From d64818b46cc29e08da16a84fd944bb323e498c58 Mon Sep 17 00:00:00 2001 From: jonaswinkler <17569239+jonaswinkler@users.noreply.github.com> Date: Mon, 22 Feb 2021 11:11:04 +0100 Subject: [PATCH] fixes #591 --- .../management/commands/document_archiver.py | 12 +++++++++--- src/documents/tests/test_management.py | 15 +++++++++++++++ 2 files changed, 24 insertions(+), 3 deletions(-) diff --git a/src/documents/management/commands/document_archiver.py b/src/documents/management/commands/document_archiver.py index 0d3a5e82d..6a6056ed7 100644 --- a/src/documents/management/commands/document_archiver.py +++ b/src/documents/management/commands/document_archiver.py @@ -31,6 +31,11 @@ def handle_document(document_id): parser_class = get_parser_class_for_mime_type(mime_type) + if not parser_class: + logger.error(f"No parser found for mime type {mime_type}, cannot " + f"archive document {document} (ID: {document_id})") + return + parser = parser_class(logging_group=uuid.uuid4()) try: @@ -66,11 +71,12 @@ def handle_document(document_id): document.archive_path) shutil.move(thumbnail, document.thumbnail_path) - with AsyncWriter(index.open_index()) as writer: - index.update_document(writer, document) + with index.open_index_writer() as writer: + index.update_document(writer, document) except Exception as e: - logger.exception(f"Error while parsing document {document}") + logger.exception(f"Error while parsing document {document} " + f"(ID: {document_id})") finally: parser.cleanup() diff --git a/src/documents/tests/test_management.py b/src/documents/tests/test_management.py index 40eaaf277..f7beb8907 100644 --- a/src/documents/tests/test_management.py +++ b/src/documents/tests/test_management.py @@ -49,6 +49,21 @@ class TestArchiver(DirectoriesMixin, TestCase): self.assertTrue(filecmp.cmp(sample_file, doc.source_path)) self.assertEqual(doc.archive_filename, "none/A.pdf") + def test_unknown_mime_type(self): + doc = self.make_models() + doc.mime_type = "sdgfh" + doc.save() + shutil.copy(sample_file, doc.source_path) + + handle_document(doc.pk) + + doc = Document.objects.get(id=doc.id) + + self.assertIsNotNone(doc.checksum) + self.assertIsNone(doc.archive_checksum) + self.assertIsNone(doc.archive_filename) + self.assertTrue(os.path.isfile(doc.source_path)) + @override_settings(PAPERLESS_FILENAME_FORMAT="{title}") def test_naming_priorities(self): doc1 = Document.objects.create(checksum="A", title="document", content="first document", mime_type="application/pdf", filename="document.pdf")