2018-07-24 21:38:44 +00:00
|
|
|
# coding: utf-8
|
2017-10-11 01:21:23 +00:00
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
2018-07-24 21:38:44 +00:00
|
|
|
import pytest
|
|
|
|
from spacy.vocab import Vocab
|
|
|
|
from spacy.tokens import Doc
|
|
|
|
from spacy.lemmatizer import Lemmatizer
|
2019-10-01 19:36:04 +00:00
|
|
|
from spacy.lookups import Lookups
|
2017-10-11 01:21:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
@pytest.fixture
|
|
|
|
def lemmatizer():
|
2019-10-01 19:36:04 +00:00
|
|
|
lookups = Lookups()
|
|
|
|
lookups.add_table("lemma_lookup", {"dogs": "dog", "boxen": "box", "mice": "mouse"})
|
|
|
|
return Lemmatizer(lookups)
|
2017-10-11 01:21:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
@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):
|
2018-11-27 00:09:36 +00:00
|
|
|
doc = Doc(vocab, words=["a"])
|
|
|
|
assert doc.text == "a "
|
|
|
|
doc = Doc(vocab, words=["a"], spaces=[False])
|
|
|
|
assert doc.text == "a"
|
2017-10-11 01:21:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
def test_lookup_lemmatization(vocab):
|
2018-11-27 00:09:36 +00:00
|
|
|
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"
|