spaCy/spacy/tests/lang/th/test_tokenizer.py
2019-09-29 17:32:12 +02:00

13 lines
374 B
Python

# coding: utf8
from __future__ import unicode_literals
import pytest
@pytest.mark.parametrize(
"text,expected_tokens", [("คุณรักผมไหม", ["คุณ", "รัก", "ผม", "ไหม"])]
)
def test_th_tokenizer(th_tokenizer, text, expected_tokens):
tokens = [token.text for token in th_tokenizer(text)]
assert tokens == expected_tokens