def __init__(self, filename):
self.analyzer = StandardAnalyzer()
store = park.SQLiteStore(filename)
self.model = Model(self.analyzer, store)
self.searcher = RandomWalkSearcher(self.model)
def test_init(self):
# Don't specify any ngram orders, which should get trigrams
# and bigrams stored.
model = self.model
self.assertEquals((3, 2, 1), model.orders)
# And make sure n=5 yields 5-grams and 4-grams
model = Model(self.analyzer, self.store, n=5)
self.assertEquals((5, 4, 3, 2, 1), model.orders)
def test_load_tokens(self):
# Ensure that model.tokens is properly reloaded from the
# database when an old Model is loaded
model = self.model
model.train(u"this is a test")
model.train(u"this is another test")
# We save on train(), so make sure the new tokens log is empty.
self.assertEqual(0, len(model.tokens.token_log))
save_token_ids = dict(model.tokens.token_ids)
save_tokens = dict(model.tokens.tokens)
model = Model(self.analyzer, self.store)
self.assertEqual(save_token_ids, model.tokens.token_ids)
self.assertEqual(save_tokens, model.tokens.tokens)
def setUp(self):
self.analyzer = WhitespaceAnalyzer()
self.store = park.SQLiteStore(":memory:")
self.model = Model(self.analyzer, self.store)
