mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-13 13:17:06 +03:00
b6e991440c
* Auto-format tests with black * Add flake8 config * Tidy up and remove unused imports * Fix redefinitions of test functions * Replace orths_and_spaces with words and spaces * Fix compatibility with pytest 4.0 * xfail test for now Test was previously overwritten by following test due to naming conflict, so failure wasn't reported * Unfail passing test * Only use fixture via arguments Fixes pytest 4.0 compatibility
41 lines
1.3 KiB
Python
41 lines
1.3 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
import dill as pickle
|
|
import numpy
|
|
from spacy.strings import StringStore
|
|
from spacy.vocab import Vocab
|
|
from spacy.attrs import NORM
|
|
|
|
|
|
@pytest.mark.parametrize("text1,text2", [("hello", "bye")])
|
|
def test_pickle_string_store(text1, text2):
|
|
stringstore = StringStore()
|
|
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)
|
|
|
|
|
|
@pytest.mark.parametrize("text1,text2", [("dog", "cat")])
|
|
def test_pickle_vocab(text1, text2):
|
|
vocab = Vocab(lex_attr_getters={int(NORM): lambda string: string[:-1]})
|
|
vocab.set_vector("dog", numpy.ones((5,), dtype="f"))
|
|
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
|
|
assert unpickled.vectors is not None
|
|
assert list(vocab["dog"].vector) == [1.0, 1.0, 1.0, 1.0, 1.0]
|