From 08e29519a62900d6ed6efe52f73476606aab163d Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal@gmail.com>
Date: Sat, 10 Oct 2015 16:03:13 +1100
Subject: [PATCH 1/4] * Add test for how spaces are attached by the parser.

---
 tests/parser/test_space_attachment.py | 12 ++++++++++++
 1 file changed, 12 insertions(+)
 create mode 100644 tests/parser/test_space_attachment.py

diff --git a/tests/parser/test_space_attachment.py b/tests/parser/test_space_attachment.py
new file mode 100644
index 000000000..73cf22cea
--- /dev/null
+++ b/tests/parser/test_space_attachment.py
@@ -0,0 +1,12 @@
+from __future__ import unicode_literals
+
+import pytest
+
+@pytest.mark.models
+def test_space_attachment(EN):
+    sentence = 'This is a test.\nTo ensure  spaces are attached well.'
+    doc = EN(sentence)
+
+    for word in doc:
+        if word.is_space:
+            assert word.head.i == (word.i - 1)

From 693dd065479481ba4296fa932b913315b3a40b8d Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal@gmail.com>
Date: Sun, 11 Oct 2015 14:29:12 +1100
Subject: [PATCH 2/4] * Add basic, non-data dependent class creation tests,
 without depending on pytest. For use in debugging MS build issues, for Issue
 #132

---
 tests/test_basic_create.py | 88 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 88 insertions(+)
 create mode 100644 tests/test_basic_create.py

diff --git a/tests/test_basic_create.py b/tests/test_basic_create.py
new file mode 100644
index 000000000..c170403fa
--- /dev/null
+++ b/tests/test_basic_create.py
@@ -0,0 +1,88 @@
+"""Some quick tests that don't depend on data files or on pytest, for debugging the
+MS windows build issues."""
+from __future__ import print_function, unicode_literals
+
+import unittest
+import re
+
+from spacy.lemmatizer import Lemmatizer
+from spacy.morphology import Morphology
+from spacy.strings import StringStore
+from spacy.vocab import Vocab
+from spacy.tokenizer import Tokenizer
+from spacy.syntax.arc_eager import ArcEager
+from spacy._ml import Model
+from spacy.tagger import Tagger
+from spacy.syntax.parser import Parser
+
+
+class TestStringStore(unittest.TestCase):
+    def test_encode_decode(self):
+        strings = StringStore()
+        hello_id = strings[u'Hello']
+        world_id = strings[u'World']
+
+        self.assertNotEqual(hello_id, world_id)
+        
+        self.assertEqual(strings[hello_id], u'Hello')
+        self.assertEqual(strings[world_id], u'World')
+
+        self.assertEqual(strings[u'Hello'], hello_id)
+        self.assertEqual(strings[u'World'], world_id)
+
+
+class TestMorphology(unittest.TestCase):
+    def test_create(self):
+        lemmatizer = Lemmatizer({}, {}, {})
+        strings = StringStore()
+        lemmatizer = Lemmatizer({}, {}, {})
+        morphology = Morphology(strings, {}, lemmatizer)
+
+
+class TestVocab(unittest.TestCase):
+    def test_create(self):
+        vocab = Vocab()
+
+    def test_get_lexeme(self):
+        vocab = Vocab()
+        lexeme = vocab[u'Hello']
+        assert lexeme.orth_ == u'Hello'
+
+
+class TestTokenizer(unittest.TestCase):
+    def test_create(self):
+        vocab = Vocab()
+        dummy_re = re.compile(r'sklfb;s')
+        tokenizer = Tokenizer(vocab, {}, dummy_re, dummy_re, dummy_re)
+        doc = tokenizer(u'I am a document.')
+        
+        self.assertEqual(len(doc), 4)
+
+
+class TestTagger(unittest.TestCase):
+    def test_create(self):
+        vocab = Vocab()
+        templates = ((1,),)
+        model = Model(vocab.morphology.n_tags, templates, model_loc=None)
+        tagger = Tagger(vocab, model)
+
+
+class TestParser(unittest.TestCase):
+    def test_create(self):
+        vocab = Vocab()
+        templates = ((1,),)
+        labels_by_action = {0: ['One', 'Two'], 1: ['Two', 'Three']}
+        transition_system = ArcEager(vocab.strings, labels_by_action)
+        model = Model(vocab.morphology.n_tags, templates, model_loc=None)
+        
+        parser = Parser(vocab.strings, transition_system, model)
+
+
+class TestMatcher(unittest.TestCase):
+    def test_create(self):
+        vocab = Vocab()
+        matcher = Matcher(vocab, [])
+
+
+if __name__ == '__main__':
+    unittest.main()

From 1f8f81f0c8e8607da9c54d990f680060308d6a9e Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal@gmail.com>
Date: Sun, 11 Oct 2015 14:38:21 +1100
Subject: [PATCH 3/4] * Fix missing import

---
 tests/test_basic_create.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tests/test_basic_create.py b/tests/test_basic_create.py
index c170403fa..15e8f353f 100644
--- a/tests/test_basic_create.py
+++ b/tests/test_basic_create.py
@@ -14,6 +14,7 @@ from spacy.syntax.arc_eager import ArcEager
 from spacy._ml import Model
 from spacy.tagger import Tagger
 from spacy.syntax.parser import Parser
+from spacy.matcher import Matcher
 
 
 class TestStringStore(unittest.TestCase):

From cc92f3f0ed6f7456d300d2a581df1542accfed08 Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal@gmail.com>
Date: Sun, 11 Oct 2015 14:59:12 +1100
Subject: [PATCH 4/4] * Fix Matcher test

---
 tests/test_basic_create.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/test_basic_create.py b/tests/test_basic_create.py
index 15e8f353f..d31a35bed 100644
--- a/tests/test_basic_create.py
+++ b/tests/test_basic_create.py
@@ -82,7 +82,7 @@ class TestParser(unittest.TestCase):
 class TestMatcher(unittest.TestCase):
     def test_create(self):
         vocab = Vocab()
-        matcher = Matcher(vocab, [])
+        matcher = Matcher(vocab, {})
 
 
 if __name__ == '__main__':