no python2 nonsense

chatter/chatterbot/comparisons.py

@@ -58,19 +58,14 @@ class LevenshteinDistance(Comparator):
         :rtype: float
         """
 
-        PYTHON = sys.version_info[0]
-
         # Return 0 if either statement has a falsy text value
         if not statement.text or not other_statement.text:
             return 0
 
         # Get the lowercase version of both strings
-        if PYTHON < 3:
+
-            statement_text = unicode(statement.text.lower()) # NOQA
+        statement_text = str(statement.text.lower())
-            other_statement_text = unicode(other_statement.text.lower()) # NOQA
+        other_statement_text = str(other_statement.text.lower())
-        else:
-            statement_text = str(statement.text.lower())
-            other_statement_text = str(other_statement.text.lower())
 
         similarity = SequenceMatcher(
             None,

chatter/chatterbot/conversation.py

@@ -33,13 +33,6 @@ class Statement(StatementMixin):
         except UnicodeEncodeError:
             pass
 
-        # Prefer decoded utf8-strings in Python 2.7
-        if sys.version_info[0] < 3:
-            try:
-                text = text.decode('utf-8')
-            except UnicodeEncodeError:
-                pass
-
         self.text = text
         self.tags = kwargs.pop('tags', [])
         self.in_response_to = kwargs.pop('in_response_to', [])

chatter/chatterbot/ext/sqlalchemy_app/types.py

@@ -13,9 +13,4 @@ class UnicodeString(TypeDecorator):
         Coerce Python bytestrings to unicode before
         saving them to the database.
         """
-        import sys
-
-        if sys.version_info[0] < 3:
-            if isinstance(value, str):
-                value = value.decode('utf-8')
         return value

chatter/chatterbot/input/variable_input_type_adapter.py

@@ -14,10 +14,8 @@ class VariableInputTypeAdapter(InputAdapter):
     def detect_type(self, statement):
         import sys
 
-        if sys.version_info[0] < 3:
+
-            string_types = basestring # NOQA
+        string_types = str
-        else:
-            string_types = str
 
         if hasattr(statement, 'text'):
             return self.OBJECT

chatter/chatterbot/preprocessors.py

@@ -30,11 +30,7 @@ def unescape_html(chatbot, statement):
     import sys
 
     # Replace HTML escape characters
-    if sys.version_info[0] < 3:
+    import html
-        from HTMLParser import HTMLParser
-        html = HTMLParser()
-    else:
-        import html
 
     statement.text = html.unescape(statement.text)
 
@@ -49,9 +45,6 @@ def convert_to_ascii(chatbot, statement):
     import unicodedata
     import sys
 
-    # Normalize unicode characters
-    if sys.version_info[0] < 3:
-        statement.text = unicode(statement.text) # NOQA
 
     text = unicodedata.normalize('NFKD', statement.text)
     text = text.encode('ascii', 'ignore').decode('utf-8')

chatter/chatterbot/trainers.py

@@ -393,10 +393,10 @@ class UbuntuCorpusTrainer(Trainer):
 
         file_kwargs = {}
 
-        if sys.version_info[0] > 2:
+
-            # Specify the encoding in Python versions 3 and up
+        # Specify the encoding in Python versions 3 and up
-            file_kwargs['encoding'] = 'utf-8'
+        file_kwargs['encoding'] = 'utf-8'
-            # WARNING: This might fail to read a unicode corpus file in Python 2.x
+        # WARNING: This might fail to read a unicode corpus file in Python 2.x
 
         for file in glob.iglob(extracted_corpus_path):
             self.logger.info('Training from: {}'.format(file))

chatter/chatterbot/utils.py

@@ -77,15 +77,8 @@ def input_function():
     """
     import sys
 
-    if sys.version_info[0] < 3:
-        user_input = str(raw_input()) # NOQA
 
-        # Avoid problems using format strings with unicode characters
+    user_input = input() # NOQA
-        if user_input:
-            user_input = user_input.decode('utf-8')
-
-    else:
-        user_input = input() # NOQA
 
     return user_input