explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-26 18:06:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update tokenizer tests for contractions

Browse Source
This commit is contained in:
Ines Montani 2017-01-04 00:48:42 +01:00
parent 109f202e8f
commit 550630df73
1 changed files with 12 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
spacy/tests/tokenizer/test_contractions.py
View File

@ -1,15 +1,10 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from ...en import English
import pytest import pytest
@pytest.fixture
def en_tokenizer():
return English.Defaults.create_tokenizer()
@pytest.mark.parametrize('text_poss,text', [("Robin's", "Robin"), ("Alexis's", "Alexis")])
@pytest.mark.parametrize('inputs', [("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, inputs):
text_poss, text = inputs
tokens = en_tokenizer(text_poss) tokens = en_tokenizer(text_poss)
assert len(tokens) == 2 assert len(tokens) == 2
assert tokens[0].text == text assert tokens[0].text == text
@ -40,9 +35,8 @@ def test_tokenizer_handles_ll_contraction(en_tokenizer, text):
assert tokens[1].lemma_ == "will" assert tokens[1].lemma_ == "will"
@pytest.mark.parametrize('inputs', [("can't", "Can't"), ("ain't", "Ain't")]) @pytest.mark.parametrize('text_lower,text_title', [("can't", "Can't"), ("ain't", "Ain't")])
def test_tokenizer_handles_capitalization(en_tokenizer, inputs): def test_tokenizer_handles_capitalization(en_tokenizer, text_lower, text_title):
text_lower, text_title = inputs
tokens_lower = en_tokenizer(text_lower) tokens_lower = en_tokenizer(text_lower)
tokens_title = en_tokenizer(text_title) tokens_title = en_tokenizer(text_title)
assert tokens_title[0].text == tokens_lower[0].text.title() assert tokens_title[0].text == tokens_lower[0].text.title()
@ -51,11 +45,11 @@ def test_tokenizer_handles_capitalization(en_tokenizer, inputs):
@pytest.mark.parametrize('pron', ["I", "You", "He", "She", "It", "We", "They"]) @pytest.mark.parametrize('pron', ["I", "You", "He", "She", "It", "We", "They"])
def test_tokenizer_keeps_title_case(en_tokenizer, pron): @pytest.mark.parametrize('contraction', ["'ll", "'d"])
for contraction in ["'ll", "'d"]: def test_tokenizer_keeps_title_case(en_tokenizer, pron, contraction):
tokens = en_tokenizer(pron + contraction) tokens = en_tokenizer(pron + contraction)
assert tokens[0].text == pron assert tokens[0].text == pron
assert tokens[1].text == contraction assert tokens[1].text == contraction
@pytest.mark.parametrize('exc', ["Ill", "ill", "Hell", "hell", "Well", "well"]) @pytest.mark.parametrize('exc', ["Ill", "ill", "Hell", "hell", "Well", "well"])
@ -64,9 +58,8 @@ def test_tokenizer_excludes_ambiguous(en_tokenizer, exc):
assert len(tokens) == 1 assert len(tokens) == 1
@pytest.mark.parametrize('inputs', [("We've", "``We've"), ("couldn't", "couldn't)")]) @pytest.mark.parametrize('wo_punct,w_punct', [("We've", "``We've"), ("couldn't", "couldn't)")])
def test_tokenizer_splits_defined_punct(en_tokenizer, inputs): def test_tokenizer_splits_defined_punct(en_tokenizer, wo_punct, w_punct):
wo_punct, w_punct = inputs
tokens = en_tokenizer(wo_punct) tokens = en_tokenizer(wo_punct)
assert len(tokens) == 2 assert len(tokens) == 2
tokens = en_tokenizer(w_punct) tokens = en_tokenizer(w_punct)