def next_tamil_letter(self):
""" method loads the corpus and returns one Tamil letter at a time in iterable"""
with codecs.open(self.filename, "r", "utf-8") as handle:
self.handle = handle
for letter in filter(utf8.istamil,utf8.get_letters_iterable(self.handle.read())):
yield letter
return
def test_letter_extract_yield_with_ascii(self):
letters = []
ta_str = u"கூவிளம் is என்பது also என்ன a சீர்"
for l in utf8.get_letters_iterable(ta_str):
letters.append(l)
act_letters = utf8.get_letters(ta_str)
assert len(letters) == len(act_letters)
self.assertEqual(letters[-4], u"a")
def test_letter_extract_yield(self):
letters = []
for l in utf8.get_letters_iterable(u"கூவிளம் என்பது என்ன சீர்"):
letters.append( l )
#print "len ==== > " , len(letters)
assert( len(letters) == 15 )
for pos,letter in enumerate(letters):
print(u"%d %s"%(pos,letter))
assert( letter == (u"ர்") )
def test_letter_extract_yield_with_ascii(self):
letters = []
for l in utf8.get_letters_iterable(u"கூவிளம் is என்பது also என்ன a சீர்"):
letters.append( l )
print "len ==== > " , len(letters)
assert(len(letters) == 25 )
for pos,letter in enumerate(letters):
print(u"%d %s"%(pos,letter))
assert( letters[-4] == u"a" )
def test_letter_extract_yield(self):
letters = []
for l in utf8.get_letters_iterable(u"கூவிளம் என்பது என்ன சீர்"):
letters.append(l)
print "len ==== > ", len(letters)
assert (len(letters) == 15)
for pos, letter in enumerate(letters):
print(u"%d %s" % (pos, letter))
assert (letter == (u"ர்"))
def test_letter_extract_yield(self):
ta_str = u"கூவிளம் என்பது என்ன சீர்"
act_letters = utf8.get_letters(ta_str)
letters = []
for l in utf8.get_letters_iterable(ta_str):
letters.append(l)
assert len(letters) == 16
assert len(letters) == len(act_letters)
assert letters[-1] == (u"ர்")
def test_letter_extract_yield_with_ascii(self):
letters = []
for l in utf8.get_letters_iterable(
u"கூவிளம் is என்பது also என்ன a சீர்"):
letters.append(l)
print "len ==== > ", len(letters)
assert (len(letters) == 25)
for pos, letter in enumerate(letters):
print(u"%d %s" % (pos, letter))
assert (letters[-4] == u"a")
def test_letter_extract_yield_with_ascii(self):
letters = []
ta_str = u"கூவிளம் is என்பது also என்ன a சீர்"
for l in utf8.get_letters_iterable(ta_str):
letters.append( l )
act_letters = utf8.get_letters(ta_str)
print( "len ==== > " , len(letters),"get_letters CALL = ",len(act_letters) )
assert(len(letters) == len(act_letters) )
for pos,letter in enumerate(letters):
if ( LINUX ): print( u"%d %s"%(pos,letter) )
self.assertEqual( letters[-4], u"a" )
def test_letter_extract_yield_with_ascii(self):
letters = []
ta_str = u"கூவிளம் is என்பது also என்ன a சீர்"
for l in utf8.get_letters_iterable(ta_str):
letters.append( l )
act_letters = utf8.get_letters(ta_str)
print( "len ==== > " , len(letters),"get_letters CALL = ",len(act_letters) )
assert(len(letters) == len(act_letters) )
for pos,letter in enumerate(letters):
if ( LINUX ): print( u"%d %s"%(pos,letter) )
self.assertEqual( letters[-4], u"a" )
def test_letter_extract_yield(self):
ta_str = u"கூவிளம் என்பது என்ன சீர்"
act_letters = utf8.get_letters(ta_str)
letters = []
for l in utf8.get_letters_iterable(ta_str):
letters.append( l )
print( "len ==== > " , len(letters) )
assert( len(letters) == 16 )
print( "len ==== > " , len(letters),"get_letters CALL = ",len(act_letters) )
assert(len(letters) == len(act_letters) )
for pos,letter in enumerate(letters):
if ( LINUX ): print(u"%d %s"%(pos,letter))
assert( letter == (u"ர்") )
def test_letter_extract_yield(self):
ta_str = u"கூவிளம் என்பது என்ன சீர்"
act_letters = utf8.get_letters(ta_str)
letters = []
for l in utf8.get_letters_iterable(ta_str):
letters.append( l )
print( "len ==== > " , len(letters) )
assert( len(letters) == 16 )
print( "len ==== > " , len(letters),"get_letters CALL = ",len(act_letters) )
assert(len(letters) == len(act_letters) )
for pos,letter in enumerate(letters):
if ( LINUX ): print(u"%d %s"%(pos,letter))
assert( letter == (u"ர்") )
def demo(self):
for l in utf8.get_letters_iterable(u"இதுதாண்டாபோலிசு"):
print("%s - %s" % (l, utf8.classify_letter(l)))
def next_tamil_letter(self):
self.handle = codecs.open(self.filename,'r','utf-8')
for letter in utf8.get_letters_iterable(self.handle.read()):
if ( utf8.istamil( letter ) ):
yield letter
return
def demo(self):
for l in utf8.get_letters_iterable(u"இதுதாண்டாபோலிசு"):
print("%s - %s"%(l,utf8.classify_letter(l)))
def next_tamil_letter(self):
self.handle = codecs.open(self.filename,'r','utf-8')
for letter in utf8.get_letters_iterable(self.handle.read()):
if ( utf8.istamil( letter ) ):
yield letter
return
