mirror of
https://github.com/explosion/spaCy.git
synced 2025-10-31 07:57:35 +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]
20 lines
584 B
Python
20 lines
584 B
Python
import pytest
|
|
|
|
|
|
@pytest.mark.parametrize("text,length", [("z.B.", 1), ("zb.", 2), ("(z.B.", 2)])
|
|
def test_lb_tokenizer_splits_prefix_interact(lb_tokenizer, text, length):
|
|
tokens = lb_tokenizer(text)
|
|
assert len(tokens) == length
|
|
|
|
|
|
@pytest.mark.parametrize("text", ["z.B.)"])
|
|
def test_lb_tokenizer_splits_suffix_interact(lb_tokenizer, text):
|
|
tokens = lb_tokenizer(text)
|
|
assert len(tokens) == 2
|
|
|
|
|
|
@pytest.mark.parametrize("text", ["(z.B.)"])
|
|
def test_lb_tokenizer_splits_even_wrap_interact(lb_tokenizer, text):
|
|
tokens = lb_tokenizer(text)
|
|
assert len(tokens) == 3
|