2017-01-05 20:11:25 +03:00
|
|
|
import pytest
|
|
|
|
|
|
|
|
|
2018-11-27 03:09:36 +03:00
|
|
|
@pytest.mark.parametrize("text", ["auf'm", "du's", "über'm", "wir's"])
|
2017-06-03 22:07:44 +03:00
|
|
|
def test_de_tokenizer_splits_contractions(de_tokenizer, text):
|
2017-01-05 20:11:25 +03:00
|
|
|
tokens = de_tokenizer(text)
|
|
|
|
assert len(tokens) == 2
|
|
|
|
|
|
|
|
|
2018-11-27 03:09:36 +03:00
|
|
|
@pytest.mark.parametrize("text", ["z.B.", "d.h.", "Jan.", "Dez.", "Chr."])
|
2017-06-03 22:07:44 +03:00
|
|
|
def test_de_tokenizer_handles_abbr(de_tokenizer, text):
|
2017-01-05 20:11:25 +03:00
|
|
|
tokens = de_tokenizer(text)
|
|
|
|
assert len(tokens) == 1
|
|
|
|
|
|
|
|
|
2017-06-03 22:07:44 +03:00
|
|
|
def test_de_tokenizer_handles_exc_in_text(de_tokenizer):
|
2017-01-05 20:11:25 +03:00
|
|
|
text = "Ich bin z.Zt. im Urlaub."
|
|
|
|
tokens = de_tokenizer(text)
|
|
|
|
assert len(tokens) == 6
|
|
|
|
assert tokens[2].text == "z.Zt."
|