wehub-resource-sync
f877c37fc6
tests / Test (macos-latest, 3.14) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.10) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.11) (push) Has been cancelled
tests / Test (windows-latest, 3.13) (push) Has been cancelled
tests / Test (windows-latest, 3.14) (push) Has been cancelled
tests / Validate (push) Has been cancelled
tests / Test (macos-latest, 3.10) (push) Has been cancelled
tests / Test (macos-latest, 3.11) (push) Has been cancelled
tests / Test (macos-latest, 3.12) (push) Has been cancelled
tests / Test (macos-latest, 3.13) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.12) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.13) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.14) (push) Has been cancelled
tests / Test (windows-latest, 3.10) (push) Has been cancelled
tests / Test (windows-latest, 3.11) (push) Has been cancelled
tests / Test (windows-latest, 3.12) (push) Has been cancelled
universe validation / Validate (push) Has been cancelled
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
|