def test_basic_segment_properties(self):
seg = Segment('')
assert (str(seg) == '')
assert (len(seg) == 0)
assert (seg != 's')
seg1 = Segment('a')
seg2 = Segment('b')
assert (seg1 < seg2)
assert (seg1 <= seg2)
assert (seg2 > seg1)
assert (seg2 >= seg1)
def test_basic(self):
corpus = Corpus('test')
for w in self.basic_info:
self.assertRaises(KeyError, corpus.find, w['spelling'], True)
corpus.add_word(Word(**w))
self.assertEqual(corpus[w['spelling']], Word(**w))
self.assertEqual(corpus.find(w['spelling']), Word(**w))
self.assertTrue(w['spelling'] in corpus)
self.assertEqual(
corpus.inventory._data, {
'#': Segment('#'),
'a': Segment('a'),
'b': Segment('b'),
'c': Segment('c'),
'd': Segment('d')
})
def test_match_feature(self):
for s, v in self.basic_info.items():
seg = Segment(s)
seg.set_features(v)
for feature, value in v.items():
for fv in ['+', '-']:
if fv == value:
self.assertTrue(seg.feature_match([fv + feature]))
self.assertTrue(seg.feature_match(fv + feature))
else:
self.assertTrue(not seg.feature_match([fv + feature]))
def test_match_feature(self):
for s,v in self.basic_info.items():
seg = Segment(s)
seg.set_features(v)
for feature, value in v.items():
for fv in ['+','-']:
if fv == value:
self.assertTrue(seg.feature_match([fv+feature]))
self.assertTrue(seg.feature_match(fv+feature))
else:
self.assertTrue(not seg.feature_match([fv+feature]))
def test_no_syllabic_feature():
seg = Segment('')
seg.set_features({'feature1':'+','feature2':'+'})
# ------------------------------------------------------------------#
# TESTING
# The following code will not be included in the actual PCT release,
# and is here for the purposes of testing for the LIBR 559C project.
# All testing is done with the Lemurian corpus - lemurian.corpus
# ------------------------------------------------------------------#
# Additional imports for testing purposes
import pickle
from corpustools.corpus.classes import Segment
# Load the corpus
corpus_path = "lemurian.corpus"
with open(corpus_path, 'rb') as file:
corpus_in = pickle.load(file)
# Corpus information
print("Corpus: ", corpus_in.name)
print("Segments in the lemurian corpus: ",
[seg for seg in corpus_in.inventory], "\n")
# Informativity of a single segment
print("Informativity for one segment:")
print(get_informativity(corpus_in, Segment("m"), rounding=3), "\n")
# Informativity for all segments in inventory
print("Informativity for all segments in inventory:")
output = all_informativity(corpus_in, rounding=4)
for s in sorted(output.keys()):
print(s, output[s])
#remove ROUNDING from output, since this is already handled in PCT's global settings
def test_no_syllabic_feature():
seg = Segment('')
seg.set_features({'feature1': '+', 'feature2': '+'})
def test_no_features():
seg = Segment('')
