Update tests after utility module change

chatterbot/adapters/input/gitter.py

@@ -1,7 +1,7 @@
 from __future__ import unicode_literals
+from time import sleep
 from chatterbot.adapters.input import InputAdapter
 from chatterbot.conversation import Statement
-from time import sleep
 import requests
 
 
@@ -120,7 +120,7 @@ def remove_mentions(self, text):
         Return a string that has no leading mentions.
         """
         import re
-        from chatterbot.utils.clean import clean_whitespace
+        from chatterbot.utils import clean_whitespace
         text_without_mentions = re.sub(r'@\S+', '', text)
         return clean_whitespace(text_without_mentions)
 

chatterbot/adapters/input/terminal.py

@@ -1,7 +1,7 @@
 from __future__ import unicode_literals
 from chatterbot.adapters.input import InputAdapter
 from chatterbot.conversation import Statement
-from chatterbot.utils.read_input import input_function
+from chatterbot.utils import input_function
 
 
 class TerminalAdapter(InputAdapter):

chatterbot/adapters/logic/logic_adapter.py

@@ -1,6 +1,6 @@
 from __future__ import unicode_literals
 from chatterbot.adapters import Adapter
-from chatterbot.utils.module_loading import import_module
+from chatterbot.utils import import_module
 
 
 class LogicAdapter(Adapter):

chatterbot/adapters/output/output_format_adapter.py

@@ -1,16 +1,21 @@
 from __future__ import unicode_literals
 from chatterbot.adapters.output import OutputAdapter
-from chatterbot.utils.read_input import input_function
 
 
 class OutputFormatAdapter(OutputAdapter):
+    """
+    Return output from the bot in a specified format.
+    """
 
     JSON = 'json'
     TEXT = 'text'
     OBJECT = 'object'
     VALID_FORMATS = (JSON, TEXT, OBJECT, )
 
     def __init__(self, *args, **kwargs):
+        """
+        Set the output format for this adapter.
+        """
         super(OutputFormatAdapter, self).__init__(**kwargs)
         self.format = kwargs.get('output_format', 'object')
 

chatterbot/adapters/output/terminal.py

@@ -1,6 +1,5 @@
 from __future__ import unicode_literals
 from chatterbot.adapters.output import OutputAdapter
-from chatterbot.utils.read_input import input_function
 
 
 class TerminalAdapter(OutputAdapter):
@@ -9,13 +8,6 @@ class TerminalAdapter(OutputAdapter):
     communicate through the terminal.
     """
 
-    def process_input(self, *args, **kwargs):
-        """
-        Read the user's input from the terminal.
-        """
-        user_input = input_function()
-        return user_input
-
     def process_response(self, statement, confidence=None):
         """
         Print the response to the user's input.

chatterbot/chatterbot.py

@@ -1,11 +1,11 @@
 from __future__ import unicode_literals
+import logging
 from .adapters.storage import StorageAdapter
 from .adapters.logic import LogicAdapter, MultiLogicAdapter
 from .adapters.input import InputAdapter
 from .adapters.output import OutputAdapter
-from .utils.queues import ResponseQueue
-from .utils.module_loading import import_module
-import logging
+from .tools.queues import ResponseQueue
+from .utils import import_module
 
 
 class ChatBot(object):
@@ -117,7 +117,7 @@ def remove_logic_adapter(self, adapter_name):
         """
         for index, adapter in enumerate(self.logic.adapters):
             if adapter_name == type(adapter).__name__:
-                del(self.logic.adapters[index])
+                del self.logic.adapters[index]
                 return True
         return False
 

chatterbot/conversation/comparisons.py

@@ -15,7 +15,6 @@ def levenshtein_distance(statement, other_statement):
     :rtype: float
     """
     import sys
-    import warnings
 
     # Use python-Levenshtein if available
     try:
@@ -58,8 +57,8 @@ def synset_distance(statement, other_statement):
     :return: The percent of similarity between the closest synset distance.
     :rtype: float
     """
-    from chatterbot.utils.wordnet import Wordnet
-    from chatterbot.utils.tokenizer import Tokenizer
+    from chatterbot.tools.wordnet import Wordnet
+    from chatterbot.tools.tokenizer import Tokenizer
     import itertools
 
     wordnet = Wordnet()
@@ -180,4 +179,4 @@ def get_wordnet_pos(pos_tag):
         ratio = len(set(lemmae_a).intersection(lemmae_b)) / float(len(set(lemmae_a).union(lemmae_b)))
     except Exception as e:
         print('Error', e)
-    return (ratio >= threshold)
+    return ratio >= threshold

chatterbot/utils/stop_words.py → chatterbot/tools/stop_words.py

@@ -16,11 +16,13 @@ def __init__(self):
         # Download the stopwords data only if it is not already downloaded
         stopwords_path = None
         if os.name == 'nt':
-            stopwords_path = os.path.join(os.getenv('APPDATA'), 'nltk_data',
-                                                'corpora', 'stopwords.zip')
+            stopwords_path = os.path.join(
+                os.getenv('APPDATA'), 'nltk_data', 'corpora', 'stopwords.zip'
+            )
         else:
-            stopwords_path = os.path.join(os.path.expanduser('~'), 'nltk_data',
-                                                'corpora', 'stopwords.zip')
+            stopwords_path = os.path.join(
+                os.path.expanduser('~'), 'nltk_data', 'corpora', 'stopwords.zip'
+            )
         try:
             if not os.path.isfile(stopwords_path):
                 find('stopwords.zip')
@@ -38,4 +40,4 @@ def remove_stopwords(self, language, tokens):
         # Remove the stop words from the set of word tokens
         tokens = set(tokens) - set(stop_words)
 
-        return tokens
+        return tokens

chatterbot/utils/tokenizer.py → chatterbot/tools/tokenizer.py

@@ -11,11 +11,13 @@ def __init__(self):
         # Download the punkt data only if it is not already downloaded
         punkt_path = None
         if os.name == 'nt':
-            punkt_path = os.path.join(os.getenv('APPDATA'), 'nltk_data',
-                                                'tokenizers', 'punkt.zip')
+            punkt_path = os.path.join(
+                os.getenv('APPDATA'), 'nltk_data', 'tokenizers', 'punkt.zip'
+            )
         else:
-            punkt_path = os.path.join(os.path.expanduser('~'), 'nltk_data',
-                                                'tokenizers', 'punkt.zip')
+            punkt_path = os.path.join(
+                os.path.expanduser('~'), 'nltk_data', 'tokenizers', 'punkt.zip'
+            )
         try:
             if not os.path.isfile(punkt_path):
                 find('punkt.zip')
@@ -28,7 +30,7 @@ def get_tokens(self, text, language='english', exclude_stop_words=True):
         Skips common stop words such as ("is, the, a, ...")
         if 'exclude_stop_words' is True.
         """
-        from chatterbot.utils.stop_words import StopWordsManager
+        from chatterbot.tools.stop_words import StopWordsManager
         from nltk import word_tokenize
 
         stopwords = StopWordsManager()
@@ -38,4 +40,4 @@ def get_tokens(self, text, language='english', exclude_stop_words=True):
         if exclude_stop_words:
             tokens = stopwords.remove_stopwords(language, tokens)
 
-        return tokens
+        return tokens

chatterbot/utils/wordnet.py → chatterbot/tools/wordnet.py

@@ -12,15 +12,17 @@ def __init__(self):
         from nltk.data import find
         from nltk import download
         import os
-        
+
         # Download the wordnet data only if it is not already downloaded
         wordnet_path = None
         if os.name == 'nt':
-            wordnet_path = os.path.join(os.getenv('APPDATA'), 'nltk_data',
-                                                'corpora', 'wordnet.zip')
+            wordnet_path = os.path.join(
+                os.getenv('APPDATA'), 'nltk_data', 'corpora', 'wordnet.zip'
+            )
         else:
-            wordnet_path = os.path.join(os.path.expanduser('~'), 'nltk_data',
-                                                'corpora', 'wordnet.zip')
+            wordnet_path = os.path.join(
+                os.path.expanduser('~'), 'nltk_data', 'corpora', 'wordnet.zip'
+            )
         try:
             if not os.path.isfile(wordnet_path):
                 find('wordnet.zip')

docs/utils.rst

@@ -8,25 +8,25 @@ a collection of miscellaneous but useful functions.
 Module Imports
 --------------
 
-.. autofunction:: chatterbot.utils.module_loading.import_module
+.. autofunction:: chatterbot.utils.import_module
 
 String cleaning
 ---------------
 
 This package of utility contains methods that are usefull
 for cleaning and normalizing strings of text.
 
-.. autofunction:: chatterbot.utils.clean.clean_whitespace
+.. autofunction:: chatterbot.utils.clean_whitespace
 
-.. autofunction:: chatterbot.utils.clean.clean
+.. autofunction:: chatterbot.utils.clean
 
 Terminal input
 --------------
 
-.. autofunction:: chatterbot.utils.read_input.input_function
+.. autofunction:: chatterbot.utils.input_function
 
 Queues
 ------
 
-.. autoclass:: chatterbot.utils.queues.ResponseQueue
+.. autoclass:: chatterbot.tools.queues.ResponseQueue
    :members:

examples/learning_feedback_example.py

@@ -22,7 +22,7 @@
 )
 
 def get_feedback():
-    from chatterbot.utils.read_input import input_function
+    from chatterbot.utils import input_function
 
     text = input_function()
 

setup.py

@@ -35,7 +35,7 @@
         'chatterbot.ext.django_chatterbot.migrations',
         'chatterbot.ext.django_chatterbot.management',
         'chatterbot.ext.django_chatterbot.management.commands',
-        'chatterbot.utils'
+        'chatterbot.tools'
     ],
     package_dir={'chatterbot': 'chatterbot'},
     include_package_data=True,

tests/test_parsing.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 from unittest import TestCase
 from datetime import timedelta, date, datetime
-from chatterbot.utils.parsing import datetime_parsing, this_week_day, previous_week_day, next_week_day, dateFromDuration
+from chatterbot.tools.parsing import datetime_parsing, this_week_day, previous_week_day, next_week_day, dateFromDuration
 
 """
   Output of the parser is an array of tuples

tests/test_queues.py

@@ -1,5 +1,5 @@
 from unittest import TestCase
-from chatterbot.utils.queues import ResponseQueue
+from chatterbot.tools.queues import ResponseQueue
 
 
 class ResponseQueueTests(TestCase):

tests/test_tools.py

@@ -0,0 +1,53 @@
+from unittest import TestCase
+
+
+class TokenizerTestCase(TestCase):
+
+    def setUp(self):
+        super(TokenizerTestCase, self).setUp()
+        from chatterbot.tools.tokenizer import Tokenizer
+
+        self.tokenizer = Tokenizer()
+
+    def test_get_tokens(self):
+        tokens = self.tokenizer.get_tokens('what time is it', exclude_stop_words=False)
+        self.assertEqual(tokens, ['what', 'time', 'is', 'it'])
+
+    def test_get_tokens_exclude_stop_words(self):
+        tokens = self.tokenizer.get_tokens('what time is it', exclude_stop_words=True)
+        self.assertEqual(tokens, {'time'})
+
+
+class StopWordsTestCase(TestCase):
+
+    def setUp(self):
+        super(StopWordsTestCase, self).setUp()
+        from chatterbot.tools.stop_words import StopWordsManager
+
+        self.stopwords_manager = StopWordsManager()
+
+    def test_remove_stop_words(self):
+        tokens = ['this', 'is', 'a', 'test', 'string']
+        words = self.stopwords_manager.remove_stopwords('english', tokens)
+
+        # This example list of words should end up with only two elements
+        self.assertEqual(len(words), 2)
+        self.assertIn('test', list(words))
+        self.assertIn('string', list(words))
+
+
+class WordnetTestCase(TestCase):
+
+    def setUp(self):
+        super(WordnetTestCase, self).setUp()
+        from chatterbot.tools.wordnet import Wordnet
+
+        self.wordnet = Wordnet()
+
+    def test_wordnet(self):
+        synsets = self.wordnet.synsets('test')
+
+        self.assertEqual(
+            0.06666666666666667,
+            synsets[0].path_similarity(synsets[1])
+        )