def __init__(self,
database_path,
language_path,
json_output_path=None,
thesaurus_path=None,
stopwords_path=None,
color=False):
if color == False:
without_color()
database = Database()
self.stopwordsFilter = None
if thesaurus_path:
thesaurus = Thesaurus()
thesaurus.load(thesaurus_path)
database.set_thesaurus(thesaurus)
#print(thesaurus.print_me())
#print("Hello")
if stopwords_path:
self.stopwordsFilter = StopwordFilter()
self.stopwordsFilter.load(stopwords_path)
database.load(database_path)
# database.print_me()
config = LangConfig()
config.load(language_path)
self.parser = Parser(database, config)
self.json_output_path = json_output_path
def make_thesaurus():
start = timer()
print("setting up thesaurus")
thesaurus = Thesaurus.Thesaurus()
thesaurus.build_jaccard_word_pair_table()
print("finished setting up thesaurus")
end = timer()
print(f"{end - start} seconds")
def make_doc_term():
start = timer()
print("setting up doc_term_table")
thesaurus = Thesaurus.Thesaurus()
thesaurus.build_doc_term_table()
print("finished setting up doc_term_table")
end = timer()
print(f"{end - start} seconds")
def __init__(
self,
textIn,
thesaurus=Thesaurus(filename="./thesauruses/thesaurusA.pickle")):
self.textOut = None
self.thesaurus = thesaurus
self.punctuation = ", . ? ! : ; -".split(" ") #Add more ???
self.textIn = textIn
def set_method_type(self, method_type):
if method_type == '1':
self._method_class = LocalMethod(self)
elif method_type == '2':
self._method_class = Thesaurus(self)
elif method_type == '3':
self._method_class = Wordnet(self)
elif method_type == '4':
self._method_class = MySpellCheker(self)
class Article:
encodings = ["utf-8", "cp932", "euc-jp", "iso-2022-jp", "latin_1"]
tokenizer = Thesaurus('thesaurus.csv')
def __init__(self, path):
print(path)
self.path = path
self.contents = self.preprocess(self.get_contents(path))
# self.contents = self.preprocess(self.get_title(path))
self.tokens = [
token.surface for token in self.tokenizer.tokenize(self.contents)
if re.match("カスタム名詞|名詞,(固有|一般|サ変)", token.part_of_speech)
]
# print(self.tokens)
def get_contents(self, path):
exceptions = []
for encoding in self.encodings:
try:
all = codecs.open(path, 'r', encoding).read()
parts = re.split("(?i)<(body|frame)[^>]*>", all, 1)
if len(parts) == 3:
head, void, body = parts
else:
print('Cannot split ' + path)
body = all
return re.sub(
"<[^>]+?>", "",
re.sub(
r"(?is)<(script|style|select|noscript)[^>]*>.*?</\1\s*>",
"", body))
except UnicodeDecodeError:
continue
print('Cannot detect encoding of ' + path)
print(exceptions)
return None
def get_title(self, path):
return re.split('\/', path)[-1]
def preprocess(self, text):
text = re.sub("&[^;]+;", " ", text)
text = mojimoji.han_to_zen(text, digit=False)
# text = re.sub('(\s| |＃)+', " ", text)
return text
def dense(self, dictionary):
values_set = set(dictionary.values())
text = [token for token in self.tokens if token in values_set]
corpus = dictionary.doc2bow(text)
return matutils.corpus2dense([corpus], len(dictionary)).T[0]
class MyApp():
"""Class for a GUI """
def __init__(self, parent,thes=""):
""" initialize the GUI with all visible elements and menus """
#self.MyParent of MyApp
self.MyParent = parent
# import a thesaurus if given as an argument or create an empty one
if thes is "":
self.t1=Thesaurus("Neuer Thesaurus")
else:
self.t1=thes
self.MyParent.title("uberthesaurus - %s"% self.t1.name)
# scrollbars for the listboxes
self.scrollbar1 = Scrollbar(self.MyParent, orient=VERTICAL)
self.scrollbar2 = Scrollbar(self.MyParent, orient=VERTICAL)
# 2 listboxes for des and terms
self.deslistbox = Listbox(self.MyParent, yscrollcommand=self.scrollbar1.set, exportselection=0)
self.termlistbox = Listbox(self.MyParent, yscrollcommand=self.scrollbar2.set, exportselection=0)
#self.termlistbox.bind("<<Double-Button-1>>", lambda event:self.deslistbox.select_set())
self.deslistbox.bind("<<ListboxSelect>>", lambda event: self.update_tlist())
# a frame for changing elements
self.myContainer1 = Frame(self.MyParent)
# add scrollbars for the listboxes
self.scrollbar1.config(command=self.deslistbox.yview)
self.scrollbar2.config(command=self.termlistbox.yview)
#add buttons for interaktion with des
self.add1_button=Button(self.MyParent, text='Hinzufuegen', command=self.add_des, width=10)
self.edit1_button=Button(self.MyParent, text='Bearbeiten', command=self.edit_des, width=10)
self.del1_button=Button(self.MyParent, text="Loeschen", command=self.del_des, width=10)
#add buttons for interaktion with terms
self.add2_button=Button(self.MyParent, text='Hinzufuegen', command=self.add_term, width=10)
self.edit2_button=Button(self.MyParent, text='Bearbeiten', command=self.edit_term, width=10)
self.del2_button=Button(self.MyParent, text="Loeschen", command=self.del_term, width=10)
# confige the spacing
self.MyParent.columnconfigure(1, weight=0)
self.MyParent.columnconfigure(1, pad=0)
self.MyParent.columnconfigure(2, pad=7)
self.MyParent.columnconfigure(3, pad=7)
self.MyParent.rowconfigure(1, weight=0)
self.MyParent.rowconfigure(2, weight=0)
self.MyParent.rowconfigure(3, weight=1)
# place all GUI-elements
self.add1_button.grid(row=1, column=0, pady=2, sticky=NW)
self.edit1_button.grid(row=2, column=0, pady=2, sticky=NW)
self.del1_button.grid(row=3, column=0, pady=2, sticky=NW)
self.deslistbox.grid(row=1, column=1, rowspan=3,pady=5, sticky=NS)
self.scrollbar1.grid(row=1, column=2, rowspan=3, pady=5, sticky=NS)
self.termlistbox.grid(row=1,column=3, rowspan=3, pady=5, sticky=NS)
self.scrollbar2.grid(row=1,column=4, rowspan=3, pady=5, sticky=NS)
self.add2_button.grid(row=1,column=5, pady=2, sticky=NW)
self.edit2_button.grid(row=2,column=5, pady=2, sticky=NW)
self.del2_button.grid(row=3,column=5, pady=2, sticky=NW)
# self.myContainer1.grid()
# Menu
self.menu = Menu(self.MyParent)
self.MyParent.config(menu=self.menu)
self.filemenu = Menu(self.menu)
self.menu.add_cascade(label="Datei", menu=self.filemenu)
# Main Menu
self.filemenu.add_command(label="Neu", command=self.new_thes)
self.filemenu.add_command(label="Verbinden", command=self.t1.connect)
self.filemenu.add_command(label="Import", command=self.importdatei)
self.filemenu.add_command(label="Export", command=self.export)
self.filemenu.add_command(label="Schliessen", command=self.exit_prog)
def update_dlist(self):
""" Updates the listbox for the descriptors"""
self.deslistbox.delete(0, END)
for elem in sorted(self.t1.entries.keys()):
self.deslistbox.insert(END, elem)
def update_tlist(self):
""" Updates the listbox for the relations and terms"""
if self.t1.entries!={}:
if self.deslistbox.curselection()!=():
tlist=self.t1.entries[self.deslistbox.get(self.deslistbox.curselection())].get_terms()
else:
tlist=self.t1.entries[self.deslistbox.get(0)].get_terms()
self.termlistbox.delete(0, END)
for key,value in sorted(tlist.iteritems()):
for elem in value:
self.termlistbox.insert(END, key + " "+elem)
else:
self.termlistbox.delete(0, END)
def del_des(self):
""" Deletes the selected element of the listbox for the descriptors"""
if self.deslistbox.curselection() != ():
self.t1.delete_entries(self.deslistbox.get(self.deslistbox.curselection()))
self.update_dlist()
self.update_tlist()
def add_des(self):
""" Deletes the selected element of the listbox for the relations and terms"""
self.des = tkSimpleDialog.askstring("Deskriptor hinzufuegen", "Deskriptor:")
if self.des is not None:
self.t1.create_entries(self.des)
self.update_dlist()
self.update_tlist()
def edit_des(self):
"""Opens up a dialog for descriptor editing"""
self.des = tkSimpleDialog.askstring("Deskriptor bearbeiten", "Bearbeiten:")
if self.des is not None:
self.t1.edit_entries(self.deslistbox.get(self.deslistbox.curselection()),self.des)
self.update_dlist()
self.update_tlist()
def del_term(self):
""" Deletes the selected term from the termlist """
if self.termlistbox.curselection() != ():
self.term=self.termlistbox.get(self.termlistbox.curselection())
self.term=self.term.split(" ")
self.t1.entries[self.deslistbox.get(self.deslistbox.curselection())].remove_term(self.term[0],self.term[1])
self.update_tlist()
def add_term(self):
"""Opens up a dialog for term adding"""
self.term = tkSimpleDialog.askstring("Term hinzufuegen", "Rel Term:")
if self.term is not None:
self.term=self.term.split(" ")
self.t1.add(self.deslistbox.get(self.deslistbox.curselection()), self.term[1], self.term[0])
self.update_dlist()
self.update_tlist()
def edit_term(self):
"""Opens up a dialog for term/rel editing"""
self.rel_term=tkSimpleDialog.askstring("Term bearbeiten", "Rel Term")
if self.rel_term is not None:
self.rel_term=self.rel_term.split(" ")
self.rel_term_old=self.termlistbox.get(self.termlistbox.curselection()).split(" ")
if self.rel_term[0]!=self.rel_term_old[0]:
self.t1.entries[self.deslistbox.get(self.deslistbox.curselection())].edit_rel(str(self.rel_term_old[0]), str(self.rel_term_old[1]), str(self.rel_term[0]))
if self.rel_term[1]!=self.rel_term_old[1]:
self.t1.entries[self.deslistbox.get(self.deslistbox.curselection())].edit_term(str(self.rel_term_old[0]), str(self.rel_term_old[1]), str(self.rel_term[1]))
self.update_dlist()
self.update_tlist()
def exit_prog(self):
"""Exits the program"""
self.MyParent.destroy()
def new_thes(self):
"""Clears all entries of the thesaurus"""
self.t1.entries={}
self.update_dlist()
self.update_tlist()
self.t1.name="Neuer Thesaurus"
self.MyParent.title("uberthesaurus - %s"% self.t1.name)
def export(self):
"""Extracts the filetype and calls the real export method if a valid filename is given"""
self.formats = [
('Comma-separated values','*.csv'),
('JavaScript Object Notation','*.json'),
('Extensible Markup Language','*.xml'),
]
self.filename = asksaveasfilename(filetypes=self.formats, title="Den Thesaurus exportieren", defaultextension=".xml")
if len(self.filename)>0:
self.t1.export_thesaurus(self.filename)
self.MyParent.title("uberthesaurus - %s"% self.t1.name)
else:
print "Keine Datei angegeben."
def importdatei(self):
"""Extracts the filetype and calls the real import method if a valid filename is given"""
self.filename = askopenfilename()
if len(self.filename)>0:
self.t1.import_thesaurus(self.filename)
self.update_dlist()
self.MyParent.title("uberthesaurus - %s"% self.t1.name)
else:
print "Keine Datei angegeben."
def __init__(self, parent,thes=""):
""" initialize the GUI with all visible elements and menus """
#self.MyParent of MyApp
self.MyParent = parent
# import a thesaurus if given as an argument or create an empty one
if thes is "":
self.t1=Thesaurus("Neuer Thesaurus")
else:
self.t1=thes
self.MyParent.title("uberthesaurus - %s"% self.t1.name)
# scrollbars for the listboxes
self.scrollbar1 = Scrollbar(self.MyParent, orient=VERTICAL)
self.scrollbar2 = Scrollbar(self.MyParent, orient=VERTICAL)
# 2 listboxes for des and terms
self.deslistbox = Listbox(self.MyParent, yscrollcommand=self.scrollbar1.set, exportselection=0)
self.termlistbox = Listbox(self.MyParent, yscrollcommand=self.scrollbar2.set, exportselection=0)
#self.termlistbox.bind("<<Double-Button-1>>", lambda event:self.deslistbox.select_set())
self.deslistbox.bind("<<ListboxSelect>>", lambda event: self.update_tlist())
# a frame for changing elements
self.myContainer1 = Frame(self.MyParent)
# add scrollbars for the listboxes
self.scrollbar1.config(command=self.deslistbox.yview)
self.scrollbar2.config(command=self.termlistbox.yview)
#add buttons for interaktion with des
self.add1_button=Button(self.MyParent, text='Hinzufuegen', command=self.add_des, width=10)
self.edit1_button=Button(self.MyParent, text='Bearbeiten', command=self.edit_des, width=10)
self.del1_button=Button(self.MyParent, text="Loeschen", command=self.del_des, width=10)
#add buttons for interaktion with terms
self.add2_button=Button(self.MyParent, text='Hinzufuegen', command=self.add_term, width=10)
self.edit2_button=Button(self.MyParent, text='Bearbeiten', command=self.edit_term, width=10)
self.del2_button=Button(self.MyParent, text="Loeschen", command=self.del_term, width=10)
# confige the spacing
self.MyParent.columnconfigure(1, weight=0)
self.MyParent.columnconfigure(1, pad=0)
self.MyParent.columnconfigure(2, pad=7)
self.MyParent.columnconfigure(3, pad=7)
self.MyParent.rowconfigure(1, weight=0)
self.MyParent.rowconfigure(2, weight=0)
self.MyParent.rowconfigure(3, weight=1)
# place all GUI-elements
self.add1_button.grid(row=1, column=0, pady=2, sticky=NW)
self.edit1_button.grid(row=2, column=0, pady=2, sticky=NW)
self.del1_button.grid(row=3, column=0, pady=2, sticky=NW)
self.deslistbox.grid(row=1, column=1, rowspan=3,pady=5, sticky=NS)
self.scrollbar1.grid(row=1, column=2, rowspan=3, pady=5, sticky=NS)
self.termlistbox.grid(row=1,column=3, rowspan=3, pady=5, sticky=NS)
self.scrollbar2.grid(row=1,column=4, rowspan=3, pady=5, sticky=NS)
self.add2_button.grid(row=1,column=5, pady=2, sticky=NW)
self.edit2_button.grid(row=2,column=5, pady=2, sticky=NW)
self.del2_button.grid(row=3,column=5, pady=2, sticky=NW)
# self.myContainer1.grid()
# Menu
self.menu = Menu(self.MyParent)
self.MyParent.config(menu=self.menu)
self.filemenu = Menu(self.menu)
self.menu.add_cascade(label="Datei", menu=self.filemenu)
# Main Menu
self.filemenu.add_command(label="Neu", command=self.new_thes)
self.filemenu.add_command(label="Verbinden", command=self.t1.connect)
self.filemenu.add_command(label="Import", command=self.importdatei)
self.filemenu.add_command(label="Export", command=self.export)
self.filemenu.add_command(label="Schliessen", command=self.exit_prog)
textSubstitutions.append(sentenceSubstitutions)
return textSubstitutions
def obfuscate(self, text):
"""Apply the functions in sequence to obfuscate the text"""
functions = [
self._tokenise, self._substituteSynonyms, self._untokenise
]
temp = text
for function in functions:
temp = function(temp)
return temp
def __repr__(self):
return "Text obfuscator on thesaurus: '{}', with replace factor: {}".format(
self._thesaurus.filename, self._replaceFactor)
if __name__ == "__main__":
seed(0)
thesaurus = Thesaurus(filename="./thesauruses/thesaurusA.pickle")
obfuscator = Obfuscator(thesaurus, replaceFactor=1)
print(obfuscator)
text = "The quick brown fox jumped over the lazy dog!"
obfuscatedText = obfuscator.obfuscate(text)
print(text)
print(obfuscatedText)
("jacoby", "N"),
]
testpair = (("kiwis", "N"), ("zealanders", "N"))
# simcache=False #whether file currently contains valid sims
k = 1000
kdisplay = 10
print(sys.argv)
Thesaurus.byblo = byblo # take command line argument as to whether this is a byblo file or not
if metric == "cosine":
compress = True
else:
compress = False
mythes = Thesaurus(vectorfilename, simcachefile, simcache, windows, k, adja, adjb, compress)
mythes.readvectors()
# if simcache:
# check=True
# else:
# for wordA in words:
# for wordB in words:
# mythes.outputsim(wordA,wordB,metric)
(word1, word2) = testpair
if simcache == False:
mythes.outputsim(word1, word2, metric)
mythes.allpairssims(metric)
def __init__(self, config=None):
self._config = config
self._parser = Parse(config)
self._indexer = Indexer(config)
self._model = Word2Vec()
self._model_1 = Thesaurus()
from thesaurus import Thesaurus
from sys import exit
thes = Thesaurus()
print('Type HELP to see a list of commands and instructions.\n')
while True:
query = input('Enter a word to look it up in the thesaurus:\n')
if query.strip() == 'HELP':
print('QUIT'.ljust(25), 'Exits the program.')
print('REQUIRE <word list(s)>'.ljust(25), 'Shows only results from these specific word list(s).')
print('REQUIRE ANY'.ljust(25), 'Does not show words that are not in a word list.')
print('RESET SETTINGS'.ljust(25), 'Resets to default settings.')
print()
print('To add a new word list, create a txt file in the filters directory with each word on a new line. Then restart the program.')
elif query.strip() == 'QUIT':
exit()
elif query.strip().lower() == 'reset settings':
thes = Thesaurus()
print('Settings have been reset.')
elif query.strip() == 'require any':
thes = Thesaurus(must_match=True)
elif len(query.strip().split()) > 1:
# change required word list(s)
def init_logic_translator(self, logic_thesaurus_path):
"""Initialize logic translator"""
self._logic_thesaurus = Thesaurus(logic_thesaurus_path, ["Logic"])
jieba.load_userdict(logic_thesaurus_path)
def init_classification(self, customized_thesaurus_path):
self._customized_thesaurus = Thesaurus(customized_thesaurus_path, ["Frequency", "Property"])
jieba.load_userdict(customized_thesaurus_path)
class TokenUtil(object):
"""Tokenizer would initialize the thesaurus and scan all utf-8 encoded vocabulary on the disk."""
def __init__(self, general_thesaurus_path):
"""Read the general thesaurus"""
jieba.initialize(general_thesaurus_path)
def init_classification(self, customized_thesaurus_path):
self._customized_thesaurus = Thesaurus(customized_thesaurus_path, ["Frequency", "Property"])
jieba.load_userdict(customized_thesaurus_path)
def get_keyword(self, content):
seg_list = jieba.cut_for_search(content)
customized_words = []
for atoken in seg_list:
if atoken in self._customized_thesaurus:
customized_words.append(atoken)
if len(customized_words) > 0:
return {'Type': 'customized',
'Token': customized_words}
else:
return {'Type': 'general',
'Token': content}
def init_logic_translator(self, logic_thesaurus_path):
"""Initialize logic translator"""
self._logic_thesaurus = Thesaurus(logic_thesaurus_path, ["Logic"])
jieba.load_userdict(logic_thesaurus_path)
def logic_translate(self, content):
"""Translate the content to logic expression for Baidu Search Engine"""
content = strdecode(content)
result_list = []
token_list = jieba.tokenize(content)
has_logic = False
for token in token_list:
if token[0] in self._logic_thesaurus:
has_logic = True
result_list.append({"Type": self._logic_thesaurus.get_attr(token[0])["Logic"],
"Content": token[0]})
else:
result_list.append({"Type": "Common",
"Content": token[0]})
if not has_logic:
return {"Type": "general",
"Content": content}
translate_finish = False
or_list = []
not_list = []
and_list = []
while(not translate_finish and len(result_list) > 0):
for index in range(len(result_list)):
if result_list[index]["Type"] == "NOT":
# 如果是NOT逻辑词
if index < len(result_list) - 1 and result_list[index + 1]["Type"] == "Common":
# 如果可以合并语句，则进行合并
not_list.append("-(" + result_list[index + 1]["Content"] + ")")
del result_list[index + 1]
del result_list[index]
break
else:
# 若不能合并语句，则将逻辑词视为普通词语
result_list[index]["Type"] = "Common"
if result_list[index]["Type"] == "AND":
# 如果是AND逻辑词
if 0 < index < len(result_list) - 1 and result_list[index + 1]["Type"] == "Common" and\
result_list[index - 1]["Type"] == "Common":
and_list.append("(" + result_list[index - 1]["Content"] + " " +
result_list[index + 1]["Content"] + ")")
del result_list[index + 1]
del result_list[index]
del result_list[index - 1]
break
else:
# 若不能合并语句，则将逻辑词视为普通词语
result_list[index]["Type"] = "Common"
if result_list[index]["Type"] == "OR":
# 如果是OR连接词
if 0 < index < len(result_list) - 1 and result_list[index + 1]["Type"] == "Common" and\
result_list[index - 1]["Type"] == "Common":
or_list.append("(" + result_list[index - 1]["Content"] + " | " +
result_list[index + 1]["Content"] + ")")
del result_list[index + 1]
del result_list[index]
del result_list[index - 1]
break
else:
# 若不能合并语句，则将逻辑词视为普通词语
result_list[index]["Type"] = "Common"
if index >= len(result_list) - 1:
# 所有逻辑词处理完成
translate_finish = True
result_content = " ".join([item["Content"] for item in result_list]) + " " + " ".join(and_list) + " " +\
" ".join(or_list) + " " + " ".join(not_list)
if(result_content == ""):
return {"Type": "general",
"Content": content}
return {"Type": "logic",
"Content": result_content}
parameters=conf.configure(sys.argv)
inputfile="allBLESS-dependencies.json"
inputpath=os.path.join(parameters['datadir'],inputfile)
print inputpath
with open(inputpath,'r') as instream:
for line in instream:
print line
pairs = json.loads(inputpath)
cluster0=[]
cluster1=[]
for (w1,w2,target) in pairs:
if target==1:
cluster1.append(w2)
else:
cluster0.append(w2)
print len(cluster0), cluster0
print len(cluster1),cluster1
exit()
words=["chicken","cricket","jaguar"]
pos="N"
mythes = Thesaurus("",parameters["simfile"],True,False,parameters["k"],1,1,False)
mythes.readsomesims(words)
for word in words:
mythes.displayneighs((word,pos),100)
'''
Created on Dec 4, 2012
@author: juliewe
'''
#test thesaurus class
from thesaurus import Thesaurus
from thesaurus import Entry
from thesaurus import Neighbours
filename='/Volumes/research/calps/data3/mlcl/DisCo/thesauri/exp4-11c.strings'
mythesaurus = Thesaurus("test")
#
e1 = Entry("cat/N","dog/N",0.8)
e2 = Entry("cat/N","ostrich/N",0.5)
e3 = Entry("dog/N","ostrich/N",0.6)
mythesaurus.addEntry(e1)
mythesaurus.addEntry(e2)
mythesaurus.addEntry(e3)
print "Similarity between cat and ostrich is ", mythesaurus.lookupSim("cat","ostrich")
print "Similarity between cat and bird is ", mythesaurus.lookupSim("cat","bird")
print "Number of entries:", Entry.entrycount
print "Number of neighbour sets:", Neighbours.entrycount
def __init__(self, synonym_file, input_file_1, input_file_2, tuple_size):
self.thesaurus = Thesaurus(synonym_file)
self.input_file_1 = input_file_1
self.input_file_2 = input_file_2
self.tuple_size = tuple_size
class Data:
structured_answers = [
AnswerStructure('Ola, tudo bem?', ['Oi tudo bem', 'Oi', 'Tudo bem']),
AnswerStructure(
'Um ser humano adulto possui entre 4 a 6 litros de sangue.', [
'quantos litros de sangue uma pessoa tem ?',
'qual a quantidade de sangue de uma pessoa adulta ?'
]),
AnswerStructure('São retirados 450 mililitros numa doação de sangue.',
['quantos litros de sangue doação ?']),
AnswerStructure('Celebre frase de Renè Descartes.', [
' De quem e a famosa frase “ Penso , logo existo ” ?',
'famosa frase “ Penso , logo existo ” ?',
'frase “ Penso , logo existo ” ?', 'Penso , logo existo',
'Penso logo existo'
]),
AnswerStructure('O chuveiro elétrico foi inventado no Brasil.', [
'De onde é a invenção do chuveiro elétrico ?',
'invenção do chuveiro elétrico ?',
'onde foi inventado o chuveiro elétrico ?',
'que país inventou o chuveiro elétrico ?'
]),
AnswerStructure(
'Quem inventou o chuveiro elétrico foi o brasileiro Francisco Canho.',
[
'Quem inventou o chuveiro elétrico ?',
'Que pessoa inventou o chuveiro elétrico ?'
]),
AnswerStructure(
'Vaticano e Russia são o menor e o maior país do mundo, respectivamente.',
[
'Qual o menor e o maior país do mundo ?',
'menor e o maior país do mundo ?', 'menor e o maior país',
'qual menor e o maior país ?', 'país', 'países'
]),
AnswerStructure('Vaticano é o menor país do mundo.', [
'Qual o menor país do mundo ?', 'menor país do mundo',
'menor país', 'Qual o menor país ?'
]),
AnswerStructure('Russia é o maior país do mundo.', [
'Qual o maior país do mundo ?', 'maior país do mundo ?',
'maior país', 'Qual o maior país ?'
]),
AnswerStructure('João Goulart.', [
'Qual o nome do presidente do Brasil que ficou conhecido como Jango ?',
'Qual o nome do presidente Jango ?', 'nome do presidente Jango ?',
'Jango ?', 'presidente conhecido como Jango'
]),
AnswerStructure(
'A velocidade da luz é de 299 792 458 metros por segundo.',
['velocidade da luz em m/s', 'qual a velocidade da luz em m/s ?']),
AnswerStructure('A velocidade da luz é de 300.000 Km/s.', [
'velocidade da luz em km/s', 'qual a velocidade da luz',
'velocidade da luz', 'qual a velocidade da luz em km/s ?'
]),
AnswerStructure('42.', [
'6x9', '6 x 9',
'qual a resposta para a vida , o universo e tudo mais ?',
'vida universo e tudo mais', 'resposta para a vida',
'resposta para o universo'
]),
]
thesaurus = Thesaurus([
Synonym(['voce', 'vc', 'oce', 'ce', 'vs', 'vossa senhoria']),
Synonym([
'tudo bem', 'Tudo bem com voce', 'Tudo bom', 'Sussa', 'De boas',
'De boa', 'Suave', 'Beleza', 'Blz', 'Firmeza', 'Fmz', 'Como vai',
'Como está', 'Na boa'
]),
Synonym(['Ola', 'Oi', 'E ai', 'Dae']),
Synonym(['sair', 'fim', 'terminar', 'tchau', 'xau', 'vlw flw', 'flw']),
Synonym(['maior', 'mais grande', 'gigante', 'grande']),
Synonym(['menor', 'mais pequeno', 'pequeno']),
Synonym(['doacao', 'doar', 'doação', 'doaçao', 'doacão']),
Synonym([
'de onde é', 'de onde e', 'onde', 'em que país', 'em que pais',
'em qual pais', 'em qual país', 'em que lugar'
]),
Synonym(['a gente', 'nós']),
Synonym(['pais', 'país']),
Synonym(['paises', 'países']),
Synonym([
'invencao', 'invenção', 'invencão', 'invençao', 'criação',
'criacao'
]),
Synonym(['inventor', 'criador']),
Synonym(['é', 'e']),
Synonym(['qual a', 'qual é a', 'qual e a']),
Synonym(['tem', 'possui']),
Synonym(['ter', 'possuir']),
Synonym([
'quantidade', 'quantos', 'qual a quantidade', 'qual quantidade',
'quanto'
]),
Synonym(['elétrico', 'eletrico']),
Synonym(['pessoa', 'ser humano adulto', 'pessoa adulta', 'adulto']),
Synonym([
'que pessoa', 'qual pessoa', 'quem', 'qual foi a pessoa',
'quem foi que'
]),
Synonym([
'metros por segundo', 'm/s', 'metros/s', 'm/sec', 'metros/sec',
'mt/s'
]),
Synonym(['quilometros por segundo', 'km/s', 'kilometros por segundo']),
])
words_to_be_ignored = frozenset([
'da', 'de', 'do', 'a', 'o', 'um', 'uma', 'é', 'para', 'pra', 'com',
'sem', '?', '.', ','
])