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
23 lines
1.0 KiB
Python
23 lines
1.0 KiB
Python
import pytest
|
|
|
|
|
|
def test_ml_tokenizer_handles_long_text(ml_tokenizer):
|
|
text = """അനാവശ്യമായി കണ്ണിലും മൂക്കിലും വായിലും സ്പർശിക്കാതിരിക്കുക"""
|
|
tokens = ml_tokenizer(text)
|
|
assert len(tokens) == 5
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,length",
|
|
[
|
|
(
|
|
"എന്നാൽ അച്ചടിയുടെ ആവിർഭാവം ലിപിയിൽ കാര്യമായ മാറ്റങ്ങൾ വരുത്തിയത് കൂട്ടക്ഷരങ്ങളെ അണുഅക്ഷരങ്ങളായി പിരിച്ചുകൊണ്ടായിരുന്നു",
|
|
10,
|
|
),
|
|
("പരമ്പരാഗതമായി മലയാളം ഇടത്തുനിന്ന് വലത്തോട്ടാണ് എഴുതുന്നത്", 5),
|
|
],
|
|
)
|
|
def test_ml_tokenizer_handles_cnts(ml_tokenizer, text, length):
|
|
tokens = ml_tokenizer(text)
|
|
assert len(tokens) == length
|