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)
notes = {}
for note in pap:
if not re.search('\d{6}', note):
continue
note_id = re.findall('\d{6}', note)[0]
note_content = re.sub(note_id, '', note).strip()
words = pre_process(note_content).split(' ')
for i, word in enumerate(words):
if not p.rec(word):
continue
basic_form = p.bform(p.rec(word)[0])
if basic_form in stop_list:
continue
# words frequencies and total words number
word = strip_sie(basic_form)
if word in words_freq:
words_freq[word] += 1
else:
words_freq[word] = 1
total_no += 1
# co-occurence frequencies
if word == STIMULUS:
min_idx = min(0, i - 12)
max_idx = min(len(words) - 1, i + 12)
