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/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

@@ -1749,18 +1749,8 @@ class MergeDocumentsAsVersionsSerializer(DocumentListSerializer):
         return attrs
 
 
-class PdfEditOperationSerializer(serializers.Serializer[dict[str, int]]):
-    page = serializers.IntegerField(min_value=1)
-    rotate = serializers.IntegerField(required=False)
-    doc = serializers.IntegerField(required=False, min_value=0)
-
-
 class EditPdfDocumentsSerializer(DocumentListSerializer, SourceModeValidationMixin):
-    operations = serializers.ListField(
-        child=PdfEditOperationSerializer(),
-        required=True,
-        allow_empty=False,
-    )
+    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)
@@ -1778,9 +1768,18 @@ class EditPdfDocumentsSerializer(DocumentListSerializer, SourceModeValidationMix
             )
 
         operations = attrs["operations"]
+        if not isinstance(operations, list):
+            raise serializers.ValidationError("operations must be a list")
 
-        if any(op.get("doc", 0) >= len(operations) for op in operations):
-            raise serializers.ValidationError("doc index is out of bounds")
+        for op in operations:
+            if not isinstance(op, dict):
+                raise serializers.ValidationError("invalid operation entry")
+            if "page" not in op or not isinstance(op["page"], int):
+                raise serializers.ValidationError("page must be an integer")
+            if "rotate" in op and not isinstance(op["rotate"], int):
+                raise serializers.ValidationError("rotate must be an integer")
+            if "doc" in op and not isinstance(op["doc"], int):
+                raise serializers.ValidationError("doc must be an integer")
 
         if attrs["update_document"]:
             max_idx = max(op.get("doc", 0) for op in operations)
@@ -1789,10 +1788,16 @@ 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:
-                if op["page"] > doc.page_count:
+                if op["page"] < 1 or op["page"] > doc.page_count:
                     raise serializers.ValidationError(
                         f"Page {op['page']} is out of bounds for document with {doc.page_count} pages.",
                     )
@@ -2123,15 +2128,19 @@ class BulkEditSerializer(
     def _validate_parameters_edit_pdf(self, parameters, document_id) -> None:
         if "operations" not in parameters:
             raise serializers.ValidationError("operations not specified")
-        operations_field = serializers.ListField(
-            child=PdfEditOperationSerializer(),
-            allow_empty=False,
-        )
-        parameters["operations"] = operations_field.run_validation(
-            parameters["operations"],
-        )
-        operations = parameters["operations"]
-
+        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")
+            if "page" not in op or not isinstance(op["page"], int):
+                raise serializers.ValidationError("page must be an integer")
+            if "rotate" in op and not isinstance(op["rotate"], int):
+                raise serializers.ValidationError("rotate must be an integer")
+            if "doc" in op and not isinstance(op["doc"], int):
+                raise serializers.ValidationError("doc must be an integer")
         if "update_document" in parameters:
             if not isinstance(parameters["update_document"], bool):
                 raise serializers.ValidationError("update_document must be a boolean")
@@ -2143,21 +2152,24 @@ class BulkEditSerializer(
         else:
             parameters["include_metadata"] = True
 
-        if any(op.get("doc", 0) >= len(operations) for op in operations):
-            raise serializers.ValidationError("doc index is out of bounds")
-
         if parameters["update_document"]:
-            max_idx = max(op.get("doc", 0) for op in operations)
+            max_idx = max(op.get("doc", 0) for op in parameters["operations"])
             if max_idx > 0:
                 raise serializers.ValidationError(
                     "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:
-            for op in operations:
-                if op["page"] > doc.page_count:
+            for op in parameters["operations"]:
+                if op["page"] < 1 or op["page"] > doc.page_count:
                     raise serializers.ValidationError(
                         f"Page {op['page']} is out of bounds for document with {doc.page_count} pages.",
                     )

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

@@ -1667,6 +1667,22 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         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")
@@ -1717,6 +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(
@@ -1728,7 +1751,7 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
             content_type="application/json",
         )
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(b"Expected a dictionary", response.content)
+        self.assertIn(b"invalid operation entry", response.content)
 
         response = self.client.post(
             "/api/documents/edit_pdf/",
@@ -1741,7 +1764,7 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
             content_type="application/json",
         )
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(b"valid integer is required", response.content)
+        self.assertIn(b"page must be an integer", response.content)
 
         response = self.client.post(
             "/api/documents/edit_pdf/",
@@ -1754,7 +1777,7 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
             content_type="application/json",
         )
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(b"valid integer is required", response.content)
+        self.assertIn(b"rotate must be an integer", response.content)
 
         response = self.client.post(
             "/api/documents/edit_pdf/",
@@ -1767,16 +1790,9 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
             content_type="application/json",
         )
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(b"valid integer is required", response.content)
+        self.assertIn(b"doc must be an integer", response.content)
 
-        # A negative doc index is rejected by PdfEditOperationSerializer's
-        # own min_value=0 field constraint, before the "doc index is out
-        # of bounds" object-level check (against len(operations)) ever
-        # runs -- hence the different expected message per case.
-        for doc_index, expected_message in (
-            (-1, b"greater than or equal to 0"),
-            (2**32, b"doc index is out of bounds"),
-        ):
+        for doc_index in (-1, 2**32):
             with self.subTest(doc_index=doc_index):
                 response = self.client.post(
                     "/api/documents/edit_pdf/",
@@ -1789,7 +1805,7 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
                     content_type="application/json",
                 )
                 self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-                self.assertIn(expected_message, response.content)
+                self.assertIn(b"doc index is out of bounds", response.content)
 
         response = self.client.post(
             "/api/documents/edit_pdf/",
@@ -1797,7 +1813,7 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
                 {
                     "documents": [self.doc2.id],
                     "update_document": True,
-                    "operations": [{"page": 1, "doc": 0}, {"page": 2, "doc": 1}],
+                    "operations": [{"page": 1, "doc": 1}, {"page": 2, "doc": 2}],
                 },
             ),
             content_type="application/json",
@@ -1822,86 +1838,6 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
         self.assertIn(b"Invalid source_mode", response.content)
 
-    @mock.patch("documents.views.bulk_edit.edit_pdf")
-    def test_edit_pdf_rejects_empty_operations(self, m) -> None:
-        """
-        An empty operations list previously reached bulk_edit.edit_pdf()
-        and crashed with `ValueError: max() iterable argument is empty`
-        (via `max(op.get("doc", 0) for op in operations)`) whenever
-        update_document was true. Must now be rejected up front.
-        """
-        self.setup_mock(m, "edit_pdf")
-        response = self.client.post(
-            "/api/documents/edit_pdf/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "operations": [],
-                    "update_document": True,
-                },
-            ),
-            content_type="application/json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        m.assert_not_called()
-
-    @mock.patch("documents.views.bulk_edit.edit_pdf")
-    def test_edit_pdf_rejects_negative_doc_index(self, m) -> None:
-        """
-        A negative `doc` index was previously silently accepted and used
-        as a wrapping Python list index instead of being rejected.
-        """
-        self.setup_mock(m, "edit_pdf")
-        response = self.client.post(
-            "/api/documents/edit_pdf/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "operations": [{"page": 1, "doc": -1}],
-                },
-            ),
-            content_type="application/json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        m.assert_not_called()
-
-    @mock.patch("documents.views.bulk_edit.edit_pdf")
-    def test_edit_pdf_rejects_out_of_bounds_doc_index(self, m) -> None:
-        """
-        A `doc` index far larger than the number of operations previously
-        drove `pdf_docs = [pikepdf.new() for _ in range(max_idx + 1)]` to
-        attempt allocating an enormous number of real objects.
-        """
-        self.setup_mock(m, "edit_pdf")
-        response = self.client.post(
-            "/api/documents/edit_pdf/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "operations": [{"page": 1, "doc": 2**33}],
-                },
-            ),
-            content_type="application/json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        m.assert_not_called()
-
-    @mock.patch("documents.views.bulk_edit.edit_pdf")
-    def test_edit_pdf_rejects_non_positive_page(self, m) -> None:
-        self.setup_mock(m, "edit_pdf")
-        response = self.client.post(
-            "/api/documents/edit_pdf/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "operations": [{"page": 0}],
-                },
-            ),
-            content_type="application/json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        m.assert_not_called()
-
     @mock.patch("documents.views.bulk_edit.edit_pdf")
     def test_edit_pdf_page_out_of_bounds(self, m) -> None:
         self.setup_mock(m, "edit_pdf")
@@ -1919,46 +1855,6 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertIn(b"out of bounds", response.content)
         m.assert_not_called()
 
-    @mock.patch("documents.serialisers.bulk_edit.edit_pdf")
-    def test_bulk_edit_edit_pdf_rejects_empty_operations(self, m) -> None:
-        """
-        Same validation gap as test_edit_pdf_rejects_empty_operations, but
-        via the legacy generic /api/documents/bulk_edit/ method="edit_pdf"
-        path, which hand-parses `parameters["operations"]` independently
-        in BulkEditSerializer._validate_parameters_edit_pdf.
-        """
-        self.setup_mock(m, "edit_pdf")
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "method": "edit_pdf",
-                    "parameters": {"operations": [], "update_document": True},
-                },
-            ),
-            content_type="application/json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        m.assert_not_called()
-
-    @mock.patch("documents.serialisers.bulk_edit.edit_pdf")
-    def test_bulk_edit_edit_pdf_rejects_out_of_bounds_doc_index(self, m) -> None:
-        self.setup_mock(m, "edit_pdf")
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "method": "edit_pdf",
-                    "parameters": {"operations": [{"page": 1, "doc": 2**33}]},
-                },
-            ),
-            content_type="application/json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        m.assert_not_called()
-
     @mock.patch("documents.views.bulk_edit.edit_pdf")
     def test_edit_pdf_insufficient_permissions(self, m) -> None:
         self.doc1.owner = User.objects.get(username="temp_admin")

src/documents/tests/test_bulk_edit.py

@@ -1643,13 +1643,12 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         mock_consume_file.assert_not_called()
 
     @mock.patch("pikepdf.open")
-    def test_edit_pdf_rejects_out_of_bounds_output_index(self, mock_open) -> None:
-        with self.assertLogs("paperless.bulk_edit", level="ERROR"):
-            with self.assertRaisesRegex(ValueError, "index is out of bounds"):
-                bulk_edit.edit_pdf(
-                    [self.doc2.id],
-                    [{"page": 1, "doc": 2**32}],
-                )
+    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()
 

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