spaCy/spacy/tests/ja/test_tokenizer.py

9 lines
188 B
Python
Raw Normal View History

2017-06-27 19:24:25 +03:00
# coding: utf-8
from __future__ import unicode_literals
import pytest
def test_japanese_tokenizer(ja_tokenizer):
tokens = ja_tokenizer("日本語だよ")
assert len(tokens) == 3