def test_syllabify(self):
"""Test Indic Syllabifier method"""
correct = ['न', 'म', 'स्ते']
syllabifier = IndianSyllabifier('hindi')
current = syllabifier.orthographic_syllabify('नमस्ते')
self.assertEqual(current, correct)
def test_syllabify(self):
"""Test Indic Syllabifier method"""
correct = ['न', 'म', 'स्ते']
syllabifier = IndianSyllabifier('hindi')
current = syllabifier.orthographic_syllabify('नमस्ते')
self.assertEqual(current, correct)
infile.close()
outfile = open(outfilename, "w")
for shlok in filestring:
#picking one shloka from the file
t_shlok = tokenizer.tokenize(shlok)
#initializing the flags
count = 0 # to count the number of phonemes after which the split has to be done
pos = 0 # to insert the -
diff = 0 # to keep track of the overflow phonemes
for i in range(len(t_shlok)):
token = t_shlok[i]
split = syl.orthographic_syllabify(token)
l = len(split)
# phonemes already covered
prev = count
#checking for purna-viram and numbers
if l == 1 and check_token(token) == False:
diff = pos = count = 0
continue
# more phonemes added
count = count + l
# word extends the meter length
if count > 8:
