spaCy/spacy/tests/lang/nl/test_text.py
Ines Montani db55577c45
Drop Python 2.7 and 3.5 (#4828)
* 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]
2019-12-22 01:53:56 +01:00

25 lines
693 B
Python

import pytest
from spacy.lang.nl.lex_attrs import like_num
@pytest.mark.parametrize("word", ["elf", "elfde"])
def test_nl_lex_attrs_capitals(word):
assert like_num(word)
assert like_num(word.upper())
@pytest.mark.parametrize(
"text,num_tokens",
[
(
"De aftredende minister-president benadrukte al dat zijn partij inhoudelijk weinig gemeen heeft met de groenen.",
16,
),
("Hij is sociaal-cultureel werker.", 5),
("Er staan een aantal dure auto's in de garage.", 10),
],
)
def test_tokenizer_doesnt_split_hyphens(nl_tokenizer, text, num_tokens):
tokens = nl_tokenizer(text)
assert len(tokens) == num_tokens