mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-04 09:57:26 +03:00
db55577c45
* Remove unicode declarations * Remove Python 3.5 and 2.7 from CI * Don't require pathlib * Replace compat helpers * Remove OrderedDict * Use f-strings * Set Cython compiler language level * Fix typo * Re-add OrderedDict for Table * Update setup.cfg * Revert CONTRIBUTING.md * Revert lookups.md * Revert top-level.md * Small adjustments and docs [ci skip]
46 lines
1.3 KiB
Python
46 lines
1.3 KiB
Python
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
|