def runc_layer(layer):
objects=[]
ref_opcode=''
# Relaction-oper-opcode opcode original dos qualificadores se nao especificado
#=====================================================
def get_o_ob():
for s in objects:
if s.name==ob: return s
return None
#=====================================================
if True:
print 'RTS-REF(1):------------'
r=layer
for s in r.topicos:
print 'Topico:',s.dt
print 'SNS:++++++++++++++++++'
for s1 in s.sinapses:
print s1.nr.dt
print '++++++++++++++++++'
print 'RTS-REF(1)(END):------------'
obj_foco=[]
#print 'N tops:' , len(layer.topicos)
for t in layer.topicos:
tp=t
nr_t=t.dt[0]
if nr_t == '': continue
if 'referencial.source' in t.dt :
sn_dt=''
for sn in tp.sinapses:
if 'indicador' not in sn.nr.dt:
for s1 in sn.nr.dt:
sn_dt+=(s1+' ')
if umisc.trim(sn_dt) != '$$id$$' and umisc.trim(sn_dt) != '':
print 'referencial.source:',sn_dt
if len(obj_foco) > 0:
lay=obj_foco[0]
lay.name+=(sn_dt)
else:
lay=mdNeural.mdLayer()
lay.name=sn_dt
#====
objects.append(lay)
obj_foco.append(lay)
rel1=False
for t in layer.topicos:
topico_rsf=t
#==============================================
for dt_top in topico_rsf.dt:
if dt_top in [ 'referencial'] or ref_opcode in [ 'refer']:
for ob1 in obj_foco:
ob1.set_topico_nr(topico_rsf)
break
print 'Obj.foco.refer:',obj_foco
return obj_foco
def get_db_pages(usr2):
resultSet = conn.sql("select pg from know_pages where USERNAME='******' order by i")
typ = []
for results in resultSet:
ts = results[0].read()
if umisc.trim(ts) != '' and umisc.trim(ts) != '\n' and umisc.trim(
ts) != '\r':
typ.append(ts)
print 'Reuse pgs:', len(typ)
return typ
def pg_open(addresss, th, pages, pgind, ind_emit, start_c):
print 'Start read page:', addresss
try:
for address in addresss:
lines_doc = []
links_k2 = []
if address != 'debug-url':
#======================
#opener = urllib2.build_opener()
address = urllib.quote(address)
#url='http://www.mind-net.com/get_Text.php?q='+address
pg_add = address
#content = opener.open(url, '' ).read()
content = call_text(address)
tmpd = ''
for d in content:
if d == '\n':
tmpd = umisc.trim(tmpd)
lines_doc.append(tmpd)
tmpd = ''
else:
tmpd += d
#======================
#opener = urllib2.build_opener()
#url='http://www.mind-net.com/get_links.php?q='+address
#content = opener.open(url, '' ).read()
content = call_links(address)
tmpd = ''
for d in content:
if d == '\n':
tmpd = umisc.trim(tmpd)
links_k2.append(tmpd)
tmpd = ''
else:
tmpd += d
#============
pages.append(Task_C(pg_add, lines_doc, links_k2))
print 'Get content for page:', pgind, ' was finished.Len:', len(
lines_doc), ' links count:', len(links_k2)
pgind += 1
else:
for line_deb in entry_doc:
lines_doc.append(line_deb)
pages.append(Task_C(pg_add, lines_doc, links_k2))
print 'Get content for page:', pgind, ' was finished.Len:', len(
lines_doc)
pgind += 1
th.finished = True
except Exception, er:
print er, '................'
th.finished = True
def post_object_by_data3p(layer, cenario, usr, termo, foco, posted_objs, senti,
l_p_ant):
if layer.name == '': return
def get_top_level(obj, foc, usr, termo_s):
rts = []
resultSet = conn.sqlX(
"SELECT lev,id_top FROM SEMANTIC_OBJECT_DT3 where OBJECT = ? and TOPICO= ? and USERNAME = ? and UID= ? order by LEV ",
([obj, foc, usr, termo_s]))
for results in resultSet:
i = results[0]
id_top = results[1]
rts.append([i, id_top])
return rts
#=======================
nameo = layer.name
if umisc.trim(nameo) == '' or umisc.trim(nameo) == '\n':
if l_p_ant != None:
nameo = l_p_ant.name
if umisc.trim(nameo) == '' or umisc.trim(nameo) == '\n':
return
fnd_tops = False
l_p_ant = layer
print 'POST:LR:', nameo
print '++------------------------------------------'
for s in layer.topicos:
print 'DT:', s.dt
fnd_tops = True
for d in s.sinapses:
print d.nr.dt
print '++------------------------------------------'
if not fnd_tops: return
print 'Post-obj:[', nameo, ']'
no_post_o = False
for [s, st] in posted_objs:
if s == nameo and st == senti:
no_post_o = True
posted_objs.append([nameo, senti])
#==========
#if not no_post_o and len(layer.topicos)>0:
if not no_post_o:
sql1 = "insert into SEMANTIC_OBJECT3(username,objeto,cenar,senti) values(?,?,?,?)"
try:
conn.sqlX(sql1, ([usr, nameo, cenario, senti]))
except Exception, err:
print 'Erro ao post(OBJECT):', err
def load_pages_know(usr):
rts = get_db_pages(usr)
if len(rts) > 0:
cnt = 0
for r in rts:
cnt += 1
entry_doc.append([Task_C('debug', r), cnt])
elif len(rts) == 0:
file = open("c:\\wamp\\www\Neural\\tst_training.txt")
cnt = 0
lsn = ''
while 1:
line = file.readline()
if not line:
#if umisc.trim(lsn) != '':
# cnt+=1
# entry_doc.append([ Task_C('debug',lsn),cnt ] )
break
#===============================
s = umisc.trim(line)
if s == '' or s == '\n':
cnt += 1
lsn = lsn.replace('\r', ' ')
lsn = lsn.replace('\n', ' ')
entry_doc.append([Task_C('debug', lsn), cnt])
post_db_page(usr, lsn)
lsn = ''
else:
lsn += (' ' + line)
def run_cmd():
try:
Pyro.core.initClient()
objectName = 'layoutBean'
hostname = '79.143.185.3'
port = '28'
print 'Creating proxy for object', objectName, ' on ', hostname + ':' + port
if port:
URI = 'PYROLOC://' + hostname + ':' + port + '/' + objectName
else:
URI = 'PYROLOC://' + hostname + '/' + objectName
print 'The URI is', URI
proxy = Pyro.core.getProxyForURI(URI)
#==
list = proxy.process_cmd('get_page', '', '')
print 'List.getted!!'
list = umisc.trim(list)
if len(list) < 5:
return
params = list
cmd = 'python entry_SemaIndexerStage1.py ' + params
print cmd
os.system(cmd)
except:
log.exception("ERROR==============")
time.sleep(2)
def sep_multiple_data_unkwon(dt):
dts = parse_t(dt)
l = len(dts) - 1
rt = []
while l >= 0:
if dts[l] in ['o', 'a', 'os', 'as']:
rt.insert(0, dts[l])
break
rt.insert(0, dts[l])
l -= 1
c = ''
for r in rt:
c += (' ' + r)
return umisc.trim(c)
def pg_open(address,th,page,pgind,ind_emit,start_c):
if ind_emit > 0 : pgind=ind_emit
if start_c > 0 :
#print 'Get content for page:',pgind,'\n'
print 'Get content for page:',pgind
else:
print 'Get content for page:',pgind
try:
opener = urllib2.build_opener()
address=urllib.quote(address)
url='http://www.mind-net.com/get_Text.php?q='+address
content = opener.open(url, '' ).read()
lines_doc=[]
tmpd=''
for d in content:
if d == '\n':
tmpd=umisc.trim(tmpd)
if tmpd.find('http://') > -1:
''' '''
else:
lines_doc.append(tmpd)
tmpd=''
else:
tmpd+=d
page.dt1=pg_add
page.dt2=lines_doc
th.finished=True
except :
th.finished=True
print 'Get content for page:',pgind,' was finished.Len:',len(lines_doc)
def post_links(endereco,termo,usr,purp):
try:
sql1="insert into WEB_CACHE_LINKS (URL,TERMO,PURPOSE,USR,PROCESSED) values(%s,%s,%s,%s,'N')"
if umisc.trim(endereco) != '':
cursorpostl.execute (sql1,(MySQLdb.escape_string(endereco),MySQLdb.escape_string(termo),purp,usr))
except:
pass
def pg_open(address,th,page,pgind,ind_emit,start_c):
if ind_emit > 0 : pgind=ind_emit
if start_c > 0 :
#print 'Get content for page:',pgind,'\n'
print 'Get content for page:',pgind
else:
print 'Get content for page:',pgind
try:
lines_doc=[]
if address != 'debug-url':
opener = urllib2.build_opener()
address=urllib.quote(address)
url='http://www.mind-net.com/get_Text.php?q='+address
content = opener.open(url, '' ).read()
tmpd=''
for d in content:
if d == '\n':
tmpd=umisc.trim(tmpd)
if tmpd.find('http://') > -1:
''' '''
else:
lines_doc.append(tmpd)
tmpd=''
else:
tmpd+=d
else:
for line_deb in entry_doc:
lines_doc.append(line_deb)
page.dt1=pg_add
page.dt2=lines_doc
th.finished=True
except Exception,er :
print er,'................'
th.finished=True
def get_db_pages(usr2,pg_ex,connc):
def fecha_pagina(uid):
print 'Close MSG:',uid
s=w_cache3.find({'doc_id':uid})
s[u'PROCESSED']='S'
w_cache3.update({'_id':s['_id']},s)
def remote_f():
print 'Getting remote-pages...'
return proxy.get_pages('',usr2)
if RemoteL:
return remote_f()
print 'PG_EX',pg_ex,len(pg_ex)
pgs_exs= pg_ex.split(',')
#resultSet = connc.sql ("select pg,i,title from web_cache3 where USR='******' and i in( "+pg_ex+" ) order by i")
resultSet=[]
for p1 in pgs_exs:
rg=None
for d in w_cache3.find({'doc_id':p1}):
rg=d
if rg != None:
try:
rtc=str(rg[u'pg'])
rtc2=str(rg[u'title'])
resultSet.append( [ rtc1.encode('latin-1'),p1,rtc2.encode('latin-1') ] )
except:
print 'Error.get.pg:',rg
log.exception("")
try:
resultSet.append( [ rg[u'PG'].encode('latin-1'),p1,rg[u'TITLE'].encode('latin-1') ] )
except:
print 'Error.get.pg(2):',rg
log.exception("")
typ=[]
print 'Collect pg:',pg_ex
#===============================================
#typ.append(['O perfil da empresa no Twitter foi criado em 20 de Fevereiro de 2008.',35835 ])
#return typ
#================================================
for [ts,ids,ids2] in resultSet:
if ids2 == None: ids2= ''
if umisc.trim(ids2) != '':
ts=(ids2+': '+ts)
#if umisc.trim(ts) != '' and umisc.trim(ts) != '\n' and umisc.trim(ts) != '\r':
typ.append([ts,ids])
if re_post and not fs_teste:
fecha_pagina(ids)
print 'Read page',ids #,ts
print 'Reuse pgs:',len(typ)
return typ
def post_cn(its):
f=open("/Neural/txt_logs","w")
print 'POST.LEN:',len(its)
for [PG,PROCESSED,TERM,USR,PURPOSE,URL_ICON,URL_PICTURE,ID_USR,NAME_USR,STORY,TITLE,DOC_ID,TP,PHONE,STREET,CITY,COUNTRY,ZIP,LATITUDE,LONGITUDE,TPS,URL] in its:
c1=str(PG)
if umisc.trim(c1) != '':
f.write( str(PG)+'|'+str(PROCESSED)+'|'+str(TERM)+'|'+str(USR)+'|'+str(PURPOSE)+'|'+str(URL_ICON)+'|'+str(URL_PICTURE)+'|'+str(ID_USR)+'|'+str(NAME_USR)+'|'+str(STORY)+'|'+str(TITLE)+'|'+str(DOC_ID)+'|'+str(TP)+'|'+str(PHONE)+'|'+str(STREET)+'|'+str(CITY)+'|'+str(COUNTRY)+'|'+str(ZIP)+'|'+str(LATITUDE)+'|'+str(LONGITUDE)+'|'+str(TPS)+'|'+str(URL)+'|'+'\n' )
f.close()
def get_aliases_ob( ):
str_ret=[]
for ir in layer_processes.lrs:
print 'get_aliases_ob()->ir(1):',ir
#if ir != None: print 'lr:',ir.name
for topico in ir.topicos:
if len(topico.dt) > 0 :
topicodt=topico.dt
if 'identificador' in topicodt or 'realid' in topicodt or 'realid2' in topicodt or 'object' in topicodt:
dtk=''
for p in topico.sinapses:
for dts1 in p.nr.dt:
dtk+=' '+umisc.trim(dts1)
if umisc.trim(dtk) != '':
print 'Collect.element:',dtk
str_ret.append(umisc.trim(dtk) )
return str_ret
def post_pagina(endereco,conteudo_i,termo,usr,purp):
try:
conteudo=''
for l in conteudo_i:
conteudo+=(l+'\n')
if umisc.trim(conteudo) != '':
sql1="insert into WEB_CACHE (URL,PG,TERMO,PURPOSE,USR,SEMA_RESUME) values(%s,%s,%s,%s,%s,'')"
cursorpostp.execute (sql1,(MySQLdb.escape_string(endereco),MySQLdb.escape_string(conteudo),MySQLdb.escape_string(termo),purp,usr))
except :
pass
def post_object_by_data_es(layer,usr):
nameo=layer.name
nameo=umisc.trim(nameo)
clear_obj(usr,nameo)
print 'Post LR:',nameo,',len:',len(nameo),', usr:'******''
for d in tp.dt:
tp_Dt+=d
tp_name=tp_Dt
for sn in tp.sinapses:
sn_dt=''
for s1 in sn.nr.dt:
sn_dt+=s1
sql1="insert into "+mdTb.table_dt+"(username,\"UID\",dt,topico,LEV,SIN,ID_TOP) values(?,?,?,?,?,'Composicao',1)"
try:
conn.sqlX (sql1,([usr,uid,sn_dt,tp_Dt,level]))
except:
print 'Erro ao post:',nameo,tp_Dt,sn_dt
log.exception("--------------------------")
#==========
post_nr(usr,sn.nr,level+1)
#========== ===============================================
post_nr(usr,tp)
#===============================================
for lnk in layer.links:
sqlc='insert into '+mdTb.table_relaction+'(OBJ_ORIG,OBJ_DEST,OPCODE,USERNAME,FOCO,FOCO_D,\"UID\") values(?,?,?,?,?,?,?)'
#====================
def get_nr_dts1(nrs):
d=''
for nr in nrs:
for n in nr.dt:
d+=n
d+=','
return d
#====================
foco_o=get_nr_dts1(lnk.foco_o)
foco_d=get_nr_dts1(lnk.foco_d)
conn.sqlX (sqlc,([nameo,lnk.lr.name,lnk.opcode,usr,foco_o,foco_d,0]))
#===============
post_object_by_data_es(lnk.lr,usr)
def get_db_pages(usr2):
def remote_f():
print 'Getting remote-pages...'
return proxy.get_pages('',usr2)
if RemoteL:
return remote_f()
resultSet = conn.sql ("select pg,title,story,i from web_cache where USERNAME='******' order by i")
#resultSet = conn.sql ("select pg,title,story,i from web_cache where USERNAME='******' and i = 96 order by i")
typ=[]
for results in resultSet:
ts=results[0].read()
ids=results[1]
if umisc.trim(ts) != '' and umisc.trim(ts) != '\n' and umisc.trim(ts) != '\r':
typ.append([ts,ids])
if len(typ) > 100: break
print 'Reuse pgs:',len(typ)
return typ
def get_aliases_ob():
str_ret = []
for ir in layer_processes.lrs:
print 'get_aliases_ob()->ir(1):', ir
for topico in ir.topicos:
if len(topico.dt) > 0:
topicodt = topico.dt
if 'identificador' in topicodt or 'realid' in topicodt or 'realid2' in topicodt or 'object' in topicodt:
tmpcs = ''
for p in topico.sinapses:
for dts1 in p.nr.dt:
tmpcs += ' ' + dts1
str_ret.append(umisc.trim(tmpcs))
return str_ret
def post_object_by_data_es(layer, usr):
cenario = 0
senti = 0
#def post_object_by_data3p( , , ,,, ,):
print 'Post LR:', nameo, ',len:', len(nameo), ', usr:'******'Post layer:', nameo
fnd_tops = False
geral_uuid = cenario
print 'POST:LR:', nameo
print '++------------------------------------------'
for s in layer.topicos:
print 'DT:', s.dt
fnd_tops = True
for d in s.sinapses:
print d.nr.dt
print '++------------------------------------------'
if not fnd_tops: return
ky1 = nameo + ' ' + str(cenario)
nameo = ky1
print 'Post-obj:[', nameo, ']'
#==========
#if not no_post_o and len(layer.topicos)>0:
print 'Insert-OBJ:'
#==
if not no_post_o:
#sql1="insert into SEMANTIC_OBJECT3(username,objeto,cenar,senti) values(?,?,?,?)"
try:
cols = {
"username": usr,
"objeto": ky1,
"cenar": str(cenario),
"sento": str(senti)
}
tb_object.insert(ky1, cols)
#conn.sqlX (sql1,([usr,nameo,cenario,senti]))
except Exception, err:
print 'Erro ao post(OBJECT):', err
def process_page(lines_doc2,id,purpose,pgs,finish,th):
ln_o=''
try:
l2=Identify.prepare_layout(id,purpose)
if True :
for s in lines_doc2:
ln_o+=' '+s
if umisc.trim(ln_o) == '':
finish.finished=True
return
ir=Identify.process_data(l2,ln_o,onto_basis,purpose,id,th)
if ir[0] != None :
result_onto_tree_er.append(ir[0])
if ir[1] != None:
result_onto_tree_bpm.append(ir[1])
finish.finished=True
except:
finish.finished=True
print 'Thread ',pgs,' was finished.','Len:',len(ln_o),' process:',start_c/10
def collect_vitrines():
import pycassa
from pycassa.pool import ConnectionPool
from pycassa.columnfamily import ColumnFamily
from pycassa import index
pool2 = ConnectionPool('MINDNET', ['79.143.185.3:9160'], timeout=100000)
tab2 = pycassa.ColumnFamily(pool2, 'cache_products')
pub = pycassa.ColumnFamily(pool2, 'to_posting2')
wb2 = pycassa.ColumnFamily(pool2, 'web_cache1') # lugar para indexar
#=================================
counter = 0
for ky, col in pub.get_range():
prods = col['id_product'].decode('hex')
rc = tab2.get(prods)
from_id3 = col['from_id']
from_id3 = from_id3.replace('\'', '')
from_id3 = from_id3.replace('[', '')
from_id3 = from_id3.replace(']', '')
from_id2 = from_id3.split(',')
from_id = ''
for ifr in from_id2:
ifr = umisc.trim(ifr)
if len(ifr) > 1:
if ifr[0] in [
'0', '1', '2', '3', '4', '5', '6', '7', '8', '9'
] and ifr[1] in [
'0', '1', '2', '3', '4', '5', '6', '7', '8', '9'
]:
from_id = ifr
break
counter += 1
col['id_post'] = str(counter)
url_lomadee = rc['lomadee_url']
pub.insert(ky, col)
prod = rc['cod_p']
rccc = wb2.get(prods.encode('hex'))
rccc['lomadee_url'] = rc['lomadee_url']
#
gerate_insert_client(from_id, prod, rccc)
#============================
return products_client
def process_p(arrpg1,dm): print 'pages ok. init process ...' thst=[] indc=0 for pg in arrpg1: indc+=1 [u,uip]=pg if umisc.trim(u)=='': continue thst.append(thread_cntl()) params=get_feeds(u,0,'',None,[],uip,u) #========================== t = Thread(target=run_cmd, args=(params,thst[len(thst)-1])) t.start() while True: fndac=False for t in thst: if not t.finished: fndac=True time.sleep(1) if not fndac: break
def pg_open(addresss, th, pages, pgind, ind_emit, start_c):
try:
for address in addresss:
lines_doc = []
if address != 'debug-url':
opener = urllib2.build_opener()
address = urllib.quote(address)
print 'Open page:', address
url = 'http://www.mind-net.com/get_Text.php?q=' + address
content = opener.open(url, '').read()
tmpd = ''
for d in content:
if d == '\n':
tmpd = umisc.trim(tmpd)
if tmpd.find('http://') > -1:
''' '''
else:
lines_doc.append(tmpd)
tmpd = ''
else:
tmpd += d
#============
pages.append(Task_C(pg_add, lines_doc))
print 'Get content for page:', pgind, ' was finished.Len:', len(
lines_doc)
pgind += 1
else:
for line_deb in entry_doc:
lines_doc.append(line_deb)
pages.append(Task_C(pg_add, lines_doc))
print 'Get content for page:', pgind, ' was finished.Len:', len(
lines_doc)
pgind += 1
th.finished = True
except Exception, er:
print er, '................'
th.finished = True
def __init__(self, prefixo, sufixo, define, returnsa):
prefix = []
defs = []
sfx = []
#==================================
for p in prefixo:
prefix.append(latinupper(p))
#==================================
for d in define:
if umisc.trim(d) != "":
defs.append(latinupper(d))
#==================================
for sf in sufixo:
sfxc = []
for sf2 in sf:
sfxc.append(latinupper(sf2))
sfx.append(sfxc)
#==================================
self.prefixo = prefix
self.define = defs
self.sufixo = sfx
self.returns = returnsa
def get_filter_in_objs(obj, sinapses_consid1, dfin1, canditates, firp):
resultSet22 = []
for mn in min_purposes:
if umisc.trim(mn) == '': continue
mn = parse_each_topico2(mn, dfin1)
#print 'start.min.p:',mn
c2 = mdTb.valida_topico31_2(mn, usr, obj, True, '', 0, 0,
sinapses_consid1)
#print 'min.p:',mn ,c2
if len(c2) == 0: return []
for c1 in c2:
if c1 in canditates or firp:
canditates.append(c1)
firp = False
canditates2 = canditates
canditates = []
for c in canditates2:
if not c in canditates:
canditates.append(c)
for c in canditates:
#
r = [[c, mg.tb_get([tb_object31], c)]]
resultSet22.append(r)
return resultSet22
def get_by_keyword(
is2
): # busca algumas palavras chave para extrair os 'samples', amostras de codigo para calibrar e treinar o processador fuzzy
isd = []
cnc = False
for ch in is2:
try:
cnc = False
try:
rows = w_cache.get(ch)
except:
cnc = True
if cnc: continue
if True:
#============================
print 'Print pg:', ch
#=================
PG = rows[u'pg']
PROCESSED = rows[u'processed']
TERMO = rows[u'termo']
USR = rows[u'usr']
PURPOSE = rows[u'purpose']
URL_ICON = rows[u'url_icon']
URL_PICTURE = rows[u'url_picture']
ID_USR = float(rows[u'id_usr'])
NAME_USR = rows[u'name_usr']
STORY = rows[u'story']
TITLE = rows[u'title']
DOC_ID = rows[u'doc_id']
TP = rows[u'tp']
PHONE = ''
STREET = ''
CITY = ''
COUNTRY = ''
ZIP = ''
LATITUDE = ''
LONGITUDE = ''
TPS = rows['tps']
URL = rows['url']
#==========
if PG != None:
pass
else:
PG = ''
if URL_ICON != None:
pass
else:
URL_ICON = ''
if URL_PICTURE != None:
pass
else:
URL_PICTURE = ''
if STORY != None:
pass
else:
STORY = ''
if TITLE != None:
pass
else:
TITLE = ''
if URL != None:
pass
else:
URL = ''
words = tokeniz(PG)
fnd = False
fnd2 = False
if 'are now friends' in PG:
fnd2 = True
elif 'is now friends with' in PG:
fnd2 = True
elif PG[:7] == 'http://':
fnd2 = True
elif 'likes' in PG:
fnd2 = True
elif '{like}' in PG:
fnd2 = True
#===
for w in words:
if 'quer' in w:
fnd = True
elif 'precis' in w:
fnd = True
elif 'poderia' in w:
fnd = True
elif 'pode' in w:
fnd = True
elif 'podi' in w:
fnd = True
elif 'gostar' in w:
fnd = True
elif 'pensand' in w:
fnd = True
elif 'comprar' in w:
fnd = True
elif 'adquirir' in w:
fnd = True
elif 'pens' in w:
fnd = True
elif 'pegar' in w:
fnd = True
elif 'encontr' in w:
fnd = True
elif 'indicar' in w:
fnd = True
#================================
if umisc.trim(PG) == '':
fnd = False
if fnd and not fnd2:
isd.append([
PG, PROCESSED, TERMO, USR, PURPOSE, URL_ICON,
URL_PICTURE, ID_USR, NAME_USR, STORY, TITLE, DOC_ID,
TP, PHONE, STREET, CITY, COUNTRY, ZIP, LATITUDE,
LONGITUDE, TPS, URL
])
#apagar o item, passando p tabela processados somente os I,DOC_ID para o processo de reprocessamento nao considerar mais esses documentos
#===================================================================
#I=0
#conn.sqlX('insert into PROC_DS (ID,DOC_ID) values(?,?)',[I,ch])
proc_ds.insert(ch, {'ch': ch})
#======================================================================
w_cache.remove(ch)
except:
log.exception("")
conn.rollback()
return []
conn.commit()
return isd
def get_ontology_ponderate(
aliases, min_purposes, max_purposes, usr, dfin,
sinapses_consid): # min_purposes=mandatory, max_purposes=max ideal
rts = []
firp = True
resultSet2 = []
canditates = []
alias = aliases
if alias == None:
alias = '%'
#======================================================================================================================================
#======================================================================================================================================
def get_filter_in_objs(obj, sinapses_consid1, dfin1, canditates, firp):
resultSet22 = []
for mn in min_purposes:
if umisc.trim(mn) == '': continue
mn = parse_each_topico2(mn, dfin1)
#print 'start.min.p:',mn
c2 = mdTb.valida_topico31_2(mn, usr, obj, True, '', 0, 0,
sinapses_consid1)
#print 'min.p:',mn ,c2
if len(c2) == 0: return []
for c1 in c2:
if c1 in canditates or firp:
canditates.append(c1)
firp = False
canditates2 = canditates
canditates = []
for c in canditates2:
if not c in canditates:
canditates.append(c)
for c in canditates:
#
r = [[c, mg.tb_get([tb_object31], c)]]
resultSet22.append(r)
return resultSet22
#======================================================================================================================================
#======================================================================================================================================
if aliases == None or umisc.trim(aliases) == '':
firp = True
for mn in min_purposes:
if umisc.trim(mn) == '': continue
mn = parse_each_topico2(mn, dfin)
#print 'start.min.p:',mn
c2 = mdTb.valida_topico31(mn, usr, None)
#print 'min.p:',mn ,c2
if len(c2) == 0: return []
for c1 in c2:
if c1 in canditates or firp:
canditates.append(c1)
firp = False
canditates2 = canditates
canditates = []
for c in canditates2:
if not c in canditates:
canditates.append(c)
for c in canditates:
#
try:
r = [[[c, mg.tb_get([tb_object31], c)]]]
except:
try:
r = [[[c, mg.tb_get([tb_object1], c)]]]
except:
#r=[[c,tb_object.get(c)]]
pass # cache temporario tb_object, nao deve haver ponderacoes nesse cache
resultSet2.append(r)
else:
#print 'Collect->get(2):',alias,usr
#
########################################################################
#if mdTb.Zeus_Mode:
# r=[[alias,tb_object1.get(alias)]]
#else:
# r=[[alias,tb_object31.get(alias)]]
r = get_filter_in_objs(alias, sinapses_consid, dfin, canditates, firp)
resultSet2.append(r)
#=============================================
for resultSet23 in resultSet2:
for resultSet in resultSet23:
for key, results in resultSet:
i = results[u'objeto']
uid = key
#====
avaliable_objs = []
#===--------------------------------------
#print 'get_object_by_data29()->(',i,',',usr,',',max_purposes,')'
ant_z = mdTb.Zeus_Mode
mdTb.Zeus_Mode = False
[obj_principal,
ratting] = get_object_by_data29(i, usr, max_purposes)
obj_principal.get_links('')
mdTb.Zeus_Mode = ant_z
#if len(obj_principal.topicos) > 0 :
rts.append([ratting, obj_principal])
rts.sort()
#===
return rts
def post_object_by_data3p(layer, cenario, usr, termo, foco, posted_objs, senti,
l_p_ant):
if layer.name == '': layer.name = 'undef'
def get_top_level(obj, foc, usr, termo_s):
rts = []
cl1 = index.create_index_expression(column_name='OBJECT', value=obj)
cl2 = index.create_index_expression(column_name='TOPICO', value=foc)
cl3 = index.create_index_expression(column_name='USERNAME', value=usr)
cl4 = index.create_index_expression(column_name='UID', value=termo_s)
clausec = index.create_index_clause([cl1, cl2, cl3, cl4],
count=1000000)
rest = tb_object_dt.get_indexed_slices(clausec)
#
#for results in resultSet:
for kl, cols in rest:
i = cols[u'lev']
id_top = cols[u'id_top']
rts.append([i, id_top])
return rts
#=======================
nameo = layer.name
print 'Post layer:', nameo
if umisc.trim(nameo) == '' or umisc.trim(nameo) == '\n':
if l_p_ant != None:
nameo = l_p_ant.name
if umisc.trim(nameo) == '' or umisc.trim(nameo) == '\n':
return
fnd_tops = False
l_p_ant = layer
geral_uuid = cenario
print 'POST:LR:', nameo
print '++------------------------------------------'
for s in layer.topicos:
print 'DT:', s.dt
fnd_tops = True
for d in s.sinapses:
print d.nr.dt
print '++------------------------------------------'
if not fnd_tops: return
ky1 = nameo + ' ' + str(cenario)
nameo = ky1
#
#nameo = filter(lambda x: x in string.printable, nameo)
nameo = nameo.replace('\n', '')
nameo = nameo.replace('\t', '')
nameo = nameo.replace('.', '')
nameo = nameo.strip('\n')
nameo = nameo.strip('\r')
nameo = nameo.strip('\t')
nameo = nameo.replace(' ', ' ')
nameo = nameo.replace(' ', ' ')
nameo = nameo.replace(' ', ' ')
nameo = nameo.replace(' ', ' ')
nameo = nameo.replace(' ', ' ')
nameo = nameo.replace(' ', ' ')
nameo = nameo.replace(' ', ' ')
nameo = nameo.replace(' ', ' ')
ky1 = nameo
#
print 'Post-obj:[', nameo, ']'
# procurar nas tabs se ja existe e carregar os topicos q tem lá antes de postar os novos
try:
print 'get.object.reuse:'
import mdTb
layer_ant = mdTb.get_object_by_data(nameo, nameo)
print 'get.object.reuse.return:', layer_ant
if layer_ant != None:
print 'reuse layer(', len(layer.topicos), '):', nameo,
#layer.dump_layer()
tps_ant_p = layer.topicos
layer.topicos = []
for stop in layer_ant.topicos:
if len(stop.dt) > 0:
if stop.dt[0].lower() == 'identificador': continue
layer.topicos.append(stop)
for atop in tps_ant_p:
layer.topicos.append(atop)
print 'result:', len(layer.topicos)
#layer.dump_layer()
except:
#log.exception("Error.get.object")
pass
#
no_post_o = False
for [s, st] in posted_objs:
if s == nameo and st == senti:
no_post_o = True
posted_objs.append([nameo, senti])
#==========
#if not no_post_o and len(layer.topicos)>0:
def post_alldt(arr):
#=======================
b = tb_object_dt.batch(queue_size=len(arr))
for k, cols in arr:
b.insert(str(k), cols)
b.send()
#
def post_nr(uid, cnt, arr1, usr, tp, level=1, id_top=1, just_sin=False):
try:
if not just_sin:
tp_Dt = ''
try:
for d in tp.dt:
if type(d) == type([]):
tp_Dt += d[0]
else:
tp_Dt += d
except Exception, e:
print 'Err:-nr.post(2):', tp.dt, '->', e
tp_name = tp_Dt
if len(tp.sinapses) == 0:
##UID,topico,LEV,sin,dt,id_top,username
kyl1 = uid + '|' + str(cnt.value())
it = {
"UID": uid,
"topico": tp_Dt,
"LEV": "1",
"sin": '',
"datach": '',
"id_top": str(id_top),
"username": usr,
"cnt": str(cnt.value())
}
arr1.append([kyl1, it])
cnt.inc()
else:
def get_db_pages(usr2, pg_ex, connc):
def remote_f():
print 'Getting remote-pages...'
return proxy.get_pages('', usr2)
if RemoteL:
return remote_f()
print 'PG_EX', pg_ex, len(pg_ex)
pgs_exs = pg_ex.split(',')
#resultSet = connc.sql ("select pg,i,title from web_cache3 where USR='******' and i in( "+pg_ex+" ) order by i")
resultSet = []
#==========================================================================================================================================
#==========================================================================================================================================
#==========================================================================================================================================
#==========================================================================================================================================
#==========================================================================================================================================
# se implementar testes,adicionar no resultSet
#resultSet=['','']
#==========================================================================================================================================
#==========================================================================================================================================
#==========================================================================================================================================
#==========================================================================================================================================
#==========================================================================================================================================
if len(resultSet) == 0:
for p1 in pgs_exs:
rg = w_cache3.get(p1)
try:
pg = rg['PG']
#
pg = pg.replace('\n', '')
pg = pg.replace('\t', '')
pg = pg.strip('\n')
pg = pg.strip('\r')
pg = pg.strip('\t')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pagina = pg
#
pg = rg[u'TITLE']
pg = pg.replace('\n', '')
pg = pg.replace('\t', '')
pg = pg.replace('.', ' ')
pg = pg.strip('\n')
pg = pg.strip('\r')
pg = pg.strip('\t')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
titulo = pg
resultSet.append([pagina, p1, titulo])
except:
pg = rg['pg']
#
pg = pg.replace('\n', '')
pg = pg.replace('\t', '')
pg = pg.strip('\n')
pg = pg.strip('\r')
pg = pg.strip('\t')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pagina = pg
#
pg = rg[u'title']
pg = pg.replace('\n', '')
pg = pg.replace('\t', '')
pg = pg.strip('\n')
pg = pg.strip('\r')
pg = pg.strip('\t')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
pg = pg.replace(' ', ' ')
titulo = pg
resultSet.append([pagina, p1, titulo])
typ = []
print 'Collect pg:', pg_ex
#===============================================
#typ.append(['O perfil da empresa no Twitter foi criado em 20 de Fevereiro de 2008.',35835 ])
#return typ
#================================================
for [ts, ids, ids2] in resultSet:
if ids2 == None: ids2 = ''
if umisc.trim(ids2) != '':
ts = (ids2 + ': ' + ts)
#if umisc.trim(ts) != '' and umisc.trim(ts) != '\n' and umisc.trim(ts) != '\r':
typ.append([ts, ids])
print 'Read page', ids #,ts
print 'Reuse pgs:', len(typ)
return typ
tp_Dt += d
except:
print 'Err:-nr.post(2):', tp.dt
#=================
for sn in tp.sinapses:
sn_dt = ''
try:
for s1 in sn.nr.dt:
if type(s1) == type([]):
sn_dt += s1[0]
else:
sn_dt += s1
except:
print 'Err:-nr.post:', sn.nr.dt
#sql1="insert into SEMANTIC_OBJECT_DT3(UID,dt,topico,LEV,sin,id_top,username) values(?,?,?,?,?,?,?)"
if umisc.trim(sn.opcode) == '':
sn.opcode = 'Relaction-oper-opcode'
#====================================================
#====================================================
kyl1 = uid + '|' + str(cnt.value())
it = {
"UID": uid,
"topico": tp_Dt,
"LEV": str(level),
"sin": sn.opcode,
"datach": sn_dt,
"id_top": str(id_top),
"username": usr,
"cnt": str(cnt.value())
}
arr1.append([kyl1, it])
def post_object_by_data3p(layer,cenario,usr,termo,foco,posted_objs,senti,l_p_ant):
if layer.name == '' : layer.name ='undef'
def get_top_level(obj,foc,usr,termo_s):
rts=[]
cl1 = index.create_index_expression(column_name='OBJECT', value=obj)
cl2 = index.create_index_expression(column_name='TOPICO', value=foc)
cl3 = index.create_index_expression(column_name='USERNAME', value=usr)
cl4 = index.create_index_expression(column_name='UID', value=termo_s)
clausec = index.create_index_clause([cl1,cl2,cl3,cl4],count=1000000)
rest=tb_object_dt.get_indexed_slices(clausec)
#
#for results in resultSet:
for kl,cols in rest:
i=cols[u'lev']
id_top=cols[u'id_top']
rts.append([i,id_top])
return rts
#=======================
nameo=layer.name
print 'Post layer:',nameo
if umisc.trim(nameo) == '' or umisc.trim(nameo) == '\n' :
if l_p_ant != None:
nameo=l_p_ant.name
if umisc.trim(nameo) == '' or umisc.trim(nameo) == '\n' :
return
fnd_tops=False
l_p_ant=layer
geral_uuid=cenario
print 'POST:LR:',nameo
print '++------------------------------------------'
for s in layer.topicos:
print 'DT:',s.dt
fnd_tops=True
for d in s.sinapses:
print d.nr.dt
print '++------------------------------------------'
if not fnd_tops: return
ky1=nameo+' '+str(cenario)
nameo=ky1
print 'Post-obj:[',nameo,']'
no_post_o=False
for [s,st] in posted_objs:
if s == nameo and st==senti :
no_post_o=True
posted_objs.append([nameo,senti])
#==========
#if not no_post_o and len(layer.topicos)>0:
def post_alldt(arr):
#=======================
b = tb_object_dt.batch(queue_size=len(arr))
for k,cols in arr:
b.insert(str(k),cols)
b.send()
#
def post_nr(uid,cnt,arr1,usr,tp,level=1,id_top=1,just_sin=False):
try:
if not just_sin:
tp_Dt=''
try:
for d in tp.dt:
if type(d) == type([] ):
tp_Dt+=d[0]
else:
tp_Dt+=d
except Exception,e:
print 'Err:-nr.post(2):',tp.dt,'->',e
tp_name=tp_Dt
if len(tp.sinapses)==0:
##UID,topico,LEV,sin,dt,id_top,username
kyl1=uid+'|'+str(cnt.value())
it={"UID":uid,"topico":tp_Dt,"LEV":"1","sin":'',"datach":'',"id_top":str(id_top),"username":usr,"cnt":str(cnt.value())}
arr1.append( [ kyl1,it ] )
cnt.inc()
else:
