From a7294596a09f0d0db6fec2c31eeaa996ead72356 Mon Sep 17 00:00:00 2001
From: kdavis-mozilla <kdavis@mozilla.com>
Date: Thu, 13 Dec 2018 06:56:32 +0100
Subject: [PATCH] Fixed #14 (Some sentences contain URL encoded text)

---
 src/corporacreator/preprocessors/common.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/src/corporacreator/preprocessors/common.py b/src/corporacreator/preprocessors/common.py
index 110792a..9e77d07 100644
--- a/src/corporacreator/preprocessors/common.py
+++ b/src/corporacreator/preprocessors/common.py
@@ -1,3 +1,5 @@
+from urllib.parse import unquote
+
 def common(sentence):
     """Cleans up the passed sentence in a language independent manner, removing or reformatting invalid data.
 
@@ -7,5 +9,7 @@ def common(sentence):
     Returns:
       (str): Cleaned up sentence.
     """
+    # Decode any URL encoded elements of sentence
+    sentence = unquote(sentence)
     # TODO: Clean up data in a language independent manner
     return sentence