From 35100c8bddc830998558e30f4a0b000f6d78e7f0 Mon Sep 17 00:00:00 2001
From: Michael Wallin <michaelmwallin@gmail.com>
Date: Sat, 4 Feb 2017 16:21:34 +0200
Subject: [PATCH 1/2] [issue 805] Add regression test and the required fixture

---
 spacy/tests/conftest.py                 |  5 +++++
 spacy/tests/regression/test_issue805.py | 15 +++++++++++++++
 2 files changed, 20 insertions(+)
 create mode 100644 spacy/tests/regression/test_issue805.py

diff --git a/spacy/tests/conftest.py b/spacy/tests/conftest.py
index 3d9e0adcc..d21d7d313 100644
--- a/spacy/tests/conftest.py
+++ b/spacy/tests/conftest.py
@@ -68,6 +68,11 @@ def fi_tokenizer():
     return Finnish.Defaults.create_tokenizer()
 
 
+@pytest.fixture
+def sv_tokenizer():
+    return Swedish.Defaults.create_tokenizer()
+
+
 @pytest.fixture
 def stringstore():
     return StringStore()
diff --git a/spacy/tests/regression/test_issue805.py b/spacy/tests/regression/test_issue805.py
new file mode 100644
index 000000000..f23aff426
--- /dev/null
+++ b/spacy/tests/regression/test_issue805.py
@@ -0,0 +1,15 @@
+# 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_issue805(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

From d25556bf8093ea69dc8c64bd769015a930bc0497 Mon Sep 17 00:00:00 2001
From: Michael Wallin <michaelmwallin@gmail.com>
Date: Sat, 4 Feb 2017 16:22:21 +0200
Subject: [PATCH 2/2] [issue 805] Fix issue

---
 spacy/sv/language_data.py        | 6 ++++--
 spacy/sv/tokenizer_exceptions.py | 1 -
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/spacy/sv/language_data.py b/spacy/sv/language_data.py
index a4a657c33..324351d06 100644
--- a/spacy/sv/language_data.py
+++ b/spacy/sv/language_data.py
@@ -5,12 +5,14 @@ from .. import language_data as base
 from ..language_data import update_exc, strings_to_exc
 
 from .stop_words import STOP_WORDS
+from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS, ORTH_ONLY
 
 
 STOP_WORDS = set(STOP_WORDS)
 
-
-TOKENIZER_EXCEPTIONS = strings_to_exc(base.EMOTICONS)
+TOKENIZER_EXCEPTIONS = dict(TOKENIZER_EXCEPTIONS)
+update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(ORTH_ONLY))
+update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.EMOTICONS))
 update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.ABBREVIATIONS))
 
 
diff --git a/spacy/sv/tokenizer_exceptions.py b/spacy/sv/tokenizer_exceptions.py
index d8d4e8823..b9705c39c 100644
--- a/spacy/sv/tokenizer_exceptions.py
+++ b/spacy/sv/tokenizer_exceptions.py
@@ -107,7 +107,6 @@ ORTH_ONLY = [
     "p.g.a.",
     "ref.",
     "resp.",
-    "s.",
     "s.a.s.",
     "s.k.",
     "st.",