Chore: add backoff ro handle 429 Wikimedia requests in tests (#11364)

Bumps [astral-sh/uv](https://github.com/astral-sh/uv) from 0.9.7-python3.12-bookworm-slim to 0.9.9-python3.12-bookworm-slim.
- [Release notes](https://github.com/astral-sh/uv/releases)
- [Changelog](https://github.com/astral-sh/uv/blob/main/CHANGELOG.md)
- [Commits](https://github.com/astral-sh/uv/compare/0.9.7...0.9.9)

---
updated-dependencies:
- dependency-name: astral-sh/uv
  dependency-version: 0.9.8-python3.12-bookworm-slim
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

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

Dockerfile

@@ -32,7 +32,7 @@ RUN set -eux \
 # Purpose: Installs s6-overlay and rootfs
 # Comments:
 #  - Don't leave anything extra in here either
-FROM ghcr.io/astral-sh/uv:0.9.7-python3.12-bookworm-slim AS s6-overlay-base
+FROM ghcr.io/astral-sh/uv:0.9.9-python3.12-bookworm-slim AS s6-overlay-base
 
 WORKDIR /usr/src/s6
 

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

@@ -747,7 +747,7 @@ export class FilterEditorComponent
     ) {
       filterRules.push({
         rule_type: FILTER_TITLE_CONTENT,
-        value: this._textFilter,
+        value: this._textFilter.trim(),
       })
     }
     if (this._textFilter && this.textFilterTarget == TEXT_FILTER_TARGET_TITLE) {
@@ -805,7 +805,7 @@ export class FilterEditorComponent
     ) {
       filterRules.push({
         rule_type: FILTER_FULLTEXT_QUERY,
-        value: this._textFilter,
+        value: this._textFilter.trim(),
       })
     }
     if (

src/documents/filters.py

@@ -160,6 +160,7 @@ class InboxFilter(Filter):
 @extend_schema_field(serializers.CharField)
 class TitleContentFilter(Filter):
     def filter(self, qs, value):
+        value = value.strip() if isinstance(value, str) else value
         if value:
             return qs.filter(Q(title__icontains=value) | Q(content__icontains=value))
         else:
@@ -214,6 +215,7 @@ class CustomFieldFilterSet(FilterSet):
 @extend_schema_field(serializers.CharField)
 class CustomFieldsFilter(Filter):
     def filter(self, qs, value):
+        value = value.strip() if isinstance(value, str) else value
         if value:
             fields_with_matching_selects = CustomField.objects.filter(
                 extra_data__icontains=value,
@@ -244,6 +246,7 @@ class CustomFieldsFilter(Filter):
 
 class MimeTypeFilter(Filter):
     def filter(self, qs, value):
+        value = value.strip() if isinstance(value, str) else value
         if value:
             return qs.filter(mime_type__icontains=value)
         else:

src/documents/mail.py

@@ -1,25 +1,26 @@
 from __future__ import annotations
 
+from dataclasses import dataclass
 from email import message_from_bytes
-from typing import TYPE_CHECKING
+from pathlib import Path
 
 from django.conf import settings
 from django.core.mail import EmailMessage
 from filelock import FileLock
 
-from documents.data_models import ConsumableDocument
 
-if TYPE_CHECKING:
-    from documents.models import Document
+@dataclass(frozen=True)
+class EmailAttachment:
+    path: Path
+    mime_type: str
+    friendly_name: str
 
 
 def send_email(
     subject: str,
     body: str,
     to: list[str],
-    attachments: list[Document | ConsumableDocument],
-    *,
-    use_archive: bool,
+    attachments: list[EmailAttachment],
 ) -> int:
     """
     Send an email with attachments.
@@ -28,8 +29,7 @@ def send_email(
         subject: Email subject
         body: Email body text
         to: List of recipient email addresses
-        attachments: List of documents to attach (the list may be empty)
-        use_archive: Whether to attach archive versions when available
+        attachments: List of attachments
 
     Returns:
         Number of emails sent
@@ -46,47 +46,41 @@ def send_email(
 
     # Something could be renaming the file concurrently so it can't be attached
     with FileLock(settings.MEDIA_LOCK):
-        for document in attachments:
-            if isinstance(document, ConsumableDocument):
-                attachment_path = document.original_file
-                friendly_filename = document.original_file.name
-            else:
-                attachment_path = (
-                    document.archive_path
-                    if use_archive and document.has_archive_version
-                    else document.source_path
-                )
-                friendly_filename = _get_unique_filename(
-                    document,
-                    used_filenames,
-                    archive=use_archive and document.has_archive_version,
-                )
-            used_filenames.add(friendly_filename)
+        for attachment in attachments:
+            filename = _get_unique_filename(
+                attachment.friendly_name,
+                used_filenames,
+            )
+            used_filenames.add(filename)
 
-            with attachment_path.open("rb") as f:
+            with attachment.path.open("rb") as f:
                 content = f.read()
-                if document.mime_type == "message/rfc822":
+                if attachment.mime_type == "message/rfc822":
                     # See https://forum.djangoproject.com/t/using-emailmessage-with-an-attached-email-file-crashes-due-to-non-ascii/37981
                     content = message_from_bytes(content)
 
                 email.attach(
-                    filename=friendly_filename,
+                    filename=filename,
                     content=content,
-                    mimetype=document.mime_type,
+                    mimetype=attachment.mime_type,
                 )
 
     return email.send()
 
 
-def _get_unique_filename(doc: Document, used_names: set[str], *, archive: bool) -> str:
+def _get_unique_filename(friendly_name: str, used_names: set[str]) -> str:
     """
-    Constructs a unique friendly filename for the given document.
+    Constructs a unique friendly filename for the given document, append a counter if needed.
+    """
+    if friendly_name not in used_names:
+        return friendly_name
 
-    The filename might not be unique enough, so a counter is appended if needed.
-    """
-    counter = 0
+    stem = Path(friendly_name).stem
+    suffix = "".join(Path(friendly_name).suffixes)
+
+    counter = 1
     while True:
-        filename = doc.get_public_filename(archive=archive, counter=counter)
+        filename = f"{stem}_{counter:02}{suffix}"
         if filename not in used_names:
             return filename
         counter += 1

src/documents/signals/handlers.py

@@ -31,11 +31,10 @@ from guardian.shortcuts import remove_perm
 
 from documents import matching
 from documents.caching import clear_document_caches
-from documents.data_models import ConsumableDocument
-from documents.data_models import DocumentSource
 from documents.file_handling import create_source_path_directory
 from documents.file_handling import delete_empty_directories
 from documents.file_handling import generate_unique_filename
+from documents.mail import EmailAttachment
 from documents.mail import send_email
 from documents.models import Correspondent
 from documents.models import CustomField
@@ -57,6 +56,7 @@ from documents.templating.workflows import parse_w_workflow_placeholders
 
 if TYPE_CHECKING:
     from documents.classifier import DocumentClassifier
+    from documents.data_models import ConsumableDocument
     from documents.data_models import DocumentMetadataOverrides
 
 logger = logging.getLogger("paperless.handlers")
@@ -1095,7 +1095,9 @@ def run_workflows(
 
         if not use_overrides:
             title = document.title
-            doc_url = f"{settings.PAPERLESS_URL}/documents/{document.pk}/"
+            doc_url = (
+                f"{settings.PAPERLESS_URL}{settings.BASE_URL}documents/{document.pk}/"
+            )
             correspondent = (
                 document.correspondent.name if document.correspondent else ""
             )
@@ -1163,28 +1165,41 @@ def run_workflows(
             else ""
         )
         try:
-            attachments = []
+            attachments: list[EmailAttachment] = []
             if action.email.include_document:
+                attachment: EmailAttachment | None = None
                 if trigger_type in [
                     WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
                     WorkflowTrigger.WorkflowTriggerType.SCHEDULED,
-                ]:
-                    # Updated and scheduled can pass the document directly
-                    attachments = [document]
+                ] and isinstance(document, Document):
+                    friendly_name = (
+                        Path(current_filename).name
+                        if current_filename
+                        else document.source_path.name
+                    )
+                    attachment = EmailAttachment(
+                        path=document.source_path,
+                        mime_type=document.mime_type,
+                        friendly_name=friendly_name,
+                    )
                 elif original_file:
-                    # For consumed and added document is not yet saved, so pass the original file
-                    attachments = [
-                        ConsumableDocument(
-                            source=DocumentSource.ApiUpload,
-                            original_file=original_file,
-                        ),
-                    ]
+                    friendly_name = (
+                        Path(current_filename).name
+                        if current_filename
+                        else original_file.name
+                    )
+                    attachment = EmailAttachment(
+                        path=original_file,
+                        mime_type=document.mime_type,
+                        friendly_name=friendly_name,
+                    )
+                if attachment:
+                    attachments = [attachment]
             n_messages = send_email(
                 subject=subject,
                 body=body,
                 to=action.email.to.split(","),
                 attachments=attachments,
-                use_archive=False,
             )
             logger.debug(
                 f"Sent {n_messages} notification email(s) to {action.email.to}",
@@ -1199,7 +1214,9 @@ def run_workflows(
     def webhook_action():
         if not use_overrides:
             title = document.title
-            doc_url = f"{settings.PAPERLESS_URL}/documents/{document.pk}/"
+            doc_url = (
+                f"{settings.PAPERLESS_URL}{settings.BASE_URL}documents/{document.pk}/"
+            )
             correspondent = (
                 document.correspondent.name if document.correspondent else ""
             )

src/documents/tests/test_api_documents.py

@@ -941,6 +941,23 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
         results = response.data["results"]
         self.assertEqual(len(results), 0)
 
+    def test_documents_title_content_filter_strips_boundary_whitespace(self):
+        doc = Document.objects.create(
+            title="Testwort",
+            content="",
+            checksum="A",
+            mime_type="application/pdf",
+        )
+
+        response = self.client.get(
+            "/api/documents/",
+            {"title_content": " Testwort "},
+        )
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        results = response.data["results"]
+        self.assertEqual(len(results), 1)
+        self.assertEqual(results[0]["id"], doc.id)
+
     def test_document_permissions_filters(self):
         """
         GIVEN:

src/documents/tests/test_workflows.py

@@ -8,8 +8,10 @@ from typing import TYPE_CHECKING
 from unittest import mock
 
 import pytest
+from django.conf import settings
 from django.contrib.auth.models import Group
 from django.contrib.auth.models import User
+from django.core import mail
 from django.test import override_settings
 from django.utils import timezone
 from guardian.shortcuts import assign_perm
@@ -21,6 +23,8 @@ from pytest_httpx import HTTPXMock
 from rest_framework.test import APIClient
 from rest_framework.test import APITestCase
 
+from documents.file_handling import create_source_path_directory
+from documents.file_handling import generate_unique_filename
 from documents.signals.handlers import run_workflows
 from documents.signals.handlers import send_webhook
 
@@ -2989,6 +2993,70 @@ class TestWorkflows(
 
         mock_email_send.assert_called_once()
 
+    @override_settings(
+        PAPERLESS_EMAIL_HOST="localhost",
+        EMAIL_ENABLED=True,
+        PAPERLESS_URL="http://localhost:8000",
+        EMAIL_BACKEND="django.core.mail.backends.locmem.EmailBackend",
+    )
+    def test_workflow_email_attachment_uses_storage_filename(self):
+        """
+        GIVEN:
+            - Document updated workflow with include document action
+            - Document stored with formatted storage-path filename
+        WHEN:
+            - Workflow sends an email
+        THEN:
+            - Attachment filename matches the stored filename
+        """
+
+        trigger = WorkflowTrigger.objects.create(
+            type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
+        )
+        email_action = WorkflowActionEmail.objects.create(
+            subject="Test Notification: {doc_title}",
+            body="Test message: {doc_url}",
+            to="me@example.com",
+            include_document=True,
+        )
+        action = WorkflowAction.objects.create(
+            type=WorkflowAction.WorkflowActionType.EMAIL,
+            email=email_action,
+        )
+        workflow = Workflow.objects.create(
+            name="Workflow attachment filename",
+            order=0,
+        )
+        workflow.triggers.add(trigger)
+        workflow.actions.add(action)
+        workflow.save()
+
+        storage_path = StoragePath.objects.create(
+            name="Fancy Path",
+            path="formatted/{{ document.pk }}/{{ title }}",
+        )
+        doc = Document.objects.create(
+            title="workflow doc",
+            correspondent=self.c,
+            checksum="workflow-email-attachment",
+            mime_type="application/pdf",
+            storage_path=storage_path,
+            original_filename="workflow-orig.pdf",
+        )
+
+        # eg what happens in update_filename_and_move_files
+        generated = generate_unique_filename(doc)
+        destination = (settings.ORIGINALS_DIR / generated).resolve()
+        create_source_path_directory(destination)
+        shutil.copy(self.SAMPLE_DIR / "simple.pdf", destination)
+        Document.objects.filter(pk=doc.pk).update(filename=generated.as_posix())
+
+        run_workflows(WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED, doc)
+
+        self.assertEqual(len(mail.outbox), 1)
+        attachment_names = [att[0] for att in mail.outbox[0].attachments]
+        self.assertEqual(attachment_names, [Path(generated).name])
+
     @override_settings(
         EMAIL_ENABLED=False,
     )
@@ -3144,6 +3212,8 @@ class TestWorkflows(
 
     @override_settings(
         PAPERLESS_URL="http://localhost:8000",
+        PAPERLESS_FORCE_SCRIPT_NAME="/paperless",
+        BASE_URL="/paperless/",
     )
     @mock.patch("documents.signals.handlers.send_webhook.delay")
     def test_workflow_webhook_action_body(self, mock_post):
@@ -3195,7 +3265,7 @@ class TestWorkflows(
 
         mock_post.assert_called_once_with(
             url="http://paperless-ngx.com",
-            data=f"Test message: http://localhost:8000/documents/{doc.id}/",
+            data=f"Test message: http://localhost:8000/paperless/documents/{doc.id}/",
             headers={},
             files=None,
             as_json=False,

src/documents/views.py

@@ -120,6 +120,7 @@ from documents.filters import PaperlessTaskFilterSet
 from documents.filters import ShareLinkFilterSet
 from documents.filters import StoragePathFilterSet
 from documents.filters import TagFilterSet
+from documents.mail import EmailAttachment
 from documents.mail import send_email
 from documents.matching import match_correspondents
 from documents.matching import match_document_types
@@ -1216,12 +1217,28 @@ class DocumentViewSet(
                 return HttpResponseForbidden("Insufficient permissions")
 
         try:
+            attachments: list[EmailAttachment] = []
+            for doc in documents:
+                attachment_path = (
+                    doc.archive_path
+                    if use_archive_version and doc.has_archive_version
+                    else doc.source_path
+                )
+                attachments.append(
+                    EmailAttachment(
+                        path=attachment_path,
+                        mime_type=doc.mime_type,
+                        friendly_name=doc.get_public_filename(
+                            archive=use_archive_version and doc.has_archive_version,
+                        ),
+                    ),
+                )
+
             send_email(
                 subject=subject,
                 body=message,
                 to=addresses,
-                attachments=documents,
-                use_archive=use_archive_version,
+                attachments=attachments,
             )
 
             logger.debug(
@@ -1863,7 +1880,7 @@ class SearchAutoCompleteView(GenericAPIView):
         user = self.request.user if hasattr(self.request, "user") else None
 
         if "term" in request.query_params:
-            term = request.query_params["term"]
+            term = request.query_params["term"].strip()
         else:
             return HttpResponseBadRequest("Term required")
 

src/locale/en_US/LC_MESSAGES/django.po

@@ -2,7 +2,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: paperless-ngx\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2025-10-28 18:06+0000\n"
+"POT-Creation-Date: 2025-11-14 16:09+0000\n"
 "PO-Revision-Date: 2022-02-17 04:17\n"
 "Last-Translator: \n"
 "Language-Team: English\n"
@@ -21,39 +21,39 @@ msgstr ""
 msgid "Documents"
 msgstr ""
 
-#: documents/filters.py:392
+#: documents/filters.py:395
 msgid "Value must be valid JSON."
 msgstr ""
 
-#: documents/filters.py:411
+#: documents/filters.py:414
 msgid "Invalid custom field query expression"
 msgstr ""
 
-#: documents/filters.py:421
+#: documents/filters.py:424
 msgid "Invalid expression list. Must be nonempty."
 msgstr ""
 
-#: documents/filters.py:442
+#: documents/filters.py:445
 msgid "Invalid logical operator {op!r}"
 msgstr ""
 
-#: documents/filters.py:456
+#: documents/filters.py:459
 msgid "Maximum number of query conditions exceeded."
 msgstr ""
 
-#: documents/filters.py:521
+#: documents/filters.py:524
 msgid "{name!r} is not a valid custom field."
 msgstr ""
 
-#: documents/filters.py:558
+#: documents/filters.py:561
 msgid "{data_type} does not support query expr {expr!r}."
 msgstr ""
 
-#: documents/filters.py:666 documents/models.py:135
+#: documents/filters.py:669 documents/models.py:135
 msgid "Maximum nesting depth exceeded."
 msgstr ""
 
-#: documents/filters.py:851
+#: documents/filters.py:854
 msgid "Custom field not found"
 msgstr ""
 

src/paperless_mail/tests/test_parsers_live.py

@@ -2,6 +2,7 @@ import os
 import shutil
 import subprocess
 import tempfile
+import time
 from pathlib import Path
 
 import httpx
@@ -53,14 +54,33 @@ class TestUrlCanary:
     Verify certain URLs are still available so testing is valid still
     """
 
-    # Wikimedia rejects requests without a browser-like User-Agent header and returns 403.
-    _WIKIMEDIA_HEADERS = {
-        "User-Agent": (
-            "Mozilla/5.0 (X11; Linux x86_64) "
-            "AppleWebKit/537.36 (KHTML, like Gecko) "
-            "Chrome/123.0.0.0 Safari/537.36"
-        ),
-    }
+    @classmethod
+    def _fetch_wikimedia(cls, url: str) -> httpx.Response:
+        """
+        Wikimedia occasionally throttles automated requests (HTTP 429). Retry a few
+        times with a short backoff so the tests stay stable, and skip if throttling
+        persists.
+        """
+        last_resp: httpx.Response | None = None
+        # Wikimedia rejects requests without a browser-like User-Agent header and returns 403.
+        headers = {
+            "User-Agent": (
+                "Mozilla/5.0 (X11; Linux x86_64) "
+                "AppleWebKit/537.36 (KHTML, like Gecko) "
+                "Chrome/123.0.0.0 Safari/537.36"
+            ),
+        }
+        for delay in (0, 1, 2):
+            resp = httpx.get(url, headers=headers, timeout=30.0)
+            if resp.status_code != httpx.codes.TOO_MANY_REQUESTS:
+                return resp
+            last_resp = resp
+            time.sleep(delay)
+
+        pytest.skip(
+            "Wikimedia throttled the canary request with HTTP 429; try rerunning later.",
+        )
+        return last_resp  # pragma: no cover
 
     def test_online_image_exception_on_not_available(self):
         """
@@ -76,11 +96,10 @@ class TestUrlCanary:
         whether this image stays online forever, so here we check if we can detect if is not
         available anymore.
         """
+        resp = self._fetch_wikimedia(
+            "https://upload.wikimedia.org/wikipedia/en/f/f7/nonexistent.png",
+        )
         with pytest.raises(httpx.HTTPStatusError) as exec_info:
-            resp = httpx.get(
-                "https://upload.wikimedia.org/wikipedia/en/f/f7/nonexistent.png",
-                headers=self._WIKIMEDIA_HEADERS,
-            )
             resp.raise_for_status()
 
         assert exec_info.value.response.status_code == httpx.codes.NOT_FOUND
@@ -100,9 +119,8 @@ class TestUrlCanary:
         """
 
         # Now check the URL used in samples/sample.html
-        resp = httpx.get(
+        resp = self._fetch_wikimedia(
             "https://upload.wikimedia.org/wikipedia/en/f/f7/RickRoll.png",
-            headers=self._WIKIMEDIA_HEADERS,
         )
         resp.raise_for_status()