mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 09:56:28 +03:00
14 lines
557 B
Python
14 lines
557 B
Python
|
from __future__ import unicode_literals
|
||
|
|
from ...tokenizer import Tokenizer
|
||
|
|
from ...symbols import ORTH, LEMMA, POS
|
||
|
|
from ...lang.en import English
|
||
|
|
|
||
|
|
def test_issue1250_cached_special_cases():
|
||
|
|
nlp = English()
|
||
|
|
nlp.tokenizer.add_special_case(u'reimbur', [{ORTH: u'reimbur', LEMMA: u'reimburse', POS: u'VERB'}])
|
||
|
|
|
||
|
|
lemmas = [w.lemma_ for w in nlp(u'reimbur, reimbur...')]
|
||
|
|
assert lemmas == ['reimburse', ',', 'reimburse', '...']
|
||
|
|
lemmas = [w.lemma_ for w in nlp(u'reimbur, reimbur...')]
|
||
|
|
assert lemmas == ['reimburse', ',', 'reimburse', '...']
|