Chore: Bulk backend dependency updates (#8212)

src/documents/tests/test_api_status.py

@@ -243,21 +243,29 @@ class TestSystemStatus(APITestCase):
         THEN:
             - The response contains an ERROR classifier status
         """
-        does_exist = tempfile.NamedTemporaryFile(
-            dir="/tmp",
-            delete=False,
-        )
-        with override_settings(MODEL_FILE=does_exist):
+        with (
+            tempfile.NamedTemporaryFile(
+                dir="/tmp",
+                delete=False,
+            ) as does_exist,
+            override_settings(MODEL_FILE=does_exist),
+        ):
             with mock.patch("documents.classifier.load_classifier") as mock_load:
                 mock_load.side_effect = ClassifierModelCorruptError()
                 Document.objects.create(
                     title="Test Document",
                 )
-                Tag.objects.create(name="Test Tag", matching_algorithm=Tag.MATCH_AUTO)
+                Tag.objects.create(
+                    name="Test Tag",
+                    matching_algorithm=Tag.MATCH_AUTO,
+                )
                 self.client.force_login(self.user)
                 response = self.client.get(self.ENDPOINT)
                 self.assertEqual(response.status_code, status.HTTP_200_OK)
-                self.assertEqual(response.data["tasks"]["classifier_status"], "ERROR")
+                self.assertEqual(
+                    response.data["tasks"]["classifier_status"],
+                    "ERROR",
+                )
                 self.assertIsNotNone(response.data["tasks"]["classifier_error"])
 
     def test_system_status_classifier_ok_no_objects(self):

src/documents/views.py

@@ -1499,7 +1499,7 @@ class BulkDownloadView(GenericAPIView):
         follow_filename_format = serializer.validated_data.get("follow_formatting")
 
         settings.SCRATCH_DIR.mkdir(parents=True, exist_ok=True)
-        temp = tempfile.NamedTemporaryFile(
+        temp = tempfile.NamedTemporaryFile(  # noqa: SIM115
             dir=settings.SCRATCH_DIR,
             suffix="-compressed-archive",
             delete=False,
@@ -1517,6 +1517,7 @@ class BulkDownloadView(GenericAPIView):
             for document in Document.objects.filter(pk__in=ids):
                 strategy.add_document(document)
 
+        # TODO(stumpylog): Investigate using FileResponse here
         with open(temp.name, "rb") as f:
             response = HttpResponse(f, content_type="application/zip")
             response["Content-Disposition"] = '{}; filename="{}"'.format(

src/paperless_tesseract/parsers.py

@@ -365,6 +365,7 @@ class RasterisedDocumentParser(DocumentParser):
         from ocrmypdf import EncryptedPdfError
         from ocrmypdf import InputFileError
         from ocrmypdf import SubprocessOutputError
+        from ocrmypdf.exceptions import DigitalSignatureError
 
         archive_path = Path(os.path.join(self.tempdir, "archive.pdf"))
         sidecar_file = Path(os.path.join(self.tempdir, "sidecar.txt"))
@@ -387,9 +388,9 @@ class RasterisedDocumentParser(DocumentParser):
 
             if not self.text:
                 raise NoTextFoundException("No text was found in the original document")
-        except EncryptedPdfError:
+        except (DigitalSignatureError, EncryptedPdfError):
             self.log.warning(
-                "This file is encrypted, OCR is impossible. Using "
+                "This file is encrypted and/or signed, OCR is impossible. Using "
                 "any text present in the original file.",
             )
             if original_has_text: