class PLPTestCase(unittest.TestCase):
def setUp(self):
self.plp = PLP('/usr/local/clp/lib/libclp_2.6.so')
def test_ver(self):
self.assertIsInstance(self.plp.ver() , unicode)
def test_rec(self):
self.assertEqual(self.plp.rec(u'żółwiem'), [18660912])
def test_orec(self):
self.assertEqual(self.plp.rec(u'zolwiem'), [])
self.assertEqual(self.plp.orec(u'zolwiem'), [18660912])
def test_bform(self):
self.assertEqual(self.plp.bform(18660912), u'żółw')
def test_label(self):
self.assertEqual(self.plp.label(18660912)[0], PLP.CZESCI_MOWY.RZECZOWNIK)
self.assertEqual(self.plp.label(self.plp.rec(u'idę')[0])[0], PLP.CZESCI_MOWY.CZASOWNIK)
def test_ogonkify(self):
self.assertItemsEqual(self.plp.ogonkify(u'gzo'), [u'gzó', u'gżo', u'gźo', u'gźó', u'gżó'])
def test_forms(self):
self.assertEqual(self.plp.forms(17786048), [
u'pogoda',
u'pogody',
u'pogodzie',
u'pogodę',
u'pogodą',
u'pogodo',
u'pogód',
u'pogodom',
u'pogodami',
u'pogodach'
])
def test_vec(self):
self.assertEqual(self.plp.vec(18660912, u'żółwiem')[0], 5)
#!/usr/bin/env python
# encoding: utf-8
from plp import PLP
p = PLP()
VERB = PLP.CZESCI_MOWY.CZASOWNIK
stimulus = u'fajka'
st_forms = set(p.forms(p.rec(u'fajka')[0]))
print st_forms
snippets_count = 0
def parse_file(filename):
global snippets_count
with open(filename, 'r') as f:
all_words = []
for line in f:
words = line.strip().split()
all_words.extend(words)
stimulus_seen = False
last_verb = None
second_to_last_verb = None
last_verb_index = 0
for i, word in enumerate(all_words):
word_utf8 = word.decode('utf-8')
if word_utf8 in st_forms or word_utf8[:-1] in st_forms:
#print 'stimulus_seen'
