[#4529] fix: gold pyx (#4530)

* fix: gold pyx

* remove print

* skip test in python2

* Add unicode declarations and don't skip test on Python 2

spacy/gold.pyx

@@ -636,9 +636,9 @@ cdef class GoldParse:
             if morphology is None:
                 morphology = [None for _ in words]
             if entities is None:
-                entities = ["-" for _ in doc]
+                entities = ["-" for _ in words]
             elif len(entities) == 0:
-                entities = ["O" for _ in doc]
+                entities = ["O" for _ in words]
             else:
                 # Translate the None values to '-', to make processing easier.
                 # See Issue #2603
@@ -701,7 +701,9 @@ cdef class GoldParse:
                             self.heads[i] = i+1
                             self.labels[i] = "subtok"
                         else:
-                            self.heads[i] = self.gold_to_cand[heads[i2j_multi[i]]]
+                            head_i = heads[i2j_multi[i]]
+                            if head_i:
+                                self.heads[i] = self.gold_to_cand[head_i]
                             self.labels[i] = deps[i2j_multi[i]]
                         # Now set NER...This is annoying because if we've split
                         # got an entity word split into two, we need to adjust the

spacy/tests/regression/test_issue4529.py

@@ -0,0 +1,13 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+import pytest
+from spacy.gold import GoldParse
+
+
+@pytest.mark.parametrize(
+    "text,words", [("A'B C", ["A", "'", "B", "C"]), ("A-B", ["A-B"])]
+)
+def test_gold_misaligned(en_tokenizer, text, words):
+    doc = en_tokenizer(text)
+    GoldParse(doc, words=words)