Merge branch 'dev' into feature-remote-ocr-2

[ci skip]

.github/workflows/ci.yml

@@ -17,59 +17,18 @@ env:
   DEFAULT_PYTHON_VERSION: "3.11"
   NLTK_DATA: "/usr/share/nltk_data"
 jobs:
-  detect-duplicate:
-    name: Detect Duplicate Run
-    runs-on: ubuntu-24.04
-    outputs:
-      should_run: ${{ steps.check.outputs.should_run }}
-    steps:
-      - name: Check if workflow should run
-        id: check
-        uses: actions/github-script@v8
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}
-          script: |
-            if (context.eventName !== 'push') {
-              core.info('Not a push event; running workflow.');
-              core.setOutput('should_run', 'true');
-              return;
-            }
-
-            const ref = context.ref || '';
-            if (!ref.startsWith('refs/heads/')) {
-              core.info('Push is not to a branch; running workflow.');
-              core.setOutput('should_run', 'true');
-              return;
-            }
-
-            const branch = ref.substring('refs/heads/'.length);
-            const { owner, repo } = context.repo;
-            const prs = await github.paginate(github.rest.pulls.list, {
-              owner,
-              repo,
-              state: 'open',
-              head: `${owner}:${branch}`,
-              per_page: 100,
-            });
-
-            if (prs.length === 0) {
-              core.info(`No open PR found for ${branch}; running workflow.`);
-              core.setOutput('should_run', 'true');
-            } else {
-              core.info(`Found ${prs.length} open PR(s) for ${branch}; skipping duplicate push run.`);
-              core.setOutput('should_run', 'false');
-            }
   pre-commit:
-    needs:
+    # We want to run on external PRs, but not on our own internal PRs as they'll be run
-      - detect-duplicate
+    # by the push to the branch. Without this if check, checks are duplicated since
-    if: needs.detect-duplicate.outputs.should_run == 'true'
+    # internal PRs match both the push and pull_request events.
+    if: github.event_name == 'push' || github.event.pull_request.head.repo.full_name != github.repository
     name: Linting Checks
     runs-on: ubuntu-24.04
     steps:
       - name: Checkout repository
         uses: actions/checkout@v5
       - name: Install python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
       - name: Check files
@@ -84,7 +43,7 @@ jobs:
         uses: actions/checkout@v5
       - name: Set up Python
         id: setup-python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
       - name: Install uv
@@ -138,7 +97,7 @@ jobs:
           docker compose --file ${{ github.workspace }}/docker/compose/docker-compose.ci-test.yml up --detach
       - name: Set up Python
         id: setup-python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v5
         with:
           python-version: "${{ matrix.python-version }}"
       - name: Install uv
@@ -183,13 +142,27 @@ jobs:
         if: always()
         uses: codecov/test-results-action@v1
         with:
+          token: ${{ secrets.CODECOV_TOKEN }}
           flags: backend-python-${{ matrix.python-version }}
           files: junit.xml
       - name: Upload backend coverage to Codecov
         uses: codecov/codecov-action@v5
         with:
+          token: ${{ secrets.CODECOV_TOKEN }}
           flags: backend-python-${{ matrix.python-version }}
           files: coverage.xml
+      - name: Upload coverage artifacts
+        uses: actions/upload-artifact@v4
+        if: always()
+        with:
+          name: backend-coverage-${{ matrix.python-version }}
+          path: |
+            .coverage
+            coverage.xml
+            junit.xml
+          retention-days: 1
+          include-hidden-files: true
+          if-no-files-found: error
       - name: Stop containers
         if: always()
         run: |
@@ -207,7 +180,7 @@ jobs:
         with:
           version: 10
       - name: Use Node.js 20
-        uses: actions/setup-node@v5
+        uses: actions/setup-node@v4
         with:
           node-version: 20.x
           cache: 'pnpm'
@@ -240,7 +213,7 @@ jobs:
         with:
           version: 10
       - name: Use Node.js 20
-        uses: actions/setup-node@v5
+        uses: actions/setup-node@v4
         with:
           node-version: 20.x
           cache: 'pnpm'
@@ -263,13 +236,26 @@ jobs:
         uses: codecov/test-results-action@v1
         if: always()
         with:
+          token: ${{ secrets.CODECOV_TOKEN }}
           flags: frontend-node-${{ matrix.node-version }}
           directory: src-ui/
       - name: Upload frontend coverage to Codecov
         uses: codecov/codecov-action@v5
         with:
+          token: ${{ secrets.CODECOV_TOKEN }}
           flags: frontend-node-${{ matrix.node-version }}
           directory: src-ui/coverage/
+      - name: Upload coverage artifacts
+        uses: actions/upload-artifact@v4
+        if: always()
+        with:
+          name: frontend-coverage-${{ matrix.shard-index }}
+          path: |
+            src-ui/coverage/lcov.info
+            src-ui/coverage/coverage-final.json
+            src-ui/junit.xml
+          retention-days: 1
+          if-no-files-found: error
   tests-frontend-e2e:
     name: "Frontend E2E Tests (Node ${{ matrix.node-version }} - ${{ matrix.shard-index }}/${{ matrix.shard-count }})"
     runs-on: ubuntu-24.04
@@ -288,7 +274,7 @@ jobs:
         with:
           version: 10
       - name: Use Node.js 20
-        uses: actions/setup-node@v5
+        uses: actions/setup-node@v4
         with:
           node-version: 20.x
           cache: 'pnpm'
@@ -331,7 +317,7 @@ jobs:
         with:
           version: 10
       - name: Use Node.js 20
-        uses: actions/setup-node@v5
+        uses: actions/setup-node@v4
         with:
           node-version: 20.x
           cache: 'pnpm'
@@ -350,6 +336,74 @@ jobs:
         env:
           CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
         run: cd src-ui && pnpm run build --configuration=production
+  sonarqube-analysis:
+    name: "SonarQube Analysis"
+    runs-on: ubuntu-24.04
+    needs:
+      - tests-backend
+      - tests-frontend
+    if: github.repository_owner == 'paperless-ngx'
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v5
+        with:
+          fetch-depth: 0
+      - name: Download all backend coverage
+        uses: actions/download-artifact@v5.0.0
+        with:
+          pattern: backend-coverage-*
+          path: ./coverage/
+      - name: Download all frontend coverage
+        uses: actions/download-artifact@v5.0.0
+        with:
+          pattern: frontend-coverage-*
+          path: ./coverage/
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
+      - name: Install coverage tools
+        run: |
+          pip install coverage
+          npm install -g nyc
+      # Merge backend coverage from all Python versions
+      - name: Merge backend coverage
+        run: |
+          coverage combine coverage/backend-coverage-*/.coverage
+          coverage xml -o merged-backend-coverage.xml
+      # Merge frontend coverage from all shards
+      - name: Merge frontend coverage
+        run: |
+          # Find all coverage-final.json files from the shards, exit with error if none found
+          shopt -s nullglob
+          files=(coverage/frontend-coverage-*/coverage/coverage-final.json)
+          if [ ${#files[@]} -eq 0 ]; then
+            echo "No frontend coverage JSON found under coverage/" >&2
+            exit 1
+          fi
+          # Create .nyc_output directory and copy each shard's coverage JSON into it with a unique name
+          mkdir -p .nyc_output
+          for coverage_json in "${files[@]}"; do
+            shard=$(basename "$(dirname "$(dirname "$coverage_json")")")
+            cp "$coverage_json" ".nyc_output/${shard}.json"
+          done
+          npx nyc merge .nyc_output .nyc_output/out.json
+          npx nyc report --reporter=lcovonly --report-dir coverage
+      - name: Upload coverage artifacts
+        uses: actions/upload-artifact@v4.6.2
+        with:
+          name: merged-coverage
+          path: |
+            merged-backend-coverage.xml
+            .nyc_output/*
+            coverage/lcov.info
+          retention-days: 7
+          if-no-files-found: error
+          include-hidden-files: true
+      - name: SonarQube Analysis
+        uses: SonarSource/sonarqube-scan-action@v5
+        env:
+          SONAR_TOKEN: ${{ secrets.SONAR_TOKEN }}
   build-docker-image:
     name: Build Docker image for ${{ github.ref_name }}
     runs-on: ubuntu-24.04
@@ -473,7 +527,7 @@ jobs:
         uses: actions/checkout@v5
       - name: Set up Python
         id: setup-python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
       - name: Install uv
@@ -621,7 +675,7 @@ jobs:
           ref: main
       - name: Set up Python
         id: setup-python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
       - name: Install uv
@@ -653,7 +707,7 @@ jobs:
           git commit -am "Changelog ${{ needs.publish-release.outputs.version }} - GHA"
           git push origin ${{ needs.publish-release.outputs.version }}-changelog
       - name: Create Pull Request
-        uses: actions/github-script@v8
+        uses: actions/github-script@v7
         with:
           script: |
             const { repo, owner } = context.repo;

.github/workflows/cleanup-tags.yml

@@ -6,9 +6,10 @@
 # This workflow will not trigger runs on forked repos.
 name: Cleanup Image Tags
 on:
-  workflow_dispatch:
+  delete:
-  schedule:
+  push:
-    - cron: '0 0 * * 0'
+    paths:
+      - ".github/workflows/cleanup-tags.yml"
 concurrency:
   group: registry-tags-cleanup
   cancel-in-progress: false

.github/workflows/pr-bot.yml

@@ -12,7 +12,7 @@ jobs:
     steps:
       - name: Label PR by file path or branch name
         # see .github/labeler.yml for the labeler config
-        uses: actions/labeler@v6
+        uses: actions/labeler@v5
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
       - name: Label by size
@@ -26,7 +26,7 @@ jobs:
           fail_if_xl: 'false'
           excluded_files: /\.lock$/ /\.txt$/ ^src-ui/pnpm-lock\.yaml$ ^src-ui/messages\.xlf$ ^src/locale/en_US/LC_MESSAGES/django\.po$
       - name: Label by PR title
-        uses: actions/github-script@v8
+        uses: actions/github-script@v7
         with:
           script: |
             const pr = context.payload.pull_request;
@@ -52,7 +52,7 @@ jobs:
             }
       - name: Label bot-generated PRs
         if: ${{ contains(github.actor, 'dependabot') || contains(github.actor, 'crowdin-bot') }}
-        uses: actions/github-script@v8
+        uses: actions/github-script@v7
         with:
           script: |
             const pr = context.payload.pull_request;
@@ -77,7 +77,7 @@ jobs:
             }
       - name: Welcome comment
         if: ${{ !contains(github.actor, 'bot') }}
-        uses: actions/github-script@v8
+        uses: actions/github-script@v7
         with:
           script: |
             const pr = context.payload.pull_request;

.github/workflows/repo-maintenance.yml

@@ -15,7 +15,7 @@ jobs:
     if: github.repository_owner == 'paperless-ngx'
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/stale@v10
+      - uses: actions/stale@v9
         with:
           days-before-stale: 7
           days-before-close: 14
@@ -57,7 +57,7 @@ jobs:
     if: github.repository_owner == 'paperless-ngx'
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/github-script@v8
+      - uses: actions/github-script@v7
         with:
           script: |
             function sleep(ms) {
@@ -114,7 +114,7 @@ jobs:
     if: github.repository_owner == 'paperless-ngx'
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/github-script@v8
+      - uses: actions/github-script@v7
         with:
           script: |
             function sleep(ms) {
@@ -206,7 +206,7 @@ jobs:
     if: github.repository_owner == 'paperless-ngx'
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/github-script@v8
+      - uses: actions/github-script@v7
         with:
           script: |
             function sleep(ms) {

.github/workflows/translate-strings.yml

@@ -17,7 +17,7 @@ jobs:
           ref: ${{ github.head_ref }}
       - name: Set up Python
         id: setup-python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v5
       - name: Install system dependencies
         run: |
           sudo apt-get update -qq
@@ -38,7 +38,7 @@ jobs:
         with:
           version: 10
       - name: Use Node.js 20
-        uses: actions/setup-node@v5
+        uses: actions/setup-node@v4
         with:
           node-version: 20.x
           cache: 'pnpm'

.pre-commit-config.yaml

@@ -49,7 +49,7 @@ repos:
           - 'prettier-plugin-organize-imports@4.1.0'
   # Python hooks
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.13.2
+    rev: v0.13.0
     hooks:
       - id: ruff-check
       - id: ruff-format
@@ -59,7 +59,7 @@ repos:
       - id: pyproject-fmt
   # Dockerfile hooks
   - repo: https://github.com/AleksaC/hadolint-py
-    rev: v2.14.0
+    rev: v2.12.1b3
     hooks:
       - id: hadolint
   # Shell script hooks

Dockerfile

@@ -32,7 +32,7 @@ RUN set -eux \
 # Purpose: Installs s6-overlay and rootfs
 # Comments:
 #  - Don't leave anything extra in here either
-FROM ghcr.io/astral-sh/uv:0.8.22-python3.12-bookworm-slim AS s6-overlay-base
+FROM ghcr.io/astral-sh/uv:0.8.17-python3.12-bookworm-slim AS s6-overlay-base
 
 WORKDIR /usr/src/s6
 

docker/compose/docker-compose.portainer.yml

@@ -32,7 +32,7 @@ services:
     volumes:
       - redisdata:/data
   db:
-    image: docker.io/library/postgres:18
+    image: docker.io/library/postgres:17
     restart: unless-stopped
     volumes:
       - pgdata:/var/lib/postgresql/data

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

@@ -35,7 +35,7 @@ services:
     volumes:
       - redisdata:/data
   db:
-    image: docker.io/library/postgres:18
+    image: docker.io/library/postgres:17
     restart: unless-stopped
     volumes:
       - pgdata:/var/lib/postgresql/data

docker/compose/docker-compose.postgres.yml

@@ -31,7 +31,7 @@ services:
     volumes:
       - redisdata:/data
   db:
-    image: docker.io/library/postgres:18
+    image: docker.io/library/postgres:17
     restart: unless-stopped
     volumes:
       - pgdata:/var/lib/postgresql/data

docs/configuration.md

@@ -1805,3 +1805,23 @@ password. All of these options come from their similarly-named [Django settings]
 #### [`PAPERLESS_EMAIL_USE_SSL=<bool>`](#PAPERLESS_EMAIL_USE_SSL) {#PAPERLESS_EMAIL_USE_SSL}
 
 : Defaults to false.
+
+## Remote OCR
+
+#### [`PAPERLESS_REMOTE_OCR_ENGINE=<str>`](#PAPERLESS_REMOTE_OCR_ENGINE) {#PAPERLESS_REMOTE_OCR_ENGINE}
+
+: The remote OCR engine to use. Currently only Azure AI is supported as "azureai".
+
+    Defaults to None, which disables remote OCR.
+
+#### [`PAPERLESS_REMOTE_OCR_API_KEY=<str>`](#PAPERLESS_REMOTE_OCR_API_KEY) {#PAPERLESS_REMOTE_OCR_API_KEY}
+
+: The API key to use for the remote OCR engine.
+
+    Defaults to None.
+
+#### [`PAPERLESS_REMOTE_OCR_ENDPOINT=<str>`](#PAPERLESS_REMOTE_OCR_ENDPOINT) {#PAPERLESS_REMOTE_OCR_ENDPOINT}
+
+: The endpoint to use for the remote OCR engine. This is required for Azure AI.
+
+    Defaults to None.

docs/index.md

@@ -25,9 +25,10 @@ physical documents into a searchable online archive so you can keep, well, _less
 ## Features
 
 -   **Organize and index** your scanned documents with tags, correspondents, types, and more.
--   _Your_ data is stored locally on _your_ server and is never transmitted or shared in any way.
+-   _Your_ data is stored locally on _your_ server and is never transmitted or shared in any way, unless you explicitly choose to do so.
 -   Performs **OCR** on your documents, adding searchable and selectable text, even to documents scanned with only images.
     -   Utilizes the open-source Tesseract engine to recognize more than 100 languages.
+    -   _New!_ Supports remote OCR with Azure AI (opt-in).
 -   Documents are saved as PDF/A format which is designed for long term storage, alongside the unaltered originals.
 -   Uses machine-learning to automatically add tags, correspondents and document types to your documents.
 -   Supports PDF documents, images, plain text files, Office documents (Word, Excel, PowerPoint, and LibreOffice equivalents)[^1] and more.

docs/usage.md

@@ -414,7 +414,7 @@ fields and permissions, which will be merged.
 
 #### Types {#workflow-trigger-types}
 
-Currently, there are four events that correspond to workflow trigger 'types':
+Currently, there are three events that correspond to workflow trigger 'types':
 
 1. **Consumption Started**: _before_ a document is consumed, so events can include filters by source (mail, consumption
    folder or API), file path, file name, mail rule
@@ -427,7 +427,7 @@ Currently, there are four events that correspond to workflow trigger 'types':
    added, created, updated date or you can specify a (date) custom field. You can also specify a day offset from the date (positive
    offsets will trigger after the date, negative offsets will trigger before).
 
-The following flow diagram illustrates the four document trigger types:
+The following flow diagram illustrates the three document trigger types:
 
 ```mermaid
 flowchart TD
@@ -637,7 +637,7 @@ When you first delete a document it is moved to the 'trash' until either it is e
 You can set how long documents remain in the trash before being automatically deleted with [`PAPERLESS_EMPTY_TRASH_DELAY`](configuration.md#PAPERLESS_EMPTY_TRASH_DELAY), which defaults
 to 30 days. Until the file is actually deleted (e.g. the trash is emptied), all files and database content remains intact and can be restored at any point up until that time.
 
-Additionally you may configure a directory where deleted files are moved to when the trash is emptied with [`PAPERLESS_EMPTY_TRASH_DIR`](configuration.md#PAPERLESS_EMPTY_TRASH_DIR).
+Additionally you may configure a directory where deleted files are moved to when they the trash is emptied with [`PAPERLESS_EMPTY_TRASH_DIR`](configuration.md#PAPERLESS_EMPTY_TRASH_DIR).
 Note that the empty trash directory only stores the original file, the archive file and all database information is permanently removed once a document is fully deleted.
 
 ## Best practices {#basic-searching}
@@ -882,6 +882,21 @@ how regularly you intend to scan documents and use paperless.
     performed the task associated with the document, move it to the
     inbox.
 
+## Remote OCR
+
+!!! important
+
+    This feature is disabled by default and will always remain strictly "opt-in".
+
+Paperless-ngx supports performing OCR on documents using remote services. At the moment, this is limited to
+[Microsoft's Azure "Document Intelligence" service](https://azure.microsoft.com/en-us/products/ai-services/ai-document-intelligence).
+This is of course a paid service (with a free tier) which requires an Azure account and subscription. Azure AI is not affiliated with
+Paperless-ngx in any way. When enabled, Paperless-ngx will automatically send appropriate documents to Azure for OCR processing, bypassing
+the local OCR engine. See the [configuration](configuration.md#PAPERLESS_REMOTE_OCR_ENGINE) options for more details.
+
+Additionally, when using a commercial service with this feature, consider both potential costs as well as any associated file size
+or page limitations (e.g. with a free tier).
+
 ## Architecture
 
 Paperless-ngx consists of the following components:

pyproject.toml

@@ -15,6 +15,7 @@ classifiers = [
 # This will allow testing to not install a webserver, mysql, etc
 
 dependencies = [
+  "azure-ai-documentintelligence>=1.0.2",
   "babel>=2.17",
   "bleach~=6.2.0",
   "celery[redis]~=5.5.1",
@@ -30,10 +31,10 @@ dependencies = [
   "django-cachalot~=2.8.0",
   "django-celery-results~=2.6.0",
   "django-compression-middleware~=0.5.0",
-  "django-cors-headers~=4.9.0",
+  "django-cors-headers~=4.8.0",
   "django-extensions~=4.1",
   "django-filter~=25.1",
-  "django-guardian~=3.2.0",
+  "django-guardian~=3.1.2",
   "django-multiselectfield~=1.0.1",
   "django-soft-delete~=1.0.18",
   "django-treenode>=0.23.2",
@@ -54,6 +55,7 @@ dependencies = [
   "ocrmypdf~=16.11.0",
   "pathvalidate~=3.3.1",
   "pdf2image~=1.17.0",
+  "psycopg-pool",
   "python-dateutil~=2.9.0",
   "python-dotenv~=1.1.0",
   "python-gnupg~=0.5.4",
@@ -232,6 +234,7 @@ testpaths = [
   "src/paperless_tesseract/tests/",
   "src/paperless_tika/tests",
   "src/paperless_text/tests/",
+  "src/paperless_remote/tests/",
 ]
 addopts = [
   "--pythonwarnings=all",
@@ -254,6 +257,7 @@ PAPERLESS_DISABLE_DBHANDLER = "true"
 PAPERLESS_CACHE_BACKEND = "django.core.cache.backends.locmem.LocMemCache"
 
 [tool.coverage.run]
+relative_files = true
 source = [
   "src/",
 ]

sonar-project.properties

@@ -0,0 +1,24 @@
+sonar.projectKey=paperless-ngx_paperless-ngx
+sonar.organization=paperless-ngx
+sonar.projectName=Paperless-ngx
+sonar.projectVersion=1.0
+
+# Source and test directories
+sonar.sources=src/,src-ui/
+sonar.test.inclusions=**/test_*.py,**/tests.py,**/*.spec.ts,**/*.test.ts
+
+# Language specific settings
+sonar.python.version=3.10,3.11,3.12,3.13
+
+# Coverage reports
+sonar.python.coverage.reportPaths=merged-backend-coverage.xml
+sonar.javascript.lcov.reportPaths=coverage/lcov.info
+
+# Test execution reports
+sonar.junit.reportPaths=**/junit.xml,**/test-results.xml
+
+# Encoding
+sonar.sourceEncoding=UTF-8
+
+# Exclusions
+sonar.exclusions=**/migrations/**,**/node_modules/**,**/static/**,**/venv/**,**/.venv/**,**/dist/**

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

@@ -174,7 +174,7 @@ test('bulk edit', async ({ page }) => {
   await expect(page.locator('pngx-document-list')).toHaveText(
     /Selected 61 of 61 documents/i
   )
-  await page.getByRole('button', { name: 'None' }).click()
+  await page.getByRole('button', { name: 'Cancel' }).click()
 
   await page.locator('pngx-document-card-small').nth(1).click()
   await page.locator('pngx-document-card-small').nth(2).click()

src-ui/package.json

@@ -11,17 +11,17 @@
   },
   "private": true,
   "dependencies": {
-    "@angular/cdk": "^20.2.6",
+    "@angular/cdk": "^20.2.2",
-    "@angular/common": "~20.3.2",
+    "@angular/common": "~20.2.4",
-    "@angular/compiler": "~20.3.2",
+    "@angular/compiler": "~20.2.4",
-    "@angular/core": "~20.3.2",
+    "@angular/core": "~20.2.4",
-    "@angular/forms": "~20.3.2",
+    "@angular/forms": "~20.2.4",
-    "@angular/localize": "~20.3.2",
+    "@angular/localize": "~20.2.4",
-    "@angular/platform-browser": "~20.3.2",
+    "@angular/platform-browser": "~20.2.4",
-    "@angular/platform-browser-dynamic": "~20.3.2",
+    "@angular/platform-browser-dynamic": "~20.2.4",
-    "@angular/router": "~20.3.2",
+    "@angular/router": "~20.2.4",
     "@ng-bootstrap/ng-bootstrap": "^19.0.1",
-    "@ng-select/ng-select": "^20.2.2",
+    "@ng-select/ng-select": "^20.1.3",
     "@ngneat/dirty-check-forms": "^3.0.3",
     "@popperjs/core": "^2.11.8",
     "bootstrap": "^5.3.8",
@@ -29,48 +29,47 @@
     "mime-names": "^1.0.0",
     "ng2-pdf-viewer": "^10.4.0",
     "ngx-bootstrap-icons": "^1.9.3",
-    "ngx-color": "^10.1.0",
+    "ngx-color": "^10.0.0",
     "ngx-cookie-service": "^20.1.0",
     "ngx-device-detector": "^10.1.0",
     "ngx-ui-tour-ng-bootstrap": "^17.0.1",
     "rxjs": "^7.8.2",
     "tslib": "^2.8.1",
     "utif": "^3.1.0",
-    "uuid": "^13.0.0",
+    "uuid": "^11.1.0",
     "zone.js": "^0.15.1"
   },
   "devDependencies": {
     "@angular-builders/custom-webpack": "^20.0.0",
     "@angular-builders/jest": "^20.0.0",
-    "@angular-devkit/core": "^20.3.3",
+    "@angular-devkit/core": "^20.2.2",
-    "@angular-devkit/schematics": "^20.3.3",
+    "@angular-devkit/schematics": "^20.2.2",
-    "@angular-eslint/builder": "20.3.0",
+    "@angular-eslint/builder": "20.2.0",
-    "@angular-eslint/eslint-plugin": "20.3.0",
+    "@angular-eslint/eslint-plugin": "20.2.0",
-    "@angular-eslint/eslint-plugin-template": "20.3.0",
+    "@angular-eslint/eslint-plugin-template": "20.2.0",
-    "@angular-eslint/schematics": "20.3.0",
+    "@angular-eslint/schematics": "20.2.0",
-    "@angular-eslint/template-parser": "20.3.0",
+    "@angular-eslint/template-parser": "20.2.0",
-    "@angular/build": "^20.3.3",
+    "@angular/build": "^20.2.2",
-    "@angular/cli": "~20.3.3",
+    "@angular/cli": "~20.2.2",
-    "@angular/compiler-cli": "~20.3.2",
+    "@angular/compiler-cli": "~20.2.4",
     "@codecov/webpack-plugin": "^1.9.1",
-    "@playwright/test": "^1.55.1",
+    "@playwright/test": "^1.55.0",
     "@types/jest": "^30.0.0",
-    "@types/node": "^24.6.1",
+    "@types/node": "^24.3.0",
-    "@typescript-eslint/eslint-plugin": "^8.45.0",
+    "@typescript-eslint/eslint-plugin": "^8.41.0",
-    "@typescript-eslint/parser": "^8.45.0",
+    "@typescript-eslint/parser": "^8.41.0",
-    "@typescript-eslint/utils": "^8.45.0",
+    "@typescript-eslint/utils": "^8.41.0",
-    "eslint": "^9.36.0",
+    "eslint": "^9.34.0",
-    "jest": "30.2.0",
+    "jest": "30.1.3",
-    "jest-environment-jsdom": "^30.2.0",
+    "jest-environment-jsdom": "^30.1.2",
     "jest-junit": "^16.0.0",
-    "jest-preset-angular": "^15.0.2",
+    "jest-preset-angular": "^15.0.0",
     "jest-websocket-mock": "^2.5.0",
-    "prettier-plugin-organize-imports": "^4.3.0",
+    "prettier-plugin-organize-imports": "^4.2.0",
     "ts-node": "~10.9.1",
     "typescript": "^5.8.3",
-    "webpack": "^5.102.0"
+    "webpack": "^5.101.3"
   },
-  "packageManager": "pnpm@10.17.1",
   "pnpm": {
     "onlyBuiltDependencies": [
       "@parcel/watcher",

src-ui/setup-jest.ts

@@ -145,14 +145,4 @@ HTMLCanvasElement.prototype.getContext = <
   typeof HTMLCanvasElement.prototype.getContext
 >jest.fn()
 
-jest.mock('uuid', () => ({
-  v4: jest.fn(() =>
-    'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx'.replace(/[xy]/g, (char: string) => {
-      const random = Math.floor(Math.random() * 16)
-      const value = char === 'x' ? random : (random & 0x3) | 0x8
-      return value.toString(16)
-    })
-  ),
-}))
-
 jest.mock('pdfjs-dist')

src-ui/src/app/components/admin/tasks/tasks.component.spec.ts

@@ -16,7 +16,6 @@ import {
   NgbNavItem,
 } from '@ng-bootstrap/ng-bootstrap'
 import { allIcons, NgxBootstrapIconsModule } from 'ngx-bootstrap-icons'
-import { throwError } from 'rxjs'
 import { routes } from 'src/app/app-routing.module'
 import {
   PaperlessTask,
@@ -29,7 +28,6 @@ import { PermissionsGuard } from 'src/app/guards/permissions.guard'
 import { CustomDatePipe } from 'src/app/pipes/custom-date.pipe'
 import { PermissionsService } from 'src/app/services/permissions.service'
 import { TasksService } from 'src/app/services/tasks.service'
-import { ToastService } from 'src/app/services/toast.service'
 import { environment } from 'src/environments/environment'
 import { ConfirmDialogComponent } from '../../common/confirm-dialog/confirm-dialog.component'
 import { PageHeaderComponent } from '../../common/page-header/page-header.component'
@@ -125,7 +123,6 @@ describe('TasksComponent', () => {
   let router: Router
   let httpTestingController: HttpTestingController
   let reloadSpy
-  let toastService: ToastService
 
   beforeEach(async () => {
     TestBed.configureTestingModule({
@@ -160,7 +157,6 @@ describe('TasksComponent', () => {
     httpTestingController = TestBed.inject(HttpTestingController)
     modalService = TestBed.inject(NgbModal)
     router = TestBed.inject(Router)
-    toastService = TestBed.inject(ToastService)
     fixture = TestBed.createComponent(TasksComponent)
     component = fixture.componentInstance
     jest.useFakeTimers()
@@ -253,42 +249,6 @@ describe('TasksComponent', () => {
     expect(dismissSpy).toHaveBeenCalledWith(selected)
   })
 
-  it('should show an error and re-enable modal buttons when dismissing multiple tasks fails', () => {
-    component.selectedTasks = new Set([tasks[0].id, tasks[1].id])
-    const error = new Error('dismiss failed')
-    const toastSpy = jest.spyOn(toastService, 'showError')
-    const dismissSpy = jest
-      .spyOn(tasksService, 'dismissTasks')
-      .mockReturnValue(throwError(() => error))
-
-    let modal: NgbModalRef
-    modalService.activeInstances.subscribe((m) => (modal = m[m.length - 1]))
-
-    component.dismissTasks()
-    expect(modal).not.toBeUndefined()
-
-    modal.componentInstance.confirmClicked.emit()
-
-    expect(dismissSpy).toHaveBeenCalledWith(new Set([tasks[0].id, tasks[1].id]))
-    expect(toastSpy).toHaveBeenCalledWith('Error dismissing tasks', error)
-    expect(modal.componentInstance.buttonsEnabled).toBe(true)
-    expect(component.selectedTasks.size).toBe(0)
-  })
-
-  it('should show an error when dismissing a single task fails', () => {
-    const error = new Error('dismiss failed')
-    const toastSpy = jest.spyOn(toastService, 'showError')
-    const dismissSpy = jest
-      .spyOn(tasksService, 'dismissTasks')
-      .mockReturnValue(throwError(() => error))
-
-    component.dismissTask(tasks[0])
-
-    expect(dismissSpy).toHaveBeenCalledWith(new Set([tasks[0].id]))
-    expect(toastSpy).toHaveBeenCalledWith('Error dismissing task', error)
-    expect(component.selectedTasks.size).toBe(0)
-  })
-
   it('should support dismiss all tasks', () => {
     let modal: NgbModalRef
     modalService.activeInstances.subscribe((m) => (modal = m[m.length - 1]))

src-ui/src/app/components/admin/tasks/tasks.component.ts

@@ -24,7 +24,6 @@ import { PaperlessTask } from 'src/app/data/paperless-task'
 import { IfPermissionsDirective } from 'src/app/directives/if-permissions.directive'
 import { CustomDatePipe } from 'src/app/pipes/custom-date.pipe'
 import { TasksService } from 'src/app/services/tasks.service'
-import { ToastService } from 'src/app/services/toast.service'
 import { ConfirmDialogComponent } from '../../common/confirm-dialog/confirm-dialog.component'
 import { PageHeaderComponent } from '../../common/page-header/page-header.component'
 import { LoadingComponentWithPermissions } from '../../loading-component/loading.component'
@@ -73,7 +72,6 @@ export class TasksComponent
   tasksService = inject(TasksService)
   private modalService = inject(NgbModal)
   private readonly router = inject(Router)
-  private readonly toastService = inject(ToastService)
 
   public activeTab: TaskTab
   public selectedTasks: Set<number> = new Set()
@@ -156,19 +154,11 @@ export class TasksComponent
       modal.componentInstance.confirmClicked.pipe(first()).subscribe(() => {
         modal.componentInstance.buttonsEnabled = false
         modal.close()
-        this.tasksService.dismissTasks(tasks).subscribe({
+        this.tasksService.dismissTasks(tasks)
-          error: (e) => {
-            this.toastService.showError($localize`Error dismissing tasks`, e)
-            modal.componentInstance.buttonsEnabled = true
-          },
-        })
         this.clearSelection()
       })
     } else {
-      this.tasksService.dismissTasks(tasks).subscribe({
+      this.tasksService.dismissTasks(tasks)
-        error: (e) =>
-          this.toastService.showError($localize`Error dismissing task`, e),
-      })
       this.clearSelection()
     }
   }

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

@@ -41,3 +41,9 @@
     min-width: 140px;
   }
 }
+
+.btn-group-xs {
+  > .btn {
+    border-radius: 0.15rem;
+  }
+}

src-ui/src/app/components/common/edit-dialog/custom-field-edit-dialog/custom-field-edit-dialog.component.ts

@@ -177,16 +177,10 @@ export class CustomFieldEditDialogComponent
   }
 
   public removeSelectOption(index: number) {
-    const globalIndex =
+    this.selectOptions.removeAt(index)
-      index + (this.selectOptionsPage - 1) * SELECT_OPTION_PAGE_SIZE
+    this._allSelectOptions.splice(
-    this._allSelectOptions.splice(globalIndex, 1)
+      index + (this.selectOptionsPage - 1) * SELECT_OPTION_PAGE_SIZE,
-
+      1
-    const totalPages = Math.max(
-      1,
-      Math.ceil(this._allSelectOptions.length / SELECT_OPTION_PAGE_SIZE)
     )
-    const targetPage = Math.min(this.selectOptionsPage, totalPages)
-
-    this.selectOptionsPage = targetPage
   }
 }

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

@@ -1,18 +1,19 @@
 <div class="mb-3">
   @if (title) {
-    <label class="form-label" [for]="inputId">{{title}}</label>
+    <label [for]="inputId">{{title}}</label>
   }
 
   <div class="input-group" [class.is-invalid]="error">
-    <button type="button" class="input-group-text" [style.background-color]="value" (click)="colorPicker.toggle()">&nbsp;&nbsp;&nbsp;</button>
+    <span class="input-group-text" [style.background-color]="value">&nbsp;&nbsp;&nbsp;</span>
 
     <ng-template #popContent>
       <div style="min-width: 200px;" class="pb-3">
         <color-slider [color]="value" (onChangeComplete)="colorChanged($event.color.hex)"></color-slider>
       </div>
+
     </ng-template>
 
-    <input #inputField class="form-control" [class.is-invalid]="error" [id]="inputId" [(ngModel)]="value" (change)="onChange(value)" [autoClose]="'outside'" [ngbPopover]="popContent" #colorPicker="ngbPopover" placement="bottom" popoverClass="shadow">
+    <input #inputField class="form-control" [class.is-invalid]="error" [id]="inputId" [(ngModel)]="value" (change)="onChange(value)" [autoClose]="'outside'" [ngbPopover]="popContent" placement="bottom" popoverClass="shadow">
 
     <button class="btn btn-outline-secondary" type="button" (click)="randomize()">
       <i-bs name="dice5"></i-bs>

src-ui/src/app/components/common/input/color/color.component.spec.ts

@@ -42,8 +42,8 @@ describe('ColorComponent', () => {
   })
 
   it('should set swatch color', () => {
-    const swatch: HTMLButtonElement = fixture.nativeElement.querySelector(
+    const swatch: HTMLSpanElement = fixture.nativeElement.querySelector(
-      'button.input-group-text'
+      'span.input-group-text'
     )
     expect(swatch.style.backgroundColor).toEqual('')
     component.value = '#ff0000'

src-ui/src/app/components/common/page-header/page-header.component.html

@@ -1,10 +1,7 @@
 <div class="row pt-3 pb-3 pb-md-2 align-items-center">
   <div class="col-md text-truncate">
-    <h3 class="text-truncate d-flex align-items-center" style="line-height: 1.4">
+    <h3 class="text-truncate" style="line-height: 1.4">
       {{title}}
-      @if (id) {
-        <span class="badge bg-primary text-primary-text-contrast ms-2 small fs-normal">ID: {{id}}</span>
-      }
       @if (subTitle) {
         <span class="h6 mb-0 d-block d-md-inline fw-normal ms-md-3 text-truncate" style="line-height: 1.4">{{subTitle}}</span>
       }

src-ui/src/app/components/common/page-header/page-header.component.scss

@@ -1,10 +1,5 @@
 h3 {
     min-height: calc(1.325rem + 0.9vw);
-
-    .badge {
-        font-size: 0.65rem;
-        line-height: 1;
-    }
 }
 
 @media (min-width: 1200px) {

src-ui/src/app/components/common/page-header/page-header.component.ts

@@ -26,9 +26,6 @@ export class PageHeaderComponent {
     return this._title
   }
 
-  @Input()
-  id: number
-
   @Input()
   subTitle: string = ''
 

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

@@ -1,4 +1,4 @@
-<pngx-page-header [(title)]="title" [id]="documentId">
+<pngx-page-header [(title)]="title">
   @if (archiveContentRenderType === ContentRenderType.PDF && !useNativePdfViewer) {
     @if (previewNumPages) {
       <div class="input-group input-group-sm d-none d-md-flex">

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

@@ -1212,7 +1212,7 @@ describe('DocumentDetailComponent', () => {
   it('should support keyboard shortcuts', () => {
     initNormally()
 
-    const hasNextSpy = jest.spyOn(component, 'hasNext').mockReturnValue(true)
+    jest.spyOn(component, 'hasNext').mockReturnValue(true)
     const nextSpy = jest.spyOn(component, 'nextDoc')
     document.dispatchEvent(
       new KeyboardEvent('keydown', { key: 'arrowright', ctrlKey: true })
@@ -1226,32 +1226,21 @@ describe('DocumentDetailComponent', () => {
     )
     expect(prevSpy).toHaveBeenCalled()
 
-    const isDirtySpy = jest
+    jest.spyOn(openDocumentsService, 'isDirty').mockReturnValue(true)
-      .spyOn(openDocumentsService, 'isDirty')
-      .mockReturnValue(true)
     const saveSpy = jest.spyOn(component, 'save')
     document.dispatchEvent(
       new KeyboardEvent('keydown', { key: 's', ctrlKey: true })
     )
     expect(saveSpy).toHaveBeenCalled()
 
-    hasNextSpy.mockReturnValue(true)
+    jest.spyOn(openDocumentsService, 'isDirty').mockReturnValue(true)
+    jest.spyOn(component, 'hasNext').mockReturnValue(true)
     const saveNextSpy = jest.spyOn(component, 'saveEditNext')
     document.dispatchEvent(
       new KeyboardEvent('keydown', { key: 's', ctrlKey: true, shiftKey: true })
     )
     expect(saveNextSpy).toHaveBeenCalled()
 
-    saveSpy.mockClear()
-    saveNextSpy.mockClear()
-    isDirtySpy.mockReturnValue(true)
-    hasNextSpy.mockReturnValue(false)
-    document.dispatchEvent(
-      new KeyboardEvent('keydown', { key: 's', ctrlKey: true, shiftKey: true })
-    )
-    expect(saveNextSpy).not.toHaveBeenCalled()
-    expect(saveSpy).toHaveBeenCalledWith(true)
-
     const closeSpy = jest.spyOn(component, 'close')
     document.dispatchEvent(new KeyboardEvent('keydown', { key: 'escape' }))
     expect(closeSpy).toHaveBeenCalled()

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

@@ -615,10 +615,7 @@ export class DocumentDetailComponent
       })
       .pipe(takeUntil(this.unsubscribeNotifier))
       .subscribe(() => {
-        if (this.openDocumentService.isDirty(this.document)) {
+        if (this.openDocumentService.isDirty(this.document)) this.saveEditNext()
-          if (this.hasNext()) this.saveEditNext()
-          else this.save(true)
-        }
       })
   }
 

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

@@ -1,5 +1,21 @@
 <div class="d-flex flex-wrap gap-4">
-  <div class="d-flex flex-wrap align-items-center gap-2" *pngxIfPermissions="{ action: PermissionAction.Change, type: PermissionType.Document }">
+  <div class="d-flex align-items-center" role="group" aria-label="Select">
+    <button class="btn btn-sm btn-outline-secondary" (click)="list.selectNone()">
+      <i-bs name="slash-circle"></i-bs>&nbsp;<ng-container i18n>Cancel</ng-container>
+      </button>
+    </div>
+    <div class="d-flex align-items-center gap-2" role="group" aria-label="Select">
+      <label class="me-2" i18n>Select:</label>
+      <div class="btn-group">
+        <button class="btn btn-sm btn-outline-primary" (click)="list.selectPage()">
+          <i-bs name="file-earmark-check"></i-bs>&nbsp;<ng-container i18n>Page</ng-container>
+          </button>
+          <button class="btn btn-sm btn-outline-primary" (click)="list.selectAll()">
+            <i-bs name="check-all"></i-bs>&nbsp;<ng-container i18n>All</ng-container>
+            </button>
+          </div>
+        </div>
+        <div class="d-flex align-items-center gap-2" *pngxIfPermissions="{ action: PermissionAction.Change, type: PermissionType.Document }">
           <label class="me-2" i18n>Edit:</label>
           @if (permissionService.currentUserCan(PermissionAction.View, PermissionType.Tag)) {
             <pngx-filterable-dropdown title="Tags" icon="tag-fill" i18n-title
@@ -73,14 +89,14 @@
               (apply)="setCustomFields($event)">
             </pngx-filterable-dropdown>
           }
-    <div class="btn-group">
-      <button type="button" class="btn btn-sm btn-outline-primary me-2" (click)="setPermissions()" [disabled]="!userOwnsAll || !userCanEditAll">
-        <i-bs name="person-fill-lock"></i-bs><div class="d-none d-sm-inline">&nbsp;<ng-container i18n>Permissions</ng-container></div>
-      </button>
-    </div>
         </div>
         <div class="d-flex align-items-center gap-2 ms-auto">
           <div class="btn-toolbar">
+
+            <button type="button" class="btn btn-sm btn-outline-primary me-2" (click)="setPermissions()" [disabled]="!userOwnsAll || !userCanEditAll">
+              <i-bs name="person-fill-lock"></i-bs><div class="d-none d-sm-inline">&nbsp;<ng-container i18n>Permissions</ng-container></div>
+            </button>
+
             <div ngbDropdown>
               <button class="btn btn-sm btn-outline-primary" id="dropdownSelect" [disabled]="!userCanEdit && !userCanAdd" ngbDropdownToggle>
                 <i-bs name="three-dots"></i-bs>
@@ -99,6 +115,7 @@
               </div>
             </div>
           </div>
+
             <div class="btn-group btn-group-sm">
               <button class="btn btn-sm btn-outline-primary" [disabled]="awaitingDownload" (click)="downloadSelected()">
                 @if (!awaitingDownload) {

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

@@ -5,7 +5,3 @@
 .dropdown-menu{
     --bs-dropdown-min-width: 12rem;
 }
-
-.btn-group .btn {
-  white-space: nowrap;
-}

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

@@ -1,36 +1,16 @@
 <pngx-page-header [title]="getTitle()">
-  <div ngbDropdown class="btn-group flex-fill d-sm-none">
+
-    <button class="btn btn-sm btn-outline-primary" id="dropdownSelectMobile" ngbDropdownToggle>
+  <div ngbDropdown class="btn-group flex-fill">
+    <button class="btn btn-sm btn-outline-primary" id="dropdownSelect" ngbDropdownToggle>
       <i-bs name="text-indent-left"></i-bs>
       <div class="d-none d-sm-inline">&nbsp;<ng-container i18n>Select</ng-container></div>
-      @if (list.selected.size > 0) {
-        <pngx-clearable-badge [selected]="list.selected.size > 0" [number]="list.selected.size" (cleared)="list.selectNone()"></pngx-clearable-badge><span class="visually-hidden">selected</span>
-      }
     </button>
-    <div ngbDropdownMenu aria-labelledby="dropdownSelectMobile" class="shadow">
+    <div ngbDropdownMenu aria-labelledby="dropdownSelect" class="shadow">
       <button ngbDropdownItem (click)="list.selectNone()" i18n>Select none</button>
       <button ngbDropdownItem (click)="list.selectPage()" i18n>Select page</button>
       <button ngbDropdownItem (click)="list.selectAll()" i18n>Select all</button>
     </div>
   </div>
-  <div class="d-none d-sm-flex flex-fill me-3">
-    <div class="input-group input-group-sm">
-      <span class="input-group-text border-0">Select:</span>
-    </div>
-    <div class="btn-group btn-group-sm flex-nowrap">
-      @if (list.selected.size > 0) {
-        <button class="btn btn-sm btn-outline-secondary" (click)="list.selectNone()">
-          <i-bs name="slash-circle"></i-bs>&nbsp;<ng-container i18n>None</ng-container>
-        </button>
-      }
-      <button class="btn btn-sm btn-outline-primary" (click)="list.selectPage()">
-        <i-bs name="file-earmark-check"></i-bs>&nbsp;<ng-container i18n>Page</ng-container>
-      </button>
-      <button class="btn btn-sm btn-outline-primary" (click)="list.selectAll()">
-        <i-bs name="check-all"></i-bs>&nbsp;<ng-container i18n>All</ng-container>
-      </button>
-    </div>
-  </div>
   <div ngbDropdown class="btn-group flex-fill">
     <button class="btn btn-sm btn-outline-primary" id="dropdownDisplayFields" ngbDropdownToggle>
       <i-bs name="card-heading"></i-bs>
@@ -148,11 +128,6 @@
           <i-bs width="1em" height="1em" name="x"></i-bs><small i18n>Reset filters</small>
           </button>
         }
-      @if (!list.isReloading && list.selected.size > 0) {
-        <button class="btn btn-link py-0" (click)="list.selectNone()">
-          <i-bs width="1em" height="1em" name="slash-circle" class="me-1"></i-bs><small i18n>Clear selection</small>
-        </button>
-      }
       </div>
       @if (list.collectionSize) {
         <ngb-pagination [pageSize]="list.pageSize" [collectionSize]="list.collectionSize" [(page)]="list.currentPage" [maxSize]="5"

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

@@ -56,7 +56,6 @@ import {
   filterRulesDiffer,
   isFullTextFilterRule,
 } from 'src/app/utils/filter-rules'
-import { ClearableBadgeComponent } from '../common/clearable-badge/clearable-badge.component'
 import { CustomFieldDisplayComponent } from '../common/custom-field-display/custom-field-display.component'
 import { PageHeaderComponent } from '../common/page-header/page-header.component'
 import { PreviewPopupComponent } from '../common/preview-popup/preview-popup.component'
@@ -73,7 +72,6 @@ import { SaveViewConfigDialogComponent } from './save-view-config-dialog/save-vi
   templateUrl: './document-list.component.html',
   styleUrls: ['./document-list.component.scss'],
   imports: [
-    ClearableBadgeComponent,
     CustomFieldDisplayComponent,
     PageHeaderComponent,
     BulkEditorComponent,

src-ui/src/app/services/tasks.service.spec.ts

@@ -51,7 +51,7 @@ describe('TasksService', () => {
   })
 
   it('calls acknowledge_tasks api endpoint on dismiss and reloads', () => {
-    tasksService.dismissTasks(new Set([1, 2, 3])).subscribe()
+    tasksService.dismissTasks(new Set([1, 2, 3]))
     const req = httpTestingController.expectOne(
       `${environment.apiBaseUrl}tasks/acknowledge/`
     )

src-ui/src/app/services/tasks.service.ts

@@ -1,7 +1,7 @@
 import { HttpClient } from '@angular/common/http'
 import { Injectable, inject } from '@angular/core'
 import { Observable, Subject } from 'rxjs'
-import { first, takeUntil, tap } from 'rxjs/operators'
+import { first, takeUntil } from 'rxjs/operators'
 import {
   PaperlessTask,
   PaperlessTaskName,
@@ -68,17 +68,14 @@ export class TasksService {
   }
 
   public dismissTasks(task_ids: Set<number>) {
-    return this.http
+    this.http
       .post(`${this.baseUrl}tasks/acknowledge/`, {
         tasks: [...task_ids],
       })
-      .pipe(
+      .pipe(first())
-        first(),
+      .subscribe((r) => {
-        takeUntil(this.unsubscribeNotifer),
-        tap(() => {
         this.reload()
       })
-      )
   }
 
   public cancelPending(): void {

src/documents/barcodes.py

@@ -164,9 +164,6 @@ class BarcodePlugin(ConsumeTaskPlugin):
                         mailrule_id=self.input_doc.mailrule_id,
                         # Can't use same folder or the consume might grab it again
                         original_file=(tmp_dir / new_document.name).resolve(),
-                        # Adding optional original_path for later uses in
-                        # workflow matching
-                        original_path=self.input_doc.original_file,
                     ),
                     # All the same metadata
                     self.metadata,

src/documents/data_models.py

@@ -156,7 +156,6 @@ class ConsumableDocument:
 
     source: DocumentSource
     original_file: Path
-    original_path: Path | None = None
     mailrule_id: int | None = None
     mime_type: str = dataclasses.field(init=False, default=None)
 

src/documents/management/commands/document_fuzzy_match.py

@@ -92,9 +92,6 @@ class Command(MultiProcessMixin, ProgressBarMixin, BaseCommand):
                 # doc to doc is obviously not useful
                 if first_doc.pk == second_doc.pk:
                     continue
-                # Skip empty documents (e.g. password-protected)
-                if first_doc.content.strip() == "" or second_doc.content.strip() == "":
-                    continue
                 # Skip matching which have already been matched together
                 # doc 1 to doc 2 is the same as doc 2 to doc 1
                 doc_1_to_doc_2 = (first_doc.pk, second_doc.pk)

src/documents/matching.py

@@ -314,19 +314,11 @@ def consumable_document_matches_workflow(
         trigger_matched = False
 
     # Document path vs trigger path
-
-    # Use the original_path if set, else us the original_file
-    match_against = (
-        document.original_path
-        if document.original_path is not None
-        else document.original_file
-    )
-
     if (
         trigger.filter_path is not None
         and len(trigger.filter_path) > 0
         and not fnmatch(
-            match_against,
+            document.original_file,
             trigger.filter_path,
         )
     ):

src/documents/permissions.py

@@ -161,21 +161,3 @@ class PaperlessNotePermissions(BasePermission):
         perms = self.perms_map[request.method]
 
         return request.user.has_perms(perms)
-
-
-class AcknowledgeTasksPermissions(BasePermission):
-    """
-    Permissions class that checks for model permissions for acknowledging tasks.
-    """
-
-    perms_map = {
-        "POST": ["documents.change_paperlesstask"],
-    }
-
-    def has_permission(self, request, view):
-        if not request.user or not request.user.is_authenticated:  # pragma: no cover
-            return False
-
-        perms = self.perms_map.get(request.method, [])
-
-        return request.user.has_perms(perms)

src/documents/sanity_checker.py

@@ -76,9 +76,7 @@ def check_sanity(*, progress=False, scheduled=True) -> SanityCheckMessages:
     messages = SanityCheckMessages()
 
     present_files = {
-        x.resolve()
+        x.resolve() for x in Path(settings.MEDIA_ROOT).glob("**/*") if not x.is_dir()
-        for x in Path(settings.MEDIA_ROOT).glob("**/*")
-        if not x.is_dir() and x.name not in settings.IGNORABLE_FILES
     }
 
     lockfile = Path(settings.MEDIA_LOCK).resolve()

src/documents/serialisers.py

@@ -6,7 +6,6 @@ import re
 from datetime import datetime
 from decimal import Decimal
 from typing import TYPE_CHECKING
-from typing import Literal
 
 import magic
 from celery import states
@@ -253,35 +252,6 @@ class OwnedObjectSerializer(
             except KeyError:
                 pass
 
-    def _get_perms(self, obj, codename: str, target: Literal["users", "groups"]):
-        """
-        Get the given permissions from context or from django-guardian.
-
-        :param codename: The permission codename, e.g. 'view' or 'change'
-        :param target: 'users' or 'groups'
-        """
-        key = f"{target}_{codename}_perms"
-        cached = self.context.get(key, {}).get(obj.pk)
-        if cached is not None:
-            return list(cached)
-
-        # Permission not found in the context, get it from guardian
-        if target == "users":
-            return list(
-                get_users_with_perms(
-                    obj,
-                    only_with_perms_in=[f"{codename}_{obj.__class__.__name__.lower()}"],
-                    with_group_users=False,
-                ).values_list("id", flat=True),
-            )
-        else:  # groups
-            return list(
-                get_groups_with_only_permission(
-                    obj,
-                    codename=f"{codename}_{obj.__class__.__name__.lower()}",
-                ).values_list("id", flat=True),
-            )
-
     @extend_schema_field(
         field={
             "type": "object",
@@ -316,14 +286,31 @@ class OwnedObjectSerializer(
         },
     )
     def get_permissions(self, obj) -> dict:
+        view_codename = f"view_{obj.__class__.__name__.lower()}"
+        change_codename = f"change_{obj.__class__.__name__.lower()}"
+
         return {
             "view": {
-                "users": self._get_perms(obj, "view", "users"),
+                "users": get_users_with_perms(
-                "groups": self._get_perms(obj, "view", "groups"),
+                    obj,
+                    only_with_perms_in=[view_codename],
+                    with_group_users=False,
+                ).values_list("id", flat=True),
+                "groups": get_groups_with_only_permission(
+                    obj,
+                    codename=view_codename,
+                ).values_list("id", flat=True),
             },
             "change": {
-                "users": self._get_perms(obj, "change", "users"),
+                "users": get_users_with_perms(
-                "groups": self._get_perms(obj, "change", "groups"),
+                    obj,
+                    only_with_perms_in=[change_codename],
+                    with_group_users=False,
+                ).values_list("id", flat=True),
+                "groups": get_groups_with_only_permission(
+                    obj,
+                    codename=change_codename,
+                ).values_list("id", flat=True),
             },
         }
 

src/documents/tests/test_api_tasks.py

@@ -135,44 +135,6 @@ class TestTasks(DirectoriesMixin, APITestCase):
         response = self.client.get(self.ENDPOINT + "?acknowledged=false")
         self.assertEqual(len(response.data), 0)
 
-    def test_acknowledge_tasks_requires_change_permission(self):
-        """
-        GIVEN:
-            - A regular user initially without change permissions
-            - A regular user with change permissions
-        WHEN:
-            - API call is made to acknowledge tasks
-        THEN:
-            - The first user is forbidden from acknowledging tasks
-            - The second user is allowed to acknowledge tasks
-        """
-        regular_user = User.objects.create_user(username="test")
-        self.client.force_authenticate(user=regular_user)
-
-        task = PaperlessTask.objects.create(
-            task_id=str(uuid.uuid4()),
-            task_file_name="task_one.pdf",
-        )
-
-        response = self.client.post(
-            self.ENDPOINT + "acknowledge/",
-            {"tasks": [task.id]},
-        )
-        self.assertEqual(response.status_code, status.HTTP_403_FORBIDDEN)
-
-        regular_user2 = User.objects.create_user(username="test2")
-        regular_user2.user_permissions.add(
-            Permission.objects.get(codename="change_paperlesstask"),
-        )
-        regular_user2.save()
-        self.client.force_authenticate(user=regular_user2)
-
-        response = self.client.post(
-            self.ENDPOINT + "acknowledge/",
-            {"tasks": [task.id]},
-        )
-        self.assertEqual(response.status_code, status.HTTP_200_OK)
-
     def test_tasks_owner_aware(self):
         """
         GIVEN:

src/documents/tests/test_barcodes.py

@@ -614,16 +614,14 @@ class TestBarcodeNewConsume(
             self.assertIsNotFile(temp_copy)
 
             # Check the split files exist
-            # Check the original_path is set
             # Check the source is unchanged
             # Check the overrides are unchanged
             for (
                 new_input_doc,
                 new_doc_overrides,
             ) in self.get_all_consume_delay_call_args():
-                self.assertIsFile(new_input_doc.original_file)
-                self.assertEqual(new_input_doc.original_path, temp_copy)
                 self.assertEqual(new_input_doc.source, DocumentSource.ConsumeFolder)
+                self.assertIsFile(new_input_doc.original_file)
                 self.assertEqual(overrides, new_doc_overrides)
 
 

src/documents/tests/test_management_fuzzy.py

@@ -206,29 +206,3 @@ class TestFuzzyMatchCommand(TestCase):
         self.assertEqual(Document.objects.count(), 2)
         self.assertIsNotNone(Document.objects.get(pk=1))
         self.assertIsNotNone(Document.objects.get(pk=2))
-
-    def test_empty_content(self):
-        """
-        GIVEN:
-            - 2 documents exist, content is empty (pw-protected)
-        WHEN:
-            - Command is called
-        THEN:
-            - No matches are found
-        """
-        Document.objects.create(
-            checksum="BEEFCAFE",
-            title="A",
-            content="",
-            mime_type="application/pdf",
-            filename="test.pdf",
-        )
-        Document.objects.create(
-            checksum="DEADBEAF",
-            title="A",
-            content="",
-            mime_type="application/pdf",
-            filename="other_test.pdf",
-        )
-        stdout, _ = self.call_command()
-        self.assertIn("No matches found", stdout)

src/documents/tests/test_sanity_check.py

@@ -169,13 +169,6 @@ class TestSanityCheck(DirectoriesMixin, TestCase):
         messages = check_sanity()
         self.assertFalse(messages.has_warning)
 
-    def test_ignore_ignorable_files(self):
-        self.make_test_data()
-        Path(self.dirs.media_dir, ".DS_Store").touch()
-        Path(self.dirs.media_dir, "desktop.ini").touch()
-        messages = check_sanity()
-        self.assertFalse(messages.has_warning)
-
     def test_archive_filename_no_checksum(self):
         doc = self.make_test_data()
         doc.archive_checksum = None

src/documents/tests/test_views.py

@@ -1,23 +1,17 @@
-import json
 import tempfile
 from datetime import timedelta
 from pathlib import Path
 
 from django.conf import settings
-from django.contrib.auth.models import Group
 from django.contrib.auth.models import Permission
 from django.contrib.auth.models import User
-from django.db import connection
 from django.test import TestCase
 from django.test import override_settings
-from django.test.utils import CaptureQueriesContext
 from django.utils import timezone
-from guardian.shortcuts import assign_perm
 from rest_framework import status
 
 from documents.models import Document
 from documents.models import ShareLink
-from documents.models import Tag
 from documents.tests.utils import DirectoriesMixin
 from paperless.models import ApplicationConfiguration
 
@@ -160,113 +154,3 @@ class TestViews(DirectoriesMixin, TestCase):
         response.render()
         self.assertEqual(response.request["PATH_INFO"], "/accounts/login/")
         self.assertContains(response, b"Share link has expired")
-
-    def test_list_with_full_permissions(self):
-        """
-        GIVEN:
-            - Tags with different permissions
-        WHEN:
-            - Request to get tag list with full permissions is made
-        THEN:
-            - Tag list is returned with the right permission information
-        """
-        user2 = User.objects.create(username="user2")
-        user3 = User.objects.create(username="user3")
-        group1 = Group.objects.create(name="group1")
-        group2 = Group.objects.create(name="group2")
-        group3 = Group.objects.create(name="group3")
-        t1 = Tag.objects.create(name="invoice", pk=1)
-        assign_perm("view_tag", self.user, t1)
-        assign_perm("view_tag", user2, t1)
-        assign_perm("view_tag", user3, t1)
-        assign_perm("view_tag", group1, t1)
-        assign_perm("view_tag", group2, t1)
-        assign_perm("view_tag", group3, t1)
-        assign_perm("change_tag", self.user, t1)
-        assign_perm("change_tag", user2, t1)
-        assign_perm("change_tag", group1, t1)
-        assign_perm("change_tag", group2, t1)
-
-        Tag.objects.create(name="bank statement", pk=2)
-        d1 = Document.objects.create(
-            title="Invoice 1",
-            content="This is the invoice of a very expensive item",
-            checksum="A",
-        )
-        d1.tags.add(t1)
-        d2 = Document.objects.create(
-            title="Invoice 2",
-            content="Internet invoice, I should pay it to continue contributing",
-            checksum="B",
-        )
-        d2.tags.add(t1)
-
-        view_permissions = Permission.objects.filter(
-            codename__contains="view_tag",
-        )
-        self.user.user_permissions.add(*view_permissions)
-        self.user.save()
-
-        self.client.force_login(self.user)
-        response = self.client.get("/api/tags/?page=1&full_perms=true")
-        results = json.loads(response.content)["results"]
-        for tag in results:
-            if tag["name"] == "invoice":
-                assert tag["permissions"] == {
-                    "view": {
-                        "users": [self.user.pk, user2.pk, user3.pk],
-                        "groups": [group1.pk, group2.pk, group3.pk],
-                    },
-                    "change": {
-                        "users": [self.user.pk, user2.pk],
-                        "groups": [group1.pk, group2.pk],
-                    },
-                }
-            elif tag["name"] == "bank statement":
-                assert tag["permissions"] == {
-                    "view": {"users": [], "groups": []},
-                    "change": {"users": [], "groups": []},
-                }
-            else:
-                assert False, f"Unexpected tag found: {tag['name']}"
-
-    def test_list_no_n_plus_1_queries(self):
-        """
-        GIVEN:
-            - Tags with different permissions
-        WHEN:
-            - Request to get tag list with full permissions is made
-        THEN:
-            - Permissions are not queried in database tag by tag,
-             i.e. there are no N+1 queries
-        """
-        view_permissions = Permission.objects.filter(
-            codename__contains="view_tag",
-        )
-        self.user.user_permissions.add(*view_permissions)
-        self.user.save()
-        self.client.force_login(self.user)
-
-        # Start by a small list, and count the number of SQL queries
-        for i in range(2):
-            Tag.objects.create(name=f"tag_{i}")
-
-        with CaptureQueriesContext(connection) as ctx_small:
-            response_small = self.client.get("/api/tags/?full_perms=true")
-            assert response_small.status_code == 200
-        num_queries_small = len(ctx_small.captured_queries)
-
-        # Complete the list, and count the number of SQL queries again
-        for i in range(2, 50):
-            Tag.objects.create(name=f"tag_{i}")
-
-        with CaptureQueriesContext(connection) as ctx_large:
-            response_large = self.client.get("/api/tags/?full_perms=true")
-            assert response_large.status_code == 200
-        num_queries_large = len(ctx_large.captured_queries)
-
-        # A few additional queries are allowed, but not a linear explosion
-        assert num_queries_large <= num_queries_small + 5, (
-            f"Possible N+1 queries detected: {num_queries_small} queries for 2 tags, "
-            f"but {num_queries_large} queries for 50 tags"
-        )

src/documents/views.py

@@ -5,11 +5,9 @@ import platform
 import re
 import tempfile
 import zipfile
-from collections import defaultdict
 from datetime import datetime
 from pathlib import Path
 from time import mktime
-from typing import Literal
 from unicodedata import normalize
 from urllib.parse import quote
 from urllib.parse import urlparse
@@ -21,7 +19,6 @@ from celery import states
 from django.conf import settings
 from django.contrib.auth.models import Group
 from django.contrib.auth.models import User
-from django.contrib.contenttypes.models import ContentType
 from django.db import connections
 from django.db.migrations.loader import MigrationLoader
 from django.db.migrations.recorder import MigrationRecorder
@@ -59,8 +56,6 @@ from drf_spectacular.utils import OpenApiParameter
 from drf_spectacular.utils import extend_schema
 from drf_spectacular.utils import extend_schema_view
 from drf_spectacular.utils import inline_serializer
-from guardian.utils import get_group_obj_perms_model
-from guardian.utils import get_user_obj_perms_model
 from langdetect import detect
 from packaging import version as packaging_version
 from redis import Redis
@@ -136,7 +131,6 @@ from documents.models import WorkflowAction
 from documents.models import WorkflowTrigger
 from documents.parsers import get_parser_class_for_mime_type
 from documents.parsers import parse_date_generator
-from documents.permissions import AcknowledgeTasksPermissions
 from documents.permissions import PaperlessAdminPermissions
 from documents.permissions import PaperlessNotePermissions
 from documents.permissions import PaperlessObjectPermissions
@@ -260,104 +254,7 @@ class PassUserMixin(GenericAPIView):
         return super().get_serializer(*args, **kwargs)
 
 
-class BulkPermissionMixin:
+class PermissionsAwareDocumentCountMixin(PassUserMixin):
-    """
-    Prefetch Django-Guardian permissions for a list before serialization, to avoid N+1 queries.
-    """
-
-    def _get_object_perms(
-        self,
-        objects: list,
-        perm_codenames: list[str],
-        actor: Literal["users", "groups"],
-    ) -> dict[int, dict[str, list[int]]]:
-        """
-        Collect object-level permissions for either users or groups.
-        """
-        model = self.queryset.model
-        obj_perm_model = (
-            get_user_obj_perms_model(model)
-            if actor == "users"
-            else get_group_obj_perms_model(model)
-        )
-        id_field = "user_id" if actor == "users" else "group_id"
-        ctype = ContentType.objects.get_for_model(model)
-        object_pks = [obj.pk for obj in objects]
-
-        perms_qs = obj_perm_model.objects.filter(
-            content_type=ctype,
-            object_pk__in=object_pks,
-            permission__codename__in=perm_codenames,
-        ).values_list("object_pk", id_field, "permission__codename")
-
-        perms: dict[int, dict[str, list[int]]] = defaultdict(lambda: defaultdict(list))
-        for object_pk, actor_id, codename in perms_qs:
-            perms[int(object_pk)][codename].append(actor_id)
-
-        # Ensure that all objects have all codenames, even if empty
-        for pk in object_pks:
-            for codename in perm_codenames:
-                perms[pk][codename]
-
-        return perms
-
-    def get_serializer_context(self):
-        """
-        Get all permissions of the current list of objects at once and pass them to the serializer.
-        This avoid fetching permissions object by object in database.
-        """
-        context = super().get_serializer_context()
-        try:
-            full_perms = get_boolean(
-                str(self.request.query_params.get("full_perms", "false")),
-            )
-        except ValueError:
-            full_perms = False
-
-        if not full_perms:
-            return context
-
-        # Check which objects are being paginated
-        page = getattr(self, "paginator", None)
-        if page and hasattr(page, "page"):
-            queryset = page.page.object_list
-        elif hasattr(self, "page"):
-            queryset = self.page
-        else:
-            queryset = self.filter_queryset(self.get_queryset())
-
-        model_name = self.queryset.model.__name__.lower()
-        permission_name_view = f"view_{model_name}"
-        permission_name_change = f"change_{model_name}"
-
-        user_perms = self._get_object_perms(
-            objects=queryset,
-            perm_codenames=[permission_name_view, permission_name_change],
-            actor="users",
-        )
-        group_perms = self._get_object_perms(
-            objects=queryset,
-            perm_codenames=[permission_name_view, permission_name_change],
-            actor="groups",
-        )
-
-        context["users_view_perms"] = {
-            pk: user_perms[pk][permission_name_view] for pk in user_perms
-        }
-        context["users_change_perms"] = {
-            pk: user_perms[pk][permission_name_change] for pk in user_perms
-        }
-        context["groups_view_perms"] = {
-            pk: group_perms[pk][permission_name_view] for pk in group_perms
-        }
-        context["groups_change_perms"] = {
-            pk: group_perms[pk][permission_name_change] for pk in group_perms
-        }
-
-        return context
-
-
-class PermissionsAwareDocumentCountMixin(BulkPermissionMixin, PassUserMixin):
     """
     Mixin to add document count to queryset, permissions-aware if needed
     """
@@ -2488,11 +2385,7 @@ class TasksViewSet(ReadOnlyModelViewSet):
             queryset = PaperlessTask.objects.filter(task_id=task_id)
         return queryset
 
-    @action(
+    @action(methods=["post"], detail=False)
-        methods=["post"],
-        detail=False,
-        permission_classes=[IsAuthenticated, AcknowledgeTasksPermissions],
-    )
     def acknowledge(self, request):
         serializer = AcknowledgeTasksViewSerializer(data=request.data)
         serializer.is_valid(raise_exception=True)

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: 2025-09-30 16:50+0000\n"
+"POT-Creation-Date: 2025-09-22 18:20+0000\n"
 "PO-Revision-Date: 2022-02-17 04:17\n"
 "Last-Translator: \n"
 "Language-Team: English\n"
@@ -1191,44 +1191,44 @@ msgstr ""
 msgid "workflow runs"
 msgstr ""
 
-#: documents/serialisers.py:141
+#: documents/serialisers.py:140
 #, python-format
 msgid "Invalid regular expression: %(error)s"
 msgstr ""
 
-#: documents/serialisers.py:607
+#: documents/serialisers.py:594
 msgid "Invalid color."
 msgstr ""
 
-#: documents/serialisers.py:636
+#: documents/serialisers.py:623
 msgid "Invalid parent tag."
 msgstr ""
 
-#: documents/serialisers.py:1793
+#: documents/serialisers.py:1780
 #, python-format
 msgid "File type %(type)s not supported"
 msgstr ""
 
-#: documents/serialisers.py:1837
+#: documents/serialisers.py:1824
 #, python-format
 msgid "Custom field id must be an integer: %(id)s"
 msgstr ""
 
-#: documents/serialisers.py:1844
+#: documents/serialisers.py:1831
 #, python-format
 msgid "Custom field with id %(id)s does not exist"
 msgstr ""
 
-#: documents/serialisers.py:1861 documents/serialisers.py:1871
+#: documents/serialisers.py:1848 documents/serialisers.py:1858
 msgid ""
 "Custom fields must be a list of integers or an object mapping ids to values."
 msgstr ""
 
-#: documents/serialisers.py:1866
+#: documents/serialisers.py:1853
 msgid "Some custom fields don't exist or were specified twice."
 msgstr ""
 
-#: documents/serialisers.py:1936
+#: documents/serialisers.py:1923
 msgid "Invalid variable detected."
 msgstr ""
 

src/paperless/settings.py

@@ -322,6 +322,7 @@ INSTALLED_APPS = [
     "paperless_tesseract.apps.PaperlessTesseractConfig",
     "paperless_text.apps.PaperlessTextConfig",
     "paperless_mail.apps.PaperlessMailConfig",
+    "paperless_remote.apps.PaperlessRemoteParserConfig",
     "django.contrib.admin",
     "rest_framework",
     "rest_framework.authtoken",
@@ -1003,18 +1004,6 @@ THREADS_PER_WORKER = os.getenv(
 # Paperless Specific Settings                                                 #
 ###############################################################################
 
-IGNORABLE_FILES: Final[list[str]] = [
-    ".DS_Store",
-    ".DS_STORE",
-    "._*",
-    ".stfolder/*",
-    ".stversions/*",
-    ".localized/*",
-    "desktop.ini",
-    "@eaDir/*",
-    "Thumbs.db",
-]
-
 CONSUMER_POLLING = int(os.getenv("PAPERLESS_CONSUMER_POLLING", 0))
 
 CONSUMER_POLLING_DELAY = int(os.getenv("PAPERLESS_CONSUMER_POLLING_DELAY", 5))
@@ -1037,7 +1026,7 @@ CONSUMER_IGNORE_PATTERNS = list(
     json.loads(
         os.getenv(
             "PAPERLESS_CONSUMER_IGNORE_PATTERNS",
-            json.dumps(IGNORABLE_FILES),
+            '[".DS_Store", ".DS_STORE", "._*", ".stfolder/*", ".stversions/*", ".localized/*", "desktop.ini", "@eaDir/*", "Thumbs.db"]',
         ),
     ),
 )
@@ -1401,3 +1390,10 @@ WEBHOOKS_ALLOW_INTERNAL_REQUESTS = __get_boolean(
     "PAPERLESS_WEBHOOKS_ALLOW_INTERNAL_REQUESTS",
     "true",
 )
+
+###############################################################################
+# Remote Parser                                                               #
+###############################################################################
+REMOTE_OCR_ENGINE = os.getenv("PAPERLESS_REMOTE_OCR_ENGINE")
+REMOTE_OCR_API_KEY = os.getenv("PAPERLESS_REMOTE_OCR_API_KEY")
+REMOTE_OCR_ENDPOINT = os.getenv("PAPERLESS_REMOTE_OCR_ENDPOINT")

src/paperless_remote/__init__.py

@@ -0,0 +1,4 @@
+# this is here so that django finds the checks.
+from paperless_remote.checks import check_remote_parser_configured
+
+__all__ = ["check_remote_parser_configured"]

src/paperless_remote/apps.py

@@ -0,0 +1,14 @@
+from django.apps import AppConfig
+
+from paperless_remote.signals import remote_consumer_declaration
+
+
+class PaperlessRemoteParserConfig(AppConfig):
+    name = "paperless_remote"
+
+    def ready(self):
+        from documents.signals import document_consumer_declaration
+
+        document_consumer_declaration.connect(remote_consumer_declaration)
+
+        AppConfig.ready(self)

src/paperless_remote/checks.py

@@ -0,0 +1,17 @@
+from django.conf import settings
+from django.core.checks import Error
+from django.core.checks import register
+
+
+@register()
+def check_remote_parser_configured(app_configs, **kwargs):
+    if settings.REMOTE_OCR_ENGINE == "azureai" and not (
+        settings.REMOTE_OCR_ENDPOINT and settings.REMOTE_OCR_API_KEY
+    ):
+        return [
+            Error(
+                "Azure AI remote parser requires endpoint and API key to be configured.",
+            ),
+        ]
+
+    return []

src/paperless_remote/parsers.py

@@ -0,0 +1,113 @@
+from pathlib import Path
+
+from django.conf import settings
+
+from paperless_tesseract.parsers import RasterisedDocumentParser
+
+
+class RemoteEngineConfig:
+    def __init__(
+        self,
+        engine: str,
+        api_key: str | None = None,
+        endpoint: str | None = None,
+    ):
+        self.engine = engine
+        self.api_key = api_key
+        self.endpoint = endpoint
+
+    def engine_is_valid(self):
+        valid = self.engine in ["azureai"] and self.api_key is not None
+        if self.engine == "azureai":
+            valid = valid and self.endpoint is not None
+        return valid
+
+
+class RemoteDocumentParser(RasterisedDocumentParser):
+    """
+    This parser uses a remote OCR engine to parse documents. Currently, it supports Azure AI Vision
+    as this is the only service that provides a remote OCR API with text-embedded PDF output.
+    """
+
+    logging_name = "paperless.parsing.remote"
+
+    def get_settings(self) -> RemoteEngineConfig:
+        """
+        Returns the configuration for the remote OCR engine, loaded from Django settings.
+        """
+        return RemoteEngineConfig(
+            engine=settings.REMOTE_OCR_ENGINE,
+            api_key=settings.REMOTE_OCR_API_KEY,
+            endpoint=settings.REMOTE_OCR_ENDPOINT,
+        )
+
+    def supported_mime_types(self):
+        if self.settings.engine_is_valid():
+            return {
+                "application/pdf": ".pdf",
+                "image/png": ".png",
+                "image/jpeg": ".jpg",
+                "image/tiff": ".tiff",
+                "image/bmp": ".bmp",
+                "image/gif": ".gif",
+                "image/webp": ".webp",
+            }
+        else:
+            return {}
+
+    def azure_ai_vision_parse(
+        self,
+        file: Path,
+    ) -> str | None:
+        """
+        Uses Azure AI Vision to parse the document and return the text content.
+        It requests a searchable PDF output with embedded text.
+        The PDF is saved to the archive_path attribute.
+        Returns the text content extracted from the document.
+        If the parsing fails, it returns None.
+        """
+        from azure.ai.documentintelligence import DocumentIntelligenceClient
+        from azure.ai.documentintelligence.models import AnalyzeDocumentRequest
+        from azure.ai.documentintelligence.models import AnalyzeOutputOption
+        from azure.ai.documentintelligence.models import DocumentContentFormat
+        from azure.core.credentials import AzureKeyCredential
+
+        client = DocumentIntelligenceClient(
+            endpoint=self.settings.endpoint,
+            credential=AzureKeyCredential(self.settings.api_key),
+        )
+
+        with file.open("rb") as f:
+            analyze_request = AnalyzeDocumentRequest(bytes_source=f.read())
+            poller = client.begin_analyze_document(
+                model_id="prebuilt-read",
+                body=analyze_request,
+                output_content_format=DocumentContentFormat.TEXT,
+                output=[AnalyzeOutputOption.PDF],  # request searchable PDF output
+                content_type="application/json",
+            )
+
+        poller.wait()
+        result_id = poller.details["operation_id"]
+        result = poller.result()
+
+        # Download the PDF with embedded text
+        self.archive_path = self.tempdir / "archive.pdf"
+        with self.archive_path.open("wb") as f:
+            for chunk in client.get_analyze_result_pdf(
+                model_id="prebuilt-read",
+                result_id=result_id,
+            ):
+                f.write(chunk)
+
+        client.close()
+        return result.content
+
+    def parse(self, document_path: Path, mime_type, file_name=None):
+        if not self.settings.engine_is_valid():
+            self.log.warning(
+                "No valid remote parser engine is configured, content will be empty.",
+            )
+            self.text = ""
+        elif self.settings.engine == "azureai":
+            self.text = self.azure_ai_vision_parse(document_path)

src/paperless_remote/signals.py

@@ -0,0 +1,18 @@
+def get_parser(*args, **kwargs):
+    from paperless_remote.parsers import RemoteDocumentParser
+
+    return RemoteDocumentParser(*args, **kwargs)
+
+
+def get_supported_mime_types():
+    from paperless_remote.parsers import RemoteDocumentParser
+
+    return RemoteDocumentParser(None).supported_mime_types()
+
+
+def remote_consumer_declaration(sender, **kwargs):
+    return {
+        "parser": get_parser,
+        "weight": 5,
+        "mime_types": get_supported_mime_types(),
+    }

src/paperless_remote/tests/test_checks.py

@@ -0,0 +1,24 @@
+from unittest import TestCase
+
+from django.test import override_settings
+
+from paperless_remote import check_remote_parser_configured
+
+
+class TestChecks(TestCase):
+    @override_settings(REMOTE_OCR_ENGINE=None)
+    def test_no_engine(self):
+        msgs = check_remote_parser_configured(None)
+        self.assertEqual(len(msgs), 0)
+
+    @override_settings(REMOTE_OCR_ENGINE="azureai")
+    @override_settings(REMOTE_OCR_API_KEY="somekey")
+    @override_settings(REMOTE_OCR_ENDPOINT=None)
+    def test_azure_no_endpoint(self):
+        msgs = check_remote_parser_configured(None)
+        self.assertEqual(len(msgs), 1)
+        self.assertTrue(
+            msgs[0].msg.startswith(
+                "Azure AI remote parser requires endpoint and API key to be configured.",
+            ),
+        )

src/paperless_remote/tests/test_parser.py

@@ -0,0 +1,101 @@
+import uuid
+from pathlib import Path
+from unittest import mock
+
+from django.test import TestCase
+from django.test import override_settings
+
+from documents.tests.utils import DirectoriesMixin
+from documents.tests.utils import FileSystemAssertsMixin
+from paperless_remote.parsers import RemoteDocumentParser
+from paperless_remote.signals import get_parser
+
+
+class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
+    SAMPLE_FILES = Path(__file__).resolve().parent / "samples"
+
+    def assertContainsStrings(self, content: str, strings: list[str]):
+        # Asserts that all strings appear in content, in the given order.
+        indices = []
+        for s in strings:
+            if s in content:
+                indices.append(content.index(s))
+            else:
+                self.fail(f"'{s}' is not in '{content}'")
+        self.assertListEqual(indices, sorted(indices))
+
+    @mock.patch("paperless_tesseract.parsers.run_subprocess")
+    @mock.patch("azure.ai.documentintelligence.DocumentIntelligenceClient")
+    def test_get_text_with_azure(self, mock_client_cls, mock_subprocess):
+        # Arrange mock Azure client
+        mock_client = mock.Mock()
+        mock_client_cls.return_value = mock_client
+
+        # Simulate poller result and its `.details`
+        mock_poller = mock.Mock()
+        mock_poller.wait.return_value = None
+        mock_poller.details = {"operation_id": "fake-op-id"}
+        mock_client.begin_analyze_document.return_value = mock_poller
+        mock_poller.result.return_value.content = "This is a test document."
+
+        # Return dummy PDF bytes
+        mock_client.get_analyze_result_pdf.return_value = [
+            b"%PDF-",
+            b"1.7 ",
+            b"FAKEPDF",
+        ]
+
+        # Simulate pdftotext by writing dummy text to sidecar file
+        def fake_run(cmd, *args, **kwargs):
+            with Path(cmd[-1]).open("w", encoding="utf-8") as f:
+                f.write("This is a test document.")
+
+        mock_subprocess.side_effect = fake_run
+
+        with override_settings(
+            REMOTE_OCR_ENGINE="azureai",
+            REMOTE_OCR_API_KEY="somekey",
+            REMOTE_OCR_ENDPOINT="https://endpoint.cognitiveservices.azure.com",
+        ):
+            parser = get_parser(uuid.uuid4())
+            parser.parse(
+                self.SAMPLE_FILES / "simple-digital.pdf",
+                "application/pdf",
+            )
+
+            self.assertContainsStrings(
+                parser.text.strip(),
+                ["This is a test document."],
+            )
+
+    @override_settings(
+        REMOTE_OCR_ENGINE="azureai",
+        REMOTE_OCR_API_KEY="key",
+        REMOTE_OCR_ENDPOINT="https://endpoint.cognitiveservices.azure.com",
+    )
+    def test_supported_mime_types_valid_config(self):
+        parser = RemoteDocumentParser(uuid.uuid4())
+        expected_types = {
+            "application/pdf": ".pdf",
+            "image/png": ".png",
+            "image/jpeg": ".jpg",
+            "image/tiff": ".tiff",
+            "image/bmp": ".bmp",
+            "image/gif": ".gif",
+            "image/webp": ".webp",
+        }
+        self.assertEqual(parser.supported_mime_types(), expected_types)
+
+    def test_supported_mime_types_invalid_config(self):
+        parser = get_parser(uuid.uuid4())
+        self.assertEqual(parser.supported_mime_types(), {})
+
+    @override_settings(
+        REMOTE_OCR_ENGINE=None,
+        REMOTE_OCR_API_KEY=None,
+        REMOTE_OCR_ENDPOINT=None,
+    )
+    def test_parse_with_invalid_config(self):
+        parser = get_parser(uuid.uuid4())
+        parser.parse(self.SAMPLE_FILES / "simple-digital.pdf", "application/pdf")
+        self.assertEqual(parser.text, "")