Merge branch 'master' of https://github.com/explosion/spaCy

spacy/tests/regression/test_issue693.py

@@ -0,0 +1,19 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+import pytest
+
+
+@pytest.mark.xfail
+@pytest.mark.models
+def test_issue693(EN):
+    """Test that doc.noun_chunks parses the complete sentence."""
+
+    text1 = "the TopTown International Airport Board and the Goodwill Space Exploration Partnership."
+    text2 = "the Goodwill Space Exploration Partnership and the TopTown International Airport Board."
+    doc1 = EN(text1)
+    doc2 = EN(text2)
+    chunks1 = [chunk for chunk in doc1.noun_chunks]
+    chunks2 = [chunk for chunk in doc2.noun_chunks]
+    assert len(chunks1) == 2
+    assert len(chunks2) == 2

spacy/tests/regression/test_issue704.py

@@ -0,0 +1,14 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+import pytest
+
+
+@pytest.mark.models
+def test_issue704(EN):
+    """Test that sentence boundaries are detected correctly."""
+
+    text = '“Atticus said to Jem one day, “I’d rather you shot at tin cans in the backyard, but I know you’ll go after birds. Shoot all the blue jays you want, if you can hit ‘em, but remember it’s a sin to kill a mockingbird.”'
+    doc = EN(text)
+    sents = [sent for sent in doc.sents]
+    assert len(sents) == 3