Fixed problem with code

code.py

@@ -19,10 +19,10 @@ def create_train(input,output1,output0):
 def tokenize(input,output):
     with open(input,'rt',encoding="utf8") as input_f, open(output,'w',encoding="utf-8") as file:
         for line in input_f:
-            text = line.lower()
-            text = re.sub(r'\\n+', " ", text)
-            text = re.sub(r'http\S+', " ", text)
-            text = re.sub(r'\/[a-z]\/', " ", text)
+            #text = line.lower()
+            #text = re.sub(r'\\n+', " ", text)
+            text = re.sub(r'http\S+', " ", line)
+            #text = re.sub(r'\/[a-z]\/', " ", text)
             #text = re.sub(r'\s{2,}', " ", text)
             #text = re.sub(r'\W\w{1,3}\W|\A\w{1,3}\W', " ", text)
             #text = re.sub(r'\W\w{1,3}\W|\A\w{1,3}\W', " ", text)