Fixes logging so I can see it

.github/workflows/ci-backend.yml

@@ -3,9 +3,21 @@ on:
   push:
     branches-ignore:
       - 'translations**'
+    paths:
+      - 'src/**'
+      - 'pyproject.toml'
+      - 'uv.lock'
+      - 'docker/compose/docker-compose.ci-test.yml'
+      - '.github/workflows/ci-backend.yml'
   pull_request:
     branches-ignore:
       - 'translations**'
+    paths:
+      - 'src/**'
+      - 'pyproject.toml'
+      - 'uv.lock'
+      - 'docker/compose/docker-compose.ci-test.yml'
+      - '.github/workflows/ci-backend.yml'
   workflow_dispatch:
 concurrency:
   group: backend-${{ github.event.pull_request.number || github.ref }}
@@ -14,55 +26,7 @@ env:
   DEFAULT_UV_VERSION: "0.10.x"
   NLTK_DATA: "/usr/share/nltk_data"
 jobs:
-  changes:
-    name: Detect Backend Changes
-    runs-on: ubuntu-slim
-    outputs:
-      backend_changed: ${{ steps.force.outputs.run_all == 'true' || steps.filter.outputs.backend == 'true' }}
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v6.0.2
-        with:
-          fetch-depth: 0
-      - name: Decide run mode
-        id: force
-        run: |
-          if [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
-            echo "run_all=true" >> "$GITHUB_OUTPUT"
-          elif [[ "${{ github.event_name }}" == "push" && ( "${{ github.ref_name }}" == "main" || "${{ github.ref_name }}" == "dev" ) ]]; then
-            echo "run_all=true" >> "$GITHUB_OUTPUT"
-          else
-            echo "run_all=false" >> "$GITHUB_OUTPUT"
-          fi
-      - name: Set diff range
-        id: range
-        if: steps.force.outputs.run_all != 'true'
-        run: |
-          if [[ "${{ github.event_name }}" == "pull_request" ]]; then
-            echo "base=${{ github.event.pull_request.base.sha }}" >> "$GITHUB_OUTPUT"
-          elif [[ "${{ github.event.created }}" == "true" ]]; then
-            echo "base=${{ github.event.repository.default_branch }}" >> "$GITHUB_OUTPUT"
-          else
-            echo "base=${{ github.event.before }}" >> "$GITHUB_OUTPUT"
-          fi
-          echo "ref=${{ github.sha }}" >> "$GITHUB_OUTPUT"
-      - name: Detect changes
-        id: filter
-        if: steps.force.outputs.run_all != 'true'
-        uses: dorny/paths-filter@v3.0.2
-        with:
-          base: ${{ steps.range.outputs.base }}
-          ref: ${{ steps.range.outputs.ref }}
-          filters: |
-            backend:
-              - 'src/**'
-              - 'pyproject.toml'
-              - 'uv.lock'
-              - 'docker/compose/docker-compose.ci-test.yml'
-              - '.github/workflows/ci-backend.yml'
   test:
-    needs: changes
-    if: needs.changes.outputs.backend_changed == 'true'
     name: "Python ${{ matrix.python-version }}"
     runs-on: ubuntu-24.04
     strategy:
@@ -136,8 +100,6 @@ jobs:
           docker compose --file docker/compose/docker-compose.ci-test.yml logs
           docker compose --file docker/compose/docker-compose.ci-test.yml down
   typing:
-    needs: changes
-    if: needs.changes.outputs.backend_changed == 'true'
     name: Check project typing
     runs-on: ubuntu-24.04
     env:
@@ -188,27 +150,3 @@ jobs:
             --show-error-codes \
             --warn-unused-configs \
             src/ | uv run mypy-baseline filter
-  gate:
-    name: Backend CI Gate
-    needs: [changes, test, typing]
-    if: always()
-    runs-on: ubuntu-slim
-    steps:
-      - name: Check gate
-        run: |
-          if [[ "${{ needs.changes.outputs.backend_changed }}" != "true" ]]; then
-            echo "No backend-relevant changes detected."
-            exit 0
-          fi
-
-          if [[ "${{ needs.test.result }}" != "success" ]]; then
-            echo "::error::Backend test job result: ${{ needs.test.result }}"
-            exit 1
-          fi
-
-          if [[ "${{ needs.typing.result }}" != "success" ]]; then
-            echo "::error::Backend typing job result: ${{ needs.typing.result }}"
-            exit 1
-          fi
-
-          echo "Backend checks passed."

.github/workflows/ci-docker.yml

@@ -149,16 +149,15 @@ jobs:
           mkdir -p /tmp/digests
           digest="${{ steps.build.outputs.digest }}"
           echo "digest=${digest}"
-          echo "${digest}" > "/tmp/digests/digest-${{ matrix.arch }}.txt"
+          touch "/tmp/digests/${digest#sha256:}"
       - name: Upload digest
         if: steps.check-push.outputs.should-push == 'true'
         uses: actions/upload-artifact@v7.0.0
         with:
           name: digests-${{ matrix.arch }}
-          path: /tmp/digests/digest-${{ matrix.arch }}.txt
+          path: /tmp/digests/*
           if-no-files-found: error
           retention-days: 1
-          archive: false
   merge-and-push:
     name: Merge and Push Manifest
     runs-on: ubuntu-24.04
@@ -172,7 +171,7 @@ jobs:
         uses: actions/download-artifact@v8.0.0
         with:
           path: /tmp/digests
-          pattern: digest-*.txt
+          pattern: digests-*
           merge-multiple: true
       - name: List digests
         run: |
@@ -218,9 +217,8 @@ jobs:
           tags=$(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "${DOCKER_METADATA_OUTPUT_JSON}")
 
           digests=""
-          for digest_file in digest-*.txt; do
-            digest=$(cat "${digest_file}")
-            digests+="${{ env.REGISTRY }}/${REPOSITORY}@${digest} "
+          for digest in *; do
+            digests+="${{ env.REGISTRY }}/${REPOSITORY}@sha256:${digest} "
           done
 
           echo "Creating manifest with tags: ${tags}"

.github/workflows/ci-docs.yml

@@ -1,9 +1,22 @@
 name: Documentation
 on:
   push:
-    branches-ignore:
-      - 'translations**'
+    branches:
+      - main
+      - dev
+    paths:
+      - 'docs/**'
+      - 'zensical.toml'
+      - 'pyproject.toml'
+      - 'uv.lock'
+      - '.github/workflows/ci-docs.yml'
   pull_request:
+    paths:
+      - 'docs/**'
+      - 'zensical.toml'
+      - 'pyproject.toml'
+      - 'uv.lock'
+      - '.github/workflows/ci-docs.yml'
   workflow_dispatch:
 concurrency:
   group: docs-${{ github.event.pull_request.number || github.ref }}
@@ -16,55 +29,7 @@ env:
   DEFAULT_UV_VERSION: "0.10.x"
   DEFAULT_PYTHON_VERSION: "3.12"
 jobs:
-  changes:
-    name: Detect Docs Changes
-    runs-on: ubuntu-slim
-    outputs:
-      docs_changed: ${{ steps.force.outputs.run_all == 'true' || steps.filter.outputs.docs == 'true' }}
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v6.0.2
-        with:
-          fetch-depth: 0
-      - name: Decide run mode
-        id: force
-        run: |
-          if [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
-            echo "run_all=true" >> "$GITHUB_OUTPUT"
-          elif [[ "${{ github.event_name }}" == "push" && ( "${{ github.ref_name }}" == "main" || "${{ github.ref_name }}" == "dev" ) ]]; then
-            echo "run_all=true" >> "$GITHUB_OUTPUT"
-          else
-            echo "run_all=false" >> "$GITHUB_OUTPUT"
-          fi
-      - name: Set diff range
-        id: range
-        if: steps.force.outputs.run_all != 'true'
-        run: |
-          if [[ "${{ github.event_name }}" == "pull_request" ]]; then
-            echo "base=${{ github.event.pull_request.base.sha }}" >> "$GITHUB_OUTPUT"
-          elif [[ "${{ github.event.created }}" == "true" ]]; then
-            echo "base=${{ github.event.repository.default_branch }}" >> "$GITHUB_OUTPUT"
-          else
-            echo "base=${{ github.event.before }}" >> "$GITHUB_OUTPUT"
-          fi
-          echo "ref=${{ github.sha }}" >> "$GITHUB_OUTPUT"
-      - name: Detect changes
-        id: filter
-        if: steps.force.outputs.run_all != 'true'
-        uses: dorny/paths-filter@v3.0.2
-        with:
-          base: ${{ steps.range.outputs.base }}
-          ref: ${{ steps.range.outputs.ref }}
-          filters: |
-            docs:
-              - 'docs/**'
-              - 'zensical.toml'
-              - 'pyproject.toml'
-              - 'uv.lock'
-              - '.github/workflows/ci-docs.yml'
   build:
-    needs: changes
-    if: needs.changes.outputs.docs_changed == 'true'
     name: Build Documentation
     runs-on: ubuntu-24.04
     steps:
@@ -99,8 +64,8 @@ jobs:
           name: github-pages-${{ github.run_id }}-${{ github.run_attempt }}
   deploy:
     name: Deploy Documentation
-    needs: [changes, build]
-    if: github.event_name == 'push' && github.ref == 'refs/heads/main' && needs.changes.outputs.docs_changed == 'true'
+    needs: build
+    if: github.event_name == 'push' && github.ref == 'refs/heads/main'
     runs-on: ubuntu-24.04
     environment:
       name: github-pages
@@ -111,22 +76,3 @@ jobs:
         id: deployment
         with:
           artifact_name: github-pages-${{ github.run_id }}-${{ github.run_attempt }}
-  gate:
-    name: Docs CI Gate
-    needs: [changes, build]
-    if: always()
-    runs-on: ubuntu-slim
-    steps:
-      - name: Check gate
-        run: |
-          if [[ "${{ needs.changes.outputs.docs_changed }}" != "true" ]]; then
-            echo "No docs-relevant changes detected."
-            exit 0
-          fi
-
-          if [[ "${{ needs.build.result }}" != "success" ]]; then
-            echo "::error::Docs build job result: ${{ needs.build.result }}"
-            exit 1
-          fi
-
-          echo "Docs checks passed."

.github/workflows/ci-frontend.yml

@@ -3,60 +3,21 @@ on:
   push:
     branches-ignore:
       - 'translations**'
+    paths:
+      - 'src-ui/**'
+      - '.github/workflows/ci-frontend.yml'
   pull_request:
     branches-ignore:
       - 'translations**'
+    paths:
+      - 'src-ui/**'
+      - '.github/workflows/ci-frontend.yml'
   workflow_dispatch:
 concurrency:
   group: frontend-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
 jobs:
-  changes:
-    name: Detect Frontend Changes
-    runs-on: ubuntu-slim
-    outputs:
-      frontend_changed: ${{ steps.force.outputs.run_all == 'true' || steps.filter.outputs.frontend == 'true' }}
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v6.0.2
-        with:
-          fetch-depth: 0
-      - name: Decide run mode
-        id: force
-        run: |
-          if [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
-            echo "run_all=true" >> "$GITHUB_OUTPUT"
-          elif [[ "${{ github.event_name }}" == "push" && ( "${{ github.ref_name }}" == "main" || "${{ github.ref_name }}" == "dev" ) ]]; then
-            echo "run_all=true" >> "$GITHUB_OUTPUT"
-          else
-            echo "run_all=false" >> "$GITHUB_OUTPUT"
-          fi
-      - name: Set diff range
-        id: range
-        if: steps.force.outputs.run_all != 'true'
-        run: |
-          if [[ "${{ github.event_name }}" == "pull_request" ]]; then
-            echo "base=${{ github.event.pull_request.base.sha }}" >> "$GITHUB_OUTPUT"
-          elif [[ "${{ github.event.created }}" == "true" ]]; then
-            echo "base=${{ github.event.repository.default_branch }}" >> "$GITHUB_OUTPUT"
-          else
-            echo "base=${{ github.event.before }}" >> "$GITHUB_OUTPUT"
-          fi
-          echo "ref=${{ github.sha }}" >> "$GITHUB_OUTPUT"
-      - name: Detect changes
-        id: filter
-        if: steps.force.outputs.run_all != 'true'
-        uses: dorny/paths-filter@v3.0.2
-        with:
-          base: ${{ steps.range.outputs.base }}
-          ref: ${{ steps.range.outputs.ref }}
-          filters: |
-            frontend:
-              - 'src-ui/**'
-              - '.github/workflows/ci-frontend.yml'
   install-dependencies:
-    needs: changes
-    if: needs.changes.outputs.frontend_changed == 'true'
     name: Install Dependencies
     runs-on: ubuntu-24.04
     steps:
@@ -84,8 +45,7 @@ jobs:
         run: cd src-ui && pnpm install
   lint:
     name: Lint
-    needs: [changes, install-dependencies]
-    if: needs.changes.outputs.frontend_changed == 'true'
+    needs: install-dependencies
     runs-on: ubuntu-24.04
     steps:
       - name: Checkout
@@ -113,8 +73,7 @@ jobs:
         run: cd src-ui && pnpm run lint
   unit-tests:
     name: "Unit Tests (${{ matrix.shard-index }}/${{ matrix.shard-count }})"
-    needs: [changes, install-dependencies]
-    if: needs.changes.outputs.frontend_changed == 'true'
+    needs: install-dependencies
     runs-on: ubuntu-24.04
     strategy:
       fail-fast: false
@@ -160,8 +119,7 @@ jobs:
           directory: src-ui/coverage/
   e2e-tests:
     name: "E2E Tests (${{ matrix.shard-index }}/${{ matrix.shard-count }})"
-    needs: [changes, install-dependencies]
-    if: needs.changes.outputs.frontend_changed == 'true'
+    needs: install-dependencies
     runs-on: ubuntu-24.04
     container: mcr.microsoft.com/playwright:v1.58.2-noble
     env:
@@ -201,8 +159,7 @@ jobs:
         run: cd src-ui && pnpm exec playwright test --shard ${{ matrix.shard-index }}/${{ matrix.shard-count }}
   bundle-analysis:
     name: Bundle Analysis
-    needs: [changes, unit-tests, e2e-tests]
-    if: needs.changes.outputs.frontend_changed == 'true'
+    needs: [unit-tests, e2e-tests]
     runs-on: ubuntu-24.04
     steps:
       - name: Checkout
@@ -232,42 +189,3 @@ jobs:
         env:
           CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
         run: cd src-ui && pnpm run build --configuration=production
-  gate:
-    name: Frontend CI Gate
-    needs: [changes, install-dependencies, lint, unit-tests, e2e-tests, bundle-analysis]
-    if: always()
-    runs-on: ubuntu-slim
-    steps:
-      - name: Check gate
-        run: |
-          if [[ "${{ needs.changes.outputs.frontend_changed }}" != "true" ]]; then
-            echo "No frontend-relevant changes detected."
-            exit 0
-          fi
-
-          if [[ "${{ needs['install-dependencies'].result }}" != "success" ]]; then
-            echo "::error::Frontend install job result: ${{ needs['install-dependencies'].result }}"
-            exit 1
-          fi
-
-          if [[ "${{ needs.lint.result }}" != "success" ]]; then
-            echo "::error::Frontend lint job result: ${{ needs.lint.result }}"
-            exit 1
-          fi
-
-          if [[ "${{ needs['unit-tests'].result }}" != "success" ]]; then
-            echo "::error::Frontend unit-tests job result: ${{ needs['unit-tests'].result }}"
-            exit 1
-          fi
-
-          if [[ "${{ needs['e2e-tests'].result }}" != "success" ]]; then
-            echo "::error::Frontend e2e-tests job result: ${{ needs['e2e-tests'].result }}"
-            exit 1
-          fi
-
-          if [[ "${{ needs['bundle-analysis'].result }}" != "success" ]]; then
-            echo "::error::Frontend bundle-analysis job result: ${{ needs['bundle-analysis'].result }}"
-            exit 1
-          fi
-
-          echo "Frontend checks passed."

.github/workflows/pr-bot.yml

@@ -2,24 +2,13 @@ name: PR Bot
 on:
   pull_request_target:
     types: [opened]
+permissions:
+  contents: read
+  pull-requests: write
 jobs:
-  anti-slop:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      issues: read
-      pull-requests: write
-    steps:
-      - uses: peakoss/anti-slop@v0.2.1
-        with:
-          max-failures: 4
-          failure-add-pr-labels: 'ai'
   pr-bot:
     name: Automated PR Bot
     runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      pull-requests: write
     steps:
       - name: Label PR by file path or branch name
         # see .github/labeler.yml for the labeler config

.pre-commit-config.yaml

@@ -50,7 +50,7 @@ repos:
           - 'prettier-plugin-organize-imports@4.1.0'
   # Python hooks
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.15.5
+    rev: v0.15.0
     hooks:
       - id: ruff-check
       - id: ruff-format

Dockerfile

@@ -30,7 +30,7 @@ RUN set -eux \
 # Purpose: Installs s6-overlay and rootfs
 # Comments:
 #  - Don't leave anything extra in here either
-FROM ghcr.io/astral-sh/uv:0.10.9-python3.12-trixie-slim AS s6-overlay-base
+FROM ghcr.io/astral-sh/uv:0.10.7-python3.12-trixie-slim AS s6-overlay-base
 
 WORKDIR /usr/src/s6
 

docker/compose/docker-compose.portainer.yml

@@ -56,7 +56,6 @@ services:
     environment:
       PAPERLESS_REDIS: redis://broker:6379
       PAPERLESS_DBHOST: db
-      PAPERLESS_DBENGINE: postgres
     env_file:
       - stack.env
 volumes:

docker/compose/docker-compose.postgres-tika.yml

@@ -62,7 +62,6 @@ services:
     environment:
       PAPERLESS_REDIS: redis://broker:6379
       PAPERLESS_DBHOST: db
-      PAPERLESS_DBENGINE: postgres
       PAPERLESS_TIKA_ENABLED: 1
       PAPERLESS_TIKA_GOTENBERG_ENDPOINT: http://gotenberg:3000
       PAPERLESS_TIKA_ENDPOINT: http://tika:9998

docker/compose/docker-compose.postgres.yml

@@ -56,7 +56,6 @@ services:
     environment:
       PAPERLESS_REDIS: redis://broker:6379
       PAPERLESS_DBHOST: db
-      PAPERLESS_DBENGINE: postgres
 volumes:
   data:
   media:

docker/compose/docker-compose.sqlite-tika.yml

@@ -51,7 +51,6 @@ services:
     env_file: docker-compose.env
     environment:
       PAPERLESS_REDIS: redis://broker:6379
-      PAPERLESS_DBENGINE: sqlite
       PAPERLESS_TIKA_ENABLED: 1
       PAPERLESS_TIKA_GOTENBERG_ENDPOINT: http://gotenberg:3000
       PAPERLESS_TIKA_ENDPOINT: http://tika:9998

docker/compose/docker-compose.sqlite.yml

@@ -42,7 +42,6 @@ services:
     env_file: docker-compose.env
     environment:
       PAPERLESS_REDIS: redis://broker:6379
-      PAPERLESS_DBENGINE: sqlite
 volumes:
   data:
   media:

docs/api.md

@@ -305,16 +305,52 @@ The following methods are supported:
         -   `"merge": true or false` (defaults to false)
     -   The `merge` flag determines if the supplied permissions will overwrite all existing permissions (including
         removing them) or be merged with existing permissions.
+-   `edit_pdf`
+    -   Requires `parameters`:
+        -   `"doc_ids": [DOCUMENT_ID]` A list of a single document ID to edit.
+        -   `"operations": [OPERATION, ...]` A list of operations to perform on the documents. Each operation is a dictionary
+            with the following keys:
+            -   `"page": PAGE_NUMBER` The page number to edit (1-based).
+            -   `"rotate": DEGREES` Optional rotation in degrees (90, 180, 270).
+            -   `"doc": OUTPUT_DOCUMENT_INDEX` Optional index of the output document for split operations.
+    -   Optional `parameters`:
+        -   `"delete_original": true` to delete the original documents after editing.
+        -   `"update_document": true` to add the edited PDF as a new version of the root document.
+        -   `"include_metadata": true` to copy metadata from the original document to the edited document.
+-   `remove_password`
+    -   Requires `parameters`:
+        -   `"password": "PASSWORD_STRING"` The password to remove from the PDF documents.
+    -   Optional `parameters`:
+        -   `"update_document": true` to add the password-less PDF as a new version of the root document.
+        -   `"delete_original": true` to delete the original document after editing.
+        -   `"include_metadata": true` to copy metadata from the original document to the new password-less document.
+-   `merge`
+    -   No additional `parameters` required.
+    -   The ordering of the merged document is determined by the list of IDs.
+    -   Optional `parameters`:
+        -   `"metadata_document_id": DOC_ID` apply metadata (tags, correspondent, etc.) from this document to the merged document.
+        -   `"delete_originals": true` to delete the original documents. This requires the calling user being the owner of
+            all documents that are merged.
+-   `split`
+    -   Requires `parameters`:
+        -   `"pages": [..]` The list should be a list of pages and/or a ranges, separated by commas e.g. `"[1,2-3,4,5-7]"`
+    -   Optional `parameters`:
+        -   `"delete_originals": true` to delete the original document after consumption. This requires the calling user being the owner of
+            the document.
+    -   The split operation only accepts a single document.
+-   `rotate`
+    -   Requires `parameters`:
+        -   `"degrees": DEGREES`. Must be an integer i.e. 90, 180, 270
+-   `delete_pages`
+    -   Requires `parameters`:
+        -   `"pages": [..]` The list should be a list of integers e.g. `"[2,3,4]"`
+    -   The delete_pages operation only accepts a single document.
 -   `modify_custom_fields`
     -   Requires `parameters`:
         -   `"add_custom_fields": { CUSTOM_FIELD_ID: VALUE }`: JSON object consisting of custom field id:value pairs to add to the document, can also be a list of custom field IDs
             to add with empty values.
         -   `"remove_custom_fields": [CUSTOM_FIELD_ID]`: custom field ids to remove from the document.
 
-#### Document-editing operations
-
-Beginning with version 10+, the API supports individual endpoints for document-editing operations (`merge`, `rotate`, `edit_pdf`, etc), thus their documentation can be found in the API spec / viewer. Legacy document-editing methods via `/api/documents/bulk_edit/` are still supported for compatibility, are deprecated and clients should migrate to the individual endpoints before they are removed in a future version.
-
 ### Objects
 
 Bulk editing for objects (tags, document types etc.) currently supports set permissions or delete
@@ -333,38 +369,41 @@ operations, using the endpoint: `/api/bulk_edit_objects/`, which requires a json
 
 ## API Versioning
 
-The REST API is versioned.
+The REST API is versioned since Paperless-ngx 1.3.0.
 
 -   Versioning ensures that changes to the API don't break older
     clients.
 -   Clients specify the specific version of the API they wish to use
     with every request and Paperless will handle the request using the
     specified API version.
--   Even if the underlying data model changes, supported older API
-    versions continue to serve compatible data.
--   If no version is specified, Paperless serves the configured default
-    API version (currently `10`).
--   Supported API versions are currently `9` and `10`.
+-   Even if the underlying data model changes, older API versions will
+    always serve compatible data.
+-   If no version is specified, Paperless will serve version 1 to ensure
+    compatibility with older clients that do not request a specific API
+    version.
 
 API versions are specified by submitting an additional HTTP `Accept`
 header with every request:
 
 ```
-Accept: application/json; version=10
+Accept: application/json; version=6
 ```
 
-If an invalid version is specified, Paperless responds with
-`406 Not Acceptable` and an error message in the body.
+If an invalid version is specified, Paperless 1.3.0 will respond with
+"406 Not Acceptable" and an error message in the body. Earlier
+versions of Paperless will serve API version 1 regardless of whether a
+version is specified via the `Accept` header.
 
 If a client wishes to verify whether it is compatible with any given
 server, the following procedure should be performed:
 
-1.  Perform an _authenticated_ request against any API endpoint. The
-    server will add two custom headers to the response:
+1.  Perform an _authenticated_ request against any API endpoint. If the
+    server is on version 1.3.0 or newer, the server will add two custom
+    headers to the response:
 
     ```
-    X-Api-Version: 10
-    X-Version: <server-version>
+    X-Api-Version: 2
+    X-Version: 1.3.0
     ```
 
 2.  Determine whether the client is compatible with this server based on
@@ -431,9 +470,4 @@ Initial API version.
 #### Version 10
 
 -   The `show_on_dashboard` and `show_in_sidebar` fields of saved views have been
-    removed. Relevant settings are now stored in the UISettings model. Compatibility is maintained
-    for versions < 10 until support for API v9 is dropped.
--   Document-editing operations such as `merge`, `rotate`, and `edit_pdf` have been
-    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.
+    removed. Relevant settings are now stored in the UISettings model.

docs/development.md

@@ -75,13 +75,13 @@ first-time setup.
 4.  Install the Python dependencies:
 
     ```bash
-    uv sync --group dev
+    $ uv sync --group dev
     ```
 
 5.  Install pre-commit hooks:
 
     ```bash
-    uv run prek install
+    $ uv run prek install
     ```
 
 6.  Apply migrations and create a superuser (also can be done via the web UI) for your development instance:
@@ -89,8 +89,8 @@ first-time setup.
     ```bash
     # src/
 
-    uv run manage.py migrate
-    uv run manage.py createsuperuser
+    $ uv run manage.py migrate
+    $ uv run manage.py createsuperuser
     ```
 
 7.  You can now either ...
@@ -103,7 +103,7 @@ first-time setup.
 
     -   spin up a bare Redis container
 
-        ```bash
+        ```
         docker run -d -p 6379:6379 --restart unless-stopped redis:latest
         ```
 
@@ -118,18 +118,18 @@ work well for development, but you can use whatever you want.
 Configure the IDE to use the `src/`-folder as the base source folder.
 Configure the following launch configurations in your IDE:
 
--   `uv run manage.py runserver`
--   `uv run manage.py document_consumer`
--   `uv run celery --app paperless worker -l DEBUG` (or any other log level)
+-   `python3 manage.py runserver`
+-   `python3 manage.py document_consumer`
+-   `celery --app paperless worker -l DEBUG` (or any other log level)
 
 To start them all:
 
 ```bash
 # src/
 
-uv run manage.py runserver & \
-  uv run manage.py document_consumer & \
-  uv run celery --app paperless worker -l DEBUG
+$ python3 manage.py runserver & \
+  python3 manage.py document_consumer & \
+  celery --app paperless worker -l DEBUG
 ```
 
 You might need the front end to test your back end code.
@@ -140,8 +140,8 @@ To build the front end once use this command:
 ```bash
 # src-ui/
 
-pnpm install
-pnpm ng build --configuration production
+$ pnpm install
+$ ng build --configuration production
 ```
 
 ### Testing
@@ -199,7 +199,7 @@ The front end is built using AngularJS. In order to get started, you need Node.j
 4.  You can launch a development server by running:
 
     ```bash
-    pnpm ng serve
+    ng serve
     ```
 
     This will automatically update whenever you save. However, in-place
@@ -217,21 +217,21 @@ commit. See [above](#code-formatting-with-pre-commit-hooks) for installation ins
 command such as
 
 ```bash
-git ls-files -- '*.ts' | xargs uv run prek run prettier --files
+$ git ls-files -- '*.ts' | xargs prek run prettier --files
 ```
 
 Front end testing uses Jest and Playwright. Unit tests and e2e tests,
 respectively, can be run non-interactively with:
 
 ```bash
-pnpm ng test
-pnpm playwright test
+$ ng test
+$ npx playwright test
 ```
 
 Playwright also includes a UI which can be run with:
 
 ```bash
-pnpm playwright test --ui
+$ npx playwright test --ui
 ```
 
 ### Building the frontend
@@ -239,7 +239,7 @@ pnpm playwright test --ui
 In order to build the front end and serve it as part of Django, execute:
 
 ```bash
-pnpm ng build --configuration production
+$ ng build --configuration production
 ```
 
 This will build the front end and put it in a location from which the
@@ -312,10 +312,10 @@ end (such as error messages).
 -   The source language of the project is "en_US".
 -   Localization files end up in the folder `src/locale/`.
 -   In order to extract strings from the application, call
-    `uv run manage.py makemessages -l en_US`. This is important after
+    `python3 manage.py makemessages -l en_US`. This is important after
     making changes to translatable strings.
 -   The message files need to be compiled for them to show up in the
-    application. Call `uv run manage.py compilemessages` to do this.
+    application. Call `python3 manage.py compilemessages` to do this.
     The generated files don't get committed into git, since these are
     derived artifacts. The build pipeline takes care of executing this
     command.

pyproject.toml

@@ -49,7 +49,6 @@ dependencies = [
   "flower~=2.0.1",
   "gotenberg-client~=0.13.1",
   "httpx-oauth~=0.16",
-  "ijson>=3.2",
   "imap-tools~=1.11.0",
   "jinja2~=3.1.5",
   "langdetect~=1.0.9",

scripts/post-consumption-example.sh

@@ -19,4 +19,6 @@ following additional information about it:
 * Correspondent: ${DOCUMENT_CORRESPONDENT}
 * Tags: ${DOCUMENT_TAGS}
 
+It was consumed with the passphrase ${PASSPHRASE}
+
 "

src-ui/messages.xlf

@@ -1217,7 +1217,7 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1758</context>
+          <context context-type="linenumber">1756</context>
         </context-group>
       </trans-unit>
       <trans-unit id="1577733187050997705" datatype="html">
@@ -2090,7 +2090,7 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">637</context>
+          <context context-type="linenumber">634</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-version-dropdown/document-version-dropdown.component.html</context>
@@ -2798,23 +2798,23 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1379</context>
+          <context context-type="linenumber">1376</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1759</context>
+          <context context-type="linenumber">1757</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">833</context>
+          <context context-type="linenumber">802</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">871</context>
+          <context context-type="linenumber">835</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">894</context>
+          <context context-type="linenumber">854</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/manage/document-attributes/custom-fields/custom-fields.component.ts</context>
@@ -3400,31 +3400,31 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1332</context>
+          <context context-type="linenumber">1329</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">470</context>
+          <context context-type="linenumber">445</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">510</context>
+          <context context-type="linenumber">485</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">548</context>
+          <context context-type="linenumber">523</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">586</context>
+          <context context-type="linenumber">561</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">648</context>
+          <context context-type="linenumber">623</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">781</context>
+          <context context-type="linenumber">756</context>
         </context-group>
       </trans-unit>
       <trans-unit id="994016933065248559" datatype="html">
@@ -3434,46 +3434,39 @@
           <context context-type="linenumber">9</context>
         </context-group>
       </trans-unit>
-      <trans-unit id="6705735915615634619" datatype="html">
-        <source>{VAR_PLURAL, plural, =1 {One page} other {<x id="INTERPOLATION"/> pages}}</source>
-        <context-group purpose="location">
-          <context context-type="sourcefile">src/app/components/common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component.html</context>
-          <context context-type="linenumber">25</context>
-        </context-group>
-      </trans-unit>
       <trans-unit id="7508164375697837821" datatype="html">
         <source>Use metadata from:</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component.html</context>
-          <context context-type="linenumber">34</context>
+          <context context-type="linenumber">22</context>
         </context-group>
       </trans-unit>
       <trans-unit id="2020403212524346652" datatype="html">
         <source>Regenerate all metadata</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component.html</context>
-          <context context-type="linenumber">36</context>
+          <context context-type="linenumber">24</context>
         </context-group>
       </trans-unit>
       <trans-unit id="2710430925353472741" datatype="html">
         <source>Try to include archive version in merge for non-PDF files</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component.html</context>
-          <context context-type="linenumber">44</context>
+          <context context-type="linenumber">32</context>
         </context-group>
       </trans-unit>
       <trans-unit id="5612366187076076264" datatype="html">
         <source>Delete original documents after successful merge</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component.html</context>
-          <context context-type="linenumber">48</context>
+          <context context-type="linenumber">36</context>
         </context-group>
       </trans-unit>
       <trans-unit id="5138283234724909648" datatype="html">
         <source>Note that only PDFs will be included.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component.html</context>
-          <context context-type="linenumber">51</context>
+          <context context-type="linenumber">39</context>
         </context-group>
       </trans-unit>
       <trans-unit id="1309641780471803652" datatype="html">
@@ -3512,7 +3505,7 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1812</context>
+          <context context-type="linenumber">1808</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6661109599266152398" datatype="html">
@@ -3523,7 +3516,7 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1813</context>
+          <context context-type="linenumber">1809</context>
         </context-group>
       </trans-unit>
       <trans-unit id="5162686434580248853" datatype="html">
@@ -3534,7 +3527,7 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1814</context>
+          <context context-type="linenumber">1810</context>
         </context-group>
       </trans-unit>
       <trans-unit id="8157388568390631653" datatype="html">
@@ -5495,11 +5488,11 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1336</context>
+          <context context-type="linenumber">1333</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">785</context>
+          <context context-type="linenumber">760</context>
         </context-group>
       </trans-unit>
       <trans-unit id="4522609911791833187" datatype="html">
@@ -7327,7 +7320,7 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">415</context>
+          <context context-type="linenumber">390</context>
         </context-group>
         <note priority="1" from="description">this string is used to separate processing, failed and added on the file upload widget</note>
       </trans-unit>
@@ -7702,81 +7695,81 @@
         <source>Error retrieving metadata</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">411</context>
+          <context context-type="linenumber">408</context>
         </context-group>
       </trans-unit>
       <trans-unit id="2218903673684131427" datatype="html">
         <source>An error occurred loading content: <x id="PH" equiv-text="err.message ?? err.toString()"/></source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">512,514</context>
+          <context context-type="linenumber">509,511</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">959,961</context>
+          <context context-type="linenumber">956,958</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6357361810318120957" datatype="html">
         <source>Document was updated</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">632</context>
+          <context context-type="linenumber">629</context>
         </context-group>
       </trans-unit>
       <trans-unit id="5154064822428631306" datatype="html">
         <source>Document was updated at <x id="PH" equiv-text="formattedModified"/>.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">633</context>
+          <context context-type="linenumber">630</context>
         </context-group>
       </trans-unit>
       <trans-unit id="8462497568316256794" datatype="html">
         <source>Reload to discard your local unsaved edits and load the latest remote version.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">634</context>
+          <context context-type="linenumber">631</context>
         </context-group>
       </trans-unit>
       <trans-unit id="7967484035994732534" datatype="html">
         <source>Reload</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">636</context>
+          <context context-type="linenumber">633</context>
         </context-group>
       </trans-unit>
       <trans-unit id="2907037627372942104" datatype="html">
         <source>Document reloaded with latest changes.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">692</context>
+          <context context-type="linenumber">689</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6435639868943916539" datatype="html">
         <source>Document reloaded.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">703</context>
+          <context context-type="linenumber">700</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6142395741265832184" datatype="html">
         <source>Next document</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">805</context>
+          <context context-type="linenumber">802</context>
         </context-group>
       </trans-unit>
       <trans-unit id="651985345816518480" datatype="html">
         <source>Previous document</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">815</context>
+          <context context-type="linenumber">812</context>
         </context-group>
       </trans-unit>
       <trans-unit id="2885986061416655600" datatype="html">
         <source>Close document</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">823</context>
+          <context context-type="linenumber">820</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/services/open-documents.service.ts</context>
@@ -7787,191 +7780,191 @@
         <source>Save document</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">830</context>
+          <context context-type="linenumber">827</context>
         </context-group>
       </trans-unit>
       <trans-unit id="1784543155727940353" datatype="html">
         <source>Save and close / next</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">839</context>
+          <context context-type="linenumber">836</context>
         </context-group>
       </trans-unit>
       <trans-unit id="7427704425579737895" datatype="html">
         <source>Error retrieving version content</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">943</context>
+          <context context-type="linenumber">940</context>
         </context-group>
       </trans-unit>
       <trans-unit id="3456881259945295697" datatype="html">
         <source>Error retrieving suggestions.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1000</context>
+          <context context-type="linenumber">997</context>
         </context-group>
       </trans-unit>
       <trans-unit id="2194092841814123758" datatype="html">
         <source>Document &quot;<x id="PH" equiv-text="newValues.title"/>&quot; saved successfully.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1212</context>
+          <context context-type="linenumber">1209</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1239</context>
+          <context context-type="linenumber">1236</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6626387786259219838" datatype="html">
         <source>Error saving document &quot;<x id="PH" equiv-text="this.document.title"/>&quot;</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1245</context>
+          <context context-type="linenumber">1242</context>
         </context-group>
       </trans-unit>
       <trans-unit id="448882439049417053" datatype="html">
         <source>Error saving document</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1300</context>
+          <context context-type="linenumber">1297</context>
         </context-group>
       </trans-unit>
       <trans-unit id="8410796510716511826" datatype="html">
         <source>Do you really want to move the document &quot;<x id="PH" equiv-text="this.document.title"/>&quot; to the trash?</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1333</context>
+          <context context-type="linenumber">1330</context>
         </context-group>
       </trans-unit>
       <trans-unit id="282586936710748252" datatype="html">
         <source>Documents can be restored prior to permanent deletion.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1334</context>
+          <context context-type="linenumber">1331</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">783</context>
+          <context context-type="linenumber">758</context>
         </context-group>
       </trans-unit>
       <trans-unit id="7295637485862454066" datatype="html">
         <source>Error deleting document</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1355</context>
+          <context context-type="linenumber">1352</context>
         </context-group>
       </trans-unit>
       <trans-unit id="619486176823357521" datatype="html">
         <source>Reprocess confirm</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1375</context>
+          <context context-type="linenumber">1372</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">829</context>
+          <context context-type="linenumber">798</context>
         </context-group>
       </trans-unit>
       <trans-unit id="2951161989614003846" datatype="html">
         <source>This operation will permanently recreate the archive file for this document.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1376</context>
+          <context context-type="linenumber">1373</context>
         </context-group>
       </trans-unit>
       <trans-unit id="302054111564709516" datatype="html">
         <source>The archive file will be re-generated with the current settings.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1377</context>
+          <context context-type="linenumber">1374</context>
         </context-group>
       </trans-unit>
       <trans-unit id="4700389117298802932" datatype="html">
         <source>Reprocess operation for &quot;<x id="PH" equiv-text="this.document.title"/>&quot; will begin in the background.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1385</context>
+          <context context-type="linenumber">1384</context>
         </context-group>
       </trans-unit>
       <trans-unit id="4409560272830824468" datatype="html">
         <source>Error executing operation</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1396</context>
+          <context context-type="linenumber">1395</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6030453331794586802" datatype="html">
         <source>Error downloading document</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1459</context>
+          <context context-type="linenumber">1458</context>
         </context-group>
       </trans-unit>
       <trans-unit id="4458954481601077369" datatype="html">
         <source>Page Fit</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1539</context>
+          <context context-type="linenumber">1538</context>
         </context-group>
       </trans-unit>
       <trans-unit id="4663705961777238777" datatype="html">
         <source>PDF edit operation for &quot;<x id="PH" equiv-text="this.document.title"/>&quot; will begin in the background.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1779</context>
+          <context context-type="linenumber">1775</context>
         </context-group>
       </trans-unit>
       <trans-unit id="9043972994040261999" datatype="html">
         <source>Error executing PDF edit operation</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1791</context>
+          <context context-type="linenumber">1787</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6172690334763056188" datatype="html">
         <source>Please enter the current password before attempting to remove it.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1802</context>
+          <context context-type="linenumber">1798</context>
         </context-group>
       </trans-unit>
       <trans-unit id="968660764814228922" datatype="html">
         <source>Password removal operation for &quot;<x id="PH" equiv-text="this.document.title"/>&quot; will begin in the background.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1836</context>
+          <context context-type="linenumber">1830</context>
         </context-group>
       </trans-unit>
       <trans-unit id="2282118435712883014" datatype="html">
         <source>Error executing password removal operation</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1850</context>
+          <context context-type="linenumber">1844</context>
         </context-group>
       </trans-unit>
       <trans-unit id="3740891324955700797" datatype="html">
         <source>Print failed.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1889</context>
+          <context context-type="linenumber">1883</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6457245677384603573" datatype="html">
         <source>Error loading document for printing.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1901</context>
+          <context context-type="linenumber">1895</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6085793215710522488" datatype="html">
         <source>An error occurred loading tiff: <x id="PH" equiv-text="err.toString()"/></source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1966</context>
+          <context context-type="linenumber">1960</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1970</context>
+          <context context-type="linenumber">1964</context>
         </context-group>
       </trans-unit>
       <trans-unit id="4958946940233632319" datatype="html">
@@ -8215,25 +8208,25 @@
         <source>Error executing bulk operation</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">321</context>
+          <context context-type="linenumber">294</context>
         </context-group>
       </trans-unit>
       <trans-unit id="7894972847287473517" datatype="html">
         <source>&quot;<x id="PH" equiv-text="items[0].name"/>&quot;</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">407</context>
+          <context context-type="linenumber">382</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">413</context>
+          <context context-type="linenumber">388</context>
         </context-group>
       </trans-unit>
       <trans-unit id="8639884465898458690" datatype="html">
         <source>&quot;<x id="PH" equiv-text="items[0].name"/>&quot; and &quot;<x id="PH_1" equiv-text="items[1].name"/>&quot;</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">409</context>
+          <context context-type="linenumber">384</context>
         </context-group>
         <note priority="1" from="description">This is for messages like &apos;modify &quot;tag1&quot; and &quot;tag2&quot;&apos;</note>
       </trans-unit>
@@ -8241,7 +8234,7 @@
         <source><x id="PH" equiv-text="list"/> and &quot;<x id="PH_1" equiv-text="items[items.length - 1].name"/>&quot;</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">417,419</context>
+          <context context-type="linenumber">392,394</context>
         </context-group>
         <note priority="1" from="description">this is for messages like &apos;modify &quot;tag1&quot;, &quot;tag2&quot; and &quot;tag3&quot;&apos;</note>
       </trans-unit>
@@ -8249,14 +8242,14 @@
         <source>Confirm tags assignment</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">434</context>
+          <context context-type="linenumber">409</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6619516195038467207" datatype="html">
         <source>This operation will add the tag &quot;<x id="PH" equiv-text="tag.name"/>&quot; to <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">440</context>
+          <context context-type="linenumber">415</context>
         </context-group>
       </trans-unit>
       <trans-unit id="1894412783609570695" datatype="html">
@@ -8265,14 +8258,14 @@
         )"/> to <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">445,447</context>
+          <context context-type="linenumber">420,422</context>
         </context-group>
       </trans-unit>
       <trans-unit id="7181166515756808573" datatype="html">
         <source>This operation will remove the tag &quot;<x id="PH" equiv-text="tag.name"/>&quot; from <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">453</context>
+          <context context-type="linenumber">428</context>
         </context-group>
       </trans-unit>
       <trans-unit id="3819792277998068944" datatype="html">
@@ -8281,7 +8274,7 @@
         )"/> from <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">458,460</context>
+          <context context-type="linenumber">433,435</context>
         </context-group>
       </trans-unit>
       <trans-unit id="2739066218579571288" datatype="html">
@@ -8292,84 +8285,84 @@
         )"/> on <x id="PH_2" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">462,466</context>
+          <context context-type="linenumber">437,441</context>
         </context-group>
       </trans-unit>
       <trans-unit id="2996713129519325161" datatype="html">
         <source>Confirm correspondent assignment</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">503</context>
+          <context context-type="linenumber">478</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6900893559485781849" datatype="html">
         <source>This operation will assign the correspondent &quot;<x id="PH" equiv-text="correspondent.name"/>&quot; to <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">505</context>
+          <context context-type="linenumber">480</context>
         </context-group>
       </trans-unit>
       <trans-unit id="1257522660364398440" datatype="html">
         <source>This operation will remove the correspondent from <x id="PH" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">507</context>
+          <context context-type="linenumber">482</context>
         </context-group>
       </trans-unit>
       <trans-unit id="5393409374423140648" datatype="html">
         <source>Confirm document type assignment</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">541</context>
+          <context context-type="linenumber">516</context>
         </context-group>
       </trans-unit>
       <trans-unit id="332180123895325027" datatype="html">
         <source>This operation will assign the document type &quot;<x id="PH" equiv-text="documentType.name"/>&quot; to <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">543</context>
+          <context context-type="linenumber">518</context>
         </context-group>
       </trans-unit>
       <trans-unit id="2236642492594872779" datatype="html">
         <source>This operation will remove the document type from <x id="PH" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">545</context>
+          <context context-type="linenumber">520</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6386555513013840736" datatype="html">
         <source>Confirm storage path assignment</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">579</context>
+          <context context-type="linenumber">554</context>
         </context-group>
       </trans-unit>
       <trans-unit id="8750527458618415924" datatype="html">
         <source>This operation will assign the storage path &quot;<x id="PH" equiv-text="storagePath.name"/>&quot; to <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">581</context>
+          <context context-type="linenumber">556</context>
         </context-group>
       </trans-unit>
       <trans-unit id="60728365335056946" datatype="html">
         <source>This operation will remove the storage path from <x id="PH" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">583</context>
+          <context context-type="linenumber">558</context>
         </context-group>
       </trans-unit>
       <trans-unit id="4187352575310415704" datatype="html">
         <source>Confirm custom field assignment</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">612</context>
+          <context context-type="linenumber">587</context>
         </context-group>
       </trans-unit>
       <trans-unit id="7966494636326273856" datatype="html">
         <source>This operation will assign the custom field &quot;<x id="PH" equiv-text="customField.name"/>&quot; to <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">618</context>
+          <context context-type="linenumber">593</context>
         </context-group>
       </trans-unit>
       <trans-unit id="5789455969634598553" datatype="html">
@@ -8378,14 +8371,14 @@
         )"/> to <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">623,625</context>
+          <context context-type="linenumber">598,600</context>
         </context-group>
       </trans-unit>
       <trans-unit id="5648572354333199245" datatype="html">
         <source>This operation will remove the custom field &quot;<x id="PH" equiv-text="customField.name"/>&quot; from <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">631</context>
+          <context context-type="linenumber">606</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6666899594015948817" datatype="html">
@@ -8394,7 +8387,7 @@
         )"/> from <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">636,638</context>
+          <context context-type="linenumber">611,613</context>
         </context-group>
       </trans-unit>
       <trans-unit id="8050047262594964176" datatype="html">
@@ -8405,91 +8398,91 @@
         )"/> on <x id="PH_2" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">640,644</context>
+          <context context-type="linenumber">615,619</context>
         </context-group>
       </trans-unit>
       <trans-unit id="8615059324209654051" datatype="html">
         <source>Move <x id="PH" equiv-text="this.list.selected.size"/> selected document(s) to the trash?</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">782</context>
+          <context context-type="linenumber">757</context>
         </context-group>
       </trans-unit>
       <trans-unit id="8585195717323764335" datatype="html">
         <source>This operation will permanently recreate the archive files for <x id="PH" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">830</context>
+          <context context-type="linenumber">799</context>
         </context-group>
       </trans-unit>
       <trans-unit id="7366623494074776040" datatype="html">
         <source>The archive files will be re-generated with the current settings.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">831</context>
+          <context context-type="linenumber">800</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6555329262222566158" datatype="html">
         <source>Rotate confirm</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">868</context>
+          <context context-type="linenumber">832</context>
         </context-group>
       </trans-unit>
       <trans-unit id="5203024009814367559" datatype="html">
         <source>This operation will add rotated versions of the <x id="PH" equiv-text="this.list.selected.size"/> document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">869</context>
+          <context context-type="linenumber">833</context>
         </context-group>
       </trans-unit>
       <trans-unit id="7910756456450124185" datatype="html">
         <source>Merge confirm</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">892</context>
+          <context context-type="linenumber">852</context>
         </context-group>
       </trans-unit>
       <trans-unit id="7643543647233874431" datatype="html">
         <source>This operation will merge <x id="PH" equiv-text="this.list.selected.size"/> selected documents into a new document.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">893</context>
+          <context context-type="linenumber">853</context>
         </context-group>
       </trans-unit>
       <trans-unit id="7869008840945899895" datatype="html">
         <source>Merged document will be queued for consumption.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">916</context>
+          <context context-type="linenumber">872</context>
         </context-group>
       </trans-unit>
       <trans-unit id="476913782630693351" datatype="html">
         <source>Custom fields updated.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">940</context>
+          <context context-type="linenumber">896</context>
         </context-group>
       </trans-unit>
       <trans-unit id="3873496751167944011" datatype="html">
         <source>Error updating custom fields.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">949</context>
+          <context context-type="linenumber">905</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6144801143088984138" datatype="html">
         <source>Share link bundle creation requested.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">989</context>
+          <context context-type="linenumber">945</context>
         </context-group>
       </trans-unit>
       <trans-unit id="46019676931295023" datatype="html">
         <source>Share link bundle creation is not available yet.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">996</context>
+          <context context-type="linenumber">952</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6307402210351946694" datatype="html">

src-ui/src/app/components/common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component.html

@@ -10,22 +10,10 @@
         <ul class="list-group"
             cdkDropList
             (cdkDropListDropped)="onDrop($event)">
-            @for (document of documents; track document.id) {
-                <li class="list-group-item d-flex align-items-center" cdkDrag>
+            @for (documentID of documentIDs; track documentID) {
+                <li class="list-group-item" cdkDrag>
                     <i-bs name="grip-vertical" class="me-2"></i-bs>
-                    <div class="d-flex flex-column">
-                        <div>
-                          @if (document.correspondent) {
-                            <b>{{document.correspondent | correspondentName | async}}: </b>
-                          }{{document.title}}
-                        </div>
-                        <small class="text-muted">
-                          {{document.created | customDate:'mediumDate'}}
-                          @if (document.page_count) {
-                            | {document.page_count, plural, =1 {One page} other {{{document.page_count}} pages}}
-                          }
-                        </small>
-                    </div>
+                    {{getDocument(documentID)?.title}}
                 </li>
             }
         </ul>

src-ui/src/app/components/common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component.ts

@@ -3,14 +3,11 @@ import {
   DragDropModule,
   moveItemInArray,
 } from '@angular/cdk/drag-drop'
-import { AsyncPipe } from '@angular/common'
 import { Component, OnInit, inject } from '@angular/core'
 import { FormsModule, ReactiveFormsModule } from '@angular/forms'
 import { NgxBootstrapIconsModule } from 'ngx-bootstrap-icons'
 import { takeUntil } from 'rxjs'
 import { Document } from 'src/app/data/document'
-import { CorrespondentNamePipe } from 'src/app/pipes/correspondent-name.pipe'
-import { CustomDatePipe } from 'src/app/pipes/custom-date.pipe'
 import { PermissionsService } from 'src/app/services/permissions.service'
 import { DocumentService } from 'src/app/services/rest/document.service'
 import { ConfirmDialogComponent } from '../confirm-dialog.component'
@@ -20,9 +17,6 @@ import { ConfirmDialogComponent } from '../confirm-dialog.component'
   templateUrl: './merge-confirm-dialog.component.html',
   styleUrl: './merge-confirm-dialog.component.scss',
   imports: [
-    AsyncPipe,
-    CorrespondentNamePipe,
-    CustomDatePipe,
     DragDropModule,
     FormsModule,
     ReactiveFormsModule,

src-ui/src/app/components/common/pdf-editor/pdf-editor.component.spec.ts

@@ -3,7 +3,6 @@ import { provideHttpClientTesting } from '@angular/common/http/testing'
 import { ComponentFixture, TestBed } from '@angular/core/testing'
 import { NgbActiveModal } from '@ng-bootstrap/ng-bootstrap'
 import { NgxBootstrapIconsModule, allIcons } from 'ngx-bootstrap-icons'
-import { DocumentService } from 'src/app/services/rest/document.service'
 import { PDFEditorComponent } from './pdf-editor.component'
 
 describe('PDFEditorComponent', () => {
@@ -140,16 +139,4 @@ describe('PDFEditorComponent', () => {
     expect(component.pages[1].page).toBe(2)
     expect(component.pages[2].page).toBe(3)
   })
-
-  it('should include selected version in preview source when provided', () => {
-    const documentService = TestBed.inject(DocumentService)
-    const previewSpy = jest
-      .spyOn(documentService, 'getPreviewUrl')
-      .mockReturnValue('preview-version')
-    component.documentID = 3
-    component.versionID = 10
-
-    expect(component.pdfSrc).toBe('preview-version')
-    expect(previewSpy).toHaveBeenCalledWith(3, false, 10)
-  })
 })

src-ui/src/app/components/common/pdf-editor/pdf-editor.component.ts

@@ -46,7 +46,6 @@ export class PDFEditorComponent extends ConfirmDialogComponent {
   activeModal: NgbActiveModal = inject(NgbActiveModal)
 
   documentID: number
-  versionID?: number
   pages: PageOperation[] = []
   totalPages = 0
   editMode: PdfEditorEditMode = this.settingsService.get(
@@ -56,11 +55,7 @@ export class PDFEditorComponent extends ConfirmDialogComponent {
   includeMetadata: boolean = true
 
   get pdfSrc(): string {
-    return this.documentService.getPreviewUrl(
-      this.documentID,
-      false,
-      this.versionID
-    )
+    return this.documentService.getPreviewUrl(this.documentID)
   }
 
   pdfLoaded(pdf: PngxPdfDocumentProxy) {

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

@@ -950,8 +950,8 @@ describe('DocumentDetailComponent', () => {
 
   it('should support reprocess, confirm and close modal after started', () => {
     initNormally()
-    const reprocessSpy = jest.spyOn(documentService, 'reprocessDocuments')
-    reprocessSpy.mockReturnValue(of(true))
+    const bulkEditSpy = jest.spyOn(documentService, 'bulkEdit')
+    bulkEditSpy.mockReturnValue(of(true))
     let openModal: NgbModalRef
     modalService.activeInstances.subscribe((modal) => (openModal = modal[0]))
     const modalSpy = jest.spyOn(modalService, 'open')
@@ -959,7 +959,7 @@ describe('DocumentDetailComponent', () => {
     component.reprocess()
     const modalCloseSpy = jest.spyOn(openModal, 'close')
     openModal.componentInstance.confirmClicked.next()
-    expect(reprocessSpy).toHaveBeenCalledWith([doc.id])
+    expect(bulkEditSpy).toHaveBeenCalledWith([doc.id], 'reprocess', {})
     expect(modalSpy).toHaveBeenCalled()
     expect(toastSpy).toHaveBeenCalled()
     expect(modalCloseSpy).toHaveBeenCalled()
@@ -967,13 +967,13 @@ describe('DocumentDetailComponent', () => {
 
   it('should show error if redo ocr call fails', () => {
     initNormally()
-    const reprocessSpy = jest.spyOn(documentService, 'reprocessDocuments')
+    const bulkEditSpy = jest.spyOn(documentService, 'bulkEdit')
     let openModal: NgbModalRef
     modalService.activeInstances.subscribe((modal) => (openModal = modal[0]))
     const toastSpy = jest.spyOn(toastService, 'showError')
     component.reprocess()
     const modalCloseSpy = jest.spyOn(openModal, 'close')
-    reprocessSpy.mockReturnValue(throwError(() => new Error('error occurred')))
+    bulkEditSpy.mockReturnValue(throwError(() => new Error('error occurred')))
     openModal.componentInstance.confirmClicked.next()
     expect(toastSpy).toHaveBeenCalled()
     expect(modalCloseSpy).not.toHaveBeenCalled()
@@ -1661,23 +1661,23 @@ describe('DocumentDetailComponent', () => {
     const closeSpy = jest.spyOn(openDocumentsService, 'closeDocument')
     const errorSpy = jest.spyOn(toastService, 'showError')
     initNormally()
-    component.selectedVersionId = 10
     component.editPdf()
     expect(modal).not.toBeUndefined()
     modal.componentInstance.documentID = doc.id
-    expect(modal.componentInstance.versionID).toBe(10)
     modal.componentInstance.pages = [{ page: 1, rotate: 0, splitAfter: false }]
     modal.componentInstance.confirm()
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/edit_pdf/`
+      `${environment.apiBaseUrl}documents/bulk_edit/`
     )
     expect(req.request.body).toEqual({
-      documents: [10],
-      operations: [{ page: 1, rotate: 0, doc: 0 }],
-      delete_original: false,
-      update_document: false,
-      include_metadata: true,
-      source_mode: 'explicit_selection',
+      documents: [doc.id],
+      method: 'edit_pdf',
+      parameters: {
+        operations: [{ page: 1, rotate: 0, doc: 0 }],
+        delete_original: false,
+        update_document: false,
+        include_metadata: true,
+      },
     })
     req.error(new ErrorEvent('failed'))
     expect(errorSpy).toHaveBeenCalled()
@@ -1688,7 +1688,7 @@ describe('DocumentDetailComponent', () => {
     modal.componentInstance.deleteOriginal = true
     modal.componentInstance.confirm()
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/edit_pdf/`
+      `${environment.apiBaseUrl}documents/bulk_edit/`
     )
     req.flush(true)
     expect(closeSpy).toHaveBeenCalled()
@@ -1698,7 +1698,6 @@ describe('DocumentDetailComponent', () => {
     let modal: NgbModalRef
     modalService.activeInstances.subscribe((m) => (modal = m[0]))
     initNormally()
-    component.selectedVersionId = 10
     component.password = 'secret'
     component.removePassword()
     const dialog =
@@ -1708,15 +1707,17 @@ describe('DocumentDetailComponent', () => {
     dialog.deleteOriginal = true
     dialog.confirm()
     const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/remove_password/`
+      `${environment.apiBaseUrl}documents/bulk_edit/`
     )
     expect(req.request.body).toEqual({
-      documents: [10],
-      password: 'secret',
-      update_document: false,
-      include_metadata: false,
-      delete_original: true,
-      source_mode: 'explicit_selection',
+      documents: [doc.id],
+      method: 'remove_password',
+      parameters: {
+        password: 'secret',
+        update_document: false,
+        include_metadata: false,
+        delete_original: true,
+      },
     })
     req.flush(true)
   })
@@ -1731,7 +1732,7 @@ describe('DocumentDetailComponent', () => {
 
     expect(errorSpy).toHaveBeenCalled()
     httpTestingController.expectNone(
-      `${environment.apiBaseUrl}documents/remove_password/`
+      `${environment.apiBaseUrl}documents/bulk_edit/`
     )
   })
 
@@ -1747,7 +1748,7 @@ describe('DocumentDetailComponent', () => {
       modal.componentInstance as PasswordRemovalConfirmDialogComponent
     dialog.confirm()
     const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/remove_password/`
+      `${environment.apiBaseUrl}documents/bulk_edit/`
     )
     req.error(new ErrorEvent('failed'))
 
@@ -1768,7 +1769,7 @@ describe('DocumentDetailComponent', () => {
       modal.componentInstance as PasswordRemovalConfirmDialogComponent
     dialog.confirm()
     const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/remove_password/`
+      `${environment.apiBaseUrl}documents/bulk_edit/`
     )
     req.flush(true)
 

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

@@ -74,10 +74,7 @@ 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 {
-  BulkEditSourceMode,
-  DocumentService,
-} from 'src/app/services/rest/document.service'
+import { DocumentService } from 'src/app/services/rest/document.service'
 import { SavedViewService } from 'src/app/services/rest/saved-view.service'
 import { StoragePathService } from 'src/app/services/rest/storage-path.service'
 import { TagService } from 'src/app/services/rest/tag.service'
@@ -1379,25 +1376,27 @@ export class DocumentDetailComponent
     modal.componentInstance.btnCaption = $localize`Proceed`
     modal.componentInstance.confirmClicked.subscribe(() => {
       modal.componentInstance.buttonsEnabled = false
-      this.documentsService.reprocessDocuments([this.document.id]).subscribe({
-        next: () => {
-          this.toastService.showInfo(
-            $localize`Reprocess operation for "${this.document.title}" will begin in the background.`
-          )
-          if (modal) {
-            modal.close()
-          }
-        },
-        error: (error) => {
-          if (modal) {
-            modal.componentInstance.buttonsEnabled = true
-          }
-          this.toastService.showError(
-            $localize`Error executing operation`,
-            error
-          )
-        },
-      })
+      this.documentsService
+        .bulkEdit([this.document.id], 'reprocess', {})
+        .subscribe({
+          next: () => {
+            this.toastService.showInfo(
+              $localize`Reprocess operation for "${this.document.title}" will begin in the background.`
+            )
+            if (modal) {
+              modal.close()
+            }
+          },
+          error: (error) => {
+            if (modal) {
+              modal.componentInstance.buttonsEnabled = true
+            }
+            this.toastService.showError(
+              $localize`Error executing operation`,
+              error
+            )
+          },
+        })
     })
   }
 
@@ -1754,23 +1753,20 @@ export class DocumentDetailComponent
       size: 'xl',
       scrollable: true,
     })
-    const sourceDocumentId = this.selectedVersionId ?? this.document.id
     modal.componentInstance.title = $localize`PDF Editor`
     modal.componentInstance.btnCaption = $localize`Proceed`
     modal.componentInstance.documentID = this.document.id
-    modal.componentInstance.versionID = sourceDocumentId
     modal.componentInstance.confirmClicked
       .pipe(takeUntil(this.unsubscribeNotifier))
       .subscribe(() => {
         modal.componentInstance.buttonsEnabled = false
         this.documentsService
-          .editPdfDocuments([sourceDocumentId], {
+          .bulkEdit([this.document.id], 'edit_pdf', {
             operations: modal.componentInstance.getOperations(),
             delete_original: modal.componentInstance.deleteOriginal,
             update_document:
               modal.componentInstance.editMode == PdfEditorEditMode.Update,
             include_metadata: modal.componentInstance.includeMetadata,
-            source_mode: BulkEditSourceMode.EXPLICIT_SELECTION,
           })
           .pipe(first(), takeUntil(this.unsubscribeNotifier))
           .subscribe({
@@ -1816,18 +1812,16 @@ export class DocumentDetailComponent
     modal.componentInstance.confirmClicked
       .pipe(takeUntil(this.unsubscribeNotifier))
       .subscribe(() => {
-        const sourceDocumentId = this.selectedVersionId ?? this.document.id
         const dialog =
           modal.componentInstance as PasswordRemovalConfirmDialogComponent
         dialog.buttonsEnabled = false
         this.networkActive = true
         this.documentsService
-          .removePasswordDocuments([sourceDocumentId], {
+          .bulkEdit([this.document.id], 'remove_password', {
             password: this.password,
             update_document: dialog.updateDocument,
             include_metadata: dialog.includeMetadata,
             delete_original: dialog.deleteOriginal,
-            source_mode: BulkEditSourceMode.EXPLICIT_SELECTION,
           })
           .pipe(first(), takeUntil(this.unsubscribeNotifier))
           .subscribe({

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

@@ -849,11 +849,13 @@ describe('BulkEditorComponent', () => {
     expect(modal).not.toBeUndefined()
     modal.componentInstance.confirm()
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/delete/`
+      `${environment.apiBaseUrl}documents/bulk_edit/`
     )
     req.flush(true)
     expect(req.request.body).toEqual({
       documents: [3, 4],
+      method: 'delete',
+      parameters: {},
     })
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
@@ -866,7 +868,7 @@ describe('BulkEditorComponent', () => {
     fixture.detectChanges()
     component.applyDelete()
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/delete/`
+      `${environment.apiBaseUrl}documents/bulk_edit/`
     )
   })
 
@@ -942,11 +944,13 @@ describe('BulkEditorComponent', () => {
     expect(modal).not.toBeUndefined()
     modal.componentInstance.confirm()
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/reprocess/`
+      `${environment.apiBaseUrl}documents/bulk_edit/`
     )
     req.flush(true)
     expect(req.request.body).toEqual({
       documents: [3, 4],
+      method: 'reprocess',
+      parameters: {},
     })
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
@@ -975,13 +979,13 @@ describe('BulkEditorComponent', () => {
     modal.componentInstance.rotate()
     modal.componentInstance.confirm()
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/rotate/`
+      `${environment.apiBaseUrl}documents/bulk_edit/`
     )
     req.flush(true)
     expect(req.request.body).toEqual({
       documents: [3, 4],
-      degrees: 90,
-      source_mode: 'latest_version',
+      method: 'rotate',
+      parameters: { degrees: 90 },
     })
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
@@ -1017,12 +1021,13 @@ describe('BulkEditorComponent', () => {
     modal.componentInstance.metadataDocumentID = 3
     modal.componentInstance.confirm()
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/merge/`
+      `${environment.apiBaseUrl}documents/bulk_edit/`
     )
     req.flush(true)
     expect(req.request.body).toEqual({
       documents: [3, 4],
-      metadata_document_id: 3,
+      method: 'merge',
+      parameters: { metadata_document_id: 3 },
     })
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
@@ -1035,13 +1040,13 @@ describe('BulkEditorComponent', () => {
     modal.componentInstance.deleteOriginals = true
     modal.componentInstance.confirm()
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/merge/`
+      `${environment.apiBaseUrl}documents/bulk_edit/`
     )
     req.flush(true)
     expect(req.request.body).toEqual({
       documents: [3, 4],
-      metadata_document_id: 3,
-      delete_originals: true,
+      method: 'merge',
+      parameters: { metadata_document_id: 3, delete_originals: true },
     })
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
@@ -1056,13 +1061,13 @@ describe('BulkEditorComponent', () => {
     modal.componentInstance.archiveFallback = true
     modal.componentInstance.confirm()
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/merge/`
+      `${environment.apiBaseUrl}documents/bulk_edit/`
     )
     req.flush(true)
     expect(req.request.body).toEqual({
       documents: [3, 4],
-      metadata_document_id: 3,
-      archive_fallback: true,
+      method: 'merge',
+      parameters: { metadata_document_id: 3, archive_fallback: true },
     })
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`

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

@@ -12,7 +12,7 @@ import {
 } from '@ng-bootstrap/ng-bootstrap'
 import { saveAs } from 'file-saver'
 import { NgxBootstrapIconsModule } from 'ngx-bootstrap-icons'
-import { first, map, Observable, Subject, switchMap, takeUntil } from 'rxjs'
+import { first, map, 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'
@@ -29,9 +29,7 @@ import { CorrespondentService } from 'src/app/services/rest/correspondent.servic
 import { CustomFieldsService } from 'src/app/services/rest/custom-fields.service'
 import { DocumentTypeService } from 'src/app/services/rest/document-type.service'
 import {
-  DocumentBulkEditMethod,
   DocumentService,
-  MergeDocumentsRequest,
   SelectionDataItem,
 } from 'src/app/services/rest/document.service'
 import { SavedViewService } from 'src/app/services/rest/saved-view.service'
@@ -257,9 +255,9 @@ export class BulkEditorComponent
     this.unsubscribeNotifier.complete()
   }
 
-  private executeBulkEditMethod(
+  private executeBulkOperation(
     modal: NgbModalRef,
-    method: DocumentBulkEditMethod,
+    method: string,
     args: any,
     overrideDocumentIDs?: number[]
   ) {
@@ -274,55 +272,32 @@ export class BulkEditorComponent
       )
       .pipe(first())
       .subscribe({
-        next: () => this.handleOperationSuccess(modal),
-        error: (error) => this.handleOperationError(modal, error),
+        next: () => {
+          if (args['delete_originals']) {
+            this.list.selected.clear()
+          }
+          this.list.reload()
+          this.list.reduceSelectionToFilter()
+          this.list.selected.forEach((id) => {
+            this.openDocumentService.refreshDocument(id)
+          })
+          this.savedViewService.maybeRefreshDocumentCounts()
+          if (modal) {
+            modal.close()
+          }
+        },
+        error: (error) => {
+          if (modal) {
+            modal.componentInstance.buttonsEnabled = true
+          }
+          this.toastService.showError(
+            $localize`Error executing bulk operation`,
+            error
+          )
+        },
       })
   }
 
-  private executeDocumentAction(
-    modal: NgbModalRef,
-    request: Observable<any>,
-    options: { deleteOriginals?: boolean } = {}
-  ) {
-    if (modal) {
-      modal.componentInstance.buttonsEnabled = false
-    }
-    request.pipe(first()).subscribe({
-      next: () => {
-        this.handleOperationSuccess(modal, options.deleteOriginals ?? false)
-      },
-      error: (error) => this.handleOperationError(modal, error),
-    })
-  }
-
-  private handleOperationSuccess(
-    modal: NgbModalRef,
-    clearSelection: boolean = false
-  ) {
-    if (clearSelection) {
-      this.list.selected.clear()
-    }
-    this.list.reload()
-    this.list.reduceSelectionToFilter()
-    this.list.selected.forEach((id) => {
-      this.openDocumentService.refreshDocument(id)
-    })
-    this.savedViewService.maybeRefreshDocumentCounts()
-    if (modal) {
-      modal.close()
-    }
-  }
-
-  private handleOperationError(modal: NgbModalRef, error: any) {
-    if (modal) {
-      modal.componentInstance.buttonsEnabled = true
-    }
-    this.toastService.showError(
-      $localize`Error executing bulk operation`,
-      error
-    )
-  }
-
   private applySelectionData(
     items: SelectionDataItem[],
     selectionModel: FilterableDropdownSelectionModel
@@ -471,13 +446,13 @@ export class BulkEditorComponent
       modal.componentInstance.confirmClicked
         .pipe(takeUntil(this.unsubscribeNotifier))
         .subscribe(() => {
-          this.executeBulkEditMethod(modal, 'modify_tags', {
+          this.executeBulkOperation(modal, 'modify_tags', {
             add_tags: changedTags.itemsToAdd.map((t) => t.id),
             remove_tags: changedTags.itemsToRemove.map((t) => t.id),
           })
         })
     } else {
-      this.executeBulkEditMethod(null, 'modify_tags', {
+      this.executeBulkOperation(null, 'modify_tags', {
         add_tags: changedTags.itemsToAdd.map((t) => t.id),
         remove_tags: changedTags.itemsToRemove.map((t) => t.id),
       })
@@ -511,12 +486,12 @@ export class BulkEditorComponent
       modal.componentInstance.confirmClicked
         .pipe(takeUntil(this.unsubscribeNotifier))
         .subscribe(() => {
-          this.executeBulkEditMethod(modal, 'set_correspondent', {
+          this.executeBulkOperation(modal, 'set_correspondent', {
             correspondent: correspondent ? correspondent.id : null,
           })
         })
     } else {
-      this.executeBulkEditMethod(null, 'set_correspondent', {
+      this.executeBulkOperation(null, 'set_correspondent', {
         correspondent: correspondent ? correspondent.id : null,
       })
     }
@@ -549,12 +524,12 @@ export class BulkEditorComponent
       modal.componentInstance.confirmClicked
         .pipe(takeUntil(this.unsubscribeNotifier))
         .subscribe(() => {
-          this.executeBulkEditMethod(modal, 'set_document_type', {
+          this.executeBulkOperation(modal, 'set_document_type', {
             document_type: documentType ? documentType.id : null,
           })
         })
     } else {
-      this.executeBulkEditMethod(null, 'set_document_type', {
+      this.executeBulkOperation(null, 'set_document_type', {
         document_type: documentType ? documentType.id : null,
       })
     }
@@ -587,12 +562,12 @@ export class BulkEditorComponent
       modal.componentInstance.confirmClicked
         .pipe(takeUntil(this.unsubscribeNotifier))
         .subscribe(() => {
-          this.executeBulkEditMethod(modal, 'set_storage_path', {
+          this.executeBulkOperation(modal, 'set_storage_path', {
             storage_path: storagePath ? storagePath.id : null,
           })
         })
     } else {
-      this.executeBulkEditMethod(null, 'set_storage_path', {
+      this.executeBulkOperation(null, 'set_storage_path', {
         storage_path: storagePath ? storagePath.id : null,
       })
     }
@@ -649,7 +624,7 @@ export class BulkEditorComponent
       modal.componentInstance.confirmClicked
         .pipe(takeUntil(this.unsubscribeNotifier))
         .subscribe(() => {
-          this.executeBulkEditMethod(modal, 'modify_custom_fields', {
+          this.executeBulkOperation(modal, 'modify_custom_fields', {
             add_custom_fields: changedCustomFields.itemsToAdd.map((f) => f.id),
             remove_custom_fields: changedCustomFields.itemsToRemove.map(
               (f) => f.id
@@ -657,7 +632,7 @@ export class BulkEditorComponent
           })
         })
     } else {
-      this.executeBulkEditMethod(null, 'modify_custom_fields', {
+      this.executeBulkOperation(null, 'modify_custom_fields', {
         add_custom_fields: changedCustomFields.itemsToAdd.map((f) => f.id),
         remove_custom_fields: changedCustomFields.itemsToRemove.map(
           (f) => f.id
@@ -787,16 +762,10 @@ export class BulkEditorComponent
         .pipe(takeUntil(this.unsubscribeNotifier))
         .subscribe(() => {
           modal.componentInstance.buttonsEnabled = false
-          this.executeDocumentAction(
-            modal,
-            this.documentService.deleteDocuments(Array.from(this.list.selected))
-          )
+          this.executeBulkOperation(modal, 'delete', {})
         })
     } else {
-      this.executeDocumentAction(
-        null,
-        this.documentService.deleteDocuments(Array.from(this.list.selected))
-      )
+      this.executeBulkOperation(null, 'delete', {})
     }
   }
 
@@ -835,12 +804,7 @@ export class BulkEditorComponent
       .pipe(takeUntil(this.unsubscribeNotifier))
       .subscribe(() => {
         modal.componentInstance.buttonsEnabled = false
-        this.executeDocumentAction(
-          modal,
-          this.documentService.reprocessDocuments(
-            Array.from(this.list.selected)
-          )
-        )
+        this.executeBulkOperation(modal, 'reprocess', {})
       })
   }
 
@@ -851,7 +815,7 @@ export class BulkEditorComponent
     modal.componentInstance.confirmClicked.subscribe(
       ({ permissions, merge }) => {
         modal.componentInstance.buttonsEnabled = false
-        this.executeBulkEditMethod(modal, 'set_permissions', {
+        this.executeBulkOperation(modal, 'set_permissions', {
           ...permissions,
           merge,
         })
@@ -874,13 +838,9 @@ export class BulkEditorComponent
       .pipe(takeUntil(this.unsubscribeNotifier))
       .subscribe(() => {
         rotateDialog.buttonsEnabled = false
-        this.executeDocumentAction(
-          modal,
-          this.documentService.rotateDocuments(
-            Array.from(this.list.selected),
-            rotateDialog.degrees
-          )
-        )
+        this.executeBulkOperation(modal, 'rotate', {
+          degrees: rotateDialog.degrees,
+        })
       })
   }
 
@@ -896,22 +856,18 @@ export class BulkEditorComponent
     mergeDialog.confirmClicked
       .pipe(takeUntil(this.unsubscribeNotifier))
       .subscribe(() => {
-        const args: MergeDocumentsRequest = {}
+        const args = {}
         if (mergeDialog.metadataDocumentID > -1) {
-          args.metadata_document_id = mergeDialog.metadataDocumentID
+          args['metadata_document_id'] = mergeDialog.metadataDocumentID
         }
         if (mergeDialog.deleteOriginals) {
-          args.delete_originals = true
+          args['delete_originals'] = true
         }
         if (mergeDialog.archiveFallback) {
-          args.archive_fallback = true
+          args['archive_fallback'] = true
         }
         mergeDialog.buttonsEnabled = false
-        this.executeDocumentAction(
-          modal,
-          this.documentService.mergeDocuments(mergeDialog.documentIDs, args),
-          { deleteOriginals: !!args.delete_originals }
-        )
+        this.executeBulkOperation(modal, 'merge', args, mergeDialog.documentIDs)
         this.toastService.showInfo(
           $localize`Merged document will be queued for consumption.`
         )

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

@@ -230,88 +230,6 @@ describe(`DocumentService`, () => {
     })
   })
 
-  it('should call appropriate api endpoint for delete documents', () => {
-    const ids = [1, 2, 3]
-    subscription = service.deleteDocuments(ids).subscribe()
-    const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}${endpoint}/delete/`
-    )
-    expect(req.request.method).toEqual('POST')
-    expect(req.request.body).toEqual({
-      documents: ids,
-    })
-  })
-
-  it('should call appropriate api endpoint for reprocess documents', () => {
-    const ids = [1, 2, 3]
-    subscription = service.reprocessDocuments(ids).subscribe()
-    const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}${endpoint}/reprocess/`
-    )
-    expect(req.request.method).toEqual('POST')
-    expect(req.request.body).toEqual({
-      documents: ids,
-    })
-  })
-
-  it('should call appropriate api endpoint for rotate documents', () => {
-    const ids = [1, 2, 3]
-    subscription = service.rotateDocuments(ids, 90).subscribe()
-    const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}${endpoint}/rotate/`
-    )
-    expect(req.request.method).toEqual('POST')
-    expect(req.request.body).toEqual({
-      documents: ids,
-      degrees: 90,
-      source_mode: 'latest_version',
-    })
-  })
-
-  it('should call appropriate api endpoint for merge documents', () => {
-    const ids = [1, 2, 3]
-    const args = { metadata_document_id: 1, delete_originals: true }
-    subscription = service.mergeDocuments(ids, args).subscribe()
-    const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}${endpoint}/merge/`
-    )
-    expect(req.request.method).toEqual('POST')
-    expect(req.request.body).toEqual({
-      documents: ids,
-      metadata_document_id: 1,
-      delete_originals: true,
-    })
-  })
-
-  it('should call appropriate api endpoint for edit pdf', () => {
-    const ids = [1]
-    const args = { operations: [{ page: 1, rotate: 90, doc: 0 }] }
-    subscription = service.editPdfDocuments(ids, args).subscribe()
-    const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}${endpoint}/edit_pdf/`
-    )
-    expect(req.request.method).toEqual('POST')
-    expect(req.request.body).toEqual({
-      documents: ids,
-      operations: [{ page: 1, rotate: 90, doc: 0 }],
-    })
-  })
-
-  it('should call appropriate api endpoint for remove password', () => {
-    const ids = [1]
-    const args = { password: 'secret', update_document: true }
-    subscription = service.removePasswordDocuments(ids, args).subscribe()
-    const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}${endpoint}/remove_password/`
-    )
-    expect(req.request.method).toEqual('POST')
-    expect(req.request.body).toEqual({
-      documents: ids,
-      password: 'secret',
-      update_document: true,
-    })
-  })
-
   it('should return the correct preview URL for a single document', () => {
     let url = service.getPreviewUrl(documents[0].id)
     expect(url).toEqual(

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

@@ -37,50 +37,6 @@ export interface SelectionData {
   selected_custom_fields: SelectionDataItem[]
 }
 
-export enum BulkEditSourceMode {
-  LATEST_VERSION = 'latest_version',
-  EXPLICIT_SELECTION = 'explicit_selection',
-}
-
-export type DocumentBulkEditMethod =
-  | 'set_correspondent'
-  | 'set_document_type'
-  | 'set_storage_path'
-  | 'add_tag'
-  | 'remove_tag'
-  | 'modify_tags'
-  | 'modify_custom_fields'
-  | 'set_permissions'
-
-export interface MergeDocumentsRequest {
-  metadata_document_id?: number
-  delete_originals?: boolean
-  archive_fallback?: boolean
-  source_mode?: BulkEditSourceMode
-}
-
-export interface EditPdfOperation {
-  page: number
-  rotate?: number
-  doc?: number
-}
-
-export interface EditPdfDocumentsRequest {
-  operations: EditPdfOperation[]
-  delete_original?: boolean
-  update_document?: boolean
-  include_metadata?: boolean
-  source_mode?: BulkEditSourceMode
-}
-
-export interface RemovePasswordDocumentsRequest {
-  password: string
-  update_document?: boolean
-  delete_original?: boolean
-  include_metadata?: boolean
-  source_mode?: BulkEditSourceMode
-}
-
 @Injectable({
   providedIn: 'root',
 })
@@ -338,7 +294,7 @@ export class DocumentService extends AbstractPaperlessService<Document> {
     return this.http.get<DocumentMetadata>(url.toString())
   }
 
-  bulkEdit(ids: number[], method: DocumentBulkEditMethod, args: any) {
+  bulkEdit(ids: number[], method: string, args: any) {
     return this.http.post(this.getResourceUrl(null, 'bulk_edit'), {
       documents: ids,
       method: method,
@@ -346,54 +302,6 @@ export class DocumentService extends AbstractPaperlessService<Document> {
     })
   }
 
-  deleteDocuments(ids: number[]) {
-    return this.http.post(this.getResourceUrl(null, 'delete'), {
-      documents: ids,
-    })
-  }
-
-  reprocessDocuments(ids: number[]) {
-    return this.http.post(this.getResourceUrl(null, 'reprocess'), {
-      documents: ids,
-    })
-  }
-
-  rotateDocuments(
-    ids: number[],
-    degrees: number,
-    sourceMode: BulkEditSourceMode = BulkEditSourceMode.LATEST_VERSION
-  ) {
-    return this.http.post(this.getResourceUrl(null, 'rotate'), {
-      documents: ids,
-      degrees,
-      source_mode: sourceMode,
-    })
-  }
-
-  mergeDocuments(ids: number[], request: MergeDocumentsRequest = {}) {
-    return this.http.post(this.getResourceUrl(null, 'merge'), {
-      documents: ids,
-      ...request,
-    })
-  }
-
-  editPdfDocuments(ids: number[], request: EditPdfDocumentsRequest) {
-    return this.http.post(this.getResourceUrl(null, 'edit_pdf'), {
-      documents: ids,
-      ...request,
-    })
-  }
-
-  removePasswordDocuments(
-    ids: number[],
-    request: RemovePasswordDocumentsRequest
-  ) {
-    return this.http.post(this.getResourceUrl(null, 'remove_password'), {
-      documents: ids,
-      ...request,
-    })
-  }
-
   getSelectionData(ids: number[]): Observable<SelectionData> {
     return this.http.post<SelectionData>(
       this.getResourceUrl(null, 'selection_data'),

src/documents/bulk_edit.py

@@ -29,21 +29,12 @@ from documents.plugins.helpers import DocumentsStatusManager
 from documents.tasks import bulk_update_documents
 from documents.tasks import consume_file
 from documents.tasks import update_document_content_maybe_archive_file
-from documents.versioning import get_latest_version_for_root
-from documents.versioning import get_root_document
 
 if TYPE_CHECKING:
     from django.contrib.auth.models import User
 
 logger: logging.Logger = logging.getLogger("paperless.bulk_edit")
 
-SourceMode = Literal["latest_version", "explicit_selection"]
-
-
-class SourceModeChoices:
-    LATEST_VERSION: SourceMode = "latest_version"
-    EXPLICIT_SELECTION: SourceMode = "explicit_selection"
-
 
 @shared_task(bind=True)
 def restore_archive_serial_numbers_task(
@@ -81,21 +72,46 @@ def restore_archive_serial_numbers(backup: dict[int, int | None]) -> None:
     logger.info(f"Restored archive serial numbers for documents {list(backup.keys())}")
 
 
-def _resolve_root_and_source_doc(
-    doc: Document,
-    *,
-    source_mode: SourceMode = SourceModeChoices.LATEST_VERSION,
-) -> tuple[Document, Document]:
-    root_doc = get_root_document(doc)
+def _get_root_ids_by_doc_id(doc_ids: list[int]) -> dict[int, int]:
+    """
+    Resolve each provided document id to its root document id.
 
-    if source_mode == SourceModeChoices.EXPLICIT_SELECTION:
-        return root_doc, doc
+    - If the id is already a root document: root id is itself.
+    - If the id is a version document: root id is its `root_document_id`.
+    """
+    qs = Document.objects.filter(id__in=doc_ids).only("id", "root_document_id")
+    return {doc.id: doc.root_document_id or doc.id for doc in qs}
 
-    # Version IDs are explicit by default, only a selected root resolves to latest
-    if doc.root_document_id is not None:
-        return root_doc, doc
 
-    return root_doc, get_latest_version_for_root(root_doc)
+def _get_root_and_current_docs_by_root_id(
+    root_ids: set[int],
+) -> tuple[dict[int, Document], dict[int, Document]]:
+    """
+    Returns:
+      - root_docs: root_id -> root Document
+      - current_docs: root_id -> newest version Document (or root if none)
+    """
+    root_docs = {
+        doc.id: doc
+        for doc in Document.objects.filter(id__in=root_ids).select_related(
+            "owner",
+        )
+    }
+    latest_versions_by_root_id: dict[int, Document] = {}
+    for version_doc in Document.objects.filter(root_document_id__in=root_ids).order_by(
+        "root_document_id",
+        "-id",
+    ):
+        root_id = version_doc.root_document_id
+        if root_id is None:
+            continue
+        latest_versions_by_root_id.setdefault(root_id, version_doc)
+
+    current_docs: dict[int, Document] = {
+        root_id: latest_versions_by_root_id.get(root_id, root_docs[root_id])
+        for root_id in root_docs
+    }
+    return root_docs, current_docs
 
 
 def set_correspondent(
@@ -405,32 +421,21 @@ def rotate(
     doc_ids: list[int],
     degrees: int,
     *,
-    source_mode: SourceMode = SourceModeChoices.LATEST_VERSION,
     user: User | None = None,
 ) -> Literal["OK"]:
     logger.info(
         f"Attempting to rotate {len(doc_ids)} documents by {degrees} degrees.",
     )
-    docs_by_id = {
-        doc.id: doc
-        for doc in Document.objects.select_related("root_document").filter(
-            id__in=doc_ids,
-        )
-    }
-    docs_by_root_id: dict[int, tuple[Document, Document]] = {}
-    for doc_id in doc_ids:
-        doc = docs_by_id.get(doc_id)
-        if doc is None:
-            continue
-        root_doc, source_doc = _resolve_root_and_source_doc(
-            doc,
-            source_mode=source_mode,
-        )
-        docs_by_root_id.setdefault(root_doc.id, (root_doc, source_doc))
-
+    doc_to_root_id = _get_root_ids_by_doc_id(doc_ids)
+    root_ids = set(doc_to_root_id.values())
+    root_docs_by_id, current_docs_by_root_id = _get_root_and_current_docs_by_root_id(
+        root_ids,
+    )
     import pikepdf
 
-    for root_doc, source_doc in docs_by_root_id.values():
+    for root_id in root_ids:
+        root_doc = root_docs_by_id[root_id]
+        source_doc = current_docs_by_root_id[root_id]
         if source_doc.mime_type != "application/pdf":
             logger.warning(
                 f"Document {root_doc.id} is not a PDF, skipping rotation.",
@@ -476,14 +481,12 @@ def merge(
     metadata_document_id: int | None = None,
     delete_originals: bool = False,
     archive_fallback: bool = False,
-    source_mode: SourceMode = SourceModeChoices.LATEST_VERSION,
     user: User | None = None,
 ) -> Literal["OK"]:
     logger.info(
         f"Attempting to merge {len(doc_ids)} documents into a single document.",
     )
-    qs = Document.objects.select_related("root_document").filter(id__in=doc_ids)
-    docs_by_id = {doc.id: doc for doc in qs}
+    qs = Document.objects.filter(id__in=doc_ids)
     affected_docs: list[int] = []
     import pikepdf
 
@@ -492,20 +495,14 @@ def merge(
     handoff_asn: int | None = None
     # use doc_ids to preserve order
     for doc_id in doc_ids:
-        doc = docs_by_id.get(doc_id)
-        if doc is None:
-            continue
-        _, source_doc = _resolve_root_and_source_doc(
-            doc,
-            source_mode=source_mode,
-        )
+        doc = qs.get(id=doc_id)
         try:
             doc_path = (
-                source_doc.archive_path
+                doc.archive_path
                 if archive_fallback
-                and source_doc.mime_type != "application/pdf"
-                and source_doc.has_archive_version
-                else source_doc.source_path
+                and doc.mime_type != "application/pdf"
+                and doc.has_archive_version
+                else doc.source_path
             )
             with pikepdf.open(str(doc_path)) as pdf:
                 version = max(version, pdf.pdf_version)
@@ -587,23 +584,18 @@ def split(
     pages: list[list[int]],
     *,
     delete_originals: bool = False,
-    source_mode: SourceMode = SourceModeChoices.LATEST_VERSION,
     user: User | None = None,
 ) -> Literal["OK"]:
     logger.info(
         f"Attempting to split document {doc_ids[0]} into {len(pages)} documents",
     )
-    doc = Document.objects.select_related("root_document").get(id=doc_ids[0])
-    _, source_doc = _resolve_root_and_source_doc(
-        doc,
-        source_mode=source_mode,
-    )
+    doc = Document.objects.get(id=doc_ids[0])
     import pikepdf
 
     consume_tasks = []
 
     try:
-        with pikepdf.open(source_doc.source_path) as pdf:
+        with pikepdf.open(doc.source_path) as pdf:
             for idx, split_doc in enumerate(pages):
                 dst: pikepdf.Pdf = pikepdf.new()
                 for page in split_doc:
@@ -667,17 +659,25 @@ def delete_pages(
     doc_ids: list[int],
     pages: list[int],
     *,
-    source_mode: SourceMode = SourceModeChoices.LATEST_VERSION,
     user: User | None = None,
 ) -> Literal["OK"]:
     logger.info(
         f"Attempting to delete pages {pages} from {len(doc_ids)} documents",
     )
     doc = Document.objects.select_related("root_document").get(id=doc_ids[0])
-    root_doc, source_doc = _resolve_root_and_source_doc(
-        doc,
-        source_mode=source_mode,
+    root_doc: Document
+    if doc.root_document_id is None or doc.root_document is None:
+        root_doc = doc
+    else:
+        root_doc = doc.root_document
+
+    source_doc = (
+        Document.objects.filter(Q(id=root_doc.id) | Q(root_document=root_doc))
+        .order_by("-id")
+        .first()
     )
+    if source_doc is None:
+        source_doc = root_doc
     pages = sorted(pages)  # sort pages to avoid index issues
     import pikepdf
 
@@ -722,7 +722,6 @@ def edit_pdf(
     delete_original: bool = False,
     update_document: bool = False,
     include_metadata: bool = True,
-    source_mode: SourceMode = SourceModeChoices.LATEST_VERSION,
     user: User | None = None,
 ) -> Literal["OK"]:
     """
@@ -737,10 +736,19 @@ def edit_pdf(
         f"Editing PDF of document {doc_ids[0]} with {len(operations)} operations",
     )
     doc = Document.objects.select_related("root_document").get(id=doc_ids[0])
-    root_doc, source_doc = _resolve_root_and_source_doc(
-        doc,
-        source_mode=source_mode,
+    root_doc: Document
+    if doc.root_document_id is None or doc.root_document is None:
+        root_doc = doc
+    else:
+        root_doc = doc.root_document
+
+    source_doc = (
+        Document.objects.filter(Q(id=root_doc.id) | Q(root_document=root_doc))
+        .order_by("-id")
+        .first()
     )
+    if source_doc is None:
+        source_doc = root_doc
     import pikepdf
 
     pdf_docs: list[pikepdf.Pdf] = []
@@ -851,7 +859,6 @@ def remove_password(
     update_document: bool = False,
     delete_original: bool = False,
     include_metadata: bool = True,
-    source_mode: SourceMode = SourceModeChoices.LATEST_VERSION,
     user: User | None = None,
 ) -> Literal["OK"]:
     """
@@ -861,10 +868,19 @@ def remove_password(
 
     for doc_id in doc_ids:
         doc = Document.objects.select_related("root_document").get(id=doc_id)
-        root_doc, source_doc = _resolve_root_and_source_doc(
-            doc,
-            source_mode=source_mode,
+        root_doc: Document
+        if doc.root_document_id is None or doc.root_document is None:
+            root_doc = doc
+        else:
+            root_doc = doc.root_document
+
+        source_doc = (
+            Document.objects.filter(Q(id=root_doc.id) | Q(root_document=root_doc))
+            .order_by("-id")
+            .first()
         )
+        if source_doc is None:
+            source_doc = root_doc
         try:
             logger.info(
                 f"Attempting password removal from document {doc_ids[0]}",

src/documents/consumer.py

@@ -1,5 +1,4 @@
 import datetime
-import hashlib
 import os
 import tempfile
 from enum import StrEnum
@@ -48,6 +47,7 @@ from documents.signals import document_consumption_started
 from documents.signals import document_updated
 from documents.signals.handlers import run_workflows
 from documents.templating.workflows import parse_w_workflow_placeholders
+from documents.utils import compute_checksum
 from documents.utils import copy_basic_file_stats
 from documents.utils import copy_file_with_basic_stats
 from documents.utils import run_subprocess
@@ -196,9 +196,7 @@ class ConsumerPlugin(
         version_doc = Document(
             root_document=root_doc_frozen,
             version_index=next_version_index + 1,
-            checksum=hashlib.md5(
-                file_for_checksum.read_bytes(),
-            ).hexdigest(),
+            checksum=compute_checksum(file_for_checksum),
             content=text or "",
             page_count=page_count,
             mime_type=mime_type,
@@ -656,10 +654,9 @@ class ConsumerPlugin(
                             document.archive_path,
                         )
 
-                        with Path(archive_path).open("rb") as f:
-                            document.archive_checksum = hashlib.md5(
-                                f.read(),
-                            ).hexdigest()
+                        document.archive_checksum = compute_checksum(
+                            Path(archive_path),
+                        )
 
                 # Don't save with the lock active. Saving will cause the file
                 # renaming logic to acquire the lock as well.
@@ -800,7 +797,7 @@ class ConsumerPlugin(
             title=title[:127],
             content=text,
             mime_type=mime_type,
-            checksum=hashlib.md5(file_for_checksum.read_bytes()).hexdigest(),
+            checksum=compute_checksum(file_for_checksum),
             created=create_date,
             modified=create_date,
             page_count=page_count,
@@ -917,10 +914,9 @@ class ConsumerPreflightPlugin(
 
     def pre_check_duplicate(self) -> None:
         """
-        Using the MD5 of the file, check this exact file doesn't already exist
+        Using the SHA256 of the file, check this exact file doesn't already exist
         """
-        with Path(self.input_doc.original_file).open("rb") as f:
-            checksum = hashlib.md5(f.read()).hexdigest()
+        checksum = compute_checksum(Path(self.input_doc.original_file))
         existing_doc = Document.global_objects.filter(
             Q(checksum=checksum) | Q(archive_checksum=checksum),
         )

src/documents/management/commands/base.py

@@ -304,7 +304,7 @@ class PaperlessCommand(RichCommand):
 
         Progress output is directed to stderr to match the convention that
         progress bars are transient UI feedback, not command output. This
-        mirrors the convention that progress bars are transient UI feedback and prevents progress bar rendering
+        mirrors tqdm's default behavior and prevents progress bar rendering
         from interfering with stdout-based assertions in tests or piped
         command output.
 

src/documents/management/commands/document_archiver.py

@@ -17,7 +17,6 @@ class Command(PaperlessCommand):
         "modified) after their initial import."
     )
 
-    supports_progress_bar = True
     supports_multiprocessing = True
 
     def add_arguments(self, parser):

src/documents/management/commands/document_exporter.py

@@ -3,10 +3,12 @@ import json
 import os
 import shutil
 import tempfile
+from itertools import chain
 from itertools import islice
 from pathlib import Path
 from typing import TYPE_CHECKING
 
+import tqdm
 from allauth.mfa.models import Authenticator
 from allauth.socialaccount.models import SocialAccount
 from allauth.socialaccount.models import SocialApp
@@ -17,6 +19,7 @@ from django.contrib.auth.models import Permission
 from django.contrib.auth.models import User
 from django.contrib.contenttypes.models import ContentType
 from django.core import serializers
+from django.core.management.base import BaseCommand
 from django.core.management.base import CommandError
 from django.core.serializers.json import DjangoJSONEncoder
 from django.db import transaction
@@ -35,7 +38,6 @@ if settings.AUDIT_LOG_ENABLED:
 
 from documents.file_handling import delete_empty_directories
 from documents.file_handling import generate_filename
-from documents.management.commands.base import PaperlessCommand
 from documents.management.commands.mixins import CryptMixin
 from documents.models import Correspondent
 from documents.models import CustomField
@@ -56,6 +58,7 @@ from documents.models import WorkflowTrigger
 from documents.settings import EXPORTER_ARCHIVE_NAME
 from documents.settings import EXPORTER_FILE_NAME
 from documents.settings import EXPORTER_THUMBNAIL_NAME
+from documents.utils import compute_checksum
 from documents.utils import copy_file_with_basic_stats
 from paperless import version
 from paperless.models import ApplicationConfiguration
@@ -79,99 +82,14 @@ def serialize_queryset_batched(
         yield serializers.serialize("python", chunk)
 
 
-class StreamingManifestWriter:
-    """Incrementally writes a JSON array to a file, one record at a time.
-
-    Writes to <target>.tmp first; on close(), optionally BLAKE2b-compares
-    with the existing file (--compare-json) and renames or discards accordingly.
-    On exception, discard() deletes the tmp file and leaves the original intact.
-    """
-
-    def __init__(
-        self,
-        path: Path,
-        *,
-        compare_json: bool = False,
-        files_in_export_dir: "set[Path] | None" = None,
-    ) -> None:
-        self._path = path.resolve()
-        self._tmp_path = self._path.with_suffix(self._path.suffix + ".tmp")
-        self._compare_json = compare_json
-        self._files_in_export_dir: set[Path] = (
-            files_in_export_dir if files_in_export_dir is not None else set()
-        )
-        self._file = None
-        self._first = True
-
-    def open(self) -> None:
-        self._path.parent.mkdir(parents=True, exist_ok=True)
-        self._file = self._tmp_path.open("w", encoding="utf-8")
-        self._file.write("[")
-        self._first = True
-
-    def write_record(self, record: dict) -> None:
-        if not self._first:
-            self._file.write(",\n")
-        else:
-            self._first = False
-        self._file.write(
-            json.dumps(record, cls=DjangoJSONEncoder, indent=2, ensure_ascii=False),
-        )
-
-    def write_batch(self, records: list[dict]) -> None:
-        for record in records:
-            self.write_record(record)
-
-    def close(self) -> None:
-        if self._file is None:
-            return
-        self._file.write("\n]")
-        self._file.close()
-        self._file = None
-        self._finalize()
-
-    def discard(self) -> None:
-        if self._file is not None:
-            self._file.close()
-            self._file = None
-        if self._tmp_path.exists():
-            self._tmp_path.unlink()
-
-    def _finalize(self) -> None:
-        """Compare with existing file (if --compare-json) then rename or discard tmp."""
-        if self._path in self._files_in_export_dir:
-            self._files_in_export_dir.remove(self._path)
-            if self._compare_json:
-                existing_hash = hashlib.blake2b(self._path.read_bytes()).hexdigest()
-                new_hash = hashlib.blake2b(self._tmp_path.read_bytes()).hexdigest()
-                if existing_hash == new_hash:
-                    self._tmp_path.unlink()
-                    return
-        self._tmp_path.rename(self._path)
-
-    def __enter__(self) -> "StreamingManifestWriter":
-        self.open()
-        return self
-
-    def __exit__(self, exc_type, exc_val, exc_tb) -> None:
-        if exc_type is not None:
-            self.discard()
-        else:
-            self.close()
-
-
-class Command(CryptMixin, PaperlessCommand):
+class Command(CryptMixin, BaseCommand):
     help = (
         "Decrypt and rename all files in our collection into a given target "
         "directory.  And include a manifest file containing document data for "
         "easy import."
     )
 
-    supports_progress_bar = True
-    supports_multiprocessing = False
-
     def add_arguments(self, parser) -> None:
-        super().add_arguments(parser)
         parser.add_argument("target")
 
         parser.add_argument(
@@ -278,6 +196,13 @@ class Command(CryptMixin, PaperlessCommand):
             help="If set, only the database will be imported, not files",
         )
 
+        parser.add_argument(
+            "--no-progress-bar",
+            default=False,
+            action="store_true",
+            help="If set, the progress bar will not be shown",
+        )
+
         parser.add_argument(
             "--passphrase",
             help="If provided, is used to encrypt sensitive data in the export",
@@ -306,6 +231,7 @@ class Command(CryptMixin, PaperlessCommand):
         self.no_thumbnail: bool = options["no_thumbnail"]
         self.zip_export: bool = options["zip"]
         self.data_only: bool = options["data_only"]
+        self.no_progress_bar: bool = options["no_progress_bar"]
         self.passphrase: str | None = options.get("passphrase")
         self.batch_size: int = options["batch_size"]
 
@@ -397,85 +323,95 @@ class Command(CryptMixin, PaperlessCommand):
         if settings.AUDIT_LOG_ENABLED:
             manifest_key_to_object_query["log_entries"] = LogEntry.objects.all()
 
-        # Crypto setup before streaming begins
-        if self.passphrase:
-            self.setup_crypto(passphrase=self.passphrase)
-        elif MailAccount.objects.count() > 0 or SocialToken.objects.count() > 0:
-            self.stdout.write(
-                self.style.NOTICE(
-                    "No passphrase was given, sensitive fields will be in plaintext",
-                ),
-            )
+        with transaction.atomic():
+            manifest_dict = {}
 
-        document_manifest: list[dict] = []
-        manifest_path = (self.target / "manifest.json").resolve()
-
-        with StreamingManifestWriter(
-            manifest_path,
-            compare_json=self.compare_json,
-            files_in_export_dir=self.files_in_export_dir,
-        ) as writer:
-            with transaction.atomic():
-                for key, qs in manifest_key_to_object_query.items():
-                    if key == "documents":
-                        # Accumulate for file-copy loop; written to manifest after
-                        for batch in serialize_queryset_batched(
-                            qs,
+            # Build an overall manifest
+            for key, object_query in manifest_key_to_object_query.items():
+                manifest_dict[key] = list(
+                    chain.from_iterable(
+                        serialize_queryset_batched(
+                            object_query,
                             batch_size=self.batch_size,
-                        ):
-                            for record in batch:
-                                self._encrypt_record_inline(record)
-                            document_manifest.extend(batch)
-                    elif self.split_manifest and key in (
-                        "notes",
-                        "custom_field_instances",
-                    ):
-                        # Written per-document in _write_split_manifest
-                        pass
-                    else:
-                        for batch in serialize_queryset_batched(
-                            qs,
-                            batch_size=self.batch_size,
-                        ):
-                            for record in batch:
-                                self._encrypt_record_inline(record)
-                            writer.write_batch(batch)
-
-            document_map: dict[int, Document] = {
-                d.pk: d for d in Document.objects.order_by("id")
-            }
-
-            # 3. Export files from each document
-            for index, document_dict in enumerate(
-                self.track(
-                    document_manifest,
-                    description="Exporting documents...",
-                    total=len(document_manifest),
-                ),
-            ):
-                document = document_map[document_dict["pk"]]
-
-                # 3.1. generate a unique filename
-                base_name = self.generate_base_name(document)
-
-                # 3.2. write filenames into manifest
-                original_target, thumbnail_target, archive_target = (
-                    self.generate_document_targets(document, base_name, document_dict)
+                        ),
+                    ),
                 )
 
-                # 3.3. write files to target folder
-                if not self.data_only:
-                    self.copy_document_files(
-                        document,
-                        original_target,
-                        thumbnail_target,
-                        archive_target,
-                    )
+            self.encrypt_secret_fields(manifest_dict)
 
-                if self.split_manifest:
-                    self._write_split_manifest(document_dict, document, base_name)
-                else:
-                    writer.write_record(document_dict)
+            # These are treated specially and included in the per-document manifest
+            # if that setting is enabled.  Otherwise, they are just exported to the bulk
+            # manifest
+            document_map: dict[int, Document] = {
+                d.pk: d for d in manifest_key_to_object_query["documents"]
+            }
+            document_manifest = manifest_dict["documents"]
+
+        # 3. Export files from each document
+        for index, document_dict in tqdm.tqdm(
+            enumerate(document_manifest),
+            total=len(document_manifest),
+            disable=self.no_progress_bar,
+        ):
+            document = document_map[document_dict["pk"]]
+
+            # 3.1. generate a unique filename
+            base_name = self.generate_base_name(document)
+
+            # 3.2. write filenames into manifest
+            original_target, thumbnail_target, archive_target = (
+                self.generate_document_targets(document, base_name, document_dict)
+            )
+
+            # 3.3. write files to target folder
+            if not self.data_only:
+                self.copy_document_files(
+                    document,
+                    original_target,
+                    thumbnail_target,
+                    archive_target,
+                )
+
+            if self.split_manifest:
+                manifest_name = base_name.with_name(f"{base_name.stem}-manifest.json")
+                if self.use_folder_prefix:
+                    manifest_name = Path("json") / manifest_name
+                manifest_name = (self.target / manifest_name).resolve()
+                manifest_name.parent.mkdir(parents=True, exist_ok=True)
+                content = [document_manifest[index]]
+                content += list(
+                    filter(
+                        lambda d: d["fields"]["document"] == document_dict["pk"],
+                        manifest_dict["notes"],
+                    ),
+                )
+                content += list(
+                    filter(
+                        lambda d: d["fields"]["document"] == document_dict["pk"],
+                        manifest_dict["custom_field_instances"],
+                    ),
+                )
+
+                self.check_and_write_json(
+                    content,
+                    manifest_name,
+                )
+
+        # These were exported already
+        if self.split_manifest:
+            del manifest_dict["documents"]
+            del manifest_dict["notes"]
+            del manifest_dict["custom_field_instances"]
+
+        # 4.1 write primary manifest to target folder
+        manifest = []
+        for key, item in manifest_dict.items():
+            manifest.extend(item)
+        manifest_path = (self.target / "manifest.json").resolve()
+        self.check_and_write_json(
+            manifest,
+            manifest_path,
+        )
 
         # 4.2 write version information to target folder
         extra_metadata_path = (self.target / "metadata.json").resolve()
@@ -597,42 +533,6 @@ class Command(CryptMixin, PaperlessCommand):
                 archive_target,
             )
 
-    def _encrypt_record_inline(self, record: dict) -> None:
-        """Encrypt sensitive fields in a single record, if passphrase is set."""
-        if not self.passphrase:
-            return
-        fields = self.CRYPT_FIELDS_BY_MODEL.get(record.get("model", ""))
-        if fields:
-            for field in fields:
-                if record["fields"].get(field):
-                    record["fields"][field] = self.encrypt_string(
-                        value=record["fields"][field],
-                    )
-
-    def _write_split_manifest(
-        self,
-        document_dict: dict,
-        document: Document,
-        base_name: Path,
-    ) -> None:
-        """Write per-document manifest file for --split-manifest mode."""
-        content = [document_dict]
-        content.extend(
-            serializers.serialize("python", Note.objects.filter(document=document)),
-        )
-        content.extend(
-            serializers.serialize(
-                "python",
-                CustomFieldInstance.objects.filter(document=document),
-            ),
-        )
-        manifest_name = base_name.with_name(f"{base_name.stem}-manifest.json")
-        if self.use_folder_prefix:
-            manifest_name = Path("json") / manifest_name
-        manifest_name = (self.target / manifest_name).resolve()
-        manifest_name.parent.mkdir(parents=True, exist_ok=True)
-        self.check_and_write_json(content, manifest_name)
-
     def check_and_write_json(
         self,
         content: list[dict] | dict,
@@ -650,14 +550,14 @@ class Command(CryptMixin, PaperlessCommand):
         if target in self.files_in_export_dir:
             self.files_in_export_dir.remove(target)
             if self.compare_json:
-                target_checksum = hashlib.blake2b(target.read_bytes()).hexdigest()
+                target_checksum = compute_checksum(target)
                 src_str = json.dumps(
                     content,
                     cls=DjangoJSONEncoder,
                     indent=2,
                     ensure_ascii=False,
                 )
-                src_checksum = hashlib.blake2b(src_str.encode("utf-8")).hexdigest()
+                src_checksum = hashlib.sha256(src_str.encode("utf-8")).hexdigest()
                 if src_checksum == target_checksum:
                     perform_write = False
 
@@ -693,7 +593,7 @@ class Command(CryptMixin, PaperlessCommand):
             source_stat = source.stat()
             target_stat = target.stat()
             if self.compare_checksums and source_checksum:
-                target_checksum = hashlib.md5(target.read_bytes()).hexdigest()
+                target_checksum = compute_checksum(target)
                 perform_copy = target_checksum != source_checksum
             elif (
                 source_stat.st_mtime != target_stat.st_mtime
@@ -707,3 +607,28 @@ class Command(CryptMixin, PaperlessCommand):
         if perform_copy:
             target.parent.mkdir(parents=True, exist_ok=True)
             copy_file_with_basic_stats(source, target)
+
+    def encrypt_secret_fields(self, manifest: dict) -> None:
+        """
+        Encrypts certain fields in the export.  Currently limited to the mail account password
+        """
+
+        if self.passphrase:
+            self.setup_crypto(passphrase=self.passphrase)
+
+            for crypt_config in self.CRYPT_FIELDS:
+                exporter_key = crypt_config["exporter_key"]
+                crypt_fields = crypt_config["fields"]
+                for manifest_record in manifest[exporter_key]:
+                    for field in crypt_fields:
+                        if manifest_record["fields"][field]:
+                            manifest_record["fields"][field] = self.encrypt_string(
+                                value=manifest_record["fields"][field],
+                            )
+
+        elif MailAccount.objects.count() > 0 or SocialToken.objects.count() > 0:
+            self.stdout.write(
+                self.style.NOTICE(
+                    "No passphrase was given, sensitive fields will be in plaintext",
+                ),
+            )

src/documents/management/commands/document_fuzzy_match.py

@@ -40,7 +40,6 @@ def _process_and_match(work: _WorkPackage) -> _WorkResult:
 class Command(PaperlessCommand):
     help = "Searches for documents where the content almost matches"
 
-    supports_progress_bar = True
     supports_multiprocessing = True
 
     def add_arguments(self, parser):

src/documents/management/commands/document_importer.py

@@ -8,13 +8,14 @@ from pathlib import Path
 from zipfile import ZipFile
 from zipfile import is_zipfile
 
-import ijson
+import tqdm
 from django.conf import settings
 from django.contrib.auth.models import Permission
 from django.contrib.auth.models import User
 from django.contrib.contenttypes.models import ContentType
 from django.core.exceptions import FieldDoesNotExist
 from django.core.management import call_command
+from django.core.management.base import BaseCommand
 from django.core.management.base import CommandError
 from django.core.serializers.base import DeserializationError
 from django.db import IntegrityError
@@ -24,7 +25,6 @@ from django.db.models.signals import post_save
 from filelock import FileLock
 
 from documents.file_handling import create_source_path_directory
-from documents.management.commands.base import PaperlessCommand
 from documents.management.commands.mixins import CryptMixin
 from documents.models import Correspondent
 from documents.models import CustomField
@@ -33,6 +33,7 @@ from documents.models import Document
 from documents.models import DocumentType
 from documents.models import Note
 from documents.models import Tag
+from documents.parsers import run_convert
 from documents.settings import EXPORTER_ARCHIVE_NAME
 from documents.settings import EXPORTER_CRYPTO_SETTINGS_NAME
 from documents.settings import EXPORTER_FILE_NAME
@@ -46,15 +47,6 @@ if settings.AUDIT_LOG_ENABLED:
     from auditlog.registry import auditlog
 
 
-def iter_manifest_records(path: Path) -> Generator[dict, None, None]:
-    """Yield records one at a time from a manifest JSON array via ijson."""
-    try:
-        with path.open("rb") as f:
-            yield from ijson.items(f, "item")
-    except ijson.JSONError as e:
-        raise CommandError(f"Failed to parse manifest file {path}: {e}") from e
-
-
 @contextmanager
 def disable_signal(sig, receiver, sender, *, weak: bool | None = None) -> Generator:
     try:
@@ -65,19 +57,22 @@ def disable_signal(sig, receiver, sender, *, weak: bool | None = None) -> Genera
         sig.connect(receiver=receiver, sender=sender, **kwargs)
 
 
-class Command(CryptMixin, PaperlessCommand):
+class Command(CryptMixin, BaseCommand):
     help = (
         "Using a manifest.json file, load the data from there, and import the "
         "documents it refers to."
     )
 
-    supports_progress_bar = True
-    supports_multiprocessing = False
-
     def add_arguments(self, parser) -> None:
-        super().add_arguments(parser)
         parser.add_argument("source")
 
+        parser.add_argument(
+            "--no-progress-bar",
+            default=False,
+            action="store_true",
+            help="If set, the progress bar will not be shown",
+        )
+
         parser.add_argument(
             "--data-only",
             default=False,
@@ -152,9 +147,14 @@ class Command(CryptMixin, PaperlessCommand):
         Loads manifest data from the various JSON files for parsing and loading the database
         """
         main_manifest_path: Path = self.source / "manifest.json"
+
+        with main_manifest_path.open() as infile:
+            self.manifest = json.load(infile)
         self.manifest_paths.append(main_manifest_path)
 
         for file in Path(self.source).glob("**/*-manifest.json"):
+            with file.open() as infile:
+                self.manifest += json.load(infile)
             self.manifest_paths.append(file)
 
     def load_metadata(self) -> None:
@@ -231,10 +231,12 @@ class Command(CryptMixin, PaperlessCommand):
 
         self.source = Path(options["source"]).resolve()
         self.data_only: bool = options["data_only"]
+        self.no_progress_bar: bool = options["no_progress_bar"]
         self.passphrase: str | None = options.get("passphrase")
         self.version: str | None = None
         self.salt: str | None = None
         self.manifest_paths = []
+        self.manifest = []
 
         # Create a temporary directory for extracting a zip file into it, even if supplied source is no zip file to keep code cleaner.
         with tempfile.TemporaryDirectory() as tmp_dir:
@@ -294,9 +296,6 @@ class Command(CryptMixin, PaperlessCommand):
             else:
                 self.stdout.write(self.style.NOTICE("Data only import completed"))
 
-            for tmp in getattr(self, "_decrypted_tmp_paths", []):
-                tmp.unlink(missing_ok=True)
-
         self.stdout.write("Updating search index...")
         call_command(
             "document_index",
@@ -349,12 +348,11 @@ class Command(CryptMixin, PaperlessCommand):
                     ) from e
 
         self.stdout.write("Checking the manifest")
-        for manifest_path in self.manifest_paths:
-            for record in iter_manifest_records(manifest_path):
-                # Only check if the document files exist if this is not data only
-                # We don't care about documents for a data only import
-                if not self.data_only and record["model"] == "documents.document":
-                    check_document_validity(record)
+        for record in self.manifest:
+            # Only check if the document files exist if this is not data only
+            # We don't care about documents for a data only import
+            if not self.data_only and record["model"] == "documents.document":
+                check_document_validity(record)
 
     def _import_files_from_manifest(self) -> None:
         settings.ORIGINALS_DIR.mkdir(parents=True, exist_ok=True)
@@ -363,31 +361,23 @@ class Command(CryptMixin, PaperlessCommand):
 
         self.stdout.write("Copy files into paperless...")
 
-        document_records = [
-            {
-                "pk": record["pk"],
-                EXPORTER_FILE_NAME: record[EXPORTER_FILE_NAME],
-                EXPORTER_THUMBNAIL_NAME: record.get(EXPORTER_THUMBNAIL_NAME),
-                EXPORTER_ARCHIVE_NAME: record.get(EXPORTER_ARCHIVE_NAME),
-            }
-            for manifest_path in self.manifest_paths
-            for record in iter_manifest_records(manifest_path)
-            if record["model"] == "documents.document"
-        ]
+        manifest_documents = list(
+            filter(lambda r: r["model"] == "documents.document", self.manifest),
+        )
 
-        for record in self.track(document_records, description="Copying files..."):
+        for record in tqdm.tqdm(manifest_documents, disable=self.no_progress_bar):
             document = Document.objects.get(pk=record["pk"])
 
             doc_file = record[EXPORTER_FILE_NAME]
             document_path = self.source / doc_file
 
-            if record[EXPORTER_THUMBNAIL_NAME]:
+            if EXPORTER_THUMBNAIL_NAME in record:
                 thumb_file = record[EXPORTER_THUMBNAIL_NAME]
                 thumbnail_path = (self.source / thumb_file).resolve()
             else:
                 thumbnail_path = None
 
-            if record[EXPORTER_ARCHIVE_NAME]:
+            if EXPORTER_ARCHIVE_NAME in record:
                 archive_file = record[EXPORTER_ARCHIVE_NAME]
                 archive_path = self.source / archive_file
             else:
@@ -402,10 +392,22 @@ class Command(CryptMixin, PaperlessCommand):
                 copy_file_with_basic_stats(document_path, document.source_path)
 
                 if thumbnail_path:
-                    copy_file_with_basic_stats(
-                        thumbnail_path,
-                        document.thumbnail_path,
-                    )
+                    if thumbnail_path.suffix in {".png", ".PNG"}:
+                        run_convert(
+                            density=300,
+                            scale="500x5000>",
+                            alpha="remove",
+                            strip=True,
+                            trim=False,
+                            auto_orient=True,
+                            input_file=f"{thumbnail_path}[0]",
+                            output_file=str(document.thumbnail_path),
+                        )
+                    else:
+                        copy_file_with_basic_stats(
+                            thumbnail_path,
+                            document.thumbnail_path,
+                        )
 
                 if archive_path:
                     create_source_path_directory(document.archive_path)
@@ -416,43 +418,33 @@ class Command(CryptMixin, PaperlessCommand):
 
             document.save()
 
-    def _decrypt_record_if_needed(self, record: dict) -> dict:
-        fields = self.CRYPT_FIELDS_BY_MODEL.get(record.get("model", ""))
-        if fields:
-            for field in fields:
-                if record["fields"].get(field):
-                    record["fields"][field] = self.decrypt_string(
-                        value=record["fields"][field],
-                    )
-        return record
-
     def decrypt_secret_fields(self) -> None:
         """
-        The converse decryption of some fields out of the export before importing to database.
-        Streams records from each manifest path and writes decrypted content to a temp file.
+        The converse decryption of some fields out of the export before importing to database
         """
-        if not self.passphrase:
-            return
-        # Salt has been loaded from metadata.json at this point, so it cannot be None
-        self.setup_crypto(passphrase=self.passphrase, salt=self.salt)
-        self._decrypted_tmp_paths: list[Path] = []
-        new_paths: list[Path] = []
-        for manifest_path in self.manifest_paths:
-            tmp = manifest_path.with_name(manifest_path.stem + ".decrypted.json")
-            with tmp.open("w", encoding="utf-8") as out:
-                out.write("[\n")
-                first = True
-                for record in iter_manifest_records(manifest_path):
-                    if not first:
-                        out.write(",\n")
-                    json.dump(
-                        self._decrypt_record_if_needed(record),
-                        out,
-                        indent=2,
-                        ensure_ascii=False,
-                    )
-                    first = False
-                out.write("\n]\n")
-            self._decrypted_tmp_paths.append(tmp)
-            new_paths.append(tmp)
-        self.manifest_paths = new_paths
+        if self.passphrase:
+            # Salt has been loaded from metadata.json at this point, so it cannot be None
+            self.setup_crypto(passphrase=self.passphrase, salt=self.salt)
+
+            had_at_least_one_record = False
+
+            for crypt_config in self.CRYPT_FIELDS:
+                importer_model: str = crypt_config["model_name"]
+                crypt_fields: str = crypt_config["fields"]
+                for record in filter(
+                    lambda x: x["model"] == importer_model,
+                    self.manifest,
+                ):
+                    had_at_least_one_record = True
+                    for field in crypt_fields:
+                        if record["fields"][field]:
+                            record["fields"][field] = self.decrypt_string(
+                                value=record["fields"][field],
+                            )
+
+            if had_at_least_one_record:
+                # It's annoying, but the DB is loaded from the JSON directly
+                # Maybe could change that in the future?
+                (self.source / "manifest.json").write_text(
+                    json.dumps(self.manifest, indent=2, ensure_ascii=False),
+                )

src/documents/management/commands/document_index.py

@@ -8,9 +8,6 @@ from documents.tasks import index_reindex
 class Command(PaperlessCommand):
     help = "Manages the document index."
 
-    supports_progress_bar = True
-    supports_multiprocessing = False
-
     def add_arguments(self, parser):
         super().add_arguments(parser)
         parser.add_argument("command", choices=["reindex", "optimize"])

src/documents/management/commands/document_llmindex.py

@@ -7,9 +7,6 @@ from documents.tasks import llmindex_index
 class Command(PaperlessCommand):
     help = "Manages the LLM-based vector index for Paperless."
 
-    supports_progress_bar = True
-    supports_multiprocessing = False
-
     def add_arguments(self, parser: Any) -> None:
         super().add_arguments(parser)
         parser.add_argument("command", choices=["rebuild", "update"])

src/documents/management/commands/document_renamer.py

@@ -7,9 +7,6 @@ from documents.models import Document
 class Command(PaperlessCommand):
     help = "Rename all documents"
 
-    supports_progress_bar = True
-    supports_multiprocessing = False
-
     def handle(self, *args, **options):
         for document in self.track(Document.objects.all(), description="Renaming..."):
             post_save.send(Document, instance=document, created=False)

src/documents/management/commands/document_retagger.py

@@ -180,9 +180,6 @@ class Command(PaperlessCommand):
         "modified) after their initial import."
     )
 
-    supports_progress_bar = True
-    supports_multiprocessing = False
-
     def add_arguments(self, parser) -> None:
         super().add_arguments(parser)
         parser.add_argument("-c", "--correspondent", default=False, action="store_true")

src/documents/management/commands/document_sanity_checker.py

@@ -24,9 +24,6 @@ _LEVEL_STYLE: dict[int, tuple[str, str]] = {
 class Command(PaperlessCommand):
     help = "This command checks your document archive for issues."
 
-    supports_progress_bar = True
-    supports_multiprocessing = False
-
     def _render_results(self, messages: SanityCheckMessages) -> None:
         """Render sanity check results as a Rich table."""
 

src/documents/management/commands/document_thumbnails.py

@@ -36,7 +36,6 @@ def _process_document(doc_id: int) -> None:
 class Command(PaperlessCommand):
     help = "This will regenerate the thumbnails for all documents."
 
-    supports_progress_bar = True
     supports_multiprocessing = True
 
     def add_arguments(self, parser) -> None:

src/documents/management/commands/loaddata_stdin.py

@@ -0,0 +1,22 @@
+import sys
+
+from django.core.management.commands.loaddata import Command as LoadDataCommand
+
+
+# This class is used to migrate data between databases
+# That's difficult to test
+class Command(LoadDataCommand):  # pragma: no cover
+    """
+    Allow the loading of data from standard in.  Sourced originally from:
+    https://gist.github.com/bmispelon/ad5a2c333443b3a1d051 (MIT licensed)
+    """
+
+    def parse_name(self, fixture_name):
+        self.compression_formats["stdin"] = (lambda x, y: sys.stdin, None)
+        if fixture_name == "-":
+            return "-", "json", "stdin"
+
+    def find_fixtures(self, fixture_label):
+        if fixture_label == "-":
+            return [("-", None, "-")]
+        return super().find_fixtures(fixture_label)

src/documents/management/commands/mixins.py

@@ -1,5 +1,6 @@
 import base64
 import os
+from argparse import ArgumentParser
 from typing import TypedDict
 
 from cryptography.fernet import Fernet
@@ -20,6 +21,25 @@ class CryptFields(TypedDict):
     fields: list[str]
 
 
+class ProgressBarMixin:
+    """
+    Many commands use a progress bar, which can be disabled
+    via this class
+    """
+
+    def add_argument_progress_bar_mixin(self, parser: ArgumentParser) -> None:
+        parser.add_argument(
+            "--no-progress-bar",
+            default=False,
+            action="store_true",
+            help="If set, the progress bar will not be shown",
+        )
+
+    def handle_progress_bar_mixin(self, *args, **options) -> None:
+        self.no_progress_bar = options["no_progress_bar"]
+        self.use_progress_bar = not self.no_progress_bar
+
+
 class CryptMixin:
     """
     Fully based on:
@@ -51,7 +71,7 @@ class CryptMixin:
     key_size = 32
     kdf_algorithm = "pbkdf2_sha256"
 
-    CRYPT_FIELDS: list[CryptFields] = [
+    CRYPT_FIELDS: CryptFields = [
         {
             "exporter_key": "mail_accounts",
             "model_name": "paperless_mail.mailaccount",
@@ -69,10 +89,6 @@ class CryptMixin:
             ],
         },
     ]
-    # O(1) lookup for per-record encryption; derived from CRYPT_FIELDS at class definition time
-    CRYPT_FIELDS_BY_MODEL: dict[str, list[str]] = {
-        cfg["model_name"]: cfg["fields"] for cfg in CRYPT_FIELDS
-    }
 
     def get_crypt_params(self) -> dict[str, dict[str, str | int]]:
         return {

src/documents/management/commands/prune_audit_logs.py

@@ -9,9 +9,6 @@ class Command(PaperlessCommand):
 
     help = "Prunes the audit logs of objects that no longer exist."
 
-    supports_progress_bar = True
-    supports_multiprocessing = False
-
     def handle(self, *args, **options):
         with transaction.atomic():
             for log_entry in self.track(

src/documents/migrations/0003_workflowaction_order.py

@@ -0,0 +1,18 @@
+# Generated by Django 5.2.9 on 2026-01-20 20:06
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0002_squashed"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="workflowaction",
+            name="order",
+            field=models.PositiveIntegerField(default=0, verbose_name="order"),
+        ),
+    ]

src/documents/migrations/0004_remove_document_storage_type.py

@@ -5,7 +5,7 @@ from django.db import migrations
 
 class Migration(migrations.Migration):
     dependencies = [
-        ("documents", "0002_squashed"),
+        ("documents", "0003_workflowaction_order"),
     ]
 
     operations = [

src/documents/migrations/0005_workflowtrigger_filter_has_any_correspondents_and_more.py

@@ -6,7 +6,7 @@ from django.db import models
 
 class Migration(migrations.Migration):
     dependencies = [
-        ("documents", "0003_remove_document_storage_type"),
+        ("documents", "0004_remove_document_storage_type"),
     ]
 
     operations = [

src/documents/migrations/0006_alter_document_checksum_unique.py

@@ -6,7 +6,7 @@ from django.db import models
 
 class Migration(migrations.Migration):
     dependencies = [
-        ("documents", "0004_workflowtrigger_filter_has_any_correspondents_and_more"),
+        ("documents", "0005_workflowtrigger_filter_has_any_correspondents_and_more"),
     ]
 
     operations = [

src/documents/migrations/0007_document_content_length.py

@@ -7,7 +7,7 @@ from django.db import models
 
 class Migration(migrations.Migration):
     dependencies = [
-        ("documents", "0005_alter_document_checksum_unique"),
+        ("documents", "0006_alter_document_checksum_unique"),
     ]
 
     operations = [

src/documents/migrations/0008_sharelinkbundle.py

@@ -46,7 +46,7 @@ def revoke_share_link_bundle_permissions(apps, schema_editor):
 class Migration(migrations.Migration):
     dependencies = [
         migrations.swappable_dependency(settings.AUTH_USER_MODEL),
-        ("documents", "0006_document_content_length"),
+        ("documents", "0007_document_content_length"),
     ]
 
     operations = [

src/documents/migrations/0009_workflowaction_passwords_alter_workflowaction_type.py

@@ -6,7 +6,7 @@ from django.db import models
 
 class Migration(migrations.Migration):
     dependencies = [
-        ("documents", "0007_sharelinkbundle"),
+        ("documents", "0008_sharelinkbundle"),
     ]
 
     operations = [

src/documents/migrations/0010_alter_document_content_length.py

@@ -7,7 +7,7 @@ from django.db import models
 
 class Migration(migrations.Migration):
     dependencies = [
-        ("documents", "0008_workflowaction_passwords_alter_workflowaction_type"),
+        ("documents", "0009_workflowaction_passwords_alter_workflowaction_type"),
     ]
 
     operations = [

src/documents/migrations/0011_optimize_integer_field_sizes.py

@@ -7,7 +7,7 @@ from django.db import models
 
 class Migration(migrations.Migration):
     dependencies = [
-        ("documents", "0009_alter_document_content_length"),
+        ("documents", "0010_alter_document_content_length"),
     ]
 
     operations = [

src/documents/migrations/0012_alter_workflowaction_type.py

@@ -6,7 +6,7 @@ from django.db import models
 
 class Migration(migrations.Migration):
     dependencies = [
-        ("documents", "0010_optimize_integer_field_sizes"),
+        ("documents", "0011_optimize_integer_field_sizes"),
     ]
 
     operations = [

src/documents/migrations/0013_document_root_document.py

@@ -7,7 +7,7 @@ from django.db import models
 
 class Migration(migrations.Migration):
     dependencies = [
-        ("documents", "0011_alter_workflowaction_type"),
+        ("documents", "0012_alter_workflowaction_type"),
     ]
 
     operations = [

src/documents/migrations/0014_alter_paperlesstask_task_name.py

@@ -6,7 +6,7 @@ from django.db import models
 
 class Migration(migrations.Migration):
     dependencies = [
-        ("documents", "0012_document_root_document"),
+        ("documents", "0013_document_root_document"),
     ]
 
     operations = [

src/documents/migrations/0015_savedview_visibility_to_ui_settings.py

@@ -124,7 +124,7 @@ def _restore_visibility_fields(apps, schema_editor):
 
 class Migration(migrations.Migration):
     dependencies = [
-        ("documents", "0013_alter_paperlesstask_task_name"),
+        ("documents", "0014_alter_paperlesstask_task_name"),
     ]
 
     operations = [

src/documents/migrations/0016_document_version_index_and_more.py

@@ -7,7 +7,7 @@ from django.db import models
 
 class Migration(migrations.Migration):
     dependencies = [
-        ("documents", "0014_savedview_visibility_to_ui_settings"),
+        ("documents", "0015_savedview_visibility_to_ui_settings"),
         migrations.swappable_dependency(settings.AUTH_USER_MODEL),
     ]
 

src/documents/migrations/0017_sha256_checksums.py

@@ -0,0 +1,130 @@
+import hashlib
+import logging
+from pathlib import Path
+
+from django.conf import settings
+from django.db import migrations
+from django.db import models
+
+logger = logging.getLogger("paperless.migrations")
+
+_CHUNK_SIZE = 65536  # 64 KiB — avoids loading entire files into memory
+_BATCH_SIZE = 500  # documents per bulk_update call
+_PROGRESS_INTERVAL = 500  # log a progress line every N documents
+
+
+def _sha256(path: Path) -> str:
+    h = hashlib.sha256()
+    with path.open("rb") as fh:
+        while chunk := fh.read(_CHUNK_SIZE):
+            h.update(chunk)
+    return h.hexdigest()
+
+
+def recompute_checksums(apps, schema_editor):
+    """Recompute all document checksums from MD5 to SHA256."""
+    Document = apps.get_model("documents", "Document")
+
+    total = Document.objects.count()
+    if total == 0:
+        return
+
+    logger.info("Recomputing SHA-256 checksums for %d document(s)...", total)
+
+    batch: list = []
+    processed = 0
+
+    for doc in Document.objects.only(
+        "pk",
+        "filename",
+        "checksum",
+        "archive_filename",
+        "archive_checksum",
+    ).iterator(chunk_size=_BATCH_SIZE):
+        updated_fields: list[str] = []
+
+        # Reconstruct source path the same way Document.source_path does
+        fname = str(doc.filename) if doc.filename else f"{doc.pk:07}.pdf"
+        source_path = (settings.ORIGINALS_DIR / Path(fname)).resolve()
+
+        if source_path.exists():
+            doc.checksum = _sha256(source_path)
+            updated_fields.append("checksum")
+        else:
+            logger.warning(
+                "Document %s: original file %s not found, checksum not updated.",
+                doc.pk,
+                source_path,
+            )
+
+        # Mirror Document.has_archive_version: archive_filename is not None
+        if doc.archive_filename is not None:
+            archive_path = (
+                settings.ARCHIVE_DIR / Path(str(doc.archive_filename))
+            ).resolve()
+            if archive_path.exists():
+                doc.archive_checksum = _sha256(archive_path)
+                updated_fields.append("archive_checksum")
+            else:
+                logger.warning(
+                    "Document %s: archive file %s not found, checksum not updated.",
+                    doc.pk,
+                    archive_path,
+                )
+
+        if updated_fields:
+            batch.append(doc)
+
+        processed += 1
+
+        if len(batch) >= _BATCH_SIZE:
+            Document.objects.bulk_update(batch, ["checksum", "archive_checksum"])
+            batch.clear()
+
+        if processed % _PROGRESS_INTERVAL == 0:
+            logger.info(
+                "SHA-256 checksum progress: %d/%d (%d%%)",
+                processed,
+                total,
+                processed * 100 // total,
+            )
+
+    if batch:
+        Document.objects.bulk_update(batch, ["checksum", "archive_checksum"])
+
+    logger.info(
+        "SHA-256 checksum recomputation complete: %d document(s) processed.",
+        total,
+    )
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0016_document_version_index_and_more"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="document",
+            name="checksum",
+            field=models.CharField(
+                editable=False,
+                help_text="The checksum of the original document.",
+                max_length=64,
+                verbose_name="checksum",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="archive_checksum",
+            field=models.CharField(
+                blank=True,
+                editable=False,
+                help_text="The checksum of the archived document.",
+                max_length=64,
+                null=True,
+                verbose_name="archive checksum",
+            ),
+        ),
+        migrations.RunPython(recompute_checksums, migrations.RunPython.noop),
+    ]

src/documents/models.py

@@ -216,14 +216,14 @@ class Document(SoftDeleteModel, ModelWithOwner):  # type: ignore[django-manager-
 
     checksum = models.CharField(
         _("checksum"),
-        max_length=32,
+        max_length=64,
         editable=False,
         help_text=_("The checksum of the original document."),
     )
 
     archive_checksum = models.CharField(
         _("archive checksum"),
-        max_length=32,
+        max_length=64,
         editable=False,
         blank=True,
         null=True,

src/documents/sanity_checker.py

@@ -11,7 +11,6 @@ is an identity function that adds no overhead.
 
 from __future__ import annotations
 
-import hashlib
 import logging
 import uuid
 from collections import defaultdict
@@ -30,6 +29,7 @@ from django.utils import timezone
 
 from documents.models import Document
 from documents.models import PaperlessTask
+from documents.utils import compute_checksum
 from paperless.config import GeneralConfig
 
 logger = logging.getLogger("paperless.sanity_checker")
@@ -218,7 +218,7 @@ def _check_original(
 
     present_files.discard(source_path)
     try:
-        checksum = hashlib.md5(source_path.read_bytes()).hexdigest()
+        checksum = compute_checksum(source_path)
     except OSError as e:
         messages.error(doc.pk, f"Cannot read original file of document: {e}")
     else:
@@ -255,7 +255,7 @@ def _check_archive(
 
         present_files.discard(archive_path)
         try:
-            checksum = hashlib.md5(archive_path.read_bytes()).hexdigest()
+            checksum = compute_checksum(archive_path)
         except OSError as e:
             messages.error(
                 doc.pk,

src/documents/serialisers.py

@@ -703,6 +703,15 @@ class StoragePathField(serializers.PrimaryKeyRelatedField):
 
 
 class CustomFieldSerializer(serializers.ModelSerializer):
+    def __init__(self, *args, **kwargs):
+        context = kwargs.get("context")
+        self.api_version = int(
+            context.get("request").version
+            if context and context.get("request")
+            else settings.REST_FRAMEWORK["DEFAULT_VERSION"],
+        )
+        super().__init__(*args, **kwargs)
+
     data_type = serializers.ChoiceField(
         choices=CustomField.FieldDataType,
         read_only=False,
@@ -782,6 +791,38 @@ class CustomFieldSerializer(serializers.ModelSerializer):
             )
         return super().validate(attrs)
 
+    def to_internal_value(self, data):
+        ret = super().to_internal_value(data)
+
+        if (
+            self.api_version < 7
+            and ret.get("data_type", "") == CustomField.FieldDataType.SELECT
+            and isinstance(ret.get("extra_data", {}).get("select_options"), list)
+        ):
+            ret["extra_data"]["select_options"] = [
+                {
+                    "label": option,
+                    "id": get_random_string(length=16),
+                }
+                for option in ret["extra_data"]["select_options"]
+            ]
+
+        return ret
+
+    def to_representation(self, instance):
+        ret = super().to_representation(instance)
+
+        if (
+            self.api_version < 7
+            and instance.data_type == CustomField.FieldDataType.SELECT
+        ):
+            # Convert the select options with ids to a list of strings
+            ret["extra_data"]["select_options"] = [
+                option["label"] for option in ret["extra_data"]["select_options"]
+            ]
+
+        return ret
+
 
 class ReadWriteSerializerMethodField(serializers.SerializerMethodField):
     """
@@ -896,6 +937,50 @@ class CustomFieldInstanceSerializer(serializers.ModelSerializer):
 
         return data
 
+    def get_api_version(self):
+        return int(
+            self.context.get("request").version
+            if self.context.get("request")
+            else settings.REST_FRAMEWORK["DEFAULT_VERSION"],
+        )
+
+    def to_internal_value(self, data):
+        ret = super().to_internal_value(data)
+
+        if (
+            self.get_api_version() < 7
+            and ret.get("field").data_type == CustomField.FieldDataType.SELECT
+            and ret.get("value") is not None
+        ):
+            # Convert the index of the option in the field.extra_data["select_options"]
+            # list to the options unique id
+            ret["value"] = ret.get("field").extra_data["select_options"][ret["value"]][
+                "id"
+            ]
+
+        return ret
+
+    def to_representation(self, instance):
+        ret = super().to_representation(instance)
+
+        if (
+            self.get_api_version() < 7
+            and instance.field.data_type == CustomField.FieldDataType.SELECT
+        ):
+            # return the index of the option in the field.extra_data["select_options"] list
+            ret["value"] = next(
+                (
+                    idx
+                    for idx, option in enumerate(
+                        instance.field.extra_data["select_options"],
+                    )
+                    if option["id"] == instance.value
+                ),
+                None,
+            )
+
+        return ret
+
     class Meta:
         model = CustomFieldInstance
         fields = [
@@ -919,6 +1004,20 @@ class NotesSerializer(serializers.ModelSerializer):
         fields = ["id", "note", "created", "user"]
         ordering = ["-created"]
 
+    def to_representation(self, instance):
+        ret = super().to_representation(instance)
+
+        request = self.context.get("request")
+        api_version = int(
+            request.version if request else settings.REST_FRAMEWORK["DEFAULT_VERSION"],
+        )
+
+        if api_version < 8 and "user" in ret:
+            user_id = ret["user"]["id"]
+            ret["user"] = user_id
+
+        return ret
+
 
 def _get_viewable_duplicates(
     document: Document,
@@ -1073,6 +1172,22 @@ class DocumentSerializer(
             doc["content"] = getattr(instance, "effective_content") or ""
         if self.truncate_content and "content" in self.fields:
             doc["content"] = doc.get("content")[0:550]
+
+        request = self.context.get("request")
+        api_version = int(
+            request.version if request else settings.REST_FRAMEWORK["DEFAULT_VERSION"],
+        )
+
+        if api_version < 9 and "created" in self.fields:
+            # provide created as a datetime for backwards compatibility
+            from django.utils import timezone
+
+            doc["created"] = timezone.make_aware(
+                datetime.combine(
+                    instance.created,
+                    datetime.min.time(),
+                ),
+            ).isoformat()
         return doc
 
     def to_internal_value(self, data):
@@ -1325,124 +1440,6 @@ class SavedViewSerializer(OwnedObjectSerializer):
             "set_permissions",
         ]
 
-    def _get_api_version(self) -> int:
-        request = self.context.get("request")
-        return int(
-            request.version if request else settings.REST_FRAMEWORK["DEFAULT_VERSION"],
-        )
-
-    def _update_legacy_visibility_preferences(
-        self,
-        saved_view_id: int,
-        *,
-        show_on_dashboard: bool | None,
-        show_in_sidebar: bool | None,
-    ) -> UiSettings | None:
-        if show_on_dashboard is None and show_in_sidebar is None:
-            return None
-
-        request = self.context.get("request")
-        user = request.user if request else self.user
-        if user is None:
-            return None
-
-        ui_settings, _ = UiSettings.objects.get_or_create(
-            user=user,
-            defaults={"settings": {}},
-        )
-        current_settings = (
-            ui_settings.settings if isinstance(ui_settings.settings, dict) else {}
-        )
-        current_settings = dict(current_settings)
-
-        saved_views_settings = current_settings.get("saved_views")
-        if isinstance(saved_views_settings, dict):
-            saved_views_settings = dict(saved_views_settings)
-        else:
-            saved_views_settings = {}
-
-        dashboard_ids = {
-            int(raw_id)
-            for raw_id in saved_views_settings.get("dashboard_views_visible_ids", [])
-            if str(raw_id).isdigit()
-        }
-        sidebar_ids = {
-            int(raw_id)
-            for raw_id in saved_views_settings.get("sidebar_views_visible_ids", [])
-            if str(raw_id).isdigit()
-        }
-
-        if show_on_dashboard is not None:
-            if show_on_dashboard:
-                dashboard_ids.add(saved_view_id)
-            else:
-                dashboard_ids.discard(saved_view_id)
-        if show_in_sidebar is not None:
-            if show_in_sidebar:
-                sidebar_ids.add(saved_view_id)
-            else:
-                sidebar_ids.discard(saved_view_id)
-
-        saved_views_settings["dashboard_views_visible_ids"] = sorted(dashboard_ids)
-        saved_views_settings["sidebar_views_visible_ids"] = sorted(sidebar_ids)
-        current_settings["saved_views"] = saved_views_settings
-        ui_settings.settings = current_settings
-        ui_settings.save(update_fields=["settings"])
-        return ui_settings
-
-    def to_representation(self, instance):
-        # TODO: remove this and related backwards compatibility code when API v9 is dropped
-        ret = super().to_representation(instance)
-        request = self.context.get("request")
-        api_version = self._get_api_version()
-
-        if api_version < 10:
-            dashboard_ids = set()
-            sidebar_ids = set()
-            user = request.user if request else None
-            if user is not None and hasattr(user, "ui_settings"):
-                ui_settings = user.ui_settings.settings or None
-                saved_views = None
-                if isinstance(ui_settings, dict):
-                    saved_views = ui_settings.get("saved_views", {})
-                if isinstance(saved_views, dict):
-                    dashboard_ids = set(
-                        saved_views.get("dashboard_views_visible_ids", []),
-                    )
-                    sidebar_ids = set(
-                        saved_views.get("sidebar_views_visible_ids", []),
-                    )
-            ret["show_on_dashboard"] = instance.id in dashboard_ids
-            ret["show_in_sidebar"] = instance.id in sidebar_ids
-
-        return ret
-
-    def to_internal_value(self, data):
-        # TODO: remove this and related backwards compatibility code when API v9 is dropped
-        api_version = self._get_api_version()
-        if api_version >= 10:
-            return super().to_internal_value(data)
-
-        normalized_data = data.copy()
-        legacy_visibility_fields = {}
-        boolean_field = serializers.BooleanField()
-
-        for field_name in ("show_on_dashboard", "show_in_sidebar"):
-            if field_name in normalized_data:
-                try:
-                    legacy_visibility_fields[field_name] = (
-                        boolean_field.to_internal_value(
-                            normalized_data.get(field_name),
-                        )
-                    )
-                except serializers.ValidationError as exc:
-                    raise serializers.ValidationError({field_name: exc.detail})
-                del normalized_data[field_name]
-
-        ret = super().to_internal_value(normalized_data)
-        ret.update(legacy_visibility_fields)
-        return ret
-
     def validate(self, attrs):
         attrs = super().validate(attrs)
         if "display_fields" in attrs and attrs["display_fields"] is not None:
@@ -1462,9 +1459,6 @@ class SavedViewSerializer(OwnedObjectSerializer):
         return attrs
 
     def update(self, instance, validated_data):
-        request = self.context.get("request")
-        show_on_dashboard = validated_data.pop("show_on_dashboard", None)
-        show_in_sidebar = validated_data.pop("show_in_sidebar", None)
         if "filter_rules" in validated_data:
             rules_data = validated_data.pop("filter_rules")
         else:
@@ -1486,19 +1480,9 @@ class SavedViewSerializer(OwnedObjectSerializer):
             SavedViewFilterRule.objects.filter(saved_view=instance).delete()
             for rule_data in rules_data:
                 SavedViewFilterRule.objects.create(saved_view=instance, **rule_data)
-        ui_settings = self._update_legacy_visibility_preferences(
-            instance.id,
-            show_on_dashboard=show_on_dashboard,
-            show_in_sidebar=show_in_sidebar,
-        )
-        if request is not None and ui_settings is not None:
-            request.user.ui_settings = ui_settings
         return instance
 
     def create(self, validated_data):
-        request = self.context.get("request")
-        show_on_dashboard = validated_data.pop("show_on_dashboard", None)
-        show_in_sidebar = validated_data.pop("show_in_sidebar", None)
         rules_data = validated_data.pop("filter_rules")
         if "user" in validated_data:
             # backwards compatibility
@@ -1506,13 +1490,6 @@ class SavedViewSerializer(OwnedObjectSerializer):
         saved_view = super().create(validated_data)
         for rule_data in rules_data:
             SavedViewFilterRule.objects.create(saved_view=saved_view, **rule_data)
-        ui_settings = self._update_legacy_visibility_preferences(
-            saved_view.id,
-            show_on_dashboard=show_on_dashboard,
-            show_in_sidebar=show_in_sidebar,
-        )
-        if request is not None and ui_settings is not None:
-            request.user.ui_settings = ui_settings
         return saved_view
 
 
@@ -1540,124 +1517,11 @@ class DocumentListSerializer(serializers.Serializer):
         return documents
 
 
-class SourceModeValidationMixin:
-    def validate_source_mode(self, source_mode: str) -> str:
-        if source_mode not in bulk_edit.SourceModeChoices.__dict__.values():
-            raise serializers.ValidationError("Invalid source_mode")
-        return source_mode
-
-
-class RotateDocumentsSerializer(DocumentListSerializer, SourceModeValidationMixin):
-    degrees = serializers.IntegerField(required=True)
-    source_mode = serializers.CharField(
-        required=False,
-        default=bulk_edit.SourceModeChoices.LATEST_VERSION,
-    )
-
-
-class MergeDocumentsSerializer(DocumentListSerializer, SourceModeValidationMixin):
-    metadata_document_id = serializers.IntegerField(
-        required=False,
-        allow_null=True,
-    )
-    delete_originals = serializers.BooleanField(required=False, default=False)
-    archive_fallback = serializers.BooleanField(required=False, default=False)
-    source_mode = serializers.CharField(
-        required=False,
-        default=bulk_edit.SourceModeChoices.LATEST_VERSION,
-    )
-
-
-class EditPdfDocumentsSerializer(DocumentListSerializer, SourceModeValidationMixin):
-    operations = serializers.ListField(required=True)
-    delete_original = serializers.BooleanField(required=False, default=False)
-    update_document = serializers.BooleanField(required=False, default=False)
-    include_metadata = serializers.BooleanField(required=False, default=True)
-    source_mode = serializers.CharField(
-        required=False,
-        default=bulk_edit.SourceModeChoices.LATEST_VERSION,
-    )
-
-    def validate(self, attrs):
-        documents = attrs["documents"]
-        if len(documents) > 1:
-            raise serializers.ValidationError(
-                "Edit PDF method only supports one document",
-            )
-
-        operations = attrs["operations"]
-        if not isinstance(operations, list):
-            raise serializers.ValidationError("operations must be a list")
-
-        for op in operations:
-            if not isinstance(op, dict):
-                raise serializers.ValidationError("invalid operation entry")
-            if "page" not in op or not isinstance(op["page"], int):
-                raise serializers.ValidationError("page must be an integer")
-            if "rotate" in op and not isinstance(op["rotate"], int):
-                raise serializers.ValidationError("rotate must be an integer")
-            if "doc" in op and not isinstance(op["doc"], int):
-                raise serializers.ValidationError("doc must be an integer")
-
-        if attrs["update_document"]:
-            max_idx = max(op.get("doc", 0) for op in operations)
-            if max_idx > 0:
-                raise serializers.ValidationError(
-                    "update_document only allowed with a single output document",
-                )
-
-        doc = Document.objects.get(id=documents[0])
-        if doc.page_count:
-            for op in operations:
-                if op["page"] < 1 or op["page"] > doc.page_count:
-                    raise serializers.ValidationError(
-                        f"Page {op['page']} is out of bounds for document with {doc.page_count} pages.",
-                    )
-        return attrs
-
-
-class RemovePasswordDocumentsSerializer(
-    DocumentListSerializer,
-    SourceModeValidationMixin,
-):
-    password = serializers.CharField(required=True)
-    update_document = serializers.BooleanField(required=False, default=False)
-    delete_original = serializers.BooleanField(required=False, default=False)
-    include_metadata = serializers.BooleanField(required=False, default=True)
-    source_mode = serializers.CharField(
-        required=False,
-        default=bulk_edit.SourceModeChoices.LATEST_VERSION,
-    )
-
-
-class DeleteDocumentsSerializer(DocumentListSerializer):
-    pass
-
-
-class ReprocessDocumentsSerializer(DocumentListSerializer):
-    pass
-
-
 class BulkEditSerializer(
     SerializerWithPerms,
     DocumentListSerializer,
     SetPermissionsMixin,
-    SourceModeValidationMixin,
 ):
-    # TODO: remove this and related backwards compatibility code when API v9 is dropped
-    # split, delete_pages can be removed entirely
-    MOVED_DOCUMENT_ACTION_ENDPOINTS = {
-        "delete": "/api/documents/delete/",
-        "reprocess": "/api/documents/reprocess/",
-        "rotate": "/api/documents/rotate/",
-        "merge": "/api/documents/merge/",
-        "edit_pdf": "/api/documents/edit_pdf/",
-        "remove_password": "/api/documents/remove_password/",
-        "split": "/api/documents/edit_pdf/",
-        "delete_pages": "/api/documents/edit_pdf/",
-    }
-    LEGACY_DOCUMENT_ACTION_METHODS = tuple(MOVED_DOCUMENT_ACTION_ENDPOINTS.keys())
-
     method = serializers.ChoiceField(
         choices=[
             "set_correspondent",
@@ -1667,8 +1531,15 @@ class BulkEditSerializer(
             "remove_tag",
             "modify_tags",
             "modify_custom_fields",
+            "delete",
+            "reprocess",
             "set_permissions",
-            *LEGACY_DOCUMENT_ACTION_METHODS,
+            "rotate",
+            "merge",
+            "split",
+            "delete_pages",
+            "edit_pdf",
+            "remove_password",
         ],
         label="Method",
         write_only=True,
@@ -1746,7 +1617,8 @@ class BulkEditSerializer(
             return bulk_edit.edit_pdf
         elif method == "remove_password":
             return bulk_edit.remove_password
-        else:
+        else:  # pragma: no cover
+            # This will never happen as it is handled by the ChoiceField
             raise serializers.ValidationError("Unsupported method.")
 
     def _validate_parameters_tags(self, parameters) -> None:
@@ -1851,13 +1723,6 @@ class BulkEditSerializer(
         except ValueError:
             raise serializers.ValidationError("invalid rotation degrees")
 
-    def _validate_source_mode(self, parameters) -> None:
-        source_mode = parameters.get(
-            "source_mode",
-            bulk_edit.SourceModeChoices.LATEST_VERSION,
-        )
-        parameters["source_mode"] = self.validate_source_mode(source_mode)
-
     def _validate_parameters_split(self, parameters) -> None:
         if "pages" not in parameters:
             raise serializers.ValidationError("pages not specified")
@@ -1958,9 +1823,6 @@ class BulkEditSerializer(
         method = attrs["method"]
         parameters = attrs["parameters"]
 
-        if "source_mode" in parameters:
-            self._validate_source_mode(parameters)
-
         if method == bulk_edit.set_correspondent:
             self._validate_parameters_correspondent(parameters)
         elif method == bulk_edit.set_document_type:

src/documents/tasks.py

@@ -1,5 +1,4 @@
 import datetime
-import hashlib
 import logging
 import shutil
 import uuid
@@ -63,6 +62,7 @@ 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 compute_checksum
 from documents.workflows.utils import get_workflows_for_trigger
 from paperless.config import AIConfig
 from paperless_ai.indexing import llm_index_add_or_update_document
@@ -323,8 +323,7 @@ def update_document_content_maybe_archive_file(document_id) -> None:
         with transaction.atomic():
             oldDocument = Document.objects.get(pk=document.pk)
             if parser.get_archive_path():
-                with Path(parser.get_archive_path()).open("rb") as f:
-                    checksum = hashlib.md5(f.read()).hexdigest()
+                checksum = compute_checksum(Path(parser.get_archive_path()))
                 # I'm going to save first so that in case the file move
                 # fails, the database is rolled back.
                 # We also don't use save() since that triggers the filehandling

src/documents/tests/conftest.py

@@ -82,8 +82,8 @@ def sample_doc(
 
     return DocumentFactory(
         title="test",
-        checksum="42995833e01aea9b3edee44bbfdd7ce1",
-        archive_checksum="62acb0bcbfbcaa62ca6ad3668e4e404b",
+        checksum="1093cf6e32adbd16b06969df09215d42c4a3a8938cc18b39455953f08d1ff2ab",
+        archive_checksum="706124ecde3c31616992fa979caed17a726b1c9ccdba70e82a4ff796cea97ccf",
         content="test content",
         pk=1,
         filename="0000001.pdf",

src/documents/tests/factories.py

@@ -60,7 +60,7 @@ class DocumentFactory(DjangoModelFactory):
         model = Document
 
     title = factory.Faker("sentence", nb_words=4)
-    checksum = factory.Faker("md5")
+    checksum = factory.Faker("sha256")
     content = factory.Faker("paragraph")
     correspondent = None
     document_type = None

src/documents/tests/test_api_bulk_edit.py

@@ -422,34 +422,6 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(args[0], [self.doc1.id])
         self.assertEqual(len(kwargs), 0)
 
-    @mock.patch("documents.views.bulk_edit.delete")
-    def test_delete_documents_endpoint(self, m) -> None:
-        self.setup_mock(m, "delete")
-        response = self.client.post(
-            "/api/documents/delete/",
-            json.dumps({"documents": [self.doc1.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.doc1.id])
-        self.assertEqual(len(kwargs), 0)
-
-    @mock.patch("documents.views.bulk_edit.reprocess")
-    def test_reprocess_documents_endpoint(self, m) -> None:
-        self.setup_mock(m, "reprocess")
-        response = self.client.post(
-            "/api/documents/reprocess/",
-            json.dumps({"documents": [self.doc1.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.doc1.id])
-        self.assertEqual(len(kwargs), 0)
-
     @mock.patch("documents.serialisers.bulk_edit.set_storage_path")
     def test_api_set_storage_path(self, m) -> None:
         """
@@ -905,7 +877,7 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(kwargs["merge"], True)
 
     @mock.patch("documents.serialisers.bulk_edit.set_storage_path")
-    @mock.patch("documents.views.bulk_edit.merge")
+    @mock.patch("documents.serialisers.bulk_edit.merge")
     def test_insufficient_global_perms(self, mock_merge, mock_set_storage) -> None:
         """
         GIVEN:
@@ -940,11 +912,12 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         mock_set_storage.assert_not_called()
 
         response = self.client.post(
-            "/api/documents/merge/",
+            "/api/documents/bulk_edit/",
             json.dumps(
                 {
                     "documents": [self.doc1.id],
-                    "metadata_document_id": self.doc1.id,
+                    "method": "merge",
+                    "parameters": {"metadata_document_id": self.doc1.id},
                 },
             ),
             content_type="application/json",
@@ -954,12 +927,15 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         mock_merge.assert_not_called()
 
         response = self.client.post(
-            "/api/documents/merge/",
+            "/api/documents/bulk_edit/",
             json.dumps(
                 {
                     "documents": [self.doc1.id],
-                    "metadata_document_id": self.doc1.id,
-                    "delete_originals": True,
+                    "method": "merge",
+                    "parameters": {
+                        "metadata_document_id": self.doc1.id,
+                        "delete_originals": True,
+                    },
                 },
             ),
             content_type="application/json",
@@ -1076,117 +1052,84 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
 
         m.assert_called_once()
 
-    @mock.patch("documents.views.bulk_edit.rotate")
+    @mock.patch("documents.serialisers.bulk_edit.rotate")
     def test_rotate(self, m) -> None:
         self.setup_mock(m, "rotate")
         response = self.client.post(
-            "/api/documents/rotate/",
+            "/api/documents/bulk_edit/",
             json.dumps(
                 {
                     "documents": [self.doc2.id, self.doc3.id],
-                    "degrees": 90,
+                    "method": "rotate",
+                    "parameters": {"degrees": 90},
                 },
             ),
             content_type="application/json",
         )
 
         self.assertEqual(response.status_code, status.HTTP_200_OK)
+
         m.assert_called_once()
         args, kwargs = m.call_args
         self.assertCountEqual(args[0], [self.doc2.id, self.doc3.id])
         self.assertEqual(kwargs["degrees"], 90)
-        self.assertEqual(kwargs["source_mode"], "latest_version")
-        self.assertEqual(kwargs["user"], self.user)
 
-    @mock.patch("documents.views.bulk_edit.rotate")
+    @mock.patch("documents.serialisers.bulk_edit.rotate")
     def test_rotate_invalid_params(self, m) -> None:
         response = self.client.post(
-            "/api/documents/rotate/",
+            "/api/documents/bulk_edit/",
             json.dumps(
                 {
                     "documents": [self.doc2.id, self.doc3.id],
-                    "degrees": "foo",
+                    "method": "rotate",
+                    "parameters": {"degrees": "foo"},
                 },
             ),
             content_type="application/json",
         )
+
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
 
         response = self.client.post(
-            "/api/documents/rotate/",
+            "/api/documents/bulk_edit/",
             json.dumps(
                 {
                     "documents": [self.doc2.id, self.doc3.id],
-                    "degrees": 90.5,
+                    "method": "rotate",
+                    "parameters": {"degrees": 90.5},
                 },
             ),
             content_type="application/json",
         )
+
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+
         m.assert_not_called()
 
-    @mock.patch("documents.views.bulk_edit.rotate")
-    def test_rotate_insufficient_permissions(self, m) -> None:
-        self.doc1.owner = User.objects.get(username="temp_admin")
-        self.doc1.save()
-        user1 = User.objects.create(username="user1")
-        user1.user_permissions.add(*Permission.objects.all())
-        user1.save()
-        self.client.force_authenticate(user=user1)
-
-        self.setup_mock(m, "rotate")
-        response = self.client.post(
-            "/api/documents/rotate/",
-            json.dumps(
-                {
-                    "documents": [self.doc1.id, self.doc2.id],
-                    "degrees": 90,
-                },
-            ),
-            content_type="application/json",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_403_FORBIDDEN)
-        m.assert_not_called()
-        self.assertEqual(response.content, b"Insufficient permissions")
-
-        response = self.client.post(
-            "/api/documents/rotate/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id, self.doc3.id],
-                    "degrees": 90,
-                },
-            ),
-            content_type="application/json",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_200_OK)
-        m.assert_called_once()
-
-    @mock.patch("documents.views.bulk_edit.merge")
+    @mock.patch("documents.serialisers.bulk_edit.merge")
     def test_merge(self, m) -> None:
         self.setup_mock(m, "merge")
         response = self.client.post(
-            "/api/documents/merge/",
+            "/api/documents/bulk_edit/",
             json.dumps(
                 {
                     "documents": [self.doc2.id, self.doc3.id],
-                    "metadata_document_id": self.doc3.id,
+                    "method": "merge",
+                    "parameters": {"metadata_document_id": self.doc3.id},
                 },
             ),
             content_type="application/json",
         )
 
         self.assertEqual(response.status_code, status.HTTP_200_OK)
+
         m.assert_called_once()
         args, kwargs = m.call_args
         self.assertCountEqual(args[0], [self.doc2.id, self.doc3.id])
         self.assertEqual(kwargs["metadata_document_id"], self.doc3.id)
-        self.assertEqual(kwargs["source_mode"], "latest_version")
         self.assertEqual(kwargs["user"], self.user)
 
-    @mock.patch("documents.views.bulk_edit.merge")
+    @mock.patch("documents.serialisers.bulk_edit.merge")
     def test_merge_and_delete_insufficient_permissions(self, m) -> None:
         self.doc1.owner = User.objects.get(username="temp_admin")
         self.doc1.save()
@@ -1197,12 +1140,15 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
 
         self.setup_mock(m, "merge")
         response = self.client.post(
-            "/api/documents/merge/",
+            "/api/documents/bulk_edit/",
             json.dumps(
                 {
                     "documents": [self.doc1.id, self.doc2.id],
-                    "metadata_document_id": self.doc2.id,
-                    "delete_originals": True,
+                    "method": "merge",
+                    "parameters": {
+                        "metadata_document_id": self.doc2.id,
+                        "delete_originals": True,
+                    },
                 },
             ),
             content_type="application/json",
@@ -1213,12 +1159,15 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(response.content, b"Insufficient permissions")
 
         response = self.client.post(
-            "/api/documents/merge/",
+            "/api/documents/bulk_edit/",
             json.dumps(
                 {
                     "documents": [self.doc2.id, self.doc3.id],
-                    "metadata_document_id": self.doc2.id,
-                    "delete_originals": True,
+                    "method": "merge",
+                    "parameters": {
+                        "metadata_document_id": self.doc2.id,
+                        "delete_originals": True,
+                    },
                 },
             ),
             content_type="application/json",
@@ -1227,15 +1176,27 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_200_OK)
         m.assert_called_once()
 
-    @mock.patch("documents.views.bulk_edit.merge")
+    @mock.patch("documents.serialisers.bulk_edit.merge")
     def test_merge_invalid_parameters(self, m) -> None:
+        """
+        GIVEN:
+            - API data for merging documents is called
+            - The parameters are invalid
+        WHEN:
+            - API is called
+        THEN:
+            - The API fails with a correct error code
+        """
         self.setup_mock(m, "merge")
         response = self.client.post(
-            "/api/documents/merge/",
+            "/api/documents/bulk_edit/",
             json.dumps(
                 {
                     "documents": [self.doc1.id, self.doc2.id],
-                    "delete_originals": "not_boolean",
+                    "method": "merge",
+                    "parameters": {
+                        "delete_originals": "not_boolean",
+                    },
                 },
             ),
             content_type="application/json",
@@ -1244,81 +1205,219 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
         m.assert_not_called()
 
-    def test_bulk_edit_allows_legacy_file_methods_with_warning(self) -> None:
-        method_payloads = {
-            "delete": {},
-            "reprocess": {},
-            "rotate": {"degrees": 90},
-            "merge": {"metadata_document_id": self.doc2.id},
-            "edit_pdf": {"operations": [{"page": 1}]},
-            "remove_password": {"password": "secret"},
-            "split": {"pages": "1,2-4"},
-            "delete_pages": {"pages": [1, 2]},
-        }
-
-        for version in (9, 10):
-            for method, parameters in method_payloads.items():
-                with self.subTest(method=method, version=version):
-                    with mock.patch(
-                        f"documents.views.bulk_edit.{method}",
-                    ) as mocked_method:
-                        self.setup_mock(mocked_method, method)
-                        with self.assertLogs("paperless.api", level="WARNING") as logs:
-                            response = self.client.post(
-                                "/api/documents/bulk_edit/",
-                                json.dumps(
-                                    {
-                                        "documents": [self.doc2.id],
-                                        "method": method,
-                                        "parameters": parameters,
-                                    },
-                                ),
-                                content_type="application/json",
-                                headers={
-                                    "Accept": f"application/json; version={version}",
-                                },
-                            )
-
-                        self.assertEqual(response.status_code, status.HTTP_200_OK)
-                        mocked_method.assert_called_once()
-                        self.assertTrue(
-                            any(
-                                "Deprecated bulk_edit method" in entry
-                                and f"'{method}'" in entry
-                                for entry in logs.output
-                            ),
-                        )
-
-    @mock.patch("documents.views.bulk_edit.edit_pdf")
-    def test_edit_pdf(self, m) -> None:
-        self.setup_mock(m, "edit_pdf")
+    @mock.patch("documents.serialisers.bulk_edit.split")
+    def test_split(self, m) -> None:
+        self.setup_mock(m, "split")
         response = self.client.post(
-            "/api/documents/edit_pdf/",
+            "/api/documents/bulk_edit/",
             json.dumps(
                 {
                     "documents": [self.doc2.id],
-                    "operations": [{"page": 1}],
-                    "source_mode": "explicit_selection",
+                    "method": "split",
+                    "parameters": {"pages": "1,2-4,5-6,7"},
                 },
             ),
             content_type="application/json",
         )
 
         self.assertEqual(response.status_code, status.HTTP_200_OK)
+
+        m.assert_called_once()
+        args, kwargs = m.call_args
+        self.assertCountEqual(args[0], [self.doc2.id])
+        self.assertEqual(kwargs["pages"], [[1], [2, 3, 4], [5, 6], [7]])
+        self.assertEqual(kwargs["user"], self.user)
+
+    def test_split_invalid_params(self) -> None:
+        response = self.client.post(
+            "/api/documents/bulk_edit/",
+            json.dumps(
+                {
+                    "documents": [self.doc2.id],
+                    "method": "split",
+                    "parameters": {},  # pages not specified
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertIn(b"pages not specified", response.content)
+
+        response = self.client.post(
+            "/api/documents/bulk_edit/",
+            json.dumps(
+                {
+                    "documents": [self.doc2.id],
+                    "method": "split",
+                    "parameters": {"pages": "1:7"},  # wrong format
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertIn(b"invalid pages specified", response.content)
+
+        response = self.client.post(
+            "/api/documents/bulk_edit/",
+            json.dumps(
+                {
+                    "documents": [
+                        self.doc1.id,
+                        self.doc2.id,
+                    ],  # only one document supported
+                    "method": "split",
+                    "parameters": {"pages": "1-2,3-7"},  # wrong format
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertIn(b"Split method only supports one document", response.content)
+
+        response = self.client.post(
+            "/api/documents/bulk_edit/",
+            json.dumps(
+                {
+                    "documents": [self.doc2.id],
+                    "method": "split",
+                    "parameters": {
+                        "pages": "1",
+                        "delete_originals": "notabool",
+                    },  # not a bool
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertIn(b"delete_originals must be a boolean", response.content)
+
+    @mock.patch("documents.serialisers.bulk_edit.delete_pages")
+    def test_delete_pages(self, m) -> None:
+        self.setup_mock(m, "delete_pages")
+        response = self.client.post(
+            "/api/documents/bulk_edit/",
+            json.dumps(
+                {
+                    "documents": [self.doc2.id],
+                    "method": "delete_pages",
+                    "parameters": {"pages": [1, 2, 3, 4]},
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+
+        m.assert_called_once()
+        args, kwargs = m.call_args
+        self.assertCountEqual(args[0], [self.doc2.id])
+        self.assertEqual(kwargs["pages"], [1, 2, 3, 4])
+
+    def test_delete_pages_invalid_params(self) -> None:
+        response = self.client.post(
+            "/api/documents/bulk_edit/",
+            json.dumps(
+                {
+                    "documents": [
+                        self.doc1.id,
+                        self.doc2.id,
+                    ],  # only one document supported
+                    "method": "delete_pages",
+                    "parameters": {
+                        "pages": [1, 2, 3, 4],
+                    },
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertIn(
+            b"Delete pages method only supports one document",
+            response.content,
+        )
+
+        response = self.client.post(
+            "/api/documents/bulk_edit/",
+            json.dumps(
+                {
+                    "documents": [self.doc2.id],
+                    "method": "delete_pages",
+                    "parameters": {},  # pages not specified
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertIn(b"pages not specified", response.content)
+
+        response = self.client.post(
+            "/api/documents/bulk_edit/",
+            json.dumps(
+                {
+                    "documents": [self.doc2.id],
+                    "method": "delete_pages",
+                    "parameters": {"pages": "1-3"},  # not a list
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertIn(b"pages must be a list", response.content)
+
+        response = self.client.post(
+            "/api/documents/bulk_edit/",
+            json.dumps(
+                {
+                    "documents": [self.doc2.id],
+                    "method": "delete_pages",
+                    "parameters": {"pages": ["1-3"]},  # not ints
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertIn(b"pages must be a list of integers", response.content)
+
+    @mock.patch("documents.serialisers.bulk_edit.edit_pdf")
+    def test_edit_pdf(self, m) -> None:
+        self.setup_mock(m, "edit_pdf")
+        response = self.client.post(
+            "/api/documents/bulk_edit/",
+            json.dumps(
+                {
+                    "documents": [self.doc2.id],
+                    "method": "edit_pdf",
+                    "parameters": {"operations": [{"page": 1}]},
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+
         m.assert_called_once()
         args, kwargs = m.call_args
         self.assertCountEqual(args[0], [self.doc2.id])
         self.assertEqual(kwargs["operations"], [{"page": 1}])
-        self.assertEqual(kwargs["source_mode"], "explicit_selection")
         self.assertEqual(kwargs["user"], self.user)
 
     def test_edit_pdf_invalid_params(self) -> None:
+        # multiple documents
         response = self.client.post(
-            "/api/documents/edit_pdf/",
+            "/api/documents/bulk_edit/",
             json.dumps(
                 {
                     "documents": [self.doc2.id, self.doc3.id],
-                    "operations": [{"page": 1}],
+                    "method": "edit_pdf",
+                    "parameters": {"operations": [{"page": 1}]},
                 },
             ),
             content_type="application/json",
@@ -1326,25 +1425,44 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
         self.assertIn(b"Edit PDF method only supports one document", response.content)
 
+        # no operations specified
         response = self.client.post(
-            "/api/documents/edit_pdf/",
+            "/api/documents/bulk_edit/",
             json.dumps(
                 {
                     "documents": [self.doc2.id],
-                    "operations": "not_a_list",
+                    "method": "edit_pdf",
+                    "parameters": {},
                 },
             ),
             content_type="application/json",
         )
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(b"Expected a list of items", response.content)
+        self.assertIn(b"operations not specified", response.content)
 
+        # operations not a list
         response = self.client.post(
-            "/api/documents/edit_pdf/",
+            "/api/documents/bulk_edit/",
             json.dumps(
                 {
                     "documents": [self.doc2.id],
-                    "operations": ["invalid_operation"],
+                    "method": "edit_pdf",
+                    "parameters": {"operations": "not_a_list"},
+                },
+            ),
+            content_type="application/json",
+        )
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertIn(b"operations must be a list", response.content)
+
+        # invalid operation
+        response = self.client.post(
+            "/api/documents/bulk_edit/",
+            json.dumps(
+                {
+                    "documents": [self.doc2.id],
+                    "method": "edit_pdf",
+                    "parameters": {"operations": ["invalid_operation"]},
                 },
             ),
             content_type="application/json",
@@ -1352,12 +1470,14 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
         self.assertIn(b"invalid operation entry", response.content)
 
+        # page not an int
         response = self.client.post(
-            "/api/documents/edit_pdf/",
+            "/api/documents/bulk_edit/",
             json.dumps(
                 {
                     "documents": [self.doc2.id],
-                    "operations": [{"page": "not_an_int"}],
+                    "method": "edit_pdf",
+                    "parameters": {"operations": [{"page": "not_an_int"}]},
                 },
             ),
             content_type="application/json",
@@ -1365,12 +1485,14 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
         self.assertIn(b"page must be an integer", response.content)
 
+        # rotate not an int
         response = self.client.post(
-            "/api/documents/edit_pdf/",
+            "/api/documents/bulk_edit/",
             json.dumps(
                 {
                     "documents": [self.doc2.id],
-                    "operations": [{"page": 1, "rotate": "not_an_int"}],
+                    "method": "edit_pdf",
+                    "parameters": {"operations": [{"page": 1, "rotate": "not_an_int"}]},
                 },
             ),
             content_type="application/json",
@@ -1378,12 +1500,14 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
         self.assertIn(b"rotate must be an integer", response.content)
 
+        # doc not an int
         response = self.client.post(
-            "/api/documents/edit_pdf/",
+            "/api/documents/bulk_edit/",
             json.dumps(
                 {
                     "documents": [self.doc2.id],
-                    "operations": [{"page": 1, "doc": "not_an_int"}],
+                    "method": "edit_pdf",
+                    "parameters": {"operations": [{"page": 1, "doc": "not_an_int"}]},
                 },
             ),
             content_type="application/json",
@@ -1391,13 +1515,53 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
         self.assertIn(b"doc must be an integer", response.content)
 
+        # update_document not a boolean
         response = self.client.post(
-            "/api/documents/edit_pdf/",
+            "/api/documents/bulk_edit/",
             json.dumps(
                 {
                     "documents": [self.doc2.id],
-                    "update_document": True,
-                    "operations": [{"page": 1, "doc": 1}, {"page": 2, "doc": 2}],
+                    "method": "edit_pdf",
+                    "parameters": {
+                        "update_document": "not_a_bool",
+                        "operations": [{"page": 1}],
+                    },
+                },
+            ),
+            content_type="application/json",
+        )
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertIn(b"update_document must be a boolean", response.content)
+
+        # include_metadata not a boolean
+        response = self.client.post(
+            "/api/documents/bulk_edit/",
+            json.dumps(
+                {
+                    "documents": [self.doc2.id],
+                    "method": "edit_pdf",
+                    "parameters": {
+                        "include_metadata": "not_a_bool",
+                        "operations": [{"page": 1}],
+                    },
+                },
+            ),
+            content_type="application/json",
+        )
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertIn(b"include_metadata must be a boolean", response.content)
+
+        # update_document True but output would be multiple documents
+        response = self.client.post(
+            "/api/documents/bulk_edit/",
+            json.dumps(
+                {
+                    "documents": [self.doc2.id],
+                    "method": "edit_pdf",
+                    "parameters": {
+                        "update_document": True,
+                        "operations": [{"page": 1, "doc": 1}, {"page": 2, "doc": 2}],
+                    },
                 },
             ),
             content_type="application/json",
@@ -1408,84 +1572,42 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
             response.content,
         )
 
-        response = self.client.post(
-            "/api/documents/edit_pdf/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "operations": [{"page": 1}],
-                    "source_mode": "not_a_mode",
-                },
-            ),
-            content_type="application/json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(b"Invalid source_mode", response.content)
-
-    @mock.patch("documents.views.bulk_edit.edit_pdf")
+    @mock.patch("documents.serialisers.bulk_edit.edit_pdf")
     def test_edit_pdf_page_out_of_bounds(self, m) -> None:
+        """
+        GIVEN:
+            - API data for editing PDF is called
+            - The page number is out of bounds
+        WHEN:
+            - API is called
+        THEN:
+            - The API fails with a correct error code
+        """
         self.setup_mock(m, "edit_pdf")
         response = self.client.post(
-            "/api/documents/edit_pdf/",
+            "/api/documents/bulk_edit/",
             json.dumps(
                 {
                     "documents": [self.doc2.id],
-                    "operations": [{"page": 99}],
+                    "method": "edit_pdf",
+                    "parameters": {"operations": [{"page": 99}]},
                 },
             ),
             content_type="application/json",
         )
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
         self.assertIn(b"out of bounds", response.content)
-        m.assert_not_called()
 
-    @mock.patch("documents.views.bulk_edit.edit_pdf")
-    def test_edit_pdf_insufficient_permissions(self, m) -> None:
-        self.doc1.owner = User.objects.get(username="temp_admin")
-        self.doc1.save()
-        user1 = User.objects.create(username="user1")
-        user1.user_permissions.add(*Permission.objects.all())
-        user1.save()
-        self.client.force_authenticate(user=user1)
-
-        self.setup_mock(m, "edit_pdf")
-        response = self.client.post(
-            "/api/documents/edit_pdf/",
-            json.dumps(
-                {
-                    "documents": [self.doc1.id],
-                    "operations": [{"page": 1}],
-                },
-            ),
-            content_type="application/json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_403_FORBIDDEN)
-        m.assert_not_called()
-        self.assertEqual(response.content, b"Insufficient permissions")
-
-        response = self.client.post(
-            "/api/documents/edit_pdf/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "operations": [{"page": 1}],
-                },
-            ),
-            content_type="application/json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_200_OK)
-        m.assert_called_once()
-
-    @mock.patch("documents.views.bulk_edit.remove_password")
+    @mock.patch("documents.serialisers.bulk_edit.remove_password")
     def test_remove_password(self, m) -> None:
         self.setup_mock(m, "remove_password")
         response = self.client.post(
-            "/api/documents/remove_password/",
+            "/api/documents/bulk_edit/",
             json.dumps(
                 {
                     "documents": [self.doc2.id],
-                    "password": "secret",
-                    "update_document": True,
+                    "method": "remove_password",
+                    "parameters": {"password": "secret", "update_document": True},
                 },
             ),
             content_type="application/json",
@@ -1497,69 +1619,36 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertCountEqual(args[0], [self.doc2.id])
         self.assertEqual(kwargs["password"], "secret")
         self.assertTrue(kwargs["update_document"])
-        self.assertEqual(kwargs["source_mode"], "latest_version")
         self.assertEqual(kwargs["user"], self.user)
 
     def test_remove_password_invalid_params(self) -> None:
         response = self.client.post(
-            "/api/documents/remove_password/",
+            "/api/documents/bulk_edit/",
             json.dumps(
                 {
                     "documents": [self.doc2.id],
+                    "method": "remove_password",
+                    "parameters": {},
                 },
             ),
             content_type="application/json",
         )
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertIn(b"password not specified", response.content)
 
         response = self.client.post(
-            "/api/documents/remove_password/",
+            "/api/documents/bulk_edit/",
             json.dumps(
                 {
                     "documents": [self.doc2.id],
-                    "password": 123,
+                    "method": "remove_password",
+                    "parameters": {"password": 123},
                 },
             ),
             content_type="application/json",
         )
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-
-    @mock.patch("documents.views.bulk_edit.remove_password")
-    def test_remove_password_insufficient_permissions(self, m) -> None:
-        self.doc1.owner = User.objects.get(username="temp_admin")
-        self.doc1.save()
-        user1 = User.objects.create(username="user1")
-        user1.user_permissions.add(*Permission.objects.all())
-        user1.save()
-        self.client.force_authenticate(user=user1)
-
-        self.setup_mock(m, "remove_password")
-        response = self.client.post(
-            "/api/documents/remove_password/",
-            json.dumps(
-                {
-                    "documents": [self.doc1.id],
-                    "password": "secret",
-                },
-            ),
-            content_type="application/json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_403_FORBIDDEN)
-        m.assert_not_called()
-        self.assertEqual(response.content, b"Insufficient permissions")
-
-        response = self.client.post(
-            "/api/documents/remove_password/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "password": "secret",
-                },
-            ),
-            content_type="application/json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_200_OK)
-        m.assert_called_once()
+        self.assertIn(b"password must be a string", response.content)
 
     @override_settings(AUDIT_LOG_ENABLED=True)
     def test_bulk_edit_audit_log_enabled_simple_field(self) -> None:

src/documents/tests/test_api_custom_fields.py

@@ -323,6 +323,113 @@ class TestCustomFieldsAPI(DirectoriesMixin, APITestCase):
 
         mock_delay.assert_called_once_with(cf_select)
 
+    def test_custom_field_select_old_version(self) -> None:
+        """
+        GIVEN:
+            - Nothing
+        WHEN:
+            - API post request is made for custom fields with api version header < 7
+            - API get request is made for custom fields with api version header < 7
+        THEN:
+            - The select options are created with unique ids
+            - The select options are returned in the old format
+        """
+        resp = self.client.post(
+            self.ENDPOINT,
+            headers={"Accept": "application/json; version=6"},
+            data=json.dumps(
+                {
+                    "data_type": "select",
+                    "name": "Select Field",
+                    "extra_data": {
+                        "select_options": [
+                            "Option 1",
+                            "Option 2",
+                        ],
+                    },
+                },
+            ),
+            content_type="application/json",
+        )
+        self.assertEqual(resp.status_code, status.HTTP_201_CREATED)
+
+        field = CustomField.objects.get(name="Select Field")
+        self.assertEqual(
+            field.extra_data["select_options"],
+            [
+                {"label": "Option 1", "id": ANY},
+                {"label": "Option 2", "id": ANY},
+            ],
+        )
+
+        resp = self.client.get(
+            f"{self.ENDPOINT}{field.id}/",
+            headers={"Accept": "application/json; version=6"},
+        )
+        self.assertEqual(resp.status_code, status.HTTP_200_OK)
+
+        data = resp.json()
+        self.assertEqual(
+            data["extra_data"]["select_options"],
+            [
+                "Option 1",
+                "Option 2",
+            ],
+        )
+
+    def test_custom_field_select_value_old_version(self) -> None:
+        """
+        GIVEN:
+            - Existing document with custom field select
+        WHEN:
+            - API post request is made to add the field for document with api version header < 7
+            - API get request is made for document with api version header < 7
+        THEN:
+            - The select value is returned in the old format, the index of the option
+        """
+        custom_field_select = CustomField.objects.create(
+            name="Select Field",
+            data_type=CustomField.FieldDataType.SELECT,
+            extra_data={
+                "select_options": [
+                    {"label": "Option 1", "id": "abc-123"},
+                    {"label": "Option 2", "id": "def-456"},
+                ],
+            },
+        )
+
+        doc = Document.objects.create(
+            title="WOW",
+            content="the content",
+            checksum="123",
+            mime_type="application/pdf",
+        )
+
+        resp = self.client.patch(
+            f"/api/documents/{doc.id}/",
+            headers={"Accept": "application/json; version=6"},
+            data=json.dumps(
+                {
+                    "custom_fields": [
+                        {"field": custom_field_select.id, "value": 1},
+                    ],
+                },
+            ),
+            content_type="application/json",
+        )
+        self.assertEqual(resp.status_code, status.HTTP_200_OK)
+        doc.refresh_from_db()
+        self.assertEqual(doc.custom_fields.first().value, "def-456")
+
+        resp = self.client.get(
+            f"/api/documents/{doc.id}/",
+            headers={"Accept": "application/json; version=6"},
+        )
+        self.assertEqual(resp.status_code, status.HTTP_200_OK)
+
+        data = resp.json()
+        self.assertEqual(data["custom_fields"][0]["value"], 1)
+
     def test_create_custom_field_monetary_validation(self) -> None:
         """
         GIVEN:

src/documents/tests/test_api_documents.py

@@ -41,7 +41,6 @@ from documents.models import SavedView
 from documents.models import ShareLink
 from documents.models import StoragePath
 from documents.models import Tag
-from documents.models import UiSettings
 from documents.models import Workflow
 from documents.models import WorkflowAction
 from documents.models import WorkflowTrigger
@@ -177,7 +176,7 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
         results = response.data["results"]
         self.assertEqual(len(results[0]), 0)
 
-    def test_document_fields_respects_created(self) -> None:
+    def test_document_fields_api_version_8_respects_created(self) -> None:
         Document.objects.create(
             title="legacy",
             checksum="123",
@@ -187,6 +186,7 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
 
         response = self.client.get(
             "/api/documents/?fields=id",
+            headers={"Accept": "application/json; version=8"},
             format="json",
         )
         self.assertEqual(response.status_code, status.HTTP_200_OK)
@@ -196,22 +196,25 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
 
         response = self.client.get(
             "/api/documents/?fields=id,created",
+            headers={"Accept": "application/json; version=8"},
             format="json",
         )
         self.assertEqual(response.status_code, status.HTTP_200_OK)
         results = response.data["results"]
         self.assertIn("id", results[0])
         self.assertIn("created", results[0])
-        self.assertEqual(results[0]["created"], "2024-01-15")
+        self.assertRegex(results[0]["created"], r"^2024-01-15T00:00:00.*$")
 
-    def test_document_created_format(self) -> None:
+    def test_document_legacy_created_format(self) -> None:
         """
         GIVEN:
             - Existing document
         WHEN:
-            - Document is requested
+            - Document is requested with api version ≥ 9
+            - Document is requested with api version < 9
         THEN:
             - Document created field is returned as date
+            - Document created field is returned as datetime
         """
         doc = Document.objects.create(
             title="none",
@@ -222,6 +225,14 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
 
         response = self.client.get(
             f"/api/documents/{doc.pk}/",
+            headers={"Accept": "application/json; version=8"},
+        )
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        self.assertRegex(response.data["created"], r"^2023-01-01T00:00:00.*$")
+
+        response = self.client.get(
+            f"/api/documents/{doc.pk}/",
+            headers={"Accept": "application/json; version=9"},
         )
         self.assertEqual(response.status_code, status.HTTP_200_OK)
         self.assertEqual(response.data["created"], "2023-01-01")
@@ -2189,205 +2200,6 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_200_OK)
         self.assertEqual(response.data["count"], 0)
 
-    def test_saved_view_api_version_backward_compatibility(self) -> None:
-        """
-        GIVEN:
-            - Saved views and UiSettings with visibility preferences
-        WHEN:
-            - API request with version=9 (legacy)
-            - API request with version=10 (current)
-        THEN:
-            - Version 9 returns show_on_dashboard and show_in_sidebar from UiSettings
-            - Version 10 omits these fields (moved to UiSettings)
-        """
-        v1 = SavedView.objects.create(
-            owner=self.user,
-            name="dashboard_view",
-            sort_field="created",
-        )
-        v2 = SavedView.objects.create(
-            owner=self.user,
-            name="sidebar_view",
-            sort_field="created",
-        )
-        v3 = SavedView.objects.create(
-            owner=self.user,
-            name="hidden_view",
-            sort_field="created",
-        )
-
-        UiSettings.objects.update_or_create(
-            user=self.user,
-            defaults={
-                "settings": {
-                    "saved_views": {
-                        "dashboard_views_visible_ids": [v1.id],
-                        "sidebar_views_visible_ids": [v2.id],
-                    },
-                },
-            },
-        )
-
-        response_v9 = self.client.get(
-            "/api/saved_views/",
-            headers={"Accept": "application/json; version=9"},
-            format="json",
-        )
-        self.assertEqual(response_v9.status_code, status.HTTP_200_OK)
-        results_v9 = {r["id"]: r for r in response_v9.data["results"]}
-        self.assertIn("show_on_dashboard", results_v9[v1.id])
-        self.assertIn("show_in_sidebar", results_v9[v1.id])
-        self.assertTrue(results_v9[v1.id]["show_on_dashboard"])
-        self.assertFalse(results_v9[v1.id]["show_in_sidebar"])
-        self.assertTrue(results_v9[v2.id]["show_in_sidebar"])
-        self.assertFalse(results_v9[v2.id]["show_on_dashboard"])
-        self.assertFalse(results_v9[v3.id]["show_on_dashboard"])
-        self.assertFalse(results_v9[v3.id]["show_in_sidebar"])
-
-        response_v10 = self.client.get(
-            "/api/saved_views/",
-            headers={"Accept": "application/json; version=10"},
-            format="json",
-        )
-        self.assertEqual(response_v10.status_code, status.HTTP_200_OK)
-        results_v10 = {r["id"]: r for r in response_v10.data["results"]}
-        self.assertNotIn("show_on_dashboard", results_v10[v1.id])
-        self.assertNotIn("show_in_sidebar", results_v10[v1.id])
-
-    def test_saved_view_api_version_9_user_without_ui_settings(self) -> None:
-        """
-        GIVEN:
-            - User with no UiSettings and a saved view
-        WHEN:
-            - API request with version=9
-        THEN:
-            - show_on_dashboard and show_in_sidebar are False (default)
-        """
-        SavedView.objects.create(
-            owner=self.user,
-            name="test_view",
-            sort_field="created",
-        )
-        UiSettings.objects.filter(user=self.user).delete()
-
-        response = self.client.get(
-            "/api/saved_views/",
-            headers={"Accept": "application/json; version=9"},
-            format="json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_200_OK)
-        result = response.data["results"][0]
-        self.assertFalse(result["show_on_dashboard"])
-        self.assertFalse(result["show_in_sidebar"])
-
-    def test_saved_view_api_version_9_create_writes_visibility_to_ui_settings(
-        self,
-    ) -> None:
-        """
-        GIVEN:
-            - No UiSettings for the current user
-        WHEN:
-            - A saved view is created through API version 9 with visibility flags
-        THEN:
-            - Visibility is persisted in UiSettings.saved_views
-        """
-        UiSettings.objects.filter(user=self.user).delete()
-
-        response = self.client.post(
-            "/api/saved_views/",
-            {
-                "name": "legacy-v9-create",
-                "sort_field": "created",
-                "filter_rules": [],
-                "show_on_dashboard": True,
-                "show_in_sidebar": False,
-            },
-            headers={"Accept": "application/json; version=9"},
-            format="json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_201_CREATED)
-        self.assertTrue(response.data["show_on_dashboard"])
-        self.assertFalse(response.data["show_in_sidebar"])
-
-        self.user.refresh_from_db()
-        self.assertTrue(hasattr(self.user, "ui_settings"))
-        saved_view_settings = self.user.ui_settings.settings["saved_views"]
-        self.assertListEqual(
-            saved_view_settings["dashboard_views_visible_ids"],
-            [response.data["id"]],
-        )
-        self.assertListEqual(saved_view_settings["sidebar_views_visible_ids"], [])
-
-    def test_saved_view_api_version_9_patch_writes_visibility_to_ui_settings(
-        self,
-    ) -> None:
-        """
-        GIVEN:
-            - Existing saved views and UiSettings visibility ids
-        WHEN:
-            - A saved view is updated through API version 9 visibility flags
-        THEN:
-            - The per-user UiSettings visibility ids are updated
-        """
-        v1 = SavedView.objects.create(
-            owner=self.user,
-            name="legacy-v9-patch-1",
-            sort_field="created",
-        )
-        v2 = SavedView.objects.create(
-            owner=self.user,
-            name="legacy-v9-patch-2",
-            sort_field="created",
-        )
-        UiSettings.objects.update_or_create(
-            user=self.user,
-            defaults={
-                "settings": {
-                    "saved_views": {
-                        "dashboard_views_visible_ids": [v1.id],
-                        "sidebar_views_visible_ids": [v1.id, v2.id],
-                    },
-                },
-            },
-        )
-
-        response = self.client.patch(
-            f"/api/saved_views/{v1.id}/",
-            {
-                "show_on_dashboard": False,
-            },
-            headers={"Accept": "application/json; version=9"},
-            format="json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_200_OK)
-        self.assertFalse(response.data["show_on_dashboard"])
-        self.assertTrue(response.data["show_in_sidebar"])
-
-        self.user.refresh_from_db()
-        saved_view_settings = self.user.ui_settings.settings["saved_views"]
-        self.assertListEqual(saved_view_settings["dashboard_views_visible_ids"], [])
-        self.assertListEqual(
-            saved_view_settings["sidebar_views_visible_ids"],
-            [v1.id, v2.id],
-        )
-
-        response = self.client.patch(
-            f"/api/saved_views/{v1.id}/",
-            {
-                "show_in_sidebar": False,
-            },
-            headers={"Accept": "application/json; version=9"},
-            format="json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_200_OK)
-        self.assertFalse(response.data["show_on_dashboard"])
-        self.assertFalse(response.data["show_in_sidebar"])
-
-        self.user.refresh_from_db()
-        saved_view_settings = self.user.ui_settings.settings["saved_views"]
-        self.assertListEqual(saved_view_settings["dashboard_views_visible_ids"], [])
-        self.assertListEqual(saved_view_settings["sidebar_views_visible_ids"], [v2.id])
-
     def test_saved_view_create_update_patch(self) -> None:
         User.objects.create_user("user1")
 
@@ -2791,6 +2603,26 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
             },
         )
 
+    def test_docnote_serializer_v7(self) -> None:
+        doc = Document.objects.create(
+            title="test",
+            mime_type="application/pdf",
+            content="this is a document which will have notes!",
+        )
+        Note.objects.create(
+            note="This is a note.",
+            document=doc,
+            user=self.user,
+        )
+        self.assertEqual(
+            self.client.get(
+                f"/api/documents/{doc.pk}/",
+                headers={"Accept": "application/json; version=7"},
+                format="json",
+            ).data["notes"][0]["user"],
+            self.user.id,
+        )
+
     def test_create_note(self) -> None:
         """
         GIVEN:
@@ -3559,13 +3391,14 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
             )
 
 
-class TestDocumentApiTagColors(DirectoriesMixin, APITestCase):
+class TestDocumentApiV2(DirectoriesMixin, APITestCase):
     def setUp(self) -> None:
         super().setUp()
 
         self.user = User.objects.create_superuser(username="temp_admin")
 
         self.client.force_authenticate(user=self.user)
+        self.client.defaults["HTTP_ACCEPT"] = "application/json; version=2"
 
     def test_tag_validate_color(self) -> None:
         self.assertEqual(

src/documents/tests/test_api_filter_by_custom_fields.py

@@ -152,7 +152,7 @@ class TestCustomFieldsSearch(DirectoriesMixin, APITestCase):
             context={
                 "request": types.SimpleNamespace(
                     method="GET",
-                    version="9",
+                    version="7",
                 ),
             },
         )

src/documents/tests/test_api_schema.py

@@ -25,39 +25,3 @@ class TestApiSchema(APITestCase):
 
         ui_response = self.client.get(self.ENDPOINT + "view/")
         self.assertEqual(ui_response.status_code, status.HTTP_200_OK)
-
-    def test_schema_includes_dedicated_document_edit_endpoints(self) -> None:
-        schema_response = self.client.get(self.ENDPOINT)
-        self.assertEqual(schema_response.status_code, status.HTTP_200_OK)
-
-        paths = schema_response.data["paths"]
-        self.assertIn("/api/documents/delete/", paths)
-        self.assertIn("/api/documents/reprocess/", paths)
-        self.assertIn("/api/documents/rotate/", paths)
-        self.assertIn("/api/documents/merge/", paths)
-        self.assertIn("/api/documents/edit_pdf/", paths)
-        self.assertIn("/api/documents/remove_password/", paths)
-
-    def test_schema_bulk_edit_advertises_legacy_document_action_methods(self) -> None:
-        schema_response = self.client.get(self.ENDPOINT)
-        self.assertEqual(schema_response.status_code, status.HTTP_200_OK)
-
-        schema = schema_response.data["components"]["schemas"]
-        bulk_schema = schema["BulkEditRequest"]
-        method_schema = bulk_schema["properties"]["method"]
-
-        # drf-spectacular emits the enum as a referenced schema for this field
-        enum_ref = method_schema["allOf"][0]["$ref"].split("/")[-1]
-        advertised_methods = schema[enum_ref]["enum"]
-
-        for action_method in [
-            "delete",
-            "reprocess",
-            "rotate",
-            "merge",
-            "edit_pdf",
-            "remove_password",
-            "split",
-            "delete_pages",
-        ]:
-            self.assertIn(action_method, advertised_methods)

src/documents/tests/test_bulk_edit.py

@@ -405,9 +405,7 @@ class TestBulkEdit(DirectoriesMixin, TestCase):
         self.assertTrue(Document.objects.filter(id=self.doc1.id).exists())
         self.assertFalse(Document.objects.filter(id=version.id).exists())
 
-    def test_resolve_root_and_source_doc_latest_version_prefers_newest_version(
-        self,
-    ) -> None:
+    def test_get_root_and_current_doc_mapping(self) -> None:
         version1 = Document.objects.create(
             checksum="B-v1",
             title="B version 1",
@@ -419,14 +417,18 @@ class TestBulkEdit(DirectoriesMixin, TestCase):
             root_document=self.doc2,
         )
 
-        root_doc, source_doc = bulk_edit._resolve_root_and_source_doc(
-            self.doc2,
-            source_mode="latest_version",
+        root_ids_by_doc_id = bulk_edit._get_root_ids_by_doc_id(
+            [self.doc2.id, version1.id, version2.id],
         )
+        self.assertEqual(root_ids_by_doc_id[self.doc2.id], self.doc2.id)
+        self.assertEqual(root_ids_by_doc_id[version1.id], self.doc2.id)
+        self.assertEqual(root_ids_by_doc_id[version2.id], self.doc2.id)
 
-        self.assertEqual(root_doc.id, self.doc2.id)
-        self.assertEqual(source_doc.id, version2.id)
-        self.assertNotEqual(source_doc.id, version1.id)
+        root_docs, current_docs = bulk_edit._get_root_and_current_docs_by_root_id(
+            {self.doc2.id},
+        )
+        self.assertEqual(root_docs[self.doc2.id].id, self.doc2.id)
+        self.assertEqual(current_docs[self.doc2.id].id, version2.id)
 
     @mock.patch("documents.tasks.bulk_update_documents.delay")
     def test_set_permissions(self, m) -> None:
@@ -660,33 +662,6 @@ class TestPDFActions(DirectoriesMixin, TestCase):
 
         self.assertEqual(result, "OK")
 
-    @mock.patch("pikepdf.open")
-    @mock.patch("documents.tasks.consume_file.s")
-    def test_merge_uses_latest_version_source_for_root_selection(
-        self,
-        mock_consume_file,
-        mock_open_pdf,
-    ) -> None:
-        version_file = self.dirs.scratch_dir / "sample2_version_merge.pdf"
-        shutil.copy(self.doc2.source_path, version_file)
-        version = Document.objects.create(
-            checksum="B-v1",
-            title="B version 1",
-            root_document=self.doc2,
-            filename=version_file,
-            mime_type="application/pdf",
-        )
-        fake_pdf = mock.MagicMock()
-        fake_pdf.pdf_version = "1.7"
-        fake_pdf.pages = [mock.Mock()]
-        mock_open_pdf.return_value.__enter__.return_value = fake_pdf
-
-        result = bulk_edit.merge([self.doc2.id])
-
-        self.assertEqual(result, "OK")
-        mock_open_pdf.assert_called_once_with(str(version.source_path))
-        mock_consume_file.assert_not_called()
-
     @mock.patch("documents.bulk_edit.delete.si")
     @mock.patch("documents.tasks.consume_file.s")
     def test_merge_and_delete_originals(
@@ -895,36 +870,6 @@ class TestPDFActions(DirectoriesMixin, TestCase):
 
         self.assertEqual(result, "OK")
 
-    @mock.patch("documents.bulk_edit.group")
-    @mock.patch("pikepdf.open")
-    @mock.patch("documents.tasks.consume_file.s")
-    def test_split_uses_latest_version_source_for_root_selection(
-        self,
-        mock_consume_file,
-        mock_open_pdf,
-        mock_group,
-    ) -> None:
-        version_file = self.dirs.scratch_dir / "sample2_version_split.pdf"
-        shutil.copy(self.doc2.source_path, version_file)
-        version = Document.objects.create(
-            checksum="B-v1",
-            title="B version 1",
-            root_document=self.doc2,
-            filename=version_file,
-            mime_type="application/pdf",
-        )
-        fake_pdf = mock.MagicMock()
-        fake_pdf.pages = [mock.Mock(), mock.Mock()]
-        mock_open_pdf.return_value.__enter__.return_value = fake_pdf
-        mock_group.return_value.delay.return_value = None
-
-        result = bulk_edit.split([self.doc2.id], [[1], [2]])
-
-        self.assertEqual(result, "OK")
-        mock_open_pdf.assert_called_once_with(version.source_path)
-        mock_consume_file.assert_not_called()
-        mock_group.return_value.delay.assert_not_called()
-
     @mock.patch("documents.bulk_edit.delete.si")
     @mock.patch("documents.tasks.consume_file.s")
     @mock.patch("documents.bulk_edit.chord")
@@ -1096,34 +1041,6 @@ class TestPDFActions(DirectoriesMixin, TestCase):
             self.assertIsNotNone(overrides)
             self.assertEqual(result, "OK")
 
-    @mock.patch("documents.data_models.magic.from_file", return_value="application/pdf")
-    @mock.patch("documents.tasks.consume_file.delay")
-    @mock.patch("pikepdf.open")
-    def test_rotate_explicit_selection_uses_root_source_when_root_selected(
-        self,
-        mock_open,
-        mock_consume_delay,
-        mock_magic,
-    ):
-        Document.objects.create(
-            checksum="B-v1",
-            title="B version 1",
-            root_document=self.doc2,
-        )
-        fake_pdf = mock.MagicMock()
-        fake_pdf.pages = [mock.Mock()]
-        mock_open.return_value.__enter__.return_value = fake_pdf
-
-        result = bulk_edit.rotate(
-            [self.doc2.id],
-            90,
-            source_mode="explicit_selection",
-        )
-
-        self.assertEqual(result, "OK")
-        mock_open.assert_called_once_with(self.doc2.source_path)
-        mock_consume_delay.assert_called_once()
-
     @mock.patch("documents.tasks.consume_file.delay")
     @mock.patch("pikepdf.Pdf.save")
     @mock.patch("documents.data_models.magic.from_file", return_value="application/pdf")
@@ -1148,34 +1065,6 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         self.assertIsNotNone(overrides)
         self.assertEqual(result, "OK")
 
-    @mock.patch("documents.data_models.magic.from_file", return_value="application/pdf")
-    @mock.patch("documents.tasks.consume_file.delay")
-    @mock.patch("pikepdf.open")
-    def test_delete_pages_explicit_selection_uses_root_source_when_root_selected(
-        self,
-        mock_open,
-        mock_consume_delay,
-        mock_magic,
-    ):
-        Document.objects.create(
-            checksum="B-v1",
-            title="B version 1",
-            root_document=self.doc2,
-        )
-        fake_pdf = mock.MagicMock()
-        fake_pdf.pages = [mock.Mock(), mock.Mock()]
-        mock_open.return_value.__enter__.return_value = fake_pdf
-
-        result = bulk_edit.delete_pages(
-            [self.doc2.id],
-            [1],
-            source_mode="explicit_selection",
-        )
-
-        self.assertEqual(result, "OK")
-        mock_open.assert_called_once_with(self.doc2.source_path)
-        mock_consume_delay.assert_called_once()
-
     @mock.patch("documents.tasks.consume_file.delay")
     @mock.patch("pikepdf.Pdf.save")
     def test_delete_pages_with_error(self, mock_pdf_save, mock_consume_delay):
@@ -1324,40 +1213,6 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         self.assertTrue(str(consumable.original_file).endswith("_edited.pdf"))
         self.assertIsNotNone(overrides)
 
-    @mock.patch("documents.data_models.magic.from_file", return_value="application/pdf")
-    @mock.patch("documents.tasks.consume_file.delay")
-    @mock.patch("pikepdf.new")
-    @mock.patch("pikepdf.open")
-    def test_edit_pdf_explicit_selection_uses_root_source_when_root_selected(
-        self,
-        mock_open,
-        mock_new,
-        mock_consume_delay,
-        mock_magic,
-    ):
-        Document.objects.create(
-            checksum="B-v1",
-            title="B version 1",
-            root_document=self.doc2,
-        )
-        fake_pdf = mock.MagicMock()
-        fake_pdf.pages = [mock.Mock()]
-        mock_open.return_value.__enter__.return_value = fake_pdf
-        output_pdf = mock.MagicMock()
-        output_pdf.pages = []
-        mock_new.return_value = output_pdf
-
-        result = bulk_edit.edit_pdf(
-            [self.doc2.id],
-            operations=[{"page": 1}],
-            update_document=True,
-            source_mode="explicit_selection",
-        )
-
-        self.assertEqual(result, "OK")
-        mock_open.assert_called_once_with(self.doc2.source_path)
-        mock_consume_delay.assert_called_once()
-
     @mock.patch("documents.bulk_edit.group")
     @mock.patch("documents.tasks.consume_file.s")
     def test_edit_pdf_without_metadata(
@@ -1478,34 +1333,6 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         self.assertEqual(consumable.root_document_id, doc.id)
         self.assertIsNotNone(overrides)
 
-    @mock.patch("documents.data_models.magic.from_file", return_value="application/pdf")
-    @mock.patch("documents.tasks.consume_file.delay")
-    @mock.patch("pikepdf.open")
-    def test_remove_password_explicit_selection_uses_root_source_when_root_selected(
-        self,
-        mock_open,
-        mock_consume_delay,
-        mock_magic,
-    ) -> None:
-        Document.objects.create(
-            checksum="A-v1",
-            title="A version 1",
-            root_document=self.doc1,
-        )
-        fake_pdf = mock.MagicMock()
-        mock_open.return_value.__enter__.return_value = fake_pdf
-
-        result = bulk_edit.remove_password(
-            [self.doc1.id],
-            password="secret",
-            update_document=True,
-            source_mode="explicit_selection",
-        )
-
-        self.assertEqual(result, "OK")
-        mock_open.assert_called_once_with(self.doc1.source_path, password="secret")
-        mock_consume_delay.assert_called_once()
-
     @mock.patch("documents.bulk_edit.chord")
     @mock.patch("documents.bulk_edit.group")
     @mock.patch("documents.tasks.consume_file.s")

src/documents/tests/test_consumer.py

@@ -245,8 +245,14 @@ class TestConsumer(
 
         self.assertIsFile(document.archive_path)
 
-        self.assertEqual(document.checksum, "42995833e01aea9b3edee44bbfdd7ce1")
-        self.assertEqual(document.archive_checksum, "62acb0bcbfbcaa62ca6ad3668e4e404b")
+        self.assertEqual(
+            document.checksum,
+            "1093cf6e32adbd16b06969df09215d42c4a3a8938cc18b39455953f08d1ff2ab",
+        )
+        self.assertEqual(
+            document.archive_checksum,
+            "706124ecde3c31616992fa979caed17a726b1c9ccdba70e82a4ff796cea97ccf",
+        )
 
         self.assertIsNotFile(filename)
 

src/documents/tests/test_management_exporter.py

@@ -63,8 +63,8 @@ class TestExportImport(
 
         self.d1 = Document.objects.create(
             content="Content",
-            checksum="42995833e01aea9b3edee44bbfdd7ce1",
-            archive_checksum="62acb0bcbfbcaa62ca6ad3668e4e404b",
+            checksum="1093cf6e32adbd16b06969df09215d42c4a3a8938cc18b39455953f08d1ff2ab",
+            archive_checksum="706124ecde3c31616992fa979caed17a726b1c9ccdba70e82a4ff796cea97ccf",
             title="wow1",
             filename="0000001.pdf",
             mime_type="application/pdf",
@@ -72,21 +72,21 @@ class TestExportImport(
         )
         self.d2 = Document.objects.create(
             content="Content",
-            checksum="9c9691e51741c1f4f41a20896af31770",
+            checksum="550d1bae0f746d4f7c6be07054eb20cc2f11988a58ef64ceae45e98f85e92a5b",
             title="wow2",
             filename="0000002.pdf",
             mime_type="application/pdf",
         )
         self.d3 = Document.objects.create(
             content="Content",
-            checksum="d38d7ed02e988e072caf924e0f3fcb76",
+            checksum="f1ba6b7ff8548214a75adec228f5468a14fe187f445bc0b9485cbf1c35b15915",
             title="wow2",
             filename="0000003.pdf",
             mime_type="application/pdf",
         )
         self.d4 = Document.objects.create(
             content="Content",
-            checksum="82186aaa94f0b98697d704b90fd1c072",
+            checksum="a81b16b6b313cfd7e60eb7b12598d1343b58622b4030cfa19a2724a02e98db1b",
             title="wow_dec",
             filename="0000004.pdf",
             mime_type="application/pdf",
@@ -147,6 +147,7 @@ class TestExportImport(
         else:
             raise ValueError(f"document with id {id} does not exist in manifest")
 
+    @override_settings(PASSPHRASE="test")
     def _do_export(
         self,
         *,
@@ -239,7 +240,7 @@ class TestExportImport(
                 )
 
                 with Path(fname).open("rb") as f:
-                    checksum = hashlib.md5(f.read()).hexdigest()
+                    checksum = hashlib.sha256(f.read()).hexdigest()
                 self.assertEqual(checksum, element["fields"]["checksum"])
 
                 # Generated field "content_length" should not be exported,
@@ -253,7 +254,7 @@ class TestExportImport(
                     self.assertIsFile(fname)
 
                     with Path(fname).open("rb") as f:
-                        checksum = hashlib.md5(f.read()).hexdigest()
+                        checksum = hashlib.sha256(f.read()).hexdigest()
                     self.assertEqual(checksum, element["fields"]["archive_checksum"])
 
             elif element["model"] == "documents.note":
@@ -440,6 +441,7 @@ class TestExportImport(
         )
         self.assertRaises(FileNotFoundError, call_command, "document_exporter", target)
 
+    @override_settings(PASSPHRASE="test")
     def test_export_zipped(self) -> None:
         """
         GIVEN:
@@ -471,6 +473,7 @@ class TestExportImport(
             self.assertIn("manifest.json", zip.namelist())
             self.assertIn("metadata.json", zip.namelist())
 
+    @override_settings(PASSPHRASE="test")
     def test_export_zipped_format(self) -> None:
         """
         GIVEN:
@@ -507,6 +510,7 @@ class TestExportImport(
             self.assertIn("manifest.json", zip.namelist())
             self.assertIn("metadata.json", zip.namelist())
 
+    @override_settings(PASSPHRASE="test")
     def test_export_zipped_with_delete(self) -> None:
         """
         GIVEN:
@@ -749,31 +753,6 @@ class TestExportImport(
             call_command("document_importer", "--no-progress-bar", self.target)
             self.assertEqual(Document.objects.count(), 4)
 
-    def test_folder_prefix_with_split(self) -> None:
-        """
-        GIVEN:
-            - Request to export documents to directory
-        WHEN:
-            - Option use_folder_prefix is used
-            - Option split manifest is used
-        THEN:
-            - Documents can be imported again
-        """
-        shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        shutil.copytree(
-            Path(__file__).parent / "samples" / "documents",
-            Path(self.dirs.media_dir) / "documents",
-        )
-
-        self._do_export(use_folder_prefix=True, split_manifest=True)
-
-        with paperless_environment():
-            self.assertEqual(Document.objects.count(), 4)
-            Document.objects.all().delete()
-            self.assertEqual(Document.objects.count(), 0)
-            call_command("document_importer", "--no-progress-bar", self.target)
-            self.assertEqual(Document.objects.count(), 4)
-
     def test_import_db_transaction_failed(self) -> None:
         """
         GIVEN:

src/documents/tests/test_management_importer.py

@@ -119,22 +119,15 @@ class TestCommandImport(
             # No read permissions
             original_path.chmod(0o222)
 
-            manifest_path = Path(temp_dir) / "manifest.json"
-            manifest_path.write_text(
-                json.dumps(
-                    [
-                        {
-                            "model": "documents.document",
-                            EXPORTER_FILE_NAME: "original.pdf",
-                            EXPORTER_ARCHIVE_NAME: "archive.pdf",
-                        },
-                    ],
-                ),
-            )
-
             cmd = Command()
             cmd.source = Path(temp_dir)
-            cmd.manifest_paths = [manifest_path]
+            cmd.manifest = [
+                {
+                    "model": "documents.document",
+                    EXPORTER_FILE_NAME: "original.pdf",
+                    EXPORTER_ARCHIVE_NAME: "archive.pdf",
+                },
+            ]
             cmd.data_only = False
             with self.assertRaises(CommandError) as cm:
                 cmd.check_manifest_validity()
@@ -267,8 +260,8 @@ class TestCommandImport(
 
         Document.objects.create(
             content="Content",
-            checksum="42995833e01aea9b3edee44bbfdd7ce1",
-            archive_checksum="62acb0bcbfbcaa62ca6ad3668e4e404b",
+            checksum="1093cf6e32adbd16b06969df09215d42c4a3a8938cc18b39455953f08d1ff2ab",
+            archive_checksum="706124ecde3c31616992fa979caed17a726b1c9ccdba70e82a4ff796cea97ccf",
             title="wow1",
             filename="0000001.pdf",
             mime_type="application/pdf",
@@ -303,7 +296,7 @@ class TestCommandImport(
         (self.dirs.scratch_dir / "manifest.json").touch()
 
         # We're not building a manifest, so it fails, but this test doesn't care
-        with self.assertRaises(CommandError):
+        with self.assertRaises(json.decoder.JSONDecodeError):
             call_command(
                 "document_importer",
                 "--no-progress-bar",
@@ -332,7 +325,7 @@ class TestCommandImport(
         )
 
         # We're not building a manifest, so it fails, but this test doesn't care
-        with self.assertRaises(CommandError):
+        with self.assertRaises(json.decoder.JSONDecodeError):
             call_command(
                 "document_importer",
                 "--no-progress-bar",

src/documents/tests/test_migration_saved_view_visibility.py

@@ -6,8 +6,8 @@ SIDEBAR_VIEWS_VISIBLE_IDS_KEY = "sidebar_views_visible_ids"
 
 
 class TestMigrateSavedViewVisibilityToUiSettings(TestMigrations):
-    migrate_from = "0013_alter_paperlesstask_task_name"
-    migrate_to = "0014_savedview_visibility_to_ui_settings"
+    migrate_from = "0013_document_root_document"
+    migrate_to = "0015_savedview_visibility_to_ui_settings"
 
     def setUpBeforeMigration(self, apps) -> None:
         User = apps.get_model("auth", "User")
@@ -132,8 +132,8 @@ class TestMigrateSavedViewVisibilityToUiSettings(TestMigrations):
 
 
 class TestReverseMigrateSavedViewVisibilityFromUiSettings(TestMigrations):
-    migrate_from = "0014_savedview_visibility_to_ui_settings"
-    migrate_to = "0013_alter_paperlesstask_task_name"
+    migrate_from = "0015_savedview_visibility_to_ui_settings"
+    migrate_to = "0014_alter_paperlesstask_task_name"
 
     def setUpBeforeMigration(self, apps) -> None:
         User = apps.get_model("auth", "User")

src/documents/tests/test_migration_share_link_bundle.py

@@ -2,8 +2,8 @@ from documents.tests.utils import TestMigrations
 
 
 class TestMigrateShareLinkBundlePermissions(TestMigrations):
-    migrate_from = "0006_document_content_length"
-    migrate_to = "0007_sharelinkbundle"
+    migrate_from = "0007_document_content_length"
+    migrate_to = "0008_sharelinkbundle"
 
     def setUpBeforeMigration(self, apps) -> None:
         User = apps.get_model("auth", "User")
@@ -24,8 +24,8 @@ class TestMigrateShareLinkBundlePermissions(TestMigrations):
 
 
 class TestReverseMigrateShareLinkBundlePermissions(TestMigrations):
-    migrate_from = "0007_sharelinkbundle"
-    migrate_to = "0006_document_content_length"
+    migrate_from = "0008_sharelinkbundle"
+    migrate_to = "0007_document_content_length"
 
     def setUpBeforeMigration(self, apps) -> None:
         User = apps.get_model("auth", "User")

src/documents/utils.py

@@ -1,3 +1,4 @@
+import hashlib
 import logging
 import shutil
 from os import utime
@@ -128,3 +129,15 @@ def get_boolean(boolstr: str) -> bool:
     Return a boolean value from a string representation.
     """
     return bool(boolstr.lower() in ("yes", "y", "1", "t", "true"))
+
+
+def compute_checksum(path: Path, chunk_size: int = 65536) -> str:
+    """
+    Return the SHA256 hex digest of the file at *path*, reading in chunks
+    of *chunk_size* bytes to avoid loading the entire file into memory.
+    """
+    h = hashlib.sha256()
+    with path.open("rb") as f:
+        while chunk := f.read(chunk_size):
+            h.update(chunk)
+    return h.hexdigest()

src/documents/views.py

@@ -176,20 +176,14 @@ from documents.serialisers import BulkEditObjectsSerializer
 from documents.serialisers import BulkEditSerializer
 from documents.serialisers import CorrespondentSerializer
 from documents.serialisers import CustomFieldSerializer
-from documents.serialisers import DeleteDocumentsSerializer
 from documents.serialisers import DocumentListSerializer
 from documents.serialisers import DocumentSerializer
 from documents.serialisers import DocumentTypeSerializer
 from documents.serialisers import DocumentVersionLabelSerializer
 from documents.serialisers import DocumentVersionSerializer
-from documents.serialisers import EditPdfDocumentsSerializer
 from documents.serialisers import EmailSerializer
-from documents.serialisers import MergeDocumentsSerializer
 from documents.serialisers import NotesSerializer
 from documents.serialisers import PostDocumentSerializer
-from documents.serialisers import RemovePasswordDocumentsSerializer
-from documents.serialisers import ReprocessDocumentsSerializer
-from documents.serialisers import RotateDocumentsSerializer
 from documents.serialisers import RunTaskViewSerializer
 from documents.serialisers import SavedViewSerializer
 from documents.serialisers import SearchResultSerializer
@@ -2120,125 +2114,6 @@ class SavedViewViewSet(BulkPermissionMixin, PassUserMixin, ModelViewSet):
     ordering_fields = ("name",)
 
 
-class DocumentOperationPermissionMixin(PassUserMixin):
-    permission_classes = (IsAuthenticated,)
-    parser_classes = (parsers.JSONParser,)
-    METHOD_NAMES_REQUIRING_USER = {
-        "split",
-        "merge",
-        "rotate",
-        "delete_pages",
-        "edit_pdf",
-        "remove_password",
-    }
-
-    def _has_document_permissions(
-        self,
-        *,
-        user: User,
-        documents: list[int],
-        method,
-        parameters: dict[str, Any],
-    ) -> bool:
-        if user.is_superuser:
-            return True
-
-        document_objs = Document.objects.select_related("owner").filter(
-            pk__in=documents,
-        )
-        user_is_owner_of_all_documents = all(
-            (doc.owner == user or doc.owner is None) for doc in document_objs
-        )
-
-        # check global and object permissions for all documents
-        has_perms = user.has_perm("documents.change_document") and all(
-            has_perms_owner_aware(user, "change_document", doc) for doc in document_objs
-        )
-
-        # check ownership for methods that change original document
-        if (
-            (
-                has_perms
-                and method
-                in [
-                    bulk_edit.set_permissions,
-                    bulk_edit.delete,
-                    bulk_edit.rotate,
-                    bulk_edit.delete_pages,
-                    bulk_edit.edit_pdf,
-                    bulk_edit.remove_password,
-                ]
-            )
-            or (
-                method in [bulk_edit.merge, bulk_edit.split]
-                and parameters.get("delete_originals")
-            )
-            or (method == bulk_edit.edit_pdf and parameters.get("update_document"))
-        ):
-            has_perms = user_is_owner_of_all_documents
-
-        # check global add permissions for methods that create documents
-        if (
-            has_perms
-            and (
-                method in [bulk_edit.split, bulk_edit.merge]
-                or (
-                    method in [bulk_edit.edit_pdf, bulk_edit.remove_password]
-                    and not parameters.get("update_document")
-                )
-            )
-            and not user.has_perm("documents.add_document")
-        ):
-            has_perms = False
-
-        # check global delete permissions for methods that delete documents
-        if (
-            has_perms
-            and (
-                method == bulk_edit.delete
-                or (
-                    method in [bulk_edit.merge, bulk_edit.split]
-                    and parameters.get("delete_originals")
-                )
-            )
-            and not user.has_perm("documents.delete_document")
-        ):
-            has_perms = False
-
-        return has_perms
-
-    def _execute_document_action(
-        self,
-        *,
-        method,
-        validated_data: dict[str, Any],
-        operation_label: str,
-    ):
-        documents = validated_data["documents"]
-        parameters = {k: v for k, v in validated_data.items() if k != "documents"}
-        user = self.request.user
-
-        if method.__name__ in self.METHOD_NAMES_REQUIRING_USER:
-            parameters["user"] = user
-
-        if not self._has_document_permissions(
-            user=user,
-            documents=documents,
-            method=method,
-            parameters=parameters,
-        ):
-            return HttpResponseForbidden("Insufficient permissions")
-
-        try:
-            result = method(documents, **parameters)
-            return Response({"result": result})
-        except Exception as e:
-            logger.warning(f"An error occurred performing {operation_label}: {e!s}")
-            return HttpResponseBadRequest(
-                f"Error performing {operation_label}, check logs for more detail.",
-            )
-
-
 @extend_schema_view(
     post=extend_schema(
         operation_id="bulk_edit",
@@ -2257,7 +2132,7 @@ class DocumentOperationPermissionMixin(PassUserMixin):
         },
     ),
 )
-class BulkEditView(DocumentOperationPermissionMixin):
+class BulkEditView(PassUserMixin):
     MODIFIED_FIELD_BY_METHOD = {
         "set_correspondent": "correspondent",
         "set_document_type": "document_type",
@@ -2279,24 +2154,11 @@ class BulkEditView(DocumentOperationPermissionMixin):
         "remove_password": None,
     }
 
+    permission_classes = (IsAuthenticated,)
     serializer_class = BulkEditSerializer
+    parser_classes = (parsers.JSONParser,)
 
     def post(self, request, *args, **kwargs):
-        request_method = request.data.get("method")
-        api_version = int(request.version or settings.REST_FRAMEWORK["DEFAULT_VERSION"])
-        # TODO: remove this and related backwards compatibility code when API v9 is dropped
-        if request_method in BulkEditSerializer.LEGACY_DOCUMENT_ACTION_METHODS:
-            endpoint = BulkEditSerializer.MOVED_DOCUMENT_ACTION_ENDPOINTS[
-                request_method
-            ]
-            logger.warning(
-                "Deprecated bulk_edit method '%s' requested on API version %s. "
-                "Use '%s' instead.",
-                request_method,
-                api_version,
-                endpoint,
-            )
-
         serializer = self.get_serializer(data=request.data)
         serializer.is_valid(raise_exception=True)
 
@@ -2304,15 +2166,82 @@ class BulkEditView(DocumentOperationPermissionMixin):
         method = serializer.validated_data.get("method")
         parameters = serializer.validated_data.get("parameters")
         documents = serializer.validated_data.get("documents")
-        if method.__name__ in self.METHOD_NAMES_REQUIRING_USER:
+        if method in [
+            bulk_edit.split,
+            bulk_edit.merge,
+            bulk_edit.rotate,
+            bulk_edit.delete_pages,
+            bulk_edit.edit_pdf,
+            bulk_edit.remove_password,
+        ]:
             parameters["user"] = user
-        if not self._has_document_permissions(
-            user=user,
-            documents=documents,
-            method=method,
-            parameters=parameters,
-        ):
-            return HttpResponseForbidden("Insufficient permissions")
+
+        if not user.is_superuser:
+            document_objs = Document.objects.select_related("owner").filter(
+                pk__in=documents,
+            )
+            user_is_owner_of_all_documents = all(
+                (doc.owner == user or doc.owner is None) for doc in document_objs
+            )
+
+            # check global and object permissions for all documents
+            has_perms = user.has_perm("documents.change_document") and all(
+                has_perms_owner_aware(user, "change_document", doc)
+                for doc in document_objs
+            )
+
+            # check ownership for methods that change original document
+            if (
+                (
+                    has_perms
+                    and method
+                    in [
+                        bulk_edit.set_permissions,
+                        bulk_edit.delete,
+                        bulk_edit.rotate,
+                        bulk_edit.delete_pages,
+                        bulk_edit.edit_pdf,
+                        bulk_edit.remove_password,
+                    ]
+                )
+                or (
+                    method in [bulk_edit.merge, bulk_edit.split]
+                    and parameters["delete_originals"]
+                )
+                or (method == bulk_edit.edit_pdf and parameters["update_document"])
+            ):
+                has_perms = user_is_owner_of_all_documents
+
+            # check global add permissions for methods that create documents
+            if (
+                has_perms
+                and (
+                    method in [bulk_edit.split, bulk_edit.merge]
+                    or (
+                        method in [bulk_edit.edit_pdf, bulk_edit.remove_password]
+                        and not parameters["update_document"]
+                    )
+                )
+                and not user.has_perm("documents.add_document")
+            ):
+                has_perms = False
+
+            # check global delete permissions for methods that delete documents
+            if (
+                has_perms
+                and (
+                    method == bulk_edit.delete
+                    or (
+                        method in [bulk_edit.merge, bulk_edit.split]
+                        and parameters["delete_originals"]
+                    )
+                )
+                and not user.has_perm("documents.delete_document")
+            ):
+                has_perms = False
+
+            if not has_perms:
+                return HttpResponseForbidden("Insufficient permissions")
 
         try:
             modified_field = self.MODIFIED_FIELD_BY_METHOD.get(method.__name__, None)
@@ -2369,168 +2298,6 @@ class BulkEditView(DocumentOperationPermissionMixin):
             )
 
 
-@extend_schema_view(
-    post=extend_schema(
-        operation_id="documents_rotate",
-        description="Rotate one or more documents",
-        responses={
-            200: inline_serializer(
-                name="RotateDocumentsResult",
-                fields={
-                    "result": serializers.CharField(),
-                },
-            ),
-        },
-    ),
-)
-class RotateDocumentsView(DocumentOperationPermissionMixin):
-    serializer_class = RotateDocumentsSerializer
-
-    def post(self, request, *args, **kwargs):
-        serializer = self.get_serializer(data=request.data)
-        serializer.is_valid(raise_exception=True)
-        return self._execute_document_action(
-            method=bulk_edit.rotate,
-            validated_data=serializer.validated_data,
-            operation_label="document rotate",
-        )
-
-
-@extend_schema_view(
-    post=extend_schema(
-        operation_id="documents_merge",
-        description="Merge selected documents into a new document",
-        responses={
-            200: inline_serializer(
-                name="MergeDocumentsResult",
-                fields={
-                    "result": serializers.CharField(),
-                },
-            ),
-        },
-    ),
-)
-class MergeDocumentsView(DocumentOperationPermissionMixin):
-    serializer_class = MergeDocumentsSerializer
-
-    def post(self, request, *args, **kwargs):
-        serializer = self.get_serializer(data=request.data)
-        serializer.is_valid(raise_exception=True)
-        return self._execute_document_action(
-            method=bulk_edit.merge,
-            validated_data=serializer.validated_data,
-            operation_label="document merge",
-        )
-
-
-@extend_schema_view(
-    post=extend_schema(
-        operation_id="documents_delete",
-        description="Move selected documents to trash",
-        responses={
-            200: inline_serializer(
-                name="DeleteDocumentsResult",
-                fields={
-                    "result": serializers.CharField(),
-                },
-            ),
-        },
-    ),
-)
-class DeleteDocumentsView(DocumentOperationPermissionMixin):
-    serializer_class = DeleteDocumentsSerializer
-
-    def post(self, request, *args, **kwargs):
-        serializer = self.get_serializer(data=request.data)
-        serializer.is_valid(raise_exception=True)
-        return self._execute_document_action(
-            method=bulk_edit.delete,
-            validated_data=serializer.validated_data,
-            operation_label="document delete",
-        )
-
-
-@extend_schema_view(
-    post=extend_schema(
-        operation_id="documents_reprocess",
-        description="Reprocess selected documents",
-        responses={
-            200: inline_serializer(
-                name="ReprocessDocumentsResult",
-                fields={
-                    "result": serializers.CharField(),
-                },
-            ),
-        },
-    ),
-)
-class ReprocessDocumentsView(DocumentOperationPermissionMixin):
-    serializer_class = ReprocessDocumentsSerializer
-
-    def post(self, request, *args, **kwargs):
-        serializer = self.get_serializer(data=request.data)
-        serializer.is_valid(raise_exception=True)
-        return self._execute_document_action(
-            method=bulk_edit.reprocess,
-            validated_data=serializer.validated_data,
-            operation_label="document reprocess",
-        )
-
-
-@extend_schema_view(
-    post=extend_schema(
-        operation_id="documents_edit_pdf",
-        description="Perform PDF edit operations on a selected document",
-        responses={
-            200: inline_serializer(
-                name="EditPdfDocumentsResult",
-                fields={
-                    "result": serializers.CharField(),
-                },
-            ),
-        },
-    ),
-)
-class EditPdfDocumentsView(DocumentOperationPermissionMixin):
-    serializer_class = EditPdfDocumentsSerializer
-
-    def post(self, request, *args, **kwargs):
-        serializer = self.get_serializer(data=request.data)
-        serializer.is_valid(raise_exception=True)
-        return self._execute_document_action(
-            method=bulk_edit.edit_pdf,
-            validated_data=serializer.validated_data,
-            operation_label="PDF edit",
-        )
-
-
-@extend_schema_view(
-    post=extend_schema(
-        operation_id="documents_remove_password",
-        description="Remove password protection from selected PDFs",
-        responses={
-            200: inline_serializer(
-                name="RemovePasswordDocumentsResult",
-                fields={
-                    "result": serializers.CharField(),
-                },
-            ),
-        },
-    ),
-)
-class RemovePasswordDocumentsView(DocumentOperationPermissionMixin):
-    serializer_class = RemovePasswordDocumentsSerializer
-
-    def post(self, request, *args, **kwargs):
-        serializer = self.get_serializer(data=request.data)
-        serializer.is_valid(raise_exception=True)
-        return self._execute_document_action(
-            method=bulk_edit.remove_password,
-            validated_data=serializer.validated_data,
-            operation_label="password removal",
-        )
-
-
 @extend_schema_view(
     post=extend_schema(
         description="Upload a document via the API",

src/locale/en_US/LC_MESSAGES/django.po

@@ -2,7 +2,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: paperless-ngx\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2026-03-10 18:57+0000\n"
+"POT-Creation-Date: 2026-03-04 23:29+0000\n"
 "PO-Revision-Date: 2022-02-17 04:17\n"
 "Last-Translator: \n"
 "Language-Team: English\n"
@@ -1299,7 +1299,7 @@ msgstr ""
 msgid "workflow runs"
 msgstr ""
 
-#: documents/serialisers.py:463 documents/serialisers.py:2470
+#: documents/serialisers.py:463 documents/serialisers.py:2332
 msgid "Insufficient permissions."
 msgstr ""
 
@@ -1307,39 +1307,39 @@ msgstr ""
 msgid "Invalid color."
 msgstr ""
 
-#: documents/serialisers.py:2093
+#: documents/serialisers.py:1955
 #, python-format
 msgid "File type %(type)s not supported"
 msgstr ""
 
-#: documents/serialisers.py:2137
+#: documents/serialisers.py:1999
 #, python-format
 msgid "Custom field id must be an integer: %(id)s"
 msgstr ""
 
-#: documents/serialisers.py:2144
+#: documents/serialisers.py:2006
 #, python-format
 msgid "Custom field with id %(id)s does not exist"
 msgstr ""
 
-#: documents/serialisers.py:2161 documents/serialisers.py:2171
+#: documents/serialisers.py:2023 documents/serialisers.py:2033
 msgid ""
 "Custom fields must be a list of integers or an object mapping ids to values."
 msgstr ""
 
-#: documents/serialisers.py:2166
+#: documents/serialisers.py:2028
 msgid "Some custom fields don't exist or were specified twice."
 msgstr ""
 
-#: documents/serialisers.py:2313
+#: documents/serialisers.py:2175
 msgid "Invalid variable detected."
 msgstr ""
 
-#: documents/serialisers.py:2526
+#: documents/serialisers.py:2388
 msgid "Duplicate document identifiers are not allowed."
 msgstr ""
 
-#: documents/serialisers.py:2556 documents/views.py:3561
+#: documents/serialisers.py:2418 documents/views.py:3328
 #, python-format
 msgid "Documents not found: %(ids)s"
 msgstr ""
@@ -1603,20 +1603,20 @@ msgstr ""
 msgid "Unable to parse URI {value}"
 msgstr ""
 
-#: documents/views.py:3573
+#: documents/views.py:3340
 #, python-format
 msgid "Insufficient permissions to share document %(id)s."
 msgstr ""
 
-#: documents/views.py:3616
+#: documents/views.py:3383
 msgid "Bundle is already being processed."
 msgstr ""
 
-#: documents/views.py:3673
+#: documents/views.py:3440
 msgid "The share link bundle is still being prepared. Please try again later."
 msgstr ""
 
-#: documents/views.py:3683
+#: documents/views.py:3450
 msgid "The share link bundle is unavailable."
 msgstr ""
 
@@ -1856,155 +1856,155 @@ msgstr ""
 msgid "paperless application settings"
 msgstr ""
 
-#: paperless/settings/__init__.py:521
+#: paperless/settings/__init__.py:752
 msgid "English (US)"
 msgstr ""
 
-#: paperless/settings/__init__.py:522
+#: paperless/settings/__init__.py:753
 msgid "Arabic"
 msgstr ""
 
-#: paperless/settings/__init__.py:523
+#: paperless/settings/__init__.py:754
 msgid "Afrikaans"
 msgstr ""
 
-#: paperless/settings/__init__.py:524
+#: paperless/settings/__init__.py:755
 msgid "Belarusian"
 msgstr ""
 
-#: paperless/settings/__init__.py:525
+#: paperless/settings/__init__.py:756
 msgid "Bulgarian"
 msgstr ""
 
-#: paperless/settings/__init__.py:526
+#: paperless/settings/__init__.py:757
 msgid "Catalan"
 msgstr ""
 
-#: paperless/settings/__init__.py:527
+#: paperless/settings/__init__.py:758
 msgid "Czech"
 msgstr ""
 
-#: paperless/settings/__init__.py:528
+#: paperless/settings/__init__.py:759
 msgid "Danish"
 msgstr ""
 
-#: paperless/settings/__init__.py:529
+#: paperless/settings/__init__.py:760
 msgid "German"
 msgstr ""
 
-#: paperless/settings/__init__.py:530
+#: paperless/settings/__init__.py:761
 msgid "Greek"
 msgstr ""
 
-#: paperless/settings/__init__.py:531
+#: paperless/settings/__init__.py:762
 msgid "English (GB)"
 msgstr ""
 
-#: paperless/settings/__init__.py:532
+#: paperless/settings/__init__.py:763
 msgid "Spanish"
 msgstr ""
 
-#: paperless/settings/__init__.py:533
+#: paperless/settings/__init__.py:764
 msgid "Persian"
 msgstr ""
 
-#: paperless/settings/__init__.py:534
+#: paperless/settings/__init__.py:765
 msgid "Finnish"
 msgstr ""
 
-#: paperless/settings/__init__.py:535
+#: paperless/settings/__init__.py:766
 msgid "French"
 msgstr ""
 
-#: paperless/settings/__init__.py:536
+#: paperless/settings/__init__.py:767
 msgid "Hungarian"
 msgstr ""
 
-#: paperless/settings/__init__.py:537
+#: paperless/settings/__init__.py:768
 msgid "Indonesian"
 msgstr ""
 
-#: paperless/settings/__init__.py:538
+#: paperless/settings/__init__.py:769
 msgid "Italian"
 msgstr ""
 
-#: paperless/settings/__init__.py:539
+#: paperless/settings/__init__.py:770
 msgid "Japanese"
 msgstr ""
 
-#: paperless/settings/__init__.py:540
+#: paperless/settings/__init__.py:771
 msgid "Korean"
 msgstr ""
 
-#: paperless/settings/__init__.py:541
+#: paperless/settings/__init__.py:772
 msgid "Luxembourgish"
 msgstr ""
 
-#: paperless/settings/__init__.py:542
+#: paperless/settings/__init__.py:773
 msgid "Norwegian"
 msgstr ""
 
-#: paperless/settings/__init__.py:543
+#: paperless/settings/__init__.py:774
 msgid "Dutch"
 msgstr ""
 
-#: paperless/settings/__init__.py:544
+#: paperless/settings/__init__.py:775
 msgid "Polish"
 msgstr ""
 
-#: paperless/settings/__init__.py:545
+#: paperless/settings/__init__.py:776
 msgid "Portuguese (Brazil)"
 msgstr ""
 
-#: paperless/settings/__init__.py:546
+#: paperless/settings/__init__.py:777
 msgid "Portuguese"
 msgstr ""
 
-#: paperless/settings/__init__.py:547
+#: paperless/settings/__init__.py:778
 msgid "Romanian"
 msgstr ""
 
-#: paperless/settings/__init__.py:548
+#: paperless/settings/__init__.py:779
 msgid "Russian"
 msgstr ""
 
-#: paperless/settings/__init__.py:549
+#: paperless/settings/__init__.py:780
 msgid "Slovak"
 msgstr ""
 
-#: paperless/settings/__init__.py:550
+#: paperless/settings/__init__.py:781
 msgid "Slovenian"
 msgstr ""
 
-#: paperless/settings/__init__.py:551
+#: paperless/settings/__init__.py:782
 msgid "Serbian"
 msgstr ""
 
-#: paperless/settings/__init__.py:552
+#: paperless/settings/__init__.py:783
 msgid "Swedish"
 msgstr ""
 
-#: paperless/settings/__init__.py:553
+#: paperless/settings/__init__.py:784
 msgid "Turkish"
 msgstr ""
 
-#: paperless/settings/__init__.py:554
+#: paperless/settings/__init__.py:785
 msgid "Ukrainian"
 msgstr ""
 
-#: paperless/settings/__init__.py:555
+#: paperless/settings/__init__.py:786
 msgid "Vietnamese"
 msgstr ""
 
-#: paperless/settings/__init__.py:556
+#: paperless/settings/__init__.py:787
 msgid "Chinese Simplified"
 msgstr ""
 
-#: paperless/settings/__init__.py:557
+#: paperless/settings/__init__.py:788
 msgid "Chinese Traditional"
 msgstr ""
 
-#: paperless/urls.py:415
+#: paperless/urls.py:379
 msgid "Paperless-ngx administration"
 msgstr ""
 

src/paperless/settings/__init__.py

@@ -6,25 +6,18 @@ import math
 import multiprocessing
 import os
 import tempfile
+from os import PathLike
 from pathlib import Path
 from typing import Final
 from urllib.parse import urlparse
 
+from celery.schedules import crontab
 from compression_middleware.middleware import CompressionMiddleware
+from dateparser.languages.loader import LocaleDataLoader
 from django.utils.translation import gettext_lazy as _
 from dotenv import load_dotenv
 
-from paperless.settings.custom import parse_beat_schedule
-from paperless.settings.custom import parse_dateparser_languages
 from paperless.settings.custom import parse_db_settings
-from paperless.settings.custom import parse_hosting_settings
-from paperless.settings.custom import parse_ignore_dates
-from paperless.settings.custom import parse_redis_url
-from paperless.settings.parsers import get_bool_from_env
-from paperless.settings.parsers import get_float_from_env
-from paperless.settings.parsers import get_int_from_env
-from paperless.settings.parsers import get_list_from_env
-from paperless.settings.parsers import get_path_from_env
 
 logger = logging.getLogger("paperless.settings")
 
@@ -52,8 +45,239 @@ for path in [
 os.environ["OMP_THREAD_LIMIT"] = "1"
 
 
+def __get_boolean(key: str, default: str = "NO") -> bool:
+    """
+    Return a boolean value based on whatever the user has supplied in the
+    environment based on whether the value "looks like" it's True or not.
+    """
+    return bool(os.getenv(key, default).lower() in ("yes", "y", "1", "t", "true"))
+
+
+def __get_int(key: str, default: int) -> int:
+    """
+    Return an integer value based on the environment variable or a default
+    """
+    return int(os.getenv(key, default))
+
+
+def __get_optional_int(key: str) -> int | None:
+    """
+    Returns None if the environment key is not present, otherwise an integer
+    """
+    if key in os.environ:
+        return __get_int(key, -1)  # pragma: no cover
+    return None
+
+
+def __get_float(key: str, default: float) -> float:
+    """
+    Return an integer value based on the environment variable or a default
+    """
+    return float(os.getenv(key, default))
+
+
+def __get_path(
+    key: str,
+    default: PathLike | str,
+) -> Path:
+    """
+    Return a normalized, absolute path based on the environment variable or a default,
+    if provided
+    """
+    if key in os.environ:
+        return Path(os.environ[key]).resolve()
+    return Path(default).resolve()
+
+
+def __get_optional_path(key: str) -> Path | None:
+    """
+    Returns None if the environment key is not present, otherwise a fully resolved Path
+    """
+    if key in os.environ:
+        return __get_path(key, "")
+    return None
+
+
+def __get_list(
+    key: str,
+    default: list[str] | None = None,
+    sep: str = ",",
+) -> list[str]:
+    """
+    Return a list of elements from the environment, as separated by the given
+    string, or the default if the key does not exist
+    """
+    if key in os.environ:
+        return list(filter(None, os.environ[key].split(sep)))
+    elif default is not None:
+        return default
+    else:
+        return []
+
+
+def _parse_redis_url(env_redis: str | None) -> tuple[str, str]:
+    """
+    Gets the Redis information from the environment or a default and handles
+    converting from incompatible django_channels and celery formats.
+
+    Returns a tuple of (celery_url, channels_url)
+    """
+
+    # Not set, return a compatible default
+    if env_redis is None:
+        return ("redis://localhost:6379", "redis://localhost:6379")
+
+    if "unix" in env_redis.lower():
+        # channels_redis socket format, looks like:
+        # "unix:///path/to/redis.sock"
+        _, path = env_redis.split(":", 1)
+        # Optionally setting a db number
+        if "?db=" in env_redis:
+            path, number = path.split("?db=")
+            return (f"redis+socket:{path}?virtual_host={number}", env_redis)
+        else:
+            return (f"redis+socket:{path}", env_redis)
+
+    elif "+socket" in env_redis.lower():
+        # celery socket style, looks like:
+        # "redis+socket:///path/to/redis.sock"
+        _, path = env_redis.split(":", 1)
+        if "?virtual_host=" in env_redis:
+            # Virtual host (aka db number)
+            path, number = path.split("?virtual_host=")
+            return (env_redis, f"unix:{path}?db={number}")
+        else:
+            return (env_redis, f"unix:{path}")
+
+    # Not a socket
+    return (env_redis, env_redis)
+
+
+def _parse_beat_schedule() -> dict:
+    """
+    Configures the scheduled tasks, according to default or
+    environment variables.  Task expiration is configured so the task will
+    expire (and not run), shortly before the default frequency will put another
+    of the same task into the queue
+
+
+    https://docs.celeryq.dev/en/stable/userguide/periodic-tasks.html#beat-entries
+    https://docs.celeryq.dev/en/latest/userguide/calling.html#expiration
+    """
+    schedule = {}
+    tasks = [
+        {
+            "name": "Check all e-mail accounts",
+            "env_key": "PAPERLESS_EMAIL_TASK_CRON",
+            # Default every ten minutes
+            "env_default": "*/10 * * * *",
+            "task": "paperless_mail.tasks.process_mail_accounts",
+            "options": {
+                # 1 minute before default schedule sends again
+                "expires": 9.0 * 60.0,
+            },
+        },
+        {
+            "name": "Train the classifier",
+            "env_key": "PAPERLESS_TRAIN_TASK_CRON",
+            # Default hourly at 5 minutes past the hour
+            "env_default": "5 */1 * * *",
+            "task": "documents.tasks.train_classifier",
+            "options": {
+                # 1 minute before default schedule sends again
+                "expires": 59.0 * 60.0,
+            },
+        },
+        {
+            "name": "Optimize the index",
+            "env_key": "PAPERLESS_INDEX_TASK_CRON",
+            # Default daily at midnight
+            "env_default": "0 0 * * *",
+            "task": "documents.tasks.index_optimize",
+            "options": {
+                # 1 hour before default schedule sends again
+                "expires": 23.0 * 60.0 * 60.0,
+            },
+        },
+        {
+            "name": "Perform sanity check",
+            "env_key": "PAPERLESS_SANITY_TASK_CRON",
+            # Default Sunday at 00:30
+            "env_default": "30 0 * * sun",
+            "task": "documents.tasks.sanity_check",
+            "options": {
+                # 1 hour before default schedule sends again
+                "expires": ((7.0 * 24.0) - 1.0) * 60.0 * 60.0,
+            },
+        },
+        {
+            "name": "Empty trash",
+            "env_key": "PAPERLESS_EMPTY_TRASH_TASK_CRON",
+            # Default daily at 01:00
+            "env_default": "0 1 * * *",
+            "task": "documents.tasks.empty_trash",
+            "options": {
+                # 1 hour before default schedule sends again
+                "expires": 23.0 * 60.0 * 60.0,
+            },
+        },
+        {
+            "name": "Check and run scheduled workflows",
+            "env_key": "PAPERLESS_WORKFLOW_SCHEDULED_TASK_CRON",
+            # Default hourly at 5 minutes past the hour
+            "env_default": "5 */1 * * *",
+            "task": "documents.tasks.check_scheduled_workflows",
+            "options": {
+                # 1 minute before default schedule sends again
+                "expires": 59.0 * 60.0,
+            },
+        },
+        {
+            "name": "Rebuild LLM index",
+            "env_key": "PAPERLESS_LLM_INDEX_TASK_CRON",
+            # Default daily at 02:10
+            "env_default": "10 2 * * *",
+            "task": "documents.tasks.llmindex_index",
+            "options": {
+                # 1 hour before default schedule sends again
+                "expires": 23.0 * 60.0 * 60.0,
+            },
+        },
+        {
+            "name": "Cleanup expired share link bundles",
+            "env_key": "PAPERLESS_SHARE_LINK_BUNDLE_CLEANUP_CRON",
+            # Default daily at 02:00
+            "env_default": "0 2 * * *",
+            "task": "documents.tasks.cleanup_expired_share_link_bundles",
+            "options": {
+                # 1 hour before default schedule sends again
+                "expires": 23.0 * 60.0 * 60.0,
+            },
+        },
+    ]
+    for task in tasks:
+        # Either get the environment setting or use the default
+        value = os.getenv(task["env_key"], task["env_default"])
+        # Don't add disabled tasks to the schedule
+        if value == "disable":
+            continue
+        # I find https://crontab.guru/ super helpful
+        # crontab(5) format
+        #   - five time-and-date fields
+        #   - separated by at least one blank
+        minute, hour, day_month, month, day_week = value.split(" ")
+
+        schedule[task["name"]] = {
+            "task": task["task"],
+            "schedule": crontab(minute, hour, day_week, day_month, month),
+            "options": task["options"],
+        }
+
+    return schedule
+
+
 # NEVER RUN WITH DEBUG IN PRODUCTION.
-DEBUG = get_bool_from_env("PAPERLESS_DEBUG", "NO")
+DEBUG = __get_boolean("PAPERLESS_DEBUG", "NO")
 
 
 ###############################################################################
@@ -62,21 +286,21 @@ DEBUG = get_bool_from_env("PAPERLESS_DEBUG", "NO")
 
 BASE_DIR: Path = Path(__file__).resolve().parent.parent.parent
 
-STATIC_ROOT = get_path_from_env("PAPERLESS_STATICDIR", BASE_DIR.parent / "static")
+STATIC_ROOT = __get_path("PAPERLESS_STATICDIR", BASE_DIR.parent / "static")
 
-MEDIA_ROOT = get_path_from_env("PAPERLESS_MEDIA_ROOT", BASE_DIR.parent / "media")
+MEDIA_ROOT = __get_path("PAPERLESS_MEDIA_ROOT", BASE_DIR.parent / "media")
 ORIGINALS_DIR = MEDIA_ROOT / "documents" / "originals"
 ARCHIVE_DIR = MEDIA_ROOT / "documents" / "archive"
 THUMBNAIL_DIR = MEDIA_ROOT / "documents" / "thumbnails"
 SHARE_LINK_BUNDLE_DIR = MEDIA_ROOT / "documents" / "share_link_bundles"
 
-DATA_DIR = get_path_from_env("PAPERLESS_DATA_DIR", BASE_DIR.parent / "data")
+DATA_DIR = __get_path("PAPERLESS_DATA_DIR", BASE_DIR.parent / "data")
 
-NLTK_DIR = get_path_from_env("PAPERLESS_NLTK_DIR", "/usr/share/nltk_data")
+NLTK_DIR = __get_path("PAPERLESS_NLTK_DIR", "/usr/share/nltk_data")
 
 # Check deprecated setting first
 EMPTY_TRASH_DIR = (
-    get_path_from_env("PAPERLESS_TRASH_DIR", os.getenv("PAPERLESS_EMPTY_TRASH_DIR"))
+    __get_path("PAPERLESS_TRASH_DIR", os.getenv("PAPERLESS_EMPTY_TRASH_DIR"))
     if os.getenv("PAPERLESS_TRASH_DIR") or os.getenv("PAPERLESS_EMPTY_TRASH_DIR")
     else None
 )
@@ -85,21 +309,21 @@ EMPTY_TRASH_DIR = (
 # threads.
 MEDIA_LOCK = MEDIA_ROOT / "media.lock"
 INDEX_DIR = DATA_DIR / "index"
-MODEL_FILE = get_path_from_env(
+MODEL_FILE = __get_path(
     "PAPERLESS_MODEL_FILE",
     DATA_DIR / "classification_model.pickle",
 )
 LLM_INDEX_DIR = DATA_DIR / "llm_index"
 
-LOGGING_DIR = get_path_from_env("PAPERLESS_LOGGING_DIR", DATA_DIR / "log")
+LOGGING_DIR = __get_path("PAPERLESS_LOGGING_DIR", DATA_DIR / "log")
 
-CONSUMPTION_DIR = get_path_from_env(
+CONSUMPTION_DIR = __get_path(
     "PAPERLESS_CONSUMPTION_DIR",
     BASE_DIR.parent / "consume",
 )
 
 # This will be created if it doesn't exist
-SCRATCH_DIR = get_path_from_env(
+SCRATCH_DIR = __get_path(
     "PAPERLESS_SCRATCH_DIR",
     Path(tempfile.gettempdir()) / "paperless",
 )
@@ -108,7 +332,7 @@ SCRATCH_DIR = get_path_from_env(
 # Application Definition                                                      #
 ###############################################################################
 
-env_apps = get_list_from_env("PAPERLESS_APPS")
+env_apps = __get_list("PAPERLESS_APPS")
 
 INSTALLED_APPS = [
     "whitenoise.runserver_nostatic",
@@ -155,7 +379,7 @@ REST_FRAMEWORK = {
     "DEFAULT_VERSION": "10",  # match src-ui/src/environments/environment.prod.ts
     # Make sure these are ordered and that the most recent version appears
     # last. See api.md#api-versioning when adding new versions.
-    "ALLOWED_VERSIONS": ["9", "10"],
+    "ALLOWED_VERSIONS": ["2", "3", "4", "5", "6", "7", "8", "9", "10"],
     # DRF Spectacular default schema
     "DEFAULT_SCHEMA_CLASS": "drf_spectacular.openapi.AutoSchema",
 }
@@ -181,7 +405,7 @@ MIDDLEWARE = [
 ]
 
 # Optional to enable compression
-if get_bool_from_env("PAPERLESS_ENABLE_COMPRESSION", "yes"):  # pragma: no cover
+if __get_boolean("PAPERLESS_ENABLE_COMPRESSION", "yes"):  # pragma: no cover
     MIDDLEWARE.insert(0, "compression_middleware.middleware.CompressionMiddleware")
 
 # Workaround to not compress streaming responses (e.g. chat).
@@ -200,8 +424,20 @@ CompressionMiddleware.process_response = patched_process_response
 ROOT_URLCONF = "paperless.urls"
 
 
+def _parse_base_paths() -> tuple[str, str, str, str, str]:
+    script_name = os.getenv("PAPERLESS_FORCE_SCRIPT_NAME")
+    base_url = (script_name or "") + "/"
+    login_url = base_url + "accounts/login/"
+    login_redirect_url = base_url + "dashboard"
+    logout_redirect_url = os.getenv(
+        "PAPERLESS_LOGOUT_REDIRECT_URL",
+        login_url + "?loggedout=1",
+    )
+    return script_name, base_url, login_url, login_redirect_url, logout_redirect_url
+
+
 FORCE_SCRIPT_NAME, BASE_URL, LOGIN_URL, LOGIN_REDIRECT_URL, LOGOUT_REDIRECT_URL = (
-    parse_hosting_settings()
+    _parse_base_paths()
 )
 
 # DRF Spectacular settings
@@ -235,7 +471,7 @@ STORAGES = {
     "default": {"BACKEND": "django.core.files.storage.FileSystemStorage"},
 }
 
-_CELERY_REDIS_URL, _CHANNELS_REDIS_URL = parse_redis_url(
+_CELERY_REDIS_URL, _CHANNELS_REDIS_URL = _parse_redis_url(
     os.getenv("PAPERLESS_REDIS", None),
 )
 _REDIS_KEY_PREFIX = os.getenv("PAPERLESS_REDIS_PREFIX", "")
@@ -284,8 +520,8 @@ EMAIL_PORT: Final[int] = int(os.getenv("PAPERLESS_EMAIL_PORT", 25))
 EMAIL_HOST_USER: Final[str] = os.getenv("PAPERLESS_EMAIL_HOST_USER", "")
 EMAIL_HOST_PASSWORD: Final[str] = os.getenv("PAPERLESS_EMAIL_HOST_PASSWORD", "")
 DEFAULT_FROM_EMAIL: Final[str] = os.getenv("PAPERLESS_EMAIL_FROM", EMAIL_HOST_USER)
-EMAIL_USE_TLS: Final[bool] = get_bool_from_env("PAPERLESS_EMAIL_USE_TLS")
-EMAIL_USE_SSL: Final[bool] = get_bool_from_env("PAPERLESS_EMAIL_USE_SSL")
+EMAIL_USE_TLS: Final[bool] = __get_boolean("PAPERLESS_EMAIL_USE_TLS")
+EMAIL_USE_SSL: Final[bool] = __get_boolean("PAPERLESS_EMAIL_USE_SSL")
 EMAIL_SUBJECT_PREFIX: Final[str] = "[Paperless-ngx] "
 EMAIL_TIMEOUT = 30.0
 EMAIL_ENABLED = EMAIL_HOST != "localhost" or EMAIL_HOST_USER != ""
@@ -310,22 +546,20 @@ ACCOUNT_DEFAULT_HTTP_PROTOCOL = os.getenv(
 )
 
 ACCOUNT_ADAPTER = "paperless.adapter.CustomAccountAdapter"
-ACCOUNT_ALLOW_SIGNUPS = get_bool_from_env("PAPERLESS_ACCOUNT_ALLOW_SIGNUPS")
-ACCOUNT_DEFAULT_GROUPS = get_list_from_env("PAPERLESS_ACCOUNT_DEFAULT_GROUPS")
+ACCOUNT_ALLOW_SIGNUPS = __get_boolean("PAPERLESS_ACCOUNT_ALLOW_SIGNUPS")
+ACCOUNT_DEFAULT_GROUPS = __get_list("PAPERLESS_ACCOUNT_DEFAULT_GROUPS")
 
 SOCIALACCOUNT_ADAPTER = "paperless.adapter.CustomSocialAccountAdapter"
-SOCIALACCOUNT_ALLOW_SIGNUPS = get_bool_from_env(
+SOCIALACCOUNT_ALLOW_SIGNUPS = __get_boolean(
     "PAPERLESS_SOCIALACCOUNT_ALLOW_SIGNUPS",
     "yes",
 )
-SOCIALACCOUNT_AUTO_SIGNUP = get_bool_from_env("PAPERLESS_SOCIAL_AUTO_SIGNUP")
+SOCIALACCOUNT_AUTO_SIGNUP = __get_boolean("PAPERLESS_SOCIAL_AUTO_SIGNUP")
 SOCIALACCOUNT_PROVIDERS = json.loads(
     os.getenv("PAPERLESS_SOCIALACCOUNT_PROVIDERS", "{}"),
 )
-SOCIAL_ACCOUNT_DEFAULT_GROUPS = get_list_from_env(
-    "PAPERLESS_SOCIAL_ACCOUNT_DEFAULT_GROUPS",
-)
-SOCIAL_ACCOUNT_SYNC_GROUPS = get_bool_from_env("PAPERLESS_SOCIAL_ACCOUNT_SYNC_GROUPS")
+SOCIAL_ACCOUNT_DEFAULT_GROUPS = __get_list("PAPERLESS_SOCIAL_ACCOUNT_DEFAULT_GROUPS")
+SOCIAL_ACCOUNT_SYNC_GROUPS = __get_boolean("PAPERLESS_SOCIAL_ACCOUNT_SYNC_GROUPS")
 SOCIAL_ACCOUNT_SYNC_GROUPS_CLAIM: Final[str] = os.getenv(
     "PAPERLESS_SOCIAL_ACCOUNT_SYNC_GROUPS_CLAIM",
     "groups",
@@ -337,8 +571,8 @@ MFA_TOTP_ISSUER = "Paperless-ngx"
 
 ACCOUNT_EMAIL_SUBJECT_PREFIX = "[Paperless-ngx] "
 
-DISABLE_REGULAR_LOGIN = get_bool_from_env("PAPERLESS_DISABLE_REGULAR_LOGIN")
-REDIRECT_LOGIN_TO_SSO = get_bool_from_env("PAPERLESS_REDIRECT_LOGIN_TO_SSO")
+DISABLE_REGULAR_LOGIN = __get_boolean("PAPERLESS_DISABLE_REGULAR_LOGIN")
+REDIRECT_LOGIN_TO_SSO = __get_boolean("PAPERLESS_REDIRECT_LOGIN_TO_SSO")
 
 AUTO_LOGIN_USERNAME = os.getenv("PAPERLESS_AUTO_LOGIN_USERNAME")
 
@@ -351,15 +585,12 @@ ACCOUNT_EMAIL_VERIFICATION = (
     )
 )
 
-ACCOUNT_EMAIL_UNKNOWN_ACCOUNTS = get_bool_from_env(
+ACCOUNT_EMAIL_UNKNOWN_ACCOUNTS = __get_boolean(
     "PAPERLESS_ACCOUNT_EMAIL_UNKNOWN_ACCOUNTS",
     "True",
 )
 
-ACCOUNT_SESSION_REMEMBER = get_bool_from_env(
-    "PAPERLESS_ACCOUNT_SESSION_REMEMBER",
-    "True",
-)
+ACCOUNT_SESSION_REMEMBER = __get_boolean("PAPERLESS_ACCOUNT_SESSION_REMEMBER", "True")
 SESSION_EXPIRE_AT_BROWSER_CLOSE = not ACCOUNT_SESSION_REMEMBER
 SESSION_COOKIE_AGE = int(
     os.getenv("PAPERLESS_SESSION_COOKIE_AGE", 60 * 60 * 24 * 7 * 3),
@@ -376,8 +607,8 @@ if AUTO_LOGIN_USERNAME:
 
 def _parse_remote_user_settings() -> str:
     global MIDDLEWARE, AUTHENTICATION_BACKENDS, REST_FRAMEWORK
-    enable = get_bool_from_env("PAPERLESS_ENABLE_HTTP_REMOTE_USER")
-    enable_api = get_bool_from_env("PAPERLESS_ENABLE_HTTP_REMOTE_USER_API")
+    enable = __get_boolean("PAPERLESS_ENABLE_HTTP_REMOTE_USER")
+    enable_api = __get_boolean("PAPERLESS_ENABLE_HTTP_REMOTE_USER_API")
     if enable or enable_api:
         MIDDLEWARE.append("paperless.auth.HttpRemoteUserMiddleware")
         AUTHENTICATION_BACKENDS.insert(
@@ -405,16 +636,16 @@ HTTP_REMOTE_USER_HEADER_NAME = _parse_remote_user_settings()
 X_FRAME_OPTIONS = "SAMEORIGIN"
 
 # The next 3 settings can also be set using just PAPERLESS_URL
-CSRF_TRUSTED_ORIGINS = get_list_from_env("PAPERLESS_CSRF_TRUSTED_ORIGINS")
+CSRF_TRUSTED_ORIGINS = __get_list("PAPERLESS_CSRF_TRUSTED_ORIGINS")
 
 if DEBUG:
     # Allow access from the angular development server during debugging
     CSRF_TRUSTED_ORIGINS.append("http://localhost:4200")
 
 # We allow CORS from localhost:8000
-CORS_ALLOWED_ORIGINS = get_list_from_env(
+CORS_ALLOWED_ORIGINS = __get_list(
     "PAPERLESS_CORS_ALLOWED_HOSTS",
-    default=["http://localhost:8000"],
+    ["http://localhost:8000"],
 )
 
 if DEBUG:
@@ -427,7 +658,7 @@ CORS_EXPOSE_HEADERS = [
     "Content-Disposition",
 ]
 
-ALLOWED_HOSTS = get_list_from_env("PAPERLESS_ALLOWED_HOSTS", default=["*"])
+ALLOWED_HOSTS = __get_list("PAPERLESS_ALLOWED_HOSTS", ["*"])
 if ALLOWED_HOSTS != ["*"]:
     # always allow localhost. Necessary e.g. for healthcheck in docker.
     ALLOWED_HOSTS.append("localhost")
@@ -447,10 +678,10 @@ def _parse_paperless_url():
 PAPERLESS_URL = _parse_paperless_url()
 
 # For use with trusted proxies
-TRUSTED_PROXIES = get_list_from_env("PAPERLESS_TRUSTED_PROXIES")
+TRUSTED_PROXIES = __get_list("PAPERLESS_TRUSTED_PROXIES")
 
-USE_X_FORWARDED_HOST = get_bool_from_env("PAPERLESS_USE_X_FORWARD_HOST", "false")
-USE_X_FORWARDED_PORT = get_bool_from_env("PAPERLESS_USE_X_FORWARD_PORT", "false")
+USE_X_FORWARDED_HOST = __get_boolean("PAPERLESS_USE_X_FORWARD_HOST", "false")
+USE_X_FORWARDED_PORT = __get_boolean("PAPERLESS_USE_X_FORWARD_PORT", "false")
 SECURE_PROXY_SSL_HEADER = (
     tuple(json.loads(os.environ["PAPERLESS_PROXY_SSL_HEADER"]))
     if "PAPERLESS_PROXY_SSL_HEADER" in os.environ
@@ -493,7 +724,7 @@ CSRF_COOKIE_NAME = f"{COOKIE_PREFIX}csrftoken"
 SESSION_COOKIE_NAME = f"{COOKIE_PREFIX}sessionid"
 LANGUAGE_COOKIE_NAME = f"{COOKIE_PREFIX}django_language"
 
-EMAIL_CERTIFICATE_FILE = get_path_from_env("PAPERLESS_EMAIL_CERTIFICATE_LOCATION")
+EMAIL_CERTIFICATE_FILE = __get_optional_path("PAPERLESS_EMAIL_CERTIFICATE_LOCATION")
 
 
 ###############################################################################
@@ -644,7 +875,7 @@ CELERY_BROKER_URL = _CELERY_REDIS_URL
 CELERY_TIMEZONE = TIME_ZONE
 
 CELERY_WORKER_HIJACK_ROOT_LOGGER = False
-CELERY_WORKER_CONCURRENCY: Final[int] = get_int_from_env("PAPERLESS_TASK_WORKERS", 1)
+CELERY_WORKER_CONCURRENCY: Final[int] = __get_int("PAPERLESS_TASK_WORKERS", 1)
 TASK_WORKERS = CELERY_WORKER_CONCURRENCY
 CELERY_WORKER_MAX_TASKS_PER_CHILD = 1
 CELERY_WORKER_SEND_TASK_EVENTS = True
@@ -657,7 +888,7 @@ CELERY_BROKER_TRANSPORT_OPTIONS = {
 }
 
 CELERY_TASK_TRACK_STARTED = True
-CELERY_TASK_TIME_LIMIT: Final[int] = get_int_from_env("PAPERLESS_WORKER_TIMEOUT", 1800)
+CELERY_TASK_TIME_LIMIT: Final[int] = __get_int("PAPERLESS_WORKER_TIMEOUT", 1800)
 
 CELERY_RESULT_EXTENDED = True
 CELERY_RESULT_BACKEND = "django-db"
@@ -669,7 +900,7 @@ CELERY_TASK_SERIALIZER = "pickle"
 CELERY_ACCEPT_CONTENT = ["application/json", "application/x-python-serialize"]
 
 # https://docs.celeryq.dev/en/stable/userguide/configuration.html#beat-schedule
-CELERY_BEAT_SCHEDULE = parse_beat_schedule()
+CELERY_BEAT_SCHEDULE = _parse_beat_schedule()
 
 # https://docs.celeryq.dev/en/stable/userguide/configuration.html#beat-schedule-filename
 CELERY_BEAT_SCHEDULE_FILENAME = str(DATA_DIR / "celerybeat-schedule.db")
@@ -677,14 +908,14 @@ CELERY_BEAT_SCHEDULE_FILENAME = str(DATA_DIR / "celerybeat-schedule.db")
 
 # Cachalot: Database read cache.
 def _parse_cachalot_settings():
-    ttl = get_int_from_env("PAPERLESS_READ_CACHE_TTL", 3600)
+    ttl = __get_int("PAPERLESS_READ_CACHE_TTL", 3600)
     ttl = min(ttl, 31536000) if ttl > 0 else 3600
-    _, redis_url = parse_redis_url(
+    _, redis_url = _parse_redis_url(
         os.getenv("PAPERLESS_READ_CACHE_REDIS_URL", _CHANNELS_REDIS_URL),
     )
     result = {
         "CACHALOT_CACHE": "read-cache",
-        "CACHALOT_ENABLED": get_bool_from_env(
+        "CACHALOT_ENABLED": __get_boolean(
             "PAPERLESS_DB_READ_CACHE_ENABLED",
             default="no",
         ),
@@ -769,9 +1000,9 @@ CONSUMER_POLLING_INTERVAL = float(os.getenv("PAPERLESS_CONSUMER_POLLING_INTERVAL
 
 CONSUMER_STABILITY_DELAY = float(os.getenv("PAPERLESS_CONSUMER_STABILITY_DELAY", 5))
 
-CONSUMER_DELETE_DUPLICATES = get_bool_from_env("PAPERLESS_CONSUMER_DELETE_DUPLICATES")
+CONSUMER_DELETE_DUPLICATES = __get_boolean("PAPERLESS_CONSUMER_DELETE_DUPLICATES")
 
-CONSUMER_RECURSIVE = get_bool_from_env("PAPERLESS_CONSUMER_RECURSIVE")
+CONSUMER_RECURSIVE = __get_boolean("PAPERLESS_CONSUMER_RECURSIVE")
 
 # Ignore regex patterns, matched against filename only
 CONSUMER_IGNORE_PATTERNS = list(
@@ -793,13 +1024,13 @@ CONSUMER_IGNORE_DIRS = list(
     ),
 )
 
-CONSUMER_SUBDIRS_AS_TAGS = get_bool_from_env("PAPERLESS_CONSUMER_SUBDIRS_AS_TAGS")
+CONSUMER_SUBDIRS_AS_TAGS = __get_boolean("PAPERLESS_CONSUMER_SUBDIRS_AS_TAGS")
 
-CONSUMER_ENABLE_BARCODES: Final[bool] = get_bool_from_env(
+CONSUMER_ENABLE_BARCODES: Final[bool] = __get_boolean(
     "PAPERLESS_CONSUMER_ENABLE_BARCODES",
 )
 
-CONSUMER_BARCODE_TIFF_SUPPORT: Final[bool] = get_bool_from_env(
+CONSUMER_BARCODE_TIFF_SUPPORT: Final[bool] = __get_boolean(
     "PAPERLESS_CONSUMER_BARCODE_TIFF_SUPPORT",
 )
 
@@ -808,7 +1039,7 @@ CONSUMER_BARCODE_STRING: Final[str] = os.getenv(
     "PATCHT",
 )
 
-CONSUMER_ENABLE_ASN_BARCODE: Final[bool] = get_bool_from_env(
+CONSUMER_ENABLE_ASN_BARCODE: Final[bool] = __get_boolean(
     "PAPERLESS_CONSUMER_ENABLE_ASN_BARCODE",
 )
 
@@ -817,26 +1048,23 @@ CONSUMER_ASN_BARCODE_PREFIX: Final[str] = os.getenv(
     "ASN",
 )
 
-CONSUMER_BARCODE_UPSCALE: Final[float] = get_float_from_env(
+CONSUMER_BARCODE_UPSCALE: Final[float] = __get_float(
     "PAPERLESS_CONSUMER_BARCODE_UPSCALE",
     0.0,
 )
 
-CONSUMER_BARCODE_DPI: Final[int] = get_int_from_env(
-    "PAPERLESS_CONSUMER_BARCODE_DPI",
-    300,
-)
+CONSUMER_BARCODE_DPI: Final[int] = __get_int("PAPERLESS_CONSUMER_BARCODE_DPI", 300)
 
-CONSUMER_BARCODE_MAX_PAGES: Final[int] = get_int_from_env(
+CONSUMER_BARCODE_MAX_PAGES: Final[int] = __get_int(
     "PAPERLESS_CONSUMER_BARCODE_MAX_PAGES",
     0,
 )
 
-CONSUMER_BARCODE_RETAIN_SPLIT_PAGES = get_bool_from_env(
+CONSUMER_BARCODE_RETAIN_SPLIT_PAGES = __get_boolean(
     "PAPERLESS_CONSUMER_BARCODE_RETAIN_SPLIT_PAGES",
 )
 
-CONSUMER_ENABLE_TAG_BARCODE: Final[bool] = get_bool_from_env(
+CONSUMER_ENABLE_TAG_BARCODE: Final[bool] = __get_boolean(
     "PAPERLESS_CONSUMER_ENABLE_TAG_BARCODE",
 )
 
@@ -849,11 +1077,11 @@ CONSUMER_TAG_BARCODE_MAPPING = dict(
     ),
 )
 
-CONSUMER_TAG_BARCODE_SPLIT: Final[bool] = get_bool_from_env(
+CONSUMER_TAG_BARCODE_SPLIT: Final[bool] = __get_boolean(
     "PAPERLESS_CONSUMER_TAG_BARCODE_SPLIT",
 )
 
-CONSUMER_ENABLE_COLLATE_DOUBLE_SIDED: Final[bool] = get_bool_from_env(
+CONSUMER_ENABLE_COLLATE_DOUBLE_SIDED: Final[bool] = __get_boolean(
     "PAPERLESS_CONSUMER_ENABLE_COLLATE_DOUBLE_SIDED",
 )
 
@@ -862,13 +1090,13 @@ CONSUMER_COLLATE_DOUBLE_SIDED_SUBDIR_NAME: Final[str] = os.getenv(
     "double-sided",
 )
 
-CONSUMER_COLLATE_DOUBLE_SIDED_TIFF_SUPPORT: Final[bool] = get_bool_from_env(
+CONSUMER_COLLATE_DOUBLE_SIDED_TIFF_SUPPORT: Final[bool] = __get_boolean(
     "PAPERLESS_CONSUMER_COLLATE_DOUBLE_SIDED_TIFF_SUPPORT",
 )
 
 CONSUMER_PDF_RECOVERABLE_MIME_TYPES = ("application/octet-stream",)
 
-OCR_PAGES = get_int_from_env("PAPERLESS_OCR_PAGES")
+OCR_PAGES = __get_optional_int("PAPERLESS_OCR_PAGES")
 
 # The default language that tesseract will attempt to use when parsing
 # documents.  It should be a 3-letter language code consistent with ISO 639.
@@ -882,20 +1110,20 @@ OCR_MODE = os.getenv("PAPERLESS_OCR_MODE", "skip")
 
 OCR_SKIP_ARCHIVE_FILE = os.getenv("PAPERLESS_OCR_SKIP_ARCHIVE_FILE", "never")
 
-OCR_IMAGE_DPI = get_int_from_env("PAPERLESS_OCR_IMAGE_DPI")
+OCR_IMAGE_DPI = __get_optional_int("PAPERLESS_OCR_IMAGE_DPI")
 
 OCR_CLEAN = os.getenv("PAPERLESS_OCR_CLEAN", "clean")
 
-OCR_DESKEW: Final[bool] = get_bool_from_env("PAPERLESS_OCR_DESKEW", "true")
+OCR_DESKEW: Final[bool] = __get_boolean("PAPERLESS_OCR_DESKEW", "true")
 
-OCR_ROTATE_PAGES: Final[bool] = get_bool_from_env("PAPERLESS_OCR_ROTATE_PAGES", "true")
+OCR_ROTATE_PAGES: Final[bool] = __get_boolean("PAPERLESS_OCR_ROTATE_PAGES", "true")
 
-OCR_ROTATE_PAGES_THRESHOLD: Final[float] = get_float_from_env(
+OCR_ROTATE_PAGES_THRESHOLD: Final[float] = __get_float(
     "PAPERLESS_OCR_ROTATE_PAGES_THRESHOLD",
     12.0,
 )
 
-OCR_MAX_IMAGE_PIXELS: Final[int | None] = get_int_from_env(
+OCR_MAX_IMAGE_PIXELS: Final[int | None] = __get_optional_int(
     "PAPERLESS_OCR_MAX_IMAGE_PIXELS",
 )
 
@@ -906,7 +1134,7 @@ OCR_COLOR_CONVERSION_STRATEGY = os.getenv(
 
 OCR_USER_ARGS = os.getenv("PAPERLESS_OCR_USER_ARGS")
 
-MAX_IMAGE_PIXELS: Final[int | None] = get_int_from_env(
+MAX_IMAGE_PIXELS: Final[int | None] = __get_optional_int(
     "PAPERLESS_MAX_IMAGE_PIXELS",
 )
 
@@ -921,7 +1149,7 @@ CONVERT_MEMORY_LIMIT = os.getenv("PAPERLESS_CONVERT_MEMORY_LIMIT")
 GS_BINARY = os.getenv("PAPERLESS_GS_BINARY", "gs")
 
 # Fallback layout for .eml consumption
-EMAIL_PARSE_DEFAULT_LAYOUT = get_int_from_env(
+EMAIL_PARSE_DEFAULT_LAYOUT = __get_int(
     "PAPERLESS_EMAIL_PARSE_DEFAULT_LAYOUT",
     1,  # MailRule.PdfLayout.TEXT_HTML but that can't be imported here
 )
@@ -935,9 +1163,23 @@ DATE_ORDER = os.getenv("PAPERLESS_DATE_ORDER", "DMY")
 FILENAME_DATE_ORDER = os.getenv("PAPERLESS_FILENAME_DATE_ORDER")
 
 
+def _parse_dateparser_languages(languages: str | None):
+    language_list = languages.split("+") if languages else []
+    # There is an unfixed issue in zh-Hant and zh-Hans locales in the dateparser lib.
+    # See: https://github.com/scrapinghub/dateparser/issues/875
+    for index, language in enumerate(language_list):
+        if language.startswith("zh-") and "zh" not in language_list:
+            logger.warning(
+                f'Chinese locale detected: {language}. dateparser might fail to parse some dates with this locale, so Chinese ("zh") will be used as a fallback.',
+            )
+            language_list.append("zh")
+
+    return list(LocaleDataLoader().get_locale_map(locales=language_list))
+
+
 # If not set, we will infer it at runtime
 DATE_PARSER_LANGUAGES = (
-    parse_dateparser_languages(
+    _parse_dateparser_languages(
         os.getenv("PAPERLESS_DATE_PARSER_LANGUAGES"),
     )
     if os.getenv("PAPERLESS_DATE_PARSER_LANGUAGES")
@@ -948,7 +1190,7 @@ DATE_PARSER_LANGUAGES = (
 # Maximum number of dates taken from document start to end to show as suggestions for
 # `created` date in the frontend. Duplicates are removed, which can result in
 # fewer dates shown.
-NUMBER_OF_SUGGESTED_DATES = get_int_from_env("PAPERLESS_NUMBER_OF_SUGGESTED_DATES", 3)
+NUMBER_OF_SUGGESTED_DATES = __get_int("PAPERLESS_NUMBER_OF_SUGGESTED_DATES", 3)
 
 # Specify the filename format for out files
 FILENAME_FORMAT = os.getenv("PAPERLESS_FILENAME_FORMAT")
@@ -956,7 +1198,7 @@ FILENAME_FORMAT = os.getenv("PAPERLESS_FILENAME_FORMAT")
 # If this is enabled, variables in filename format will resolve to
 # empty-string instead of 'none'.
 # Directories with 'empty names' are omitted, too.
-FILENAME_FORMAT_REMOVE_NONE = get_bool_from_env(
+FILENAME_FORMAT_REMOVE_NONE = __get_boolean(
     "PAPERLESS_FILENAME_FORMAT_REMOVE_NONE",
     "NO",
 )
@@ -967,7 +1209,7 @@ THUMBNAIL_FONT_NAME = os.getenv(
 )
 
 # Tika settings
-TIKA_ENABLED = get_bool_from_env("PAPERLESS_TIKA_ENABLED", "NO")
+TIKA_ENABLED = __get_boolean("PAPERLESS_TIKA_ENABLED", "NO")
 TIKA_ENDPOINT = os.getenv("PAPERLESS_TIKA_ENDPOINT", "http://localhost:9998")
 TIKA_GOTENBERG_ENDPOINT = os.getenv(
     "PAPERLESS_TIKA_GOTENBERG_ENDPOINT",
@@ -977,21 +1219,52 @@ TIKA_GOTENBERG_ENDPOINT = os.getenv(
 if TIKA_ENABLED:
     INSTALLED_APPS.append("paperless_tika.apps.PaperlessTikaConfig")
 
-AUDIT_LOG_ENABLED = get_bool_from_env("PAPERLESS_AUDIT_LOG_ENABLED", "true")
+AUDIT_LOG_ENABLED = __get_boolean("PAPERLESS_AUDIT_LOG_ENABLED", "true")
 if AUDIT_LOG_ENABLED:
     INSTALLED_APPS.append("auditlog")
     MIDDLEWARE.append("auditlog.middleware.AuditlogMiddleware")
 
 
+def _parse_ignore_dates(
+    env_ignore: str,
+    date_order: str = DATE_ORDER,
+) -> set[datetime.datetime]:
+    """
+    If the PAPERLESS_IGNORE_DATES environment variable is set, parse the
+    user provided string(s) into dates
+
+    Args:
+        env_ignore (str): The value of the environment variable, comma separated dates
+        date_order (str, optional): The format of the date strings.
+                                    Defaults to DATE_ORDER.
+
+    Returns:
+        Set[datetime.datetime]: The set of parsed date objects
+    """
+    import dateparser
+
+    ignored_dates = set()
+    for s in env_ignore.split(","):
+        d = dateparser.parse(
+            s,
+            settings={
+                "DATE_ORDER": date_order,
+            },
+        )
+        if d:
+            ignored_dates.add(d.date())
+    return ignored_dates
+
+
 # List dates that should be ignored when trying to parse date from document text
 IGNORE_DATES: set[datetime.date] = set()
 
 if os.getenv("PAPERLESS_IGNORE_DATES") is not None:
-    IGNORE_DATES = parse_ignore_dates(os.getenv("PAPERLESS_IGNORE_DATES"), DATE_ORDER)
+    IGNORE_DATES = _parse_ignore_dates(os.getenv("PAPERLESS_IGNORE_DATES"))
 
 ENABLE_UPDATE_CHECK = os.getenv("PAPERLESS_ENABLE_UPDATE_CHECK", "default")
 if ENABLE_UPDATE_CHECK != "default":
-    ENABLE_UPDATE_CHECK = get_bool_from_env("PAPERLESS_ENABLE_UPDATE_CHECK")
+    ENABLE_UPDATE_CHECK = __get_boolean("PAPERLESS_ENABLE_UPDATE_CHECK")
 
 APP_TITLE = os.getenv("PAPERLESS_APP_TITLE", None)
 APP_LOGO = os.getenv("PAPERLESS_APP_LOGO", None)
@@ -1036,7 +1309,7 @@ def _get_nltk_language_setting(ocr_lang: str) -> str | None:
     return iso_code_to_nltk.get(ocr_lang)
 
 
-NLTK_ENABLED: Final[bool] = get_bool_from_env("PAPERLESS_ENABLE_NLTK", "yes")
+NLTK_ENABLED: Final[bool] = __get_boolean("PAPERLESS_ENABLE_NLTK", "yes")
 
 NLTK_LANGUAGE: str | None = _get_nltk_language_setting(OCR_LANGUAGE)
 
@@ -1045,7 +1318,7 @@ NLTK_LANGUAGE: str | None = _get_nltk_language_setting(OCR_LANGUAGE)
 ###############################################################################
 
 EMAIL_GNUPG_HOME: Final[str | None] = os.getenv("PAPERLESS_EMAIL_GNUPG_HOME")
-EMAIL_ENABLE_GPG_DECRYPTOR: Final[bool] = get_bool_from_env(
+EMAIL_ENABLE_GPG_DECRYPTOR: Final[bool] = __get_boolean(
     "PAPERLESS_ENABLE_GPG_DECRYPTOR",
 )
 
@@ -1053,7 +1326,7 @@ EMAIL_ENABLE_GPG_DECRYPTOR: Final[bool] = get_bool_from_env(
 ###############################################################################
 # Soft Delete                                                                 #
 ###############################################################################
-EMPTY_TRASH_DELAY = max(get_int_from_env("PAPERLESS_EMPTY_TRASH_DELAY", 30), 1)
+EMPTY_TRASH_DELAY = max(__get_int("PAPERLESS_EMPTY_TRASH_DELAY", 30), 1)
 
 
 ###############################################################################
@@ -1078,17 +1351,21 @@ OUTLOOK_OAUTH_ENABLED = bool(
 ###############################################################################
 # Webhooks
 ###############################################################################
-WEBHOOKS_ALLOWED_SCHEMES = {
+WEBHOOKS_ALLOWED_SCHEMES = set(
     s.lower()
-    for s in get_list_from_env(
+    for s in __get_list(
         "PAPERLESS_WEBHOOKS_ALLOWED_SCHEMES",
-        default=["http", "https"],
+        ["http", "https"],
     )
-}
-WEBHOOKS_ALLOWED_PORTS = {
-    int(p) for p in get_list_from_env("PAPERLESS_WEBHOOKS_ALLOWED_PORTS", default=[])
-}
-WEBHOOKS_ALLOW_INTERNAL_REQUESTS = get_bool_from_env(
+)
+WEBHOOKS_ALLOWED_PORTS = set(
+    int(p)
+    for p in __get_list(
+        "PAPERLESS_WEBHOOKS_ALLOWED_PORTS",
+        [],
+    )
+)
+WEBHOOKS_ALLOW_INTERNAL_REQUESTS = __get_boolean(
     "PAPERLESS_WEBHOOKS_ALLOW_INTERNAL_REQUESTS",
     "true",
 )
@@ -1103,7 +1380,7 @@ REMOTE_OCR_ENDPOINT = os.getenv("PAPERLESS_REMOTE_OCR_ENDPOINT")
 ################################################################################
 # AI Settings                                                                  #
 ################################################################################
-AI_ENABLED = get_bool_from_env("PAPERLESS_AI_ENABLED", "NO")
+AI_ENABLED = __get_boolean("PAPERLESS_AI_ENABLED", "NO")
 LLM_EMBEDDING_BACKEND = os.getenv(
     "PAPERLESS_AI_LLM_EMBEDDING_BACKEND",
 )  # "huggingface" or "openai"

src/paperless/settings/custom.py

@@ -1,191 +1,11 @@
-import datetime
-import logging
 import os
 from pathlib import Path
 from typing import Any
 
-from celery.schedules import crontab
-from dateparser.languages.loader import LocaleDataLoader
-
 from paperless.settings.parsers import get_choice_from_env
 from paperless.settings.parsers import get_int_from_env
 from paperless.settings.parsers import parse_dict_from_str
 
-logger = logging.getLogger(__name__)
-
-
-def parse_hosting_settings() -> tuple[str | None, str, str, str, str]:
-    script_name = os.getenv("PAPERLESS_FORCE_SCRIPT_NAME")
-    base_url = (script_name or "") + "/"
-    login_url = base_url + "accounts/login/"
-    login_redirect_url = base_url + "dashboard"
-    logout_redirect_url = os.getenv(
-        "PAPERLESS_LOGOUT_REDIRECT_URL",
-        login_url + "?loggedout=1",
-    )
-    return script_name, base_url, login_url, login_redirect_url, logout_redirect_url
-
-
-def parse_redis_url(env_redis: str | None) -> tuple[str, str]:
-    """
-    Gets the Redis information from the environment or a default and handles
-    converting from incompatible django_channels and celery formats.
-
-    Returns a tuple of (celery_url, channels_url)
-    """
-
-    # Not set, return a compatible default
-    if env_redis is None:
-        return ("redis://localhost:6379", "redis://localhost:6379")
-
-    if "unix" in env_redis.lower():
-        # channels_redis socket format, looks like:
-        # "unix:///path/to/redis.sock"
-        _, path = env_redis.split(":", maxsplit=1)
-        # Optionally setting a db number
-        if "?db=" in env_redis:
-            path, number = path.split("?db=")
-            return (f"redis+socket:{path}?virtual_host={number}", env_redis)
-        else:
-            return (f"redis+socket:{path}", env_redis)
-
-    elif "+socket" in env_redis.lower():
-        # celery socket style, looks like:
-        # "redis+socket:///path/to/redis.sock"
-        _, path = env_redis.split(":", maxsplit=1)
-        if "?virtual_host=" in env_redis:
-            # Virtual host (aka db number)
-            path, number = path.split("?virtual_host=")
-            return (env_redis, f"unix:{path}?db={number}")
-        else:
-            return (env_redis, f"unix:{path}")
-
-    # Not a socket
-    return (env_redis, env_redis)
-
-
-def parse_beat_schedule() -> dict:
-    """
-    Configures the scheduled tasks, according to default or
-    environment variables.  Task expiration is configured so the task will
-    expire (and not run), shortly before the default frequency will put another
-    of the same task into the queue
-
-
-    https://docs.celeryq.dev/en/stable/userguide/periodic-tasks.html#beat-entries
-    https://docs.celeryq.dev/en/latest/userguide/calling.html#expiration
-    """
-    schedule = {}
-    tasks = [
-        {
-            "name": "Check all e-mail accounts",
-            "env_key": "PAPERLESS_EMAIL_TASK_CRON",
-            # Default every ten minutes
-            "env_default": "*/10 * * * *",
-            "task": "paperless_mail.tasks.process_mail_accounts",
-            "options": {
-                # 1 minute before default schedule sends again
-                "expires": 9.0 * 60.0,
-            },
-        },
-        {
-            "name": "Train the classifier",
-            "env_key": "PAPERLESS_TRAIN_TASK_CRON",
-            # Default hourly at 5 minutes past the hour
-            "env_default": "5 */1 * * *",
-            "task": "documents.tasks.train_classifier",
-            "options": {
-                # 1 minute before default schedule sends again
-                "expires": 59.0 * 60.0,
-            },
-        },
-        {
-            "name": "Optimize the index",
-            "env_key": "PAPERLESS_INDEX_TASK_CRON",
-            # Default daily at midnight
-            "env_default": "0 0 * * *",
-            "task": "documents.tasks.index_optimize",
-            "options": {
-                # 1 hour before default schedule sends again
-                "expires": 23.0 * 60.0 * 60.0,
-            },
-        },
-        {
-            "name": "Perform sanity check",
-            "env_key": "PAPERLESS_SANITY_TASK_CRON",
-            # Default Sunday at 00:30
-            "env_default": "30 0 * * sun",
-            "task": "documents.tasks.sanity_check",
-            "options": {
-                # 1 hour before default schedule sends again
-                "expires": ((7.0 * 24.0) - 1.0) * 60.0 * 60.0,
-            },
-        },
-        {
-            "name": "Empty trash",
-            "env_key": "PAPERLESS_EMPTY_TRASH_TASK_CRON",
-            # Default daily at 01:00
-            "env_default": "0 1 * * *",
-            "task": "documents.tasks.empty_trash",
-            "options": {
-                # 1 hour before default schedule sends again
-                "expires": 23.0 * 60.0 * 60.0,
-            },
-        },
-        {
-            "name": "Check and run scheduled workflows",
-            "env_key": "PAPERLESS_WORKFLOW_SCHEDULED_TASK_CRON",
-            # Default hourly at 5 minutes past the hour
-            "env_default": "5 */1 * * *",
-            "task": "documents.tasks.check_scheduled_workflows",
-            "options": {
-                # 1 minute before default schedule sends again
-                "expires": 59.0 * 60.0,
-            },
-        },
-        {
-            "name": "Rebuild LLM index",
-            "env_key": "PAPERLESS_LLM_INDEX_TASK_CRON",
-            # Default daily at 02:10
-            "env_default": "10 2 * * *",
-            "task": "documents.tasks.llmindex_index",
-            "options": {
-                # 1 hour before default schedule sends again
-                "expires": 23.0 * 60.0 * 60.0,
-            },
-        },
-        {
-            "name": "Cleanup expired share link bundles",
-            "env_key": "PAPERLESS_SHARE_LINK_BUNDLE_CLEANUP_CRON",
-            # Default daily at 02:00
-            "env_default": "0 2 * * *",
-            "task": "documents.tasks.cleanup_expired_share_link_bundles",
-            "options": {
-                # 1 hour before default schedule sends again
-                "expires": 23.0 * 60.0 * 60.0,
-            },
-        },
-    ]
-    for task in tasks:
-        # Either get the environment setting or use the default
-        value = os.getenv(task["env_key"], task["env_default"])
-        # Don't add disabled tasks to the schedule
-        if value == "disable":
-            continue
-        # I find https://crontab.guru/ super helpful
-        # crontab(5) format
-        #   - five time-and-date fields
-        #   - separated by at least one blank
-        minute, hour, day_month, month, day_week = value.split(" ")
-
-        schedule[task["name"]] = {
-            "task": task["task"],
-            "schedule": crontab(minute, hour, day_week, day_month, month),
-            "options": task["options"],
-        }
-
-    return schedule
-
 
 def parse_db_settings(data_dir: Path) -> dict[str, dict[str, Any]]:
     """Parse database settings from environment variables.
@@ -209,6 +29,7 @@ def parse_db_settings(data_dir: Path) -> dict[str, dict[str, Any]]:
         engine = get_choice_from_env(
             "PAPERLESS_DBENGINE",
             {"sqlite", "postgresql", "mariadb"},
+            default="sqlite",
         )
     except ValueError:
         # MariaDB users already had to set PAPERLESS_DBENGINE, so it was picked up above
@@ -299,48 +120,3 @@ def parse_db_settings(data_dir: Path) -> dict[str, dict[str, Any]]:
     )
 
     return {"default": db_config}
-
-
-def parse_dateparser_languages(languages: str | None) -> list[str]:
-    language_list = languages.split("+") if languages else []
-    # There is an unfixed issue in zh-Hant and zh-Hans locales in the dateparser lib.
-    # See: https://github.com/scrapinghub/dateparser/issues/875
-    for index, language in enumerate(language_list):
-        if language.startswith("zh-") and "zh" not in language_list:
-            logger.warning(
-                f"Chinese locale detected: {language}. dateparser might fail to parse"
-                f' some dates with this locale, so Chinese ("zh") will be used as a fallback.',
-            )
-            language_list.append("zh")
-
-    return list(LocaleDataLoader().get_locale_map(locales=language_list))
-
-
-def parse_ignore_dates(
-    env_ignore: str,
-    date_order: str,
-) -> set[datetime.date]:
-    """
-    If the PAPERLESS_IGNORE_DATES environment variable is set, parse the
-    user provided string(s) into dates
-
-    Args:
-        env_ignore (str): The value of the environment variable, comma separated dates
-        date_order (str): The format of the date strings.
-
-    Returns:
-        set[datetime.date]: The set of parsed date objects
-    """
-    import dateparser
-
-    ignored_dates = set()
-    for s in env_ignore.split(","):
-        d = dateparser.parse(
-            s,
-            settings={
-                "DATE_ORDER": date_order,
-            },
-        )
-        if d:
-            ignored_dates.add(d.date())
-    return ignored_dates

src/paperless/settings/parsers.py

@@ -156,108 +156,6 @@ def parse_dict_from_str(
     return settings
 
 
-def get_bool_from_env(key: str, default: str = "NO") -> bool:
-    """
-    Return a boolean value based on whatever the user has supplied in the
-    environment based on whether the value "looks like" it's True or not.
-    """
-    return str_to_bool(os.getenv(key, default))
-
-
-@overload
-def get_float_from_env(key: str) -> float | None: ...
-
-
-@overload
-def get_float_from_env(key: str, default: None) -> float | None: ...
-
-
-@overload
-def get_float_from_env(key: str, default: float) -> float: ...
-
-
-def get_float_from_env(key: str, default: float | None = None) -> float | None:
-    """
-    Return a float value based on the environment variable.
-    If default is provided, returns that value when key is missing.
-    If default is None, returns None when key is missing.
-    """
-    if key not in os.environ:
-        return default
-
-    return float(os.environ[key])
-
-
-@overload
-def get_path_from_env(key: str) -> Path | None: ...
-
-
-@overload
-def get_path_from_env(key: str, default: None) -> Path | None: ...
-
-
-@overload
-def get_path_from_env(key: str, default: Path | str) -> Path: ...
-
-
-def get_path_from_env(key: str, default: Path | str | None = None) -> Path | None:
-    """
-    Return a Path object based on the environment variable.
-    If default is provided, returns that value when key is missing.
-    If default is None, returns None when key is missing.
-    """
-    if key not in os.environ:
-        return default if default is None else Path(default).resolve()
-
-    return Path(os.environ[key]).resolve()
-
-
-def get_list_from_env(
-    key: str,
-    separator: str = ",",
-    default: list[T] | None = None,
-    *,
-    strip_whitespace: bool = True,
-    remove_empty: bool = True,
-    required: bool = False,
-) -> list[str] | list[T]:
-    """
-    Get and parse a list from an environment variable or return a default.
-
-    Args:
-        key: Environment variable name
-        separator: Character(s) to split on (default: ',')
-        default: Default value to return if env var is not set or empty
-        strip_whitespace: Whether to strip whitespace from each element
-        remove_empty: Whether to remove empty strings from the result
-        required: If True, raise an error when the env var is missing and no default provided
-
-    Returns:
-        List of strings or list of type-cast values, or default if env var is empty/None
-
-    Raises:
-        ValueError: If required=True and env var is missing and there is no default
-    """
-    # Get the environment variable value
-    env_value = os.environ.get(key)
-
-    # Handle required environment variables
-    if required and env_value is None and default is None:
-        raise ValueError(f"Required environment variable '{key}' is not set")
-
-    if env_value:
-        items = env_value.split(separator)
-        if strip_whitespace:
-            items = [item.strip() for item in items]
-        if remove_empty:
-            items = [item for item in items if item]
-        return items
-    elif default is not None:
-        return default
-    else:
-        return []
-
-
 def get_choice_from_env(
     env_key: str,
     choices: set[str],

src/paperless/tests/settings/test_custom_parsers.py

@@ -1,279 +1,10 @@
-import datetime
 import os
 from pathlib import Path
-from typing import Any
 
 import pytest
-from celery.schedules import crontab
 from pytest_mock import MockerFixture
 
-from paperless.settings.custom import parse_beat_schedule
-from paperless.settings.custom import parse_dateparser_languages
 from paperless.settings.custom import parse_db_settings
-from paperless.settings.custom import parse_hosting_settings
-from paperless.settings.custom import parse_ignore_dates
-from paperless.settings.custom import parse_redis_url
-
-
-class TestRedisSocketConversion:
-    @pytest.mark.parametrize(
-        ("input_url", "expected"),
-        [
-            pytest.param(
-                None,
-                ("redis://localhost:6379", "redis://localhost:6379"),
-                id="none_uses_default",
-            ),
-            pytest.param(
-                "redis+socket:///run/redis/redis.sock",
-                (
-                    "redis+socket:///run/redis/redis.sock",
-                    "unix:///run/redis/redis.sock",
-                ),
-                id="celery_style_socket",
-            ),
-            pytest.param(
-                "unix:///run/redis/redis.sock",
-                (
-                    "redis+socket:///run/redis/redis.sock",
-                    "unix:///run/redis/redis.sock",
-                ),
-                id="redis_py_style_socket",
-            ),
-            pytest.param(
-                "redis+socket:///run/redis/redis.sock?virtual_host=5",
-                (
-                    "redis+socket:///run/redis/redis.sock?virtual_host=5",
-                    "unix:///run/redis/redis.sock?db=5",
-                ),
-                id="celery_style_socket_with_db",
-            ),
-            pytest.param(
-                "unix:///run/redis/redis.sock?db=10",
-                (
-                    "redis+socket:///run/redis/redis.sock?virtual_host=10",
-                    "unix:///run/redis/redis.sock?db=10",
-                ),
-                id="redis_py_style_socket_with_db",
-            ),
-            pytest.param(
-                "redis://myredishost:6379",
-                ("redis://myredishost:6379", "redis://myredishost:6379"),
-                id="host_with_port_unchanged",
-            ),
-            # Credentials in unix:// URL contain multiple colons (user:password@)
-            # Regression test for https://github.com/paperless-ngx/paperless-ngx/pull/12239
-            pytest.param(
-                "unix://user:password@/run/redis/redis.sock",
-                (
-                    "redis+socket://user:password@/run/redis/redis.sock",
-                    "unix://user:password@/run/redis/redis.sock",
-                ),
-                id="redis_py_style_socket_with_credentials",
-            ),
-            pytest.param(
-                "redis+socket://user:password@/run/redis/redis.sock",
-                (
-                    "redis+socket://user:password@/run/redis/redis.sock",
-                    "unix://user:password@/run/redis/redis.sock",
-                ),
-                id="celery_style_socket_with_credentials",
-            ),
-        ],
-    )
-    def test_redis_socket_parsing(
-        self,
-        input_url: str | None,
-        expected: tuple[str, str],
-    ) -> None:
-        """
-        GIVEN:
-            - Various Redis connection URI formats
-        WHEN:
-            - The URI is parsed
-        THEN:
-            - Socket based URIs are translated
-            - Non-socket URIs are unchanged
-            - None provided uses default
-        """
-        result = parse_redis_url(input_url)
-        assert expected == result
-
-
-class TestParseHostingSettings:
-    @pytest.mark.parametrize(
-        ("env", "expected"),
-        [
-            pytest.param(
-                {},
-                (
-                    None,
-                    "/",
-                    "/accounts/login/",
-                    "/dashboard",
-                    "/accounts/login/?loggedout=1",
-                ),
-                id="no_env_vars",
-            ),
-            pytest.param(
-                {"PAPERLESS_FORCE_SCRIPT_NAME": "/paperless"},
-                (
-                    "/paperless",
-                    "/paperless/",
-                    "/paperless/accounts/login/",
-                    "/paperless/dashboard",
-                    "/paperless/accounts/login/?loggedout=1",
-                ),
-                id="force_script_name_only",
-            ),
-            pytest.param(
-                {
-                    "PAPERLESS_FORCE_SCRIPT_NAME": "/docs",
-                    "PAPERLESS_LOGOUT_REDIRECT_URL": "/custom/logout",
-                },
-                (
-                    "/docs",
-                    "/docs/",
-                    "/docs/accounts/login/",
-                    "/docs/dashboard",
-                    "/custom/logout",
-                ),
-                id="force_script_name_and_logout_redirect",
-            ),
-        ],
-    )
-    def test_parse_hosting_settings(
-        self,
-        mocker: MockerFixture,
-        env: dict[str, str],
-        expected: tuple[str | None, str, str, str, str],
-    ) -> None:
-        """Test parse_hosting_settings with various env configurations."""
-        mocker.patch.dict(os.environ, env, clear=True)
-
-        result = parse_hosting_settings()
-
-        assert result == expected
-
-
-def make_expected_schedule(
-    overrides: dict[str, dict[str, Any]] | None = None,
-    disabled: set[str] | None = None,
-) -> dict[str, Any]:
-    """
-    Build the expected schedule with optional overrides and disabled tasks.
-    """
-
-    mail_expire = 9.0 * 60.0
-    classifier_expire = 59.0 * 60.0
-    index_expire = 23.0 * 60.0 * 60.0
-    sanity_expire = ((7.0 * 24.0) - 1.0) * 60.0 * 60.0
-    empty_trash_expire = 23.0 * 60.0 * 60.0
-    workflow_expire = 59.0 * 60.0
-    llm_index_expire = 23.0 * 60.0 * 60.0
-    share_link_cleanup_expire = 23.0 * 60.0 * 60.0
-
-    schedule: dict[str, Any] = {
-        "Check all e-mail accounts": {
-            "task": "paperless_mail.tasks.process_mail_accounts",
-            "schedule": crontab(minute="*/10"),
-            "options": {"expires": mail_expire},
-        },
-        "Train the classifier": {
-            "task": "documents.tasks.train_classifier",
-            "schedule": crontab(minute="5", hour="*/1"),
-            "options": {"expires": classifier_expire},
-        },
-        "Optimize the index": {
-            "task": "documents.tasks.index_optimize",
-            "schedule": crontab(minute=0, hour=0),
-            "options": {"expires": index_expire},
-        },
-        "Perform sanity check": {
-            "task": "documents.tasks.sanity_check",
-            "schedule": crontab(minute=30, hour=0, day_of_week="sun"),
-            "options": {"expires": sanity_expire},
-        },
-        "Empty trash": {
-            "task": "documents.tasks.empty_trash",
-            "schedule": crontab(minute=0, hour="1"),
-            "options": {"expires": empty_trash_expire},
-        },
-        "Check and run scheduled workflows": {
-            "task": "documents.tasks.check_scheduled_workflows",
-            "schedule": crontab(minute="5", hour="*/1"),
-            "options": {"expires": workflow_expire},
-        },
-        "Rebuild LLM index": {
-            "task": "documents.tasks.llmindex_index",
-            "schedule": crontab(minute="10", hour="2"),
-            "options": {"expires": llm_index_expire},
-        },
-        "Cleanup expired share link bundles": {
-            "task": "documents.tasks.cleanup_expired_share_link_bundles",
-            "schedule": crontab(minute=0, hour="2"),
-            "options": {"expires": share_link_cleanup_expire},
-        },
-    }
-
-    overrides = overrides or {}
-    disabled = disabled or set()
-
-    for key, val in overrides.items():
-        schedule[key] = {**schedule.get(key, {}), **val}
-
-    for key in disabled:
-        schedule.pop(key, None)
-
-    return schedule
-
-
-class TestParseBeatSchedule:
-    @pytest.mark.parametrize(
-        ("env", "expected"),
-        [
-            pytest.param({}, make_expected_schedule(), id="defaults"),
-            pytest.param(
-                {"PAPERLESS_EMAIL_TASK_CRON": "*/50 * * * mon"},
-                make_expected_schedule(
-                    overrides={
-                        "Check all e-mail accounts": {
-                            "schedule": crontab(minute="*/50", day_of_week="mon"),
-                        },
-                    },
-                ),
-                id="email-changed",
-            ),
-            pytest.param(
-                {"PAPERLESS_INDEX_TASK_CRON": "disable"},
-                make_expected_schedule(disabled={"Optimize the index"}),
-                id="index-disabled",
-            ),
-            pytest.param(
-                {
-                    "PAPERLESS_EMAIL_TASK_CRON": "disable",
-                    "PAPERLESS_TRAIN_TASK_CRON": "disable",
-                    "PAPERLESS_SANITY_TASK_CRON": "disable",
-                    "PAPERLESS_INDEX_TASK_CRON": "disable",
-                    "PAPERLESS_EMPTY_TRASH_TASK_CRON": "disable",
-                    "PAPERLESS_WORKFLOW_SCHEDULED_TASK_CRON": "disable",
-                    "PAPERLESS_LLM_INDEX_TASK_CRON": "disable",
-                    "PAPERLESS_SHARE_LINK_BUNDLE_CLEANUP_CRON": "disable",
-                },
-                {},
-                id="all-disabled",
-            ),
-        ],
-    )
-    def test_parse_beat_schedule(
-        self,
-        env: dict[str, str],
-        expected: dict[str, Any],
-        mocker: MockerFixture,
-    ) -> None:
-        mocker.patch.dict(os.environ, env, clear=False)
-        schedule = parse_beat_schedule()
-        assert schedule == expected
 
 
 class TestParseDbSettings:
@@ -533,85 +264,3 @@ class TestParseDbSettings:
         settings = parse_db_settings(tmp_path)
 
         assert settings == expected_database_settings
-
-
-class TestParseIgnoreDates:
-    """Tests the parsing of the PAPERLESS_IGNORE_DATES setting value."""
-
-    def test_no_ignore_dates_set(self) -> None:
-        """
-        GIVEN:
-            - No ignore dates are set
-        THEN:
-            - No ignore dates are parsed
-        """
-        assert parse_ignore_dates("", "YMD") == set()
-
-    @pytest.mark.parametrize(
-        ("env_str", "date_format", "expected"),
-        [
-            pytest.param(
-                "1985-05-01",
-                "YMD",
-                {datetime.date(1985, 5, 1)},
-                id="single-ymd",
-            ),
-            pytest.param(
-                "1985-05-01,1991-12-05",
-                "YMD",
-                {datetime.date(1985, 5, 1), datetime.date(1991, 12, 5)},
-                id="multiple-ymd",
-            ),
-            pytest.param(
-                "2010-12-13",
-                "YMD",
-                {datetime.date(2010, 12, 13)},
-                id="single-ymd-2",
-            ),
-            pytest.param(
-                "11.01.10",
-                "DMY",
-                {datetime.date(2010, 1, 11)},
-                id="single-dmy",
-            ),
-            pytest.param(
-                "11.01.2001,15-06-1996",
-                "DMY",
-                {datetime.date(2001, 1, 11), datetime.date(1996, 6, 15)},
-                id="multiple-dmy",
-            ),
-        ],
-    )
-    def test_ignore_dates_parsed(
-        self,
-        env_str: str,
-        date_format: str,
-        expected: set[datetime.date],
-    ) -> None:
-        """
-        GIVEN:
-            - Ignore dates are set per certain inputs
-        THEN:
-            - All ignore dates are parsed
-        """
-        assert parse_ignore_dates(env_str, date_format) == expected
-
-
-@pytest.mark.parametrize(
-    ("languages", "expected"),
-    [
-        ("de", ["de"]),
-        ("zh", ["zh"]),
-        ("fr+en", ["fr", "en"]),
-        # Locales must be supported
-        ("en-001+fr-CA", ["en-001", "fr-CA"]),
-        ("en-001+fr", ["en-001", "fr"]),
-        # Special case for Chinese: variants seem to miss some dates,
-        # so we always add "zh" as a fallback.
-        ("en+zh-Hans-HK", ["en", "zh-Hans-HK", "zh"]),
-        ("en+zh-Hans", ["en", "zh-Hans", "zh"]),
-        ("en+zh-Hans+zh-Hant", ["en", "zh-Hans", "zh-Hant", "zh"]),
-    ],
-)
-def test_parse_dateparser_languages(languages: str, expected: list[str]) -> None:
-    assert sorted(parse_dateparser_languages(languages)) == sorted(expected)

src/paperless/tests/settings/test_environment_parsers.py

@@ -4,12 +4,8 @@ from pathlib import Path
 import pytest
 from pytest_mock import MockerFixture
 
-from paperless.settings.parsers import get_bool_from_env
 from paperless.settings.parsers import get_choice_from_env
-from paperless.settings.parsers import get_float_from_env
 from paperless.settings.parsers import get_int_from_env
-from paperless.settings.parsers import get_list_from_env
-from paperless.settings.parsers import get_path_from_env
 from paperless.settings.parsers import parse_dict_from_str
 from paperless.settings.parsers import str_to_bool
 
@@ -209,29 +205,6 @@ class TestParseDictFromString:
         assert isinstance(result["database"]["port"], int)
 
 
-class TestGetBoolFromEnv:
-    def test_existing_env_var(self, mocker):
-        """Test that an existing environment variable is read and converted."""
-        mocker.patch.dict(os.environ, {"TEST_VAR": "true"})
-        assert get_bool_from_env("TEST_VAR") is True
-
-    def test_missing_env_var_uses_default_no(self, mocker):
-        """Test that a missing environment variable uses default 'NO' and returns False."""
-        mocker.patch.dict(os.environ, {}, clear=True)
-        assert get_bool_from_env("MISSING_VAR") is False
-
-    def test_missing_env_var_with_explicit_default(self, mocker):
-        """Test that a missing environment variable uses the provided default."""
-        mocker.patch.dict(os.environ, {}, clear=True)
-        assert get_bool_from_env("MISSING_VAR", default="yes") is True
-
-    def test_invalid_value_raises_error(self, mocker):
-        """Test that an invalid value raises ValueError (delegates to str_to_bool)."""
-        mocker.patch.dict(os.environ, {"INVALID_VAR": "maybe"})
-        with pytest.raises(ValueError):
-            get_bool_from_env("INVALID_VAR")
-
-
 class TestGetIntFromEnv:
     @pytest.mark.parametrize(
         ("env_value", "expected"),
@@ -286,199 +259,6 @@ class TestGetIntFromEnv:
             get_int_from_env("INVALID_INT")
 
 
-class TestGetFloatFromEnv:
-    @pytest.mark.parametrize(
-        ("env_value", "expected"),
-        [
-            pytest.param("3.14", 3.14, id="pi"),
-            pytest.param("42", 42.0, id="int_as_float"),
-            pytest.param("-2.5", -2.5, id="negative"),
-            pytest.param("0.0", 0.0, id="zero_float"),
-            pytest.param("0", 0.0, id="zero_int"),
-            pytest.param("1.5e2", 150.0, id="sci_positive"),
-            pytest.param("1e-3", 0.001, id="sci_negative"),
-            pytest.param("-1.23e4", -12300.0, id="sci_large"),
-        ],
-    )
-    def test_existing_env_var_valid_floats(self, mocker, env_value, expected):
-        """Test that existing environment variables with valid floats return correct values."""
-        mocker.patch.dict(os.environ, {"FLOAT_VAR": env_value})
-        assert get_float_from_env("FLOAT_VAR") == expected
-
-    @pytest.mark.parametrize(
-        ("default", "expected"),
-        [
-            pytest.param(3.14, 3.14, id="pi_default"),
-            pytest.param(0.0, 0.0, id="zero_default"),
-            pytest.param(-2.5, -2.5, id="negative_default"),
-            pytest.param(None, None, id="none_default"),
-        ],
-    )
-    def test_missing_env_var_with_defaults(self, mocker, default, expected):
-        """Test that missing environment variables return provided defaults."""
-        mocker.patch.dict(os.environ, {}, clear=True)
-        assert get_float_from_env("MISSING_VAR", default=default) == expected
-
-    def test_missing_env_var_no_default(self, mocker):
-        """Test that missing environment variable with no default returns None."""
-        mocker.patch.dict(os.environ, {}, clear=True)
-        assert get_float_from_env("MISSING_VAR") is None
-
-    @pytest.mark.parametrize(
-        "invalid_value",
-        [
-            pytest.param("not_a_number", id="text"),
-            pytest.param("42.5.0", id="double_decimal"),
-            pytest.param("42a", id="alpha_suffix"),
-            pytest.param("", id="empty"),
-            pytest.param(" ", id="whitespace"),
-            pytest.param("true", id="boolean"),
-            pytest.param("1.2.3", id="triple_decimal"),
-        ],
-    )
-    def test_invalid_float_values_raise_error(self, mocker, invalid_value):
-        """Test that invalid float values raise ValueError."""
-        mocker.patch.dict(os.environ, {"INVALID_FLOAT": invalid_value})
-        with pytest.raises(ValueError):
-            get_float_from_env("INVALID_FLOAT")
-
-
-class TestGetPathFromEnv:
-    @pytest.mark.parametrize(
-        "env_value",
-        [
-            pytest.param("/tmp/test", id="absolute"),
-            pytest.param("relative/path", id="relative"),
-            pytest.param("/path/with spaces/file.txt", id="spaces"),
-            pytest.param(".", id="current_dir"),
-            pytest.param("..", id="parent_dir"),
-            pytest.param("/", id="root"),
-        ],
-    )
-    def test_existing_env_var_paths(self, mocker, env_value):
-        """Test that existing environment variables with paths return resolved Path objects."""
-        mocker.patch.dict(os.environ, {"PATH_VAR": env_value})
-        result = get_path_from_env("PATH_VAR")
-        assert isinstance(result, Path)
-        assert result == Path(env_value).resolve()
-
-    def test_missing_env_var_no_default(self, mocker):
-        """Test that missing environment variable with no default returns None."""
-        mocker.patch.dict(os.environ, {}, clear=True)
-        assert get_path_from_env("MISSING_VAR") is None
-
-    def test_missing_env_var_with_none_default(self, mocker):
-        """Test that missing environment variable with None default returns None."""
-        mocker.patch.dict(os.environ, {}, clear=True)
-        assert get_path_from_env("MISSING_VAR", default=None) is None
-
-    @pytest.mark.parametrize(
-        "default_path_str",
-        [
-            pytest.param("/default/path", id="absolute_default"),
-            pytest.param("relative/default", id="relative_default"),
-            pytest.param(".", id="current_default"),
-        ],
-    )
-    def test_missing_env_var_with_path_defaults(self, mocker, default_path_str):
-        """Test that missing environment variables return resolved default Path objects."""
-        mocker.patch.dict(os.environ, {}, clear=True)
-        default_path = Path(default_path_str)
-        result = get_path_from_env("MISSING_VAR", default=default_path)
-        assert isinstance(result, Path)
-        assert result == default_path.resolve()
-
-    def test_relative_paths_are_resolved(self, mocker):
-        """Test that relative paths are properly resolved to absolute paths."""
-        mocker.patch.dict(os.environ, {"REL_PATH": "relative/path"})
-        result = get_path_from_env("REL_PATH")
-        assert result is not None
-        assert result.is_absolute()
-
-
-class TestGetListFromEnv:
-    @pytest.mark.parametrize(
-        ("env_value", "expected"),
-        [
-            pytest.param("a,b,c", ["a", "b", "c"], id="basic_comma_separated"),
-            pytest.param("single", ["single"], id="single_element"),
-            pytest.param("", [], id="empty_string"),
-            pytest.param("a, b , c", ["a", "b", "c"], id="whitespace_trimmed"),
-            pytest.param("a,,b,c", ["a", "b", "c"], id="empty_elements_removed"),
-        ],
-    )
-    def test_existing_env_var_basic_parsing(self, mocker, env_value, expected):
-        """Test that existing environment variables are parsed correctly."""
-        mocker.patch.dict(os.environ, {"LIST_VAR": env_value})
-        result = get_list_from_env("LIST_VAR")
-        assert result == expected
-
-    @pytest.mark.parametrize(
-        ("separator", "env_value", "expected"),
-        [
-            pytest.param("|", "a|b|c", ["a", "b", "c"], id="pipe_separator"),
-            pytest.param(":", "a:b:c", ["a", "b", "c"], id="colon_separator"),
-            pytest.param(";", "a;b;c", ["a", "b", "c"], id="semicolon_separator"),
-        ],
-    )
-    def test_custom_separators(self, mocker, separator, env_value, expected):
-        """Test that custom separators work correctly."""
-        mocker.patch.dict(os.environ, {"LIST_VAR": env_value})
-        result = get_list_from_env("LIST_VAR", separator=separator)
-        assert result == expected
-
-    @pytest.mark.parametrize(
-        ("default", "expected"),
-        [
-            pytest.param(
-                ["default1", "default2"],
-                ["default1", "default2"],
-                id="string_list_default",
-            ),
-            pytest.param([1, 2, 3], [1, 2, 3], id="int_list_default"),
-            pytest.param(None, [], id="none_default_returns_empty_list"),
-        ],
-    )
-    def test_missing_env_var_with_defaults(self, mocker, default, expected):
-        """Test that missing environment variables return provided defaults."""
-        mocker.patch.dict(os.environ, {}, clear=True)
-        result = get_list_from_env("MISSING_VAR", default=default)
-        assert result == expected
-
-    def test_missing_env_var_no_default(self, mocker):
-        """Test that missing environment variable with no default returns empty list."""
-        mocker.patch.dict(os.environ, {}, clear=True)
-        result = get_list_from_env("MISSING_VAR")
-        assert result == []
-
-    def test_required_env_var_missing_raises_error(self, mocker):
-        """Test that missing required environment variable raises ValueError."""
-        mocker.patch.dict(os.environ, {}, clear=True)
-        with pytest.raises(
-            ValueError,
-            match="Required environment variable 'REQUIRED_VAR' is not set",
-        ):
-            get_list_from_env("REQUIRED_VAR", required=True)
-
-    def test_required_env_var_with_default_does_not_raise(self, mocker):
-        """Test that required environment variable with default does not raise error."""
-        mocker.patch.dict(os.environ, {}, clear=True)
-        result = get_list_from_env("REQUIRED_VAR", default=["default"], required=True)
-        assert result == ["default"]
-
-    def test_strip_whitespace_false(self, mocker):
-        """Test that whitespace is preserved when strip_whitespace=False."""
-        mocker.patch.dict(os.environ, {"LIST_VAR": " a , b , c "})
-        result = get_list_from_env("LIST_VAR", strip_whitespace=False)
-        assert result == [" a ", " b ", " c "]
-
-    def test_remove_empty_false(self, mocker):
-        """Test that empty elements are preserved when remove_empty=False."""
-        mocker.patch.dict(os.environ, {"LIST_VAR": "a,,b,,c"})
-        result = get_list_from_env("LIST_VAR", remove_empty=False)
-        assert result == ["a", "", "b", "", "c"]
-
-
 class TestGetEnvChoice:
     @pytest.fixture
     def valid_choices(self) -> set[str]:
@@ -614,3 +394,21 @@ class TestGetEnvChoice:
         result = get_choice_from_env("TEST_ENV", large_choices)
 
         assert result == "option_50"
+
+    def test_different_env_keys(
+        self,
+        mocker: MockerFixture,
+        valid_choices: set[str],
+    ) -> None:
+        """Test function works with different environment variable keys."""
+        test_cases = [
+            ("DJANGO_ENV", "development"),
+            ("DATABASE_BACKEND", "staging"),
+            ("LOG_LEVEL", "production"),
+            ("APP_MODE", "development"),
+        ]
+
+        for env_key, env_value in test_cases:
+            mocker.patch.dict("os.environ", {env_key: env_value})
+            result = get_choice_from_env(env_key, valid_choices)
+            assert result == env_value

src/paperless/tests/settings/test_settings.py

@@ -1,56 +0,0 @@
-import os
-from unittest import TestCase
-from unittest import mock
-
-from paperless.settings import _parse_paperless_url
-from paperless.settings import default_threads_per_worker
-
-
-class TestThreadCalculation(TestCase):
-    def test_workers_threads(self) -> None:
-        """
-        GIVEN:
-            - Certain CPU counts
-        WHEN:
-            - Threads per worker is calculated
-        THEN:
-            - Threads per worker less than or equal to CPU count
-            - At least 1 thread per worker
-        """
-        default_workers = 1
-
-        for i in range(1, 64):
-            with mock.patch(
-                "paperless.settings.multiprocessing.cpu_count",
-            ) as cpu_count:
-                cpu_count.return_value = i
-
-                default_threads = default_threads_per_worker(default_workers)
-
-                self.assertGreaterEqual(default_threads, 1)
-
-                self.assertLessEqual(default_workers * default_threads, i)
-
-
-class TestPaperlessURLSettings(TestCase):
-    def test_paperless_url(self) -> None:
-        """
-        GIVEN:
-            - PAPERLESS_URL is set
-        WHEN:
-            - The URL is parsed
-        THEN:
-            - The URL is returned and present in related settings
-        """
-        with mock.patch.dict(
-            os.environ,
-            {
-                "PAPERLESS_URL": "https://example.com",
-            },
-        ):
-            url = _parse_paperless_url()
-            self.assertEqual("https://example.com", url)
-            from django.conf import settings
-
-            self.assertIn(url, settings.CSRF_TRUSTED_ORIGINS)
-            self.assertIn(url, settings.CORS_ALLOWED_ORIGINS)

src/paperless/tests/test_adapter.py

@@ -1,100 +1,107 @@
-import logging
+from unittest import mock
 
-import pytest
 from allauth.account.adapter import get_adapter
 from allauth.core import context
 from allauth.socialaccount.adapter import get_adapter as get_social_adapter
+from django.conf import settings
 from django.contrib.auth.models import AnonymousUser
 from django.contrib.auth.models import Group
 from django.contrib.auth.models import User
 from django.forms import ValidationError
 from django.http import HttpRequest
+from django.test import TestCase
+from django.test import override_settings
 from django.urls import reverse
-from pytest_django.fixtures import SettingsWrapper
-from pytest_mock import MockerFixture
 from rest_framework.authtoken.models import Token
 
 from paperless.adapter import DrfTokenStrategy
 
 
-@pytest.mark.django_db
-class TestCustomAccountAdapter:
-    def test_is_open_for_signup(self, settings: SettingsWrapper) -> None:
+class TestCustomAccountAdapter(TestCase):
+    def test_is_open_for_signup(self) -> None:
         adapter = get_adapter()
 
         # With no accounts, signups should be allowed
-        assert adapter.is_open_for_signup(None)
+        self.assertTrue(adapter.is_open_for_signup(None))
 
         User.objects.create_user("testuser")
 
+        # Test when ACCOUNT_ALLOW_SIGNUPS is True
         settings.ACCOUNT_ALLOW_SIGNUPS = True
-        assert adapter.is_open_for_signup(None)
+        self.assertTrue(adapter.is_open_for_signup(None))
 
+        # Test when ACCOUNT_ALLOW_SIGNUPS is False
         settings.ACCOUNT_ALLOW_SIGNUPS = False
-        assert not adapter.is_open_for_signup(None)
+        self.assertFalse(adapter.is_open_for_signup(None))
 
-    def test_is_safe_url(self, settings: SettingsWrapper) -> None:
+    def test_is_safe_url(self) -> None:
         request = HttpRequest()
-        request.get_host = lambda: "example.com"
+        request.get_host = mock.Mock(return_value="example.com")
         with context.request_context(request):
             adapter = get_adapter()
+            with override_settings(ALLOWED_HOSTS=["*"]):
+                # True because request host is same
+                url = "https://example.com"
+                self.assertTrue(adapter.is_safe_url(url))
 
-            settings.ALLOWED_HOSTS = ["*"]
-            # True because request host is same
-            assert adapter.is_safe_url("https://example.com")
+            url = "https://evil.com"
             # False despite wildcard because request host is different
-            assert not adapter.is_safe_url("https://evil.com")
+            self.assertFalse(adapter.is_safe_url(url))
 
             settings.ALLOWED_HOSTS = ["example.com"]
+            url = "https://example.com"
             # True because request host is same
-            assert adapter.is_safe_url("https://example.com")
+            self.assertTrue(adapter.is_safe_url(url))
 
             settings.ALLOWED_HOSTS = ["*", "example.com"]
+            url = "//evil.com"
             # False because request host is not in allowed hosts
-            assert not adapter.is_safe_url("//evil.com")
+            self.assertFalse(adapter.is_safe_url(url))
 
-    def test_pre_authenticate(
-        self,
-        settings: SettingsWrapper,
-        mocker: MockerFixture,
-    ) -> None:
-        mocker.patch("allauth.core.internal.ratelimit.consume", return_value=True)
+    @mock.patch("allauth.core.internal.ratelimit.consume", return_value=True)
+    def test_pre_authenticate(self, mock_consume) -> None:
         adapter = get_adapter()
         request = HttpRequest()
-        request.get_host = lambda: "example.com"
+        request.get_host = mock.Mock(return_value="example.com")
 
         settings.DISABLE_REGULAR_LOGIN = False
         adapter.pre_authenticate(request)
 
         settings.DISABLE_REGULAR_LOGIN = True
-        with pytest.raises(ValidationError):
+        with self.assertRaises(ValidationError):
             adapter.pre_authenticate(request)
 
-    def test_get_reset_password_from_key_url(self, settings: SettingsWrapper) -> None:
+    def test_get_reset_password_from_key_url(self) -> None:
         request = HttpRequest()
-        request.get_host = lambda: "foo.org"
+        request.get_host = mock.Mock(return_value="foo.org")
         with context.request_context(request):
             adapter = get_adapter()
 
-            settings.PAPERLESS_URL = None
-            settings.ACCOUNT_DEFAULT_HTTP_PROTOCOL = "https"
-            expected_url = f"https://foo.org{reverse('account_reset_password_from_key', kwargs={'uidb36': 'UID', 'key': 'KEY'})}"
-            assert adapter.get_reset_password_from_key_url("UID-KEY") == expected_url
+            # Test when PAPERLESS_URL is None
+            with override_settings(
+                PAPERLESS_URL=None,
+                ACCOUNT_DEFAULT_HTTP_PROTOCOL="https",
+            ):
+                expected_url = f"https://foo.org{reverse('account_reset_password_from_key', kwargs={'uidb36': 'UID', 'key': 'KEY'})}"
+                self.assertEqual(
+                    adapter.get_reset_password_from_key_url("UID-KEY"),
+                    expected_url,
+                )
 
-            settings.PAPERLESS_URL = "https://bar.com"
-            expected_url = f"https://bar.com{reverse('account_reset_password_from_key', kwargs={'uidb36': 'UID', 'key': 'KEY'})}"
-            assert adapter.get_reset_password_from_key_url("UID-KEY") == expected_url
+            # Test when PAPERLESS_URL is not None
+            with override_settings(PAPERLESS_URL="https://bar.com"):
+                expected_url = f"https://bar.com{reverse('account_reset_password_from_key', kwargs={'uidb36': 'UID', 'key': 'KEY'})}"
+                self.assertEqual(
+                    adapter.get_reset_password_from_key_url("UID-KEY"),
+                    expected_url,
+                )
 
-    def test_save_user_adds_groups(
-        self,
-        settings: SettingsWrapper,
-        mocker: MockerFixture,
-    ) -> None:
-        settings.ACCOUNT_DEFAULT_GROUPS = ["group1", "group2"]
+    @override_settings(ACCOUNT_DEFAULT_GROUPS=["group1", "group2"])
+    def test_save_user_adds_groups(self) -> None:
         Group.objects.create(name="group1")
         user = User.objects.create_user("testuser")
         adapter = get_adapter()
-        form = mocker.MagicMock(
+        form = mock.Mock(
             cleaned_data={
                 "username": "testuser",
                 "email": "user@example.com",
@@ -103,81 +110,88 @@ class TestCustomAccountAdapter:
 
         user = adapter.save_user(HttpRequest(), user, form, commit=True)
 
-        assert user.groups.count() == 1
-        assert user.groups.filter(name="group1").exists()
-        assert not user.groups.filter(name="group2").exists()
+        self.assertEqual(user.groups.count(), 1)
+        self.assertTrue(user.groups.filter(name="group1").exists())
+        self.assertFalse(user.groups.filter(name="group2").exists())
 
-    def test_fresh_install_save_creates_superuser(self, mocker: MockerFixture) -> None:
+    def test_fresh_install_save_creates_superuser(self) -> None:
         adapter = get_adapter()
-        form = mocker.MagicMock(
+        form = mock.Mock(
             cleaned_data={
                 "username": "testuser",
                 "email": "user@paperless-ngx.com",
             },
         )
         user = adapter.save_user(HttpRequest(), User(), form, commit=True)
-        assert user.is_superuser
+        self.assertTrue(user.is_superuser)
 
-        form = mocker.MagicMock(
+        # Next time, it should not create a superuser
+        form = mock.Mock(
             cleaned_data={
                 "username": "testuser2",
                 "email": "user2@paperless-ngx.com",
             },
         )
         user2 = adapter.save_user(HttpRequest(), User(), form, commit=True)
-        assert not user2.is_superuser
+        self.assertFalse(user2.is_superuser)
 
 
-class TestCustomSocialAccountAdapter:
-    @pytest.mark.django_db
-    def test_is_open_for_signup(self, settings: SettingsWrapper) -> None:
+class TestCustomSocialAccountAdapter(TestCase):
+    def test_is_open_for_signup(self) -> None:
         adapter = get_social_adapter()
 
+        # Test when SOCIALACCOUNT_ALLOW_SIGNUPS is True
         settings.SOCIALACCOUNT_ALLOW_SIGNUPS = True
-        assert adapter.is_open_for_signup(None, None)
+        self.assertTrue(adapter.is_open_for_signup(None, None))
 
+        # Test when SOCIALACCOUNT_ALLOW_SIGNUPS is False
         settings.SOCIALACCOUNT_ALLOW_SIGNUPS = False
-        assert not adapter.is_open_for_signup(None, None)
+        self.assertFalse(adapter.is_open_for_signup(None, None))
 
     def test_get_connect_redirect_url(self) -> None:
         adapter = get_social_adapter()
-        assert adapter.get_connect_redirect_url(None, None) == reverse("base")
+        request = None
+        socialaccount = None
 
-    @pytest.mark.django_db
-    def test_save_user_adds_groups(
-        self,
-        settings: SettingsWrapper,
-        mocker: MockerFixture,
-    ) -> None:
-        settings.SOCIAL_ACCOUNT_DEFAULT_GROUPS = ["group1", "group2"]
+        # Test the default URL
+        expected_url = reverse("base")
+        self.assertEqual(
+            adapter.get_connect_redirect_url(request, socialaccount),
+            expected_url,
+        )
+
+    @override_settings(SOCIAL_ACCOUNT_DEFAULT_GROUPS=["group1", "group2"])
+    def test_save_user_adds_groups(self) -> None:
         Group.objects.create(name="group1")
         adapter = get_social_adapter()
+        request = HttpRequest()
         user = User.objects.create_user("testuser")
-        sociallogin = mocker.MagicMock(user=user)
+        sociallogin = mock.Mock(
+            user=user,
+        )
 
-        user = adapter.save_user(HttpRequest(), sociallogin, None)
+        user = adapter.save_user(request, sociallogin, None)
 
-        assert user.groups.count() == 1
-        assert user.groups.filter(name="group1").exists()
-        assert not user.groups.filter(name="group2").exists()
+        self.assertEqual(user.groups.count(), 1)
+        self.assertTrue(user.groups.filter(name="group1").exists())
+        self.assertFalse(user.groups.filter(name="group2").exists())
 
-    def test_error_logged_on_authentication_error(
-        self,
-        caplog: pytest.LogCaptureFixture,
-    ) -> None:
+    def test_error_logged_on_authentication_error(self) -> None:
         adapter = get_social_adapter()
-        with caplog.at_level(logging.INFO, logger="paperless.auth"):
+        request = HttpRequest()
+        with self.assertLogs("paperless.auth", level="INFO") as log_cm:
             adapter.on_authentication_error(
-                HttpRequest(),
+                request,
                 provider="test-provider",
                 error="Error",
                 exception="Test authentication error",
             )
-        assert any("Test authentication error" in msg for msg in caplog.messages)
+        self.assertTrue(
+            any("Test authentication error" in message for message in log_cm.output),
+        )
 
 
-@pytest.mark.django_db
-class TestDrfTokenStrategy:
+class TestDrfTokenStrategy(TestCase):
     def test_create_access_token_creates_new_token(self) -> None:
         """
         GIVEN:
@@ -187,6 +201,7 @@ class TestDrfTokenStrategy:
         THEN:
             - A new token is created and its key is returned
         """
+
         user = User.objects.create_user("testuser")
         request = HttpRequest()
         request.user = user
@@ -194,9 +209,13 @@ class TestDrfTokenStrategy:
         strategy = DrfTokenStrategy()
         token_key = strategy.create_access_token(request)
 
-        assert token_key is not None
-        assert Token.objects.filter(user=user).exists()
-        assert token_key == Token.objects.get(user=user).key
+        # Verify a token was created
+        self.assertIsNotNone(token_key)
+        self.assertTrue(Token.objects.filter(user=user).exists())
+
+        # Verify the returned key matches the created token
+        token = Token.objects.get(user=user)
+        self.assertEqual(token_key, token.key)
 
     def test_create_access_token_returns_existing_token(self) -> None:
         """
@@ -207,6 +226,7 @@ class TestDrfTokenStrategy:
         THEN:
             - The same token key is returned (no new token created)
         """
+
         user = User.objects.create_user("testuser")
         existing_token = Token.objects.create(user=user)
 
@@ -216,8 +236,11 @@ class TestDrfTokenStrategy:
         strategy = DrfTokenStrategy()
         token_key = strategy.create_access_token(request)
 
-        assert token_key == existing_token.key
-        assert Token.objects.filter(user=user).count() == 1
+        # Verify the existing token key is returned
+        self.assertEqual(token_key, existing_token.key)
+
+        # Verify only one token exists (no duplicate created)
+        self.assertEqual(Token.objects.filter(user=user).count(), 1)
 
     def test_create_access_token_returns_none_for_unauthenticated_user(self) -> None:
         """
@@ -228,11 +251,12 @@ class TestDrfTokenStrategy:
         THEN:
             - None is returned and no token is created
         """
+
         request = HttpRequest()
         request.user = AnonymousUser()
 
         strategy = DrfTokenStrategy()
         token_key = strategy.create_access_token(request)
 
-        assert token_key is None
-        assert Token.objects.count() == 0
+        self.assertIsNone(token_key)
+        self.assertEqual(Token.objects.count(), 0)

src/paperless/tests/test_checks.py

@@ -1,15 +1,16 @@
 import os
-from collections.abc import Callable
-from dataclasses import dataclass
 from pathlib import Path
 from unittest import mock
 
 import pytest
 from django.core.checks import Error
 from django.core.checks import Warning
-from pytest_django.fixtures import SettingsWrapper
+from django.test import TestCase
+from django.test import override_settings
 from pytest_mock import MockerFixture
 
+from documents.tests.utils import DirectoriesMixin
+from documents.tests.utils import FileSystemAssertsMixin
 from paperless.checks import audit_log_check
 from paperless.checks import binaries_check
 from paperless.checks import check_deprecated_db_settings
@@ -19,84 +20,54 @@ from paperless.checks import paths_check
 from paperless.checks import settings_values_check
 
 
-@dataclass(frozen=True, slots=True)
-class PaperlessTestDirs:
-    data_dir: Path
-    media_dir: Path
-    consumption_dir: Path
-
-
-# TODO: consolidate with documents/tests/conftest.py PaperlessDirs/paperless_dirs
-#       once the paperless and documents test suites are ready to share fixtures.
-@pytest.fixture()
-def directories(tmp_path: Path, settings: SettingsWrapper) -> PaperlessTestDirs:
-    data_dir = tmp_path / "data"
-    media_dir = tmp_path / "media"
-    consumption_dir = tmp_path / "consumption"
-
-    for d in (data_dir, media_dir, consumption_dir):
-        d.mkdir()
-
-    settings.DATA_DIR = data_dir
-    settings.MEDIA_ROOT = media_dir
-    settings.CONSUMPTION_DIR = consumption_dir
-
-    return PaperlessTestDirs(
-        data_dir=data_dir,
-        media_dir=media_dir,
-        consumption_dir=consumption_dir,
-    )
-
-
-class TestChecks:
+class TestChecks(DirectoriesMixin, TestCase):
     def test_binaries(self) -> None:
-        assert binaries_check(None) == []
+        self.assertEqual(binaries_check(None), [])
 
-    def test_binaries_fail(self, settings: SettingsWrapper) -> None:
-        settings.CONVERT_BINARY = "uuuhh"
-        assert len(binaries_check(None)) == 1
+    @override_settings(CONVERT_BINARY="uuuhh")
+    def test_binaries_fail(self) -> None:
+        self.assertEqual(len(binaries_check(None)), 1)
 
-    @pytest.mark.usefixtures("directories")
     def test_paths_check(self) -> None:
-        assert paths_check(None) == []
+        self.assertEqual(paths_check(None), [])
 
-    def test_paths_check_dont_exist(self, settings: SettingsWrapper) -> None:
-        settings.MEDIA_ROOT = Path("uuh")
-        settings.DATA_DIR = Path("whatever")
-        settings.CONSUMPTION_DIR = Path("idontcare")
+    @override_settings(
+        MEDIA_ROOT=Path("uuh"),
+        DATA_DIR=Path("whatever"),
+        CONSUMPTION_DIR=Path("idontcare"),
+    )
+    def test_paths_check_dont_exist(self) -> None:
+        msgs = paths_check(None)
+        self.assertEqual(len(msgs), 3, str(msgs))
+
+        for msg in msgs:
+            self.assertTrue(msg.msg.endswith("is set but doesn't exist."))
+
+    def test_paths_check_no_access(self) -> None:
+        Path(self.dirs.data_dir).chmod(0o000)
+        Path(self.dirs.media_dir).chmod(0o000)
+        Path(self.dirs.consumption_dir).chmod(0o000)
+
+        self.addCleanup(os.chmod, self.dirs.data_dir, 0o777)
+        self.addCleanup(os.chmod, self.dirs.media_dir, 0o777)
+        self.addCleanup(os.chmod, self.dirs.consumption_dir, 0o777)
 
         msgs = paths_check(None)
+        self.assertEqual(len(msgs), 3)
 
-        assert len(msgs) == 3, str(msgs)
         for msg in msgs:
-            assert msg.msg.endswith("is set but doesn't exist.")
+            self.assertTrue(msg.msg.endswith("is not writeable"))
 
-    def test_paths_check_no_access(self, directories: PaperlessTestDirs) -> None:
-        directories.data_dir.chmod(0o000)
-        directories.media_dir.chmod(0o000)
-        directories.consumption_dir.chmod(0o000)
+    @override_settings(DEBUG=False)
+    def test_debug_disabled(self) -> None:
+        self.assertEqual(debug_mode_check(None), [])
 
-        try:
-            msgs = paths_check(None)
-        finally:
-            directories.data_dir.chmod(0o777)
-            directories.media_dir.chmod(0o777)
-            directories.consumption_dir.chmod(0o777)
-
-        assert len(msgs) == 3
-        for msg in msgs:
-            assert msg.msg.endswith("is not writeable")
-
-    def test_debug_disabled(self, settings: SettingsWrapper) -> None:
-        settings.DEBUG = False
-        assert debug_mode_check(None) == []
-
-    def test_debug_enabled(self, settings: SettingsWrapper) -> None:
-        settings.DEBUG = True
-        assert len(debug_mode_check(None)) == 1
+    @override_settings(DEBUG=True)
+    def test_debug_enabled(self) -> None:
+        self.assertEqual(len(debug_mode_check(None)), 1)
 
 
-class TestSettingsChecksAgainstDefaults:
+class TestSettingsChecksAgainstDefaults(DirectoriesMixin, TestCase):
     def test_all_valid(self) -> None:
         """
         GIVEN:
@@ -107,71 +78,104 @@ class TestSettingsChecksAgainstDefaults:
             - No system check errors reported
         """
         msgs = settings_values_check(None)
-        assert len(msgs) == 0
+        self.assertEqual(len(msgs), 0)
 
 
-class TestOcrSettingsChecks:
-    @pytest.mark.parametrize(
-        ("setting", "value", "expected_msg"),
-        [
-            pytest.param(
-                "OCR_OUTPUT_TYPE",
-                "notapdf",
-                'OCR output type "notapdf"',
-                id="invalid-output-type",
-            ),
-            pytest.param(
-                "OCR_MODE",
-                "makeitso",
-                'OCR output mode "makeitso"',
-                id="invalid-mode",
-            ),
-            pytest.param(
-                "OCR_MODE",
-                "skip_noarchive",
-                "deprecated",
-                id="deprecated-mode",
-            ),
-            pytest.param(
-                "OCR_SKIP_ARCHIVE_FILE",
-                "invalid",
-                'OCR_SKIP_ARCHIVE_FILE setting "invalid"',
-                id="invalid-skip-archive-file",
-            ),
-            pytest.param(
-                "OCR_CLEAN",
-                "cleanme",
-                'OCR clean mode "cleanme"',
-                id="invalid-clean",
-            ),
-        ],
-    )
-    def test_invalid_setting_produces_one_error(
-        self,
-        settings: SettingsWrapper,
-        setting: str,
-        value: str,
-        expected_msg: str,
-    ) -> None:
+class TestOcrSettingsChecks(DirectoriesMixin, TestCase):
+    @override_settings(OCR_OUTPUT_TYPE="notapdf")
+    def test_invalid_output_type(self) -> None:
         """
         GIVEN:
             - Default settings
-            - One OCR setting is set to an invalid value
+            - OCR output type is invalid
         WHEN:
             - Settings are validated
         THEN:
-            - Exactly one system check error is reported containing the expected message
+            - system check error reported for OCR output type
         """
-        setattr(settings, setting, value)
-
         msgs = settings_values_check(None)
+        self.assertEqual(len(msgs), 1)
 
-        assert len(msgs) == 1
-        assert expected_msg in msgs[0].msg
+        msg = msgs[0]
+
+        self.assertIn('OCR output type "notapdf"', msg.msg)
+
+    @override_settings(OCR_MODE="makeitso")
+    def test_invalid_ocr_type(self) -> None:
+        """
+        GIVEN:
+            - Default settings
+            - OCR type is invalid
+        WHEN:
+            - Settings are validated
+        THEN:
+            - system check error reported for OCR type
+        """
+        msgs = settings_values_check(None)
+        self.assertEqual(len(msgs), 1)
+
+        msg = msgs[0]
+
+        self.assertIn('OCR output mode "makeitso"', msg.msg)
+
+    @override_settings(OCR_MODE="skip_noarchive")
+    def test_deprecated_ocr_type(self) -> None:
+        """
+        GIVEN:
+            - Default settings
+            - OCR type is deprecated
+        WHEN:
+            - Settings are validated
+        THEN:
+            - deprecation warning reported for OCR type
+        """
+        msgs = settings_values_check(None)
+        self.assertEqual(len(msgs), 1)
+
+        msg = msgs[0]
+
+        self.assertIn("deprecated", msg.msg)
+
+    @override_settings(OCR_SKIP_ARCHIVE_FILE="invalid")
+    def test_invalid_ocr_skip_archive_file(self) -> None:
+        """
+        GIVEN:
+            - Default settings
+            - OCR_SKIP_ARCHIVE_FILE is invalid
+        WHEN:
+            - Settings are validated
+        THEN:
+            - system check error reported for OCR_SKIP_ARCHIVE_FILE
+        """
+        msgs = settings_values_check(None)
+        self.assertEqual(len(msgs), 1)
+
+        msg = msgs[0]
+
+        self.assertIn('OCR_SKIP_ARCHIVE_FILE setting "invalid"', msg.msg)
+
+    @override_settings(OCR_CLEAN="cleanme")
+    def test_invalid_ocr_clean(self) -> None:
+        """
+        GIVEN:
+            - Default settings
+            - OCR cleaning type is invalid
+        WHEN:
+            - Settings are validated
+        THEN:
+            - system check error reported for OCR cleaning type
+        """
+        msgs = settings_values_check(None)
+        self.assertEqual(len(msgs), 1)
+
+        msg = msgs[0]
+
+        self.assertIn('OCR clean mode "cleanme"', msg.msg)
 
 
-class TestTimezoneSettingsChecks:
-    def test_invalid_timezone(self, settings: SettingsWrapper) -> None:
+class TestTimezoneSettingsChecks(DirectoriesMixin, TestCase):
+    @override_settings(TIME_ZONE="TheMoon\\MyCrater")
+    def test_invalid_timezone(self) -> None:
         """
         GIVEN:
             - Default settings
@@ -181,16 +185,17 @@ class TestTimezoneSettingsChecks:
         THEN:
             - system check error reported for timezone
         """
-        settings.TIME_ZONE = "TheMoon\\MyCrater"
-
         msgs = settings_values_check(None)
+        self.assertEqual(len(msgs), 1)
 
-        assert len(msgs) == 1
-        assert 'Timezone "TheMoon\\MyCrater"' in msgs[0].msg
+        msg = msgs[0]
+
+        self.assertIn('Timezone "TheMoon\\MyCrater"', msg.msg)
 
 
-class TestEmailCertSettingsChecks:
-    def test_not_valid_file(self, settings: SettingsWrapper) -> None:
+class TestEmailCertSettingsChecks(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
+    @override_settings(EMAIL_CERTIFICATE_FILE=Path("/tmp/not_actually_here.pem"))
+    def test_not_valid_file(self) -> None:
         """
         GIVEN:
             - Default settings
@@ -200,22 +205,19 @@ class TestEmailCertSettingsChecks:
         THEN:
             - system check error reported for email certificate
         """
-        cert_path = Path("/tmp/not_actually_here.pem")
-        assert not cert_path.is_file()
-        settings.EMAIL_CERTIFICATE_FILE = cert_path
+        self.assertIsNotFile("/tmp/not_actually_here.pem")
 
         msgs = settings_values_check(None)
 
-        assert len(msgs) == 1
-        assert "Email cert /tmp/not_actually_here.pem is not a file" in msgs[0].msg
+        self.assertEqual(len(msgs), 1)
+
+        msg = msgs[0]
+
+        self.assertIn("Email cert /tmp/not_actually_here.pem is not a file", msg.msg)
 
 
-class TestAuditLogChecks:
-    def test_was_enabled_once(
-        self,
-        settings: SettingsWrapper,
-        mocker: MockerFixture,
-    ) -> None:
+class TestAuditLogChecks(TestCase):
+    def test_was_enabled_once(self) -> None:
         """
         GIVEN:
             - Audit log is not enabled
@@ -224,18 +226,23 @@ class TestAuditLogChecks:
         THEN:
             - system check error reported for disabling audit log
         """
-        settings.AUDIT_LOG_ENABLED = False
-        introspect_mock = mocker.MagicMock()
+        introspect_mock = mock.MagicMock()
         introspect_mock.introspection.table_names.return_value = ["auditlog_logentry"]
-        mocker.patch.dict(
-            "paperless.checks.connections",
-            {"default": introspect_mock},
-        )
+        with override_settings(AUDIT_LOG_ENABLED=False):
+            with mock.patch.dict(
+                "paperless.checks.connections",
+                {"default": introspect_mock},
+            ):
+                msgs = audit_log_check(None)
 
-        msgs = audit_log_check(None)
+                self.assertEqual(len(msgs), 1)
 
-        assert len(msgs) == 1
-        assert "auditlog table was found but audit log is disabled." in msgs[0].msg
+                msg = msgs[0]
+
+                self.assertIn(
+                    ("auditlog table was found but audit log is disabled."),
+                    msg.msg,
+                )
 
 
 DEPRECATED_VARS: dict[str, str] = {
@@ -264,16 +271,20 @@ class TestDeprecatedDbSettings:
     @pytest.mark.parametrize(
         ("env_var", "db_option_key"),
         [
-            pytest.param("PAPERLESS_DB_TIMEOUT", "timeout", id="db-timeout"),
-            pytest.param(
-                "PAPERLESS_DB_POOLSIZE",
-                "pool.min_size / pool.max_size",
-                id="db-poolsize",
-            ),
-            pytest.param("PAPERLESS_DBSSLMODE", "sslmode", id="ssl-mode"),
-            pytest.param("PAPERLESS_DBSSLROOTCERT", "sslrootcert", id="ssl-rootcert"),
-            pytest.param("PAPERLESS_DBSSLCERT", "sslcert", id="ssl-cert"),
-            pytest.param("PAPERLESS_DBSSLKEY", "sslkey", id="ssl-key"),
+            ("PAPERLESS_DB_TIMEOUT", "timeout"),
+            ("PAPERLESS_DB_POOLSIZE", "pool.min_size / pool.max_size"),
+            ("PAPERLESS_DBSSLMODE", "sslmode"),
+            ("PAPERLESS_DBSSLROOTCERT", "sslrootcert"),
+            ("PAPERLESS_DBSSLCERT", "sslcert"),
+            ("PAPERLESS_DBSSLKEY", "sslkey"),
+        ],
+        ids=[
+            "db-timeout",
+            "db-poolsize",
+            "ssl-mode",
+            "ssl-rootcert",
+            "ssl-cert",
+            "ssl-key",
         ],
     )
     def test_single_deprecated_var_produces_one_warning(
@@ -392,10 +403,7 @@ class TestV3MinimumUpgradeVersionCheck:
     """Test suite for check_v3_minimum_upgrade_version system check."""
 
     @pytest.fixture
-    def build_conn_mock(
-        self,
-        mocker: MockerFixture,
-    ) -> Callable[[list[str], list[str]], mock.MagicMock]:
+    def build_conn_mock(self, mocker: MockerFixture):
         """Factory fixture that builds a connections['default'] mock.
 
         Usage::
@@ -415,7 +423,7 @@ class TestV3MinimumUpgradeVersionCheck:
     def test_no_migrations_table_fresh_install(
         self,
         mocker: MockerFixture,
-        build_conn_mock: Callable[[list[str], list[str]], mock.MagicMock],
+        build_conn_mock,
     ) -> None:
         """
         GIVEN:
@@ -434,7 +442,7 @@ class TestV3MinimumUpgradeVersionCheck:
     def test_no_documents_migrations_fresh_install(
         self,
         mocker: MockerFixture,
-        build_conn_mock: Callable[[list[str], list[str]], mock.MagicMock],
+        build_conn_mock,
     ) -> None:
         """
         GIVEN:
@@ -453,7 +461,7 @@ class TestV3MinimumUpgradeVersionCheck:
     def test_v3_state_with_0001_squashed(
         self,
         mocker: MockerFixture,
-        build_conn_mock: Callable[[list[str], list[str]], mock.MagicMock],
+        build_conn_mock,
     ) -> None:
         """
         GIVEN:
@@ -477,7 +485,7 @@ class TestV3MinimumUpgradeVersionCheck:
     def test_v3_state_with_0002_squashed_only(
         self,
         mocker: MockerFixture,
-        build_conn_mock: Callable[[list[str], list[str]], mock.MagicMock],
+        build_conn_mock,
     ) -> None:
         """
         GIVEN:
@@ -496,7 +504,7 @@ class TestV3MinimumUpgradeVersionCheck:
     def test_v2_20_9_state_ready_to_upgrade(
         self,
         mocker: MockerFixture,
-        build_conn_mock: Callable[[list[str], list[str]], mock.MagicMock],
+        build_conn_mock,
     ) -> None:
         """
         GIVEN:
@@ -523,7 +531,7 @@ class TestV3MinimumUpgradeVersionCheck:
     def test_v2_20_8_raises_error(
         self,
         mocker: MockerFixture,
-        build_conn_mock: Callable[[list[str], list[str]], mock.MagicMock],
+        build_conn_mock,
     ) -> None:
         """
         GIVEN:
@@ -550,7 +558,7 @@ class TestV3MinimumUpgradeVersionCheck:
     def test_very_old_version_raises_error(
         self,
         mocker: MockerFixture,
-        build_conn_mock: Callable[[list[str], list[str]], mock.MagicMock],
+        build_conn_mock,
     ) -> None:
         """
         GIVEN:
@@ -577,7 +585,7 @@ class TestV3MinimumUpgradeVersionCheck:
     def test_error_hint_mentions_v2_20_9(
         self,
         mocker: MockerFixture,
-        build_conn_mock: Callable[[list[str], list[str]], mock.MagicMock],
+        build_conn_mock,
     ) -> None:
         """
         GIVEN:

src/paperless/tests/test_settings.py

@@ -0,0 +1,482 @@
+import datetime
+import os
+from unittest import TestCase
+from unittest import mock
+
+import pytest
+from celery.schedules import crontab
+
+from paperless.settings import _parse_base_paths
+from paperless.settings import _parse_beat_schedule
+from paperless.settings import _parse_dateparser_languages
+from paperless.settings import _parse_ignore_dates
+from paperless.settings import _parse_paperless_url
+from paperless.settings import _parse_redis_url
+from paperless.settings import default_threads_per_worker
+
+
+class TestIgnoreDateParsing(TestCase):
+    """
+    Tests the parsing of the PAPERLESS_IGNORE_DATES setting value
+    """
+
+    def _parse_checker(self, test_cases) -> None:
+        """
+        Helper function to check ignore date parsing
+
+        Args:
+            test_cases (_type_): _description_
+        """
+        for env_str, date_format, expected_date_set in test_cases:
+            self.assertSetEqual(
+                _parse_ignore_dates(env_str, date_format),
+                expected_date_set,
+            )
+
+    def test_no_ignore_dates_set(self) -> None:
+        """
+        GIVEN:
+            - No ignore dates are set
+        THEN:
+            - No ignore dates are parsed
+        """
+        self.assertSetEqual(_parse_ignore_dates(""), set())
+
+    def test_single_ignore_dates_set(self) -> None:
+        """
+        GIVEN:
+            - Ignore dates are set per certain inputs
+        THEN:
+            - All ignore dates are parsed
+        """
+        test_cases = [
+            ("1985-05-01", "YMD", {datetime.date(1985, 5, 1)}),
+            (
+                "1985-05-01,1991-12-05",
+                "YMD",
+                {datetime.date(1985, 5, 1), datetime.date(1991, 12, 5)},
+            ),
+            ("2010-12-13", "YMD", {datetime.date(2010, 12, 13)}),
+            ("11.01.10", "DMY", {datetime.date(2010, 1, 11)}),
+            (
+                "11.01.2001,15-06-1996",
+                "DMY",
+                {datetime.date(2001, 1, 11), datetime.date(1996, 6, 15)},
+            ),
+        ]
+
+        self._parse_checker(test_cases)
+
+
+class TestThreadCalculation(TestCase):
+    def test_workers_threads(self) -> None:
+        """
+        GIVEN:
+            - Certain CPU counts
+        WHEN:
+            - Threads per worker is calculated
+        THEN:
+            - Threads per worker less than or equal to CPU count
+            - At least 1 thread per worker
+        """
+        default_workers = 1
+
+        for i in range(1, 64):
+            with mock.patch(
+                "paperless.settings.multiprocessing.cpu_count",
+            ) as cpu_count:
+                cpu_count.return_value = i
+
+                default_threads = default_threads_per_worker(default_workers)
+
+                self.assertGreaterEqual(default_threads, 1)
+
+                self.assertLessEqual(default_workers * default_threads, i)
+
+
+class TestRedisSocketConversion(TestCase):
+    def test_redis_socket_parsing(self) -> None:
+        """
+        GIVEN:
+            - Various Redis connection URI formats
+        WHEN:
+            - The URI is parsed
+        THEN:
+            - Socket based URIs are translated
+            - Non-socket URIs are unchanged
+            - None provided uses default
+        """
+
+        for input, expected in [
+            # Nothing is set
+            (None, ("redis://localhost:6379", "redis://localhost:6379")),
+            # celery style
+            (
+                "redis+socket:///run/redis/redis.sock",
+                (
+                    "redis+socket:///run/redis/redis.sock",
+                    "unix:///run/redis/redis.sock",
+                ),
+            ),
+            # redis-py / channels-redis style
+            (
+                "unix:///run/redis/redis.sock",
+                (
+                    "redis+socket:///run/redis/redis.sock",
+                    "unix:///run/redis/redis.sock",
+                ),
+            ),
+            # celery style with db
+            (
+                "redis+socket:///run/redis/redis.sock?virtual_host=5",
+                (
+                    "redis+socket:///run/redis/redis.sock?virtual_host=5",
+                    "unix:///run/redis/redis.sock?db=5",
+                ),
+            ),
+            # redis-py / channels-redis style with db
+            (
+                "unix:///run/redis/redis.sock?db=10",
+                (
+                    "redis+socket:///run/redis/redis.sock?virtual_host=10",
+                    "unix:///run/redis/redis.sock?db=10",
+                ),
+            ),
+            # Just a host with a port
+            (
+                "redis://myredishost:6379",
+                ("redis://myredishost:6379", "redis://myredishost:6379"),
+            ),
+        ]:
+            result = _parse_redis_url(input)
+            self.assertTupleEqual(expected, result)
+
+
+class TestCeleryScheduleParsing(TestCase):
+    MAIL_EXPIRE_TIME = 9.0 * 60.0
+    CLASSIFIER_EXPIRE_TIME = 59.0 * 60.0
+    INDEX_EXPIRE_TIME = 23.0 * 60.0 * 60.0
+    SANITY_EXPIRE_TIME = ((7.0 * 24.0) - 1.0) * 60.0 * 60.0
+    EMPTY_TRASH_EXPIRE_TIME = 23.0 * 60.0 * 60.0
+    RUN_SCHEDULED_WORKFLOWS_EXPIRE_TIME = 59.0 * 60.0
+    LLM_INDEX_EXPIRE_TIME = 23.0 * 60.0 * 60.0
+    CLEANUP_EXPIRED_SHARE_BUNDLES_EXPIRE_TIME = 23.0 * 60.0 * 60.0
+
+    def test_schedule_configuration_default(self) -> None:
+        """
+        GIVEN:
+            - No configured task schedules
+        WHEN:
+            - The celery beat schedule is built
+        THEN:
+            - The default schedule is returned
+        """
+        schedule = _parse_beat_schedule()
+
+        self.assertDictEqual(
+            {
+                "Check all e-mail accounts": {
+                    "task": "paperless_mail.tasks.process_mail_accounts",
+                    "schedule": crontab(minute="*/10"),
+                    "options": {"expires": self.MAIL_EXPIRE_TIME},
+                },
+                "Train the classifier": {
+                    "task": "documents.tasks.train_classifier",
+                    "schedule": crontab(minute="5", hour="*/1"),
+                    "options": {"expires": self.CLASSIFIER_EXPIRE_TIME},
+                },
+                "Optimize the index": {
+                    "task": "documents.tasks.index_optimize",
+                    "schedule": crontab(minute=0, hour=0),
+                    "options": {"expires": self.INDEX_EXPIRE_TIME},
+                },
+                "Perform sanity check": {
+                    "task": "documents.tasks.sanity_check",
+                    "schedule": crontab(minute=30, hour=0, day_of_week="sun"),
+                    "options": {"expires": self.SANITY_EXPIRE_TIME},
+                },
+                "Empty trash": {
+                    "task": "documents.tasks.empty_trash",
+                    "schedule": crontab(minute=0, hour="1"),
+                    "options": {"expires": self.EMPTY_TRASH_EXPIRE_TIME},
+                },
+                "Check and run scheduled workflows": {
+                    "task": "documents.tasks.check_scheduled_workflows",
+                    "schedule": crontab(minute="5", hour="*/1"),
+                    "options": {"expires": self.RUN_SCHEDULED_WORKFLOWS_EXPIRE_TIME},
+                },
+                "Rebuild LLM index": {
+                    "task": "documents.tasks.llmindex_index",
+                    "schedule": crontab(minute=10, hour=2),
+                    "options": {
+                        "expires": self.LLM_INDEX_EXPIRE_TIME,
+                    },
+                },
+                "Cleanup expired share link bundles": {
+                    "task": "documents.tasks.cleanup_expired_share_link_bundles",
+                    "schedule": crontab(minute=0, hour=2),
+                    "options": {
+                        "expires": self.CLEANUP_EXPIRED_SHARE_BUNDLES_EXPIRE_TIME,
+                    },
+                },
+            },
+            schedule,
+        )
+
+    def test_schedule_configuration_changed(self) -> None:
+        """
+        GIVEN:
+            - Email task is configured non-default
+        WHEN:
+            - The celery beat schedule is built
+        THEN:
+            - The email task is configured per environment
+            - The default schedule is returned for other tasks
+        """
+        with mock.patch.dict(
+            os.environ,
+            {"PAPERLESS_EMAIL_TASK_CRON": "*/50 * * * mon"},
+        ):
+            schedule = _parse_beat_schedule()
+
+        self.assertDictEqual(
+            {
+                "Check all e-mail accounts": {
+                    "task": "paperless_mail.tasks.process_mail_accounts",
+                    "schedule": crontab(minute="*/50", day_of_week="mon"),
+                    "options": {"expires": self.MAIL_EXPIRE_TIME},
+                },
+                "Train the classifier": {
+                    "task": "documents.tasks.train_classifier",
+                    "schedule": crontab(minute="5", hour="*/1"),
+                    "options": {"expires": self.CLASSIFIER_EXPIRE_TIME},
+                },
+                "Optimize the index": {
+                    "task": "documents.tasks.index_optimize",
+                    "schedule": crontab(minute=0, hour=0),
+                    "options": {"expires": self.INDEX_EXPIRE_TIME},
+                },
+                "Perform sanity check": {
+                    "task": "documents.tasks.sanity_check",
+                    "schedule": crontab(minute=30, hour=0, day_of_week="sun"),
+                    "options": {"expires": self.SANITY_EXPIRE_TIME},
+                },
+                "Empty trash": {
+                    "task": "documents.tasks.empty_trash",
+                    "schedule": crontab(minute=0, hour="1"),
+                    "options": {"expires": self.EMPTY_TRASH_EXPIRE_TIME},
+                },
+                "Check and run scheduled workflows": {
+                    "task": "documents.tasks.check_scheduled_workflows",
+                    "schedule": crontab(minute="5", hour="*/1"),
+                    "options": {"expires": self.RUN_SCHEDULED_WORKFLOWS_EXPIRE_TIME},
+                },
+                "Rebuild LLM index": {
+                    "task": "documents.tasks.llmindex_index",
+                    "schedule": crontab(minute=10, hour=2),
+                    "options": {
+                        "expires": self.LLM_INDEX_EXPIRE_TIME,
+                    },
+                },
+                "Cleanup expired share link bundles": {
+                    "task": "documents.tasks.cleanup_expired_share_link_bundles",
+                    "schedule": crontab(minute=0, hour=2),
+                    "options": {
+                        "expires": self.CLEANUP_EXPIRED_SHARE_BUNDLES_EXPIRE_TIME,
+                    },
+                },
+            },
+            schedule,
+        )
+
+    def test_schedule_configuration_disabled(self) -> None:
+        """
+        GIVEN:
+            - Search index task is disabled
+        WHEN:
+            - The celery beat schedule is built
+        THEN:
+            - The search index task is not present
+            - The default schedule is returned for other tasks
+        """
+        with mock.patch.dict(os.environ, {"PAPERLESS_INDEX_TASK_CRON": "disable"}):
+            schedule = _parse_beat_schedule()
+
+        self.assertDictEqual(
+            {
+                "Check all e-mail accounts": {
+                    "task": "paperless_mail.tasks.process_mail_accounts",
+                    "schedule": crontab(minute="*/10"),
+                    "options": {"expires": self.MAIL_EXPIRE_TIME},
+                },
+                "Train the classifier": {
+                    "task": "documents.tasks.train_classifier",
+                    "schedule": crontab(minute="5", hour="*/1"),
+                    "options": {"expires": self.CLASSIFIER_EXPIRE_TIME},
+                },
+                "Perform sanity check": {
+                    "task": "documents.tasks.sanity_check",
+                    "schedule": crontab(minute=30, hour=0, day_of_week="sun"),
+                    "options": {"expires": self.SANITY_EXPIRE_TIME},
+                },
+                "Empty trash": {
+                    "task": "documents.tasks.empty_trash",
+                    "schedule": crontab(minute=0, hour="1"),
+                    "options": {"expires": self.EMPTY_TRASH_EXPIRE_TIME},
+                },
+                "Check and run scheduled workflows": {
+                    "task": "documents.tasks.check_scheduled_workflows",
+                    "schedule": crontab(minute="5", hour="*/1"),
+                    "options": {"expires": self.RUN_SCHEDULED_WORKFLOWS_EXPIRE_TIME},
+                },
+                "Rebuild LLM index": {
+                    "task": "documents.tasks.llmindex_index",
+                    "schedule": crontab(minute=10, hour=2),
+                    "options": {
+                        "expires": self.LLM_INDEX_EXPIRE_TIME,
+                    },
+                },
+                "Cleanup expired share link bundles": {
+                    "task": "documents.tasks.cleanup_expired_share_link_bundles",
+                    "schedule": crontab(minute=0, hour=2),
+                    "options": {
+                        "expires": self.CLEANUP_EXPIRED_SHARE_BUNDLES_EXPIRE_TIME,
+                    },
+                },
+            },
+            schedule,
+        )
+
+    def test_schedule_configuration_disabled_all(self) -> None:
+        """
+        GIVEN:
+            - All tasks are disabled
+        WHEN:
+            - The celery beat schedule is built
+        THEN:
+            - No tasks are scheduled
+        """
+        with mock.patch.dict(
+            os.environ,
+            {
+                "PAPERLESS_EMAIL_TASK_CRON": "disable",
+                "PAPERLESS_TRAIN_TASK_CRON": "disable",
+                "PAPERLESS_SANITY_TASK_CRON": "disable",
+                "PAPERLESS_INDEX_TASK_CRON": "disable",
+                "PAPERLESS_EMPTY_TRASH_TASK_CRON": "disable",
+                "PAPERLESS_WORKFLOW_SCHEDULED_TASK_CRON": "disable",
+                "PAPERLESS_LLM_INDEX_TASK_CRON": "disable",
+                "PAPERLESS_SHARE_LINK_BUNDLE_CLEANUP_CRON": "disable",
+            },
+        ):
+            schedule = _parse_beat_schedule()
+
+        self.assertDictEqual(
+            {},
+            schedule,
+        )
+
+
+class TestPaperlessURLSettings(TestCase):
+    def test_paperless_url(self) -> None:
+        """
+        GIVEN:
+            - PAPERLESS_URL is set
+        WHEN:
+            - The URL is parsed
+        THEN:
+            - The URL is returned and present in related settings
+        """
+        with mock.patch.dict(
+            os.environ,
+            {
+                "PAPERLESS_URL": "https://example.com",
+            },
+        ):
+            url = _parse_paperless_url()
+            self.assertEqual("https://example.com", url)
+            from django.conf import settings
+
+            self.assertIn(url, settings.CSRF_TRUSTED_ORIGINS)
+            self.assertIn(url, settings.CORS_ALLOWED_ORIGINS)
+
+
+class TestPathSettings(TestCase):
+    def test_default_paths(self) -> None:
+        """
+        GIVEN:
+            - PAPERLESS_FORCE_SCRIPT_NAME is not set
+        WHEN:
+            - Settings are parsed
+        THEN:
+            - Paths are as expected
+        """
+        base_paths = _parse_base_paths()
+        self.assertEqual(None, base_paths[0])  # FORCE_SCRIPT_NAME
+        self.assertEqual("/", base_paths[1])  # BASE_URL
+        self.assertEqual("/accounts/login/", base_paths[2])  # LOGIN_URL
+        self.assertEqual("/dashboard", base_paths[3])  # LOGIN_REDIRECT_URL
+        self.assertEqual(
+            "/accounts/login/?loggedout=1",
+            base_paths[4],
+        )  # LOGOUT_REDIRECT_URL
+
+    @mock.patch("os.environ", {"PAPERLESS_FORCE_SCRIPT_NAME": "/paperless"})
+    def test_subpath(self) -> None:
+        """
+        GIVEN:
+            - PAPERLESS_FORCE_SCRIPT_NAME is set
+        WHEN:
+            - Settings are parsed
+        THEN:
+            - The path is returned and present in related settings
+        """
+        base_paths = _parse_base_paths()
+        self.assertEqual("/paperless", base_paths[0])  # FORCE_SCRIPT_NAME
+        self.assertEqual("/paperless/", base_paths[1])  # BASE_URL
+        self.assertEqual("/paperless/accounts/login/", base_paths[2])  # LOGIN_URL
+        self.assertEqual("/paperless/dashboard", base_paths[3])  # LOGIN_REDIRECT_URL
+        self.assertEqual(
+            "/paperless/accounts/login/?loggedout=1",
+            base_paths[4],
+        )  # LOGOUT_REDIRECT_URL
+
+    @mock.patch(
+        "os.environ",
+        {
+            "PAPERLESS_FORCE_SCRIPT_NAME": "/paperless",
+            "PAPERLESS_LOGOUT_REDIRECT_URL": "/foobar/",
+        },
+    )
+    def test_subpath_with_explicit_logout_url(self) -> None:
+        """
+        GIVEN:
+            - PAPERLESS_FORCE_SCRIPT_NAME is set and so is PAPERLESS_LOGOUT_REDIRECT_URL
+        WHEN:
+            - Settings are parsed
+        THEN:
+            - The correct logout redirect URL is returned
+        """
+        base_paths = _parse_base_paths()
+        self.assertEqual("/paperless/", base_paths[1])  # BASE_URL
+        self.assertEqual("/foobar/", base_paths[4])  # LOGOUT_REDIRECT_URL
+
+
+@pytest.mark.parametrize(
+    ("languages", "expected"),
+    [
+        ("de", ["de"]),
+        ("zh", ["zh"]),
+        ("fr+en", ["fr", "en"]),
+        # Locales must be supported
+        ("en-001+fr-CA", ["en-001", "fr-CA"]),
+        ("en-001+fr", ["en-001", "fr"]),
+        # Special case for Chinese: variants seem to miss some dates,
+        # so we always add "zh" as a fallback.
+        ("en+zh-Hans-HK", ["en", "zh-Hans-HK", "zh"]),
+        ("en+zh-Hans", ["en", "zh-Hans", "zh"]),
+        ("en+zh-Hans+zh-Hant", ["en", "zh-Hans", "zh-Hant", "zh"]),
+    ],
+)
+def test_parser_date_parser_languages(languages, expected) -> None:
+    assert sorted(_parse_dateparser_languages(languages)) == sorted(expected)

src/paperless/tests/test_utils.py

@@ -9,50 +9,35 @@ from paperless.utils import ocr_to_dateparser_languages
 @pytest.mark.parametrize(
     ("ocr_language", "expected"),
     [
-        pytest.param("eng", ["en"], id="single-language"),
-        pytest.param("fra+ita+lao", ["fr", "it", "lo"], id="multiple-languages"),
-        pytest.param("fil", ["fil"], id="no-two-letter-equivalent"),
-        pytest.param(
-            "aze_cyrl+srp_latn",
-            ["az-Cyrl", "sr-Latn"],
-            id="script-supported-by-dateparser",
-        ),
-        pytest.param(
-            "deu_frak",
-            ["de"],
-            id="script-not-supported-falls-back-to-language",
-        ),
-        pytest.param(
-            "chi_tra+chi_sim",
-            ["zh"],
-            id="chinese-variants-collapse-to-general",
-        ),
-        pytest.param(
-            "eng+unsupported_language+por",
-            ["en", "pt"],
-            id="unsupported-language-skipped",
-        ),
-        pytest.param(
-            "unsupported1+unsupported2",
-            [],
-            id="all-unsupported-returns-empty",
-        ),
-        pytest.param("eng+eng", ["en"], id="duplicates-deduplicated"),
-        pytest.param(
-            "ita_unknownscript",
-            ["it"],
-            id="unknown-script-falls-back-to-language",
-        ),
+        # One language
+        ("eng", ["en"]),
+        # Multiple languages
+        ("fra+ita+lao", ["fr", "it", "lo"]),
+        # Languages that don't have a two-letter equivalent
+        ("fil", ["fil"]),
+        # Languages with a script part supported by dateparser
+        ("aze_cyrl+srp_latn", ["az-Cyrl", "sr-Latn"]),
+        # Languages with a script part not supported by dateparser
+        # In this case, default to the language without script
+        ("deu_frak", ["de"]),
+        # Traditional and simplified chinese don't have the same name in dateparser,
+        # so they're converted to the general chinese language
+        ("chi_tra+chi_sim", ["zh"]),
+        # If a language is not supported by dateparser, fallback to the supported ones
+        ("eng+unsupported_language+por", ["en", "pt"]),
+        # If no language is supported, fallback to default
+        ("unsupported1+unsupported2", []),
+        # Duplicate languages, should not duplicate in result
+        ("eng+eng", ["en"]),
+        # Language with script, but script is not mapped
+        ("ita_unknownscript", ["it"]),
     ],
 )
-def test_ocr_to_dateparser_languages(ocr_language: str, expected: list[str]) -> None:
+def test_ocr_to_dateparser_languages(ocr_language, expected):
     assert sorted(ocr_to_dateparser_languages(ocr_language)) == sorted(expected)
 
 
-def test_ocr_to_dateparser_languages_exception(
-    monkeypatch: pytest.MonkeyPatch,
-    caplog: pytest.LogCaptureFixture,
-) -> None:
+def test_ocr_to_dateparser_languages_exception(monkeypatch, caplog):
     # Patch LocaleDataLoader.get_locale_map to raise an exception
     class DummyLoader:
         def get_locale_map(self, locales=None):

src/paperless/tests/test_views.py

@@ -1,31 +1,24 @@
+import tempfile
 from pathlib import Path
 
-from django.test import Client
-from pytest_django.fixtures import SettingsWrapper
+from django.test import override_settings
 
 
-def test_favicon_view(
-    client: Client,
-    tmp_path: Path,
-    settings: SettingsWrapper,
-) -> None:
-    favicon_path = tmp_path / "paperless" / "img" / "favicon.ico"
-    favicon_path.parent.mkdir(parents=True)
-    favicon_path.write_bytes(b"FAKE ICON DATA")
+def test_favicon_view(client):
+    with tempfile.TemporaryDirectory() as tmpdir:
+        static_dir = Path(tmpdir)
+        favicon_path = static_dir / "paperless" / "img" / "favicon.ico"
+        favicon_path.parent.mkdir(parents=True, exist_ok=True)
+        favicon_path.write_bytes(b"FAKE ICON DATA")
 
-    settings.STATIC_ROOT = tmp_path
-
-    response = client.get("/favicon.ico")
-    assert response.status_code == 200
-    assert response["Content-Type"] == "image/x-icon"
-    assert b"".join(response.streaming_content) == b"FAKE ICON DATA"
+        with override_settings(STATIC_ROOT=static_dir):
+            response = client.get("/favicon.ico")
+            assert response.status_code == 200
+            assert response["Content-Type"] == "image/x-icon"
+            assert b"".join(response.streaming_content) == b"FAKE ICON DATA"
 
 
-def test_favicon_view_missing_file(
-    client: Client,
-    tmp_path: Path,
-    settings: SettingsWrapper,
-) -> None:
-    settings.STATIC_ROOT = tmp_path
-    response = client.get("/favicon.ico")
-    assert response.status_code == 404
+def test_favicon_view_missing_file(client):
+    with override_settings(STATIC_ROOT=Path(tempfile.mkdtemp())):
+        response = client.get("/favicon.ico")
+        assert response.status_code == 404

src/paperless/urls.py

@@ -21,18 +21,12 @@ from documents.views import BulkEditView
 from documents.views import ChatStreamingView
 from documents.views import CorrespondentViewSet
 from documents.views import CustomFieldViewSet
-from documents.views import DeleteDocumentsView
 from documents.views import DocumentTypeViewSet
-from documents.views import EditPdfDocumentsView
 from documents.views import GlobalSearchView
 from documents.views import IndexView
 from documents.views import LogViewSet
-from documents.views import MergeDocumentsView
 from documents.views import PostDocumentView
 from documents.views import RemoteVersionView
-from documents.views import RemovePasswordDocumentsView
-from documents.views import ReprocessDocumentsView
-from documents.views import RotateDocumentsView
 from documents.views import SavedViewViewSet
 from documents.views import SearchAutoCompleteView
 from documents.views import SelectionDataView
@@ -138,36 +132,6 @@ urlpatterns = [
                                 BulkEditView.as_view(),
                                 name="bulk_edit",
                             ),
-                            re_path(
-                                "^delete/",
-                                DeleteDocumentsView.as_view(),
-                                name="delete_documents",
-                            ),
-                            re_path(
-                                "^reprocess/",
-                                ReprocessDocumentsView.as_view(),
-                                name="reprocess_documents",
-                            ),
-                            re_path(
-                                "^rotate/",
-                                RotateDocumentsView.as_view(),
-                                name="rotate_documents",
-                            ),
-                            re_path(
-                                "^merge/",
-                                MergeDocumentsView.as_view(),
-                                name="merge_documents",
-                            ),
-                            re_path(
-                                "^edit_pdf/",
-                                EditPdfDocumentsView.as_view(),
-                                name="edit_pdf_documents",
-                            ),
-                            re_path(
-                                "^remove_password/",
-                                RemovePasswordDocumentsView.as_view(),
-                                name="remove_password_documents",
-                            ),
                             re_path(
                                 "^bulk_download/",
                                 BulkDownloadView.as_view(),

src/paperless_ai/base_model.py

@@ -1,4 +1,4 @@
-from pydantic import BaseModel
+from llama_index.core.bridge.pydantic import BaseModel
 
 
 class DocumentClassifierSchema(BaseModel):

src/paperless_ai/chat.py

@@ -1,6 +1,10 @@
 import logging
 import sys
 
+from llama_index.core import VectorStoreIndex
+from llama_index.core.prompts import PromptTemplate
+from llama_index.core.query_engine import RetrieverQueryEngine
+
 from documents.models import Document
 from paperless_ai.client import AIClient
 from paperless_ai.indexing import load_or_build_index
@@ -10,13 +14,15 @@ logger = logging.getLogger("paperless_ai.chat")
 MAX_SINGLE_DOC_CONTEXT_CHARS = 15000
 SINGLE_DOC_SNIPPET_CHARS = 800
 
-CHAT_PROMPT_TMPL = """Context information is below.
+CHAT_PROMPT_TMPL = PromptTemplate(
+    template="""Context information is below.
     ---------------------
     {context_str}
     ---------------------
     Given the context information and not prior knowledge, answer the query.
     Query: {query_str}
-    Answer:"""
+    Answer:""",
+)
 
 
 def stream_chat_with_documents(query_str: str, documents: list[Document]):
@@ -37,10 +43,6 @@ def stream_chat_with_documents(query_str: str, documents: list[Document]):
         yield "Sorry, I couldn't find any content to answer your question."
         return
 
-    from llama_index.core import VectorStoreIndex
-    from llama_index.core.prompts import PromptTemplate
-    from llama_index.core.query_engine import RetrieverQueryEngine
-
     local_index = VectorStoreIndex(nodes=nodes)
     retriever = local_index.as_retriever(
         similarity_top_k=3 if len(documents) == 1 else 5,
@@ -83,8 +85,7 @@ def stream_chat_with_documents(query_str: str, documents: list[Document]):
             for node in top_nodes
         )
 
-    prompt_template = PromptTemplate(template=CHAT_PROMPT_TMPL)
-    prompt = prompt_template.partial_format(
+    prompt = CHAT_PROMPT_TMPL.partial_format(
         context_str=context,
         query_str=query_str,
     ).format(llm=client.llm)

src/paperless_ai/client.py

@@ -1,10 +1,9 @@
 import logging
-from typing import TYPE_CHECKING
 
-if TYPE_CHECKING:
-    from llama_index.core.llms import ChatMessage
-    from llama_index.llms.ollama import Ollama
-    from llama_index.llms.openai import OpenAI
+from llama_index.core.llms import ChatMessage
+from llama_index.core.program.function_program import get_function_tool
+from llama_index.llms.ollama import Ollama
+from llama_index.llms.openai import OpenAI
 
 from paperless.config import AIConfig
 from paperless_ai.base_model import DocumentClassifierSchema
@@ -21,18 +20,14 @@ class AIClient:
         self.settings = AIConfig()
         self.llm = self.get_llm()
 
-    def get_llm(self) -> "Ollama | OpenAI":
+    def get_llm(self) -> Ollama | OpenAI:
         if self.settings.llm_backend == "ollama":
-            from llama_index.llms.ollama import Ollama
-
             return Ollama(
                 model=self.settings.llm_model or "llama3.1",
                 base_url=self.settings.llm_endpoint or "http://localhost:11434",
                 request_timeout=120,
             )
         elif self.settings.llm_backend == "openai":
-            from llama_index.llms.openai import OpenAI
-
             return OpenAI(
                 model=self.settings.llm_model or "gpt-3.5-turbo",
                 api_base=self.settings.llm_endpoint or None,
@@ -48,9 +43,6 @@ class AIClient:
             self.settings.llm_model,
         )
 
-        from llama_index.core.llms import ChatMessage
-        from llama_index.core.program.function_program import get_function_tool
-
         user_msg = ChatMessage(role="user", content=prompt)
         tool = get_function_tool(DocumentClassifierSchema)
         result = self.llm.chat_with_tools(
@@ -66,7 +58,7 @@ class AIClient:
         parsed = DocumentClassifierSchema(**tool_calls[0].tool_kwargs)
         return parsed.model_dump()
 
-    def run_chat(self, messages: list["ChatMessage"]) -> str:
+    def run_chat(self, messages: list[ChatMessage]) -> str:
         logger.debug(
             "Running chat query against %s with model %s",
             self.settings.llm_backend,

src/paperless_ai/embedding.py

@@ -1,12 +1,13 @@
 import json
 from typing import TYPE_CHECKING
 
-from django.conf import settings
-
 if TYPE_CHECKING:
     from pathlib import Path
 
-    from llama_index.core.base.embeddings.base import BaseEmbedding
+from django.conf import settings
+from llama_index.core.base.embeddings.base import BaseEmbedding
+from llama_index.embeddings.huggingface import HuggingFaceEmbedding
+from llama_index.embeddings.openai import OpenAIEmbedding
 
 from documents.models import Document
 from documents.models import Note
@@ -14,21 +15,17 @@ from paperless.config import AIConfig
 from paperless.models import LLMEmbeddingBackend
 
 
-def get_embedding_model() -> "BaseEmbedding":
+def get_embedding_model() -> BaseEmbedding:
     config = AIConfig()
 
     match config.llm_embedding_backend:
         case LLMEmbeddingBackend.OPENAI:
-            from llama_index.embeddings.openai import OpenAIEmbedding
-
             return OpenAIEmbedding(
                 model=config.llm_embedding_model or "text-embedding-3-small",
                 api_key=config.llm_api_key,
                 api_base=config.llm_endpoint or None,
             )
         case LLMEmbeddingBackend.HUGGINGFACE:
-            from llama_index.embeddings.huggingface import HuggingFaceEmbedding
-
             return HuggingFaceEmbedding(
                 model_name=config.llm_embedding_model
                 or "sentence-transformers/all-MiniLM-L6-v2",

src/paperless_ai/indexing.py

@@ -4,12 +4,26 @@ from collections.abc import Callable
 from collections.abc import Iterable
 from datetime import timedelta
 from pathlib import Path
-from typing import TYPE_CHECKING
 from typing import TypeVar
 
+import faiss
+import llama_index.core.settings as llama_settings
 from celery import states
 from django.conf import settings
 from django.utils import timezone
+from llama_index.core import Document as LlamaDocument
+from llama_index.core import StorageContext
+from llama_index.core import VectorStoreIndex
+from llama_index.core import load_index_from_storage
+from llama_index.core.indices.prompt_helper import PromptHelper
+from llama_index.core.node_parser import SimpleNodeParser
+from llama_index.core.prompts import PromptTemplate
+from llama_index.core.retrievers import VectorIndexRetriever
+from llama_index.core.schema import BaseNode
+from llama_index.core.storage.docstore import SimpleDocumentStore
+from llama_index.core.storage.index_store import SimpleIndexStore
+from llama_index.core.text_splitter import TokenTextSplitter
+from llama_index.vector_stores.faiss import FaissVectorStore
 
 from documents.models import Document
 from documents.models import PaperlessTask
@@ -20,10 +34,6 @@ from paperless_ai.embedding import get_embedding_model
 _T = TypeVar("_T")
 IterWrapper = Callable[[Iterable[_T]], Iterable[_T]]
 
-if TYPE_CHECKING:
-    from llama_index.core import VectorStoreIndex
-    from llama_index.core.schema import BaseNode
-
 
 def _identity(iterable: Iterable[_T]) -> Iterable[_T]:
     return iterable
@@ -65,23 +75,12 @@ def get_or_create_storage_context(*, rebuild=False):
         settings.LLM_INDEX_DIR.mkdir(parents=True, exist_ok=True)
 
     if rebuild or not settings.LLM_INDEX_DIR.exists():
-        import faiss
-        from llama_index.core import StorageContext
-        from llama_index.core.storage.docstore import SimpleDocumentStore
-        from llama_index.core.storage.index_store import SimpleIndexStore
-        from llama_index.vector_stores.faiss import FaissVectorStore
-
         embedding_dim = get_embedding_dim()
         faiss_index = faiss.IndexFlatL2(embedding_dim)
         vector_store = FaissVectorStore(faiss_index=faiss_index)
         docstore = SimpleDocumentStore()
         index_store = SimpleIndexStore()
     else:
-        from llama_index.core import StorageContext
-        from llama_index.core.storage.docstore import SimpleDocumentStore
-        from llama_index.core.storage.index_store import SimpleIndexStore
-        from llama_index.vector_stores.faiss import FaissVectorStore
-
         vector_store = FaissVectorStore.from_persist_dir(settings.LLM_INDEX_DIR)
         docstore = SimpleDocumentStore.from_persist_dir(settings.LLM_INDEX_DIR)
         index_store = SimpleIndexStore.from_persist_dir(settings.LLM_INDEX_DIR)
@@ -94,7 +93,7 @@ def get_or_create_storage_context(*, rebuild=False):
     )
 
 
-def build_document_node(document: Document) -> list["BaseNode"]:
+def build_document_node(document: Document) -> list[BaseNode]:
     """
     Given a Document, returns parsed Nodes ready for indexing.
     """
@@ -113,9 +112,6 @@ def build_document_node(document: Document) -> list["BaseNode"]:
         "added": document.added.isoformat() if document.added else None,
         "modified": document.modified.isoformat(),
     }
-    from llama_index.core import Document as LlamaDocument
-    from llama_index.core.node_parser import SimpleNodeParser
-
     doc = LlamaDocument(text=text, metadata=metadata)
     parser = SimpleNodeParser()
     return parser.get_nodes_from_documents([doc])
@@ -126,10 +122,6 @@ def load_or_build_index(nodes=None):
     Load an existing VectorStoreIndex if present,
     or build a new one using provided nodes if storage is empty.
     """
-    import llama_index.core.settings as llama_settings
-    from llama_index.core import VectorStoreIndex
-    from llama_index.core import load_index_from_storage
-
     embed_model = get_embedding_model()
     llama_settings.Settings.embed_model = embed_model
     storage_context = get_or_create_storage_context()
@@ -151,7 +143,7 @@ def load_or_build_index(nodes=None):
         )
 
 
-def remove_document_docstore_nodes(document: Document, index: "VectorStoreIndex"):
+def remove_document_docstore_nodes(document: Document, index: VectorStoreIndex):
     """
     Removes existing documents from docstore for a given document from the index.
     This is necessary because FAISS IndexFlatL2 is append-only.
@@ -182,8 +174,6 @@ def update_llm_index(
     """
     Rebuild or update the LLM index.
     """
-    from llama_index.core import VectorStoreIndex
-
     nodes = []
 
     documents = Document.objects.all()
@@ -197,8 +187,6 @@ def update_llm_index(
         (settings.LLM_INDEX_DIR / "meta.json").unlink(missing_ok=True)
         # Rebuild index from scratch
         logger.info("Rebuilding LLM index.")
-        import llama_index.core.settings as llama_settings
-
         embed_model = get_embedding_model()
         llama_settings.Settings.embed_model = embed_model
         storage_context = get_or_create_storage_context(rebuild=True)
@@ -283,10 +271,6 @@ def llm_index_remove_document(document: Document):
 
 
 def truncate_content(content: str) -> str:
-    from llama_index.core.indices.prompt_helper import PromptHelper
-    from llama_index.core.prompts import PromptTemplate
-    from llama_index.core.text_splitter import TokenTextSplitter
-
     prompt_helper = PromptHelper(
         context_window=8192,
         num_output=512,
@@ -331,8 +315,6 @@ def query_similar_documents(
         else None
     )
 
-    from llama_index.core.retrievers import VectorIndexRetriever
-
     retriever = VectorIndexRetriever(
         index=index,
         similarity_top_k=top_k,

src/paperless_ai/tests/test_ai_indexing.py

@@ -181,11 +181,11 @@ def test_load_or_build_index_builds_when_nodes_given(
 ) -> None:
     with (
         patch(
-            "llama_index.core.load_index_from_storage",
+            "paperless_ai.indexing.load_index_from_storage",
             side_effect=ValueError("Index not found"),
         ),
         patch(
-            "llama_index.core.VectorStoreIndex",
+            "paperless_ai.indexing.VectorStoreIndex",
             return_value=MagicMock(),
         ) as mock_index_cls,
         patch(
@@ -206,7 +206,7 @@ def test_load_or_build_index_raises_exception_when_no_nodes(
 ) -> None:
     with (
         patch(
-            "llama_index.core.load_index_from_storage",
+            "paperless_ai.indexing.load_index_from_storage",
             side_effect=ValueError("Index not found"),
         ),
         patch(
@@ -225,11 +225,11 @@ def test_load_or_build_index_succeeds_when_nodes_given(
 ) -> None:
     with (
         patch(
-            "llama_index.core.load_index_from_storage",
+            "paperless_ai.indexing.load_index_from_storage",
             side_effect=ValueError("Index not found"),
         ),
         patch(
-            "llama_index.core.VectorStoreIndex",
+            "paperless_ai.indexing.VectorStoreIndex",
             return_value=MagicMock(),
         ) as mock_index_cls,
         patch(
@@ -334,7 +334,7 @@ def test_query_similar_documents(
         patch(
             "paperless_ai.indexing.vector_store_file_exists",
         ) as mock_vector_store_exists,
-        patch("llama_index.core.retrievers.VectorIndexRetriever") as mock_retriever_cls,
+        patch("paperless_ai.indexing.VectorIndexRetriever") as mock_retriever_cls,
         patch("paperless_ai.indexing.Document.objects.filter") as mock_filter,
     ):
         mock_storage.return_value = MagicMock()

src/paperless_ai/tests/test_chat.py

@@ -45,7 +45,7 @@ def test_stream_chat_with_one_document_full_content(mock_document) -> None:
         patch("paperless_ai.chat.AIClient") as mock_client_cls,
         patch("paperless_ai.chat.load_or_build_index") as mock_load_index,
         patch(
-            "llama_index.core.query_engine.RetrieverQueryEngine.from_args",
+            "paperless_ai.chat.RetrieverQueryEngine.from_args",
         ) as mock_query_engine_cls,
     ):
         mock_client = MagicMock()
@@ -76,7 +76,7 @@ def test_stream_chat_with_multiple_documents_retrieval(patch_embed_nodes) -> Non
         patch("paperless_ai.chat.AIClient") as mock_client_cls,
         patch("paperless_ai.chat.load_or_build_index") as mock_load_index,
         patch(
-            "llama_index.core.query_engine.RetrieverQueryEngine.from_args",
+            "paperless_ai.chat.RetrieverQueryEngine.from_args",
         ) as mock_query_engine_cls,
         patch.object(VectorStoreIndex, "as_retriever") as mock_as_retriever,
     ):

src/paperless_ai/tests/test_client.py

@@ -18,13 +18,13 @@ def mock_ai_config():
 
 @pytest.fixture
 def mock_ollama_llm():
-    with patch("llama_index.llms.ollama.Ollama") as MockOllama:
+    with patch("paperless_ai.client.Ollama") as MockOllama:
         yield MockOllama
 
 
 @pytest.fixture
 def mock_openai_llm():
-    with patch("llama_index.llms.openai.OpenAI") as MockOpenAI:
+    with patch("paperless_ai.client.OpenAI") as MockOpenAI:
         yield MockOpenAI