def entities(data):
response = {}
text_array = data
title = text_array.title()
output = nltk.word_tokenize(title)
for a in output:
text = KBBI(a)
# try:
# text = KBBI(a)
# except Exception as e:
# return e
text_dumps = json.dumps(text.serialisasi(), indent=2)
text_loads = json.loads(text_dumps)
A = json.dumps(text_loads["entri"], indent=2)
B = json.loads(A)
C = ''
data = []
for i in B:
C = json.dumps(i["makna"])
D = json.loads(C)
print(i)
for c in D:
data.append({"arti": c["submakna"]})
#print(json.dumps(i["submakna"]))
response.update({a: data})
return jsonify(response)
def aktual_objek(request, laman):
kueri = request.param
try:
return laman[kueri]
except KeyError:
laman[kueri] = KBBI(kueri)
return laman[kueri]
def ambilDariKBBI(kata):
# ambil ke KBBI menggunakan try except
# untuk mengetahui apakah kata
# tsb ada dalam KBBI atau tidak
try:
# coba akses ke KBBI daring
kata = KBBI(kata, auth)
# jika tidak ada kesalahan
# maka tersedia
return kata.serialisasi()
except TidakDitemukan as e:
# kata tidak tersedia
# kembalikan kepada user
return False
def init(filepath):
#sentence = docx2txt.process("C:/xampp/htdocs/stemming_naziefadriani/dokumen/Bab_21.docx")
print(filepath)
sentence = docx2txt.process(filepath)
output = stemmer.stem(sentence)
output = list(output.split(' '))
total_kata = len(output)
# kalo pengen liat isi dari variabel output hilangkan pagar di bawah ini
# output
spell = SpellChecker(language=None)
spell2 = SpellChecker()
spell.word_frequency.load_text_file('./katadasar.txt')
misspelled = spell.unknown(output)
misspelled2 = spell2.unknown(output)
koreksi = list()
keliru = list()
for word in misspelled:
#print(spell.correction(word))
if spell2.correction(word) in misspelled2:
keliru.append(spell2.correction(word))
#print('keliru')
#print(spell2.correction(word))
koreksi.append(spell.correction(word))
#print (word)
#print()
#print(spell.candidates(word))
auth = AutentikasiKBBI("*****@*****.**", "oko123oko")
# roh = KBBI("ikan", auth)
masalah = list()
masalah_baru = list()
for k in koreksi:
try:
huk = KBBI(k, auth)
except TidakDitemukan as e:
huk = e.objek
print(e)
masalah_baru.append(str(e))
masalah.append(str(huk))
#print(huk)
total_kata_dokumen = len(sentence)
dibuang = total_kata_dokumen - total_kata
total_masalah = len(masalah)
total_kata_baku = total_kata - total_masalah
return (total_kata_dokumen, total_kata, dibuang, total_kata_baku,
total_masalah, masalah, masalah_baru)
def init(filepath):
print(filepath)
sentence = docx2txt.process(filepath)
output = stemmer.stem(sentence)
output = list(output.split(' '))
total_kata = len(output)
spell = SpellChecker(language=None)
spell2 = SpellChecker() # bahasa inggris
spell.word_frequency.load_text_file('./katadasar.txt')
misspelled = spell.unknown(output)
misspelled2 = spell2.unknown(output)
koreksi = list()
keliru = list()
masalah = list()
masalah_baru = list()
for word in misspelled:
udah_diperiksa = False
try:
huk = KBBI(word, auth)
except TidakDitemukan as e:
huk = e.objek
print(e)
tampung_string = str(e)
tampung_string = tampung_string.split(' tidak ditemukan')
# masalah_baru.append(str(e))
masalah_baru.append(tampung_string[0])
masalah.append(str(huk))
udah_diperiksa = True
if spell2.correction(word) in misspelled2:
keliru.append(spell2.correction(word))
if not udah_diperiksa:
koreksi.append(word)
rekomendasi_koreksi = list()
for kata in koreksi:
rekomendasi_koreksi.append(spell.correction(kata))
print(koreksi)
total_kata_dokumen = len(sentence)
dibuang = total_kata_dokumen - total_kata
total_masalah = len(misspelled)
total_kata_baku = total_kata - total_masalah
return (total_kata_dokumen, total_kata, dibuang, total_kata_baku,
total_masalah, masalah, masalah_baru, koreksi, rekomendasi_koreksi)
async def kbbi(self, ctx, arg):
if len(arg) > 0:
try:
data = KBBI(arg)
await ctx.send("```Mencari Kata -> {}\n\n{}```".format(
arg, data))
except:
await ctx.send(
"```Kata '{}' Tidak ditemukan dalam KBBI.```".format(arg))
else:
await ctx.send("Kata tidak boleh Kosong.")
def find_kbbi(keyword, ex=True):
try:
entry = KBBI(keyword)
except KBBI.TidakDitemukan as e:
result = str(e)
else:
result = "Definisi {}:\n".format(keyword)
if ex:
result += '\n'.join(entry.arti_contoh)
else:
result += str(entry)
return result
def search():
try:
body = request.get_json()
word = "" if "kata" not in body else body["kata"]
if word == None or word == "":
return response("kata harus di isi", 422)
kbbiWord: KBBI = KBBI(word)
return response(kbbiWord.serialisasi(), 200)
except TidakDitemukan:
return response("kata tidak ditemukan", 404)
except:
return response("terjadi kesalahan pada server", 500)
async def kbbi(client, message):
await message.edit("`Processing...`")
if message.reply_to_message:
kata = message.reply_to_message.text
else:
args = message.text.split(None, 1)
if len(args) == 1:
await message.edit("Usage : kbbi (kata)")
return
kata = args[1]
try:
result = "KBBI Result of **{}** \n\n".format(kata)
result += str(KBBI(kata))
await message.edit(result)
except Exception as e:
await message.edit(e)
def terikat_lah():
return KBBI("-lah")
def akhiran_kan():
return KBBI("-kan")
def awalan_me():
return KBBI("me-")
def bin():
return KBBI("bin")
def civitas_academica():
return KBBI("civitas academica")
async def kbbi(self, ctx, *q_kbbi):
print('@@ Running kbbi command')
q_kbbi = " ".join(q_kbbi)
try:
cari_kata = KBBI(q_kbbi)
except KBBI.TidakDitemukan:
print('@@ No results.')
return await self.bot.say(
'Tidak dapat menemukan kata tersebut di KBBI')
json_d = cari_kata.serialisasi()[q_kbbi]
dataset = []
for v in json_d:
build_data = {}
build_data['nama'] = v['nama']
makna_tbl = []
cnth_tbl = []
for j in v['makna']:
text = ''
for z, _ in j['kelas'].items():
text += '*({z})* '.format(z=z)
text += "; ".join(j['submakna'])
makna_tbl.append(text)
cnth_tbl.append("; ".join(j['contoh']).replace(
'-- ', '- ').replace('--, ', '- '))
build_data['makna'] = "\n".join(makna_tbl)
build_data['contoh'] = "\n".join(cnth_tbl)
build_data['takbaku'] = ", ".join(v['bentuk_tidak_baku'])
build_data['kata_dasar'] = ", ".join(v['kata_dasar'])
dataset.append(build_data)
def return_format(x):
if isinstance(x, list):
return []
elif isinstance(x, dict):
return {}
return ''
def sanity_check(dataset):
for n, d in enumerate(dataset):
for k, v in d.items():
if v.isspace():
dataset[n][k] = return_format(v)
return dataset
dataset = sanity_check(dataset)
first_run = True
dataset_total = len(dataset)
pos = 1
print(dataset)
while True:
if first_run:
pos = 1
datap = dataset[pos - 1]
embed = discord.Embed(title="KBBI: {}".format(q_kbbi),
color=0x81e28d)
embed.add_field(name=datap['nama'],
value=datap['makna'],
inline=False)
embed.add_field(name='Contoh',
value="Tidak ada"
if not datap['contoh'] else datap['contoh'],
inline=False)
embed.add_field(name='Kata Dasar',
value="Tidak ada" if not datap['kata_dasar']
else datap['kata_dasar'],
inline=False)
embed.add_field(name='Bentuk tak baku',
value="Tidak ada"
if not datap['takbaku'] else datap['takbaku'],
inline=False)
msg = await self.bot.say(embed=embed)
first_run = False
if dataset_total < 2:
break
elif pos == 1:
to_react = ['⏩', '✅']
elif dataset_total == pos:
to_react = ['⏪', '✅']
elif pos > 1 and pos < dataset_total:
to_react = ['⏪', '⏩', '✅']
for react in to_react:
await self.bot.add_reaction(msg, react)
def check_react(reaction, user):
e = str(reaction.emoji)
return e.startswith(tuple(to_react))
res = await self.bot.wait_for_reaction(message=msg,
user=ctx.message.author,
timeout=20,
check=check_react)
if res is None:
return await self.bot.clear_reactions(msg)
elif '✅' in str(res.reaction.emoji):
return await self.bot.clear_reactions(msg)
elif '⏪' in str(res.reaction.emoji):
await self.bot.clear_reactions(msg)
pos -= 1
datap = dataset[pos - 1]
embed = discord.Embed(title="KBBI: {}".format(q_kbbi),
color=0x81e28d)
embed.add_field(name=datap['nama'],
value=datap['makna'],
inline=False)
embed.add_field(name='Contoh',
value="Tidak ada"
if not datap['contoh'] else datap['contoh'],
inline=False)
embed.add_field(name='Kata Dasar',
value="Tidak ada" if not datap['kata_dasar']
else datap['kata_dasar'],
inline=False)
embed.add_field(name='Bentuk tak baku',
value="Tidak ada"
if not datap['takbaku'] else datap['takbaku'],
inline=False)
msg = await self.bot.edit_message(msg, embed=embed)
elif '⏩' in str(res.reaction.emoji):
await self.bot.clear_reactions(msg)
pos += 1
datap = dataset[pos - 1]
embed = discord.Embed(title="KBBI: {}".format(q_kbbi),
color=0x81e28d)
embed.add_field(name=datap['nama'],
value=datap['makna'],
inline=False)
embed.add_field(name='Contoh',
value="Tidak ada"
if not datap['contoh'] else datap['contoh'],
inline=False)
embed.add_field(name='Kata Dasar',
value="Tidak ada" if not datap['kata_dasar']
else datap['kata_dasar'],
inline=False)
embed.add_field(name='Bentuk tak baku',
value="Tidak ada"
if not datap['takbaku'] else datap['takbaku'],
inline=False)
msg = await self.bot.edit_message(msg, embed=embed)
def tampak():
return KBBI("tampak")
def keratabasa():
return KBBI("keratabasa")
def makin():
return KBBI("makin")
def semakin():
return KBBI("semakin")
def khayal():
return KBBI("khayal")
def lampir():
return KBBI("lampir")
def kan():
return KBBI("kan")
def menjadikan():
return KBBI("menjadikan")
def quo_vadis():
return KBBI("quo vadis?")