ChatterBot 1.2.5__py3-none-any.whl → 1.2.6__py3-none-any.whl

chatterbot/__init__.py

@@ -4,7 +4,7 @@ ChatterBot is a machine learning, conversational dialog engine.
 from .chatterbot import ChatBot
 
 
-__version__ = '1.2.5'
+__version__ = '1.2.6'
 
 __all__ = (
     'ChatBot',

chatterbot/storage/sql_storage.py

@@ -44,7 +44,7 @@ class SQLStorageAdapter(StorageAdapter):
                 dbapi_connection.execute('PRAGMA journal_mode=WAL')
                 dbapi_connection.execute('PRAGMA synchronous=NORMAL')
 
-        if not inspect(self.engine).has_table(self.engine, 'statement'):
+        if not inspect(self.engine).has_table('statement'):
             self.create_database()
 
         # Check if the expected index exists on the text field of the statement table

chatterbot/tagging.py

@@ -1,3 +1,4 @@
+from typing import List, Union, Tuple
 from chatterbot import languages
 from chatterbot.utils import get_model_for_language
 import spacy
@@ -20,7 +21,7 @@ class LowercaseTagger(object):
             'chatterbot_lowercase_indexer', name='chatterbot_lowercase_indexer', last=True
         )
 
-    def get_text_index_string(self, text):
+    def get_text_index_string(self, text: Union[str, List[str]]):
         if isinstance(text, list):
             documents = self.nlp.pipe(text)
             return [document._.search_index for document in documents]
@@ -28,7 +29,7 @@ class LowercaseTagger(object):
             document = self.nlp(text)
             return document._.search_index
 
-    def as_nlp_pipeline(self, texts):
+    def as_nlp_pipeline(self, texts: Union[List[str], Tuple[str, dict]]):
 
         process_as_tuples = texts and isinstance(texts[0], tuple)
 
@@ -52,7 +53,7 @@ class PosLemmaTagger(object):
             'chatterbot_bigram_indexer', name='chatterbot_bigram_indexer', last=True
         )
 
-    def get_text_index_string(self, text):
+    def get_text_index_string(self, text: Union[str, List[str]]):
         """
         Return a string of text containing part-of-speech, lemma pairs.
         """
@@ -63,7 +64,7 @@ class PosLemmaTagger(object):
             document = self.nlp(text)
             return document._.search_index
 
-    def as_nlp_pipeline(self, texts):
+    def as_nlp_pipeline(self, texts: Union[List[str], Tuple[str, dict]]):
         """
         Accepts a single string or a list of strings, or a list of tuples
         where the first element is the text and the second element is a

chatterbot/trainers.py

@@ -1,12 +1,13 @@
 import os
-import sys
 import csv
 import time
 import glob
 import json
 import tarfile
+from typing import List, Union
 from tqdm import tqdm
 from dateutil import parser as date_parser
+from chatterbot.chatterbot import ChatBot
 from chatterbot.conversation import Statement
 
 
@@ -20,7 +21,7 @@ class Trainer(object):
            the environment variable if it is set.
     """
 
-    def __init__(self, chatbot, **kwargs):
+    def __init__(self, chatbot: ChatBot, **kwargs):
         self.chatbot = chatbot
 
         environment_default = bool(int(os.environ.get('CHATTERBOT_SHOW_TRAINING_PROGRESS', True)))
@@ -30,7 +31,7 @@ class Trainer(object):
             environment_default
         )
 
-    def get_preprocessed_statement(self, input_statement):
+    def get_preprocessed_statement(self, input_statement: Statement) -> Statement:
         """
         Preprocess the input statement.
         """
@@ -58,7 +59,7 @@ class Trainer(object):
             )
             super().__init__(message or default)
 
-    def _generate_export_data(self):
+    def _generate_export_data(self) -> list:
         result = []
         for statement in self.chatbot.storage.filter():
             if statement.in_response_to:
@@ -82,7 +83,7 @@ class ListTrainer(Trainer):
     where the list represents a conversation.
     """
 
-    def train(self, conversation: list):
+    def train(self, conversation: List[str]):
         """
         Train the chat bot based on the provided list of
         statements that represents a single conversation.
@@ -95,7 +96,6 @@ class ListTrainer(Trainer):
         # Run the pipeline in bulk to improve performance
         documents = self.chatbot.tagger.as_nlp_pipeline(conversation)
 
-        # for text in enumerate(conversation):
         for document in tqdm(documents, desc='List Trainer', disable=self.disable_progress):
             statement_search_text = document._.search_index
 
@@ -123,7 +123,7 @@ class ChatterBotCorpusTrainer(Trainer):
     ChatterBot dialog corpus.
     """
 
-    def train(self, *corpus_paths):
+    def train(self, *corpus_paths: Union[str, List[str]]):
         from chatterbot.corpus import load_corpus, list_corpus_files
 
         data_file_paths = []
@@ -178,7 +178,17 @@ class GenericFileTrainer(Trainer):
     or directory of those file types.
     """
 
-    def __init__(self, chatbot, **kwargs):
+    # NOTE: If the value is an integer, this be the
+    # column index instead of the key or header
+    DEFAULT_STATEMENT_TO_HEADER_MAPPING = {
+        'text': 'text',
+        'conversation': 'conversation',
+        'created_at': 'created_at',
+        'persona': 'persona',
+        'tags': 'tags'
+    }
+
+    def __init__(self, chatbot: ChatBot, **kwargs):
         """
         data_path: str The path to the data file or directory.
         field_map: dict A dictionary containing the column name to header mapping.
@@ -187,22 +197,12 @@ class GenericFileTrainer(Trainer):
 
         self.file_extension = None
 
-        # NOTE: If the key is an integer, this be the
-        # column index instead of the key or header
-        DEFAULT_STATEMENT_TO_HEADER_MAPPING = {
-            'text': 'text',
-            'conversation': 'conversation',
-            'created_at': 'created_at',
-            'persona': 'persona',
-            'tags': 'tags'
-        }
-
         self.field_map = kwargs.get(
             'field_map',
-            DEFAULT_STATEMENT_TO_HEADER_MAPPING
+            self.DEFAULT_STATEMENT_TO_HEADER_MAPPING
         )
 
-    def _get_file_list(self, data_path, limit):
+    def _get_file_list(self, data_path: str, limit: Union[int, None]):
         """
         Get a list of files to read from the data set.
         """
@@ -302,6 +302,20 @@ class GenericFileTrainer(Trainer):
                         f'Current mapping: {self.field_map}'
                     )
 
+            response_to_search_index_mapping = {}
+
+            if 'in_response_to' in self.field_map.keys():
+                # Generate the search_in_response_to value for the in_response_to fields
+                response_documents = self.chatbot.tagger.as_nlp_pipeline([
+                    (
+                        row[self.field_map['in_response_to']]
+                    ) for row in data if len(row) > 0 and row[self.field_map['in_response_to']] is not None
+                ])
+
+                # (Process the response values the same way as the text values)
+                for document in response_documents:
+                    response_to_search_index_mapping[document.text] = document._.search_index
+
             for document, context in documents:
                 statement = Statement(
                     text=document.text,
@@ -314,14 +328,19 @@ class GenericFileTrainer(Trainer):
                     statement.created_at = date_parser.parse(context['created_at'])
 
                 statement.search_text = document._.search_index
-                statement.search_in_response_to = previous_statement_search_text
 
                 # Use the in_response_to attribute for the previous statement if
                 # one is defined, otherwise use the last statement which was created
                 if 'in_response_to' in self.field_map.keys():
                     statement.in_response_to = context.get(self.field_map['in_response_to'], None)
+                    statement.search_in_response_to = response_to_search_index_mapping.get(
+                        context.get(self.field_map['in_response_to'], None), ''
+                    )
                 else:
+                    # List-type data such as CSVs with no response specified can use
+                    # the previous statement as the in_response_to value
                     statement.in_response_to = previous_statement_text
+                    statement.search_in_response_to = previous_statement_search_text
 
                 for preprocessor in self.chatbot.preprocessors:
                     statement = preprocessor(statement)
@@ -345,7 +364,6 @@ class GenericFileTrainer(Trainer):
                 )
             )
 
-
 class CsvFileTrainer(GenericFileTrainer):
     """
     .. note::
@@ -358,11 +376,11 @@ class CsvFileTrainer(GenericFileTrainer):
     parameter is set to 'tsv'.
 
     :param str file_extension: The file extension to look for when searching for files (defaults to 'csv').
-    :param str field_map: A dictionary containing the database column name to header mapping.
+    :param dict field_map: A dictionary containing the database column name to header mapping.
                           Values can be either the header name (str) or the column index (int).
     """
 
-    def __init__(self, chatbot, **kwargs):
+    def __init__(self, chatbot: ChatBot, **kwargs):
         super().__init__(chatbot, **kwargs)
 
         self.file_extension = kwargs.get('file_extension', 'csv')
@@ -376,26 +394,26 @@ class JsonFileTrainer(GenericFileTrainer):
     Allow chatbots to be trained with data from a JSON file or
     directory of JSON files.
 
-    :param str field_map: A dictionary containing the database column name to header mapping.
+    :param dict field_map: A dictionary containing the database column name to header mapping.
     """
 
-    def __init__(self, chatbot, **kwargs):
+    DEFAULT_STATEMENT_TO_KEY_MAPPING = {
+        'text': 'text',
+        'conversation': 'conversation',
+        'created_at': 'created_at',
+        'in_response_to': 'in_response_to',
+        'persona': 'persona',
+        'tags': 'tags'
+    }
+
+    def __init__(self, chatbot: ChatBot, **kwargs):
         super().__init__(chatbot, **kwargs)
 
         self.file_extension = 'json'
 
-        DEFAULT_STATEMENT_TO_KEY_MAPPING = {
-            'text': 'text',
-            'conversation': 'conversation',
-            'created_at': 'created_at',
-            'in_response_to': 'in_response_to',
-            'persona': 'persona',
-            'tags': 'tags'
-        }
-
         self.field_map = kwargs.get(
             'field_map',
-            DEFAULT_STATEMENT_TO_KEY_MAPPING
+            self.DEFAULT_STATEMENT_TO_KEY_MAPPING
         )
 
 
@@ -412,7 +430,7 @@ class UbuntuCorpusTrainer(CsvFileTrainer):
     :param str ubuntu_corpus_data_directory: The directory where the Ubuntu corpus data is already located, or where it should be downloaded and extracted.
     """
 
-    def __init__(self, chatbot, **kwargs):
+    def __init__(self, chatbot: ChatBot, **kwargs):
         super().__init__(chatbot, **kwargs)
         home_directory = os.path.expanduser('~')
 
@@ -434,7 +452,7 @@ class UbuntuCorpusTrainer(CsvFileTrainer):
             'persona': 1,
         }
 
-    def is_downloaded(self, file_path):
+    def is_downloaded(self, file_path: str):
         """
         Check if the data file is already downloaded.
         """
@@ -444,7 +462,7 @@ class UbuntuCorpusTrainer(CsvFileTrainer):
 
         return False
 
-    def is_extracted(self, file_path):
+    def is_extracted(self, file_path: str):
         """
         Check if the data file is already extracted.
         """
@@ -454,7 +472,7 @@ class UbuntuCorpusTrainer(CsvFileTrainer):
             return True
         return False
 
-    def download(self, url, show_status=True):
+    def download(self, url: str, show_status=True):
         """
         Download a file from the given url.
         Show a progress indicator for the download status.
@@ -493,7 +511,7 @@ class UbuntuCorpusTrainer(CsvFileTrainer):
             print('Download location: %s' % file_path)
         return file_path
 
-    def extract(self, file_path):
+    def extract(self, file_path: str):
         """
         Extract a tar file at the specified file path.
         """
@@ -533,7 +551,7 @@ class UbuntuCorpusTrainer(CsvFileTrainer):
 
         return True
     
-    def _get_file_list(self, data_path, limit):
+    def _get_file_list(self, data_path: str, limit: Union[int, None]):
         """
         Get a list of files to read from the data set.
         """
@@ -564,7 +582,7 @@ class UbuntuCorpusTrainer(CsvFileTrainer):
 
             yield file_path
 
-    def train(self, data_download_url, limit=None):
+    def train(self, data_download_url: str, limit: Union[int, None] = None):
         """
         :param str data_download_url: The URL to download the Ubuntu dialog corpus from.
         :param int limit: The maximum number of files to train from.

{chatterbot-1.2.5.dist-info → chatterbot-1.2.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ChatterBot
-Version: 1.2.5
+Version: 1.2.6
 Summary: ChatterBot is a machine learning, conversational dialog engine
 Author: Gunther Cox
 License-Expression: BSD-3-Clause
@@ -66,10 +66,11 @@ known conversations. The language independent design of ChatterBot allows it
 to be trained to speak any language.
 
 [![Package Version](https://img.shields.io/pypi/v/chatterbot.svg)](https://pypi.python.org/pypi/chatterbot/)
-[![Python 3.9](https://img.shields.io/badge/python-3.9-blue.svg)](https://www.python.org/downloads/release/python-360/)
+[![Python 3.12](https://img.shields.io/badge/python-3.12-blue.svg)](https://www.python.org/downloads/release/python-360/)
 [![Coverage Status](https://img.shields.io/coveralls/gunthercox/ChatterBot.svg)](https://coveralls.io/r/gunthercox/ChatterBot)
-[![Code Climate](https://codeclimate.com/github/gunthercox/ChatterBot/badges/gpa.svg)](https://codeclimate.com/github/gunthercox/ChatterBot)
+[![Follow on Bluesky](https://img.shields.io/badge/🦋%20Bluesky-1185fe)](https://bsky.app/profile/chatterbot.us)
 [![Join the chat at https://gitter.im/chatterbot/Lobby](https://badges.gitter.im/chatterbot/Lobby.svg)](https://gitter.im/chatterbot/Lobby?utm_source=badge&utm_medium=badge&utm_content=badge)
+<!-- [![Code Climate](https://codeclimate.com/github/gunthercox/ChatterBot/badges/gpa.svg)](https://codeclimate.com/github/gunthercox/ChatterBot) -->
 
 An example of typical input would be something like this:
 

{chatterbot-1.2.5.dist-info → chatterbot-1.2.6.dist-info}/RECORD

@@ -1,4 +1,4 @@
-chatterbot/__init__.py,sha256=QJV-6PyWrpW0rpSjVn0lKcH3dqb77TlYoU74kv8uVjc,158
+chatterbot/__init__.py,sha256=wHoKxLsCOplHJ02JmxRCg5cRL-Z-blQblhJKdE95Pck,158
 chatterbot/__main__.py,sha256=zvH4uxtGlGrP-ht_LkhX29duzjm3hRH800SDCq4YOwg,637
 chatterbot/adapters.py,sha256=LJ_KqLpHKPdYAFpMGK63RVH4weV5X0Zh5uGyan6qdVU,878
 chatterbot/chatterbot.py,sha256=nqxdeTBWdA_LDIEWTMf2gphvpNfd0c9htNwrxa_7pzo,12543
@@ -14,8 +14,8 @@ chatterbot/parsing.py,sha256=vS-w70cMkjq4YEpDOv_pXWhAI6Zj06WYDAcMDhYDj0M,23174
 chatterbot/preprocessors.py,sha256=kqsgnejSj6Z1rr9U2TGHKOp-MMaFWBdNT41EwyhQFls,1389
 chatterbot/response_selection.py,sha256=JpUVuBYrgxhHkDMRHXyWvhluSLxQED5mAhE1-VvJSmg,2970
 chatterbot/search.py,sha256=FTwwON2eKPWqoc5uoKh4AUmuXDCqyfMcMcXB4wijpxg,4910
-chatterbot/tagging.py,sha256=czcI2g18vILujphkjvobRyEewJU8-QjS7QRzY-hCZ4o,2429
-chatterbot/trainers.py,sha256=S_y-Q67hgU7p1A_ixJsR91nW_FniJUsSzbdtAQ8KJQM,19749
+chatterbot/tagging.py,sha256=si0PQ3CY5EbiZ0-PIslbBtExZaQZ3NYrLUGoourweKo,2585
+chatterbot/trainers.py,sha256=CZezNX68Byg9gg2z-PUZbTc5pqzTzbhgSmqHx7P6Ivg,20973
 chatterbot/utils.py,sha256=ubPiBapvUvdFVhrDjxqq5IGekUh9qMUJs_dQ605xLAI,2924
 chatterbot/vectorstores.py,sha256=-S1NB8PrZzoFIu95n2W7N4UaXuCUpyDUXIGYFebjv08,2056
 chatterbot/ext/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -60,10 +60,10 @@ chatterbot/storage/__init__.py,sha256=ADw0WQe0YKr1UIDQLaxwf0mHDnuKW_CSzgz11K4TM-
 chatterbot/storage/django_storage.py,sha256=BpuVEO4rPOiPu7f7KW1Zyar2LqEXy6I4HgPYhyGP0kE,6305
 chatterbot/storage/mongodb.py,sha256=Ozvdvcjb3LGZxcvbSQGzwP9VloYQbmsa2FaKunFpMyU,7934
 chatterbot/storage/redis.py,sha256=FKROrzZ-7WXZ8ZoK0dKmTDdS45TxL04XOSeu0p3Jrak,12675
-chatterbot/storage/sql_storage.py,sha256=dAMLByFKQgbiTFoBUtKDeqadYRdwVO5fz1OONTcVCH4,13076
+chatterbot/storage/sql_storage.py,sha256=wESsp0OKuXjYmAZ7dl-ztX7lt4xEpjD0WCBQXK22__4,13063
 chatterbot/storage/storage_adapter.py,sha256=fvyb-qNiB0HMJ0siVMCWUIY--6d-C47N1_kKZVFZAv4,6110
-chatterbot-1.2.5.dist-info/licenses/LICENSE,sha256=5b04U8mi0wp5gJMYlKi49EalnD9Q2nwY_6UEI_Avgu4,1476
-chatterbot-1.2.5.dist-info/METADATA,sha256=UgfV52vY3Rq4A_8rVZurYhKcU0DeNwply-UBh42aTd0,7049
-chatterbot-1.2.5.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-chatterbot-1.2.5.dist-info/top_level.txt,sha256=W2TzAbAJ-eBXTIKZZhVlkrh87msJNmBQpyhkrHqjSrE,11
-chatterbot-1.2.5.dist-info/RECORD,,
+chatterbot-1.2.6.dist-info/licenses/LICENSE,sha256=5b04U8mi0wp5gJMYlKi49EalnD9Q2nwY_6UEI_Avgu4,1476
+chatterbot-1.2.6.dist-info/METADATA,sha256=lOBXOb2GEaOguy3_Rwqo_TEP77GeunbhiI9BGqB1zfc,7175
+chatterbot-1.2.6.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+chatterbot-1.2.6.dist-info/top_level.txt,sha256=W2TzAbAJ-eBXTIKZZhVlkrh87msJNmBQpyhkrHqjSrE,11
+chatterbot-1.2.6.dist-info/RECORD,,