def setUp(self): # Download pre-built CACM index; append a random value to avoid filename clashes. r = randint(0, 10000000) self.collection_url = 'https://github.com/castorini/anserini-data/raw/master/CACM/lucene-index.cacm.tar.gz' self.tarball_name = 'lucene-index.cacm-{}.tar.gz'.format(r) self.index_dir = 'index{}/'.format(r) filename, headers = urlretrieve(self.collection_url, self.tarball_name) tarball = tarfile.open(self.tarball_name) tarball.extractall(self.index_dir) tarball.close() self.searcher = search.SimpleSearcher(f'{self.index_dir}lucene-index.cacm')