From 654fe447b11676ee004df8f5f74bc1f94b000304 Mon Sep 17 00:00:00 2001
From: ines <ines@ines.io>
Date: Sun, 5 Feb 2017 11:47:07 +0100
Subject: [PATCH] Add Swedish tokenizer tests (see #807)

---
 spacy/tests/sv/__init__.py       |  0
 spacy/tests/sv/test_tokenizer.py | 24 ++++++++++++++++++++++++
 2 files changed, 24 insertions(+)
 create mode 100644 spacy/tests/sv/__init__.py
 create mode 100644 spacy/tests/sv/test_tokenizer.py

diff --git a/spacy/tests/sv/__init__.py b/spacy/tests/sv/__init__.py
new file mode 100644
index 000000000..e69de29bb
diff --git a/spacy/tests/sv/test_tokenizer.py b/spacy/tests/sv/test_tokenizer.py
new file mode 100644
index 000000000..c3305ca7b
--- /dev/null
+++ b/spacy/tests/sv/test_tokenizer.py
@@ -0,0 +1,24 @@
+# encoding: utf8
+from __future__ import unicode_literals
+
+import pytest
+
+
+SV_TOKEN_EXCEPTION_TESTS = [
+    ('Smörsåsen används bl.a. till fisk', ['Smörsåsen', 'används', 'bl.a.', 'till', 'fisk']),
+    ('Jag kommer först kl. 13 p.g.a. diverse förseningar', ['Jag', 'kommer', 'först', 'kl.', '13', 'p.g.a.', 'diverse', 'förseningar'])
+]
+
+
+@pytest.mark.parametrize('text,expected_tokens', SV_TOKEN_EXCEPTION_TESTS)
+def test_tokenizer_handles_exception_cases(sv_tokenizer, text, expected_tokens):
+    tokens = sv_tokenizer(text)
+    token_list = [token.text for token in tokens if not token.is_space]
+    assert expected_tokens == token_list
+
+
+@pytest.mark.parametrize('text', ["driveru", "hajaru", "Serru", "Fixaru"])
+def test_tokenizer_handles_verb_exceptions(sv_tokenizer, text):
+    tokens = sv_tokenizer(text)
+    assert len(tokens) == 2
+    assert tokens[1].text == "u"