spaCy/spacy/tests/regression/test_issue852.py
2017-02-24 18:22:49 +01:00

13 lines
382 B
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# 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