def test_get_gloss_tier_gloss_tier_absent(self):
"""Test get_gloss_tier with utt not containing a gloss_tier."""
session_str = ('*CHI:\t‹wâu nîyi› . 1198552_1209903\n%pho:\t‹wo ni›'
'\n%mod:\t‹ˈwo *›\n%eng:\tegg me\n%xactmor:\t[wo ni]\n'
'%xmortyp:\t[ni pro]\n%xtarmor:\t[wo *]\n@End')
reader = CreeReader(io.StringIO(session_str))
reader.load_next_record()
actual_output = reader.get_gloss_tier()
desired_output = ''
self.assertEqual(actual_output, desired_output)
def test_get_morpheme_language_english(self):
"""Test get_morpheme_language with english mopheme."""
seg = 'fly'
gloss = 'Eng'
pos = 'V'
actual_output = CreeReader.get_morpheme_language(seg, gloss, pos)
desired_output = 'English'
self.assertEqual(actual_output, desired_output)
def test_get_morpheme_language_cree(self):
"""Test get_morpheme_language with (pseudo-)cree morpheme."""
seg = 'hem'
gloss = '1sg'
pos = 'V'
actual_output = CreeReader.get_morpheme_language(seg, gloss, pos)
desired_output = 'Cree'
self.assertEqual(actual_output, desired_output)
def test_get_poses(self):
"""Test get_poses.
Just one test because the method only calls get_morphemes.
"""
seg_word = 'first~second~third'
actual_output = CreeReader.get_glosses(seg_word)
desired_output = ['first', 'second', 'third']
self.assertEqual(actual_output, desired_output)
def test_get_segments(self):
"""Test get_segments.
Just one test because the method only calls get_morphemes.
"""
seg_word = 'first'
actual_output = CreeReader.get_segments(seg_word)
desired_output = ['first']
self.assertEqual(actual_output, desired_output)
def test_parse_no_misalignments_single_word(self):
"""Test parse() with no misalignments."""
session_str = ('*CHI:\tchair . 2883660_2884622\n'
'%pho:\t*\n'
'%mod:\t*\n'
'%eng:\tohhhhhh\n'
'@End')
parser = CreeSessionParser(self.dummy_cha_path)
parser.reader = CreeReader(io.StringIO(session_str))
session = parser.parse()
utt = session.utterances[0]
utterance = [
utt.source_id == 'dummy_0',
utt.addressee is None,
utt.utterance_raw == 'chair .',
utt.utterance == 'chair',
utt.translation == 'ohhhhhh',
utt.morpheme_raw == '',
utt.gloss_raw == '',
utt.pos_raw == '',
utt.sentence_type == 'default',
utt.start_raw == '2883660',
utt.end_raw == '2884622',
utt.comment == '',
utt.warning == ''
]
w = utt.words[0]
words = [
w.word_language == '',
w.word == 'chair',
w.word_actual == 'chair',
w.word_target == 'chair',
w.warning == ''
]
assert (False not in utterance
and False not in words
and len(utt.morphemes) == 0)
def test_parse_no_misalignments_multiple_words(self):
"""Test parse() with no misalignemnts."""
session_str = ('*CHI:\t‹wâu nîyi› . 1198552_1209903\n'
'%pho:\t‹wo ni›\n'
'%mod:\t‹ˈwo *›\n'
'%eng:\tegg me\n'
'%xactmor:\t[wo ni]\n'
'%xmortyp:\t[ni pro]\n'
'%xtarmor:\t[wo *]\n'
'%xmormea:\t[egg 1]\n'
'@End')
parser = CreeSessionParser(self.dummy_cha_path)
parser.reader = CreeReader(io.StringIO(session_str))
session = parser.parse()
utt = session.utterances[0]
utterance = [
utt.source_id == 'dummy_0',
utt.addressee is None,
utt.utterance_raw == '‹wâu nîyi› .',
utt.utterance == 'wâu nîyi',
utt.translation == 'egg me',
utt.morpheme_raw == '[wo *]',
utt.gloss_raw == '[egg 1]',
utt.pos_raw == '[ni pro]',
utt.sentence_type == 'default',
utt.start_raw == '1198552',
utt.end_raw == '1209903',
utt.comment == '',
utt.warning == ''
]
w1 = utt.words[0]
w2 = utt.words[1]
words = [
w1.word_language == '',
w1.word == 'wâu',
w1.word_actual == 'wâu',
w1.word_target == 'wâu',
w1.warning == '',
w2.word_language == '',
w2.word == 'nîyi',
w2.word_actual == 'nîyi',
w2.word_target == 'nîyi',
w2.warning == ''
]
m1 = utt.morphemes[0][0]
m2 = utt.morphemes[1][0]
morphemes = [
m1.gloss_raw == 'egg',
m1.morpheme == 'wo',
m1.morpheme_language == 'Cree',
m1.pos_raw == 'ni',
m2.gloss_raw == '1',
m2.morpheme == '',
m2.morpheme_language == 'Cree',
m2.pos_raw == 'pro'
]
assert (False not in utterance
and False not in words
and False not in morphemes)
def get_reader(session_file):
return CreeReader(session_file)
def test_get_morphemes_multiple_tildes(self):
"""Test get_morphemes with morpheme-word containing 3 tildes."""
morph_word = 'first~second~third~fourth'
actual_output = CreeReader.get_morphemes(morph_word)
desired_output = ['first', 'second', 'third', 'fourth']
self.assertEqual(actual_output, desired_output)
def test_get_morphemes_one_tilde(self):
"""Test get_morphemes with morpheme-word containing one tilde."""
morph_word = 'first~second'
actual_output = CreeReader.get_morphemes(morph_word)
desired_output = ['first', 'second']
self.assertEqual(actual_output, desired_output)
def test_get_main_morpheme(self):
"""Test get_main_morpheme. Should return 'segment'."""
actual_output = CreeReader.get_main_morpheme()
desired_output = 'segment'
self.assertEqual(actual_output, desired_output)
def test_get_morphemes_empty_string(self):
"""Test get_morphemes with morpheme-word containing no tilde."""
morph_word = ''
actual_output = CreeReader.get_morphemes(morph_word)
desired_output = []
self.assertEqual(actual_output, desired_output)
