From c283e9edfe9618e5b48193dad4b0b1844ffee72a Mon Sep 17 00:00:00 2001
From: Jim O'Regan <jaoregan@tcd.ie>
Date: Mon, 11 Sep 2017 08:57:48 +0100
Subject: [PATCH] first stab at test

---
 spacy/tests/lang/ga/__init__.py       |  0
 spacy/tests/lang/ga/test_tokenizer.py | 18 ++++++++++++++++++
 2 files changed, 18 insertions(+)
 create mode 100644 spacy/tests/lang/ga/__init__.py
 create mode 100644 spacy/tests/lang/ga/test_tokenizer.py

diff --git a/spacy/tests/lang/ga/__init__.py b/spacy/tests/lang/ga/__init__.py
new file mode 100644
index 000000000..e69de29bb
diff --git a/spacy/tests/lang/ga/test_tokenizer.py b/spacy/tests/lang/ga/test_tokenizer.py
new file mode 100644
index 000000000..fe5cb0b2f
--- /dev/null
+++ b/spacy/tests/lang/ga/test_tokenizer.py
@@ -0,0 +1,18 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+import pytest
+
+
+SV_TOKEN_EXCEPTION_TESTS = [
+    ('B\'fhearr fanacht as amharc', ['B\'', 'fhearr', 'fanacht', 'as', 'amharc']),
+    ('Daoine a bhfuil Gaeilge acu, m.sh. tusa agus mise', ['Daoine', 'a', 'bhfuil', 'Gaeilge', 'acu', ',', 'm.sh.', 'tusa', 'agus', 'mise'])
+]
+
+
+@pytest.mark.parametrize('text,expected_tokens', GA_TOKEN_EXCEPTION_TESTS)
+def test_tokenizer_handles_exception_cases(ga_tokenizer, text, expected_tokens):
+    tokens = ga_tokenizer(text)
+    token_list = [token.text for token in tokens if not token.is_space]
+    assert expected_tokens == token_list
+