mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 01:16:28 +03:00
Add Swedish tokenizer tests (see #807)
This commit is contained in:
parent
6715615d55
commit
654fe447b1
0
spacy/tests/sv/__init__.py
Normal file
0
spacy/tests/sv/__init__.py
Normal file
24
spacy/tests/sv/test_tokenizer.py
Normal file
24
spacy/tests/sv/test_tokenizer.py
Normal 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"
|
Loading…
Reference in New Issue
Block a user