add unit tests where we don't ignore stopwords

nltk · Nov 17, 2017 · c818bb5 · c818bb5
1 parent 49d76a2
commit c818bb5
Showing 1 changed file with 13 additions and 0 deletions.
diff --git a/nltk/test/unit/test_stem.py b/nltk/test/unit/test_stem.py
@@ -15,6 +15,7 @@ def test_arabic(self):
         this unit testing for test the snowball arabic light stemmer
         this stemmer deals with prefixes and suffixes
         """
+        # Test where the ignore_stopwords=True.
         ar_stemmer = SnowballStemmer("arabic", True)
         assert ar_stemmer.stem('الْعَرَبِــــــيَّة') == "عرب"
         assert ar_stemmer.stem("العربية") == "عرب"
@@ -25,6 +26,18 @@ def test_arabic(self):
         assert ar_stemmer.stem("الطالبون") == "طالب"
         assert ar_stemmer.stem("اللذان") == "اللذان"
         assert ar_stemmer.stem("من") == "من"
+        #Test where the ignore_stopwords=False.
+        ar_stemmer = SnowballStemmer("arabic", False)
+        assert ar_stemmer.stem("اللذان") == "اللذ" # this is a stop word
+        assert ar_stemmer.stem("الطالبات") == "طالب"
+        assert ar_stemmer.stem("الكلمات") == "كلم"
+        # test where create the arabic stemmer without given init value to ignore_stopwords
+        ar_stemmer = SnowballStemmer("arabic")
+        assert ar_stemmer.stem('الْعَرَبِــــــيَّة') == "عرب"
+        assert ar_stemmer.stem("العربية") == "عرب"
+        assert ar_stemmer.stem("فقالوا") == "قال"
+        assert ar_stemmer.stem("الطالبات") == "طالب"
+        assert ar_stemmer.stem("الكلمات") == "كلم"
 
     def test_russian(self):
         # Russian words both consisting of Cyrillic