def soundex_convert(name_string):
"""Combine the three FSTs above and use it to convert a name into a Soundex"""
f1 = letters_to_numbers()
f2 = truncate_to_three_digits()
f3 = add_zero_padding()
output = compose(name_string, f1, f2, f3)[0]
return ''.join(output)
def soundex_convert(name_string):
"""Combine the three FSTs above and use it to convert a name into a Soundex"""
char_list = [char for char in name_string]
target = compose(char_list, letters_to_numbers(),
truncate_to_three_digits(), add_zero_padding())
return ''.join(target[0])
def parse(self, word):
"""Parse a word morphologically
e.g.
p = Parser()
word = ['p','a','n','i','c','k','i','n','g']
p.parse(word)
---> 'panic+present participle form'
"""
# Ok so now let's do the second FST
f2 = FST('morphology-parse') # Detecting affixes ('ing' and 'ed')
# Indicate initial and final states
states = ['start', 'i', 'n', 'g', 'e', 'd']
for state in states:
f2.add_state(state)
f2.initial_state = 'start'
f2.set_final('d')
f2.set_final('g')
for letter in string.ascii_lowercase:
if not letter in 'ie':
f2.add_arc('start', 'start', letter, letter)
if not letter == 'n':
f2.add_arc('i', 'start', letter, ('i', letter))
if not letter == 'd':
f2.add_arc('e', 'start', letter, ['e', letter])
if not letter == 'g':
f2.add_arc('n', 'start', letter, ['i', 'n', letter])
f2.add_arc('start', 'i', 'i', '')
f2.add_arc('i', 'n', 'n', '')
f2.add_arc('n', 'g', 'g', '+present participle form')
f2.add_arc('start', 'e', 'e', '')
f2.add_arc('e', 'd', 'd', '+past form')
f3 = FST('morphology-parse') # K-deletion
# Indicate initial and final states
f3.add_state('start')
f3.add_state('vowel')
f3.add_state('consonant')
f3.add_state('c')
f3.add_state('k')
f3.add_state('lick_l')
f3.add_state('lick_i')
f3.add_state('lick_c')
f3.add_state('lick_k')
f3.add_state('parse')
f3.initial_state = 'start'
f3.set_final('parse')
vowels = 'aeiou'
for vowel in vowels:
f3.add_arc('start', 'vowel', vowel, vowel)
f3.add_arc('vowel', 'vowel', vowel, vowel)
f3.add_arc('consonant', 'vowel', vowel, vowel)
f3.add_arc('c', 'vowel', vowel, vowel)
for letter in string.ascii_lowercase:
f3.add_arc('parse', 'parse', letter, letter)
if letter in vowels:
continue
if not letter == 'c':
f3.add_arc('vowel', 'consonant', letter, letter)
if not letter == 'l':
f3.add_arc('start', 'consonant', letter, letter)
if not letter == 'k':
f3.add_arc('c', 'consonant', letter, letter)
f3.add_arc('consonant', 'consonant', letter, letter)
f3.add_arc('vowel', 'c', 'c', 'c')
f3.add_arc('c', 'k', 'k', '')
f3.add_arc('start', 'lick_l', 'l', 'l')
f3.add_arc('lick_l', 'lick_i', 'i', 'i')
f3.add_arc('lick_i', 'lick_c', 'c', 'c')
f3.add_arc('lick_c', 'lick_k', 'k', 'k')
f3.add_arc('lick_k', 'parse', '+', '+')
f3.add_arc('k', 'parse', '+', '+')
f3.add_arc('consonant', 'parse', '+', '+')
f3.add_arc('parse', 'parse', ' ', ' ')
output = compose(word, f2, f3)[0]
return "".join(output)
def parse(self, word):
"""Parse a word morphologically want, sync, panic, havoc, and lick
e.g. -ed and -ing
p = Parser() past form \ present participle form
word = ['p', 'a', 'n', 'i', 'c', 'k','e','d']
p.parse(word)
---> 'panic+past form'
"""
f2=fst.FST('lexicon')
for i in range(1,56):
f2.add_state(str(i))
f2.initial_state = '1'
f2.add_arc('1','2','w','w')
f2.add_arc('2','3','a','a')
f2.add_arc('3','4','n','n')
f2.add_arc('4','5','t','t')
f2.add_arc('5','6','e','^')
f2.add_arc('6','7','d','d')
f2.add_arc('7','8','','#')
f2.add_arc('5','9','i','^')
f2.add_arc('9','10','n','n')
f2.add_arc('10','11','g','g')
f2.add_arc('11','8','','#')
f2.add_arc('1','12','s','s')
f2.add_arc('12','13','y','y')
f2.add_arc('13','14','n','n')
f2.add_arc('14','15','c','c')
f2.add_arc('15','16','e','^')
f2.add_arc('16','17','d','d')
f2.add_arc('17','18','','#')
f2.add_arc('15','19','i','^')
f2.add_arc('19','20','n','n')
f2.add_arc('20','21','g','g')
f2.add_arc('21','18','','#')
f2.add_arc('1','22','p','p')
f2.add_arc('22','23','a','a')
f2.add_arc('23','24','n','n')
f2.add_arc('24','25','i','i')
f2.add_arc('25','26','c','c')
f2.add_arc('26','27','k','^')
f2.add_arc('27','28','e','e')
f2.add_arc('28','29','d','d')
f2.add_arc('29','30','','#')
f2.add_arc('27','31','i','i')
f2.add_arc('31','32','n','n')
f2.add_arc('32','33','g','g')
f2.add_arc('33','30','','#')
f2.add_arc('1','34','h','h')
f2.add_arc('34','35','a','a')
f2.add_arc('35','36','v','v')
f2.add_arc('36','37','o','o')
f2.add_arc('37','38','c','c')
f2.add_arc('38','39','k','^')
f2.add_arc('39','40','e','e')
f2.add_arc('40','41','d','d')
f2.add_arc('41','42','','#')
f2.add_arc('39','43','i','i')
f2.add_arc('43','44','n','n')
f2.add_arc('44','45','g','g')
f2.add_arc('45','42','','#')
f2.add_arc('1','46','l','l')
f2.add_arc('46','47','i','i')
f2.add_arc('47','48','c','c')
f2.add_arc('48','49','k','k')
f2.add_arc('49','50','e','^')
f2.add_arc('50','51','d','d')
f2.add_arc('51','52','','#')
f2.add_arc('49','53','i','^')
f2.add_arc('53','54','n','n')
f2.add_arc('54','55','g','g')
f2.add_arc('55','52','','#')
f2.set_final('8')
f2.set_final('18')
f2.set_final('30')
f2.set_final('42')
f2.set_final('52')
f3=fst.FST('rule')
for i in range(1,53):
f3.add_state(str(i))
f3.initial_state = '1'
f3.add_arc('1','2','p','p')
f3.add_arc('2','3','a','a')
f3.add_arc('3','4','n','n')
f3.add_arc('4','5','i','i')
f3.add_arc('5','6','c','c')
f3.add_arc('6','7','^','')
f3.add_arc('7','8','e','')
f3.add_arc('8','9','d','+past form')
f3.add_arc('9','10','#','')
f3.add_arc('7','11','i','')
f3.add_arc('11','12','n','')
f3.add_arc('12','13','g','+present participle')
f3.add_arc('13','10','#','')
f3.add_arc('1','14','h','h')
f3.add_arc('14','15','a','a')
f3.add_arc('15','16','v','v')
f3.add_arc('16','17','o','o')
f3.add_arc('17','18','c','c')
f3.add_arc('18','19','^','')
f3.add_arc('19','20','e','')
f3.add_arc('20','21','d','+past form')
f3.add_arc('21','22','#','')
f3.add_arc('19','23','i','')
f3.add_arc('23','24','n','')
f3.add_arc('24','25','g','+present participle')
f3.add_arc('25','22','#','')
f3.add_arc('1','26','l','l')
f3.add_arc('26','27','i','i')
f3.add_arc('27','28','c','c')
f3.add_arc('28','29','k','k')
f3.add_arc('29','30','^','')
f3.add_arc('30','31','d','+past form')
f3.add_arc('31','32','#','')
f3.add_arc('30','33','n','')
f3.add_arc('33','34','g','+present participle')
f3.add_arc('34','32','#','')
f3.add_arc('1','35','s','s')
f3.add_arc('35','36','y','y')
f3.add_arc('36','37','n','n')
f3.add_arc('37','38','c','c')
f3.add_arc('38','39','^','')
f3.add_arc('39','40','d','+past form')
f3.add_arc('40','41','#','')
f3.add_arc('38','42','n','')
f3.add_arc('42','43','g','+present participle')
f3.add_arc('43','41','#','')
f3.add_arc('1','44','w','w')
f3.add_arc('44','45','a','a')
f3.add_arc('45','46','n','n')
f3.add_arc('46','47','t','t')
f3.add_arc('47','48','^','')
f3.add_arc('48','49','d','+past form')
f3.add_arc('49','50','#','')
f3.add_arc('47','51','n','')
f3.add_arc('51','52','g','+present participle')
f3.add_arc('52','50','#','')
f3.set_final('10')
f3.set_final('22')
f3.set_final('32')
f3.set_final('41')
f3.set_final('50')
output=''.join(fsmutils.compose(word,f2,f3)[0])
return output
'''output = ['p','a','n','i','c','+past form']