
+def _rewrite_whoosh_relative_range(query: str) -> str:
+    """Rewrite Whoosh-style relative date ranges ([-N unit to now]) to ISO 8601.
+
+    Supports: second, minute, hour, day, week, month, year (singular and plural).
+    Example: ``added:[-1 week to now]`` → ``added:[2025-01-01T… TO 2025-01-08T…]``
+    """
+    now = datetime.now(UTC)
+
+    def _sub(m: regex.Match[str]) -> str:
+        n = int(m.group("n"))
+        unit = m.group("unit").lower()
+        delta_map: dict[str, timedelta | relativedelta] = {
+            "second": timedelta(seconds=n),
+            "minute": timedelta(minutes=n),
+            "hour": timedelta(hours=n),
+            "day": timedelta(days=n),
+            "week": timedelta(weeks=n),
+            "month": relativedelta(months=n),
+            "year": relativedelta(years=n),
+        }
+        lo = now - delta_map[unit]
+        return f"[{_fmt(lo)} TO {_fmt(now)}]"
+
+    try:
+        return _WHOOSH_REL_RANGE_RE.sub(_sub, query, timeout=_REGEX_TIMEOUT)
+    except TimeoutError:  # pragma: no cover
+        raise ValueError(
+            "Query too complex to process (Whoosh relative range rewrite timed out)",
+        )
+
+
+def _rewrite_8digit_date(query: str, tz: tzinfo) -> str:
+    """Rewrite field:YYYYMMDD date tokens to an ISO 8601 day range.
+
+    Runs after ``_rewrite_compact_date`` so 14-digit timestamps are already
+    converted and won't spuriously match here.
+
+    For DateField fields (e.g. ``created``) uses UTC midnight boundaries.
+    For DateTimeField fields (e.g. ``added``, ``modified``) uses local TZ
+    midnight boundaries converted to UTC — matching the ``_datetime_range``
+    behaviour for keyword dates.
+    """
+
+    def _sub(m: regex.Match[str]) -> str:
+        field = m.group("field")
+        raw = m.group("date8")
+        try:
+            year, month, day = int(raw[0:4]), int(raw[4:6]), int(raw[6:8])
+            d = date(year, month, day)
+            if field in _DATE_ONLY_FIELDS:
+                lo = datetime(d.year, d.month, d.day, tzinfo=UTC)
+                hi = lo + timedelta(days=1)
+            else:
+                # DateTimeField: use local-timezone midnight → UTC
+                lo = datetime(d.year, d.month, d.day, tzinfo=tz).astimezone(UTC)
+                hi = datetime(
+                    (d + timedelta(days=1)).year,
+                    (d + timedelta(days=1)).month,
+                    (d + timedelta(days=1)).day,
+                    tzinfo=tz,
+                ).astimezone(UTC)
+            return f"{field}:[{_fmt(lo)} TO {_fmt(hi)}]"
+        except ValueError:
+            return m.group(0)
+
+    try:
+        return _DATE8_RE.sub(_sub, query, timeout=_REGEX_TIMEOUT)
+    except TimeoutError:  # pragma: no cover
+        raise ValueError(
+            "Query too complex to process (8-digit date rewrite timed out)",
+        )
+
+
+def rewrite_natural_date_keywords(query: str, tz: tzinfo) -> str:
+    """
+    Rewrite natural date syntax to ISO 8601 format for Tantivy compatibility.
+
+    Performs the first stage of query preprocessing, converting various date
+    formats and keywords to ISO 8601 datetime ranges that Tantivy can parse:
+    - Compact 14-digit dates (YYYYMMDDHHmmss)
+    - Whoosh relative ranges ([-7 days to now], [now-1h TO now+2h])
+    - 8-digit dates with field awareness (created:20240115)
+    - Natural keywords (field:today, field:last_week, etc.)
+
+    Args:
+        query: Raw user query string
+        tz: Timezone for converting local date boundaries to UTC
+
+    Returns:
+        Query with date syntax rewritten to ISO 8601 ranges
+
+    Note:
+        Bare keywords without field prefixes pass through unchanged.
+    """
+    query = _rewrite_compact_date(query)
+    query = _rewrite_whoosh_relative_range(query)
+    query = _rewrite_8digit_date(query, tz)
+    query = _rewrite_relative_range(query)
+
+    def _replace(m: regex.Match[str]) -> str:
+        field, keyword = m.group(1), m.group(2)
+        if field in _DATE_ONLY_FIELDS:
+            return f"{field}:{_date_only_range(keyword, tz)}"
+        return f"{field}:{_datetime_range(keyword, tz)}"
+
+    try:
+        return _FIELD_DATE_RE.sub(_replace, query, timeout=_REGEX_TIMEOUT)
+    except TimeoutError:  # pragma: no cover
+        raise ValueError(
+            "Query too complex to process (date keyword rewrite timed out)",
+        )
+
+
+def normalize_query(query: str) -> str:
+    """
+    Normalize query syntax for better search behavior.
+
+    Expands comma-separated field values to explicit AND clauses and
+    collapses excessive whitespace for cleaner parsing:
+    - tag:foo,bar → tag:foo AND tag:bar
+    - multiple spaces → single spaces
+
+    Args:
+        query: Query string after date rewriting
+
+    Returns:
+        Normalized query string ready for Tantivy parsing
+    """
+
+    def _expand(m: regex.Match[str]) -> str:
+        field = m.group(1)
+        values = [v.strip() for v in m.group(2).split(",") if v.strip()]
+        return " AND ".join(f"{field}:{v}" for v in values)
+
+    try:
+        query = regex.sub(
+            r"(\w+):([^\s\[\]]+(?:,[^\s\[\]]+)+)",
+            _expand,
+            query,
+            timeout=_REGEX_TIMEOUT,
+        )
+        return regex.sub(r" {2,}", " ", query, timeout=_REGEX_TIMEOUT).strip()
+    except TimeoutError:  # pragma: no cover
+        raise ValueError("Query too complex to process (normalization timed out)")
+
+
+_MAX_U64 = 2**64 - 1  # u64 max — used as inclusive upper bound for "any owner" range
+
+
+def build_permission_filter(
+    schema: tantivy.Schema,
+    user: AbstractBaseUser,
+) -> tantivy.Query:
+    """
+    Build a query filter for user document permissions.
+
+    Creates a query that matches only documents visible to the specified user
+    according to paperless-ngx permission rules:
+    - Public documents (no owner) are visible to all users
+    - Private documents are visible to their owner
+    - Documents explicitly shared with the user are visible
+
+    Args:
+        schema: Tantivy schema for field validation
+        user: User to check permissions for
+
+    Returns:
+        Tantivy query that filters results to visible documents
+
+    Implementation Notes:
+        - Uses range_query instead of term_query to work around unsigned integer
+          type detection bug in tantivy-py 0.25
+        - Uses boolean_query for "no owner" check since exists_query is not
+          available in tantivy-py 0.25.1 (available in master)
+        - Uses disjunction_max_query to combine permission clauses with OR logic
+    """
+    owner_any = tantivy.Query.range_query(
+        schema,
+        "owner_id",
+        tantivy.FieldType.Unsigned,
+        1,
+        _MAX_U64,
+    )
+    no_owner = tantivy.Query.boolean_query(
+        [
+            (tantivy.Occur.Must, tantivy.Query.all_query()),
+            (tantivy.Occur.MustNot, owner_any),
+        ],
+    )
+    owned = tantivy.Query.range_query(
+        schema,
+        "owner_id",
+        tantivy.FieldType.Unsigned,
+        user.pk,
+        user.pk,
+    )
+    shared = tantivy.Query.range_query(
+        schema,
+        "viewer_id",
+        tantivy.FieldType.Unsigned,
+        user.pk,
+        user.pk,
+    )
+    return tantivy.Query.disjunction_max_query([no_owner, owned, shared])
+
+
+DEFAULT_SEARCH_FIELDS = [
+    "title",
+    "content",
+    "correspondent",
+    "document_type",
+    "tag",
+]
+_FIELD_BOOSTS = {"title": 2.0}
+
+
+def parse_user_query(
+    index: tantivy.Index,
+    raw_query: str,
+    tz: tzinfo,
+) -> tantivy.Query:
+    """
+    Parse user query through the complete preprocessing pipeline.
+
+    Transforms the raw user query through multiple stages:
+    1. Date keyword rewriting (today → ISO 8601 ranges)
+    2. Query normalization (comma expansion, whitespace cleanup)
+    3. Tantivy parsing with field boosts
+    4. Optional fuzzy query blending (if ADVANCED_FUZZY_SEARCH_THRESHOLD set)
+
+    Args:
+        index: Tantivy index with registered tokenizers
+        raw_query: Original user query string
+        tz: Timezone for date boundary calculations
+
+    Returns:
+        Parsed Tantivy query ready for execution
+
+    Note:
+        When ADVANCED_FUZZY_SEARCH_THRESHOLD is configured, adds a low-priority
+        fuzzy query as a Should clause (0.1 boost) to catch approximate matches
+        while keeping exact matches ranked higher. The threshold value is applied
+        as a post-search score filter, not during query construction.
+    """
+
+    query_str = rewrite_natural_date_keywords(raw_query, tz)
+    query_str = normalize_query(query_str)
+
+    exact = index.parse_query(
+        query_str,
+        DEFAULT_SEARCH_FIELDS,
+        field_boosts=_FIELD_BOOSTS,
+    )
+
+    threshold = settings.ADVANCED_FUZZY_SEARCH_THRESHOLD
+    if threshold is not None:
+        fuzzy = index.parse_query(
+            query_str,
+            DEFAULT_SEARCH_FIELDS,
+            field_boosts=_FIELD_BOOSTS,
+            # (prefix=True, distance=1, transposition_cost_one=True) — edit-distance fuzziness
+            fuzzy_fields={f: (True, 1, True) for f in DEFAULT_SEARCH_FIELDS},
+        )
+        return tantivy.Query.boolean_query(
+            [
+                (tantivy.Occur.Should, exact),
+                # 0.1 boost keeps fuzzy hits ranked below exact matches (intentional)
+                (tantivy.Occur.Should, tantivy.Query.boost_query(fuzzy, 0.1)),
+            ],
+        )
+
+    return exact

src/documents/search/_schema.py

@@ -0,0 +1,165 @@
+from __future__ import annotations
+
+import logging
+import shutil
+from typing import TYPE_CHECKING
+
+import tantivy
+from django.conf import settings
+
+if TYPE_CHECKING:
+    from pathlib import Path
+
+logger = logging.getLogger("paperless.search")
+
+SCHEMA_VERSION = 1
+
+
+def build_schema() -> tantivy.Schema:
+    """
+    Build the Tantivy schema for the paperless document index.
+
+    Creates a comprehensive schema supporting full-text search, filtering,
+    sorting, and autocomplete functionality. Includes fields for document
+    content, metadata, permissions, custom fields, and notes.
+
+    Returns:
+        Configured Tantivy schema ready for index creation
+    """
+    sb = tantivy.SchemaBuilder()
+
+    sb.add_unsigned_field("id", stored=True, indexed=True, fast=True)
+    sb.add_text_field("checksum", stored=True, tokenizer_name="raw")
+
+    for field in (
+        "title",
+        "correspondent",
+        "document_type",
+        "storage_path",
+        "original_filename",
+        "content",
+    ):
+        sb.add_text_field(field, stored=True, tokenizer_name="paperless_text")
+
+    # Shadow sort fields - fast, not stored/indexed
+    for field in ("title_sort", "correspondent_sort", "type_sort"):
+        sb.add_text_field(
+            field,
+            stored=False,
+            tokenizer_name="simple_analyzer",
+            fast=True,
+        )
+
+    # CJK support - not stored, indexed only
+    sb.add_text_field("bigram_content", stored=False, tokenizer_name="bigram_analyzer")
+
+    # Autocomplete prefix scan - stored, not indexed
+    sb.add_text_field("autocomplete_word", stored=True, tokenizer_name="raw")
+
+    sb.add_text_field("tag", stored=True, tokenizer_name="paperless_text")
+
+    # JSON fields — structured queries: notes.user:alice, custom_fields.name:invoice
+    sb.add_json_field("notes", stored=True, tokenizer_name="paperless_text")
+    sb.add_json_field("custom_fields", stored=True, tokenizer_name="paperless_text")
+
+    for field in (
+        "correspondent_id",
+        "document_type_id",
+        "storage_path_id",
+        "tag_id",
+        "owner_id",
+        "viewer_id",
+    ):
+        sb.add_unsigned_field(field, stored=False, indexed=True, fast=True)
+
+    for field in ("created", "modified", "added"):
+        sb.add_date_field(field, stored=True, indexed=True, fast=True)
+
+    for field in ("asn", "page_count", "num_notes"):
+        sb.add_unsigned_field(field, stored=True, indexed=True, fast=True)
+
+    return sb.build()
+
+
+def needs_rebuild(index_dir: Path) -> bool:
+    """
+    Check if the search index needs rebuilding.
+
+    Compares the current schema version and search language configuration
+    against sentinel files to determine if the index is compatible with
+    the current paperless-ngx version and settings.
+
+    Args:
+        index_dir: Path to the search index directory
+
+    Returns:
+        True if the index needs rebuilding, False if it's up to date
+    """
+    version_file = index_dir / ".schema_version"
+    if not version_file.exists():
+        return True
+    try:
+        if int(version_file.read_text().strip()) != SCHEMA_VERSION:
+            logger.info("Search index schema version mismatch - rebuilding.")
+            return True
+    except ValueError:
+        return True
+
+    language_file = index_dir / ".schema_language"
+    if not language_file.exists():
+        logger.info("Search index language sentinel missing - rebuilding.")
+        return True
+    if language_file.read_text().strip() != (settings.SEARCH_LANGUAGE or ""):
+        logger.info("Search index language changed - rebuilding.")
+        return True
+
+    return False
+
+
+def wipe_index(index_dir: Path) -> None:
+    """
+    Delete all contents of the index directory to prepare for rebuild.
+
+    Recursively removes all files and subdirectories within the index
+    directory while preserving the directory itself.
+
+    Args:
+        index_dir: Path to the search index directory to clear
+    """
+    for child in index_dir.iterdir():
+        if child.is_dir():
+            shutil.rmtree(child)
+        else:
+            child.unlink()
+
+
+def _write_sentinels(index_dir: Path) -> None:
+    """Write schema version and language sentinel files so the next index open can skip rebuilding."""
+    (index_dir / ".schema_version").write_text(str(SCHEMA_VERSION))
+    (index_dir / ".schema_language").write_text(settings.SEARCH_LANGUAGE or "")
+
+
+def open_or_rebuild_index(index_dir: Path | None = None) -> tantivy.Index:
+    """
+    Open the Tantivy index, creating or rebuilding as needed.
+
+    Checks if the index needs rebuilding due to schema version or language
+    changes. If rebuilding is needed, wipes the directory and creates a fresh
+    index with the current schema and configuration.
+
+    Args:
+        index_dir: Path to index directory (defaults to settings.INDEX_DIR)
+
+    Returns:
+        Opened Tantivy index (caller must register custom tokenizers)
+    """
+    if index_dir is None:
+        index_dir = settings.INDEX_DIR
+    if not index_dir.exists():
+        return tantivy.Index(build_schema())
+    if needs_rebuild(index_dir):
+        wipe_index(index_dir)
+        idx = tantivy.Index(build_schema(), path=str(index_dir))
+        _write_sentinels(index_dir)
+        return idx
+    return tantivy.Index.open(str(index_dir))

src/documents/search/_tokenizer.py

@@ -0,0 +1,116 @@
+from __future__ import annotations
+
+import logging
+
+import tantivy
+
+logger = logging.getLogger("paperless.search")
+
+# Mapping of ISO 639-1 codes (and common aliases) -> Tantivy Snowball name
+_LANGUAGE_MAP: dict[str, str] = {
+    "ar": "Arabic",
+    "arabic": "Arabic",
+    "da": "Danish",
+    "danish": "Danish",
+    "nl": "Dutch",
+    "dutch": "Dutch",
+    "en": "English",
+    "english": "English",
+    "fi": "Finnish",
+    "finnish": "Finnish",
+    "fr": "French",
+    "french": "French",
+    "de": "German",
+    "german": "German",
+    "el": "Greek",
+    "greek": "Greek",
+    "hu": "Hungarian",
+    "hungarian": "Hungarian",
+    "it": "Italian",
+    "italian": "Italian",
+    "no": "Norwegian",
+    "norwegian": "Norwegian",
+    "pt": "Portuguese",
+    "portuguese": "Portuguese",
+    "ro": "Romanian",
+    "romanian": "Romanian",
+    "ru": "Russian",
+    "russian": "Russian",
+    "es": "Spanish",
+    "spanish": "Spanish",
+    "sv": "Swedish",
+    "swedish": "Swedish",
+    "ta": "Tamil",
+    "tamil": "Tamil",
+    "tr": "Turkish",
+    "turkish": "Turkish",
+}
+
+SUPPORTED_LANGUAGES: frozenset[str] = frozenset(_LANGUAGE_MAP)
+
+
+def register_tokenizers(index: tantivy.Index, language: str | None) -> None:
+    """
+    Register all custom tokenizers required by the paperless schema.
+
+    Must be called on every Index instance since Tantivy requires tokenizer
+    re-registration after each index open/creation. Registers tokenizers for
+    full-text search, sorting, CJK language support, and fast-field indexing.
+
+    Args:
+        index: Tantivy index instance to register tokenizers on
+        language: ISO 639-1 language code for stemming (None to disable)
+
+    Note:
+        simple_analyzer is registered as both a text and fast-field tokenizer
+        since sort shadow fields (title_sort, correspondent_sort, type_sort)
+        use fast=True and Tantivy requires fast-field tokenizers to exist
+        even for documents that omit those fields.
+    """
+    index.register_tokenizer("paperless_text", _paperless_text(language))
+    index.register_tokenizer("simple_analyzer", _simple_analyzer())
+    index.register_tokenizer("bigram_analyzer", _bigram_analyzer())
+    # Fast-field tokenizer required for fast=True text fields in the schema
+    index.register_fast_field_tokenizer("simple_analyzer", _simple_analyzer())
+
+
+def _paperless_text(language: str | None) -> tantivy.TextAnalyzer:
+    """Main full-text tokenizer for content, title, etc: simple -> remove_long(65) -> lowercase -> ascii_fold [-> stemmer]"""
+    builder = (
+        tantivy.TextAnalyzerBuilder(tantivy.Tokenizer.simple())
+        .filter(tantivy.Filter.remove_long(65))
+        .filter(tantivy.Filter.lowercase())
+        .filter(tantivy.Filter.ascii_fold())
+    )
+    if language:
+        tantivy_lang = _LANGUAGE_MAP.get(language.lower())
+        if tantivy_lang:
+            builder = builder.filter(tantivy.Filter.stemmer(tantivy_lang))
+        else:
+            logger.warning(
+                "Unsupported search language '%s' - stemming disabled. Supported: %s",
+                language,
+                ", ".join(sorted(SUPPORTED_LANGUAGES)),
+            )
+    return builder.build()
+
+
+def _simple_analyzer() -> tantivy.TextAnalyzer:
+    """Tokenizer for shadow sort fields (title_sort, correspondent_sort, type_sort): simple -> lowercase -> ascii_fold."""
+    return (
+        tantivy.TextAnalyzerBuilder(tantivy.Tokenizer.simple())
+        .filter(tantivy.Filter.lowercase())
+        .filter(tantivy.Filter.ascii_fold())
+        .build()
+    )
+
+
+def _bigram_analyzer() -> tantivy.TextAnalyzer:
+    """Enables substring search in CJK text: ngram(2,2) -> lowercase. CJK / no-whitespace language support."""
+    return (
+        tantivy.TextAnalyzerBuilder(
+            tantivy.Tokenizer.ngram(min_gram=2, max_gram=2, prefix_only=False),
+        )
+        .filter(tantivy.Filter.lowercase())
+        .build()
+    )

src/documents/serialisers.py

@@ -1293,22 +1293,18 @@ class SearchResultSerializer(DocumentSerializer):
         documents = self.context.get("documents")
         # Otherwise we fetch this document.
         if documents is None:  # pragma: no cover
-            # In practice we only serialize **lists** of whoosh.searching.Hit.
+            # In practice we only serialize **lists** of SearchHit dicts.
-            # I'm keeping this check for completeness but marking it no cover for now.
+            # Keeping this check for completeness but marking it no cover for now.
             documents = self.fetch_documents([hit["id"]])
         document = documents[hit["id"]]
 
-        notes = ",".join(
+        highlights = hit.get("highlights", {})
-            [str(c.note) for c in document.notes.all()],
-        )
         r = super().to_representation(document)
         r["__search_hit__"] = {
-            "score": hit.score,
+            "score": hit["score"],
-            "highlights": hit.highlights("content", text=document.content),
+            "highlights": highlights.get("content", ""),
-            "note_highlights": (
+            "note_highlights": highlights.get("notes") or None,
-                hit.highlights("notes", text=notes) if document else None
+            "rank": hit["rank"],
-            ),
-            "rank": hit.rank,
         }
 
         return r
@@ -1558,6 +1554,41 @@ class DocumentListSerializer(serializers.Serializer):
         return documents
 
 
+class DocumentSelectionSerializer(DocumentListSerializer):
+    documents = serializers.ListField(
+        required=False,
+        label="Documents",
+        write_only=True,
+        child=serializers.IntegerField(),
+    )
+
+    all = serializers.BooleanField(
+        default=False,
+        required=False,
+        write_only=True,
+    )
+
+    filters = serializers.DictField(
+        required=False,
+        allow_empty=True,
+        write_only=True,
+    )
+
+    def validate(self, attrs):
+        if attrs.get("all", False):
+            attrs.setdefault("documents", [])
+            return attrs
+
+        if "documents" not in attrs:
+            raise serializers.ValidationError(
+                "documents is required unless all is true.",
+            )
+
+        documents = attrs["documents"]
+        self._validate_document_id_list(documents)
+        return attrs
+
+
 class SourceModeValidationMixin:
     def validate_source_mode(self, source_mode: str) -> str:
         if source_mode not in bulk_edit.SourceModeChoices.__dict__.values():
@@ -1565,7 +1596,7 @@ class SourceModeValidationMixin:
         return source_mode
 
 
-class RotateDocumentsSerializer(DocumentListSerializer, SourceModeValidationMixin):
+class RotateDocumentsSerializer(DocumentSelectionSerializer, SourceModeValidationMixin):
     degrees = serializers.IntegerField(required=True)
     source_mode = serializers.CharField(
         required=False,
@@ -1648,17 +1679,17 @@ class RemovePasswordDocumentsSerializer(
     )
 
 
-class DeleteDocumentsSerializer(DocumentListSerializer):
+class DeleteDocumentsSerializer(DocumentSelectionSerializer):
     pass
 
 
-class ReprocessDocumentsSerializer(DocumentListSerializer):
+class ReprocessDocumentsSerializer(DocumentSelectionSerializer):
     pass
 
 
 class BulkEditSerializer(
     SerializerWithPerms,
-    DocumentListSerializer,
+    DocumentSelectionSerializer,
     SetPermissionsMixin,
     SourceModeValidationMixin,
 ):
@@ -1986,6 +2017,19 @@ class BulkEditSerializer(
             raise serializers.ValidationError("password must be a string")
 
     def validate(self, attrs):
+        attrs = super().validate(attrs)
+
+        if attrs.get("all", False) and attrs["method"] in [
+            bulk_edit.merge,
+            bulk_edit.split,
+            bulk_edit.delete_pages,
+            bulk_edit.edit_pdf,
+            bulk_edit.remove_password,
+        ]:
+            raise serializers.ValidationError(
+                "This method does not support all=true.",
+            )
+
         method = attrs["method"]
         parameters = attrs["parameters"]
 
@@ -2243,7 +2287,7 @@ class DocumentVersionLabelSerializer(serializers.Serializer):
         return normalized or None
 
 
-class BulkDownloadSerializer(DocumentListSerializer):
+class BulkDownloadSerializer(DocumentSelectionSerializer):
     content = serializers.ChoiceField(
         choices=["archive", "originals", "both"],
         default="archive",
@@ -2602,13 +2646,25 @@ class ShareLinkBundleSerializer(OwnedObjectSerializer):
 
 class BulkEditObjectsSerializer(SerializerWithPerms, SetPermissionsMixin):
     objects = serializers.ListField(
-        required=True,
+        required=False,
-        allow_empty=False,
+        allow_empty=True,
         label="Objects",
         write_only=True,
         child=serializers.IntegerField(),
     )
 
+    all = serializers.BooleanField(
+        default=False,
+        required=False,
+        write_only=True,
+    )
+
+    filters = serializers.DictField(
+        required=False,
+        allow_empty=True,
+        write_only=True,
+    )
+
     object_type = serializers.ChoiceField(
         choices=[
             "tags",
@@ -2681,10 +2737,20 @@ class BulkEditObjectsSerializer(SerializerWithPerms, SetPermissionsMixin):
 
     def validate(self, attrs):
         object_type = attrs["object_type"]
-        objects = attrs["objects"]
+        objects = attrs.get("objects")
+        apply_to_all = attrs.get("all", False)
         operation = attrs.get("operation")
 
-        self._validate_objects(objects, object_type)
+        if apply_to_all:
+            attrs.setdefault("objects", [])
+        else:
+            if objects is None:
+                raise serializers.ValidationError(
+                    "objects is required unless all is true.",
+                )
+            if len(objects) == 0:
+                raise serializers.ValidationError("objects must not be empty")
+            self._validate_objects(objects, object_type)
 
         if operation == "set_permissions":
             permissions = attrs.get("permissions")

src/documents/signals/handlers.py

@@ -790,15 +790,12 @@ def cleanup_user_deletion(sender, instance: User | Group, **kwargs) -> None:
 
 
 def add_to_index(sender, document, **kwargs) -> None:
-    from documents import index
+    from documents.search import get_backend
 
-    index.add_or_update_document(document)
+    get_backend().add_or_update(
-    if document.root_document_id is not None and document.root_document is not None:
+        document,
-        # keep in sync when a new version is consumed.
+        effective_content=document.get_effective_content(),
-        index.add_or_update_document(
+    )
-            document.root_document,
-            effective_content=document.content,
-        )
 
 
 def run_workflows_added(

src/documents/tasks.py

@@ -4,11 +4,9 @@ import shutil
 import uuid
 import zipfile
 from collections.abc import Callable
-from collections.abc import Iterable
 from pathlib import Path
 from tempfile import TemporaryDirectory
 from tempfile import mkstemp
-from typing import TypeVar
 
 from celery import Task
 from celery import shared_task
@@ -20,9 +18,7 @@ from django.db import transaction
 from django.db.models.signals import post_save
 from django.utils import timezone
 from filelock import FileLock
-from whoosh.writing import AsyncWriter
 
-from documents import index
 from documents import sanity_checker
 from documents.barcodes import BarcodePlugin
 from documents.bulk_download import ArchiveOnlyStrategy
@@ -60,7 +56,9 @@ from documents.signals import document_updated
 from documents.signals.handlers import cleanup_document_deletion
 from documents.signals.handlers import run_workflows
 from documents.signals.handlers import send_websocket_document_updated
+from documents.utils import IterWrapper
 from documents.utils import compute_checksum
+from documents.utils import identity
 from documents.workflows.utils import get_workflows_for_trigger
 from paperless.config import AIConfig
 from paperless.parsers import ParserContext
@@ -69,34 +67,16 @@ from paperless_ai.indexing import llm_index_add_or_update_document
 from paperless_ai.indexing import llm_index_remove_document
 from paperless_ai.indexing import update_llm_index
 
-_T = TypeVar("_T")
-IterWrapper = Callable[[Iterable[_T]], Iterable[_T]]
-
-
 if settings.AUDIT_LOG_ENABLED:
     from auditlog.models import LogEntry
 logger = logging.getLogger("paperless.tasks")
 
 
-def _identity(iterable: Iterable[_T]) -> Iterable[_T]:
-    return iterable
-
-
 @shared_task
 def index_optimize() -> None:
-    ix = index.open_index()
+    logger.info(
-    writer = AsyncWriter(ix)
+        "index_optimize is a no-op — Tantivy manages segment merging automatically.",
-    writer.commit(optimize=True)
+    )
-
-
-def index_reindex(*, iter_wrapper: IterWrapper[Document] = _identity) -> None:
-    documents = Document.objects.all()
-
-    ix = index.open_index(recreate=True)
-
-    with AsyncWriter(ix) as writer:
-        for document in iter_wrapper(documents):
-            index.update_document(writer, document)
 
 
 @shared_task
@@ -270,9 +250,9 @@ def sanity_check(*, scheduled=True, raise_on_error=True):
 
 @shared_task
 def bulk_update_documents(document_ids) -> None:
-    documents = Document.objects.filter(id__in=document_ids)
+    from documents.search import get_backend
 
-    ix = index.open_index()
+    documents = Document.objects.filter(id__in=document_ids)
 
     for doc in documents:
         clear_document_caches(doc.pk)
@@ -283,9 +263,9 @@ def bulk_update_documents(document_ids) -> None:
         )
         post_save.send(Document, instance=doc, created=False)
 
-    with AsyncWriter(ix) as writer:
+    with get_backend().batch_update() as batch:
         for doc in documents:
-            index.update_document(writer, doc)
+            batch.add_or_update(doc)
 
     ai_config = AIConfig()
     if ai_config.llm_index_enabled:
@@ -389,8 +369,9 @@ def update_document_content_maybe_archive_file(document_id) -> None:
             logger.info(
                 f"Updating index for document {document_id} ({document.archive_checksum})",
             )
-            with index.open_index_writer() as writer:
+            from documents.search import get_backend
-                index.update_document(writer, document)
+
+            get_backend().add_or_update(document)
 
             ai_config = AIConfig()
             if ai_config.llm_index_enabled:
@@ -633,7 +614,7 @@ def update_document_parent_tags(tag: Tag, new_parent: Tag) -> None:
 @shared_task
 def llmindex_index(
     *,
-    iter_wrapper: IterWrapper[Document] = _identity,
+    iter_wrapper: IterWrapper[Document] = identity,
     rebuild=False,
     scheduled=True,
     auto=False,

src/documents/tests/conftest.py

@@ -1,5 +1,6 @@
 import shutil
 import zoneinfo
+from collections.abc import Generator
 from dataclasses import dataclass
 from pathlib import Path
 from typing import TYPE_CHECKING
@@ -92,6 +93,26 @@ def sample_doc(
     )
 
 
+@pytest.fixture()
+def _search_index(
+    tmp_path: Path,
+    settings: SettingsWrapper,
+) -> Generator[None, None, None]:
+    """Create a temp index directory and point INDEX_DIR at it.
+
+    Resets the backend singleton before and after so each test gets a clean
+    index rather than reusing a stale singleton from another test.
+    """
+    from documents.search import reset_backend
+
+    index_dir = tmp_path / "index"
+    index_dir.mkdir()
+    settings.INDEX_DIR = index_dir
+    reset_backend()
+    yield
+    reset_backend()
+
+
 @pytest.fixture()
 def settings_timezone(settings: SettingsWrapper) -> zoneinfo.ZoneInfo:
     return zoneinfo.ZoneInfo(settings.TIME_ZONE)

src/documents/tests/search/conftest.py

@@ -0,0 +1,33 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+import pytest
+
+from documents.search._backend import TantivyBackend
+from documents.search._backend import reset_backend
+
+if TYPE_CHECKING:
+    from collections.abc import Generator
+    from pathlib import Path
+
+    from pytest_django.fixtures import SettingsWrapper
+
+
+@pytest.fixture
+def index_dir(tmp_path: Path, settings: SettingsWrapper) -> Path:
+    path = tmp_path / "index"
+    path.mkdir()
+    settings.INDEX_DIR = path
+    return path
+
+
+@pytest.fixture
+def backend() -> Generator[TantivyBackend, None, None]:
+    b = TantivyBackend()  # path=None → in-memory index
+    b.open()
+    try:
+        yield b
+    finally:
+        b.close()
+        reset_backend()

src/documents/tests/search/test_backend.py

@@ -0,0 +1,502 @@
+import pytest
+from django.contrib.auth.models import User
+
+from documents.models import CustomField
+from documents.models import CustomFieldInstance
+from documents.models import Document
+from documents.models import Note
+from documents.search._backend import TantivyBackend
+from documents.search._backend import get_backend
+from documents.search._backend import reset_backend
+
+pytestmark = [pytest.mark.search, pytest.mark.django_db]
+
+
+class TestWriteBatch:
+    """Test WriteBatch context manager functionality."""
+
+    def test_rolls_back_on_exception(self, backend: TantivyBackend):
+        """Batch operations must rollback on exception to preserve index integrity."""
+        doc = Document.objects.create(
+            title="Rollback Target",
+            content="should survive",
+            checksum="RB1",
+            pk=1,
+        )
+        backend.add_or_update(doc)
+
+        try:
+            with backend.batch_update() as batch:
+                batch.remove(doc.pk)
+                raise RuntimeError("simulated failure")
+        except RuntimeError:
+            pass
+
+        r = backend.search(
+            "should survive",
+            user=None,
+            page=1,
+            page_size=10,
+            sort_field=None,
+            sort_reverse=False,
+        )
+        assert r.total == 1
+
+
+class TestSearch:
+    """Test search functionality."""
+
+    def test_scores_normalised_top_hit_is_one(self, backend: TantivyBackend):
+        """Search scores must be normalized so top hit has score 1.0 for UI consistency."""
+        for i, title in enumerate(["bank invoice", "bank statement", "bank receipt"]):
+            doc = Document.objects.create(
+                title=title,
+                content=title,
+                checksum=f"SN{i}",
+                pk=10 + i,
+            )
+            backend.add_or_update(doc)
+        r = backend.search(
+            "bank",
+            user=None,
+            page=1,
+            page_size=10,
+            sort_field=None,
+            sort_reverse=False,
+        )
+        assert r.hits[0]["score"] == pytest.approx(1.0)
+        assert all(0.0 <= h["score"] <= 1.0 for h in r.hits)
+
+    def test_sort_field_ascending(self, backend: TantivyBackend):
+        """Searching with sort_reverse=False must return results in ascending ASN order."""
+        for asn in [30, 10, 20]:
+            doc = Document.objects.create(
+                title="sortable",
+                content="sortable content",
+                checksum=f"SFA{asn}",
+                archive_serial_number=asn,
+            )
+            backend.add_or_update(doc)
+
+        r = backend.search(
+            "sortable",
+            user=None,
+            page=1,
+            page_size=10,
+            sort_field="archive_serial_number",
+            sort_reverse=False,
+        )
+        assert r.total == 3
+        asns = [Document.objects.get(pk=h["id"]).archive_serial_number for h in r.hits]
+        assert asns == [10, 20, 30]
+
+    def test_sort_field_descending(self, backend: TantivyBackend):
+        """Searching with sort_reverse=True must return results in descending ASN order."""
+        for asn in [30, 10, 20]:
+            doc = Document.objects.create(
+                title="sortable",
+                content="sortable content",
+                checksum=f"SFD{asn}",
+                archive_serial_number=asn,
+            )
+            backend.add_or_update(doc)
+
+        r = backend.search(
+            "sortable",
+            user=None,
+            page=1,
+            page_size=10,
+            sort_field="archive_serial_number",
+            sort_reverse=True,
+        )
+        assert r.total == 3
+        asns = [Document.objects.get(pk=h["id"]).archive_serial_number for h in r.hits]
+        assert asns == [30, 20, 10]
+
+    def test_fuzzy_threshold_filters_low_score_hits(
+        self,
+        backend: TantivyBackend,
+        settings,
+    ):
+        """When ADVANCED_FUZZY_SEARCH_THRESHOLD exceeds all normalized scores, hits must be filtered out."""
+        doc = Document.objects.create(
+            title="Invoice document",
+            content="financial report",
+            checksum="FT1",
+            pk=120,
+        )
+        backend.add_or_update(doc)
+
+        # Threshold above 1.0 filters every hit (normalized scores top out at 1.0)
+        settings.ADVANCED_FUZZY_SEARCH_THRESHOLD = 1.1
+        r = backend.search(
+            "invoice",
+            user=None,
+            page=1,
+            page_size=10,
+            sort_field=None,
+            sort_reverse=False,
+        )
+        assert r.hits == []
+
+    def test_owner_filter(self, backend: TantivyBackend):
+        """Document owners can search their private documents; other users cannot access them."""
+        owner = User.objects.create_user("owner")
+        other = User.objects.create_user("other")
+        doc = Document.objects.create(
+            title="Private",
+            content="secret",
+            checksum="PF1",
+            pk=20,
+            owner=owner,
+        )
+        backend.add_or_update(doc)
+
+        assert (
+            backend.search(
+                "secret",
+                user=owner,
+                page=1,
+                page_size=10,
+                sort_field=None,
+                sort_reverse=False,
+            ).total
+            == 1
+        )
+        assert (
+            backend.search(
+                "secret",
+                user=other,
+                page=1,
+                page_size=10,
+                sort_field=None,
+                sort_reverse=False,
+            ).total
+            == 0
+        )
+
+
+class TestRebuild:
+    """Test index rebuilding functionality."""
+
+    def test_with_iter_wrapper_called(self, backend: TantivyBackend):
+        """Index rebuild must pass documents through iter_wrapper for progress tracking."""
+        seen = []
+
+        def wrapper(docs):
+            for doc in docs:
+                seen.append(doc.pk)
+                yield doc
+
+        Document.objects.create(title="Tracked", content="x", checksum="TW1", pk=30)
+        backend.rebuild(Document.objects.all(), iter_wrapper=wrapper)
+        assert 30 in seen
+
+
+class TestAutocomplete:
+    """Test autocomplete functionality."""
+
+    def test_basic_functionality(self, backend: TantivyBackend):
+        """Autocomplete must return words matching the given prefix."""
+        doc = Document.objects.create(
+            title="Invoice from Microsoft Corporation",
+            content="payment details",
+            checksum="AC1",
+            pk=40,
+        )
+        backend.add_or_update(doc)
+
+        results = backend.autocomplete("micro", limit=10)
+        assert "microsoft" in results
+
+    def test_results_ordered_by_document_frequency(self, backend: TantivyBackend):
+        """Autocomplete results must be ordered by document frequency to prioritize common terms."""
+        # "payment" appears in 3 docs; "payslip" in 1 — "pay" prefix should
+        # return "payment" before "payslip".
+        for i, (title, checksum) in enumerate(
+            [
+                ("payment invoice", "AF1"),
+                ("payment receipt", "AF2"),
+                ("payment confirmation", "AF3"),
+                ("payslip march", "AF4"),
+            ],
+            start=41,
+        ):
+            doc = Document.objects.create(
+                title=title,
+                content="details",
+                checksum=checksum,
+                pk=i,
+            )
+            backend.add_or_update(doc)
+
+        results = backend.autocomplete("pay", limit=10)
+        assert results.index("payment") < results.index("payslip")
+
+
+class TestMoreLikeThis:
+    """Test more like this functionality."""
+
+    def test_excludes_original(self, backend: TantivyBackend):
+        """More like this queries must exclude the reference document from results."""
+        doc1 = Document.objects.create(
+            title="Important document",
+            content="financial information",
+            checksum="MLT1",
+            pk=50,
+        )
+        doc2 = Document.objects.create(
+            title="Another document",
+            content="financial report",
+            checksum="MLT2",
+            pk=51,
+        )
+        backend.add_or_update(doc1)
+        backend.add_or_update(doc2)
+
+        results = backend.more_like_this(doc_id=50, user=None, page=1, page_size=10)
+        returned_ids = [hit["id"] for hit in results.hits]
+        assert 50 not in returned_ids  # Original document excluded
+
+    def test_with_user_applies_permission_filter(self, backend: TantivyBackend):
+        """more_like_this with a user must exclude documents that user cannot see."""
+        viewer = User.objects.create_user("mlt_viewer")
+        other = User.objects.create_user("mlt_other")
+        public_doc = Document.objects.create(
+            title="Public financial document",
+            content="quarterly financial analysis report figures",
+            checksum="MLT3",
+            pk=52,
+        )
+        private_doc = Document.objects.create(
+            title="Private financial document",
+            content="quarterly financial analysis report figures",
+            checksum="MLT4",
+            pk=53,
+            owner=other,
+        )
+        backend.add_or_update(public_doc)
+        backend.add_or_update(private_doc)
+
+        results = backend.more_like_this(doc_id=52, user=viewer, page=1, page_size=10)
+        returned_ids = [hit["id"] for hit in results.hits]
+        # private_doc is owned by other, so viewer cannot see it
+        assert 53 not in returned_ids
+
+    def test_document_not_in_index_returns_empty(self, backend: TantivyBackend):
+        """more_like_this for a doc_id absent from the index must return empty results."""
+        results = backend.more_like_this(doc_id=9999, user=None, page=1, page_size=10)
+        assert results.hits == []
+        assert results.total == 0
+
+
+class TestSingleton:
+    """Test get_backend() and reset_backend() singleton lifecycle."""
+
+    @pytest.fixture(autouse=True)
+    def _clean(self):
+        reset_backend()
+        yield
+        reset_backend()
+
+    def test_returns_same_instance_on_repeated_calls(self, index_dir):
+        """Singleton pattern: repeated calls to get_backend() must return the same instance."""
+        assert get_backend() is get_backend()
+
+    def test_reinitializes_when_index_dir_changes(self, tmp_path, settings):
+        """Backend singleton must reinitialize when INDEX_DIR setting changes for test isolation."""
+        settings.INDEX_DIR = tmp_path / "a"
+        (tmp_path / "a").mkdir()
+        b1 = get_backend()
+
+        settings.INDEX_DIR = tmp_path / "b"
+        (tmp_path / "b").mkdir()
+        b2 = get_backend()
+
+        assert b1 is not b2
+        assert b2._path == tmp_path / "b"
+
+    def test_reset_forces_new_instance(self, index_dir):
+        """reset_backend() must force creation of a new backend instance on next get_backend() call."""
+        b1 = get_backend()
+        reset_backend()
+        b2 = get_backend()
+        assert b1 is not b2
+
+
+class TestFieldHandling:
+    """Test handling of various document fields."""
+
+    def test_none_values_handled_correctly(self, backend: TantivyBackend):
+        """Document fields with None values must not cause indexing errors."""
+        doc = Document.objects.create(
+            title="Test Doc",
+            content="test content",
+            checksum="NV1",
+            pk=60,
+            original_filename=None,
+            page_count=None,
+        )
+        # Should not raise an exception
+        backend.add_or_update(doc)
+
+        results = backend.search(
+            "test",
+            user=None,
+            page=1,
+            page_size=10,
+            sort_field=None,
+            sort_reverse=False,
+        )
+        assert results.total == 1
+
+    def test_custom_fields_include_name_and_value(self, backend: TantivyBackend):
+        """Custom fields must be indexed with both field name and value for structured queries."""
+        # Create a custom field
+        field = CustomField.objects.create(
+            name="Invoice Number",
+            data_type=CustomField.FieldDataType.STRING,
+        )
+        doc = Document.objects.create(
+            title="Invoice",
+            content="test",
+            checksum="CF1",
+            pk=70,
+        )
+        CustomFieldInstance.objects.create(
+            document=doc,
+            field=field,
+            value_text="INV-2024-001",
+        )
+
+        # Should not raise an exception during indexing
+        backend.add_or_update(doc)
+
+        results = backend.search(
+            "invoice",
+            user=None,
+            page=1,
+            page_size=10,
+            sort_field=None,
+            sort_reverse=False,
+        )
+        assert results.total == 1
+
+    def test_select_custom_field_indexes_label_not_id(self, backend: TantivyBackend):
+        """SELECT custom fields must index the human-readable label, not the opaque option ID."""
+        field = CustomField.objects.create(
+            name="Category",
+            data_type=CustomField.FieldDataType.SELECT,
+            extra_data={
+                "select_options": [
+                    {"id": "opt_abc", "label": "Invoice"},
+                    {"id": "opt_def", "label": "Receipt"},
+                ],
+            },
+        )
+        doc = Document.objects.create(
+            title="Categorised doc",
+            content="test",
+            checksum="SEL1",
+            pk=71,
+        )
+        CustomFieldInstance.objects.create(
+            document=doc,
+            field=field,
+            value_select="opt_abc",
+        )
+        backend.add_or_update(doc)
+
+        # Label should be findable
+        results = backend.search(
+            "custom_fields.value:invoice",
+            user=None,
+            page=1,
+            page_size=10,
+            sort_field=None,
+            sort_reverse=False,
+        )
+        assert results.total == 1
+
+        # Opaque ID must not appear in the index
+        results = backend.search(
+            "custom_fields.value:opt_abc",
+            user=None,
+            page=1,
+            page_size=10,
+            sort_field=None,
+            sort_reverse=False,
+        )
+        assert results.total == 0
+
+    def test_none_custom_field_value_not_indexed(self, backend: TantivyBackend):
+        """Custom field instances with no value set must not produce an index entry."""
+        field = CustomField.objects.create(
+            name="Optional",
+            data_type=CustomField.FieldDataType.SELECT,
+            extra_data={"select_options": [{"id": "opt_1", "label": "Yes"}]},
+        )
+        doc = Document.objects.create(
+            title="Unset field doc",
+            content="test",
+            checksum="SEL2",
+            pk=72,
+        )
+        CustomFieldInstance.objects.create(
+            document=doc,
+            field=field,
+            value_select=None,
+        )
+        backend.add_or_update(doc)
+
+        # The string "none" must not appear as an indexed value
+        results = backend.search(
+            "custom_fields.value:none",
+            user=None,
+            page=1,
+            page_size=10,
+            sort_field=None,
+            sort_reverse=False,
+        )
+        assert results.total == 0
+
+    def test_notes_include_user_information(self, backend: TantivyBackend):
+        """Notes must be indexed with user information when available for structured queries."""
+        user = User.objects.create_user("notewriter")
+        doc = Document.objects.create(
+            title="Doc with notes",
+            content="test",
+            checksum="NT1",
+            pk=80,
+        )
+        Note.objects.create(document=doc, note="Important note", user=user)
+
+        # Should not raise an exception during indexing
+        backend.add_or_update(doc)
+
+        # Test basic document search first
+        results = backend.search(
+            "test",
+            user=None,
+            page=1,
+            page_size=10,
+            sort_field=None,
+            sort_reverse=False,
+        )
+        assert results.total == 1, (
+            f"Expected 1, got {results.total}. Document content should be searchable."
+        )
+
+        # Test notes search — must use structured JSON syntax now that note
+        # is no longer in DEFAULT_SEARCH_FIELDS
+        results = backend.search(
+            "notes.note:important",
+            user=None,
+            page=1,
+            page_size=10,
+            sort_field=None,
+            sort_reverse=False,
+        )
+        assert results.total == 1, (
+            f"Expected 1, got {results.total}. Note content should be searchable via notes.note: prefix."
+        )

src/documents/tests/search/test_migration_fulltext_query_field_prefixes.py

@@ -0,0 +1,138 @@
+import pytest
+
+from documents.tests.utils import TestMigrations
+
+pytestmark = pytest.mark.search
+
+
+class TestMigrateFulltextQueryFieldPrefixes(TestMigrations):
+    migrate_from = "0016_sha256_checksums"
+    migrate_to = "0017_migrate_fulltext_query_field_prefixes"
+
+    def setUpBeforeMigration(self, apps) -> None:
+        User = apps.get_model("auth", "User")
+        SavedView = apps.get_model("documents", "SavedView")
+        SavedViewFilterRule = apps.get_model("documents", "SavedViewFilterRule")
+
+        user = User.objects.create(username="testuser")
+
+        def make_rule(value: str):
+            view = SavedView.objects.create(
+                owner=user,
+                name=f"view-{value}",
+                sort_field="created",
+            )
+            return SavedViewFilterRule.objects.create(
+                saved_view=view,
+                rule_type=20,  # fulltext query
+                value=value,
+            )
+
+        # Simple field prefixes
+        self.rule_note = make_rule("note:invoice")
+        self.rule_cf = make_rule("custom_field:amount")
+
+        # Combined query
+        self.rule_combined = make_rule("note:invoice AND custom_field:total")
+
+        # Parenthesized groups (Whoosh syntax)
+        self.rule_parens = make_rule("(note:invoice OR note:receipt)")
+
+        # Prefix operators
+        self.rule_plus = make_rule("+note:foo")
+        self.rule_minus = make_rule("-note:bar")
+
+        # Boosted
+        self.rule_boost = make_rule("note:test^2")
+
+        # Should NOT be rewritten — no field prefix match
+        self.rule_no_match = make_rule("title:hello content:world")
+
+        # Should NOT false-positive on word boundaries
+        self.rule_denote = make_rule("denote:foo")
+
+        # Already using new syntax — should be idempotent
+        self.rule_already_migrated = make_rule("notes.note:foo")
+        self.rule_already_migrated_cf = make_rule("custom_fields.value:bar")
+
+        # Null value — should not crash
+        view_null = SavedView.objects.create(
+            owner=user,
+            name="view-null",
+            sort_field="created",
+        )
+        self.rule_null = SavedViewFilterRule.objects.create(
+            saved_view=view_null,
+            rule_type=20,
+            value=None,
+        )
+
+        # Non-fulltext rule type — should be untouched
+        view_other = SavedView.objects.create(
+            owner=user,
+            name="view-other-type",
+            sort_field="created",
+        )
+        self.rule_other_type = SavedViewFilterRule.objects.create(
+            saved_view=view_other,
+            rule_type=0,  # title contains
+            value="note:something",
+        )
+
+    def test_note_prefix_rewritten(self):
+        self.rule_note.refresh_from_db()
+        self.assertEqual(self.rule_note.value, "notes.note:invoice")
+
+    def test_custom_field_prefix_rewritten(self):
+        self.rule_cf.refresh_from_db()
+        self.assertEqual(self.rule_cf.value, "custom_fields.value:amount")
+
+    def test_combined_query_rewritten(self):
+        self.rule_combined.refresh_from_db()
+        self.assertEqual(
+            self.rule_combined.value,
+            "notes.note:invoice AND custom_fields.value:total",
+        )
+
+    def test_parenthesized_groups(self):
+        self.rule_parens.refresh_from_db()
+        self.assertEqual(
+            self.rule_parens.value,
+            "(notes.note:invoice OR notes.note:receipt)",
+        )
+
+    def test_plus_prefix(self):
+        self.rule_plus.refresh_from_db()
+        self.assertEqual(self.rule_plus.value, "+notes.note:foo")
+
+    def test_minus_prefix(self):
+        self.rule_minus.refresh_from_db()
+        self.assertEqual(self.rule_minus.value, "-notes.note:bar")
+
+    def test_boosted(self):
+        self.rule_boost.refresh_from_db()
+        self.assertEqual(self.rule_boost.value, "notes.note:test^2")
+
+    def test_no_match_unchanged(self):
+        self.rule_no_match.refresh_from_db()
+        self.assertEqual(self.rule_no_match.value, "title:hello content:world")
+
+    def test_word_boundary_no_false_positive(self):
+        self.rule_denote.refresh_from_db()
+        self.assertEqual(self.rule_denote.value, "denote:foo")
+
+    def test_already_migrated_idempotent(self):
+        self.rule_already_migrated.refresh_from_db()
+        self.assertEqual(self.rule_already_migrated.value, "notes.note:foo")
+
+    def test_already_migrated_cf_idempotent(self):
+        self.rule_already_migrated_cf.refresh_from_db()
+        self.assertEqual(self.rule_already_migrated_cf.value, "custom_fields.value:bar")
+
+    def test_null_value_no_crash(self):
+        self.rule_null.refresh_from_db()
+        self.assertIsNone(self.rule_null.value)
+
+    def test_non_fulltext_rule_untouched(self):
+        self.rule_other_type.refresh_from_db()
+        self.assertEqual(self.rule_other_type.value, "note:something")

src/documents/tests/search/test_query.py

@@ -0,0 +1,530 @@
+from __future__ import annotations
+
+import re
+from datetime import UTC
+from datetime import datetime
+from datetime import tzinfo
+from typing import TYPE_CHECKING
+from zoneinfo import ZoneInfo
+
+import pytest
+import tantivy
+import time_machine
+
+from documents.search._query import _date_only_range
+from documents.search._query import _datetime_range
+from documents.search._query import _rewrite_compact_date
+from documents.search._query import build_permission_filter
+from documents.search._query import normalize_query
+from documents.search._query import parse_user_query
+from documents.search._query import rewrite_natural_date_keywords
+from documents.search._schema import build_schema
+from documents.search._tokenizer import register_tokenizers
+
+if TYPE_CHECKING:
+    from django.contrib.auth.base_user import AbstractBaseUser
+
+pytestmark = pytest.mark.search
+
+EASTERN = ZoneInfo("America/New_York")  # UTC-5 / UTC-4 (DST)
+AUCKLAND = ZoneInfo("Pacific/Auckland")  # UTC+13 in southern-hemisphere summer
+
+
+def _range(result: str, field: str) -> tuple[str, str]:
+    m = re.search(rf"{field}:\[(.+?) TO (.+?)\]", result)
+    assert m, f"No range for {field!r} in: {result!r}"
+    return m.group(1), m.group(2)
+
+
+class TestCreatedDateField:
+    """
+    created is a Django DateField: indexed as midnight UTC of the local calendar
+    date. No offset arithmetic needed - the local calendar date is what matters.
+    """
+
+    @pytest.mark.parametrize(
+        ("tz", "expected_lo", "expected_hi"),
+        [
+            pytest.param(UTC, "2026-03-28T00:00:00Z", "2026-03-29T00:00:00Z", id="utc"),
+            pytest.param(
+                EASTERN,
+                "2026-03-28T00:00:00Z",
+                "2026-03-29T00:00:00Z",
+                id="eastern_same_calendar_date",
+            ),
+        ],
+    )
+    @time_machine.travel(datetime(2026, 3, 28, 15, 30, tzinfo=UTC), tick=False)
+    def test_today(self, tz: tzinfo, expected_lo: str, expected_hi: str) -> None:
+        lo, hi = _range(rewrite_natural_date_keywords("created:today", tz), "created")
+        assert lo == expected_lo
+        assert hi == expected_hi
+
+    @time_machine.travel(datetime(2026, 3, 28, 3, 0, tzinfo=UTC), tick=False)
+    def test_today_auckland_ahead_of_utc(self) -> None:
+        # UTC 03:00 -> Auckland (UTC+13) = 16:00 same date; local date = 2026-03-28
+        lo, _ = _range(
+            rewrite_natural_date_keywords("created:today", AUCKLAND),
+            "created",
+        )
+        assert lo == "2026-03-28T00:00:00Z"
+
+    @pytest.mark.parametrize(
+        ("field", "keyword", "expected_lo", "expected_hi"),
+        [
+            pytest.param(
+                "created",
+                "yesterday",
+                "2026-03-27T00:00:00Z",
+                "2026-03-28T00:00:00Z",
+                id="yesterday",
+            ),
+            pytest.param(
+                "created",
+                "this_week",
+                "2026-03-23T00:00:00Z",
+                "2026-03-30T00:00:00Z",
+                id="this_week_mon_sun",
+            ),
+            pytest.param(
+                "created",
+                "last_week",
+                "2026-03-16T00:00:00Z",
+                "2026-03-23T00:00:00Z",
+                id="last_week",
+            ),
+            pytest.param(
+                "created",
+                "this_month",
+                "2026-03-01T00:00:00Z",
+                "2026-04-01T00:00:00Z",
+                id="this_month",
+            ),
+            pytest.param(
+                "created",
+                "last_month",
+                "2026-02-01T00:00:00Z",
+                "2026-03-01T00:00:00Z",
+                id="last_month",
+            ),
+            pytest.param(
+                "created",
+                "this_year",
+                "2026-01-01T00:00:00Z",
+                "2027-01-01T00:00:00Z",
+                id="this_year",
+            ),
+            pytest.param(
+                "created",
+                "last_year",
+                "2025-01-01T00:00:00Z",
+                "2026-01-01T00:00:00Z",
+                id="last_year",
+            ),
+        ],
+    )
+    @time_machine.travel(datetime(2026, 3, 28, 15, 0, tzinfo=UTC), tick=False)
+    def test_date_keywords(
+        self,
+        field: str,
+        keyword: str,
+        expected_lo: str,
+        expected_hi: str,
+    ) -> None:
+        # 2026-03-28 is Saturday; Mon-Sun week calculation built into expectations
+        query = f"{field}:{keyword}"
+        lo, hi = _range(rewrite_natural_date_keywords(query, UTC), field)
+        assert lo == expected_lo
+        assert hi == expected_hi
+
+    @time_machine.travel(datetime(2026, 12, 15, 12, 0, tzinfo=UTC), tick=False)
+    def test_this_month_december_wraps_to_next_year(self) -> None:
+        # December: next month must roll over to January 1 of next year
+        lo, hi = _range(
+            rewrite_natural_date_keywords("created:this_month", UTC),
+            "created",
+        )
+        assert lo == "2026-12-01T00:00:00Z"
+        assert hi == "2027-01-01T00:00:00Z"
+
+    @time_machine.travel(datetime(2026, 1, 15, 12, 0, tzinfo=UTC), tick=False)
+    def test_last_month_january_wraps_to_previous_year(self) -> None:
+        # January: last month must roll back to December 1 of previous year
+        lo, hi = _range(
+            rewrite_natural_date_keywords("created:last_month", UTC),
+            "created",
+        )
+        assert lo == "2025-12-01T00:00:00Z"
+        assert hi == "2026-01-01T00:00:00Z"
+
+    def test_unknown_keyword_raises(self) -> None:
+        with pytest.raises(ValueError, match="Unknown keyword"):
+            _date_only_range("bogus_keyword", UTC)
+
+
+class TestDateTimeFields:
+    """
+    added/modified store full UTC datetimes. Natural keywords must convert
+    the local day boundaries to UTC - timezone offset arithmetic IS required.
+    """
+
+    @time_machine.travel(datetime(2026, 3, 28, 15, 30, tzinfo=UTC), tick=False)
+    def test_added_today_eastern(self) -> None:
+        # EDT = UTC-4; local midnight 2026-03-28 00:00 EDT = 2026-03-28 04:00 UTC
+        lo, hi = _range(rewrite_natural_date_keywords("added:today", EASTERN), "added")
+        assert lo == "2026-03-28T04:00:00Z"
+        assert hi == "2026-03-29T04:00:00Z"
+
+    @time_machine.travel(datetime(2026, 3, 29, 2, 0, tzinfo=UTC), tick=False)
+    def test_added_today_auckland_midnight_crossing(self) -> None:
+        # UTC 02:00 on 2026-03-29 -> Auckland (UTC+13) = 2026-03-29 15:00 local
+        # Auckland midnight = UTC 2026-03-28 11:00
+        lo, hi = _range(rewrite_natural_date_keywords("added:today", AUCKLAND), "added")
+        assert lo == "2026-03-28T11:00:00Z"
+        assert hi == "2026-03-29T11:00:00Z"
+
+    @time_machine.travel(datetime(2026, 3, 28, 15, 0, tzinfo=UTC), tick=False)
+    def test_modified_today_utc(self) -> None:
+        lo, hi = _range(
+            rewrite_natural_date_keywords("modified:today", UTC),
+            "modified",
+        )
+        assert lo == "2026-03-28T00:00:00Z"
+        assert hi == "2026-03-29T00:00:00Z"
+
+    @pytest.mark.parametrize(
+        ("keyword", "expected_lo", "expected_hi"),
+        [
+            pytest.param(
+                "yesterday",
+                "2026-03-27T00:00:00Z",
+                "2026-03-28T00:00:00Z",
+                id="yesterday",
+            ),
+            pytest.param(
+                "this_week",
+                "2026-03-23T00:00:00Z",
+                "2026-03-30T00:00:00Z",
+                id="this_week",
+            ),
+            pytest.param(
+                "last_week",
+                "2026-03-16T00:00:00Z",
+                "2026-03-23T00:00:00Z",
+                id="last_week",
+            ),
+            pytest.param(
+                "this_month",
+                "2026-03-01T00:00:00Z",
+                "2026-04-01T00:00:00Z",
+                id="this_month",
+            ),
+            pytest.param(
+                "last_month",
+                "2026-02-01T00:00:00Z",
+                "2026-03-01T00:00:00Z",
+                id="last_month",
+            ),
+            pytest.param(
+                "this_year",
+                "2026-01-01T00:00:00Z",
+                "2027-01-01T00:00:00Z",
+                id="this_year",
+            ),
+            pytest.param(
+                "last_year",
+                "2025-01-01T00:00:00Z",
+                "2026-01-01T00:00:00Z",
+                id="last_year",
+            ),
+        ],
+    )
+    @time_machine.travel(datetime(2026, 3, 28, 12, 0, tzinfo=UTC), tick=False)
+    def test_datetime_keywords_utc(
+        self,
+        keyword: str,
+        expected_lo: str,
+        expected_hi: str,
+    ) -> None:
+        # 2026-03-28 is Saturday; weekday()==5 so Monday=2026-03-23
+        lo, hi = _range(rewrite_natural_date_keywords(f"added:{keyword}", UTC), "added")
+        assert lo == expected_lo
+        assert hi == expected_hi
+
+    @time_machine.travel(datetime(2026, 12, 15, 12, 0, tzinfo=UTC), tick=False)
+    def test_this_month_december_wraps_to_next_year(self) -> None:
+        # December: next month wraps to January of next year
+        lo, hi = _range(rewrite_natural_date_keywords("added:this_month", UTC), "added")
+        assert lo == "2026-12-01T00:00:00Z"
+        assert hi == "2027-01-01T00:00:00Z"
+
+    @time_machine.travel(datetime(2026, 1, 15, 12, 0, tzinfo=UTC), tick=False)
+    def test_last_month_january_wraps_to_previous_year(self) -> None:
+        # January: last month wraps back to December of previous year
+        lo, hi = _range(rewrite_natural_date_keywords("added:last_month", UTC), "added")
+        assert lo == "2025-12-01T00:00:00Z"
+        assert hi == "2026-01-01T00:00:00Z"
+
+    def test_unknown_keyword_raises(self) -> None:
+        with pytest.raises(ValueError, match="Unknown keyword"):
+            _datetime_range("bogus_keyword", UTC)
+
+
+class TestWhooshQueryRewriting:
+    """All Whoosh query syntax variants must be rewritten to ISO 8601 before Tantivy parses them."""
+
+    @time_machine.travel(datetime(2026, 3, 28, 15, 0, tzinfo=UTC), tick=False)
+    def test_compact_date_shim_rewrites_to_iso(self) -> None:
+        result = rewrite_natural_date_keywords("created:20240115120000", UTC)
+        assert "2024-01-15" in result
+        assert "20240115120000" not in result
+
+    @time_machine.travel(datetime(2026, 3, 28, 15, 0, tzinfo=UTC), tick=False)
+    def test_relative_range_shim_removes_now(self) -> None:
+        result = rewrite_natural_date_keywords("added:[now-7d TO now]", UTC)
+        assert "now" not in result
+        assert "2026-03-" in result
+
+    @time_machine.travel(datetime(2026, 3, 28, 12, 0, tzinfo=UTC), tick=False)
+    def test_bracket_minus_7_days(self) -> None:
+        lo, hi = _range(
+            rewrite_natural_date_keywords("added:[-7 days to now]", UTC),
+            "added",
+        )
+        assert lo == "2026-03-21T12:00:00Z"
+        assert hi == "2026-03-28T12:00:00Z"
+
+    @time_machine.travel(datetime(2026, 3, 28, 12, 0, tzinfo=UTC), tick=False)
+    def test_bracket_minus_1_week(self) -> None:
+        lo, hi = _range(
+            rewrite_natural_date_keywords("added:[-1 week to now]", UTC),
+            "added",
+        )
+        assert lo == "2026-03-21T12:00:00Z"
+        assert hi == "2026-03-28T12:00:00Z"
+
+    @time_machine.travel(datetime(2026, 3, 28, 12, 0, tzinfo=UTC), tick=False)
+    def test_bracket_minus_1_month_uses_relativedelta(self) -> None:
+        # relativedelta(months=1) from 2026-03-28 = 2026-02-28 (not 29)
+        lo, hi = _range(
+            rewrite_natural_date_keywords("created:[-1 month to now]", UTC),
+            "created",
+        )
+        assert lo == "2026-02-28T12:00:00Z"
+        assert hi == "2026-03-28T12:00:00Z"
+
+    @time_machine.travel(datetime(2026, 3, 28, 12, 0, tzinfo=UTC), tick=False)
+    def test_bracket_minus_1_year(self) -> None:
+        lo, hi = _range(
+            rewrite_natural_date_keywords("modified:[-1 year to now]", UTC),
+            "modified",
+        )
+        assert lo == "2025-03-28T12:00:00Z"
+        assert hi == "2026-03-28T12:00:00Z"
+
+    @time_machine.travel(datetime(2026, 3, 28, 12, 0, tzinfo=UTC), tick=False)
+    def test_bracket_plural_unit_hours(self) -> None:
+        lo, hi = _range(
+            rewrite_natural_date_keywords("added:[-3 hours to now]", UTC),
+            "added",
+        )
+        assert lo == "2026-03-28T09:00:00Z"
+        assert hi == "2026-03-28T12:00:00Z"
+
+    @time_machine.travel(datetime(2026, 3, 28, 12, 0, tzinfo=UTC), tick=False)
+    def test_bracket_case_insensitive(self) -> None:
+        result = rewrite_natural_date_keywords("added:[-1 WEEK TO NOW]", UTC)
+        assert "now" not in result.lower()
+        lo, hi = _range(result, "added")
+        assert lo == "2026-03-21T12:00:00Z"
+        assert hi == "2026-03-28T12:00:00Z"
+
+    @time_machine.travel(datetime(2026, 3, 28, 12, 0, tzinfo=UTC), tick=False)
+    def test_relative_range_swaps_bounds_when_lo_exceeds_hi(self) -> None:
+        # [now+1h TO now-1h] has lo > hi before substitution; they must be swapped
+        lo, hi = _range(
+            rewrite_natural_date_keywords("added:[now+1h TO now-1h]", UTC),
+            "added",
+        )
+        assert lo == "2026-03-28T11:00:00Z"
+        assert hi == "2026-03-28T13:00:00Z"
+
+    def test_8digit_created_date_field_always_uses_utc_midnight(self) -> None:
+        # created is a DateField: boundaries are always UTC midnight, no TZ offset
+        result = rewrite_natural_date_keywords("created:20231201", EASTERN)
+        lo, hi = _range(result, "created")
+        assert lo == "2023-12-01T00:00:00Z"
+        assert hi == "2023-12-02T00:00:00Z"
+
+    def test_8digit_added_datetime_field_converts_local_midnight_to_utc(self) -> None:
+        # added is DateTimeField: midnight Dec 1 Eastern (EST = UTC-5) = 05:00 UTC
+        result = rewrite_natural_date_keywords("added:20231201", EASTERN)
+        lo, hi = _range(result, "added")
+        assert lo == "2023-12-01T05:00:00Z"
+        assert hi == "2023-12-02T05:00:00Z"
+
+    def test_8digit_modified_datetime_field_converts_local_midnight_to_utc(
+        self,
+    ) -> None:
+        result = rewrite_natural_date_keywords("modified:20231201", EASTERN)
+        lo, hi = _range(result, "modified")
+        assert lo == "2023-12-01T05:00:00Z"
+        assert hi == "2023-12-02T05:00:00Z"
+
+    def test_8digit_invalid_date_passes_through_unchanged(self) -> None:
+        assert rewrite_natural_date_keywords("added:20231340", UTC) == "added:20231340"
+
+    def test_compact_14digit_invalid_date_passes_through_unchanged(self) -> None:
+        # Month=13 makes datetime() raise ValueError; the token must be left as-is
+        assert _rewrite_compact_date("20231300120000") == "20231300120000"
+
+
+class TestParseUserQuery:
+    """parse_user_query runs the full preprocessing pipeline."""
+
+    @pytest.fixture
+    def query_index(self) -> tantivy.Index:
+        schema = build_schema()
+        idx = tantivy.Index(schema, path=None)
+        register_tokenizers(idx, "")
+        return idx
+
+    def test_returns_tantivy_query(self, query_index: tantivy.Index) -> None:
+        assert isinstance(parse_user_query(query_index, "invoice", UTC), tantivy.Query)
+
+    def test_fuzzy_mode_does_not_raise(
+        self,
+        query_index: tantivy.Index,
+        settings,
+    ) -> None:
+        settings.ADVANCED_FUZZY_SEARCH_THRESHOLD = 0.5
+        assert isinstance(parse_user_query(query_index, "invoice", UTC), tantivy.Query)
+
+    def test_date_rewriting_applied_before_tantivy_parse(
+        self,
+        query_index: tantivy.Index,
+    ) -> None:
+        # created:today must be rewritten to an ISO range before Tantivy parses it;
+        # if passed raw, Tantivy would reject "today" as an invalid date value
+        with time_machine.travel(datetime(2026, 3, 28, 12, 0, tzinfo=UTC), tick=False):
+            q = parse_user_query(query_index, "created:today", UTC)
+        assert isinstance(q, tantivy.Query)
+
+
+class TestPassthrough:
+    """Queries without field prefixes or unrelated content pass through unchanged."""
+
+    def test_bare_keyword_no_field_prefix_unchanged(self) -> None:
+        # Bare 'today' with no field: prefix passes through unchanged
+        result = rewrite_natural_date_keywords("bank statement today", UTC)
+        assert "today" in result
+
+    def test_unrelated_query_unchanged(self) -> None:
+        assert rewrite_natural_date_keywords("title:invoice", UTC) == "title:invoice"
+
+
+class TestNormalizeQuery:
+    """normalize_query expands comma-separated values and collapses whitespace."""
+
+    def test_normalize_expands_comma_separated_tags(self) -> None:
+        assert normalize_query("tag:foo,bar") == "tag:foo AND tag:bar"
+
+    def test_normalize_expands_three_values(self) -> None:
+        assert normalize_query("tag:foo,bar,baz") == "tag:foo AND tag:bar AND tag:baz"
+
+    def test_normalize_collapses_whitespace(self) -> None:
+        assert normalize_query("bank   statement") == "bank statement"
+
+    def test_normalize_no_commas_unchanged(self) -> None:
+        assert normalize_query("bank statement") == "bank statement"
+
+
+class TestPermissionFilter:
+    """
+    build_permission_filter tests use an in-memory index — no DB access needed.
+
+    Users are constructed as unsaved model instances (django_user_model(pk=N))
+    so no database round-trip occurs; only .pk is read by build_permission_filter.
+    """
+
+    @pytest.fixture
+    def perm_index(self) -> tantivy.Index:
+        schema = build_schema()
+        idx = tantivy.Index(schema, path=None)
+        register_tokenizers(idx, "")
+        return idx
+
+    def _add_doc(
+        self,
+        idx: tantivy.Index,
+        doc_id: int,
+        owner_id: int | None = None,
+        viewer_ids: tuple[int, ...] = (),
+    ) -> None:
+        writer = idx.writer()
+        doc = tantivy.Document()
+        doc.add_unsigned("id", doc_id)
+        # Only add owner_id field if the document has an owner
+        if owner_id is not None:
+            doc.add_unsigned("owner_id", owner_id)
+        for vid in viewer_ids:
+            doc.add_unsigned("viewer_id", vid)
+        writer.add_document(doc)
+        writer.commit()
+        idx.reload()
+
+    def test_perm_no_owner_visible_to_any_user(
+        self,
+        perm_index: tantivy.Index,
+        django_user_model: type[AbstractBaseUser],
+    ) -> None:
+        """Documents with no owner must be visible to every user."""
+        self._add_doc(perm_index, doc_id=1, owner_id=None)
+        user = django_user_model(pk=99)
+        perm = build_permission_filter(perm_index.schema, user)
+        assert perm_index.searcher().search(perm, limit=10).count == 1
+
+    def test_perm_owned_by_user_is_visible(
+        self,
+        perm_index: tantivy.Index,
+        django_user_model: type[AbstractBaseUser],
+    ) -> None:
+        """A document owned by the requesting user must be visible."""
+        self._add_doc(perm_index, doc_id=2, owner_id=42)
+        user = django_user_model(pk=42)
+        perm = build_permission_filter(perm_index.schema, user)
+        assert perm_index.searcher().search(perm, limit=10).count == 1
+
+    def test_perm_owned_by_other_not_visible(
+        self,
+        perm_index: tantivy.Index,
+        django_user_model: type[AbstractBaseUser],
+    ) -> None:
+        """A document owned by a different user must not be visible."""
+        self._add_doc(perm_index, doc_id=3, owner_id=42)
+        user = django_user_model(pk=99)
+        perm = build_permission_filter(perm_index.schema, user)
+        assert perm_index.searcher().search(perm, limit=10).count == 0
+
+    def test_perm_shared_viewer_is_visible(
+        self,
+        perm_index: tantivy.Index,
+        django_user_model: type[AbstractBaseUser],
+    ) -> None:
+        """A document explicitly shared with a user must be visible to that user."""
+        self._add_doc(perm_index, doc_id=4, owner_id=42, viewer_ids=(99,))
+        user = django_user_model(pk=99)
+        perm = build_permission_filter(perm_index.schema, user)
+        assert perm_index.searcher().search(perm, limit=10).count == 1
+
+    def test_perm_only_owned_docs_hidden_from_others(
+        self,
+        perm_index: tantivy.Index,
+        django_user_model: type[AbstractBaseUser],
+    ) -> None:
+        """Only unowned documents appear when the user owns none of them."""
+        self._add_doc(perm_index, doc_id=5, owner_id=10)  # owned by 10
+        self._add_doc(perm_index, doc_id=6, owner_id=None)  # unowned
+        user = django_user_model(pk=20)
+        perm = build_permission_filter(perm_index.schema, user)
+        assert perm_index.searcher().search(perm, limit=10).count == 1  # only unowned

src/documents/tests/search/test_schema.py

@@ -0,0 +1,63 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+import pytest
+
+from documents.search._schema import SCHEMA_VERSION
+from documents.search._schema import needs_rebuild
+
+if TYPE_CHECKING:
+    from pathlib import Path
+
+    from pytest_django.fixtures import SettingsWrapper
+
+pytestmark = pytest.mark.search
+
+
+class TestNeedsRebuild:
+    """needs_rebuild covers all sentinel-file states that require a full reindex."""
+
+    def test_returns_true_when_version_file_missing(self, index_dir: Path) -> None:
+        assert needs_rebuild(index_dir) is True
+
+    def test_returns_false_when_version_and_language_match(
+        self,
+        index_dir: Path,
+        settings: SettingsWrapper,
+    ) -> None:
+        settings.SEARCH_LANGUAGE = "en"
+        (index_dir / ".schema_version").write_text(str(SCHEMA_VERSION))
+        (index_dir / ".schema_language").write_text("en")
+        assert needs_rebuild(index_dir) is False
+
+    def test_returns_true_on_schema_version_mismatch(self, index_dir: Path) -> None:
+        (index_dir / ".schema_version").write_text(str(SCHEMA_VERSION - 1))
+        assert needs_rebuild(index_dir) is True
+
+    def test_returns_true_when_version_file_not_an_integer(
+        self,
+        index_dir: Path,
+    ) -> None:
+        (index_dir / ".schema_version").write_text("not-a-number")
+        assert needs_rebuild(index_dir) is True
+
+    def test_returns_true_when_language_sentinel_missing(
+        self,
+        index_dir: Path,
+        settings: SettingsWrapper,
+    ) -> None:
+        settings.SEARCH_LANGUAGE = "en"
+        (index_dir / ".schema_version").write_text(str(SCHEMA_VERSION))
+        # .schema_language intentionally absent
+        assert needs_rebuild(index_dir) is True
+
+    def test_returns_true_when_language_sentinel_content_differs(
+        self,
+        index_dir: Path,
+        settings: SettingsWrapper,
+    ) -> None:
+        settings.SEARCH_LANGUAGE = "de"
+        (index_dir / ".schema_version").write_text(str(SCHEMA_VERSION))
+        (index_dir / ".schema_language").write_text("en")
+        assert needs_rebuild(index_dir) is True

src/documents/tests/search/test_tokenizer.py

@@ -0,0 +1,78 @@
+from __future__ import annotations
+
+import logging
+from typing import TYPE_CHECKING
+
+import pytest
+import tantivy
+
+from documents.search._tokenizer import _bigram_analyzer
+from documents.search._tokenizer import _paperless_text
+from documents.search._tokenizer import register_tokenizers
+
+if TYPE_CHECKING:
+    from _pytest.logging import LogCaptureFixture
+
+pytestmark = pytest.mark.search
+
+
+class TestTokenizers:
+    @pytest.fixture
+    def content_index(self) -> tantivy.Index:
+        """Index with just a content field for ASCII folding tests."""
+        sb = tantivy.SchemaBuilder()
+        sb.add_text_field("content", stored=True, tokenizer_name="paperless_text")
+        schema = sb.build()
+        idx = tantivy.Index(schema, path=None)
+        idx.register_tokenizer("paperless_text", _paperless_text(""))
+        return idx
+
+    @pytest.fixture
+    def bigram_index(self) -> tantivy.Index:
+        """Index with bigram field for CJK tests."""
+        sb = tantivy.SchemaBuilder()
+        sb.add_text_field(
+            "bigram_content",
+            stored=False,
+            tokenizer_name="bigram_analyzer",
+        )
+        schema = sb.build()
+        idx = tantivy.Index(schema, path=None)
+        idx.register_tokenizer("bigram_analyzer", _bigram_analyzer())
+        return idx
+
+    def test_ascii_fold_finds_accented_content(
+        self,
+        content_index: tantivy.Index,
+    ) -> None:
+        """ASCII folding allows searching accented text with plain ASCII queries."""
+        writer = content_index.writer()
+        doc = tantivy.Document()
+        doc.add_text("content", "café résumé")
+        writer.add_document(doc)
+        writer.commit()
+        content_index.reload()
+        q = content_index.parse_query("cafe resume", ["content"])
+        assert content_index.searcher().search(q, limit=5).count == 1
+
+    def test_bigram_finds_cjk_substring(self, bigram_index: tantivy.Index) -> None:
+        """Bigram tokenizer enables substring search in CJK languages without whitespace delimiters."""
+        writer = bigram_index.writer()
+        doc = tantivy.Document()
+        doc.add_text("bigram_content", "東京都")
+        writer.add_document(doc)
+        writer.commit()
+        bigram_index.reload()
+        q = bigram_index.parse_query("東京", ["bigram_content"])
+        assert bigram_index.searcher().search(q, limit=5).count == 1
+
+    def test_unsupported_language_logs_warning(self, caplog: LogCaptureFixture) -> None:
+        """Unsupported language codes should log a warning and disable stemming gracefully."""
+        sb = tantivy.SchemaBuilder()
+        sb.add_text_field("content", stored=True, tokenizer_name="paperless_text")
+        schema = sb.build()
+        idx = tantivy.Index(schema, path=None)
+
+        with caplog.at_level(logging.WARNING, logger="paperless.search"):
+            register_tokenizers(idx, "klingon")
+        assert "klingon" in caplog.text

src/documents/tests/test_admin.py

@@ -1,6 +1,7 @@
 import types
 from unittest.mock import patch
 
+import tantivy
 from django.contrib.admin.sites import AdminSite
 from django.contrib.auth.models import Permission
 from django.contrib.auth.models import User
@@ -8,36 +9,54 @@ from django.test import TestCase
 from django.utils import timezone
 from rest_framework import status
 
-from documents import index
 from documents.admin import DocumentAdmin
 from documents.admin import TagAdmin
 from documents.models import Document
 from documents.models import Tag
+from documents.search import get_backend
+from documents.search import reset_backend
 from documents.tests.utils import DirectoriesMixin
 from paperless.admin import PaperlessUserAdmin
 
 
 class TestDocumentAdmin(DirectoriesMixin, TestCase):
     def get_document_from_index(self, doc):
-        ix = index.open_index()
+        backend = get_backend()
-        with ix.searcher() as searcher:
+        searcher = backend._index.searcher()
-            return searcher.document(id=doc.id)
+        results = searcher.search(
+            tantivy.Query.range_query(
+                backend._schema,
+                "id",
+                tantivy.FieldType.Unsigned,
+                doc.pk,
+                doc.pk,
+            ),
+            limit=1,
+        )
+        if results.hits:
+            return searcher.doc(results.hits[0][1]).to_dict()
+        return None
 
     def setUp(self) -> None:
         super().setUp()
+        reset_backend()
         self.doc_admin = DocumentAdmin(model=Document, admin_site=AdminSite())
 
+    def tearDown(self) -> None:
+        reset_backend()
+        super().tearDown()
+
     def test_save_model(self) -> None:
         doc = Document.objects.create(title="test")
 
         doc.title = "new title"
         self.doc_admin.save_model(None, doc, None, None)
         self.assertEqual(Document.objects.get(id=doc.id).title, "new title")
-        self.assertEqual(self.get_document_from_index(doc)["id"], doc.id)
+        self.assertEqual(self.get_document_from_index(doc)["id"], [doc.id])
 
     def test_delete_model(self) -> None:
         doc = Document.objects.create(title="test")
-        index.add_or_update_document(doc)
+        get_backend().add_or_update(doc)
         self.assertIsNotNone(self.get_document_from_index(doc))
 
         self.doc_admin.delete_model(None, doc)
@@ -53,7 +72,7 @@ class TestDocumentAdmin(DirectoriesMixin, TestCase):
                 checksum=f"{i:02}",
             )
             docs.append(doc)
-            index.add_or_update_document(doc)
+            get_backend().add_or_update(doc)
 
         self.assertEqual(Document.objects.count(), 42)
 

src/documents/tests/test_api_bulk_edit.py

@@ -614,6 +614,63 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
         self.assertEqual(Document.objects.count(), 5)
 
+    def test_api_requires_documents_unless_all_is_true(self) -> None:
+        response = self.client.post(
+            "/api/documents/bulk_edit/",
+            json.dumps(
+                {
+                    "method": "set_storage_path",
+                    "parameters": {"storage_path": self.sp1.id},
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertIn(b"documents is required unless all is true", response.content)
+
+    @mock.patch("documents.serialisers.bulk_edit.set_storage_path")
+    def test_api_bulk_edit_with_all_true_resolves_documents_from_filters(
+        self,
+        m,
+    ) -> None:
+        self.setup_mock(m, "set_storage_path")
+
+        response = self.client.post(
+            "/api/documents/bulk_edit/",
+            json.dumps(
+                {
+                    "all": True,
+                    "filters": {"title__icontains": "B"},
+                    "method": "set_storage_path",
+                    "parameters": {"storage_path": self.sp1.id},
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        m.assert_called_once()
+        args, kwargs = m.call_args
+        self.assertEqual(args[0], [self.doc2.id])
+        self.assertEqual(kwargs["storage_path"], self.sp1.id)
+
+    def test_api_bulk_edit_with_all_true_rejects_unsupported_methods(self) -> None:
+        response = self.client.post(
+            "/api/documents/bulk_edit/",
+            json.dumps(
+                {
+                    "all": True,
+                    "method": "merge",
+                    "parameters": {"metadata_document_id": self.doc2.id},
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertIn(b"This method does not support all=true", response.content)
+
     def test_api_invalid_method(self) -> None:
         self.assertEqual(Document.objects.count(), 5)
         response = self.client.post(

src/documents/tests/test_api_document_versions.py

@@ -109,7 +109,7 @@ class TestDocumentVersioningApi(DirectoriesMixin, APITestCase):
             mime_type="application/pdf",
         )
 
-        with mock.patch("documents.index.remove_document_from_index"):
+        with mock.patch("documents.search.get_backend"):
             resp = self.client.delete(f"/api/documents/{root.id}/versions/{root.id}/")
 
         self.assertEqual(resp.status_code, status.HTTP_400_BAD_REQUEST)
@@ -137,10 +137,7 @@ class TestDocumentVersioningApi(DirectoriesMixin, APITestCase):
             content="v2-content",
         )
 
-        with (
+        with mock.patch("documents.search.get_backend"):
-            mock.patch("documents.index.remove_document_from_index"),
-            mock.patch("documents.index.add_or_update_document"),
-        ):
             resp = self.client.delete(f"/api/documents/{root.id}/versions/{v2.id}/")
 
         self.assertEqual(resp.status_code, status.HTTP_200_OK)
@@ -149,10 +146,7 @@ class TestDocumentVersioningApi(DirectoriesMixin, APITestCase):
         root.refresh_from_db()
         self.assertEqual(root.content, "root-content")
 
-        with (
+        with mock.patch("documents.search.get_backend"):
-            mock.patch("documents.index.remove_document_from_index"),
-            mock.patch("documents.index.add_or_update_document"),
-        ):
             resp = self.client.delete(f"/api/documents/{root.id}/versions/{v1.id}/")
 
         self.assertEqual(resp.status_code, status.HTTP_200_OK)
@@ -175,10 +169,7 @@ class TestDocumentVersioningApi(DirectoriesMixin, APITestCase):
         )
         version_id = version.id
 
-        with (
+        with mock.patch("documents.search.get_backend"):
-            mock.patch("documents.index.remove_document_from_index"),
-            mock.patch("documents.index.add_or_update_document"),
-        ):
             resp = self.client.delete(
                 f"/api/documents/{root.id}/versions/{version_id}/",
             )
@@ -225,7 +216,7 @@ class TestDocumentVersioningApi(DirectoriesMixin, APITestCase):
             root_document=other_root,
         )
 
-        with mock.patch("documents.index.remove_document_from_index"):
+        with mock.patch("documents.search.get_backend"):
             resp = self.client.delete(
                 f"/api/documents/{root.id}/versions/{other_version.id}/",
             )
@@ -245,10 +236,7 @@ class TestDocumentVersioningApi(DirectoriesMixin, APITestCase):
             root_document=root,
         )
 
-        with (
+        with mock.patch("documents.search.get_backend"):
-            mock.patch("documents.index.remove_document_from_index"),
-            mock.patch("documents.index.add_or_update_document"),
-        ):
             resp = self.client.delete(
                 f"/api/documents/{version.id}/versions/{version.id}/",
             )
@@ -275,18 +263,17 @@ class TestDocumentVersioningApi(DirectoriesMixin, APITestCase):
             root_document=root,
         )
 
-        with (
+        with mock.patch("documents.search.get_backend") as mock_get_backend:
-            mock.patch("documents.index.remove_document_from_index") as remove_index,
+            mock_backend = mock.MagicMock()
-            mock.patch("documents.index.add_or_update_document") as add_or_update,
+            mock_get_backend.return_value = mock_backend
-        ):
             resp = self.client.delete(
                 f"/api/documents/{root.id}/versions/{version.id}/",
             )
 
         self.assertEqual(resp.status_code, status.HTTP_200_OK)
-        remove_index.assert_called_once_with(version)
+        mock_backend.remove.assert_called_once_with(version.pk)
-        add_or_update.assert_called_once()
+        mock_backend.add_or_update.assert_called_once()
-        self.assertEqual(add_or_update.call_args[0][0].id, root.id)
+        self.assertEqual(mock_backend.add_or_update.call_args[0][0].id, root.id)
 
     def test_delete_version_returns_403_without_permission(self) -> None:
         owner = User.objects.create_user(username="owner")

src/documents/tests/test_api_documents.py

@@ -1119,21 +1119,19 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
             [u1_doc1.id],
         )
 
-    def test_pagination_all(self) -> None:
+    def test_pagination_results(self) -> None:
         """
         GIVEN:
             - A set of 50 documents
         WHEN:
             - API request for document filtering
         THEN:
-            - Results are paginated (25 items) and response["all"] returns all ids (50 items)
+            - Results are paginated (25 items) and count reflects all results (50 items)
         """
         t = Tag.objects.create(name="tag")
-        docs = []
         for i in range(50):
             d = Document.objects.create(checksum=i, content=f"test{i}")
             d.tags.add(t)
-            docs.append(d)
 
         response = self.client.get(
             f"/api/documents/?tags__id__in={t.id}",
@@ -1141,9 +1139,84 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_200_OK)
         results = response.data["results"]
         self.assertEqual(len(results), 25)
-        self.assertEqual(len(response.data["all"]), 50)
+        self.assertEqual(response.data["count"], 50)
+        self.assertNotIn("all", response.data)
+
+    def test_pagination_all_for_api_version_9(self) -> None:
+        """
+        GIVEN:
+            - A set of documents matching a filter
+        WHEN:
+            - API request uses legacy version 9
+        THEN:
+            - Response includes "all" for backward compatibility
+        """
+        t = Tag.objects.create(name="tag")
+        docs = []
+        for i in range(4):
+            d = Document.objects.create(checksum=i, content=f"test{i}")
+            d.tags.add(t)
+            docs.append(d)
+
+        response = self.client.get(
+            f"/api/documents/?tags__id__in={t.id}",
+            headers={"Accept": "application/json; version=9"},
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        self.assertIn("all", response.data)
         self.assertCountEqual(response.data["all"], [d.id for d in docs])
 
+    def test_list_with_include_selection_data(self) -> None:
+        correspondent = Correspondent.objects.create(name="c1")
+        doc_type = DocumentType.objects.create(name="dt1")
+        storage_path = StoragePath.objects.create(name="sp1")
+        tag = Tag.objects.create(name="tag")
+
+        matching_doc = Document.objects.create(
+            checksum="A",
+            correspondent=correspondent,
+            document_type=doc_type,
+            storage_path=storage_path,
+        )
+        matching_doc.tags.add(tag)
+
+        non_matching_doc = Document.objects.create(checksum="B")
+        non_matching_doc.tags.add(Tag.objects.create(name="other"))
+
+        response = self.client.get(
+            f"/api/documents/?tags__id__in={tag.id}&include_selection_data=true",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        self.assertIn("selection_data", response.data)
+
+        selected_correspondent = next(
+            item
+            for item in response.data["selection_data"]["selected_correspondents"]
+            if item["id"] == correspondent.id
+        )
+        selected_tag = next(
+            item
+            for item in response.data["selection_data"]["selected_tags"]
+            if item["id"] == tag.id
+        )
+        selected_type = next(
+            item
+            for item in response.data["selection_data"]["selected_document_types"]
+            if item["id"] == doc_type.id
+        )
+        selected_storage_path = next(
+            item
+            for item in response.data["selection_data"]["selected_storage_paths"]
+            if item["id"] == storage_path.id
+        )
+
+        self.assertEqual(selected_correspondent["document_count"], 1)
+        self.assertEqual(selected_tag["document_count"], 1)
+        self.assertEqual(selected_type["document_count"], 1)
+        self.assertEqual(selected_storage_path["document_count"], 1)
+
     def test_statistics(self) -> None:
         doc1 = Document.objects.create(
             title="none1",

src/documents/tests/test_api_objects.py

@@ -145,6 +145,22 @@ class TestApiObjects(DirectoriesMixin, APITestCase):
             response.data["last_correspondence"],
         )
 
+    def test_paginated_objects_include_all_only_for_legacy_version(self) -> None:
+        response_v10 = self.client.get("/api/correspondents/")
+        self.assertEqual(response_v10.status_code, status.HTTP_200_OK)
+        self.assertNotIn("all", response_v10.data)
+
+        response_v9 = self.client.get(
+            "/api/correspondents/",
+            headers={"Accept": "application/json; version=9"},
+        )
+        self.assertEqual(response_v9.status_code, status.HTTP_200_OK)
+        self.assertIn("all", response_v9.data)
+        self.assertCountEqual(
+            response_v9.data["all"],
+            [self.c1.id, self.c2.id, self.c3.id],
+        )
+
 
 class TestApiStoragePaths(DirectoriesMixin, APITestCase):
     ENDPOINT = "/api/storage_paths/"
@@ -794,6 +810,62 @@ class TestBulkEditObjects(APITestCase):
         self.assertEqual(response.status_code, status.HTTP_200_OK)
         self.assertEqual(StoragePath.objects.count(), 0)
 
+    def test_bulk_objects_delete_all_filtered(self) -> None:
+        """
+        GIVEN:
+            - Existing objects that can be filtered by name
+        WHEN:
+            - bulk_edit_objects API endpoint is called with all=true and filters
+        THEN:
+            - Matching objects are deleted without passing explicit IDs
+        """
+        Correspondent.objects.create(name="c2")
+
+        response = self.client.post(
+            "/api/bulk_edit_objects/",
+            json.dumps(
+                {
+                    "all": True,
+                    "filters": {"name__icontains": "c"},
+                    "object_type": "correspondents",
+                    "operation": "delete",
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        self.assertEqual(Correspondent.objects.count(), 0)
+
+    def test_bulk_objects_delete_all_filtered_tags_includes_descendants(self) -> None:
+        """
+        GIVEN:
+            - Root tag with descendants
+        WHEN:
+            - bulk_edit_objects API endpoint is called with all=true
+        THEN:
+            - Root tags and descendants are deleted
+        """
+        parent = Tag.objects.create(name="parent")
+        child = Tag.objects.create(name="child", tn_parent=parent)
+
+        response = self.client.post(
+            "/api/bulk_edit_objects/",
+            json.dumps(
+                {
+                    "all": True,
+                    "filters": {"is_root": True},
+                    "object_type": "tags",
+                    "operation": "delete",
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        self.assertFalse(Tag.objects.filter(id=parent.id).exists())
+        self.assertFalse(Tag.objects.filter(id=child.id).exists())
+
     def test_bulk_edit_object_permissions_insufficient_global_perms(self) -> None:
         """
         GIVEN:
@@ -881,3 +953,40 @@ class TestBulkEditObjects(APITestCase):
 
         self.assertEqual(response.status_code, status.HTTP_403_FORBIDDEN)
         self.assertEqual(response.content, b"Insufficient permissions")
+
+    def test_bulk_edit_all_filtered_permissions_insufficient_object_perms(
+        self,
+    ) -> None:
+        """
+        GIVEN:
+            - Filter-matching objects include one that the user cannot edit
+        WHEN:
+            - bulk_edit_objects API endpoint is called with all=true
+        THEN:
+            - Operation applies only to editable objects
+        """
+        self.t2.owner = User.objects.get(username="temp_admin")
+        self.t2.save()
+
+        self.user1.user_permissions.add(
+            *Permission.objects.filter(codename="delete_tag"),
+        )
+        self.user1.save()
+        self.client.force_authenticate(user=self.user1)
+
+        response = self.client.post(
+            "/api/bulk_edit_objects/",
+            json.dumps(
+                {
+                    "all": True,
+                    "filters": {"name__icontains": "t"},
+                    "object_type": "tags",
+                    "operation": "delete",
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        self.assertTrue(Tag.objects.filter(id=self.t2.id).exists())
+        self.assertFalse(Tag.objects.filter(id=self.t1.id).exists())

src/documents/tests/test_api_search.py

@@ -2,6 +2,7 @@ import datetime
 from datetime import timedelta
 from unittest import mock
 
+import pytest
 from dateutil.relativedelta import relativedelta
 from django.contrib.auth.models import Group
 from django.contrib.auth.models import Permission
@@ -11,9 +12,7 @@ from django.utils import timezone
 from guardian.shortcuts import assign_perm
 from rest_framework import status
 from rest_framework.test import APITestCase
-from whoosh.writing import AsyncWriter
 
-from documents import index
 from documents.bulk_edit import set_permissions
 from documents.models import Correspondent
 from documents.models import CustomField
@@ -25,18 +24,27 @@ from documents.models import SavedView
 from documents.models import StoragePath
 from documents.models import Tag
 from documents.models import Workflow
+from documents.search import get_backend
+from documents.search import reset_backend
 from documents.tests.utils import DirectoriesMixin
 from paperless_mail.models import MailAccount
 from paperless_mail.models import MailRule
 
+pytestmark = pytest.mark.search
+
 
 class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
     def setUp(self) -> None:
         super().setUp()
+        reset_backend()
 
         self.user = User.objects.create_superuser(username="temp_admin")
         self.client.force_authenticate(user=self.user)
 
+    def tearDown(self) -> None:
+        reset_backend()
+        super().tearDown()
+
     def test_search(self) -> None:
         d1 = Document.objects.create(
             title="invoice",
@@ -57,37 +65,96 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
             checksum="C",
             original_filename="someepdf.pdf",
         )
-        with AsyncWriter(index.open_index()) as writer:
+        backend = get_backend()
-            # Note to future self: there is a reason we dont use a model signal handler to update the index: some operations edit many documents at once
+        backend.add_or_update(d1)
-            # (retagger, renamer) and we don't want to open a writer for each of these, but rather perform the entire operation with one writer.
+        backend.add_or_update(d2)
-            # That's why we can't open the writer in a model on_save handler or something.
+        backend.add_or_update(d3)
-            index.update_document(writer, d1)
+
-            index.update_document(writer, d2)
-            index.update_document(writer, d3)
         response = self.client.get("/api/documents/?query=bank")
         results = response.data["results"]
         self.assertEqual(response.data["count"], 3)
         self.assertEqual(len(results), 3)
-        self.assertCountEqual(response.data["all"], [d1.id, d2.id, d3.id])
 
         response = self.client.get("/api/documents/?query=september")
         results = response.data["results"]
         self.assertEqual(response.data["count"], 1)
         self.assertEqual(len(results), 1)
-        self.assertCountEqual(response.data["all"], [d3.id])
         self.assertEqual(results[0]["original_file_name"], "someepdf.pdf")
 
         response = self.client.get("/api/documents/?query=statement")
         results = response.data["results"]
         self.assertEqual(response.data["count"], 2)
         self.assertEqual(len(results), 2)
-        self.assertCountEqual(response.data["all"], [d2.id, d3.id])
 
         response = self.client.get("/api/documents/?query=sfegdfg")
         results = response.data["results"]
         self.assertEqual(response.data["count"], 0)
         self.assertEqual(len(results), 0)
-        self.assertCountEqual(response.data["all"], [])
+
+    def test_search_returns_all_for_api_version_9(self) -> None:
+        d1 = Document.objects.create(
+            title="invoice",
+            content="bank payment",
+            checksum="A",
+            pk=1,
+        )
+        d2 = Document.objects.create(
+            title="bank statement",
+            content="bank transfer",
+            checksum="B",
+            pk=2,
+        )
+        backend = get_backend()
+        backend.add_or_update(d1)
+        backend.add_or_update(d2)
+
+        response = self.client.get(
+            "/api/documents/?query=bank",
+            headers={"Accept": "application/json; version=9"},
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        self.assertIn("all", response.data)
+        self.assertCountEqual(response.data["all"], [d1.id, d2.id])
+
+    def test_search_with_include_selection_data(self) -> None:
+        correspondent = Correspondent.objects.create(name="c1")
+        doc_type = DocumentType.objects.create(name="dt1")
+        storage_path = StoragePath.objects.create(name="sp1")
+        tag = Tag.objects.create(name="tag")
+
+        matching_doc = Document.objects.create(
+            title="bank statement",
+            content="bank content",
+            checksum="A",
+            correspondent=correspondent,
+            document_type=doc_type,
+            storage_path=storage_path,
+        )
+        matching_doc.tags.add(tag)
+
+        get_backend().add_or_update(matching_doc)
+
+        response = self.client.get(
+            "/api/documents/?query=bank&include_selection_data=true",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        self.assertIn("selection_data", response.data)
+
+        selected_correspondent = next(
+            item
+            for item in response.data["selection_data"]["selected_correspondents"]
+            if item["id"] == correspondent.id
+        )
+        selected_tag = next(
+            item
+            for item in response.data["selection_data"]["selected_tags"]
+            if item["id"] == tag.id
+        )
+
+        self.assertEqual(selected_correspondent["document_count"], 1)
+        self.assertEqual(selected_tag["document_count"], 1)
 
     def test_search_custom_field_ordering(self) -> None:
         custom_field = CustomField.objects.create(
@@ -125,10 +192,10 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
             value_int=20,
         )
 
-        with AsyncWriter(index.open_index()) as writer:
+        backend = get_backend()
-            index.update_document(writer, d1)
+        backend.add_or_update(d1)
-            index.update_document(writer, d2)
+        backend.add_or_update(d2)
-            index.update_document(writer, d3)
+        backend.add_or_update(d3)
 
         response = self.client.get(
             f"/api/documents/?query=match&ordering=custom_field_{custom_field.pk}",
@@ -149,15 +216,15 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
         )
 
     def test_search_multi_page(self) -> None:
-        with AsyncWriter(index.open_index()) as writer:
+        backend = get_backend()
-            for i in range(55):
+        for i in range(55):
-                doc = Document.objects.create(
+            doc = Document.objects.create(
-                    checksum=str(i),
+                checksum=str(i),
-                    pk=i + 1,
+                pk=i + 1,
-                    title=f"Document {i + 1}",
+                title=f"Document {i + 1}",
-                    content="content",
+                content="content",
-                )
+            )
-                index.update_document(writer, doc)
+            backend.add_or_update(doc)
 
         # This is here so that we test that no document gets returned twice (might happen if the paging is not working)
         seen_ids = []
@@ -184,15 +251,15 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
             seen_ids.append(result["id"])
 
     def test_search_invalid_page(self) -> None:
-        with AsyncWriter(index.open_index()) as writer:
+        backend = get_backend()
-            for i in range(15):
+        for i in range(15):
-                doc = Document.objects.create(
+            doc = Document.objects.create(
-                    checksum=str(i),
+                checksum=str(i),
-                    pk=i + 1,
+                pk=i + 1,
-                    title=f"Document {i + 1}",
+                title=f"Document {i + 1}",
-                    content="content",
+                content="content",
-                )
+            )
-                index.update_document(writer, doc)
+            backend.add_or_update(doc)
 
         response = self.client.get("/api/documents/?query=content&page=0&page_size=10")
         self.assertEqual(response.status_code, status.HTTP_404_NOT_FOUND)
@@ -230,26 +297,25 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
             pk=3,
             checksum="C",
         )
-        with index.open_index_writer() as writer:
+        backend = get_backend()
-            index.update_document(writer, d1)
+        backend.add_or_update(d1)
-            index.update_document(writer, d2)
+        backend.add_or_update(d2)
-            index.update_document(writer, d3)
+        backend.add_or_update(d3)
 
         response = self.client.get("/api/documents/?query=added:[-1 week to now]")
         results = response.data["results"]
         # Expect 3 documents returned
         self.assertEqual(len(results), 3)
 
-        for idx, subset in enumerate(
+        result_map = {r["id"]: r for r in results}
-            [
+        self.assertEqual(set(result_map.keys()), {1, 2, 3})
-                {"id": 1, "title": "invoice"},
+        for subset in [
-                {"id": 2, "title": "bank statement 1"},
+            {"id": 1, "title": "invoice"},
-                {"id": 3, "title": "bank statement 3"},
+            {"id": 2, "title": "bank statement 1"},
-            ],
+            {"id": 3, "title": "bank statement 3"},
-        ):
+        ]:
-            result = results[idx]
+            r = result_map[subset["id"]]
-            # Assert subset in results
+            self.assertDictEqual(r, {**r, **subset})
-            self.assertDictEqual(result, {**result, **subset})
 
     @override_settings(
         TIME_ZONE="America/Chicago",
@@ -285,10 +351,10 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
             # 7 days, 1 hour and 1 minute ago
             added=timezone.now() - timedelta(days=7, hours=1, minutes=1),
         )
-        with index.open_index_writer() as writer:
+        backend = get_backend()
-            index.update_document(writer, d1)
+        backend.add_or_update(d1)
-            index.update_document(writer, d2)
+        backend.add_or_update(d2)
-            index.update_document(writer, d3)
+        backend.add_or_update(d3)
 
         response = self.client.get("/api/documents/?query=added:[-1 week to now]")
         results = response.data["results"]
@@ -296,12 +362,14 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
         # Expect 2 documents returned
         self.assertEqual(len(results), 2)
 
-        for idx, subset in enumerate(
+        result_map = {r["id"]: r for r in results}
-            [{"id": 1, "title": "invoice"}, {"id": 2, "title": "bank statement 1"}],
+        self.assertEqual(set(result_map.keys()), {1, 2})
-        ):
+        for subset in [
-            result = results[idx]
+            {"id": 1, "title": "invoice"},
-            # Assert subset in results
+            {"id": 2, "title": "bank statement 1"},
-            self.assertDictEqual(result, {**result, **subset})
+        ]:
+            r = result_map[subset["id"]]
+            self.assertDictEqual(r, {**r, **subset})
 
     @override_settings(
         TIME_ZONE="Europe/Sofia",
@@ -337,10 +405,10 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
             # 7 days, 1 hour and 1 minute ago
             added=timezone.now() - timedelta(days=7, hours=1, minutes=1),
         )
-        with index.open_index_writer() as writer:
+        backend = get_backend()
-            index.update_document(writer, d1)
+        backend.add_or_update(d1)
-            index.update_document(writer, d2)
+        backend.add_or_update(d2)
-            index.update_document(writer, d3)
+        backend.add_or_update(d3)
 
         response = self.client.get("/api/documents/?query=added:[-1 week to now]")
         results = response.data["results"]
@@ -348,12 +416,14 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
         # Expect 2 documents returned
         self.assertEqual(len(results), 2)
 
-        for idx, subset in enumerate(
+        result_map = {r["id"]: r for r in results}
-            [{"id": 1, "title": "invoice"}, {"id": 2, "title": "bank statement 1"}],
+        self.assertEqual(set(result_map.keys()), {1, 2})
-        ):
+        for subset in [
-            result = results[idx]
+            {"id": 1, "title": "invoice"},
-            # Assert subset in results
+            {"id": 2, "title": "bank statement 1"},
-            self.assertDictEqual(result, {**result, **subset})
+        ]:
+            r = result_map[subset["id"]]
+            self.assertDictEqual(r, {**r, **subset})
 
     def test_search_added_in_last_month(self) -> None:
         """
@@ -389,10 +459,10 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
             added=timezone.now() - timedelta(days=7, hours=1, minutes=1),
         )
 
-        with index.open_index_writer() as writer:
+        backend = get_backend()
-            index.update_document(writer, d1)
+        backend.add_or_update(d1)
-            index.update_document(writer, d2)
+        backend.add_or_update(d2)
-            index.update_document(writer, d3)
+        backend.add_or_update(d3)
 
         response = self.client.get("/api/documents/?query=added:[-1 month to now]")
         results = response.data["results"]
@@ -400,12 +470,14 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
         # Expect 2 documents returned
         self.assertEqual(len(results), 2)
 
-        for idx, subset in enumerate(
+        result_map = {r["id"]: r for r in results}
-            [{"id": 1, "title": "invoice"}, {"id": 3, "title": "bank statement 3"}],
+        self.assertEqual(set(result_map.keys()), {1, 3})
-        ):
+        for subset in [
-            result = results[idx]
+            {"id": 1, "title": "invoice"},
-            # Assert subset in results
+            {"id": 3, "title": "bank statement 3"},
-            self.assertDictEqual(result, {**result, **subset})
+        ]:
+            r = result_map[subset["id"]]
+            self.assertDictEqual(r, {**r, **subset})
 
     @override_settings(
         TIME_ZONE="America/Denver",
@@ -445,10 +517,10 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
             added=timezone.now() - timedelta(days=7, hours=1, minutes=1),
         )
 
-        with index.open_index_writer() as writer:
+        backend = get_backend()
-            index.update_document(writer, d1)
+        backend.add_or_update(d1)
-            index.update_document(writer, d2)
+        backend.add_or_update(d2)
-            index.update_document(writer, d3)
+        backend.add_or_update(d3)
 
         response = self.client.get("/api/documents/?query=added:[-1 month to now]")
         results = response.data["results"]
@@ -456,12 +528,14 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
         # Expect 2 documents returned
         self.assertEqual(len(results), 2)
 
-        for idx, subset in enumerate(
+        result_map = {r["id"]: r for r in results}
-            [{"id": 1, "title": "invoice"}, {"id": 3, "title": "bank statement 3"}],
+        self.assertEqual(set(result_map.keys()), {1, 3})
-        ):
+        for subset in [
-            result = results[idx]
+            {"id": 1, "title": "invoice"},
-            # Assert subset in results
+            {"id": 3, "title": "bank statement 3"},
-            self.assertDictEqual(result, {**result, **subset})
+        ]:
+            r = result_map[subset["id"]]
+            self.assertDictEqual(r, {**r, **subset})
 
     @override_settings(
         TIME_ZONE="Europe/Sofia",
@@ -501,10 +575,10 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
         # Django converts dates to UTC
         d3.refresh_from_db()
 
-        with index.open_index_writer() as writer:
+        backend = get_backend()
-            index.update_document(writer, d1)
+        backend.add_or_update(d1)
-            index.update_document(writer, d2)
+        backend.add_or_update(d2)
-            index.update_document(writer, d3)
+        backend.add_or_update(d3)
 
         response = self.client.get("/api/documents/?query=added:20231201")
         results = response.data["results"]
@@ -512,12 +586,8 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
         # Expect 1 document returned
         self.assertEqual(len(results), 1)
 
-        for idx, subset in enumerate(
+        self.assertEqual(results[0]["id"], 3)
-            [{"id": 3, "title": "bank statement 3"}],
+        self.assertEqual(results[0]["title"], "bank statement 3")
-        ):
-            result = results[idx]
-            # Assert subset in results
-            self.assertDictEqual(result, {**result, **subset})
 
     def test_search_added_invalid_date(self) -> None:
         """
@@ -526,7 +596,7 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
         WHEN:
             - Query with invalid added date
         THEN:
-            - No documents returned
+            - 400 Bad Request returned (Tantivy rejects invalid date field syntax)
         """
         d1 = Document.objects.create(
             title="invoice",
@@ -535,16 +605,14 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
             pk=1,
         )
 
-        with index.open_index_writer() as writer:
+        get_backend().add_or_update(d1)
-            index.update_document(writer, d1)
 
         response = self.client.get("/api/documents/?query=added:invalid-date")
-        results = response.data["results"]
 
-        # Expect 0 document returned
+        # Tantivy rejects unparsable field queries with a 400
-        self.assertEqual(len(results), 0)
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
 
-    @mock.patch("documents.index.autocomplete")
+    @mock.patch("documents.search._backend.TantivyBackend.autocomplete")
     def test_search_autocomplete_limits(self, m) -> None:
         """
         GIVEN:
@@ -556,7 +624,7 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
             - Limit requests are obeyed
         """
 
-        m.side_effect = lambda ix, term, limit, user: [term for _ in range(limit)]
+        m.side_effect = lambda term, limit, user=None: [term for _ in range(limit)]
 
         response = self.client.get("/api/search/autocomplete/?term=test")
         self.assertEqual(response.status_code, status.HTTP_200_OK)
@@ -609,32 +677,29 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
             owner=u1,
         )
 
-        with AsyncWriter(index.open_index()) as writer:
+        backend = get_backend()
-            index.update_document(writer, d1)
+        backend.add_or_update(d1)
-            index.update_document(writer, d2)
+        backend.add_or_update(d2)
-            index.update_document(writer, d3)
+        backend.add_or_update(d3)
 
         response = self.client.get("/api/search/autocomplete/?term=app")
         self.assertEqual(response.status_code, status.HTTP_200_OK)
-        self.assertEqual(response.data, [b"apples", b"applebaum", b"appletini"])
+        self.assertEqual(response.data, ["applebaum", "apples", "appletini"])
 
         d3.owner = u2
-
+        d3.save()
-        with AsyncWriter(index.open_index()) as writer:
+        backend.add_or_update(d3)
-            index.update_document(writer, d3)
 
         response = self.client.get("/api/search/autocomplete/?term=app")
         self.assertEqual(response.status_code, status.HTTP_200_OK)
-        self.assertEqual(response.data, [b"apples", b"applebaum"])
+        self.assertEqual(response.data, ["applebaum", "apples"])
 
         assign_perm("view_document", u1, d3)
-
+        backend.add_or_update(d3)
-        with AsyncWriter(index.open_index()) as writer:
-            index.update_document(writer, d3)
 
         response = self.client.get("/api/search/autocomplete/?term=app")
         self.assertEqual(response.status_code, status.HTTP_200_OK)
-        self.assertEqual(response.data, [b"apples", b"applebaum", b"appletini"])
+        self.assertEqual(response.data, ["applebaum", "apples", "appletini"])
 
     def test_search_autocomplete_field_name_match(self) -> None:
         """
@@ -652,8 +717,7 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
             checksum="1",
         )
 
-        with AsyncWriter(index.open_index()) as writer:
+        get_backend().add_or_update(d1)
-            index.update_document(writer, d1)
 
         response = self.client.get("/api/search/autocomplete/?term=created:2023")
         self.assertEqual(response.status_code, status.HTTP_200_OK)
@@ -674,33 +738,36 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
             checksum="1",
         )
 
-        with AsyncWriter(index.open_index()) as writer:
+        get_backend().add_or_update(d1)
-            index.update_document(writer, d1)
 
         response = self.client.get("/api/search/autocomplete/?term=auto")
         self.assertEqual(response.status_code, status.HTTP_200_OK)
-        self.assertEqual(response.data[0], b"auto")
+        self.assertEqual(response.data[0], "auto")
 
-    def test_search_spelling_suggestion(self) -> None:
+    def test_search_no_spelling_suggestion(self) -> None:
-        with AsyncWriter(index.open_index()) as writer:
+        """
-            for i in range(55):
+        GIVEN:
-                doc = Document.objects.create(
+            - Documents exist with various terms
-                    checksum=str(i),
+        WHEN:
-                    pk=i + 1,
+            - Query for documents with any term
-                    title=f"Document {i + 1}",
+        THEN:
-                    content=f"Things document {i + 1}",
+            - corrected_query is always None (Tantivy has no spell correction)
-                )
+        """
-                index.update_document(writer, doc)
+        backend = get_backend()
+        for i in range(5):
+            doc = Document.objects.create(
+                checksum=str(i),
+                pk=i + 1,
+                title=f"Document {i + 1}",
+                content=f"Things document {i + 1}",
+            )
+            backend.add_or_update(doc)
 
         response = self.client.get("/api/documents/?query=thing")
-        correction = response.data["corrected_query"]
+        self.assertIsNone(response.data["corrected_query"])
-
-        self.assertEqual(correction, "things")
 
         response = self.client.get("/api/documents/?query=things")
-        correction = response.data["corrected_query"]
+        self.assertIsNone(response.data["corrected_query"])
-
-        self.assertEqual(correction, None)
 
     def test_search_spelling_suggestion_suppressed_for_private_terms(self):
         owner = User.objects.create_user("owner")
@@ -709,24 +776,24 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
             Permission.objects.get(codename="view_document"),
         )
 
-        with AsyncWriter(index.open_index()) as writer:
+        backend = get_backend()
-            for i in range(55):
+        for i in range(5):
-                private_doc = Document.objects.create(
+            private_doc = Document.objects.create(
-                    checksum=f"p{i}",
+                checksum=f"p{i}",
-                    pk=100 + i,
+                pk=100 + i,
-                    title=f"Private Document {i + 1}",
+                title=f"Private Document {i + 1}",
-                    content=f"treasury document {i + 1}",
+                content=f"treasury document {i + 1}",
-                    owner=owner,
+                owner=owner,
-                )
+            )
-                visible_doc = Document.objects.create(
+            visible_doc = Document.objects.create(
-                    checksum=f"v{i}",
+                checksum=f"v{i}",
-                    pk=200 + i,
+                pk=200 + i,
-                    title=f"Visible Document {i + 1}",
+                title=f"Visible Document {i + 1}",
-                    content=f"public ledger {i + 1}",
+                content=f"public ledger {i + 1}",
-                    owner=attacker,
+                owner=attacker,
-                )
+            )
-                index.update_document(writer, private_doc)
+            backend.add_or_update(private_doc)
-                index.update_document(writer, visible_doc)
+            backend.add_or_update(visible_doc)
 
         self.client.force_authenticate(user=attacker)
 
@@ -736,26 +803,6 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
         self.assertEqual(response.data["count"], 0)
         self.assertIsNone(response.data["corrected_query"])
 
-    @mock.patch(
-        "whoosh.searching.Searcher.correct_query",
-        side_effect=Exception("Test error"),
-    )
-    def test_corrected_query_error(self, mock_correct_query) -> None:
-        """
-        GIVEN:
-            - A query that raises an error on correction
-        WHEN:
-            - API request for search with that query
-        THEN:
-            - The error is logged and the search proceeds
-        """
-        with self.assertLogs("paperless.index", level="INFO") as cm:
-            response = self.client.get("/api/documents/?query=2025-06-04")
-            self.assertEqual(response.status_code, status.HTTP_200_OK)
-            error_str = cm.output[0]
-            expected_str = "Error while correcting query '2025-06-04': Test error"
-            self.assertIn(expected_str, error_str)
-
     def test_search_more_like(self) -> None:
         """
         GIVEN:
@@ -785,16 +832,16 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
             checksum="C",
         )
         d4 = Document.objects.create(
-            title="Monty Python & the Holy Grail",
+            title="Quarterly Report",
-            content="And now for something completely different",
+            content="quarterly revenue profit margin earnings growth",
             pk=4,
             checksum="ABC",
         )
-        with AsyncWriter(index.open_index()) as writer:
+        backend = get_backend()
-            index.update_document(writer, d1)
+        backend.add_or_update(d1)
-            index.update_document(writer, d2)
+        backend.add_or_update(d2)
-            index.update_document(writer, d3)
+        backend.add_or_update(d3)
-            index.update_document(writer, d4)
+        backend.add_or_update(d4)
 
         response = self.client.get(f"/api/documents/?more_like_id={d2.id}")
 
@@ -802,9 +849,10 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
 
         results = response.data["results"]
 
-        self.assertEqual(len(results), 2)
+        self.assertGreaterEqual(len(results), 1)
-        self.assertEqual(results[0]["id"], d3.id)
+        result_ids = [r["id"] for r in results]
-        self.assertEqual(results[1]["id"], d1.id)
+        self.assertIn(d3.id, result_ids)
+        self.assertNotIn(d4.id, result_ids)
 
     def test_search_more_like_requires_view_permission_on_seed_document(
         self,
@@ -846,10 +894,10 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
             pk=12,
         )
 
-        with AsyncWriter(index.open_index()) as writer:
+        backend = get_backend()
-            index.update_document(writer, private_seed)
+        backend.add_or_update(private_seed)
-            index.update_document(writer, visible_doc)
+        backend.add_or_update(visible_doc)
-            index.update_document(writer, other_doc)
+        backend.add_or_update(other_doc)
 
         self.client.force_authenticate(user=attacker)
 
@@ -923,9 +971,9 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
             value_text="foobard4",
         )
 
-        with AsyncWriter(index.open_index()) as writer:
+        backend = get_backend()
-            for doc in Document.objects.all():
+        for doc in Document.objects.all():
-                index.update_document(writer, doc)
+            backend.add_or_update(doc)
 
         def search_query(q):
             r = self.client.get("/api/documents/?query=test" + q)
@@ -1141,9 +1189,9 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
         Document.objects.create(checksum="3", content="test 3", owner=u2)
         Document.objects.create(checksum="4", content="test 4")
 
-        with AsyncWriter(index.open_index()) as writer:
+        backend = get_backend()
-            for doc in Document.objects.all():
+        for doc in Document.objects.all():
-                index.update_document(writer, doc)
+            backend.add_or_update(doc)
 
         self.client.force_authenticate(user=u1)
         r = self.client.get("/api/documents/?query=test")
@@ -1194,9 +1242,9 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
         d3 = Document.objects.create(checksum="3", content="test 3", owner=u2)
         Document.objects.create(checksum="4", content="test 4")
 
-        with AsyncWriter(index.open_index()) as writer:
+        backend = get_backend()
-            for doc in Document.objects.all():
+        for doc in Document.objects.all():
-                index.update_document(writer, doc)
+            backend.add_or_update(doc)
 
         self.client.force_authenticate(user=u1)
         r = self.client.get("/api/documents/?query=test")
@@ -1216,9 +1264,9 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
         assign_perm("view_document", u1, d3)
         assign_perm("view_document", u2, d1)
 
-        with AsyncWriter(index.open_index()) as writer:
+        backend.add_or_update(d1)
-            for doc in [d1, d2, d3]:
+        backend.add_or_update(d2)
-                index.update_document(writer, doc)
+        backend.add_or_update(d3)
 
         self.client.force_authenticate(user=u1)
         r = self.client.get("/api/documents/?query=test")
@@ -1281,9 +1329,9 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
             user=u1,
         )
 
-        with AsyncWriter(index.open_index()) as writer:
+        backend = get_backend()
-            for doc in Document.objects.all():
+        for doc in Document.objects.all():
-                index.update_document(writer, doc)
+            backend.add_or_update(doc)
 
         def search_query(q):
             r = self.client.get("/api/documents/?query=test" + q)
@@ -1316,13 +1364,14 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
             search_query("&ordering=-num_notes"),
             [d1.id, d3.id, d2.id],
         )
+        # 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],
         )
 
     @mock.patch("documents.bulk_edit.bulk_update_documents")
@@ -1379,12 +1428,12 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
         )
         set_permissions([4, 5], set_permissions={}, owner=user2, merge=False)
 
-        with index.open_index_writer() as writer:
+        backend = get_backend()
-            index.update_document(writer, d1)
+        backend.add_or_update(d1)
-            index.update_document(writer, d2)
+        backend.add_or_update(d2)
-            index.update_document(writer, d3)
+        backend.add_or_update(d3)
-            index.update_document(writer, d4)
+        backend.add_or_update(d4)
-            index.update_document(writer, d5)
+        backend.add_or_update(d5)
 
         correspondent1 = Correspondent.objects.create(name="bank correspondent 1")
         Correspondent.objects.create(name="correspondent 2")

src/documents/tests/test_api_status.py

@@ -191,40 +191,42 @@ class TestSystemStatus(APITestCase):
         self.assertEqual(response.status_code, status.HTTP_200_OK)
         self.assertEqual(response.data["tasks"]["celery_status"], "OK")
 
-    @override_settings(INDEX_DIR=Path("/tmp/index"))
+    @mock.patch("documents.search.get_backend")
-    @mock.patch("whoosh.index.FileIndex.last_modified")
+    def test_system_status_index_ok(self, mock_get_backend) -> None:
-    def test_system_status_index_ok(self, mock_last_modified) -> None:
         """
         GIVEN:
-            - The index last modified time is set
+            - The index is accessible
         WHEN:
             - The user requests the system status
         THEN:
             - The response contains the correct index status
         """
-        mock_last_modified.return_value = 1707839087
+        mock_get_backend.return_value = mock.MagicMock()
-        self.client.force_login(self.user)
+        # Use the temp dir created in setUp (self.tmp_dir) as a real INDEX_DIR
-        response = self.client.get(self.ENDPOINT)
+        # with a real file so the mtime lookup works
+        sentinel = self.tmp_dir / "sentinel.txt"
+        sentinel.write_text("ok")
+        with self.settings(INDEX_DIR=self.tmp_dir):
+            self.client.force_login(self.user)
+            response = self.client.get(self.ENDPOINT)
         self.assertEqual(response.status_code, status.HTTP_200_OK)
         self.assertEqual(response.data["tasks"]["index_status"], "OK")
         self.assertIsNotNone(response.data["tasks"]["index_last_modified"])
 
-    @override_settings(INDEX_DIR=Path("/tmp/index/"))
+    @mock.patch("documents.search.get_backend")
-    @mock.patch("documents.index.open_index", autospec=True)
+    def test_system_status_index_error(self, mock_get_backend) -> None:
-    def test_system_status_index_error(self, mock_open_index) -> None:
         """
         GIVEN:
-            - The index is not found
+            - The index cannot be opened
         WHEN:
             - The user requests the system status
         THEN:
             - The response contains the correct index status
         """
-        mock_open_index.return_value = None
+        mock_get_backend.side_effect = Exception("Index error")
-        mock_open_index.side_effect = Exception("Index error")
         self.client.force_login(self.user)
         response = self.client.get(self.ENDPOINT)
-        mock_open_index.assert_called_once()
+        mock_get_backend.assert_called_once()
         self.assertEqual(response.status_code, status.HTTP_200_OK)
         self.assertEqual(response.data["tasks"]["index_status"], "ERROR")
         self.assertIsNotNone(response.data["tasks"]["index_error"])

src/documents/tests/test_delayedquery.py

@@ -1,58 +0,0 @@
-from django.test import TestCase
-from whoosh import query
-
-from documents.index import get_permissions_criterias
-from documents.models import User
-
-
-class TestDelayedQuery(TestCase):
-    def setUp(self) -> None:
-        super().setUp()
-        # all tests run without permission criteria, so has_no_owner query will always
-        # be appended.
-        self.has_no_owner = query.Or([query.Term("has_owner", text=False)])
-
-    def _get_testset__id__in(self, param, field):
-        return (
-            {f"{param}__id__in": "42,43"},
-            query.And(
-                [
-                    query.Or(
-                        [
-                            query.Term(f"{field}_id", "42"),
-                            query.Term(f"{field}_id", "43"),
-                        ],
-                    ),
-                    self.has_no_owner,
-                ],
-            ),
-        )
-
-    def _get_testset__id__none(self, param, field):
-        return (
-            {f"{param}__id__none": "42,43"},
-            query.And(
-                [
-                    query.Not(query.Term(f"{field}_id", "42")),
-                    query.Not(query.Term(f"{field}_id", "43")),
-                    self.has_no_owner,
-                ],
-            ),
-        )
-
-    def test_get_permission_criteria(self) -> None:
-        # tests contains tuples of user instances and the expected filter
-        tests = (
-            (None, [query.Term("has_owner", text=False)]),
-            (User(42, username="foo", is_superuser=True), []),
-            (
-                User(42, username="foo", is_superuser=False),
-                [
-                    query.Term("has_owner", text=False),
-                    query.Term("owner_id", 42),
-                    query.Term("viewer_id", "42"),
-                ],
-            ),
-        )
-        for user, expected in tests:
-            self.assertEqual(get_permissions_criterias(user), expected)

src/documents/tests/test_index.py

@@ -1,371 +0,0 @@
-from datetime import datetime
-from unittest import mock
-
-from django.conf import settings
-from django.contrib.auth.models import User
-from django.test import SimpleTestCase
-from django.test import TestCase
-from django.test import override_settings
-from django.utils.timezone import get_current_timezone
-from django.utils.timezone import timezone
-
-from documents import index
-from documents.models import Document
-from documents.tests.utils import DirectoriesMixin
-
-
-class TestAutoComplete(DirectoriesMixin, TestCase):
-    def test_auto_complete(self) -> None:
-        doc1 = Document.objects.create(
-            title="doc1",
-            checksum="A",
-            content="test test2 test3",
-        )
-        doc2 = Document.objects.create(title="doc2", checksum="B", content="test test2")
-        doc3 = Document.objects.create(title="doc3", checksum="C", content="test2")
-
-        index.add_or_update_document(doc1)
-        index.add_or_update_document(doc2)
-        index.add_or_update_document(doc3)
-
-        ix = index.open_index()
-
-        self.assertListEqual(
-            index.autocomplete(ix, "tes"),
-            [b"test2", b"test", b"test3"],
-        )
-        self.assertListEqual(
-            index.autocomplete(ix, "tes", limit=3),
-            [b"test2", b"test", b"test3"],
-        )
-        self.assertListEqual(index.autocomplete(ix, "tes", limit=1), [b"test2"])
-        self.assertListEqual(index.autocomplete(ix, "tes", limit=0), [])
-
-    def test_archive_serial_number_ranging(self) -> None:
-        """
-        GIVEN:
-            - Document with an archive serial number above schema allowed size
-        WHEN:
-            - Document is provided to the index
-        THEN:
-            - Error is logged
-            - Document ASN is reset to 0 for the index
-        """
-        doc1 = Document.objects.create(
-            title="doc1",
-            checksum="A",
-            content="test test2 test3",
-            # yes, this is allowed, unless full_clean is run
-            # DRF does call the validators, this test won't
-            archive_serial_number=Document.ARCHIVE_SERIAL_NUMBER_MAX + 1,
-        )
-        with self.assertLogs("paperless.index", level="ERROR") as cm:
-            with mock.patch(
-                "documents.index.AsyncWriter.update_document",
-            ) as mocked_update_doc:
-                index.add_or_update_document(doc1)
-
-                mocked_update_doc.assert_called_once()
-                _, kwargs = mocked_update_doc.call_args
-
-                self.assertEqual(kwargs["asn"], 0)
-
-                error_str = cm.output[0]
-                expected_str = "ERROR:paperless.index:Not indexing Archive Serial Number 4294967296 of document 1"
-                self.assertIn(expected_str, error_str)
-
-    def test_archive_serial_number_is_none(self) -> None:
-        """
-        GIVEN:
-            - Document with no archive serial number
-        WHEN:
-            - Document is provided to the index
-        THEN:
-            - ASN isn't touched
-        """
-        doc1 = Document.objects.create(
-            title="doc1",
-            checksum="A",
-            content="test test2 test3",
-        )
-        with mock.patch(
-            "documents.index.AsyncWriter.update_document",
-        ) as mocked_update_doc:
-            index.add_or_update_document(doc1)
-
-            mocked_update_doc.assert_called_once()
-            _, kwargs = mocked_update_doc.call_args
-
-            self.assertIsNone(kwargs["asn"])
-
-    @override_settings(TIME_ZONE="Pacific/Auckland")
-    def test_added_today_respects_local_timezone_boundary(self) -> None:
-        tz = get_current_timezone()
-        fixed_now = datetime(2025, 7, 20, 15, 0, 0, tzinfo=tz)
-
-        # Fake a time near the local boundary (1 AM NZT = 13:00 UTC on previous UTC day)
-        local_dt = datetime(2025, 7, 20, 1, 0, 0).replace(tzinfo=tz)
-        utc_dt = local_dt.astimezone(timezone.utc)
-
-        doc = Document.objects.create(
-            title="Time zone",
-            content="Testing added:today",
-            checksum="edgecase123",
-            added=utc_dt,
-        )
-
-        with index.open_index_writer() as writer:
-            index.update_document(writer, doc)
-
-        superuser = User.objects.create_superuser(username="testuser")
-        self.client.force_login(superuser)
-
-        with mock.patch("documents.index.now", return_value=fixed_now):
-            response = self.client.get("/api/documents/?query=added:today")
-            results = response.json()["results"]
-            self.assertEqual(len(results), 1)
-            self.assertEqual(results[0]["id"], doc.id)
-
-            response = self.client.get("/api/documents/?query=added:yesterday")
-            results = response.json()["results"]
-            self.assertEqual(len(results), 0)
-
-
-@override_settings(TIME_ZONE="UTC")
-class TestRewriteNaturalDateKeywords(SimpleTestCase):
-    """
-    Unit tests for rewrite_natural_date_keywords function.
-    """
-
-    def _rewrite_with_now(self, query: str, now_dt: datetime) -> str:
-        with mock.patch("documents.index.now", return_value=now_dt):
-            return index.rewrite_natural_date_keywords(query)
-
-    def _assert_rewrite_contains(
-        self,
-        query: str,
-        now_dt: datetime,
-        *expected_fragments: str,
-    ) -> str:
-        result = self._rewrite_with_now(query, now_dt)
-        for fragment in expected_fragments:
-            self.assertIn(fragment, result)
-        return result
-
-    def test_range_keywords(self) -> None:
-        """
-        Test various different range keywords
-        """
-        cases = [
-            (
-                "added:today",
-                datetime(2025, 7, 20, 15, 30, 45, tzinfo=timezone.utc),
-                ("added:[20250720", "TO 20250720"),
-            ),
-            (
-                "added:yesterday",
-                datetime(2025, 7, 20, 15, 30, 45, tzinfo=timezone.utc),
-                ("added:[20250719", "TO 20250719"),
-            ),
-            (
-                "added:this month",
-                datetime(2025, 7, 15, 12, 0, 0, tzinfo=timezone.utc),
-                ("added:[20250701", "TO 20250731"),
-            ),
-            (
-                "added:previous month",
-                datetime(2025, 7, 15, 12, 0, 0, tzinfo=timezone.utc),
-                ("added:[20250601", "TO 20250630"),
-            ),
-            (
-                "added:this year",
-                datetime(2025, 7, 15, 12, 0, 0, tzinfo=timezone.utc),
-                ("added:[20250101", "TO 20251231"),
-            ),
-            (
-                "added:previous year",
-                datetime(2025, 7, 15, 12, 0, 0, tzinfo=timezone.utc),
-                ("added:[20240101", "TO 20241231"),
-            ),
-            # Previous quarter from July 15, 2025 is April-June.
-            (
-                "added:previous quarter",
-                datetime(2025, 7, 15, 12, 0, 0, tzinfo=timezone.utc),
-                ("added:[20250401", "TO 20250630"),
-            ),
-            # July 20, 2025 is a Sunday (weekday 6) so previous week is July 7-13.
-            (
-                "added:previous week",
-                datetime(2025, 7, 20, 12, 0, 0, tzinfo=timezone.utc),
-                ("added:[20250707", "TO 20250713"),
-            ),
-        ]
-
-        for query, now_dt, fragments in cases:
-            with self.subTest(query=query):
-                self._assert_rewrite_contains(query, now_dt, *fragments)
-
-    def test_additional_fields(self) -> None:
-        fixed_now = datetime(2025, 7, 20, 15, 30, 45, tzinfo=timezone.utc)
-        # created
-        self._assert_rewrite_contains("created:today", fixed_now, "created:[20250720")
-        # modified
-        self._assert_rewrite_contains("modified:today", fixed_now, "modified:[20250720")
-
-    def test_basic_syntax_variants(self) -> None:
-        """
-        Test that quoting, casing, and multi-clause queries are parsed.
-        """
-        fixed_now = datetime(2025, 7, 20, 15, 30, 45, tzinfo=timezone.utc)
-
-        # quoted keywords
-        result1 = self._rewrite_with_now('added:"today"', fixed_now)
-        result2 = self._rewrite_with_now("added:'today'", fixed_now)
-        self.assertIn("added:[20250720", result1)
-        self.assertIn("added:[20250720", result2)
-
-        # case insensitivity
-        for query in ("added:TODAY", "added:Today", "added:ToDaY"):
-            with self.subTest(case_variant=query):
-                self._assert_rewrite_contains(query, fixed_now, "added:[20250720")
-
-        # multiple clauses
-        result = self._rewrite_with_now("added:today created:yesterday", fixed_now)
-        self.assertIn("added:[20250720", result)
-        self.assertIn("created:[20250719", result)
-
-    def test_no_match(self) -> None:
-        """
-        Test that queries without keywords are unchanged.
-        """
-        query = "title:test content:example"
-        result = index.rewrite_natural_date_keywords(query)
-        self.assertEqual(query, result)
-
-    @override_settings(TIME_ZONE="Pacific/Auckland")
-    def test_timezone_awareness(self) -> None:
-        """
-        Test timezone conversion.
-        """
-        # July 20, 2025 1:00 AM NZST = July 19, 2025 13:00 UTC
-        fixed_now = datetime(2025, 7, 20, 1, 0, 0, tzinfo=get_current_timezone())
-        result = self._rewrite_with_now("added:today", fixed_now)
-        # Should convert to UTC properly
-        self.assertIn("added:[20250719", result)
-
-
-class TestIndexResilience(DirectoriesMixin, SimpleTestCase):
-    def _assert_recreate_called(self, mock_create_in) -> None:
-        mock_create_in.assert_called_once()
-        path_arg, schema_arg = mock_create_in.call_args.args
-        self.assertEqual(path_arg, settings.INDEX_DIR)
-        self.assertEqual(schema_arg.__class__.__name__, "Schema")
-
-    def test_transient_missing_segment_does_not_force_recreate(self) -> None:
-        """
-        GIVEN:
-            - Index directory exists
-        WHEN:
-            - open_index is called
-            - Opening the index raises FileNotFoundError once due to a
-              transient missing segment
-        THEN:
-            - Index is opened successfully on retry
-            - Index is not recreated
-        """
-        file_marker = settings.INDEX_DIR / "file_marker.txt"
-        file_marker.write_text("keep")
-        expected_index = object()
-
-        with (
-            mock.patch("documents.index.exists_in", return_value=True),
-            mock.patch(
-                "documents.index.open_dir",
-                side_effect=[FileNotFoundError("missing"), expected_index],
-            ) as mock_open_dir,
-            mock.patch(
-                "documents.index.create_in",
-            ) as mock_create_in,
-            mock.patch(
-                "documents.index.rmtree",
-            ) as mock_rmtree,
-        ):
-            ix = index.open_index()
-
-        self.assertIs(ix, expected_index)
-        self.assertGreaterEqual(mock_open_dir.call_count, 2)
-        mock_rmtree.assert_not_called()
-        mock_create_in.assert_not_called()
-        self.assertEqual(file_marker.read_text(), "keep")
-
-    def test_transient_errors_exhaust_retries_and_recreate(self) -> None:
-        """
-        GIVEN:
-            - Index directory exists
-        WHEN:
-            - open_index is called
-            - Opening the index raises FileNotFoundError multiple times due to
-              transient missing segments
-        THEN:
-            - Index is recreated after retries are exhausted
-        """
-        recreated_index = object()
-
-        with (
-            self.assertLogs("paperless.index", level="ERROR") as cm,
-            mock.patch("documents.index.exists_in", return_value=True),
-            mock.patch(
-                "documents.index.open_dir",
-                side_effect=FileNotFoundError("missing"),
-            ) as mock_open_dir,
-            mock.patch("documents.index.rmtree") as mock_rmtree,
-            mock.patch(
-                "documents.index.create_in",
-                return_value=recreated_index,
-            ) as mock_create_in,
-        ):
-            ix = index.open_index()
-
-        self.assertIs(ix, recreated_index)
-        self.assertEqual(mock_open_dir.call_count, 4)
-        mock_rmtree.assert_called_once_with(settings.INDEX_DIR)
-        self._assert_recreate_called(mock_create_in)
-        self.assertIn(
-            "Error while opening the index after retries, recreating.",
-            cm.output[0],
-        )
-
-    def test_non_transient_error_recreates_index(self) -> None:
-        """
-        GIVEN:
-            - Index directory exists
-        WHEN:
-            - open_index is called
-            - Opening the index raises a "non-transient" error
-        THEN:
-            - Index is recreated
-        """
-        recreated_index = object()
-
-        with (
-            self.assertLogs("paperless.index", level="ERROR") as cm,
-            mock.patch("documents.index.exists_in", return_value=True),
-            mock.patch(
-                "documents.index.open_dir",
-                side_effect=RuntimeError("boom"),
-            ),
-            mock.patch("documents.index.rmtree") as mock_rmtree,
-            mock.patch(
-                "documents.index.create_in",
-                return_value=recreated_index,
-            ) as mock_create_in,
-        ):
-            ix = index.open_index()
-
-        self.assertIs(ix, recreated_index)
-        mock_rmtree.assert_called_once_with(settings.INDEX_DIR)
-        self._assert_recreate_called(mock_create_in)
-        self.assertIn(
-            "Error while opening the index, recreating.",
-            cm.output[0],
-        )

src/documents/tests/test_management.py

@@ -103,16 +103,75 @@ class TestArchiver(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
 
 
 @pytest.mark.management
-class TestMakeIndex(TestCase):
+@pytest.mark.django_db
-    @mock.patch("documents.management.commands.document_index.index_reindex")
+class TestMakeIndex:
-    def test_reindex(self, m) -> None:
+    def test_reindex(self, mocker: MockerFixture) -> None:
+        """Reindex command must call the backend rebuild method to recreate the index."""
+        mock_get_backend = mocker.patch(
+            "documents.management.commands.document_index.get_backend",
+        )
         call_command("document_index", "reindex", skip_checks=True)
-        m.assert_called_once()
+        mock_get_backend.return_value.rebuild.assert_called_once()
 
-    @mock.patch("documents.management.commands.document_index.index_optimize")
+    def test_optimize(self) -> None:
-    def test_optimize(self, m) -> None:
+        """Optimize command must execute without error (Tantivy handles optimization automatically)."""
         call_command("document_index", "optimize", skip_checks=True)
-        m.assert_called_once()
+
+    def test_reindex_recreate_wipes_index(self, mocker: MockerFixture) -> None:
+        """Reindex with --recreate must wipe the index before rebuilding."""
+        mock_wipe = mocker.patch(
+            "documents.management.commands.document_index.wipe_index",
+        )
+        mock_get_backend = mocker.patch(
+            "documents.management.commands.document_index.get_backend",
+        )
+        call_command("document_index", "reindex", recreate=True, skip_checks=True)
+        mock_wipe.assert_called_once()
+        mock_get_backend.return_value.rebuild.assert_called_once()
+
+    def test_reindex_without_recreate_does_not_wipe_index(
+        self,
+        mocker: MockerFixture,
+    ) -> None:
+        """Reindex without --recreate must not wipe the index."""
+        mock_wipe = mocker.patch(
+            "documents.management.commands.document_index.wipe_index",
+        )
+        mocker.patch(
+            "documents.management.commands.document_index.get_backend",
+        )
+        call_command("document_index", "reindex", skip_checks=True)
+        mock_wipe.assert_not_called()
+
+    def test_reindex_if_needed_skips_when_up_to_date(
+        self,
+        mocker: MockerFixture,
+    ) -> None:
+        """Conditional reindex must skip rebuild when schema version and language match."""
+        mocker.patch(
+            "documents.management.commands.document_index.needs_rebuild",
+            return_value=False,
+        )
+        mock_get_backend = mocker.patch(
+            "documents.management.commands.document_index.get_backend",
+        )
+        call_command("document_index", "reindex", if_needed=True, skip_checks=True)
+        mock_get_backend.return_value.rebuild.assert_not_called()
+
+    def test_reindex_if_needed_runs_when_rebuild_needed(
+        self,
+        mocker: MockerFixture,
+    ) -> None:
+        """Conditional reindex must proceed with rebuild when schema version or language changed."""
+        mocker.patch(
+            "documents.management.commands.document_index.needs_rebuild",
+            return_value=True,
+        )
+        mock_get_backend = mocker.patch(
+            "documents.management.commands.document_index.get_backend",
+        )
+        call_command("document_index", "reindex", if_needed=True, skip_checks=True)
+        mock_get_backend.return_value.rebuild.assert_called_once()
 
 
 @pytest.mark.management

src/documents/tests/test_management_exporter.py

@@ -389,7 +389,7 @@ class TestExportImport(
         self.assertIsFile(
             str(self.target / doc_from_manifest[EXPORTER_FILE_NAME]),
         )
-        self.d3.delete()
+        self.d3.hard_delete()
 
         manifest = self._do_export()
         self.assertRaises(
@@ -868,6 +868,52 @@ class TestExportImport(
             for obj in manifest:
                 self.assertNotEqual(obj["model"], "auditlog.logentry")
 
+    def test_export_import_soft_deleted_document(self) -> None:
+        """
+        GIVEN:
+            - A document with a note and custom field instance has been soft-deleted
+        WHEN:
+            - Export and re-import are performed
+        THEN:
+            - The soft-deleted document, note, and custom field instance
+              survive the round-trip with deleted_at preserved
+        """
+        shutil.rmtree(Path(self.dirs.media_dir) / "documents")
+        shutil.copytree(
+            Path(__file__).parent / "samples" / "documents",
+            Path(self.dirs.media_dir) / "documents",
+        )
+
+        # d1 has self.note and self.cfi1 attached via setUp
+        self.d1.delete()
+
+        self._do_export()
+
+        with paperless_environment():
+            Document.global_objects.all().hard_delete()
+            Correspondent.objects.all().delete()
+            DocumentType.objects.all().delete()
+            Tag.objects.all().delete()
+
+            call_command(
+                "document_importer",
+                "--no-progress-bar",
+                self.target,
+                skip_checks=True,
+            )
+
+            self.assertEqual(Document.global_objects.count(), 4)
+            reimported_doc = Document.global_objects.get(pk=self.d1.pk)
+            self.assertIsNotNone(reimported_doc.deleted_at)
+
+            self.assertEqual(Note.global_objects.count(), 1)
+            reimported_note = Note.global_objects.get(pk=self.note.pk)
+            self.assertIsNotNone(reimported_note.deleted_at)
+
+            self.assertEqual(CustomFieldInstance.global_objects.count(), 1)
+            reimported_cfi = CustomFieldInstance.global_objects.get(pk=self.cfi1.pk)
+            self.assertIsNotNone(reimported_cfi.deleted_at)
+
     def test_export_data_only(self) -> None:
         """
         GIVEN:

src/documents/tests/test_matchables.py

@@ -452,7 +452,10 @@ class TestDocumentConsumptionFinishedSignal(TestCase):
     """
 
     def setUp(self) -> None:
+        from documents.search import reset_backend
+
         TestCase.setUp(self)
+        reset_backend()
         User.objects.create_user(username="test_consumer", password="12345")
         self.doc_contains = Document.objects.create(
             content="I contain the keyword.",
@@ -464,6 +467,9 @@ class TestDocumentConsumptionFinishedSignal(TestCase):
         override_settings(INDEX_DIR=self.index_dir).enable()
 
     def tearDown(self) -> None:
+        from documents.search import reset_backend
+
+        reset_backend()
         shutil.rmtree(self.index_dir, ignore_errors=True)
 
     def test_tag_applied_any(self) -> None:

src/documents/tests/test_tag_hierarchy.py

@@ -11,10 +11,12 @@ from documents.models import WorkflowAction
 from documents.models import WorkflowTrigger
 from documents.serialisers import TagSerializer
 from documents.signals.handlers import run_workflows
+from documents.tests.utils import DirectoriesMixin
 
 
-class TestTagHierarchy(APITestCase):
+class TestTagHierarchy(DirectoriesMixin, APITestCase):
     def setUp(self) -> None:
+        super().setUp()
         self.user = User.objects.create_superuser(username="admin")
         self.client.force_authenticate(user=self.user)
 

src/documents/tests/test_task_signals.py

@@ -2,6 +2,7 @@ import uuid
 from unittest import mock
 
 import celery
+from django.contrib.auth import get_user_model
 from django.test import TestCase
 
 from documents.data_models import ConsumableDocument
@@ -20,6 +21,11 @@ from documents.tests.utils import DirectoriesMixin
 
 @mock.patch("documents.consumer.magic.from_file", fake_magic_from_file)
 class TestTaskSignalHandler(DirectoriesMixin, TestCase):
+    @classmethod
+    def setUpTestData(cls) -> None:
+        super().setUpTestData()
+        cls.user = get_user_model().objects.create_user(username="testuser")
+
     def util_call_before_task_publish_handler(
         self,
         headers_to_use,
@@ -57,7 +63,7 @@ class TestTaskSignalHandler(DirectoriesMixin, TestCase):
                 ),
                 DocumentMetadataOverrides(
                     title="Hello world",
-                    owner_id=1,
+                    owner_id=self.user.id,
                 ),
             ),
             # kwargs
@@ -75,7 +81,7 @@ class TestTaskSignalHandler(DirectoriesMixin, TestCase):
         self.assertEqual(headers["id"], task.task_id)
         self.assertEqual("hello-999.pdf", task.task_file_name)
         self.assertEqual(PaperlessTask.TaskName.CONSUME_FILE, task.task_name)
-        self.assertEqual(1, task.owner_id)
+        self.assertEqual(self.user.id, task.owner_id)
         self.assertEqual(celery.states.PENDING, task.status)
 
     def test_task_prerun_handler(self) -> None:
@@ -208,10 +214,12 @@ class TestTaskSignalHandler(DirectoriesMixin, TestCase):
             mime_type="application/pdf",
         )
 
-        with mock.patch("documents.index.add_or_update_document") as add:
+        with mock.patch("documents.search.get_backend") as mock_get_backend:
+            mock_backend = mock.MagicMock()
+            mock_get_backend.return_value = mock_backend
             add_to_index(sender=None, document=root)
 
-        add.assert_called_once_with(root)
+        mock_backend.add_or_update.assert_called_once_with(root, effective_content="")
 
     def test_add_to_index_reindexes_root_for_version_documents(self) -> None:
         root = Document.objects.create(
@@ -226,13 +234,17 @@ class TestTaskSignalHandler(DirectoriesMixin, TestCase):
             root_document=root,
         )
 
-        with mock.patch("documents.index.add_or_update_document") as add:
+        with mock.patch("documents.search.get_backend") as mock_get_backend:
+            mock_backend = mock.MagicMock()
+            mock_get_backend.return_value = mock_backend
             add_to_index(sender=None, document=version)
 
-        self.assertEqual(add.call_count, 2)
+        self.assertEqual(mock_backend.add_or_update.call_count, 1)
-        self.assertEqual(add.call_args_list[0].args[0].id, version.id)
-        self.assertEqual(add.call_args_list[1].args[0].id, root.id)
         self.assertEqual(
-            add.call_args_list[1].kwargs,
+            mock_backend.add_or_update.call_args_list[0].args[0].id,
+            version.id,
+        )
+        self.assertEqual(
+            mock_backend.add_or_update.call_args_list[0].kwargs,
             {"effective_content": version.content},
         )