self = <swh.search.tests.test_in_memory.InmemorySearchTest testMethod=test_origin_intrinsic_metadata_long_description> def test_origin_intrinsic_metadata_long_description(self): """Checks ElasticSearch does not try to store large values untokenize, which would be inefficient and crash it with: Document contains at least one immense term in field="intrinsic_metadata.http://schema.org/description.@value" (whose UTF8 encoding is longer than the max length 32766), all of which were skipped. """ # noqa origin1 = {"url": "http://origin1"} self.search.origin_update( [ { **origin1, "intrinsic_metadata": { "@context": "https://doi.org/10.5063/schema/codemeta-2.0", "description": " ".join(f"foo{i}" for i in range(100000)), }, }, ] ) self.search.flush() actual_page = self.search.origin_search(metadata_pattern="foo42") assert actual_page.next_page_token is None > assert actual_page.results == [origin1] E AssertionError: assert [] == [{'url': 'http://origin1'}] E Right contains one more item: {'url': 'http://origin1'} E Full diff: E - [{'url': 'http://origin1'}] E + [] .tox/py3/lib/python3.7/site-packages/swh/search/tests/test_search.py:555: AssertionError