paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-02 13:45:10 -05:00
Code Issues Packages Projects Releases Wiki Activity

fixes #591

Browse Source
This commit is contained in:
jonaswinkler 2021-02-22 11:11:04 +01:00
parent 99a18516b2
commit d64818b46c
2 changed files with 24 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
src/documents/management/commands/document_archiver.py
View File

@ -31,6 +31,11 @@ def handle_document(document_id):
parser_class = get_parser_class_for_mime_type(mime_type) 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()) parser = parser_class(logging_group=uuid.uuid4())
try: try:
@ -66,11 +71,12 @@ def handle_document(document_id):
document.archive_path) document.archive_path)
shutil.move(thumbnail, document.thumbnail_path) shutil.move(thumbnail, document.thumbnail_path)
with AsyncWriter(index.open_index()) as writer: with index.open_index_writer() as writer:
index.update_document(writer, document) index.update_document(writer, document)
except Exception as e: 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: finally:
parser.cleanup() parser.cleanup()

15
src/documents/tests/test_management.py
View File

@ -49,6 +49,21 @@ class TestArchiver(DirectoriesMixin, TestCase):
self.assertTrue(filecmp.cmp(sample_file, doc.source_path)) self.assertTrue(filecmp.cmp(sample_file, doc.source_path))
self.assertEqual(doc.archive_filename, "none/A.pdf") 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}") @override_settings(PAPERLESS_FILENAME_FORMAT="{title}")
def test_naming_priorities(self): def test_naming_priorities(self):
doc1 = Document.objects.create(checksum="A", title="document", content="first document", mime_type="application/pdf", filename="document.pdf") doc1 = Document.objects.create(checksum="A", title="document", content="first document", mime_type="application/pdf", filename="document.pdf")