explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-12 18:26:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add test for #1250: Tokenizer cache clobbered special-case attrs

Browse Source
This commit is contained in:
Matthew Honnibal 2017-10-24 16:07:18 +02:00
parent 18f1c1d0ba
commit 63f0bde749
1 changed files with 13 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
spacy/tests/regression/test_issue1250.py Normal file
View File

@ -0,0 +1,13 @@
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', '...']