2017-10-17 15:20:58 +00:00
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
|
|
from ...language import Language
|
2017-10-17 16:19:57 +00:00
|
|
|
from ...compat import pickle, unicode_
|
2017-10-17 15:20:58 +00:00
|
|
|
|
|
|
|
|
|
|
|
def test_pickle_single_doc():
|
|
|
|
nlp = Language()
|
|
|
|
doc = nlp(u'pickle roundtrip')
|
|
|
|
data = pickle.dumps(doc, 1)
|
|
|
|
doc2 = pickle.loads(data)
|
|
|
|
assert doc2.text == 'pickle roundtrip'
|
|
|
|
|
|
|
|
|
|
|
|
def test_list_of_docs_pickles_efficiently():
|
|
|
|
nlp = Language()
|
2017-10-17 16:19:57 +00:00
|
|
|
for i in range(10000):
|
|
|
|
_ = nlp.vocab[unicode_(i)]
|
2017-10-17 15:20:58 +00:00
|
|
|
one_pickled = pickle.dumps(nlp(u'0'), -1)
|
2017-10-17 16:19:57 +00:00
|
|
|
docs = list(nlp.pipe(unicode_(i) for i in range(100)))
|
2017-10-17 15:20:58 +00:00
|
|
|
many_pickled = pickle.dumps(docs, -1)
|
|
|
|
assert len(many_pickled) < (len(one_pickled) * 2)
|
|
|
|
many_unpickled = pickle.loads(many_pickled)
|
|
|
|
assert many_unpickled[0].text == '0'
|
|
|
|
assert many_unpickled[-1].text == '99'
|
2017-10-17 16:19:57 +00:00
|
|
|
assert len(many_unpickled) == 100
|