spaCy/spacy/tests/lang/th/test_tokenizer.py

14 lines
408 B
Python

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