ChatterBot 1.2.1__py3-none-any.whl → 1.2.2__py3-none-any.whl

chatterbot/__init__.py

@@ -4,7 +4,7 @@ ChatterBot is a machine learning, conversational dialog engine.
 from .chatterbot import ChatBot
 
 
-__version__ = '1.2.1'
+__version__ = '1.2.2'
 
 __all__ = (
     'ChatBot',

chatterbot/chatterbot.py

@@ -2,7 +2,10 @@ import logging
 from chatterbot.storage import StorageAdapter
 from chatterbot.logic import LogicAdapter
 from chatterbot.search import TextSearch, IndexedTextSearch
+from chatterbot.tagging import PosLemmaTagger
+from chatterbot import languages
 from chatterbot import utils
+import spacy
 
 
 class ChatBot(object):
@@ -27,6 +30,12 @@ class ChatBot(object):
 
         self.storage = utils.initialize_class(storage_adapter, **kwargs)
 
+        Tagger = kwargs.get('tagger', PosLemmaTagger)
+
+        self.tagger = Tagger(language=kwargs.get(
+            'tagger_language', languages.ENG
+        ))
+
         primary_search_algorithm = IndexedTextSearch(self, **kwargs)
         text_search_algorithm = TextSearch(self, **kwargs)
 
@@ -51,6 +60,9 @@ class ChatBot(object):
         for preprocessor in preprocessors:
             self.preprocessors.append(utils.import_module(preprocessor))
 
+        # NOTE: 'xx' is the language code for a multi-language model
+        self.nlp = spacy.blank(self.tagger.language.ISO_639_1)
+
         self.logger = kwargs.get('logger', logging.getLogger(__name__))
 
         # Allow the bot to save input it receives so that it can learn
@@ -105,16 +117,27 @@ class ChatBot(object):
         for preprocessor in self.preprocessors:
             input_statement = preprocessor(input_statement)
 
+        # Mark the statement as being a response to the previous
+        if input_statement.in_response_to is None:
+            previous_statement = self.get_latest_response(input_statement.conversation)
+            if previous_statement:
+                input_statement.in_response_to = previous_statement.text
+
         # Make sure the input statement has its search text saved
 
         if not input_statement.search_text:
-            _search_text = self.storage.tagger.get_text_index_string(input_statement.text)
+            _search_text = self.tagger.get_text_index_string(input_statement.text)
             input_statement.search_text = _search_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_text_index_string(input_statement.in_response_to)
+            input_statement.search_in_response_to = self.tagger.get_text_index_string(
+                input_statement.in_response_to
+            )
 
-        response = self.generate_response(input_statement, additional_response_selection_parameters)
+        response = self.generate_response(
+            input_statement,
+            additional_response_selection_parameters
+        )
 
         # Update any response data that needs to be changed
         if persist_values_to_response:
@@ -128,10 +151,13 @@ class ChatBot(object):
                     setattr(response, response_key, response_value)
 
         if not self.read_only:
-            self.learn_response(input_statement)
+
+            # Save the input statement
+            self.storage.create(**input_statement.serialize())
 
             # Save the response generated for the input
-            self.storage.create(**response.serialize())
+            self.learn_response(response, previous_statement=input_statement)
+
 
         return response
 
@@ -194,6 +220,8 @@ class ChatBot(object):
                 if result_option.count > most_common.count:
                     most_common = result_option
 
+            self.logger.info('Selecting "{}" as the most common response'.format(most_common.statement.text))
+
             if most_common.count > 1:
                 result = most_common.statement
 
@@ -204,6 +232,8 @@ class ChatBot(object):
             persona='bot:' + self.name
         )
 
+        response.add_tags(*result.get_tags())
+
         response.confidence = result.confidence
 
         return response
@@ -228,11 +258,14 @@ class ChatBot(object):
             statement.in_response_to = previous_statement
 
         self.logger.info('Adding "{}" as a response to "{}"'.format(
-            statement.text,
-            previous_statement_text
+            previous_statement_text,
+            statement.text
         ))
 
-        # Save the input statement
+        if not statement.persona:
+            statement.persona = 'bot:' + self.name
+
+        # Save the response statement
         return self.storage.create(**statement.serialize())
 
     def get_latest_response(self, conversation):

chatterbot/comparisons.py

@@ -19,15 +19,22 @@ class Comparator:
     def __call__(self, statement_a, statement_b):
         return self.compare(statement_a, statement_b)
 
-    def compare(self, statement_a, statement_b):
+    def compare_text(self, text_a, text_b):
         """
-        Implemented in subclasses: compare statement_a to statement_b.
+        Implemented in subclasses: compare text_a to text_b.
 
         :return: The percent of similarity between the statements based on the implemented algorithm.
         :rtype: float
         """
         return 0
 
+    def compare(self, statement_a, statement_b):
+        """
+        :return: The percent of similarity between the statements based on the implemented algorithm.
+        :rtype: float
+        """
+        return self.compare_text(statement_a.text, statement_b.text)
+
 
 class LevenshteinDistance(Comparator):
     """
@@ -39,21 +46,21 @@ class LevenshteinDistance(Comparator):
     based on the Levenshtein distance algorithm.
     """
 
-    def compare(self, statement_a, statement_b):
+    def compare_text(self, text_a, text_b):
         """
-        Compare the two input statements.
+        Compare the two pieces of text.
 
         :return: The percent of similarity between the text of the statements.
         :rtype: float
         """
 
-        # Return 0 if either statement has a falsy text value
-        if not statement_a.text or not statement_b.text:
+        # Return 0 if either statement has a None text value
+        if text_a is None or text_b is None:
             return 0
 
         # Get the lowercase version of both strings
-        statement_a_text = str(statement_a.text.lower())
-        statement_b_text = str(statement_b.text.lower())
+        statement_a_text = str(text_a.lower())
+        statement_b_text = str(text_b.lower())
 
         similarity = SequenceMatcher(
             None,
@@ -103,15 +110,20 @@ class SpacySimilarity(Comparator):
         # Disable the Named Entity Recognition (NER) component because it is not necessary
         self.nlp = spacy.load(model, exclude=['ner'])
 
-    def compare(self, statement_a, statement_b):
+    def compare_text(self, text_a, text_b):
         """
-        Compare the two input statements.
+        Compare the similarity of two strings.
 
         :return: The percent of similarity between the closest synset distance.
         :rtype: float
         """
-        document_a = self.nlp(statement_a.text)
-        document_b = self.nlp(statement_b.text)
+
+        # Return 0 if either statement has a None text value
+        if text_a is None or text_b is None:
+            return 0
+
+        document_a = self.nlp(text_a)
+        document_b = self.nlp(text_b)
 
         return document_a.similarity(document_b)
 
@@ -155,14 +167,19 @@ class JaccardSimilarity(Comparator):
         # Disable the Named Entity Recognition (NER) component because it is not necessary
         self.nlp = spacy.load(model, exclude=['ner'])
 
-    def compare(self, statement_a, statement_b):
+    def compare_text(self, text_a, text_b):
         """
         Return the calculated similarity of two
         statements based on the Jaccard index.
         """
+
+        # Return 0 if either statement has a None text value
+        if text_a is None or text_b is None:
+            return 0
+
         # Make both strings lowercase
-        document_a = self.nlp(statement_a.text.lower())
-        document_b = self.nlp(statement_b.text.lower())
+        document_a = self.nlp(text_a.lower())
+        document_b = self.nlp(text_b.lower())
 
         statement_a_lemmas = frozenset([
             token.lemma_ for token in document_a if not token.is_stop

chatterbot/logic/best_match.py

@@ -23,10 +23,13 @@ class BestMatch(LogicAdapter):
         self.excluded_words = kwargs.get('excluded_words')
 
     def process(self, input_statement, additional_response_selection_parameters=None):
+
+        # Get all statements that have a response text similar to the input statement
         search_results = self.search_algorithm.search(input_statement)
 
         # Use the input statement as the closest match if no other results are found
-        closest_match = next(search_results, input_statement)
+        input_statement.confidence = 0  # Use 0 confidence when no other results are found
+        closest_match = input_statement
 
         # Search for the closest match to the input statement
         for result in search_results:
@@ -36,8 +39,8 @@ class BestMatch(LogicAdapter):
             if result.confidence >= self.maximum_similarity_threshold:
                 break
 
-        self.chatbot.logger.info('Using "{}" as a close match to "{}" with a confidence of {}'.format(
-            closest_match.text, input_statement.text, closest_match.confidence
+        self.chatbot.logger.info('Selecting "{}" as a response to "{}" with a confidence of {}'.format(
+            closest_match.in_response_to, input_statement.text, closest_match.confidence
         ))
 
         recent_repeated_responses = filters.get_recent_repeated_responses(
@@ -51,39 +54,34 @@ class BestMatch(LogicAdapter):
             ))
 
         response_selection_parameters = {
-            'search_in_response_to': closest_match.search_text,
+            'search_text': closest_match.search_text,
+            'persona_not_startswith': 'bot:',
             'exclude_text': recent_repeated_responses,
             'exclude_text_words': self.excluded_words
         }
 
         alternate_response_selection_parameters = {
-            'search_in_response_to': self.chatbot.storage.tagger.get_text_index_string(
+            'search_in_response_to': self.chatbot.tagger.get_text_index_string(
                 input_statement.text
             ),
+            'persona_not_startswith': 'bot:',
             'exclude_text': recent_repeated_responses,
             'exclude_text_words': self.excluded_words
         }
 
         if additional_response_selection_parameters:
-            response_selection_parameters.update(additional_response_selection_parameters)
-            alternate_response_selection_parameters.update(additional_response_selection_parameters)
-
-        # Get all statements that are in response to the closest match
-        response_list = list(self.chatbot.storage.filter(**response_selection_parameters))
+            response_selection_parameters.update(
+                additional_response_selection_parameters
+            )
+            alternate_response_selection_parameters.update(
+                additional_response_selection_parameters
+            )
 
-        alternate_response_list = []
 
-        if not response_list:
-            self.chatbot.logger.info('No responses found. Generating alternate response list.')
-            alternate_response_list = list(self.chatbot.storage.filter(**alternate_response_selection_parameters))
+        # Get all statements with text similar to the closest match
+        response_list = list(self.chatbot.storage.filter(**response_selection_parameters))
 
         if response_list:
-            self.chatbot.logger.info(
-                'Selecting response from {} optimal responses.'.format(
-                    len(response_list)
-                )
-            )
-
             response = self.select_response(
                 input_statement,
                 response_list,
@@ -91,26 +89,35 @@ class BestMatch(LogicAdapter):
             )
 
             response.confidence = closest_match.confidence
-            self.chatbot.logger.info('Response selected. Using "{}"'.format(response.text))
-        elif alternate_response_list:
+            self.chatbot.logger.info('Selecting "{}" from {} optimal responses.'.format(
+                response.text,
+                len(response_list)
+            ))
+        else:
             '''
             The case where there was no responses returned for the selected match
             but a value exists for the statement the match is in response to.
             '''
-            self.chatbot.logger.info(
-                'Selecting response from {} optimal alternate responses.'.format(
-                    len(alternate_response_list)
+            self.chatbot.logger.info('No responses found. Generating alternate response list.')
+
+            alternate_response_list = list(self.chatbot.storage.filter(
+                **alternate_response_selection_parameters
+            ))
+
+            if alternate_response_list:
+                response = self.select_response(
+                    input_statement,
+                    alternate_response_list,
+                    self.chatbot.storage
                 )
-            )
-            response = self.select_response(
-                input_statement,
-                alternate_response_list,
-                self.chatbot.storage
-            )
 
-            response.confidence = closest_match.confidence
-            self.chatbot.logger.info('Alternate response selected. Using "{}"'.format(response.text))
-        else:
-            response = self.get_default_response(input_statement)
+                response.confidence = closest_match.confidence
+                self.chatbot.logger.info('Selected alternative response "{}" from {} options'.format(
+                    response.text,
+                    len(alternate_response_list)
+                ))
+            else:
+                response = self.get_default_response(input_statement)
+                self.chatbot.logger.info('Using "%s" as a default response.', response.text)
 
         return response

chatterbot/response_selection.py

@@ -37,7 +37,7 @@ def get_most_frequent_response(input_statement, response_list, storage=None):
             matching_response = statement
             occurrence_count = count
 
-    # Choose the most commonly occuring matching response
+    # Choose the most commonly occurring matching response
     return matching_response
 
 

chatterbot/search.py

@@ -21,7 +21,7 @@ class IndexedTextSearch:
         )
 
         self.compare_statements = statement_comparison_function(
-            language=self.chatbot.storage.tagger.language
+            language=self.chatbot.tagger.language
         )
 
         self.search_page_size = kwargs.get(
@@ -43,19 +43,8 @@ class IndexedTextSearch:
         """
         self.chatbot.logger.info('Beginning search for close text match')
 
-        input_search_text = input_statement.search_text
-
-        if not input_statement.search_text:
-            self.chatbot.logger.warning(
-                'No value for search_text was available on the provided input'
-            )
-
-            input_search_text = self.chatbot.storage.tagger.get_text_index_string(
-                input_statement.text
-            )
-
         search_parameters = {
-            'search_text_contains': input_search_text,
+            'search_in_response_to_contains': input_statement.search_text,
             'persona_not_startswith': 'bot:',
             'page_size': self.search_page_size
         }
@@ -71,14 +60,16 @@ class IndexedTextSearch:
 
         # Find the closest matching known statement
         for statement in statement_list:
-            confidence = self.compare_statements(input_statement, statement)
+            confidence = self.compare_statements.compare_text(
+                input_statement.text, statement.in_response_to
+            )
 
             if confidence > best_confidence_so_far:
                 best_confidence_so_far = confidence
                 statement.confidence = confidence
 
                 self.chatbot.logger.info('Similar text found: {} {}'.format(
-                    statement.text, confidence
+                    statement.in_response_to, confidence
                 ))
 
                 yield statement
@@ -107,7 +98,7 @@ class TextSearch:
         )
 
         self.compare_statements = statement_comparison_function(
-            language=self.chatbot.storage.tagger.language
+            language=self.chatbot.tagger.language
         )
 
         self.search_page_size = kwargs.get(
@@ -145,7 +136,9 @@ class TextSearch:
 
         # Find the closest matching known statement
         for statement in statement_list:
-            confidence = self.compare_statements(input_statement, statement)
+            confidence = self.compare_statements.compare_text(
+                input_statement.text, statement.in_response_to
+            )
 
             if confidence > best_confidence_so_far:
                 best_confidence_so_far = confidence

chatterbot/storage/django_storage.py

@@ -44,6 +44,7 @@ class DjangoStorageAdapter(StorageAdapter):
         exclude_text_words = kwargs.pop('exclude_text_words', [])
         persona_not_startswith = kwargs.pop('persona_not_startswith', None)
         search_text_contains = kwargs.pop('search_text_contains', None)
+        search_in_response_to_contains = kwargs.pop('search_in_response_to_contains', None)
 
         # Convert a single sting into a list if only one tag is provided
         if type(tags) == str:
@@ -83,6 +84,16 @@ class DjangoStorageAdapter(StorageAdapter):
                 or_query
             )
 
+        if search_in_response_to_contains:
+            or_query = Q()
+
+            for word in search_in_response_to_contains.split(' '):
+                or_query |= Q(search_in_response_to__contains=word)
+
+            statements = statements.filter(
+                or_query
+            )
+
         if order_by:
             statements = statements.order_by(*order_by)
 
@@ -99,13 +110,6 @@ class DjangoStorageAdapter(StorageAdapter):
 
         tags = kwargs.pop('tags', [])
 
-        if 'search_text' not in kwargs:
-            kwargs['search_text'] = self.tagger.get_text_index_string(kwargs['text'])
-
-        if 'search_in_response_to' not in kwargs:
-            if kwargs.get('in_response_to'):
-                kwargs['search_in_response_to'] = self.tagger.get_text_index_string(kwargs['in_response_to'])
-
         statement = Statement(**kwargs)
 
         statement.save()
@@ -129,20 +133,6 @@ class DjangoStorageAdapter(StorageAdapter):
 
         tag_cache = {}
 
-        # Check if any statements already have a search text
-        have_search_text = any(statement.search_text for statement in statements)
-
-        # Generate search text values in bulk
-        if not have_search_text:
-            search_text_documents = self.tagger.as_nlp_pipeline([statement.text for statement in statements])
-            response_search_text_documents = self.tagger.as_nlp_pipeline([statement.in_response_to or '' for statement in statements])
-
-            for statement, search_text_document, response_search_text_document in zip(
-                statements, search_text_documents, response_search_text_documents
-            ):
-                statement.search_text = search_text_document._.search_index
-                statement.search_in_response_to = response_search_text_document._.search_index
-
         for statement in statements:
 
             statement_data = statement.serialize()
@@ -176,10 +166,10 @@ class DjangoStorageAdapter(StorageAdapter):
         else:
             statement = Statement.objects.create(
                 text=statement.text,
-                search_text=self.tagger.get_text_index_string(statement.text),
+                search_text=statement.search_text,
                 conversation=statement.conversation,
                 in_response_to=statement.in_response_to,
-                search_in_response_to=self.tagger.get_text_index_string(statement.in_response_to),
+                search_in_response_to=statement.search_in_response_to,
                 created_at=statement.created_at
             )
 

chatterbot/storage/mongodb.py

@@ -82,6 +82,7 @@ class MongoDatabaseAdapter(StorageAdapter):
         exclude_text_words = kwargs.pop('exclude_text_words', [])
         persona_not_startswith = kwargs.pop('persona_not_startswith', None)
         search_text_contains = kwargs.pop('search_text_contains', None)
+        search_in_response_to_contains = kwargs.pop('search_in_response_to_contains', None)
 
         if tags:
             kwargs['tags'] = {
@@ -127,6 +128,12 @@ class MongoDatabaseAdapter(StorageAdapter):
             ])
             kwargs['search_text'] = re.compile(or_regex)
 
+        if search_in_response_to_contains:
+            or_regex = '|'.join([
+                '{}'.format(re.escape(word)) for word in search_in_response_to_contains.split(' ')
+            ])
+            kwargs['search_in_response_to'] = re.compile(or_regex)
+
         mongo_ordering = []
 
         if order_by:
@@ -159,13 +166,6 @@ class MongoDatabaseAdapter(StorageAdapter):
         if 'tags' in kwargs:
             kwargs['tags'] = list(set(kwargs['tags']))
 
-        if 'search_text' not in kwargs:
-            kwargs['search_text'] = self.tagger.get_text_index_string(kwargs['text'])
-
-        if 'search_in_response_to' not in kwargs:
-            if kwargs.get('in_response_to'):
-                kwargs['search_in_response_to'] = self.tagger.get_text_index_string(kwargs['in_response_to'])
-
         inserted = self.statements.insert_one(kwargs)
 
         kwargs['id'] = inserted.inserted_id
@@ -178,20 +178,6 @@ class MongoDatabaseAdapter(StorageAdapter):
         """
         create_statements = []
 
-        # Check if any statements already have a search text
-        have_search_text = any(statement.search_text for statement in statements)
-
-        # Generate search text values in bulk
-        if not have_search_text:
-            search_text_documents = self.tagger.as_nlp_pipeline([statement.text for statement in statements])
-            response_search_text_documents = self.tagger.as_nlp_pipeline([statement.in_response_to or '' for statement in statements])
-
-            for statement, search_text_document, response_search_text_document in zip(
-                statements, search_text_documents, response_search_text_documents
-            ):
-                statement.search_text = search_text_document._.search_index
-                statement.search_in_response_to = response_search_text_document._.search_index
-
         for statement in statements:
             statement_data = statement.serialize()
             tag_data = list(set(statement_data.pop('tags', [])))
@@ -206,11 +192,6 @@ class MongoDatabaseAdapter(StorageAdapter):
         data.pop('id', None)
         data.pop('tags', None)
 
-        data['search_text'] = self.tagger.get_text_index_string(data['text'])
-
-        if data.get('in_response_to'):
-            data['search_in_response_to'] = self.tagger.get_text_index_string(data['in_response_to'])
-
         update_data = {
             '$set': data
         }

chatterbot/storage/sql_storage.py

@@ -114,8 +114,8 @@ class SQLStorageAdapter(StorageAdapter):
         record = query.first()
 
         session.delete(record)
-
-        self._session_finish(session)
+        session.commit()
+        session.close()
 
     def filter(self, **kwargs):
         """
@@ -139,6 +139,7 @@ class SQLStorageAdapter(StorageAdapter):
         exclude_text_words = kwargs.pop('exclude_text_words', [])
         persona_not_startswith = kwargs.pop('persona_not_startswith', None)
         search_text_contains = kwargs.pop('search_text_contains', None)
+        search_in_response_to_contains = kwargs.pop('search_in_response_to_contains', None)
 
         # Convert a single sting into a list if only one tag is provided
         if type(tags) == str:
@@ -180,6 +181,14 @@ class SQLStorageAdapter(StorageAdapter):
                 or_(*or_query)
             )
 
+        if search_in_response_to_contains:
+            or_query = [
+                Statement.search_in_response_to.contains(word) for word in search_in_response_to_contains.split(' ')
+            ]
+            statements = statements.filter(
+                or_(*or_query)
+            )
+
         if order_by:
 
             if 'created_at' in order_by:
@@ -196,7 +205,15 @@ class SQLStorageAdapter(StorageAdapter):
 
         session.close()
 
-    def create(self, **kwargs):
+    def create(
+        self,
+        text,
+        in_response_to=None,
+        tags=None,
+        search_text=None,
+        search_in_response_to=None,
+        **kwargs
+    ):
         """
         Creates a new statement matching the keyword arguments specified.
         Returns the created statement.
@@ -206,19 +223,25 @@ class SQLStorageAdapter(StorageAdapter):
 
         session = self.Session()
 
-        tags = set(kwargs.pop('tags', []))
-
-        if 'search_text' not in kwargs:
-            kwargs['search_text'] = self.tagger.get_text_index_string(kwargs['text'])
-
-        if 'search_in_response_to' not in kwargs:
-            in_response_to = kwargs.get('in_response_to')
-            if in_response_to:
-                kwargs['search_in_response_to'] = self.tagger.get_text_index_string(in_response_to)
-
-        statement = Statement(**kwargs)
-
-        for tag_name in tags:
+        if search_text is None:
+            if self.raise_on_missing_search_text:
+                raise Exception('generate a search_text value')
+
+        if search_in_response_to is None and in_response_to is not None:
+            if self.raise_on_missing_search_text:
+                raise Exception('generate a search_in_response_to value')
+
+        statement = Statement(
+            text=text,
+            in_response_to=in_response_to,
+            search_text=search_text,
+            search_in_response_to=search_in_response_to,
+            **kwargs
+        )
+
+        tags = frozenset(tags) if tags else frozenset()
+        for tag_name in frozenset(tags):
+            # TODO: Query existing tags in bulk
             tag = session.query(Tag).filter_by(name=tag_name).first()
 
             if not tag:
@@ -235,7 +258,7 @@ class SQLStorageAdapter(StorageAdapter):
 
         statement_object = self.model_to_object(statement)
 
-        self._session_finish(session)
+        session.close()
 
         return statement_object
 
@@ -256,14 +279,8 @@ class SQLStorageAdapter(StorageAdapter):
 
         # Generate search text values in bulk
         if not have_search_text:
-            search_text_documents = self.tagger.as_nlp_pipeline([statement.text for statement in statements])
-            response_search_text_documents = self.tagger.as_nlp_pipeline([statement.in_response_to or '' for statement in statements])
-
-            for statement, search_text_document, response_search_text_document in zip(
-                statements, search_text_documents, response_search_text_documents
-            ):
-                statement.search_text = search_text_document._.search_index
-                statement.search_in_response_to = response_search_text_document._.search_index
+            if self.raise_on_missing_search_text:
+                raise Exception('generate bulk_search_text values')
 
         for statement in statements:
 
@@ -305,48 +322,50 @@ class SQLStorageAdapter(StorageAdapter):
         Statement = self.get_model('statement')
         Tag = self.get_model('tag')
 
-        if statement is not None:
-            session = self.Session()
-            record = None
-
-            if hasattr(statement, 'id') and statement.id is not None:
-                record = session.query(Statement).get(statement.id)
-            else:
-                record = session.query(Statement).filter(
-                    Statement.text == statement.text,
-                    Statement.conversation == statement.conversation,
-                ).first()
-
-                # Create a new statement entry if one does not already exist
-                if not record:
-                    record = Statement(
-                        text=statement.text,
-                        conversation=statement.conversation,
-                        persona=statement.persona
-                    )
+        session = self.Session()
+        record = None
 
-            # Update the response value
-            record.in_response_to = statement.in_response_to
+        if hasattr(statement, 'id') and statement.id is not None:
+            record = session.query(Statement).get(statement.id)
+        else:
+            record = session.query(Statement).filter(
+                Statement.text == statement.text,
+                Statement.conversation == statement.conversation,
+            ).first()
+
+            # Create a new statement entry if one does not already exist
+            if not record:
+                record = Statement(
+                    text=statement.text,
+                    conversation=statement.conversation,
+                    persona=statement.persona
+                )
 
-            record.created_at = statement.created_at
+        # Update the response value
+        record.in_response_to = statement.in_response_to
 
-            record.search_text = self.tagger.get_text_index_string(statement.text)
+        record.created_at = statement.created_at
 
-            if statement.in_response_to:
-                record.search_in_response_to = self.tagger.get_text_index_string(statement.in_response_to)
+        if not statement.search_text:
+            if self.raise_on_missing_search_text:
+                raise Exception('update issued without search_text value')
 
-            for tag_name in statement.get_tags():
-                tag = session.query(Tag).filter_by(name=tag_name).first()
+        if statement.in_response_to and not statement.search_in_response_to:
+            if self.raise_on_missing_search_text:
+                raise Exception('update issued without search_in_response_to value')
 
-                if not tag:
-                    # Create the record
-                    tag = Tag(name=tag_name)
+        for tag_name in statement.get_tags():
+            tag = session.query(Tag).filter_by(name=tag_name).first()
 
-                record.tags.append(tag)
+            if not tag:
+                # Create the record
+                tag = Tag(name=tag_name)
 
-            session.add(record)
+            record.tags.append(tag)
 
-            self._session_finish(session)
+        session.add(record)
+        session.commit()
+        session.close()
 
     def get_random(self):
         """
@@ -388,13 +407,3 @@ class SQLStorageAdapter(StorageAdapter):
         """
         from chatterbot.ext.sqlalchemy_app.models import Base
         Base.metadata.create_all(self.engine)
-
-    def _session_finish(self, session, statement_text=None):
-        from sqlalchemy.exc import InvalidRequestError
-        try:
-            session.commit()
-        except InvalidRequestError:
-            # Log the statement text and the exception
-            self.logger.exception(statement_text)
-        finally:
-            session.close()

chatterbot/storage/storage_adapter.py

@@ -1,6 +1,4 @@
 import logging
-from chatterbot import languages
-from chatterbot.tagging import PosLemmaTagger
 
 
 class StorageAdapter(object):
@@ -17,11 +15,9 @@ class StorageAdapter(object):
         """
         self.logger = kwargs.get('logger', logging.getLogger(__name__))
 
-        Tagger = kwargs.get('tagger', PosLemmaTagger)
-
-        self.tagger = Tagger(language=kwargs.get(
-            'tagger_language', languages.ENG
-        ))
+        self.raise_on_missing_search_text = kwargs.get(
+            'raise_on_missing_search_text', True
+        )
 
     def get_model(self, model_name):
         """
@@ -116,6 +112,12 @@ class StorageAdapter(object):
             this parameter, then the statement will be included in the
             result set.
             Defaults to None
+
+        :param search_in_response_to: If the ``search_in_response_to`` field
+            of a statement contains a word that is in the string provided to
+            this parameter, then the statement will be included in the
+            result set.
+            Defaults to None
         """
         raise self.AdapterMethodNotImplementedError(
             'The `filter` method is not implemented by this adapter.'

chatterbot/trainers.py

@@ -93,7 +93,7 @@ class ListTrainer(Trainer):
         statements_to_create = []
 
         # Run the pipeline in bulk to improve performance
-        documents = self.chatbot.storage.tagger.as_nlp_pipeline(conversation)
+        documents = self.chatbot.tagger.as_nlp_pipeline(conversation)
 
         # for text in enumerate(conversation):
         for document in tqdm(documents, desc='List Trainer', disable=not self.show_training_progress):
@@ -143,7 +143,7 @@ class ChatterBotCorpusTrainer(Trainer):
             for conversation in corpus:
 
                 # Run the pipeline in bulk to improve performance
-                documents = self.chatbot.storage.tagger.as_nlp_pipeline(conversation)
+                documents = self.chatbot.tagger.as_nlp_pipeline(conversation)
 
                 previous_statement_text = None
                 previous_statement_search_text = ''
@@ -344,7 +344,7 @@ class UbuntuCorpusTrainer(Trainer):
                     previous_statement_text = None
                     previous_statement_search_text = ''
 
-                    documents = self.chatbot.storage.tagger.as_nlp_pipeline([
+                    documents = self.chatbot.tagger.as_nlp_pipeline([
                         (
                             row[3],
                             {

{ChatterBot-1.2.1.dist-info → chatterbot-1.2.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: ChatterBot
-Version: 1.2.1
+Version: 1.2.2
 Summary: ChatterBot is a machine learning, conversational dialog engine
 Author: Gunther Cox
 License: Copyright (c) 2016 - 2025, Gunther Cox

{ChatterBot-1.2.1.dist-info → chatterbot-1.2.2.dist-info}/RECORD

@@ -1,8 +1,8 @@
-chatterbot/__init__.py,sha256=Edfsbjoii_j0I4OOI1p1JLwfVRpwUW_8NhjfoNuvZRI,158
+chatterbot/__init__.py,sha256=a8HpoSxm94mcHPYO24QiFVYS4WzYafqOGq7j_VuTIr8,158
 chatterbot/__main__.py,sha256=nk19D56TlPT9Zdqkq4qZZrOnLKEc4YTwUVWmXYwSyHg,207
 chatterbot/adapters.py,sha256=LJ_KqLpHKPdYAFpMGK63RVH4weV5X0Zh5uGyan6qdVU,878
-chatterbot/chatterbot.py,sha256=WhV4sSa8psrm6DebtAewIEwkz3MrnjWRftQeZMQso2w,9328
-chatterbot/comparisons.py,sha256=bSVTsCbFEiyVv0Rg60addtrxgjbG3QlJa3murgDWkws,6145
+chatterbot/chatterbot.py,sha256=YLKLkQ-XI4Unr3rbzjpGIupOqenuevm21tAnx-yFFgQ,10400
+chatterbot/comparisons.py,sha256=8-qLFWC1Z7tZ3iPUpyY6AD9l-whSo3QE1Rno_SzIp-I,6570
 chatterbot/components.py,sha256=ld3Xam8olBClvE5QqcFYggE7Q7tODCFek7BO7lhfyeU,1782
 chatterbot/constants.py,sha256=c_KPQKc82CHX6H3maeyTYqWatx6j-N-8HJhmejoVi60,1875
 chatterbot/conversation.py,sha256=Y-WOxPN7I3igRyAEe5py1sfS6JIYPdbwjVlY3kM8Ys8,3175
@@ -12,10 +12,10 @@ chatterbot/filters.py,sha256=vDSDJz2FM10xT6ybs7qJiqy4X5I4gTEfwEnjBGUxZ9g,847
 chatterbot/languages.py,sha256=XSenfc5FxHk_JWG5gGHsZvjvrPBbCaVCm_OU-BeER_M,32784
 chatterbot/parsing.py,sha256=vS-w70cMkjq4YEpDOv_pXWhAI6Zj06WYDAcMDhYDj0M,23174
 chatterbot/preprocessors.py,sha256=aI4v987dZc7GOKhO43i0i73EX748hehYSpzikFHpEXs,1271
-chatterbot/response_selection.py,sha256=9E7CJKlC3UCHTGvEmYvfE9cEHOltJeU77z9NfRzmeB8,2950
-chatterbot/search.py,sha256=Bx6j_NIdp7YDnJvunE7rmk9ma37AKYw96R0iu2i4chc,5141
+chatterbot/response_selection.py,sha256=aYeZ54jpGIcQnI-1-TDcua_f1p3PiM5_iMg4hF5ZaIU,2951
+chatterbot/search.py,sha256=FTwwON2eKPWqoc5uoKh4AUmuXDCqyfMcMcXB4wijpxg,4910
 chatterbot/tagging.py,sha256=GLY9wg_rvn6pSYVML-HcxkIo_3BZ3SAyj-q1oNZY8pI,2584
-chatterbot/trainers.py,sha256=4u6RDRPpAnecTEAOrGcDvMTjEn8Kxn8slM4UnovDvNk,13339
+chatterbot/trainers.py,sha256=U1yh0_V7FFL51MeQe1P1Q59weceDbkHh_2kDiDYpSEc,13315
 chatterbot/utils.py,sha256=ckQXvsjp2FO9GcWxziY67JovN7mShnE4RlzdYarQY5k,3277
 chatterbot/ext/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 chatterbot/ext/django_chatterbot/__init__.py,sha256=iWzmBzpAsYwkwi1faxAPFY9L1bbL97RgVXK2uqULIMc,92
@@ -48,19 +48,19 @@ chatterbot/ext/django_chatterbot/migrations/__init__.py,sha256=47DEQpj8HBSa-_TIm
 chatterbot/ext/sqlalchemy_app/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 chatterbot/ext/sqlalchemy_app/models.py,sha256=pjU4e2BUSitw_IAkrk4iFQ9pZRU35y5MomvX7aiBFCw,2492
 chatterbot/logic/__init__.py,sha256=28-5swBCPfSVMl8xB5C8frOKZ2oj28rQfenbd9E4r-4,531
-chatterbot/logic/best_match.py,sha256=iueuuK6WTTywqskwC1CuWD2uHgA65Hz30h8tce_H1bU,4619
+chatterbot/logic/best_match.py,sha256=8TNW0uZ_Uq-XPfaZUMUZDVH6KzDT65j59xblxQBv-dQ,4820
 chatterbot/logic/logic_adapter.py,sha256=5kNEirh5fiF5hhSMFXD7bIkKwXHmrSsSS4qDm-6xry0,4694
 chatterbot/logic/mathematical_evaluation.py,sha256=GPDKUwNFajERof2R-MkPGi2jJRP-rKAGm_f0V9JHDHE,2282
 chatterbot/logic/specific_response.py,sha256=_VeJaa3kun0J7cVzLOlTYK1tBpth0B6UWms7QwtcNpY,1082
 chatterbot/logic/time_adapter.py,sha256=mxdoQGeC5IjREH4PU5iHYOIPEvnYnzgysocR8xMYWXc,2406
 chatterbot/logic/unit_conversion.py,sha256=DT50HHE3njUo_ttDSU8S-fwBylarhDF3l_McRLSX6Ic,5823
 chatterbot/storage/__init__.py,sha256=IymIHfeisvULQzUYsQSiUBbWIZ1m5EzyMVI082tTw5w,369
-chatterbot/storage/django_storage.py,sha256=b_hJkBm0ZNgBB16HjJaNYVFEPs0AApRjOZpuiGNDaXk,6990
-chatterbot/storage/mongodb.py,sha256=s6rzn0m_eu4kkXeb80vVCyHyZrdrVW_Zf8PlttUHQlk,8962
-chatterbot/storage/sql_storage.py,sha256=X3PKKYcS4tiBWmuvxNMTLxK0shUQlchW0UPB1Mb1rqI,13144
-chatterbot/storage/storage_adapter.py,sha256=QwY3cGVpZLxkmww0OnPGZbdOykuOZT7WSKYHq84TgI0,5956
-ChatterBot-1.2.1.dist-info/LICENSE,sha256=5b04U8mi0wp5gJMYlKi49EalnD9Q2nwY_6UEI_Avgu4,1476
-ChatterBot-1.2.1.dist-info/METADATA,sha256=dF7H-ZhaTdjCYSDFhsChT8h38fFQfykFmXvB6s1v1n0,8311
-ChatterBot-1.2.1.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-ChatterBot-1.2.1.dist-info/top_level.txt,sha256=W2TzAbAJ-eBXTIKZZhVlkrh87msJNmBQpyhkrHqjSrE,11
-ChatterBot-1.2.1.dist-info/RECORD,,
+chatterbot/storage/django_storage.py,sha256=S5S4GipD7FyNJy4RWu5-S8sLPuSJIObwTtqTpnJu-ok,6159
+chatterbot/storage/mongodb.py,sha256=Ozvdvcjb3LGZxcvbSQGzwP9VloYQbmsa2FaKunFpMyU,7934
+chatterbot/storage/sql_storage.py,sha256=VVYZvclG_74IN-MrG0edc-RQ2gUO6gRQyCWWSO0MmCk,13082
+chatterbot/storage/storage_adapter.py,sha256=fvyb-qNiB0HMJ0siVMCWUIY--6d-C47N1_kKZVFZAv4,6110
+chatterbot-1.2.2.dist-info/LICENSE,sha256=5b04U8mi0wp5gJMYlKi49EalnD9Q2nwY_6UEI_Avgu4,1476
+chatterbot-1.2.2.dist-info/METADATA,sha256=EGYwvpQjhqJOfjlQWI83memJr0sXKo9QwM_wbp1wtrg,8311
+chatterbot-1.2.2.dist-info/WHEEL,sha256=nn6H5-ilmfVryoAQl3ZQ2l8SH5imPWFpm1A5FgEuFV4,91
+chatterbot-1.2.2.dist-info/top_level.txt,sha256=W2TzAbAJ-eBXTIKZZhVlkrh87msJNmBQpyhkrHqjSrE,11
+chatterbot-1.2.2.dist-info/RECORD,,

{ChatterBot-1.2.1.dist-info → chatterbot-1.2.2.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.8.0)
+Generator: setuptools (75.8.1)
 Root-Is-Purelib: true
 Tag: py3-none-any