#from urllib import urlopen
from codecs import getwriter
import sys

sys.stdout = getwriter('utf-8')(sys.stdout)

#ind = urlopen('http://www.unicode.org/udhr/d/udhr_ind.txt').read().decode('utf-8').split()
ind = open('/home/pat/repo/udhr/udhr_ind.txt').read().decode('utf-8').split()
print "Indonesian sample: "
print ' '.join(ind[:100])
print
#eng = urlopen('http://www.unicode.org/udhr/d/udhr_eng.txt').read().decode('utf-8').split()
eng = open('/home/pat/repo/udhr/udhr_eng.txt').read().decode('utf-8').split()
print "English sample: "
print ' '.join(eng[:100])
print


print 'apa' in ' '.join(ind).lower()
print 'kabar' in ' '.join(ind).lower()