From 7f551050b13177023c4b453fa00dbf2ada6db255 Mon Sep 17 00:00:00 2001
From: Ines Montani <ines@ines.io>
Date: Tue, 16 Jul 2019 13:07:35 +0200
Subject: [PATCH] Add regression test for #3972

---
 spacy/tests/regression/test_issue3972.py | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)
 create mode 100644 spacy/tests/regression/test_issue3972.py

diff --git a/spacy/tests/regression/test_issue3972.py b/spacy/tests/regression/test_issue3972.py
new file mode 100644
index 000000000..e82dff269
--- /dev/null
+++ b/spacy/tests/regression/test_issue3972.py
@@ -0,0 +1,18 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+import pytest
+from spacy.matcher import PhraseMatcher
+from spacy.tokens import Doc
+
+
+@pytest.mark.xfail
+def test_issue3972(en_vocab):
+    """Test that the PhraseMatcher returns duplicates for duplicate match IDs.
+    """
+    matcher = PhraseMatcher(en_vocab)
+    matcher.add("A", None, Doc(en_vocab, words=["New", "York"]))
+    matcher.add("B", None, Doc(en_vocab, words=["New", "York"]))
+    doc = Doc(en_vocab, words=["I", "live", "in", "New", "York"])
+    matches = matcher(doc)
+    assert len(matches) == 2