fix for piskvorky#520: raise KeyError when no matching doctag

gensim/models/doc2vec.py

@@ -305,12 +305,12 @@ def trained_item(self, indexed_tuple):
         returned by indexed_doctags()); a no-op for this implementation"""
         pass
 
-    def _int_index(self, index, missing=None):
+    def _int_index(self, index):
         """Return int index for either string or int index"""
         if isinstance(index, int):
             return index
         else:
-            return self.max_rawint + 1 + self.doctags[index].offset if index in self.doctags else missing
+            return self.max_rawint + 1 + self.doctags[index].offset
 
     def _key_index(self, i_index, missing=None):
         """Return string index for given int index, if available"""

gensim/test/test_doc2vec.py

@@ -89,6 +89,16 @@ def test_int_doctags(self):
         self.assertEqual(model.docvecs[0].shape, (300,))
         self.assertRaises(KeyError, model.__getitem__, '_*0')
 
+    def test_missing_string_doctag(self):
+        """Test doc2vec doctag alternatives"""
+        corpus = list(DocsLeeCorpus(True))
+        # force duplicated tags
+        corpus = corpus[0:10] + corpus
+
+        model = doc2vec.Doc2Vec(min_count=1)
+        model.build_vocab(corpus)
+        self.assertRaises(KeyError, model.docvecs.__getitem__, 'not_a_tag')
+
     def test_string_doctags(self):
         """Test doc2vec doctag alternatives"""
         corpus = list(DocsLeeCorpus(True))