mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-22 03:49:17 +03:00
58 lines
1.2 KiB
Python
58 lines
1.2 KiB
Python
from __future__ import unicode_literals
|
|
import pytest
|
|
|
|
from spacy.en import English
|
|
|
|
@pytest.fixture
|
|
def EN():
|
|
return English()
|
|
|
|
|
|
def test_possess(EN):
|
|
tokens = EN("Mike's")
|
|
assert EN.vocab.strings[tokens[0].orth] == "Mike"
|
|
assert EN.vocab.strings[tokens[1].orth] == "'s"
|
|
assert len(tokens) == 2
|
|
|
|
|
|
def test_apostrophe(EN):
|
|
tokens = EN("schools'")
|
|
assert len(tokens) == 2
|
|
assert tokens[1].orth_ == "'"
|
|
assert tokens[0].orth_ == "schools"
|
|
|
|
|
|
def test_LL(EN):
|
|
tokens = EN("we'll")
|
|
assert len(tokens) == 2
|
|
assert tokens[1].orth_ == "'ll"
|
|
assert tokens[1].lemma_ == "will"
|
|
assert tokens[0].orth_ == "we"
|
|
|
|
|
|
def test_aint(EN):
|
|
tokens = EN("ain't")
|
|
assert len(tokens) == 2
|
|
assert tokens[0].orth_ == "ai"
|
|
assert tokens[0].lemma_ == "be"
|
|
assert tokens[1].orth_ == "n't"
|
|
assert tokens[1].lemma_ == "not"
|
|
|
|
|
|
def test_capitalized(EN):
|
|
tokens = EN("can't")
|
|
assert len(tokens) == 2
|
|
tokens = EN("Can't")
|
|
assert len(tokens) == 2
|
|
tokens = EN("Ain't")
|
|
assert len(tokens) == 2
|
|
assert tokens[0].orth_ == "Ai"
|
|
assert tokens[0].lemma_ == "be"
|
|
|
|
|
|
def test_punct(EN):
|
|
tokens = EN("We've")
|
|
assert len(tokens) == 2
|
|
tokens = EN("``We've")
|
|
assert len(tokens) == 3
|