2019-01-16 15:45:50 +03:00
|
|
|
import pytest
|
|
|
|
|
|
|
|
|
|
|
|
SV_TOKEN_EXCEPTION_TESTS = [
|
2019-02-08 16:14:49 +03:00
|
|
|
(
|
|
|
|
"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"],
|
|
|
|
),
|
|
|
|
(
|
|
|
|
"Anders I. tycker om ord med i i.",
|
|
|
|
["Anders", "I.", "tycker", "om", "ord", "med", "i", "i", "."],
|
|
|
|
),
|
2019-01-16 15:45:50 +03:00
|
|
|
]
|
|
|
|
|
|
|
|
|
2019-02-08 16:14:49 +03:00
|
|
|
@pytest.mark.parametrize("text,expected_tokens", SV_TOKEN_EXCEPTION_TESTS)
|
2019-01-16 15:45:50 +03:00
|
|
|
def test_sv_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
|
|
|
|
|
|
|
|
|
2019-02-08 16:14:49 +03:00
|
|
|
@pytest.mark.parametrize("text", ["driveru", "hajaru", "Serru", "Fixaru"])
|
2019-01-16 15:45:50 +03:00
|
|
|
def test_sv_tokenizer_handles_verb_exceptions(sv_tokenizer, text):
|
|
|
|
tokens = sv_tokenizer(text)
|
|
|
|
assert len(tokens) == 2
|
|
|
|
assert tokens[1].text == "u"
|
|
|
|
|
|
|
|
|
2019-02-08 16:14:49 +03:00
|
|
|
@pytest.mark.parametrize("text", ["bl.a", "m.a.o.", "Jan.", "Dec.", "kr.", "osv."])
|
2019-01-16 15:45:50 +03:00
|
|
|
def test_sv_tokenizer_handles_abbr(sv_tokenizer, text):
|
|
|
|
tokens = sv_tokenizer(text)
|
|
|
|
assert len(tokens) == 1
|
|
|
|
|
|
|
|
|
2019-02-08 16:14:49 +03:00
|
|
|
@pytest.mark.parametrize("text", ["Jul.", "jul.", "sön.", "Sön."])
|
2019-01-16 15:45:50 +03:00
|
|
|
def test_sv_tokenizer_handles_ambiguous_abbr(sv_tokenizer, text):
|
|
|
|
tokens = sv_tokenizer(text)
|
|
|
|
assert len(tokens) == 2
|
|
|
|
|
|
|
|
|
|
|
|
def test_sv_tokenizer_handles_exc_in_text(sv_tokenizer):
|
|
|
|
text = "Det er bl.a. ikke meningen"
|
|
|
|
tokens = sv_tokenizer(text)
|
|
|
|
assert len(tokens) == 5
|
|
|
|
assert tokens[2].text == "bl.a."
|
|
|
|
|
|
|
|
|
|
|
|
def test_sv_tokenizer_handles_custom_base_exc(sv_tokenizer):
|
|
|
|
text = "Her er noget du kan kigge i."
|
|
|
|
tokens = sv_tokenizer(text)
|
|
|
|
assert len(tokens) == 8
|
|
|
|
assert tokens[6].text == "i"
|
|
|
|
assert tokens[7].text == "."
|