explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-27 17:54:39 +03:00
Code Issues Packages Projects Releases Wiki Activity

Move basic contraction tests to test_contractions.py

Browse Source
This commit is contained in:
Ines Montani 2017-01-05 18:09:53 +01:00
parent bbe7cab3a1
commit 65f937d5c6
1 changed files with 17 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
spacy/tests/en/tokenizer/test_contractions.py
View File

@ -7,6 +7,23 @@ from __future__ import unicode_literals
import pytest import pytest
def test_tokenizer_handles_basic_contraction(en_tokenizer):
text = "don't giggle"
tokens = en_tokenizer(text)
assert len(tokens) == 3
assert tokens[1].text == "n't"
text = "i said don't!"
tokens = en_tokenizer(text)
assert len(tokens) == 5
assert tokens[4].text == "!"
@pytest.mark.parametrize('text', ["`ain't", '''"isn't''', "can't!"])
def test_tokenizer_handles_basic_contraction_punct(en_tokenizer, text):
tokens = en_tokenizer(text)
assert len(tokens) == 3
@pytest.mark.parametrize('text_poss,text', [("Robin's", "Robin"), ("Alexis's", "Alexis")]) @pytest.mark.parametrize('text_poss,text', [("Robin's", "Robin"), ("Alexis's", "Alexis")])
def test_tokenizer_handles_poss_contraction(en_tokenizer, text_poss, text): def test_tokenizer_handles_poss_contraction(en_tokenizer, text_poss, text):
tokens = en_tokenizer(text_poss) tokens = en_tokenizer(text_poss)