Whoops, the tagged PDF check catches our fixture sample files, which broke these

- configuration.md: replace PAPERLESS_OCR_SKIP_ARCHIVE_FILE section with
  PAPERLESS_ARCHIVE_FILE_GENERATION; update OCR_MODE docs to reflect auto
  as default and document new 'off' mode
- setup.md: update resource-constrained device tip to use new setting names
- migration-v3.md: add OCR and archive settings section documenting all
  removed settings, their replacements, and migration examples

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

.gitignore

@@ -111,3 +111,4 @@ celerybeat-schedule*
 
 # ignore pnpm package store folder created when setting up the devcontainer
 .pnpm-store/
+.worktrees

.mypy-baseline.txt

@@ -2437,17 +2437,3 @@ src/paperless_tesseract/tests/test_parser_custom_settings.py:0: error: Item "Non
 src/paperless_tesseract/tests/test_parser_custom_settings.py:0: error: Item "None" of "ApplicationConfiguration | None" has no attribute "unpaper_clean"  [union-attr]
 src/paperless_tesseract/tests/test_parser_custom_settings.py:0: error: Item "None" of "ApplicationConfiguration | None" has no attribute "unpaper_clean"  [union-attr]
 src/paperless_tesseract/tests/test_parser_custom_settings.py:0: error: Item "None" of "ApplicationConfiguration | None" has no attribute "user_args"  [union-attr]
-src/paperless_text/parsers.py:0: error: Function is missing a type annotation for one or more arguments  [no-untyped-def]
-src/paperless_text/parsers.py:0: error: Function is missing a type annotation for one or more arguments  [no-untyped-def]
-src/paperless_text/parsers.py:0: error: Incompatible types in assignment (expression has type "str", variable has type "None")  [assignment]
-src/paperless_text/signals.py:0: error: Function is missing a type annotation  [no-untyped-def]
-src/paperless_text/signals.py:0: error: Function is missing a type annotation  [no-untyped-def]
-src/paperless_tika/parsers.py:0: error: Argument 1 to "make_thumbnail_from_pdf" has incompatible type "None"; expected "Path"  [arg-type]
-src/paperless_tika/parsers.py:0: error: Function is missing a return type annotation  [no-untyped-def]
-src/paperless_tika/parsers.py:0: error: Function is missing a type annotation  [no-untyped-def]
-src/paperless_tika/parsers.py:0: error: Function is missing a type annotation  [no-untyped-def]
-src/paperless_tika/parsers.py:0: error: Function is missing a type annotation for one or more arguments  [no-untyped-def]
-src/paperless_tika/parsers.py:0: error: Function is missing a type annotation for one or more arguments  [no-untyped-def]
-src/paperless_tika/parsers.py:0: error: Incompatible types in assignment (expression has type "str | None", variable has type "None")  [assignment]
-src/paperless_tika/signals.py:0: error: Function is missing a type annotation  [no-untyped-def]
-src/paperless_tika/signals.py:0: error: Function is missing a type annotation  [no-untyped-def]

docs/configuration.md

@@ -801,11 +801,14 @@ parsing documents.
 
 #### [`PAPERLESS_OCR_MODE=<mode>`](#PAPERLESS_OCR_MODE) {#PAPERLESS_OCR_MODE}
 
-: Tell paperless when and how to perform ocr on your documents. Three
+: Tell paperless when and how to perform ocr on your documents. Four
 modes are available:
 
-    -   `skip`: Paperless skips all pages and will perform ocr only on
-        pages where no text is present. This is the safest option.
+    -   `auto` (default): Paperless detects whether a document already
+        has embedded text via pdftotext. If sufficient text is found,
+        OCR is skipped for that document (`--skip-text`). If no text is
+        present, OCR runs normally. This is the safest option for mixed
+        document collections.
 
     -   `redo`: Paperless will OCR all pages of your documents and
         attempt to replace any existing text layers with new text. This
@@ -823,24 +826,58 @@ modes are available:
         significantly larger and text won't appear as sharp when zoomed
         in.
 
-    The default is `skip`, which only performs OCR when necessary and
-    always creates archived documents.
+    -   `off`: Paperless never invokes the OCR engine. For PDFs, text
+        is extracted via pdftotext only. For image documents, text will
+        be empty. Archive file generation still works via format
+        conversion (no Tesseract or Ghostscript required).
+
+    The default is `auto`.
 
     Read more about this in the [OCRmyPDF
     documentation](https://ocrmypdf.readthedocs.io/en/latest/advanced.html#when-ocr-is-skipped).
 
-#### [`PAPERLESS_OCR_SKIP_ARCHIVE_FILE=<mode>`](#PAPERLESS_OCR_SKIP_ARCHIVE_FILE) {#PAPERLESS_OCR_SKIP_ARCHIVE_FILE}
+#### [`PAPERLESS_ARCHIVE_FILE_GENERATION=<mode>`](#PAPERLESS_ARCHIVE_FILE_GENERATION) {#PAPERLESS_ARCHIVE_FILE_GENERATION}
 
-: Specify when you would like paperless to skip creating an archived
-version of your documents. This is useful if you don't want to have two
-almost-identical versions of your documents in the media folder.
+: Controls when paperless creates a PDF/A archive version of your
+documents. Archive files are stored alongside the original and are used
+for display in the web interface.
 
-    -   `never`: Never skip creating an archived version.
-    -   `with_text`: Skip creating an archived version for documents
-    that already have embedded text.
-    -   `always`: Always skip creating an archived version.
+    -   `auto` (default): Produce archives for scanned or image-based
+        documents. Skip archive generation for born-digital PDFs that
+        already contain embedded text. This is the recommended setting
+        for mixed document collections.
+    -   `always`: Always produce a PDF/A archive when the parser
+        supports it, regardless of whether the document already has
+        text.
+    -   `never`: Never produce an archive. Only the original file is
+        stored. Saves disk space but the web viewer will display the
+        original file directly.
 
-    The default is `never`.
+    **Behaviour by file type and mode** (`auto` column shows the default):
+
+    | Document type              | `never` | `auto` (default)           | `always` |
+    | -------------------------- | ------- | -------------------------- | -------- |
+    | Scanned image (TIFF, JPEG) | No      | **Yes**                    | Yes      |
+    | Image-based PDF            | No      | **Yes** (short/no text, untagged) | Yes |
+    | Born-digital PDF           | No      | No (tagged or has embedded text)  | Yes |
+    | Plain text, email, HTML    | No      | No                         | No       |
+    | DOCX / ODT (via Tika)      | Yes\*   | Yes\*                      | Yes\*    |
+
+    \* Tika always produces a PDF rendition for display; this counts as
+    the archive regardless of the setting.
+
+    !!! note
+
+        This setting applies to the built-in Tesseract parser. Parsers
+        that must always convert documents to PDF for display (e.g. DOCX,
+        ODT via Tika) will produce a PDF regardless of this setting.
+
+    !!! note
+
+        The **remote OCR parser** (Azure AI) always produces a searchable
+        PDF and stores it as the archive copy, regardless of this setting.
+        `ARCHIVE_FILE_GENERATION=never` has no effect when the remote
+        parser handles a document.
 
 #### [`PAPERLESS_OCR_CLEAN=<mode>`](#PAPERLESS_OCR_CLEAN) {#PAPERLESS_OCR_CLEAN}
 

docs/migration-v3.md

@@ -104,6 +104,65 @@ Multiple options are combined in a single value:
 PAPERLESS_DB_OPTIONS="sslmode=require;sslrootcert=/certs/ca.pem;pool.max_size=10"
 ```
 
+## OCR and Archive File Generation Settings
+
+The settings that control OCR behaviour and archive file generation have been redesigned. The old settings that coupled these two concerns together are **removed** — there are no migration shims.
+
+### Removed settings
+
+| Removed Setting                             | Replacement                                                           |
+| ------------------------------------------- | --------------------------------------------------------------------- |
+| `PAPERLESS_OCR_MODE=skip`                   | `PAPERLESS_OCR_MODE=auto` (new default)                               |
+| `PAPERLESS_OCR_MODE=skip_noarchive`         | `PAPERLESS_OCR_MODE=auto` + `PAPERLESS_ARCHIVE_FILE_GENERATION=never` |
+| `PAPERLESS_OCR_SKIP_ARCHIVE_FILE=never`     | `PAPERLESS_ARCHIVE_FILE_GENERATION=always`                            |
+| `PAPERLESS_OCR_SKIP_ARCHIVE_FILE=with_text` | `PAPERLESS_ARCHIVE_FILE_GENERATION=auto` (new default)                |
+| `PAPERLESS_OCR_SKIP_ARCHIVE_FILE=always`    | `PAPERLESS_ARCHIVE_FILE_GENERATION=never`                             |
+
+### What changed and why
+
+Previously, `OCR_MODE` conflated two independent concerns: whether to run OCR and whether to produce an archive. `skip` meant "skip OCR if text exists, but always produce an archive". `skip_noarchive` meant "skip OCR if text exists, and also skip the archive". This made it impossible to, for example, disable OCR entirely while still producing archives.
+
+The new settings are independent:
+
+- [`PAPERLESS_OCR_MODE`](configuration.md#PAPERLESS_OCR_MODE) controls OCR: `auto` (default), `force`, `redo`, `off`.
+- [`PAPERLESS_ARCHIVE_FILE_GENERATION`](configuration.md#PAPERLESS_ARCHIVE_FILE_GENERATION) controls archive production: `auto` (default), `always`, `never`.
+
+### Action Required
+
+Remove any `PAPERLESS_OCR_SKIP_ARCHIVE_FILE` variable from your environment. If you relied on `OCR_MODE=skip` or `OCR_MODE=skip_noarchive`, update accordingly:
+
+```bash
+# v2: skip OCR when text present, always archive
+PAPERLESS_OCR_MODE=skip
+# v3: equivalent (auto is the new default)
+# No change needed — auto is the default
+
+# v2: skip OCR when text present, skip archive too
+PAPERLESS_OCR_MODE=skip_noarchive
+# v3: equivalent
+PAPERLESS_OCR_MODE=auto
+PAPERLESS_ARCHIVE_FILE_GENERATION=never
+
+# v2: always skip archive
+PAPERLESS_OCR_SKIP_ARCHIVE_FILE=always
+# v3: equivalent
+PAPERLESS_ARCHIVE_FILE_GENERATION=never
+
+# v2: skip archive only for born-digital docs
+PAPERLESS_OCR_SKIP_ARCHIVE_FILE=with_text
+# v3: equivalent (auto is the new default)
+PAPERLESS_ARCHIVE_FILE_GENERATION=auto
+```
+
+Paperless will emit a startup warning if the old environment variables are still set.
+
+### Remote OCR parser
+
+If you use the **remote OCR parser** (Azure AI), note that it always produces a
+searchable PDF and stores it as the archive copy. `ARCHIVE_FILE_GENERATION=never`
+has no effect for documents handled by the remote parser — the archive is produced
+unconditionally by the remote engine.
+
 ## OpenID Connect Token Endpoint Authentication
 
 Some existing OpenID Connect setups may require an explicit token endpoint authentication method after upgrading to v3.

docs/setup.md

@@ -633,12 +633,11 @@ hardware, but a few settings can improve performance:
   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
+- Keep [`PAPERLESS_OCR_MODE`](configuration.md#PAPERLESS_OCR_MODE) at its default value `auto` 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.
+- Set [`PAPERLESS_ARCHIVE_FILE_GENERATION`](configuration.md#PAPERLESS_ARCHIVE_FILE_GENERATION) to `never` to skip archive
+  file generation entirely, saving disk space at the cost of in-browser PDF/A viewing.
 - 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.

pyproject.toml

@@ -269,10 +269,6 @@ testpaths = [
   "src/documents/tests/",
   "src/paperless/tests/",
   "src/paperless_mail/tests/",
-  "src/paperless_tesseract/tests/",
-  "src/paperless_tika/tests",
-  "src/paperless_text/tests/",
-  "src/paperless_remote/tests/",
   "src/paperless_ai/tests",
 ]
 

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

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

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

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

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

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

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

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

src-ui/messages.xlf

@@ -297,11 +297,11 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">87</context>
+          <context context-type="linenumber">88</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">89</context>
+          <context context-type="linenumber">90</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/dashboard/dashboard.component.html</context>
@@ -324,11 +324,11 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">94</context>
+          <context context-type="linenumber">95</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">96</context>
+          <context context-type="linenumber">97</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/share-link-bundle-dialog/share-link-bundle-dialog.component.html</context>
@@ -375,15 +375,15 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">54</context>
+          <context context-type="linenumber">55</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">273</context>
+          <context context-type="linenumber">274</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">275</context>
+          <context context-type="linenumber">276</context>
         </context-group>
       </trans-unit>
       <trans-unit id="5890330709052835856" datatype="html">
@@ -728,11 +728,11 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">308</context>
+          <context context-type="linenumber">309</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">311</context>
+          <context context-type="linenumber">312</context>
         </context-group>
       </trans-unit>
       <trans-unit id="2272120016352772836" datatype="html">
@@ -1139,11 +1139,11 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">233</context>
+          <context context-type="linenumber">234</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">235</context>
+          <context context-type="linenumber">236</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/manage/saved-views/saved-views.component.html</context>
@@ -1700,7 +1700,7 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">204</context>
+          <context context-type="linenumber">205</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/common/input/tags/tags.component.ts</context>
@@ -1782,15 +1782,15 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.ts</context>
-          <context context-type="linenumber">156</context>
+          <context context-type="linenumber">164</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.ts</context>
-          <context context-type="linenumber">230</context>
+          <context context-type="linenumber">238</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.ts</context>
-          <context context-type="linenumber">255</context>
+          <context context-type="linenumber">263</context>
         </context-group>
       </trans-unit>
       <trans-unit id="2991443309752293110" datatype="html">
@@ -1801,11 +1801,11 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">296</context>
+          <context context-type="linenumber">297</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">298</context>
+          <context context-type="linenumber">299</context>
         </context-group>
       </trans-unit>
       <trans-unit id="103921551219467537" datatype="html">
@@ -2224,11 +2224,11 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">256</context>
+          <context context-type="linenumber">257</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">259</context>
+          <context context-type="linenumber">260</context>
         </context-group>
       </trans-unit>
       <trans-unit id="3818027200170621545" datatype="html">
@@ -2581,11 +2581,11 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">287</context>
+          <context context-type="linenumber">288</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">289</context>
+          <context context-type="linenumber">290</context>
         </context-group>
       </trans-unit>
       <trans-unit id="4569276013106377105" datatype="html">
@@ -2897,90 +2897,90 @@
         <source>Logged in as <x id="INTERPOLATION" equiv-text="{{this.settingsService.displayName}}"/></source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">46</context>
+          <context context-type="linenumber">47</context>
         </context-group>
       </trans-unit>
       <trans-unit id="2127032578120864096" datatype="html">
         <source>My Profile</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">50</context>
+          <context context-type="linenumber">51</context>
         </context-group>
       </trans-unit>
       <trans-unit id="3797778920049399855" datatype="html">
         <source>Logout</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">57</context>
+          <context context-type="linenumber">58</context>
         </context-group>
       </trans-unit>
       <trans-unit id="4895326106573044490" datatype="html">
         <source>Documentation</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">62</context>
+          <context context-type="linenumber">63</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">317</context>
+          <context context-type="linenumber">318</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">320</context>
+          <context context-type="linenumber">321</context>
         </context-group>
       </trans-unit>
       <trans-unit id="472206565520537964" datatype="html">
         <source>Saved views</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">104</context>
+          <context context-type="linenumber">105</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">134</context>
+          <context context-type="linenumber">135</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6988090220128974198" datatype="html">
         <source>Open documents</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">143</context>
+          <context context-type="linenumber">144</context>
         </context-group>
       </trans-unit>
       <trans-unit id="5687256342387781369" datatype="html">
         <source>Close all</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">163</context>
+          <context context-type="linenumber">164</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">165</context>
+          <context context-type="linenumber">166</context>
         </context-group>
       </trans-unit>
       <trans-unit id="3897348120591552265" datatype="html">
         <source>Manage</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">174</context>
+          <context context-type="linenumber">175</context>
         </context-group>
       </trans-unit>
       <trans-unit id="8008131619909556709" datatype="html">
         <source>Attributes</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">181</context>
+          <context context-type="linenumber">182</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">183</context>
+          <context context-type="linenumber">184</context>
         </context-group>
       </trans-unit>
       <trans-unit id="7437910965833684826" datatype="html">
         <source>Correspondents</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">209</context>
+          <context context-type="linenumber">210</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/dashboard/widgets/statistics-widget/statistics-widget.component.html</context>
@@ -2995,7 +2995,7 @@
         <source>Document types</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">214</context>
+          <context context-type="linenumber">215</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/manage/document-attributes/document-attributes.component.ts</context>
@@ -3006,7 +3006,7 @@
         <source>Storage paths</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">219</context>
+          <context context-type="linenumber">220</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/manage/document-attributes/document-attributes.component.ts</context>
@@ -3017,7 +3017,7 @@
         <source>Custom fields</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">224</context>
+          <context context-type="linenumber">225</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/bulk-editor/bulk-editor.component.html</context>
@@ -3040,11 +3040,11 @@
         <source>Workflows</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">242</context>
+          <context context-type="linenumber">243</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">244</context>
+          <context context-type="linenumber">245</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/manage/workflows/workflows.component.html</context>
@@ -3055,92 +3055,92 @@
         <source>Mail</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">249</context>
+          <context context-type="linenumber">250</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">252</context>
+          <context context-type="linenumber">253</context>
         </context-group>
       </trans-unit>
       <trans-unit id="7844706011418789951" datatype="html">
         <source>Administration</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">267</context>
+          <context context-type="linenumber">268</context>
         </context-group>
       </trans-unit>
       <trans-unit id="3008420115644088420" datatype="html">
         <source>Configuration</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">280</context>
+          <context context-type="linenumber">281</context>
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">282</context>
+          <context context-type="linenumber">283</context>
         </context-group>
       </trans-unit>
       <trans-unit id="1534029177398918729" datatype="html">
         <source>GitHub</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">327</context>
+          <context context-type="linenumber">328</context>
         </context-group>
       </trans-unit>
       <trans-unit id="4112664765954374539" datatype="html">
         <source>is available.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">336,337</context>
+          <context context-type="linenumber">337,338</context>
         </context-group>
       </trans-unit>
       <trans-unit id="1175891574282637937" datatype="html">
         <source>Click to view.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">337</context>
+          <context context-type="linenumber">338</context>
         </context-group>
       </trans-unit>
       <trans-unit id="9811291095862612" datatype="html">
         <source>Paperless-ngx can automatically check for updates</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">341</context>
+          <context context-type="linenumber">342</context>
         </context-group>
       </trans-unit>
       <trans-unit id="894819944961861800" datatype="html">
         <source> How does this work? </source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">348,350</context>
+          <context context-type="linenumber">349,351</context>
         </context-group>
       </trans-unit>
       <trans-unit id="509090351011426949" datatype="html">
         <source>Update available</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.html</context>
-          <context context-type="linenumber">361</context>
+          <context context-type="linenumber">362</context>
         </context-group>
       </trans-unit>
       <trans-unit id="1542489069631984294" datatype="html">
         <source>Sidebar views updated</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.ts</context>
-          <context context-type="linenumber">343</context>
+          <context context-type="linenumber">383</context>
         </context-group>
       </trans-unit>
       <trans-unit id="3547923076537026828" datatype="html">
         <source>Error updating sidebar views</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.ts</context>
-          <context context-type="linenumber">346</context>
+          <context context-type="linenumber">386</context>
         </context-group>
       </trans-unit>
       <trans-unit id="2526035785704676448" datatype="html">
         <source>An error occurred while saving update checking settings.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.ts</context>
-          <context context-type="linenumber">367</context>
+          <context context-type="linenumber">407</context>
         </context-group>
       </trans-unit>
       <trans-unit id="4580988005648117665" datatype="html">
@@ -11187,21 +11187,21 @@
         <source>Successfully completed one-time migratration of settings to the database!</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/services/settings.service.ts</context>
-          <context context-type="linenumber">609</context>
+          <context context-type="linenumber">635</context>
         </context-group>
       </trans-unit>
       <trans-unit id="5558341108007064934" datatype="html">
         <source>Unable to migrate settings to the database, please try saving manually.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/services/settings.service.ts</context>
-          <context context-type="linenumber">610</context>
+          <context context-type="linenumber">636</context>
         </context-group>
       </trans-unit>
       <trans-unit id="1168781785897678748" datatype="html">
         <source>You can restart the tour from the settings page.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/services/settings.service.ts</context>
-          <context context-type="linenumber">683</context>
+          <context context-type="linenumber">708</context>
         </context-group>
       </trans-unit>
       <trans-unit id="3852289441366561594" datatype="html">

src-ui/src/app/components/app-frame/app-frame.component.html

@@ -1,7 +1,7 @@
 <nav class="navbar navbar-dark fixed-top bg-primary flex-md-nowrap p-0 shadow-sm">
   <button class="navbar-toggler d-md-none collapsed border-0" type="button" data-toggle="collapse"
     data-target="#sidebarMenu" aria-controls="sidebarMenu" aria-expanded="false" aria-label="Toggle navigation"
-    (click)="isMenuCollapsed = !isMenuCollapsed">
+    (click)="mobileSearchHidden = false; isMenuCollapsed = !isMenuCollapsed">
     <span class="navbar-toggler-icon"></span>
   </button>
   <a class="navbar-brand d-flex align-items-center me-0 px-3 py-3 order-sm-0"
@@ -24,7 +24,8 @@
       }
     </div>
   </a>
-  <div class="search-container flex-grow-1 py-2 pb-3 pb-sm-2 px-3 ps-md-4 me-sm-auto order-3 order-sm-1">
+  <div class="search-container flex-grow-1 py-2 pb-3 pb-sm-2 px-3 ps-md-4 me-sm-auto order-3 order-sm-1"
+    [class.mobile-hidden]="mobileSearchHidden">
     <div class="col-12 col-md-7">
       <pngx-global-search></pngx-global-search>
     </div>
@@ -378,7 +379,7 @@
       </div>
     </nav>
 
-    <main role="main" class="ms-sm-auto px-md-4"
+    <main role="main" class="ms-sm-auto px-md-4" [class.mobile-search-hidden]="mobileSearchHidden"
       [ngClass]="slimSidebarEnabled ? 'col-slim' : 'col-md-9 col-lg-10 col-xxxl-11'">
       <router-outlet></router-outlet>
     </main>

src-ui/src/app/components/app-frame/app-frame.component.scss

@@ -44,6 +44,23 @@
   .sidebar {
     top: 3.5rem;
   }
+
+  .search-container {
+    max-height: 4.5rem;
+    overflow: hidden;
+    transition: max-height .2s ease, opacity .2s ease, padding-top .2s ease, padding-bottom .2s ease;
+
+    &.mobile-hidden {
+      max-height: 0;
+      opacity: 0;
+      padding-top: 0 !important;
+      padding-bottom: 0 !important;
+    }
+  }
+
+  main.mobile-search-hidden {
+    padding-top: 56px;
+  }
 }
 
 main {

src-ui/src/app/components/app-frame/app-frame.component.spec.ts

@@ -293,6 +293,59 @@ describe('AppFrameComponent', () => {
     expect(component.isMenuCollapsed).toBeTruthy()
   })
 
+  it('should hide mobile search when scrolling down and show it when scrolling up', () => {
+    Object.defineProperty(globalThis, 'innerWidth', {
+      value: 767,
+    })
+
+    component.ngOnInit()
+
+    Object.defineProperty(globalThis, 'scrollY', {
+      configurable: true,
+      value: 40,
+    })
+    component.onWindowScroll()
+    expect(component.mobileSearchHidden).toBe(true)
+
+    Object.defineProperty(globalThis, 'scrollY', {
+      configurable: true,
+      value: 0,
+    })
+    component.onWindowScroll()
+    expect(component.mobileSearchHidden).toBe(false)
+  })
+
+  it('should keep mobile search visible on desktop scroll or resize', () => {
+    Object.defineProperty(globalThis, 'innerWidth', {
+      value: 1024,
+    })
+    component.ngOnInit()
+    component.mobileSearchHidden = true
+
+    component.onWindowScroll()
+
+    expect(component.mobileSearchHidden).toBe(false)
+
+    component.mobileSearchHidden = true
+    component.onWindowResize()
+  })
+
+  it('should keep mobile search visible while the mobile menu is expanded', () => {
+    Object.defineProperty(globalThis, 'innerWidth', {
+      value: 767,
+    })
+    component.ngOnInit()
+    component.isMenuCollapsed = false
+
+    Object.defineProperty(globalThis, 'scrollY', {
+      configurable: true,
+      value: 40,
+    })
+    component.onWindowScroll()
+
+    expect(component.mobileSearchHidden).toBe(false)
+  })
+
   it('should support close document & navigate on close current doc', () => {
     const closeSpy = jest.spyOn(openDocumentsService, 'closeDocument')
     closeSpy.mockReturnValue(of(true))

src-ui/src/app/components/app-frame/app-frame.component.ts

@@ -51,6 +51,8 @@ import { ComponentWithPermissions } from '../with-permissions/with-permissions.c
 import { GlobalSearchComponent } from './global-search/global-search.component'
 import { ToastsDropdownComponent } from './toasts-dropdown/toasts-dropdown.component'
 
+const SCROLL_THRESHOLD = 16
+
 @Component({
   selector: 'pngx-app-frame',
   templateUrl: './app-frame.component.html',
@@ -94,6 +96,10 @@ export class AppFrameComponent
 
   slimSidebarAnimating: boolean = false
 
+  public mobileSearchHidden: boolean = false
+
+  private lastScrollY: number = 0
+
   constructor() {
     super()
     const permissionsService = this.permissionsService
@@ -111,6 +117,8 @@ export class AppFrameComponent
   }
 
   ngOnInit(): void {
+    this.lastScrollY = window.scrollY
+
     if (this.settingsService.get(SETTINGS_KEYS.UPDATE_CHECKING_ENABLED)) {
       this.checkForUpdates()
     }
@@ -263,6 +271,38 @@ export class AppFrameComponent
     return this.settingsService.get(SETTINGS_KEYS.AI_ENABLED)
   }
 
+  @HostListener('window:resize')
+  onWindowResize(): void {
+    if (!this.isMobileViewport()) {
+      this.mobileSearchHidden = false
+    }
+  }
+
+  @HostListener('window:scroll')
+  onWindowScroll(): void {
+    const currentScrollY = window.scrollY
+
+    if (!this.isMobileViewport() || this.isMenuCollapsed === false) {
+      this.mobileSearchHidden = false
+      this.lastScrollY = currentScrollY
+      return
+    }
+
+    const delta = currentScrollY - this.lastScrollY
+
+    if (currentScrollY <= 0 || delta < -SCROLL_THRESHOLD) {
+      this.mobileSearchHidden = false
+    } else if (currentScrollY > SCROLL_THRESHOLD && delta > SCROLL_THRESHOLD) {
+      this.mobileSearchHidden = true
+    }
+
+    this.lastScrollY = currentScrollY
+  }
+
+  private isMobileViewport(): boolean {
+    return window.innerWidth < 768
+  }
+
   closeMenu() {
     this.isMenuCollapsed = true
   }

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

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

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

@@ -300,7 +300,7 @@ describe('BulkEditorComponent', () => {
       parameters: { add_tags: [101], remove_tags: [] },
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -332,7 +332,7 @@ describe('BulkEditorComponent', () => {
       .expectOne(`${environment.apiBaseUrl}documents/bulk_edit/`)
       .flush(true)
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -423,7 +423,7 @@ describe('BulkEditorComponent', () => {
       parameters: { correspondent: 101 },
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -455,7 +455,7 @@ describe('BulkEditorComponent', () => {
       .expectOne(`${environment.apiBaseUrl}documents/bulk_edit/`)
       .flush(true)
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -521,7 +521,7 @@ describe('BulkEditorComponent', () => {
       parameters: { document_type: 101 },
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -553,7 +553,7 @@ describe('BulkEditorComponent', () => {
       .expectOne(`${environment.apiBaseUrl}documents/bulk_edit/`)
       .flush(true)
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -619,7 +619,7 @@ describe('BulkEditorComponent', () => {
       parameters: { storage_path: 101 },
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -651,7 +651,7 @@ describe('BulkEditorComponent', () => {
       .expectOne(`${environment.apiBaseUrl}documents/bulk_edit/`)
       .flush(true)
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -717,7 +717,7 @@ describe('BulkEditorComponent', () => {
       parameters: { add_custom_fields: [101], remove_custom_fields: [102] },
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -749,7 +749,7 @@ describe('BulkEditorComponent', () => {
       .expectOne(`${environment.apiBaseUrl}documents/bulk_edit/`)
       .flush(true)
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -858,7 +858,7 @@ describe('BulkEditorComponent', () => {
       documents: [3, 4],
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -951,7 +951,7 @@ describe('BulkEditorComponent', () => {
       documents: [3, 4],
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -986,7 +986,7 @@ describe('BulkEditorComponent', () => {
       source_mode: 'latest_version',
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -1027,7 +1027,7 @@ describe('BulkEditorComponent', () => {
       metadata_document_id: 3,
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -1046,7 +1046,7 @@ describe('BulkEditorComponent', () => {
       delete_originals: true,
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -1067,7 +1067,7 @@ describe('BulkEditorComponent', () => {
       archive_fallback: true,
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -1153,7 +1153,7 @@ describe('BulkEditorComponent', () => {
       },
     })
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`
@@ -1460,7 +1460,7 @@ describe('BulkEditorComponent', () => {
     expect(toastServiceShowInfoSpy).toHaveBeenCalled()
     expect(listReloadSpy).toHaveBeenCalled()
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     ) // list reload
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id`

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

@@ -16,7 +16,6 @@ import { first, map, Observable, Subject, switchMap, takeUntil } from 'rxjs'
 import { ConfirmDialogComponent } from 'src/app/components/common/confirm-dialog/confirm-dialog.component'
 import { CustomField } from 'src/app/data/custom-field'
 import { MatchingModel } from 'src/app/data/matching-model'
-import { SelectionDataItem } from 'src/app/data/results'
 import { SETTINGS_KEYS } from 'src/app/data/ui-settings'
 import { IfPermissionsDirective } from 'src/app/directives/if-permissions.directive'
 import { DocumentListViewService } from 'src/app/services/document-list-view.service'
@@ -33,6 +32,7 @@ import {
   DocumentBulkEditMethod,
   DocumentService,
   MergeDocumentsRequest,
+  SelectionDataItem,
 } from 'src/app/services/rest/document.service'
 import { SavedViewService } from 'src/app/services/rest/saved-view.service'
 import { ShareLinkBundleService } from 'src/app/services/rest/share-link-bundle.service'

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

@@ -56,13 +56,20 @@ $paperless-card-breakpoints: (
 
 .sticky-top {
   z-index: 990; // below main navbar
-  top: calc(7rem - 2px); // height of navbar (mobile)
+  top: calc(7rem - 2px); // height of navbar + search row (mobile)
+  transition: top 0.2s ease;
 
   @media (min-width: 580px) {
     top: 3.5rem; // height of navbar
   }
 }
 
+@media (max-width: 579.98px) {
+  :host-context(main.mobile-search-hidden) .sticky-top {
+    top: calc(3.5rem - 2px); // height of navbar only when search is hidden
+  }
+}
+
 .table .form-check {
   padding: 0.2rem;
   min-height: 0;

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

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

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

@@ -1,5 +1,3 @@
-import { Document } from './document'
-
 export interface Results<T> {
   count: number
 
@@ -7,20 +5,3 @@ export interface Results<T> {
 
   all: number[]
 }
-
-export interface SelectionDataItem {
-  id: number
-  document_count: number
-}
-
-export interface SelectionData {
-  selected_storage_paths: SelectionDataItem[]
-  selected_correspondents: SelectionDataItem[]
-  selected_tags: SelectionDataItem[]
-  selected_document_types: SelectionDataItem[]
-  selected_custom_fields: SelectionDataItem[]
-}
-
-export interface DocumentResults extends Results<Document> {
-  selection_data?: SelectionData
-}

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

@@ -21,6 +21,7 @@ import {
   FILTER_HAS_TAGS_ANY,
 } from '../data/filter-rule-type'
 import { SavedView } from '../data/saved-view'
+import { DOCUMENT_LIST_SERVICE } from '../data/storage-keys'
 import { SETTINGS_KEYS } from '../data/ui-settings'
 import { PermissionsGuard } from '../guards/permissions.guard'
 import { DocumentListViewService } from './document-list-view.service'
@@ -126,10 +127,13 @@ describe('DocumentListViewService', () => {
     expect(documentListViewService.currentPage).toEqual(1)
     documentListViewService.reload()
     const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     )
     expect(req.request.method).toEqual('GET')
     req.flush(full_results)
+    httpTestingController.expectOne(
+      `${environment.apiBaseUrl}documents/selection_data/`
+    )
     expect(req.request.method).toEqual('GET')
     expect(documentListViewService.isReloading).toBeFalsy()
     expect(documentListViewService.activeSavedViewId).toBeNull()
@@ -141,12 +145,12 @@ describe('DocumentListViewService', () => {
   it('should handle error on page request out of range', () => {
     documentListViewService.currentPage = 50
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=50&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=50&page_size=50&ordering=-created&truncate_content=true`
     )
     expect(req.request.method).toEqual('GET')
     req.flush([], { status: 404, statusText: 'Unexpected error' })
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     )
     expect(req.request.method).toEqual('GET')
     expect(documentListViewService.currentPage).toEqual(1)
@@ -163,7 +167,7 @@ describe('DocumentListViewService', () => {
     ]
     documentListViewService.setFilterRules(filterRulesAny)
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__in=${tags__id__in}`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&tags__id__in=${tags__id__in}`
     )
     expect(req.request.method).toEqual('GET')
     req.flush(
@@ -171,13 +175,13 @@ describe('DocumentListViewService', () => {
       { status: 404, statusText: 'Unexpected error' }
     )
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     )
     expect(req.request.method).toEqual('GET')
     // reset the list
     documentListViewService.setFilterRules([])
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     )
   })
 
@@ -185,7 +189,7 @@ describe('DocumentListViewService', () => {
     documentListViewService.currentPage = 1
     documentListViewService.sortField = 'custom_field_999'
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-custom_field_999&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-custom_field_999&truncate_content=true`
     )
     expect(req.request.method).toEqual('GET')
     req.flush(
@@ -194,7 +198,7 @@ describe('DocumentListViewService', () => {
     )
     // resets itself
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     )
   })
 
@@ -209,7 +213,7 @@ describe('DocumentListViewService', () => {
     ]
     documentListViewService.setFilterRules(filterRulesAny)
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__in=${tags__id__in}`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&tags__id__in=${tags__id__in}`
     )
     expect(req.request.method).toEqual('GET')
     req.flush('Generic error', { status: 404, statusText: 'Unexpected error' })
@@ -217,7 +221,7 @@ describe('DocumentListViewService', () => {
     // reset the list
     documentListViewService.setFilterRules([])
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     )
   })
 
@@ -226,7 +230,7 @@ describe('DocumentListViewService', () => {
     expect(documentListViewService.sortReverse).toBeTruthy()
     documentListViewService.setSort('added', false)
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=added&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=added&truncate_content=true`
     )
     expect(req.request.method).toEqual('GET')
     expect(documentListViewService.sortField).toEqual('added')
@@ -234,17 +238,40 @@ describe('DocumentListViewService', () => {
 
     documentListViewService.sortField = 'created'
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=created&truncate_content=true`
     )
     expect(documentListViewService.sortField).toEqual('created')
     documentListViewService.sortReverse = true
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     )
     expect(req.request.method).toEqual('GET')
     expect(documentListViewService.sortReverse).toBeTruthy()
   })
 
+  it('restores only known list view state fields from local storage', () => {
+    try {
+      localStorage.setItem(
+        DOCUMENT_LIST_SERVICE.CURRENT_VIEW_CONFIG,
+        '{"currentPage":3,"sortField":"title","sortReverse":false,"__proto__":{"polluted":true},"injected":"ignored"}'
+      )
+
+      const restoredService = TestBed.runInInjectionContext(
+        () => new DocumentListViewService()
+      )
+
+      expect(restoredService.currentPage).toEqual(3)
+      expect(restoredService.sortField).toEqual('title')
+      expect(restoredService.sortReverse).toBeFalsy()
+      expect(
+        (restoredService as any).activeListViewState.injected
+      ).toBeUndefined()
+      expect(({} as any).polluted).toBeUndefined()
+    } finally {
+      localStorage.removeItem(DOCUMENT_LIST_SERVICE.CURRENT_VIEW_CONFIG)
+    }
+  })
+
   it('should load from query params', () => {
     expect(documentListViewService.currentPage).toEqual(1)
     const page = 2
@@ -259,7 +286,7 @@ describe('DocumentListViewService', () => {
     const req = httpTestingController.expectOne(
       `${environment.apiBaseUrl}documents/?page=${page}&page_size=${
         documentListViewService.pageSize
-      }&ordering=${reverse ? '-' : ''}${sort}&truncate_content=true&include_selection_data=true`
+      }&ordering=${reverse ? '-' : ''}${sort}&truncate_content=true`
     )
     expect(req.request.method).toEqual('GET')
     expect(documentListViewService.currentPage).toEqual(page)
@@ -276,7 +303,7 @@ describe('DocumentListViewService', () => {
     }
     documentListViewService.loadFromQueryParams(convertToParamMap(params))
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=${documentListViewService.currentPage}&page_size=${documentListViewService.pageSize}&ordering=-added&truncate_content=true&include_selection_data=true&tags__id__all=${tags__id__all}`
+      `${environment.apiBaseUrl}documents/?page=${documentListViewService.currentPage}&page_size=${documentListViewService.pageSize}&ordering=-added&truncate_content=true&tags__id__all=${tags__id__all}`
     )
     expect(req.request.method).toEqual('GET')
     expect(documentListViewService.filterRules).toEqual([
@@ -286,12 +313,15 @@ describe('DocumentListViewService', () => {
       },
     ])
     req.flush(full_results)
+    httpTestingController.expectOne(
+      `${environment.apiBaseUrl}documents/selection_data/`
+    )
   })
 
   it('should use filter rules to update query params', () => {
     documentListViewService.setFilterRules(filterRules)
     const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=${documentListViewService.currentPage}&page_size=${documentListViewService.pageSize}&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__all=${tags__id__all}`
+      `${environment.apiBaseUrl}documents/?page=${documentListViewService.currentPage}&page_size=${documentListViewService.pageSize}&ordering=-created&truncate_content=true&tags__id__all=${tags__id__all}`
     )
     expect(req.request.method).toEqual('GET')
   })
@@ -300,26 +330,34 @@ describe('DocumentListViewService', () => {
     documentListViewService.currentPage = 2
     let req = httpTestingController.expectOne((request) =>
       request.urlWithParams.startsWith(
-        `${environment.apiBaseUrl}documents/?page=2&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+        `${environment.apiBaseUrl}documents/?page=2&page_size=50&ordering=-created&truncate_content=true`
       )
     )
     expect(req.request.method).toEqual('GET')
     req.flush(full_results)
+    req = httpTestingController.expectOne(
+      `${environment.apiBaseUrl}documents/selection_data/`
+    )
+    req.flush([])
 
     documentListViewService.setFilterRules(filterRules, true)
 
     const filteredReqs = httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__all=${tags__id__all}`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&tags__id__all=${tags__id__all}`
     )
     expect(filteredReqs).toHaveLength(1)
     filteredReqs[0].flush(full_results)
+    req = httpTestingController.expectOne(
+      `${environment.apiBaseUrl}documents/selection_data/`
+    )
+    req.flush([])
     expect(documentListViewService.currentPage).toEqual(1)
   })
 
   it('should support quick filter', () => {
     documentListViewService.quickFilter(filterRules)
     const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=${documentListViewService.currentPage}&page_size=${documentListViewService.pageSize}&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__all=${tags__id__all}`
+      `${environment.apiBaseUrl}documents/?page=${documentListViewService.currentPage}&page_size=${documentListViewService.pageSize}&ordering=-created&truncate_content=true&tags__id__all=${tags__id__all}`
     )
     expect(req.request.method).toEqual('GET')
   })
@@ -342,21 +380,21 @@ describe('DocumentListViewService', () => {
       convertToParamMap(params)
     )
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=${page}&page_size=${documentListViewService.pageSize}&ordering=-added&truncate_content=true&include_selection_data=true&tags__id__all=${tags__id__all}`
+      `${environment.apiBaseUrl}documents/?page=${page}&page_size=${documentListViewService.pageSize}&ordering=-added&truncate_content=true&tags__id__all=${tags__id__all}`
     )
     expect(req.request.method).toEqual('GET')
     // reset the list
     documentListViewService.currentPage = 1
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-added&truncate_content=true&include_selection_data=true&tags__id__all=9`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-added&truncate_content=true&tags__id__all=9`
     )
     documentListViewService.setFilterRules([])
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-added&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-added&truncate_content=true`
     )
     documentListViewService.sortField = 'created'
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     )
     documentListViewService.activateSavedView(null)
   })
@@ -364,18 +402,21 @@ describe('DocumentListViewService', () => {
   it('should support navigating next / previous', () => {
     documentListViewService.setFilterRules([])
     let req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     )
     expect(documentListViewService.currentPage).toEqual(1)
     documentListViewService.pageSize = 3
     req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=3&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=3&ordering=-created&truncate_content=true`
     )
     expect(req.request.method).toEqual('GET')
     req.flush({
       count: 3,
       results: documents.slice(0, 3),
     })
+    httpTestingController
+      .expectOne(`${environment.apiBaseUrl}documents/selection_data/`)
+      .flush([])
     expect(documentListViewService.hasNext(documents[0].id)).toBeTruthy()
     expect(documentListViewService.hasPrevious(documents[0].id)).toBeFalsy()
     documentListViewService.getNext(documents[0].id).subscribe((docId) => {
@@ -422,7 +463,7 @@ describe('DocumentListViewService', () => {
     expect(documentListViewService.currentPage).toEqual(1)
     documentListViewService.pageSize = 3
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=3&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=3&ordering=-created&truncate_content=true`
     )
     jest
       .spyOn(documentListViewService, 'getLastPage')
@@ -437,7 +478,7 @@ describe('DocumentListViewService', () => {
     expect(reloadSpy).toHaveBeenCalled()
     expect(documentListViewService.currentPage).toEqual(2)
     const reqs = httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=2&page_size=3&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=2&page_size=3&ordering=-created&truncate_content=true`
     )
     expect(reqs.length).toBeGreaterThan(0)
   })
@@ -472,11 +513,11 @@ describe('DocumentListViewService', () => {
       .mockReturnValue(documents)
     documentListViewService.currentPage = 2
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=2&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=2&page_size=50&ordering=-created&truncate_content=true`
     )
     documentListViewService.pageSize = 3
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=2&page_size=3&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=2&page_size=3&ordering=-created&truncate_content=true`
     )
     const reloadSpy = jest.spyOn(documentListViewService, 'reload')
     documentListViewService.getPrevious(1).subscribe({
@@ -486,7 +527,7 @@ describe('DocumentListViewService', () => {
     expect(reloadSpy).toHaveBeenCalled()
     expect(documentListViewService.currentPage).toEqual(1)
     const reqs = httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=3&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=3&ordering=-created&truncate_content=true`
     )
     expect(reqs.length).toBeGreaterThan(0)
   })
@@ -499,10 +540,13 @@ describe('DocumentListViewService', () => {
   it('should support select a document', () => {
     documentListViewService.reload()
     const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     )
     expect(req.request.method).toEqual('GET')
     req.flush(full_results)
+    httpTestingController.expectOne(
+      `${environment.apiBaseUrl}documents/selection_data/`
+    )
     documentListViewService.toggleSelected(documents[0])
     expect(documentListViewService.isSelected(documents[0])).toBeTruthy()
     documentListViewService.toggleSelected(documents[0])
@@ -524,13 +568,16 @@ describe('DocumentListViewService', () => {
   it('should support select page', () => {
     documentListViewService.pageSize = 3
     const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=3&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=3&ordering=-created&truncate_content=true`
     )
     expect(req.request.method).toEqual('GET')
     req.flush({
       count: 3,
       results: documents.slice(0, 3),
     })
+    httpTestingController.expectOne(
+      `${environment.apiBaseUrl}documents/selection_data/`
+    )
     documentListViewService.selectPage()
     expect(documentListViewService.selected.size).toEqual(3)
     expect(documentListViewService.isSelected(documents[5])).toBeFalsy()
@@ -539,10 +586,13 @@ describe('DocumentListViewService', () => {
   it('should support select range', () => {
     documentListViewService.reload()
     const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     )
     expect(req.request.method).toEqual('GET')
     req.flush(full_results)
+    httpTestingController.expectOne(
+      `${environment.apiBaseUrl}documents/selection_data/`
+    )
     documentListViewService.toggleSelected(documents[0])
     expect(documentListViewService.isSelected(documents[0])).toBeTruthy()
     documentListViewService.selectRangeTo(documents[2])
@@ -562,7 +612,7 @@ describe('DocumentListViewService', () => {
 
     documentListViewService.setFilterRules(filterRules)
     httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__all=9`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&tags__id__all=9`
     )
     const reqs = httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=100000&fields=id&tags__id__all=9`
@@ -578,7 +628,7 @@ describe('DocumentListViewService', () => {
     const cancelSpy = jest.spyOn(documentListViewService, 'cancelPending')
     documentListViewService.reload()
     httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true&tags__id__all=9`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&tags__id__all=9`
     )
     expect(cancelSpy).toHaveBeenCalled()
   })
@@ -597,7 +647,7 @@ describe('DocumentListViewService', () => {
     documentListViewService.setFilterRules([])
     expect(documentListViewService.sortField).toEqual('created')
     httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     )
   })
 
@@ -624,11 +674,11 @@ describe('DocumentListViewService', () => {
     expect(localStorageSpy).toHaveBeenCalled()
     // reload triggered
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     )
     documentListViewService.displayFields = null
     httpTestingController.match(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     )
     expect(documentListViewService.displayFields).toEqual(
       DEFAULT_DISPLAY_FIELDS.filter((f) => f.id !== DisplayField.ADDED).map(
@@ -668,7 +718,7 @@ describe('DocumentListViewService', () => {
   it('should generate quick filter URL preserving default state', () => {
     documentListViewService.reload()
     httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
     )
     const urlTree = documentListViewService.getQuickFilterUrl(filterRules)
     expect(urlTree).toBeDefined()

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

@@ -1,6 +1,6 @@
 import { Injectable, inject } from '@angular/core'
 import { ParamMap, Router, UrlTree } from '@angular/router'
-import { Observable, Subject, takeUntil } from 'rxjs'
+import { Observable, Subject, first, takeUntil } from 'rxjs'
 import {
   DEFAULT_DISPLAY_FIELDS,
   DisplayField,
@@ -8,7 +8,6 @@ import {
   Document,
 } from '../data/document'
 import { FilterRule } from '../data/filter-rule'
-import { DocumentResults, SelectionData } from '../data/results'
 import { SavedView } from '../data/saved-view'
 import { DOCUMENT_LIST_SERVICE } from '../data/storage-keys'
 import { SETTINGS_KEYS } from '../data/ui-settings'
@@ -18,13 +17,27 @@ import {
   isFullTextFilterRule,
 } from '../utils/filter-rules'
 import { paramsFromViewState, paramsToViewState } from '../utils/query-params'
-import { DocumentService } from './rest/document.service'
+import { DocumentService, SelectionData } from './rest/document.service'
 import { SettingsService } from './settings.service'
 
 const LIST_DEFAULT_DISPLAY_FIELDS: DisplayField[] = DEFAULT_DISPLAY_FIELDS.map(
   (f) => f.id
 ).filter((f) => f !== DisplayField.ADDED)
 
+const RESTORABLE_LIST_VIEW_STATE_KEYS: (keyof ListViewState)[] = [
+  'title',
+  'documents',
+  'currentPage',
+  'collectionSize',
+  'sortField',
+  'sortReverse',
+  'filterRules',
+  'selected',
+  'pageSize',
+  'displayMode',
+  'displayFields',
+]
+
 /**
  * Captures the current state of the list view.
  */
@@ -113,6 +126,32 @@ export class DocumentListViewService {
 
   private displayFieldsInitialized: boolean = false
 
+  private restoreListViewState(savedState: unknown): ListViewState {
+    const newState = this.defaultListViewState()
+
+    if (
+      !savedState ||
+      typeof savedState !== 'object' ||
+      Array.isArray(savedState)
+    ) {
+      return newState
+    }
+
+    const parsedState = savedState as Partial<
+      Record<keyof ListViewState, unknown>
+    >
+    const mutableState = newState as Record<keyof ListViewState, unknown>
+
+    for (const key of RESTORABLE_LIST_VIEW_STATE_KEYS) {
+      const value = parsedState[key]
+      if (value != null) {
+        mutableState[key] = value
+      }
+    }
+
+    return newState
+  }
+
   get activeSavedViewId() {
     return this._activeSavedViewId
   }
@@ -128,14 +167,7 @@ export class DocumentListViewService {
     if (documentListViewConfigJson) {
       try {
         let savedState: ListViewState = JSON.parse(documentListViewConfigJson)
-        // Remove null elements from the restored state
-        Object.keys(savedState).forEach((k) => {
-          if (savedState[k] == null) {
-            delete savedState[k]
-          }
-        })
-        // only use restored state attributes instead of defaults if they are not null
-        let newState = Object.assign(this.defaultListViewState(), savedState)
+        let newState = this.restoreListViewState(savedState)
         this.listViewStates.set(null, newState)
       } catch (e) {
         localStorage.removeItem(DOCUMENT_LIST_SERVICE.CURRENT_VIEW_CONFIG)
@@ -261,17 +293,27 @@ export class DocumentListViewService {
         activeListViewState.sortField,
         activeListViewState.sortReverse,
         activeListViewState.filterRules,
-        { truncate_content: true, include_selection_data: true }
+        { truncate_content: true }
       )
       .pipe(takeUntil(this.unsubscribeNotifier))
       .subscribe({
         next: (result) => {
-          const resultWithSelectionData = result as DocumentResults
           this.initialized = true
           this.isReloading = false
           activeListViewState.collectionSize = result.count
           activeListViewState.documents = result.results
-          this.selectionData = resultWithSelectionData.selection_data ?? null
+
+          this.documentService
+            .getSelectionData(result.all)
+            .pipe(first())
+            .subscribe({
+              next: (selectionData) => {
+                this.selectionData = selectionData
+              },
+              error: () => {
+                this.selectionData = null
+              },
+            })
 
           if (updateQueryParams && !this._activeSavedViewId) {
             let base = ['/documents']

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

@@ -12,7 +12,7 @@ import {
 import { DocumentMetadata } from 'src/app/data/document-metadata'
 import { DocumentSuggestions } from 'src/app/data/document-suggestions'
 import { FilterRule } from 'src/app/data/filter-rule'
-import { Results, SelectionData } from 'src/app/data/results'
+import { Results } from 'src/app/data/results'
 import { SETTINGS_KEYS } from 'src/app/data/ui-settings'
 import { queryParamsFromFilterRules } from '../../utils/query-params'
 import {
@@ -24,6 +24,19 @@ import { SettingsService } from '../settings.service'
 import { AbstractPaperlessService } from './abstract-paperless-service'
 import { CustomFieldsService } from './custom-fields.service'
 
+export interface SelectionDataItem {
+  id: number
+  document_count: number
+}
+
+export interface SelectionData {
+  selected_storage_paths: SelectionDataItem[]
+  selected_correspondents: SelectionDataItem[]
+  selected_tags: SelectionDataItem[]
+  selected_document_types: SelectionDataItem[]
+  selected_custom_fields: SelectionDataItem[]
+}
+
 export enum BulkEditSourceMode {
   LATEST_VERSION = 'latest_version',
   EXPLICIT_SELECTION = 'explicit_selection',

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

@@ -166,6 +166,23 @@ describe('SettingsService', () => {
     expect(settingsService.get(SETTINGS_KEYS.THEME_COLOR)).toEqual('#9fbf2f')
   })
 
+  it('ignores unsafe top-level keys from loaded settings', () => {
+    const req = httpTestingController.expectOne(
+      `${environment.apiBaseUrl}ui_settings/`
+    )
+    const payload = JSON.parse(
+      JSON.stringify(ui_settings).replace(
+        '"settings":{',
+        '"settings":{"__proto__":{"polluted":"yes"},'
+      )
+    )
+    payload.settings.app_title = 'Safe Title'
+    req.flush(payload)
+
+    expect(settingsService.get(SETTINGS_KEYS.APP_TITLE)).toEqual('Safe Title')
+    expect(({} as any).polluted).toBeUndefined()
+  })
+
   it('correctly allows updating settings of various types', () => {
     const req = httpTestingController.expectOne(
       `${environment.apiBaseUrl}ui_settings/`

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

@@ -276,6 +276,8 @@ const ISO_LANGUAGE_OPTION: LanguageOption = {
   dateInputFormat: 'yyyy-mm-dd',
 }
 
+const UNSAFE_OBJECT_KEYS = new Set(['__proto__', 'prototype', 'constructor'])
+
 @Injectable({
   providedIn: 'root',
 })
@@ -291,7 +293,7 @@ export class SettingsService {
 
   protected baseUrl: string = environment.apiBaseUrl + 'ui_settings/'
 
-  private settings: Object = {}
+  private settings: Record<string, any> = {}
   currentUser: User
 
   public settingsSaved: EventEmitter<any> = new EventEmitter()
@@ -320,6 +322,21 @@ export class SettingsService {
     this._renderer = rendererFactory.createRenderer(null, null)
   }
 
+  private isSafeObjectKey(key: string): boolean {
+    return !UNSAFE_OBJECT_KEYS.has(key)
+  }
+
+  private assignSafeSettings(source: Record<string, any>) {
+    if (!source || typeof source !== 'object' || Array.isArray(source)) {
+      return
+    }
+
+    for (const key of Object.keys(source)) {
+      if (!this.isSafeObjectKey(key)) continue
+      this.settings[key] = source[key]
+    }
+  }
+
   // this is called by the app initializer in app.module
   public initializeSettings(): Observable<UiSettings> {
     return this.http.get<UiSettings>(this.baseUrl).pipe(
@@ -338,7 +355,7 @@ export class SettingsService {
         })
       }),
       tap((uisettings) => {
-        Object.assign(this.settings, uisettings.settings)
+        this.assignSafeSettings(uisettings.settings)
         if (this.get(SETTINGS_KEYS.APP_TITLE)?.length) {
           environment.appTitle = this.get(SETTINGS_KEYS.APP_TITLE)
         }
@@ -533,7 +550,11 @@ export class SettingsService {
     let settingObj = this.settings
     keys.forEach((keyPart, index) => {
       keyPart = keyPart.replace(/-/g, '_')
-      if (!settingObj.hasOwnProperty(keyPart)) return
+      if (
+        !this.isSafeObjectKey(keyPart) ||
+        !Object.prototype.hasOwnProperty.call(settingObj, keyPart)
+      )
+        return
       if (index == keys.length - 1) value = settingObj[keyPart]
       else settingObj = settingObj[keyPart]
     })
@@ -579,7 +600,9 @@ export class SettingsService {
     const keys = key.replace('general-settings:', '').split(':')
     keys.forEach((keyPart, index) => {
       keyPart = keyPart.replace(/-/g, '_')
-      if (!settingObj.hasOwnProperty(keyPart)) settingObj[keyPart] = {}
+      if (!this.isSafeObjectKey(keyPart)) return
+      if (!Object.prototype.hasOwnProperty.call(settingObj, keyPart))
+        settingObj[keyPart] = {}
       if (index == keys.length - 1) settingObj[keyPart] = value
       else settingObj = settingObj[keyPart]
     })
@@ -602,7 +625,10 @@ export class SettingsService {
 
   maybeMigrateSettings() {
     if (
-      !this.settings.hasOwnProperty('documentListSize') &&
+      !Object.prototype.hasOwnProperty.call(
+        this.settings,
+        'documentListSize'
+      ) &&
       localStorage.getItem(SETTINGS_KEYS.DOCUMENT_LIST_SIZE)
     ) {
       // lets migrate
@@ -610,8 +636,7 @@ export class SettingsService {
       const errorMessage = $localize`Unable to migrate settings to the database, please try saving manually.`
 
       try {
-        for (const setting in SETTINGS_KEYS) {
-          const key = SETTINGS_KEYS[setting]
+        for (const key of Object.values(SETTINGS_KEYS)) {
           const value = localStorage.getItem(key)
           this.set(key, value)
         }

src/documents/checks.py

@@ -3,25 +3,20 @@ from django.core.checks import Error
 from django.core.checks import Warning
 from django.core.checks import register
 
-from documents.signals import document_consumer_declaration
 from documents.templating.utils import convert_format_str_to_template_format
+from paperless.parsers.registry import get_parser_registry
 
 
 @register()
 def parser_check(app_configs, **kwargs):
-    parsers = []
-    for response in document_consumer_declaration.send(None):
-        parsers.append(response[1])
-
-    if len(parsers) == 0:
+    if not get_parser_registry().all_parsers():
         return [
             Error(
                 "No parsers found. This is a bug. The consumer won't be "
                 "able to consume any documents without parsers.",
             ),
         ]
-    else:
-        return []
+    return []
 
 
 @register()

src/documents/consumer.py

@@ -1,6 +1,6 @@
 import datetime
-import hashlib
 import os
+import shutil
 import tempfile
 from enum import StrEnum
 from pathlib import Path
@@ -32,9 +32,7 @@ from documents.models import DocumentType
 from documents.models import StoragePath
 from documents.models import Tag
 from documents.models import WorkflowTrigger
-from documents.parsers import DocumentParser
 from documents.parsers import ParseError
-from documents.parsers import get_parser_class_for_mime_type
 from documents.permissions import set_permissions_for_object
 from documents.plugins.base import AlwaysRunPluginMixin
 from documents.plugins.base import ConsumeTaskPlugin
@@ -48,44 +46,22 @@ from documents.signals import document_consumption_started
 from documents.signals import document_updated
 from documents.signals.handlers import run_workflows
 from documents.templating.workflows import parse_w_workflow_placeholders
+from documents.utils import compute_checksum
 from documents.utils import copy_basic_file_stats
 from documents.utils import copy_file_with_basic_stats
 from documents.utils import run_subprocess
+from paperless.config import OcrConfig
+from paperless.models import ArchiveFileGenerationChoices
 from paperless.parsers import ParserContext
-from paperless.parsers.mail import MailDocumentParser
-from paperless.parsers.remote import RemoteDocumentParser
-from paperless.parsers.tesseract import RasterisedDocumentParser
-from paperless.parsers.text import TextDocumentParser
-from paperless.parsers.tika import TikaDocumentParser
+from paperless.parsers import ParserProtocol
+from paperless.parsers.registry import get_parser_registry
+from paperless.parsers.utils import PDF_TEXT_MIN_LENGTH
+from paperless.parsers.utils import extract_pdf_text
+from paperless.parsers.utils import is_tagged_pdf
 
 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,
-        (
-            MailDocumentParser,
-            RasterisedDocumentParser,
-            RemoteDocumentParser,
-            TextDocumentParser,
-            TikaDocumentParser,
-        ),
-    ):
-        parser.__exit__(None, None, None)
-    else:
-        parser.cleanup()
-
-
 class WorkflowTriggerPlugin(
     NoCleanupPluginMixin,
     NoSetupPluginMixin,
@@ -134,6 +110,44 @@ class ConsumerStatusShortMessage(StrEnum):
     FAILED = "failed"
 
 
+def should_produce_archive(
+    parser: "ParserProtocol",
+    mime_type: str,
+    document_path: Path,
+) -> bool:
+    """Return True if a PDF/A archive should be produced for this document.
+
+    IMPORTANT: *parser* must be an instantiated parser, not the class.
+    ``requires_pdf_rendition`` and ``can_produce_archive`` are instance
+    ``@property`` methods — accessing them on the class returns the descriptor
+    (always truthy).
+    """
+    # Must produce a PDF so the frontend can display the original format at all.
+    if parser.requires_pdf_rendition:
+        return True
+
+    # Parser cannot produce an archive (e.g. TextDocumentParser).
+    if not parser.can_produce_archive:
+        return False
+
+    generation = OcrConfig().archive_file_generation
+
+    if generation == ArchiveFileGenerationChoices.ALWAYS:
+        return True
+    if generation == ArchiveFileGenerationChoices.NEVER:
+        return False
+
+    # auto: produce archives for scanned/image documents; skip for born-digital PDFs.
+    if mime_type.startswith("image/"):
+        return True
+    if mime_type == "application/pdf":
+        if is_tagged_pdf(document_path):
+            return False
+        text = extract_pdf_text(document_path)
+        return text is None or len(text) <= PDF_TEXT_MIN_LENGTH
+    return False
+
+
 class ConsumerPluginMixin:
     if TYPE_CHECKING:
         from logging import Logger
@@ -226,9 +240,7 @@ class ConsumerPlugin(
         version_doc = Document(
             root_document=root_doc_frozen,
             version_index=next_version_index + 1,
-            checksum=hashlib.md5(
-                file_for_checksum.read_bytes(),
-            ).hexdigest(),
+            checksum=compute_checksum(file_for_checksum),
             content=text or "",
             page_count=page_count,
             mime_type=mime_type,
@@ -368,18 +380,15 @@ class ConsumerPlugin(
         Return the document object if it was successfully created.
         """
 
-        tempdir = None
+        # Preflight has already run including progress update to 0%
+        self.log.info(f"Consuming {self.filename}")
 
-        try:
-            # Preflight has already run including progress update to 0%
-            self.log.info(f"Consuming {self.filename}")
-
-            # For the actual work, copy the file into a tempdir
-            tempdir = tempfile.TemporaryDirectory(
-                prefix="paperless-ngx",
-                dir=settings.SCRATCH_DIR,
-            )
-            self.working_copy = Path(tempdir.name) / Path(self.filename)
+        # For the actual work, copy the file into a tempdir
+        with tempfile.TemporaryDirectory(
+            prefix="paperless-ngx",
+            dir=settings.SCRATCH_DIR,
+        ) as tmpdir:
+            self.working_copy = Path(tmpdir) / Path(self.filename)
             copy_file_with_basic_stats(self.input_doc.original_file, self.working_copy)
             self.unmodified_original = None
 
@@ -411,7 +420,7 @@ class ConsumerPlugin(
                     self.log.debug(f"Detected mime type after qpdf: {mime_type}")
                     # Save the original file for later
                     self.unmodified_original = (
-                        Path(tempdir.name) / Path("uo") / Path(self.filename)
+                        Path(tmpdir) / Path("uo") / Path(self.filename)
                     )
                     self.unmodified_original.parent.mkdir(exist_ok=True)
                     copy_file_with_basic_stats(
@@ -422,11 +431,14 @@ class ConsumerPlugin(
                     self.log.error(f"Error attempting to clean PDF: {e}")
 
             # Based on the mime type, get the parser for that type
-            parser_class: type[DocumentParser] | None = get_parser_class_for_mime_type(
-                mime_type,
+            parser_class: type[ParserProtocol] | None = (
+                get_parser_registry().get_parser_for_file(
+                    mime_type,
+                    self.filename,
+                    self.working_copy,
+                )
             )
             if not parser_class:
-                tempdir.cleanup()
                 self._fail(
                     ConsumerStatusShortMessage.UNSUPPORTED_TYPE,
                     f"Unsupported mime type {mime_type}",
@@ -441,319 +453,284 @@ class ConsumerPlugin(
             )
 
             self.run_pre_consume_script()
-        except:
-            if tempdir:
-                tempdir.cleanup()
-            raise
 
-        def progress_callback(
-            current_progress,
-            max_progress,
-        ) -> None:  # pragma: no cover
-            # recalculate progress to be within 20 and 80
-            p = int((current_progress / max_progress) * 50 + 20)
-            self._send_progress(p, 100, ProgressStatusOptions.WORKING)
-
-        # This doesn't parse the document yet, but gives us a parser.
-
-        document_parser: DocumentParser = parser_class(
-            self.logging_group,
-            progress_callback=progress_callback,
-        )
-
-        parser_is_new_style = isinstance(
-            document_parser,
-            (
-                MailDocumentParser,
-                RasterisedDocumentParser,
-                RemoteDocumentParser,
-                TextDocumentParser,
-                TikaDocumentParser,
-            ),
-        )
-
-        # 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 parser_is_new_style:
-            document_parser.__enter__()
-
-        self.log.debug(f"Parser: {type(document_parser).__name__}")
-
-        # Parse the document. This may take some time.
-
-        text = None
-        date = None
-        thumbnail = None
-        archive_path = None
-        page_count = None
-
-        try:
-            self._send_progress(
-                20,
-                100,
-                ProgressStatusOptions.WORKING,
-                ConsumerStatusShortMessage.PARSING_DOCUMENT,
-            )
-            self.log.debug(f"Parsing {self.filename}...")
-
-            # TODO(stumpylog): Remove me in the future when all parsers use new protocol
-            if parser_is_new_style:
+            # This doesn't parse the document yet, but gives us a parser.
+            with parser_class() as document_parser:
                 document_parser.configure(
                     ParserContext(mailrule_id=self.input_doc.mailrule_id),
                 )
-                # 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)
 
-            self.log.debug(f"Generating thumbnail for {self.filename}...")
-            self._send_progress(
-                70,
-                100,
-                ProgressStatusOptions.WORKING,
-                ConsumerStatusShortMessage.GENERATING_THUMBNAIL,
-            )
-            # TODO(stumpylog): Remove me in the future when all parsers use new protocol
-            if parser_is_new_style:
-                thumbnail = document_parser.get_thumbnail(self.working_copy, mime_type)
-            else:
-                thumbnail = document_parser.get_thumbnail(
-                    self.working_copy,
-                    mime_type,
-                    self.filename,
+                self.log.debug(
+                    f"Parser: {document_parser.name} v{document_parser.version}",
                 )
 
-            text = document_parser.get_text()
-            date = document_parser.get_date()
-            if date is None:
+                # Parse the document. This may take some time.
+
+                text = None
+                date = None
+                thumbnail = None
+                archive_path = None
+                page_count = None
+
+                try:
+                    self._send_progress(
+                        20,
+                        100,
+                        ProgressStatusOptions.WORKING,
+                        ConsumerStatusShortMessage.PARSING_DOCUMENT,
+                    )
+                    self.log.debug(f"Parsing {self.filename}...")
+
+                    produce_archive = should_produce_archive(
+                        document_parser,
+                        mime_type,
+                        self.working_copy,
+                    )
+                    document_parser.parse(
+                        self.working_copy,
+                        mime_type,
+                        produce_archive=produce_archive,
+                    )
+
+                    self.log.debug(f"Generating thumbnail for {self.filename}...")
+                    self._send_progress(
+                        70,
+                        100,
+                        ProgressStatusOptions.WORKING,
+                        ConsumerStatusShortMessage.GENERATING_THUMBNAIL,
+                    )
+                    thumbnail = document_parser.get_thumbnail(
+                        self.working_copy,
+                        mime_type,
+                    )
+
+                    text = document_parser.get_text()
+                    date = document_parser.get_date()
+                    if date is None:
+                        self._send_progress(
+                            90,
+                            100,
+                            ProgressStatusOptions.WORKING,
+                            ConsumerStatusShortMessage.PARSE_DATE,
+                        )
+                        with get_date_parser() as date_parser:
+                            date = next(date_parser.parse(self.filename, text), None)
+                    archive_path = document_parser.get_archive_path()
+                    page_count = document_parser.get_page_count(
+                        self.working_copy,
+                        mime_type,
+                    )
+
+                except ParseError as e:
+                    self._fail(
+                        str(e),
+                        f"Error occurred while consuming document {self.filename}: {e}",
+                        exc_info=True,
+                        exception=e,
+                    )
+                except Exception as e:
+                    self._fail(
+                        str(e),
+                        f"Unexpected error while consuming document {self.filename}: {e}",
+                        exc_info=True,
+                        exception=e,
+                    )
+
+                # Prepare the document classifier.
+
+                # TODO: I don't really like to do this here, but this way we avoid
+                #   reloading the classifier multiple times, since there are multiple
+                #   post-consume hooks that all require the classifier.
+
+                classifier = load_classifier()
+
                 self._send_progress(
-                    90,
+                    95,
                     100,
                     ProgressStatusOptions.WORKING,
-                    ConsumerStatusShortMessage.PARSE_DATE,
+                    ConsumerStatusShortMessage.SAVE_DOCUMENT,
                 )
-                with get_date_parser() as date_parser:
-                    date = next(date_parser.parse(self.filename, text), None)
-            archive_path = document_parser.get_archive_path()
-            page_count = document_parser.get_page_count(self.working_copy, mime_type)
-
-        except ParseError as e:
-            _parser_cleanup(document_parser)
-            if tempdir:
-                tempdir.cleanup()
-            self._fail(
-                str(e),
-                f"Error occurred while consuming document {self.filename}: {e}",
-                exc_info=True,
-                exception=e,
-            )
-        except Exception as e:
-            _parser_cleanup(document_parser)
-            if tempdir:
-                tempdir.cleanup()
-            self._fail(
-                str(e),
-                f"Unexpected error while consuming document {self.filename}: {e}",
-                exc_info=True,
-                exception=e,
-            )
-
-        # Prepare the document classifier.
-
-        # TODO: I don't really like to do this here, but this way we avoid
-        #   reloading the classifier multiple times, since there are multiple
-        #   post-consume hooks that all require the classifier.
-
-        classifier = load_classifier()
-
-        self._send_progress(
-            95,
-            100,
-            ProgressStatusOptions.WORKING,
-            ConsumerStatusShortMessage.SAVE_DOCUMENT,
-        )
-        # now that everything is done, we can start to store the document
-        # in the system. This will be a transaction and reasonably fast.
-        try:
-            with transaction.atomic():
-                # store the document.
-                if self.input_doc.root_document_id:
-                    # If this is a new version of an existing document, we need
-                    # to make sure we're not creating a new document, but updating
-                    # the existing one.
-                    root_doc = Document.objects.get(
-                        pk=self.input_doc.root_document_id,
-                    )
-                    original_document = self._create_version_from_root(
-                        root_doc,
-                        text=text,
-                        page_count=page_count,
-                        mime_type=mime_type,
-                    )
-                    actor = None
-
-                    # Save the new version, potentially creating an audit log entry for the version addition if enabled.
-                    if (
-                        settings.AUDIT_LOG_ENABLED
-                        and self.metadata.actor_id is not None
-                    ):
-                        actor = User.objects.filter(pk=self.metadata.actor_id).first()
-                        if actor is not None:
-                            from auditlog.context import (  # type: ignore[import-untyped]
-                                set_actor,
+                # now that everything is done, we can start to store the document
+                # in the system. This will be a transaction and reasonably fast.
+                try:
+                    with transaction.atomic():
+                        # store the document.
+                        if self.input_doc.root_document_id:
+                            # If this is a new version of an existing document, we need
+                            # to make sure we're not creating a new document, but updating
+                            # the existing one.
+                            root_doc = Document.objects.get(
+                                pk=self.input_doc.root_document_id,
                             )
+                            original_document = self._create_version_from_root(
+                                root_doc,
+                                text=text,
+                                page_count=page_count,
+                                mime_type=mime_type,
+                            )
+                            actor = None
 
-                            with set_actor(actor):
+                            # Save the new version, potentially creating an audit log entry for the version addition if enabled.
+                            if (
+                                settings.AUDIT_LOG_ENABLED
+                                and self.metadata.actor_id is not None
+                            ):
+                                actor = User.objects.filter(
+                                    pk=self.metadata.actor_id,
+                                ).first()
+                                if actor is not None:
+                                    from auditlog.context import (  # type: ignore[import-untyped]
+                                        set_actor,
+                                    )
+
+                                    with set_actor(actor):
+                                        original_document.save()
+                                else:
+                                    original_document.save()
+                            else:
                                 original_document.save()
+
+                            # Create a log entry for the version addition, if enabled
+                            if settings.AUDIT_LOG_ENABLED:
+                                from auditlog.models import (  # type: ignore[import-untyped]
+                                    LogEntry,
+                                )
+
+                                LogEntry.objects.log_create(
+                                    instance=root_doc,
+                                    changes={
+                                        "Version Added": ["None", original_document.id],
+                                    },
+                                    action=LogEntry.Action.UPDATE,
+                                    actor=actor,
+                                    additional_data={
+                                        "reason": "Version added",
+                                        "version_id": original_document.id,
+                                    },
+                                )
+                            document = original_document
                         else:
-                            original_document.save()
-                    else:
-                        original_document.save()
-
-                    # Create a log entry for the version addition, if enabled
-                    if settings.AUDIT_LOG_ENABLED:
-                        from auditlog.models import (  # type: ignore[import-untyped]
-                            LogEntry,
-                        )
-
-                        LogEntry.objects.log_create(
-                            instance=root_doc,
-                            changes={
-                                "Version Added": ["None", original_document.id],
-                            },
-                            action=LogEntry.Action.UPDATE,
-                            actor=actor,
-                            additional_data={
-                                "reason": "Version added",
-                                "version_id": original_document.id,
-                            },
-                        )
-                    document = original_document
-                else:
-                    document = self._store(
-                        text=text,
-                        date=date,
-                        page_count=page_count,
-                        mime_type=mime_type,
-                    )
-
-                # If we get here, it was successful. Proceed with post-consume
-                # hooks. If they fail, nothing will get changed.
-
-                document_consumption_finished.send(
-                    sender=self.__class__,
-                    document=document,
-                    logging_group=self.logging_group,
-                    classifier=classifier,
-                    original_file=self.unmodified_original
-                    if self.unmodified_original
-                    else self.working_copy,
-                )
-
-                # After everything is in the database, copy the files into
-                # place. If this fails, we'll also rollback the transaction.
-                with FileLock(settings.MEDIA_LOCK):
-                    generated_filename = generate_unique_filename(document)
-                    if (
-                        len(str(generated_filename))
-                        > Document.MAX_STORED_FILENAME_LENGTH
-                    ):
-                        self.log.warning(
-                            "Generated source filename exceeds db path limit, falling back to default naming",
-                        )
-                        generated_filename = generate_filename(
-                            document,
-                            use_format=False,
-                        )
-                    document.filename = generated_filename
-                    create_source_path_directory(document.source_path)
-
-                    self._write(
-                        self.unmodified_original
-                        if self.unmodified_original is not None
-                        else self.working_copy,
-                        document.source_path,
-                    )
-
-                    self._write(
-                        thumbnail,
-                        document.thumbnail_path,
-                    )
-
-                    if archive_path and Path(archive_path).is_file():
-                        generated_archive_filename = generate_unique_filename(
-                            document,
-                            archive_filename=True,
-                        )
-                        if (
-                            len(str(generated_archive_filename))
-                            > Document.MAX_STORED_FILENAME_LENGTH
-                        ):
-                            self.log.warning(
-                                "Generated archive filename exceeds db path limit, falling back to default naming",
+                            document = self._store(
+                                text=text,
+                                date=date,
+                                page_count=page_count,
+                                mime_type=mime_type,
                             )
-                            generated_archive_filename = generate_filename(
-                                document,
-                                archive_filename=True,
-                                use_format=False,
-                            )
-                        document.archive_filename = generated_archive_filename
-                        create_source_path_directory(document.archive_path)
-                        self._write(
-                            archive_path,
-                            document.archive_path,
+
+                        # If we get here, it was successful. Proceed with post-consume
+                        # hooks. If they fail, nothing will get changed.
+
+                        document_consumption_finished.send(
+                            sender=self.__class__,
+                            document=document,
+                            logging_group=self.logging_group,
+                            classifier=classifier,
+                            original_file=self.unmodified_original
+                            if self.unmodified_original
+                            else self.working_copy,
                         )
 
-                        with Path(archive_path).open("rb") as f:
-                            document.archive_checksum = hashlib.md5(
-                                f.read(),
-                            ).hexdigest()
+                        # After everything is in the database, copy the files into
+                        # place. If this fails, we'll also rollback the transaction.
+                        with FileLock(settings.MEDIA_LOCK):
+                            generated_filename = generate_unique_filename(document)
+                            if (
+                                len(str(generated_filename))
+                                > Document.MAX_STORED_FILENAME_LENGTH
+                            ):
+                                self.log.warning(
+                                    "Generated source filename exceeds db path limit, falling back to default naming",
+                                )
+                                generated_filename = generate_filename(
+                                    document,
+                                    use_format=False,
+                                )
+                            document.filename = generated_filename
+                            create_source_path_directory(document.source_path)
 
-                # Don't save with the lock active. Saving will cause the file
-                # renaming logic to acquire the lock as well.
-                # This triggers things like file renaming
-                document.save()
+                            self._write(
+                                self.unmodified_original
+                                if self.unmodified_original is not None
+                                else self.working_copy,
+                                document.source_path,
+                            )
 
-                if document.root_document_id:
-                    document_updated.send(
-                        sender=self.__class__,
-                        document=document.root_document,
+                            self._write(
+                                thumbnail,
+                                document.thumbnail_path,
+                            )
+
+                            if archive_path and Path(archive_path).is_file():
+                                generated_archive_filename = generate_unique_filename(
+                                    document,
+                                    archive_filename=True,
+                                )
+                                if (
+                                    len(str(generated_archive_filename))
+                                    > Document.MAX_STORED_FILENAME_LENGTH
+                                ):
+                                    self.log.warning(
+                                        "Generated archive filename exceeds db path limit, falling back to default naming",
+                                    )
+                                    generated_archive_filename = generate_filename(
+                                        document,
+                                        archive_filename=True,
+                                        use_format=False,
+                                    )
+                                document.archive_filename = generated_archive_filename
+                                create_source_path_directory(document.archive_path)
+                                self._write(
+                                    archive_path,
+                                    document.archive_path,
+                                )
+
+                                document.archive_checksum = compute_checksum(
+                                    document.archive_path,
+                                )
+
+                        # Don't save with the lock active. Saving will cause the file
+                        # renaming logic to acquire the lock as well.
+                        # This triggers things like file renaming
+                        document.save()
+
+                        if document.root_document_id:
+                            document_updated.send(
+                                sender=self.__class__,
+                                document=document.root_document,
+                            )
+
+                        # Delete the file only if it was successfully consumed
+                        self.log.debug(
+                            f"Deleting original file {self.input_doc.original_file}",
+                        )
+                        self.input_doc.original_file.unlink()
+                        self.log.debug(f"Deleting working copy {self.working_copy}")
+                        self.working_copy.unlink()
+                        if self.unmodified_original is not None:  # pragma: no cover
+                            self.log.debug(
+                                f"Deleting unmodified original file {self.unmodified_original}",
+                            )
+                            self.unmodified_original.unlink()
+
+                        # https://github.com/jonaswinkler/paperless-ng/discussions/1037
+                        shadow_file = (
+                            Path(self.input_doc.original_file).parent
+                            / f"._{Path(self.input_doc.original_file).name}"
+                        )
+
+                        if Path(shadow_file).is_file():
+                            self.log.debug(f"Deleting shadow file {shadow_file}")
+                            Path(shadow_file).unlink()
+
+                except Exception as e:
+                    self._fail(
+                        str(e),
+                        f"The following error occurred while storing document "
+                        f"{self.filename} after parsing: {e}",
+                        exc_info=True,
+                        exception=e,
                     )
 
-                # Delete the file only if it was successfully consumed
-                self.log.debug(f"Deleting original file {self.input_doc.original_file}")
-                self.input_doc.original_file.unlink()
-                self.log.debug(f"Deleting working copy {self.working_copy}")
-                self.working_copy.unlink()
-                if self.unmodified_original is not None:  # pragma: no cover
-                    self.log.debug(
-                        f"Deleting unmodified original file {self.unmodified_original}",
-                    )
-                    self.unmodified_original.unlink()
-
-                # https://github.com/jonaswinkler/paperless-ng/discussions/1037
-                shadow_file = (
-                    Path(self.input_doc.original_file).parent
-                    / f"._{Path(self.input_doc.original_file).name}"
-                )
-
-                if Path(shadow_file).is_file():
-                    self.log.debug(f"Deleting shadow file {shadow_file}")
-                    Path(shadow_file).unlink()
-
-        except Exception as e:
-            self._fail(
-                str(e),
-                f"The following error occurred while storing document "
-                f"{self.filename} after parsing: {e}",
-                exc_info=True,
-                exception=e,
-            )
-        finally:
-            _parser_cleanup(document_parser)
-            tempdir.cleanup()
-
         self.run_post_consume_script(document)
 
         self.log.info(f"Document {document} consumption finished")
@@ -849,7 +826,7 @@ class ConsumerPlugin(
             title=title[:127],
             content=text,
             mime_type=mime_type,
-            checksum=hashlib.md5(file_for_checksum.read_bytes()).hexdigest(),
+            checksum=compute_checksum(file_for_checksum),
             created=create_date,
             modified=create_date,
             page_count=page_count,
@@ -897,7 +874,7 @@ class ConsumerPlugin(
             self.metadata.view_users is not None
             or self.metadata.view_groups is not None
             or self.metadata.change_users is not None
-            or self.metadata.change_users is not None
+            or self.metadata.change_groups is not None
         ):
             permissions = {
                 "view": {
@@ -930,7 +907,7 @@ class ConsumerPlugin(
             Path(source).open("rb") as read_file,
             Path(target).open("wb") as write_file,
         ):
-            write_file.write(read_file.read())
+            shutil.copyfileobj(read_file, write_file)
 
         # Attempt to copy file's original stats, but it's ok if we can't
         try:
@@ -966,10 +943,9 @@ class ConsumerPreflightPlugin(
 
     def pre_check_duplicate(self) -> None:
         """
-        Using the MD5 of the file, check this exact file doesn't already exist
+        Using the SHA256 of the file, check this exact file doesn't already exist
         """
-        with Path(self.input_doc.original_file).open("rb") as f:
-            checksum = hashlib.md5(f.read()).hexdigest()
+        checksum = compute_checksum(Path(self.input_doc.original_file))
         existing_doc = Document.global_objects.filter(
             Q(checksum=checksum) | Q(archive_checksum=checksum),
         )

src/documents/management/commands/document_exporter.py

@@ -56,6 +56,7 @@ from documents.models import WorkflowTrigger
 from documents.settings import EXPORTER_ARCHIVE_NAME
 from documents.settings import EXPORTER_FILE_NAME
 from documents.settings import EXPORTER_THUMBNAIL_NAME
+from documents.utils import compute_checksum
 from documents.utils import copy_file_with_basic_stats
 from paperless import version
 from paperless.models import ApplicationConfiguration
@@ -693,7 +694,7 @@ class Command(CryptMixin, PaperlessCommand):
             source_stat = source.stat()
             target_stat = target.stat()
             if self.compare_checksums and source_checksum:
-                target_checksum = hashlib.md5(target.read_bytes()).hexdigest()
+                target_checksum = compute_checksum(target)
                 perform_copy = target_checksum != source_checksum
             elif (
                 source_stat.st_mtime != target_stat.st_mtime

src/documents/management/commands/document_thumbnails.py

@@ -3,19 +3,18 @@ import shutil
 
 from documents.management.commands.base import PaperlessCommand
 from documents.models import Document
-from documents.parsers import get_parser_class_for_mime_type
-from paperless.parsers.mail import MailDocumentParser
-from paperless.parsers.remote import RemoteDocumentParser
-from paperless.parsers.tesseract import RasterisedDocumentParser
-from paperless.parsers.text import TextDocumentParser
-from paperless.parsers.tika import TikaDocumentParser
+from paperless.parsers.registry import get_parser_registry
 
 logger = logging.getLogger("paperless.management.thumbnails")
 
 
 def _process_document(doc_id: int) -> None:
     document: Document = Document.objects.get(id=doc_id)
-    parser_class = get_parser_class_for_mime_type(document.mime_type)
+    parser_class = get_parser_registry().get_parser_for_file(
+        document.mime_type,
+        document.original_filename or "",
+        document.source_path,
+    )
 
     if parser_class is None:
         logger.warning(
@@ -25,40 +24,9 @@ def _process_document(doc_id: int) -> None:
         )
         return
 
-    parser = parser_class(logging_group=None)
-
-    parser_is_new_style = isinstance(
-        parser,
-        (
-            MailDocumentParser,
-            RasterisedDocumentParser,
-            RemoteDocumentParser,
-            TextDocumentParser,
-            TikaDocumentParser,
-        ),
-    )
-
-    # TODO(stumpylog): Remove branch in the future when all parsers use new protocol
-    if parser_is_new_style:
-        parser.__enter__()
-
-    try:
-        # TODO(stumpylog): Remove branch in the future when all parsers use new protocol
-        if parser_is_new_style:
-            thumb = parser.get_thumbnail(document.source_path, document.mime_type)
-        else:
-            thumb = parser.get_thumbnail(
-                document.source_path,
-                document.mime_type,
-                document.get_public_filename(),
-            )
+    with parser_class() as parser:
+        thumb = parser.get_thumbnail(document.source_path, document.mime_type)
         shutil.move(thumb, document.thumbnail_path)
-    finally:
-        # TODO(stumpylog): Cleanup once all parsers are handled
-        if parser_is_new_style:
-            parser.__exit__(None, None, None)
-        else:
-            parser.cleanup()
 
 
 class Command(PaperlessCommand):

src/documents/migrations/0016_sha256_checksums.py

@@ -0,0 +1,130 @@
+import hashlib
+import logging
+from pathlib import Path
+
+from django.conf import settings
+from django.db import migrations
+from django.db import models
+
+logger = logging.getLogger("paperless.migrations")
+
+_CHUNK_SIZE = 65536  # 64 KiB — avoids loading entire files into memory
+_BATCH_SIZE = 500  # documents per bulk_update call
+_PROGRESS_INTERVAL = 500  # log a progress line every N documents
+
+
+def _sha256(path: Path) -> str:
+    h = hashlib.sha256()
+    with path.open("rb") as fh:
+        while chunk := fh.read(_CHUNK_SIZE):
+            h.update(chunk)
+    return h.hexdigest()
+
+
+def recompute_checksums(apps, schema_editor):
+    """Recompute all document checksums from MD5 to SHA256."""
+    Document = apps.get_model("documents", "Document")
+
+    total = Document.objects.count()
+    if total == 0:
+        return
+
+    logger.info("Recomputing SHA-256 checksums for %d document(s)...", total)
+
+    batch: list = []
+    processed = 0
+
+    for doc in Document.objects.only(
+        "pk",
+        "filename",
+        "checksum",
+        "archive_filename",
+        "archive_checksum",
+    ).iterator(chunk_size=_BATCH_SIZE):
+        updated_fields: list[str] = []
+
+        # Reconstruct source path the same way Document.source_path does
+        fname = str(doc.filename) if doc.filename else f"{doc.pk:07}.pdf"
+        source_path = (settings.ORIGINALS_DIR / Path(fname)).resolve()
+
+        if source_path.exists():
+            doc.checksum = _sha256(source_path)
+            updated_fields.append("checksum")
+        else:
+            logger.warning(
+                "Document %s: original file %s not found, checksum not updated.",
+                doc.pk,
+                source_path,
+            )
+
+        # Mirror Document.has_archive_version: archive_filename is not None
+        if doc.archive_filename is not None:
+            archive_path = (
+                settings.ARCHIVE_DIR / Path(str(doc.archive_filename))
+            ).resolve()
+            if archive_path.exists():
+                doc.archive_checksum = _sha256(archive_path)
+                updated_fields.append("archive_checksum")
+            else:
+                logger.warning(
+                    "Document %s: archive file %s not found, checksum not updated.",
+                    doc.pk,
+                    archive_path,
+                )
+
+        if updated_fields:
+            batch.append(doc)
+
+        processed += 1
+
+        if len(batch) >= _BATCH_SIZE:
+            Document.objects.bulk_update(batch, ["checksum", "archive_checksum"])
+            batch.clear()
+
+        if processed % _PROGRESS_INTERVAL == 0:
+            logger.info(
+                "SHA-256 checksum progress: %d/%d (%d%%)",
+                processed,
+                total,
+                processed * 100 // total,
+            )
+
+    if batch:
+        Document.objects.bulk_update(batch, ["checksum", "archive_checksum"])
+
+    logger.info(
+        "SHA-256 checksum recomputation complete: %d document(s) processed.",
+        total,
+    )
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0015_document_version_index_and_more"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="document",
+            name="checksum",
+            field=models.CharField(
+                editable=False,
+                help_text="The checksum of the original document.",
+                max_length=64,
+                verbose_name="checksum",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="archive_checksum",
+            field=models.CharField(
+                blank=True,
+                editable=False,
+                help_text="The checksum of the archived document.",
+                max_length=64,
+                null=True,
+                verbose_name="archive checksum",
+            ),
+        ),
+        migrations.RunPython(recompute_checksums, migrations.RunPython.noop),
+    ]

src/documents/models.py

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

src/documents/parsers.py

@@ -3,84 +3,47 @@ from __future__ import annotations
 import logging
 import mimetypes
 import os
-import re
 import shutil
 import subprocess
 import tempfile
-from functools import lru_cache
 from pathlib import Path
 from typing import TYPE_CHECKING
 
 from django.conf import settings
 
 from documents.loggers import LoggingMixin
-from documents.signals import document_consumer_declaration
 from documents.utils import copy_file_with_basic_stats
 from documents.utils import run_subprocess
+from paperless.parsers.registry import get_parser_registry
 
 if TYPE_CHECKING:
     import datetime
 
-# This regular expression will try to find dates in the document at
-# hand and will match the following formats:
-# - XX.YY.ZZZZ with XX + YY being 1 or 2 and ZZZZ being 2 or 4 digits
-# - XX/YY/ZZZZ with XX + YY being 1 or 2 and ZZZZ being 2 or 4 digits
-# - XX-YY-ZZZZ with XX + YY being 1 or 2 and ZZZZ being 2 or 4 digits
-# - ZZZZ.XX.YY with XX + YY being 1 or 2 and ZZZZ being 2 or 4 digits
-# - ZZZZ/XX/YY with XX + YY being 1 or 2 and ZZZZ being 2 or 4 digits
-# - ZZZZ-XX-YY with XX + YY being 1 or 2 and ZZZZ being 2 or 4 digits
-# - XX. MONTH ZZZZ with XX being 1 or 2 and ZZZZ being 2 or 4 digits
-# - MONTH ZZZZ, with ZZZZ being 4 digits
-# - MONTH XX, ZZZZ with XX being 1 or 2 and ZZZZ being 4 digits
-# - XX MON ZZZZ with XX being 1 or 2 and ZZZZ being 4 digits. MONTH is 3 letters
-# - XXPP MONTH ZZZZ with XX being 1 or 2 and PP being 2 letters and ZZZZ being 4 digits
-
-# TODO: isn't there a date parsing library for this?
-
-DATE_REGEX = re.compile(
-    r"(\b|(?!=([_-])))(\d{1,2})[\.\/-](\d{1,2})[\.\/-](\d{4}|\d{2})(\b|(?=([_-])))|"
-    r"(\b|(?!=([_-])))(\d{4}|\d{2})[\.\/-](\d{1,2})[\.\/-](\d{1,2})(\b|(?=([_-])))|"
-    r"(\b|(?!=([_-])))(\d{1,2}[\. ]+[a-zéûäëčžúřěáíóńźçŞğü]{3,9} \d{4}|[a-zéûäëčžúřěáíóńźçŞğü]{3,9} \d{1,2}, \d{4})(\b|(?=([_-])))|"
-    r"(\b|(?!=([_-])))([^\W\d_]{3,9} \d{1,2}, (\d{4}))(\b|(?=([_-])))|"
-    r"(\b|(?!=([_-])))([^\W\d_]{3,9} \d{4})(\b|(?=([_-])))|"
-    r"(\b|(?!=([_-])))(\d{1,2}[^ 0-9]{2}[\. ]+[^ ]{3,9}[ \.\/-]\d{4})(\b|(?=([_-])))|"
-    r"(\b|(?!=([_-])))(\b\d{1,2}[ \.\/-][a-zéûäëčžúřěáíóńźçŞğü]{3}[ \.\/-]\d{4})(\b|(?=([_-])))",
-    re.IGNORECASE,
-)
-
-
 logger = logging.getLogger("paperless.parsing")
 
 
-@lru_cache(maxsize=8)
 def is_mime_type_supported(mime_type: str) -> bool:
     """
     Returns True if the mime type is supported, False otherwise
     """
-    return get_parser_class_for_mime_type(mime_type) is not None
+    return get_parser_registry().get_parser_for_file(mime_type, "") is not None
 
 
-@lru_cache(maxsize=8)
 def get_default_file_extension(mime_type: str) -> str:
     """
     Returns the default file extension for a mimetype, or
     an empty string if it could not be determined
     """
-    for response in document_consumer_declaration.send(None):
-        parser_declaration = response[1]
-        supported_mime_types = parser_declaration["mime_types"]
-
-        if mime_type in supported_mime_types:
-            return supported_mime_types[mime_type]
+    parser_class = get_parser_registry().get_parser_for_file(mime_type, "")
+    if parser_class is not None:
+        supported = parser_class.supported_mime_types()
+        if mime_type in supported:
+            return supported[mime_type]
 
     ext = mimetypes.guess_extension(mime_type)
-    if ext:
-        return ext
-    else:
-        return ""
+    return ext if ext else ""
 
 
-@lru_cache(maxsize=8)
 def is_file_ext_supported(ext: str) -> bool:
     """
     Returns True if the file extension is supported, False otherwise
@@ -94,44 +57,17 @@ def is_file_ext_supported(ext: str) -> bool:
 
 def get_supported_file_extensions() -> set[str]:
     extensions = set()
-    for response in document_consumer_declaration.send(None):
-        parser_declaration = response[1]
-        supported_mime_types = parser_declaration["mime_types"]
-
-        for mime_type in supported_mime_types:
+    for parser_class in get_parser_registry().all_parsers():
+        for mime_type, ext in parser_class.supported_mime_types().items():
             extensions.update(mimetypes.guess_all_extensions(mime_type))
             # Python's stdlib might be behind, so also add what the parser
             # says is the default extension
             # This makes image/webp supported on Python < 3.11
-            extensions.add(supported_mime_types[mime_type])
+            extensions.add(ext)
 
     return extensions
 
 
-def get_parser_class_for_mime_type(mime_type: str) -> type[DocumentParser] | None:
-    """
-    Returns the best parser (by weight) for the given mimetype or
-    None if no parser exists
-    """
-
-    options = []
-
-    for response in document_consumer_declaration.send(None):
-        parser_declaration = response[1]
-        supported_mime_types = parser_declaration["mime_types"]
-
-        if mime_type in supported_mime_types:
-            options.append(parser_declaration)
-
-    if not options:
-        return None
-
-    best_parser = sorted(options, key=lambda _: _["weight"], reverse=True)[0]
-
-    # Return the parser with the highest weight.
-    return best_parser["parser"]
-
-
 def run_convert(
     input_file,
     output_file,

src/documents/sanity_checker.py

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

src/documents/signals/__init__.py

@@ -2,5 +2,4 @@ from django.dispatch import Signal
 
 document_consumption_started = Signal()
 document_consumption_finished = Signal()
-document_consumer_declaration = Signal()
 document_updated = Signal()

src/documents/tasks.py

@@ -1,5 +1,4 @@
 import datetime
-import hashlib
 import logging
 import shutil
 import uuid
@@ -35,6 +34,7 @@ from documents.consumer import AsnCheckPlugin
 from documents.consumer import ConsumerPlugin
 from documents.consumer import ConsumerPreflightPlugin
 from documents.consumer import WorkflowTriggerPlugin
+from documents.consumer import should_produce_archive
 from documents.data_models import ConsumableDocument
 from documents.data_models import DocumentMetadataOverrides
 from documents.double_sided import CollatePlugin
@@ -52,25 +52,20 @@ from documents.models import StoragePath
 from documents.models import Tag
 from documents.models import WorkflowRun
 from documents.models import WorkflowTrigger
-from documents.parsers import DocumentParser
-from documents.parsers import get_parser_class_for_mime_type
 from documents.plugins.base import ConsumeTaskPlugin
-from documents.plugins.base import ProgressManager
 from documents.plugins.base import StopConsumeTaskError
+from documents.plugins.helpers import ProgressManager
 from documents.plugins.helpers import ProgressStatusOptions
 from documents.sanity_checker import SanityCheckFailedException
 from documents.signals import document_updated
 from documents.signals.handlers import cleanup_document_deletion
 from documents.signals.handlers import run_workflows
 from documents.signals.handlers import send_websocket_document_updated
+from documents.utils import compute_checksum
 from documents.workflows.utils import get_workflows_for_trigger
 from paperless.config import AIConfig
 from paperless.parsers import ParserContext
-from paperless.parsers.mail import MailDocumentParser
-from paperless.parsers.remote import RemoteDocumentParser
-from paperless.parsers.tesseract import RasterisedDocumentParser
-from paperless.parsers.text import TextDocumentParser
-from paperless.parsers.tika import TikaDocumentParser
+from paperless.parsers.registry import get_parser_registry
 from paperless_ai.indexing import llm_index_add_or_update_document
 from paperless_ai.indexing import llm_index_remove_document
 from paperless_ai.indexing import update_llm_index
@@ -310,8 +305,10 @@ def update_document_content_maybe_archive_file(document_id) -> None:
 
     mime_type = document.mime_type
 
-    parser_class: type[DocumentParser] | None = get_parser_class_for_mime_type(
+    parser_class = get_parser_registry().get_parser_for_file(
         mime_type,
+        document.original_filename or "",
+        document.source_path,
     )
 
     if not parser_class:
@@ -321,138 +318,100 @@ def update_document_content_maybe_archive_file(document_id) -> None:
         )
         return
 
-    parser: DocumentParser = parser_class(logging_group=uuid.uuid4())
+    with parser_class() as parser:
+        parser.configure(ParserContext())
 
-    parser_is_new_style = isinstance(
-        parser,
-        (
-            MailDocumentParser,
-            RasterisedDocumentParser,
-            RemoteDocumentParser,
-            TextDocumentParser,
-            TikaDocumentParser,
-        ),
-    )
-
-    # TODO(stumpylog): Remove branch in the future when all parsers use new protocol
-    if parser_is_new_style:
-        parser.__enter__()
-
-    try:
-        # TODO(stumpylog): Remove branch in the future when all parsers use new protocol
-        if parser_is_new_style:
-            parser.configure(ParserContext())
-            parser.parse(document.source_path, mime_type)
-        else:
+        try:
+            produce_archive = should_produce_archive(
+                parser,
+                mime_type,
+                document.source_path,
+            )
             parser.parse(
                 document.source_path,
                 mime_type,
-                document.get_public_filename(),
+                produce_archive=produce_archive,
             )
 
-        # TODO(stumpylog): Remove branch in the future when all parsers use new protocol
-        if parser_is_new_style:
             thumbnail = parser.get_thumbnail(document.source_path, mime_type)
-        else:
-            thumbnail = parser.get_thumbnail(
-                document.source_path,
-                mime_type,
-                document.get_public_filename(),
-            )
 
-        with transaction.atomic():
-            oldDocument = Document.objects.get(pk=document.pk)
-            if parser.get_archive_path():
-                with Path(parser.get_archive_path()).open("rb") as f:
-                    checksum = hashlib.md5(f.read()).hexdigest()
-                # I'm going to save first so that in case the file move
-                # fails, the database is rolled back.
-                # We also don't use save() since that triggers the filehandling
-                # logic, and we don't want that yet (file not yet in place)
-                document.archive_filename = generate_unique_filename(
-                    document,
-                    archive_filename=True,
-                )
-                Document.objects.filter(pk=document.pk).update(
-                    archive_checksum=checksum,
-                    content=parser.get_text(),
-                    archive_filename=document.archive_filename,
-                )
-                newDocument = Document.objects.get(pk=document.pk)
-                if settings.AUDIT_LOG_ENABLED:
-                    LogEntry.objects.log_create(
-                        instance=oldDocument,
-                        changes={
-                            "content": [oldDocument.content, newDocument.content],
-                            "archive_checksum": [
-                                oldDocument.archive_checksum,
-                                newDocument.archive_checksum,
-                            ],
-                            "archive_filename": [
-                                oldDocument.archive_filename,
-                                newDocument.archive_filename,
-                            ],
-                        },
-                        additional_data={
-                            "reason": "Update document content",
-                        },
-                        action=LogEntry.Action.UPDATE,
-                    )
-            else:
-                Document.objects.filter(pk=document.pk).update(
-                    content=parser.get_text(),
-                )
-
-                if settings.AUDIT_LOG_ENABLED:
-                    LogEntry.objects.log_create(
-                        instance=oldDocument,
-                        changes={
-                            "content": [oldDocument.content, parser.get_text()],
-                        },
-                        additional_data={
-                            "reason": "Update document content",
-                        },
-                        action=LogEntry.Action.UPDATE,
-                    )
-
-            with FileLock(settings.MEDIA_LOCK):
+            with transaction.atomic():
+                oldDocument = Document.objects.get(pk=document.pk)
                 if parser.get_archive_path():
-                    create_source_path_directory(document.archive_path)
-                    shutil.move(parser.get_archive_path(), document.archive_path)
-                shutil.move(thumbnail, document.thumbnail_path)
+                    checksum = compute_checksum(parser.get_archive_path())
+                    # I'm going to save first so that in case the file move
+                    # fails, the database is rolled back.
+                    # We also don't use save() since that triggers the filehandling
+                    # logic, and we don't want that yet (file not yet in place)
+                    document.archive_filename = generate_unique_filename(
+                        document,
+                        archive_filename=True,
+                    )
+                    Document.objects.filter(pk=document.pk).update(
+                        archive_checksum=checksum,
+                        content=parser.get_text(),
+                        archive_filename=document.archive_filename,
+                    )
+                    newDocument = Document.objects.get(pk=document.pk)
+                    if settings.AUDIT_LOG_ENABLED:
+                        LogEntry.objects.log_create(
+                            instance=oldDocument,
+                            changes={
+                                "content": [oldDocument.content, newDocument.content],
+                                "archive_checksum": [
+                                    oldDocument.archive_checksum,
+                                    newDocument.archive_checksum,
+                                ],
+                                "archive_filename": [
+                                    oldDocument.archive_filename,
+                                    newDocument.archive_filename,
+                                ],
+                            },
+                            additional_data={
+                                "reason": "Update document content",
+                            },
+                            action=LogEntry.Action.UPDATE,
+                        )
+                else:
+                    Document.objects.filter(pk=document.pk).update(
+                        content=parser.get_text(),
+                    )
 
-        document.refresh_from_db()
-        logger.info(
-            f"Updating index for document {document_id} ({document.archive_checksum})",
-        )
-        with index.open_index_writer() as writer:
-            index.update_document(writer, document)
+                    if settings.AUDIT_LOG_ENABLED:
+                        LogEntry.objects.log_create(
+                            instance=oldDocument,
+                            changes={
+                                "content": [oldDocument.content, parser.get_text()],
+                            },
+                            additional_data={
+                                "reason": "Update document content",
+                            },
+                            action=LogEntry.Action.UPDATE,
+                        )
 
-        ai_config = AIConfig()
-        if ai_config.llm_index_enabled:
-            llm_index_add_or_update_document(document)
+                with FileLock(settings.MEDIA_LOCK):
+                    if parser.get_archive_path():
+                        create_source_path_directory(document.archive_path)
+                        shutil.move(parser.get_archive_path(), document.archive_path)
+                    shutil.move(thumbnail, document.thumbnail_path)
 
-        clear_document_caches(document.pk)
+            document.refresh_from_db()
+            logger.info(
+                f"Updating index for document {document_id} ({document.archive_checksum})",
+            )
+            with index.open_index_writer() as writer:
+                index.update_document(writer, document)
 
-    except Exception:
-        logger.exception(
-            f"Error while parsing document {document} (ID: {document_id})",
-        )
-    finally:
-        # TODO(stumpylog): Remove branch in the future when all parsers use new protocol
-        if isinstance(
-            parser,
-            (
-                MailDocumentParser,
-                RasterisedDocumentParser,
-                RemoteDocumentParser,
-                TextDocumentParser,
-                TikaDocumentParser,
-            ),
-        ):
-            parser.__exit__(None, None, None)
-        else:
-            parser.cleanup()
+            ai_config = AIConfig()
+            if ai_config.llm_index_enabled:
+                llm_index_add_or_update_document(document)
+
+            clear_document_caches(document.pk)
+
+        except Exception:
+            logger.exception(
+                f"Error while parsing document {document} (ID: {document_id})",
+            )
 
 
 @shared_task
@@ -583,13 +542,13 @@ def check_scheduled_workflows() -> None:
                             id__in=matched_ids,
                         )
 
-                if documents.count() > 0:
+                if documents.exists():
                     documents = prefilter_documents_by_workflowtrigger(
                         documents,
                         trigger,
                     )
 
-                if documents.count() > 0:
+                if documents.exists():
                     logger.debug(
                         f"Found {documents.count()} documents for trigger {trigger}",
                     )

src/documents/templates/account/login.html

@@ -9,7 +9,7 @@
     <p>
       {% translate "Please sign in." %}
       {% if ACCOUNT_ALLOW_SIGNUPS %}
-          <br/>{% blocktrans %}Don't have an account yet? <a href="{{ signup_url }}">Sign up</a>{% endblocktrans %}
+          <br/>{% translate "Don't have an account yet?" %} <a href="{{ signup_url }}">{% translate "Sign up" %}</a>
       {% endif %}
     </p>
 {% endblock form_top_content %}
@@ -25,12 +25,12 @@
         {% translate "Username" as i18n_username %}
         {% translate "Password" as i18n_password %}
         <div class="form-floating form-stacked-top">
-            <input type="text" name="login" id="inputUsername" placeholder="{{ i18n_username }}" class="form-control" autocorrect="off" autocapitalize="none" required autofocus>
-            <label for="inputUsername">{{ i18n_username }}</label>
+            <input type="text" name="login" id="inputUsername" placeholder="{{ i18n_username|force_escape }}" class="form-control" autocorrect="off" autocapitalize="none" required autofocus>
+            <label for="inputUsername">{{ i18n_username|force_escape }}</label>
         </div>
         <div class="form-floating form-stacked-bottom">
-            <input type="password" name="password" id="inputPassword" placeholder="{{ i18n_password }}" class="form-control" required>
-            <label for="inputPassword">{{ i18n_password }}</label>
+            <input type="password" name="password" id="inputPassword" placeholder="{{ i18n_password|force_escape }}" class="form-control" required>
+            <label for="inputPassword">{{ i18n_password|force_escape }}</label>
         </div>
         <div class="d-grid mt-3">
             <button class="btn btn-lg btn-primary" type="submit">{% translate "Sign in" %}</button>

src/documents/templates/account/password_reset.html

@@ -14,8 +14,8 @@
     {% endif %}
     {% translate "Email" as i18n_email %}
     <div class="form-floating">
-        <input type="email" name="{{form.email.name}}" id="inputEmail" placeholder="{{ i18n_email }}" class="form-control" required>
-        <label for="inputEmail">{{ i18n_email }}</label>
+        <input type="email" name="{{form.email.name}}" id="inputEmail" placeholder="{{ i18n_email|force_escape }}" class="form-control" required>
+        <label for="inputEmail">{{ i18n_email|force_escape }}</label>
     </div>
     <div class="d-grid mt-3">
         <button class="btn btn-lg btn-primary" type="submit">{% translate "Send me instructions!" %}</button>

src/documents/templates/account/password_reset_from_key.html

@@ -17,12 +17,12 @@
         {% translate "New Password" as i18n_new_password1 %}
         {% translate "Confirm Password" as i18n_new_password2 %}
         <div class="form-floating form-stacked-top">
-            <input type="password" name="{{form.password1.name}}" id="inputPassword1" placeholder="{{ i18n_new_password1 }}" class="form-control" required>
-            <label for="inputPassword1">{{ i18n_new_password1 }}</label>
+            <input type="password" name="{{form.password1.name}}" id="inputPassword1" placeholder="{{ i18n_new_password1|force_escape }}" class="form-control" required>
+            <label for="inputPassword1">{{ i18n_new_password1|force_escape }}</label>
         </div>
         <div class="form-floating form-stacked-bottom">
-            <input type="password" name="{{form.password2.name}}" id="inputPassword2" placeholder="{{ i18n_new_password2 }}" class="form-control" required>
-            <label for="inputPassword2">{{ i18n_new_password2 }}</label>
+            <input type="password" name="{{form.password2.name}}" id="inputPassword2" placeholder="{{ i18n_new_password2|force_escape }}" class="form-control" required>
+            <label for="inputPassword2">{{ i18n_new_password2|force_escape }}</label>
         </div>
         <div class="d-grid mt-3">
             <button class="btn btn-lg btn-primary" type="submit">{% translate "Change my password" %}</button>

src/documents/templates/account/password_reset_from_key_done.html

@@ -11,5 +11,5 @@
 
 {% block form_content %}
     {% url 'account_login' as login_url %}
-    <p>{% blocktranslate %}Your new password has been set. You can now <a href="{{ login_url }}">log in</a>{% endblocktranslate %}.</p>
+    <p>{% translate "Your new password has been set. You can now" %} <a href="{{ login_url }}">{% translate "log in" %}</a>.</p>
 {% endblock form_content %}

src/documents/templates/account/signup.html

@@ -8,7 +8,7 @@
 {% block form_top_content %}
 		{% if not FIRST_INSTALL %}
 			<p>
-					{% blocktrans %}Already have an account? <a href="{{ login_url }}">Sign in</a>{% endblocktrans %}
+					{% translate "Already have an account?" %} <a href="{{ login_url }}">{% translate "Sign in" %}</a>
 			</p>
 		{% endif %}
 {% endblock form_top_content %}
@@ -16,7 +16,7 @@
 {% block form_content %}
 		{% if FIRST_INSTALL %}
 			<p>
-				{% blocktrans %}Note: This is the first user account for this installation and will be granted superuser privileges.{% endblocktrans %}
+				{% translate "Note: This is the first user account for this installation and will be granted superuser privileges." %}
 			</p>
 		{% endif %}
     {% translate "Username" as i18n_username %}
@@ -24,20 +24,20 @@
     {% translate "Password" as i18n_password1 %}
     {% translate "Password (again)" as i18n_password2 %}
     <div class="form-floating form-stacked-top">
-        <input type="text" name="username" id="inputUsername" placeholder="{{ i18n_username }}" class="form-control" autocorrect="off" autocapitalize="none" required autofocus>
-        <label for="inputUsername">{{ i18n_username }}</label>
+        <input type="text" name="username" id="inputUsername" placeholder="{{ i18n_username|force_escape }}" class="form-control" autocorrect="off" autocapitalize="none" required autofocus>
+        <label for="inputUsername">{{ i18n_username|force_escape }}</label>
     </div>
     <div class="form-floating form-stacked-middle">
-        <input type="email" name="email" id="inputEmail" placeholder="{{ i18n_email }}" class="form-control">
-        <label for="inputEmail">{{ i18n_email }}</label>
+        <input type="email" name="email" id="inputEmail" placeholder="{{ i18n_email|force_escape }}" class="form-control">
+        <label for="inputEmail">{{ i18n_email|force_escape }}</label>
     </div>
     <div class="form-floating form-stacked-middle">
-        <input type="password" name="password1" id="inputPassword1" placeholder="{{ i18n_password1 }}" class="form-control" required>
-        <label for="inputPassword1">{{ i18n_password1 }}</label>
+        <input type="password" name="password1" id="inputPassword1" placeholder="{{ i18n_password1|force_escape }}" class="form-control" required>
+        <label for="inputPassword1">{{ i18n_password1|force_escape }}</label>
     </div>
     <div class="form-floating form-stacked-bottom">
-        <input type="password" name="password2" id="inputPassword2" placeholder="{{ i18n_password2 }}" class="form-control" required>
-        <label for="inputPassword2">{{ i18n_password2 }}</label>
+        <input type="password" name="password2" id="inputPassword2" placeholder="{{ i18n_password2|force_escape }}" class="form-control" required>
+        <label for="inputPassword2">{{ i18n_password2|force_escape }}</label>
     </div>
     <div class="d-grid mt-3">
         <button class="btn btn-lg btn-primary" type="submit">{% translate "Sign up" %}</button>

src/documents/templates/mfa/authenticate.html

@@ -9,15 +9,15 @@
 
 {% block form_top_content %}
 	<p>
-		{% blocktranslate %}Your account is protected by two-factor authentication. Please enter an authenticator code:{% endblocktranslate %}
+		{% translate "Your account is protected by two-factor authentication. Please enter an authenticator code:" %}
 	</p>
 {% endblock form_top_content %}
 
 {% block form_content %}
 {% translate "Code" as i18n_code %}
 <div class="form-floating">
-		<input type="code" name="code" id="inputCode" autocomplete="one-time-code" placeholder="{{ i18n_code }}" class="form-control" required autofocus>
-		<label for="inputCode">{{ i18n_code }}</label>
+		<input type="code" name="code" id="inputCode" autocomplete="one-time-code" placeholder="{{ i18n_code|force_escape }}" class="form-control" required autofocus>
+		<label for="inputCode">{{ i18n_code|force_escape }}</label>
 </div>
 <div class="d-grid mt-3">
 		<button class="btn btn-lg btn-primary" type="submit">{% translate "Sign in" %}</button>

src/documents/templates/socialaccount/authentication_error.html

@@ -7,5 +7,5 @@
 
 {% block form_content %}
     {% url 'account_login' as login_url %}
-    <p>{% blocktranslate %}An error occurred while attempting to login via your social network account. Back to the <a href="{{ login_url }}">login page</a>{% endblocktranslate %}</p>
+    <p>{% translate "An error occurred while attempting to login via your social network account. Back to the" %} <a href="{{ login_url }}">{% translate "login page" %}</a></p>
 {% endblock form_content %}

src/documents/templates/socialaccount/login.html

@@ -7,7 +7,9 @@
 
 {% block form_content %}
     <p>
-        {% blocktrans with provider.name as provider %}You are about to connect a new third-party account from {{ provider }}.{% endblocktrans %}
+        {% filter force_escape %}
+            {% blocktrans with provider=provider.name %}You are about to connect a new third-party account from {{ provider }}.{% endblocktrans %}
+        {% endfilter %}
     </p>
     <div class="d-grid mt-3">
         <button class="btn btn-lg btn-primary" type="submit">{% translate "Continue" %}</button>

src/documents/templates/socialaccount/signup.html

@@ -7,18 +7,20 @@
 
 {% block form_content %}
     <p>
-        {% blocktrans with provider_name=account.get_provider.name %}You are about to use your {{provider_name}} account to login.{% endblocktrans %}
-        {% blocktrans %}As a final step, please complete the following form:{% endblocktrans %}
+        {% filter force_escape %}
+            {% blocktrans with provider_name=account.get_provider.name %}You are about to use your {{ provider_name }} account to login.{% endblocktrans %}
+        {% endfilter %}
+        {% translate "As a final step, please complete the following form:" %}
     </p>
     {% translate "Username" as i18n_username %}
     {% translate "Email (optional)" as i18n_email %}
     <div class="form-floating form-stacked-top">
-        <input type="text" name="{{ form.username.name }}" id="inputUsername" placeholder="{{ i18n_username }}" class="form-control" autocorrect="off" autocapitalize="none" required autofocus value="{{ form.username.value }}">
-        <label for="inputUsername">{{ i18n_username }}</label>
+        <input type="text" name="{{ form.username.name }}" id="inputUsername" placeholder="{{ i18n_username|force_escape }}" class="form-control" autocorrect="off" autocapitalize="none" required autofocus value="{{ form.username.value }}">
+        <label for="inputUsername">{{ i18n_username|force_escape }}</label>
     </div>
     <div class="form-floating form-stacked-bottom">
-        <input type="email" name="{{ form.email.name }}" id="inputEmail" placeholder="{{ i18n_email }}" class="form-control" autocorrect="off" autocapitalize="none" autofocus value="{{ form.email.value }}">
-        <label for="inputEmail">{{ i18n_email }}</label>
+        <input type="email" name="{{ form.email.name }}" id="inputEmail" placeholder="{{ i18n_email|force_escape }}" class="form-control" autocorrect="off" autocapitalize="none" autofocus value="{{ form.email.value }}">
+        <label for="inputEmail">{{ i18n_email|force_escape }}</label>
     </div>
     {% if redirect_field_value %}
         <input type="hidden" name="{{ redirect_field_name }}" value="{{ redirect_field_value }}" />

src/documents/tests/conftest.py

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

src/documents/tests/factories.py

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

src/documents/tests/test_api_app_config.py

@@ -46,7 +46,7 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
                 "pages": None,
                 "language": None,
                 "mode": None,
-                "skip_archive_file": None,
+                "archive_file_generation": None,
                 "image_dpi": None,
                 "unpaper_clean": None,
                 "deskew": None,

src/documents/tests/test_api_documents.py

@@ -1144,56 +1144,6 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
         self.assertEqual(len(response.data["all"]), 50)
         self.assertCountEqual(response.data["all"], [d.id for d in docs])
 
-    def test_list_with_include_selection_data(self) -> None:
-        correspondent = Correspondent.objects.create(name="c1")
-        doc_type = DocumentType.objects.create(name="dt1")
-        storage_path = StoragePath.objects.create(name="sp1")
-        tag = Tag.objects.create(name="tag")
-
-        matching_doc = Document.objects.create(
-            checksum="A",
-            correspondent=correspondent,
-            document_type=doc_type,
-            storage_path=storage_path,
-        )
-        matching_doc.tags.add(tag)
-
-        non_matching_doc = Document.objects.create(checksum="B")
-        non_matching_doc.tags.add(Tag.objects.create(name="other"))
-
-        response = self.client.get(
-            f"/api/documents/?tags__id__in={tag.id}&include_selection_data=true",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_200_OK)
-        self.assertIn("selection_data", response.data)
-
-        selected_correspondent = next(
-            item
-            for item in response.data["selection_data"]["selected_correspondents"]
-            if item["id"] == correspondent.id
-        )
-        selected_tag = next(
-            item
-            for item in response.data["selection_data"]["selected_tags"]
-            if item["id"] == tag.id
-        )
-        selected_type = next(
-            item
-            for item in response.data["selection_data"]["selected_document_types"]
-            if item["id"] == doc_type.id
-        )
-        selected_storage_path = next(
-            item
-            for item in response.data["selection_data"]["selected_storage_paths"]
-            if item["id"] == storage_path.id
-        )
-
-        self.assertEqual(selected_correspondent["document_count"], 1)
-        self.assertEqual(selected_tag["document_count"], 1)
-        self.assertEqual(selected_type["document_count"], 1)
-        self.assertEqual(selected_storage_path["document_count"], 1)
-
     def test_statistics(self) -> None:
         doc1 = Document.objects.create(
             title="none1",

src/documents/tests/test_api_search.py

@@ -89,46 +89,6 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
         self.assertEqual(len(results), 0)
         self.assertCountEqual(response.data["all"], [])
 
-    def test_search_with_include_selection_data(self) -> None:
-        correspondent = Correspondent.objects.create(name="c1")
-        doc_type = DocumentType.objects.create(name="dt1")
-        storage_path = StoragePath.objects.create(name="sp1")
-        tag = Tag.objects.create(name="tag")
-
-        matching_doc = Document.objects.create(
-            title="bank statement",
-            content="bank content",
-            checksum="A",
-            correspondent=correspondent,
-            document_type=doc_type,
-            storage_path=storage_path,
-        )
-        matching_doc.tags.add(tag)
-
-        with AsyncWriter(index.open_index()) as writer:
-            index.update_document(writer, matching_doc)
-
-        response = self.client.get(
-            "/api/documents/?query=bank&include_selection_data=true",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_200_OK)
-        self.assertIn("selection_data", response.data)
-
-        selected_correspondent = next(
-            item
-            for item in response.data["selection_data"]["selected_correspondents"]
-            if item["id"] == correspondent.id
-        )
-        selected_tag = next(
-            item
-            for item in response.data["selection_data"]["selected_tags"]
-            if item["id"] == tag.id
-        )
-
-        self.assertEqual(selected_correspondent["document_count"], 1)
-        self.assertEqual(selected_tag["document_count"], 1)
-
     def test_search_custom_field_ordering(self) -> None:
         custom_field = CustomField.objects.create(
             name="Sortable field",

src/documents/tests/test_barcodes.py

@@ -1020,7 +1020,7 @@ class TestTagBarcode(DirectoriesMixin, SampleDirMixin, GetReaderPluginMixin, Tes
         CONSUMER_TAG_BARCODE_SPLIT=True,
         CONSUMER_TAG_BARCODE_MAPPING={"TAG:(.*)": "\\g<1>"},
         CELERY_TASK_ALWAYS_EAGER=True,
-        OCR_MODE="skip",
+        OCR_MODE="auto",
     )
     def test_consume_barcode_file_tag_split_and_assignment(self) -> None:
         """

src/documents/tests/test_checks.py

@@ -13,8 +13,10 @@ class TestDocumentChecks(TestCase):
     def test_parser_check(self) -> None:
         self.assertEqual(parser_check(None), [])
 
-        with mock.patch("documents.checks.document_consumer_declaration.send") as m:
-            m.return_value = []
+        with mock.patch("documents.checks.get_parser_registry") as mock_registry_fn:
+            mock_registry = mock.MagicMock()
+            mock_registry.all_parsers.return_value = []
+            mock_registry_fn.return_value = mock_registry
 
             self.assertEqual(
                 parser_check(None),

src/documents/tests/test_consumer.py

@@ -27,7 +27,6 @@ from documents.models import Document
 from documents.models import DocumentType
 from documents.models import StoragePath
 from documents.models import Tag
-from documents.parsers import DocumentParser
 from documents.parsers import ParseError
 from documents.plugins.helpers import ProgressStatusOptions
 from documents.tasks import sanity_check
@@ -38,62 +37,106 @@ from documents.tests.utils import GetConsumerMixin
 from paperless_mail.models import MailRule
 
 
-class _BaseTestParser(DocumentParser):
-    def get_settings(self) -> None:
+class _BaseNewStyleParser:
+    """Minimal ParserProtocol implementation for use in consumer tests."""
+
+    name: str = "test-parser"
+    version: str = "0.1"
+    author: str = "test"
+    url: str = "test"
+
+    @classmethod
+    def supported_mime_types(cls) -> dict:
+        return {
+            "application/pdf": ".pdf",
+            "image/png": ".png",
+            "message/rfc822": ".eml",
+        }
+
+    @classmethod
+    def score(cls, mime_type: str, filename: str, path=None):
+        return 0 if mime_type in cls.supported_mime_types() else None
+
+    @property
+    def can_produce_archive(self) -> bool:
+        return True
+
+    @property
+    def requires_pdf_rendition(self) -> bool:
+        return False
+
+    def __init__(self) -> None:
+        self._tmpdir: Path | None = None
+        self._text: str | None = None
+        self._archive: Path | None = None
+        self._thumb: Path | None = None
+
+    def __enter__(self):
+        self._tmpdir = Path(
+            tempfile.mkdtemp(prefix="paperless-test-", dir=settings.SCRATCH_DIR),
+        )
+        _, thumb = tempfile.mkstemp(suffix=".webp", dir=self._tmpdir)
+        self._thumb = Path(thumb)
+        return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb) -> None:
+        if self._tmpdir and self._tmpdir.exists():
+            shutil.rmtree(self._tmpdir, ignore_errors=True)
+
+    def configure(self, context) -> None:
         """
-        This parser does not implement additional settings yet
+        Test parser doesn't do anything with context
         """
+
+    def parse(self, document_path, mime_type, *, produce_archive: bool = True) -> None:
+        raise NotImplementedError
+
+    def get_text(self) -> str | None:
+        return self._text
+
+    def get_date(self):
         return None
 
+    def get_archive_path(self):
+        return self._archive
 
-class DummyParser(_BaseTestParser):
-    def __init__(self, logging_group, scratch_dir, archive_path) -> None:
-        super().__init__(logging_group, None)
-        _, self.fake_thumb = tempfile.mkstemp(suffix=".webp", dir=scratch_dir)
-        self.archive_path = archive_path
+    def get_thumbnail(self, document_path, mime_type) -> Path:
+        return self._thumb
 
-    def get_thumbnail(self, document_path, mime_type, file_name=None):
-        return self.fake_thumb
+    def get_page_count(self, document_path, mime_type):
+        return None
 
-    def parse(self, document_path, mime_type, file_name=None) -> None:
-        self.text = "The Text"
+    def extract_metadata(self, document_path, mime_type) -> list:
+        return []
 
 
-class CopyParser(_BaseTestParser):
-    def get_thumbnail(self, document_path, mime_type, file_name=None):
-        return self.fake_thumb
+class DummyParser(_BaseNewStyleParser):
+    _ARCHIVE_SRC = (
+        Path(__file__).parent / "samples" / "documents" / "archive" / "0000001.pdf"
+    )
 
-    def __init__(self, logging_group, progress_callback=None) -> None:
-        super().__init__(logging_group, progress_callback)
-        _, self.fake_thumb = tempfile.mkstemp(suffix=".webp", dir=self.tempdir)
-
-    def parse(self, document_path, mime_type, file_name=None) -> None:
-        self.text = "The text"
-        self.archive_path = Path(self.tempdir / "archive.pdf")
-        shutil.copy(document_path, self.archive_path)
+    def parse(self, document_path, mime_type, *, produce_archive: bool = True) -> None:
+        self._text = "The Text"
+        if produce_archive and self._tmpdir:
+            self._archive = self._tmpdir / "archive.pdf"
+            shutil.copy(self._ARCHIVE_SRC, self._archive)
 
 
-class FaultyParser(_BaseTestParser):
-    def __init__(self, logging_group, scratch_dir) -> None:
-        super().__init__(logging_group)
-        _, self.fake_thumb = tempfile.mkstemp(suffix=".webp", dir=scratch_dir)
+class CopyParser(_BaseNewStyleParser):
+    def parse(self, document_path, mime_type, *, produce_archive: bool = True) -> None:
+        self._text = "The text"
+        if produce_archive and self._tmpdir:
+            self._archive = self._tmpdir / "archive.pdf"
+            shutil.copy(document_path, self._archive)
 
-    def get_thumbnail(self, document_path, mime_type, file_name=None):
-        return self.fake_thumb
 
-    def parse(self, document_path, mime_type, file_name=None):
+class FaultyParser(_BaseNewStyleParser):
+    def parse(self, document_path, mime_type, *, produce_archive: bool = True) -> None:
         raise ParseError("Does not compute.")
 
 
-class FaultyGenericExceptionParser(_BaseTestParser):
-    def __init__(self, logging_group, scratch_dir) -> None:
-        super().__init__(logging_group)
-        _, self.fake_thumb = tempfile.mkstemp(suffix=".webp", dir=scratch_dir)
-
-    def get_thumbnail(self, document_path, mime_type, file_name=None):
-        return self.fake_thumb
-
-    def parse(self, document_path, mime_type, file_name=None):
+class FaultyGenericExceptionParser(_BaseNewStyleParser):
+    def parse(self, document_path, mime_type, *, produce_archive: bool = True) -> None:
         raise Exception("Generic exception.")
 
 
@@ -147,38 +190,12 @@ class TestConsumer(
         self.assertEqual(payload["data"]["max_progress"], last_progress_max)
         self.assertEqual(payload["data"]["status"], last_status)
 
-    def make_dummy_parser(self, logging_group, progress_callback=None):
-        return DummyParser(
-            logging_group,
-            self.dirs.scratch_dir,
-            self.get_test_archive_file(),
-        )
-
-    def make_faulty_parser(self, logging_group, progress_callback=None):
-        return FaultyParser(logging_group, self.dirs.scratch_dir)
-
-    def make_faulty_generic_exception_parser(
-        self,
-        logging_group,
-        progress_callback=None,
-    ):
-        return FaultyGenericExceptionParser(logging_group, self.dirs.scratch_dir)
-
     def setUp(self) -> None:
         super().setUp()
 
-        patcher = mock.patch("documents.parsers.document_consumer_declaration.send")
-        m = patcher.start()
-        m.return_value = [
-            (
-                None,
-                {
-                    "parser": self.make_dummy_parser,
-                    "mime_types": {"application/pdf": ".pdf"},
-                    "weight": 0,
-                },
-            ),
-        ]
+        patcher = mock.patch("documents.consumer.get_parser_registry")
+        mock_registry = patcher.start()
+        mock_registry.return_value.get_parser_for_file.return_value = DummyParser
         self.addCleanup(patcher.stop)
 
     def get_test_file(self):
@@ -213,7 +230,11 @@ class TestConsumer(
         shutil.copy(src, dst)
         return dst
 
-    @override_settings(FILENAME_FORMAT=None, TIME_ZONE="America/Chicago")
+    @override_settings(
+        FILENAME_FORMAT=None,
+        TIME_ZONE="America/Chicago",
+        ARCHIVE_FILE_GENERATION="always",
+    )
     def testNormalOperation(self) -> None:
         filename = self.get_test_file()
 
@@ -244,8 +265,14 @@ class TestConsumer(
 
         self.assertIsFile(document.archive_path)
 
-        self.assertEqual(document.checksum, "42995833e01aea9b3edee44bbfdd7ce1")
-        self.assertEqual(document.archive_checksum, "62acb0bcbfbcaa62ca6ad3668e4e404b")
+        self.assertEqual(
+            document.checksum,
+            "1093cf6e32adbd16b06969df09215d42c4a3a8938cc18b39455953f08d1ff2ab",
+        )
+        self.assertEqual(
+            document.archive_checksum,
+            "706124ecde3c31616992fa979caed17a726b1c9ccdba70e82a4ff796cea97ccf",
+        )
 
         self.assertIsNotFile(filename)
 
@@ -547,9 +574,9 @@ class TestConsumer(
             ) as consumer:
                 consumer.run()
 
-    @mock.patch("documents.parsers.document_consumer_declaration.send")
+    @mock.patch("documents.consumer.get_parser_registry")
     def testNoParsers(self, m) -> None:
-        m.return_value = []
+        m.return_value.get_parser_for_file.return_value = None
 
         with self.assertRaisesMessage(
             ConsumerError,
@@ -560,18 +587,9 @@ class TestConsumer(
 
         self._assert_first_last_send_progress(last_status="FAILED")
 
-    @mock.patch("documents.parsers.document_consumer_declaration.send")
+    @mock.patch("documents.consumer.get_parser_registry")
     def testFaultyParser(self, m) -> None:
-        m.return_value = [
-            (
-                None,
-                {
-                    "parser": self.make_faulty_parser,
-                    "mime_types": {"application/pdf": ".pdf"},
-                    "weight": 0,
-                },
-            ),
-        ]
+        m.return_value.get_parser_for_file.return_value = FaultyParser
 
         with self.get_consumer(self.get_test_file()) as consumer:
             with self.assertRaisesMessage(
@@ -582,18 +600,9 @@ class TestConsumer(
 
         self._assert_first_last_send_progress(last_status="FAILED")
 
-    @mock.patch("documents.parsers.document_consumer_declaration.send")
+    @mock.patch("documents.consumer.get_parser_registry")
     def testGenericParserException(self, m) -> None:
-        m.return_value = [
-            (
-                None,
-                {
-                    "parser": self.make_faulty_generic_exception_parser,
-                    "mime_types": {"application/pdf": ".pdf"},
-                    "weight": 0,
-                },
-            ),
-        ]
+        m.return_value.get_parser_for_file.return_value = FaultyGenericExceptionParser
 
         with self.get_consumer(self.get_test_file()) as consumer:
             with self.assertRaisesMessage(
@@ -624,7 +633,10 @@ class TestConsumer(
         # Database empty
         self.assertEqual(Document.objects.all().count(), 0)
 
-    @override_settings(FILENAME_FORMAT="{correspondent}/{title}")
+    @override_settings(
+        FILENAME_FORMAT="{correspondent}/{title}",
+        ARCHIVE_FILE_GENERATION="always",
+    )
     def testFilenameHandling(self) -> None:
         with self.get_consumer(
             self.get_test_file(),
@@ -641,7 +653,7 @@ class TestConsumer(
         self._assert_first_last_send_progress()
 
     @mock.patch("documents.consumer.generate_unique_filename")
-    @override_settings(FILENAME_FORMAT="{pk}")
+    @override_settings(FILENAME_FORMAT="{pk}", ARCHIVE_FILE_GENERATION="always")
     def testFilenameHandlingFallsBackWhenGeneratedPathExceedsDbLimit(self, m):
         m.side_effect = lambda doc, archive_filename=False: Path(
             ("a" * 1100 + ".pdf") if not archive_filename else ("b" * 1100 + ".pdf"),
@@ -668,7 +680,10 @@ class TestConsumer(
 
         self._assert_first_last_send_progress()
 
-    @override_settings(FILENAME_FORMAT="{correspondent}/{title}")
+    @override_settings(
+        FILENAME_FORMAT="{correspondent}/{title}",
+        ARCHIVE_FILE_GENERATION="always",
+    )
     @mock.patch("documents.signals.handlers.generate_unique_filename")
     def testFilenameHandlingUnstableFormat(self, m) -> None:
         filenames = ["this", "that", "now this", "i cannot decide"]
@@ -1016,8 +1031,8 @@ class TestConsumer(
         self.assertEqual(Document.objects.count(), 2)
         self._assert_first_last_send_progress()
 
-    @override_settings(FILENAME_FORMAT="{title}")
-    @mock.patch("documents.parsers.document_consumer_declaration.send")
+    @override_settings(FILENAME_FORMAT="{title}", ARCHIVE_FILE_GENERATION="always")
+    @mock.patch("documents.consumer.get_parser_registry")
     def test_similar_filenames(self, m) -> None:
         shutil.copy(
             Path(__file__).parent / "samples" / "simple.pdf",
@@ -1031,16 +1046,7 @@ class TestConsumer(
             Path(__file__).parent / "samples" / "simple-noalpha.png",
             settings.CONSUMPTION_DIR / "simple.png.pdf",
         )
-        m.return_value = [
-            (
-                None,
-                {
-                    "parser": CopyParser,
-                    "mime_types": {"application/pdf": ".pdf", "image/png": ".png"},
-                    "weight": 0,
-                },
-            ),
-        ]
+        m.return_value.get_parser_for_file.return_value = CopyParser
 
         with self.get_consumer(settings.CONSUMPTION_DIR / "simple.png") as consumer:
             consumer.run()
@@ -1068,8 +1074,10 @@ class TestConsumer(
 
         sanity_check()
 
+    @mock.patch("documents.consumer.get_parser_registry")
     @mock.patch("documents.consumer.run_subprocess")
-    def test_try_to_clean_invalid_pdf(self, m) -> None:
+    def test_try_to_clean_invalid_pdf(self, m, mock_registry) -> None:
+        mock_registry.return_value.get_parser_for_file.return_value = None
         shutil.copy(
             Path(__file__).parent / "samples" / "invalid_pdf.pdf",
             settings.CONSUMPTION_DIR / "invalid_pdf.pdf",
@@ -1091,10 +1099,10 @@ class TestConsumer(
 
     @mock.patch("paperless_mail.models.MailRule.objects.get")
     @mock.patch("paperless.parsers.mail.MailDocumentParser.parse")
-    @mock.patch("documents.parsers.document_consumer_declaration.send")
+    @mock.patch("documents.consumer.get_parser_registry")
     def test_mail_parser_receives_mailrule(
         self,
-        mock_consumer_declaration_send: mock.Mock,
+        mock_get_parser_registry: mock.Mock,
         mock_mail_parser_parse: mock.Mock,
         mock_mailrule_get: mock.Mock,
     ) -> None:
@@ -1106,18 +1114,11 @@ class TestConsumer(
         THEN:
             - The mail parser should receive the mail rule
         """
-        from paperless_mail.signals import get_parser as mail_get_parser
+        from paperless.parsers.mail import MailDocumentParser
 
-        mock_consumer_declaration_send.return_value = [
-            (
-                None,
-                {
-                    "parser": mail_get_parser,
-                    "mime_types": {"message/rfc822": ".eml"},
-                    "weight": 0,
-                },
-            ),
-        ]
+        mock_get_parser_registry.return_value.get_parser_for_file.return_value = (
+            MailDocumentParser
+        )
         mock_mailrule_get.return_value = mock.Mock(
             pdf_layout=MailRule.PdfLayout.HTML_ONLY,
         )
@@ -1141,6 +1142,7 @@ class TestConsumer(
             mock_mail_parser_parse.assert_called_once_with(
                 consumer.working_copy,
                 "message/rfc822",
+                produce_archive=True,
             )
 
 
@@ -1288,7 +1290,14 @@ class PreConsumeTestCase(DirectoriesMixin, GetConsumerMixin, TestCase):
     def test_no_pre_consume_script(self, m) -> None:
         with self.get_consumer(self.test_file) as c:
             c.run()
-            m.assert_not_called()
+            # Verify no pre-consume script subprocess was invoked
+            # (run_subprocess may still be called by _extract_text_for_archive_check)
+            script_calls = [
+                call
+                for call in m.call_args_list
+                if call.args and call.args[0] and call.args[0][0] not in ("pdftotext",)
+            ]
+            self.assertEqual(script_calls, [])
 
     @mock.patch("documents.consumer.run_subprocess")
     @override_settings(PRE_CONSUME_SCRIPT="does-not-exist")
@@ -1304,9 +1313,16 @@ class PreConsumeTestCase(DirectoriesMixin, GetConsumerMixin, TestCase):
                 with self.get_consumer(self.test_file) as c:
                     c.run()
 
-                    m.assert_called_once()
+                    self.assertTrue(m.called)
 
-                    args, _ = m.call_args
+                    # Find the call that invoked the pre-consume script
+                    # (run_subprocess may also be called by _extract_text_for_archive_check)
+                    script_call = next(
+                        call
+                        for call in m.call_args_list
+                        if call.args and call.args[0] and call.args[0][0] == script.name
+                    )
+                    args, _ = script_call
 
                     command = args[0]
                     environment = args[1]

src/documents/tests/test_consumer_archive.py

@@ -0,0 +1,189 @@
+"""Tests for should_produce_archive()."""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import TYPE_CHECKING
+from unittest.mock import MagicMock
+
+import pytest
+
+from documents.consumer import should_produce_archive
+
+if TYPE_CHECKING:
+    from pytest_mock import MockerFixture
+
+
+def _parser_instance(
+    *,
+    can_produce: bool = True,
+    requires_rendition: bool = False,
+) -> MagicMock:
+    """Return a mock parser instance with the given capability flags."""
+    instance = MagicMock()
+    instance.can_produce_archive = can_produce
+    instance.requires_pdf_rendition = requires_rendition
+    return instance
+
+
+@pytest.fixture()
+def null_app_config(mocker) -> MagicMock:
+    """Mock ApplicationConfiguration with all fields None → falls back to Django settings."""
+    return mocker.MagicMock(
+        output_type=None,
+        pages=None,
+        language=None,
+        mode=None,
+        archive_file_generation=None,
+        image_dpi=None,
+        unpaper_clean=None,
+        deskew=None,
+        rotate_pages=None,
+        rotate_pages_threshold=None,
+        max_image_pixels=None,
+        color_conversion_strategy=None,
+        user_args=None,
+    )
+
+
+@pytest.fixture(autouse=True)
+def patch_app_config(mocker, null_app_config):
+    """Patch BaseConfig._get_config_instance for all tests in this module."""
+    mocker.patch(
+        "paperless.config.BaseConfig._get_config_instance",
+        return_value=null_app_config,
+    )
+
+
+class TestShouldProduceArchive:
+    @pytest.mark.parametrize(
+        ("generation", "can_produce", "requires_rendition", "mime", "expected"),
+        [
+            pytest.param(
+                "never",
+                True,
+                False,
+                "application/pdf",
+                False,
+                id="never-returns-false",
+            ),
+            pytest.param(
+                "always",
+                True,
+                False,
+                "application/pdf",
+                True,
+                id="always-returns-true",
+            ),
+            pytest.param(
+                "never",
+                True,
+                True,
+                "application/pdf",
+                True,
+                id="requires-rendition-overrides-never",
+            ),
+            pytest.param(
+                "always",
+                False,
+                False,
+                "text/plain",
+                False,
+                id="cannot-produce-overrides-always",
+            ),
+            pytest.param(
+                "always",
+                False,
+                True,
+                "application/pdf",
+                True,
+                id="requires-rendition-wins-even-if-cannot-produce",
+            ),
+            pytest.param(
+                "auto",
+                True,
+                False,
+                "image/tiff",
+                True,
+                id="auto-image-returns-true",
+            ),
+            pytest.param(
+                "auto",
+                True,
+                False,
+                "message/rfc822",
+                False,
+                id="auto-non-pdf-non-image-returns-false",
+            ),
+        ],
+    )
+    def test_generation_setting(
+        self,
+        settings,
+        generation: str,
+        can_produce: bool,  # noqa: FBT001
+        requires_rendition: bool,  # noqa: FBT001
+        mime: str,
+        expected: bool,  # noqa: FBT001
+    ) -> None:
+        settings.ARCHIVE_FILE_GENERATION = generation
+        parser = _parser_instance(
+            can_produce=can_produce,
+            requires_rendition=requires_rendition,
+        )
+        assert should_produce_archive(parser, mime, Path("/tmp/doc")) is expected
+
+    @pytest.mark.parametrize(
+        ("extracted_text", "expected"),
+        [
+            pytest.param(
+                "This is a born-digital PDF with lots of text content. " * 10,
+                False,
+                id="born-digital-long-text-skips-archive",
+            ),
+            pytest.param(None, True, id="no-text-scanned-produces-archive"),
+            pytest.param("tiny", True, id="short-text-treated-as-scanned"),
+        ],
+    )
+    def test_auto_pdf_archive_decision(
+        self,
+        mocker: MockerFixture,
+        settings,
+        extracted_text: str | None,
+        expected: bool,  # noqa: FBT001
+    ) -> None:
+        settings.ARCHIVE_FILE_GENERATION = "auto"
+        mocker.patch("documents.consumer.is_tagged_pdf", return_value=False)
+        mocker.patch("documents.consumer.extract_pdf_text", return_value=extracted_text)
+        parser = _parser_instance(can_produce=True, requires_rendition=False)
+        assert (
+            should_produce_archive(parser, "application/pdf", Path("/tmp/doc.pdf"))
+            is expected
+        )
+
+    def test_tagged_pdf_skips_archive_in_auto_mode(
+        self,
+        mocker: MockerFixture,
+        settings,
+    ) -> None:
+        """Tagged PDFs (e.g. Word exports) are treated as born-digital regardless of text length."""
+        settings.ARCHIVE_FILE_GENERATION = "auto"
+        mocker.patch("documents.consumer.is_tagged_pdf", return_value=True)
+        parser = _parser_instance(can_produce=True, requires_rendition=False)
+        assert (
+            should_produce_archive(parser, "application/pdf", Path("/tmp/doc.pdf"))
+            is False
+        )
+
+    def test_tagged_pdf_does_not_call_pdftotext(
+        self,
+        mocker: MockerFixture,
+        settings,
+    ) -> None:
+        """When a PDF is tagged, pdftotext is not invoked (fast path)."""
+        settings.ARCHIVE_FILE_GENERATION = "auto"
+        mocker.patch("documents.consumer.is_tagged_pdf", return_value=True)
+        mock_extract = mocker.patch("documents.consumer.extract_pdf_text")
+        parser = _parser_instance(can_produce=True, requires_rendition=False)
+        should_produce_archive(parser, "application/pdf", Path("/tmp/doc.pdf"))
+        mock_extract.assert_not_called()

src/documents/tests/test_management.py

@@ -27,7 +27,10 @@ sample_file: Path = Path(__file__).parent / "samples" / "simple.pdf"
 
 
 @pytest.mark.management
-@override_settings(FILENAME_FORMAT="{correspondent}/{title}")
+@override_settings(
+    FILENAME_FORMAT="{correspondent}/{title}",
+    ARCHIVE_FILE_GENERATION="always",
+)
 class TestArchiver(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
     def make_models(self):
         return Document.objects.create(

src/documents/tests/test_management_exporter.py

@@ -63,8 +63,8 @@ class TestExportImport(
 
         self.d1 = Document.objects.create(
             content="Content",
-            checksum="42995833e01aea9b3edee44bbfdd7ce1",
-            archive_checksum="62acb0bcbfbcaa62ca6ad3668e4e404b",
+            checksum="1093cf6e32adbd16b06969df09215d42c4a3a8938cc18b39455953f08d1ff2ab",
+            archive_checksum="706124ecde3c31616992fa979caed17a726b1c9ccdba70e82a4ff796cea97ccf",
             title="wow1",
             filename="0000001.pdf",
             mime_type="application/pdf",
@@ -72,21 +72,21 @@ class TestExportImport(
         )
         self.d2 = Document.objects.create(
             content="Content",
-            checksum="9c9691e51741c1f4f41a20896af31770",
+            checksum="550d1bae0f746d4f7c6be07054eb20cc2f11988a58ef64ceae45e98f85e92a5b",
             title="wow2",
             filename="0000002.pdf",
             mime_type="application/pdf",
         )
         self.d3 = Document.objects.create(
             content="Content",
-            checksum="d38d7ed02e988e072caf924e0f3fcb76",
+            checksum="f1ba6b7ff8548214a75adec228f5468a14fe187f445bc0b9485cbf1c35b15915",
             title="wow2",
             filename="0000003.pdf",
             mime_type="application/pdf",
         )
         self.d4 = Document.objects.create(
             content="Content",
-            checksum="82186aaa94f0b98697d704b90fd1c072",
+            checksum="a81b16b6b313cfd7e60eb7b12598d1343b58622b4030cfa19a2724a02e98db1b",
             title="wow_dec",
             filename="0000004.pdf",
             mime_type="application/pdf",
@@ -239,7 +239,7 @@ class TestExportImport(
                 )
 
                 with Path(fname).open("rb") as f:
-                    checksum = hashlib.md5(f.read()).hexdigest()
+                    checksum = hashlib.sha256(f.read()).hexdigest()
                 self.assertEqual(checksum, element["fields"]["checksum"])
 
                 # Generated field "content_length" should not be exported,
@@ -253,7 +253,7 @@ class TestExportImport(
                     self.assertIsFile(fname)
 
                     with Path(fname).open("rb") as f:
-                        checksum = hashlib.md5(f.read()).hexdigest()
+                        checksum = hashlib.sha256(f.read()).hexdigest()
                     self.assertEqual(checksum, element["fields"]["archive_checksum"])
 
             elif element["model"] == "documents.note":

src/documents/tests/test_management_importer.py

@@ -277,8 +277,8 @@ class TestCommandImport(
 
         Document.objects.create(
             content="Content",
-            checksum="42995833e01aea9b3edee44bbfdd7ce1",
-            archive_checksum="62acb0bcbfbcaa62ca6ad3668e4e404b",
+            checksum="1093cf6e32adbd16b06969df09215d42c4a3a8938cc18b39455953f08d1ff2ab",
+            archive_checksum="706124ecde3c31616992fa979caed17a726b1c9ccdba70e82a4ff796cea97ccf",
             title="wow1",
             filename="0000001.pdf",
             mime_type="application/pdf",

src/documents/tests/test_migration_sha256_checksums.py

@@ -0,0 +1,132 @@
+import hashlib
+import shutil
+import tempfile
+from pathlib import Path
+
+from django.conf import settings
+from django.db import connection
+from django.test import override_settings
+
+from documents.tests.utils import TestMigrations
+
+
+def _sha256(data: bytes) -> str:
+    return hashlib.sha256(data).hexdigest()
+
+
+class TestSha256ChecksumDataMigration(TestMigrations):
+    """recompute_checksums correctly updates document checksums from MD5 to SHA256."""
+
+    migrate_from = "0015_document_version_index_and_more"
+    migrate_to = "0016_sha256_checksums"
+    reset_sequences = True
+
+    ORIGINAL_CONTENT = b"original file content for sha256 migration test"
+    ARCHIVE_CONTENT = b"archive file content for sha256 migration test"
+
+    def setUpBeforeMigration(self, apps) -> None:
+        self._originals_dir = Path(tempfile.mkdtemp())
+        self._archive_dir = Path(tempfile.mkdtemp())
+        self._settings_override = override_settings(
+            ORIGINALS_DIR=self._originals_dir,
+            ARCHIVE_DIR=self._archive_dir,
+        )
+        self._settings_override.enable()
+        Document = apps.get_model("documents", "Document")
+
+        # doc1: original file present, no archive
+        (settings.ORIGINALS_DIR / "doc1.txt").write_bytes(self.ORIGINAL_CONTENT)
+        self.doc1_id = Document.objects.create(
+            title="Doc 1",
+            mime_type="text/plain",
+            filename="doc1.txt",
+            checksum="a" * 32,
+        ).pk
+
+        # doc2: original and archive both present
+        (settings.ORIGINALS_DIR / "doc2.txt").write_bytes(self.ORIGINAL_CONTENT)
+        (settings.ARCHIVE_DIR / "doc2.pdf").write_bytes(self.ARCHIVE_CONTENT)
+        self.doc2_id = Document.objects.create(
+            title="Doc 2",
+            mime_type="text/plain",
+            filename="doc2.txt",
+            checksum="b" * 32,
+            archive_filename="doc2.pdf",
+            archive_checksum="c" * 32,
+        ).pk
+
+        # doc3: original file missing — checksum must stay unchanged
+        self.doc3_id = Document.objects.create(
+            title="Doc 3",
+            mime_type="text/plain",
+            filename="missing_original.txt",
+            checksum="d" * 32,
+        ).pk
+
+        # doc4: original present, archive_filename set but archive file missing
+        (settings.ORIGINALS_DIR / "doc4.txt").write_bytes(self.ORIGINAL_CONTENT)
+        self.doc4_id = Document.objects.create(
+            title="Doc 4",
+            mime_type="text/plain",
+            filename="doc4.txt",
+            checksum="e" * 32,
+            archive_filename="missing_archive.pdf",
+            archive_checksum="f" * 32,
+        ).pk
+
+        # doc5: original present, archive_filename is None — archive_checksum must stay null
+        (settings.ORIGINALS_DIR / "doc5.txt").write_bytes(self.ORIGINAL_CONTENT)
+        self.doc5_id = Document.objects.create(
+            title="Doc 5",
+            mime_type="text/plain",
+            filename="doc5.txt",
+            checksum="0" * 32,
+            archive_filename=None,
+            archive_checksum=None,
+        ).pk
+
+    def _fixture_teardown(self) -> None:
+        super()._fixture_teardown()
+        # Django's SQLite backend returns [] from sequence_reset_sql(), so
+        # reset_sequences=True flushes rows but never clears sqlite_sequence.
+        # Explicitly delete the entry so subsequent tests start from pk=1.
+        if connection.vendor == "sqlite":
+            with connection.cursor() as cursor:
+                cursor.execute(
+                    "DELETE FROM sqlite_sequence WHERE name='documents_document'",
+                )
+
+    def tearDown(self) -> None:
+        super().tearDown()
+        self._settings_override.disable()
+        shutil.rmtree(self._originals_dir, ignore_errors=True)
+        shutil.rmtree(self._archive_dir, ignore_errors=True)
+
+    def test_original_checksum_updated_to_sha256_when_file_exists(self) -> None:
+        Document = self.apps.get_model("documents", "Document")
+        doc = Document.objects.get(pk=self.doc1_id)
+        self.assertEqual(doc.checksum, _sha256(self.ORIGINAL_CONTENT))
+
+    def test_both_checksums_updated_when_original_and_archive_exist(self) -> None:
+        Document = self.apps.get_model("documents", "Document")
+        doc = Document.objects.get(pk=self.doc2_id)
+        self.assertEqual(doc.checksum, _sha256(self.ORIGINAL_CONTENT))
+        self.assertEqual(doc.archive_checksum, _sha256(self.ARCHIVE_CONTENT))
+
+    def test_checksum_unchanged_when_original_file_missing(self) -> None:
+        Document = self.apps.get_model("documents", "Document")
+        doc = Document.objects.get(pk=self.doc3_id)
+        self.assertEqual(doc.checksum, "d" * 32)
+
+    def test_archive_checksum_unchanged_when_archive_file_missing(self) -> None:
+        Document = self.apps.get_model("documents", "Document")
+        doc = Document.objects.get(pk=self.doc4_id)
+        # Original was updated (file exists)
+        self.assertEqual(doc.checksum, _sha256(self.ORIGINAL_CONTENT))
+        # Archive was not updated (file missing)
+        self.assertEqual(doc.archive_checksum, "f" * 32)
+
+    def test_archive_checksum_stays_null_when_no_archive_filename(self) -> None:
+        Document = self.apps.get_model("documents", "Document")
+        doc = Document.objects.get(pk=self.doc5_id)
+        self.assertIsNone(doc.archive_checksum)

src/documents/tests/test_parsers.py

@@ -1,132 +1,16 @@
-from tempfile import TemporaryDirectory
-from unittest import mock
-
-from django.apps import apps
 from django.test import TestCase
 from django.test import override_settings
 
 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.registry import get_parser_registry
+from paperless.parsers.registry import reset_parser_registry
 from paperless.parsers.tesseract import RasterisedDocumentParser
 from paperless.parsers.text import TextDocumentParser
 from paperless.parsers.tika import TikaDocumentParser
 
 
-class TestParserDiscovery(TestCase):
-    @mock.patch("documents.parsers.document_consumer_declaration.send")
-    def test_get_parser_class_1_parser(self, m, *args) -> None:
-        """
-        GIVEN:
-            - Parser declared for a given mimetype
-        WHEN:
-            - Attempt to get parser for the mimetype
-        THEN:
-            - Declared parser class is returned
-        """
-
-        class DummyParser:
-            pass
-
-        m.return_value = (
-            (
-                None,
-                {
-                    "weight": 0,
-                    "parser": DummyParser,
-                    "mime_types": {"application/pdf": ".pdf"},
-                },
-            ),
-        )
-
-        self.assertEqual(get_parser_class_for_mime_type("application/pdf"), DummyParser)
-
-    @mock.patch("documents.parsers.document_consumer_declaration.send")
-    def test_get_parser_class_n_parsers(self, m, *args) -> None:
-        """
-        GIVEN:
-            - Two parsers declared for a given mimetype
-            - Second parser has a higher weight
-        WHEN:
-            - Attempt to get parser for the mimetype
-        THEN:
-            - Second parser class is returned
-        """
-
-        class DummyParser1:
-            pass
-
-        class DummyParser2:
-            pass
-
-        m.return_value = (
-            (
-                None,
-                {
-                    "weight": 0,
-                    "parser": DummyParser1,
-                    "mime_types": {"application/pdf": ".pdf"},
-                },
-            ),
-            (
-                None,
-                {
-                    "weight": 1,
-                    "parser": DummyParser2,
-                    "mime_types": {"application/pdf": ".pdf"},
-                },
-            ),
-        )
-
-        self.assertEqual(
-            get_parser_class_for_mime_type("application/pdf"),
-            DummyParser2,
-        )
-
-    @mock.patch("documents.parsers.document_consumer_declaration.send")
-    def test_get_parser_class_0_parsers(self, m, *args) -> None:
-        """
-        GIVEN:
-            - No parsers are declared
-        WHEN:
-            - Attempt to get parser for the mimetype
-        THEN:
-            - No parser class is returned
-        """
-        m.return_value = []
-        with TemporaryDirectory():
-            self.assertIsNone(get_parser_class_for_mime_type("application/pdf"))
-
-    @mock.patch("documents.parsers.document_consumer_declaration.send")
-    def test_get_parser_class_no_valid_parser(self, m, *args) -> None:
-        """
-        GIVEN:
-            - No parser declared for a given mimetype
-            - Parser declared for a different mimetype
-        WHEN:
-            - Attempt to get parser for the given mimetype
-        THEN:
-            - No parser class is returned
-        """
-
-        class DummyParser:
-            pass
-
-        m.return_value = (
-            (
-                None,
-                {
-                    "weight": 0,
-                    "parser": DummyParser,
-                    "mime_types": {"application/pdf": ".pdf"},
-                },
-            ),
-        )
-
-        self.assertIsNone(get_parser_class_for_mime_type("image/tiff"))
-
-
 class TestParserAvailability(TestCase):
     def test_tesseract_parser(self) -> None:
         """
@@ -151,7 +35,7 @@ class TestParserAvailability(TestCase):
             self.assertIn(ext, supported_exts)
             self.assertEqual(get_default_file_extension(mime_type), ext)
             self.assertIsInstance(
-                get_parser_class_for_mime_type(mime_type)(logging_group=None),
+                get_parser_registry().get_parser_for_file(mime_type, "")(),
                 RasterisedDocumentParser,
             )
 
@@ -175,7 +59,7 @@ class TestParserAvailability(TestCase):
             self.assertIn(ext, supported_exts)
             self.assertEqual(get_default_file_extension(mime_type), ext)
             self.assertIsInstance(
-                get_parser_class_for_mime_type(mime_type)(logging_group=None),
+                get_parser_registry().get_parser_for_file(mime_type, "")(),
                 TextDocumentParser,
             )
 
@@ -198,22 +82,23 @@ class TestParserAvailability(TestCase):
             ),
         ]
 
-        # Force the app ready to notice the settings override
-        with override_settings(TIKA_ENABLED=True, INSTALLED_APPS=["paperless_tika"]):
-            app = apps.get_app_config("paperless_tika")
-            app.ready()
+        self.addCleanup(reset_parser_registry)
+
+        # Reset and rebuild the registry with Tika enabled.
+        with override_settings(TIKA_ENABLED=True):
+            reset_parser_registry()
             supported_exts = get_supported_file_extensions()
 
-        for mime_type, ext in supported_mimes_and_exts:
-            self.assertIn(ext, supported_exts)
-            self.assertEqual(get_default_file_extension(mime_type), ext)
-            self.assertIsInstance(
-                get_parser_class_for_mime_type(mime_type)(logging_group=None),
-                TikaDocumentParser,
-            )
+            for mime_type, ext in supported_mimes_and_exts:
+                self.assertIn(ext, supported_exts)
+                self.assertEqual(get_default_file_extension(mime_type), ext)
+                self.assertIsInstance(
+                    get_parser_registry().get_parser_for_file(mime_type, "")(),
+                    TikaDocumentParser,
+                )
 
     def test_no_parser_for_mime(self) -> None:
-        self.assertIsNone(get_parser_class_for_mime_type("text/sdgsdf"))
+        self.assertIsNone(get_parser_registry().get_parser_for_file("text/sdgsdf", ""))
 
     def test_default_extension(self) -> None:
         # Test no parser declared still returns a an extension

src/documents/tests/test_tasks.py

@@ -232,6 +232,7 @@ class TestEmptyTrashTask(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         self.assertEqual(Document.global_objects.count(), 0)
 
 
+@override_settings(ARCHIVE_FILE_GENERATION="always")
 class TestUpdateContent(DirectoriesMixin, TestCase):
     def test_update_content_maybe_archive_file(self) -> None:
         """

src/documents/utils.py

@@ -1,3 +1,4 @@
+import hashlib
 import logging
 import shutil
 from os import utime
@@ -128,3 +129,28 @@ def get_boolean(boolstr: str) -> bool:
     Return a boolean value from a string representation.
     """
     return bool(boolstr.lower() in ("yes", "y", "1", "t", "true"))
+
+
+def compute_checksum(path: Path, chunk_size: int = 65536) -> str:
+    """
+    Compute the SHA-256 checksum of a file.
+
+    Reads the file in chunks to avoid loading the entire file into memory.
+
+    Args:
+        path (Path): Path to the file to hash.
+        chunk_size (int, optional): Number of bytes to read per chunk.
+            Defaults to 65536.
+
+    Returns:
+        str: Hexadecimal SHA-256 digest of the file contents.
+
+    Raises:
+        FileNotFoundError: If the file does not exist.
+        OSError: If the file cannot be read.
+    """
+    h = hashlib.sha256()
+    with path.open("rb") as f:
+        while chunk := f.read(chunk_size):
+            h.update(chunk)
+    return h.hexdigest()

src/documents/views.py

@@ -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
@@ -159,7 +158,6 @@ from documents.models import UiSettings
 from documents.models import Workflow
 from documents.models import WorkflowAction
 from documents.models import WorkflowTrigger
-from documents.parsers import get_parser_class_for_mime_type
 from documents.permissions import AcknowledgeTasksPermissions
 from documents.permissions import PaperlessAdminPermissions
 from documents.permissions import PaperlessNotePermissions
@@ -227,7 +225,7 @@ 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.parsers.registry import get_parser_registry
 from paperless.serialisers import GroupSerializer
 from paperless.serialisers import UserSerializer
 from paperless.views import StandardPagination
@@ -838,61 +836,6 @@ class DocumentViewSet(
         "custom_field_",
     )
 
-    def _get_selection_data_for_queryset(self, queryset):
-        correspondents = Correspondent.objects.annotate(
-            document_count=Count(
-                "documents",
-                filter=Q(documents__in=queryset),
-                distinct=True,
-            ),
-        )
-        tags = Tag.objects.annotate(
-            document_count=Count(
-                "documents",
-                filter=Q(documents__in=queryset),
-                distinct=True,
-            ),
-        )
-        document_types = DocumentType.objects.annotate(
-            document_count=Count(
-                "documents",
-                filter=Q(documents__in=queryset),
-                distinct=True,
-            ),
-        )
-        storage_paths = StoragePath.objects.annotate(
-            document_count=Count(
-                "documents",
-                filter=Q(documents__in=queryset),
-                distinct=True,
-            ),
-        )
-        custom_fields = CustomField.objects.annotate(
-            document_count=Count(
-                "fields__document",
-                filter=Q(fields__document__in=queryset),
-                distinct=True,
-            ),
-        )
-
-        return {
-            "selected_correspondents": [
-                {"id": t.id, "document_count": t.document_count} for t in correspondents
-            ],
-            "selected_tags": [
-                {"id": t.id, "document_count": t.document_count} for t in tags
-            ],
-            "selected_document_types": [
-                {"id": t.id, "document_count": t.document_count} for t in document_types
-            ],
-            "selected_storage_paths": [
-                {"id": t.id, "document_count": t.document_count} for t in storage_paths
-            ],
-            "selected_custom_fields": [
-                {"id": t.id, "document_count": t.document_count} for t in custom_fields
-            ],
-        }
-
     def get_queryset(self):
         latest_version_content = Subquery(
             Document.objects.filter(root_document=OuterRef("pk"))
@@ -1040,25 +983,6 @@ class DocumentViewSet(
 
         return response
 
-    def list(self, request, *args, **kwargs):
-        if not get_boolean(
-            str(request.query_params.get("include_selection_data", "false")),
-        ):
-            return super().list(request, *args, **kwargs)
-
-        queryset = self.filter_queryset(self.get_queryset())
-        selection_data = self._get_selection_data_for_queryset(queryset)
-
-        page = self.paginate_queryset(queryset)
-        if page is not None:
-            serializer = self.get_serializer(page, many=True)
-            response = self.get_paginated_response(serializer.data)
-            response.data["selection_data"] = selection_data
-            return response
-
-        serializer = self.get_serializer(queryset, many=True)
-        return Response({"results": serializer.data, "selection_data": selection_data})
-
     def destroy(self, request, *args, **kwargs):
         from documents import index
 
@@ -1158,17 +1082,17 @@ class DocumentViewSet(
         if not Path(file).is_file():
             return None
 
-        parser_class = get_parser_class_for_mime_type(mime_type)
+        parser_class = get_parser_registry().get_parser_for_file(
+            mime_type,
+            Path(file).name,
+            Path(file),
+        )
         if parser_class:
-            parser = parser_class(progress_callback=None, logging_group=None)
-            cm = parser if isinstance(parser, ParserProtocol) else nullcontext(parser)
-
             try:
-                with cm:
+                with parser_class() as parser:
                     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.
                 return []
         else:  # pragma: no cover
             logger.warning(f"No parser for {mime_type}")
@@ -2099,26 +2023,14 @@ class UnifiedSearchViewSet(DocumentViewSet):
                         else None
                     )
 
-                    if get_boolean(
-                        str(
-                            request.query_params.get(
-                                "include_selection_data",
-                                "false",
-                            ),
-                        ),
-                    ):
-                        result_ids = response.data.get("all", [])
-                        response.data["selection_data"] = (
-                            self._get_selection_data_for_queryset(
-                                Document.objects.filter(pk__in=result_ids),
-                            )
-                        )
-
                     return response
             except NotFound:
                 raise
             except PermissionDenied as e:
-                return HttpResponseForbidden(str(e.detail))
+                invalid_more_like_id_message = _("Invalid more_like_id")
+                if str(e.detail) == str(invalid_more_like_id_message):
+                    return HttpResponseForbidden(invalid_more_like_id_message)
+                return HttpResponseForbidden(_("Insufficient permissions."))
             except Exception as e:
                 logger.warning(f"An error occurred listing search results: {e!s}")
                 return HttpResponseBadRequest(

src/documents/workflows/actions.py

@@ -282,7 +282,7 @@ def execute_password_removal_action(
     passwords = action.passwords
     if not passwords:
         logger.warning(
-            "Password removal action %s has no passwords configured",
+            "Workflow action %s has no configured unlock values",
             action.pk,
             extra={"group": logging_group},
         )
@@ -321,22 +321,23 @@ def execute_password_removal_action(
                 user=document.owner,
             )
             logger.info(
-                "Removed password from document %s using workflow action %s",
+                "Unlocked document %s using workflow action %s",
                 document.pk,
                 action.pk,
                 extra={"group": logging_group},
             )
             return
-        except ValueError as e:
+        except ValueError:
             logger.warning(
-                "Password removal failed for document %s with supplied password: %s",
+                "Workflow action %s could not unlock document %s with one configured value",
+                action.pk,
                 document.pk,
-                e,
                 extra={"group": logging_group},
             )
 
     logger.error(
-        "Password removal failed for document %s after trying all provided passwords",
+        "Workflow action %s could not unlock document %s with any configured value",
+        action.pk,
         document.pk,
         extra={"group": logging_group},
     )

src/locale/en_US/LC_MESSAGES/django.po

@@ -2,7 +2,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: paperless-ngx\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2026-03-21 09:25+0000\n"
+"POT-Creation-Date: 2026-03-26 14:37+0000\n"
 "PO-Revision-Date: 2022-02-17 04:17\n"
 "Last-Translator: \n"
 "Language-Team: English\n"
@@ -1300,8 +1300,8 @@ msgid "workflow runs"
 msgstr ""
 
 #: documents/serialisers.py:463 documents/serialisers.py:815
-#: documents/serialisers.py:2501 documents/views.py:1992
-#: paperless_mail/serialisers.py:143
+#: documents/serialisers.py:2501 documents/views.py:1990
+#: documents/views.py:2033 paperless_mail/serialisers.py:143
 msgid "Insufficient permissions."
 msgstr ""
 
@@ -1341,7 +1341,7 @@ msgstr ""
 msgid "Duplicate document identifiers are not allowed."
 msgstr ""
 
-#: documents/serialisers.py:2587 documents/views.py:3598
+#: documents/serialisers.py:2587 documents/views.py:3599
 #, python-format
 msgid "Documents not found: %(ids)s"
 msgstr ""
@@ -1383,13 +1383,18 @@ msgid "Please sign in."
 msgstr ""
 
 #: documents/templates/account/login.html:12
-#, python-format
-msgid "Don't have an account yet? <a href=\"%(signup_url)s\">Sign up</a>"
+msgid "Don't have an account yet?"
+msgstr ""
+
+#: documents/templates/account/login.html:12
+#: documents/templates/account/signup.html:43
+#: documents/templates/socialaccount/signup.html:29
+msgid "Sign up"
 msgstr ""
 
 #: documents/templates/account/login.html:25
 #: documents/templates/account/signup.html:22
-#: documents/templates/socialaccount/signup.html:13
+#: documents/templates/socialaccount/signup.html:15
 msgid "Username"
 msgstr ""
 
@@ -1399,6 +1404,7 @@ msgid "Password"
 msgstr ""
 
 #: documents/templates/account/login.html:36
+#: documents/templates/account/signup.html:11
 #: documents/templates/mfa/authenticate.html:23
 msgid "Sign in"
 msgstr ""
@@ -1477,10 +1483,11 @@ msgid "Password reset complete."
 msgstr ""
 
 #: documents/templates/account/password_reset_from_key_done.html:14
-#, python-format
-msgid ""
-"Your new password has been set. You can now <a href=\"%(login_url)s\">log "
-"in</a>"
+msgid "Your new password has been set. You can now"
+msgstr ""
+
+#: documents/templates/account/password_reset_from_key_done.html:14
+msgid "log in"
 msgstr ""
 
 #: documents/templates/account/signup.html:5
@@ -1488,8 +1495,7 @@ msgid "Paperless-ngx sign up"
 msgstr ""
 
 #: documents/templates/account/signup.html:11
-#, python-format
-msgid "Already have an account? <a href=\"%(login_url)s\">Sign in</a>"
+msgid "Already have an account?"
 msgstr ""
 
 #: documents/templates/account/signup.html:19
@@ -1499,7 +1505,7 @@ msgid ""
 msgstr ""
 
 #: documents/templates/account/signup.html:23
-#: documents/templates/socialaccount/signup.html:14
+#: documents/templates/socialaccount/signup.html:16
 msgid "Email (optional)"
 msgstr ""
 
@@ -1507,11 +1513,6 @@ msgstr ""
 msgid "Password (again)"
 msgstr ""
 
-#: documents/templates/account/signup.html:43
-#: documents/templates/socialaccount/signup.html:27
-msgid "Sign up"
-msgstr ""
-
 #: documents/templates/index.html:61
 msgid "Paperless-ngx is loading..."
 msgstr ""
@@ -1556,18 +1557,21 @@ msgid "Paperless-ngx social account sign in"
 msgstr ""
 
 #: documents/templates/socialaccount/authentication_error.html:10
-#, python-format
 msgid ""
 "An error occurred while attempting to login via your social network account. "
-"Back to the <a href=\"%(login_url)s\">login page</a>"
+"Back to the"
 msgstr ""
 
-#: documents/templates/socialaccount/login.html:10
+#: documents/templates/socialaccount/authentication_error.html:10
+msgid "login page"
+msgstr ""
+
+#: documents/templates/socialaccount/login.html:11
 #, python-format
 msgid "You are about to connect a new third-party account from %(provider)s."
 msgstr ""
 
-#: documents/templates/socialaccount/login.html:13
+#: documents/templates/socialaccount/login.html:15
 msgid "Continue"
 msgstr ""
 
@@ -1575,12 +1579,12 @@ msgstr ""
 msgid "Paperless-ngx social account sign up"
 msgstr ""
 
-#: documents/templates/socialaccount/signup.html:10
+#: documents/templates/socialaccount/signup.html:11
 #, python-format
 msgid "You are about to use your %(provider_name)s account to login."
 msgstr ""
 
-#: documents/templates/socialaccount/signup.html:11
+#: documents/templates/socialaccount/signup.html:13
 msgid "As a final step, please complete the following form:"
 msgstr ""
 
@@ -1605,24 +1609,24 @@ msgstr ""
 msgid "Unable to parse URI {value}"
 msgstr ""
 
-#: documents/views.py:1985
+#: documents/views.py:1983 documents/views.py:2030
 msgid "Invalid more_like_id"
 msgstr ""
 
-#: documents/views.py:3610
+#: documents/views.py:3611
 #, python-format
 msgid "Insufficient permissions to share document %(id)s."
 msgstr ""
 
-#: documents/views.py:3653
+#: documents/views.py:3654
 msgid "Bundle is already being processed."
 msgstr ""
 
-#: documents/views.py:3710
+#: documents/views.py:3711
 msgid "The share link bundle is still being prepared. Please try again later."
 msgstr ""
 
-#: documents/views.py:3720
+#: documents/views.py:3721
 msgid "The share link bundle is unavailable."
 msgstr ""
 
@@ -1862,151 +1866,151 @@ msgstr ""
 msgid "paperless application settings"
 msgstr ""
 
-#: paperless/settings/__init__.py:521
+#: paperless/settings/__init__.py:518
 msgid "English (US)"
 msgstr ""
 
-#: paperless/settings/__init__.py:522
+#: paperless/settings/__init__.py:519
 msgid "Arabic"
 msgstr ""
 
-#: paperless/settings/__init__.py:523
+#: paperless/settings/__init__.py:520
 msgid "Afrikaans"
 msgstr ""
 
-#: paperless/settings/__init__.py:524
+#: paperless/settings/__init__.py:521
 msgid "Belarusian"
 msgstr ""
 
-#: paperless/settings/__init__.py:525
+#: paperless/settings/__init__.py:522
 msgid "Bulgarian"
 msgstr ""
 
-#: paperless/settings/__init__.py:526
+#: paperless/settings/__init__.py:523
 msgid "Catalan"
 msgstr ""
 
-#: paperless/settings/__init__.py:527
+#: paperless/settings/__init__.py:524
 msgid "Czech"
 msgstr ""
 
-#: paperless/settings/__init__.py:528
+#: paperless/settings/__init__.py:525
 msgid "Danish"
 msgstr ""
 
-#: paperless/settings/__init__.py:529
+#: paperless/settings/__init__.py:526
 msgid "German"
 msgstr ""
 
-#: paperless/settings/__init__.py:530
+#: paperless/settings/__init__.py:527
 msgid "Greek"
 msgstr ""
 
-#: paperless/settings/__init__.py:531
+#: paperless/settings/__init__.py:528
 msgid "English (GB)"
 msgstr ""
 
-#: paperless/settings/__init__.py:532
+#: paperless/settings/__init__.py:529
 msgid "Spanish"
 msgstr ""
 
-#: paperless/settings/__init__.py:533
+#: paperless/settings/__init__.py:530
 msgid "Persian"
 msgstr ""
 
-#: paperless/settings/__init__.py:534
+#: paperless/settings/__init__.py:531
 msgid "Finnish"
 msgstr ""
 
-#: paperless/settings/__init__.py:535
+#: paperless/settings/__init__.py:532
 msgid "French"
 msgstr ""
 
-#: paperless/settings/__init__.py:536
+#: paperless/settings/__init__.py:533
 msgid "Hungarian"
 msgstr ""
 
-#: paperless/settings/__init__.py:537
+#: paperless/settings/__init__.py:534
 msgid "Indonesian"
 msgstr ""
 
-#: paperless/settings/__init__.py:538
+#: paperless/settings/__init__.py:535
 msgid "Italian"
 msgstr ""
 
-#: paperless/settings/__init__.py:539
+#: paperless/settings/__init__.py:536
 msgid "Japanese"
 msgstr ""
 
-#: paperless/settings/__init__.py:540
+#: paperless/settings/__init__.py:537
 msgid "Korean"
 msgstr ""
 
-#: paperless/settings/__init__.py:541
+#: paperless/settings/__init__.py:538
 msgid "Luxembourgish"
 msgstr ""
 
-#: paperless/settings/__init__.py:542
+#: paperless/settings/__init__.py:539
 msgid "Norwegian"
 msgstr ""
 
-#: paperless/settings/__init__.py:543
+#: paperless/settings/__init__.py:540
 msgid "Dutch"
 msgstr ""
 
-#: paperless/settings/__init__.py:544
+#: paperless/settings/__init__.py:541
 msgid "Polish"
 msgstr ""
 
-#: paperless/settings/__init__.py:545
+#: paperless/settings/__init__.py:542
 msgid "Portuguese (Brazil)"
 msgstr ""
 
-#: paperless/settings/__init__.py:546
+#: paperless/settings/__init__.py:543
 msgid "Portuguese"
 msgstr ""
 
-#: paperless/settings/__init__.py:547
+#: paperless/settings/__init__.py:544
 msgid "Romanian"
 msgstr ""
 
-#: paperless/settings/__init__.py:548
+#: paperless/settings/__init__.py:545
 msgid "Russian"
 msgstr ""
 
-#: paperless/settings/__init__.py:549
+#: paperless/settings/__init__.py:546
 msgid "Slovak"
 msgstr ""
 
-#: paperless/settings/__init__.py:550
+#: paperless/settings/__init__.py:547
 msgid "Slovenian"
 msgstr ""
 
-#: paperless/settings/__init__.py:551
+#: paperless/settings/__init__.py:548
 msgid "Serbian"
 msgstr ""
 
-#: paperless/settings/__init__.py:552
+#: paperless/settings/__init__.py:549
 msgid "Swedish"
 msgstr ""
 
-#: paperless/settings/__init__.py:553
+#: paperless/settings/__init__.py:550
 msgid "Turkish"
 msgstr ""
 
-#: paperless/settings/__init__.py:554
+#: paperless/settings/__init__.py:551
 msgid "Ukrainian"
 msgstr ""
 
-#: paperless/settings/__init__.py:555
+#: paperless/settings/__init__.py:552
 msgid "Vietnamese"
 msgstr ""
 
-#: paperless/settings/__init__.py:556
+#: paperless/settings/__init__.py:553
 msgid "Chinese Simplified"
 msgstr ""
 
-#: paperless/settings/__init__.py:557
+#: paperless/settings/__init__.py:554
 msgid "Chinese Traditional"
 msgstr ""
 
@@ -2052,7 +2056,7 @@ msgid ""
 "process all matching rules that you have defined."
 msgstr ""
 
-#: paperless_mail/apps.py:11
+#: paperless_mail/apps.py:8
 msgid "Paperless mail"
 msgstr ""
 

src/paperless/checks.py

@@ -3,6 +3,7 @@ import os
 import pwd
 import shutil
 import stat
+import subprocess
 from pathlib import Path
 
 from django.conf import settings
@@ -131,23 +132,14 @@ def settings_values_check(app_configs, **kwargs):
                 Error(f'OCR output type "{settings.OCR_OUTPUT_TYPE}" is not valid'),
             )
 
-        if settings.OCR_MODE not in {"force", "skip", "redo", "skip_noarchive"}:
+        if settings.OCR_MODE not in {"auto", "force", "redo", "off"}:
             msgs.append(Error(f'OCR output mode "{settings.OCR_MODE}" is not valid'))
 
-        if settings.OCR_MODE == "skip_noarchive":
-            msgs.append(
-                Warning(
-                    'OCR output mode "skip_noarchive" is deprecated and will be '
-                    "removed in a future version. Please use "
-                    "PAPERLESS_OCR_SKIP_ARCHIVE_FILE instead.",
-                ),
-            )
-
-        if settings.OCR_SKIP_ARCHIVE_FILE not in {"never", "with_text", "always"}:
+        if settings.ARCHIVE_FILE_GENERATION not in {"auto", "always", "never"}:
             msgs.append(
                 Error(
-                    "OCR_SKIP_ARCHIVE_FILE setting "
-                    f'"{settings.OCR_SKIP_ARCHIVE_FILE}" is not valid',
+                    "PAPERLESS_ARCHIVE_FILE_GENERATION setting "
+                    f'"{settings.ARCHIVE_FILE_GENERATION}" is not valid',
                 ),
             )
 
@@ -299,3 +291,97 @@ def check_deprecated_db_settings(
         )
 
     return warnings
+
+
+@register()
+def check_deprecated_v2_ocr_env_vars(
+    app_configs: object,
+    **kwargs: object,
+) -> list[Warning]:
+    """Warn when deprecated v2 OCR environment variables are set.
+
+    Users upgrading from v2 may still have these in their environment or
+    config files, where they are now silently ignored.
+    """
+    warnings: list[Warning] = []
+
+    if os.environ.get("PAPERLESS_OCR_SKIP_ARCHIVE_FILE"):
+        warnings.append(
+            Warning(
+                "PAPERLESS_OCR_SKIP_ARCHIVE_FILE is set but has no effect. "
+                "Use PAPERLESS_ARCHIVE_FILE_GENERATION=never/always/auto instead.",
+                id="paperless.W002",
+            ),
+        )
+
+    ocr_mode = os.environ.get("PAPERLESS_OCR_MODE", "")
+    if ocr_mode in {"skip", "skip_noarchive"}:
+        warnings.append(
+            Warning(
+                f"PAPERLESS_OCR_MODE={ocr_mode!r} is not a valid value. "
+                f"Use PAPERLESS_OCR_MODE=auto (and PAPERLESS_ARCHIVE_FILE_GENERATION=never "
+                f"if you used skip_noarchive) instead.",
+                id="paperless.W003",
+            ),
+        )
+
+    return warnings
+
+
+@register()
+def check_remote_parser_configured(app_configs, **kwargs) -> list[Error]:
+    if settings.REMOTE_OCR_ENGINE == "azureai" and not (
+        settings.REMOTE_OCR_ENDPOINT and settings.REMOTE_OCR_API_KEY
+    ):
+        return [
+            Error(
+                "Azure AI remote parser requires endpoint and API key to be configured.",
+            ),
+        ]
+
+    return []
+
+
+def get_tesseract_langs():
+    proc = subprocess.run(
+        [shutil.which("tesseract"), "--list-langs"],
+        capture_output=True,
+    )
+
+    # Decode bytes to string, split on newlines, trim out the header
+    proc_lines = proc.stdout.decode("utf8", errors="ignore").strip().split("\n")[1:]
+
+    return [x.strip() for x in proc_lines]
+
+
+@register()
+def check_default_language_available(app_configs, **kwargs):
+    errs = []
+
+    if not settings.OCR_LANGUAGE:
+        errs.append(
+            Warning(
+                "No OCR language has been specified with PAPERLESS_OCR_LANGUAGE. "
+                "This means that tesseract will fallback to english.",
+            ),
+        )
+        return errs
+
+    # binaries_check in paperless will check and report if this doesn't exist
+    # So skip trying to do anything here and let that handle missing binaries
+    if shutil.which("tesseract") is not None:
+        installed_langs = get_tesseract_langs()
+
+        specified_langs = [x.strip() for x in settings.OCR_LANGUAGE.split("+")]
+
+        for lang in specified_langs:
+            if lang not in installed_langs:
+                errs.append(
+                    Error(
+                        f"The selected ocr language {lang} is "
+                        f"not installed. Paperless cannot OCR your documents "
+                        f"without it. Please fix PAPERLESS_OCR_LANGUAGE.",
+                    ),
+                )
+
+    return errs

src/paperless/config.py

@@ -46,7 +46,7 @@ class OcrConfig(OutputTypeConfig):
     pages: int | None = dataclasses.field(init=False)
     language: str = dataclasses.field(init=False)
     mode: str = dataclasses.field(init=False)
-    skip_archive_file: str = dataclasses.field(init=False)
+    archive_file_generation: str = dataclasses.field(init=False)
     image_dpi: int | None = dataclasses.field(init=False)
     clean: str = dataclasses.field(init=False)
     deskew: bool = dataclasses.field(init=False)
@@ -64,8 +64,8 @@ class OcrConfig(OutputTypeConfig):
         self.pages = app_config.pages or settings.OCR_PAGES
         self.language = app_config.language or settings.OCR_LANGUAGE
         self.mode = app_config.mode or settings.OCR_MODE
-        self.skip_archive_file = (
-            app_config.skip_archive_file or settings.OCR_SKIP_ARCHIVE_FILE
+        self.archive_file_generation = (
+            app_config.archive_file_generation or settings.ARCHIVE_FILE_GENERATION
         )
         self.image_dpi = app_config.image_dpi or settings.OCR_IMAGE_DPI
         self.clean = app_config.unpaper_clean or settings.OCR_CLEAN

src/paperless/migrations/0008_replace_skip_archive_file.py

@@ -0,0 +1,44 @@
+# Generated by Django 5.2.12 on 2026-03-26 20:31
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("paperless", "0007_optimize_integer_field_sizes"),
+    ]
+
+    operations = [
+        migrations.RemoveField(
+            model_name="applicationconfiguration",
+            name="skip_archive_file",
+        ),
+        migrations.AddField(
+            model_name="applicationconfiguration",
+            name="archive_file_generation",
+            field=models.CharField(
+                blank=True,
+                choices=[("auto", "auto"), ("always", "always"), ("never", "never")],
+                max_length=8,
+                null=True,
+                verbose_name="Controls archive file generation",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="applicationconfiguration",
+            name="mode",
+            field=models.CharField(
+                blank=True,
+                choices=[
+                    ("auto", "auto"),
+                    ("force", "force"),
+                    ("redo", "redo"),
+                    ("off", "off"),
+                ],
+                max_length=16,
+                null=True,
+                verbose_name="Sets the OCR mode",
+            ),
+        ),
+    ]

src/paperless/models.py

@@ -36,20 +36,20 @@ class ModeChoices(models.TextChoices):
     and our own custom setting
     """
 
-    SKIP = ("skip", _("skip"))
-    REDO = ("redo", _("redo"))
+    AUTO = ("auto", _("auto"))
     FORCE = ("force", _("force"))
-    SKIP_NO_ARCHIVE = ("skip_noarchive", _("skip_noarchive"))
+    REDO = ("redo", _("redo"))
+    OFF = ("off", _("off"))
 
 
-class ArchiveFileChoices(models.TextChoices):
+class ArchiveFileGenerationChoices(models.TextChoices):
     """
     Settings to control creation of an archive PDF file
     """
 
-    NEVER = ("never", _("never"))
-    WITH_TEXT = ("with_text", _("with_text"))
+    AUTO = ("auto", _("auto"))
     ALWAYS = ("always", _("always"))
+    NEVER = ("never", _("never"))
 
 
 class CleanChoices(models.TextChoices):
@@ -126,12 +126,12 @@ class ApplicationConfiguration(AbstractSingletonModel):
         choices=ModeChoices.choices,
     )
 
-    skip_archive_file = models.CharField(
-        verbose_name=_("Controls the generation of an archive file"),
+    archive_file_generation = models.CharField(
+        verbose_name=_("Controls archive file generation"),
         null=True,
         blank=True,
-        max_length=16,
-        choices=ArchiveFileChoices.choices,
+        max_length=8,
+        choices=ArchiveFileGenerationChoices.choices,
     )
 
     image_dpi = models.PositiveSmallIntegerField(

src/paperless/parsers/registry.py

@@ -33,6 +33,7 @@ name, version, author, url, supported_mime_types (callable), score (callable).
 from __future__ import annotations
 
 import logging
+import threading
 from importlib.metadata import entry_points
 from typing import TYPE_CHECKING
 
@@ -49,6 +50,7 @@ logger = logging.getLogger("paperless.parsers.registry")
 
 _registry: ParserRegistry | None = None
 _discovery_complete: bool = False
+_lock = threading.Lock()
 
 # Attribute names that every registered external parser class must expose.
 _REQUIRED_ATTRS: tuple[str, ...] = (
@@ -74,7 +76,6 @@ def get_parser_registry() -> ParserRegistry:
     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.
 
@@ -85,14 +86,15 @@ def get_parser_registry() -> ParserRegistry:
     """
     global _registry, _discovery_complete
 
-    if _registry is None:
-        _registry = ParserRegistry()
-        _registry.register_defaults()
+    with _lock:
+        if _registry is None:
+            r = ParserRegistry()
+            r.register_defaults()
+            _registry = r
 
-    if not _discovery_complete:
-        _registry.discover()
-        _registry.log_summary()
-        _discovery_complete = True
+        if not _discovery_complete:
+            _registry.discover()
+            _discovery_complete = True
 
     return _registry
 
@@ -113,9 +115,11 @@ def init_builtin_parsers() -> None:
     """
     global _registry
 
-    if _registry is None:
-        _registry = ParserRegistry()
-        _registry.register_defaults()
+    with _lock:
+        if _registry is None:
+            r = ParserRegistry()
+            r.register_defaults()
+            _registry = r
 
 
 def reset_parser_registry() -> None:
@@ -304,6 +308,23 @@ class ParserRegistry:
                 getattr(cls, "url", "unknown"),
             )
 
+    # ------------------------------------------------------------------
+    # Inspection helpers
+    # ------------------------------------------------------------------
+
+    def all_parsers(self) -> list[type[ParserProtocol]]:
+        """Return all registered parser classes (external first, then builtins).
+
+        Used by compatibility wrappers that need to iterate every parser to
+        compute the full set of supported MIME types and file extensions.
+
+        Returns
+        -------
+        list[type[ParserProtocol]]
+            External parsers followed by built-in parsers.
+        """
+        return [*self._external, *self._builtins]
+
     # ------------------------------------------------------------------
     # Parser resolution
     # ------------------------------------------------------------------
@@ -334,7 +355,7 @@ class ParserRegistry:
         mime_type:
             The detected MIME type of the file.
         filename:
-            The original filename, including extension.
+            The original filename, including extension.  May be empty in some cases
         path:
             Optional filesystem path to the file. Forwarded to each
             parser's score method.

src/paperless/parsers/tesseract.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import importlib.resources
 import logging
 import os
 import re
@@ -18,9 +19,11 @@ from documents.parsers import make_thumbnail_from_pdf
 from documents.utils import maybe_override_pixel_limit
 from documents.utils import run_subprocess
 from paperless.config import OcrConfig
-from paperless.models import ArchiveFileChoices
 from paperless.models import CleanChoices
 from paperless.models import ModeChoices
+from paperless.parsers.utils import PDF_TEXT_MIN_LENGTH
+from paperless.parsers.utils import extract_pdf_text
+from paperless.parsers.utils import is_tagged_pdf
 from paperless.parsers.utils import read_file_handle_unicode_errors
 from paperless.version import __full_version_str__
 
@@ -250,36 +253,7 @@ class RasterisedDocumentParser:
         if not Path(pdf_file).is_file():
             return None
 
-        try:
-            text = None
-            with tempfile.NamedTemporaryFile(
-                mode="w+",
-                dir=self.tempdir,
-            ) as tmp:
-                run_subprocess(
-                    [
-                        "pdftotext",
-                        "-q",
-                        "-layout",
-                        "-enc",
-                        "UTF-8",
-                        str(pdf_file),
-                        tmp.name,
-                    ],
-                    logger=self.log,
-                )
-                text = read_file_handle_unicode_errors(Path(tmp.name))
-
-            return post_process_text(text)
-
-        except Exception:
-            #  If pdftotext fails, fall back to OCR.
-            self.log.warning(
-                "Error while getting text from PDF document with pdftotext",
-                exc_info=True,
-            )
-            # probably not a PDF file.
-            return None
+        return post_process_text(extract_pdf_text(Path(pdf_file), log=self.log))
 
     def construct_ocrmypdf_parameters(
         self,
@@ -289,6 +263,7 @@ class RasterisedDocumentParser:
         sidecar_file: Path,
         *,
         safe_fallback: bool = False,
+        skip_text: bool = False,
     ) -> dict[str, Any]:
         ocrmypdf_args: dict[str, Any] = {
             "input_file_or_options": input_file,
@@ -307,15 +282,14 @@ class RasterisedDocumentParser:
                 self.settings.color_conversion_strategy
             )
 
-        if self.settings.mode == ModeChoices.FORCE or safe_fallback:
+        if safe_fallback or self.settings.mode == ModeChoices.FORCE:
             ocrmypdf_args["force_ocr"] = True
-        elif self.settings.mode in {
-            ModeChoices.SKIP,
-            ModeChoices.SKIP_NO_ARCHIVE,
-        }:
-            ocrmypdf_args["skip_text"] = True
         elif self.settings.mode == ModeChoices.REDO:
             ocrmypdf_args["redo_ocr"] = True
+        elif skip_text or self.settings.mode == ModeChoices.OFF:
+            ocrmypdf_args["skip_text"] = True
+        elif self.settings.mode == ModeChoices.AUTO:
+            pass  # no extra flag: normal OCR (text not found case)
         else:  # pragma: no cover
             raise ParseError(f"Invalid ocr mode: {self.settings.mode}")
 
@@ -400,6 +374,62 @@ class RasterisedDocumentParser:
 
         return ocrmypdf_args
 
+    def _convert_image_to_pdfa(self, document_path: Path, mime_type: str) -> Path:
+        """Convert an image to a PDF/A-2b file without invoking the OCR engine.
+
+        Uses img2pdf for the initial image->PDF wrapping, then pikepdf to stamp
+        PDF/A-2b conformance metadata.
+
+        No Tesseract and no Ghostscript are invoked.
+        """
+        import img2pdf
+        import pikepdf
+
+        plain_pdf_path = Path(self.tempdir) / "image_plain.pdf"
+        try:
+            layout_fun = None
+            if self.settings.image_dpi is not None:
+                layout_fun = img2pdf.get_fixed_dpi_layout_fun(
+                    (self.settings.image_dpi, self.settings.image_dpi),
+                )
+            plain_pdf_path.write_bytes(
+                img2pdf.convert(str(document_path), layout_fun=layout_fun),
+            )
+        except Exception as e:
+            raise ParseError(
+                f"img2pdf conversion failed for {document_path}: {e!s}",
+            ) from e
+
+        icc_data = (
+            importlib.resources.files("ocrmypdf.data").joinpath("sRGB.icc").read_bytes()
+        )
+
+        pdfa_path = Path(self.tempdir) / "archive.pdf"
+        try:
+            with pikepdf.open(plain_pdf_path) as pdf:
+                cs = pdf.make_stream(icc_data)
+                cs["/N"] = 3
+                output_intent = pikepdf.Dictionary(
+                    Type=pikepdf.Name("/OutputIntent"),
+                    S=pikepdf.Name("/GTS_PDFA1"),
+                    OutputConditionIdentifier=pikepdf.String("sRGB"),
+                    DestOutputProfile=cs,
+                )
+                pdf.Root["/OutputIntents"] = pdf.make_indirect(
+                    pikepdf.Array([output_intent]),
+                )
+                meta = pdf.open_metadata(set_pikepdf_as_editor=False)
+                meta["pdfaid:part"] = "2"
+                meta["pdfaid:conformance"] = "B"
+                pdf.save(pdfa_path)
+        except Exception as e:
+            self.log.warning(
+                f"PDF/A metadata stamping failed ({e!s}); falling back to plain PDF.",
+            )
+            pdfa_path.write_bytes(plain_pdf_path.read_bytes())
+
+        return pdfa_path
+
     def parse(
         self,
         document_path: Path,
@@ -409,57 +439,106 @@ class RasterisedDocumentParser:
     ) -> None:
         # This forces tesseract to use one core per page.
         os.environ["OMP_THREAD_LIMIT"] = "1"
-        VALID_TEXT_LENGTH = 50
 
         if mime_type == "application/pdf":
             text_original = self.extract_text(None, document_path)
-            original_has_text = (
-                text_original is not None and len(text_original) > VALID_TEXT_LENGTH
+            original_has_text = is_tagged_pdf(document_path, log=self.log) or (
+                text_original is not None and len(text_original) > PDF_TEXT_MIN_LENGTH
             )
         else:
             text_original = None
             original_has_text = False
 
-        # If the original has text, and the user doesn't want an archive,
-        # we're done here
-        skip_archive_for_text = (
-            self.settings.mode == ModeChoices.SKIP_NO_ARCHIVE
-            or self.settings.skip_archive_file
-            in {
-                ArchiveFileChoices.WITH_TEXT,
-                ArchiveFileChoices.ALWAYS,
-            }
-        )
-        if skip_archive_for_text and original_has_text:
-            self.log.debug("Document has text, skipping OCRmyPDF entirely.")
+        # --- OCR_MODE=off: never invoke OCR engine ---
+        if self.settings.mode == ModeChoices.OFF:
+            if not produce_archive:
+                self.text = text_original or ""
+                return
+            if self.is_image(mime_type):
+                try:
+                    self.archive_path = self._convert_image_to_pdfa(
+                        document_path,
+                        mime_type,
+                    )
+                    self.text = ""
+                except Exception as e:
+                    raise ParseError(
+                        f"Image to PDF/A conversion failed: {e!s}",
+                    ) from e
+                return
+            # PDFs in off mode: PDF/A conversion only via skip_text
+            import ocrmypdf
+            from ocrmypdf import SubprocessOutputError
+
+            archive_path = Path(self.tempdir) / "archive.pdf"
+            sidecar_file = Path(self.tempdir) / "sidecar.txt"
+            args = self.construct_ocrmypdf_parameters(
+                document_path,
+                mime_type,
+                archive_path,
+                sidecar_file,
+                skip_text=True,
+            )
+            try:
+                self.log.debug(
+                    f"Calling OCRmyPDF (off mode, PDF/A conversion only): {args}",
+                )
+                ocrmypdf.ocr(**args)
+                self.archive_path = archive_path
+                self.text = self.extract_text(None, archive_path) or text_original or ""
+            except SubprocessOutputError as e:
+                if "Ghostscript PDF/A rendering" in str(e):
+                    self.log.warning(
+                        "Ghostscript PDF/A rendering failed, consider setting "
+                        "PAPERLESS_OCR_USER_ARGS: "
+                        "'{\"continue_on_soft_render_error\": true}'",
+                    )
+                raise ParseError(
+                    f"SubprocessOutputError: {e!s}. See logs for more information.",
+                ) from e
+            except Exception as e:
+                raise ParseError(f"{e.__class__.__name__}: {e!s}") from e
+            return
+
+        # --- OCR_MODE=auto: skip ocrmypdf entirely if text exists and no archive needed ---
+        if (
+            self.settings.mode == ModeChoices.AUTO
+            and original_has_text
+            and not produce_archive
+        ):
+            self.log.debug(
+                "Document has text and no archive requested; skipping OCRmyPDF entirely.",
+            )
             self.text = text_original
             return
 
-        # Either no text was in the original or there should be an archive
-        # file created, so OCR the file and create an archive with any
-        # text located via OCR
-
+        # --- All other paths: run ocrmypdf ---
         import ocrmypdf
         from ocrmypdf import EncryptedPdfError
         from ocrmypdf import InputFileError
         from ocrmypdf import SubprocessOutputError
         from ocrmypdf.exceptions import DigitalSignatureError
+        from ocrmypdf.exceptions import PriorOcrFoundError
 
         archive_path = Path(self.tempdir) / "archive.pdf"
         sidecar_file = Path(self.tempdir) / "sidecar.txt"
 
+        # auto mode with existing text: PDF/A conversion only (no OCR).
+        skip_text = self.settings.mode == ModeChoices.AUTO and original_has_text
+
         args = self.construct_ocrmypdf_parameters(
             document_path,
             mime_type,
             archive_path,
             sidecar_file,
+            skip_text=skip_text,
         )
 
         try:
             self.log.debug(f"Calling OCRmyPDF with args: {args}")
             ocrmypdf.ocr(**args)
 
-            if self.settings.skip_archive_file != ArchiveFileChoices.ALWAYS:
+            if produce_archive:
                 self.archive_path = archive_path
 
             self.text = self.extract_text(sidecar_file, archive_path)
@@ -479,11 +558,10 @@ class RasterisedDocumentParser:
                     "Ghostscript PDF/A rendering failed, consider setting "
                     "PAPERLESS_OCR_USER_ARGS: '{\"continue_on_soft_render_error\": true}'",
                 )
-
             raise ParseError(
                 f"SubprocessOutputError: {e!s}. See logs for more information.",
             ) from e
-        except (NoTextFoundException, InputFileError) as e:
+        except (NoTextFoundException, InputFileError, PriorOcrFoundError) as e:
             self.log.warning(
                 f"Encountered an error while running OCR: {e!s}. "
                 f"Attempting force OCR to get the text.",
@@ -492,8 +570,6 @@ class RasterisedDocumentParser:
             archive_path_fallback = Path(self.tempdir) / "archive-fallback.pdf"
             sidecar_file_fallback = Path(self.tempdir) / "sidecar-fallback.txt"
 
-            # Attempt to run OCR with safe settings.
-
             args = self.construct_ocrmypdf_parameters(
                 document_path,
                 mime_type,
@@ -505,25 +581,18 @@ class RasterisedDocumentParser:
             try:
                 self.log.debug(f"Fallback: Calling OCRmyPDF with args: {args}")
                 ocrmypdf.ocr(**args)
-
-                # Don't return the archived file here, since this file
-                # is bigger and blurry due to --force-ocr.
-
                 self.text = self.extract_text(
                     sidecar_file_fallback,
                     archive_path_fallback,
                 )
-
+                if produce_archive:
+                    self.archive_path = archive_path_fallback
             except Exception as e:
-                # If this fails, we have a serious issue at hand.
                 raise ParseError(f"{e.__class__.__name__}: {e!s}") from e
 
         except Exception as e:
-            # Anything else is probably serious.
             raise ParseError(f"{e.__class__.__name__}: {e!s}") from e
 
-        # As a last resort, if we still don't have any text for any reason,
-        # try to extract the text from the original document.
         if not self.text:
             if original_has_text:
                 self.text = text_original

src/paperless/parsers/utils.py

@@ -10,15 +10,104 @@ from __future__ import annotations
 
 import logging
 import re
+import tempfile
+from pathlib import Path
 from typing import TYPE_CHECKING
 
 if TYPE_CHECKING:
-    from pathlib import Path
-
     from paperless.parsers import MetadataEntry
 
 logger = logging.getLogger("paperless.parsers.utils")
 
+# Minimum character count for a PDF to be considered "born-digital" (has real text).
+# Used by both the consumer (archive decision) and the tesseract parser (skip-OCR decision).
+PDF_TEXT_MIN_LENGTH = 50
+
+
+def is_tagged_pdf(
+    path: Path,
+    log: logging.Logger | None = None,
+) -> bool:
+    """Return True if the PDF declares itself as tagged (born-digital indicator).
+
+    Tagged PDFs (e.g. exported from Word or LibreOffice) have ``/MarkInfo``
+    with ``/Marked true`` in the document root.  This is a reliable signal
+    that the document has a logical structure and embedded text — running OCR
+    on it is unnecessary and archive generation can be skipped.
+
+    https://github.com/ocrmypdf/OCRmyPDF/blob/4e974ebd465a5921b2e79004f098f5d203010282/src/ocrmypdf/pdfinfo/info.py#L449
+
+    Parameters
+    ----------
+    path:
+        Absolute path to the PDF file.
+    log:
+        Logger for warnings.  Falls back to the module-level logger when omitted.
+
+    Returns
+    -------
+    bool
+        ``True`` when the PDF is tagged, ``False`` otherwise or on any error.
+    """
+    import pikepdf
+
+    _log = log or logger
+    try:
+        with pikepdf.open(path) as pdf:
+            mark_info = pdf.Root.get("/MarkInfo")
+            if mark_info is None:
+                return False
+            return bool(mark_info.get("/Marked", False))
+    except Exception:
+        _log.warning("Could not check PDF tag status for %s", path, exc_info=True)
+        return False
+
+
+def extract_pdf_text(
+    path: Path,
+    log: logging.Logger | None = None,
+) -> str | None:
+    """Run pdftotext on *path* and return the extracted text, or None on failure.
+
+    Parameters
+    ----------
+    path:
+        Absolute path to the PDF file.
+    log:
+        Logger for warnings.  Falls back to the module-level logger when omitted.
+
+    Returns
+    -------
+    str | None
+        Extracted text, or ``None`` if pdftotext fails or the file is not a PDF.
+    """
+    from documents.utils import run_subprocess
+
+    _log = log or logger
+    try:
+        with tempfile.TemporaryDirectory() as tmpdir:
+            out_path = Path(tmpdir) / "text.txt"
+            run_subprocess(
+                [
+                    "pdftotext",
+                    "-q",
+                    "-layout",
+                    "-enc",
+                    "UTF-8",
+                    str(path),
+                    str(out_path),
+                ],
+                logger=_log,
+            )
+            text = read_file_handle_unicode_errors(out_path, log=_log)
+            return text or None
+    except Exception:
+        _log.warning(
+            "Error while getting text from PDF document with pdftotext",
+            exc_info=True,
+        )
+        return None
+
 
 def read_file_handle_unicode_errors(
     filepath: Path,

src/paperless/settings/__init__.py

@@ -21,6 +21,7 @@ from paperless.settings.custom import parse_hosting_settings
 from paperless.settings.custom import parse_ignore_dates
 from paperless.settings.custom import parse_redis_url
 from paperless.settings.parsers import get_bool_from_env
+from paperless.settings.parsers import get_choice_from_env
 from paperless.settings.parsers import get_float_from_env
 from paperless.settings.parsers import get_int_from_env
 from paperless.settings.parsers import get_list_from_env
@@ -121,10 +122,7 @@ INSTALLED_APPS = [
     "django_extensions",
     "paperless",
     "documents.apps.DocumentsConfig",
-    "paperless_tesseract.apps.PaperlessTesseractConfig",
-    "paperless_text.apps.PaperlessTextConfig",
     "paperless_mail.apps.PaperlessMailConfig",
-    "paperless_remote.apps.PaperlessRemoteParserConfig",
     "django.contrib.admin",
     "rest_framework",
     "rest_framework.authtoken",
@@ -877,10 +875,17 @@ OCR_LANGUAGE = os.getenv("PAPERLESS_OCR_LANGUAGE", "eng")
 # OCRmyPDF --output-type options are available.
 OCR_OUTPUT_TYPE = os.getenv("PAPERLESS_OCR_OUTPUT_TYPE", "pdfa")
 
-# skip. redo, force
-OCR_MODE = os.getenv("PAPERLESS_OCR_MODE", "skip")
+OCR_MODE = get_choice_from_env(
+    "PAPERLESS_OCR_MODE",
+    {"auto", "force", "redo", "off"},
+    default="auto",
+)
 
-OCR_SKIP_ARCHIVE_FILE = os.getenv("PAPERLESS_OCR_SKIP_ARCHIVE_FILE", "never")
+ARCHIVE_FILE_GENERATION = get_choice_from_env(
+    "PAPERLESS_ARCHIVE_FILE_GENERATION",
+    {"auto", "always", "never"},
+    default="auto",
+)
 
 OCR_IMAGE_DPI = get_int_from_env("PAPERLESS_OCR_IMAGE_DPI")
 
@@ -974,8 +979,8 @@ TIKA_GOTENBERG_ENDPOINT = os.getenv(
     "http://localhost:3000",
 )
 
-if TIKA_ENABLED:
-    INSTALLED_APPS.append("paperless_tika.apps.PaperlessTikaConfig")
+# Tika parser is now integrated into the main parser registry
+# No separate Django app needed
 
 AUDIT_LOG_ENABLED = get_bool_from_env("PAPERLESS_AUDIT_LOG_ENABLED", "true")
 if AUDIT_LOG_ENABLED:

src/paperless/tests/parsers/conftest.py

@@ -90,35 +90,6 @@ def text_parser() -> Generator[TextDocumentParser, None, None]:
         yield parser
 
 
-# ------------------------------------------------------------------
-# Remote parser sample files
-# ------------------------------------------------------------------
-
-
-@pytest.fixture(scope="session")
-def remote_samples_dir(samples_dir: Path) -> Path:
-    """Absolute path to the remote parser sample files directory.
-
-    Returns
-    -------
-    Path
-        ``<samples_dir>/remote/``
-    """
-    return samples_dir / "remote"
-
-
-@pytest.fixture(scope="session")
-def sample_pdf_file(remote_samples_dir: Path) -> Path:
-    """Path to a simple digital PDF sample file.
-
-    Returns
-    -------
-    Path
-        Absolute path to ``remote/simple-digital.pdf``.
-    """
-    return remote_samples_dir / "simple-digital.pdf"
-
-
 # ------------------------------------------------------------------
 # Remote parser instance
 # ------------------------------------------------------------------
@@ -737,7 +708,7 @@ def null_app_config(mocker: MockerFixture) -> MagicMock:
         pages=None,
         language=None,
         mode=None,
-        skip_archive_file=None,
+        archive_file_generation=None,
         image_dpi=None,
         unpaper_clean=None,
         deskew=None,

src/paperless/tests/parsers/test_parse_modes.py

@@ -0,0 +1,436 @@
+"""
+Focused tests for RasterisedDocumentParser.parse() mode behaviour.
+
+These tests mock ``ocrmypdf.ocr`` so they run without a real Tesseract/OCRmyPDF
+installation and execute quickly.  The intent is to verify the *control flow*
+introduced by the ``produce_archive`` flag and the ``OCR_MODE=auto/off`` logic,
+not to test OCRmyPDF itself.
+
+Fixtures are pulled from conftest.py in this package.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import TYPE_CHECKING
+
+import pytest
+
+if TYPE_CHECKING:
+    from pytest_mock import MockerFixture
+
+    from paperless.parsers.tesseract import RasterisedDocumentParser
+
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+_LONG_TEXT = "This is a test document with enough text. " * 5  # >50 chars
+_SHORT_TEXT = "Hi."  # <50 chars
+
+
+def _make_extract_text(text: str | None):
+    """Return a side_effect function for ``extract_text`` that returns *text*."""
+
+    def _extract(sidecar_file, pdf_file):
+        return text
+
+    return _extract
+
+
+# ---------------------------------------------------------------------------
+# AUTO mode — PDF with sufficient text layer
+# ---------------------------------------------------------------------------
+
+
+class TestAutoModeWithText:
+    """AUTO mode, original PDF has detectable text (>50 chars)."""
+
+    def test_auto_text_no_archive_skips_ocrmypdf(
+        self,
+        mocker: MockerFixture,
+        tesseract_parser: RasterisedDocumentParser,
+        simple_digital_pdf_file: Path,
+    ) -> None:
+        """
+        GIVEN:
+            - AUTO mode, produce_archive=False
+            - PDF with text > VALID_TEXT_LENGTH
+        WHEN:
+            - parse() is called
+        THEN:
+            - ocrmypdf.ocr is NOT called (early return path)
+            - archive_path remains None
+            - text is set from the original
+        """
+        # Patch extract_text to return long text (simulating detectable text layer)
+        mocker.patch.object(
+            tesseract_parser,
+            "extract_text",
+            return_value=_LONG_TEXT,
+        )
+        mock_ocr = mocker.patch("ocrmypdf.ocr")
+
+        tesseract_parser.settings.mode = "auto"
+        tesseract_parser.parse(
+            simple_digital_pdf_file,
+            "application/pdf",
+            produce_archive=False,
+        )
+
+        mock_ocr.assert_not_called()
+        assert tesseract_parser.archive_path is None
+        assert tesseract_parser.get_text() == _LONG_TEXT
+
+    def test_auto_text_with_archive_calls_ocrmypdf_skip_text(
+        self,
+        mocker: MockerFixture,
+        tesseract_parser: RasterisedDocumentParser,
+        simple_digital_pdf_file: Path,
+    ) -> None:
+        """
+        GIVEN:
+            - AUTO mode, produce_archive=True
+            - PDF with text > VALID_TEXT_LENGTH
+        WHEN:
+            - parse() is called
+        THEN:
+            - ocrmypdf.ocr IS called with skip_text=True
+            - archive_path is set
+        """
+        mocker.patch.object(
+            tesseract_parser,
+            "extract_text",
+            return_value=_LONG_TEXT,
+        )
+        mock_ocr = mocker.patch("ocrmypdf.ocr")
+
+        tesseract_parser.settings.mode = "auto"
+        tesseract_parser.parse(
+            simple_digital_pdf_file,
+            "application/pdf",
+            produce_archive=True,
+        )
+
+        mock_ocr.assert_called_once()
+        call_kwargs = mock_ocr.call_args.kwargs
+        assert call_kwargs.get("skip_text") is True
+        assert "force_ocr" not in call_kwargs
+        assert "redo_ocr" not in call_kwargs
+        assert tesseract_parser.archive_path is not None
+
+
+# ---------------------------------------------------------------------------
+# AUTO mode — PDF without text layer (or too short)
+# ---------------------------------------------------------------------------
+
+
+class TestAutoModeNoText:
+    """AUTO mode, original PDF has no detectable text (<= 50 chars)."""
+
+    def test_auto_no_text_with_archive_calls_ocrmypdf_no_extra_flag(
+        self,
+        mocker: MockerFixture,
+        tesseract_parser: RasterisedDocumentParser,
+        multi_page_images_pdf_file: Path,
+    ) -> None:
+        """
+        GIVEN:
+            - AUTO mode, produce_archive=True
+            - PDF with no text (or text <= VALID_TEXT_LENGTH)
+        WHEN:
+            - parse() is called
+        THEN:
+            - ocrmypdf.ocr IS called WITHOUT skip_text/force_ocr/redo_ocr
+            - archive_path is set (since produce_archive=True)
+        """
+        # Return "no text" for the original; return real text for archive
+        extract_call_count = 0
+
+        def _extract_side(sidecar_file, pdf_file):
+            nonlocal extract_call_count
+            extract_call_count += 1
+            if extract_call_count == 1:
+                return None  # original has no text
+            return _LONG_TEXT  # text from archive after OCR
+
+        mocker.patch.object(tesseract_parser, "extract_text", side_effect=_extract_side)
+        mock_ocr = mocker.patch("ocrmypdf.ocr")
+
+        tesseract_parser.settings.mode = "auto"
+        tesseract_parser.parse(
+            multi_page_images_pdf_file,
+            "application/pdf",
+            produce_archive=True,
+        )
+
+        mock_ocr.assert_called_once()
+        call_kwargs = mock_ocr.call_args.kwargs
+        assert "skip_text" not in call_kwargs
+        assert "force_ocr" not in call_kwargs
+        assert "redo_ocr" not in call_kwargs
+        assert tesseract_parser.archive_path is not None
+
+    def test_auto_no_text_no_archive_calls_ocrmypdf(
+        self,
+        mocker: MockerFixture,
+        tesseract_parser: RasterisedDocumentParser,
+        multi_page_images_pdf_file: Path,
+    ) -> None:
+        """
+        GIVEN:
+            - AUTO mode, produce_archive=False
+            - PDF with no text
+        WHEN:
+            - parse() is called
+        THEN:
+            - ocrmypdf.ocr IS called (no early return since no text detected)
+            - archive_path is NOT set (produce_archive=False)
+        """
+        extract_call_count = 0
+
+        def _extract_side(sidecar_file, pdf_file):
+            nonlocal extract_call_count
+            extract_call_count += 1
+            if extract_call_count == 1:
+                return None
+            return _LONG_TEXT
+
+        mocker.patch.object(tesseract_parser, "extract_text", side_effect=_extract_side)
+        mock_ocr = mocker.patch("ocrmypdf.ocr")
+
+        tesseract_parser.settings.mode = "auto"
+        tesseract_parser.parse(
+            multi_page_images_pdf_file,
+            "application/pdf",
+            produce_archive=False,
+        )
+
+        mock_ocr.assert_called_once()
+        assert tesseract_parser.archive_path is None
+
+
+# ---------------------------------------------------------------------------
+# OFF mode — PDF
+# ---------------------------------------------------------------------------
+
+
+class TestOffModePdf:
+    """OCR_MODE=off, document is a PDF."""
+
+    def test_off_no_archive_returns_pdftotext(
+        self,
+        mocker: MockerFixture,
+        tesseract_parser: RasterisedDocumentParser,
+        simple_digital_pdf_file: Path,
+    ) -> None:
+        """
+        GIVEN:
+            - OFF mode, produce_archive=False
+            - PDF with text
+        WHEN:
+            - parse() is called
+        THEN:
+            - ocrmypdf.ocr is NOT called
+            - archive_path is None
+            - text comes from pdftotext (extract_text)
+        """
+        mocker.patch.object(
+            tesseract_parser,
+            "extract_text",
+            return_value=_LONG_TEXT,
+        )
+        mock_ocr = mocker.patch("ocrmypdf.ocr")
+
+        tesseract_parser.settings.mode = "off"
+        tesseract_parser.parse(
+            simple_digital_pdf_file,
+            "application/pdf",
+            produce_archive=False,
+        )
+
+        mock_ocr.assert_not_called()
+        assert tesseract_parser.archive_path is None
+        assert tesseract_parser.get_text() == _LONG_TEXT
+
+    def test_off_with_archive_calls_ocrmypdf_skip_text(
+        self,
+        mocker: MockerFixture,
+        tesseract_parser: RasterisedDocumentParser,
+        simple_digital_pdf_file: Path,
+    ) -> None:
+        """
+        GIVEN:
+            - OFF mode, produce_archive=True
+            - PDF document
+        WHEN:
+            - parse() is called
+        THEN:
+            - ocrmypdf.ocr IS called with skip_text=True (PDF/A conversion only)
+            - archive_path is set
+        """
+        mocker.patch.object(
+            tesseract_parser,
+            "extract_text",
+            return_value=_LONG_TEXT,
+        )
+        mock_ocr = mocker.patch("ocrmypdf.ocr")
+
+        tesseract_parser.settings.mode = "off"
+        tesseract_parser.parse(
+            simple_digital_pdf_file,
+            "application/pdf",
+            produce_archive=True,
+        )
+
+        mock_ocr.assert_called_once()
+        call_kwargs = mock_ocr.call_args.kwargs
+        assert call_kwargs.get("skip_text") is True
+        assert "force_ocr" not in call_kwargs
+        assert "redo_ocr" not in call_kwargs
+        assert tesseract_parser.archive_path is not None
+
+
+# ---------------------------------------------------------------------------
+# OFF mode — image
+# ---------------------------------------------------------------------------
+
+
+class TestOffModeImage:
+    """OCR_MODE=off, document is an image (PNG)."""
+
+    def test_off_image_no_archive_no_ocrmypdf(
+        self,
+        mocker: MockerFixture,
+        tesseract_parser: RasterisedDocumentParser,
+        simple_png_file: Path,
+    ) -> None:
+        """
+        GIVEN:
+            - OFF mode, produce_archive=False
+            - Image document (PNG)
+        WHEN:
+            - parse() is called
+        THEN:
+            - ocrmypdf.ocr is NOT called
+            - archive_path is None
+            - text is empty string (images have no text layer)
+        """
+        mock_ocr = mocker.patch("ocrmypdf.ocr")
+
+        tesseract_parser.settings.mode = "off"
+        tesseract_parser.parse(simple_png_file, "image/png", produce_archive=False)
+
+        mock_ocr.assert_not_called()
+        assert tesseract_parser.archive_path is None
+        assert tesseract_parser.get_text() == ""
+
+    def test_off_image_with_archive_uses_img2pdf_path(
+        self,
+        mocker: MockerFixture,
+        tesseract_parser: RasterisedDocumentParser,
+        simple_png_file: Path,
+    ) -> None:
+        """
+        GIVEN:
+            - OFF mode, produce_archive=True
+            - Image document (PNG)
+        WHEN:
+            - parse() is called
+        THEN:
+            - _convert_image_to_pdfa() is called instead of ocrmypdf.ocr
+            - archive_path is set to the returned path
+            - text is empty string
+        """
+        fake_archive = Path("/tmp/fake-archive.pdf")
+        mock_convert = mocker.patch.object(
+            tesseract_parser,
+            "_convert_image_to_pdfa",
+            return_value=fake_archive,
+        )
+        mock_ocr = mocker.patch("ocrmypdf.ocr")
+
+        tesseract_parser.settings.mode = "off"
+        tesseract_parser.parse(simple_png_file, "image/png", produce_archive=True)
+
+        mock_convert.assert_called_once_with(simple_png_file, "image/png")
+        mock_ocr.assert_not_called()
+        assert tesseract_parser.archive_path == fake_archive
+        assert tesseract_parser.get_text() == ""
+
+
+# ---------------------------------------------------------------------------
+# produce_archive=False never sets archive_path for FORCE / REDO / AUTO modes
+# ---------------------------------------------------------------------------
+
+
+class TestProduceArchiveFalse:
+    """Verify produce_archive=False never results in an archive regardless of mode."""
+
+    @pytest.mark.parametrize("mode", ["force", "redo"])
+    def test_produce_archive_false_force_redo_modes(
+        self,
+        mode: str,
+        mocker: MockerFixture,
+        tesseract_parser: RasterisedDocumentParser,
+        multi_page_images_pdf_file: Path,
+    ) -> None:
+        """
+        GIVEN:
+            - FORCE or REDO mode, produce_archive=False
+            - Any PDF
+        WHEN:
+            - parse() is called (ocrmypdf mocked to succeed)
+        THEN:
+            - archive_path is NOT set even though ocrmypdf ran
+        """
+        mocker.patch.object(
+            tesseract_parser,
+            "extract_text",
+            return_value=_LONG_TEXT,
+        )
+        mocker.patch("ocrmypdf.ocr")
+
+        tesseract_parser.settings.mode = mode
+        tesseract_parser.parse(
+            multi_page_images_pdf_file,
+            "application/pdf",
+            produce_archive=False,
+        )
+
+        assert tesseract_parser.archive_path is None
+        assert tesseract_parser.get_text() is not None
+
+    def test_produce_archive_false_auto_with_text(
+        self,
+        mocker: MockerFixture,
+        tesseract_parser: RasterisedDocumentParser,
+        simple_digital_pdf_file: Path,
+    ) -> None:
+        """
+        GIVEN:
+            - AUTO mode, produce_archive=False
+            - PDF with text > VALID_TEXT_LENGTH
+        WHEN:
+            - parse() is called
+        THEN:
+            - ocrmypdf is skipped entirely (early return)
+            - archive_path is None
+        """
+        mocker.patch.object(
+            tesseract_parser,
+            "extract_text",
+            return_value=_LONG_TEXT,
+        )
+        mock_ocr = mocker.patch("ocrmypdf.ocr")
+
+        tesseract_parser.settings.mode = "auto"
+        tesseract_parser.parse(
+            simple_digital_pdf_file,
+            "application/pdf",
+            produce_archive=False,
+        )
+
+        mock_ocr.assert_not_called()
+        assert tesseract_parser.archive_path is None

src/paperless/tests/parsers/test_remote_parser.py

@@ -277,20 +277,20 @@ class TestRemoteParserParse:
     def test_parse_returns_text_from_azure(
         self,
         remote_parser: RemoteDocumentParser,
-        sample_pdf_file: Path,
+        simple_digital_pdf_file: Path,
         azure_client: Mock,
     ) -> None:
-        remote_parser.parse(sample_pdf_file, "application/pdf")
+        remote_parser.parse(simple_digital_pdf_file, "application/pdf")
 
         assert remote_parser.get_text() == _DEFAULT_TEXT
 
     def test_parse_sets_archive_path(
         self,
         remote_parser: RemoteDocumentParser,
-        sample_pdf_file: Path,
+        simple_digital_pdf_file: Path,
         azure_client: Mock,
     ) -> None:
-        remote_parser.parse(sample_pdf_file, "application/pdf")
+        remote_parser.parse(simple_digital_pdf_file, "application/pdf")
 
         archive = remote_parser.get_archive_path()
         assert archive is not None
@@ -300,11 +300,11 @@ class TestRemoteParserParse:
     def test_parse_closes_client_on_success(
         self,
         remote_parser: RemoteDocumentParser,
-        sample_pdf_file: Path,
+        simple_digital_pdf_file: Path,
         azure_client: Mock,
     ) -> None:
         remote_parser.configure(ParserContext())
-        remote_parser.parse(sample_pdf_file, "application/pdf")
+        remote_parser.parse(simple_digital_pdf_file, "application/pdf")
 
         azure_client.close.assert_called_once()
 
@@ -312,9 +312,9 @@ class TestRemoteParserParse:
     def test_parse_sets_empty_text_when_not_configured(
         self,
         remote_parser: RemoteDocumentParser,
-        sample_pdf_file: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
-        remote_parser.parse(sample_pdf_file, "application/pdf")
+        remote_parser.parse(simple_digital_pdf_file, "application/pdf")
 
         assert remote_parser.get_text() == ""
         assert remote_parser.get_archive_path() is None
@@ -328,10 +328,10 @@ class TestRemoteParserParse:
     def test_get_date_always_none(
         self,
         remote_parser: RemoteDocumentParser,
-        sample_pdf_file: Path,
+        simple_digital_pdf_file: Path,
         azure_client: Mock,
     ) -> None:
-        remote_parser.parse(sample_pdf_file, "application/pdf")
+        remote_parser.parse(simple_digital_pdf_file, "application/pdf")
 
         assert remote_parser.get_date() is None
 
@@ -345,33 +345,33 @@ class TestRemoteParserParseError:
     def test_parse_returns_none_on_azure_error(
         self,
         remote_parser: RemoteDocumentParser,
-        sample_pdf_file: Path,
+        simple_digital_pdf_file: Path,
         failing_azure_client: Mock,
     ) -> None:
-        remote_parser.parse(sample_pdf_file, "application/pdf")
+        remote_parser.parse(simple_digital_pdf_file, "application/pdf")
 
         assert remote_parser.get_text() is None
 
     def test_parse_closes_client_on_error(
         self,
         remote_parser: RemoteDocumentParser,
-        sample_pdf_file: Path,
+        simple_digital_pdf_file: Path,
         failing_azure_client: Mock,
     ) -> None:
-        remote_parser.parse(sample_pdf_file, "application/pdf")
+        remote_parser.parse(simple_digital_pdf_file, "application/pdf")
 
         failing_azure_client.close.assert_called_once()
 
     def test_parse_logs_error_on_azure_failure(
         self,
         remote_parser: RemoteDocumentParser,
-        sample_pdf_file: Path,
+        simple_digital_pdf_file: Path,
         failing_azure_client: Mock,
         mocker: MockerFixture,
     ) -> None:
         mock_log = mocker.patch("paperless.parsers.remote.logger")
 
-        remote_parser.parse(sample_pdf_file, "application/pdf")
+        remote_parser.parse(simple_digital_pdf_file, "application/pdf")
 
         mock_log.error.assert_called_once()
         assert "Azure AI Vision parsing failed" in mock_log.error.call_args[0][0]
@@ -386,18 +386,18 @@ class TestRemoteParserPageCount:
     def test_page_count_for_pdf(
         self,
         remote_parser: RemoteDocumentParser,
-        sample_pdf_file: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
-        count = remote_parser.get_page_count(sample_pdf_file, "application/pdf")
+        count = remote_parser.get_page_count(simple_digital_pdf_file, "application/pdf")
         assert isinstance(count, int)
         assert count >= 1
 
     def test_page_count_returns_none_for_image_mime(
         self,
         remote_parser: RemoteDocumentParser,
-        sample_pdf_file: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
-        count = remote_parser.get_page_count(sample_pdf_file, "image/png")
+        count = remote_parser.get_page_count(simple_digital_pdf_file, "image/png")
         assert count is None
 
     def test_page_count_returns_none_for_invalid_pdf(
@@ -420,25 +420,31 @@ class TestRemoteParserMetadata:
     def test_extract_metadata_non_pdf_returns_empty(
         self,
         remote_parser: RemoteDocumentParser,
-        sample_pdf_file: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
-        result = remote_parser.extract_metadata(sample_pdf_file, "image/png")
+        result = remote_parser.extract_metadata(simple_digital_pdf_file, "image/png")
         assert result == []
 
     def test_extract_metadata_pdf_returns_list(
         self,
         remote_parser: RemoteDocumentParser,
-        sample_pdf_file: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
-        result = remote_parser.extract_metadata(sample_pdf_file, "application/pdf")
+        result = remote_parser.extract_metadata(
+            simple_digital_pdf_file,
+            "application/pdf",
+        )
         assert isinstance(result, list)
 
     def test_extract_metadata_pdf_entries_have_required_keys(
         self,
         remote_parser: RemoteDocumentParser,
-        sample_pdf_file: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
-        result = remote_parser.extract_metadata(sample_pdf_file, "application/pdf")
+        result = remote_parser.extract_metadata(
+            simple_digital_pdf_file,
+            "application/pdf",
+        )
         for entry in result:
             assert "namespace" in entry
             assert "prefix" in entry

src/paperless/tests/parsers/test_tesseract_custom_settings.py

@@ -89,15 +89,35 @@ class TestParserSettingsFromDb(DirectoriesMixin, FileSystemAssertsMixin, TestCas
         WHEN:
             - OCR parameters are constructed
         THEN:
-            - Configuration from database is utilized
+            - Configuration from database is utilized (AUTO mode with skip_text=True
+              triggers skip_text; AUTO mode alone does not add any extra flag)
         """
+        # AUTO mode with skip_text=True explicitly passed: skip_text is set
         with override_settings(OCR_MODE="redo"):
             instance = ApplicationConfiguration.objects.all().first()
-            instance.mode = ModeChoices.SKIP
+            instance.mode = ModeChoices.AUTO
+            instance.save()
+
+            params = RasterisedDocumentParser(None).construct_ocrmypdf_parameters(
+                input_file="input.pdf",
+                output_file="output.pdf",
+                sidecar_file="sidecar.txt",
+                mime_type="application/pdf",
+                safe_fallback=False,
+                skip_text=True,
+            )
+        self.assertTrue(params["skip_text"])
+        self.assertNotIn("redo_ocr", params)
+        self.assertNotIn("force_ocr", params)
+
+        # AUTO mode alone (no skip_text): no extra OCR flag is set
+        with override_settings(OCR_MODE="redo"):
+            instance = ApplicationConfiguration.objects.all().first()
+            instance.mode = ModeChoices.AUTO
             instance.save()
 
             params = self.get_params()
-        self.assertTrue(params["skip_text"])
+        self.assertNotIn("skip_text", params)
         self.assertNotIn("redo_ocr", params)
         self.assertNotIn("force_ocr", params)
 

src/paperless/tests/parsers/test_tesseract_parser.py

@@ -370,15 +370,26 @@ class TestParsePdf:
         tesseract_parser: RasterisedDocumentParser,
         tesseract_samples_dir: Path,
     ) -> None:
+        """
+        GIVEN:
+            - Multi-page digital PDF with sufficient text layer
+            - Default settings (mode=auto, produce_archive=True)
+        WHEN:
+            - Document is parsed
+        THEN:
+            - Archive is created (AUTO mode + text present + produce_archive=True
+              → PDF/A conversion via skip_text)
+            - Text is extracted
+        """
         tesseract_parser.parse(
-            tesseract_samples_dir / "simple-digital.pdf",
+            tesseract_samples_dir / "multi-page-digital.pdf",
             "application/pdf",
         )
         assert tesseract_parser.archive_path is not None
         assert tesseract_parser.archive_path.is_file()
         assert_ordered_substrings(
-            tesseract_parser.get_text(),
-            ["This is a test document."],
+            tesseract_parser.get_text().lower(),
+            ["page 1", "page 2", "page 3"],
         )
 
     def test_with_form_default(
@@ -397,7 +408,7 @@ class TestParsePdf:
             ["Please enter your name in here:", "This is a PDF document with a form."],
         )
 
-    def test_with_form_redo_produces_no_archive(
+    def test_with_form_redo_no_archive_when_not_requested(
         self,
         tesseract_parser: RasterisedDocumentParser,
         tesseract_samples_dir: Path,
@@ -406,6 +417,7 @@ class TestParsePdf:
         tesseract_parser.parse(
             tesseract_samples_dir / "with-form.pdf",
             "application/pdf",
+            produce_archive=False,
         )
         assert tesseract_parser.archive_path is None
         assert_ordered_substrings(
@@ -433,7 +445,7 @@ class TestParsePdf:
         tesseract_parser: RasterisedDocumentParser,
         tesseract_samples_dir: Path,
     ) -> None:
-        tesseract_parser.settings.mode = "skip"
+        tesseract_parser.settings.mode = "auto"
         tesseract_parser.parse(tesseract_samples_dir / "signed.pdf", "application/pdf")
         assert tesseract_parser.archive_path is None
         assert_ordered_substrings(
@@ -449,7 +461,7 @@ class TestParsePdf:
         tesseract_parser: RasterisedDocumentParser,
         tesseract_samples_dir: Path,
     ) -> None:
-        tesseract_parser.settings.mode = "skip"
+        tesseract_parser.settings.mode = "auto"
         tesseract_parser.parse(
             tesseract_samples_dir / "encrypted.pdf",
             "application/pdf",
@@ -559,7 +571,7 @@ class TestParseMultiPage:
     @pytest.mark.parametrize(
         "mode",
         [
-            pytest.param("skip", id="skip"),
+            pytest.param("auto", id="auto"),
             pytest.param("redo", id="redo"),
             pytest.param("force", id="force"),
         ],
@@ -587,7 +599,7 @@ class TestParseMultiPage:
         tesseract_parser: RasterisedDocumentParser,
         tesseract_samples_dir: Path,
     ) -> None:
-        tesseract_parser.settings.mode = "skip"
+        tesseract_parser.settings.mode = "auto"
         tesseract_parser.parse(
             tesseract_samples_dir / "multi-page-images.pdf",
             "application/pdf",
@@ -735,16 +747,18 @@ class TestSkipArchive:
         """
         GIVEN:
             - File with existing text layer
-            - Mode: skip_noarchive
+            - Mode: auto, produce_archive=False
         WHEN:
             - Document is parsed
         THEN:
-            - Text extracted; no archive created
+            - Text extracted from original; no archive created (text exists +
+              produce_archive=False skips OCRmyPDF entirely)
         """
-        tesseract_parser.settings.mode = "skip_noarchive"
+        tesseract_parser.settings.mode = "auto"
         tesseract_parser.parse(
             tesseract_samples_dir / "multi-page-digital.pdf",
             "application/pdf",
+            produce_archive=False,
         )
         assert tesseract_parser.archive_path is None
         assert_ordered_substrings(
@@ -760,13 +774,13 @@ class TestSkipArchive:
         """
         GIVEN:
             - File with image-only pages (no text layer)
-            - Mode: skip_noarchive
+            - Mode: auto, skip_archive_file: auto
         WHEN:
             - Document is parsed
         THEN:
-            - Text extracted; archive created (OCR needed)
+            - Text extracted; archive created (OCR needed, no existing text)
         """
-        tesseract_parser.settings.mode = "skip_noarchive"
+        tesseract_parser.settings.mode = "auto"
         tesseract_parser.parse(
             tesseract_samples_dir / "multi-page-images.pdf",
             "application/pdf",
@@ -778,41 +792,58 @@ class TestSkipArchive:
         )
 
     @pytest.mark.parametrize(
-        ("skip_archive_file", "filename", "expect_archive"),
+        ("produce_archive", "filename", "expect_archive"),
         [
-            pytest.param("never", "multi-page-digital.pdf", True, id="never-with-text"),
-            pytest.param("never", "multi-page-images.pdf", True, id="never-no-text"),
             pytest.param(
-                "with_text",
+                True,
                 "multi-page-digital.pdf",
-                False,
-                id="with-text-layer",
+                True,
+                id="produce-archive-with-text",
             ),
             pytest.param(
-                "with_text",
+                True,
                 "multi-page-images.pdf",
                 True,
-                id="with-text-no-layer",
+                id="produce-archive-no-text",
             ),
             pytest.param(
-                "always",
+                False,
                 "multi-page-digital.pdf",
                 False,
-                id="always-with-text",
+                id="no-archive-with-text-layer",
+            ),
+            pytest.param(
+                False,
+                "multi-page-images.pdf",
+                False,
+                id="no-archive-no-text-layer",
             ),
-            pytest.param("always", "multi-page-images.pdf", False, id="always-no-text"),
         ],
     )
-    def test_skip_archive_file_setting(
+    def test_produce_archive_flag(
         self,
-        skip_archive_file: str,
+        produce_archive: bool,  # noqa: FBT001
         filename: str,
-        expect_archive: str,
+        expect_archive: bool,  # noqa: FBT001
         tesseract_parser: RasterisedDocumentParser,
         tesseract_samples_dir: Path,
     ) -> None:
-        tesseract_parser.settings.skip_archive_file = skip_archive_file
-        tesseract_parser.parse(tesseract_samples_dir / filename, "application/pdf")
+        """
+        GIVEN:
+            - Various PDFs (with and without text layers)
+            - produce_archive flag set to True or False
+        WHEN:
+            - Document is parsed
+        THEN:
+            - archive_path is set if and only if produce_archive=True
+            - Text is always extracted
+        """
+        tesseract_parser.settings.mode = "auto"
+        tesseract_parser.parse(
+            tesseract_samples_dir / filename,
+            "application/pdf",
+            produce_archive=produce_archive,
+        )
         text = tesseract_parser.get_text().lower()
         assert_ordered_substrings(text, ["page 1", "page 2", "page 3"])
         if expect_archive:
@@ -820,6 +851,59 @@ class TestSkipArchive:
         else:
             assert tesseract_parser.archive_path is None
 
+    def test_tagged_pdf_skips_ocr_in_auto_mode(
+        self,
+        mocker: MockerFixture,
+        tesseract_parser: RasterisedDocumentParser,
+        tesseract_samples_dir: Path,
+    ) -> None:
+        """
+        GIVEN:
+            - A tagged PDF (e.g. exported from Word, /MarkInfo /Marked true)
+            - Mode: auto, produce_archive=False
+        WHEN:
+            - Document is parsed
+        THEN:
+            - OCRmyPDF is not invoked (tagged ⇒ original_has_text=True)
+            - Text is extracted from the original via pdftotext
+            - No archive is produced
+        """
+        tesseract_parser.settings.mode = "auto"
+        mock_ocr = mocker.patch("ocrmypdf.ocr")
+        tesseract_parser.parse(
+            tesseract_samples_dir / "simple-digital.pdf",
+            "application/pdf",
+            produce_archive=False,
+        )
+        mock_ocr.assert_not_called()
+        assert tesseract_parser.archive_path is None
+        assert tesseract_parser.get_text()
+
+    def test_tagged_pdf_produces_pdfa_archive_without_ocr(
+        self,
+        tesseract_parser: RasterisedDocumentParser,
+        tesseract_samples_dir: Path,
+    ) -> None:
+        """
+        GIVEN:
+            - A tagged PDF (e.g. exported from Word, /MarkInfo /Marked true)
+            - Mode: auto, produce_archive=True
+        WHEN:
+            - Document is parsed
+        THEN:
+            - OCRmyPDF runs with skip_text (PDF/A conversion only, no OCR)
+            - Archive is produced
+            - Text is preserved from the original
+        """
+        tesseract_parser.settings.mode = "auto"
+        tesseract_parser.parse(
+            tesseract_samples_dir / "simple-digital.pdf",
+            "application/pdf",
+            produce_archive=True,
+        )
+        assert tesseract_parser.archive_path is not None
+        assert tesseract_parser.get_text()
+
 
 # ---------------------------------------------------------------------------
 # Parse — mixed pages / sidecar
@@ -835,13 +919,13 @@ class TestParseMixed:
         """
         GIVEN:
             - File with text in some pages (image) and some pages (digital)
-            - Mode: skip
+            - Mode: auto (skip_text), skip_archive_file: always
         WHEN:
             - Document is parsed
         THEN:
             - All pages extracted; archive created; sidecar notes skipped pages
         """
-        tesseract_parser.settings.mode = "skip"
+        tesseract_parser.settings.mode = "auto"
         tesseract_parser.parse(
             tesseract_samples_dir / "multi-page-mixed.pdf",
             "application/pdf",
@@ -898,17 +982,18 @@ class TestParseMixed:
     ) -> None:
         """
         GIVEN:
-            - File with mixed pages
-            - Mode: skip_noarchive
+            - File with mixed pages (some with text, some image-only)
+            - Mode: auto, produce_archive=False
         WHEN:
             - Document is parsed
         THEN:
-            - No archive created (file has text layer); later-page text present
+            - No archive created (produce_archive=False); text from text layer present
         """
-        tesseract_parser.settings.mode = "skip_noarchive"
+        tesseract_parser.settings.mode = "auto"
         tesseract_parser.parse(
             tesseract_samples_dir / "multi-page-mixed.pdf",
             "application/pdf",
+            produce_archive=False,
         )
         assert tesseract_parser.archive_path is None
         assert_ordered_substrings(
@@ -923,12 +1008,12 @@ class TestParseMixed:
 
 
 class TestParseRotate:
-    def test_rotate_skip_mode(
+    def test_rotate_auto_mode(
         self,
         tesseract_parser: RasterisedDocumentParser,
         tesseract_samples_dir: Path,
     ) -> None:
-        tesseract_parser.settings.mode = "skip"
+        tesseract_parser.settings.mode = "auto"
         tesseract_parser.settings.rotate = True
         tesseract_parser.parse(tesseract_samples_dir / "rotated.pdf", "application/pdf")
         assert_ordered_substrings(
@@ -955,12 +1040,19 @@ class TestParseRtl:
     ) -> None:
         """
         GIVEN:
-            - PDF with RTL Arabic text
+            - PDF with RTL Arabic text in its text layer (short: 18 chars)
+            - mode=off, produce_archive=True: PDF/A conversion via skip_text, no OCR engine
         WHEN:
             - Document is parsed
         THEN:
-            - Arabic content is extracted (normalised for bidi)
+            - Arabic content is extracted from the PDF text layer (normalised for bidi)
+
+        Note: The RTL PDF has a short text layer (< VALID_TEXT_LENGTH=50) so AUTO mode
+        would attempt full OCR, which fails due to PriorOcrFoundError and falls back to
+        force-ocr with English Tesseract (producing garbage).  Using mode="off" forces
+        skip_text=True so the Arabic text layer is preserved through PDF/A conversion.
         """
+        tesseract_parser.settings.mode = "off"
         tesseract_parser.parse(
             tesseract_samples_dir / "rtl-test.pdf",
             "application/pdf",
@@ -1023,11 +1115,11 @@ class TestOcrmypdfParameters:
         assert ("clean" in params) == expected_clean
         assert ("clean_final" in params) == expected_clean_final
 
-    def test_clean_final_skip_mode(
+    def test_clean_final_auto_mode(
         self,
         make_tesseract_parser: MakeTesseractParser,
     ) -> None:
-        with make_tesseract_parser(OCR_CLEAN="clean-final", OCR_MODE="skip") as parser:
+        with make_tesseract_parser(OCR_CLEAN="clean-final", OCR_MODE="auto") as parser:
             params = parser.construct_ocrmypdf_parameters("", "", "", "")
         assert params["clean_final"] is True
         assert "clean" not in params
@@ -1044,9 +1136,9 @@ class TestOcrmypdfParameters:
     @pytest.mark.parametrize(
         ("ocr_mode", "ocr_deskew", "expect_deskew"),
         [
-            pytest.param("skip", True, True, id="skip-deskew-on"),
+            pytest.param("auto", True, True, id="auto-deskew-on"),
             pytest.param("redo", True, False, id="redo-deskew-off"),
-            pytest.param("skip", False, False, id="skip-no-deskew"),
+            pytest.param("auto", False, False, id="auto-no-deskew"),
         ],
     )
     def test_deskew_option(

src/paperless/tests/parsers/test_tika_parser.py

@@ -77,10 +77,10 @@ class TestTikaParserRegistryInterface:
     def test_get_page_count_returns_int_with_pdf_archive(
         self,
         tika_parser: TikaDocumentParser,
-        sample_pdf_file: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
-        tika_parser._archive_path = sample_pdf_file
-        count = tika_parser.get_page_count(sample_pdf_file, "application/pdf")
+        tika_parser._archive_path = simple_digital_pdf_file
+        count = tika_parser.get_page_count(simple_digital_pdf_file, "application/pdf")
         assert isinstance(count, int)
         assert count > 0
 

src/paperless/tests/test_checks.py

@@ -5,6 +5,7 @@ from pathlib import Path
 from unittest import mock
 
 import pytest
+from django.core.checks import ERROR
 from django.core.checks import Error
 from django.core.checks import Warning
 from pytest_django.fixtures import SettingsWrapper
@@ -12,7 +13,9 @@ from pytest_mock import MockerFixture
 
 from paperless.checks import audit_log_check
 from paperless.checks import binaries_check
+from paperless.checks import check_default_language_available
 from paperless.checks import check_deprecated_db_settings
+from paperless.checks import check_remote_parser_configured
 from paperless.checks import check_v3_minimum_upgrade_version
 from paperless.checks import debug_mode_check
 from paperless.checks import paths_check
@@ -129,13 +132,13 @@ class TestOcrSettingsChecks:
             pytest.param(
                 "OCR_MODE",
                 "skip_noarchive",
-                "deprecated",
-                id="deprecated-mode",
+                'OCR output mode "skip_noarchive"',
+                id="deprecated-mode-now-invalid",
             ),
             pytest.param(
-                "OCR_SKIP_ARCHIVE_FILE",
+                "ARCHIVE_FILE_GENERATION",
                 "invalid",
-                'OCR_SKIP_ARCHIVE_FILE setting "invalid"',
+                'PAPERLESS_ARCHIVE_FILE_GENERATION setting "invalid"',
                 id="invalid-skip-archive-file",
             ),
             pytest.param(
@@ -626,3 +629,116 @@ class TestV3MinimumUpgradeVersionCheck:
         conn.introspection.table_names.side_effect = OperationalError("DB unavailable")
         mocker.patch.dict("paperless.checks.connections", {"default": conn})
         assert check_v3_minimum_upgrade_version(None) == []
+
+
+class TestRemoteParserChecks:
+    def test_no_engine(self, settings: SettingsWrapper) -> None:
+        settings.REMOTE_OCR_ENGINE = None
+        msgs = check_remote_parser_configured(None)
+
+        assert len(msgs) == 0
+
+    def test_azure_no_endpoint(self, settings: SettingsWrapper) -> None:
+
+        settings.REMOTE_OCR_ENGINE = "azureai"
+        settings.REMOTE_OCR_API_KEY = "somekey"
+        settings.REMOTE_OCR_ENDPOINT = None
+
+        msgs = check_remote_parser_configured(None)
+
+        assert len(msgs) == 1
+
+        msg = msgs[0]
+
+        assert (
+            "Azure AI remote parser requires endpoint and API key to be configured."
+            in msg.msg
+        )
+
+
+class TestTesseractChecks:
+    def test_default_language(self) -> None:
+        check_default_language_available(None)
+
+    def test_no_language(self, settings: SettingsWrapper) -> None:
+
+        settings.OCR_LANGUAGE = ""
+
+        msgs = check_default_language_available(None)
+
+        assert len(msgs) == 1
+        msg = msgs[0]
+
+        assert (
+            "No OCR language has been specified with PAPERLESS_OCR_LANGUAGE" in msg.msg
+        )
+
+    def test_invalid_language(
+        self,
+        settings: SettingsWrapper,
+        mocker: MockerFixture,
+    ) -> None:
+
+        settings.OCR_LANGUAGE = "ita"
+
+        tesser_lang_mock = mocker.patch("paperless.checks.get_tesseract_langs")
+        tesser_lang_mock.return_value = ["deu", "eng"]
+
+        msgs = check_default_language_available(None)
+
+        assert len(msgs) == 1
+        msg = msgs[0]
+
+        assert msg.level == ERROR
+        assert "The selected ocr language ita is not installed" in msg.msg
+
+    def test_multi_part_language(
+        self,
+        settings: SettingsWrapper,
+        mocker: MockerFixture,
+    ) -> None:
+        """
+        GIVEN:
+            - An OCR language which is multi part (ie chi-sim)
+            - The language is correctly formatted
+        WHEN:
+            - Installed packages are checked
+        THEN:
+            - No errors are reported
+        """
+
+        settings.OCR_LANGUAGE = "chi_sim"
+
+        tesser_lang_mock = mocker.patch("paperless.checks.get_tesseract_langs")
+        tesser_lang_mock.return_value = ["chi_sim", "eng"]
+
+        msgs = check_default_language_available(None)
+
+        assert len(msgs) == 0
+
+    def test_multi_part_language_bad_format(
+        self,
+        settings: SettingsWrapper,
+        mocker: MockerFixture,
+    ) -> None:
+        """
+        GIVEN:
+            - An OCR language which is multi part (ie chi-sim)
+            - The language is correctly NOT formatted
+        WHEN:
+            - Installed packages are checked
+        THEN:
+            - No errors are reported
+        """
+        settings.OCR_LANGUAGE = "chi-sim"
+
+        tesser_lang_mock = mocker.patch("paperless.checks.get_tesseract_langs")
+        tesser_lang_mock.return_value = ["chi_sim", "eng"]
+
+        msgs = check_default_language_available(None)
+
+        assert len(msgs) == 1
+        msg = msgs[0]
+
+        assert msg.level == ERROR
+        assert "The selected ocr language chi-sim is not installed" in msg.msg

src/paperless/tests/test_checks_v3.py

@@ -0,0 +1,64 @@
+"""Tests for v3 system checks: deprecated v2 OCR env var warnings."""
+
+from __future__ import annotations
+
+import os
+from typing import TYPE_CHECKING
+
+import pytest
+
+from paperless.checks import check_deprecated_v2_ocr_env_vars
+
+if TYPE_CHECKING:
+    from pytest_mock import MockerFixture
+
+
+class TestDeprecatedV2OcrEnvVarWarnings:
+    def test_no_deprecated_vars_returns_empty(self, mocker: MockerFixture) -> None:
+        """No warnings when neither deprecated variable is set."""
+        mocker.patch.dict(os.environ, {"PAPERLESS_OCR_MODE": "auto"}, clear=True)
+        result = check_deprecated_v2_ocr_env_vars(None)
+        assert result == []
+
+    @pytest.mark.parametrize(
+        ("env_var", "env_value", "expected_id", "expected_fragment"),
+        [
+            pytest.param(
+                "PAPERLESS_OCR_SKIP_ARCHIVE_FILE",
+                "always",
+                "paperless.W002",
+                "PAPERLESS_OCR_SKIP_ARCHIVE_FILE",
+                id="skip-archive-file-warns",
+            ),
+            pytest.param(
+                "PAPERLESS_OCR_MODE",
+                "skip",
+                "paperless.W003",
+                "skip",
+                id="ocr-mode-skip-warns",
+            ),
+            pytest.param(
+                "PAPERLESS_OCR_MODE",
+                "skip_noarchive",
+                "paperless.W003",
+                "skip_noarchive",
+                id="ocr-mode-skip-noarchive-warns",
+            ),
+        ],
+    )
+    def test_deprecated_var_produces_one_warning(
+        self,
+        mocker: MockerFixture,
+        env_var: str,
+        env_value: str,
+        expected_id: str,
+        expected_fragment: str,
+    ) -> None:
+        """Each deprecated setting in isolation produces exactly one warning."""
+        mocker.patch.dict(os.environ, {env_var: env_value}, clear=True)
+        result = check_deprecated_v2_ocr_env_vars(None)
+
+        assert len(result) == 1
+        warning = result[0]
+        assert warning.id == expected_id
+        assert expected_fragment in warning.msg

src/paperless/tests/test_ocr_config.py

@@ -0,0 +1,66 @@
+"""Tests for OcrConfig archive_file_generation field behavior."""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+import pytest
+from django.test import override_settings
+
+from paperless.config import OcrConfig
+
+if TYPE_CHECKING:
+    from unittest.mock import MagicMock
+
+
+@pytest.fixture()
+def null_app_config(mocker) -> MagicMock:
+    """Mock ApplicationConfiguration with all fields None → falls back to Django settings."""
+    return mocker.MagicMock(
+        output_type=None,
+        pages=None,
+        language=None,
+        mode=None,
+        archive_file_generation=None,
+        image_dpi=None,
+        unpaper_clean=None,
+        deskew=None,
+        rotate_pages=None,
+        rotate_pages_threshold=None,
+        max_image_pixels=None,
+        color_conversion_strategy=None,
+        user_args=None,
+    )
+
+
+@pytest.fixture()
+def make_ocr_config(mocker, null_app_config):
+    mocker.patch(
+        "paperless.config.BaseConfig._get_config_instance",
+        return_value=null_app_config,
+    )
+
+    def _make(**django_settings_overrides):
+        with override_settings(**django_settings_overrides):
+            return OcrConfig()
+
+    return _make
+
+
+class TestOcrConfigArchiveFileGeneration:
+    def test_auto_from_settings(self, make_ocr_config) -> None:
+        cfg = make_ocr_config(OCR_MODE="auto", ARCHIVE_FILE_GENERATION="auto")
+        assert cfg.archive_file_generation == "auto"
+
+    def test_always_from_settings(self, make_ocr_config) -> None:
+        cfg = make_ocr_config(ARCHIVE_FILE_GENERATION="always")
+        assert cfg.archive_file_generation == "always"
+
+    def test_never_from_settings(self, make_ocr_config) -> None:
+        cfg = make_ocr_config(ARCHIVE_FILE_GENERATION="never")
+        assert cfg.archive_file_generation == "never"
+
+    def test_db_value_overrides_setting(self, make_ocr_config, null_app_config) -> None:
+        null_app_config.archive_file_generation = "never"
+        cfg = make_ocr_config(ARCHIVE_FILE_GENERATION="always")
+        assert cfg.archive_file_generation == "never"

src/paperless/tests/test_parser_utils.py

@@ -0,0 +1,25 @@
+"""Tests for paperless.parsers.utils helpers."""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from paperless.parsers.utils import is_tagged_pdf
+
+SAMPLES = Path(__file__).parent / "samples" / "tesseract"
+
+
+class TestIsTaggedPdf:
+    def test_tagged_pdf_returns_true(self) -> None:
+        assert is_tagged_pdf(SAMPLES / "simple-digital.pdf") is True
+
+    def test_untagged_pdf_returns_false(self) -> None:
+        assert is_tagged_pdf(SAMPLES / "multi-page-images.pdf") is False
+
+    def test_nonexistent_path_returns_false(self) -> None:
+        assert is_tagged_pdf(Path("/nonexistent/file.pdf")) is False
+
+    def test_corrupt_pdf_returns_false(self, tmp_path: Path) -> None:
+        bad = tmp_path / "bad.pdf"
+        bad.write_bytes(b"not a pdf")
+        assert is_tagged_pdf(bad) is False

src/paperless_mail/apps.py

@@ -1,18 +1,8 @@
 from django.apps import AppConfig
-from django.conf import settings
 from django.utils.translation import gettext_lazy as _
 
-from paperless_mail.signals import mail_consumer_declaration
-
 
 class PaperlessMailConfig(AppConfig):
     name = "paperless_mail"
 
     verbose_name = _("Paperless mail")
-
-    def ready(self) -> None:
-        from documents.signals import document_consumer_declaration
-
-        if settings.TIKA_ENABLED:
-            document_consumer_declaration.connect(mail_consumer_declaration)
-        AppConfig.ready(self)

src/paperless_mail/signals.py

@@ -1,19 +0,0 @@
-def get_parser(*args, **kwargs):
-    from paperless.parsers.mail import MailDocumentParser
-
-    # MailDocumentParser accepts no constructor args in the new-style protocol.
-    # Pop legacy args that arrive from the signal-based consumer path.
-    # Phase 4 will replace this signal path with the ParserRegistry.
-    kwargs.pop("logging_group", None)
-    kwargs.pop("progress_callback", None)
-    return MailDocumentParser()
-
-
-def mail_consumer_declaration(sender, **kwargs):
-    return {
-        "parser": get_parser,
-        "weight": 20,
-        "mime_types": {
-            "message/rfc822": ".eml",
-        },
-    }

src/paperless_mail/templates/email_msg_template.html

@@ -1,4 +1,3 @@
-{% autoescape off %}
 <!doctype html>
 <html>
 
@@ -13,36 +12,34 @@
     <!-- Header -->
     <div class="grid gap-x-2 bg-slate-200 p-4">
 
-      <div class="col-start-9 col-span-4 row-start-1 text-right">{{ date }}</div>
+      <div class="col-start-9 col-span-4 row-start-1 text-right">{{ date|safe }}</div>
 
       <div class="col-start-1 row-start-1 text-slate-400 text-right">{{ from_label }}</div>
-      <div class="col-start-2 col-span-7 row-start-1">{{ from }}</div>
+      <div class="col-start-2 col-span-7 row-start-1">{{ from|safe }}</div>
 
       <div class="col-start-1 row-start-2 text-slate-400 text-right">{{ subject_label }}</div>
-      <div class=" col-start-2 col-span-10 row-start-2 font-bold">{{ subject }}</div>
+      <div class=" col-start-2 col-span-10 row-start-2 font-bold">{{ subject|safe }}</div>
 
       <div class="col-start-1 row-start-3 text-slate-400 text-right">{{ to_label }}</div>
-      <div class="col-start-2 col-span-10 row-start-3 text-sm my-0.5">{{ to }}</div>
+      <div class="col-start-2 col-span-10 row-start-3 text-sm my-0.5">{{ to|safe }}</div>
 
       <div class="col-start-1 row-start-4 text-slate-400 text-right">{{ cc_label }}</div>
-      <div class="col-start-2 col-span-10 row-start-4 text-sm my-0.5">{{ cc }}</div>
+      <div class="col-start-2 col-span-10 row-start-4 text-sm my-0.5">{{ cc|safe }}</div>
 
       <div class="col-start-1 row-start-5 text-slate-400 text-right">{{ bcc_label }}</div>
-      <div class="col-start-2 col-span-10 row-start-5" text-sm my-0.5>{{ bcc }}</div>
+      <div class="col-start-2 col-span-10 row-start-5" text-sm my-0.5>{{ bcc|safe }}</div>
 
 			<div class="col-start-1 row-start-6	 text-slate-400 text-right">{{ attachments_label }}</div>
-      <div class="col-start-2 col-span-10 row-start-6">{{ attachments }}</div>
+      <div class="col-start-2 col-span-10 row-start-6">{{ attachments|safe }}</div>
     </div>
 
     <!-- Separator-->
     <div class="border-t border-solid border-b w-full h-[1px] box-content border-black mb-5 bg-slate-200"></div>
 
     <!-- Content-->
-    <div class="w-full break-words">{{ content }}</div>
+    <div class="w-full break-words">{{ content|safe }}</div>
 	</div>
 
 </body>
 
 </html>
-
-{% endautoescape %}

src/paperless_mail/tests/test_mail_oauth.py

@@ -191,7 +191,10 @@ class TestMailOAuth(
                 ).exists(),
             )
 
-            self.assertIn("Error getting access token: test_error", cm.output[0])
+            self.assertIn(
+                "Error getting access token from OAuth provider",
+                cm.output[0],
+            )
 
     def test_oauth_callback_view_insufficient_permissions(self) -> None:
         """

src/paperless_mail/views.py

@@ -138,13 +138,16 @@ class MailAccountViewSet(ModelViewSet, PassUserMixin):
                         existing_account.refresh_from_db()
                         account.password = existing_account.password
                     else:
+                        logger.error(
+                            "Mail account connectivity test failed: Unable to refresh oauth token",
+                        )
                         raise MailError("Unable to refresh oauth token")
 
                 mailbox_login(M, account)
                 return Response({"success": True})
-            except MailError as e:
+            except MailError:
                 logger.error(
-                    f"Mail account {account} test failed: {e}",
+                    "Mail account connectivity test failed",
                 )
                 return HttpResponseBadRequest("Unable to connect to server")
 
@@ -218,7 +221,7 @@ class OauthCallbackView(GenericAPIView):
 
         if code is None:
             logger.error(
-                f"Invalid oauth callback request, code: {code}, scope: {scope}",
+                "Invalid oauth callback request: missing code",
             )
             return HttpResponseBadRequest("Invalid request, see logs for more detail")
 
@@ -229,7 +232,7 @@ class OauthCallbackView(GenericAPIView):
         state = request.query_params.get("state", "")
         if not oauth_manager.validate_state(state):
             logger.error(
-                f"Invalid oauth callback request received state: {state}, expected: {oauth_manager.state}",
+                "Invalid oauth callback request: state validation failed",
             )
             return HttpResponseBadRequest("Invalid request, see logs for more detail")
 
@@ -276,8 +279,8 @@ class OauthCallbackView(GenericAPIView):
             return HttpResponseRedirect(
                 f"{oauth_manager.oauth_redirect_url}?oauth_success=1&account_id={account.pk}",
             )
-        except GetAccessTokenError as e:
-            logger.error(f"Error getting access token: {e}")
+        except GetAccessTokenError:
+            logger.error("Error getting access token from OAuth provider")
             return HttpResponseRedirect(
                 f"{oauth_manager.oauth_redirect_url}?oauth_success=0",
             )

src/paperless_remote/__init__.py

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

src/paperless_remote/apps.py

@@ -1,14 +0,0 @@
-from django.apps import AppConfig
-
-from paperless_remote.signals import remote_consumer_declaration
-
-
-class PaperlessRemoteParserConfig(AppConfig):
-    name = "paperless_remote"
-
-    def ready(self) -> None:
-        from documents.signals import document_consumer_declaration
-
-        document_consumer_declaration.connect(remote_consumer_declaration)
-
-        AppConfig.ready(self)

src/paperless_remote/checks.py

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

src/paperless_remote/signals.py

@@ -1,38 +0,0 @@
-from __future__ import annotations
-
-from typing import Any
-
-
-def get_parser(*args: Any, **kwargs: Any) -> Any:
-    from paperless.parsers.remote import RemoteDocumentParser
-
-    # The new RemoteDocumentParser does not accept the progress_callback
-    # kwarg injected by the old signal-based consumer.  logging_group is
-    # forwarded as a positional arg.
-    # Phase 4 will replace this signal path with the new ParserRegistry.
-    kwargs.pop("progress_callback", None)
-    return RemoteDocumentParser(*args, **kwargs)
-
-
-def get_supported_mime_types() -> dict[str, str]:
-    from django.conf import settings
-
-    from paperless.parsers.remote import RemoteDocumentParser
-    from paperless.parsers.remote import RemoteEngineConfig
-
-    config = RemoteEngineConfig(
-        engine=settings.REMOTE_OCR_ENGINE,
-        api_key=settings.REMOTE_OCR_API_KEY,
-        endpoint=settings.REMOTE_OCR_ENDPOINT,
-    )
-    if not config.engine_is_valid():
-        return {}
-    return RemoteDocumentParser.supported_mime_types()
-
-
-def remote_consumer_declaration(sender: Any, **kwargs: Any) -> dict[str, Any]:
-    return {
-        "parser": get_parser,
-        "weight": 5,
-        "mime_types": get_supported_mime_types(),
-    }