Fix export_for_training to encode utf8

.github/lock.yml

@@ -1,7 +1,7 @@
 # Configuration for Lock Threads - https://github.com/dessant/lock-threads
 
 # Number of days of inactivity before a closed issue or pull request is locked
-daysUntilLock: 365
+daysUntilLock: 300
 
 # Skip issues and pull requests created before a given timestamp. Timestamp must
 # follow ISO 8601 (`YYYY-MM-DD`). Set to `false` to disable

.gitignore

@@ -1,9 +1,9 @@
 bin
 build
 dist
-include
-lib
 venv
+.env
+.out
 .tox
 .coverage
 *.pyc
@@ -15,17 +15,3 @@ venv
 
 # Database files
 *.sqlite3
-*.db
-
-# IntelliJ
-.idea
-*.iml
-
-examples/settings.py
-examples/ubuntu_dialogs*
-sentence_tokenizer.pickle
-.env
-.out
-
-# ignore Ubuntu corpus files
-data

MANIFEST.in

@@ -1,6 +1,7 @@
 include LICENSE
 include README.md
 include requirements.txt
+include setup.cfg
 
 global-exclude __pycache__
 global-exclude *.py[co]

chatterbot/__init__.py

@@ -3,10 +3,6 @@
 """
 from .chatterbot import ChatBot
 
-__version__ = '1.0.5'
-__author__ = 'Gunther Cox'
-__email__ = 'gunthercx@gmail.com'
-__url__ = 'https://github.com/gunthercox/ChatterBot'
 
 __all__ = (
     'ChatBot',

chatterbot/__main__.py

@@ -1,30 +1,20 @@
-import importlib
+import configparser
 import sys
 import os
 
 
 def get_chatterbot_version():
-    chatterbot = importlib.import_module('chatterbot')
-    return chatterbot.__version__
+    config = configparser.ConfigParser()
 
+    current_directory = os.path.dirname(os.path.abspath(__file__))
+    parent_directory = os.path.abspath(os.path.join(current_directory, os.pardir))
+    config_file_path = os.path.join(parent_directory, 'setup.cfg')
 
-def get_nltk_data_directories():
-    import nltk.data
+    config.read(config_file_path)
 
-    data_directories = []
-
-    # Find each data directory in the NLTK path that has content
-    for path in nltk.data.path:
-        if os.path.exists(path):
-            if os.listdir(path):
-                data_directories.append(path)
-
-    return os.linesep.join(data_directories)
+    return config['chatterbot']['version']
 
 
 if __name__ == '__main__':
     if '--version' in sys.argv:
         print(get_chatterbot_version())
-
-    if 'list_nltk_data' in sys.argv:
-        print(get_nltk_data_directories())

chatterbot/chatterbot.py

@@ -1,7 +1,7 @@
 import logging
 from chatterbot.storage import StorageAdapter
 from chatterbot.logic import LogicAdapter
-from chatterbot.search import IndexedTextSearch
+from chatterbot.search import TextSearch, IndexedTextSearch
 from chatterbot import utils
 
 
@@ -13,12 +13,6 @@ class ChatBot(object):
     def __init__(self, name, **kwargs):
         self.name = name
 
-        primary_search_algorithm = IndexedTextSearch(self, **kwargs)
-
-        self.search_algorithms = {
-            primary_search_algorithm.name: primary_search_algorithm
-        }
-
         storage_adapter = kwargs.get('storage_adapter', 'chatterbot.storage.SQLStorageAdapter')
 
         logic_adapters = kwargs.get('logic_adapters', [
@@ -33,6 +27,14 @@ def __init__(self, name, **kwargs):
 
         self.storage = utils.initialize_class(storage_adapter, **kwargs)
 
+        primary_search_algorithm = IndexedTextSearch(self, **kwargs)
+        text_search_algorithm = TextSearch(self, **kwargs)
+
+        self.search_algorithms = {
+            primary_search_algorithm.name: primary_search_algorithm,
+            text_search_algorithm.name: text_search_algorithm
+        }
+
         for adapter in logic_adapters:
             utils.validate_adapter_class(adapter, LogicAdapter)
             logic_adapter = utils.initialize_class(adapter, self, **kwargs)
@@ -54,31 +56,6 @@ def __init__(self, name, **kwargs):
         # Allow the bot to save input it receives so that it can learn
         self.read_only = kwargs.get('read_only', False)
 
-        if kwargs.get('initialize', True):
-            self.initialize()
-
-    def get_initialization_functions(self):
-        initialization_functions = set()
-
-        initialization_functions.update(utils.get_initialization_functions(
-            self, 'storage.tagger'
-        ))
-
-        for search_algorithm in self.search_algorithms.values():
-            search_algorithm_functions = utils.get_initialization_functions(
-                search_algorithm, 'compare_statements'
-            )
-            initialization_functions.update(search_algorithm_functions)
-
-        return initialization_functions
-
-    def initialize(self):
-        """
-        Do any work that needs to be done before the chatbot can process responses.
-        """
-        for function in self.get_initialization_functions():
-            function()
-
     def get_response(self, statement=None, **kwargs):
         """
         Return the bot's response based on the input.
@@ -131,10 +108,10 @@ def get_response(self, statement=None, **kwargs):
         # Make sure the input statement has its search text saved
 
         if not input_statement.search_text:
-            input_statement.search_text = self.storage.tagger.get_bigram_pair_string(input_statement.text)
+            input_statement.search_text = self.storage.tagger.get_text_index_string(input_statement.text)
 
         if not input_statement.search_in_response_to and input_statement.in_response_to:
-            input_statement.search_in_response_to = self.storage.tagger.get_bigram_pair_string(input_statement.in_response_to)
+            input_statement.search_in_response_to = self.storage.tagger.get_text_index_string(input_statement.in_response_to)
 
         response = self.generate_response(input_statement, additional_response_selection_parameters)