spaCy/spacy/tests/regression/test_issue852.py

13 lines
382 B
Python
Raw Normal View History

2017-02-24 20:22:49 +03:00
# encoding: utf8
from __future__ import unicode_literals
import pytest
@pytest.mark.parametrize('text', ["au-delàs", "pair-programmâmes",
"terra-formées", "σ-compacts"])
def test_issue852(fr_tokenizer, text):
"""Test that French tokenizer exceptions are imported correctly."""
tokens = fr_tokenizer(text)
assert len(tokens) == 1