* Upd tests

tests/parser/test_ner.py

@@ -1,4 +1,6 @@
+import pytest
 
+@pytest.mark.models
 def test_simple_types(EN):
     tokens = EN(u'Mr. Best flew to New York on Saturday morning.')
     ents = list(tokens.ents)

tests/serialize/test_huffman.py

@@ -96,6 +96,7 @@ def test_rosetta():
     assert my_exp_len == py_exp_len
 
 
+@pytest.mark.slow
 def test_vocab(EN):
     codec = HuffmanCodec([(w.orth, numpy.exp(w.prob)) for w in EN.vocab])
     expected_length = 0
@@ -105,6 +106,7 @@ def test_vocab(EN):
     assert 8 < expected_length < 15
 
 
+@pytest.mark.slow
 def test_freqs():
     freqs = []
     words = []

tests/serialize/test_packer.py

@@ -120,5 +120,3 @@ def test_packer_annotated(tokenizer):
     assert [t.tag_ for t in result] == ['DT', 'NN', 'VBD']
     assert [t.dep_ for t in result] == ['det', 'nsubj', 'ROOT']
     assert [(t.head.i - t.i) for t in result] == [1, 1, 0]
-
-

tests/spans/test_merge.py

@@ -1,6 +1,8 @@
 from __future__ import unicode_literals
+import pytest
 
 
+@pytest.mark.models
 def test_merge_tokens(EN):
     tokens = EN(u'Los Angeles start.')
     assert len(tokens) == 4
@@ -12,6 +14,7 @@ def test_merge_tokens(EN):
     assert tokens[0].head.orth_ == 'start'
 
 
+@pytest.mark.models
 def test_merge_heads(EN):
     tokens = EN(u'I found a pilates class near work.')
     assert len(tokens) == 8

tests/test_docs.py

@@ -1,8 +1,9 @@
 # -*- coding: utf-8 -*-
 """Sphinx doctest is just too hard. Manually paste doctest examples here"""
 from spacy.en.attrs import IS_LOWER
+import pytest
 
-
+@pytest.mark.models
 def test_1():
     import spacy.en
     from spacy.parts_of_speech import ADV
@@ -21,6 +22,7 @@ def test_1():
     assert o == -11.07155704498291
 
 
+@pytest.mark.models
 def test2():
     import spacy.en
     from spacy.parts_of_speech import ADV
@@ -41,6 +43,7 @@ def test2():
     -11.07155704498291
 
 
+@pytest.mark.models
 def test3():
     import spacy.en
     from spacy.parts_of_speech import ADV

tests/tokens/test_token_api.py

@@ -7,6 +7,7 @@ from spacy.en.attrs import IS_STOP
 import pytest
 
 
+@pytest.mark.models
 def test_strings(EN):
     tokens = EN(u'Give it back! He pleaded.')
     token = tokens[0]

tests/tokens/test_tokens_api.py

@@ -5,7 +5,7 @@ from spacy.tokens import Doc
 import pytest
 
 
-def test_getitem(EN):
+def mest_getitem(EN):
     tokens = EN(u'Give it back! He pleaded.')
     assert tokens[0].orth_ == 'Give'
     assert tokens[-1].orth_ == '.'
@@ -13,10 +13,19 @@ def test_getitem(EN):
         tokens[len(tokens)]
 
 
-def test_serialize(EN):
+def mest_serialize(EN):
     tokens = EN(u'Give it back! He pleaded.')
-    packed = tokens.serialize()
-    new_tokens = Doc.deserialize(EN.vocab, packed)
+    packed = tokens.to_bytes()
+    new_tokens = Doc(EN.vocab).from_bytes(packed)
+    assert tokens.string == new_tokens.string
+    assert [t.orth_ for t in tokens] == [t.orth_ for t in new_tokens]
+    assert [t.orth for t in tokens] == [t.orth for t in new_tokens]
+
+
+def test_serialize_whitespace(EN):
+    tokens = EN(u' Give it back! He pleaded. ')
+    packed = tokens.to_bytes()
+    new_tokens = Doc(EN.vocab).from_bytes(packed)
     assert tokens.string == new_tokens.string
     assert [t.orth_ for t in tokens] == [t.orth_ for t in new_tokens]
     assert [t.orth for t in tokens] == [t.orth for t in new_tokens]

tests/tokens/test_vec.py

@@ -4,13 +4,14 @@ from spacy.en import English
 
 import pytest
 
-
+@pytest.mark.vectors
 def test_vec(EN):
     hype = EN.vocab['hype']
     assert hype.orth_ == 'hype'
     assert 0.08 >= hype.repvec[0] > 0.07
 
 
+@pytest.mark.vectors
 def test_capitalized(EN):
     hype = EN.vocab['Hype']
     assert hype.orth_ == 'Hype'