mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 10:26:35 +03:00
fe5f5d6ac6
* Update Makefile For more recent python version * updated for bsc changes New tokenization changes * Update test_text.py * updating tests and requirements * changed failed test in test/lang/ca changed failed test in test/lang/ca * Update .gitignore deleted stashed changes line * back to python 3.6 and remove transformer requirements As per request * Update test_exception.py Change the test * Update test_exception.py Remove test print * Update Makefile For more recent python version * updated for bsc changes New tokenization changes * updating tests and requirements * Update requirements.txt Removed spacy-transfromers from requirements * Update test_exception.py Added final punctuation to ensure consistency * Update Makefile Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Format * Update test to check all tokens Co-authored-by: cayorodriguez <crodriguezp@gmail.com> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
19 lines
493 B
Python
19 lines
493 B
Python
import pytest
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,expected_tokens",
|
|
[
|
|
("d'un", ["d'", "un"]),
|
|
("s'ha", ["s'", "ha"]),
|
|
("del", ["d", "el"]),
|
|
("cantar-te", ["cantar", "-te"]),
|
|
("-hola", ["-", "hola"]),
|
|
],
|
|
)
|
|
def test_contractions(ca_tokenizer, text, expected_tokens):
|
|
"""Test that the contractions are split into two tokens"""
|
|
tokens = ca_tokenizer(text)
|
|
assert len(tokens) == 2
|
|
assert [t.text for t in tokens] == expected_tokens
|