mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 18:06:29 +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]
14 lines
479 B
Python
14 lines
479 B
Python
import pytest
|
|
|
|
|
|
def test_ur_tokenizer_handles_long_text(ur_tokenizer):
|
|
text = """اصل میں، رسوا ہونے کی ہمیں کچھ عادت سی ہو گئی ہے۔"""
|
|
tokens = ur_tokenizer(text)
|
|
assert len(tokens) == 14
|
|
|
|
|
|
@pytest.mark.parametrize("text,length", [("تحریر باسط حبیب", 3), ("میرا پاکستان", 2)])
|
|
def test_ur_tokenizer_handles_cnts(ur_tokenizer, text, length):
|
|
tokens = ur_tokenizer(text)
|
|
assert len(tokens) == length
|