mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 18:06:29 +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
878 B
Python
38 lines
878 B
Python
import pytest
|
|
from spacy.vocab import Vocab
|
|
from spacy.tokens import Doc
|
|
from spacy.lemmatizer import Lemmatizer
|
|
from spacy.lookups import Lookups
|
|
|
|
|
|
@pytest.fixture
|
|
def lemmatizer():
|
|
lookups = Lookups()
|
|
lookups.add_table("lemma_lookup", {"dogs": "dog", "boxen": "box", "mice": "mouse"})
|
|
return Lemmatizer(lookups)
|
|
|
|
|
|
@pytest.fixture
|
|
def vocab(lemmatizer):
|
|
return Vocab(lemmatizer=lemmatizer)
|
|
|
|
|
|
def test_empty_doc(vocab):
|
|
doc = Doc(vocab)
|
|
assert len(doc) == 0
|
|
|
|
|
|
def test_single_word(vocab):
|
|
doc = Doc(vocab, words=["a"])
|
|
assert doc.text == "a "
|
|
doc = Doc(vocab, words=["a"], spaces=[False])
|
|
assert doc.text == "a"
|
|
|
|
|
|
def test_lookup_lemmatization(vocab):
|
|
doc = Doc(vocab, words=["dogs", "dogses"])
|
|
assert doc[0].text == "dogs"
|
|
assert doc[0].lemma_ == "dog"
|
|
assert doc[1].text == "dogses"
|
|
assert doc[1].lemma_ == "dogses"
|