Add regression test for #4120

spacy/tests/regression/test_issue4120.py

@@ -0,0 +1,27 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+import pytest
+from spacy.matcher import Matcher
+from spacy.tokens import Doc
+
+
+@pytest.mark.xfail
+def test_issue4120(en_vocab):
+    """Test that matches without a final {OP: ?} token are returned."""
+    matcher = Matcher(en_vocab)
+    matcher.add("TEST", None, [{"ORTH": "a"}, {"OP": "?"}])
+    doc1 = Doc(en_vocab, words=["a"])
+    assert len(matcher(doc1)) == 1  # works
+    doc2 = Doc(en_vocab, words=["a", "b", "c"])
+    assert len(matcher(doc2)) == 2  # doesn't work
+
+    matcher = Matcher(en_vocab)
+    matcher.add("TEST", None, [{"ORTH": "a"}, {"OP": "?"}, {"ORTH": "b"}])
+    doc3 = Doc(en_vocab, words=["a", "b", "b", "c"])
+    assert len(matcher(doc3)) == 2  # works
+
+    matcher = Matcher(en_vocab)
+    matcher.add("TEST", None, [{"ORTH": "a"}, {"OP": "?"}, {"ORTH": "b", "OP": "?"}])
+    doc4 = Doc(en_vocab, words=["a", "b", "b", "c"])
+    assert len(matcher(doc4)) == 3  # doesn't work