mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 12:18:04 +03:00
19 lines
341 B
Python
19 lines
341 B
Python
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
|
|
from spacy.en import English
|
|
|
|
|
|
#def test_hyphen():
|
|
# tokens = EN.tokenize('best-known')
|
|
# assert len(tokens) == 3
|
|
|
|
|
|
def test_period():
|
|
EN = English()
|
|
tokens = EN.tokenizer('best.Known')
|
|
assert len(tokens) == 3
|
|
tokens = EN('zombo.com')
|
|
assert len(tokens) == 1
|