mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 02:16:32 +03:00
db55577c45
* Remove unicode declarations * Remove Python 3.5 and 2.7 from CI * Don't require pathlib * Replace compat helpers * Remove OrderedDict * Use f-strings * Set Cython compiler language level * Fix typo * Re-add OrderedDict for Table * Update setup.cfg * Revert CONTRIBUTING.md * Revert lookups.md * Revert top-level.md * Small adjustments and docs [ci skip]
38 lines
1.3 KiB
Python
38 lines
1.3 KiB
Python
import pytest
|
|
import numpy
|
|
import srsly
|
|
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 = srsly.pickle_dumps(stringstore, protocol=-1)
|
|
unpickled = srsly.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 = srsly.pickle_dumps(vocab)
|
|
unpickled = srsly.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]
|