fixing Issue #3521 by adding all hyphen variants for each stopword

spacy/lang/en/stop_words.py

@@ -39,7 +39,7 @@ made make many may me meanwhile might mine more moreover most mostly move much
 must my myself
 
 name namely neither never nevertheless next nine no nobody none noone nor not
-nothing now nowhere n't
+nothing now nowhere 
 
 of off often on once one only onto or other others otherwise our ours ourselves
 out over own
@@ -66,7 +66,10 @@ whereafter whereas whereby wherein whereupon wherever whether which while
 whither who whoever whole whom whose why will with within without would
 
 yet you your yours yourself yourselves
-
-'d 'll 'm 're 's 've
 """.split()
 )
+
+for hyphen in ["'", "`", "‘", "´", "’"]:
+    for stopword in "n't 'd 'll 'm 're 's 've".split():
+        STOP_WORDS.add(stopword.replace("'", hyphen))
+

spacy/tests/regression/test_issue3521.py

@@ -1,7 +1,5 @@
 import pytest
 
-from spacy.lang.en import English
-
 
 @pytest.mark.parametrize(
     "word",
@@ -12,9 +10,7 @@ from spacy.lang.en import English
         "I’d",
     ],
 )
-def test_issue3521(fr_tokenizer, word):
+def test_issue3521(en_tokenizer, word):
-    nlp = English()
+    tok = en_tokenizer(word)[1]
-
+    # 'not' and 'would' should be stopwords, also in their abbreviated forms
-    tok = nlp(word)[1]
     assert tok.is_stop
-