Use the shared stuff with LLM endpoint

* Chore(deps): Bump the pre-commit-dependencies group with 4 updates

---
updated-dependencies:
- dependency-name: https://github.com/codespell-project/codespell
  dependency-version: 2.4.2
  dependency-type: direct:production
  dependency-group: pre-commit-dependencies
- dependency-name: prettier
  dependency-version: 3.8.1
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: pre-commit-dependencies
- dependency-name: prettier-plugin-organize-imports
  dependency-version: 4.3.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: pre-commit-dependencies
- dependency-name: https://github.com/lovesegfault/beautysh
  dependency-version: 6.4.3
  dependency-type: direct:production
  dependency-group: pre-commit-dependencies
...

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

* Drop this, it seems more trouble than its worth

* Re-run prek with new prettier

---------

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>

.github/dependabot.yml

@@ -12,6 +12,8 @@ updates:
     open-pull-requests-limit: 10
     schedule:
       interval: "monthly"
+    cooldown:
+      default-days: 7
     labels:
       - "frontend"
       - "dependencies"
@@ -36,7 +38,9 @@ updates:
     directory: "/"
     # Check for updates once a week
     schedule:
-      interval: "weekly"
+      interval: "monthly"
+    cooldown:
+      default-days: 7
     labels:
       - "backend"
       - "dependencies"
@@ -97,6 +101,8 @@ updates:
     schedule:
       # Check for updates to GitHub Actions every month
       interval: "monthly"
+    cooldown:
+      default-days: 7
     labels:
       - "ci-cd"
       - "dependencies"
@@ -112,7 +118,9 @@ updates:
       - "/"
       - "/.devcontainer/"
     schedule:
-      interval: "weekly"
+      interval: "monthly"
+    cooldown:
+      default-days: 7
     open-pull-requests-limit: 5
     labels:
       - "dependencies"
@@ -123,7 +131,9 @@ updates:
   - package-ecosystem: "docker-compose"
     directory: "/docker/compose/"
     schedule:
-      interval: "weekly"
+      interval: "monthly"
+    cooldown:
+      default-days: 7
     open-pull-requests-limit: 5
     labels:
       - "dependencies"
@@ -147,3 +157,11 @@ updates:
       postgres:
         patterns:
           - "docker.io/library/postgres*"
+  - package-ecosystem: "pre-commit" # See documentation for possible values
+    directory: "/" # Location of package manifests
+    schedule:
+      interval: "monthly"
+    groups:
+      pre-commit-dependencies:
+        patterns:
+          - "*"

.github/workflows/ci-docker.yml

@@ -104,9 +104,9 @@ jobs:
           echo "repository=${repo_name}"
           echo "name=${repo_name}" >> $GITHUB_OUTPUT
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3.12.0
+        uses: docker/setup-buildx-action@v4.0.0
       - name: Login to GitHub Container Registry
-        uses: docker/login-action@v3.7.0
+        uses: docker/login-action@v4.0.0
         with:
           registry: ${{ env.REGISTRY }}
           username: ${{ github.actor }}
@@ -179,22 +179,22 @@ jobs:
           echo "Downloaded digests:"
           ls -la /tmp/digests/
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3.12.0
+        uses: docker/setup-buildx-action@v4.0.0
       - name: Login to GitHub Container Registry
-        uses: docker/login-action@v3.7.0
+        uses: docker/login-action@v4.0.0
         with:
           registry: ${{ env.REGISTRY }}
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
       - name: Login to Docker Hub
         if: needs.build-arch.outputs.push-external == 'true'
-        uses: docker/login-action@v3.7.0
+        uses: docker/login-action@v4.0.0
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
       - name: Login to Quay.io
         if: needs.build-arch.outputs.push-external == 'true'
-        uses: docker/login-action@v3.7.0
+        uses: docker/login-action@v4.0.0
         with:
           registry: quay.io
           username: ${{ secrets.QUAY_USERNAME }}

.github/workflows/ci-frontend.yml

@@ -67,7 +67,7 @@ jobs:
         with:
           version: 10
       - name: Use Node.js 24
-        uses: actions/setup-node@v6.2.0
+        uses: actions/setup-node@v6.3.0
         with:
           node-version: 24.x
           cache: 'pnpm'
@@ -95,7 +95,7 @@ jobs:
         with:
           version: 10
       - name: Use Node.js 24
-        uses: actions/setup-node@v6.2.0
+        uses: actions/setup-node@v6.3.0
         with:
           node-version: 24.x
           cache: 'pnpm'
@@ -130,7 +130,7 @@ jobs:
         with:
           version: 10
       - name: Use Node.js 24
-        uses: actions/setup-node@v6.2.0
+        uses: actions/setup-node@v6.3.0
         with:
           node-version: 24.x
           cache: 'pnpm'
@@ -181,7 +181,7 @@ jobs:
         with:
           version: 10
       - name: Use Node.js 24
-        uses: actions/setup-node@v6.2.0
+        uses: actions/setup-node@v6.3.0
         with:
           node-version: 24.x
           cache: 'pnpm'
@@ -214,7 +214,7 @@ jobs:
         with:
           version: 10
       - name: Use Node.js 24
-        uses: actions/setup-node@v6.2.0
+        uses: actions/setup-node@v6.3.0
         with:
           node-version: 24.x
           cache: 'pnpm'

.github/workflows/ci-release.yml

@@ -35,7 +35,7 @@ jobs:
         with:
           version: 10
       - name: Use Node.js 24
-        uses: actions/setup-node@v6.2.0
+        uses: actions/setup-node@v6.3.0
         with:
           node-version: 24.x
           cache: 'pnpm'

.github/workflows/translate-strings.yml

@@ -40,7 +40,7 @@ jobs:
         with:
           version: 10
       - name: Use Node.js 24
-        uses: actions/setup-node@v6.2.0
+        uses: actions/setup-node@v6.3.0
         with:
           node-version: 24.x
           cache: 'pnpm'

.pre-commit-config.yaml

@@ -29,7 +29,7 @@ repos:
       - id: check-case-conflict
       - id: detect-private-key
   - repo: https://github.com/codespell-project/codespell
-    rev: v2.4.1
+    rev: v2.4.2
     hooks:
       - id: codespell
         additional_dependencies: [tomli]
@@ -46,8 +46,8 @@ repos:
           - ts
           - markdown
         additional_dependencies:
-          - prettier@3.3.3
-          - 'prettier-plugin-organize-imports@4.1.0'
+          - prettier@3.8.1
+          - 'prettier-plugin-organize-imports@4.3.0'
   # Python hooks
   - repo: https://github.com/astral-sh/ruff-pre-commit
     rev: v0.15.5
@@ -65,7 +65,7 @@ repos:
       - id: hadolint
   # Shell script hooks
   - repo: https://github.com/lovesegfault/beautysh
-    rev: v6.4.2
+    rev: v6.4.3
     hooks:
       - id: beautysh
         types: [file]

.prettierrc.js

@@ -5,14 +5,6 @@ const config = {
 	singleQuote: true,
 	// https://prettier.io/docs/en/options.html#trailing-commas
 	trailingComma: 'es5',
-	overrides: [
-		{
-			files: ['docs/*.md'],
-			options: {
-				tabWidth: 4,
-			},
-		},
-	],
 	plugins: [require('prettier-plugin-organize-imports')],
 }
 

Dockerfile

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

docker/compose/docker-compose.portainer.yml

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

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

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

docker/compose/docker-compose.postgres.yml

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

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

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

docker/compose/docker-compose.sqlite.yml

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

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

@@ -10,8 +10,12 @@ cd "${PAPERLESS_SRC_DIR}"
 
 # The whole migrate, with flock, needs to run as the right user
 if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	exec s6-setlock -n "${data_dir}/migration_lock" python3 manage.py check --tag compatibility paperless
 	exec s6-setlock -n "${data_dir}/migration_lock" python3 manage.py migrate --skip-checks --no-input
 else
+	exec s6-setuidgid paperless \
+		s6-setlock -n "${data_dir}/migration_lock" \
+		python3 manage.py check --tag compatibility paperless
 	exec s6-setuidgid paperless \
 		s6-setlock -n "${data_dir}/migration_lock" \
 		python3 manage.py migrate --skip-checks --no-input

docs/administration.md

@@ -10,16 +10,16 @@ consuming documents at that time.
 
 Options available to any installation of paperless:
 
--   Use the [document exporter](#exporter). The document exporter exports all your documents,
-    thumbnails, metadata, and database contents to a specific folder. You may import your
-    documents and settings into a fresh instance of paperless again or store your
-    documents in another DMS with this export.
+- Use the [document exporter](#exporter). The document exporter exports all your documents,
+  thumbnails, metadata, and database contents to a specific folder. You may import your
+  documents and settings into a fresh instance of paperless again or store your
+  documents in another DMS with this export.
 
-    The document exporter is also able to update an already existing
-    export. Therefore, incremental backups with `rsync` are entirely
-    possible.
+  The document exporter is also able to update an already existing
+  export. Therefore, incremental backups with `rsync` are entirely
+  possible.
 
-    The exporter does not include API tokens and they will need to be re-generated after importing.
+  The exporter does not include API tokens and they will need to be re-generated after importing.
 
 !!! caution
 
@@ -29,28 +29,27 @@ Options available to any installation of paperless:
 
 Options available to docker installations:
 
--   Backup the docker volumes. These usually reside within
-    `/var/lib/docker/volumes` on the host and you need to be root in
-    order to access them.
+- Backup the docker volumes. These usually reside within
+  `/var/lib/docker/volumes` on the host and you need to be root in
+  order to access them.
 
-    Paperless uses 4 volumes:
-
-    -   `paperless_media`: This is where your documents are stored.
-    -   `paperless_data`: This is where auxiliary data is stored. This
-        folder also contains the SQLite database, if you use it.
-    -   `paperless_pgdata`: Exists only if you use PostgreSQL and
-        contains the database.
-    -   `paperless_dbdata`: Exists only if you use MariaDB and contains
-        the database.
+  Paperless uses 4 volumes:
+  - `paperless_media`: This is where your documents are stored.
+  - `paperless_data`: This is where auxiliary data is stored. This
+    folder also contains the SQLite database, if you use it.
+  - `paperless_pgdata`: Exists only if you use PostgreSQL and
+    contains the database.
+  - `paperless_dbdata`: Exists only if you use MariaDB and contains
+    the database.
 
 Options available to bare-metal and non-docker installations:
 
--   Backup the entire paperless folder. This ensures that if your
-    paperless instance crashes at some point or your disk fails, you can
-    simply copy the folder back into place and it works.
+- Backup the entire paperless folder. This ensures that if your
+  paperless instance crashes at some point or your disk fails, you can
+  simply copy the folder back into place and it works.
 
-    When using PostgreSQL or MariaDB, you'll also have to backup the
-    database.
+  When using PostgreSQL or MariaDB, you'll also have to backup the
+  database.
 
 ### Restoring {#migrating-restoring}
 
@@ -509,19 +508,19 @@ collection for issues.
 
 The issues detected by the sanity checker are as follows:
 
--   Missing original files.
--   Missing archive files.
--   Inaccessible original files due to improper permissions.
--   Inaccessible archive files due to improper permissions.
--   Corrupted original documents by comparing their checksum against
-    what is stored in the database.
--   Corrupted archive documents by comparing their checksum against what
-    is stored in the database.
--   Missing thumbnails.
--   Inaccessible thumbnails due to improper permissions.
--   Documents without any content (warning).
--   Orphaned files in the media directory (warning). These are files
-    that are not referenced by any document in paperless.
+- Missing original files.
+- Missing archive files.
+- Inaccessible original files due to improper permissions.
+- Inaccessible archive files due to improper permissions.
+- Corrupted original documents by comparing their checksum against
+  what is stored in the database.
+- Corrupted archive documents by comparing their checksum against what
+  is stored in the database.
+- Missing thumbnails.
+- Inaccessible thumbnails due to improper permissions.
+- Documents without any content (warning).
+- Orphaned files in the media directory (warning). These are files
+  that are not referenced by any document in paperless.
 
 ```
 document_sanity_checker

docs/advanced_usage.md

@@ -25,20 +25,20 @@ documents.
 
 The following algorithms are available:
 
--   **None:** No matching will be performed.
--   **Any:** Looks for any occurrence of any word provided in match in
-    the PDF. If you define the match as `Bank1 Bank2`, it will match
-    documents containing either of these terms.
--   **All:** Requires that every word provided appears in the PDF,
-    albeit not in the order provided.
--   **Exact:** Matches only if the match appears exactly as provided
-    (i.e. preserve ordering) in the PDF.
--   **Regular expression:** Parses the match as a regular expression and
-    tries to find a match within the document.
--   **Fuzzy match:** Uses a partial matching based on locating the tag text
-    inside the document, using a [partial ratio](https://rapidfuzz.github.io/RapidFuzz/Usage/fuzz.html#partial-ratio)
--   **Auto:** Tries to automatically match new documents. This does not
-    require you to set a match. See the [notes below](#automatic-matching).
+- **None:** No matching will be performed.
+- **Any:** Looks for any occurrence of any word provided in match in
+  the PDF. If you define the match as `Bank1 Bank2`, it will match
+  documents containing either of these terms.
+- **All:** Requires that every word provided appears in the PDF,
+  albeit not in the order provided.
+- **Exact:** Matches only if the match appears exactly as provided
+  (i.e. preserve ordering) in the PDF.
+- **Regular expression:** Parses the match as a regular expression and
+  tries to find a match within the document.
+- **Fuzzy match:** Uses a partial matching based on locating the tag text
+  inside the document, using a [partial ratio](https://rapidfuzz.github.io/RapidFuzz/Usage/fuzz.html#partial-ratio)
+- **Auto:** Tries to automatically match new documents. This does not
+  require you to set a match. See the [notes below](#automatic-matching).
 
 When using the _any_ or _all_ matching algorithms, you can search for
 terms that consist of multiple words by enclosing them in double quotes.
@@ -69,33 +69,33 @@ Paperless tries to hide much of the involved complexity with this
 approach. However, there are a couple caveats you need to keep in mind
 when using this feature:
 
--   Changes to your documents are not immediately reflected by the
-    matching algorithm. The neural network needs to be _trained_ on your
-    documents after changes. Paperless periodically (default: once each
-    hour) checks for changes and does this automatically for you.
--   The Auto matching algorithm only takes documents into account which
-    are NOT placed in your inbox (i.e. have any inbox tags assigned to
-    them). This ensures that the neural network only learns from
-    documents which you have correctly tagged before.
--   The matching algorithm can only work if there is a correlation
-    between the tag, correspondent, document type, or storage path and
-    the document itself. Your bank statements usually contain your bank
-    account number and the name of the bank, so this works reasonably
-    well, However, tags such as "TODO" cannot be automatically
-    assigned.
--   The matching algorithm needs a reasonable number of documents to
-    identify when to assign tags, correspondents, storage paths, and
-    types. If one out of a thousand documents has the correspondent
-    "Very obscure web shop I bought something five years ago", it will
-    probably not assign this correspondent automatically if you buy
-    something from them again. The more documents, the better.
--   Paperless also needs a reasonable amount of negative examples to
-    decide when not to assign a certain tag, correspondent, document
-    type, or storage path. This will usually be the case as you start
-    filling up paperless with documents. Example: If all your documents
-    are either from "Webshop" or "Bank", paperless will assign one
-    of these correspondents to ANY new document, if both are set to
-    automatic matching.
+- Changes to your documents are not immediately reflected by the
+  matching algorithm. The neural network needs to be _trained_ on your
+  documents after changes. Paperless periodically (default: once each
+  hour) checks for changes and does this automatically for you.
+- The Auto matching algorithm only takes documents into account which
+  are NOT placed in your inbox (i.e. have any inbox tags assigned to
+  them). This ensures that the neural network only learns from
+  documents which you have correctly tagged before.
+- The matching algorithm can only work if there is a correlation
+  between the tag, correspondent, document type, or storage path and
+  the document itself. Your bank statements usually contain your bank
+  account number and the name of the bank, so this works reasonably
+  well, However, tags such as "TODO" cannot be automatically
+  assigned.
+- The matching algorithm needs a reasonable number of documents to
+  identify when to assign tags, correspondents, storage paths, and
+  types. If one out of a thousand documents has the correspondent
+  "Very obscure web shop I bought something five years ago", it will
+  probably not assign this correspondent automatically if you buy
+  something from them again. The more documents, the better.
+- Paperless also needs a reasonable amount of negative examples to
+  decide when not to assign a certain tag, correspondent, document
+  type, or storage path. This will usually be the case as you start
+  filling up paperless with documents. Example: If all your documents
+  are either from "Webshop" or "Bank", paperless will assign one
+  of these correspondents to ANY new document, if both are set to
+  automatic matching.
 
 ## Hooking into the consumption process {#consume-hooks}
 
@@ -243,12 +243,12 @@ webserver:
 
 Troubleshooting:
 
--   Monitor the Docker Compose log
-    `cd ~/paperless-ngx; docker compose logs -f`
--   Check your script's permission e.g. in case of permission error
-    `sudo chmod 755 post-consumption-example.sh`
--   Pipe your scripts's output to a log file e.g.
-    `echo "${DOCUMENT_ID}" | tee --append /usr/src/paperless/scripts/post-consumption-example.log`
+- Monitor the Docker Compose log
+  `cd ~/paperless-ngx; docker compose logs -f`
+- Check your script's permission e.g. in case of permission error
+  `sudo chmod 755 post-consumption-example.sh`
+- Pipe your scripts's output to a log file e.g.
+  `echo "${DOCUMENT_ID}" | tee --append /usr/src/paperless/scripts/post-consumption-example.log`
 
 ## File name handling {#file-name-handling}
 
@@ -307,35 +307,35 @@ will create a directory structure as follows:
 
 Paperless provides the following variables for use within filenames:
 
--   `{{ asn }}`: The archive serial number of the document, or "none".
--   `{{ correspondent }}`: The name of the correspondent, or "none".
--   `{{ document_type }}`: The name of the document type, or "none".
--   `{{ tag_list }}`: A comma separated list of all tags assigned to the
-    document.
--   `{{ title }}`: The title of the document.
--   `{{ created }}`: The full date (ISO 8601 format, e.g. `2024-03-14`) the document was created.
--   `{{ created_year }}`: Year created only, formatted as the year with
-    century.
--   `{{ created_year_short }}`: Year created only, formatted as the year
-    without century, zero padded.
--   `{{ created_month }}`: Month created only (number 01-12).
--   `{{ created_month_name }}`: Month created name, as per locale
--   `{{ created_month_name_short }}`: Month created abbreviated name, as per
-    locale
--   `{{ created_day }}`: Day created only (number 01-31).
--   `{{ added }}`: The full date (ISO format) the document was added to
-    paperless.
--   `{{ added_year }}`: Year added only.
--   `{{ added_year_short }}`: Year added only, formatted as the year without
-    century, zero padded.
--   `{{ added_month }}`: Month added only (number 01-12).
--   `{{ added_month_name }}`: Month added name, as per locale
--   `{{ added_month_name_short }}`: Month added abbreviated name, as per
-    locale
--   `{{ added_day }}`: Day added only (number 01-31).
--   `{{ owner_username }}`: Username of document owner, if any, or "none"
--   `{{ original_name }}`: Document original filename, minus the extension, if any, or "none"
--   `{{ doc_pk }}`: The paperless identifier (primary key) for the document.
+- `{{ asn }}`: The archive serial number of the document, or "none".
+- `{{ correspondent }}`: The name of the correspondent, or "none".
+- `{{ document_type }}`: The name of the document type, or "none".
+- `{{ tag_list }}`: A comma separated list of all tags assigned to the
+  document.
+- `{{ title }}`: The title of the document.
+- `{{ created }}`: The full date (ISO 8601 format, e.g. `2024-03-14`) the document was created.
+- `{{ created_year }}`: Year created only, formatted as the year with
+  century.
+- `{{ created_year_short }}`: Year created only, formatted as the year
+  without century, zero padded.
+- `{{ created_month }}`: Month created only (number 01-12).
+- `{{ created_month_name }}`: Month created name, as per locale
+- `{{ created_month_name_short }}`: Month created abbreviated name, as per
+  locale
+- `{{ created_day }}`: Day created only (number 01-31).
+- `{{ added }}`: The full date (ISO format) the document was added to
+  paperless.
+- `{{ added_year }}`: Year added only.
+- `{{ added_year_short }}`: Year added only, formatted as the year without
+  century, zero padded.
+- `{{ added_month }}`: Month added only (number 01-12).
+- `{{ added_month_name }}`: Month added name, as per locale
+- `{{ added_month_name_short }}`: Month added abbreviated name, as per
+  locale
+- `{{ added_day }}`: Day added only (number 01-31).
+- `{{ owner_username }}`: Username of document owner, if any, or "none"
+- `{{ original_name }}`: Document original filename, minus the extension, if any, or "none"
+- `{{ doc_pk }}`: The paperless identifier (primary key) for the document.
 
 !!! warning
 
@@ -388,10 +388,10 @@ before empty placeholders are removed as well, empty directories are omitted.
 When a single storage layout is not sufficient for your use case, storage paths allow for more complex
 structure to set precisely where each document is stored in the file system.
 
--   Each storage path is a [`PAPERLESS_FILENAME_FORMAT`](configuration.md#PAPERLESS_FILENAME_FORMAT) and
-    follows the rules described above
--   Each document is assigned a storage path using the matching algorithms described above, but can be
-    overwritten at any time
+- Each storage path is a [`PAPERLESS_FILENAME_FORMAT`](configuration.md#PAPERLESS_FILENAME_FORMAT) and
+  follows the rules described above
+- Each document is assigned a storage path using the matching algorithms described above, but can be
+  overwritten at any time
 
 For example, you could define the following two storage paths:
 
@@ -457,13 +457,13 @@ The `get_cf_value` filter retrieves a value from custom field data with optional
 
 ###### Parameters
 
--   `custom_fields`: This _must_ be the provided custom field data
--   `name` (str): Name of the custom field to retrieve
--   `default` (str, optional): Default value to return if field is not found or has no value
+- `custom_fields`: This _must_ be the provided custom field data
+- `name` (str): Name of the custom field to retrieve
+- `default` (str, optional): Default value to return if field is not found or has no value
 
 ###### Returns
 
--   `str | None`: The field value, default value, or `None` if neither exists
+- `str | None`: The field value, default value, or `None` if neither exists
 
 ###### Examples
 
@@ -487,12 +487,12 @@ The `datetime` filter formats a datetime string or datetime object using Python'
 
 ###### Parameters
 
--   `value` (str | datetime): Date/time value to format (strings will be parsed automatically)
--   `format` (str): Python strftime format string
+- `value` (str | datetime): Date/time value to format (strings will be parsed automatically)
+- `format` (str): Python strftime format string
 
 ###### Returns
 
--   `str`: Formatted datetime string
+- `str`: Formatted datetime string
 
 ###### Examples
 
@@ -525,13 +525,13 @@ An ISO string can also be provided to control the output format.
 
 ###### Parameters
 
--   `value` (date | datetime | str): Date, datetime object or ISO string to format (datetime should be timezone-aware)
--   `format` (str): Format type - either a Babel preset ('short', 'medium', 'long', 'full') or custom pattern
--   `locale` (str): Locale code for localization (e.g., 'en_US', 'fr_FR', 'de_DE')
+- `value` (date | datetime | str): Date, datetime object or ISO string to format (datetime should be timezone-aware)
+- `format` (str): Format type - either a Babel preset ('short', 'medium', 'long', 'full') or custom pattern
+- `locale` (str): Locale code for localization (e.g., 'en_US', 'fr_FR', 'de_DE')
 
 ###### Returns
 
--   `str`: Localized, formatted date string
+- `str`: Localized, formatted date string
 
 ###### Examples
 
@@ -565,15 +565,15 @@ See the [supported format codes](https://unicode.org/reports/tr35/tr35-dates.htm
 
 ### Format Presets
 
--   **short**: Abbreviated format (e.g., "1/15/24")
--   **medium**: Medium-length format (e.g., "Jan 15, 2024")
--   **long**: Long format with full month name (e.g., "January 15, 2024")
--   **full**: Full format including day of week (e.g., "Monday, January 15, 2024")
+- **short**: Abbreviated format (e.g., "1/15/24")
+- **medium**: Medium-length format (e.g., "Jan 15, 2024")
+- **long**: Long format with full month name (e.g., "January 15, 2024")
+- **full**: Full format including day of week (e.g., "Monday, January 15, 2024")
 
 #### Additional Variables
 
--   `{{ tag_name_list }}`: A list of tag names applied to the document, ordered by the tag name. Note this is a list, not a single string
--   `{{ custom_fields }}`: A mapping of custom field names to their type and value. A user can access the mapping by field name or check if a field is applied by checking its existence in the variable.
+- `{{ tag_name_list }}`: A list of tag names applied to the document, ordered by the tag name. Note this is a list, not a single string
+- `{{ custom_fields }}`: A mapping of custom field names to their type and value. A user can access the mapping by field name or check if a field is applied by checking its existence in the variable.
 
 !!! tip
 
@@ -675,15 +675,15 @@ installation, you can use volumes to accomplish this:
 
 ```yaml
 services:
+  # ...
+  webserver:
+    environment:
+      - PAPERLESS_ENABLE_FLOWER
+    ports:
+      - 5555:5555 # (2)!
     # ...
-    webserver:
-        environment:
-            - PAPERLESS_ENABLE_FLOWER
-        ports:
-            - 5555:5555 # (2)!
-        # ...
-        volumes:
-            - /path/to/my/flowerconfig.py:/usr/src/paperless/src/paperless/flowerconfig.py:ro # (1)!
+    volumes:
+      - /path/to/my/flowerconfig.py:/usr/src/paperless/src/paperless/flowerconfig.py:ro # (1)!
 ```
 
 1. Note the `:ro` tag means the file will be mounted as read only.
@@ -714,11 +714,11 @@ For example, using Docker Compose:
 
 ```yaml
 services:
+  # ...
+  webserver:
     # ...
-    webserver:
-        # ...
-        volumes:
-            - /path/to/my/scripts:/custom-cont-init.d:ro # (1)!
+    volumes:
+      - /path/to/my/scripts:/custom-cont-init.d:ro # (1)!
 ```
 
 1. Note the `:ro` tag means the folder will be mounted as read only. This is for extra security against changes
@@ -771,16 +771,16 @@ Paperless is able to utilize barcodes for automatically performing some tasks.
 
 At this time, the library utilized for detection of barcodes supports the following types:
 
--   AN-13/UPC-A
--   UPC-E
--   EAN-8
--   Code 128
--   Code 93
--   Code 39
--   Codabar
--   Interleaved 2 of 5
--   QR Code
--   SQ Code
+- AN-13/UPC-A
+- UPC-E
+- EAN-8
+- Code 128
+- Code 93
+- Code 39
+- Codabar
+- Interleaved 2 of 5
+- QR Code
+- SQ Code
 
 For usage in Paperless, the type of barcode does not matter, only the contents of it.
 
@@ -793,8 +793,8 @@ below.
 If document splitting is enabled, Paperless splits _after_ a separator barcode by default.
 This means:
 
--   any page containing the configured separator barcode starts a new document, starting with the **next** page
--   pages containing the separator barcode are discarded
+- any page containing the configured separator barcode starts a new document, starting with the **next** page
+- pages containing the separator barcode are discarded
 
 This is intended for dedicated separator sheets such as PATCH-T pages.
 
@@ -831,10 +831,10 @@ to `true`.
 When enabled, documents will be split at pages containing tag barcodes, similar to how
 ASN barcodes work. Key features:
 
--   The page with the tag barcode is **retained** in the resulting document
--   **Each split document extracts its own tags** - only tags on pages within that document are assigned
--   Multiple tag barcodes can trigger multiple splits in the same document
--   Works seamlessly with ASN barcodes - each split document gets its own ASN and tags
+- The page with the tag barcode is **retained** in the resulting document
+- **Each split document extracts its own tags** - only tags on pages within that document are assigned
+- Multiple tag barcodes can trigger multiple splits in the same document
+- Works seamlessly with ASN barcodes - each split document gets its own ASN and tags
 
 This is useful for batch scanning where you place tag barcode pages between different
 documents to both separate and categorize them in a single operation.
@@ -996,9 +996,9 @@ If using docker, you'll need to add the following volume mounts to your `docker-
 
 ```yaml
 webserver:
-    volumes:
-        - /home/user/.gnupg/pubring.gpg:/usr/src/paperless/.gnupg/pubring.gpg
-        - <path to gpg-agent socket>:/usr/src/paperless/.gnupg/S.gpg-agent
+  volumes:
+    - /home/user/.gnupg/pubring.gpg:/usr/src/paperless/.gnupg/pubring.gpg
+    - <path to gpg-agent socket>:/usr/src/paperless/.gnupg/S.gpg-agent
 ```
 
 For a 'bare-metal' installation no further configuration is necessary. If you
@@ -1006,9 +1006,9 @@ want to use a separate `GNUPG_HOME`, you can do so by configuring the [PAPERLESS
 
 ### Troubleshooting
 
--   Make sure, that `gpg-agent` is running on your host machine
--   Make sure, that encryption and decryption works from inside the container using the `gpg` commands from above.
--   Check that all files in `/usr/src/paperless/.gnupg` have correct permissions
+- Make sure, that `gpg-agent` is running on your host machine
+- Make sure, that encryption and decryption works from inside the container using the `gpg` commands from above.
+- Check that all files in `/usr/src/paperless/.gnupg` have correct permissions
 
 ```shell
 paperless@9da1865df327:~/.gnupg$ ls -al

docs/api.md

@@ -66,10 +66,10 @@ Full text searching is available on the `/api/documents/` endpoint. Two
 specific query parameters cause the API to return full text search
 results:
 
--   `/api/documents/?query=your%20search%20query`: Search for a document
-    using a full text query. For details on the syntax, see [Basic Usage - Searching](usage.md#basic-usage_searching).
--   `/api/documents/?more_like_id=1234`: Search for documents similar to
-    the document with id 1234.
+- `/api/documents/?query=your%20search%20query`: Search for a document
+  using a full text query. For details on the syntax, see [Basic Usage - Searching](usage.md#basic-usage_searching).
+- `/api/documents/?more_like_id=1234`: Search for documents similar to
+  the document with id 1234.
 
 Pagination works exactly the same as it does for normal requests on this
 endpoint.
@@ -106,12 +106,12 @@ attribute with various information about the search results:
 }
 ```
 
--   `score` is an indication how well this document matches the query
-    relative to the other search results.
--   `highlights` is an excerpt from the document content and highlights
-    the search terms with `<span>` tags as shown above.
--   `rank` is the index of the search results. The first result will
-    have rank 0.
+- `score` is an indication how well this document matches the query
+  relative to the other search results.
+- `highlights` is an excerpt from the document content and highlights
+  the search terms with `<span>` tags as shown above.
+- `rank` is the index of the search results. The first result will
+  have rank 0.
 
 ### Filtering by custom fields
 
@@ -122,33 +122,33 @@ use cases:
 1. Documents with a custom field "due" (date) between Aug 1, 2024 and
    Sept 1, 2024 (inclusive):
 
-    `?custom_field_query=["due", "range", ["2024-08-01", "2024-09-01"]]`
+   `?custom_field_query=["due", "range", ["2024-08-01", "2024-09-01"]]`
 
 2. Documents with a custom field "customer" (text) that equals "bob"
    (case sensitive):
 
-    `?custom_field_query=["customer", "exact", "bob"]`
+   `?custom_field_query=["customer", "exact", "bob"]`
 
 3. Documents with a custom field "answered" (boolean) set to `true`:
 
-    `?custom_field_query=["answered", "exact", true]`
+   `?custom_field_query=["answered", "exact", true]`
 
 4. Documents with a custom field "favorite animal" (select) set to either
    "cat" or "dog":
 
-    `?custom_field_query=["favorite animal", "in", ["cat", "dog"]]`
+   `?custom_field_query=["favorite animal", "in", ["cat", "dog"]]`
 
 5. Documents with a custom field "address" (text) that is empty:
 
-    `?custom_field_query=["OR", [["address", "isnull", true], ["address", "exact", ""]]]`
+   `?custom_field_query=["OR", [["address", "isnull", true], ["address", "exact", ""]]]`
 
 6. Documents that don't have a field called "foo":
 
-    `?custom_field_query=["foo", "exists", false]`
+   `?custom_field_query=["foo", "exists", false]`
 
 7. Documents that have document links "references" to both document 3 and 7:
 
-    `?custom_field_query=["references", "contains", [3, 7]]`
+   `?custom_field_query=["references", "contains", [3, 7]]`
 
 All field types support basic operations including `exact`, `in`, `isnull`,
 and `exists`. String, URL, and monetary fields support case-insensitive
@@ -164,8 +164,8 @@ Get auto completions for a partial search term.
 
 Query parameters:
 
--   `term`: The incomplete term.
--   `limit`: Amount of results. Defaults to 10.
+- `term`: The incomplete term.
+- `limit`: Amount of results. Defaults to 10.
 
 Results returned by the endpoint are ordered by importance of the term
 in the document index. The first result is the term that has the highest
@@ -189,19 +189,19 @@ from there.
 
 The endpoint supports the following optional form fields:
 
--   `title`: Specify a title that the consumer should use for the
-    document.
--   `created`: Specify a DateTime where the document was created (e.g.
-    "2016-04-19" or "2016-04-19 06:15:00+02:00").
--   `correspondent`: Specify the ID of a correspondent that the consumer
-    should use for the document.
--   `document_type`: Similar to correspondent.
--   `storage_path`: Similar to correspondent.
--   `tags`: Similar to correspondent. Specify this multiple times to
-    have multiple tags added to the document.
--   `archive_serial_number`: An optional archive serial number to set.
--   `custom_fields`: Either an array of custom field ids to assign (with an empty
-    value) to the document or an object mapping field id -> value.
+- `title`: Specify a title that the consumer should use for the
+  document.
+- `created`: Specify a DateTime where the document was created (e.g.
+  "2016-04-19" or "2016-04-19 06:15:00+02:00").
+- `correspondent`: Specify the ID of a correspondent that the consumer
+  should use for the document.
+- `document_type`: Similar to correspondent.
+- `storage_path`: Similar to correspondent.
+- `tags`: Similar to correspondent. Specify this multiple times to
+  have multiple tags added to the document.
+- `archive_serial_number`: An optional archive serial number to set.
+- `custom_fields`: Either an array of custom field ids to assign (with an empty
+  value) to the document or an object mapping field id -> value.
 
 The endpoint will immediately return HTTP 200 if the document consumption
 process was started successfully, with the UUID of the consumption task
@@ -215,16 +215,16 @@ consumption including the ID of a created document if consumption succeeded.
 
 Document versions are file-level versions linked to one root document.
 
--   Root document metadata (title, tags, correspondent, document type, storage path, custom fields, permissions) remains shared.
--   Version-specific file data (file, mime type, checksums, archive info, extracted text content) belongs to the selected/latest version.
+- Root document metadata (title, tags, correspondent, document type, storage path, custom fields, permissions) remains shared.
+- Version-specific file data (file, mime type, checksums, archive info, extracted text content) belongs to the selected/latest version.
 
 Version-aware endpoints:
 
--   `GET /api/documents/{id}/`: returns root document data; `content` resolves to latest version content by default. Use `?version={version_id}` to resolve content for a specific version.
--   `PATCH /api/documents/{id}/`: content updates target the selected version (`?version={version_id}`) or latest version by default; non-content metadata updates target the root document.
--   `GET /api/documents/{id}/download/`, `GET /api/documents/{id}/preview/`, `GET /api/documents/{id}/thumb/`, `GET /api/documents/{id}/metadata/`: accept `?version={version_id}`.
--   `POST /api/documents/{id}/update_version/`: uploads a new version using multipart form field `document` and optional `version_label`.
--   `DELETE /api/documents/{root_id}/versions/{version_id}/`: deletes a non-root version.
+- `GET /api/documents/{id}/`: returns root document data; `content` resolves to latest version content by default. Use `?version={version_id}` to resolve content for a specific version.
+- `PATCH /api/documents/{id}/`: content updates target the selected version (`?version={version_id}`) or latest version by default; non-content metadata updates target the root document.
+- `GET /api/documents/{id}/download/`, `GET /api/documents/{id}/preview/`, `GET /api/documents/{id}/thumb/`, `GET /api/documents/{id}/metadata/`: accept `?version={version_id}`.
+- `POST /api/documents/{id}/update_version/`: uploads a new version using multipart form field `document` and optional `version_label`.
+- `DELETE /api/documents/{root_id}/versions/{version_id}/`: deletes a non-root version.
 
 ## Permissions
 
@@ -282,74 +282,38 @@ a json payload of the format:
 
 The following methods are supported:
 
--   `set_correspondent`
-    -   Requires `parameters`: `{ "correspondent": CORRESPONDENT_ID }`
--   `set_document_type`
-    -   Requires `parameters`: `{ "document_type": DOCUMENT_TYPE_ID }`
--   `set_storage_path`
-    -   Requires `parameters`: `{ "storage_path": STORAGE_PATH_ID }`
--   `add_tag`
-    -   Requires `parameters`: `{ "tag": TAG_ID }`
--   `remove_tag`
-    -   Requires `parameters`: `{ "tag": TAG_ID }`
--   `modify_tags`
-    -   Requires `parameters`: `{ "add_tags": [LIST_OF_TAG_IDS] }` and `{ "remove_tags": [LIST_OF_TAG_IDS] }`
--   `delete`
-    -   No `parameters` required
--   `reprocess`
-    -   No `parameters` required
--   `set_permissions`
-    -   Requires `parameters`:
-        -   `"set_permissions": PERMISSIONS_OBJ` (see format [above](#permissions)) and / or
-        -   `"owner": OWNER_ID or null`
-        -   `"merge": true or false` (defaults to false)
-    -   The `merge` flag determines if the supplied permissions will overwrite all existing permissions (including
-        removing them) or be merged with existing permissions.
--   `edit_pdf`
-    -   Requires `parameters`:
-        -   `"doc_ids": [DOCUMENT_ID]` A list of a single document ID to edit.
-        -   `"operations": [OPERATION, ...]` A list of operations to perform on the documents. Each operation is a dictionary
-            with the following keys:
-            -   `"page": PAGE_NUMBER` The page number to edit (1-based).
-            -   `"rotate": DEGREES` Optional rotation in degrees (90, 180, 270).
-            -   `"doc": OUTPUT_DOCUMENT_INDEX` Optional index of the output document for split operations.
-    -   Optional `parameters`:
-        -   `"delete_original": true` to delete the original documents after editing.
-        -   `"update_document": true` to add the edited PDF as a new version of the root document.
-        -   `"include_metadata": true` to copy metadata from the original document to the edited document.
--   `remove_password`
-    -   Requires `parameters`:
-        -   `"password": "PASSWORD_STRING"` The password to remove from the PDF documents.
-    -   Optional `parameters`:
-        -   `"update_document": true` to add the password-less PDF as a new version of the root document.
-        -   `"delete_original": true` to delete the original document after editing.
-        -   `"include_metadata": true` to copy metadata from the original document to the new password-less document.
--   `merge`
-    -   No additional `parameters` required.
-    -   The ordering of the merged document is determined by the list of IDs.
-    -   Optional `parameters`:
-        -   `"metadata_document_id": DOC_ID` apply metadata (tags, correspondent, etc.) from this document to the merged document.
-        -   `"delete_originals": true` to delete the original documents. This requires the calling user being the owner of
-            all documents that are merged.
--   `split`
-    -   Requires `parameters`:
-        -   `"pages": [..]` The list should be a list of pages and/or a ranges, separated by commas e.g. `"[1,2-3,4,5-7]"`
-    -   Optional `parameters`:
-        -   `"delete_originals": true` to delete the original document after consumption. This requires the calling user being the owner of
-            the document.
-    -   The split operation only accepts a single document.
--   `rotate`
-    -   Requires `parameters`:
-        -   `"degrees": DEGREES`. Must be an integer i.e. 90, 180, 270
--   `delete_pages`
-    -   Requires `parameters`:
-        -   `"pages": [..]` The list should be a list of integers e.g. `"[2,3,4]"`
-    -   The delete_pages operation only accepts a single document.
--   `modify_custom_fields`
-    -   Requires `parameters`:
-        -   `"add_custom_fields": { CUSTOM_FIELD_ID: VALUE }`: JSON object consisting of custom field id:value pairs to add to the document, can also be a list of custom field IDs
-            to add with empty values.
-        -   `"remove_custom_fields": [CUSTOM_FIELD_ID]`: custom field ids to remove from the document.
+- `set_correspondent`
+  - Requires `parameters`: `{ "correspondent": CORRESPONDENT_ID }`
+- `set_document_type`
+  - Requires `parameters`: `{ "document_type": DOCUMENT_TYPE_ID }`
+- `set_storage_path`
+  - Requires `parameters`: `{ "storage_path": STORAGE_PATH_ID }`
+- `add_tag`
+  - Requires `parameters`: `{ "tag": TAG_ID }`
+- `remove_tag`
+  - Requires `parameters`: `{ "tag": TAG_ID }`
+- `modify_tags`
+  - Requires `parameters`: `{ "add_tags": [LIST_OF_TAG_IDS] }` and `{ "remove_tags": [LIST_OF_TAG_IDS] }`
+- `delete`
+  - No `parameters` required
+- `reprocess`
+  - No `parameters` required
+- `set_permissions`
+  - Requires `parameters`:
+    - `"set_permissions": PERMISSIONS_OBJ` (see format [above](#permissions)) and / or
+    - `"owner": OWNER_ID or null`
+    - `"merge": true or false` (defaults to false)
+  - The `merge` flag determines if the supplied permissions will overwrite all existing permissions (including
+    removing them) or be merged with existing permissions.
+- `modify_custom_fields`
+  - Requires `parameters`:
+    - `"add_custom_fields": { CUSTOM_FIELD_ID: VALUE }`: JSON object consisting of custom field id:value pairs to add to the document, can also be a list of custom field IDs
+      to add with empty values.
+    - `"remove_custom_fields": [CUSTOM_FIELD_ID]`: custom field ids to remove from the document.
+
+#### Document-editing operations
+
+Beginning with version 10+, the API supports individual endpoints for document-editing operations (`merge`, `rotate`, `edit_pdf`, etc), thus their documentation can be found in the API spec / viewer. Legacy document-editing methods via `/api/documents/bulk_edit/` are still supported for compatibility, are deprecated and clients should migrate to the individual endpoints before they are removed in a future version.
 
 ### Objects
 
@@ -371,16 +335,16 @@ operations, using the endpoint: `/api/bulk_edit_objects/`, which requires a json
 
 The REST API is versioned.
 
--   Versioning ensures that changes to the API don't break older
-    clients.
--   Clients specify the specific version of the API they wish to use
-    with every request and Paperless will handle the request using the
-    specified API version.
--   Even if the underlying data model changes, supported older API
-    versions continue to serve compatible data.
--   If no version is specified, Paperless serves the configured default
-    API version (currently `10`).
--   Supported API versions are currently `9` and `10`.
+- Versioning ensures that changes to the API don't break older
+  clients.
+- Clients specify the specific version of the API they wish to use
+  with every request and Paperless will handle the request using the
+  specified API version.
+- Even if the underlying data model changes, supported older API
+  versions continue to serve compatible data.
+- If no version is specified, Paperless serves the configured default
+  API version (currently `10`).
+- Supported API versions are currently `9` and `10`.
 
 API versions are specified by submitting an additional HTTP `Accept`
 header with every request:
@@ -420,51 +384,56 @@ Initial API version.
 
 #### Version 2
 
--   Added field `Tag.color`. This read/write string field contains a hex
-    color such as `#a6cee3`.
--   Added read-only field `Tag.text_color`. This field contains the text
-    color to use for a specific tag, which is either black or white
-    depending on the brightness of `Tag.color`.
--   Removed field `Tag.colour`.
+- Added field `Tag.color`. This read/write string field contains a hex
+  color such as `#a6cee3`.
+- Added read-only field `Tag.text_color`. This field contains the text
+  color to use for a specific tag, which is either black or white
+  depending on the brightness of `Tag.color`.
+- Removed field `Tag.colour`.
 
 #### Version 3
 
--   Permissions endpoints have been added.
--   The format of the `/api/ui_settings/` has changed.
+- Permissions endpoints have been added.
+- The format of the `/api/ui_settings/` has changed.
 
 #### Version 4
 
--   Consumption templates were refactored to workflows and API endpoints
-    changed as such.
+- Consumption templates were refactored to workflows and API endpoints
+  changed as such.
 
 #### Version 5
 
--   Added bulk deletion methods for documents and objects.
+- Added bulk deletion methods for documents and objects.
 
 #### Version 6
 
--   Moved acknowledge tasks endpoint to be under `/api/tasks/acknowledge/`.
+- Moved acknowledge tasks endpoint to be under `/api/tasks/acknowledge/`.
 
 #### Version 7
 
--   The format of select type custom fields has changed to return the options
-    as an array of objects with `id` and `label` fields as opposed to a simple
-    list of strings. When creating or updating a custom field value of a
-    document for a select type custom field, the value should be the `id` of
-    the option whereas previously was the index of the option.
+- The format of select type custom fields has changed to return the options
+  as an array of objects with `id` and `label` fields as opposed to a simple
+  list of strings. When creating or updating a custom field value of a
+  document for a select type custom field, the value should be the `id` of
+  the option whereas previously was the index of the option.
 
 #### Version 8
 
--   The user field of document notes now returns a simplified user object
-    rather than just the user ID.
+- The user field of document notes now returns a simplified user object
+  rather than just the user ID.
 
 #### Version 9
 
--   The document `created` field is now a date, not a datetime. The
-    `created_date` field is considered deprecated and will be removed in a
-    future version.
+- The document `created` field is now a date, not a datetime. The
+  `created_date` field is considered deprecated and will be removed in a
+  future version.
 
 #### Version 10
 
--   The `show_on_dashboard` and `show_in_sidebar` fields of saved views have been
-    removed. Relevant settings are now stored in the UISettings model.
+- The `show_on_dashboard` and `show_in_sidebar` fields of saved views have been
+  removed. Relevant settings are now stored in the UISettings model. Compatibility is maintained
+  for versions < 10 until support for API v9 is dropped.
+- Document-editing operations such as `merge`, `rotate`, and `edit_pdf` have been
+  moved from the bulk edit endpoint to their own individual endpoints. Using these methods via
+  the bulk edit endpoint is still supported for compatibility with versions < 10 until support
+  for API v9 is dropped.

docs/configuration.md

@@ -8,17 +8,17 @@ common [OCR](#ocr) related settings and some frontend settings. If set, these wi
 preference over the settings via environment variables. If not set, the environment setting
 or applicable default will be utilized instead.
 
--   If you run paperless on docker, `paperless.conf` is not used.
-    Rather, configure paperless by copying necessary options to
-    `docker-compose.env`.
+- If you run paperless on docker, `paperless.conf` is not used.
+  Rather, configure paperless by copying necessary options to
+  `docker-compose.env`.
 
--   If you are running paperless on anything else, paperless will search
-    for the configuration file in these locations and use the first one
-    it finds:
-    -   The environment variable `PAPERLESS_CONFIGURATION_PATH`
-    -   `/path/to/paperless/paperless.conf`
-    -   `/etc/paperless.conf`
-    -   `/usr/local/etc/paperless.conf`
+- If you are running paperless on anything else, paperless will search
+  for the configuration file in these locations and use the first one
+  it finds:
+  - The environment variable `PAPERLESS_CONFIGURATION_PATH`
+  - `/path/to/paperless/paperless.conf`
+  - `/etc/paperless.conf`
+  - `/usr/local/etc/paperless.conf`
 
 ## Required services
 
@@ -1947,6 +1947,12 @@ current backend. If not supplied, defaults to "gpt-3.5-turbo" for OpenAI and "ll
 
     Defaults to None.
 
+#### [`PAPERLESS_AI_LLM_ALLOW_INTERNAL_ENDPOINTS=<bool>`](#PAPERLESS_AI_LLM_ALLOW_INTERNAL_ENDPOINTS) {#PAPERLESS_AI_LLM_ALLOW_INTERNAL_ENDPOINTS}
+
+: If set to false, Paperless blocks AI endpoint URLs that resolve to non-public addresses (e.g., localhost, etc).
+
+    Defaults to true, which allows internal endpoints.
+
 #### [`PAPERLESS_AI_LLM_INDEX_TASK_CRON=<cron expression>`](#PAPERLESS_AI_LLM_INDEX_TASK_CRON) {#PAPERLESS_AI_LLM_INDEX_TASK_CRON}
 
 : Configures the schedule to update the AI embeddings of text content and metadata for all documents. Only performed if

docs/development.md

@@ -6,23 +6,23 @@ on Paperless-ngx.
 Check out the source from GitHub. The repository is organized in the
 following way:
 
--   `main` always represents the latest release and will only see
-    changes when a new release is made.
--   `dev` contains the code that will be in the next release.
--   `feature-X` contains bigger changes that will be in some release, but
-    not necessarily the next one.
+- `main` always represents the latest release and will only see
+  changes when a new release is made.
+- `dev` contains the code that will be in the next release.
+- `feature-X` contains bigger changes that will be in some release, but
+  not necessarily the next one.
 
 When making functional changes to Paperless-ngx, _always_ make your changes
 on the `dev` branch.
 
 Apart from that, the folder structure is as follows:
 
--   `docs/` - Documentation.
--   `src-ui/` - Code of the front end.
--   `src/` - Code of the back end.
--   `scripts/` - Various scripts that help with different parts of
-    development.
--   `docker/` - Files required to build the docker image.
+- `docs/` - Documentation.
+- `src-ui/` - Code of the front end.
+- `src/` - Code of the back end.
+- `scripts/` - Various scripts that help with different parts of
+  development.
+- `docker/` - Files required to build the docker image.
 
 ## Contributing to Paperless-ngx
 
@@ -94,18 +94,17 @@ first-time setup.
     ```
 
 7.  You can now either ...
+    - install Redis or
 
-    -   install Redis or
+    - use the included `scripts/start_services.sh` to use Docker to fire
+      up a Redis instance (and some other services such as Tika,
+      Gotenberg and a database server) or
 
-    -   use the included `scripts/start_services.sh` to use Docker to fire
-        up a Redis instance (and some other services such as Tika,
-        Gotenberg and a database server) or
+    - spin up a bare Redis container
 
-    -   spin up a bare Redis container
-
-        ```bash
-        docker run -d -p 6379:6379 --restart unless-stopped redis:latest
-        ```
+      ```bash
+      docker run -d -p 6379:6379 --restart unless-stopped redis:latest
+      ```
 
 8.  Continue with either back-end or front-end development – or both :-).
 
@@ -118,9 +117,9 @@ work well for development, but you can use whatever you want.
 Configure the IDE to use the `src/`-folder as the base source folder.
 Configure the following launch configurations in your IDE:
 
--   `uv run manage.py runserver`
--   `uv run manage.py document_consumer`
--   `uv run celery --app paperless worker -l DEBUG` (or any other log level)
+- `uv run manage.py runserver`
+- `uv run manage.py document_consumer`
+- `uv run celery --app paperless worker -l DEBUG` (or any other log level)
 
 To start them all:
 
@@ -146,11 +145,11 @@ pnpm ng build --configuration production
 
 ### Testing
 
--   Run `pytest` in the `src/` directory to execute all tests. This also
-    generates a HTML coverage report. When running tests, `paperless.conf`
-    is loaded as well. However, the tests rely on the default
-    configuration. This is not ideal. But for now, make sure no settings
-    except for DEBUG are overridden when testing.
+- Run `pytest` in the `src/` directory to execute all tests. This also
+  generates a HTML coverage report. When running tests, `paperless.conf`
+  is loaded as well. However, the tests rely on the default
+  configuration. This is not ideal. But for now, make sure no settings
+  except for DEBUG are overridden when testing.
 
 !!! note
 
@@ -254,14 +253,14 @@ these parts have to be translated separately.
 
 ### Front end localization
 
--   The AngularJS front end does localization according to the [Angular
-    documentation](https://angular.io/guide/i18n).
--   The source language of the project is "en_US".
--   The source strings end up in the file `src-ui/messages.xlf`.
--   The translated strings need to be placed in the
-    `src-ui/src/locale/` folder.
--   In order to extract added or changed strings from the source files,
-    call `ng extract-i18n`.
+- The AngularJS front end does localization according to the [Angular
+  documentation](https://angular.io/guide/i18n).
+- The source language of the project is "en_US".
+- The source strings end up in the file `src-ui/messages.xlf`.
+- The translated strings need to be placed in the
+  `src-ui/src/locale/` folder.
+- In order to extract added or changed strings from the source files,
+  call `ng extract-i18n`.
 
 Adding new languages requires adding the translated files in the
 `src-ui/src/locale/` folder and adjusting a couple files.
@@ -307,18 +306,18 @@ A majority of the strings that appear in the back end appear only when
 the admin is used. However, some of these are still shown on the front
 end (such as error messages).
 
--   The django application does localization according to the [Django
-    documentation](https://docs.djangoproject.com/en/3.1/topics/i18n/translation/).
--   The source language of the project is "en_US".
--   Localization files end up in the folder `src/locale/`.
--   In order to extract strings from the application, call
-    `uv run manage.py makemessages -l en_US`. This is important after
-    making changes to translatable strings.
--   The message files need to be compiled for them to show up in the
-    application. Call `uv run manage.py compilemessages` to do this.
-    The generated files don't get committed into git, since these are
-    derived artifacts. The build pipeline takes care of executing this
-    command.
+- The django application does localization according to the [Django
+  documentation](https://docs.djangoproject.com/en/3.1/topics/i18n/translation/).
+- The source language of the project is "en_US".
+- Localization files end up in the folder `src/locale/`.
+- In order to extract strings from the application, call
+  `uv run manage.py makemessages -l en_US`. This is important after
+  making changes to translatable strings.
+- The message files need to be compiled for them to show up in the
+  application. Call `uv run manage.py compilemessages` to do this.
+  The generated files don't get committed into git, since these are
+  derived artifacts. The build pipeline takes care of executing this
+  command.
 
 Adding new languages requires adding the translated files in the
 `src/locale/`-folder and adjusting the file
@@ -381,10 +380,10 @@ base code.
 Paperless-ngx uses parsers to add documents. A parser is
 responsible for:
 
--   Retrieving the content from the original
--   Creating a thumbnail
--   _optional:_ Retrieving a created date from the original
--   _optional:_ Creating an archived document from the original
+- Retrieving the content from the original
+- Creating a thumbnail
+- _optional:_ Retrieving a created date from the original
+- _optional:_ Creating an archived document from the original
 
 Custom parsers can be added to Paperless-ngx to support more file types. In
 order to do that, you need to write the parser itself and announce its
@@ -442,17 +441,17 @@ def myparser_consumer_declaration(sender, **kwargs):
     }
 ```
 
--   `parser` is a reference to a class that extends `DocumentParser`.
--   `weight` is used whenever two or more parsers are able to parse a
-    file: The parser with the higher weight wins. This can be used to
-    override the parsers provided by Paperless-ngx.
--   `mime_types` is a dictionary. The keys are the mime types your
-    parser supports and the value is the default file extension that
-    Paperless-ngx should use when storing files and serving them for
-    download. We could guess that from the file extensions, but some
-    mime types have many extensions associated with them and the Python
-    methods responsible for guessing the extension do not always return
-    the same value.
+- `parser` is a reference to a class that extends `DocumentParser`.
+- `weight` is used whenever two or more parsers are able to parse a
+  file: The parser with the higher weight wins. This can be used to
+  override the parsers provided by Paperless-ngx.
+- `mime_types` is a dictionary. The keys are the mime types your
+  parser supports and the value is the default file extension that
+  Paperless-ngx should use when storing files and serving them for
+  download. We could guess that from the file extensions, but some
+  mime types have many extensions associated with them and the Python
+  methods responsible for guessing the extension do not always return
+  the same value.
 
 ## Using Visual Studio Code devcontainer
 
@@ -471,9 +470,8 @@ To get started:
 2. VS Code will prompt you with "Reopen in container". Do so and wait for the environment to start.
 
 3. In case your host operating system is Windows:
-
-    - The Source Control view in Visual Studio Code might show: "The detected Git repository is potentially unsafe as the folder is owned by someone other than the current user." Use "Manage Unsafe Repositories" to fix this.
-    - Git might have detecteded modifications for all files, because Windows is using CRLF line endings. Run `git checkout .` in the containers terminal to fix this issue.
+   - The Source Control view in Visual Studio Code might show: "The detected Git repository is potentially unsafe as the folder is owned by someone other than the current user." Use "Manage Unsafe Repositories" to fix this.
+   - Git might have detecteded modifications for all files, because Windows is using CRLF line endings. Run `git checkout .` in the containers terminal to fix this issue.
 
 4. Initialize the project by running the task **Project Setup: Run all Init Tasks**. This
    will initialize the database tables and create a superuser. Then you can compile the front end
@@ -538,12 +536,12 @@ class MyDateParserPlugin(DateParserPluginBase):
 
 Your parser instance is initialized with a `DateParserConfig` object accessible via `self.config`. This provides:
 
--   `languages: list[str]` - List of language codes for date parsing
--   `timezone_str: str` - Timezone string for date localization
--   `ignore_dates: set[datetime.date]` - Dates that should be filtered out
--   `reference_time: datetime.datetime` - Current time for filtering future dates
--   `filename_date_order: str | None` - Date order preference for filenames (e.g., "DMY", "MDY")
--   `content_date_order: str` - Date order preference for content
+- `languages: list[str]` - List of language codes for date parsing
+- `timezone_str: str` - Timezone string for date localization
+- `ignore_dates: set[datetime.date]` - Dates that should be filtered out
+- `reference_time: datetime.datetime` - Current time for filtering future dates
+- `filename_date_order: str | None` - Date order preference for filenames (e.g., "DMY", "MDY")
+- `content_date_order: str` - Date order preference for content
 
 The base class provides two helper methods you can use:
 

docs/faq.md

@@ -44,28 +44,28 @@ system. On Linux, chances are high that this location is
 You can always drag those files out of that folder to use them
 elsewhere. Here are a couple notes about that.
 
--   Paperless-ngx never modifies your original documents. It keeps
-    checksums of all documents and uses a scheduled sanity checker to
-    check that they remain the same.
--   By default, paperless uses the internal ID of each document as its
-    filename. This might not be very convenient for export. However, you
-    can adjust the way files are stored in paperless by
-    [configuring the filename format](advanced_usage.md#file-name-handling).
--   [The exporter](administration.md#exporter) is
-    another easy way to get your files out of paperless with reasonable
-    file names.
+- Paperless-ngx never modifies your original documents. It keeps
+  checksums of all documents and uses a scheduled sanity checker to
+  check that they remain the same.
+- By default, paperless uses the internal ID of each document as its
+  filename. This might not be very convenient for export. However, you
+  can adjust the way files are stored in paperless by
+  [configuring the filename format](advanced_usage.md#file-name-handling).
+- [The exporter](administration.md#exporter) is
+  another easy way to get your files out of paperless with reasonable
+  file names.
 
 ## _What file types does paperless-ngx support?_
 
 **A:** Currently, the following files are supported:
 
--   PDF documents, PNG images, JPEG images, TIFF images, GIF images and
-    WebP images are processed with OCR and converted into PDF documents.
--   Plain text documents are supported as well and are added verbatim to
-    paperless.
--   With the optional Tika integration enabled (see [Tika configuration](https://docs.paperless-ngx.com/configuration#tika)),
-    Paperless also supports various Office documents (.docx, .doc, odt,
-    .ppt, .pptx, .odp, .xls, .xlsx, .ods).
+- PDF documents, PNG images, JPEG images, TIFF images, GIF images and
+  WebP images are processed with OCR and converted into PDF documents.
+- Plain text documents are supported as well and are added verbatim to
+  paperless.
+- With the optional Tika integration enabled (see [Tika configuration](https://docs.paperless-ngx.com/configuration#tika)),
+  Paperless also supports various Office documents (.docx, .doc, odt,
+  .ppt, .pptx, .odp, .xls, .xlsx, .ods).
 
 Paperless-ngx determines the type of a file by inspecting its content
 rather than its file extensions. However, files processed via the

docs/index.md

@@ -28,36 +28,36 @@ 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, unless you explicitly choose to do so.
--   Performs **OCR** on your documents, adding searchable and selectable text, even to documents scanned with only images.
-    -   Utilizes the open-source Tesseract engine to recognize more than 100 languages.
-    -   _New!_ Supports remote OCR with Azure AI (opt-in).
--   Documents are saved as PDF/A format which is designed for long term storage, alongside the unaltered originals.
--   Uses machine-learning to automatically add tags, correspondents and document types to your documents.
--   **New**: Paperless-ngx can now leverage AI (Large Language Models or LLMs) for document suggestions. This is an optional feature that can be enabled (and is disabled by default).
--   Supports PDF documents, images, plain text files, Office documents (Word, Excel, PowerPoint, and LibreOffice equivalents)[^1] and more.
--   Paperless stores your documents plain on disk. Filenames and folders are managed by paperless and their format can be configured freely with different configurations assigned to different documents.
--   **Beautiful, modern web application** that features:
-    -   Customizable dashboard with statistics.
-    -   Filtering by tags, correspondents, types, and more.
-    -   Bulk editing of tags, correspondents, types and more.
-    -   Drag-and-drop uploading of documents throughout the app.
-    -   Customizable views can be saved and displayed on the dashboard and / or sidebar.
-    -   Support for custom fields of various data types.
-    -   Shareable public links with optional expiration.
--   **Full text search** helps you find what you need:
-    -   Auto completion suggests relevant words from your documents.
-    -   Results are sorted by relevance to your search query.
-    -   Highlighting shows you which parts of the document matched the query.
-    -   Searching for similar documents ("More like this")
--   **Email processing**[^1]: import documents from your email accounts:
-    -   Configure multiple accounts and rules for each account.
-    -   After processing, paperless can perform actions on the messages such as marking as read, deleting and more.
--   A built-in robust **multi-user permissions** system that supports 'global' permissions as well as per document or object.
--   A powerful workflow system that gives you even more control.
--   **Optimized** for multi core systems: Paperless-ngx consumes multiple documents in parallel.
--   The integrated sanity checker makes sure that your document archive is in good health.
+- **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, unless you explicitly choose to do so.
+- Performs **OCR** on your documents, adding searchable and selectable text, even to documents scanned with only images.
+  - Utilizes the open-source Tesseract engine to recognize more than 100 languages.
+  - _New!_ Supports remote OCR with Azure AI (opt-in).
+- Documents are saved as PDF/A format which is designed for long term storage, alongside the unaltered originals.
+- Uses machine-learning to automatically add tags, correspondents and document types to your documents.
+- **New**: Paperless-ngx can now leverage AI (Large Language Models or LLMs) for document suggestions. This is an optional feature that can be enabled (and is disabled by default).
+- Supports PDF documents, images, plain text files, Office documents (Word, Excel, PowerPoint, and LibreOffice equivalents)[^1] and more.
+- Paperless stores your documents plain on disk. Filenames and folders are managed by paperless and their format can be configured freely with different configurations assigned to different documents.
+- **Beautiful, modern web application** that features:
+  - Customizable dashboard with statistics.
+  - Filtering by tags, correspondents, types, and more.
+  - Bulk editing of tags, correspondents, types and more.
+  - Drag-and-drop uploading of documents throughout the app.
+  - Customizable views can be saved and displayed on the dashboard and / or sidebar.
+  - Support for custom fields of various data types.
+  - Shareable public links with optional expiration.
+- **Full text search** helps you find what you need:
+  - Auto completion suggests relevant words from your documents.
+  - Results are sorted by relevance to your search query.
+  - Highlighting shows you which parts of the document matched the query.
+  - Searching for similar documents ("More like this")
+- **Email processing**[^1]: import documents from your email accounts:
+  - Configure multiple accounts and rules for each account.
+  - After processing, paperless can perform actions on the messages such as marking as read, deleting and more.
+- A built-in robust **multi-user permissions** system that supports 'global' permissions as well as per document or object.
+- A powerful workflow system that gives you even more control.
+- **Optimized** for multi core systems: Paperless-ngx consumes multiple documents in parallel.
+- The integrated sanity checker makes sure that your document archive is in good health.
 
 [^1]: Office document and email consumption support is optional and provided by Apache Tika (see [configuration](https://docs.paperless-ngx.com/configuration/#tika))
 

docs/migration-v3.md

@@ -42,12 +42,12 @@ The `CONSUMER_BARCODE_SCANNER` setting has been removed. zxing-cpp is now the on
 
 ### Action Required
 
--   If you were already using `CONSUMER_BARCODE_SCANNER=ZXING`, simply remove the setting.
--   If you had `CONSUMER_BARCODE_SCANNER=PYZBAR` or were using the default, no functional changes are needed beyond
-    removing the setting. zxing-cpp supports all the same barcode formats and you should see improved detection
-    reliability.
--   The `libzbar0` / `libzbar-dev` system packages are no longer required and can be removed from any custom Docker
-    images or host installations.
+- If you were already using `CONSUMER_BARCODE_SCANNER=ZXING`, simply remove the setting.
+- If you had `CONSUMER_BARCODE_SCANNER=PYZBAR` or were using the default, no functional changes are needed beyond
+  removing the setting. zxing-cpp supports all the same barcode formats and you should see improved detection
+  reliability.
+- The `libzbar0` / `libzbar-dev` system packages are no longer required and can be removed from any custom Docker
+  images or host installations.
 
 ## Database Engine
 

docs/setup.md

@@ -44,8 +44,8 @@ account. In short, it automates the [Docker Compose setup](#docker) described be
 
 #### Prerequisites
 
--   Docker and Docker Compose must be [installed](https://docs.docker.com/engine/install/){:target="\_blank"}.
--   macOS users will need [GNU sed](https://formulae.brew.sh/formula/gnu-sed) with support for running as `sed` as well as [wget](https://formulae.brew.sh/formula/wget).
+- Docker and Docker Compose must be [installed](https://docs.docker.com/engine/install/){:target="\_blank"}.
+- macOS users will need [GNU sed](https://formulae.brew.sh/formula/gnu-sed) with support for running as `sed` as well as [wget](https://formulae.brew.sh/formula/wget).
 
 #### Run the installation script
 
@@ -63,7 +63,7 @@ credentials you provided during the installation script.
 
 #### Prerequisites
 
--   Docker and Docker Compose must be [installed](https://docs.docker.com/engine/install/){:target="\_blank"}.
+- Docker and Docker Compose must be [installed](https://docs.docker.com/engine/install/){:target="\_blank"}.
 
 #### Installation
 
@@ -101,7 +101,7 @@ credentials you provided during the installation script.
 
     ```yaml
     ports:
-        - 8010:8000
+      - 8010:8000
     ```
 
 3.  Modify `docker-compose.env` with any configuration options you need.
@@ -145,11 +145,11 @@ a [superuser](usage.md#superusers) account.
 If you want to run Paperless as a rootless container, make this
 change in `docker-compose.yml`:
 
--   Set the `user` running the container to map to the `paperless`
-    user in the container. This value (`user_id` below) should be
-    the same ID that `USERMAP_UID` and `USERMAP_GID` are set to in
-    `docker-compose.env`. See `USERMAP_UID` and `USERMAP_GID`
-    [here](configuration.md#docker).
+- Set the `user` running the container to map to the `paperless`
+  user in the container. This value (`user_id` below) should be
+  the same ID that `USERMAP_UID` and `USERMAP_GID` are set to in
+  `docker-compose.env`. See `USERMAP_UID` and `USERMAP_GID`
+  [here](configuration.md#docker).
 
 Your entry for Paperless should contain something like:
 
@@ -171,26 +171,25 @@ to enable polling and disable inotify. See [here](configuration.md#polling).
 
 #### Prerequisites
 
--   Paperless runs on Linux only, Windows is not supported.
--   Python 3.11, 3.12, 3.13, or 3.14 is required. As a policy, Paperless-ngx aims to support at least the three most recent Python versions and drops support for versions as they reach end-of-life. Newer versions may work, but some dependencies may not be fully compatible.
+- Paperless runs on Linux only, Windows is not supported.
+- Python 3.11, 3.12, 3.13, or 3.14 is required. As a policy, Paperless-ngx aims to support at least the three most recent Python versions and drops support for versions as they reach end-of-life. Newer versions may work, but some dependencies may not be fully compatible.
 
 #### Installation
 
 1.  Install dependencies. Paperless requires the following packages:
-
-    -   `python3`
-    -   `python3-pip`
-    -   `python3-dev`
-    -   `default-libmysqlclient-dev` for MariaDB
-    -   `pkg-config` for mysqlclient (python dependency)
-    -   `fonts-liberation` for generating thumbnails for plain text
-        files
-    -   `imagemagick` >= 6 for PDF conversion
-    -   `gnupg` for handling encrypted documents
-    -   `libpq-dev` for PostgreSQL
-    -   `libmagic-dev` for mime type detection
-    -   `mariadb-client` for MariaDB compile time
-    -   `poppler-utils` for barcode detection
+    - `python3`
+    - `python3-pip`
+    - `python3-dev`
+    - `default-libmysqlclient-dev` for MariaDB
+    - `pkg-config` for mysqlclient (python dependency)
+    - `fonts-liberation` for generating thumbnails for plain text
+      files
+    - `imagemagick` >= 6 for PDF conversion
+    - `gnupg` for handling encrypted documents
+    - `libpq-dev` for PostgreSQL
+    - `libmagic-dev` for mime type detection
+    - `mariadb-client` for MariaDB compile time
+    - `poppler-utils` for barcode detection
 
     Use this list for your preferred package management:
 
@@ -200,18 +199,17 @@ to enable polling and disable inotify. See [here](configuration.md#polling).
 
     These dependencies are required for OCRmyPDF, which is used for text
     recognition.
-
-    -   `unpaper`
-    -   `ghostscript`
-    -   `icc-profiles-free`
-    -   `qpdf`
-    -   `liblept5`
-    -   `libxml2`
-    -   `pngquant` (suggested for certain PDF image optimizations)
-    -   `zlib1g`
-    -   `tesseract-ocr` >= 4.0.0 for OCR
-    -   `tesseract-ocr` language packs (`tesseract-ocr-eng`,
-        `tesseract-ocr-deu`, etc)
+    - `unpaper`
+    - `ghostscript`
+    - `icc-profiles-free`
+    - `qpdf`
+    - `liblept5`
+    - `libxml2`
+    - `pngquant` (suggested for certain PDF image optimizations)
+    - `zlib1g`
+    - `tesseract-ocr` >= 4.0.0 for OCR
+    - `tesseract-ocr` language packs (`tesseract-ocr-eng`,
+      `tesseract-ocr-deu`, etc)
 
     Use this list for your preferred package management:
 
@@ -220,16 +218,14 @@ to enable polling and disable inotify. See [here](configuration.md#polling).
     ```
 
     On Raspberry Pi, these libraries are required as well:
-
-    -   `libatlas-base-dev`
-    -   `libxslt1-dev`
-    -   `mime-support`
+    - `libatlas-base-dev`
+    - `libxslt1-dev`
+    - `mime-support`
 
     You will also need these for installing some of the python dependencies:
-
-    -   `build-essential`
-    -   `python3-setuptools`
-    -   `python3-wheel`
+    - `build-essential`
+    - `python3-setuptools`
+    - `python3-wheel`
 
     Use this list for your preferred package management:
 
@@ -279,44 +275,41 @@ to enable polling and disable inotify. See [here](configuration.md#polling).
 6.  Configure Paperless-ngx. See [configuration](configuration.md) for details.
     Edit the included `paperless.conf` and adjust the settings to your
     needs. Required settings for getting Paperless-ngx running are:
-
-    -   [`PAPERLESS_REDIS`](configuration.md#PAPERLESS_REDIS) should point to your Redis server, such as
-        `redis://localhost:6379`.
-    -   [`PAPERLESS_DBENGINE`](configuration.md#PAPERLESS_DBENGINE) is optional, and should be one of `postgres`,
-        `mariadb`, or `sqlite`
-    -   [`PAPERLESS_DBHOST`](configuration.md#PAPERLESS_DBHOST) should be the hostname on which your
-        PostgreSQL server is running. Do not configure this to use
-        SQLite instead. Also configure port, database name, user and
-        password as necessary.
-    -   [`PAPERLESS_CONSUMPTION_DIR`](configuration.md#PAPERLESS_CONSUMPTION_DIR) should point to the folder
-        that Paperless-ngx should watch for incoming documents.
-        Likewise, [`PAPERLESS_DATA_DIR`](configuration.md#PAPERLESS_DATA_DIR) and
-        [`PAPERLESS_MEDIA_ROOT`](configuration.md#PAPERLESS_MEDIA_ROOT) define where Paperless-ngx stores its data.
-        If needed, these can point to the same directory.
-    -   [`PAPERLESS_SECRET_KEY`](configuration.md#PAPERLESS_SECRET_KEY) should be a random sequence of
-        characters. It's used for authentication. Failure to do so
-        allows third parties to forge authentication credentials.
-    -   Set [`PAPERLESS_URL`](configuration.md#PAPERLESS_URL) if you are behind a reverse proxy. This should
-        point to your domain. Please see
-        [configuration](configuration.md) for more
-        information.
+    - [`PAPERLESS_REDIS`](configuration.md#PAPERLESS_REDIS) should point to your Redis server, such as
+      `redis://localhost:6379`.
+    - [`PAPERLESS_DBENGINE`](configuration.md#PAPERLESS_DBENGINE) is optional, and should be one of `postgres`,
+      `mariadb`, or `sqlite`
+    - [`PAPERLESS_DBHOST`](configuration.md#PAPERLESS_DBHOST) should be the hostname on which your
+      PostgreSQL server is running. Do not configure this to use
+      SQLite instead. Also configure port, database name, user and
+      password as necessary.
+    - [`PAPERLESS_CONSUMPTION_DIR`](configuration.md#PAPERLESS_CONSUMPTION_DIR) should point to the folder
+      that Paperless-ngx should watch for incoming documents.
+      Likewise, [`PAPERLESS_DATA_DIR`](configuration.md#PAPERLESS_DATA_DIR) and
+      [`PAPERLESS_MEDIA_ROOT`](configuration.md#PAPERLESS_MEDIA_ROOT) define where Paperless-ngx stores its data.
+      If needed, these can point to the same directory.
+    - [`PAPERLESS_SECRET_KEY`](configuration.md#PAPERLESS_SECRET_KEY) should be a random sequence of
+      characters. It's used for authentication. Failure to do so
+      allows third parties to forge authentication credentials.
+    - Set [`PAPERLESS_URL`](configuration.md#PAPERLESS_URL) if you are behind a reverse proxy. This should
+      point to your domain. Please see
+      [configuration](configuration.md) for more
+      information.
 
     You can make many more adjustments, especially for OCR.
     The following options are recommended for most users:
-
-    -   Set [`PAPERLESS_OCR_LANGUAGE`](configuration.md#PAPERLESS_OCR_LANGUAGE) to the language most of your
-        documents are written in.
-    -   Set [`PAPERLESS_TIME_ZONE`](configuration.md#PAPERLESS_TIME_ZONE) to your local time zone.
+    - Set [`PAPERLESS_OCR_LANGUAGE`](configuration.md#PAPERLESS_OCR_LANGUAGE) to the language most of your
+      documents are written in.
+    - Set [`PAPERLESS_TIME_ZONE`](configuration.md#PAPERLESS_TIME_ZONE) to your local time zone.
 
     !!! warning
 
         Ensure your Redis instance [is secured](https://redis.io/docs/latest/operate/oss_and_stack/management/security/).
 
 7.  Create the following directories if they do not already exist:
-
-    -   `/opt/paperless/media`
-    -   `/opt/paperless/data`
-    -   `/opt/paperless/consume`
+    - `/opt/paperless/media`
+    - `/opt/paperless/data`
+    - `/opt/paperless/consume`
 
     Adjust these paths if you configured different folders.
     Then verify that the `paperless` user has write permissions:
@@ -391,11 +384,10 @@ to enable polling and disable inotify. See [here](configuration.md#polling).
     starting point.
 
     Paperless needs:
-
-    -   The `webserver` script to run the webserver.
-    -   The `consumer` script to watch the input folder.
-    -   The `taskqueue` script for background workers (document consumption, etc.).
-    -   The `scheduler` script for periodic tasks such as email checking.
+    - The `webserver` script to run the webserver.
+    - The `consumer` script to watch the input folder.
+    - The `taskqueue` script for background workers (document consumption, etc.).
+    - The `scheduler` script for periodic tasks such as email checking.
 
     !!! note
 
@@ -501,19 +493,19 @@ your setup depending on how you installed Paperless.
 This section describes how to update an existing Paperless Docker
 installation. Keep these points in mind:
 
--   Read the [changelog](changelog.md) and
-    take note of breaking changes.
--   Decide whether to stay on SQLite or migrate to PostgreSQL.
-    Both work fine with Paperless-ngx.
-    However, if you already have a database server running
-    for other services, you might as well use it for Paperless as well.
--   The task scheduler of Paperless, which is used to execute periodic
-    tasks such as email checking and maintenance, requires a
-    [Redis](https://redis.io/) message broker instance. The
-    Docker Compose route takes care of that.
--   The layout of the folder structure for your documents and data
-    remains the same, so you can plug your old Docker volumes into
-    paperless-ngx and expect it to find everything where it should be.
+- Read the [changelog](changelog.md) and
+  take note of breaking changes.
+- Decide whether to stay on SQLite or migrate to PostgreSQL.
+  Both work fine with Paperless-ngx.
+  However, if you already have a database server running
+  for other services, you might as well use it for Paperless as well.
+- The task scheduler of Paperless, which is used to execute periodic
+  tasks such as email checking and maintenance, requires a
+  [Redis](https://redis.io/) message broker instance. The
+  Docker Compose route takes care of that.
+- The layout of the folder structure for your documents and data
+  remains the same, so you can plug your old Docker volumes into
+  paperless-ngx and expect it to find everything where it should be.
 
 Migration to Paperless-ngx is then performed in a few simple steps:
 
@@ -598,7 +590,6 @@ commands as well.
 1.  Stop and remove the Paperless container.
 2.  If using an external database, stop that container.
 3.  Update Redis configuration.
-
     1. If `REDIS_URL` is already set, change it to [`PAPERLESS_REDIS`](configuration.md#PAPERLESS_REDIS)
        and continue to step 4.
 
@@ -610,22 +601,18 @@ commands as well.
        the new Redis container.
 
 4.  Update user mapping.
-
     1. If set, change the environment variable `PUID` to `USERMAP_UID`.
 
     1. If set, change the environment variable `PGID` to `USERMAP_GID`.
 
 5.  Update configuration paths.
-
     1. Set the environment variable [`PAPERLESS_DATA_DIR`](configuration.md#PAPERLESS_DATA_DIR) to `/config`.
 
 6.  Update media paths.
-
     1. Set the environment variable [`PAPERLESS_MEDIA_ROOT`](configuration.md#PAPERLESS_MEDIA_ROOT) to
        `/data/media`.
 
 7.  Update timezone.
-
     1. Set the environment variable [`PAPERLESS_TIME_ZONE`](configuration.md#PAPERLESS_TIME_ZONE) to the same
        value as `TZ`.
 
@@ -639,33 +626,33 @@ commands as well.
 Paperless runs on Raspberry Pi. Some tasks can be slow on lower-powered
 hardware, but a few settings can improve performance:
 
--   Stick with SQLite to save some resources. See [troubleshooting](troubleshooting.md#log-reports-creating-paperlesstask-failed)
-    if you encounter issues with SQLite locking.
--   If you do not need the filesystem-based consumer, consider disabling it
-    entirely by setting [`PAPERLESS_CONSUMER_DISABLE`](configuration.md#PAPERLESS_CONSUMER_DISABLE) to `true`.
--   Consider setting [`PAPERLESS_OCR_PAGES`](configuration.md#PAPERLESS_OCR_PAGES) to 1, so that Paperless
-    OCRs only the first page of your documents. In most cases, this page
-    contains enough information to be able to find it.
--   [`PAPERLESS_TASK_WORKERS`](configuration.md#PAPERLESS_TASK_WORKERS) and [`PAPERLESS_THREADS_PER_WORKER`](configuration.md#PAPERLESS_THREADS_PER_WORKER) are
-    configured to use all cores. The Raspberry Pi models 3 and up have 4
-    cores, meaning that Paperless will use 2 workers and 2 threads per
-    worker. This may result in sluggish response times during
-    consumption, so you might want to lower these settings (example: 2
-    workers and 1 thread to always have some computing power left for
-    other tasks).
--   Keep [`PAPERLESS_OCR_MODE`](configuration.md#PAPERLESS_OCR_MODE) at its default value `skip` and consider
-    OCRing your documents before feeding them into Paperless. Some
-    scanners are able to do this!
--   Set [`PAPERLESS_OCR_SKIP_ARCHIVE_FILE`](configuration.md#PAPERLESS_OCR_SKIP_ARCHIVE_FILE) to `with_text` to skip archive
-    file generation for already OCRed documents, or `always` to skip it
-    for all documents.
--   If you want to perform OCR on the device, consider using
-    `PAPERLESS_OCR_CLEAN=none`. This will speed up OCR times and use
-    less memory at the expense of slightly worse OCR results.
--   If using Docker, consider setting [`PAPERLESS_WEBSERVER_WORKERS`](configuration.md#PAPERLESS_WEBSERVER_WORKERS) to 1. This will save some memory.
--   Consider setting [`PAPERLESS_ENABLE_NLTK`](configuration.md#PAPERLESS_ENABLE_NLTK) to false, to disable the
-    more advanced language processing, which can take more memory and
-    processing time.
+- Stick with SQLite to save some resources. See [troubleshooting](troubleshooting.md#log-reports-creating-paperlesstask-failed)
+  if you encounter issues with SQLite locking.
+- If you do not need the filesystem-based consumer, consider disabling it
+  entirely by setting [`PAPERLESS_CONSUMER_DISABLE`](configuration.md#PAPERLESS_CONSUMER_DISABLE) to `true`.
+- Consider setting [`PAPERLESS_OCR_PAGES`](configuration.md#PAPERLESS_OCR_PAGES) to 1, so that Paperless
+  OCRs only the first page of your documents. In most cases, this page
+  contains enough information to be able to find it.
+- [`PAPERLESS_TASK_WORKERS`](configuration.md#PAPERLESS_TASK_WORKERS) and [`PAPERLESS_THREADS_PER_WORKER`](configuration.md#PAPERLESS_THREADS_PER_WORKER) are
+  configured to use all cores. The Raspberry Pi models 3 and up have 4
+  cores, meaning that Paperless will use 2 workers and 2 threads per
+  worker. This may result in sluggish response times during
+  consumption, so you might want to lower these settings (example: 2
+  workers and 1 thread to always have some computing power left for
+  other tasks).
+- Keep [`PAPERLESS_OCR_MODE`](configuration.md#PAPERLESS_OCR_MODE) at its default value `skip` and consider
+  OCRing your documents before feeding them into Paperless. Some
+  scanners are able to do this!
+- Set [`PAPERLESS_OCR_SKIP_ARCHIVE_FILE`](configuration.md#PAPERLESS_OCR_SKIP_ARCHIVE_FILE) to `with_text` to skip archive
+  file generation for already OCRed documents, or `always` to skip it
+  for all documents.
+- If you want to perform OCR on the device, consider using
+  `PAPERLESS_OCR_CLEAN=none`. This will speed up OCR times and use
+  less memory at the expense of slightly worse OCR results.
+- If using Docker, consider setting [`PAPERLESS_WEBSERVER_WORKERS`](configuration.md#PAPERLESS_WEBSERVER_WORKERS) to 1. This will save some memory.
+- Consider setting [`PAPERLESS_ENABLE_NLTK`](configuration.md#PAPERLESS_ENABLE_NLTK) to false, to disable the
+  more advanced language processing, which can take more memory and
+  processing time.
 
 For details, refer to [configuration](configuration.md).
 

docs/troubleshooting.md

@@ -4,27 +4,27 @@
 
 Check for the following issues:
 
--   Ensure that the directory you're putting your documents in is the
-    folder paperless is watching. With docker, this setting is performed
-    in the `docker-compose.yml` file. Without Docker, look at the
-    `CONSUMPTION_DIR` setting. Don't adjust this setting if you're
-    using docker.
+- Ensure that the directory you're putting your documents in is the
+  folder paperless is watching. With docker, this setting is performed
+  in the `docker-compose.yml` file. Without Docker, look at the
+  `CONSUMPTION_DIR` setting. Don't adjust this setting if you're
+  using docker.
 
--   Ensure that redis is up and running. Paperless does its task
-    processing asynchronously, and for documents to arrive at the task
-    processor, it needs redis to run.
+- Ensure that redis is up and running. Paperless does its task
+  processing asynchronously, and for documents to arrive at the task
+  processor, it needs redis to run.
 
--   Ensure that the task processor is running. Docker does this
-    automatically. Manually invoke the task processor by executing
+- Ensure that the task processor is running. Docker does this
+  automatically. Manually invoke the task processor by executing
 
-    ```shell-session
-    celery --app paperless worker
-    ```
+  ```shell-session
+  celery --app paperless worker
+  ```
 
--   Look at the output of paperless and inspect it for any errors.
+- Look at the output of paperless and inspect it for any errors.
 
--   Go to the admin interface, and check if there are failed tasks. If
-    so, the tasks will contain an error message.
+- Go to the admin interface, and check if there are failed tasks. If
+  so, the tasks will contain an error message.
 
 ## Consumer warns `OCR for XX failed`
 
@@ -78,12 +78,12 @@ Ensure that `chown` is possible on these directories.
 This indicates that the Auto matching algorithm found no documents to
 learn from. This may have two reasons:
 
--   You don't use the Auto matching algorithm: The error can be safely
-    ignored in this case.
--   You are using the Auto matching algorithm: The classifier explicitly
-    excludes documents with Inbox tags. Verify that there are documents
-    in your archive without inbox tags. The algorithm will only learn
-    from documents not in your inbox.
+- You don't use the Auto matching algorithm: The error can be safely
+  ignored in this case.
+- You are using the Auto matching algorithm: The classifier explicitly
+  excludes documents with Inbox tags. Verify that there are documents
+  in your archive without inbox tags. The algorithm will only learn
+  from documents not in your inbox.
 
 ## UserWarning in sklearn on every single document
 
@@ -127,10 +127,10 @@ change in the `docker-compose.yml` file:
 # The gotenberg chromium route is used to convert .eml files. We do not
 # want to allow external content like tracking pixels or even javascript.
 command:
-    - 'gotenberg'
-    - '--chromium-disable-javascript=true'
-    - '--chromium-allow-list=file:///tmp/.*'
-    - '--api-timeout=60s'
+  - 'gotenberg'
+  - '--chromium-disable-javascript=true'
+  - '--chromium-allow-list=file:///tmp/.*'
+  - '--api-timeout=60s'
 ```
 
 ## Permission denied errors in the consumption directory

docs/usage.md

@@ -14,42 +14,42 @@ for finding and managing your documents.
 Paperless essentially consists of two different parts for managing your
 documents:
 
--   The _consumer_ watches a specified folder and adds all documents in
-    that folder to paperless.
--   The _web server_ (web UI) provides a UI that you use to manage and
-    search documents.
+- The _consumer_ watches a specified folder and adds all documents in
+  that folder to paperless.
+- The _web server_ (web UI) provides a UI that you use to manage and
+  search documents.
 
 Each document has data fields that you can assign to them:
 
--   A _Document_ is a piece of paper that sometimes contains valuable
-    information.
--   The _correspondent_ of a document is the person, institution or
-    company that a document either originates from, or is sent to.
--   A _tag_ is a label that you can assign to documents. Think of labels
-    as more powerful folders: Multiple documents can be grouped together
-    with a single tag, however, a single document can also have multiple
-    tags. This is not possible with folders. The reason folders are not
-    implemented in paperless is simply that tags are much more versatile
-    than folders.
--   A _document type_ is used to demarcate the type of a document such
-    as letter, bank statement, invoice, contract, etc. It is used to
-    identify what a document is about.
--   The document _storage path_ is the location where the document files
-    are stored. See [Storage Paths](advanced_usage.md#storage-paths) for
-    more information.
--   The _date added_ of a document is the date the document was scanned
-    into paperless. You cannot and should not change this date.
--   The _date created_ of a document is the date the document was
-    initially issued. This can be the date you bought a product, the
-    date you signed a contract, or the date a letter was sent to you.
--   The _archive serial number_ (short: ASN) of a document is the
-    identifier of the document in your physical document binders. See
-    [recommended workflow](#usage-recommended-workflow) below.
--   The _content_ of a document is the text that was OCR'ed from the
-    document. This text is fed into the search engine and is used for
-    matching tags, correspondents and document types.
--   Paperless-ngx also supports _custom fields_ which can be used to
-    store additional metadata about a document.
+- A _Document_ is a piece of paper that sometimes contains valuable
+  information.
+- The _correspondent_ of a document is the person, institution or
+  company that a document either originates from, or is sent to.
+- A _tag_ is a label that you can assign to documents. Think of labels
+  as more powerful folders: Multiple documents can be grouped together
+  with a single tag, however, a single document can also have multiple
+  tags. This is not possible with folders. The reason folders are not
+  implemented in paperless is simply that tags are much more versatile
+  than folders.
+- A _document type_ is used to demarcate the type of a document such
+  as letter, bank statement, invoice, contract, etc. It is used to
+  identify what a document is about.
+- The document _storage path_ is the location where the document files
+  are stored. See [Storage Paths](advanced_usage.md#storage-paths) for
+  more information.
+- The _date added_ of a document is the date the document was scanned
+  into paperless. You cannot and should not change this date.
+- The _date created_ of a document is the date the document was
+  initially issued. This can be the date you bought a product, the
+  date you signed a contract, or the date a letter was sent to you.
+- The _archive serial number_ (short: ASN) of a document is the
+  identifier of the document in your physical document binders. See
+  [recommended workflow](#usage-recommended-workflow) below.
+- The _content_ of a document is the text that was OCR'ed from the
+  document. This text is fed into the search engine and is used for
+  matching tags, correspondents and document types.
+- Paperless-ngx also supports _custom fields_ which can be used to
+  store additional metadata about a document.
 
 ## The Web UI
 
@@ -93,12 +93,12 @@ download the document or share it via a share link.
 
 Think of versions as **file history** for a document.
 
--   Versions track the underlying file and extracted text content (OCR/text).
--   Metadata such as tags, correspondent, document type, storage path and custom fields stay on the "root" document.
--   Version files follow normal filename formatting (including storage paths) and add a `_vN` suffix (for example `_v1`, `_v2`).
--   By default, search and document content use the latest version.
--   In document detail, selecting a version switches the preview, file metadata and content (and download etc buttons) to that version.
--   Deleting a non-root version keeps metadata and falls back to the latest remaining version.
+- Versions track the underlying file and extracted text content (OCR/text).
+- Metadata such as tags, correspondent, document type, storage path and custom fields stay on the "root" document.
+- Version files follow normal filename formatting (including storage paths) and add a `_vN` suffix (for example `_v1`, `_v2`).
+- By default, search and document content use the latest version.
+- In document detail, selecting a version switches the preview, file metadata and content (and download etc buttons) to that version.
+- Deleting a non-root version keeps metadata and falls back to the latest remaining version.
 
 ### Management Lists
 
@@ -218,21 +218,20 @@ patterns can include wildcards and multiple patterns separated by a comma.
 The actions all ensure that the same mail is not consumed twice by
 different means. These are as follows:
 
--   **Delete:** Immediately deletes mail that paperless has consumed
-    documents from. Use with caution.
--   **Mark as read:** Mark consumed mail as read. Paperless will not
-    consume documents from already read mails. If you read a mail before
-    paperless sees it, it will be ignored.
--   **Flag:** Sets the 'important' flag on mails with consumed
-    documents. Paperless will not consume flagged mails.
--   **Move to folder:** Moves consumed mails out of the way so that
-    paperless won't consume them again.
--   **Add custom Tag:** Adds a custom tag to mails with consumed
-    documents (the IMAP standard calls these "keywords"). Paperless
-    will not consume mails already tagged. Not all mail servers support
-    this feature!
-
-    -   **Apple Mail support:** Apple Mail clients allow differently colored tags. For this to work use `apple:<color>` (e.g. _apple:green_) as a custom tag. Available colors are _red_, _orange_, _yellow_, _blue_, _green_, _violet_ and _grey_.
+- **Delete:** Immediately deletes mail that paperless has consumed
+  documents from. Use with caution.
+- **Mark as read:** Mark consumed mail as read. Paperless will not
+  consume documents from already read mails. If you read a mail before
+  paperless sees it, it will be ignored.
+- **Flag:** Sets the 'important' flag on mails with consumed
+  documents. Paperless will not consume flagged mails.
+- **Move to folder:** Moves consumed mails out of the way so that
+  paperless won't consume them again.
+- **Add custom Tag:** Adds a custom tag to mails with consumed
+  documents (the IMAP standard calls these "keywords"). Paperless
+  will not consume mails already tagged. Not all mail servers support
+  this feature!
+  - **Apple Mail support:** Apple Mail clients allow differently colored tags. For this to work use `apple:<color>` (e.g. _apple:green_) as a custom tag. Available colors are _red_, _orange_, _yellow_, _blue_, _green_, _violet_ and _grey_.
 
 !!! warning
 
@@ -325,12 +324,12 @@ or using [email](#workflow-action-email) or [webhook](#workflow-action-webhook)
 
 "Share links" are public links to files (or an archive of files) and can be created and managed under the 'Send' button on the document detail screen or from the bulk editor.
 
--   Share links do not require a user to login and thus link directly to a file or bundled download.
--   Links are unique and are of the form `{paperless-url}/share/{randomly-generated-slug}`.
--   Links can optionally have an expiration time set.
--   After a link expires or is deleted users will be redirected to the regular paperless-ngx login.
--   From the document detail screen you can create a share link for that single document.
--   From the bulk editor you can create a **share link bundle** for any selection. Paperless-ngx prepares a ZIP archive in the background and exposes a single share link. You can revisit the "Manage share link bundles" dialog to monitor progress, retry failed bundles, or delete links.
+- Share links do not require a user to login and thus link directly to a file or bundled download.
+- Links are unique and are of the form `{paperless-url}/share/{randomly-generated-slug}`.
+- Links can optionally have an expiration time set.
+- After a link expires or is deleted users will be redirected to the regular paperless-ngx login.
+- From the document detail screen you can create a share link for that single document.
+- From the bulk editor you can create a **share link bundle** for any selection. Paperless-ngx prepares a ZIP archive in the background and exposes a single share link. You can revisit the "Manage share link bundles" dialog to monitor progress, retry failed bundles, or delete links.
 
 !!! tip
 
@@ -514,25 +513,25 @@ flowchart TD
 
 Workflows allow you to filter by:
 
--   Source, e.g. documents uploaded via consume folder, API (& the web UI) and mail fetch
--   File name, including wildcards e.g. \*.pdf will apply to all pdfs.
--   File path, including wildcards. Note that enabling `PAPERLESS_CONSUMER_RECURSIVE` would allow, for
-    example, automatically assigning documents to different owners based on the upload directory.
--   Mail rule. Choosing this option will force 'mail fetch' to be the workflow source.
--   Content matching (`Added`, `Updated` and `Scheduled` triggers only). Filter document content using the matching settings.
+- Source, e.g. documents uploaded via consume folder, API (& the web UI) and mail fetch
+- File name, including wildcards e.g. \*.pdf will apply to all pdfs.
+- File path, including wildcards. Note that enabling `PAPERLESS_CONSUMER_RECURSIVE` would allow, for
+  example, automatically assigning documents to different owners based on the upload directory.
+- Mail rule. Choosing this option will force 'mail fetch' to be the workflow source.
+- Content matching (`Added`, `Updated` and `Scheduled` triggers only). Filter document content using the matching settings.
 
 There are also 'advanced' filters available for `Added`, `Updated` and `Scheduled` triggers:
 
--   Any Tags: Filter for documents with any of the specified tags.
--   All Tags: Filter for documents with all of the specified tags.
--   No Tags: Filter for documents with none of the specified tags.
--   Document type: Filter documents with this document type.
--   Not Document types: Filter documents without any of these document types.
--   Correspondent: Filter documents with this correspondent.
--   Not Correspondents: Filter documents without any of these correspondents.
--   Storage path: Filter documents with this storage path.
--   Not Storage paths: Filter documents without any of these storage paths.
--   Custom field query: Filter documents with a custom field query (the same as used for the document list filters).
+- Any Tags: Filter for documents with any of the specified tags.
+- All Tags: Filter for documents with all of the specified tags.
+- No Tags: Filter for documents with none of the specified tags.
+- Document type: Filter documents with this document type.
+- Not Document types: Filter documents without any of these document types.
+- Correspondent: Filter documents with this correspondent.
+- Not Correspondents: Filter documents without any of these correspondents.
+- Storage path: Filter documents with this storage path.
+- Not Storage paths: Filter documents without any of these storage paths.
+- Custom field query: Filter documents with a custom field query (the same as used for the document list filters).
 
 ### Workflow Actions
 
@@ -544,37 +543,37 @@ The following workflow action types are available:
 
 "Assignment" actions can assign:
 
--   Title, see [workflow placeholders](usage.md#workflow-placeholders) below
--   Tags, correspondent, document type and storage path
--   Document owner
--   View and / or edit permissions to users or groups
--   Custom fields. Note that no value for the field will be set
+- Title, see [workflow placeholders](usage.md#workflow-placeholders) below
+- Tags, correspondent, document type and storage path
+- Document owner
+- View and / or edit permissions to users or groups
+- Custom fields. Note that no value for the field will be set
 
 ##### Removal {#workflow-action-removal}
 
 "Removal" actions can remove either all of or specific sets of the following:
 
--   Tags, correspondents, document types or storage paths
--   Document owner
--   View and / or edit permissions
--   Custom fields
+- Tags, correspondents, document types or storage paths
+- Document owner
+- View and / or edit permissions
+- Custom fields
 
 ##### Email {#workflow-action-email}
 
 "Email" actions can send documents via email. This action requires a mail server to be [configured](configuration.md#email-sending). You can specify:
 
--   The recipient email address(es) separated by commas
--   The subject and body of the email, which can include placeholders, see [placeholders](usage.md#workflow-placeholders) below
--   Whether to include the document as an attachment
+- The recipient email address(es) separated by commas
+- The subject and body of the email, which can include placeholders, see [placeholders](usage.md#workflow-placeholders) below
+- Whether to include the document as an attachment
 
 ##### Webhook {#workflow-action-webhook}
 
 "Webhook" actions send a POST request to a specified URL. You can specify:
 
--   The URL to send the request to
--   The request body as text or as key-value pairs, which can include placeholders, see [placeholders](usage.md#workflow-placeholders) below.
--   Encoding for the request body, either JSON or form data
--   The request headers as key-value pairs
+- The URL to send the request to
+- The request body as text or as key-value pairs, which can include placeholders, see [placeholders](usage.md#workflow-placeholders) below.
+- Encoding for the request body, either JSON or form data
+- The request headers as key-value pairs
 
 For security reasons, webhooks can be limited to specific ports and disallowed from connecting to local URLs. See the relevant
 [configuration settings](configuration.md#workflow-webhooks) to change this behavior. If you are allowing non-admins to create workflows,
@@ -605,33 +604,33 @@ The available inputs differ depending on the type of workflow trigger.
 This is because at the time of consumption (when the text is to be set), no automatic tags etc. have been
 applied. You can use the following placeholders in the template with any trigger type:
 
--   `{{correspondent}}`: assigned correspondent name
--   `{{document_type}}`: assigned document type name
--   `{{owner_username}}`: assigned owner username
--   `{{added}}`: added datetime
--   `{{added_year}}`: added year
--   `{{added_year_short}}`: added year
--   `{{added_month}}`: added month
--   `{{added_month_name}}`: added month name
--   `{{added_month_name_short}}`: added month short name
--   `{{added_day}}`: added day
--   `{{added_time}}`: added time in HH:MM format
--   `{{original_filename}}`: original file name without extension
--   `{{filename}}`: current file name without extension (for "added" workflows this may not be final yet, you can use `{{original_filename}}`)
--   `{{doc_title}}`: current document title (cannot be used in title assignment)
+- `{{correspondent}}`: assigned correspondent name
+- `{{document_type}}`: assigned document type name
+- `{{owner_username}}`: assigned owner username
+- `{{added}}`: added datetime
+- `{{added_year}}`: added year
+- `{{added_year_short}}`: added year
+- `{{added_month}}`: added month
+- `{{added_month_name}}`: added month name
+- `{{added_month_name_short}}`: added month short name
+- `{{added_day}}`: added day
+- `{{added_time}}`: added time in HH:MM format
+- `{{original_filename}}`: original file name without extension
+- `{{filename}}`: current file name without extension (for "added" workflows this may not be final yet, you can use `{{original_filename}}`)
+- `{{doc_title}}`: current document title (cannot be used in title assignment)
 
 The following placeholders are only available for "added" or "updated" triggers
 
--   `{{created}}`: created datetime
--   `{{created_year}}`: created year
--   `{{created_year_short}}`: created year
--   `{{created_month}}`: created month
--   `{{created_month_name}}`: created month name
--   `{{created_month_name_short}}`: created month short name
--   `{{created_day}}`: created day
--   `{{created_time}}`: created time in HH:MM format
--   `{{doc_url}}`: URL to the document in the web UI. Requires the `PAPERLESS_URL` setting to be set.
--   `{{doc_id}}`: Document ID
+- `{{created}}`: created datetime
+- `{{created_year}}`: created year
+- `{{created_year_short}}`: created year
+- `{{created_month}}`: created month
+- `{{created_month_name}}`: created month name
+- `{{created_month_name_short}}`: created month short name
+- `{{created_day}}`: created day
+- `{{created_time}}`: created time in HH:MM format
+- `{{doc_url}}`: URL to the document in the web UI. Requires the `PAPERLESS_URL` setting to be set.
+- `{{doc_id}}`: Document ID
 
 ##### Examples
 
@@ -676,26 +675,26 @@ Multiple fields may be attached to a document but the same field name cannot be
 
 The following custom field types are supported:
 
--   `Text`: any text
--   `Boolean`: true / false (check / unchecked) field
--   `Date`: date
--   `URL`: a valid url
--   `Integer`: integer number e.g. 12
--   `Number`: float number e.g. 12.3456
--   `Monetary`: [ISO 4217 currency code](https://en.wikipedia.org/wiki/ISO_4217#List_of_ISO_4217_currency_codes) and a number with exactly two decimals, e.g. USD12.30
--   `Document Link`: reference(s) to other document(s) displayed as links, automatically creates a symmetrical link in reverse
--   `Select`: a pre-defined list of strings from which the user can choose
+- `Text`: any text
+- `Boolean`: true / false (check / unchecked) field
+- `Date`: date
+- `URL`: a valid url
+- `Integer`: integer number e.g. 12
+- `Number`: float number e.g. 12.3456
+- `Monetary`: [ISO 4217 currency code](https://en.wikipedia.org/wiki/ISO_4217#List_of_ISO_4217_currency_codes) and a number with exactly two decimals, e.g. USD12.30
+- `Document Link`: reference(s) to other document(s) displayed as links, automatically creates a symmetrical link in reverse
+- `Select`: a pre-defined list of strings from which the user can choose
 
 ## PDF Actions
 
 Paperless-ngx supports basic editing operations for PDFs (these operations currently cannot be performed on non-PDF files). When viewing an individual document you can
 open the 'PDF Editor' to use a simple UI for re-arranging, rotating, deleting pages and splitting documents.
 
--   Merging documents: available when selecting multiple documents for 'bulk editing'.
--   Rotating documents: available when selecting multiple documents for 'bulk editing' and via the pdf editor on an individual document's details page.
--   Splitting documents: via the pdf editor on an individual document's details page.
--   Deleting pages: via the pdf editor on an individual document's details page.
--   Re-arranging pages: via the pdf editor on an individual document's details page.
+- Merging documents: available when selecting multiple documents for 'bulk editing'.
+- Rotating documents: available when selecting multiple documents for 'bulk editing' and via the pdf editor on an individual document's details page.
+- Splitting documents: via the pdf editor on an individual document's details page.
+- Deleting pages: via the pdf editor on an individual document's details page.
+- Re-arranging pages: via the pdf editor on an individual document's details page.
 
 !!! important
 
@@ -773,18 +772,18 @@ the system.
 Here are a couple examples of tags and types that you could use in your
 collection.
 
--   An `inbox` tag for newly added documents that you haven't manually
-    edited yet.
--   A tag `car` for everything car related (repairs, registration,
-    insurance, etc)
--   A tag `todo` for documents that you still need to do something with,
-    such as reply, or perform some task online.
--   A tag `bank account x` for all bank statement related to that
-    account.
--   A tag `mail` for anything that you added to paperless via its mail
-    processing capabilities.
--   A tag `missing_metadata` when you still need to add some metadata to
-    a document, but can't or don't want to do this right now.
+- An `inbox` tag for newly added documents that you haven't manually
+  edited yet.
+- A tag `car` for everything car related (repairs, registration,
+  insurance, etc)
+- A tag `todo` for documents that you still need to do something with,
+  such as reply, or perform some task online.
+- A tag `bank account x` for all bank statement related to that
+  account.
+- A tag `mail` for anything that you added to paperless via its mail
+  processing capabilities.
+- A tag `missing_metadata` when you still need to add some metadata to
+  a document, but can't or don't want to do this right now.
 
 ## Searching {#basic-usage_searching}
 
@@ -873,8 +872,8 @@ The following diagram shows how easy it is to manage your documents.
 
 ### Preparations in paperless
 
--   Create an inbox tag that gets assigned to all new documents.
--   Create a TODO tag.
+- Create an inbox tag that gets assigned to all new documents.
+- Create a TODO tag.
 
 ### Processing of the physical documents
 
@@ -948,15 +947,15 @@ Some documents require attention and require you to act on the document.
 You may take two different approaches to handle these documents based on
 how regularly you intend to scan documents and use paperless.
 
--   If you scan and process your documents in paperless regularly,
-    assign a TODO tag to all scanned documents that you need to process.
-    Create a saved view on the dashboard that shows all documents with
-    this tag.
--   If you do not scan documents regularly and use paperless solely for
-    archiving, create a physical todo box next to your physical inbox
-    and put documents you need to process in the TODO box. When you
-    performed the task associated with the document, move it to the
-    inbox.
+- If you scan and process your documents in paperless regularly,
+  assign a TODO tag to all scanned documents that you need to process.
+  Create a saved view on the dashboard that shows all documents with
+  this tag.
+- If you do not scan documents regularly and use paperless solely for
+  archiving, create a physical todo box next to your physical inbox
+  and put documents you need to process in the TODO box. When you
+  performed the task associated with the document, move it to the
+  inbox.
 
 ## Remote OCR
 
@@ -977,64 +976,63 @@ or page limitations (e.g. with a free tier).
 
 Paperless-ngx consists of the following components:
 
--   **The webserver:** This serves the administration pages, the API,
-    and the new frontend. This is the main tool you'll be using to interact
-    with paperless. You may start the webserver directly with
+- **The webserver:** This serves the administration pages, the API,
+  and the new frontend. This is the main tool you'll be using to interact
+  with paperless. You may start the webserver directly with
 
-    ```shell-session
-    cd /path/to/paperless/src/
-    granian --interface asginl --ws "paperless.asgi:application"
-    ```
+  ```shell-session
+  cd /path/to/paperless/src/
+  granian --interface asginl --ws "paperless.asgi:application"
+  ```
 
-    or by any other means such as Apache `mod_wsgi`.
+  or by any other means such as Apache `mod_wsgi`.
 
--   **The consumer:** This is what watches your consumption folder for
-    documents. However, the consumer itself does not really consume your
-    documents. Now it notifies a task processor that a new file is ready
-    for consumption. I suppose it should be named differently. This was
-    also used to check your emails, but that's now done elsewhere as
-    well.
+- **The consumer:** This is what watches your consumption folder for
+  documents. However, the consumer itself does not really consume your
+  documents. Now it notifies a task processor that a new file is ready
+  for consumption. I suppose it should be named differently. This was
+  also used to check your emails, but that's now done elsewhere as
+  well.
 
-    Start the consumer with the management command `document_consumer`:
+  Start the consumer with the management command `document_consumer`:
 
-    ```shell-session
-    cd /path/to/paperless/src/
-    python3 manage.py document_consumer
-    ```
+  ```shell-session
+  cd /path/to/paperless/src/
+  python3 manage.py document_consumer
+  ```
 
--   **The task processor:** Paperless relies on [Celery - Distributed
-    Task Queue](https://docs.celeryq.dev/en/stable/index.html) for doing
-    most of the heavy lifting. This is a task queue that accepts tasks
-    from multiple sources and processes these in parallel. It also comes
-    with a scheduler that executes certain commands periodically.
+- **The task processor:** Paperless relies on [Celery - Distributed
+  Task Queue](https://docs.celeryq.dev/en/stable/index.html) for doing
+  most of the heavy lifting. This is a task queue that accepts tasks
+  from multiple sources and processes these in parallel. It also comes
+  with a scheduler that executes certain commands periodically.
 
-    This task processor is responsible for:
+  This task processor is responsible for:
+  - Consuming documents. When the consumer finds new documents, it
+    notifies the task processor to start a consumption task.
+  - The task processor also performs the consumption of any
+    documents you upload through the web interface.
+  - Consuming emails. It periodically checks your configured
+    accounts for new emails and notifies the task processor to
+    consume the attachment of an email.
+  - Maintaining the search index and the automatic matching
+    algorithm. These are things that paperless needs to do from time
+    to time in order to operate properly.
 
-    -   Consuming documents. When the consumer finds new documents, it
-        notifies the task processor to start a consumption task.
-    -   The task processor also performs the consumption of any
-        documents you upload through the web interface.
-    -   Consuming emails. It periodically checks your configured
-        accounts for new emails and notifies the task processor to
-        consume the attachment of an email.
-    -   Maintaining the search index and the automatic matching
-        algorithm. These are things that paperless needs to do from time
-        to time in order to operate properly.
+  This allows paperless to process multiple documents from your
+  consumption folder in parallel! On a modern multi core system, this
+  makes the consumption process with full OCR blazingly fast.
 
-    This allows paperless to process multiple documents from your
-    consumption folder in parallel! On a modern multi core system, this
-    makes the consumption process with full OCR blazingly fast.
+  The task processor comes with a built-in admin interface that you
+  can use to check whenever any of the tasks fail and inspect the
+  errors (i.e., wrong email credentials, errors during consuming a
+  specific file, etc).
 
-    The task processor comes with a built-in admin interface that you
-    can use to check whenever any of the tasks fail and inspect the
-    errors (i.e., wrong email credentials, errors during consuming a
-    specific file, etc).
+- A [redis](https://redis.io/) message broker: This is a really
+  lightweight service that is responsible for getting the tasks from
+  the webserver and the consumer to the task scheduler. These run in a
+  different process (maybe even on different machines!), and
+  therefore, this is necessary.
 
--   A [redis](https://redis.io/) message broker: This is a really
-    lightweight service that is responsible for getting the tasks from
-    the webserver and the consumer to the task scheduler. These run in a
-    different process (maybe even on different machines!), and
-    therefore, this is necessary.
-
--   Optional: A database server. Paperless supports PostgreSQL, MariaDB
-    and SQLite for storing its data.
+- Optional: A database server. Paperless supports PostgreSQL, MariaDB
+  and SQLite for storing its data.

pyproject.toml

@@ -45,7 +45,7 @@ dependencies = [
   "drf-spectacular-sidecar~=2026.1.1",
   "drf-writable-nested~=0.7.1",
   "faiss-cpu>=1.10",
-  "filelock~=3.24.3",
+  "filelock~=3.20.3",
   "flower~=2.0.1",
   "gotenberg-client~=0.13.1",
   "httpx-oauth~=0.16",

src-ui/messages.xlf

@@ -1217,7 +1217,7 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1760</context>
+          <context context-type="linenumber">1758</context>
         </context-group>
       </trans-unit>
       <trans-unit id="1577733187050997705" datatype="html">
@@ -2802,19 +2802,19 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1761</context>
+          <context context-type="linenumber">1759</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">802</context>
+          <context context-type="linenumber">833</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">835</context>
+          <context context-type="linenumber">871</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">854</context>
+          <context context-type="linenumber">894</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/manage/document-attributes/custom-fields/custom-fields.component.ts</context>
@@ -3404,27 +3404,27 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">445</context>
+          <context context-type="linenumber">470</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">485</context>
+          <context context-type="linenumber">510</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">523</context>
+          <context context-type="linenumber">548</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">561</context>
+          <context context-type="linenumber">586</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">623</context>
+          <context context-type="linenumber">648</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">756</context>
+          <context context-type="linenumber">781</context>
         </context-group>
       </trans-unit>
       <trans-unit id="994016933065248559" datatype="html">
@@ -3512,7 +3512,7 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1814</context>
+          <context context-type="linenumber">1812</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6661109599266152398" datatype="html">
@@ -3523,7 +3523,7 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1815</context>
+          <context context-type="linenumber">1813</context>
         </context-group>
       </trans-unit>
       <trans-unit id="5162686434580248853" datatype="html">
@@ -3534,7 +3534,7 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1816</context>
+          <context context-type="linenumber">1814</context>
         </context-group>
       </trans-unit>
       <trans-unit id="8157388568390631653" datatype="html">
@@ -5499,7 +5499,7 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">760</context>
+          <context context-type="linenumber">785</context>
         </context-group>
       </trans-unit>
       <trans-unit id="4522609911791833187" datatype="html">
@@ -7327,7 +7327,7 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">390</context>
+          <context context-type="linenumber">415</context>
         </context-group>
         <note priority="1" from="description">this string is used to separate processing, failed and added on the file upload widget</note>
       </trans-unit>
@@ -7851,7 +7851,7 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">758</context>
+          <context context-type="linenumber">783</context>
         </context-group>
       </trans-unit>
       <trans-unit id="7295637485862454066" datatype="html">
@@ -7869,7 +7869,7 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">798</context>
+          <context context-type="linenumber">829</context>
         </context-group>
       </trans-unit>
       <trans-unit id="2951161989614003846" datatype="html">
@@ -7890,88 +7890,88 @@
         <source>Reprocess operation for &quot;<x id="PH" equiv-text="this.document.title"/>&quot; will begin in the background.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1387</context>
+          <context context-type="linenumber">1385</context>
         </context-group>
       </trans-unit>
       <trans-unit id="4409560272830824468" datatype="html">
         <source>Error executing operation</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1398</context>
+          <context context-type="linenumber">1396</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6030453331794586802" datatype="html">
         <source>Error downloading document</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1461</context>
+          <context context-type="linenumber">1459</context>
         </context-group>
       </trans-unit>
       <trans-unit id="4458954481601077369" datatype="html">
         <source>Page Fit</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1541</context>
+          <context context-type="linenumber">1539</context>
         </context-group>
       </trans-unit>
       <trans-unit id="4663705961777238777" datatype="html">
         <source>PDF edit operation for &quot;<x id="PH" equiv-text="this.document.title"/>&quot; will begin in the background.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1781</context>
+          <context context-type="linenumber">1779</context>
         </context-group>
       </trans-unit>
       <trans-unit id="9043972994040261999" datatype="html">
         <source>Error executing PDF edit operation</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1793</context>
+          <context context-type="linenumber">1791</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6172690334763056188" datatype="html">
         <source>Please enter the current password before attempting to remove it.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1804</context>
+          <context context-type="linenumber">1802</context>
         </context-group>
       </trans-unit>
       <trans-unit id="968660764814228922" datatype="html">
         <source>Password removal operation for &quot;<x id="PH" equiv-text="this.document.title"/>&quot; will begin in the background.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1838</context>
+          <context context-type="linenumber">1836</context>
         </context-group>
       </trans-unit>
       <trans-unit id="2282118435712883014" datatype="html">
         <source>Error executing password removal operation</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1852</context>
+          <context context-type="linenumber">1850</context>
         </context-group>
       </trans-unit>
       <trans-unit id="3740891324955700797" datatype="html">
         <source>Print failed.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1891</context>
+          <context context-type="linenumber">1889</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6457245677384603573" datatype="html">
         <source>Error loading document for printing.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1903</context>
+          <context context-type="linenumber">1901</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6085793215710522488" datatype="html">
         <source>An error occurred loading tiff: <x id="PH" equiv-text="err.toString()"/></source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1968</context>
+          <context context-type="linenumber">1966</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-detail/document-detail.component.ts</context>
-          <context context-type="linenumber">1972</context>
+          <context context-type="linenumber">1970</context>
         </context-group>
       </trans-unit>
       <trans-unit id="4958946940233632319" datatype="html">
@@ -8215,25 +8215,25 @@
         <source>Error executing bulk operation</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">294</context>
+          <context context-type="linenumber">321</context>
         </context-group>
       </trans-unit>
       <trans-unit id="7894972847287473517" datatype="html">
         <source>&quot;<x id="PH" equiv-text="items[0].name"/>&quot;</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">382</context>
+          <context context-type="linenumber">407</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">388</context>
+          <context context-type="linenumber">413</context>
         </context-group>
       </trans-unit>
       <trans-unit id="8639884465898458690" datatype="html">
         <source>&quot;<x id="PH" equiv-text="items[0].name"/>&quot; and &quot;<x id="PH_1" equiv-text="items[1].name"/>&quot;</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">384</context>
+          <context context-type="linenumber">409</context>
         </context-group>
         <note priority="1" from="description">This is for messages like &apos;modify &quot;tag1&quot; and &quot;tag2&quot;&apos;</note>
       </trans-unit>
@@ -8241,7 +8241,7 @@
         <source><x id="PH" equiv-text="list"/> and &quot;<x id="PH_1" equiv-text="items[items.length - 1].name"/>&quot;</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">392,394</context>
+          <context context-type="linenumber">417,419</context>
         </context-group>
         <note priority="1" from="description">this is for messages like &apos;modify &quot;tag1&quot;, &quot;tag2&quot; and &quot;tag3&quot;&apos;</note>
       </trans-unit>
@@ -8249,14 +8249,14 @@
         <source>Confirm tags assignment</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">409</context>
+          <context context-type="linenumber">434</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6619516195038467207" datatype="html">
         <source>This operation will add the tag &quot;<x id="PH" equiv-text="tag.name"/>&quot; to <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">415</context>
+          <context context-type="linenumber">440</context>
         </context-group>
       </trans-unit>
       <trans-unit id="1894412783609570695" datatype="html">
@@ -8265,14 +8265,14 @@
         )"/> to <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">420,422</context>
+          <context context-type="linenumber">445,447</context>
         </context-group>
       </trans-unit>
       <trans-unit id="7181166515756808573" datatype="html">
         <source>This operation will remove the tag &quot;<x id="PH" equiv-text="tag.name"/>&quot; from <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">428</context>
+          <context context-type="linenumber">453</context>
         </context-group>
       </trans-unit>
       <trans-unit id="3819792277998068944" datatype="html">
@@ -8281,7 +8281,7 @@
         )"/> from <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">433,435</context>
+          <context context-type="linenumber">458,460</context>
         </context-group>
       </trans-unit>
       <trans-unit id="2739066218579571288" datatype="html">
@@ -8292,84 +8292,84 @@
         )"/> on <x id="PH_2" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">437,441</context>
+          <context context-type="linenumber">462,466</context>
         </context-group>
       </trans-unit>
       <trans-unit id="2996713129519325161" datatype="html">
         <source>Confirm correspondent assignment</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">478</context>
+          <context context-type="linenumber">503</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6900893559485781849" datatype="html">
         <source>This operation will assign the correspondent &quot;<x id="PH" equiv-text="correspondent.name"/>&quot; to <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">480</context>
+          <context context-type="linenumber">505</context>
         </context-group>
       </trans-unit>
       <trans-unit id="1257522660364398440" datatype="html">
         <source>This operation will remove the correspondent from <x id="PH" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">482</context>
+          <context context-type="linenumber">507</context>
         </context-group>
       </trans-unit>
       <trans-unit id="5393409374423140648" datatype="html">
         <source>Confirm document type assignment</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">516</context>
+          <context context-type="linenumber">541</context>
         </context-group>
       </trans-unit>
       <trans-unit id="332180123895325027" datatype="html">
         <source>This operation will assign the document type &quot;<x id="PH" equiv-text="documentType.name"/>&quot; to <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">518</context>
+          <context context-type="linenumber">543</context>
         </context-group>
       </trans-unit>
       <trans-unit id="2236642492594872779" datatype="html">
         <source>This operation will remove the document type from <x id="PH" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">520</context>
+          <context context-type="linenumber">545</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6386555513013840736" datatype="html">
         <source>Confirm storage path assignment</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">554</context>
+          <context context-type="linenumber">579</context>
         </context-group>
       </trans-unit>
       <trans-unit id="8750527458618415924" datatype="html">
         <source>This operation will assign the storage path &quot;<x id="PH" equiv-text="storagePath.name"/>&quot; to <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">556</context>
+          <context context-type="linenumber">581</context>
         </context-group>
       </trans-unit>
       <trans-unit id="60728365335056946" datatype="html">
         <source>This operation will remove the storage path from <x id="PH" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">558</context>
+          <context context-type="linenumber">583</context>
         </context-group>
       </trans-unit>
       <trans-unit id="4187352575310415704" datatype="html">
         <source>Confirm custom field assignment</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">587</context>
+          <context context-type="linenumber">612</context>
         </context-group>
       </trans-unit>
       <trans-unit id="7966494636326273856" datatype="html">
         <source>This operation will assign the custom field &quot;<x id="PH" equiv-text="customField.name"/>&quot; to <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">593</context>
+          <context context-type="linenumber">618</context>
         </context-group>
       </trans-unit>
       <trans-unit id="5789455969634598553" datatype="html">
@@ -8378,14 +8378,14 @@
         )"/> to <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">598,600</context>
+          <context context-type="linenumber">623,625</context>
         </context-group>
       </trans-unit>
       <trans-unit id="5648572354333199245" datatype="html">
         <source>This operation will remove the custom field &quot;<x id="PH" equiv-text="customField.name"/>&quot; from <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">606</context>
+          <context context-type="linenumber">631</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6666899594015948817" datatype="html">
@@ -8394,7 +8394,7 @@
         )"/> from <x id="PH_1" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">611,613</context>
+          <context context-type="linenumber">636,638</context>
         </context-group>
       </trans-unit>
       <trans-unit id="8050047262594964176" datatype="html">
@@ -8405,91 +8405,91 @@
         )"/> on <x id="PH_2" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">615,619</context>
+          <context context-type="linenumber">640,644</context>
         </context-group>
       </trans-unit>
       <trans-unit id="8615059324209654051" datatype="html">
         <source>Move <x id="PH" equiv-text="this.list.selected.size"/> selected document(s) to the trash?</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">757</context>
+          <context context-type="linenumber">782</context>
         </context-group>
       </trans-unit>
       <trans-unit id="8585195717323764335" datatype="html">
         <source>This operation will permanently recreate the archive files for <x id="PH" equiv-text="this.list.selected.size"/> selected document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">799</context>
+          <context context-type="linenumber">830</context>
         </context-group>
       </trans-unit>
       <trans-unit id="7366623494074776040" datatype="html">
         <source>The archive files will be re-generated with the current settings.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">800</context>
+          <context context-type="linenumber">831</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6555329262222566158" datatype="html">
         <source>Rotate confirm</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">832</context>
+          <context context-type="linenumber">868</context>
         </context-group>
       </trans-unit>
       <trans-unit id="5203024009814367559" datatype="html">
         <source>This operation will add rotated versions of the <x id="PH" equiv-text="this.list.selected.size"/> document(s).</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">833</context>
+          <context context-type="linenumber">869</context>
         </context-group>
       </trans-unit>
       <trans-unit id="7910756456450124185" datatype="html">
         <source>Merge confirm</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">852</context>
+          <context context-type="linenumber">892</context>
         </context-group>
       </trans-unit>
       <trans-unit id="7643543647233874431" datatype="html">
         <source>This operation will merge <x id="PH" equiv-text="this.list.selected.size"/> selected documents into a new document.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">853</context>
+          <context context-type="linenumber">893</context>
         </context-group>
       </trans-unit>
       <trans-unit id="7869008840945899895" datatype="html">
         <source>Merged document will be queued for consumption.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">872</context>
+          <context context-type="linenumber">916</context>
         </context-group>
       </trans-unit>
       <trans-unit id="476913782630693351" datatype="html">
         <source>Custom fields updated.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">896</context>
+          <context context-type="linenumber">940</context>
         </context-group>
       </trans-unit>
       <trans-unit id="3873496751167944011" datatype="html">
         <source>Error updating custom fields.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">905</context>
+          <context context-type="linenumber">949</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6144801143088984138" datatype="html">
         <source>Share link bundle creation requested.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">945</context>
+          <context context-type="linenumber">989</context>
         </context-group>
       </trans-unit>
       <trans-unit id="46019676931295023" datatype="html">
         <source>Share link bundle creation is not available yet.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.ts</context>
-          <context context-type="linenumber">952</context>
+          <context context-type="linenumber">996</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6307402210351946694" datatype="html">

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

@@ -31,8 +31,8 @@ export enum EditDialogMode {
 
 @Directive()
 export abstract class EditDialogComponent<
-    T extends ObjectWithPermissions | ObjectWithId,
-  >
+  T extends ObjectWithPermissions | ObjectWithId,
+>
   extends LoadingComponentWithPermissions
   implements OnInit
 {

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

@@ -950,8 +950,8 @@ describe('DocumentDetailComponent', () => {
 
   it('should support reprocess, confirm and close modal after started', () => {
     initNormally()
-    const bulkEditSpy = jest.spyOn(documentService, 'bulkEdit')
-    bulkEditSpy.mockReturnValue(of(true))
+    const reprocessSpy = jest.spyOn(documentService, 'reprocessDocuments')
+    reprocessSpy.mockReturnValue(of(true))
     let openModal: NgbModalRef
     modalService.activeInstances.subscribe((modal) => (openModal = modal[0]))
     const modalSpy = jest.spyOn(modalService, 'open')
@@ -959,7 +959,7 @@ describe('DocumentDetailComponent', () => {
     component.reprocess()
     const modalCloseSpy = jest.spyOn(openModal, 'close')
     openModal.componentInstance.confirmClicked.next()
-    expect(bulkEditSpy).toHaveBeenCalledWith([doc.id], 'reprocess', {})
+    expect(reprocessSpy).toHaveBeenCalledWith([doc.id])
     expect(modalSpy).toHaveBeenCalled()
     expect(toastSpy).toHaveBeenCalled()
     expect(modalCloseSpy).toHaveBeenCalled()
@@ -967,13 +967,13 @@ describe('DocumentDetailComponent', () => {
 
   it('should show error if redo ocr call fails', () => {
     initNormally()
-    const bulkEditSpy = jest.spyOn(documentService, 'bulkEdit')
+    const reprocessSpy = jest.spyOn(documentService, 'reprocessDocuments')
     let openModal: NgbModalRef
     modalService.activeInstances.subscribe((modal) => (openModal = modal[0]))
     const toastSpy = jest.spyOn(toastService, 'showError')
     component.reprocess()
     const modalCloseSpy = jest.spyOn(openModal, 'close')
-    bulkEditSpy.mockReturnValue(throwError(() => new Error('error occurred')))
+    reprocessSpy.mockReturnValue(throwError(() => new Error('error occurred')))
     openModal.componentInstance.confirmClicked.next()
     expect(toastSpy).toHaveBeenCalled()
     expect(modalCloseSpy).not.toHaveBeenCalled()
@@ -1644,9 +1644,9 @@ describe('DocumentDetailComponent', () => {
     expect(
       fixture.debugElement.query(By.css('.preview-sticky img'))
     ).not.toBeUndefined()
-    ;(component.document.mime_type =
+    ;((component.document.mime_type =
       'application/vnd.openxmlformats-officedocument.wordprocessingml.document'),
-      fixture.detectChanges()
+      fixture.detectChanges())
     expect(component.archiveContentRenderType).toEqual(
       component.ContentRenderType.Other
     )
@@ -1669,18 +1669,15 @@ describe('DocumentDetailComponent', () => {
     modal.componentInstance.pages = [{ page: 1, rotate: 0, splitAfter: false }]
     modal.componentInstance.confirm()
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/bulk_edit/`
+      `${environment.apiBaseUrl}documents/edit_pdf/`
     )
     expect(req.request.body).toEqual({
       documents: [10],
-      method: 'edit_pdf',
-      parameters: {
-        operations: [{ page: 1, rotate: 0, doc: 0 }],
-        delete_original: false,
-        update_document: false,
-        include_metadata: true,
-        source_mode: 'explicit_selection',
-      },
+      operations: [{ page: 1, rotate: 0, doc: 0 }],
+      delete_original: false,
+      update_document: false,
+      include_metadata: true,
+      source_mode: 'explicit_selection',
     })
     req.error(new ErrorEvent('failed'))
     expect(errorSpy).toHaveBeenCalled()
@@ -1691,7 +1688,7 @@ describe('DocumentDetailComponent', () => {
     modal.componentInstance.deleteOriginal = true
     modal.componentInstance.confirm()
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/bulk_edit/`
+      `${environment.apiBaseUrl}documents/edit_pdf/`
     )
     req.flush(true)
     expect(closeSpy).toHaveBeenCalled()
@@ -1711,18 +1708,15 @@ describe('DocumentDetailComponent', () => {
     dialog.deleteOriginal = true
     dialog.confirm()
     const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/bulk_edit/`
+      `${environment.apiBaseUrl}documents/remove_password/`
     )
     expect(req.request.body).toEqual({
       documents: [10],
-      method: 'remove_password',
-      parameters: {
-        password: 'secret',
-        update_document: false,
-        include_metadata: false,
-        delete_original: true,
-        source_mode: 'explicit_selection',
-      },
+      password: 'secret',
+      update_document: false,
+      include_metadata: false,
+      delete_original: true,
+      source_mode: 'explicit_selection',
     })
     req.flush(true)
   })
@@ -1737,7 +1731,7 @@ describe('DocumentDetailComponent', () => {
 
     expect(errorSpy).toHaveBeenCalled()
     httpTestingController.expectNone(
-      `${environment.apiBaseUrl}documents/bulk_edit/`
+      `${environment.apiBaseUrl}documents/remove_password/`
     )
   })
 
@@ -1753,7 +1747,7 @@ describe('DocumentDetailComponent', () => {
       modal.componentInstance as PasswordRemovalConfirmDialogComponent
     dialog.confirm()
     const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/bulk_edit/`
+      `${environment.apiBaseUrl}documents/remove_password/`
     )
     req.error(new ErrorEvent('failed'))
 
@@ -1774,7 +1768,7 @@ describe('DocumentDetailComponent', () => {
       modal.componentInstance as PasswordRemovalConfirmDialogComponent
     dialog.confirm()
     const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/bulk_edit/`
+      `${environment.apiBaseUrl}documents/remove_password/`
     )
     req.flush(true)
 

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

@@ -1379,27 +1379,25 @@ export class DocumentDetailComponent
     modal.componentInstance.btnCaption = $localize`Proceed`
     modal.componentInstance.confirmClicked.subscribe(() => {
       modal.componentInstance.buttonsEnabled = false
-      this.documentsService
-        .bulkEdit([this.document.id], 'reprocess', {})
-        .subscribe({
-          next: () => {
-            this.toastService.showInfo(
-              $localize`Reprocess operation for "${this.document.title}" will begin in the background.`
-            )
-            if (modal) {
-              modal.close()
-            }
-          },
-          error: (error) => {
-            if (modal) {
-              modal.componentInstance.buttonsEnabled = true
-            }
-            this.toastService.showError(
-              $localize`Error executing operation`,
-              error
-            )
-          },
-        })
+      this.documentsService.reprocessDocuments([this.document.id]).subscribe({
+        next: () => {
+          this.toastService.showInfo(
+            $localize`Reprocess operation for "${this.document.title}" will begin in the background.`
+          )
+          if (modal) {
+            modal.close()
+          }
+        },
+        error: (error) => {
+          if (modal) {
+            modal.componentInstance.buttonsEnabled = true
+          }
+          this.toastService.showError(
+            $localize`Error executing operation`,
+            error
+          )
+        },
+      })
     })
   }
 
@@ -1766,7 +1764,7 @@ export class DocumentDetailComponent
       .subscribe(() => {
         modal.componentInstance.buttonsEnabled = false
         this.documentsService
-          .bulkEdit([sourceDocumentId], 'edit_pdf', {
+          .editPdfDocuments([sourceDocumentId], {
             operations: modal.componentInstance.getOperations(),
             delete_original: modal.componentInstance.deleteOriginal,
             update_document:
@@ -1824,7 +1822,7 @@ export class DocumentDetailComponent
         dialog.buttonsEnabled = false
         this.networkActive = true
         this.documentsService
-          .bulkEdit([sourceDocumentId], 'remove_password', {
+          .removePasswordDocuments([sourceDocumentId], {
             password: this.password,
             update_document: dialog.updateDocument,
             include_metadata: dialog.includeMetadata,

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

@@ -1,3 +1,4 @@
+import { DatePipe } from '@angular/common'
 import { provideHttpClient, withInterceptorsFromDi } from '@angular/common/http'
 import {
   HttpTestingController,
@@ -138,6 +139,7 @@ describe('BulkEditorComponent', () => {
           },
         },
         FilterPipe,
+        DatePipe,
         SettingsService,
         {
           provide: UserService,
@@ -849,13 +851,11 @@ describe('BulkEditorComponent', () => {
     expect(modal).not.toBeUndefined()
     modal.componentInstance.confirm()
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/bulk_edit/`
+      `${environment.apiBaseUrl}documents/delete/`
     )
     req.flush(true)
     expect(req.request.body).toEqual({
       documents: [3, 4],
-      method: 'delete',
-      parameters: {},
     })
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
@@ -868,7 +868,7 @@ describe('BulkEditorComponent', () => {
     fixture.detectChanges()
     component.applyDelete()
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/bulk_edit/`
+      `${environment.apiBaseUrl}documents/delete/`
     )
   })
 
@@ -944,13 +944,11 @@ describe('BulkEditorComponent', () => {
     expect(modal).not.toBeUndefined()
     modal.componentInstance.confirm()
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/bulk_edit/`
+      `${environment.apiBaseUrl}documents/reprocess/`
     )
     req.flush(true)
     expect(req.request.body).toEqual({
       documents: [3, 4],
-      method: 'reprocess',
-      parameters: {},
     })
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
@@ -979,13 +977,13 @@ describe('BulkEditorComponent', () => {
     modal.componentInstance.rotate()
     modal.componentInstance.confirm()
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/bulk_edit/`
+      `${environment.apiBaseUrl}documents/rotate/`
     )
     req.flush(true)
     expect(req.request.body).toEqual({
       documents: [3, 4],
-      method: 'rotate',
-      parameters: { degrees: 90 },
+      degrees: 90,
+      source_mode: 'latest_version',
     })
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
@@ -1021,13 +1019,12 @@ describe('BulkEditorComponent', () => {
     modal.componentInstance.metadataDocumentID = 3
     modal.componentInstance.confirm()
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/bulk_edit/`
+      `${environment.apiBaseUrl}documents/merge/`
     )
     req.flush(true)
     expect(req.request.body).toEqual({
       documents: [3, 4],
-      method: 'merge',
-      parameters: { metadata_document_id: 3 },
+      metadata_document_id: 3,
     })
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
@@ -1040,13 +1037,13 @@ describe('BulkEditorComponent', () => {
     modal.componentInstance.deleteOriginals = true
     modal.componentInstance.confirm()
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/bulk_edit/`
+      `${environment.apiBaseUrl}documents/merge/`
     )
     req.flush(true)
     expect(req.request.body).toEqual({
       documents: [3, 4],
-      method: 'merge',
-      parameters: { metadata_document_id: 3, delete_originals: true },
+      metadata_document_id: 3,
+      delete_originals: true,
     })
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
@@ -1061,13 +1058,13 @@ describe('BulkEditorComponent', () => {
     modal.componentInstance.archiveFallback = true
     modal.componentInstance.confirm()
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/bulk_edit/`
+      `${environment.apiBaseUrl}documents/merge/`
     )
     req.flush(true)
     expect(req.request.body).toEqual({
       documents: [3, 4],
-      method: 'merge',
-      parameters: { metadata_document_id: 3, archive_fallback: true },
+      metadata_document_id: 3,
+      archive_fallback: true,
     })
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`

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

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

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

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

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

@@ -42,6 +42,45 @@ export enum BulkEditSourceMode {
   EXPLICIT_SELECTION = 'explicit_selection',
 }
 
+export type DocumentBulkEditMethod =
+  | 'set_correspondent'
+  | 'set_document_type'
+  | 'set_storage_path'
+  | 'add_tag'
+  | 'remove_tag'
+  | 'modify_tags'
+  | 'modify_custom_fields'
+  | 'set_permissions'
+
+export interface MergeDocumentsRequest {
+  metadata_document_id?: number
+  delete_originals?: boolean
+  archive_fallback?: boolean
+  source_mode?: BulkEditSourceMode
+}
+
+export interface EditPdfOperation {
+  page: number
+  rotate?: number
+  doc?: number
+}
+
+export interface EditPdfDocumentsRequest {
+  operations: EditPdfOperation[]
+  delete_original?: boolean
+  update_document?: boolean
+  include_metadata?: boolean
+  source_mode?: BulkEditSourceMode
+}
+
+export interface RemovePasswordDocumentsRequest {
+  password: string
+  update_document?: boolean
+  delete_original?: boolean
+  include_metadata?: boolean
+  source_mode?: BulkEditSourceMode
+}
+
 @Injectable({
   providedIn: 'root',
 })
@@ -299,7 +338,7 @@ export class DocumentService extends AbstractPaperlessService<Document> {
     return this.http.get<DocumentMetadata>(url.toString())
   }
 
-  bulkEdit(ids: number[], method: string, args: any) {
+  bulkEdit(ids: number[], method: DocumentBulkEditMethod, args: any) {
     return this.http.post(this.getResourceUrl(null, 'bulk_edit'), {
       documents: ids,
       method: method,
@@ -307,6 +346,54 @@ export class DocumentService extends AbstractPaperlessService<Document> {
     })
   }
 
+  deleteDocuments(ids: number[]) {
+    return this.http.post(this.getResourceUrl(null, 'delete'), {
+      documents: ids,
+    })
+  }
+
+  reprocessDocuments(ids: number[]) {
+    return this.http.post(this.getResourceUrl(null, 'reprocess'), {
+      documents: ids,
+    })
+  }
+
+  rotateDocuments(
+    ids: number[],
+    degrees: number,
+    sourceMode: BulkEditSourceMode = BulkEditSourceMode.LATEST_VERSION
+  ) {
+    return this.http.post(this.getResourceUrl(null, 'rotate'), {
+      documents: ids,
+      degrees,
+      source_mode: sourceMode,
+    })
+  }
+
+  mergeDocuments(ids: number[], request: MergeDocumentsRequest = {}) {
+    return this.http.post(this.getResourceUrl(null, 'merge'), {
+      documents: ids,
+      ...request,
+    })
+  }
+
+  editPdfDocuments(ids: number[], request: EditPdfDocumentsRequest) {
+    return this.http.post(this.getResourceUrl(null, 'edit_pdf'), {
+      documents: ids,
+      ...request,
+    })
+  }
+
+  removePasswordDocuments(
+    ids: number[],
+    request: RemovePasswordDocumentsRequest
+  ) {
+    return this.http.post(this.getResourceUrl(null, 'remove_password'), {
+      documents: ids,
+      ...request,
+    })
+  }
+
   getSelectionData(ids: number[]): Observable<SelectionData> {
     return this.http.post<SelectionData>(
       this.getResourceUrl(null, 'selection_data'),

src-ui/src/app/utils/color.ts

@@ -62,7 +62,7 @@ export function hslToRgb(h, s, l) {
  * @return  Array           The HSL representation
  */
 export function rgbToHsl(r, g, b) {
-  ;(r /= 255), (g /= 255), (b /= 255)
+  ;((r /= 255), (g /= 255), (b /= 255))
   var max = Math.max(r, g, b),
     min = Math.min(r, g, b)
   var h,

src-ui/src/environments/environment.ts

@@ -5,7 +5,7 @@
 export const environment = {
   production: false,
   apiBaseUrl: 'http://localhost:8000/api/',
-  apiVersion: '9',
+  apiVersion: '10',
   appTitle: 'Paperless-ngx',
   tag: 'dev',
   version: 'DEVELOPMENT',

src/documents/consumer.py

@@ -51,29 +51,11 @@ from documents.templating.workflows import parse_w_workflow_placeholders
 from documents.utils import copy_basic_file_stats
 from documents.utils import copy_file_with_basic_stats
 from documents.utils import run_subprocess
-from paperless.parsers.text import TextDocumentParser
-from paperless.parsers.tika import TikaDocumentParser
 from paperless_mail.parsers import MailDocumentParser
 
 LOGGING_NAME: Final[str] = "paperless.consumer"
 
 
-def _parser_cleanup(parser: DocumentParser) -> None:
-    """
-    Call cleanup on a parser, handling the new-style context-manager parsers.
-
-    New-style parsers (e.g. TextDocumentParser) use __exit__ for teardown
-    instead of a cleanup() method.  This shim will be removed once all existing parsers
-    have switched to the new style and this consumer is updated to use it
-
-    TODO(stumpylog): Remove me in the future
-    """
-    if isinstance(parser, (TextDocumentParser, TikaDocumentParser)):
-        parser.__exit__(None, None, None)
-    else:
-        parser.cleanup()
-
-
 class WorkflowTriggerPlugin(
     NoCleanupPluginMixin,
     NoSetupPluginMixin,
@@ -449,12 +431,6 @@ class ConsumerPlugin(
             progress_callback=progress_callback,
         )
 
-        # New-style parsers use __enter__/__exit__ for resource management.
-        # _parser_cleanup (below) handles __exit__; call __enter__ here.
-        # TODO(stumpylog): Remove me in the future
-        if isinstance(document_parser, (TextDocumentParser, TikaDocumentParser)):
-            document_parser.__enter__()
-
         self.log.debug(f"Parser: {type(document_parser).__name__}")
 
         # Parse the document. This may take some time.
@@ -483,9 +459,6 @@ class ConsumerPlugin(
                     self.filename,
                     self.input_doc.mailrule_id,
                 )
-            elif isinstance(document_parser, (TextDocumentParser, TikaDocumentParser)):
-                # TODO(stumpylog): Remove me in the future
-                document_parser.parse(self.working_copy, mime_type)
             else:
                 document_parser.parse(self.working_copy, mime_type, self.filename)
 
@@ -496,15 +469,11 @@ class ConsumerPlugin(
                 ProgressStatusOptions.WORKING,
                 ConsumerStatusShortMessage.GENERATING_THUMBNAIL,
             )
-            if isinstance(document_parser, (TextDocumentParser, TikaDocumentParser)):
-                # TODO(stumpylog): Remove me in the future
-                thumbnail = document_parser.get_thumbnail(self.working_copy, mime_type)
-            else:
-                thumbnail = document_parser.get_thumbnail(
-                    self.working_copy,
-                    mime_type,
-                    self.filename,
-                )
+            thumbnail = document_parser.get_thumbnail(
+                self.working_copy,
+                mime_type,
+                self.filename,
+            )
 
             text = document_parser.get_text()
             date = document_parser.get_date()
@@ -521,7 +490,7 @@ class ConsumerPlugin(
             page_count = document_parser.get_page_count(self.working_copy, mime_type)
 
         except ParseError as e:
-            _parser_cleanup(document_parser)
+            document_parser.cleanup()
             if tempdir:
                 tempdir.cleanup()
             self._fail(
@@ -531,7 +500,7 @@ class ConsumerPlugin(
                 exception=e,
             )
         except Exception as e:
-            _parser_cleanup(document_parser)
+            document_parser.cleanup()
             if tempdir:
                 tempdir.cleanup()
             self._fail(
@@ -733,7 +702,7 @@ class ConsumerPlugin(
                 exception=e,
             )
         finally:
-            _parser_cleanup(document_parser)
+            document_parser.cleanup()
             tempdir.cleanup()
 
         self.run_post_consume_script(document)

src/documents/management/commands/document_thumbnails.py

@@ -30,7 +30,6 @@ def _process_document(doc_id: int) -> None:
         )
         shutil.move(thumb, document.thumbnail_path)
     finally:
-        # TODO(stumpylog): Cleanup once all parsers are handled
         parser.cleanup()
 
 

src/documents/matching.py

@@ -169,7 +169,7 @@ def match_storage_paths(document: Document, classifier: DocumentClassifier, user
 def matches(matching_model: MatchingModel, document: Document):
     search_flags = 0
 
-    document_content = document.content
+    document_content = document.get_effective_content() or ""
 
     # Check that match is not empty
     if not matching_model.match.strip():

src/documents/migrations/0003_remove_document_storage_type.py

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

src/documents/migrations/0003_workflowaction_order.py

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

src/documents/migrations/0004_workflowtrigger_filter_has_any_correspondents_and_more.py

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

src/documents/migrations/0005_alter_document_checksum_unique.py

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

src/documents/migrations/0006_document_content_length.py

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

src/documents/migrations/0007_sharelinkbundle.py

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

src/documents/migrations/0008_workflowaction_passwords_alter_workflowaction_type.py

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

src/documents/migrations/0009_alter_document_content_length.py

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

src/documents/migrations/0010_optimize_integer_field_sizes.py

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

src/documents/migrations/0011_alter_workflowaction_type.py

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

src/documents/migrations/0012_document_root_document.py

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

src/documents/migrations/0013_alter_paperlesstask_task_name.py

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

src/documents/migrations/0014_savedview_visibility_to_ui_settings.py

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

src/documents/migrations/0015_document_version_index_and_more.py

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

src/documents/models.py

@@ -361,6 +361,42 @@ class Document(SoftDeleteModel, ModelWithOwner):  # type: ignore[django-manager-
             res += f" {self.title}"
         return res
 
+    def get_effective_content(self) -> str | None:
+        """
+        Returns the effective content for the document.
+
+        For root documents, this is the latest version's content when available.
+        For version documents, this is always the document's own content.
+        If the queryset already annotated ``effective_content``, that value is used.
+        """
+        if hasattr(self, "effective_content"):
+            return getattr(self, "effective_content")
+
+        if self.root_document_id is not None or self.pk is None:
+            return self.content
+
+        prefetched_cache = getattr(self, "_prefetched_objects_cache", None)
+        prefetched_versions = (
+            prefetched_cache.get("versions")
+            if isinstance(prefetched_cache, dict)
+            else None
+        )
+        if prefetched_versions:
+            latest_prefetched = max(prefetched_versions, key=lambda doc: doc.id)
+            return latest_prefetched.content
+
+        latest_version_content = (
+            Document.objects.filter(root_document=self)
+            .order_by("-id")
+            .values_list("content", flat=True)
+            .first()
+        )
+        return (
+            latest_version_content
+            if latest_version_content is not None
+            else self.content
+        )
+
     @property
     def suggestion_content(self):
         """
@@ -373,15 +409,21 @@ class Document(SoftDeleteModel, ModelWithOwner):  # type: ignore[django-manager-
         This improves processing speed for large documents while keeping
         enough context for accurate suggestions.
         """
-        if not self.content or len(self.content) <= 1200000:
-            return self.content
+        effective_content = self.get_effective_content()
+        if not effective_content or len(effective_content) <= 1200000:
+            return effective_content
         else:
             # Use 80% from the start and 20% from the end
             # to preserve both opening and closing context.
             head_len = 800000
             tail_len = 200000
 
-            return " ".join((self.content[:head_len], self.content[-tail_len:]))
+            return " ".join(
+                (
+                    effective_content[:head_len],
+                    effective_content[-tail_len:],
+                ),
+            )
 
     @property
     def source_path(self) -> Path:

src/documents/serialisers.py

@@ -1540,11 +1540,124 @@ class DocumentListSerializer(serializers.Serializer):
         return documents
 
 
+class SourceModeValidationMixin:
+    def validate_source_mode(self, source_mode: str) -> str:
+        if source_mode not in bulk_edit.SourceModeChoices.__dict__.values():
+            raise serializers.ValidationError("Invalid source_mode")
+        return source_mode
+
+
+class RotateDocumentsSerializer(DocumentListSerializer, SourceModeValidationMixin):
+    degrees = serializers.IntegerField(required=True)
+    source_mode = serializers.CharField(
+        required=False,
+        default=bulk_edit.SourceModeChoices.LATEST_VERSION,
+    )
+
+
+class MergeDocumentsSerializer(DocumentListSerializer, SourceModeValidationMixin):
+    metadata_document_id = serializers.IntegerField(
+        required=False,
+        allow_null=True,
+    )
+    delete_originals = serializers.BooleanField(required=False, default=False)
+    archive_fallback = serializers.BooleanField(required=False, default=False)
+    source_mode = serializers.CharField(
+        required=False,
+        default=bulk_edit.SourceModeChoices.LATEST_VERSION,
+    )
+
+
+class EditPdfDocumentsSerializer(DocumentListSerializer, SourceModeValidationMixin):
+    operations = serializers.ListField(required=True)
+    delete_original = serializers.BooleanField(required=False, default=False)
+    update_document = serializers.BooleanField(required=False, default=False)
+    include_metadata = serializers.BooleanField(required=False, default=True)
+    source_mode = serializers.CharField(
+        required=False,
+        default=bulk_edit.SourceModeChoices.LATEST_VERSION,
+    )
+
+    def validate(self, attrs):
+        documents = attrs["documents"]
+        if len(documents) > 1:
+            raise serializers.ValidationError(
+                "Edit PDF method only supports one document",
+            )
+
+        operations = attrs["operations"]
+        if not isinstance(operations, list):
+            raise serializers.ValidationError("operations must be a list")
+
+        for op in operations:
+            if not isinstance(op, dict):
+                raise serializers.ValidationError("invalid operation entry")
+            if "page" not in op or not isinstance(op["page"], int):
+                raise serializers.ValidationError("page must be an integer")
+            if "rotate" in op and not isinstance(op["rotate"], int):
+                raise serializers.ValidationError("rotate must be an integer")
+            if "doc" in op and not isinstance(op["doc"], int):
+                raise serializers.ValidationError("doc must be an integer")
+
+        if attrs["update_document"]:
+            max_idx = max(op.get("doc", 0) for op in operations)
+            if max_idx > 0:
+                raise serializers.ValidationError(
+                    "update_document only allowed with a single output document",
+                )
+
+        doc = Document.objects.get(id=documents[0])
+        if doc.page_count:
+            for op in operations:
+                if op["page"] < 1 or op["page"] > doc.page_count:
+                    raise serializers.ValidationError(
+                        f"Page {op['page']} is out of bounds for document with {doc.page_count} pages.",
+                    )
+        return attrs
+
+
+class RemovePasswordDocumentsSerializer(
+    DocumentListSerializer,
+    SourceModeValidationMixin,
+):
+    password = serializers.CharField(required=True)
+    update_document = serializers.BooleanField(required=False, default=False)
+    delete_original = serializers.BooleanField(required=False, default=False)
+    include_metadata = serializers.BooleanField(required=False, default=True)
+    source_mode = serializers.CharField(
+        required=False,
+        default=bulk_edit.SourceModeChoices.LATEST_VERSION,
+    )
+
+
+class DeleteDocumentsSerializer(DocumentListSerializer):
+    pass
+
+
+class ReprocessDocumentsSerializer(DocumentListSerializer):
+    pass
+
+
 class BulkEditSerializer(
     SerializerWithPerms,
     DocumentListSerializer,
     SetPermissionsMixin,
+    SourceModeValidationMixin,
 ):
+    # TODO: remove this and related backwards compatibility code when API v9 is dropped
+    # split, delete_pages can be removed entirely
+    MOVED_DOCUMENT_ACTION_ENDPOINTS = {
+        "delete": "/api/documents/delete/",
+        "reprocess": "/api/documents/reprocess/",
+        "rotate": "/api/documents/rotate/",
+        "merge": "/api/documents/merge/",
+        "edit_pdf": "/api/documents/edit_pdf/",
+        "remove_password": "/api/documents/remove_password/",
+        "split": "/api/documents/edit_pdf/",
+        "delete_pages": "/api/documents/edit_pdf/",
+    }
+    LEGACY_DOCUMENT_ACTION_METHODS = tuple(MOVED_DOCUMENT_ACTION_ENDPOINTS.keys())
+
     method = serializers.ChoiceField(
         choices=[
             "set_correspondent",
@@ -1554,15 +1667,8 @@ class BulkEditSerializer(
             "remove_tag",
             "modify_tags",
             "modify_custom_fields",
-            "delete",
-            "reprocess",
             "set_permissions",
-            "rotate",
-            "merge",
-            "split",
-            "delete_pages",
-            "edit_pdf",
-            "remove_password",
+            *LEGACY_DOCUMENT_ACTION_METHODS,
         ],
         label="Method",
         write_only=True,
@@ -1640,8 +1746,7 @@ class BulkEditSerializer(
             return bulk_edit.edit_pdf
         elif method == "remove_password":
             return bulk_edit.remove_password
-        else:  # pragma: no cover
-            # This will never happen as it is handled by the ChoiceField
+        else:
             raise serializers.ValidationError("Unsupported method.")
 
     def _validate_parameters_tags(self, parameters) -> None:
@@ -1751,9 +1856,7 @@ class BulkEditSerializer(
             "source_mode",
             bulk_edit.SourceModeChoices.LATEST_VERSION,
         )
-        if source_mode not in bulk_edit.SourceModeChoices.__dict__.values():
-            raise serializers.ValidationError("Invalid source_mode")
-        parameters["source_mode"] = source_mode
+        parameters["source_mode"] = self.validate_source_mode(source_mode)
 
     def _validate_parameters_split(self, parameters) -> None:
         if "pages" not in parameters:

src/documents/tasks.py

@@ -399,7 +399,6 @@ def update_document_content_maybe_archive_file(document_id) -> None:
             f"Error while parsing document {document} (ID: {document_id})",
         )
     finally:
-        # TODO(stumpylog): Cleanup once all parsers are handled
         parser.cleanup()
 
 

src/documents/tests/test_api_app_config.py

@@ -5,6 +5,7 @@ from unittest.mock import patch
 
 from django.contrib.auth.models import User
 from django.core.files.uploadedfile import SimpleUploadedFile
+from django.test import override_settings
 from rest_framework import status
 from rest_framework.test import APITestCase
 
@@ -693,3 +694,17 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
                 content_type="application/json",
             )
             mock_update.assert_called_once()
+
+    @override_settings(LLM_ALLOW_INTERNAL_ENDPOINTS=False)
+    def test_update_llm_endpoint_blocks_internal_endpoint_when_disallowed(self) -> None:
+        response = self.client.patch(
+            f"{self.ENDPOINT}1/",
+            json.dumps(
+                {
+                    "llm_endpoint": "http://127.0.0.1:11434",
+                },
+            ),
+            content_type="application/json",
+        )
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertIn("non-public address", str(response.data).lower())

src/documents/tests/test_api_bulk_edit.py

@@ -422,6 +422,34 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(args[0], [self.doc1.id])
         self.assertEqual(len(kwargs), 0)
 
+    @mock.patch("documents.views.bulk_edit.delete")
+    def test_delete_documents_endpoint(self, m) -> None:
+        self.setup_mock(m, "delete")
+        response = self.client.post(
+            "/api/documents/delete/",
+            json.dumps({"documents": [self.doc1.id]}),
+            content_type="application/json",
+        )
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        m.assert_called_once()
+        args, kwargs = m.call_args
+        self.assertEqual(args[0], [self.doc1.id])
+        self.assertEqual(len(kwargs), 0)
+
+    @mock.patch("documents.views.bulk_edit.reprocess")
+    def test_reprocess_documents_endpoint(self, m) -> None:
+        self.setup_mock(m, "reprocess")
+        response = self.client.post(
+            "/api/documents/reprocess/",
+            json.dumps({"documents": [self.doc1.id]}),
+            content_type="application/json",
+        )
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        m.assert_called_once()
+        args, kwargs = m.call_args
+        self.assertEqual(args[0], [self.doc1.id])
+        self.assertEqual(len(kwargs), 0)
+
     @mock.patch("documents.serialisers.bulk_edit.set_storage_path")
     def test_api_set_storage_path(self, m) -> None:
         """
@@ -877,7 +905,7 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(kwargs["merge"], True)
 
     @mock.patch("documents.serialisers.bulk_edit.set_storage_path")
-    @mock.patch("documents.serialisers.bulk_edit.merge")
+    @mock.patch("documents.views.bulk_edit.merge")
     def test_insufficient_global_perms(self, mock_merge, mock_set_storage) -> None:
         """
         GIVEN:
@@ -912,12 +940,11 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         mock_set_storage.assert_not_called()
 
         response = self.client.post(
-            "/api/documents/bulk_edit/",
+            "/api/documents/merge/",
             json.dumps(
                 {
                     "documents": [self.doc1.id],
-                    "method": "merge",
-                    "parameters": {"metadata_document_id": self.doc1.id},
+                    "metadata_document_id": self.doc1.id,
                 },
             ),
             content_type="application/json",
@@ -927,15 +954,12 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         mock_merge.assert_not_called()
 
         response = self.client.post(
-            "/api/documents/bulk_edit/",
+            "/api/documents/merge/",
             json.dumps(
                 {
                     "documents": [self.doc1.id],
-                    "method": "merge",
-                    "parameters": {
-                        "metadata_document_id": self.doc1.id,
-                        "delete_originals": True,
-                    },
+                    "metadata_document_id": self.doc1.id,
+                    "delete_originals": True,
                 },
             ),
             content_type="application/json",
@@ -1052,85 +1076,57 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
 
         m.assert_called_once()
 
-    @mock.patch("documents.serialisers.bulk_edit.rotate")
+    @mock.patch("documents.views.bulk_edit.rotate")
     def test_rotate(self, m) -> None:
         self.setup_mock(m, "rotate")
         response = self.client.post(
-            "/api/documents/bulk_edit/",
+            "/api/documents/rotate/",
             json.dumps(
                 {
                     "documents": [self.doc2.id, self.doc3.id],
-                    "method": "rotate",
-                    "parameters": {"degrees": 90},
+                    "degrees": 90,
                 },
             ),
             content_type="application/json",
         )
 
         self.assertEqual(response.status_code, status.HTTP_200_OK)
-
         m.assert_called_once()
         args, kwargs = m.call_args
         self.assertCountEqual(args[0], [self.doc2.id, self.doc3.id])
         self.assertEqual(kwargs["degrees"], 90)
-
-    @mock.patch("documents.serialisers.bulk_edit.rotate")
-    def test_rotate_invalid_params(self, m) -> None:
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id, self.doc3.id],
-                    "method": "rotate",
-                    "parameters": {"degrees": "foo"},
-                },
-            ),
-            content_type="application/json",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id, self.doc3.id],
-                    "method": "rotate",
-                    "parameters": {"degrees": 90.5},
-                },
-            ),
-            content_type="application/json",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-
-        m.assert_not_called()
-
-    @mock.patch("documents.serialisers.bulk_edit.merge")
-    def test_merge(self, m) -> None:
-        self.setup_mock(m, "merge")
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id, self.doc3.id],
-                    "method": "merge",
-                    "parameters": {"metadata_document_id": self.doc3.id},
-                },
-            ),
-            content_type="application/json",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_200_OK)
-
-        m.assert_called_once()
-        args, kwargs = m.call_args
-        self.assertCountEqual(args[0], [self.doc2.id, self.doc3.id])
-        self.assertEqual(kwargs["metadata_document_id"], self.doc3.id)
+        self.assertEqual(kwargs["source_mode"], "latest_version")
         self.assertEqual(kwargs["user"], self.user)
 
-    @mock.patch("documents.serialisers.bulk_edit.merge")
-    def test_merge_and_delete_insufficient_permissions(self, m) -> None:
+    @mock.patch("documents.views.bulk_edit.rotate")
+    def test_rotate_invalid_params(self, m) -> None:
+        response = self.client.post(
+            "/api/documents/rotate/",
+            json.dumps(
+                {
+                    "documents": [self.doc2.id, self.doc3.id],
+                    "degrees": "foo",
+                },
+            ),
+            content_type="application/json",
+        )
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+
+        response = self.client.post(
+            "/api/documents/rotate/",
+            json.dumps(
+                {
+                    "documents": [self.doc2.id, self.doc3.id],
+                    "degrees": 90.5,
+                },
+            ),
+            content_type="application/json",
+        )
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        m.assert_not_called()
+
+    @mock.patch("documents.views.bulk_edit.rotate")
+    def test_rotate_insufficient_permissions(self, m) -> None:
         self.doc1.owner = User.objects.get(username="temp_admin")
         self.doc1.save()
         user1 = User.objects.create(username="user1")
@@ -1138,17 +1134,13 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         user1.save()
         self.client.force_authenticate(user=user1)
 
-        self.setup_mock(m, "merge")
+        self.setup_mock(m, "rotate")
         response = self.client.post(
-            "/api/documents/bulk_edit/",
+            "/api/documents/rotate/",
             json.dumps(
                 {
                     "documents": [self.doc1.id, self.doc2.id],
-                    "method": "merge",
-                    "parameters": {
-                        "metadata_document_id": self.doc2.id,
-                        "delete_originals": True,
-                    },
+                    "degrees": 90,
                 },
             ),
             content_type="application/json",
@@ -1159,15 +1151,11 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(response.content, b"Insufficient permissions")
 
         response = self.client.post(
-            "/api/documents/bulk_edit/",
+            "/api/documents/rotate/",
             json.dumps(
                 {
                     "documents": [self.doc2.id, self.doc3.id],
-                    "method": "merge",
-                    "parameters": {
-                        "metadata_document_id": self.doc2.id,
-                        "delete_originals": True,
-                    },
+                    "degrees": 90,
                 },
             ),
             content_type="application/json",
@@ -1176,27 +1164,78 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_200_OK)
         m.assert_called_once()
 
-    @mock.patch("documents.serialisers.bulk_edit.merge")
-    def test_merge_invalid_parameters(self, m) -> None:
-        """
-        GIVEN:
-            - API data for merging documents is called
-            - The parameters are invalid
-        WHEN:
-            - API is called
-        THEN:
-            - The API fails with a correct error code
-        """
+    @mock.patch("documents.views.bulk_edit.merge")
+    def test_merge(self, m) -> None:
         self.setup_mock(m, "merge")
         response = self.client.post(
-            "/api/documents/bulk_edit/",
+            "/api/documents/merge/",
+            json.dumps(
+                {
+                    "documents": [self.doc2.id, self.doc3.id],
+                    "metadata_document_id": self.doc3.id,
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        m.assert_called_once()
+        args, kwargs = m.call_args
+        self.assertCountEqual(args[0], [self.doc2.id, self.doc3.id])
+        self.assertEqual(kwargs["metadata_document_id"], self.doc3.id)
+        self.assertEqual(kwargs["source_mode"], "latest_version")
+        self.assertEqual(kwargs["user"], self.user)
+
+    @mock.patch("documents.views.bulk_edit.merge")
+    def test_merge_and_delete_insufficient_permissions(self, m) -> None:
+        self.doc1.owner = User.objects.get(username="temp_admin")
+        self.doc1.save()
+        user1 = User.objects.create(username="user1")
+        user1.user_permissions.add(*Permission.objects.all())
+        user1.save()
+        self.client.force_authenticate(user=user1)
+
+        self.setup_mock(m, "merge")
+        response = self.client.post(
+            "/api/documents/merge/",
             json.dumps(
                 {
                     "documents": [self.doc1.id, self.doc2.id],
-                    "method": "merge",
-                    "parameters": {
-                        "delete_originals": "not_boolean",
-                    },
+                    "metadata_document_id": self.doc2.id,
+                    "delete_originals": True,
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_403_FORBIDDEN)
+        m.assert_not_called()
+        self.assertEqual(response.content, b"Insufficient permissions")
+
+        response = self.client.post(
+            "/api/documents/merge/",
+            json.dumps(
+                {
+                    "documents": [self.doc2.id, self.doc3.id],
+                    "metadata_document_id": self.doc2.id,
+                    "delete_originals": True,
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        m.assert_called_once()
+
+    @mock.patch("documents.views.bulk_edit.merge")
+    def test_merge_invalid_parameters(self, m) -> None:
+        self.setup_mock(m, "merge")
+        response = self.client.post(
+            "/api/documents/merge/",
+            json.dumps(
+                {
+                    "documents": [self.doc1.id, self.doc2.id],
+                    "delete_originals": "not_boolean",
                 },
             ),
             content_type="application/json",
@@ -1205,207 +1244,67 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
         m.assert_not_called()
 
-    @mock.patch("documents.serialisers.bulk_edit.split")
-    def test_split(self, m) -> None:
-        self.setup_mock(m, "split")
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "method": "split",
-                    "parameters": {"pages": "1,2-4,5-6,7"},
-                },
-            ),
-            content_type="application/json",
-        )
+    def test_bulk_edit_allows_legacy_file_methods_with_warning(self) -> None:
+        method_payloads = {
+            "delete": {},
+            "reprocess": {},
+            "rotate": {"degrees": 90},
+            "merge": {"metadata_document_id": self.doc2.id},
+            "edit_pdf": {"operations": [{"page": 1}]},
+            "remove_password": {"password": "secret"},
+            "split": {"pages": "1,2-4"},
+            "delete_pages": {"pages": [1, 2]},
+        }
 
-        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        for version in (9, 10):
+            for method, parameters in method_payloads.items():
+                with self.subTest(method=method, version=version):
+                    with mock.patch(
+                        f"documents.views.bulk_edit.{method}",
+                    ) as mocked_method:
+                        self.setup_mock(mocked_method, method)
+                        with self.assertLogs("paperless.api", level="WARNING") as logs:
+                            response = self.client.post(
+                                "/api/documents/bulk_edit/",
+                                json.dumps(
+                                    {
+                                        "documents": [self.doc2.id],
+                                        "method": method,
+                                        "parameters": parameters,
+                                    },
+                                ),
+                                content_type="application/json",
+                                headers={
+                                    "Accept": f"application/json; version={version}",
+                                },
+                            )
 
-        m.assert_called_once()
-        args, kwargs = m.call_args
-        self.assertCountEqual(args[0], [self.doc2.id])
-        self.assertEqual(kwargs["pages"], [[1], [2, 3, 4], [5, 6], [7]])
-        self.assertEqual(kwargs["user"], self.user)
+                        self.assertEqual(response.status_code, status.HTTP_200_OK)
+                        mocked_method.assert_called_once()
+                        self.assertTrue(
+                            any(
+                                "Deprecated bulk_edit method" in entry
+                                and f"'{method}'" in entry
+                                for entry in logs.output
+                            ),
+                        )
 
-    def test_split_invalid_params(self) -> None:
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "method": "split",
-                    "parameters": {},  # pages not specified
-                },
-            ),
-            content_type="application/json",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(b"pages not specified", response.content)
-
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "method": "split",
-                    "parameters": {"pages": "1:7"},  # wrong format
-                },
-            ),
-            content_type="application/json",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(b"invalid pages specified", response.content)
-
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [
-                        self.doc1.id,
-                        self.doc2.id,
-                    ],  # only one document supported
-                    "method": "split",
-                    "parameters": {"pages": "1-2,3-7"},  # wrong format
-                },
-            ),
-            content_type="application/json",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(b"Split method only supports one document", response.content)
-
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "method": "split",
-                    "parameters": {
-                        "pages": "1",
-                        "delete_originals": "notabool",
-                    },  # not a bool
-                },
-            ),
-            content_type="application/json",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(b"delete_originals must be a boolean", response.content)
-
-    @mock.patch("documents.serialisers.bulk_edit.delete_pages")
-    def test_delete_pages(self, m) -> None:
-        self.setup_mock(m, "delete_pages")
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "method": "delete_pages",
-                    "parameters": {"pages": [1, 2, 3, 4]},
-                },
-            ),
-            content_type="application/json",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_200_OK)
-
-        m.assert_called_once()
-        args, kwargs = m.call_args
-        self.assertCountEqual(args[0], [self.doc2.id])
-        self.assertEqual(kwargs["pages"], [1, 2, 3, 4])
-
-    def test_delete_pages_invalid_params(self) -> None:
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [
-                        self.doc1.id,
-                        self.doc2.id,
-                    ],  # only one document supported
-                    "method": "delete_pages",
-                    "parameters": {
-                        "pages": [1, 2, 3, 4],
-                    },
-                },
-            ),
-            content_type="application/json",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(
-            b"Delete pages method only supports one document",
-            response.content,
-        )
-
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "method": "delete_pages",
-                    "parameters": {},  # pages not specified
-                },
-            ),
-            content_type="application/json",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(b"pages not specified", response.content)
-
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "method": "delete_pages",
-                    "parameters": {"pages": "1-3"},  # not a list
-                },
-            ),
-            content_type="application/json",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(b"pages must be a list", response.content)
-
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "method": "delete_pages",
-                    "parameters": {"pages": ["1-3"]},  # not ints
-                },
-            ),
-            content_type="application/json",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(b"pages must be a list of integers", response.content)
-
-    @mock.patch("documents.serialisers.bulk_edit.edit_pdf")
+    @mock.patch("documents.views.bulk_edit.edit_pdf")
     def test_edit_pdf(self, m) -> None:
         self.setup_mock(m, "edit_pdf")
         response = self.client.post(
-            "/api/documents/bulk_edit/",
+            "/api/documents/edit_pdf/",
             json.dumps(
                 {
                     "documents": [self.doc2.id],
-                    "method": "edit_pdf",
-                    "parameters": {
-                        "operations": [{"page": 1}],
-                        "source_mode": "explicit_selection",
-                    },
+                    "operations": [{"page": 1}],
+                    "source_mode": "explicit_selection",
                 },
             ),
             content_type="application/json",
         )
 
         self.assertEqual(response.status_code, status.HTTP_200_OK)
-
         m.assert_called_once()
         args, kwargs = m.call_args
         self.assertCountEqual(args[0], [self.doc2.id])
@@ -1414,14 +1313,12 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(kwargs["user"], self.user)
 
     def test_edit_pdf_invalid_params(self) -> None:
-        # multiple documents
         response = self.client.post(
-            "/api/documents/bulk_edit/",
+            "/api/documents/edit_pdf/",
             json.dumps(
                 {
                     "documents": [self.doc2.id, self.doc3.id],
-                    "method": "edit_pdf",
-                    "parameters": {"operations": [{"page": 1}]},
+                    "operations": [{"page": 1}],
                 },
             ),
             content_type="application/json",
@@ -1429,44 +1326,25 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
         self.assertIn(b"Edit PDF method only supports one document", response.content)
 
-        # no operations specified
         response = self.client.post(
-            "/api/documents/bulk_edit/",
+            "/api/documents/edit_pdf/",
             json.dumps(
                 {
                     "documents": [self.doc2.id],
-                    "method": "edit_pdf",
-                    "parameters": {},
+                    "operations": "not_a_list",
                 },
             ),
             content_type="application/json",
         )
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(b"operations not specified", response.content)
+        self.assertIn(b"Expected a list of items", response.content)
 
-        # operations not a list
         response = self.client.post(
-            "/api/documents/bulk_edit/",
+            "/api/documents/edit_pdf/",
             json.dumps(
                 {
                     "documents": [self.doc2.id],
-                    "method": "edit_pdf",
-                    "parameters": {"operations": "not_a_list"},
-                },
-            ),
-            content_type="application/json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(b"operations must be a list", response.content)
-
-        # invalid operation
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "method": "edit_pdf",
-                    "parameters": {"operations": ["invalid_operation"]},
+                    "operations": ["invalid_operation"],
                 },
             ),
             content_type="application/json",
@@ -1474,14 +1352,12 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
         self.assertIn(b"invalid operation entry", response.content)
 
-        # page not an int
         response = self.client.post(
-            "/api/documents/bulk_edit/",
+            "/api/documents/edit_pdf/",
             json.dumps(
                 {
                     "documents": [self.doc2.id],
-                    "method": "edit_pdf",
-                    "parameters": {"operations": [{"page": "not_an_int"}]},
+                    "operations": [{"page": "not_an_int"}],
                 },
             ),
             content_type="application/json",
@@ -1489,14 +1365,12 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
         self.assertIn(b"page must be an integer", response.content)
 
-        # rotate not an int
         response = self.client.post(
-            "/api/documents/bulk_edit/",
+            "/api/documents/edit_pdf/",
             json.dumps(
                 {
                     "documents": [self.doc2.id],
-                    "method": "edit_pdf",
-                    "parameters": {"operations": [{"page": 1, "rotate": "not_an_int"}]},
+                    "operations": [{"page": 1, "rotate": "not_an_int"}],
                 },
             ),
             content_type="application/json",
@@ -1504,14 +1378,12 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
         self.assertIn(b"rotate must be an integer", response.content)
 
-        # doc not an int
         response = self.client.post(
-            "/api/documents/bulk_edit/",
+            "/api/documents/edit_pdf/",
             json.dumps(
                 {
                     "documents": [self.doc2.id],
-                    "method": "edit_pdf",
-                    "parameters": {"operations": [{"page": 1, "doc": "not_an_int"}]},
+                    "operations": [{"page": 1, "doc": "not_an_int"}],
                 },
             ),
             content_type="application/json",
@@ -1519,53 +1391,13 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
         self.assertIn(b"doc must be an integer", response.content)
 
-        # update_document not a boolean
         response = self.client.post(
-            "/api/documents/bulk_edit/",
+            "/api/documents/edit_pdf/",
             json.dumps(
                 {
                     "documents": [self.doc2.id],
-                    "method": "edit_pdf",
-                    "parameters": {
-                        "update_document": "not_a_bool",
-                        "operations": [{"page": 1}],
-                    },
-                },
-            ),
-            content_type="application/json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(b"update_document must be a boolean", response.content)
-
-        # include_metadata not a boolean
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "method": "edit_pdf",
-                    "parameters": {
-                        "include_metadata": "not_a_bool",
-                        "operations": [{"page": 1}],
-                    },
-                },
-            ),
-            content_type="application/json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(b"include_metadata must be a boolean", response.content)
-
-        # update_document True but output would be multiple documents
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "method": "edit_pdf",
-                    "parameters": {
-                        "update_document": True,
-                        "operations": [{"page": 1, "doc": 1}, {"page": 2, "doc": 2}],
-                    },
+                    "update_document": True,
+                    "operations": [{"page": 1, "doc": 1}, {"page": 2, "doc": 2}],
                 },
             ),
             content_type="application/json",
@@ -1576,17 +1408,13 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
             response.content,
         )
 
-        # invalid source mode
         response = self.client.post(
-            "/api/documents/bulk_edit/",
+            "/api/documents/edit_pdf/",
             json.dumps(
                 {
                     "documents": [self.doc2.id],
-                    "method": "edit_pdf",
-                    "parameters": {
-                        "operations": [{"page": 1}],
-                        "source_mode": "not_a_mode",
-                    },
+                    "operations": [{"page": 1}],
+                    "source_mode": "not_a_mode",
                 },
             ),
             content_type="application/json",
@@ -1594,42 +1422,70 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
         self.assertIn(b"Invalid source_mode", response.content)
 
-    @mock.patch("documents.serialisers.bulk_edit.edit_pdf")
+    @mock.patch("documents.views.bulk_edit.edit_pdf")
     def test_edit_pdf_page_out_of_bounds(self, m) -> None:
-        """
-        GIVEN:
-            - API data for editing PDF is called
-            - The page number is out of bounds
-        WHEN:
-            - API is called
-        THEN:
-            - The API fails with a correct error code
-        """
         self.setup_mock(m, "edit_pdf")
         response = self.client.post(
-            "/api/documents/bulk_edit/",
+            "/api/documents/edit_pdf/",
             json.dumps(
                 {
                     "documents": [self.doc2.id],
-                    "method": "edit_pdf",
-                    "parameters": {"operations": [{"page": 99}]},
+                    "operations": [{"page": 99}],
                 },
             ),
             content_type="application/json",
         )
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
         self.assertIn(b"out of bounds", response.content)
+        m.assert_not_called()
 
-    @mock.patch("documents.serialisers.bulk_edit.remove_password")
-    def test_remove_password(self, m) -> None:
-        self.setup_mock(m, "remove_password")
+    @mock.patch("documents.views.bulk_edit.edit_pdf")
+    def test_edit_pdf_insufficient_permissions(self, m) -> None:
+        self.doc1.owner = User.objects.get(username="temp_admin")
+        self.doc1.save()
+        user1 = User.objects.create(username="user1")
+        user1.user_permissions.add(*Permission.objects.all())
+        user1.save()
+        self.client.force_authenticate(user=user1)
+
+        self.setup_mock(m, "edit_pdf")
         response = self.client.post(
-            "/api/documents/bulk_edit/",
+            "/api/documents/edit_pdf/",
+            json.dumps(
+                {
+                    "documents": [self.doc1.id],
+                    "operations": [{"page": 1}],
+                },
+            ),
+            content_type="application/json",
+        )
+        self.assertEqual(response.status_code, status.HTTP_403_FORBIDDEN)
+        m.assert_not_called()
+        self.assertEqual(response.content, b"Insufficient permissions")
+
+        response = self.client.post(
+            "/api/documents/edit_pdf/",
             json.dumps(
                 {
                     "documents": [self.doc2.id],
-                    "method": "remove_password",
-                    "parameters": {"password": "secret", "update_document": True},
+                    "operations": [{"page": 1}],
+                },
+            ),
+            content_type="application/json",
+        )
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        m.assert_called_once()
+
+    @mock.patch("documents.views.bulk_edit.remove_password")
+    def test_remove_password(self, m) -> None:
+        self.setup_mock(m, "remove_password")
+        response = self.client.post(
+            "/api/documents/remove_password/",
+            json.dumps(
+                {
+                    "documents": [self.doc2.id],
+                    "password": "secret",
+                    "update_document": True,
                 },
             ),
             content_type="application/json",
@@ -1641,36 +1497,69 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertCountEqual(args[0], [self.doc2.id])
         self.assertEqual(kwargs["password"], "secret")
         self.assertTrue(kwargs["update_document"])
+        self.assertEqual(kwargs["source_mode"], "latest_version")
         self.assertEqual(kwargs["user"], self.user)
 
     def test_remove_password_invalid_params(self) -> None:
         response = self.client.post(
-            "/api/documents/bulk_edit/",
+            "/api/documents/remove_password/",
             json.dumps(
                 {
                     "documents": [self.doc2.id],
-                    "method": "remove_password",
-                    "parameters": {},
                 },
             ),
             content_type="application/json",
         )
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(b"password not specified", response.content)
 
         response = self.client.post(
-            "/api/documents/bulk_edit/",
+            "/api/documents/remove_password/",
             json.dumps(
                 {
                     "documents": [self.doc2.id],
-                    "method": "remove_password",
-                    "parameters": {"password": 123},
+                    "password": 123,
                 },
             ),
             content_type="application/json",
         )
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(b"password must be a string", response.content)
+
+    @mock.patch("documents.views.bulk_edit.remove_password")
+    def test_remove_password_insufficient_permissions(self, m) -> None:
+        self.doc1.owner = User.objects.get(username="temp_admin")
+        self.doc1.save()
+        user1 = User.objects.create(username="user1")
+        user1.user_permissions.add(*Permission.objects.all())
+        user1.save()
+        self.client.force_authenticate(user=user1)
+
+        self.setup_mock(m, "remove_password")
+        response = self.client.post(
+            "/api/documents/remove_password/",
+            json.dumps(
+                {
+                    "documents": [self.doc1.id],
+                    "password": "secret",
+                },
+            ),
+            content_type="application/json",
+        )
+        self.assertEqual(response.status_code, status.HTTP_403_FORBIDDEN)
+        m.assert_not_called()
+        self.assertEqual(response.content, b"Insufficient permissions")
+
+        response = self.client.post(
+            "/api/documents/remove_password/",
+            json.dumps(
+                {
+                    "documents": [self.doc2.id],
+                    "password": "secret",
+                },
+            ),
+            content_type="application/json",
+        )
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        m.assert_called_once()
 
     @override_settings(AUDIT_LOG_ENABLED=True)
     def test_bulk_edit_audit_log_enabled_simple_field(self) -> None:

src/documents/tests/test_api_schema.py

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

src/documents/tests/test_document_model.py

@@ -156,6 +156,46 @@ class TestDocument(TestCase):
         )
         self.assertEqual(doc.get_public_filename(), "2020-12-25 test")
 
+    def test_suggestion_content_uses_latest_version_content_for_root_documents(
+        self,
+    ) -> None:
+        root = Document.objects.create(
+            title="root",
+            checksum="root",
+            mime_type="application/pdf",
+            content="outdated root content",
+        )
+        version = Document.objects.create(
+            title="v1",
+            checksum="v1",
+            mime_type="application/pdf",
+            root_document=root,
+            content="latest version content",
+        )
+
+        self.assertEqual(root.suggestion_content, version.content)
+
+    def test_content_length_is_per_document_row_for_versions(self) -> None:
+        root = Document.objects.create(
+            title="root",
+            checksum="root",
+            mime_type="application/pdf",
+            content="abc",
+        )
+        version = Document.objects.create(
+            title="v1",
+            checksum="v1",
+            mime_type="application/pdf",
+            root_document=root,
+            content="abcdefgh",
+        )
+
+        root.refresh_from_db()
+        version.refresh_from_db()
+
+        self.assertEqual(root.content_length, 3)
+        self.assertEqual(version.content_length, 8)
+
 
 def test_suggestion_content() -> None:
     """

src/documents/tests/test_matchables.py

@@ -48,6 +48,52 @@ class _TestMatchingBase(TestCase):
 
 
 class TestMatching(_TestMatchingBase):
+    def test_matches_uses_latest_version_content_for_root_documents(self) -> None:
+        root = Document.objects.create(
+            title="root",
+            checksum="root",
+            mime_type="application/pdf",
+            content="root content without token",
+        )
+        Document.objects.create(
+            title="v1",
+            checksum="v1",
+            mime_type="application/pdf",
+            root_document=root,
+            content="latest version contains keyword",
+        )
+        tag = Tag.objects.create(
+            name="tag",
+            match="keyword",
+            matching_algorithm=Tag.MATCH_ANY,
+        )
+
+        self.assertTrue(matching.matches(tag, root))
+
+    def test_matches_does_not_fall_back_to_root_content_when_version_exists(
+        self,
+    ) -> None:
+        root = Document.objects.create(
+            title="root",
+            checksum="root",
+            mime_type="application/pdf",
+            content="root contains keyword",
+        )
+        Document.objects.create(
+            title="v1",
+            checksum="v1",
+            mime_type="application/pdf",
+            root_document=root,
+            content="latest version without token",
+        )
+        tag = Tag.objects.create(
+            name="tag",
+            match="keyword",
+            matching_algorithm=Tag.MATCH_ANY,
+        )
+
+        self.assertFalse(matching.matches(tag, root))
+
     def test_match_none(self) -> None:
         self._test_matching(
             "",

src/documents/tests/test_migration_saved_view_visibility.py

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

src/documents/tests/test_migration_share_link_bundle.py

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

src/documents/tests/test_parsers.py

@@ -9,9 +9,9 @@ from documents.parsers import get_default_file_extension
 from documents.parsers import get_parser_class_for_mime_type
 from documents.parsers import get_supported_file_extensions
 from documents.parsers import is_file_ext_supported
-from paperless.parsers.text import TextDocumentParser
-from paperless.parsers.tika import TikaDocumentParser
 from paperless_tesseract.parsers import RasterisedDocumentParser
+from paperless_text.parsers import TextDocumentParser
+from paperless_tika.parsers import TikaDocumentParser
 
 
 class TestParserDiscovery(TestCase):

src/documents/views.py

@@ -7,7 +7,6 @@ import tempfile
 import zipfile
 from collections import defaultdict
 from collections import deque
-from contextlib import nullcontext
 from datetime import datetime
 from pathlib import Path
 from time import mktime
@@ -177,14 +176,20 @@ from documents.serialisers import BulkEditObjectsSerializer
 from documents.serialisers import BulkEditSerializer
 from documents.serialisers import CorrespondentSerializer
 from documents.serialisers import CustomFieldSerializer
+from documents.serialisers import DeleteDocumentsSerializer
 from documents.serialisers import DocumentListSerializer
 from documents.serialisers import DocumentSerializer
 from documents.serialisers import DocumentTypeSerializer
 from documents.serialisers import DocumentVersionLabelSerializer
 from documents.serialisers import DocumentVersionSerializer
+from documents.serialisers import EditPdfDocumentsSerializer
 from documents.serialisers import EmailSerializer
+from documents.serialisers import MergeDocumentsSerializer
 from documents.serialisers import NotesSerializer
 from documents.serialisers import PostDocumentSerializer
+from documents.serialisers import RemovePasswordDocumentsSerializer
+from documents.serialisers import ReprocessDocumentsSerializer
+from documents.serialisers import RotateDocumentsSerializer
 from documents.serialisers import RunTaskViewSerializer
 from documents.serialisers import SavedViewSerializer
 from documents.serialisers import SearchResultSerializer
@@ -220,7 +225,6 @@ from paperless.celery import app as celery_app
 from paperless.config import AIConfig
 from paperless.config import GeneralConfig
 from paperless.models import ApplicationConfiguration
-from paperless.parsers import ParserProtocol
 from paperless.serialisers import GroupSerializer
 from paperless.serialisers import UserSerializer
 from paperless.views import StandardPagination
@@ -1080,11 +1084,9 @@ class DocumentViewSet(
         parser_class = get_parser_class_for_mime_type(mime_type)
         if parser_class:
             parser = parser_class(progress_callback=None, logging_group=None)
-            cm = parser if isinstance(parser, ParserProtocol) else nullcontext(parser)
 
             try:
-                with cm:
-                    return parser.extract_metadata(file, mime_type)
+                return parser.extract_metadata(file, mime_type)
             except Exception:  # pragma: no cover
                 logger.exception(f"Issue getting metadata for {file}")
                 # TODO: cover GPG errors, remove later.
@@ -1526,13 +1528,17 @@ class DocumentViewSet(
 
         return Response(sorted(entries, key=lambda x: x["timestamp"], reverse=True))
 
+    @extend_schema(
+        operation_id="documents_email_document",
+        deprecated=True,
+    )
     @action(
         methods=["post"],
         detail=True,
         url_path="email",
         permission_classes=[IsAuthenticated, ViewDocumentsPermissions],
     )
-    # TODO: deprecated as of 2.19, remove in future release
+    # TODO: deprecated, remove with drop of support for API v9
     def email_document(self, request, pk=None):
         request_data = request.data.copy()
         request_data.setlist("documents", [pk])
@@ -2118,6 +2124,125 @@ class SavedViewViewSet(BulkPermissionMixin, PassUserMixin, ModelViewSet):
     ordering_fields = ("name",)
 
 
+class DocumentOperationPermissionMixin(PassUserMixin):
+    permission_classes = (IsAuthenticated,)
+    parser_classes = (parsers.JSONParser,)
+    METHOD_NAMES_REQUIRING_USER = {
+        "split",
+        "merge",
+        "rotate",
+        "delete_pages",
+        "edit_pdf",
+        "remove_password",
+    }
+
+    def _has_document_permissions(
+        self,
+        *,
+        user: User,
+        documents: list[int],
+        method,
+        parameters: dict[str, Any],
+    ) -> bool:
+        if user.is_superuser:
+            return True
+
+        document_objs = Document.objects.select_related("owner").filter(
+            pk__in=documents,
+        )
+        user_is_owner_of_all_documents = all(
+            (doc.owner == user or doc.owner is None) for doc in document_objs
+        )
+
+        # check global and object permissions for all documents
+        has_perms = user.has_perm("documents.change_document") and all(
+            has_perms_owner_aware(user, "change_document", doc) for doc in document_objs
+        )
+
+        # check ownership for methods that change original document
+        if (
+            (
+                has_perms
+                and method
+                in [
+                    bulk_edit.set_permissions,
+                    bulk_edit.delete,
+                    bulk_edit.rotate,
+                    bulk_edit.delete_pages,
+                    bulk_edit.edit_pdf,
+                    bulk_edit.remove_password,
+                ]
+            )
+            or (
+                method in [bulk_edit.merge, bulk_edit.split]
+                and parameters.get("delete_originals")
+            )
+            or (method == bulk_edit.edit_pdf and parameters.get("update_document"))
+        ):
+            has_perms = user_is_owner_of_all_documents
+
+        # check global add permissions for methods that create documents
+        if (
+            has_perms
+            and (
+                method in [bulk_edit.split, bulk_edit.merge]
+                or (
+                    method in [bulk_edit.edit_pdf, bulk_edit.remove_password]
+                    and not parameters.get("update_document")
+                )
+            )
+            and not user.has_perm("documents.add_document")
+        ):
+            has_perms = False
+
+        # check global delete permissions for methods that delete documents
+        if (
+            has_perms
+            and (
+                method == bulk_edit.delete
+                or (
+                    method in [bulk_edit.merge, bulk_edit.split]
+                    and parameters.get("delete_originals")
+                )
+            )
+            and not user.has_perm("documents.delete_document")
+        ):
+            has_perms = False
+
+        return has_perms
+
+    def _execute_document_action(
+        self,
+        *,
+        method,
+        validated_data: dict[str, Any],
+        operation_label: str,
+    ):
+        documents = validated_data["documents"]
+        parameters = {k: v for k, v in validated_data.items() if k != "documents"}
+        user = self.request.user
+
+        if method.__name__ in self.METHOD_NAMES_REQUIRING_USER:
+            parameters["user"] = user
+
+        if not self._has_document_permissions(
+            user=user,
+            documents=documents,
+            method=method,
+            parameters=parameters,
+        ):
+            return HttpResponseForbidden("Insufficient permissions")
+
+        try:
+            result = method(documents, **parameters)
+            return Response({"result": result})
+        except Exception as e:
+            logger.warning(f"An error occurred performing {operation_label}: {e!s}")
+            return HttpResponseBadRequest(
+                f"Error performing {operation_label}, check logs for more detail.",
+            )
+
+
 @extend_schema_view(
     post=extend_schema(
         operation_id="bulk_edit",
@@ -2136,7 +2261,7 @@ class SavedViewViewSet(BulkPermissionMixin, PassUserMixin, ModelViewSet):
         },
     ),
 )
-class BulkEditView(PassUserMixin):
+class BulkEditView(DocumentOperationPermissionMixin):
     MODIFIED_FIELD_BY_METHOD = {
         "set_correspondent": "correspondent",
         "set_document_type": "document_type",
@@ -2158,11 +2283,24 @@ class BulkEditView(PassUserMixin):
         "remove_password": None,
     }
 
-    permission_classes = (IsAuthenticated,)
     serializer_class = BulkEditSerializer
-    parser_classes = (parsers.JSONParser,)
 
     def post(self, request, *args, **kwargs):
+        request_method = request.data.get("method")
+        api_version = int(request.version or settings.REST_FRAMEWORK["DEFAULT_VERSION"])
+        # TODO: remove this and related backwards compatibility code when API v9 is dropped
+        if request_method in BulkEditSerializer.LEGACY_DOCUMENT_ACTION_METHODS:
+            endpoint = BulkEditSerializer.MOVED_DOCUMENT_ACTION_ENDPOINTS[
+                request_method
+            ]
+            logger.warning(
+                "Deprecated bulk_edit method '%s' requested on API version %s. "
+                "Use '%s' instead.",
+                request_method,
+                api_version,
+                endpoint,
+            )
+
         serializer = self.get_serializer(data=request.data)
         serializer.is_valid(raise_exception=True)
 
@@ -2170,82 +2308,15 @@ class BulkEditView(PassUserMixin):
         method = serializer.validated_data.get("method")
         parameters = serializer.validated_data.get("parameters")
         documents = serializer.validated_data.get("documents")
-        if method in [
-            bulk_edit.split,
-            bulk_edit.merge,
-            bulk_edit.rotate,
-            bulk_edit.delete_pages,
-            bulk_edit.edit_pdf,
-            bulk_edit.remove_password,
-        ]:
+        if method.__name__ in self.METHOD_NAMES_REQUIRING_USER:
             parameters["user"] = user
-
-        if not user.is_superuser:
-            document_objs = Document.objects.select_related("owner").filter(
-                pk__in=documents,
-            )
-            user_is_owner_of_all_documents = all(
-                (doc.owner == user or doc.owner is None) for doc in document_objs
-            )
-
-            # check global and object permissions for all documents
-            has_perms = user.has_perm("documents.change_document") and all(
-                has_perms_owner_aware(user, "change_document", doc)
-                for doc in document_objs
-            )
-
-            # check ownership for methods that change original document
-            if (
-                (
-                    has_perms
-                    and method
-                    in [
-                        bulk_edit.set_permissions,
-                        bulk_edit.delete,
-                        bulk_edit.rotate,
-                        bulk_edit.delete_pages,
-                        bulk_edit.edit_pdf,
-                        bulk_edit.remove_password,
-                    ]
-                )
-                or (
-                    method in [bulk_edit.merge, bulk_edit.split]
-                    and parameters["delete_originals"]
-                )
-                or (method == bulk_edit.edit_pdf and parameters["update_document"])
-            ):
-                has_perms = user_is_owner_of_all_documents
-
-            # check global add permissions for methods that create documents
-            if (
-                has_perms
-                and (
-                    method in [bulk_edit.split, bulk_edit.merge]
-                    or (
-                        method in [bulk_edit.edit_pdf, bulk_edit.remove_password]
-                        and not parameters["update_document"]
-                    )
-                )
-                and not user.has_perm("documents.add_document")
-            ):
-                has_perms = False
-
-            # check global delete permissions for methods that delete documents
-            if (
-                has_perms
-                and (
-                    method == bulk_edit.delete
-                    or (
-                        method in [bulk_edit.merge, bulk_edit.split]
-                        and parameters["delete_originals"]
-                    )
-                )
-                and not user.has_perm("documents.delete_document")
-            ):
-                has_perms = False
-
-            if not has_perms:
-                return HttpResponseForbidden("Insufficient permissions")
+        if not self._has_document_permissions(
+            user=user,
+            documents=documents,
+            method=method,
+            parameters=parameters,
+        ):
+            return HttpResponseForbidden("Insufficient permissions")
 
         try:
             modified_field = self.MODIFIED_FIELD_BY_METHOD.get(method.__name__, None)
@@ -2302,6 +2373,168 @@ class BulkEditView(PassUserMixin):
             )
 
 
+@extend_schema_view(
+    post=extend_schema(
+        operation_id="documents_rotate",
+        description="Rotate one or more documents",
+        responses={
+            200: inline_serializer(
+                name="RotateDocumentsResult",
+                fields={
+                    "result": serializers.CharField(),
+                },
+            ),
+        },
+    ),
+)
+class RotateDocumentsView(DocumentOperationPermissionMixin):
+    serializer_class = RotateDocumentsSerializer
+
+    def post(self, request, *args, **kwargs):
+        serializer = self.get_serializer(data=request.data)
+        serializer.is_valid(raise_exception=True)
+        return self._execute_document_action(
+            method=bulk_edit.rotate,
+            validated_data=serializer.validated_data,
+            operation_label="document rotate",
+        )
+
+
+@extend_schema_view(
+    post=extend_schema(
+        operation_id="documents_merge",
+        description="Merge selected documents into a new document",
+        responses={
+            200: inline_serializer(
+                name="MergeDocumentsResult",
+                fields={
+                    "result": serializers.CharField(),
+                },
+            ),
+        },
+    ),
+)
+class MergeDocumentsView(DocumentOperationPermissionMixin):
+    serializer_class = MergeDocumentsSerializer
+
+    def post(self, request, *args, **kwargs):
+        serializer = self.get_serializer(data=request.data)
+        serializer.is_valid(raise_exception=True)
+        return self._execute_document_action(
+            method=bulk_edit.merge,
+            validated_data=serializer.validated_data,
+            operation_label="document merge",
+        )
+
+
+@extend_schema_view(
+    post=extend_schema(
+        operation_id="documents_delete",
+        description="Move selected documents to trash",
+        responses={
+            200: inline_serializer(
+                name="DeleteDocumentsResult",
+                fields={
+                    "result": serializers.CharField(),
+                },
+            ),
+        },
+    ),
+)
+class DeleteDocumentsView(DocumentOperationPermissionMixin):
+    serializer_class = DeleteDocumentsSerializer
+
+    def post(self, request, *args, **kwargs):
+        serializer = self.get_serializer(data=request.data)
+        serializer.is_valid(raise_exception=True)
+        return self._execute_document_action(
+            method=bulk_edit.delete,
+            validated_data=serializer.validated_data,
+            operation_label="document delete",
+        )
+
+
+@extend_schema_view(
+    post=extend_schema(
+        operation_id="documents_reprocess",
+        description="Reprocess selected documents",
+        responses={
+            200: inline_serializer(
+                name="ReprocessDocumentsResult",
+                fields={
+                    "result": serializers.CharField(),
+                },
+            ),
+        },
+    ),
+)
+class ReprocessDocumentsView(DocumentOperationPermissionMixin):
+    serializer_class = ReprocessDocumentsSerializer
+
+    def post(self, request, *args, **kwargs):
+        serializer = self.get_serializer(data=request.data)
+        serializer.is_valid(raise_exception=True)
+        return self._execute_document_action(
+            method=bulk_edit.reprocess,
+            validated_data=serializer.validated_data,
+            operation_label="document reprocess",
+        )
+
+
+@extend_schema_view(
+    post=extend_schema(
+        operation_id="documents_edit_pdf",
+        description="Perform PDF edit operations on a selected document",
+        responses={
+            200: inline_serializer(
+                name="EditPdfDocumentsResult",
+                fields={
+                    "result": serializers.CharField(),
+                },
+            ),
+        },
+    ),
+)
+class EditPdfDocumentsView(DocumentOperationPermissionMixin):
+    serializer_class = EditPdfDocumentsSerializer
+
+    def post(self, request, *args, **kwargs):
+        serializer = self.get_serializer(data=request.data)
+        serializer.is_valid(raise_exception=True)
+        return self._execute_document_action(
+            method=bulk_edit.edit_pdf,
+            validated_data=serializer.validated_data,
+            operation_label="PDF edit",
+        )
+
+
+@extend_schema_view(
+    post=extend_schema(
+        operation_id="documents_remove_password",
+        description="Remove password protection from selected PDFs",
+        responses={
+            200: inline_serializer(
+                name="RemovePasswordDocumentsResult",
+                fields={
+                    "result": serializers.CharField(),
+                },
+            ),
+        },
+    ),
+)
+class RemovePasswordDocumentsView(DocumentOperationPermissionMixin):
+    serializer_class = RemovePasswordDocumentsSerializer
+
+    def post(self, request, *args, **kwargs):
+        serializer = self.get_serializer(data=request.data)
+        serializer.is_valid(raise_exception=True)
+        return self._execute_document_action(
+            method=bulk_edit.remove_password,
+            validated_data=serializer.validated_data,
+            operation_label="password removal",
+        )
+
+
 @extend_schema_view(
     post=extend_schema(
         description="Upload a document via the API",

src/documents/workflows/webhooks.py

@@ -1,12 +1,14 @@
-import ipaddress
 import logging
-import socket
-from urllib.parse import urlparse
 
 import httpx
 from celery import shared_task
 from django.conf import settings
 
+from paperless.network import format_host_for_url
+from paperless.network import is_public_ip
+from paperless.network import resolve_hostname_ips
+from paperless.network import validate_outbound_http_url
+
 logger = logging.getLogger("paperless.workflows.webhooks")
 
 
@@ -34,23 +36,19 @@ class WebhookTransport(httpx.HTTPTransport):
             raise httpx.ConnectError("No hostname in request URL")
 
         try:
-            addr_info = socket.getaddrinfo(hostname, None)
-        except socket.gaierror as e:
-            raise httpx.ConnectError(f"Could not resolve hostname: {hostname}") from e
-
-        ips = [info[4][0] for info in addr_info if info and info[4]]
-        if not ips:
-            raise httpx.ConnectError(f"Could not resolve hostname: {hostname}")
+            ips = resolve_hostname_ips(hostname)
+        except ValueError as e:
+            raise httpx.ConnectError(str(e)) from e
 
         if not self.allow_internal:
             for ip_str in ips:
-                if not WebhookTransport.is_public_ip(ip_str):
+                if not is_public_ip(ip_str):
                     raise httpx.ConnectError(
                         f"Connection blocked: {hostname} resolves to a non-public address",
                     )
 
         ip_str = ips[0]
-        formatted_ip = self._format_ip_for_url(ip_str)
+        formatted_ip = format_host_for_url(ip_str)
 
         new_headers = httpx.Headers(request.headers)
         if "host" in new_headers:
@@ -69,40 +67,6 @@ class WebhookTransport(httpx.HTTPTransport):
 
         return super().handle_request(request)
 
-    def _format_ip_for_url(self, ip: str) -> str:
-        """
-        Format IP address for use in URL (wrap IPv6 in brackets)
-        """
-        try:
-            ip_obj = ipaddress.ip_address(ip)
-            if ip_obj.version == 6:
-                return f"[{ip}]"
-            return ip
-        except ValueError:
-            return ip
-
-    @staticmethod
-    def is_public_ip(ip: str | int) -> bool:
-        try:
-            obj = ipaddress.ip_address(ip)
-            return not (
-                obj.is_private
-                or obj.is_loopback
-                or obj.is_link_local
-                or obj.is_multicast
-                or obj.is_unspecified
-            )
-        except ValueError:  # pragma: no cover
-            return False
-
-    @staticmethod
-    def resolve_first_ip(host: str) -> str | None:
-        try:
-            info = socket.getaddrinfo(host, None)
-            return info[0][4][0] if info else None
-        except Exception:  # pragma: no cover
-            return None
-
 
 @shared_task(
     retry_backoff=True,
@@ -118,21 +82,24 @@ def send_webhook(
     *,
     as_json: bool = False,
 ):
-    p = urlparse(url)
-    if p.scheme.lower() not in settings.WEBHOOKS_ALLOWED_SCHEMES or not p.hostname:
-        logger.warning("Webhook blocked: invalid scheme/hostname")
+    try:
+        parsed = validate_outbound_http_url(
+            url,
+            allowed_schemes=settings.WEBHOOKS_ALLOWED_SCHEMES,
+            allowed_ports=settings.WEBHOOKS_ALLOWED_PORTS,
+            # Internal-address checks happen in transport to preserve ConnectError behavior.
+            allow_internal=True,
+        )
+    except ValueError as e:
+        logger.warning("Webhook blocked: %s", e)
+        raise
+
+    hostname = parsed.hostname
+    if hostname is None:  # pragma: no cover
         raise ValueError("Invalid URL scheme or hostname.")
 
-    port = p.port or (443 if p.scheme == "https" else 80)
-    if (
-        len(settings.WEBHOOKS_ALLOWED_PORTS) > 0
-        and port not in settings.WEBHOOKS_ALLOWED_PORTS
-    ):
-        logger.warning("Webhook blocked: port not permitted")
-        raise ValueError("Destination port not permitted.")
-
     transport = WebhookTransport(
-        hostname=p.hostname,
+        hostname=hostname,
         allow_internal=settings.WEBHOOKS_ALLOW_INTERNAL_REQUESTS,
     )
 

src/paperless/celery.py

@@ -1,7 +1,6 @@
 import os
 
 from celery import Celery
-from celery.signals import worker_process_init
 
 # Set the default Django settings module for the 'celery' program.
 os.environ.setdefault("DJANGO_SETTINGS_MODULE", "paperless.settings")
@@ -16,19 +15,3 @@ app.config_from_object("django.conf:settings", namespace="CELERY")
 
 # Load task modules from all registered Django apps.
 app.autodiscover_tasks()
-
-
-@worker_process_init.connect
-def on_worker_process_init(**kwargs) -> None:  # pragma: no cover
-    """
-    Register built-in parsers eagerly in each Celery worker process.
-
-    This registers only the built-in parsers (no entrypoint discovery) so
-    that workers can begin consuming documents immediately.  Entrypoint
-    discovery for third-party parsers is deferred to the first call of
-    get_parser_registry() inside a task, keeping worker_process_init
-    well within its 4-second timeout budget.
-    """
-    from paperless.parsers.registry import init_builtin_parsers
-
-    init_builtin_parsers()

src/paperless/checks.py

@@ -7,6 +7,7 @@ from pathlib import Path
 
 from django.conf import settings
 from django.core.checks import Error
+from django.core.checks import Tags
 from django.core.checks import Warning
 from django.core.checks import register
 from django.db import connections
@@ -204,15 +205,16 @@ def audit_log_check(app_configs, **kwargs):
     return result
 
 
-@register()
+@register(Tags.compatibility)
 def check_v3_minimum_upgrade_version(
     app_configs: object,
     **kwargs: object,
 ) -> list[Error]:
-    """Enforce that upgrades to v3 must start from v2.20.9.
+    """
+    Enforce that upgrades to v3 must start from v2.20.10.
 
     v3 squashes all prior migrations into 0001_squashed and 0002_squashed.
-    If a user skips v2.20.9, the data migration in 1075_workflowaction_order
+    If a user skips v2.20.10, the data migration in 1075_workflowaction_order
     never runs and the squash may apply schema changes against an incomplete
     database state.
     """
@@ -239,7 +241,7 @@ def check_v3_minimum_upgrade_version(
         if {"0001_squashed", "0002_squashed"} & applied:
             return []
 
-        # On v2.20.9 exactly — squash will pick up cleanly from here
+        # On v2.20.10 exactly — squash will pick up cleanly from here
         if "1075_workflowaction_order" in applied:
             return []
 
@@ -250,8 +252,8 @@ def check_v3_minimum_upgrade_version(
         Error(
             "Cannot upgrade to Paperless-ngx v3 from this version.",
             hint=(
-                "Upgrading to v3 can only be performed from v2.20.9."
-                "Please upgrade to v2.20.9, run migrations, then upgrade to v3."
+                "Upgrading to v3 can only be performed from v2.20.10."
+                "Please upgrade to v2.20.10, run migrations, then upgrade to v3."
                 "See https://docs.paperless-ngx.com/setup/#upgrading for details."
             ),
             id="paperless.E002",

src/paperless/config.py

@@ -188,6 +188,7 @@ class AIConfig(BaseConfig):
     llm_model: str = dataclasses.field(init=False)
     llm_api_key: str = dataclasses.field(init=False)
     llm_endpoint: str = dataclasses.field(init=False)
+    llm_allow_internal_endpoints: bool = dataclasses.field(init=False)
 
     def __post_init__(self) -> None:
         app_config = self._get_config_instance()
@@ -203,6 +204,7 @@ class AIConfig(BaseConfig):
         self.llm_model = app_config.llm_model or settings.LLM_MODEL
         self.llm_api_key = app_config.llm_api_key or settings.LLM_API_KEY
         self.llm_endpoint = app_config.llm_endpoint or settings.LLM_ENDPOINT
+        self.llm_allow_internal_endpoints = settings.LLM_ALLOW_INTERNAL_ENDPOINTS
 
     @property
     def llm_index_enabled(self) -> bool:

src/paperless/network.py

@@ -0,0 +1,76 @@
+import ipaddress
+import socket
+from collections.abc import Collection
+from urllib.parse import ParseResult
+from urllib.parse import urlparse
+
+
+def is_public_ip(ip: str | int) -> bool:
+    try:
+        obj = ipaddress.ip_address(ip)
+        return not (
+            obj.is_private
+            or obj.is_loopback
+            or obj.is_link_local
+            or obj.is_multicast
+            or obj.is_unspecified
+        )
+    except ValueError:  # pragma: no cover
+        return False
+
+
+def resolve_hostname_ips(hostname: str) -> list[str]:
+    try:
+        addr_info = socket.getaddrinfo(hostname, None)
+    except socket.gaierror as e:
+        raise ValueError(f"Could not resolve hostname: {hostname}") from e
+
+    ips = [info[4][0] for info in addr_info if info and info[4]]
+    if not ips:
+        raise ValueError(f"Could not resolve hostname: {hostname}")
+    return ips
+
+
+def format_host_for_url(host: str) -> str:
+    """
+    Format IP address for URL use (wrap IPv6 in brackets).
+    """
+    try:
+        ip_obj = ipaddress.ip_address(host)
+        if ip_obj.version == 6:
+            return f"[{host}]"
+        return host
+    except ValueError:
+        return host
+
+
+def validate_outbound_http_url(
+    url: str,
+    *,
+    allowed_schemes: Collection[str] = ("http", "https"),
+    allowed_ports: Collection[int] | None = None,
+    allow_internal: bool = False,
+) -> ParseResult:
+    parsed = urlparse(url)
+    scheme = parsed.scheme.lower()
+
+    if scheme not in allowed_schemes or not parsed.hostname:
+        raise ValueError("Invalid URL scheme or hostname.")
+
+    default_port = 443 if scheme == "https" else 80
+    try:
+        port = parsed.port or default_port
+    except ValueError as e:
+        raise ValueError("Invalid URL scheme or hostname.") from e
+
+    if allowed_ports and port not in allowed_ports:
+        raise ValueError("Destination port not permitted.")
+
+    if not allow_internal:
+        for ip_str in resolve_hostname_ips(parsed.hostname):
+            if not is_public_ip(ip_str):
+                raise ValueError(
+                    f"Connection blocked: {parsed.hostname} resolves to a non-public address",
+                )
+
+    return parsed

src/paperless/parsers/__init__.py

@@ -1,379 +0,0 @@
-"""
-Public interface for the Paperless-ngx parser plugin system.
-
-This module defines ParserProtocol — the structural contract that every
-document parser must satisfy, whether it is a built-in parser shipped with
-Paperless-ngx or a third-party parser installed via a Python entrypoint.
-
-Phase 1/2 scope: only the Protocol is defined here. The transitional
-DocumentParser ABC (Phase 3) and concrete built-in parsers (Phase 3+) will
-be added in later phases, so there are intentionally no imports of parser
-implementations here.
-
-Usage example (third-party parser)::
-
-    from paperless.parsers import ParserProtocol
-
-    class MyParser:
-        name = "my-parser"
-        version = "1.0.0"
-        author = "Acme Corp"
-        url = "https://example.com/my-parser"
-
-        @classmethod
-        def supported_mime_types(cls) -> dict[str, str]:
-            return {"application/x-my-format": ".myf"}
-
-        @classmethod
-        def score(cls, mime_type, filename, path=None):
-            return 10
-
-        # … implement remaining protocol methods …
-
-    assert isinstance(MyParser(), ParserProtocol)
-"""
-
-from __future__ import annotations
-
-from typing import TYPE_CHECKING
-from typing import Protocol
-from typing import Self
-from typing import TypedDict
-from typing import runtime_checkable
-
-if TYPE_CHECKING:
-    import datetime
-    from pathlib import Path
-    from types import TracebackType
-
-__all__ = [
-    "MetadataEntry",
-    "ParserProtocol",
-]
-
-
-class MetadataEntry(TypedDict):
-    """A single metadata field extracted from a document.
-
-    All four keys are required. Values are always serialised to strings —
-    type-specific conversion (dates, integers, lists) is the responsibility
-    of the parser before returning.
-    """
-
-    namespace: str
-    """URI of the metadata namespace (e.g. 'http://ns.adobe.com/pdf/1.3/')."""
-
-    prefix: str
-    """Conventional namespace prefix (e.g. 'pdf', 'xmp', 'dc')."""
-
-    key: str
-    """Field name within the namespace (e.g. 'Author', 'CreateDate')."""
-
-    value: str
-    """String representation of the field value."""
-
-
-@runtime_checkable
-class ParserProtocol(Protocol):
-    """Structural contract for all Paperless-ngx document parsers.
-
-    Both built-in parsers and third-party plugins (discovered via the
-    "paperless_ngx.parsers" entrypoint group) must satisfy this Protocol.
-    Because it is decorated with runtime_checkable, isinstance(obj,
-    ParserProtocol) works at runtime based on method presence, which is
-    useful for validation in ParserRegistry.discover.
-
-    Parsers must expose four string attributes at the class level so the
-    registry can log attribution information without instantiating the parser:
-
-    name : str
-        Human-readable parser name (e.g. "Tesseract OCR").
-    version : str
-        Semantic version string (e.g. "1.2.3").
-    author : str
-        Author or organisation name.
-    url : str
-        URL for documentation, source code, or issue tracker.
-    """
-
-    # ------------------------------------------------------------------
-    # Class-level identity (checked by the registry, not Protocol methods)
-    # ------------------------------------------------------------------
-
-    name: str
-    version: str
-    author: str
-    url: str
-
-    # ------------------------------------------------------------------
-    # Class methods
-    # ------------------------------------------------------------------
-
-    @classmethod
-    def supported_mime_types(cls) -> dict[str, str]:
-        """Return a mapping of supported MIME types to preferred file extensions.
-
-        The keys are MIME type strings (e.g. "application/pdf"), and the
-        values are the preferred file extension including the leading dot
-        (e.g. ".pdf").  The registry uses this mapping both to decide whether
-        a parser is a candidate for a given file and to determine the default
-        extension when creating archive copies.
-
-        Returns
-        -------
-        dict[str, str]
-            {mime_type: extension} mapping — may be empty if the parser
-            has been temporarily disabled.
-        """
-        ...
-
-    @classmethod
-    def score(
-        cls,
-        mime_type: str,
-        filename: str,
-        path: Path | None = None,
-    ) -> int | None:
-        """Return a priority score for handling this file, or None to decline.
-
-        The registry calls this after confirming that the MIME type is in
-        supported_mime_types. Parsers may inspect filename and optionally
-        the file at path to refine their confidence level.
-
-        A higher score wins. Return None to explicitly decline handling a file
-        even though the MIME type is listed as supported (e.g. when a feature
-        flag is disabled, or a required service is not configured).
-
-        Parameters
-        ----------
-        mime_type:
-            The detected MIME type of the file to be parsed.
-        filename:
-            The original filename, including extension.
-        path:
-            Optional filesystem path to the file. Parsers that need to
-            inspect file content (e.g. magic-byte sniffing) may use this.
-            May be None when scoring happens before the file is available locally.
-
-        Returns
-        -------
-        int | None
-            Priority score (higher wins), or None to decline.
-        """
-        ...
-
-    # ------------------------------------------------------------------
-    # Properties
-    # ------------------------------------------------------------------
-
-    @property
-    def can_produce_archive(self) -> bool:
-        """Whether this parser can produce a searchable PDF archive copy.
-
-        If True, the consumption pipeline may request an archive version when
-        processing the document, subject to the ARCHIVE_FILE_GENERATION
-        setting. If False, only thumbnail and text extraction are performed.
-        """
-        ...
-
-    @property
-    def requires_pdf_rendition(self) -> bool:
-        """Whether the parser must produce a PDF for the frontend to display.
-
-        True for formats the browser cannot display natively (e.g. DOCX, ODT).
-        When True, the pipeline always stores the PDF output regardless of the
-        ARCHIVE_FILE_GENERATION setting, since the original format cannot be
-        shown to the user.
-        """
-        ...
-
-    # ------------------------------------------------------------------
-    # Core parsing interface
-    # ------------------------------------------------------------------
-
-    def parse(
-        self,
-        document_path: Path,
-        mime_type: str,
-        *,
-        produce_archive: bool = True,
-    ) -> None:
-        """Parse document_path and populate internal state.
-
-        After a successful call, callers retrieve results via get_text,
-        get_date, and get_archive_path.
-
-        Parameters
-        ----------
-        document_path:
-            Absolute path to the document file to parse.
-        mime_type:
-            Detected MIME type of the document.
-        produce_archive:
-            When True (the default) and can_produce_archive is also True,
-            the parser should produce a searchable PDF at the path returned
-            by get_archive_path. Pass False when only text extraction and
-            thumbnail generation are required and disk I/O should be minimised.
-
-        Raises
-        ------
-        documents.parsers.ParseError
-            If parsing fails for any reason.
-        """
-        ...
-
-    # ------------------------------------------------------------------
-    # Result accessors
-    # ------------------------------------------------------------------
-
-    def get_text(self) -> str | None:
-        """Return the plain-text content extracted during parse.
-
-        Returns
-        -------
-        str | None
-            Extracted text, or None if no text could be found.
-        """
-        ...
-
-    def get_date(self) -> datetime.datetime | None:
-        """Return the document date detected during parse.
-
-        Returns
-        -------
-        datetime.datetime | None
-            Detected document date, or None if no date was found.
-        """
-        ...
-
-    def get_archive_path(self) -> Path | None:
-        """Return the path to the generated archive PDF, or None.
-
-        Returns
-        -------
-        Path | None
-            Path to the searchable PDF archive, or None if no archive was
-            produced (e.g. because produce_archive=False or the parser does
-            not support archive generation).
-        """
-        ...
-
-    # ------------------------------------------------------------------
-    # Thumbnail and metadata
-    # ------------------------------------------------------------------
-
-    def get_thumbnail(self, document_path: Path, mime_type: str) -> Path:
-        """Generate and return the path to a thumbnail image for the document.
-
-        May be called independently of parse. The returned path must point to
-        an existing WebP image file inside the parser's temporary working
-        directory.
-
-        Parameters
-        ----------
-        document_path:
-            Absolute path to the source document.
-        mime_type:
-            Detected MIME type of the document.
-
-        Returns
-        -------
-        Path
-            Path to the generated thumbnail image (WebP format preferred).
-        """
-        ...
-
-    def get_page_count(
-        self,
-        document_path: Path,
-        mime_type: str,
-    ) -> int | None:
-        """Return the number of pages in the document, if determinable.
-
-        Parameters
-        ----------
-        document_path:
-            Absolute path to the source document.
-        mime_type:
-            Detected MIME type of the document.
-
-        Returns
-        -------
-        int | None
-            Page count, or None if the parser cannot determine it.
-        """
-        ...
-
-    def extract_metadata(
-        self,
-        document_path: Path,
-        mime_type: str,
-    ) -> list[MetadataEntry]:
-        """Extract format-specific metadata from the document.
-
-        Called by the API view layer on demand — not during the consumption
-        pipeline. Results are returned to the frontend for per-file display.
-
-        For documents with an archive version, this method is called twice:
-        once for the original file (with its native MIME type) and once for
-        the archive file (with ``"application/pdf"``). Parsers that produce
-        archives should handle both cases.
-
-        Implementations must not raise. A failure to read metadata is not
-        fatal — log a warning and return whatever partial results were
-        collected, or ``[]`` if none.
-
-        Parameters
-        ----------
-        document_path:
-            Absolute path to the file to extract metadata from.
-        mime_type:
-            MIME type of the file at ``document_path``. May be
-            ``"application/pdf"`` when called for the archive version.
-
-        Returns
-        -------
-        list[MetadataEntry]
-            Zero or more metadata entries. Returns ``[]`` if no metadata
-            could be extracted or the format does not support it.
-        """
-        ...
-
-    # ------------------------------------------------------------------
-    # Context manager
-    # ------------------------------------------------------------------
-
-    def __enter__(self) -> Self:
-        """Enter the parser context, returning the parser instance.
-
-        Implementations should perform any resource allocation here if not
-        done in __init__ (e.g. creating API clients or temp directories).
-
-        Returns
-        -------
-        Self
-            The parser instance itself.
-        """
-        ...
-
-    def __exit__(
-        self,
-        exc_type: type[BaseException] | None,
-        exc_val: BaseException | None,
-        exc_tb: TracebackType | None,
-    ) -> None:
-        """Exit the parser context and release all resources.
-
-        Implementations must clean up all temporary files and other resources
-        regardless of whether an exception occurred.
-
-        Parameters
-        ----------
-        exc_type:
-            The exception class, or None if no exception was raised.
-        exc_val:
-            The exception instance, or None.
-        exc_tb:
-            The traceback, or None.
-        """
-        ...

src/paperless/parsers/registry.py

@@ -1,364 +0,0 @@
-"""
-Singleton registry that tracks all document parsers available to
-Paperless-ngx — both built-ins shipped with the application and third-party
-plugins installed via Python entrypoints.
-
-Public surface
---------------
-get_parser_registry
-    Lazy-initialise and return the shared ParserRegistry. This is the primary
-    entry point for production code.
-
-init_builtin_parsers
-    Register built-in parsers only, without entrypoint discovery. Safe to
-    call from Celery worker_process_init where importing all entrypoints
-    would be wasteful or cause side effects.
-
-reset_parser_registry
-    Reset module-level state. For tests only.
-
-Entrypoint group
-----------------
-Third-party parsers must advertise themselves under the
-"paperless_ngx.parsers" entrypoint group in their pyproject.toml::
-
-    [project.entry-points."paperless_ngx.parsers"]
-    my_parser = "my_package.parsers:MyParser"
-
-The loaded class must expose the following attributes at the class level
-(not just on instances) for the registry to accept it:
-name, version, author, url, supported_mime_types (callable), score (callable).
-"""
-
-from __future__ import annotations
-
-import logging
-from importlib.metadata import entry_points
-from typing import TYPE_CHECKING
-
-if TYPE_CHECKING:
-    from pathlib import Path
-
-    from paperless.parsers import ParserProtocol
-
-logger = logging.getLogger("paperless.parsers.registry")
-
-# ---------------------------------------------------------------------------
-# Module-level singleton state
-# ---------------------------------------------------------------------------
-
-_registry: ParserRegistry | None = None
-_discovery_complete: bool = False
-
-# Attribute names that every registered external parser class must expose.
-_REQUIRED_ATTRS: tuple[str, ...] = (
-    "name",
-    "version",
-    "author",
-    "url",
-    "supported_mime_types",
-    "score",
-)
-
-
-# ---------------------------------------------------------------------------
-# Module-level accessor functions
-# ---------------------------------------------------------------------------
-
-
-def get_parser_registry() -> ParserRegistry:
-    """Return the shared ParserRegistry instance.
-
-    On the first call this function:
-
-    1. Creates a new ParserRegistry.
-    2. Calls register_defaults to install built-in parsers.
-    3. Calls discover to load third-party plugins via importlib.metadata entrypoints.
-    4. Calls log_summary to emit a startup summary.
-
-    Subsequent calls return the same instance immediately.
-
-    Returns
-    -------
-    ParserRegistry
-        The shared registry singleton.
-    """
-    global _registry, _discovery_complete
-
-    if _registry is None:
-        _registry = ParserRegistry()
-        _registry.register_defaults()
-
-    if not _discovery_complete:
-        _registry.discover()
-        _registry.log_summary()
-        _discovery_complete = True
-
-    return _registry
-
-
-def init_builtin_parsers() -> None:
-    """Register built-in parsers without performing entrypoint discovery.
-
-    Intended for use in Celery worker_process_init handlers where importing
-    all installed entrypoints would be wasteful, slow, or could produce
-    undesirable side effects. Entrypoint discovery (third-party plugins) is
-    deliberately not performed.
-
-    Safe to call multiple times — subsequent calls are no-ops.
-
-    Returns
-    -------
-    None
-    """
-    global _registry
-
-    if _registry is None:
-        _registry = ParserRegistry()
-        _registry.register_defaults()
-
-
-def reset_parser_registry() -> None:
-    """Reset the module-level registry state to its initial values.
-
-    Resets _registry and _discovery_complete so the next call to
-    get_parser_registry will re-initialise everything from scratch.
-
-    FOR TESTS ONLY. Do not call this in production code — resetting the
-    registry mid-request causes all subsequent parser lookups to go through
-    discovery again, which is expensive and may have unexpected side effects
-    in multi-threaded environments.
-
-    Returns
-    -------
-    None
-    """
-    global _registry, _discovery_complete
-
-    _registry = None
-    _discovery_complete = False
-
-
-# ---------------------------------------------------------------------------
-# Registry class
-# ---------------------------------------------------------------------------
-
-
-class ParserRegistry:
-    """Registry that maps MIME types to the best available parser class.
-
-    Parsers are partitioned into two lists:
-
-    _builtins
-        Parser classes registered via register_builtin (populated by
-        register_defaults in Phase 3+).
-
-    _external
-        Parser classes loaded from installed Python entrypoints via discover.
-
-    When resolving a parser for a file, external parsers are evaluated
-    alongside built-in parsers using a uniform scoring mechanism. Both lists
-    are iterated together; the class with the highest score wins. If an
-    external parser wins, its attribution details are logged so users can
-    identify which third-party package handled their document.
-    """
-
-    def __init__(self) -> None:
-        self._external: list[type[ParserProtocol]] = []
-        self._builtins: list[type[ParserProtocol]] = []
-
-    # ------------------------------------------------------------------
-    # Registration
-    # ------------------------------------------------------------------
-
-    def register_builtin(self, parser_class: type[ParserProtocol]) -> None:
-        """Register a built-in parser class.
-
-        Built-in parsers are shipped with Paperless-ngx and are appended to
-        the _builtins list. They are never overridden by external parsers;
-        instead, scoring determines which parser wins for any given file.
-
-        Parameters
-        ----------
-        parser_class:
-            The parser class to register. Must satisfy ParserProtocol.
-        """
-        self._builtins.append(parser_class)
-
-    def register_defaults(self) -> None:
-        """Register the built-in parsers that ship with Paperless-ngx.
-
-        Each parser that has been migrated to the new ParserProtocol interface
-        is registered here.  Parsers are added in ascending weight order so
-        that log output is predictable; scoring determines which parser wins
-        at runtime regardless of registration order.
-        """
-        from paperless.parsers.text import TextDocumentParser
-
-        self.register_builtin(TextDocumentParser)
-
-    # ------------------------------------------------------------------
-    # Discovery
-    # ------------------------------------------------------------------
-
-    def discover(self) -> None:
-        """Load third-party parsers from the "paperless_ngx.parsers" entrypoint group.
-
-        For each advertised entrypoint the method:
-
-        1. Calls ep.load() to import the class.
-        2. Validates that the class exposes all required attributes.
-        3. On success, appends the class to _external and logs an info message.
-        4. On failure (import error or missing attributes), logs an appropriate
-           warning/error and continues to the next entrypoint.
-
-        Errors during discovery of a single parser do not prevent other parsers
-        from being loaded.
-
-        Returns
-        -------
-        None
-        """
-        eps = entry_points(group="paperless_ngx.parsers")
-
-        for ep in eps:
-            try:
-                parser_class = ep.load()
-            except Exception:
-                logger.exception(
-                    "Failed to load parser entrypoint '%s' — skipping.",
-                    ep.name,
-                )
-                continue
-
-            missing = [
-                attr for attr in _REQUIRED_ATTRS if not hasattr(parser_class, attr)
-            ]
-            if missing:
-                logger.warning(
-                    "Parser loaded from entrypoint '%s' is missing required "
-                    "attributes %r — skipping.",
-                    ep.name,
-                    missing,
-                )
-                continue
-
-            self._external.append(parser_class)
-            logger.info(
-                "Loaded third-party parser '%s' v%s by %s (entrypoint: '%s').",
-                parser_class.name,
-                parser_class.version,
-                parser_class.author,
-                ep.name,
-            )
-
-    # ------------------------------------------------------------------
-    # Summary logging
-    # ------------------------------------------------------------------
-
-    def log_summary(self) -> None:
-        """Log a startup summary of all registered parsers.
-
-        Built-in parsers are listed first, followed by any external parsers
-        discovered from entrypoints.  If no external parsers were found a
-        short informational message is logged instead of an empty list.
-
-        Returns
-        -------
-        None
-        """
-        logger.info(
-            "Built-in parsers (%d):",
-            len(self._builtins),
-        )
-        for cls in self._builtins:
-            logger.info(
-                "  [built-in] %s v%s — %s",
-                getattr(cls, "name", repr(cls)),
-                getattr(cls, "version", "unknown"),
-                getattr(cls, "url", "built-in"),
-            )
-
-        if not self._external:
-            logger.info("No third-party parsers discovered.")
-            return
-
-        logger.info(
-            "Third-party parsers (%d):",
-            len(self._external),
-        )
-        for cls in self._external:
-            logger.info(
-                "  [external] %s v%s by %s — report issues at %s",
-                getattr(cls, "name", repr(cls)),
-                getattr(cls, "version", "unknown"),
-                getattr(cls, "author", "unknown"),
-                getattr(cls, "url", "unknown"),
-            )
-
-    # ------------------------------------------------------------------
-    # Parser resolution
-    # ------------------------------------------------------------------
-
-    def get_parser_for_file(
-        self,
-        mime_type: str,
-        filename: str,
-        path: Path | None = None,
-    ) -> type[ParserProtocol] | None:
-        """Return the best parser class for the given file, or None.
-
-        All registered parsers (external first, then built-ins) are evaluated
-        against the file. A parser is eligible if mime_type appears in the dict
-        returned by its supported_mime_types classmethod, and its score
-        classmethod returns a non-None integer.
-
-        The parser with the highest score wins. When two parsers return the
-        same score, the one that appears earlier in the evaluation order wins
-        (external parsers are evaluated before built-ins, giving third-party
-        packages a chance to override defaults at equal priority).
-
-        When an external parser is selected, its identity is logged at INFO
-        level so operators can trace which package handled a document.
-
-        Parameters
-        ----------
-        mime_type:
-            The detected MIME type of the file.
-        filename:
-            The original filename, including extension.
-        path:
-            Optional filesystem path to the file. Forwarded to each
-            parser's score method.
-
-        Returns
-        -------
-        type[ParserProtocol] | None
-            The winning parser class, or None if no parser can handle the file.
-        """
-        best_score: int | None = None
-        best_parser: type[ParserProtocol] | None = None
-
-        # External parsers are placed first so that, at equal scores, an
-        # external parser wins over a built-in (first-seen policy).
-        for parser_class in (*self._external, *self._builtins):
-            if mime_type not in parser_class.supported_mime_types():
-                continue
-
-            score = parser_class.score(mime_type, filename, path)
-            if score is None:
-                continue
-
-            if best_score is None or score > best_score:
-                best_score = score
-                best_parser = parser_class
-
-        if best_parser is not None and best_parser in self._external:
-            logger.info(
-                "Document handled by third-party parser '%s' v%s — %s",
-                getattr(best_parser, "name", repr(best_parser)),
-                getattr(best_parser, "version", "unknown"),
-                getattr(best_parser, "url", "unknown"),
-            )
-
-        return best_parser

src/paperless/parsers/text.py

@@ -1,320 +0,0 @@
-"""
-Built-in plain-text document parser.
-
-Handles text/plain, text/csv, and application/csv MIME types by reading the
-file content directly.  Thumbnails are generated by rendering a page-sized
-WebP image from the first 100,000 characters using Pillow.
-"""
-
-from __future__ import annotations
-
-import logging
-import shutil
-import tempfile
-from pathlib import Path
-from typing import TYPE_CHECKING
-from typing import Self
-
-from django.conf import settings
-from PIL import Image
-from PIL import ImageDraw
-from PIL import ImageFont
-
-from paperless.version import __full_version_str__
-
-if TYPE_CHECKING:
-    import datetime
-    from types import TracebackType
-
-    from paperless.parsers import MetadataEntry
-
-logger = logging.getLogger("paperless.parsing.text")
-
-_SUPPORTED_MIME_TYPES: dict[str, str] = {
-    "text/plain": ".txt",
-    "text/csv": ".csv",
-    "application/csv": ".csv",
-}
-
-
-class TextDocumentParser:
-    """Parse plain-text documents (txt, csv) for Paperless-ngx.
-
-    This parser reads the file content directly as UTF-8 text and renders a
-    simple thumbnail using Pillow.  It does not perform OCR and does not
-    produce a searchable PDF archive copy.
-
-    Class attributes
-    ----------------
-    name : str
-        Human-readable parser name.
-    version : str
-        Semantic version string, kept in sync with Paperless-ngx releases.
-    author : str
-        Maintainer name.
-    url : str
-        Issue tracker / source URL.
-    """
-
-    name: str = "Paperless-ngx Text Parser"
-    version: str = __full_version_str__
-    author: str = "Paperless-ngx Contributors"
-    url: str = "https://github.com/paperless-ngx/paperless-ngx"
-
-    # ------------------------------------------------------------------
-    # Class methods
-    # ------------------------------------------------------------------
-
-    @classmethod
-    def supported_mime_types(cls) -> dict[str, str]:
-        """Return the MIME types this parser handles.
-
-        Returns
-        -------
-        dict[str, str]
-            Mapping of MIME type to preferred file extension.
-        """
-        return _SUPPORTED_MIME_TYPES
-
-    @classmethod
-    def score(
-        cls,
-        mime_type: str,
-        filename: str,
-        path: Path | None = None,
-    ) -> int | None:
-        """Return the priority score for handling this file.
-
-        Parameters
-        ----------
-        mime_type:
-            Detected MIME type of the file.
-        filename:
-            Original filename including extension.
-        path:
-            Optional filesystem path. Not inspected by this parser.
-
-        Returns
-        -------
-        int | None
-            10 if the MIME type is supported, otherwise None.
-        """
-        if mime_type in _SUPPORTED_MIME_TYPES:
-            return 10
-        return None
-
-    # ------------------------------------------------------------------
-    # Properties
-    # ------------------------------------------------------------------
-
-    @property
-    def can_produce_archive(self) -> bool:
-        """Whether this parser can produce a searchable PDF archive copy.
-
-        Returns
-        -------
-        bool
-            Always False — the text parser does not produce a PDF archive.
-        """
-        return False
-
-    @property
-    def requires_pdf_rendition(self) -> bool:
-        """Whether the parser must produce a PDF for the frontend to display.
-
-        Returns
-        -------
-        bool
-            Always False — plain text files are displayable as-is.
-        """
-        return False
-
-    # ------------------------------------------------------------------
-    # Lifecycle
-    # ------------------------------------------------------------------
-
-    def __init__(self, logging_group: object = None) -> None:
-        settings.SCRATCH_DIR.mkdir(parents=True, exist_ok=True)
-        self._tempdir = Path(
-            tempfile.mkdtemp(prefix="paperless-", dir=settings.SCRATCH_DIR),
-        )
-        self._text: str | None = None
-
-    def __enter__(self) -> Self:
-        return self
-
-    def __exit__(
-        self,
-        exc_type: type[BaseException] | None,
-        exc_val: BaseException | None,
-        exc_tb: TracebackType | None,
-    ) -> None:
-        logger.debug("Cleaning up temporary directory %s", self._tempdir)
-        shutil.rmtree(self._tempdir, ignore_errors=True)
-
-    # ------------------------------------------------------------------
-    # Core parsing interface
-    # ------------------------------------------------------------------
-
-    def parse(
-        self,
-        document_path: Path,
-        mime_type: str,
-        *,
-        produce_archive: bool = True,
-    ) -> None:
-        """Read the document and store its text content.
-
-        Parameters
-        ----------
-        document_path:
-            Absolute path to the text file.
-        mime_type:
-            Detected MIME type of the document.
-        produce_archive:
-            Ignored — this parser never produces a PDF archive.
-
-        Raises
-        ------
-        documents.parsers.ParseError
-            If the file cannot be read.
-        """
-        self._text = self._read_text(document_path)
-
-    # ------------------------------------------------------------------
-    # Result accessors
-    # ------------------------------------------------------------------
-
-    def get_text(self) -> str | None:
-        """Return the plain-text content extracted during parse.
-
-        Returns
-        -------
-        str | None
-            Extracted text, or None if parse has not been called yet.
-        """
-        return self._text
-
-    def get_date(self) -> datetime.datetime | None:
-        """Return the document date detected during parse.
-
-        Returns
-        -------
-        datetime.datetime | None
-            Always None — the text parser does not detect dates.
-        """
-        return None
-
-    def get_archive_path(self) -> Path | None:
-        """Return the path to a generated archive PDF, or None.
-
-        Returns
-        -------
-        Path | None
-            Always None — the text parser does not produce a PDF archive.
-        """
-        return None
-
-    # ------------------------------------------------------------------
-    # Thumbnail and metadata
-    # ------------------------------------------------------------------
-
-    def get_thumbnail(self, document_path: Path, mime_type: str) -> Path:
-        """Render the first portion of the document as a WebP thumbnail.
-
-        Parameters
-        ----------
-        document_path:
-            Absolute path to the source document.
-        mime_type:
-            Detected MIME type of the document.
-
-        Returns
-        -------
-        Path
-            Path to the generated WebP thumbnail inside the temporary directory.
-        """
-        max_chars = 100_000
-        file_size_limit = 50 * 1024 * 1024
-
-        if document_path.stat().st_size > file_size_limit:
-            text = "[File too large to preview]"
-        else:
-            with Path(document_path).open("r", encoding="utf-8", errors="replace") as f:
-                text = f.read(max_chars)
-
-        img = Image.new("RGB", (500, 700), color="white")
-        draw = ImageDraw.Draw(img)
-        font = ImageFont.truetype(
-            font=settings.THUMBNAIL_FONT_NAME,
-            size=20,
-            layout_engine=ImageFont.Layout.BASIC,
-        )
-        draw.multiline_text((5, 5), text, font=font, fill="black", spacing=4)
-
-        out_path = self._tempdir / "thumb.webp"
-        img.save(out_path, format="WEBP")
-
-        return out_path
-
-    def get_page_count(
-        self,
-        document_path: Path,
-        mime_type: str,
-    ) -> int | None:
-        """Return the number of pages in the document.
-
-        Parameters
-        ----------
-        document_path:
-            Absolute path to the source document.
-        mime_type:
-            Detected MIME type of the document.
-
-        Returns
-        -------
-        int | None
-            Always None — page count is not meaningful for plain text.
-        """
-        return None
-
-    def extract_metadata(
-        self,
-        document_path: Path,
-        mime_type: str,
-    ) -> list[MetadataEntry]:
-        """Extract format-specific metadata from the document.
-
-        Returns
-        -------
-        list[MetadataEntry]
-            Always ``[]`` — plain text files carry no structured metadata.
-        """
-        return []
-
-    # ------------------------------------------------------------------
-    # Private helpers
-    # ------------------------------------------------------------------
-
-    def _read_text(self, filepath: Path) -> str:
-        """Read file content, replacing invalid UTF-8 bytes rather than failing.
-
-        Parameters
-        ----------
-        filepath:
-            Path to the file to read.
-
-        Returns
-        -------
-        str
-            File content as a string.
-        """
-        try:
-            return filepath.read_text(encoding="utf-8")
-        except UnicodeDecodeError as exc:
-            logger.warning(
-                "Unicode error reading %s, replacing bad bytes: %s",
-                filepath,
-                exc,
-            )
-            return filepath.read_bytes().decode("utf-8", errors="replace")

src/paperless/parsers/tika.py

@@ -1,440 +0,0 @@
-"""
-Built-in Tika document parser.
-
-Handles Office documents (DOCX, ODT, XLS, XLSX, PPT, PPTX, RTF, etc.) by
-sending them to an Apache Tika server for text extraction and a Gotenberg
-server for PDF conversion.  Because the source formats cannot be rendered by
-a browser natively, the parser always produces a PDF rendition for display.
-"""
-
-from __future__ import annotations
-
-import logging
-import shutil
-import tempfile
-from contextlib import ExitStack
-from pathlib import Path
-from typing import TYPE_CHECKING
-from typing import Self
-
-import httpx
-from django.conf import settings
-from django.utils import timezone
-from gotenberg_client import GotenbergClient
-from gotenberg_client.options import PdfAFormat
-from tika_client import TikaClient
-
-from documents.parsers import ParseError
-from documents.parsers import make_thumbnail_from_pdf
-from paperless.config import OutputTypeConfig
-from paperless.models import OutputTypeChoices
-from paperless.version import __full_version_str__
-
-if TYPE_CHECKING:
-    import datetime
-    from types import TracebackType
-
-    from paperless.parsers import MetadataEntry
-
-logger = logging.getLogger("paperless.parsing.tika")
-
-_SUPPORTED_MIME_TYPES: dict[str, str] = {
-    "application/msword": ".doc",
-    "application/vnd.openxmlformats-officedocument.wordprocessingml.document": ".docx",
-    "application/vnd.ms-excel": ".xls",
-    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet": ".xlsx",
-    "application/vnd.ms-powerpoint": ".ppt",
-    "application/vnd.openxmlformats-officedocument.presentationml.presentation": ".pptx",
-    "application/vnd.openxmlformats-officedocument.presentationml.slideshow": ".ppsx",
-    "application/vnd.oasis.opendocument.presentation": ".odp",
-    "application/vnd.oasis.opendocument.spreadsheet": ".ods",
-    "application/vnd.oasis.opendocument.text": ".odt",
-    "application/vnd.oasis.opendocument.graphics": ".odg",
-    "text/rtf": ".rtf",
-}
-
-
-class TikaDocumentParser:
-    """Parse Office documents via Apache Tika and Gotenberg for Paperless-ngx.
-
-    Text extraction is handled by the Tika server.  PDF conversion for display
-    is handled by Gotenberg (LibreOffice route).  Because the source formats
-    cannot be rendered by a browser natively, ``requires_pdf_rendition`` is
-    True and the PDF is always produced regardless of the ``produce_archive``
-    flag passed to ``parse``.
-
-    Both ``TikaClient`` and ``GotenbergClient`` are opened once in
-    ``__enter__`` via an ``ExitStack`` and shared across ``parse``,
-    ``extract_metadata``, and ``_convert_to_pdf`` calls, then closed via
-    ``ExitStack.close()`` in ``__exit__``.  The parser must always be used
-    as a context manager.
-
-    Class attributes
-    ----------------
-    name : str
-        Human-readable parser name.
-    version : str
-        Semantic version string, kept in sync with Paperless-ngx releases.
-    author : str
-        Maintainer name.
-    url : str
-        Issue tracker / source URL.
-    """
-
-    name: str = "Paperless-ngx Tika Parser"
-    version: str = __full_version_str__
-    author: str = "Paperless-ngx Contributors"
-    url: str = "https://github.com/paperless-ngx/paperless-ngx"
-
-    # ------------------------------------------------------------------
-    # Class methods
-    # ------------------------------------------------------------------
-
-    @classmethod
-    def supported_mime_types(cls) -> dict[str, str]:
-        """Return the MIME types this parser handles.
-
-        Returns
-        -------
-        dict[str, str]
-            Mapping of MIME type to preferred file extension.
-        """
-        return _SUPPORTED_MIME_TYPES
-
-    @classmethod
-    def score(
-        cls,
-        mime_type: str,
-        filename: str,
-        path: Path | None = None,
-    ) -> int | None:
-        """Return the priority score for handling this file.
-
-        Returns ``None`` when Tika integration is disabled so the registry
-        skips this parser entirely.
-
-        Parameters
-        ----------
-        mime_type:
-            Detected MIME type of the file.
-        filename:
-            Original filename including extension.
-        path:
-            Optional filesystem path. Not inspected by this parser.
-
-        Returns
-        -------
-        int | None
-            10 if TIKA_ENABLED and the MIME type is supported, otherwise None.
-        """
-        if not settings.TIKA_ENABLED:
-            return None
-        if mime_type in _SUPPORTED_MIME_TYPES:
-            return 10
-        return None
-
-    # ------------------------------------------------------------------
-    # Properties
-    # ------------------------------------------------------------------
-
-    @property
-    def can_produce_archive(self) -> bool:
-        """Whether this parser can produce a searchable PDF archive copy.
-
-        Returns
-        -------
-        bool
-            Always False — Tika produces a display PDF, not an OCR archive.
-        """
-        return False
-
-    @property
-    def requires_pdf_rendition(self) -> bool:
-        """Whether the parser must produce a PDF for the frontend to display.
-
-        Returns
-        -------
-        bool
-            Always True — Office formats cannot be rendered natively in a
-            browser, so a PDF conversion is always required for display.
-        """
-        return True
-
-    # ------------------------------------------------------------------
-    # Lifecycle
-    # ------------------------------------------------------------------
-
-    def __init__(self, logging_group: object = None) -> None:
-        settings.SCRATCH_DIR.mkdir(parents=True, exist_ok=True)
-        self._tempdir = Path(
-            tempfile.mkdtemp(prefix="paperless-", dir=settings.SCRATCH_DIR),
-        )
-        self._text: str | None = None
-        self._date: datetime.datetime | None = None
-        self._archive_path: Path | None = None
-        self._exit_stack = ExitStack()
-        self._tika_client: TikaClient | None = None
-        self._gotenberg_client: GotenbergClient | None = None
-
-    def __enter__(self) -> Self:
-        self._tika_client = self._exit_stack.enter_context(
-            TikaClient(
-                tika_url=settings.TIKA_ENDPOINT,
-                timeout=settings.CELERY_TASK_TIME_LIMIT,
-            ),
-        )
-        self._gotenberg_client = self._exit_stack.enter_context(
-            GotenbergClient(
-                host=settings.TIKA_GOTENBERG_ENDPOINT,
-                timeout=settings.CELERY_TASK_TIME_LIMIT,
-            ),
-        )
-        return self
-
-    def __exit__(
-        self,
-        exc_type: type[BaseException] | None,
-        exc_val: BaseException | None,
-        exc_tb: TracebackType | None,
-    ) -> None:
-        self._exit_stack.close()
-        logger.debug("Cleaning up temporary directory %s", self._tempdir)
-        shutil.rmtree(self._tempdir, ignore_errors=True)
-
-    # ------------------------------------------------------------------
-    # Core parsing interface
-    # ------------------------------------------------------------------
-
-    def parse(
-        self,
-        document_path: Path,
-        mime_type: str,
-        *,
-        produce_archive: bool = True,
-    ) -> None:
-        """Send the document to Tika for text extraction and Gotenberg for PDF.
-
-        Because ``requires_pdf_rendition`` is True the PDF conversion is
-        always performed — the ``produce_archive`` flag is intentionally
-        ignored.
-
-        Parameters
-        ----------
-        document_path:
-            Absolute path to the document file to parse.
-        mime_type:
-            Detected MIME type of the document.
-        produce_archive:
-            Accepted for protocol compatibility but ignored; the PDF rendition
-            is always produced since the source format cannot be displayed
-            natively in the browser.
-
-        Raises
-        ------
-        documents.parsers.ParseError
-            If Tika or Gotenberg returns an error.
-        """
-        if TYPE_CHECKING:
-            assert self._tika_client is not None
-
-        logger.info("Sending %s to Tika server", document_path)
-
-        try:
-            try:
-                parsed = self._tika_client.tika.as_text.from_file(
-                    document_path,
-                    mime_type,
-                )
-            except httpx.HTTPStatusError as err:
-                # Workaround https://issues.apache.org/jira/browse/TIKA-4110
-                # Tika fails with some files as multi-part form data
-                if err.response.status_code == httpx.codes.INTERNAL_SERVER_ERROR:
-                    parsed = self._tika_client.tika.as_text.from_buffer(
-                        document_path.read_bytes(),
-                        mime_type,
-                    )
-                else:  # pragma: no cover
-                    raise
-        except Exception as err:
-            raise ParseError(
-                f"Could not parse {document_path} with tika server at "
-                f"{settings.TIKA_ENDPOINT}: {err}",
-            ) from err
-
-        self._text = parsed.content
-        if self._text is not None:
-            self._text = self._text.strip()
-
-        self._date = parsed.created
-        if self._date is not None and timezone.is_naive(self._date):
-            self._date = timezone.make_aware(self._date)
-
-        # Always convert — requires_pdf_rendition=True means the browser
-        # cannot display the source format natively.
-        self._archive_path = self._convert_to_pdf(document_path)
-
-    # ------------------------------------------------------------------
-    # Result accessors
-    # ------------------------------------------------------------------
-
-    def get_text(self) -> str | None:
-        """Return the plain-text content extracted during parse.
-
-        Returns
-        -------
-        str | None
-            Extracted text, or None if parse has not been called yet.
-        """
-        return self._text
-
-    def get_date(self) -> datetime.datetime | None:
-        """Return the document date detected during parse.
-
-        Returns
-        -------
-        datetime.datetime | None
-            Creation date from Tika metadata, or None if not detected.
-        """
-        return self._date
-
-    def get_archive_path(self) -> Path | None:
-        """Return the path to the generated PDF rendition, or None.
-
-        Returns
-        -------
-        Path | None
-            Path to the PDF produced by Gotenberg, or None if parse has not
-            been called yet.
-        """
-        return self._archive_path
-
-    # ------------------------------------------------------------------
-    # Thumbnail and metadata
-    # ------------------------------------------------------------------
-
-    def get_thumbnail(self, document_path: Path, mime_type: str) -> Path:
-        """Generate a thumbnail from the PDF rendition of the document.
-
-        Converts the document to PDF first if not already done.
-
-        Parameters
-        ----------
-        document_path:
-            Absolute path to the source document.
-        mime_type:
-            Detected MIME type of the document.
-
-        Returns
-        -------
-        Path
-            Path to the generated WebP thumbnail inside the temporary directory.
-        """
-        if self._archive_path is None:
-            self._archive_path = self._convert_to_pdf(document_path)
-        return make_thumbnail_from_pdf(self._archive_path, self._tempdir)
-
-    def get_page_count(
-        self,
-        document_path: Path,
-        mime_type: str,
-    ) -> int | None:
-        """Return the number of pages in the document.
-
-        Returns
-        -------
-        int | None
-            Always None — page count is not available from Tika.
-        """
-        return None
-
-    def extract_metadata(
-        self,
-        document_path: Path,
-        mime_type: str,
-    ) -> list[MetadataEntry]:
-        """Extract format-specific metadata via the Tika metadata endpoint.
-
-        Returns
-        -------
-        list[MetadataEntry]
-            All key/value pairs returned by Tika, or ``[]`` on error.
-        """
-        if TYPE_CHECKING:
-            assert self._tika_client is not None
-
-        try:
-            parsed = self._tika_client.metadata.from_file(document_path, mime_type)
-            return [
-                {
-                    "namespace": "",
-                    "prefix": "",
-                    "key": key,
-                    "value": parsed.data[key],
-                }
-                for key in parsed.data
-            ]
-        except Exception as e:
-            logger.warning(
-                "Error while fetching document metadata for %s: %s",
-                document_path,
-                e,
-            )
-            return []
-
-    # ------------------------------------------------------------------
-    # Private helpers
-    # ------------------------------------------------------------------
-
-    def _convert_to_pdf(self, document_path: Path) -> Path:
-        """Convert the document to PDF using Gotenberg's LibreOffice route.
-
-        Parameters
-        ----------
-        document_path:
-            Absolute path to the source document.
-
-        Returns
-        -------
-        Path
-            Path to the generated PDF inside the temporary directory.
-
-        Raises
-        ------
-        documents.parsers.ParseError
-            If Gotenberg returns an error.
-        """
-        if TYPE_CHECKING:
-            assert self._gotenberg_client is not None
-
-        pdf_path = self._tempdir / "convert.pdf"
-
-        logger.info("Converting %s to PDF as %s", document_path, pdf_path)
-
-        with self._gotenberg_client.libre_office.to_pdf() as route:
-            # Set the output format of the resulting PDF.
-            # OutputTypeConfig reads the database-stored ApplicationConfiguration
-            # first, then falls back to the PAPERLESS_OCR_OUTPUT_TYPE env var.
-            output_type = OutputTypeConfig().output_type
-            if output_type in {
-                OutputTypeChoices.PDF_A,
-                OutputTypeChoices.PDF_A2,
-            }:
-                route.pdf_format(PdfAFormat.A2b)
-            elif output_type == OutputTypeChoices.PDF_A1:
-                logger.warning(
-                    "Gotenberg does not support PDF/A-1a, choosing PDF/A-2b instead",
-                )
-                route.pdf_format(PdfAFormat.A2b)
-            elif output_type == OutputTypeChoices.PDF_A3:
-                route.pdf_format(PdfAFormat.A3b)
-
-            route.convert(document_path)
-
-            try:
-                response = route.run()
-                pdf_path.write_bytes(response.content)
-                return pdf_path
-            except Exception as err:
-                raise ParseError(
-                    f"Error while converting document to PDF: {err}",
-                ) from err

src/paperless/serialisers.py

@@ -6,6 +6,7 @@ from allauth.mfa.models import Authenticator
 from allauth.mfa.totp.internal.auth import TOTP
 from allauth.socialaccount.models import SocialAccount
 from allauth.socialaccount.models import SocialApp
+from django.conf import settings
 from django.contrib.auth.models import Group
 from django.contrib.auth.models import Permission
 from django.contrib.auth.models import User
@@ -15,6 +16,7 @@ from rest_framework import serializers
 from rest_framework.authtoken.serializers import AuthTokenSerializer
 
 from paperless.models import ApplicationConfiguration
+from paperless.network import validate_outbound_http_url
 from paperless.validators import reject_dangerous_svg
 from paperless_mail.serialisers import ObfuscatedPasswordField
 
@@ -236,6 +238,20 @@ class ApplicationConfigurationSerializer(serializers.ModelSerializer):
             reject_dangerous_svg(file)
         return file
 
+    def validate_llm_endpoint(self, value: str | None) -> str | None:
+        if not value:
+            return value
+
+        try:
+            validate_outbound_http_url(
+                value,
+                allow_internal=settings.LLM_ALLOW_INTERNAL_ENDPOINTS,
+            )
+        except ValueError as e:
+            raise serializers.ValidationError(str(e)) from e
+
+        return value
+
     class Meta:
         model = ApplicationConfiguration
         fields = "__all__"

src/paperless/settings/__init__.py

@@ -1112,3 +1112,7 @@ LLM_BACKEND = os.getenv("PAPERLESS_AI_LLM_BACKEND")  # "ollama" or "openai"
 LLM_MODEL = os.getenv("PAPERLESS_AI_LLM_MODEL")
 LLM_API_KEY = os.getenv("PAPERLESS_AI_LLM_API_KEY")
 LLM_ENDPOINT = os.getenv("PAPERLESS_AI_LLM_ENDPOINT")
+LLM_ALLOW_INTERNAL_ENDPOINTS = get_bool_from_env(
+    "PAPERLESS_AI_LLM_ALLOW_INTERNAL_ENDPOINTS",
+    "true",
+)

src/paperless/settings/custom.py

@@ -209,7 +209,6 @@ def parse_db_settings(data_dir: Path) -> dict[str, dict[str, Any]]:
         engine = get_choice_from_env(
             "PAPERLESS_DBENGINE",
             {"sqlite", "postgresql", "mariadb"},
-            default="sqlite",
         )
     except ValueError:
         # MariaDB users already had to set PAPERLESS_DBENGINE, so it was picked up above

src/paperless/tests/conftest.py

@@ -1,48 +0,0 @@
-"""
-Fixtures defined here are available to every test module under
-src/paperless/tests/ (including sub-packages such as parsers/).
-
-Session-scoped fixtures for the shared samples directory live here so
-sub-package conftest files can reference them without duplicating path logic.
-Parser-specific fixtures (concrete parser instances, format-specific sample
-files) live in paperless/tests/parsers/conftest.py.
-"""
-
-from __future__ import annotations
-
-from pathlib import Path
-from typing import TYPE_CHECKING
-
-import pytest
-
-from paperless.parsers.registry import reset_parser_registry
-
-if TYPE_CHECKING:
-    from collections.abc import Generator
-
-
-@pytest.fixture(scope="session")
-def samples_dir() -> Path:
-    """Absolute path to the shared parser sample files directory.
-
-    Sub-package conftest files derive format-specific paths from this root,
-    e.g. ``samples_dir / "text" / "test.txt"``.
-
-    Returns
-    -------
-    Path
-        Directory containing all sample documents used by parser tests.
-    """
-    return (Path(__file__).parent / "samples").resolve()
-
-
-@pytest.fixture(autouse=True)
-def clean_registry() -> Generator[None, None, None]:
-    """Reset the parser registry before and after every test.
-
-    This prevents registry state from leaking between tests that call
-    get_parser_registry() or init_builtin_parsers().
-    """
-    reset_parser_registry()
-    yield
-    reset_parser_registry()

src/paperless/tests/parsers/conftest.py

@@ -1,160 +0,0 @@
-"""
-Parser fixtures that are used across multiple test modules in this package
-are defined here.  Format-specific sample-file fixtures are grouped by parser
-so it is easy to see which files belong to which test module.
-"""
-
-from __future__ import annotations
-
-from typing import TYPE_CHECKING
-
-import pytest
-
-from paperless.parsers.text import TextDocumentParser
-from paperless.parsers.tika import TikaDocumentParser
-
-if TYPE_CHECKING:
-    from collections.abc import Generator
-    from pathlib import Path
-
-
-# ------------------------------------------------------------------
-# Text parser sample files
-# ------------------------------------------------------------------
-
-
-@pytest.fixture(scope="session")
-def text_samples_dir(samples_dir: Path) -> Path:
-    """Absolute path to the text parser sample files directory.
-
-    Returns
-    -------
-    Path
-        ``<samples_dir>/text/``
-    """
-    return samples_dir / "text"
-
-
-@pytest.fixture(scope="session")
-def sample_txt_file(text_samples_dir: Path) -> Path:
-    """Path to a valid UTF-8 plain-text sample file.
-
-    Returns
-    -------
-    Path
-        Absolute path to ``text/test.txt``.
-    """
-    return text_samples_dir / "test.txt"
-
-
-@pytest.fixture(scope="session")
-def malformed_txt_file(text_samples_dir: Path) -> Path:
-    """Path to a text file containing invalid UTF-8 bytes.
-
-    Returns
-    -------
-    Path
-        Absolute path to ``text/decode_error.txt``.
-    """
-    return text_samples_dir / "decode_error.txt"
-
-
-# ------------------------------------------------------------------
-# Text parser instance
-# ------------------------------------------------------------------
-
-
-@pytest.fixture()
-def text_parser() -> Generator[TextDocumentParser, None, None]:
-    """Yield a TextDocumentParser and clean up its temporary directory afterwards.
-
-    Yields
-    ------
-    TextDocumentParser
-        A ready-to-use parser instance.
-    """
-    with TextDocumentParser() as parser:
-        yield parser
-
-
-# ------------------------------------------------------------------
-# Tika parser sample files
-# ------------------------------------------------------------------
-
-
-@pytest.fixture(scope="session")
-def tika_samples_dir(samples_dir: Path) -> Path:
-    """Absolute path to the Tika parser sample files directory.
-
-    Returns
-    -------
-    Path
-        ``<samples_dir>/tika/``
-    """
-    return samples_dir / "tika"
-
-
-@pytest.fixture(scope="session")
-def sample_odt_file(tika_samples_dir: Path) -> Path:
-    """Path to a sample ODT file.
-
-    Returns
-    -------
-    Path
-        Absolute path to ``tika/sample.odt``.
-    """
-    return tika_samples_dir / "sample.odt"
-
-
-@pytest.fixture(scope="session")
-def sample_docx_file(tika_samples_dir: Path) -> Path:
-    """Path to a sample DOCX file.
-
-    Returns
-    -------
-    Path
-        Absolute path to ``tika/sample.docx``.
-    """
-    return tika_samples_dir / "sample.docx"
-
-
-@pytest.fixture(scope="session")
-def sample_doc_file(tika_samples_dir: Path) -> Path:
-    """Path to a sample DOC file.
-
-    Returns
-    -------
-    Path
-        Absolute path to ``tika/sample.doc``.
-    """
-    return tika_samples_dir / "sample.doc"
-
-
-@pytest.fixture(scope="session")
-def sample_broken_odt(tika_samples_dir: Path) -> Path:
-    """Path to a broken ODT file that triggers the multi-part fallback.
-
-    Returns
-    -------
-    Path
-        Absolute path to ``tika/multi-part-broken.odt``.
-    """
-    return tika_samples_dir / "multi-part-broken.odt"
-
-
-# ------------------------------------------------------------------
-# Tika parser instance
-# ------------------------------------------------------------------
-
-
-@pytest.fixture()
-def tika_parser() -> Generator[TikaDocumentParser, None, None]:
-    """Yield a TikaDocumentParser and clean up its temporary directory afterwards.
-
-    Yields
-    ------
-    TikaDocumentParser
-        A ready-to-use parser instance.
-    """
-    with TikaDocumentParser() as parser:
-        yield parser

src/paperless/tests/parsers/test_text_parser.py

@@ -1,256 +0,0 @@
-"""
-Tests for paperless.parsers.text.TextDocumentParser.
-
-All tests use the context-manager protocol for parser lifecycle.  Sample
-files are provided by session-scoped fixtures defined in conftest.py.
-"""
-
-from __future__ import annotations
-
-import tempfile
-from pathlib import Path
-
-import pytest
-
-from paperless.parsers import ParserProtocol
-from paperless.parsers.text import TextDocumentParser
-
-
-class TestTextParserProtocol:
-    """Verify that TextDocumentParser satisfies the ParserProtocol contract."""
-
-    def test_isinstance_satisfies_protocol(
-        self,
-        text_parser: TextDocumentParser,
-    ) -> None:
-        assert isinstance(text_parser, ParserProtocol)
-
-    def test_class_attributes_present(self) -> None:
-        assert isinstance(TextDocumentParser.name, str) and TextDocumentParser.name
-        assert (
-            isinstance(TextDocumentParser.version, str) and TextDocumentParser.version
-        )
-        assert isinstance(TextDocumentParser.author, str) and TextDocumentParser.author
-        assert isinstance(TextDocumentParser.url, str) and TextDocumentParser.url
-
-    def test_supported_mime_types_returns_dict(self) -> None:
-        mime_types = TextDocumentParser.supported_mime_types()
-        assert isinstance(mime_types, dict)
-        assert "text/plain" in mime_types
-        assert "text/csv" in mime_types
-        assert "application/csv" in mime_types
-
-    @pytest.mark.parametrize(
-        ("mime_type", "expected"),
-        [
-            ("text/plain", 10),
-            ("text/csv", 10),
-            ("application/csv", 10),
-            ("application/pdf", None),
-            ("image/png", None),
-        ],
-    )
-    def test_score(self, mime_type: str, expected: int | None) -> None:
-        assert TextDocumentParser.score(mime_type, "file.txt") == expected
-
-    def test_can_produce_archive_is_false(
-        self,
-        text_parser: TextDocumentParser,
-    ) -> None:
-        assert text_parser.can_produce_archive is False
-
-    def test_requires_pdf_rendition_is_false(
-        self,
-        text_parser: TextDocumentParser,
-    ) -> None:
-        assert text_parser.requires_pdf_rendition is False
-
-
-class TestTextParserLifecycle:
-    """Verify context-manager behaviour and temporary directory cleanup."""
-
-    def test_context_manager_cleans_up_tempdir(self) -> None:
-        with TextDocumentParser() as parser:
-            tempdir = parser._tempdir
-            assert tempdir.exists()
-        assert not tempdir.exists()
-
-    def test_context_manager_cleans_up_after_exception(self) -> None:
-        tempdir: Path | None = None
-        with pytest.raises(RuntimeError):
-            with TextDocumentParser() as parser:
-                tempdir = parser._tempdir
-                raise RuntimeError("boom")
-        assert tempdir is not None
-        assert not tempdir.exists()
-
-
-class TestTextParserParse:
-    """Verify parse() and the result accessors."""
-
-    def test_parse_valid_utf8(
-        self,
-        text_parser: TextDocumentParser,
-        sample_txt_file: Path,
-    ) -> None:
-        text_parser.parse(sample_txt_file, "text/plain")
-
-        assert text_parser.get_text() == "This is a test file.\n"
-
-    def test_parse_returns_none_for_archive_path(
-        self,
-        text_parser: TextDocumentParser,
-        sample_txt_file: Path,
-    ) -> None:
-        text_parser.parse(sample_txt_file, "text/plain")
-
-        assert text_parser.get_archive_path() is None
-
-    def test_parse_returns_none_for_date(
-        self,
-        text_parser: TextDocumentParser,
-        sample_txt_file: Path,
-    ) -> None:
-        text_parser.parse(sample_txt_file, "text/plain")
-
-        assert text_parser.get_date() is None
-
-    def test_parse_invalid_utf8_bytes_replaced(
-        self,
-        text_parser: TextDocumentParser,
-        malformed_txt_file: Path,
-    ) -> None:
-        """
-        GIVEN:
-            - A text file containing invalid UTF-8 byte sequences
-        WHEN:
-            - The file is parsed
-        THEN:
-            - Parsing succeeds
-            - Invalid bytes are replaced with the Unicode replacement character
-        """
-        text_parser.parse(malformed_txt_file, "text/plain")
-
-        assert text_parser.get_text() == "Pantothens\ufffdure\n"
-
-    def test_get_text_none_before_parse(
-        self,
-        text_parser: TextDocumentParser,
-    ) -> None:
-        assert text_parser.get_text() is None
-
-
-class TestTextParserThumbnail:
-    """Verify thumbnail generation."""
-
-    def test_thumbnail_exists_and_is_file(
-        self,
-        text_parser: TextDocumentParser,
-        sample_txt_file: Path,
-    ) -> None:
-        thumb = text_parser.get_thumbnail(sample_txt_file, "text/plain")
-
-        assert thumb.exists()
-        assert thumb.is_file()
-
-    def test_thumbnail_large_file_does_not_read_all(
-        self,
-        text_parser: TextDocumentParser,
-    ) -> None:
-        """
-        GIVEN:
-            - A text file larger than 50 MB
-        WHEN:
-            - A thumbnail is requested
-        THEN:
-            - The thumbnail is generated without loading the full file
-        """
-        with tempfile.NamedTemporaryFile(
-            delete=False,
-            mode="w",
-            encoding="utf-8",
-            suffix=".txt",
-        ) as tmp:
-            tmp.write("A" * (51 * 1024 * 1024))
-            large_file = Path(tmp.name)
-
-        try:
-            thumb = text_parser.get_thumbnail(large_file, "text/plain")
-            assert thumb.exists()
-            assert thumb.is_file()
-        finally:
-            large_file.unlink(missing_ok=True)
-
-    def test_get_page_count_returns_none(
-        self,
-        text_parser: TextDocumentParser,
-        sample_txt_file: Path,
-    ) -> None:
-        assert text_parser.get_page_count(sample_txt_file, "text/plain") is None
-
-
-class TestTextParserMetadata:
-    """Verify extract_metadata behaviour."""
-
-    def test_extract_metadata_returns_empty_list(
-        self,
-        text_parser: TextDocumentParser,
-        sample_txt_file: Path,
-    ) -> None:
-        result = text_parser.extract_metadata(sample_txt_file, "text/plain")
-
-        assert result == []
-
-    def test_extract_metadata_returns_list_type(
-        self,
-        text_parser: TextDocumentParser,
-        sample_txt_file: Path,
-    ) -> None:
-        result = text_parser.extract_metadata(sample_txt_file, "text/plain")
-
-        assert isinstance(result, list)
-
-    def test_extract_metadata_ignores_mime_type(
-        self,
-        text_parser: TextDocumentParser,
-        sample_txt_file: Path,
-    ) -> None:
-        """extract_metadata returns [] regardless of the mime_type argument."""
-        assert text_parser.extract_metadata(sample_txt_file, "application/pdf") == []
-        assert text_parser.extract_metadata(sample_txt_file, "text/csv") == []
-
-
-class TestTextParserRegistry:
-    """Verify that TextDocumentParser is registered by default."""
-
-    def test_registered_in_defaults(self) -> None:
-        from paperless.parsers.registry import ParserRegistry
-
-        registry = ParserRegistry()
-        registry.register_defaults()
-
-        assert TextDocumentParser in registry._builtins
-
-    def test_get_parser_for_text_plain(self) -> None:
-        from paperless.parsers.registry import get_parser_registry
-
-        registry = get_parser_registry()
-        parser_cls = registry.get_parser_for_file("text/plain", "doc.txt")
-
-        assert parser_cls is TextDocumentParser
-
-    def test_get_parser_for_text_csv(self) -> None:
-        from paperless.parsers.registry import get_parser_registry
-
-        registry = get_parser_registry()
-        parser_cls = registry.get_parser_for_file("text/csv", "data.csv")
-
-        assert parser_cls is TextDocumentParser
-
-    def test_get_parser_for_unknown_type_returns_none(self) -> None:
-        from paperless.parsers.registry import get_parser_registry
-
-        registry = get_parser_registry()
-        parser_cls = registry.get_parser_for_file("application/pdf", "doc.pdf")
-
-        assert parser_cls is None

src/paperless/tests/test_checks.py

@@ -581,11 +581,11 @@ class TestV3MinimumUpgradeVersionCheck:
     ) -> None:
         """
         GIVEN:
-            - DB is on an old v2 version (pre-v2.20.9)
+            - DB is on an old v2 version (pre-v2.20.10)
         WHEN:
             - The v3 upgrade check runs
         THEN:
-            - The error hint explicitly references v2.20.9 so users know what to do
+            - The error hint explicitly references v2.20.10 so users know what to do
         """
         mocker.patch.dict(
             "paperless.checks.connections",
@@ -593,7 +593,7 @@ class TestV3MinimumUpgradeVersionCheck:
         )
         result = check_v3_minimum_upgrade_version(None)
         assert len(result) == 1
-        assert "v2.20.9" in result[0].hint
+        assert "v2.20.10" in result[0].hint
 
     def test_db_error_is_swallowed(self, mocker: MockerFixture) -> None:
         """

src/paperless/tests/test_registry.py

@@ -1,714 +0,0 @@
-"""
-Tests for :mod:`paperless.parsers` (ParserProtocol) and
-:mod:`paperless.parsers.registry` (ParserRegistry + module-level helpers).
-
-All tests use pytest-style functions/classes — no unittest.TestCase.
-The ``clean_registry`` fixture ensures complete isolation between tests by
-resetting the module-level singleton before and after every test.
-"""
-
-from __future__ import annotations
-
-import logging
-from importlib.metadata import EntryPoint
-from pathlib import Path
-from typing import Self
-from unittest.mock import MagicMock
-from unittest.mock import patch
-
-import pytest
-
-from paperless.parsers import ParserProtocol
-from paperless.parsers.registry import ParserRegistry
-from paperless.parsers.registry import get_parser_registry
-from paperless.parsers.registry import init_builtin_parsers
-from paperless.parsers.registry import reset_parser_registry
-
-
-@pytest.fixture()
-def dummy_parser_cls() -> type:
-    """Return a class that fully satisfies :class:`ParserProtocol`.
-
-    GIVEN: A need to exercise registry and Protocol logic with a minimal
-           but complete parser.
-    WHEN:  A test requests this fixture.
-    THEN:  A class with all required attributes and methods is returned.
-    """
-
-    class DummyParser:
-        name = "dummy-parser"
-        version = "0.1.0"
-        author = "Test Author"
-        url = "https://example.com/dummy-parser"
-
-        @classmethod
-        def supported_mime_types(cls) -> dict[str, str]:
-            return {"text/plain": ".txt"}
-
-        @classmethod
-        def score(
-            cls,
-            mime_type: str,
-            filename: str,
-            path: Path | None = None,
-        ) -> int | None:
-            return 10
-
-        @property
-        def can_produce_archive(self) -> bool:
-            return False
-
-        @property
-        def requires_pdf_rendition(self) -> bool:
-            return False
-
-        def parse(
-            self,
-            document_path: Path,
-            mime_type: str,
-            *,
-            produce_archive: bool = True,
-        ) -> None:
-            """
-            Required to exist, but doesn't need to do anything
-            """
-
-        def get_text(self) -> str | None:
-            return None
-
-        def get_date(self) -> None:
-            return None
-
-        def get_archive_path(self) -> Path | None:
-            return None
-
-        def get_thumbnail(
-            self,
-            document_path: Path,
-            mime_type: str,
-        ) -> Path:
-            return Path("/tmp/thumbnail.webp")
-
-        def get_page_count(
-            self,
-            document_path: Path,
-            mime_type: str,
-        ) -> int | None:
-            return None
-
-        def extract_metadata(
-            self,
-            document_path: Path,
-            mime_type: str,
-        ) -> list:
-            return []
-
-        def __enter__(self) -> Self:
-            return self
-
-        def __exit__(self, exc_type, exc_val, exc_tb) -> None:
-            """
-            Required to exist, but doesn't need to do anything
-            """
-
-    return DummyParser
-
-
-class TestParserProtocol:
-    """Verify runtime isinstance() checks against ParserProtocol."""
-
-    def test_compliant_class_instance_passes_isinstance(
-        self,
-        dummy_parser_cls: type,
-    ) -> None:
-        """
-        GIVEN: A class that implements every method required by ParserProtocol.
-        WHEN:  isinstance() is called with the Protocol.
-        THEN:  The check passes (returns True).
-        """
-        instance = dummy_parser_cls()
-        assert isinstance(instance, ParserProtocol)
-
-    def test_non_compliant_class_instance_fails_isinstance(self) -> None:
-        """
-        GIVEN: A plain class with no parser-related methods.
-        WHEN:  isinstance() is called with ParserProtocol.
-        THEN:  The check fails (returns False).
-        """
-
-        class Unrelated:
-            pass
-
-        assert not isinstance(Unrelated(), ParserProtocol)
-
-    @pytest.mark.parametrize(
-        "missing_method",
-        [
-            pytest.param("parse", id="missing-parse"),
-            pytest.param("get_text", id="missing-get_text"),
-            pytest.param("get_thumbnail", id="missing-get_thumbnail"),
-            pytest.param("__enter__", id="missing-__enter__"),
-            pytest.param("__exit__", id="missing-__exit__"),
-        ],
-    )
-    def test_partial_compliant_fails_isinstance(
-        self,
-        dummy_parser_cls: type,
-        missing_method: str,
-    ) -> None:
-        """
-        GIVEN: A class that satisfies ParserProtocol except for one method.
-        WHEN:  isinstance() is called with ParserProtocol.
-        THEN:  The check fails because the Protocol is not fully satisfied.
-        """
-        # Create a subclass and delete the specified method to break compliance.
-        partial_cls = type(
-            "PartialParser",
-            (dummy_parser_cls,),
-            {missing_method: None},  # Replace with None — not callable
-        )
-        assert not isinstance(partial_cls(), ParserProtocol)
-
-
-class TestRegistrySingleton:
-    """Verify the module-level singleton lifecycle functions."""
-
-    def test_get_parser_registry_returns_instance(self) -> None:
-        """
-        GIVEN: No registry has been created yet.
-        WHEN:  get_parser_registry() is called.
-        THEN:  A ParserRegistry instance is returned.
-        """
-        registry = get_parser_registry()
-        assert isinstance(registry, ParserRegistry)
-
-    def test_get_parser_registry_same_instance_on_repeated_calls(self) -> None:
-        """
-        GIVEN: A registry instance was created by a prior call.
-        WHEN:  get_parser_registry() is called a second time.
-        THEN:  The exact same object (identity) is returned.
-        """
-        first = get_parser_registry()
-        second = get_parser_registry()
-        assert first is second
-
-    def test_reset_parser_registry_gives_fresh_instance(self) -> None:
-        """
-        GIVEN: A registry instance already exists.
-        WHEN:  reset_parser_registry() is called and then get_parser_registry()
-               is called again.
-        THEN:  A new, distinct registry instance is returned.
-        """
-        first = get_parser_registry()
-        reset_parser_registry()
-        second = get_parser_registry()
-        assert first is not second
-
-    def test_init_builtin_parsers_does_not_run_discover(
-        self,
-        monkeypatch: pytest.MonkeyPatch,
-    ) -> None:
-        """
-        GIVEN: discover() would raise an exception if called.
-        WHEN:  init_builtin_parsers() is called.
-        THEN:  No exception is raised, confirming discover() was not invoked.
-        """
-
-        def exploding_discover(self) -> None:
-            raise RuntimeError(
-                "discover() must not be called from init_builtin_parsers",
-            )
-
-        monkeypatch.setattr(ParserRegistry, "discover", exploding_discover)
-
-        # Should complete without raising.
-        init_builtin_parsers()
-
-    def test_init_builtin_parsers_idempotent(self) -> None:
-        """
-        GIVEN: init_builtin_parsers() has already been called once.
-        WHEN:  init_builtin_parsers() is called a second time.
-        THEN:  No error is raised and the same registry instance is reused.
-        """
-        init_builtin_parsers()
-        # Capture the registry created by the first call.
-        import paperless.parsers.registry as reg_module
-
-        first_registry = reg_module._registry
-
-        init_builtin_parsers()
-
-        assert reg_module._registry is first_registry
-
-
-class TestParserRegistryGetParserForFile:
-    """Verify parser selection logic in get_parser_for_file()."""
-
-    def test_returns_none_when_no_parsers_registered(self) -> None:
-        """
-        GIVEN: A registry with no parsers registered.
-        WHEN:  get_parser_for_file() is called for any MIME type.
-        THEN:  None is returned.
-        """
-        registry = ParserRegistry()
-        result = registry.get_parser_for_file("text/plain", "doc.txt")
-        assert result is None
-
-    def test_returns_none_for_unsupported_mime_type(
-        self,
-        dummy_parser_cls: type,
-    ) -> None:
-        """
-        GIVEN: A registry with a parser that supports only 'text/plain'.
-        WHEN:  get_parser_for_file() is called with 'application/pdf'.
-        THEN:  None is returned.
-        """
-        registry = ParserRegistry()
-        registry.register_builtin(dummy_parser_cls)
-        result = registry.get_parser_for_file("application/pdf", "file.pdf")
-        assert result is None
-
-    def test_returns_parser_for_supported_mime_type(
-        self,
-        dummy_parser_cls: type,
-    ) -> None:
-        """
-        GIVEN: A registry with a parser registered for 'text/plain'.
-        WHEN:  get_parser_for_file() is called with 'text/plain'.
-        THEN:  The registered parser class is returned.
-        """
-        registry = ParserRegistry()
-        registry.register_builtin(dummy_parser_cls)
-        result = registry.get_parser_for_file("text/plain", "readme.txt")
-        assert result is dummy_parser_cls
-
-    def test_highest_score_wins(self) -> None:
-        """
-        GIVEN: Two parsers both supporting 'text/plain' with scores 5 and 20.
-        WHEN:  get_parser_for_file() is called for 'text/plain'.
-        THEN:  The parser with score 20 is returned.
-        """
-
-        class LowScoreParser:
-            name = "low"
-            version = "1.0"
-            author = "A"
-            url = "https://example.com/low"
-
-            @classmethod
-            def supported_mime_types(cls):
-                return {"text/plain": ".txt"}
-
-            @classmethod
-            def score(cls, mime_type, filename, path=None):
-                return 5
-
-        class HighScoreParser:
-            name = "high"
-            version = "1.0"
-            author = "B"
-            url = "https://example.com/high"
-
-            @classmethod
-            def supported_mime_types(cls):
-                return {"text/plain": ".txt"}
-
-            @classmethod
-            def score(cls, mime_type, filename, path=None):
-                return 20
-
-        registry = ParserRegistry()
-        registry.register_builtin(LowScoreParser)
-        registry.register_builtin(HighScoreParser)
-        result = registry.get_parser_for_file("text/plain", "readme.txt")
-        assert result is HighScoreParser
-
-    def test_parser_returning_none_score_is_skipped(self) -> None:
-        """
-        GIVEN: A parser that returns None from score() for the given file.
-        WHEN:  get_parser_for_file() is called.
-        THEN:  That parser is skipped and None is returned (no other candidates).
-        """
-
-        class DecliningParser:
-            name = "declining"
-            version = "1.0"
-            author = "A"
-            url = "https://example.com"
-
-            @classmethod
-            def supported_mime_types(cls):
-                return {"text/plain": ".txt"}
-
-            @classmethod
-            def score(cls, mime_type, filename, path=None):
-                return None  # Explicitly declines
-
-        registry = ParserRegistry()
-        registry.register_builtin(DecliningParser)
-        result = registry.get_parser_for_file("text/plain", "readme.txt")
-        assert result is None
-
-    def test_all_parsers_decline_returns_none(self) -> None:
-        """
-        GIVEN: Multiple parsers that all return None from score().
-        WHEN:  get_parser_for_file() is called.
-        THEN:  None is returned.
-        """
-
-        class AlwaysDeclines:
-            name = "declines"
-            version = "1.0"
-            author = "A"
-            url = "https://example.com"
-
-            @classmethod
-            def supported_mime_types(cls):
-                return {"text/plain": ".txt"}
-
-            @classmethod
-            def score(cls, mime_type, filename, path=None):
-                return None
-
-        registry = ParserRegistry()
-        registry.register_builtin(AlwaysDeclines)
-        registry._external.append(AlwaysDeclines)
-        result = registry.get_parser_for_file("text/plain", "file.txt")
-        assert result is None
-
-    def test_external_parser_beats_builtin_same_score(self) -> None:
-        """
-        GIVEN: An external and a built-in parser both returning score 10.
-        WHEN:  get_parser_for_file() is called.
-        THEN:  The external parser wins because externals are evaluated first
-               and the first-seen-wins policy applies at equal scores.
-        """
-
-        class BuiltinParser:
-            name = "builtin"
-            version = "1.0"
-            author = "Core"
-            url = "https://example.com/builtin"
-
-            @classmethod
-            def supported_mime_types(cls):
-                return {"text/plain": ".txt"}
-
-            @classmethod
-            def score(cls, mime_type, filename, path=None):
-                return 10
-
-        class ExternalParser:
-            name = "external"
-            version = "2.0"
-            author = "Third Party"
-            url = "https://example.com/external"
-
-            @classmethod
-            def supported_mime_types(cls):
-                return {"text/plain": ".txt"}
-
-            @classmethod
-            def score(cls, mime_type, filename, path=None):
-                return 10
-
-        registry = ParserRegistry()
-        registry.register_builtin(BuiltinParser)
-        registry._external.append(ExternalParser)
-        result = registry.get_parser_for_file("text/plain", "file.txt")
-        assert result is ExternalParser
-
-    def test_builtin_wins_when_external_declines(self) -> None:
-        """
-        GIVEN: An external parser that declines (score None) and a built-in
-               that returns score 5.
-        WHEN:  get_parser_for_file() is called.
-        THEN:  The built-in parser is returned.
-        """
-
-        class DecliningExternal:
-            name = "declining-external"
-            version = "1.0"
-            author = "Third Party"
-            url = "https://example.com/declining"
-
-            @classmethod
-            def supported_mime_types(cls):
-                return {"text/plain": ".txt"}
-
-            @classmethod
-            def score(cls, mime_type, filename, path=None):
-                return None
-
-        class AcceptingBuiltin:
-            name = "accepting-builtin"
-            version = "1.0"
-            author = "Core"
-            url = "https://example.com/accepting"
-
-            @classmethod
-            def supported_mime_types(cls):
-                return {"text/plain": ".txt"}
-
-            @classmethod
-            def score(cls, mime_type, filename, path=None):
-                return 5
-
-        registry = ParserRegistry()
-        registry.register_builtin(AcceptingBuiltin)
-        registry._external.append(DecliningExternal)
-        result = registry.get_parser_for_file("text/plain", "file.txt")
-        assert result is AcceptingBuiltin
-
-
-class TestDiscover:
-    """Verify entrypoint discovery in ParserRegistry.discover()."""
-
-    def test_discover_with_no_entrypoints(self) -> None:
-        """
-        GIVEN: No entrypoints are registered under 'paperless_ngx.parsers'.
-        WHEN:  discover() is called.
-        THEN:  _external remains empty and no errors are raised.
-        """
-        registry = ParserRegistry()
-
-        with patch(
-            "paperless.parsers.registry.entry_points",
-            return_value=[],
-        ):
-            registry.discover()
-
-        assert registry._external == []
-
-    def test_discover_adds_valid_external_parser(self) -> None:
-        """
-        GIVEN: One valid entrypoint whose loaded class has all required attrs.
-        WHEN:  discover() is called.
-        THEN:  The class is appended to _external.
-        """
-
-        class ValidExternal:
-            name = "valid-external"
-            version = "3.0.0"
-            author = "Someone"
-            url = "https://example.com/valid"
-
-            @classmethod
-            def supported_mime_types(cls):
-                return {"application/pdf": ".pdf"}
-
-            @classmethod
-            def score(cls, mime_type, filename, path=None):
-                return 5
-
-        mock_ep = MagicMock(spec=EntryPoint)
-        mock_ep.name = "valid_external"
-        mock_ep.load.return_value = ValidExternal
-
-        registry = ParserRegistry()
-
-        with patch(
-            "paperless.parsers.registry.entry_points",
-            return_value=[mock_ep],
-        ):
-            registry.discover()
-
-        assert ValidExternal in registry._external
-
-    def test_discover_skips_entrypoint_with_load_error(
-        self,
-        caplog: pytest.LogCaptureFixture,
-    ) -> None:
-        """
-        GIVEN: An entrypoint whose load() method raises ImportError.
-        WHEN:  discover() is called.
-        THEN:  The entrypoint is skipped, an error is logged, and _external
-               remains empty.
-        """
-        mock_ep = MagicMock(spec=EntryPoint)
-        mock_ep.name = "broken_ep"
-        mock_ep.load.side_effect = ImportError("missing dependency")
-
-        registry = ParserRegistry()
-
-        with caplog.at_level(logging.ERROR, logger="paperless.parsers.registry"):
-            with patch(
-                "paperless.parsers.registry.entry_points",
-                return_value=[mock_ep],
-            ):
-                registry.discover()
-
-        assert registry._external == []
-        assert any(
-            "broken_ep" in record.message
-            for record in caplog.records
-            if record.levelno >= logging.ERROR
-        )
-
-    def test_discover_skips_entrypoint_with_missing_attrs(
-        self,
-        caplog: pytest.LogCaptureFixture,
-    ) -> None:
-        """
-        GIVEN: A class loaded from an entrypoint that is missing the 'score'
-               attribute.
-        WHEN:  discover() is called.
-        THEN:  The entrypoint is skipped, a warning is logged, and _external
-               remains empty.
-        """
-
-        class MissingScore:
-            name = "missing-score"
-            version = "1.0"
-            author = "Someone"
-            url = "https://example.com"
-
-            # 'score' classmethod is intentionally absent.
-
-            @classmethod
-            def supported_mime_types(cls):
-                return {"text/plain": ".txt"}
-
-        mock_ep = MagicMock(spec=EntryPoint)
-        mock_ep.name = "missing_score_ep"
-        mock_ep.load.return_value = MissingScore
-
-        registry = ParserRegistry()
-
-        with caplog.at_level(logging.WARNING, logger="paperless.parsers.registry"):
-            with patch(
-                "paperless.parsers.registry.entry_points",
-                return_value=[mock_ep],
-            ):
-                registry.discover()
-
-        assert registry._external == []
-        assert any(
-            "missing_score_ep" in record.message
-            for record in caplog.records
-            if record.levelno >= logging.WARNING
-        )
-
-    def test_discover_logs_loaded_parser_info(
-        self,
-        caplog: pytest.LogCaptureFixture,
-    ) -> None:
-        """
-        GIVEN: A valid entrypoint that loads successfully.
-        WHEN:  discover() is called.
-        THEN:  An INFO log message is emitted containing the parser name,
-               version, author, and entrypoint name.
-        """
-
-        class LoggableParser:
-            name = "loggable"
-            version = "4.2.0"
-            author = "Log Tester"
-            url = "https://example.com/loggable"
-
-            @classmethod
-            def supported_mime_types(cls):
-                return {"image/png": ".png"}
-
-            @classmethod
-            def score(cls, mime_type, filename, path=None):
-                return 1
-
-        mock_ep = MagicMock(spec=EntryPoint)
-        mock_ep.name = "loggable_ep"
-        mock_ep.load.return_value = LoggableParser
-
-        registry = ParserRegistry()
-
-        with caplog.at_level(logging.INFO, logger="paperless.parsers.registry"):
-            with patch(
-                "paperless.parsers.registry.entry_points",
-                return_value=[mock_ep],
-            ):
-                registry.discover()
-
-        info_messages = " ".join(
-            r.message for r in caplog.records if r.levelno == logging.INFO
-        )
-        assert "loggable" in info_messages
-        assert "4.2.0" in info_messages
-        assert "Log Tester" in info_messages
-        assert "loggable_ep" in info_messages
-
-
-class TestLogSummary:
-    """Verify log output from ParserRegistry.log_summary()."""
-
-    def test_log_summary_with_no_external_parsers(
-        self,
-        dummy_parser_cls: type,
-        caplog: pytest.LogCaptureFixture,
-    ) -> None:
-        """
-        GIVEN: A registry with one built-in parser and no external parsers.
-        WHEN:  log_summary() is called.
-        THEN:  The built-in parser name appears in the logs.
-        """
-        registry = ParserRegistry()
-        registry.register_builtin(dummy_parser_cls)
-
-        with caplog.at_level(logging.INFO, logger="paperless.parsers.registry"):
-            registry.log_summary()
-
-        all_messages = " ".join(r.message for r in caplog.records)
-        assert dummy_parser_cls.name in all_messages
-
-    def test_log_summary_with_external_parsers(
-        self,
-        caplog: pytest.LogCaptureFixture,
-    ) -> None:
-        """
-        GIVEN: A registry with one external parser registered.
-        WHEN:  log_summary() is called.
-        THEN:  The external parser name, version, author, and url appear in
-               the log output.
-        """
-
-        class ExtParser:
-            name = "ext-parser"
-            version = "9.9.9"
-            author = "Ext Corp"
-            url = "https://ext.example.com"
-
-            @classmethod
-            def supported_mime_types(cls):
-                return {}
-
-            @classmethod
-            def score(cls, mime_type, filename, path=None):
-                return None
-
-        registry = ParserRegistry()
-        registry._external.append(ExtParser)
-
-        with caplog.at_level(logging.INFO, logger="paperless.parsers.registry"):
-            registry.log_summary()
-
-        all_messages = " ".join(r.message for r in caplog.records)
-        assert "ext-parser" in all_messages
-        assert "9.9.9" in all_messages
-        assert "Ext Corp" in all_messages
-        assert "https://ext.example.com" in all_messages
-
-    def test_log_summary_logs_no_third_party_message_when_none(
-        self,
-        caplog: pytest.LogCaptureFixture,
-    ) -> None:
-        """
-        GIVEN: A registry with no external parsers.
-        WHEN:  log_summary() is called.
-        THEN:  A message containing 'No third-party parsers discovered.' is
-               logged.
-        """
-        registry = ParserRegistry()
-
-        with caplog.at_level(logging.INFO, logger="paperless.parsers.registry"):
-            registry.log_summary()
-
-        all_messages = " ".join(r.message for r in caplog.records)
-        assert "No third-party parsers discovered." in all_messages

src/paperless/urls.py

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

src/paperless_ai/client.py

@@ -7,6 +7,7 @@ if TYPE_CHECKING:
     from llama_index.llms.openai import OpenAI
 
 from paperless.config import AIConfig
+from paperless.network import validate_outbound_http_url
 from paperless_ai.base_model import DocumentClassifierSchema
 
 logger = logging.getLogger("paperless_ai.client")
@@ -25,17 +26,28 @@ class AIClient:
         if self.settings.llm_backend == "ollama":
             from llama_index.llms.ollama import Ollama
 
+            endpoint = self.settings.llm_endpoint or "http://localhost:11434"
+            validate_outbound_http_url(
+                endpoint,
+                allow_internal=self.settings.llm_allow_internal_endpoints,
+            )
             return Ollama(
                 model=self.settings.llm_model or "llama3.1",
-                base_url=self.settings.llm_endpoint or "http://localhost:11434",
+                base_url=endpoint,
                 request_timeout=120,
             )
         elif self.settings.llm_backend == "openai":
             from llama_index.llms.openai import OpenAI
 
+            endpoint = self.settings.llm_endpoint or None
+            if endpoint:
+                validate_outbound_http_url(
+                    endpoint,
+                    allow_internal=self.settings.llm_allow_internal_endpoints,
+                )
             return OpenAI(
                 model=self.settings.llm_model or "gpt-3.5-turbo",
-                api_base=self.settings.llm_endpoint or None,
+                api_base=endpoint,
                 api_key=self.settings.llm_api_key,
             )
         else:

src/paperless_ai/embedding.py

@@ -12,6 +12,7 @@ from documents.models import Document
 from documents.models import Note
 from paperless.config import AIConfig
 from paperless.models import LLMEmbeddingBackend
+from paperless.network import validate_outbound_http_url
 
 
 def get_embedding_model() -> "BaseEmbedding":
@@ -21,10 +22,16 @@ def get_embedding_model() -> "BaseEmbedding":
         case LLMEmbeddingBackend.OPENAI:
             from llama_index.embeddings.openai import OpenAIEmbedding
 
+            endpoint = config.llm_endpoint or None
+            if endpoint:
+                validate_outbound_http_url(
+                    endpoint,
+                    allow_internal=config.llm_allow_internal_endpoints,
+                )
             return OpenAIEmbedding(
                 model=config.llm_embedding_model or "text-embedding-3-small",
                 api_key=config.llm_api_key,
-                api_base=config.llm_endpoint or None,
+                api_base=endpoint,
             )
         case LLMEmbeddingBackend.HUGGINGFACE:
             from llama_index.embeddings.huggingface import HuggingFaceEmbedding

src/paperless_ai/tests/test_client.py

@@ -12,6 +12,7 @@ from paperless_ai.client import AIClient
 def mock_ai_config():
     with patch("paperless_ai.client.AIConfig") as MockAIConfig:
         mock_config = MagicMock()
+        mock_config.llm_allow_internal_endpoints = True
         MockAIConfig.return_value = mock_config
         yield mock_config
 
@@ -59,6 +60,17 @@ def test_get_llm_openai(mock_ai_config, mock_openai_llm):
     assert client.llm == mock_openai_llm.return_value
 
 
+def test_get_llm_openai_blocks_internal_endpoint_when_disallowed(mock_ai_config):
+    mock_ai_config.llm_backend = "openai"
+    mock_ai_config.llm_model = "test_model"
+    mock_ai_config.llm_api_key = "test_api_key"
+    mock_ai_config.llm_endpoint = "http://127.0.0.1:1234"
+    mock_ai_config.llm_allow_internal_endpoints = False
+
+    with pytest.raises(ValueError, match="non-public address"):
+        AIClient()
+
+
 def test_get_llm_unsupported_backend(mock_ai_config):
     mock_ai_config.llm_backend = "unsupported"
 

src/paperless_ai/tests/test_embedding.py

@@ -15,6 +15,7 @@ from paperless_ai.embedding import get_embedding_model
 @pytest.fixture
 def mock_ai_config():
     with patch("paperless_ai.embedding.AIConfig") as MockAIConfig:
+        MockAIConfig.return_value.llm_allow_internal_endpoints = True
         yield MockAIConfig
 
 
@@ -77,6 +78,19 @@ def test_get_embedding_model_openai(mock_ai_config):
         assert model == MockOpenAIEmbedding.return_value
 
 
+def test_get_embedding_model_openai_blocks_internal_endpoint_when_disallowed(
+    mock_ai_config,
+):
+    mock_ai_config.return_value.llm_embedding_backend = LLMEmbeddingBackend.OPENAI
+    mock_ai_config.return_value.llm_embedding_model = "text-embedding-3-small"
+    mock_ai_config.return_value.llm_api_key = "test_api_key"
+    mock_ai_config.return_value.llm_endpoint = "http://127.0.0.1:11434"
+    mock_ai_config.return_value.llm_allow_internal_endpoints = False
+
+    with pytest.raises(ValueError, match="non-public address"):
+        get_embedding_model()
+
+
 def test_get_embedding_model_huggingface(mock_ai_config):
     mock_ai_config.return_value.llm_embedding_backend = LLMEmbeddingBackend.HUGGINGFACE
     mock_ai_config.return_value.llm_embedding_model = (

src/paperless_text/parsers.py

@@ -0,0 +1,50 @@
+from pathlib import Path
+
+from django.conf import settings
+from PIL import Image
+from PIL import ImageDraw
+from PIL import ImageFont
+
+from documents.parsers import DocumentParser
+
+
+class TextDocumentParser(DocumentParser):
+    """
+    This parser directly parses a text document (.txt, .md, or .csv)
+    """
+
+    logging_name = "paperless.parsing.text"
+
+    def get_thumbnail(self, document_path: Path, mime_type, file_name=None) -> Path:
+        # Avoid reading entire file into memory
+        max_chars = 100_000
+        file_size_limit = 50 * 1024 * 1024
+
+        if document_path.stat().st_size > file_size_limit:
+            text = "[File too large to preview]"
+        else:
+            with Path(document_path).open("r", encoding="utf-8", errors="replace") as f:
+                text = f.read(max_chars)
+
+        img = Image.new("RGB", (500, 700), color="white")
+        draw = ImageDraw.Draw(img)
+        font = ImageFont.truetype(
+            font=settings.THUMBNAIL_FONT_NAME,
+            size=20,
+            layout_engine=ImageFont.Layout.BASIC,
+        )
+        draw.multiline_text((5, 5), text, font=font, fill="black", spacing=4)
+
+        out_path = self.tempdir / "thumb.webp"
+        img.save(out_path, format="WEBP")
+
+        return out_path
+
+    def parse(self, document_path, mime_type, file_name=None) -> None:
+        self.text = self.read_file_handle_unicode_errors(document_path)
+
+    def get_settings(self) -> None:
+        """
+        This parser does not implement additional settings yet
+        """
+        return None

src/paperless_text/signals.py

@@ -1,13 +1,7 @@
 def get_parser(*args, **kwargs):
-    from paperless.parsers.text import TextDocumentParser
+    from paperless_text.parsers import TextDocumentParser
 
-    # The new TextDocumentParser does not accept the legacy logging_group /
-    # progress_callback kwargs injected by the old signal-based consumer.
-    # These are dropped here; Phase 4 will replace this signal path with the
-    # new ParserRegistry so the shim can be removed at that point.
-    kwargs.pop("logging_group", None)
-    kwargs.pop("progress_callback", None)
-    return TextDocumentParser()
+    return TextDocumentParser(*args, **kwargs)
 
 
 def text_consumer_declaration(sender, **kwargs):

src/paperless_text/tests/conftest.py

@@ -0,0 +1,30 @@
+from collections.abc import Generator
+from pathlib import Path
+
+import pytest
+
+from paperless_text.parsers import TextDocumentParser
+
+
+@pytest.fixture(scope="session")
+def sample_dir() -> Path:
+    return (Path(__file__).parent / Path("samples")).resolve()
+
+
+@pytest.fixture()
+def text_parser() -> Generator[TextDocumentParser, None, None]:
+    try:
+        parser = TextDocumentParser(logging_group=None)
+        yield parser
+    finally:
+        parser.cleanup()
+
+
+@pytest.fixture(scope="session")
+def sample_txt_file(sample_dir: Path) -> Path:
+    return sample_dir / "test.txt"
+
+
+@pytest.fixture(scope="session")
+def malformed_txt_file(sample_dir: Path) -> Path:
+    return sample_dir / "decode_error.txt"

src/paperless_text/tests/test_parser.py

@@ -0,0 +1,69 @@
+import tempfile
+from pathlib import Path
+
+from paperless_text.parsers import TextDocumentParser
+
+
+class TestTextParser:
+    def test_thumbnail(
+        self,
+        text_parser: TextDocumentParser,
+        sample_txt_file: Path,
+    ) -> None:
+        # just make sure that it does not crash
+        f = text_parser.get_thumbnail(sample_txt_file, "text/plain")
+        assert f.exists()
+        assert f.is_file()
+
+    def test_parse(
+        self,
+        text_parser: TextDocumentParser,
+        sample_txt_file: Path,
+    ) -> None:
+        text_parser.parse(sample_txt_file, "text/plain")
+
+        assert text_parser.get_text() == "This is a test file.\n"
+        assert text_parser.get_archive_path() is None
+
+    def test_parse_invalid_bytes(
+        self,
+        text_parser: TextDocumentParser,
+        malformed_txt_file: Path,
+    ) -> None:
+        """
+        GIVEN:
+            - Text file which contains invalid UTF bytes
+        WHEN:
+            - The file is parsed
+        THEN:
+            - Parsing continues
+            - Invalid bytes are removed
+        """
+
+        text_parser.parse(malformed_txt_file, "text/plain")
+
+        assert text_parser.get_text() == "Pantothens<EFBFBD>ure\n"
+        assert text_parser.get_archive_path() is None
+
+    def test_thumbnail_large_file(self, text_parser: TextDocumentParser) -> None:
+        """
+        GIVEN:
+            - A very large text file (>50MB)
+        WHEN:
+            - A thumbnail is requested
+        THEN:
+            - A thumbnail is created without reading the entire file into memory
+        """
+        with tempfile.NamedTemporaryFile(
+            delete=False,
+            mode="w",
+            encoding="utf-8",
+            suffix=".txt",
+        ) as tmp:
+            tmp.write("A" * (51 * 1024 * 1024))  # 51 MB of 'A'
+            large_file = Path(tmp.name)
+
+            thumb = text_parser.get_thumbnail(large_file, "text/plain")
+            assert thumb.exists()
+            assert thumb.is_file()
+            large_file.unlink()

src/paperless_tika/parsers.py

@@ -0,0 +1,136 @@
+from pathlib import Path
+
+import httpx
+from django.conf import settings
+from django.utils import timezone
+from gotenberg_client import GotenbergClient
+from gotenberg_client.options import PdfAFormat
+from tika_client import TikaClient
+
+from documents.parsers import DocumentParser
+from documents.parsers import ParseError
+from documents.parsers import make_thumbnail_from_pdf
+from paperless.config import OutputTypeConfig
+from paperless.models import OutputTypeChoices
+
+
+class TikaDocumentParser(DocumentParser):
+    """
+    This parser sends documents to a local tika server
+    """
+
+    logging_name = "paperless.parsing.tika"
+
+    def get_thumbnail(self, document_path, mime_type, file_name=None):
+        if not self.archive_path:
+            self.archive_path = self.convert_to_pdf(document_path, file_name)
+
+        return make_thumbnail_from_pdf(
+            self.archive_path,
+            self.tempdir,
+            self.logging_group,
+        )
+
+    def extract_metadata(self, document_path, mime_type):
+        try:
+            with TikaClient(
+                tika_url=settings.TIKA_ENDPOINT,
+                timeout=settings.CELERY_TASK_TIME_LIMIT,
+            ) as client:
+                parsed = client.metadata.from_file(document_path, mime_type)
+                return [
+                    {
+                        "namespace": "",
+                        "prefix": "",
+                        "key": key,
+                        "value": parsed.data[key],
+                    }
+                    for key in parsed.data
+                ]
+        except Exception as e:
+            self.log.warning(
+                f"Error while fetching document metadata for {document_path}: {e}",
+            )
+            return []
+
+    def parse(self, document_path: Path, mime_type: str, file_name=None) -> None:
+        self.log.info(f"Sending {document_path} to Tika server")
+
+        try:
+            with TikaClient(
+                tika_url=settings.TIKA_ENDPOINT,
+                timeout=settings.CELERY_TASK_TIME_LIMIT,
+            ) as client:
+                try:
+                    parsed = client.tika.as_text.from_file(document_path, mime_type)
+                except httpx.HTTPStatusError as err:
+                    # Workaround https://issues.apache.org/jira/browse/TIKA-4110
+                    # Tika fails with some files as multi-part form data
+                    if err.response.status_code == httpx.codes.INTERNAL_SERVER_ERROR:
+                        parsed = client.tika.as_text.from_buffer(
+                            document_path.read_bytes(),
+                            mime_type,
+                        )
+                    else:  # pragma: no cover
+                        raise
+        except Exception as err:
+            raise ParseError(
+                f"Could not parse {document_path} with tika server at "
+                f"{settings.TIKA_ENDPOINT}: {err}",
+            ) from err
+
+        self.text = parsed.content
+        if self.text is not None:
+            self.text = self.text.strip()
+
+        self.date = parsed.created
+        if self.date is not None and timezone.is_naive(self.date):
+            self.date = timezone.make_aware(self.date)
+
+        self.archive_path = self.convert_to_pdf(document_path, file_name)
+
+    def convert_to_pdf(self, document_path: Path, file_name):
+        pdf_path = Path(self.tempdir) / "convert.pdf"
+
+        self.log.info(f"Converting {document_path} to PDF as {pdf_path}")
+
+        with (
+            GotenbergClient(
+                host=settings.TIKA_GOTENBERG_ENDPOINT,
+                timeout=settings.CELERY_TASK_TIME_LIMIT,
+            ) as client,
+            client.libre_office.to_pdf() as route,
+        ):
+            # Set the output format of the resulting PDF
+            if settings.OCR_OUTPUT_TYPE in {
+                OutputTypeChoices.PDF_A,
+                OutputTypeChoices.PDF_A2,
+            }:
+                route.pdf_format(PdfAFormat.A2b)
+            elif settings.OCR_OUTPUT_TYPE == OutputTypeChoices.PDF_A1:
+                self.log.warning(
+                    "Gotenberg does not support PDF/A-1a, choosing PDF/A-2b instead",
+                )
+                route.pdf_format(PdfAFormat.A2b)
+            elif settings.OCR_OUTPUT_TYPE == OutputTypeChoices.PDF_A3:
+                route.pdf_format(PdfAFormat.A3b)
+
+            route.convert(document_path)
+
+            try:
+                response = route.run()
+
+                pdf_path.write_bytes(response.content)
+
+                return pdf_path
+
+            except Exception as err:
+                raise ParseError(
+                    f"Error while converting document to PDF: {err}",
+                ) from err
+
+    def get_settings(self) -> OutputTypeConfig:
+        """
+        This parser only uses the PDF output type configuration currently
+        """
+        return OutputTypeConfig()

src/paperless_tika/signals.py

@@ -1,13 +1,7 @@
 def get_parser(*args, **kwargs):
-    from paperless.parsers.tika import TikaDocumentParser
+    from paperless_tika.parsers import TikaDocumentParser
 
-    # The new TikaDocumentParser does not accept the legacy logging_group /
-    # progress_callback kwargs injected by the old signal-based consumer.
-    # These are dropped here; Phase 4 will replace this signal path with the
-    # new ParserRegistry so the shim can be removed at that point.
-    kwargs.pop("logging_group", None)
-    kwargs.pop("progress_callback", None)
-    return TikaDocumentParser()
+    return TikaDocumentParser(*args, **kwargs)
 
 
 def tika_consumer_declaration(sender, **kwargs):

src/paperless_tika/tests/conftest.py

@@ -0,0 +1,40 @@
+from collections.abc import Generator
+from pathlib import Path
+
+import pytest
+
+from paperless_tika.parsers import TikaDocumentParser
+
+
+@pytest.fixture()
+def tika_parser() -> Generator[TikaDocumentParser, None, None]:
+    try:
+        parser = TikaDocumentParser(logging_group=None)
+        yield parser
+    finally:
+        parser.cleanup()
+
+
+@pytest.fixture(scope="session")
+def sample_dir() -> Path:
+    return (Path(__file__).parent / Path("samples")).resolve()
+
+
+@pytest.fixture(scope="session")
+def sample_odt_file(sample_dir: Path) -> Path:
+    return sample_dir / "sample.odt"
+
+
+@pytest.fixture(scope="session")
+def sample_docx_file(sample_dir: Path) -> Path:
+    return sample_dir / "sample.docx"
+
+
+@pytest.fixture(scope="session")
+def sample_doc_file(sample_dir: Path) -> Path:
+    return sample_dir / "sample.doc"
+
+
+@pytest.fixture(scope="session")
+def sample_broken_odt(sample_dir: Path) -> Path:
+    return sample_dir / "multi-part-broken.odt"