def _consume(filepath):
if os.path.isdir(filepath):
return
if not os.path.isfile(filepath):
logger.debug(f"Not consuming file {filepath}: File has moved.")
return
if not is_file_ext_supported(os.path.splitext(filepath)[1]):
logger.warning(
f"Not consuming file {filepath}: Unknown file extension.")
return
tag_ids = None
try:
if settings.CONSUMER_SUBDIRS_AS_TAGS:
tag_ids = _tags_from_path(filepath)
except Exception as e:
logger.error("Error creating tags from path: {}".format(e))
try:
async_task("documents.tasks.consume_file",
filepath,
override_tag_ids=tag_ids if tag_ids else None,
task_name=os.path.basename(filepath)[:100])
except Exception as e:
# Catch all so that the consumer won't crash.
# This is also what the test case is listening for to check for
# errors.
logger.error("Error while consuming document: {}".format(e))
def test_file_extensions(self):
for ext in [".pdf", ".jpe", ".jpg", ".jpeg", ".txt", ".csv"]:
self.assertIn(ext, get_supported_file_extensions())
self.assertEqual(get_default_file_extension('application/pdf'), ".pdf")
self.assertEqual(get_default_file_extension('image/png'), ".png")
self.assertEqual(get_default_file_extension('image/jpeg'), ".jpg")
self.assertEqual(get_default_file_extension('text/plain'), ".txt")
self.assertEqual(get_default_file_extension('text/csv'), ".csv")
self.assertEqual(get_default_file_extension('application/zip'), ".zip")
self.assertEqual(get_default_file_extension('aasdasd/dgfgf'), "")
self.assertEqual(get_parser_class_for_mime_type('application/pdf'), RasterisedDocumentParser)
self.assertEqual(get_parser_class_for_mime_type('text/plain'), TextDocumentParser)
self.assertEqual(get_parser_class_for_mime_type('text/sdgsdf'), None)
self.assertTrue(is_file_ext_supported('.pdf'))
self.assertFalse(is_file_ext_supported('.hsdfh'))