Add Swedish tokenizer tests (see #807)

This commit is contained in:
ines 2017-02-05 11:47:07 +01:00
parent 6715615d55
commit 654fe447b1
2 changed files with 24 additions and 0 deletions

View File

View File

@ -0,0 +1,24 @@
# encoding: utf8
from __future__ import unicode_literals
import pytest
SV_TOKEN_EXCEPTION_TESTS = [
('Smörsåsen används bl.a. till fisk', ['Smörsåsen', 'används', 'bl.a.', 'till', 'fisk']),
('Jag kommer först kl. 13 p.g.a. diverse förseningar', ['Jag', 'kommer', 'först', 'kl.', '13', 'p.g.a.', 'diverse', 'förseningar'])
]
@pytest.mark.parametrize('text,expected_tokens', SV_TOKEN_EXCEPTION_TESTS)
def test_tokenizer_handles_exception_cases(sv_tokenizer, text, expected_tokens):
tokens = sv_tokenizer(text)
token_list = [token.text for token in tokens if not token.is_space]
assert expected_tokens == token_list
@pytest.mark.parametrize('text', ["driveru", "hajaru", "Serru", "Fixaru"])
def test_tokenizer_handles_verb_exceptions(sv_tokenizer, text):
tokens = sv_tokenizer(text)
assert len(tokens) == 2
assert tokens[1].text == "u"