def check_condition(self, bot, session, interlocutor, interpreted_phrase, answering_engine):
input_phrase = interpreted_phrase.interpretation
text_utils = answering_engine.text_utils
tokens = text_utils.tokenizer.tokenize(input_phrase)
tagsets = list(text_utils.postagger.tag(tokens))
lemmas = text_utils.lemmatizer.lemmatize(tagsets)
#edges = syntan.parse(tokens, tagsets)
# заглушка вместо парсинга:
edges = [(word, iword, None, None, None) for (iword, word) in enumerate(tokens)]
phrase_tokens = []
for word_index, (token, tagset, lemma) in enumerate(zip(tokens, tagsets, lemmas)):
t = PhraseToken()
t.word = token
t.norm_word = token.lower()
t.lemma = lemma[2]
t.tagset = tagset[1]
t.word_index = word_index
phrase_tokens.append(t)
chunks = text_utils.chunker.parse(tokens)
for chunk_index, chunk in enumerate(chunks):
phrase_tokens[chunk.tokens[0].index].is_chunk_starter = True
for token in chunk.tokens:
phrase_tokens[token.index].chunk_index = chunk_index
for mask in self.masks:
mx = match(phrase_tokens, mask.mask_terms)
if mx:
#print('{} groups in matching:'.format(mx.groups_count()))
res = RuleConditionMatching.create(True)
for group_name, tokens in mx.index2group.items():
normal_words = normalize_chunk(tokens, edges, text_utils.flexer, text_utils.word2tags)
#print('{}={} normal={}'.format(group_name, ' '.join(t.word for t in tokens), ' '.join(normal_words)))
res.add_group(group_name.upper(), normal_words, tokens)
return res
return RuleConditionMatching.create(False)
def extract_chunks(self, sample):
tokens = self.tokenizer.tokenize(sample)
tagsets = list(self.postagger.tag(tokens))
lemmas = self.lemmatizer.lemmatize(tagsets)
#edges = syntan.parse(tokens, tagsets)
phrase_tokens = []
for word_index, (token, tagset, lemma) in enumerate(zip(tokens, tagsets, lemmas)):
t = PhraseToken()
t.word = token
t.norm_word = token.lower()
t.lemma = lemma[2]
t.tagset = tagset[1]
t.word_index = word_index
phrase_tokens.append(t)
chunks = self.chunker.parse(tokens)
for chunk_index, chunk in enumerate(chunks):
phrase_tokens[chunk.tokens[0].index].is_chunk_starter = True
for token in chunk.tokens:
phrase_tokens[token.index].chunk_index = chunk_index
return chunks
def check_condition(self, bot, session, interlocutor, interpreted_phrase,
answering_engine):
if self.is_raw:
input_phrase = interpreted_phrase.raw_phrase
else:
input_phrase = interpreted_phrase.interpretation
text_utils = answering_engine.text_utils
tokens = text_utils.tokenizer.tokenize(input_phrase)
tagsets = list(text_utils.postagger.tag(tokens))
lemmas = text_utils.lemmatizer.lemmatize(tagsets)
#edges = syntan.parse(tokens, tagsets)
# заглушка вместо парсинга:
edges = [(word, iword, None, None, None)
for (iword, word) in enumerate(tokens)]
phrase_tokens = []
for word_index, (token, tagset,
lemma) in enumerate(zip(tokens, tagsets, lemmas)):
t = PhraseToken()
t.word = token
t.norm_word = token.lower()
t.lemma = lemma[2]
t.tagset = tagset[1]
t.word_index = word_index
phrase_tokens.append(t)
chunks = text_utils.chunker.parse(tokens)
for chunk_index, chunk in enumerate(chunks):
phrase_tokens[chunk.tokens[0].index].is_chunk_starter = True
for token in chunk.tokens:
phrase_tokens[token.index].chunk_index = chunk_index
for mask in self.masks:
mx = match(phrase_tokens, mask.mask_terms)
if mx:
#print('{} groups in matching:'.format(mx.groups_count()))
res = RuleConditionMatching.create(True)
for group_name, tokens in mx.index2group.items():
normal_words1 = normalize_chunk(tokens, edges,
text_utils.flexer,
text_utils.word2tags)
normal_words2 = normalize_chunk(
tokens,
edges,
text_utils.flexer,
text_utils.word2tags,
target_tags={'ЧИСЛО': 'ЕД'})
normal_words = list(
set(normal_words1) | set(normal_words2))
if group_name in self.constraints_w2v:
constraints_satisfied = True
for c in self.constraints_w2v[group_name]:
hit = False
for chunk_word in normal_words:
sim = text_utils.word_similarity(
c.anchor, chunk_word)
if sim >= c.sim:
hit = True
break
if not hit:
constraints_satisfied = False
break
if not constraints_satisfied:
return RuleConditionMatching.create(False)
#print('{}={} normal={}'.format(group_name, ' '.join(t.word for t in tokens), ' '.join(normal_words)))
res.add_group(group_name.upper(), normal_words, tokens)
return res
return RuleConditionMatching.create(False)
def do_action(self, bot, session, interlocutor, interpreted_phrase,
condition_matching_results, text_utils):
if self.np_sources:
if condition_matching_results is None:
condition_matching_results = RuleConditionMatching.create(True)
for np, question in self.np_sources.items():
if bot.get_engine().does_bot_know_answer(
question, bot, session, interlocutor):
interpreted_phrase2 = InterpretedPhrase(question)
answers = bot.get_engine().build_answers(
session, bot, interlocutor, interpreted_phrase2)
if answers:
answer = answers[0]
tokens = text_utils.tokenize(answer)
tagsets = list(text_utils.postagger.tag(tokens))
lemmas = text_utils.lemmatizer.lemmatize(tagsets)
phrase_tokens = []
for word_index, (token, tagset, lemma) in enumerate(
zip(tokens, tagsets, lemmas)):
t = PhraseToken()
t.word = token
t.norm_word = token.lower()
t.lemma = lemma[2]
t.tagset = tagset[1]
t.word_index = word_index
phrase_tokens.append(t)
condition_matching_results.add_group(
np, tokens, phrase_tokens)
else:
return None
# Сначала попробуем убрать из списка те реплики, которые мы уже произносили.
new_utterances = []
for utterance0 in self.phrases:
utterance = self.prepare4saying(utterance0,
condition_matching_results,
text_utils)
if '$' in utterance:
# Не удалось подставить значение в один из $-слотов, значит
# надо исключить фразу.
continue
if session.count_bot_phrase(utterance) == 0:
if self.known_answer_policy == 'skip' and utterance[-1] == '?':
# Проверим, что бот еще не знает ответ на этот вопрос:
if bot.does_bot_know_answer(utterance, session,
interlocutor):
continue
new_utterances.append(utterance)
uttered = False
if len(new_utterances) > 0:
# Выбираем одну из оставшихся фраз.
if len(new_utterances) == 1:
bot.say(session, new_utterances[0])
else:
bot.say(session, random.choice(new_utterances))
uttered = True
else:
# Все фразы бот уже произнес
# Если задан список фраз на случай исчерпания (типа "не знаю больше ничего про кошек"),
# то выдадим одну из них.
new_utterances = []
for utterance0 in self.exhausted_phrases:
utterance = self.prepare4saying(utterance0,
condition_matching_results,
text_utils)
if '$' in utterance:
# Не удалось подставить значение в один из $-слотов, значит
# надо исключить фразу.
continue
if session.count_bot_phrase(utterance) == 0:
if self.known_answer_policy == 'skip' and utterance[
-1] == '?':
# Проверим, что бот еще не знает ответ на этот вопрос:
if bot.does_bot_know_answer(utterance, session,
interlocutor):
continue
new_utterances.append(utterance)
if new_utterances:
bot.say(session, random.choice(new_utterances))
uttered = True
else:
if self.known_answer_policy == 'skip':
pass
else:
# Начиная с этого момента данное правило будет повторно выдавать
# одну из фраз.
#for src_phrase in sorted(self.phrases, key=lambda z: random.random()):
# random_phrase = self.prepare4saying(src_phrase, condition_matching_results, text_utils)
# if '$' not in random_phrase:
# bot.say(session, random_phrase)
# uttered = True
# break
uttered = False
return uttered