spaCy/spacy/tests/vocab_vectors/test_vocab_api.py
Daniël de Kok e2b70df012
Configure isort to use the Black profile, recursively isort the spacy module (#12721)
* Use isort with Black profile

* isort all the things

* Fix import cycles as a result of import sorting

* Add DOCBIN_ALL_ATTRS type definition

* Add isort to requirements

* Remove isort from build dependencies check

* Typo
2023-06-14 17:48:41 +02:00

84 lines
2.1 KiB
Python

import os
import pytest
from spacy.attrs import IS_ALPHA, LEMMA, ORTH
from spacy.lang.en import English
from spacy.parts_of_speech import NOUN, VERB
from spacy.vocab import Vocab
from ..util import make_tempdir
@pytest.mark.issue(1868)
def test_issue1868():
"""Test Vocab.__contains__ works with int keys."""
vocab = Vocab()
lex = vocab["hello"]
assert lex.orth in vocab
assert lex.orth_ in vocab
assert "some string" not in vocab
int_id = vocab.strings.add("some string")
assert int_id not in vocab
@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),
],
)
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] # noqa: F841
assert text in en_vocab
assert "LKsdjvlsakdvlaksdvlkasjdvljasdlkfvm" not in en_vocab
def test_vocab_writing_system(en_vocab):
assert en_vocab.writing_system["direction"] == "ltr"
assert en_vocab.writing_system["has_case"] is True
def test_to_disk():
nlp = English()
with make_tempdir() as d:
nlp.vocab.to_disk(d)
assert "vectors" in os.listdir(d)
assert "lookups.bin" in os.listdir(d)
def test_to_disk_exclude():
nlp = English()
with make_tempdir() as d:
nlp.vocab.to_disk(d, exclude=("vectors", "lookups"))
assert "vectors" not in os.listdir(d)
assert "lookups.bin" not in os.listdir(d)