mirror of https://github.com/explosion/spaCy.git
13 lines
459 B
Python
13 lines
459 B
Python
|
# coding: utf8
|
||
|
|
from __future__ import unicode_literals
|
||
|
|
|
||
|
|
|
||
|
|
def test_issue2835(en_tokenizer):
|
||
|
|
"""Check that sentence doesn't cause an infinite loop in the tokenizer."""
|
||
|
|
text = """
|
||
|
|
oow.jspsearch.eventoracleopenworldsearch.technologyoraclesolarissearch.technologystoragesearch.technologylinuxsearch.technologyserverssearch.technologyvirtualizationsearch.technologyengineeredsystemspcodewwmkmppscem:
|
||
|
|
"""
|
||
|
|
doc = en_tokenizer(text)
|
||
|
|
assert doc
|
||
|
|
|