From 69eab727d7fbb9c766ed42a0fa07ba6c2851cebd Mon Sep 17 00:00:00 2001
From: Magnus Burton <magnus.burton@hotmail.com>
Date: Thu, 19 Jan 2017 14:08:52 +0100
Subject: [PATCH] Added loops to handle contractions with verbs

---
 spacy/sv/tokenizer_exceptions.py | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/spacy/sv/tokenizer_exceptions.py b/spacy/sv/tokenizer_exceptions.py
index 43732612f..a7fc33b18 100644
--- a/spacy/sv/tokenizer_exceptions.py
+++ b/spacy/sv/tokenizer_exceptions.py
@@ -4,6 +4,26 @@ from __future__ import unicode_literals
 from ..symbols import *
 from ..language_data import PRON_LEMMA
 
+# Verbs
+
+for verb_data in [
+    {ORTH: "driver"},
+    {ORTH: "kör"},
+    {ORTH: "hörr", LEMMA: "hör"},
+    {ORTH: "fattar"},
+    {ORTH: "hajar", LEMMA: "förstår"},
+    {ORTH: "lever"},
+    {ORTH: "serr", LEMMA: "ser"},
+    {ORTH: "fixar"}
+]:
+    verb_data_tc = dict(verb_data)
+    verb_data_tc[ORTH] = verb_data_tc[ORTH].title()
+
+    for data in [verb_data, verb_data_tc]:
+        EXC[data[ORTH] + "u"] = [
+            dict(data),
+            {ORTH: "u", LEMMA: PRON_LEMMA, NORM: "du"}
+        ]
 
 TOKENIZER_EXCEPTIONS = {
     "jan.": [