Fix BasicTokenizer to respect never_split parameters (#2557)

* add failing test

* fix call to _run_split_on_punc

* format with black

src/transformers/tokenization_bert.py

@@ -341,7 +341,7 @@ class BasicTokenizer(object):
             if self.do_lower_case and token not in never_split:
                 token = token.lower()
                 token = self._run_strip_accents(token)
-            split_tokens.extend(self._run_split_on_punc(token))
+            split_tokens.extend(self._run_split_on_punc(token, never_split))
 
         output_tokens = whitespace_tokenize(" ".join(split_tokens))
         return output_tokens