mirror of https://github.com/explosion/spaCy.git
* Upd contractions test
This commit is contained in:
parent
0d9972f4b0
commit
199025609f
|
@ -1,32 +1,37 @@
|
|||
from __future__ import unicode_literals
|
||||
import pytest
|
||||
|
||||
from spacy.en import EN
|
||||
from spacy.en import English
|
||||
|
||||
@pytest.fixture
|
||||
def EN():
|
||||
return English(pos_tag=False)
|
||||
|
||||
|
||||
def test_possess():
|
||||
tokens = EN.tokenize("Mike's")
|
||||
assert EN.lexicon.strings[tokens[0].sic] == "Mike"
|
||||
assert EN.lexicon.strings[tokens[1].sic] == "'s"
|
||||
def test_possess(EN):
|
||||
tokens = EN("Mike's")
|
||||
assert EN.vocab.strings[tokens[0].sic] == "Mike"
|
||||
assert EN.vocab.strings[tokens[1].sic] == "'s"
|
||||
assert len(tokens) == 2
|
||||
|
||||
|
||||
def test_apostrophe():
|
||||
tokens = EN.tokenize("schools'")
|
||||
def test_apostrophe(EN):
|
||||
tokens = EN("schools'")
|
||||
assert len(tokens) == 2
|
||||
assert tokens[1].string == "'"
|
||||
assert tokens[0].string == "schools"
|
||||
|
||||
|
||||
def test_LL():
|
||||
tokens = EN.tokenize("we'll")
|
||||
def test_LL(EN):
|
||||
tokens = EN("we'll")
|
||||
assert len(tokens) == 2
|
||||
assert tokens[1].string == "'ll"
|
||||
assert tokens[1].lemma == "will"
|
||||
assert tokens[0].string == "we"
|
||||
|
||||
|
||||
def test_aint():
|
||||
tokens = EN.tokenize("ain't")
|
||||
def test_aint(EN):
|
||||
tokens = EN("ain't")
|
||||
assert len(tokens) == 2
|
||||
assert tokens[0].string == "ai"
|
||||
assert tokens[0].lemma == "be"
|
||||
|
@ -34,19 +39,19 @@ def test_aint():
|
|||
assert tokens[1].lemma == "not"
|
||||
|
||||
|
||||
def test_capitalized():
|
||||
tokens = EN.tokenize("can't")
|
||||
def test_capitalized(EN):
|
||||
tokens = EN("can't")
|
||||
assert len(tokens) == 2
|
||||
tokens = EN.tokenize("Can't")
|
||||
tokens = EN("Can't")
|
||||
assert len(tokens) == 2
|
||||
tokens = EN.tokenize("Ain't")
|
||||
tokens = EN("Ain't")
|
||||
assert len(tokens) == 2
|
||||
assert tokens[0].string == "Ai"
|
||||
assert tokens[0].lemma == "be"
|
||||
|
||||
|
||||
def test_punct():
|
||||
tokens = EN.tokenize("We've")
|
||||
def test_punct(EN):
|
||||
tokens = EN("We've")
|
||||
assert len(tokens) == 2
|
||||
tokens = EN.tokenize("``We've")
|
||||
tokens = EN("``We've")
|
||||
assert len(tokens) == 3
|
||||
|
|
Loading…
Reference in New Issue