2017-03-15 19:39:54 +03:00
|
|
|
# coding: utf-8
|
2017-03-07 19:15:18 +03:00
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
2017-03-07 22:58:55 +03:00
|
|
|
import pytest
|
|
|
|
import dill as pickle
|
2017-12-07 11:53:30 +03:00
|
|
|
import numpy
|
2018-07-25 00:38:44 +03:00
|
|
|
from spacy.strings import StringStore
|
|
|
|
from spacy.vocab import Vocab
|
|
|
|
from spacy.attrs import NORM
|
2017-03-07 19:15:18 +03:00
|
|
|
|
|
|
|
|
2017-03-15 19:39:54 +03:00
|
|
|
@pytest.mark.parametrize('text1,text2', [('hello', 'bye')])
|
2018-07-25 00:38:44 +03:00
|
|
|
def test_pickle_string_store(text1, text2):
|
|
|
|
stringstore = StringStore()
|
2017-03-15 19:39:54 +03:00
|
|
|
store1 = stringstore[text1]
|
|
|
|
store2 = stringstore[text2]
|
|
|
|
data = pickle.dumps(stringstore, protocol=-1)
|
|
|
|
unpickled = pickle.loads(data)
|
|
|
|
assert unpickled[text1] == store1
|
|
|
|
assert unpickled[text2] == store2
|
|
|
|
assert len(stringstore) == len(unpickled)
|
2017-03-07 19:15:18 +03:00
|
|
|
|
2017-03-07 22:58:55 +03:00
|
|
|
|
2017-03-15 19:39:54 +03:00
|
|
|
@pytest.mark.parametrize('text1,text2', [('dog', 'cat')])
|
|
|
|
def test_pickle_vocab(text1, text2):
|
2017-03-07 22:58:55 +03:00
|
|
|
vocab = Vocab(lex_attr_getters={int(NORM): lambda string: string[:-1]})
|
2017-12-07 11:53:30 +03:00
|
|
|
vocab.set_vector('dog', numpy.ones((5,), dtype='f'))
|
2017-03-15 19:39:54 +03:00
|
|
|
lex1 = vocab[text1]
|
|
|
|
lex2 = vocab[text2]
|
|
|
|
assert lex1.norm_ == text1[:-1]
|
|
|
|
assert lex2.norm_ == text2[:-1]
|
|
|
|
data = pickle.dumps(vocab)
|
|
|
|
unpickled = pickle.loads(data)
|
|
|
|
assert unpickled[text1].orth == lex1.orth
|
|
|
|
assert unpickled[text2].orth == lex2.orth
|
|
|
|
assert unpickled[text1].norm == lex1.norm
|
|
|
|
assert unpickled[text2].norm == lex2.norm
|
|
|
|
assert unpickled[text1].norm != unpickled[text2].norm
|
2017-12-07 11:53:30 +03:00
|
|
|
assert unpickled.vectors is not None
|
|
|
|
assert list(vocab['dog'].vector) == [1.,1.,1.,1.,1.]
|