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

Bumps the frontend-eslint-dependencies group in /src-ui with 4 updates: [@typescript-eslint/eslint-plugin](https://github.com/typescript-eslint/typescript-eslint/tree/HEAD/packages/eslint-plugin), [@typescript-eslint/parser](https://github.com/typescript-eslint/typescript-eslint/tree/HEAD/packages/parser), [@typescript-eslint/utils](https://github.com/typescript-eslint/typescript-eslint/tree/HEAD/packages/utils) and [eslint](https://github.com/eslint/eslint).


Updates `@typescript-eslint/eslint-plugin` from 8.38.0 to 8.41.0
- [Release notes](https://github.com/typescript-eslint/typescript-eslint/releases)
- [Changelog](https://github.com/typescript-eslint/typescript-eslint/blob/main/packages/eslint-plugin/CHANGELOG.md)
- [Commits](https://github.com/typescript-eslint/typescript-eslint/commits/v8.41.0/packages/eslint-plugin)

Updates `@typescript-eslint/parser` from 8.38.0 to 8.41.0
- [Release notes](https://github.com/typescript-eslint/typescript-eslint/releases)
- [Changelog](https://github.com/typescript-eslint/typescript-eslint/blob/main/packages/parser/CHANGELOG.md)
- [Commits](https://github.com/typescript-eslint/typescript-eslint/commits/v8.41.0/packages/parser)

Updates `@typescript-eslint/utils` from 8.38.0 to 8.41.0
- [Release notes](https://github.com/typescript-eslint/typescript-eslint/releases)
- [Changelog](https://github.com/typescript-eslint/typescript-eslint/blob/main/packages/utils/CHANGELOG.md)
- [Commits](https://github.com/typescript-eslint/typescript-eslint/commits/v8.41.0/packages/utils)

Updates `eslint` from 9.32.0 to 9.34.0
- [Release notes](https://github.com/eslint/eslint/releases)
- [Changelog](https://github.com/eslint/eslint/blob/main/CHANGELOG.md)
- [Commits](https://github.com/eslint/eslint/compare/v9.32.0...v9.34.0)

---
updated-dependencies:
- dependency-name: "@typescript-eslint/eslint-plugin"
  dependency-version: 8.41.0
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: frontend-eslint-dependencies
- dependency-name: "@typescript-eslint/parser"
  dependency-version: 8.41.0
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: frontend-eslint-dependencies
- dependency-name: "@typescript-eslint/utils"
  dependency-version: 8.41.0
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: frontend-eslint-dependencies
- dependency-name: eslint
  dependency-version: 9.34.0
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: frontend-eslint-dependencies
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: shamoon <4887959+shamoon@users.noreply.github.com>

.devcontainer/devcontainer.json

@@ -3,7 +3,7 @@
     "dockerComposeFile": "docker-compose.devcontainer.sqlite-tika.yml",
     "service": "paperless-development",
     "workspaceFolder": "/usr/src/paperless/paperless-ngx",
-    "postCreateCommand": "/bin/bash -c 'uv sync --group dev && uv run pre-commit install'",
+    "postCreateCommand": "/bin/bash -c 'rm -rf .venv/.*  && uv sync --group dev && uv run pre-commit install'",
     "customizations": {
         "vscode": {
           "extensions": [

.github/workflows/ci.yml

@@ -26,7 +26,7 @@ jobs:
     runs-on: ubuntu-24.04
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
       - name: Install python
         uses: actions/setup-python@v5
         with:
@@ -40,7 +40,7 @@ jobs:
       - pre-commit
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
       - name: Set up Python
         id: setup-python
         uses: actions/setup-python@v5
@@ -90,7 +90,7 @@ jobs:
       fail-fast: false
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
       - name: Start containers
         run: |
           docker compose --file ${{ github.workspace }}/docker/compose/docker-compose.ci-test.yml pull --quiet
@@ -162,7 +162,7 @@ jobs:
     needs:
       - pre-commit
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
       - name: Install pnpm
         uses: pnpm/action-setup@v4
         with:
@@ -195,7 +195,7 @@ jobs:
         shard-index: [1, 2, 3, 4]
         shard-count: [4]
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
       - name: Install pnpm
         uses: pnpm/action-setup@v4
         with:
@@ -245,7 +245,7 @@ jobs:
         shard-index: [1, 2]
         shard-count: [2]
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
       - name: Install pnpm
         uses: pnpm/action-setup@v4
         with:
@@ -288,7 +288,7 @@ jobs:
       - tests-frontend
       - tests-frontend-e2e
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
       - name: Install pnpm
         uses: pnpm/action-setup@v4
         with:
@@ -363,7 +363,7 @@ jobs:
             type=semver,pattern={{version}}
             type=semver,pattern={{major}}.{{minor}}
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
       # If https://github.com/docker/buildx/issues/1044 is resolved,
       # the append input with a native arm64 arch could be used to
       # significantly speed up building
@@ -433,7 +433,7 @@ jobs:
     runs-on: ubuntu-24.04
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
       - name: Set up Python
         id: setup-python
         uses: actions/setup-python@v5
@@ -453,12 +453,12 @@ jobs:
           sudo apt-get update -qq
           sudo apt-get install -qq --no-install-recommends gettext liblept5
       - name: Download frontend artifact
-        uses: actions/download-artifact@v4
+        uses: actions/download-artifact@v5
         with:
           name: frontend-compiled
           path: src/documents/static/frontend/
       - name: Download documentation artifact
-        uses: actions/download-artifact@v4
+        uses: actions/download-artifact@v5
         with:
           name: documentation
           path: docs/_build/html/
@@ -538,7 +538,7 @@ jobs:
     if: github.ref_type == 'tag' && (startsWith(github.ref_name, 'v') || contains(github.ref_name, '-beta.rc'))
     steps:
       - name: Download release artifact
-        uses: actions/download-artifact@v4
+        uses: actions/download-artifact@v5
         with:
           name: release
           path: ./
@@ -579,7 +579,7 @@ jobs:
     if: needs.publish-release.outputs.prerelease == 'false'
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
         with:
           ref: main
       - name: Set up Python

.github/workflows/cleanup-tags.yml

@@ -28,7 +28,7 @@ jobs:
     steps:
       - name: Clean temporary images
         if: "${{ env.TOKEN != '' }}"
-        uses: stumpylog/image-cleaner-action/ephemeral@v0.10.0
+        uses: stumpylog/image-cleaner-action/ephemeral@v0.11.0
         with:
           token: "${{ env.TOKEN }}"
           owner: "${{ github.repository_owner }}"
@@ -54,7 +54,7 @@ jobs:
     steps:
       - name: Clean untagged images
         if: "${{ env.TOKEN != '' }}"
-        uses: stumpylog/image-cleaner-action/untagged@v0.10.0
+        uses: stumpylog/image-cleaner-action/untagged@v0.11.0
         with:
           token: "${{ env.TOKEN }}"
           owner: "${{ github.repository_owner }}"

.github/workflows/codeql-analysis.yml

@@ -34,7 +34,7 @@ jobs:
         # Learn more about CodeQL language support at https://git.io/codeql-language-support
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
       # Initializes the CodeQL tools for scanning.
       - name: Initialize CodeQL
         uses: github/codeql-action/init@v3

.github/workflows/crowdin.yml

@@ -13,7 +13,7 @@ jobs:
     runs-on: ubuntu-24.04
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
         with:
           token: ${{ secrets.PNGX_BOT_PAT }}
       - name: crowdin action

.github/workflows/pr-bot.yml

@@ -37,7 +37,7 @@ jobs:
               labels.push('bug');
             } else if (/^feature/i.test(title)) {
               labels.push('enhancement');
-            } else if (!/^(dependabot)/i.test(title)) {
+            } else if (!/^(dependabot)/i.test(title) && !/^(chore)/i.test(title)) {
               labels.push('enhancement'); // Default fallback
             }
 

.github/workflows/translate-strings.yml

@@ -11,7 +11,7 @@ jobs:
       contents: write
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
         with:
           token: ${{ secrets.PNGX_BOT_PAT }}
           ref: ${{ github.head_ref }}

.pre-commit-config.yaml

@@ -18,7 +18,7 @@ repos:
         exclude_types:
           - svg
           - pofile
-        exclude: "(^LICENSE$)"
+        exclude: "(^LICENSE$|^src/documents/static/bootstrap.min.css$)"
       - id: mixed-line-ending
         args:
           - "--fix=lf"
@@ -51,7 +51,7 @@ repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
     rev: v0.12.2
     hooks:
-      - id: ruff
+      - id: ruff-check
       - id: ruff-format
   - repo: https://github.com/tox-dev/pyproject-fmt
     rev: "v2.6.0"

.yamlfmt

@@ -0,0 +1 @@
+line_ending: lf

docs/configuration.md

@@ -1800,3 +1800,23 @@ 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.
+    -   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

@@ -850,6 +850,21 @@ 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",
@@ -205,18 +206,9 @@ lint.per-file-ignores."docker/wait-for-redis.py" = [
   "INP001",
   "T201",
 ]
-lint.per-file-ignores."src/documents/management/commands/document_consumer.py" = [
-  "PTH",
-] # TODO Enable & remove
-lint.per-file-ignores."src/documents/migrations/1012_fix_archive_files.py" = [
-  "PTH",
-] # TODO Enable & remove
 lint.per-file-ignores."src/documents/models.py" = [
   "SIM115",
 ]
-lint.per-file-ignores."src/documents/parsers.py" = [
-  "PTH",
-] # TODO Enable & remove
 lint.per-file-ignores."src/paperless_tesseract/tests/test_parser.py" = [
   "RUF001",
 ]
@@ -239,6 +231,7 @@ testpaths = [
   "src/paperless_tesseract/tests/",
   "src/paperless_tika/tests",
   "src/paperless_text/tests/",
+  "src/paperless_remote/tests/",
 ]
 addopts = [
   "--pythonwarnings=all",

src-ui/messages.xlf

@@ -5,14 +5,14 @@
       <trans-unit id="ngb.alert.close" datatype="html">
         <source>Close</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/alert/alert.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/alert/alert.ts</context>
           <context context-type="linenumber">50</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.carousel.slide-number" datatype="html">
         <source> Slide <x id="INTERPOLATION" equiv-text="ueryList&lt;NgbSli"/> of <x id="INTERPOLATION_1" equiv-text="EventSource = N"/> </source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/carousel/carousel.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/carousel/carousel.ts</context>
           <context context-type="linenumber">131,135</context>
         </context-group>
         <note priority="1" from="description">Currently selected slide number read by screen reader</note>
@@ -20,212 +20,212 @@
       <trans-unit id="ngb.carousel.previous" datatype="html">
         <source>Previous</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/carousel/carousel.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/carousel/carousel.ts</context>
           <context context-type="linenumber">157,159</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.carousel.next" datatype="html">
         <source>Next</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/carousel/carousel.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/carousel/carousel.ts</context>
           <context context-type="linenumber">198</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.datepicker.previous-month" datatype="html">
         <source>Previous month</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/datepicker/datepicker-navigation.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/datepicker/datepicker-navigation.ts</context>
           <context context-type="linenumber">83,85</context>
         </context-group>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/datepicker/datepicker-navigation.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/datepicker/datepicker-navigation.ts</context>
           <context context-type="linenumber">112</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.datepicker.next-month" datatype="html">
         <source>Next month</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/datepicker/datepicker-navigation.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/datepicker/datepicker-navigation.ts</context>
           <context context-type="linenumber">112</context>
         </context-group>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/datepicker/datepicker-navigation.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/datepicker/datepicker-navigation.ts</context>
           <context context-type="linenumber">112</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.timepicker.HH" datatype="html">
         <source>HH</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.toast.close-aria" datatype="html">
         <source>Close</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.datepicker.select-month" datatype="html">
         <source>Select month</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.pagination.first" datatype="html">
         <source>««</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.timepicker.hours" datatype="html">
         <source>Hours</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.pagination.previous" datatype="html">
         <source>«</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.timepicker.MM" datatype="html">
         <source>MM</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.pagination.next" datatype="html">
         <source>»</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.datepicker.select-year" datatype="html">
         <source>Select year</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.timepicker.minutes" datatype="html">
         <source>Minutes</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.pagination.last" datatype="html">
         <source>»»</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.pagination.first-aria" datatype="html">
         <source>First</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.timepicker.increment-hours" datatype="html">
         <source>Increment hours</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.pagination.previous-aria" datatype="html">
         <source>Previous</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.timepicker.decrement-hours" datatype="html">
         <source>Decrement hours</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.pagination.next-aria" datatype="html">
         <source>Next</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.timepicker.increment-minutes" datatype="html">
         <source>Increment minutes</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.pagination.last-aria" datatype="html">
         <source>Last</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.timepicker.decrement-minutes" datatype="html">
         <source>Decrement minutes</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.timepicker.SS" datatype="html">
         <source>SS</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.timepicker.seconds" datatype="html">
         <source>Seconds</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.timepicker.increment-seconds" datatype="html">
         <source>Increment seconds</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.timepicker.decrement-seconds" datatype="html">
         <source>Decrement seconds</source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
       </trans-unit>
       <trans-unit id="ngb.timepicker.PM" datatype="html">
         <source><x id="INTERPOLATION"/></source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/ngb-config.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
       </trans-unit>
@@ -233,7 +233,7 @@
         <source><x id="INTERPOLATION" equiv-text="barConfig);
 	pu"/></source>
         <context-group purpose="location">
-          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.1.4_@angular+core@20.1.4_@angular+_4264661dcfc97b5bf5cf26958990f623/node_modules/src/progressbar/progressbar.ts</context>
+          <context context-type="sourcefile">node_modules/.pnpm/@ng-bootstrap+ng-bootstrap@19.0.1_@angular+common@20.2.4_@angular+core@20.2.4_@angular+_db9461b4835bfc9061e01150e14e6256/node_modules/src/progressbar/progressbar.ts</context>
           <context context-type="linenumber">41,42</context>
         </context-group>
       </trans-unit>
@@ -553,7 +553,7 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/edit-dialog/custom-field-edit-dialog/custom-field-edit-dialog.component.html</context>
-          <context context-type="linenumber">45</context>
+          <context context-type="linenumber">55</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/edit-dialog/document-type-edit-dialog/document-type-edit-dialog.component.html</context>
@@ -1444,7 +1444,7 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/edit-dialog/custom-field-edit-dialog/custom-field-edit-dialog.component.html</context>
-          <context context-type="linenumber">44</context>
+          <context context-type="linenumber">54</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/edit-dialog/document-type-edit-dialog/document-type-edit-dialog.component.html</context>
@@ -3673,42 +3673,42 @@
         <source>Warning: existing instances of this field will retain their current value index (e.g. option #1, #2, #3) after editing the options here</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/edit-dialog/custom-field-edit-dialog/custom-field-edit-dialog.component.html</context>
-          <context context-type="linenumber">32</context>
+          <context context-type="linenumber">42</context>
         </context-group>
       </trans-unit>
       <trans-unit id="2739003406164860877" datatype="html">
         <source>Default Currency</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/edit-dialog/custom-field-edit-dialog/custom-field-edit-dialog.component.html</context>
-          <context context-type="linenumber">37</context>
+          <context context-type="linenumber">47</context>
         </context-group>
       </trans-unit>
       <trans-unit id="7615210738790237590" datatype="html">
         <source>3-character currency code</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/edit-dialog/custom-field-edit-dialog/custom-field-edit-dialog.component.html</context>
-          <context context-type="linenumber">37</context>
+          <context context-type="linenumber">47</context>
         </context-group>
       </trans-unit>
       <trans-unit id="607636736207886379" datatype="html">
         <source>Use locale</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/edit-dialog/custom-field-edit-dialog/custom-field-edit-dialog.component.html</context>
-          <context context-type="linenumber">37</context>
+          <context context-type="linenumber">47</context>
         </context-group>
       </trans-unit>
       <trans-unit id="528950215505228201" datatype="html">
         <source>Create new custom field</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/edit-dialog/custom-field-edit-dialog/custom-field-edit-dialog.component.ts</context>
-          <context context-type="linenumber">93</context>
+          <context context-type="linenumber">118</context>
         </context-group>
       </trans-unit>
       <trans-unit id="8751213029607178010" datatype="html">
         <source>Edit custom field</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/edit-dialog/custom-field-edit-dialog/custom-field-edit-dialog.component.ts</context>
-          <context context-type="linenumber">97</context>
+          <context context-type="linenumber">122</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6672809941092516947" datatype="html">

src-ui/package.json

@@ -11,27 +11,27 @@
   },
   "private": true,
   "dependencies": {
-    "@angular/cdk": "^20.1.4",
-    "@angular/common": "~20.1.4",
-    "@angular/compiler": "~20.1.4",
-    "@angular/core": "~20.1.4",
-    "@angular/forms": "~20.1.4",
-    "@angular/localize": "~20.1.4",
-    "@angular/platform-browser": "~20.1.4",
-    "@angular/platform-browser-dynamic": "~20.1.4",
-    "@angular/router": "~20.1.4",
+    "@angular/cdk": "^20.2.2",
+    "@angular/common": "~20.2.4",
+    "@angular/compiler": "~20.2.4",
+    "@angular/core": "~20.2.4",
+    "@angular/forms": "~20.2.4",
+    "@angular/localize": "~20.2.4",
+    "@angular/platform-browser": "~20.2.4",
+    "@angular/platform-browser-dynamic": "~20.2.4",
+    "@angular/router": "~20.2.4",
     "@ng-bootstrap/ng-bootstrap": "^19.0.1",
-    "@ng-select/ng-select": "^20.0.1",
+    "@ng-select/ng-select": "^20.1.3",
     "@ngneat/dirty-check-forms": "^3.0.3",
     "@popperjs/core": "^2.11.8",
-    "bootstrap": "^5.3.7",
+    "bootstrap": "^5.3.8",
     "file-saver": "^2.0.5",
     "mime-names": "^1.0.0",
     "ng2-pdf-viewer": "^10.4.0",
     "ngx-bootstrap-icons": "^1.9.3",
     "ngx-color": "^10.0.0",
-    "ngx-cookie-service": "^20.0.1",
-    "ngx-device-detector": "^10.0.2",
+    "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",
@@ -42,33 +42,33 @@
   "devDependencies": {
     "@angular-builders/custom-webpack": "^20.0.0",
     "@angular-builders/jest": "^20.0.0",
-    "@angular-devkit/core": "^20.1.4",
-    "@angular-devkit/schematics": "^20.1.4",
-    "@angular-eslint/builder": "20.1.1",
-    "@angular-eslint/eslint-plugin": "20.1.1",
-    "@angular-eslint/eslint-plugin-template": "20.1.1",
-    "@angular-eslint/schematics": "20.1.1",
-    "@angular-eslint/template-parser": "20.1.1",
-    "@angular/build": "^20.1.4",
-    "@angular/cli": "~20.1.4",
-    "@angular/compiler-cli": "~20.1.4",
+    "@angular-devkit/core": "^20.2.2",
+    "@angular-devkit/schematics": "^20.2.2",
+    "@angular-eslint/builder": "20.2.0",
+    "@angular-eslint/eslint-plugin": "20.2.0",
+    "@angular-eslint/eslint-plugin-template": "20.2.0",
+    "@angular-eslint/schematics": "20.2.0",
+    "@angular-eslint/template-parser": "20.2.0",
+    "@angular/build": "^20.2.2",
+    "@angular/cli": "~20.2.2",
+    "@angular/compiler-cli": "~20.2.4",
     "@codecov/webpack-plugin": "^1.9.1",
-    "@playwright/test": "^1.54.2",
+    "@playwright/test": "^1.55.0",
     "@types/jest": "^30.0.0",
-    "@types/node": "^24.1.0",
-    "@typescript-eslint/eslint-plugin": "^8.38.0",
-    "@typescript-eslint/parser": "^8.38.0",
-    "@typescript-eslint/utils": "^8.38.0",
-    "eslint": "^9.32.0",
-    "jest": "30.0.5",
-    "jest-environment-jsdom": "^30.0.5",
+    "@types/node": "^24.3.0",
+    "@typescript-eslint/eslint-plugin": "^8.41.0",
+    "@typescript-eslint/parser": "^8.41.0",
+    "@typescript-eslint/utils": "^8.41.0",
+    "eslint": "^9.34.0",
+    "jest": "30.1.3",
+    "jest-environment-jsdom": "^30.1.2",
     "jest-junit": "^16.0.0",
     "jest-preset-angular": "^15.0.0",
     "jest-websocket-mock": "^2.5.0",
     "prettier-plugin-organize-imports": "^4.2.0",
     "ts-node": "~10.9.1",
     "typescript": "^5.8.3",
-    "webpack": "^5.101.0"
+    "webpack": "^5.101.3"
   },
   "pnpm": {
     "onlyBuiltDependencies": [

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

@@ -28,6 +28,16 @@
               </div>
             }
           </div>
+          @if (allSelectOptions.length > SELECT_OPTION_PAGE_SIZE) {
+            <ngb-pagination
+              class="d-flex justify-content-end"
+              [pageSize]="SELECT_OPTION_PAGE_SIZE"
+              [collectionSize]="allSelectOptions.length"
+              [(page)]="selectOptionsPage"
+              [maxSize]="5"
+              size="sm"
+            ></ngb-pagination>
+          }
           @if (object?.id) {
             <small class="d-block mt-2" i18n>Warning: existing instances of this field will retain their current value index (e.g. option #1, #2, #3) after editing the options here</small>
           }

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

@@ -125,4 +125,42 @@ describe('CustomFieldEditDialogComponent', () => {
     fixture.detectChanges()
     expect(document.activeElement).toBe(selectOptionInputs.last.nativeElement)
   })
+
+  it('should send all select options including those changed in form on save', () => {
+    component.dialogMode = EditDialogMode.EDIT
+    component.object = {
+      id: 1,
+      name: 'Field 1',
+      data_type: CustomFieldDataType.Select,
+      extra_data: {
+        select_options: Array.from({ length: 50 }, (_, i) => ({
+          label: `Option ${i + 1}`,
+          id: `${i + 1}-xyz`,
+        })),
+      },
+    }
+    fixture.detectChanges()
+    component.ngOnInit()
+    component.selectOptionsPage = 2
+    fixture.detectChanges()
+    component.objectForm
+      .get('extra_data')
+      .get('select_options')
+      .get('0')
+      .get('label')
+      .setValue('Updated Option 9')
+    const formValues = (component as any).getFormValues()
+    // first item unchanged
+    expect(formValues.extra_data.select_options[0]).toEqual({
+      label: 'Option 1',
+      id: '1-xyz',
+    })
+    // page 2 first item updated
+    expect(
+      formValues.extra_data.select_options[component.SELECT_OPTION_PAGE_SIZE]
+    ).toEqual({
+      label: 'Updated Option 9',
+      id: '9-xyz',
+    })
+  })
 })

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

@@ -14,6 +14,7 @@ import {
   FormsModule,
   ReactiveFormsModule,
 } from '@angular/forms'
+import { NgbPaginationModule } from '@ng-bootstrap/ng-bootstrap'
 import { NgxBootstrapIconsModule } from 'ngx-bootstrap-icons'
 import { takeUntil } from 'rxjs'
 import {
@@ -28,6 +29,8 @@ import { SelectComponent } from '../../input/select/select.component'
 import { TextComponent } from '../../input/text/text.component'
 import { EditDialogComponent, EditDialogMode } from '../edit-dialog.component'
 
+const SELECT_OPTION_PAGE_SIZE = 8
+
 @Component({
   selector: 'pngx-custom-field-edit-dialog',
   templateUrl: './custom-field-edit-dialog.component.html',
@@ -37,6 +40,7 @@ import { EditDialogComponent, EditDialogMode } from '../edit-dialog.component'
     TextComponent,
     FormsModule,
     ReactiveFormsModule,
+    NgbPaginationModule,
     NgxBootstrapIconsModule,
   ],
 })
@@ -45,6 +49,21 @@ export class CustomFieldEditDialogComponent
   implements OnInit, AfterViewInit
 {
   CustomFieldDataType = CustomFieldDataType
+  SELECT_OPTION_PAGE_SIZE = SELECT_OPTION_PAGE_SIZE
+
+  private _allSelectOptions: any[] = []
+  public get allSelectOptions(): any[] {
+    return this._allSelectOptions
+  }
+
+  private _selectOptionsPage: number
+  public get selectOptionsPage(): number {
+    return this._selectOptionsPage
+  }
+  public set selectOptionsPage(v: number) {
+    this._selectOptionsPage = v
+    this.updateSelectOptions()
+  }
 
   @ViewChildren('selectOption')
   private selectOptionInputs: QueryList<ElementRef>
@@ -67,17 +86,10 @@ export class CustomFieldEditDialogComponent
       this.objectForm.get('data_type').disable()
     }
     if (this.object?.data_type === CustomFieldDataType.Select) {
-      this.selectOptions.clear()
-      this.object.extra_data.select_options
-        .filter((option) => option)
-        .forEach((option) =>
-          this.selectOptions.push(
-            new FormGroup({
-              label: new FormControl(option.label),
-              id: new FormControl(option.id),
-            })
-          )
-        )
+      this._allSelectOptions = [
+        ...(this.object.extra_data.select_options ?? []),
+      ]
+      this.selectOptionsPage = 1
     }
   }
 
@@ -87,6 +99,19 @@ export class CustomFieldEditDialogComponent
       .subscribe(() => {
         this.selectOptionInputs.last?.nativeElement.focus()
       })
+
+    this.objectForm.valueChanges
+      .pipe(takeUntil(this.unsubscribeNotifier))
+      .subscribe((change) => {
+        // Update the relevant select options values if changed in the form, which is only a page of the entire list
+        this.objectForm
+          .get('extra_data.select_options')
+          ?.value.forEach((option, index) => {
+            this._allSelectOptions[
+              index + (this.selectOptionsPage - 1) * SELECT_OPTION_PAGE_SIZE
+            ] = option
+          })
+      })
   }
 
   getCreateTitle() {
@@ -108,6 +133,17 @@ export class CustomFieldEditDialogComponent
     })
   }
 
+  protected getFormValues() {
+    const formValues = super.getFormValues()
+    if (
+      this.objectForm.get('data_type')?.value === CustomFieldDataType.Select
+    ) {
+      // Make sure we send all select options, with updated values
+      formValues.extra_data.select_options = this._allSelectOptions
+    }
+    return formValues
+  }
+
   getDataTypes() {
     return DATA_TYPE_LABELS
   }
@@ -116,13 +152,35 @@ export class CustomFieldEditDialogComponent
     return this.dialogMode === EditDialogMode.EDIT
   }
 
+  private updateSelectOptions() {
+    this.selectOptions.clear()
+    this._allSelectOptions
+      .slice(
+        (this.selectOptionsPage - 1) * SELECT_OPTION_PAGE_SIZE,
+        this.selectOptionsPage * SELECT_OPTION_PAGE_SIZE
+      )
+      .forEach((option) =>
+        this.selectOptions.push(
+          new FormGroup({
+            label: new FormControl(option.label),
+            id: new FormControl(option.id),
+          })
+        )
+      )
+  }
+
   public addSelectOption() {
-    this.selectOptions.push(
-      new FormGroup({ label: new FormControl(null), id: new FormControl(null) })
+    this._allSelectOptions.push({ label: null, id: null })
+    this.selectOptionsPage = Math.ceil(
+      this.allSelectOptions.length / SELECT_OPTION_PAGE_SIZE
     )
   }
 
   public removeSelectOption(index: number) {
     this.selectOptions.removeAt(index)
+    this._allSelectOptions.splice(
+      index + (this.selectOptionsPage - 1) * SELECT_OPTION_PAGE_SIZE,
+      1
+    )
   }
 }

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

@@ -147,9 +147,13 @@ export abstract class EditDialogComponent<
     )
   }
 
+  protected getFormValues(): any {
+    return Object.assign({}, this.objectForm.value)
+  }
+
   save() {
     this.error = null
-    const formValues = Object.assign({}, this.objectForm.value)
+    const formValues = this.getFormValues()
     const permissionsObject: PermissionsFormObject =
       this.objectForm.get('permissions_form')?.value
     if (permissionsObject) {

src/documents/management/commands/document_consumer.py

@@ -32,7 +32,7 @@ except ImportError:  # pragma: no cover
 logger = logging.getLogger("paperless.management.consumer")
 
 
-def _tags_from_path(filepath) -> list[int]:
+def _tags_from_path(filepath: Path) -> list[int]:
     """
     Walk up the directory tree from filepath to CONSUMPTION_DIR
     and get or create Tag IDs for every directory.
@@ -41,7 +41,7 @@ def _tags_from_path(filepath) -> list[int]:
     """
     db.close_old_connections()
     tag_ids = set()
-    path_parts = Path(filepath).relative_to(settings.CONSUMPTION_DIR).parent.parts
+    path_parts = filepath.relative_to(settings.CONSUMPTION_DIR).parent.parts
     for part in path_parts:
         tag_ids.add(
             Tag.objects.get_or_create(name__iexact=part, defaults={"name": part})[0].pk,
@@ -50,17 +50,13 @@ def _tags_from_path(filepath) -> list[int]:
     return list(tag_ids)
 
 
-def _is_ignored(filepath: str) -> bool:
+def _is_ignored(filepath: Path) -> bool:
     """
     Checks if the given file should be ignored, based on configured
     patterns.
 
     Returns True if the file is ignored, False otherwise
     """
-    filepath = os.path.abspath(
-        os.path.normpath(filepath),
-    )
-
     # Trim out the consume directory, leaving only filename and it's
     # path relative to the consume directory
     filepath_relative = PurePath(filepath).relative_to(settings.CONSUMPTION_DIR)
@@ -85,15 +81,15 @@ def _is_ignored(filepath: str) -> bool:
     return False
 
 
-def _consume(filepath: str) -> None:
-    if os.path.isdir(filepath) or _is_ignored(filepath):
+def _consume(filepath: Path) -> None:
+    if filepath.is_dir() or _is_ignored(filepath):
         return
 
-    if not os.path.isfile(filepath):
+    if not filepath.is_file():
         logger.debug(f"Not consuming file {filepath}: File has moved.")
         return
 
-    if not is_file_ext_supported(os.path.splitext(filepath)[1]):
+    if not is_file_ext_supported(filepath.suffix):
         logger.warning(f"Not consuming file {filepath}: Unknown file extension.")
         return
 
@@ -107,7 +103,7 @@ def _consume(filepath: str) -> None:
 
     while (read_try_count < os_error_retry_count) and not file_open_ok:
         try:
-            with open(filepath, "rb"):
+            with filepath.open("rb"):
                 file_open_ok = True
         except OSError as e:
             read_try_count += 1
@@ -141,7 +137,7 @@ def _consume(filepath: str) -> None:
         logger.exception("Error while consuming document")
 
 
-def _consume_wait_unmodified(file: str) -> None:
+def _consume_wait_unmodified(file: Path) -> None:
     """
     Waits for the given file to appear unmodified based on file size
     and modification time.  Will wait a configured number of seconds
@@ -157,7 +153,7 @@ def _consume_wait_unmodified(file: str) -> None:
     current_try = 0
     while current_try < settings.CONSUMER_POLLING_RETRY_COUNT:
         try:
-            stat_data = os.stat(file)
+            stat_data = file.stat()
             new_mtime = stat_data.st_mtime
             new_size = stat_data.st_size
         except FileNotFoundError:
@@ -182,10 +178,10 @@ class Handler(FileSystemEventHandler):
         self._pool = pool
 
     def on_created(self, event):
-        self._pool.submit(_consume_wait_unmodified, event.src_path)
+        self._pool.submit(_consume_wait_unmodified, Path(event.src_path))
 
     def on_moved(self, event):
-        self._pool.submit(_consume_wait_unmodified, event.dest_path)
+        self._pool.submit(_consume_wait_unmodified, Path(event.dest_path))
 
 
 class Command(BaseCommand):
@@ -227,9 +223,9 @@ class Command(BaseCommand):
         if not directory:
             raise CommandError("CONSUMPTION_DIR does not appear to be set.")
 
-        directory = os.path.abspath(directory)
+        directory = Path(directory).resolve()
 
-        if not os.path.isdir(directory):
+        if not directory.is_dir():
             raise CommandError(f"Consumption directory {directory} does not exist")
 
         # Consumer will need this
@@ -238,11 +234,11 @@ class Command(BaseCommand):
         if recursive:
             for dirpath, _, filenames in os.walk(directory):
                 for filename in filenames:
-                    filepath = os.path.join(dirpath, filename)
+                    filepath = Path(dirpath) / filename
                     _consume(filepath)
         else:
-            for entry in os.scandir(directory):
-                _consume(entry.path)
+            for filepath in directory.iterdir():
+                _consume(filepath)
 
         if options["oneshot"]:
             return
@@ -310,7 +306,7 @@ class Command(BaseCommand):
                 try:
                     for event in inotify.read(timeout=timeout_ms):
                         path = inotify.get_path(event.wd) if recursive else directory
-                        filepath = os.path.join(path, event.name)
+                        filepath = Path(path) / event.name
                         if flags.MODIFY in flags.from_mask(event.mask):
                             notified_files.pop(filepath, None)
                         else:
@@ -327,9 +323,7 @@ class Command(BaseCommand):
 
                         # Also make sure the file exists still, some scanners might write a
                         # temporary file first
-                        file_still_exists = os.path.exists(filepath) and os.path.isfile(
-                            filepath,
-                        )
+                        file_still_exists = filepath.exists() and filepath.is_file()
 
                         if waited_long_enough and file_still_exists:
                             _consume(filepath)

src/documents/migrations/1012_fix_archive_files.py

@@ -5,6 +5,7 @@ import logging
 import os
 import shutil
 from collections import defaultdict
+from pathlib import Path
 from time import sleep
 
 import pathvalidate
@@ -50,38 +51,38 @@ def many_to_dictionary(field):  # pragma: no cover
     return mydictionary
 
 
-def archive_name_from_filename(filename):
-    return os.path.splitext(filename)[0] + ".pdf"
+def archive_name_from_filename(filename: Path) -> Path:
+    return Path(filename.stem + ".pdf")
 
 
-def archive_path_old(doc):
+def archive_path_old(doc) -> Path:
     if doc.filename:
-        fname = archive_name_from_filename(doc.filename)
+        fname = archive_name_from_filename(Path(doc.filename))
     else:
-        fname = f"{doc.pk:07}.pdf"
+        fname = Path(f"{doc.pk:07}.pdf")
 
-    return os.path.join(settings.ARCHIVE_DIR, fname)
+    return settings.ARCHIVE_DIR / fname
 
 
 STORAGE_TYPE_GPG = "gpg"
 
 
-def archive_path_new(doc):
+def archive_path_new(doc) -> Path | None:
     if doc.archive_filename is not None:
-        return os.path.join(settings.ARCHIVE_DIR, str(doc.archive_filename))
+        return settings.ARCHIVE_DIR / doc.archive_filename
     else:
         return None
 
 
-def source_path(doc):
+def source_path(doc) -> Path:
     if doc.filename:
-        fname = str(doc.filename)
+        fname = doc.filename
     else:
         fname = f"{doc.pk:07}{doc.file_type}"
         if doc.storage_type == STORAGE_TYPE_GPG:
-            fname += ".gpg"  # pragma: no cover
+            fname = Path(str(fname) + ".gpg")  # pragma: no cover
 
-    return os.path.join(settings.ORIGINALS_DIR, fname)
+    return settings.ORIGINALS_DIR / fname
 
 
 def generate_unique_filename(doc, *, archive_filename=False):
@@ -104,7 +105,7 @@ def generate_unique_filename(doc, *, archive_filename=False):
             # still the same as before.
             return new_filename
 
-        if os.path.exists(os.path.join(root, new_filename)):
+        if (root / new_filename).exists():
             counter += 1
         else:
             return new_filename
@@ -202,18 +203,18 @@ def create_archive_version(doc, retry_count=3):
                 parser,
                 source_path(doc),
                 doc.mime_type,
-                os.path.basename(doc.filename),
+                Path(doc.filename).name,
             )
             doc.content = parser.get_text()
 
-            if parser.get_archive_path() and os.path.isfile(parser.get_archive_path()):
+            if parser.get_archive_path() and Path(parser.get_archive_path()).is_file():
                 doc.archive_filename = generate_unique_filename(
                     doc,
                     archive_filename=True,
                 )
-                with open(parser.get_archive_path(), "rb") as f:
+                with Path(parser.get_archive_path()).open("rb") as f:
                     doc.archive_checksum = hashlib.md5(f.read()).hexdigest()
-                os.makedirs(os.path.dirname(archive_path_new(doc)), exist_ok=True)
+                archive_path_new(doc).parent.mkdir(parents=True, exist_ok=True)
                 shutil.copy2(parser.get_archive_path(), archive_path_new(doc))
             else:
                 doc.archive_checksum = None
@@ -264,7 +265,7 @@ def move_old_to_new_locations(apps, schema_editor):
     # check that archive files of all unaffected documents are in place
     for doc in Document.objects.filter(archive_checksum__isnull=False):
         old_path = archive_path_old(doc)
-        if doc.id not in affected_document_ids and not os.path.isfile(old_path):
+        if doc.id not in affected_document_ids and not old_path.is_file():
             raise ValueError(
                 f"Archived document ID:{doc.id} does not exist at: {old_path}",
             )
@@ -285,12 +286,12 @@ def move_old_to_new_locations(apps, schema_editor):
         if doc.id in affected_document_ids:
             old_path = archive_path_old(doc)
             # remove affected archive versions
-            if os.path.isfile(old_path):
+            if old_path.is_file():
                 logger.debug(f"Removing {old_path}")
-                os.unlink(old_path)
+                old_path.unlink()
         else:
             # Set archive path for unaffected files
-            doc.archive_filename = archive_name_from_filename(doc.filename)
+            doc.archive_filename = archive_name_from_filename(Path(doc.filename))
             Document.objects.filter(id=doc.id).update(
                 archive_filename=doc.archive_filename,
             )
@@ -316,7 +317,7 @@ def move_new_to_old_locations(apps, schema_editor):
                 f"filename.",
             )
         old_archive_paths.add(old_archive_path)
-        if new_archive_path != old_archive_path and os.path.isfile(old_archive_path):
+        if new_archive_path != old_archive_path and old_archive_path.is_file():
             raise ValueError(
                 f"Cannot migrate: Cannot move {new_archive_path} to "
                 f"{old_archive_path}: file already exists.",

src/documents/parsers.py

@@ -169,7 +169,7 @@ def run_convert(
     args += ["-depth", str(depth)] if depth else []
     args += ["-auto-orient"] if auto_orient else []
     args += ["-define", "pdf:use-cropbox=true"] if use_cropbox else []
-    args += [input_file, output_file]
+    args += [str(input_file), str(output_file)]
 
     logger.debug("Execute: " + " ".join(args), extra={"group": logging_group})
 
@@ -188,8 +188,8 @@ def get_default_thumbnail() -> Path:
     return (Path(__file__).parent / "resources" / "document.webp").resolve()
 
 
-def make_thumbnail_from_pdf_gs_fallback(in_path, temp_dir, logging_group=None) -> str:
-    out_path = os.path.join(temp_dir, "convert_gs.webp")
+def make_thumbnail_from_pdf_gs_fallback(in_path, temp_dir, logging_group=None) -> Path:
+    out_path: Path = Path(temp_dir) / "convert_gs.webp"
 
     # if convert fails, fall back to extracting
     # the first PDF page as a PNG using Ghostscript
@@ -199,7 +199,7 @@ def make_thumbnail_from_pdf_gs_fallback(in_path, temp_dir, logging_group=None) -
         extra={"group": logging_group},
     )
     # Ghostscript doesn't handle WebP outputs
-    gs_out_path = os.path.join(temp_dir, "gs_out.png")
+    gs_out_path: Path = Path(temp_dir) / "gs_out.png"
     cmd = [settings.GS_BINARY, "-q", "-sDEVICE=pngalpha", "-o", gs_out_path, in_path]
 
     try:
@@ -227,16 +227,16 @@ def make_thumbnail_from_pdf_gs_fallback(in_path, temp_dir, logging_group=None) -
         # The caller might expect a generated thumbnail that can be moved,
         # so we need to copy it before it gets moved.
         # https://github.com/paperless-ngx/paperless-ngx/issues/3631
-        default_thumbnail_path = os.path.join(temp_dir, "document.webp")
+        default_thumbnail_path: Path = Path(temp_dir) / "document.webp"
         copy_file_with_basic_stats(get_default_thumbnail(), default_thumbnail_path)
         return default_thumbnail_path
 
 
-def make_thumbnail_from_pdf(in_path, temp_dir, logging_group=None) -> Path:
+def make_thumbnail_from_pdf(in_path: Path, temp_dir: Path, logging_group=None) -> Path:
     """
     The thumbnail of a PDF is just a 500px wide image of the first page.
     """
-    out_path = temp_dir / "convert.webp"
+    out_path: Path = temp_dir / "convert.webp"
 
     # Run convert to get a decent thumbnail
     try:

src/documents/tests/test_classifier.py

@@ -654,7 +654,7 @@ class TestClassifier(DirectoriesMixin, TestCase):
         },
     )
     @override_settings(
-        MODEL_FILE=(Path(__file__).parent / "data" / "model.pickle").as_posix(),
+        MODEL_FILE=str(Path(__file__).parent / "data" / "model.pickle"),
     )
     @pytest.mark.skip(
         reason="Disabled caching due to high memory usage - need to investigate.",

src/documents/tests/test_consumer.py

@@ -254,7 +254,7 @@ class TestConsumer(
         # https://github.com/jonaswinkler/paperless-ng/discussions/1037
 
         filename = self.get_test_file()
-        shadow_file = Path(self.dirs.scratch_dir / "._sample.pdf")
+        shadow_file = Path(self.dirs.scratch_dir) / "._sample.pdf"
 
         shutil.copy(filename, shadow_file)
 

src/documents/tests/test_management_consumer.py

@@ -258,66 +258,66 @@ class TestConsumer(DirectoriesMixin, ConsumerThreadMixin, TransactionTestCase):
     def test_is_ignored(self):
         test_paths = [
             {
-                "path": (Path(self.dirs.consumption_dir) / "foo.pdf").as_posix(),
+                "path": str(Path(self.dirs.consumption_dir) / "foo.pdf"),
                 "ignore": False,
             },
             {
-                "path": (
-                    Path(self.dirs.consumption_dir) / "foo" / "bar.pdf"
-                ).as_posix(),
+                "path": str(
+                    Path(self.dirs.consumption_dir) / "foo" / "bar.pdf",
+                ),
                 "ignore": False,
             },
             {
-                "path": (Path(self.dirs.consumption_dir) / ".DS_STORE").as_posix(),
+                "path": str(Path(self.dirs.consumption_dir) / ".DS_STORE"),
                 "ignore": True,
             },
             {
-                "path": (Path(self.dirs.consumption_dir) / ".DS_Store").as_posix(),
+                "path": str(Path(self.dirs.consumption_dir) / ".DS_Store"),
                 "ignore": True,
             },
             {
-                "path": (
-                    Path(self.dirs.consumption_dir) / ".stfolder" / "foo.pdf"
-                ).as_posix(),
+                "path": str(
+                    Path(self.dirs.consumption_dir) / ".stfolder" / "foo.pdf",
+                ),
                 "ignore": True,
             },
             {
-                "path": (Path(self.dirs.consumption_dir) / ".stfolder.pdf").as_posix(),
+                "path": str(Path(self.dirs.consumption_dir) / ".stfolder.pdf"),
                 "ignore": False,
             },
             {
-                "path": (
-                    Path(self.dirs.consumption_dir) / ".stversions" / "foo.pdf"
-                ).as_posix(),
+                "path": str(
+                    Path(self.dirs.consumption_dir) / ".stversions" / "foo.pdf",
+                ),
                 "ignore": True,
             },
             {
-                "path": (
-                    Path(self.dirs.consumption_dir) / ".stversions.pdf"
-                ).as_posix(),
+                "path": str(
+                    Path(self.dirs.consumption_dir) / ".stversions.pdf",
+                ),
                 "ignore": False,
             },
             {
-                "path": (Path(self.dirs.consumption_dir) / "._foo.pdf").as_posix(),
+                "path": str(Path(self.dirs.consumption_dir) / "._foo.pdf"),
                 "ignore": True,
             },
             {
-                "path": (Path(self.dirs.consumption_dir) / "my_foo.pdf").as_posix(),
+                "path": str(Path(self.dirs.consumption_dir) / "my_foo.pdf"),
                 "ignore": False,
             },
             {
-                "path": (
-                    Path(self.dirs.consumption_dir) / "._foo" / "bar.pdf"
-                ).as_posix(),
+                "path": str(
+                    Path(self.dirs.consumption_dir) / "._foo" / "bar.pdf",
+                ),
                 "ignore": True,
             },
             {
-                "path": (
+                "path": str(
                     Path(self.dirs.consumption_dir)
                     / "@eaDir"
                     / "SYNO@.fileindexdb"
-                    / "_1jk.fnm"
-                ).as_posix(),
+                    / "_1jk.fnm",
+                ),
                 "ignore": True,
             },
         ]
@@ -330,7 +330,7 @@ class TestConsumer(DirectoriesMixin, ConsumerThreadMixin, TransactionTestCase):
                 f'_is_ignored("{filepath}") != {expected_ignored_result}',
             )
 
-    @mock.patch("documents.management.commands.document_consumer.open")
+    @mock.patch("documents.management.commands.document_consumer.Path.open")
     def test_consume_file_busy(self, open_mock):
         # Calling this mock always raises this
         open_mock.side_effect = OSError

src/documents/tests/test_management_exporter.py

@@ -230,9 +230,9 @@ class TestExportImport(
 
         for element in manifest:
             if element["model"] == "documents.document":
-                fname = (
-                    self.target / element[document_exporter.EXPORTER_FILE_NAME]
-                ).as_posix()
+                fname = str(
+                    self.target / element[document_exporter.EXPORTER_FILE_NAME],
+                )
                 self.assertIsFile(fname)
                 self.assertIsFile(
                     self.target / element[document_exporter.EXPORTER_THUMBNAIL_NAME],
@@ -462,9 +462,9 @@ class TestExportImport(
 
         call_command(*args)
 
-        expected_file = (
-            self.target / f"export-{timezone.localdate().isoformat()}.zip"
-        ).as_posix()
+        expected_file = str(
+            self.target / f"export-{timezone.localdate().isoformat()}.zip",
+        )
 
         self.assertIsFile(expected_file)
 
@@ -498,9 +498,9 @@ class TestExportImport(
         ):
             call_command(*args)
 
-        expected_file = (
-            self.target / f"export-{timezone.localdate().isoformat()}.zip"
-        ).as_posix()
+        expected_file = str(
+            self.target / f"export-{timezone.localdate().isoformat()}.zip",
+        )
 
         self.assertIsFile(expected_file)
 
@@ -544,9 +544,9 @@ class TestExportImport(
 
         call_command(*args)
 
-        expected_file = (
-            self.target / f"export-{timezone.localdate().isoformat()}.zip"
-        ).as_posix()
+        expected_file = str(
+            self.target / f"export-{timezone.localdate().isoformat()}.zip",
+        )
 
         self.assertIsFile(expected_file)
         self.assertIsNotFile(existing_file)

src/documents/tests/test_migration_archive_files.py

@@ -19,15 +19,15 @@ migration_1012_obj = importlib.import_module(
 )
 
 
-def archive_name_from_filename(filename):
-    return Path(filename).stem + ".pdf"
+def archive_name_from_filename(filename: Path) -> Path:
+    return Path(filename.stem + ".pdf")
 
 
-def archive_path_old(self):
+def archive_path_old(self) -> Path:
     if self.filename:
-        fname = archive_name_from_filename(self.filename)
+        fname = archive_name_from_filename(Path(self.filename))
     else:
-        fname = f"{self.pk:07}.pdf"
+        fname = Path(f"{self.pk:07}.pdf")
 
     return Path(settings.ARCHIVE_DIR) / fname
 

src/documents/views.py

@@ -2764,7 +2764,7 @@ class SystemStatusView(PassUserMixin):
             install_type = "docker"
 
         db_conn = connections["default"]
-        db_url = db_conn.settings_dict["NAME"]
+        db_url = str(db_conn.settings_dict["NAME"])
         db_error = None
 
         try:

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",
@@ -679,7 +680,7 @@ def _parse_db_settings() -> dict:
     databases = {
         "default": {
             "ENGINE": "django.db.backends.sqlite3",
-            "NAME": str(DATA_DIR / "db.sqlite3"),
+            "NAME": DATA_DIR / "db.sqlite3",
             "OPTIONS": {},
         },
     }
@@ -807,7 +808,7 @@ LANGUAGES = [
     ("zh-tw", _("Chinese Traditional")),
 ]
 
-LOCALE_PATHS = [str(BASE_DIR / "locale")]
+LOCALE_PATHS = [BASE_DIR / "locale"]
 
 TIME_ZONE = os.getenv("PAPERLESS_TIME_ZONE", "UTC")
 
@@ -848,21 +849,21 @@ LOGGING = {
         "file_paperless": {
             "class": "concurrent_log_handler.ConcurrentRotatingFileHandler",
             "formatter": "verbose",
-            "filename": str(LOGGING_DIR / "paperless.log"),
+            "filename": LOGGING_DIR / "paperless.log",
             "maxBytes": LOGROTATE_MAX_SIZE,
             "backupCount": LOGROTATE_MAX_BACKUPS,
         },
         "file_mail": {
             "class": "concurrent_log_handler.ConcurrentRotatingFileHandler",
             "formatter": "verbose",
-            "filename": str(LOGGING_DIR / "mail.log"),
+            "filename": LOGGING_DIR / "mail.log",
             "maxBytes": LOGROTATE_MAX_SIZE,
             "backupCount": LOGROTATE_MAX_BACKUPS,
         },
         "file_celery": {
             "class": "concurrent_log_handler.ConcurrentRotatingFileHandler",
             "formatter": "verbose",
-            "filename": str(LOGGING_DIR / "celery.log"),
+            "filename": LOGGING_DIR / "celery.log",
             "maxBytes": LOGROTATE_MAX_SIZE,
             "backupCount": LOGROTATE_MAX_BACKUPS,
         },
@@ -921,7 +922,7 @@ CELERY_ACCEPT_CONTENT = ["application/json", "application/x-python-serialize"]
 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")
+CELERY_BEAT_SCHEDULE_FILENAME = DATA_DIR / "celerybeat-schedule.db"
 
 
 # Cachalot: Database read cache.
@@ -1388,3 +1389,10 @@ 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 +1,15 @@
+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:
+        return [
+            Error(
+                "Azure AI remote parser requires endpoint 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 = 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)
+
+        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 = ""
+            return
+        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 +1,29 @@
+from django.test 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 to be configured.",
+            ),
+        )
+
+    @override_settings(REMOTE_OCR_ENGINE="something")
+    @override_settings(REMOTE_OCR_API_KEY="somekey")
+    def test_valid_configuration(self):
+        msgs = check_remote_parser_configured(None)
+        self.assertEqual(len(msgs), 0)

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, strings):
+        # 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, "")

src/paperless_tesseract/tests/test_parser.py

@@ -69,13 +69,13 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         """
         parser = RasterisedDocumentParser(uuid.uuid4())
         page_count = parser.get_page_count(
-            (self.SAMPLE_FILES / "simple-digital.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "simple-digital.pdf"),
             "application/pdf",
         )
         self.assertEqual(page_count, 1)
 
         page_count = parser.get_page_count(
-            (self.SAMPLE_FILES / "multi-page-mixed.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "multi-page-mixed.pdf"),
             "application/pdf",
         )
         self.assertEqual(page_count, 6)
@@ -92,7 +92,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         parser = RasterisedDocumentParser(uuid.uuid4())
         with self.assertLogs("paperless.parsing.tesseract", level="WARNING") as cm:
             page_count = parser.get_page_count(
-                (self.SAMPLE_FILES / "password-protected.pdf").as_posix(),
+                str(self.SAMPLE_FILES / "password-protected.pdf"),
                 "application/pdf",
             )
             self.assertEqual(page_count, None)
@@ -101,7 +101,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
     def test_thumbnail(self):
         parser = RasterisedDocumentParser(uuid.uuid4())
         thumb = parser.get_thumbnail(
-            (self.SAMPLE_FILES / "simple-digital.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "simple-digital.pdf"),
             "application/pdf",
         )
         self.assertIsFile(thumb)
@@ -109,7 +109,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
     @mock.patch("documents.parsers.run_convert")
     def test_thumbnail_fallback(self, m):
         def call_convert(input_file, output_file, **kwargs):
-            if ".pdf" in input_file:
+            if ".pdf" in str(input_file):
                 raise ParseError("Does not compute.")
             else:
                 run_convert(input_file=input_file, output_file=output_file, **kwargs)
@@ -118,7 +118,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
 
         parser = RasterisedDocumentParser(uuid.uuid4())
         thumb = parser.get_thumbnail(
-            (self.SAMPLE_FILES / "simple-digital.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "simple-digital.pdf"),
             "application/pdf",
         )
         self.assertIsFile(thumb)
@@ -126,7 +126,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
     def test_thumbnail_encrypted(self):
         parser = RasterisedDocumentParser(uuid.uuid4())
         thumb = parser.get_thumbnail(
-            (self.SAMPLE_FILES / "encrypted.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "encrypted.pdf"),
             "application/pdf",
         )
         self.assertIsFile(thumb)
@@ -134,17 +134,17 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
     def test_get_dpi(self):
         parser = RasterisedDocumentParser(None)
 
-        dpi = parser.get_dpi((self.SAMPLE_FILES / "simple-no-dpi.png").as_posix())
+        dpi = parser.get_dpi(str(self.SAMPLE_FILES / "simple-no-dpi.png"))
         self.assertEqual(dpi, None)
 
-        dpi = parser.get_dpi((self.SAMPLE_FILES / "simple.png").as_posix())
+        dpi = parser.get_dpi(str(self.SAMPLE_FILES / "simple.png"))
         self.assertEqual(dpi, 72)
 
     def test_simple_digital(self):
         parser = RasterisedDocumentParser(None)
 
         parser.parse(
-            (self.SAMPLE_FILES / "simple-digital.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "simple-digital.pdf"),
             "application/pdf",
         )
 
@@ -156,7 +156,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         parser = RasterisedDocumentParser(None)
 
         parser.parse(
-            (self.SAMPLE_FILES / "with-form.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "with-form.pdf"),
             "application/pdf",
         )
 
@@ -172,7 +172,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         parser = RasterisedDocumentParser(None)
 
         parser.parse(
-            (self.SAMPLE_FILES / "with-form.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "with-form.pdf"),
             "application/pdf",
         )
 
@@ -186,7 +186,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
     def test_signed(self):
         parser = RasterisedDocumentParser(None)
 
-        parser.parse((self.SAMPLE_FILES / "signed.pdf").as_posix(), "application/pdf")
+        parser.parse(str(self.SAMPLE_FILES / "signed.pdf"), "application/pdf")
 
         self.assertIsNone(parser.archive_path)
         self.assertContainsStrings(
@@ -202,7 +202,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         parser = RasterisedDocumentParser(None)
 
         parser.parse(
-            (self.SAMPLE_FILES / "encrypted.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "encrypted.pdf"),
             "application/pdf",
         )
 
@@ -213,7 +213,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
     def test_with_form_error_notext(self):
         parser = RasterisedDocumentParser(None)
         parser.parse(
-            (self.SAMPLE_FILES / "with-form.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "with-form.pdf"),
             "application/pdf",
         )
 
@@ -227,7 +227,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         parser = RasterisedDocumentParser(None)
 
         parser.parse(
-            (self.SAMPLE_FILES / "with-form.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "with-form.pdf"),
             "application/pdf",
         )
 
@@ -239,7 +239,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
     def test_image_simple(self):
         parser = RasterisedDocumentParser(None)
 
-        parser.parse((self.SAMPLE_FILES / "simple.png").as_posix(), "image/png")
+        parser.parse(str(self.SAMPLE_FILES / "simple.png"), "image/png")
 
         self.assertIsFile(parser.archive_path)
 
@@ -255,7 +255,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
             dest_file = Path(tempdir) / "simple-alpha.png"
             shutil.copy(sample_file, dest_file)
 
-            parser.parse(dest_file.as_posix(), "image/png")
+            parser.parse(str(dest_file), "image/png")
 
             self.assertIsFile(parser.archive_path)
 
@@ -265,7 +265,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         parser = RasterisedDocumentParser(None)
 
         dpi = parser.calculate_a4_dpi(
-            (self.SAMPLE_FILES / "simple-no-dpi.png").as_posix(),
+            str(self.SAMPLE_FILES / "simple-no-dpi.png"),
         )
 
         self.assertEqual(dpi, 62)
@@ -277,7 +277,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
 
         def f():
             parser.parse(
-                (self.SAMPLE_FILES / "simple-no-dpi.png").as_posix(),
+                str(self.SAMPLE_FILES / "simple-no-dpi.png"),
                 "image/png",
             )
 
@@ -287,7 +287,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
     def test_image_no_dpi_default(self):
         parser = RasterisedDocumentParser(None)
 
-        parser.parse((self.SAMPLE_FILES / "simple-no-dpi.png").as_posix(), "image/png")
+        parser.parse(str(self.SAMPLE_FILES / "simple-no-dpi.png"), "image/png")
 
         self.assertIsFile(parser.archive_path)
 
@@ -299,7 +299,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
     def test_multi_page(self):
         parser = RasterisedDocumentParser(None)
         parser.parse(
-            (self.SAMPLE_FILES / "multi-page-digital.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "multi-page-digital.pdf"),
             "application/pdf",
         )
         self.assertIsFile(parser.archive_path)
@@ -312,7 +312,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
     def test_multi_page_pages_skip(self):
         parser = RasterisedDocumentParser(None)
         parser.parse(
-            (self.SAMPLE_FILES / "multi-page-digital.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "multi-page-digital.pdf"),
             "application/pdf",
         )
         self.assertIsFile(parser.archive_path)
@@ -325,7 +325,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
     def test_multi_page_pages_redo(self):
         parser = RasterisedDocumentParser(None)
         parser.parse(
-            (self.SAMPLE_FILES / "multi-page-digital.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "multi-page-digital.pdf"),
             "application/pdf",
         )
         self.assertIsFile(parser.archive_path)
@@ -338,7 +338,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
     def test_multi_page_pages_force(self):
         parser = RasterisedDocumentParser(None)
         parser.parse(
-            (self.SAMPLE_FILES / "multi-page-digital.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "multi-page-digital.pdf"),
             "application/pdf",
         )
         self.assertIsFile(parser.archive_path)
@@ -351,7 +351,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
     def test_multi_page_analog_pages_skip(self):
         parser = RasterisedDocumentParser(None)
         parser.parse(
-            (self.SAMPLE_FILES / "multi-page-images.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "multi-page-images.pdf"),
             "application/pdf",
         )
         self.assertIsFile(parser.archive_path)
@@ -375,7 +375,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         """
         parser = RasterisedDocumentParser(None)
         parser.parse(
-            (self.SAMPLE_FILES / "multi-page-images.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "multi-page-images.pdf"),
             "application/pdf",
         )
         self.assertIsFile(parser.archive_path)
@@ -397,7 +397,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         """
         parser = RasterisedDocumentParser(None)
         parser.parse(
-            (self.SAMPLE_FILES / "multi-page-images.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "multi-page-images.pdf"),
             "application/pdf",
         )
         self.assertIsFile(parser.archive_path)
@@ -419,7 +419,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         """
         parser = RasterisedDocumentParser(None)
         parser.parse(
-            (self.SAMPLE_FILES / "multi-page-digital.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "multi-page-digital.pdf"),
             "application/pdf",
         )
         self.assertIsNone(parser.archive_path)
@@ -442,7 +442,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         """
         parser = RasterisedDocumentParser(None)
         parser.parse(
-            (self.SAMPLE_FILES / "multi-page-images.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "multi-page-images.pdf"),
             "application/pdf",
         )
 
@@ -467,7 +467,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         """
         parser = RasterisedDocumentParser(None)
         parser.parse(
-            (self.SAMPLE_FILES / "multi-page-digital.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "multi-page-digital.pdf"),
             "application/pdf",
         )
         self.assertIsNotNone(parser.archive_path)
@@ -490,7 +490,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         """
         parser = RasterisedDocumentParser(None)
         parser.parse(
-            (self.SAMPLE_FILES / "multi-page-images.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "multi-page-images.pdf"),
             "application/pdf",
         )
         self.assertIsNotNone(parser.archive_path)
@@ -513,7 +513,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         """
         parser = RasterisedDocumentParser(None)
         parser.parse(
-            (self.SAMPLE_FILES / "multi-page-digital.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "multi-page-digital.pdf"),
             "application/pdf",
         )
         self.assertIsNone(parser.archive_path)
@@ -536,7 +536,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         """
         parser = RasterisedDocumentParser(None)
         parser.parse(
-            (self.SAMPLE_FILES / "multi-page-images.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "multi-page-images.pdf"),
             "application/pdf",
         )
         self.assertIsNotNone(parser.archive_path)
@@ -559,7 +559,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         """
         parser = RasterisedDocumentParser(None)
         parser.parse(
-            (self.SAMPLE_FILES / "multi-page-digital.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "multi-page-digital.pdf"),
             "application/pdf",
         )
         self.assertIsNone(parser.archive_path)
@@ -582,7 +582,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         """
         parser = RasterisedDocumentParser(None)
         parser.parse(
-            (self.SAMPLE_FILES / "multi-page-images.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "multi-page-images.pdf"),
             "application/pdf",
         )
         self.assertIsNone(parser.archive_path)
@@ -605,7 +605,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         """
         parser = RasterisedDocumentParser(None)
         parser.parse(
-            (self.SAMPLE_FILES / "multi-page-mixed.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "multi-page-mixed.pdf"),
             "application/pdf",
         )
         self.assertIsNotNone(parser.archive_path)
@@ -636,7 +636,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         """
         parser = RasterisedDocumentParser(None)
         parser.parse(
-            (self.SAMPLE_FILES / "single-page-mixed.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "single-page-mixed.pdf"),
             "application/pdf",
         )
         self.assertIsNotNone(parser.archive_path)
@@ -673,7 +673,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         """
         parser = RasterisedDocumentParser(None)
         parser.parse(
-            (self.SAMPLE_FILES / "multi-page-mixed.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "multi-page-mixed.pdf"),
             "application/pdf",
         )
         self.assertIsNone(parser.archive_path)
@@ -685,7 +685,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
     @override_settings(OCR_MODE="skip", OCR_ROTATE_PAGES=True)
     def test_rotate(self):
         parser = RasterisedDocumentParser(None)
-        parser.parse((self.SAMPLE_FILES / "rotated.pdf").as_posix(), "application/pdf")
+        parser.parse(str(self.SAMPLE_FILES / "rotated.pdf"), "application/pdf")
         self.assertContainsStrings(
             parser.get_text(),
             [
@@ -707,7 +707,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         """
         parser = RasterisedDocumentParser(None)
         parser.parse(
-            (self.SAMPLE_FILES / "multi-page-images.tiff").as_posix(),
+            str(self.SAMPLE_FILES / "multi-page-images.tiff"),
             "image/tiff",
         )
         self.assertIsFile(parser.archive_path)
@@ -752,9 +752,9 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
             - Text from all pages extracted
         """
         parser = RasterisedDocumentParser(None)
-        sample_file = (
-            self.SAMPLE_FILES / "multi-page-images-alpha-rgb.tiff"
-        ).as_posix()
+        sample_file = str(
+            self.SAMPLE_FILES / "multi-page-images-alpha-rgb.tiff",
+        )
         with tempfile.NamedTemporaryFile() as tmp_file:
             shutil.copy(sample_file, tmp_file.name)
             parser.parse(
@@ -843,7 +843,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         parser = RasterisedDocumentParser(None)
 
         parser.parse(
-            (self.SAMPLE_FILES / "rtl-test.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "rtl-test.pdf"),
             "application/pdf",
         )
 
@@ -858,7 +858,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         self.assertRaises(
             ParseError,
             parser.parse,
-            (self.SAMPLE_FILES / "simple-digital.pdf").as_posix(),
+            str(self.SAMPLE_FILES / "simple-digital.pdf"),
             "application/pdf",
         )
 
@@ -868,32 +868,32 @@ class TestParserFileTypes(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
 
     def test_bmp(self):
         parser = RasterisedDocumentParser(None)
-        parser.parse((self.SAMPLE_FILES / "simple.bmp").as_posix(), "image/bmp")
+        parser.parse(str(self.SAMPLE_FILES / "simple.bmp"), "image/bmp")
         self.assertIsFile(parser.archive_path)
         self.assertIn("this is a test document", parser.get_text().lower())
 
     def test_jpg(self):
         parser = RasterisedDocumentParser(None)
-        parser.parse((self.SAMPLE_FILES / "simple.jpg").as_posix(), "image/jpeg")
+        parser.parse(str(self.SAMPLE_FILES / "simple.jpg"), "image/jpeg")
         self.assertIsFile(parser.archive_path)
         self.assertIn("this is a test document", parser.get_text().lower())
 
     def test_heic(self):
         parser = RasterisedDocumentParser(None)
-        parser.parse((self.SAMPLE_FILES / "simple.heic").as_posix(), "image/heic")
+        parser.parse(str(self.SAMPLE_FILES / "simple.heic"), "image/heic")
         self.assertIsFile(parser.archive_path)
         self.assertIn("pizza", parser.get_text().lower())
 
     @override_settings(OCR_IMAGE_DPI=200)
     def test_gif(self):
         parser = RasterisedDocumentParser(None)
-        parser.parse((self.SAMPLE_FILES / "simple.gif").as_posix(), "image/gif")
+        parser.parse(str(self.SAMPLE_FILES / "simple.gif"), "image/gif")
         self.assertIsFile(parser.archive_path)
         self.assertIn("this is a test document", parser.get_text().lower())
 
     def test_tiff(self):
         parser = RasterisedDocumentParser(None)
-        parser.parse((self.SAMPLE_FILES / "simple.tif").as_posix(), "image/tiff")
+        parser.parse(str(self.SAMPLE_FILES / "simple.tif"), "image/tiff")
         self.assertIsFile(parser.archive_path)
         self.assertIn("this is a test document", parser.get_text().lower())
 
@@ -901,7 +901,7 @@ class TestParserFileTypes(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
     def test_webp(self):
         parser = RasterisedDocumentParser(None)
         parser.parse(
-            (self.SAMPLE_FILES / "document.webp").as_posix(),
+            str(self.SAMPLE_FILES / "document.webp"),
             "image/webp",
         )
         self.assertIsFile(parser.archive_path)

uv.lock

@@ -95,6 +95,34 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/af/cc/55a32a2c98022d88812b5986d2a92c4ff3ee087e83b712ebc703bba452bf/Automat-24.8.1-py3-none-any.whl", hash = "sha256:bf029a7bc3da1e2c24da2343e7598affaa9f10bf0ab63ff808566ce90551e02a", size = 42585, upload-time = "2024-08-19T17:31:56.729Z" },
 ]
 
+[[package]]
+name = "azure-ai-documentintelligence"
+version = "1.0.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "azure-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "isodate", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "typing-extensions", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/44/7b/8115cd713e2caa5e44def85f2b7ebd02a74ae74d7113ba20bdd41fd6dd80/azure_ai_documentintelligence-1.0.2.tar.gz", hash = "sha256:4d75a2513f2839365ebabc0e0e1772f5601b3a8c9a71e75da12440da13b63484", size = 170940 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/d9/75/c9ec040f23082f54ffb1977ff8f364c2d21c79a640a13d1c1809e7fd6b1a/azure_ai_documentintelligence-1.0.2-py3-none-any.whl", hash = "sha256:e1fb446abbdeccc9759d897898a0fe13141ed29f9ad11fc705f951925822ed59", size = 106005 },
+]
+
+[[package]]
+name = "azure-core"
+version = "1.33.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "requests", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "six", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "typing-extensions", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/75/aa/7c9db8edd626f1a7d99d09ef7926f6f4fb34d5f9fa00dc394afdfe8e2a80/azure_core-1.33.0.tar.gz", hash = "sha256:f367aa07b5e3005fec2c1e184b882b0b039910733907d001c20fb08ebb8c0eb9", size = 295633 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/07/b7/76b7e144aa53bd206bf1ce34fa75350472c3f69bf30e5c8c18bc9881035d/azure_core-1.33.0-py3-none-any.whl", hash = "sha256:9b5b6d0223a1d38c37500e6971118c1e0f13f54951e6893968b38910bc9cda8f", size = 207071 },
+]
+
 [[package]]
 name = "babel"
 version = "2.17.0"
@@ -1402,6 +1430,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/c7/fc/4e5a141c3f7c7bed550ac1f69e599e92b6be449dd4677ec09f325cad0955/inotifyrecursive-0.3.5-py3-none-any.whl", hash = "sha256:7e5f4a2e1dc2bef0efa3b5f6b339c41fb4599055a2b54909d020e9e932cc8d2f", size = 8009, upload-time = "2020-11-20T12:38:46.981Z" },
 ]
 
+[[package]]
+name = "isodate"
+version = "0.7.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/54/4d/e940025e2ce31a8ce1202635910747e5a87cc3a6a6bb2d00973375014749/isodate-0.7.2.tar.gz", hash = "sha256:4cd1aa0f43ca76f4a6c6c0292a85f40b35ec2e43e315b59f06e6d32171a953e6", size = 29705 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/15/aa/0aca39a37d3c7eb941ba736ede56d689e7be91cab5d9ca846bde3999eba6/isodate-0.7.2-py3-none-any.whl", hash = "sha256:28009937d8031054830160fce6d409ed342816b543597cece116d966c6d99e15", size = 22320 },
+]
+
 [[package]]
 name = "jinja2"
 version = "3.1.6"
@@ -2010,6 +2047,7 @@ name = "paperless-ngx"
 version = "2.18.3"
 source = { virtual = "." }
 dependencies = [
+    { name = "azure-ai-documentintelligence", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "babel", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "bleach", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "celery", extra = ["redis"], marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -2144,6 +2182,7 @@ typing = [
 
 [package.metadata]
 requires-dist = [
+    { name = "azure-ai-documentintelligence", specifier = ">=1.0.2" },
     { name = "babel", specifier = ">=2.17" },
     { name = "bleach", specifier = "~=6.2.0" },
     { name = "celery", extras = ["redis"], specifier = "~=5.5.1" },