How to use the pyserini.search function in pyserini

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)

        _, _ = urlretrieve(self.collection_url, self.tarball_name)

        tarball = tarfile.open(self.tarball_name)
        tarball.extractall(self.index_dir)
        tarball.close()

        self.index_path = os.path.join(self.index_dir, 'lucene-index.cacm')
        self.searcher = search.SimpleSearcher(self.index_path)
        self.index_reader = index.IndexReader(self.index_path)

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')

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)

        _, _ = 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')
        self.index_utils = index.IndexReader(f'{self.index_dir}lucene-index.cacm')

def test_robust04(self):
        topics = search.get_topics('robust04')
        self.assertEqual(len(topics), 250)
        self.assertTrue(isinstance(next(iter(topics.keys())), int))

def test_query_doc_score_custom_similarity(self):
        custom_bm25 = search.LuceneSimilarities.bm25(0.8, 0.2)
        queries = ['information retrieval', 'databases']
        self.searcher.set_bm25(0.8, 0.2)

        for query in queries:
            hits = self.searcher.search(query)

            # We're going to verify that the score of each hit is about the same as the output of
            # compute_query_document_score
            for i in range(0, len(hits)):
                self.assertAlmostEqual(hits[i].score,
                                       self.index_reader.compute_query_document_score(
                                           hits[i].docid, query, similarity=custom_bm25), places=4)

        custom_qld = search.LuceneSimilarities.qld(500)
        self.searcher.set_qld(500)

        for query in queries:
            hits = self.searcher.search(query)

            # We're going to verify that the score of each hit is about the same as the output of
            # compute_query_document_score
            for i in range(0, len(hits)):
                self.assertAlmostEqual(hits[i].score,
                                       self.index_reader.compute_query_document_score(
                                           hits[i].docid, query, similarity=custom_qld), places=4)

def test_covid_round1(self):
        topics = search.get_topics('covid_round1')
        self.assertEqual(len(topics), 30)
        self.assertEqual('coronavirus origin', topics[1]['query'])
        self.assertEqual('coronavirus remdesivir', topics[30]['query'])
        self.assertTrue(isinstance(next(iter(topics.keys())), int))

def __init__(self, lucene_index_path: str, min_df: int = 1, verbose: bool = False):
        self.min_df: int = min_df
        self.verbose: bool = verbose
        self.index_reader = index.IndexReader(lucene_index_path)
        self.searcher = search.SimpleSearcher(lucene_index_path)
        self.num_docs: int = self.searcher.num_docs

        # build vocabulary
        self.vocabulary_ = set()
        for term in self.index_reader.terms():
            if term.df > self.min_df:
                self.vocabulary_.add(term.term)

        # build term to index mapping
        self.term_to_index = {}
        for i, term in enumerate(self.vocabulary_):
            self.term_to_index[term] = i
        self.vocabulary_size = len(self.vocabulary_)

        if self.verbose:
            print(f'Found {self.vocabulary_size} terms with min_df={self.min_df}')