Fix: ensure django setup is run for management comments under 3.14

docs/configuration.md

@@ -1209,6 +1209,14 @@ left unassigned, preventing low-confidence guesses from being applied.
 
     Defaults to 0.6.
 
+#### [`PAPERLESS_MATCH_REGEX_TIMEOUT_SECONDS=<float>`](#PAPERLESS_MATCH_REGEX_TIMEOUT_SECONDS) {#PAPERLESS_MATCH_REGEX_TIMEOUT_SECONDS}
+
+: Sets the timeout, in seconds, for regular expression matching. Increase this
+value if date parsing or user-defined matching rules time out when processing
+long documents, especially on slower hardware.
+
+    Defaults to 0.1 seconds.
+
 #### [`PAPERLESS_DATE_PARSER_LANGUAGES=<lang>`](#PAPERLESS_DATE_PARSER_LANGUAGES) {#PAPERLESS_DATE_PARSER_LANGUAGES}
 
 : Specifies which language Paperless should use when parsing dates from documents.

src/documents/bulk_edit.py

@@ -899,17 +899,26 @@ def edit_pdf(
     pdf_docs: list[pikepdf.Pdf] = []
 
     try:
+        if not operations:
+            raise ValueError("Output document index is out of bounds")
+
+        max_idx = max(op.get("doc", 0) for op in operations)
+        if update_document and max_idx > 0:
+            logger.error(
+                "Update requested but multiple output documents specified",
+            )
+            raise ValueError("Multiple output documents specified")
+
+        if any(
+            op.get("doc", 0) < 0 or op.get("doc", 0) >= len(operations)
+            for op in operations
+        ):
+            raise ValueError("Output document index is out of bounds")
+
         with pikepdf.open(pair.source_doc.source_path) as src:
             # prepare output documents
-            max_idx = max(op.get("doc", 0) for op in operations)
             pdf_docs = [pikepdf.new() for _ in range(max_idx + 1)]
 
-            if update_document and len(pdf_docs) > 1:
-                logger.error(
-                    "Update requested but multiple output documents specified",
-                )
-                raise ValueError("Multiple output documents specified")
-
             for op in operations:
                 dst = pdf_docs[op.get("doc", 0)]
                 page = src.pages[op["page"] - 1]

src/documents/management/commands/base.py

@@ -21,6 +21,7 @@ from typing import ClassVar
 from typing import Generic
 from typing import TypeVar
 
+import django
 from django import db
 from django.core.management import CommandError
 from django.db.models import QuerySet
@@ -534,7 +535,10 @@ class PaperlessCommand(RichCommand):
         with self._create_progress(description) as progress:
             task_id = progress.add_task(description, total=total)
 
-            with ProcessPoolExecutor(max_workers=self.process_count) as executor:
+            with ProcessPoolExecutor(
+                max_workers=self.process_count,
+                initializer=django.setup,
+            ) as executor:
                 # Submit all tasks and map futures back to items
                 future_to_item = {executor.submit(fn, item): item for item in items}
 

src/documents/serialisers.py

@@ -210,9 +210,6 @@ class MatchingModelSerializer(serializers.ModelSerializer[Any]):
         return match
 
 
-PERMISSION_ACTIONS = ("view", "change")
-
-
 class SetPermissionsMixin:
     def _validate_user_ids(self, user_ids):
         users = User.objects.none()
@@ -235,9 +232,12 @@ class SetPermissionsMixin:
         return groups
 
     def validate_set_permissions(self, set_permissions=None):
-        permissions_dict = {action: {} for action in PERMISSION_ACTIONS}
+        permissions_dict = {
+            "view": {},
+            "change": {},
+        }
         if set_permissions is not None:
-            for action in PERMISSION_ACTIONS:
+            for action in ["view", "change"]:
                 if action in set_permissions:
                     if "users" in set_permissions[action]:
                         users = set_permissions[action]["users"]
@@ -265,31 +265,41 @@ class SerializerWithPerms(serializers.Serializer[dict[str, Any]]):
         super().__init__(*args, **kwargs)
 
 
-class _PermissionSetSerializer(serializers.Serializer[dict[str, Any]]):
-    users = serializers.ListField(
-        child=serializers.IntegerField(),
-        required=False,
-        allow_null=True,
-    )
-    groups = serializers.ListField(
-        child=serializers.IntegerField(),
-        required=False,
-        allow_null=True,
-    )
-
-
-class SetPermissionsSerializer(serializers.Serializer[dict[str, Any]]):
-    view = _PermissionSetSerializer(required=False)
-    change = _PermissionSetSerializer(required=False)
-
-    def to_internal_value(self, data):
-        if isinstance(data, dict):
-            unknown_keys = set(data) - set(PERMISSION_ACTIONS)
-            if unknown_keys:
-                raise serializers.ValidationError(
-                    {key: "Unknown permission action." for key in sorted(unknown_keys)},
-                )
-        return super().to_internal_value(data)
+@extend_schema_field(
+    field={
+        "type": "object",
+        "properties": {
+            "view": {
+                "type": "object",
+                "properties": {
+                    "users": {
+                        "type": "array",
+                        "items": {"type": "integer"},
+                    },
+                    "groups": {
+                        "type": "array",
+                        "items": {"type": "integer"},
+                    },
+                },
+            },
+            "change": {
+                "type": "object",
+                "properties": {
+                    "users": {
+                        "type": "array",
+                        "items": {"type": "integer"},
+                    },
+                    "groups": {
+                        "type": "array",
+                        "items": {"type": "integer"},
+                    },
+                },
+            },
+        },
+    },
+)
+class SetPermissionsSerializer(serializers.DictField):
+    pass
 
 
 class OwnedObjectSerializer(
@@ -460,6 +470,7 @@ class OwnedObjectSerializer(
 
     set_permissions = SetPermissionsSerializer(
         label="Set permissions",
+        allow_empty=True,
         required=False,
         write_only=True,
     )
@@ -1739,7 +1750,7 @@ class MergeDocumentsAsVersionsSerializer(DocumentListSerializer):
 
 
 class EditPdfDocumentsSerializer(DocumentListSerializer, SourceModeValidationMixin):
-    operations = serializers.ListField(required=True)
+    operations = serializers.ListField(required=True, allow_empty=False)
     delete_original = serializers.BooleanField(required=False, default=False)
     update_document = serializers.BooleanField(required=False, default=False)
     include_metadata = serializers.BooleanField(required=False, default=True)
@@ -1777,6 +1788,12 @@ class EditPdfDocumentsSerializer(DocumentListSerializer, SourceModeValidationMix
                     "update_document only allowed with a single output document",
                 )
 
+        if any(
+            op.get("doc", 0) < 0 or op.get("doc", 0) >= len(operations)
+            for op in operations
+        ):
+            raise serializers.ValidationError("doc index is out of bounds")
+
         doc = Document.objects.get(id=documents[0])
         if doc.page_count:
             for op in operations:
@@ -2034,13 +2051,8 @@ class BulkEditSerializer(
     def _validate_parameters_set_permissions(self, parameters) -> None:
         if "set_permissions" not in parameters:
             raise serializers.ValidationError("set_permissions not specified")
-        set_permissions = parameters["set_permissions"]
-        if set_permissions is not None:
-            set_permissions = SetPermissionsSerializer().run_validation(
-                set_permissions,
-            )
         parameters["set_permissions"] = self.validate_set_permissions(
-            set_permissions,
+            parameters["set_permissions"],
         )
         if "owner" in parameters and parameters["owner"] is not None:
             self._validate_owner(parameters["owner"])
@@ -2118,6 +2130,8 @@ class BulkEditSerializer(
             raise serializers.ValidationError("operations not specified")
         if not isinstance(parameters["operations"], list):
             raise serializers.ValidationError("operations must be a list")
+        if not parameters["operations"]:
+            raise serializers.ValidationError("operations must not be empty")
         for op in parameters["operations"]:
             if not isinstance(op, dict):
                 raise serializers.ValidationError("invalid operation entry")
@@ -2145,6 +2159,12 @@ class BulkEditSerializer(
                     "update_document only allowed with a single output document",
                 )
 
+        if any(
+            op.get("doc", 0) < 0 or op.get("doc", 0) >= len(parameters["operations"])
+            for op in parameters["operations"]
+        ):
+            raise serializers.ValidationError("doc index is out of bounds")
+
         doc = Document.objects.get(id=document_id)
         # doc existence is already validated
         if doc.page_count:
@@ -2995,8 +3015,9 @@ class BulkEditObjectsSerializer(SerializerWithPerms, SetPermissionsMixin):
         allow_null=True,
     )
 
-    permissions = SetPermissionsSerializer(
+    permissions = serializers.DictField(
         label="Set permissions",
+        allow_empty=False,
         required=False,
         write_only=True,
     )
@@ -3032,8 +3053,8 @@ class BulkEditObjectsSerializer(SerializerWithPerms, SetPermissionsMixin):
             )
         return objects
 
-    def _validate_permissions(self, permissions) -> dict:
-        return self.validate_set_permissions(
+    def _validate_permissions(self, permissions) -> None:
+        self.validate_set_permissions(
             permissions,
         )
 
@@ -3057,11 +3078,7 @@ class BulkEditObjectsSerializer(SerializerWithPerms, SetPermissionsMixin):
         if operation == "set_permissions":
             permissions = attrs.get("permissions")
             if permissions is not None:
-                if not permissions:
-                    raise serializers.ValidationError(
-                        "permissions must not be empty",
-                    )
-                attrs["permissions"] = self._validate_permissions(permissions)
+                self._validate_permissions(permissions)
 
         return attrs
 

src/documents/signals/handlers.py

@@ -1189,13 +1189,18 @@ def before_task_publish_handler(
         trigger_source = _determine_trigger_source(headers)
         owner_id = _extract_owner_id(task_type, task_kwargs)
 
-        PaperlessTask.objects.create(
+        # A retried task is republished with the same task_id, so this fires
+        # again for it; get_or_create keeps the original PENDING record
+        # instead of raising a duplicate-key IntegrityError on the retry.
+        PaperlessTask.objects.get_or_create(
             task_id=task_id,
-            task_type=task_type,
-            trigger_source=trigger_source,
-            status=PaperlessTask.Status.PENDING,
-            input_data=input_data,
-            owner_id=owner_id,
+            defaults={
+                "task_type": task_type,
+                "trigger_source": trigger_source,
+                "status": PaperlessTask.Status.PENDING,
+                "input_data": input_data,
+                "owner_id": owner_id,
+            },
         )
     except Exception:  # pragma: no cover
         logger.exception("Creating PaperlessTask failed")

src/documents/tests/test_api_bulk_edit.py

@@ -1165,98 +1165,6 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertIn(b"set_permissions not specified", response.content)
         m.assert_not_called()
 
-    @mock.patch("documents.serialisers.bulk_edit.set_permissions")
-    def test_set_permissions_rejects_non_dict_value(self, m) -> None:
-        self.setup_mock(m, "set_permissions")
-
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "method": "set_permissions",
-                    "parameters": {"set_permissions": False},
-                },
-            ),
-            content_type="application/json",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(b"Expected a dictionary", response.content)
-        m.assert_not_called()
-
-    @mock.patch("documents.serialisers.bulk_edit.set_permissions")
-    def test_set_permissions_rejects_non_list_users(self, m) -> None:
-        self.setup_mock(m, "set_permissions")
-
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "method": "set_permissions",
-                    "parameters": {
-                        "set_permissions": {"view": {"users": False}},
-                    },
-                },
-            ),
-            content_type="application/json",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(b"Expected a list", response.content)
-        m.assert_not_called()
-
-    @mock.patch("documents.serialisers.bulk_edit.set_permissions")
-    def test_set_permissions_rejects_unknown_action(self, m) -> None:
-        self.setup_mock(m, "set_permissions")
-
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "method": "set_permissions",
-                    "parameters": {
-                        "set_permissions": {"not_a_real_action": {"users": [1]}},
-                    },
-                },
-            ),
-            content_type="application/json",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(b"Unknown permission action", response.content)
-        m.assert_not_called()
-
-    @mock.patch("documents.serialisers.bulk_edit.set_permissions")
-    def test_set_permissions_null_is_a_noop(self, m) -> None:
-        """
-        A `set_permissions: null` value is a deliberate no-op (e.g. a
-        request that only updates `owner`), not a validation error --
-        this must keep working even though every other non-dict value is
-        now rejected.
-        """
-        self.setup_mock(m, "set_permissions")
-
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "method": "set_permissions",
-                    "parameters": {
-                        "set_permissions": None,
-                        "owner": self.user.id,
-                    },
-                },
-            ),
-            content_type="application/json",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_200_OK)
-        m.assert_called_once()
-
     @mock.patch("documents.serialisers.bulk_edit.set_permissions")
     def test_set_permissions_merge(self, m) -> None:
         self.setup_mock(m, "set_permissions")
@@ -1392,7 +1300,7 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.client.force_authenticate(user=user1)
 
         permissions = {
-            "view": {"users": [user1.id]},
+            "owner": user1.id,
         }
 
         response = self.client.post(
@@ -1741,6 +1649,40 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
 
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
 
+    def test_legacy_bulk_edit_rejects_out_of_bounds_pdf_doc_index(self) -> None:
+        response = self.client.post(
+            "/api/documents/bulk_edit/",
+            json.dumps(
+                {
+                    "documents": [self.doc2.id],
+                    "method": "edit_pdf",
+                    "parameters": {
+                        "operations": [{"page": 1, "doc": 2**32}],
+                    },
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertIn(b"doc index is out of bounds", response.content)
+
+    def test_legacy_bulk_edit_rejects_empty_pdf_operations(self) -> None:
+        response = self.client.post(
+            "/api/documents/bulk_edit/",
+            json.dumps(
+                {
+                    "documents": [self.doc2.id],
+                    "method": "edit_pdf",
+                    "parameters": {"operations": []},
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertIn(b"operations must not be empty", response.content)
+
     @mock.patch("documents.views.bulk_edit.edit_pdf")
     def test_edit_pdf(self, m) -> None:
         self.setup_mock(m, "edit_pdf")
@@ -1791,6 +1733,13 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
         self.assertIn(b"Expected a list of items", response.content)
 
+        response = self.client.post(
+            "/api/documents/edit_pdf/",
+            {"documents": [self.doc2.id], "operations": []},
+            format="json",
+        )
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+
         response = self.client.post(
             "/api/documents/edit_pdf/",
             json.dumps(
@@ -1843,6 +1792,21 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
         self.assertIn(b"doc must be an integer", response.content)
 
+        for doc_index in (-1, 2**32):
+            with self.subTest(doc_index=doc_index):
+                response = self.client.post(
+                    "/api/documents/edit_pdf/",
+                    json.dumps(
+                        {
+                            "documents": [self.doc2.id],
+                            "operations": [{"page": 1, "doc": doc_index}],
+                        },
+                    ),
+                    content_type="application/json",
+                )
+                self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+                self.assertIn(b"doc index is out of bounds", response.content)
+
         response = self.client.post(
             "/api/documents/edit_pdf/",
             json.dumps(

src/documents/tests/test_api_permissions.py

@@ -1499,109 +1499,6 @@ class TestBulkEditObjectPermissions(APITestCase):
         self.assertEqual(response.status_code, status.HTTP_403_FORBIDDEN)
         self.assertTrue(Tag.objects.filter(pk=self.t1.id).exists())
 
-    def test_bulk_object_set_permissions_rejects_empty_permissions(self) -> None:
-        """
-        GIVEN:
-            - Existing objects
-        WHEN:
-            - bulk_edit_objects API endpoint is called with set_permissions
-              operation and an empty permissions dict
-        THEN:
-            - Validation fails rather than silently applying a no-op
-        """
-        response = self.client.post(
-            "/api/bulk_edit_objects/",
-            json.dumps(
-                {
-                    "objects": [self.t1.id],
-                    "object_type": "tags",
-                    "operation": "set_permissions",
-                    "permissions": {},
-                },
-            ),
-            content_type="application/json",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-
-    def test_bulk_object_set_permissions_rejects_non_dict_permissions(self) -> None:
-        """
-        GIVEN:
-            - Existing objects
-        WHEN:
-            - bulk_edit_objects API endpoint is called with set_permissions
-              operation and a non-dict permissions value
-        THEN:
-            - Validation fails rather than crashing
-        """
-        response = self.client.post(
-            "/api/bulk_edit_objects/",
-            json.dumps(
-                {
-                    "objects": [self.t1.id],
-                    "object_type": "tags",
-                    "operation": "set_permissions",
-                    "permissions": False,
-                },
-            ),
-            content_type="application/json",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-
-    def test_bulk_object_set_permissions_rejects_unknown_action(self) -> None:
-        """
-        GIVEN:
-            - Existing objects
-        WHEN:
-            - bulk_edit_objects API endpoint is called with set_permissions
-              operation and an unrecognized permission action name
-        THEN:
-            - Validation fails rather than silently no-oping
-        """
-        response = self.client.post(
-            "/api/bulk_edit_objects/",
-            json.dumps(
-                {
-                    "objects": [self.t1.id],
-                    "object_type": "tags",
-                    "operation": "set_permissions",
-                    "permissions": {"not_a_real_action": {"users": [self.user1.id]}},
-                },
-            ),
-            content_type="application/json",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-
-    def test_bulk_object_set_permissions_null_users_is_a_noop(self) -> None:
-        """
-        GIVEN:
-            - Existing objects
-        WHEN:
-            - bulk_edit_objects API endpoint is called with set_permissions
-              operation and an explicit null for users/groups on an action
-        THEN:
-            - Request succeeds and is treated as "no users/groups for this
-              action", not a crash -- the normalized (id-checked) dict
-              returned by validate_set_permissions must actually be used,
-              not discarded in favor of the raw un-normalized input.
-        """
-        response = self.client.post(
-            "/api/bulk_edit_objects/",
-            json.dumps(
-                {
-                    "objects": [self.t1.id],
-                    "object_type": "tags",
-                    "operation": "set_permissions",
-                    "permissions": {"view": {"users": None}},
-                },
-            ),
-            content_type="application/json",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_200_OK)
-
     def test_bulk_edit_object_permissions_validation(self) -> None:
         """
         GIVEN:

src/documents/tests/test_bulk_edit.py

@@ -1642,6 +1642,16 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         mock_group.assert_not_called()
         mock_consume_file.assert_not_called()
 
+    @mock.patch("pikepdf.open")
+    def test_edit_pdf_rejects_invalid_operations(self, mock_open) -> None:
+        for operations in ([], [{"page": 1, "doc": 2**32}]):
+            with self.subTest(operations=operations):
+                with self.assertLogs("paperless.bulk_edit", level="ERROR"):
+                    with self.assertRaisesRegex(ValueError, "index is out of bounds"):
+                        bulk_edit.edit_pdf([self.doc2.id], operations)
+
+        mock_open.assert_not_called()
+
     @mock.patch("documents.bulk_edit.update_document_content_maybe_archive_file.delay")
     @mock.patch("documents.tasks.consume_file.apply_async")
     @mock.patch("documents.bulk_edit.tempfile.mkdtemp")

src/documents/tests/test_regex.py

@@ -1,5 +1,6 @@
 import pytest
 import regex
+from django.conf import settings
 from pytest_mock import MockerFixture
 
 from documents.regex import safe_regex_finditer
@@ -9,6 +10,12 @@ from documents.regex import safe_regex_sub
 from documents.regex import validate_regex_pattern
 
 
+def test_regex_timeout_uses_configured_setting() -> None:
+    from documents.regex import REGEX_TIMEOUT_SECONDS
+
+    assert REGEX_TIMEOUT_SECONDS == settings.MATCH_REGEX_TIMEOUT_SECONDS
+
+
 class TestValidateRegexPattern:
     def test_valid_pattern(self) -> None:
         validate_regex_pattern(r"\d+")

src/documents/tests/test_task_signals.py

@@ -106,6 +106,17 @@ class TestBeforeTaskPublishHandler:
         assert task.task_type == PaperlessTask.TaskType.TRAIN_CLASSIFIER
         assert task.trigger_source == PaperlessTask.TriggerSource.MANUAL
 
+        # A Celery retry republishes with the same task_id; this must not
+        # raise a duplicate-key IntegrityError, and must leave the original
+        # PENDING record alone.
+        send_publish(
+            "documents.tasks.train_classifier",
+            (),
+            {},
+            headers={"id": task_id},
+        )
+        assert PaperlessTask.objects.filter(task_id=task_id).count() == 1
+
     def test_creates_task_for_sanity_check(self) -> None:
         task_id = send_publish("documents.tasks.sanity_check", (), {})
         task = PaperlessTask.objects.get(task_id=task_id)

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: 2026-09-12 23:18+0000\n"
+"POT-Creation-Date: 2026-09-13 22:13+0000\n"
 "PO-Revision-Date: 2022-02-17 04:17\n"
 "Last-Translator: \n"
 "Language-Team: English\n"
@@ -1632,7 +1632,7 @@ msgid "workflow runs"
 msgstr ""
 
 #: documents/serialisers.py:525 documents/serialisers.py:882
-#: documents/serialisers.py:2854 documents/views.py:319 documents/views.py:2694
+#: documents/serialisers.py:2868 documents/views.py:319 documents/views.py:2694
 #: paperless_mail/serialisers.py:156
 msgid "Insufficient permissions."
 msgstr ""
@@ -1641,39 +1641,39 @@ msgstr ""
 msgid "Invalid color."
 msgstr ""
 
-#: documents/serialisers.py:2327
+#: documents/serialisers.py:2341
 #, python-format
 msgid "File type %(type)s not supported"
 msgstr ""
 
-#: documents/serialisers.py:2371
+#: documents/serialisers.py:2385
 #, python-format
 msgid "Custom field id must be an integer: %(id)s"
 msgstr ""
 
-#: documents/serialisers.py:2378
+#: documents/serialisers.py:2392
 #, python-format
 msgid "Custom field with id %(id)s does not exist"
 msgstr ""
 
-#: documents/serialisers.py:2395 documents/serialisers.py:2405
+#: documents/serialisers.py:2409 documents/serialisers.py:2419
 msgid ""
 "Custom fields must be a list of integers or an object mapping ids to values."
 msgstr ""
 
-#: documents/serialisers.py:2400
+#: documents/serialisers.py:2414
 msgid "Some custom fields don't exist or were specified twice."
 msgstr ""
 
-#: documents/serialisers.py:2547
+#: documents/serialisers.py:2561
 msgid "Invalid variable detected."
 msgstr ""
 
-#: documents/serialisers.py:2910
+#: documents/serialisers.py:2924
 msgid "Duplicate document identifiers are not allowed."
 msgstr ""
 
-#: documents/serialisers.py:2940 documents/views.py:4707
+#: documents/serialisers.py:2954 documents/views.py:4707
 #, python-format
 msgid "Documents not found: %(ids)s"
 msgstr ""
@@ -2258,151 +2258,151 @@ msgstr ""
 msgid "paperless application settings"
 msgstr ""
 
-#: paperless/settings/__init__.py:556
+#: paperless/settings/__init__.py:560
 msgid "English (US)"
 msgstr ""
 
-#: paperless/settings/__init__.py:557
+#: paperless/settings/__init__.py:561
 msgid "Arabic"
 msgstr ""
 
-#: paperless/settings/__init__.py:558
+#: paperless/settings/__init__.py:562
 msgid "Afrikaans"
 msgstr ""
 
-#: paperless/settings/__init__.py:559
+#: paperless/settings/__init__.py:563
 msgid "Belarusian"
 msgstr ""
 
-#: paperless/settings/__init__.py:560
+#: paperless/settings/__init__.py:564
 msgid "Bulgarian"
 msgstr ""
 
-#: paperless/settings/__init__.py:561
+#: paperless/settings/__init__.py:565
 msgid "Catalan"
 msgstr ""
 
-#: paperless/settings/__init__.py:562
+#: paperless/settings/__init__.py:566
 msgid "Czech"
 msgstr ""
 
-#: paperless/settings/__init__.py:563
+#: paperless/settings/__init__.py:567
 msgid "Danish"
 msgstr ""
 
-#: paperless/settings/__init__.py:564
+#: paperless/settings/__init__.py:568
 msgid "German"
 msgstr ""
 
-#: paperless/settings/__init__.py:565
+#: paperless/settings/__init__.py:569
 msgid "Greek"
 msgstr ""
 
-#: paperless/settings/__init__.py:566
+#: paperless/settings/__init__.py:570
 msgid "English (GB)"
 msgstr ""
 
-#: paperless/settings/__init__.py:567
+#: paperless/settings/__init__.py:571
 msgid "Spanish"
 msgstr ""
 
-#: paperless/settings/__init__.py:568
+#: paperless/settings/__init__.py:572
 msgid "Persian"
 msgstr ""
 
-#: paperless/settings/__init__.py:569
+#: paperless/settings/__init__.py:573
 msgid "Finnish"
 msgstr ""
 
-#: paperless/settings/__init__.py:570
+#: paperless/settings/__init__.py:574
 msgid "French"
 msgstr ""
 
-#: paperless/settings/__init__.py:571
+#: paperless/settings/__init__.py:575
 msgid "Hungarian"
 msgstr ""
 
-#: paperless/settings/__init__.py:572
+#: paperless/settings/__init__.py:576
 msgid "Indonesian"
 msgstr ""
 
-#: paperless/settings/__init__.py:573
+#: paperless/settings/__init__.py:577
 msgid "Italian"
 msgstr ""
 
-#: paperless/settings/__init__.py:574
+#: paperless/settings/__init__.py:578
 msgid "Japanese"
 msgstr ""
 
-#: paperless/settings/__init__.py:575
+#: paperless/settings/__init__.py:579
 msgid "Korean"
 msgstr ""
 
-#: paperless/settings/__init__.py:576
+#: paperless/settings/__init__.py:580
 msgid "Luxembourgish"
 msgstr ""
 
-#: paperless/settings/__init__.py:577
+#: paperless/settings/__init__.py:581
 msgid "Norwegian"
 msgstr ""
 
-#: paperless/settings/__init__.py:578
+#: paperless/settings/__init__.py:582
 msgid "Dutch"
 msgstr ""
 
-#: paperless/settings/__init__.py:579
+#: paperless/settings/__init__.py:583
 msgid "Polish"
 msgstr ""
 
-#: paperless/settings/__init__.py:580
+#: paperless/settings/__init__.py:584
 msgid "Portuguese (Brazil)"
 msgstr ""
 
-#: paperless/settings/__init__.py:581
+#: paperless/settings/__init__.py:585
 msgid "Portuguese"
 msgstr ""
 
-#: paperless/settings/__init__.py:582
+#: paperless/settings/__init__.py:586
 msgid "Romanian"
 msgstr ""
 
-#: paperless/settings/__init__.py:583
+#: paperless/settings/__init__.py:587
 msgid "Russian"
 msgstr ""
 
-#: paperless/settings/__init__.py:584
+#: paperless/settings/__init__.py:588
 msgid "Slovak"
 msgstr ""
 
-#: paperless/settings/__init__.py:585
+#: paperless/settings/__init__.py:589
 msgid "Slovenian"
 msgstr ""
 
-#: paperless/settings/__init__.py:586
+#: paperless/settings/__init__.py:590
 msgid "Serbian"
 msgstr ""
 
-#: paperless/settings/__init__.py:587
+#: paperless/settings/__init__.py:591
 msgid "Swedish"
 msgstr ""
 
-#: paperless/settings/__init__.py:588
+#: paperless/settings/__init__.py:592
 msgid "Turkish"
 msgstr ""
 
-#: paperless/settings/__init__.py:589
+#: paperless/settings/__init__.py:593
 msgid "Ukrainian"
 msgstr ""
 
-#: paperless/settings/__init__.py:590
+#: paperless/settings/__init__.py:594
 msgid "Vietnamese"
 msgstr ""
 
-#: paperless/settings/__init__.py:591
+#: paperless/settings/__init__.py:595
 msgid "Chinese Simplified"
 msgstr ""
 
-#: paperless/settings/__init__.py:592
+#: paperless/settings/__init__.py:596
 msgid "Chinese Traditional"
 msgstr ""
 

src/paperless/settings/__init__.py

@@ -102,6 +102,10 @@ CLASSIFIER_MATCH_THRESHOLD: Final[float] = get_float_from_env(
     "PAPERLESS_CLASSIFIER_MATCH_THRESHOLD",
     0.6,
 )
+MATCH_REGEX_TIMEOUT_SECONDS: Final[float] = get_float_from_env(
+    "PAPERLESS_MATCH_REGEX_TIMEOUT_SECONDS",
+    0.1,
+)
 LLM_INDEX_DIR = DATA_DIR / "llm_index"
 LLM_INDEX_LOCK = LLM_INDEX_DIR / "index.lock"
 # Cross-process read/write lock guarding the LLM index compaction/migration