def test_ResolveContentId_pre_encoded_corpus_url_mismatch(): """Test that corpuses with different pre-trained URLs have different IDs.""" config_1 = corpus_pb2.Corpus( pre_encoded_corpus_url="mysql://*****:*****@foo:3306/clgen?charset=utf-8" ) config_2 = corpus_pb2.Corpus( pre_encoded_corpus_url="sqlite:////tmp/encoded.db") assert corpuses.ResolveContentId(config_1) != corpuses.ResolveContentId( config_2)
def test_ResolveContentId_pre_encoded_corpus_url(): """Test that pre_encoded_corpus_url field returns checksum of URL.""" config = corpus_pb2.Corpus( pre_encoded_corpus_url="mysql://*****:*****@foo:3306/clgen?charset=utf-8" ) assert corpuses.ResolveContentId(config) == ( "1fb56a3a74a939ee5be79172b3510a498abe7f3c")