Merge branch 'dev' into feature-pw-removal-workflow-action

Added a test for the remove_password function to ensure it deletes the original document when specified.

Dockerfile

@@ -30,7 +30,7 @@ RUN set -eux \
 # Purpose: Installs s6-overlay and rootfs
 # Comments:
 #  - Don't leave anything extra in here either
-FROM ghcr.io/astral-sh/uv:0.9.24-python3.12-trixie-slim AS s6-overlay-base
+FROM ghcr.io/astral-sh/uv:0.9.15-python3.12-trixie-slim AS s6-overlay-base
 
 WORKDIR /usr/src/s6
 

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

@@ -430,6 +430,24 @@
           </div>
         </div>
       }
+      @case (WorkflowActionType.PasswordRemoval) {
+        <div class="row">
+          <div class="col">
+            <p class="small" i18n>
+              One or more passwords separated by commas or new lines. The workflow will try them in order until one succeeds.
+            </p>
+            <pngx-input-textarea
+              i18n-title
+              title="Passwords"
+              formControlName="passwords"
+              rows="4"
+              [error]="error?.actions?.[i]?.passwords"
+              hint="Passwords are stored in plain text. Use with caution."
+              i18n-hint
+            ></pngx-input-textarea>
+          </div>
+        </div>
+      }
     }
   </div>
 </ng-template>

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

@@ -139,6 +139,10 @@ export const WORKFLOW_ACTION_OPTIONS = [
     id: WorkflowActionType.Webhook,
     name: $localize`Webhook`,
   },
+  {
+    id: WorkflowActionType.PasswordRemoval,
+    name: $localize`Password removal`,
+  },
 ]
 
 export enum TriggerFilterType {
@@ -1133,6 +1137,7 @@ export class WorkflowEditDialogComponent
           headers: new FormControl(action.webhook?.headers),
           include_document: new FormControl(!!action.webhook?.include_document),
         }),
+        passwords: new FormControl(action.passwords),
       }),
       { emitEvent }
     )

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

@@ -176,6 +176,7 @@ export enum ZoomSetting {
     NgxBootstrapIconsModule,
     PdfViewerModule,
     TextAreaComponent,
+    PasswordRemovalConfirmDialogComponent,
   ],
 })
 export class DocumentDetailComponent

src-ui/src/app/data/workflow-action.ts

@@ -5,6 +5,7 @@ export enum WorkflowActionType {
   Removal = 2,
   Email = 3,
   Webhook = 4,
+  PasswordRemoval = 5,
 }
 
 export interface WorkflowActionEmail extends ObjectWithId {
@@ -97,4 +98,6 @@ export interface WorkflowAction extends ObjectWithId {
   email?: WorkflowActionEmail
 
   webhook?: WorkflowActionWebhook
+
+  passwords?: string
 }

src/documents/migrations/1075_workflowaction_passwords_alter_workflowaction_type.py

@@ -0,0 +1,38 @@
+# Generated by Django 5.2.7 on 2025-12-29 03:56
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "1074_workflowrun_deleted_at_workflowrun_restored_at_and_more"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="workflowaction",
+            name="passwords",
+            field=models.TextField(
+                blank=True,
+                help_text="Passwords to try when removing PDF protection. Separate with commas or new lines.",
+                null=True,
+                verbose_name="passwords",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="workflowaction",
+            name="type",
+            field=models.PositiveIntegerField(
+                choices=[
+                    (1, "Assignment"),
+                    (2, "Removal"),
+                    (3, "Email"),
+                    (4, "Webhook"),
+                    (5, "Password removal"),
+                ],
+                default=1,
+                verbose_name="Workflow Action Type",
+            ),
+        ),
+    ]

src/documents/models.py

@@ -1287,6 +1287,10 @@ class WorkflowAction(models.Model):
             4,
             _("Webhook"),
         )
+        PASSWORD_REMOVAL = (
+            5,
+            _("Password removal"),
+        )
 
     type = models.PositiveIntegerField(
         _("Workflow Action Type"),
@@ -1514,6 +1518,15 @@ class WorkflowAction(models.Model):
         verbose_name=_("webhook"),
     )
 
+    passwords = models.TextField(
+        _("passwords"),
+        null=True,
+        blank=True,
+        help_text=_(
+            "Passwords to try when removing PDF protection. Separate with commas or new lines.",
+        ),
+    )
+
     class Meta:
         verbose_name = _("workflow action")
         verbose_name_plural = _("workflow actions")

src/documents/serialisers.py

@@ -580,34 +580,30 @@ class TagSerializer(MatchingModelSerializer, OwnedObjectSerializer):
         ),
     )
     def get_children(self, obj):
-        children_map = self.context.get("children_map")
-        if children_map is not None:
-            children = children_map.get(obj.pk, [])
-        else:
-            filter_q = self.context.get("document_count_filter")
-            request = self.context.get("request")
-            if filter_q is None:
-                user = getattr(request, "user", None) if request else None
-                filter_q = get_document_count_filter_for_user(user)
-                self.context["document_count_filter"] = filter_q
+        filter_q = self.context.get("document_count_filter")
+        request = self.context.get("request")
+        if filter_q is None:
+            user = getattr(request, "user", None) if request else None
+            filter_q = get_document_count_filter_for_user(user)
+            self.context["document_count_filter"] = filter_q
 
-            children = (
-                obj.get_children_queryset()
-                .select_related("owner")
-                .annotate(document_count=Count("documents", filter=filter_q))
-            )
+        children_queryset = (
+            obj.get_children_queryset()
+            .select_related("owner")
+            .annotate(document_count=Count("documents", filter=filter_q))
+        )
 
-            view = self.context.get("view")
-            ordering = (
-                OrderingFilter().get_ordering(request, children, view)
-                if request and view
-                else None
-            )
-            ordering = ordering or (Lower("name"),)
-            children = children.order_by(*ordering)
+        view = self.context.get("view")
+        ordering = (
+            OrderingFilter().get_ordering(request, children_queryset, view)
+            if request and view
+            else None
+        )
+        ordering = ordering or (Lower("name"),)
+        children_queryset = children_queryset.order_by(*ordering)
 
         serializer = TagSerializer(
-            children,
+            children_queryset,
             many=True,
             user=self.user,
             full_perms=self.full_perms,
@@ -2453,6 +2449,7 @@ class WorkflowActionSerializer(serializers.ModelSerializer):
             "remove_change_groups",
             "email",
             "webhook",
+            "passwords",
         ]
 
     def validate(self, attrs):
@@ -2509,6 +2506,20 @@ class WorkflowActionSerializer(serializers.ModelSerializer):
                 "Webhook data is required for webhook actions",
             )
 
+        if (
+            "type" in attrs
+            and attrs["type"] == WorkflowAction.WorkflowActionType.PASSWORD_REMOVAL
+        ):
+            passwords = attrs.get("passwords")
+            if passwords is None or not isinstance(passwords, str):
+                raise serializers.ValidationError(
+                    "Passwords are required for password removal actions",
+                )
+            if not passwords.strip():
+                raise serializers.ValidationError(
+                    "Passwords are required for password removal actions",
+                )
+
         return attrs
 
 

src/documents/signals/handlers.py

@@ -46,6 +46,7 @@ from documents.permissions import get_objects_for_user_owner_aware
 from documents.templating.utils import convert_format_str_to_template_format
 from documents.workflows.actions import build_workflow_action_context
 from documents.workflows.actions import execute_email_action
+from documents.workflows.actions import execute_password_removal_action
 from documents.workflows.actions import execute_webhook_action
 from documents.workflows.mutations import apply_assignment_to_document
 from documents.workflows.mutations import apply_assignment_to_overrides
@@ -792,6 +793,8 @@ def run_workflows(
                         logging_group,
                         original_file,
                     )
+                elif action.type == WorkflowAction.WorkflowActionType.PASSWORD_REMOVAL:
+                    execute_password_removal_action(action, document, logging_group)
 
             if not use_overrides:
                 # limit title to 128 characters

src/documents/tests/test_api_workflows.py

@@ -808,3 +808,57 @@ class TestApiWorkflows(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_200_OK)
         self.action.refresh_from_db()
         self.assertEqual(self.action.assign_title, "Patched Title")
+
+    def test_password_action_passwords_field(self):
+        """
+        GIVEN:
+            - Nothing
+        WHEN:
+            - A workflow password removal action is created with passwords set
+        THEN:
+            - The passwords field is correctly stored and retrieved
+        """
+        passwords = "password1,password2\npassword3"
+        response = self.client.post(
+            "/api/workflow_actions/",
+            {
+                "type": WorkflowAction.WorkflowActionType.PASSWORD_REMOVAL,
+                "passwords": passwords,
+            },
+        )
+        self.assertEqual(response.status_code, status.HTTP_201_CREATED)
+        self.assertEqual(response.data["passwords"], passwords)
+
+    def test_password_action_no_passwords_field(self):
+        """
+        GIVEN:
+            - Nothing
+        WHEN:
+            - A workflow password removal action is created with no passwords set
+            - A workflow password removal action is created with passwords set to empty string
+        THEN:
+            - The required validation error is raised
+        """
+        response = self.client.post(
+            "/api/workflow_actions/",
+            {
+                "type": WorkflowAction.WorkflowActionType.PASSWORD_REMOVAL,
+            },
+        )
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertIn(
+            "Passwords are required",
+            str(response.data["non_field_errors"][0]),
+        )
+        response = self.client.post(
+            "/api/workflow_actions/",
+            {
+                "type": WorkflowAction.WorkflowActionType.PASSWORD_REMOVAL,
+                "passwords": "",
+            },
+        )
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertIn(
+            "Passwords are required",
+            str(response.data["non_field_errors"][0]),
+        )

src/documents/tests/test_workflows.py

@@ -2,6 +2,7 @@ import datetime
 import json
 import shutil
 import socket
+import tempfile
 from datetime import timedelta
 from pathlib import Path
 from typing import TYPE_CHECKING
@@ -60,6 +61,7 @@ from documents.tests.utils import DirectoriesMixin
 from documents.tests.utils import DummyProgressManager
 from documents.tests.utils import FileSystemAssertsMixin
 from documents.tests.utils import SampleDirMixin
+from documents.workflows.actions import execute_password_removal_action
 from paperless_mail.models import MailAccount
 from paperless_mail.models import MailRule
 
@@ -3610,6 +3612,196 @@ class TestWorkflows(
 
         mock_post.assert_called_once()
 
+    @mock.patch("documents.bulk_edit.remove_password")
+    def test_password_removal_action_attempts_multiple_passwords(
+        self,
+        mock_remove_password,
+    ):
+        """
+        GIVEN:
+            - Workflow password removal action
+            - Multiple passwords provided
+        WHEN:
+            - Document updated triggering the workflow
+        THEN:
+            - Password removal is attempted until one succeeds
+        """
+        doc = Document.objects.create(
+            title="Protected",
+            checksum="pw-checksum",
+        )
+        trigger = WorkflowTrigger.objects.create(
+            type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
+        )
+        action = WorkflowAction.objects.create(
+            type=WorkflowAction.WorkflowActionType.PASSWORD_REMOVAL,
+            passwords="wrong, right\n extra ",
+        )
+        workflow = Workflow.objects.create(name="Password workflow")
+        workflow.triggers.add(trigger)
+        workflow.actions.add(action)
+
+        mock_remove_password.side_effect = [
+            ValueError("wrong password"),
+            "OK",
+        ]
+
+        run_workflows(trigger.type, doc)
+
+        assert mock_remove_password.call_count == 2
+        mock_remove_password.assert_has_calls(
+            [
+                mock.call(
+                    [doc.id],
+                    password="wrong",
+                    update_document=True,
+                    user=doc.owner,
+                ),
+                mock.call(
+                    [doc.id],
+                    password="right",
+                    update_document=True,
+                    user=doc.owner,
+                ),
+            ],
+        )
+
+    @mock.patch("documents.bulk_edit.remove_password")
+    def test_password_removal_action_fails_without_correct_password(
+        self,
+        mock_remove_password,
+    ):
+        """
+        GIVEN:
+            - Workflow password removal action
+            - No correct password provided
+        WHEN:
+            - Document updated triggering the workflow
+        THEN:
+            - Password removal is attempted for all passwords and fails
+        """
+        doc = Document.objects.create(
+            title="Protected",
+            checksum="pw-checksum-2",
+        )
+        trigger = WorkflowTrigger.objects.create(
+            type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
+        )
+        action = WorkflowAction.objects.create(
+            type=WorkflowAction.WorkflowActionType.PASSWORD_REMOVAL,
+            passwords=" \n , ",
+        )
+        workflow = Workflow.objects.create(name="Password workflow missing passwords")
+        workflow.triggers.add(trigger)
+        workflow.actions.add(action)
+
+        run_workflows(trigger.type, doc)
+
+        mock_remove_password.assert_not_called()
+
+    @mock.patch("documents.bulk_edit.remove_password")
+    def test_password_removal_action_skips_without_passwords(
+        self,
+        mock_remove_password,
+    ):
+        """
+        GIVEN:
+            - Workflow password removal action with no passwords
+        WHEN:
+            - Workflow is run
+        THEN:
+            - Password removal is not attempted
+        """
+        doc = Document.objects.create(
+            title="Protected",
+            checksum="pw-checksum-2",
+        )
+        trigger = WorkflowTrigger.objects.create(
+            type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
+        )
+        action = WorkflowAction.objects.create(
+            type=WorkflowAction.WorkflowActionType.PASSWORD_REMOVAL,
+            passwords="",
+        )
+        workflow = Workflow.objects.create(name="Password workflow missing passwords")
+        workflow.triggers.add(trigger)
+        workflow.actions.add(action)
+
+        run_workflows(trigger.type, doc)
+
+        mock_remove_password.assert_not_called()
+
+    @mock.patch("documents.bulk_edit.remove_password")
+    def test_password_removal_consumable_document_deferred(
+        self,
+        mock_remove_password,
+    ):
+        """
+        GIVEN:
+            - Workflow password removal action
+            - Simulated consumption trigger (a ConsumableDocument is used)
+        WHEN:
+            - Document consumption is finished
+        THEN:
+            - Password removal is attempted
+        """
+        action = WorkflowAction.objects.create(
+            type=WorkflowAction.WorkflowActionType.PASSWORD_REMOVAL,
+            passwords="first, second",
+        )
+
+        temp_dir = Path(tempfile.mkdtemp())
+        original_file = temp_dir / "file.pdf"
+        original_file.write_bytes(b"pdf content")
+        consumable = ConsumableDocument(
+            source=DocumentSource.ApiUpload,
+            original_file=original_file,
+        )
+
+        execute_password_removal_action(action, consumable, logging_group=None)
+
+        mock_remove_password.assert_not_called()
+
+        mock_remove_password.side_effect = [
+            ValueError("bad password"),
+            "OK",
+        ]
+
+        doc = Document.objects.create(
+            checksum="pw-checksum-consumed",
+            title="Protected",
+        )
+
+        document_consumption_finished.send(
+            sender=self.__class__,
+            document=doc,
+        )
+
+        assert mock_remove_password.call_count == 2
+        mock_remove_password.assert_has_calls(
+            [
+                mock.call(
+                    [doc.id],
+                    password="first",
+                    update_document=True,
+                    user=doc.owner,
+                ),
+                mock.call(
+                    [doc.id],
+                    password="second",
+                    update_document=True,
+                    user=doc.owner,
+                ),
+            ],
+        )
+
+        # ensure handler disconnected after first run
+        document_consumption_finished.send(
+            sender=self.__class__,
+            document=doc,
+        )
+        assert mock_remove_password.call_count == 2
+
 
 class TestWebhookSend:
     def test_send_webhook_data_or_json(

src/documents/views.py

@@ -448,43 +448,8 @@ class TagViewSet(ModelViewSet, PermissionsAwareDocumentCountMixin):
     def get_serializer_context(self):
         context = super().get_serializer_context()
         context["document_count_filter"] = self.get_document_count_filter()
-        if hasattr(self, "_children_map"):
-            context["children_map"] = self._children_map
         return context
 
-    def list(self, request, *args, **kwargs):
-        """
-        Build a children map once to avoid per-parent queries in the serializer.
-        """
-        queryset = self.filter_queryset(self.get_queryset())
-        ordering = OrderingFilter().get_ordering(request, queryset, self) or (
-            Lower("name"),
-        )
-        queryset = queryset.order_by(*ordering)
-
-        all_tags = list(queryset)
-        descendant_pks = {pk for tag in all_tags for pk in tag.get_descendants_pks()}
-
-        if descendant_pks:
-            filter_q = self.get_document_count_filter()
-            children_source = (
-                Tag.objects.filter(pk__in=descendant_pks | {t.pk for t in all_tags})
-                .select_related("owner")
-                .annotate(document_count=Count("documents", filter=filter_q))
-                .order_by(*ordering)
-            )
-        else:
-            children_source = all_tags
-
-        children_map = {}
-        for tag in children_source:
-            children_map.setdefault(tag.tn_parent_id, []).append(tag)
-        self._children_map = children_map
-
-        page = self.paginate_queryset(queryset)
-        serializer = self.get_serializer(page, many=True)
-        return self.get_paginated_response(serializer.data)
-
     def perform_update(self, serializer):
         old_parent = self.get_object().get_parent()
         tag = serializer.save()

src/documents/workflows/actions.py

@@ -1,4 +1,5 @@
 import logging
+import re
 from pathlib import Path
 
 from django.conf import settings
@@ -14,6 +15,7 @@ from documents.models import Document
 from documents.models import DocumentType
 from documents.models import WorkflowAction
 from documents.models import WorkflowTrigger
+from documents.signals import document_consumption_finished
 from documents.templating.workflows import parse_w_workflow_placeholders
 from documents.workflows.webhooks import send_webhook
 
@@ -259,3 +261,74 @@ def execute_webhook_action(
             f"Error occurred sending webhook: {e}",
             extra={"group": logging_group},
         )
+
+
+def execute_password_removal_action(
+    action: WorkflowAction,
+    document: Document | ConsumableDocument,
+    logging_group,
+) -> None:
+    """
+    Try to remove a password from a document using the configured list.
+    """
+    passwords = action.passwords
+    if not passwords:
+        logger.warning(
+            "Password removal action %s has no passwords configured",
+            action.pk,
+            extra={"group": logging_group},
+        )
+        return
+
+    passwords = [
+        password.strip()
+        for password in re.split(r"[,\n]", passwords)
+        if password.strip()
+    ]
+
+    if isinstance(document, ConsumableDocument):
+        # hook the consumption-finished signal to attempt password removal later
+        def handler(sender, **kwargs):
+            consumed_document: Document = kwargs.get("document")
+            if consumed_document is not None:
+                execute_password_removal_action(
+                    action,
+                    consumed_document,
+                    logging_group,
+                )
+            document_consumption_finished.disconnect(handler)
+
+        document_consumption_finished.connect(handler, weak=False)
+        return
+
+    # import here to avoid circular dependency
+    from documents.bulk_edit import remove_password
+
+    for password in passwords:
+        try:
+            remove_password(
+                [document.id],
+                password=password,
+                update_document=True,
+                user=document.owner,
+            )
+            logger.info(
+                "Removed password from document %s using workflow action %s",
+                document.pk,
+                action.pk,
+                extra={"group": logging_group},
+            )
+            return
+        except ValueError as e:
+            logger.warning(
+                "Password removal failed for document %s with supplied password: %s",
+                document.pk,
+                e,
+                extra={"group": logging_group},
+            )
+
+    logger.error(
+        "Password removal failed for document %s after trying all provided passwords",
+        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: 2026-01-12 21:04+0000\n"
+"POT-Creation-Date: 2026-01-08 21:50+0000\n"
 "PO-Revision-Date: 2022-02-17 04:17\n"
 "Last-Translator: \n"
 "Language-Team: English\n"
@@ -1219,35 +1219,35 @@ msgstr ""
 msgid "workflow runs"
 msgstr ""
 
-#: documents/serialisers.py:646
+#: documents/serialisers.py:642
 msgid "Invalid color."
 msgstr ""
 
-#: documents/serialisers.py:1850
+#: documents/serialisers.py:1846
 #, python-format
 msgid "File type %(type)s not supported"
 msgstr ""
 
-#: documents/serialisers.py:1894
+#: documents/serialisers.py:1890
 #, python-format
 msgid "Custom field id must be an integer: %(id)s"
 msgstr ""
 
-#: documents/serialisers.py:1901
+#: documents/serialisers.py:1897
 #, python-format
 msgid "Custom field with id %(id)s does not exist"
 msgstr ""
 
-#: documents/serialisers.py:1918 documents/serialisers.py:1928
+#: documents/serialisers.py:1914 documents/serialisers.py:1924
 msgid ""
 "Custom fields must be a list of integers or an object mapping ids to values."
 msgstr ""
 
-#: documents/serialisers.py:1923
+#: documents/serialisers.py:1919
 msgid "Some custom fields don't exist or were specified twice."
 msgstr ""
 
-#: documents/serialisers.py:2038
+#: documents/serialisers.py:2034
 msgid "Invalid variable detected."
 msgstr ""