explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-11-04 01:48:04 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix french lemmatization (#3180)

Browse Source
This commit is contained in:
foufaster 2019-01-27 06:01:30 +01:00 committed by Matthew Honnibal
parent f9ca09caa0
commit 8bd85fd9d5
2 changed files with 11 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/lang/fr/lemmatizer/lemmatizer.py
View File

@ -131,7 +131,7 @@ def lemmatize(string, index, exceptions, rules):
if not forms: if not forms:
forms.extend(oov_forms) forms.extend(oov_forms)
if not forms and string in LOOKUP.keys(): if not forms and string in LOOKUP.keys():
forms.append(LOOKUP[string]) forms.append(LOOKUP[string][0])
if not forms: if not forms:
forms.append(string) forms.append(string)
return list(set(forms)) return list(set(forms))

10
spacy/tests/regression/test_issue3178.py Normal file
View File

@ -0,0 +1,10 @@
from __future__ import unicode_literals
import pytest
import spacy
@pytest.mark.models('fr')
def test_issue1959(FR):
texts = ['Je suis la mauvaise herbe', "Me, myself and moi"]
for text in texts:
FR(text)