From ee97fd3cb4b3fe5d62a28e8cd936073d11678bbf Mon Sep 17 00:00:00 2001
From: ines <ines@ines.io>
Date: Sat, 11 Nov 2017 00:14:03 +0100
Subject: [PATCH] Add regression test for #1547

---
 spacy/tests/regression/test_issue1547.py | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)
 create mode 100644 spacy/tests/regression/test_issue1547.py

diff --git a/spacy/tests/regression/test_issue1547.py b/spacy/tests/regression/test_issue1547.py
new file mode 100644
index 000000000..aa7076dd3
--- /dev/null
+++ b/spacy/tests/regression/test_issue1547.py
@@ -0,0 +1,17 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+import pytest
+
+from ...vocab import Vocab
+from ...tokens import Doc, Span
+
+
+@pytest.mark.xfail
+def test_issue1547():
+    """Test that entity labels still match after merging tokens."""
+    words = ['\n', 'worda', '.', '\n', 'wordb', '-', 'Biosphere', '2', '-', ' \n']
+    doc = Doc(Vocab(), words=words)
+    doc.ents = [Span(doc, 6, 8, label=doc.vocab.strings['PRODUCT'])]
+    doc[5:7].merge()
+    assert [ent.text for ent in doc.ents]