spaCy/spacy/tests/tokenizer/test_whitespace.py
Ines Montani b6e991440c 💫 Tidy up and auto-format tests (#2967)
* Auto-format tests with black

* Add flake8 config

* Tidy up and remove unused imports

* Fix redefinitions of test functions

* Replace orths_and_spaces with words and spaces

* Fix compatibility with pytest 4.0

* xfail test for now

Test was previously overwritten by following test due to naming conflict, so failure wasn't reported

* Unfail passing test

* Only use fixture via arguments

Fixes pytest 4.0 compatibility
2018-11-27 01:09:36 +01:00

49 lines
1.3 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
import pytest
@pytest.mark.parametrize("text", ["lorem ipsum"])
def test_tokenizer_splits_single_space(tokenizer, text):
tokens = tokenizer(text)
assert len(tokens) == 2
@pytest.mark.parametrize("text", ["lorem ipsum"])
def test_tokenizer_splits_double_space(tokenizer, text):
tokens = tokenizer(text)
assert len(tokens) == 3
assert tokens[1].text == " "
@pytest.mark.parametrize("text", ["lorem ipsum "])
def test_tokenizer_handles_double_trainling_ws(tokenizer, text):
tokens = tokenizer(text)
assert repr(tokens.text_with_ws) == repr(text)
@pytest.mark.parametrize("text", ["lorem\nipsum"])
def test_tokenizer_splits_newline(tokenizer, text):
tokens = tokenizer(text)
assert len(tokens) == 3
assert tokens[1].text == "\n"
@pytest.mark.parametrize("text", ["lorem \nipsum"])
def test_tokenizer_splits_newline_space(tokenizer, text):
tokens = tokenizer(text)
assert len(tokens) == 3
@pytest.mark.parametrize("text", ["lorem \nipsum"])
def test_tokenizer_splits_newline_double_space(tokenizer, text):
tokens = tokenizer(text)
assert len(tokens) == 3
@pytest.mark.parametrize("text", ["lorem \n ipsum"])
def test_tokenizer_splits_newline_space_wrap(tokenizer, text):
tokens = tokenizer(text)
assert len(tokens) == 3