spaCy/spacy/tests/vocab_vectors/test_vocab_api.py
Ines Montani b6e991440c 💫 Tidy up and auto-format tests (#2967)
* 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
2018-11-27 01:09:36 +01:00

48 lines
1.2 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
import pytest
from spacy.attrs import LEMMA, ORTH, PROB, IS_ALPHA
from spacy.parts_of_speech import NOUN, VERB
@pytest.mark.parametrize(
"text1,text2", [("Hello", "bye"), ("Hello", "hello"), ("Hello", "Hello,")]
)
def test_vocab_api_neq(en_vocab, text1, text2):
assert en_vocab[text1].orth != en_vocab[text2].orth
@pytest.mark.parametrize("text", "Hello")
def test_vocab_api_eq(en_vocab, text):
lex = en_vocab[text]
assert en_vocab[text].orth == lex.orth
@pytest.mark.parametrize("text", ["example"])
def test_vocab_api_shape_attr(en_vocab, text):
lex = en_vocab[text]
assert lex.orth != lex.shape
@pytest.mark.parametrize(
"string,symbol",
[
("IS_ALPHA", IS_ALPHA),
("NOUN", NOUN),
("VERB", VERB),
("LEMMA", LEMMA),
("ORTH", ORTH),
("PROB", PROB),
],
)
def test_vocab_api_symbols(en_vocab, string, symbol):
assert en_vocab.strings[string] == symbol
@pytest.mark.parametrize("text", "Hello")
def test_vocab_api_contains(en_vocab, text):
_ = en_vocab[text]
assert text in en_vocab
assert "LKsdjvlsakdvlaksdvlkasjdvljasdlkfvm" not in en_vocab