spaCy/spacy/tests/lang/yo/test_text.py
Olamilekan Wahab a741de7cf6 Adding support for Yoruba Language (#4614)
* Adding Support for Yoruba

* test text

* Updated test string.

* Fixing encoding declaration.

* Adding encoding to stop_words.py

* Added contributor agreement and removed iranlowo.

* Added removed test files and removed iranlowo to keep project bare.

* Returned CONTRIBUTING.md to default state.

* Added delted conftest entries

* Tidy up and auto-format

* Revert CONTRIBUTING.md

Co-authored-by: Ines Montani <ines@ines.io>
2019-12-21 14:11:50 +01:00

33 lines
1.5 KiB
Python

# coding: utf8
from __future__ import unicode_literals
import pytest
from spacy.lang.yo.lex_attrs import like_num
def test_yo_tokenizer_handles_long_text(yo_tokenizer):
text = """Àwọn ọmọ ìlú tí wọ́n ń ṣàmúlò ayélujára ti bẹ̀rẹ̀ ìkọkúkọ sórí àwòrán ààrẹ Nkurunziza nínú ìfẹ̀hónúhàn pẹ̀lú àmì ìdámọ̀: Nkurunziza àti Burundi:
Ọmọ ilé ẹ̀kọ́ gíga ní ẹ̀wọ̀n fún kíkọ ìkọkúkọ sí orí àwòrán Ààrẹ .
Bí mo bá ṣe èyí ní Burundi , ó ṣe é ṣe kí a fi mí sí àtìmọ́lé
Ìjọba Burundi fi akẹ́kọ̀ọ́bìnrin sí àtìmọ́lé látàrí ẹ̀sùn ìkọkúkọ sí orí àwòrán ààrẹ. A túwíìtì àwòrán ìkọkúkọ wa ní ìbánikẹ́dùn ìṣẹ̀lẹ̀ náà.
Wọ́n ní kí a dán an wò, kí a kọ nǹkan sí orí àwòrán ààrẹ mo sì ṣe bẹ́ẹ̀. Mo ní ìgbóyà wípé ẹnikẹ́ni kò ní mú mi níbí.
Ìfòfinlíle mú àtakò"""
tokens = yo_tokenizer(text)
assert len(tokens) == 121
@pytest.mark.parametrize(
"text,match",
[("ení", True), ("ogun", True), ("mewadinlogun", True), ("ten", False)],
)
def test_lex_attrs_like_number(yo_tokenizer, text, match):
tokens = yo_tokenizer(text)
assert len(tokens) == 1
assert tokens[0].like_num == match
@pytest.mark.parametrize("word", ["eji", "ejila", "ogun", "aárùn"])
def test_yo_lex_attrs_capitals(word):
assert like_num(word)
assert like_num(word.upper())