def test_parse_all_multi_cluster(self):
# test we partition correctly by cluster number
sample_data = self.read_sample_data("data/diamond_output_sample_multicluster.txt")
clusters_by_number, queries_by_number = core.parse_all_clusters(sample_data, Record(), 0, 0)
self.assertEqual(len(clusters_by_number), 3)
self.assertEqual(sorted(clusters_by_number), [1, 2, 4])
self.assertEqual(len(queries_by_number), 3)
self.assertEqual(sorted(queries_by_number), [1, 2, 4])
for i in [1, 2, 4]:
self.assertEqual(len(clusters_by_number[i]), i)
self.assertEqual(len(queries_by_number[i]), i)
def parse_all_wrapper(coverage_threshold, ident_threshold):
clusters_by_number, queries_by_number = core.parse_all_clusters(self.sample_data,
Record(), coverage_threshold, ident_threshold)
# make sure we only found one cluster number
self.assertEqual(len(clusters_by_number), 1)
self.assertEqual(list(clusters_by_number), [24])
self.assertEqual(len(queries_by_number), 1)
self.assertEqual(list(queries_by_number), [24])
# now test the values of those queries
queries = queries_by_number[24]
clusters = clusters_by_number[24]
return queries, clusters
def test_parse_all_empty(self):
for sample_data in ["", "\n", "\r\n", "\n\n"]:
clusters, queries = core.parse_all_clusters(
sample_data, Record(), 0, 0)
self.assertEqual(len(clusters), 0)
self.assertEqual(len(queries), 0)
