→ Fichamentos

Estudos para Mnemônicos Yupana

Postado por glerm em Fichamentos, Rascunhos on fevereiro 13th, 2012

Estudos para criação de sintaxe-semântica com remix da wikipedia

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52

 
#!/usr/bin/python
# -*- coding: utf-8 -*-
import sys
import urllib2
from stripogram import html2text
import random
import re
 
#emabaralhador do baralho
def scramble(string):
        palavras=string.split()
        random.shuffle(palavras,random.random)
        return ' '.join([p for p in palavras])
 
 
 
# busca=[(meme,lingua),(...)] pt(portugues), el (grego), hi (hindi) ou en (ingles), mas da pra implemntar mais mexendo na expressã regular regex, mais abaixo
busca=[('Alchemy','en'),('Nuvem','pt'),('Vida','pt'),('Turing_Test','en'),('Oráculo','pt'),('Curupira','pt'),('Μαντείο','el'),('Ποίηση' ,'el'),('नैतिकता', 'hi'),('मनोविज्ञान','hi')]
 
brain='' #inicializando cerebro
 
letras=140 #limite de caracteres
 
 
### mais sobre expressões regulares:
#<TAG\b[^>]*>(.*?)</TAG> - expressão regular pra tirar uma tag da uma ideia de como cortar trechos
# http://www.pythonregex.com/
 
for b in busca:
        opener = urllib2.build_opener()
        opener.addheaders = [('User-agent', 'Mozilla/5.0')]
        infile = opener.open('http://'+b[1]+'.wikipedia.org/wiki/'+b[0])
        page = infile.read()
        html = page
        pattern = re.compile('(?<=p>).+(?=</p)', re.DOTALL)
        p=pattern.search(html).group()
        text = html2text(p)
        regex = re.compile("(.*?)(Contents|Índice|\[edit\]|\[editar\]|Πίνακας|\[Επεξεργασία\]|अनुक्रम|\[संपादित करें\])",re.DOTALL)
        r = regex.search(text)
        t=r.groups()
        bio=t[0]
        brain=brain+bio
 
 
sorte = scramble(brain)#embaralhador
sorte = "#wiqua "+sorte
sorte = sorte[:letras]
sorte = scramble(sorte)
 
 
print sorte

Separação de sílabas:

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71

import string
import re
 
def syllables (text):
    text = " " + text + " "
 
    vowel_list       = ['a', 'e', 'i', 'o', 'u', 'y']
    vowel_pairs      = ['ai', 'au', 'aw', 'ee','ea', 'oa', 'oi', 'ou', 'oo', 'ow', 'oy', 'uu']
    consonant_list   = ['b', 'c', 'd', 'f', 'g', 'h', 'j', 'k', 'l', 'm', 'n', 'p', 'q', 'r', 's', 't', 'v', 'w', 'x', 'z']
    consonant_blends = ['bl', 'br', 'ch', 'chr', 'cl', 'cr', 'dr', 'fl', 'fr', 'gl', 'gr', 'kn', 'pl', 'pr',
                        'sc', 'sh', 'sk', 'sl', 'sm', 'sn', 'sp', 'spr', 'squ', 'st', 'str', 'sw',
                        'th', 'tr', 'thr', 'nt', 'wh']
 
    # Cut numbers in digits
    p = re.compile ("([0-9])([0-9])", re.IGNORECASE)
    for i in range (2):
        text = p.sub ("\\1#\\2", text)
 
    # Cut i / vowel (- o) / consonant
    p = re.compile ("i([aeiuy])([bcdfghjklmnpqrstvwxz])", re.IGNORECASE)
    text = p.sub ("i+\\1+\\2", text)
 
    # Cut the / vowel / consonant
    p = re.compile ("the([aeiouy])([bcdfghjklmnpqrstvwxz])", re.IGNORECASE)
    text = p.sub ("the+\\1+\\2", text)
 
    # Cut vowel / vowel except for pairs
    position = 0
    while position < len (text)-1:
        if text [position] in vowel_list and text [position+1] in vowel_list:
            if not (text [position:position+2] in vowel_pairs):
                if not (text [position-1:position+3] in ["tion", "dual", "nion", "quir", "tiou"]):
                    text = text [:position+1] + "_" + text [position+1:]
        position = position + 1
 
    # Cut consonant / consonant (ll, mm, ...)
    p = re.compile ("([bcdfghjklmnpqrstvwxz])\\1([^ ])", re.IGNORECASE)
    text = p.sub ("\\1-\\1\\2", text)
 
    # Cut vowel / consonant vowel
    start = 0
    end = 0
    while start < len (text)-1:
        if text [start] in vowel_list and text [start+1] in consonant_list:
            end = start + 1
            while end <= len (text)-1 and text [end] in consonant_list:
                end = end + 1
            if end <= len (text)-1 and (text [start+1:end] in consonant_list or text [start+1:end] in consonant_blends) and text [end] in vowel_list and text [end:end+2] <> "e ":
                text = text [:start+1] + "/" + text [start+1:]
        start = start + 1
 
    # Cut vowel consonant / consonant+ vowel (trumpet, simple, understanding, ...)
    start = 0
    end = 0
    while start < len (text)-1:
        if text [start] in vowel_list and text [start+1] in consonant_list:
            end = start + 2
            while end <= len (text)-1 and text [end] in consonant_list:
                end = end + 1
            if end <= len (text)-1 and end > start+2 and text [end] in vowel_list:
                if not (text [start+1:end] in consonant_blends):
                    text = text [:start+2] + "-" + text [start+2:]
        start = start + 1
 
    # Return the words splitted
    return text
 
wordlist =  ["2008", "piano", "waffle", "kissing", "diode", "museum", "simple", "hundred", "understanding", "trumpet", "paper", "preparing", "strengh", "theatre", "facetious", "abstemious", "statement", "consent", "extent", "event", "documents", "fire", "oil", "pattern", "fireplace", "theme", "based", "site", "sites", "within", "browse", "required", "ensures", "dictionary", "dichotomy", "pamphlet", "methan", "etherosexual"]
 
for word in wordlist:
    print syllables (word)

script de interação com gtalk

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88

#!/usr/bin/python
# -*- coding: utf-8 -*-
 
# PyGtalkRobot: A simple jabber/xmpp bot framework using Regular Expression Pattern as command controller
# Copyright (c) 2008 Demiao Lin <ldmiao@gmail.com>
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.
#
# Homepage: http://code.google.com/p/pygtalkrobot/
#
 
#
# This is an sample PyGtalkRobot that serves to set the show type and status text of robot by receiving message commands.
#
 
import sys
import time
 
from PyGtalkRobot import GtalkRobot
 
############################################################################################################################
 
class SampleBot(GtalkRobot):
 
    #Regular Expression Pattern Tips:
    # I or IGNORECASE <=> (?i)      case insensitive matching
    # L or LOCALE <=> (?L)          make \w, \W, \b, \B dependent on the current locale
    # M or MULTILINE <=> (?m)       matches every new line and not only start/end of the whole string
    # S or DOTALL <=> (?s)          '.' matches ALL chars, including newline
    # U or UNICODE <=> (?u)         Make \w, \W, \b, and \B dependent on the Unicode character properties database.
    # X or VERBOSE <=> (?x)         Ignores whitespace outside character sets
 
    #"command_" is the command prefix, "001" is the priviledge num, "setState" is the method name.
    #This method is used to change the state and status text of the bot.
    def command_001_setState(self, user, message, args):
        #the __doc__ of the function is the Regular Expression of this command, if matched, this command method will be called. 
        #The parameter "args" is a list, which will hold the matched string in parenthesis of Regular Expression.
        '''(available|online|on|busy|dnd|away|idle|out|off|xa)( +(.*))?$(?i)'''
        show = args[0]
        status = args[1]
        jid = user.getStripped()
 
        # Verify if the user is the Administrator of this bot
#        if jid == ('organismo@gmail.com') :
 #           print jid, " ---> ",bot.getResources(jid), bot.getShow(jid), bot.getStatus(jid)
  #          self.setState(show, status)
   #         self.replyMessage(user, "State settings changed！")
 
        # Verify if the user is the Administrator of this bot
        if jid == ('organismo@gmail.com') :
            print jid, " ---> ",bot.getResources(jid), bot.getShow(jid), bot.getStatus(jid)
            self.setState(show, status)
            self.replyMessage(user, "State settings changed！")
 
    #This method is used to send email for users.
    def command_002_SendEmail(self, user, message, args):
        #email yupanakernel@gmail.com hello dmeiao, nice to meet you, bla bla ...
        '''[email|mail|em|m]\s+(.*?@.+?)\s+(.*?),\s*(.*?)(?i)'''
        email_addr = args[0]
        subject = args[1]
        body = args[2]
        #call_send_email_function(email_addr, subject,  body)
 
        self.replyMessage(user, "\nEmail sent to "+ email_addr +" at: "+time.strftime("%Y-%m-%d %a %H:%M:%S", time.gmtime()))
 
    #This method is used to response users.
    def command_100_default(self, user, message, args):
        '''.*?(?s)(?m)'''
       # self.replyMessage(user, time.strftime("%Y-%m-%d %a %H:%M:%S", time.gmtime()))
	self.replyMessage(user,"Você disse: "+ message + "\n")
 
 
############################################################################################################################
if __name__ == "__main__":
    bot = SampleBot()
    bot.setState('available', "<3 == Ψ")
    bot.start("yupanakernel@gmail.com", "senhasupersecretaperigo")

postando em IRC

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43

# -*- coding: utf-8 -*-
 
#guardar esse arquivo para estudos basicos e pra criar um tutorial no futuro...
 
import sys
import socket
import string
 
HOST="irc.freenode.net"
PORT=6667
NICK="yupana"
IDENT="senha"
REALNAME="yupana"
CHAN="#metareciclagem"
readbuffer=" "
 
s=socket.socket( )
s.connect((HOST, PORT))
s.send("NICK %s\r\n" % NICK)
s.send("USER %s %s bla :%s\r\n" % (IDENT, HOST, REALNAME))
s.send("JOIN :%s\r\n" % CHAN)
s.send("PRIVMSG %s :%s\r\n" % (CHAN, "Ola"))
s.send("PRIVMSG %s :%s\r\n" % (CHAN, "Eu sou Yupana. Meu código esta em https://github.com/glerm/yupana. Se precisar aprofundar sobre IRC, tente esse link: http://www.irchelp.org/irchelp/rfc/rfc.html"))
 
while 1:
	readbuffer=readbuffer+s.recv(1024)
	temp=string.split(readbuffer, "\n")
	readbuffer=temp.pop( )
 
	for line in temp:
		line=string.rstrip(line)
		line=string.split(line)
 
		if(line[0]=="PING"):
			s.send("PONG %s\r\n" % line[1])
 
		if(line[1]=="PRIVMSG"):
			l=line[3].split(':')+line[4:] #split do ponto e virgula so pra testar, bug se tentar fazer frases tipo "Seguinte: blablabla"
			s.send("PRIVMSG %s :%s\r\n" % (CHAN, "Você disse: "+" ".join(l[1:])))
 
 
 
		#print line #debug mode

Postando no WordPress

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16

# -*- coding: utf-8 -*-
 
#depende de https://github.com/maxcutler/python-wordpress-xmlrpc
from wordpress_xmlrpc import Client, WordPressPost
from wordpress_xmlrpc.methods.posts import GetRecentPosts, NewPost
from wordpress_xmlrpc.methods.users import GetUserInfo
 
wp = Client('http://yupana.pontaodaeco.org/xmlrpc.php', 'gesuselva', 'kernelpanic')
 
 
post = WordPressPost()
post.title = 'Que as atuais máquinas informacionais e comunicacionais não se contentem em veicular conteúdos representativos, mas que concorram igualmente para a confecção de novos agenciamentos de enunciação (individuais e/ou coletivos)?'
post.description = '<h1></h1><br><p>ﻊﺑﻭﺭ ﺎﻠﺣﺩﻭﺩ aquilo que dissolve no solo e continua a jornada electroquímica dos corpos finalmente será separada daquilo que sempre esteve apenas permeando - <a href=\"https://github.com/glerm/yupana\"/>um dicionário em aglutinação movendo aqueles braços, pernas, cabeça, tripas.</a> esta árvore de sinais, continua se espalhando e entidades que חציית הגבול</p><img src=\"http://upload.wikimedia.org/wikipedia/commons/2/20/Boltzmanns-molecule.jpg\"/>'
post.tags = 'yupana, kernel'
post.categories = ['coding']
wp.call(NewPost(post, True))

Postando no twitter. Antes precisa criar uma chave de API.

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17

#!/usr/bin/python
# -*- coding: utf-8 -*-
 
import twitter
import random
 
string="segundo o último hoax utilizava sistemas de numeração binários
 e de outras bases diferentes da decimal, como o numero 144,
 cuja a raiz quadrada é 12. Quantas tautologias precisamos?"
 
def twitta(string):
        api = twitter.Api(
        consumer_key=' ',
        consumer_secret=' ', 
        access_token_key=' ', 
        access_token_secret=' ')
        status = api.PostUpdate(string) #AQUI VAI O POST

Na Wiki MediaWiki (mesma usada na wikipedia):

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33

from wikitools import wiki
from wikitools import api
# create a Wiki object
site = wiki.Wiki("http://my.wikisite.org/w/api.php") 
# define the params for the query
params = {'action':'query', 'titles':'Main Page'}
# create the request object
request = api.APIRequest(site, params)
# query the API
result = request.query()
 
#The result will look something like:
#{u'query':
#	{u'pages':
		#{u'15580374':
		#	{u'ns': 0, u'pageid': 15580374, u'title': u'Main Page'}
		#}
	#}
#}
 
#For most normal usage, you may not have to do API queries yourself and can just
#use the various classes. For example, to add a template to the top of all the 
#pages in namespace 0 in a category:
 
from wikitools import wiki
from wikitools import category
site = wiki.Wiki("http://my.wikisite.org/w/api.php") 
# Create object for "Category:Foo"
cat = category.Category(site, "Foo")
# iterate through all the pages in ns 0
for article in cat.getAllMembersGen(namespaces=[0]):
	# edit each page
	article.edit(prependtext="{{template}}\n")

Comente