explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 17:36:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

unicode string for python 2.7

Browse Source
This commit is contained in:
svlandeg 2019-04-02 13:52:07 +02:00
parent eca9cc5417
commit 673c81bbb4
2 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/lang/en/stop_words.py
View File

@ -70,6 +70,6 @@ yet you your yours yourself yourselves
) )
for hyphen in ["'", "`", "‘", "´", "’"]: for hyphen in ["'", "`", "‘", "´", "’"]:
for stopword in "n't 'd 'll 'm 're 's 've".split(): for stopword in u"n't 'd 'll 'm 're 's 've".split():
STOP_WORDS.add(stopword.replace("'", hyphen)) STOP_WORDS.add(stopword.replace("'", hyphen))

8
spacy/tests/regression/test_issue3521.py
View File

@ -4,10 +4,10 @@ import pytest
@pytest.mark.parametrize( @pytest.mark.parametrize(
"word", "word",
[ [
"don't", u"don't",
"don’t", u"don’t",
"I'd", u"I'd",
"I’d", u"I’d",
], ],
) )
def test_issue3521(en_tokenizer, word): def test_issue3521(en_tokenizer, word):