Modernise Doc array tests and don't depend on models

spacy/tests/tokens/test_array.py

@@ -1,38 +1,42 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+from ...attrs import ORTH, SHAPE, POS, DEP
+from ..util import get_doc
+
 import pytest
 
-from spacy import attrs
 
-
-def test_attr_of_token(EN):
-    text = u'An example sentence.'
-    tokens = EN(text, tag=True, parse=False)
-    example = EN.vocab[u'example']
+def test_array_attr_of_token(en_tokenizer, en_vocab):
+    text = "An example sentence"
+    tokens = en_tokenizer(text)
+    example = tokens.vocab["example"]
     assert example.orth != example.shape
-    feats_array = tokens.to_array((attrs.ORTH, attrs.SHAPE))
+    feats_array = tokens.to_array((ORTH, SHAPE))
+    assert feats_array[0][0] != feats_array[0][1]
     assert feats_array[0][0] != feats_array[0][1]
 
 
-@pytest.mark.models
-def test_tag(EN):
-    text = u'A nice sentence.'
-    tokens = EN(text)
-    assert tokens[0].tag != tokens[1].tag != tokens[2].tag != tokens[3].tag
-    feats_array = tokens.to_array((attrs.ORTH, attrs.TAG))
-    assert feats_array[0][1] == tokens[0].tag
-    assert feats_array[1][1] == tokens[1].tag
-    assert feats_array[2][1] == tokens[2].tag
-    assert feats_array[3][1] == tokens[3].tag
+def test_array_tag(en_tokenizer):
+    text = "A nice sentence."
+    tags = ['DET', 'ADJ', 'NOUN', 'PUNCT']
+    tokens = en_tokenizer(text)
+    doc = get_doc(tokens.vocab, [t.text for t in tokens], tags=tags)
+    assert doc[0].pos != doc[1].pos != doc[2].pos != doc[3].pos
+    feats_array = doc.to_array((ORTH, POS))
+    assert feats_array[0][1] == doc[0].pos
+    assert feats_array[1][1] == doc[1].pos
+    assert feats_array[2][1] == doc[2].pos
+    assert feats_array[3][1] == doc[3].pos
 
 
-@pytest.mark.models
-def test_dep(EN):
-    text = u'A nice sentence.'
-    tokens = EN(text)
-    feats_array = tokens.to_array((attrs.ORTH, attrs.DEP))
-    assert feats_array[0][1] == tokens[0].dep
-    assert feats_array[1][1] == tokens[1].dep
-    assert feats_array[2][1] == tokens[2].dep
-    assert feats_array[3][1] == tokens[3].dep
+def test_array_dep(en_tokenizer):
+    text = "A nice sentence."
+    deps = ['det', 'amod', 'ROOT', 'punct']
+    tokens = en_tokenizer(text)
+    doc = get_doc(tokens.vocab, [t.text for t in tokens], deps=deps)
+    feats_array = doc.to_array((ORTH, DEP))
+    assert feats_array[0][1] == doc[0].dep
+    assert feats_array[1][1] == doc[1].dep
+    assert feats_array[2][1] == doc[2].dep
+    assert feats_array[3][1] == doc[3].dep