Add tests for Doc creation

spacy/tests/doc/test_creation.py

@@ -0,0 +1,37 @@
+'''Test Doc sets up tokens correctly.'''
+from __future__ import unicode_literals
+import pytest
+
+from ...vocab import Vocab
+from ...tokens.doc import Doc
+from ...lemmatizerlookup import Lemmatizer
+
+
+@pytest.fixture
+def lemmatizer():
+    return Lemmatizer({'dogs': 'dog', 'boxen': 'box', 'mice': 'mouse'})
+
+
+@pytest.fixture
+def vocab(lemmatizer):
+    return Vocab(lemmatizer=lemmatizer)
+
+
+def test_empty_doc(vocab):
+    doc = Doc(vocab)
+    assert len(doc) == 0
+
+
+def test_single_word(vocab):
+    doc = Doc(vocab, words=['a'])
+    assert doc.text == 'a '
+    doc = Doc(vocab, words=['a'], spaces=[False])
+    assert doc.text == 'a'
+
+
+def test_lookup_lemmatization(vocab):
+    doc = Doc(vocab, words=['dogs', 'dogses'])
+    assert doc[0].text == 'dogs'
+    assert doc[0].lemma_ == 'dog'
+    assert doc[1].text == 'dogses'
+    assert doc[1].lemma_ == 'dogses'