from sumy.parsers.plaintext import PlaintextParser
from sumy.nlp.tokenizers import Tokenizer
from sumy.summarizers.lsa import LsaSummarizer as Summarizer
from sumy.nlp.stemmers import Stemmer
from sumy.utils import get_stop_words
from chatterbot import ChatBot
from chatterbot.trainers import ListTrainer
import re
import mysql.connector

# Requires: chatterbot sumy, a wiki...

bot = ChatBot(
    'Teddy',
    storage_adapter='chatterbot.storage.SQLStorageAdapter',
    input_adapter='chatterbot.input.TerminalAdapter',
    output_adapter='chatterbot.output.TerminalAdapter',
    database='./database.sqlite3'
)
bot.set_trainer(ListTrainer)

cnx = mysql.connector.connect(user='XXXXXXXXX', password='XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX',
                              host='127.0.0.1',
                              database='my_wiki')
cursor = cnx.cursor()
print('Loading wiki data...')
cursor.execute("SELECT old_text FROM text")
result = cursor.fetchall()
for row in result:
  sat = str(row[0])
  name = re.findall(r"'''(.*?)'''", sat)
  if name:
    soup = name[0]
    data = re.sub("[[]", '', soup)
    data1 = re.sub("[]]", '', data)
    data2 = re.sub("[']", '', data1)
    print(data2)
    str1 = str(data2)
    sentence = ''
    validLetters = ".abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ "
    text = ''.join([char for char in sat if char in validLetters])
    LANGUAGE = "english"
    SENTENCES_COUNT = 20
    parser = PlaintextParser.from_string(text, Tokenizer(LANGUAGE))
    stemmer = Stemmer(LANGUAGE)
    summarizer = Summarizer(stemmer)
    summarizer.stop_words = get_stop_words(LANGUAGE)
    for sentence in summarizer(parser.document, SENTENCES_COUNT):
      bot.train([
        str1,
        sentence,
      ])

print('Done loading wiki data... Database has been saved.')
while True:
    try:
     bot_input = bot.get_response(None)

    except(KeyboardInterrupt, EOFError, SystemExit):
        cnx.close()
        break