explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-04-25 03:13:41 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Add tests for unicode puncuation character lemmatization

Browse Source
This commit is contained in:
Matthew Honnibal 2015-10-09 18:43:14 +11:00
parent c5b2c4ead8
commit b71ba2eed5
1 changed files with 12 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
tests/tagger/test_lemmatizer.py
View File

@ -1,3 +1,4 @@
# -*- coding: utf-8 -*-
from __future__ import unicode_literals from __future__ import unicode_literals
from spacy.lemmatizer import Lemmatizer, read_index, read_exc from spacy.lemmatizer import Lemmatizer, read_index, read_exc
@ -34,3 +35,14 @@ def test_noun_lemmas(lemmatizer):
assert do('planets') == set(['planet']) assert do('planets') == set(['planet'])
assert do('ring') == set(['ring']) assert do('ring') == set(['ring'])
assert do('axes') == set(['axis', 'axe', 'ax']) assert do('axes') == set(['axis', 'axe', 'ax'])
def test_smart_quotes(lemmatizer):
do = lemmatizer.punct
assert do('“') == set(['``'])
assert do('“') == set(['``'])
def test_smart_quotes(lemmatizer):
do = lemmatizer.punct
assert do('–') == set(["--"])