def test_iter_morphemes_prefixes(self):
"""Test iter_morphemes with prefixes."""
word = 'pfxone#pfxtwo#stem:POS|stem&FUS=stemgloss'
actual_output = list(JapaneseMiiProReader.iter_morphemes(word))
desired_output = [('pfxone', '', 'pfx'), ('pfxtwo', '', 'pfx'),
('stem&FUS', 'stemgloss', 'stem:POS')]
self.assertEqual(actual_output, desired_output)
def test_iter_morphemes_compound_gloss(self):
"""Test iter_morphemes with compound and stem gloss."""
word = 'CMPPOS|+CMPPOSONE|cmpstemone+CMPPOSTWO|cmpstemtwo=cmpgloss'
actual_output = list(JapaneseMiiProReader.iter_morphemes(word))
desired_output = [('=cmpstemone', 'cmpgloss', 'CMPPOSONE'),
('=cmpstemtwo', 'cmpgloss', 'CMPPOSTWO')]
self.assertEqual(actual_output, desired_output)
def test_iter_morphemes_suffixes_stemgloss(self):
"""Test iter_morphemes with suffixes and stem gloss."""
word = 'stem:POS|stem&FUS-SFXONE-SFXTWO=stemgloss'
actual_output = list(JapaneseMiiProReader.iter_morphemes(word))
desired_output = [('stem&FUS', 'stemgloss', 'stem:POS'),
('', 'SFXONE', 'sfx'), ('', 'SFXTWO', 'sfx')]
self.assertEqual(actual_output, desired_output)
def test_iter_morphemes_suffixes_colon(self):
"""Test iter_morphemes with suffix and colon."""
word = 'stem:POS|stem&FUS-SFXONE:contr-SFXTWO:SFXTWOseg=stemgloss'
actual_output = list(JapaneseMiiProReader.iter_morphemes(word))
desired_output = [('stem&FUS', 'stemgloss', 'stem:POS'),
('', 'SFXONE:contr', 'sfx'),
('SFXTWOseg', 'SFXTWO', 'sfx')]
self.assertEqual(actual_output, desired_output)
def test_iter_morphemes_compound_suffixes(self):
"""Test iter_morphemes with compound and suffixes."""
word = ('CMPPOS|+CMPPOSONE|cmpstemone-SFXONE'
'+CMPPOSTWO|cmpstemtwo-SFXTWO=cmpgloss')
actual_output = list(JapaneseMiiProReader.iter_morphemes(word))
desired_output = [('=cmpstemone', 'cmpgloss', 'CMPPOSONE'),
('', 'SFXONE', 'sfx'),
('=cmpstemtwo', 'cmpgloss', 'CMPPOSTWO'),
('', 'SFXTWO', 'sfx')]
self.assertEqual(actual_output, desired_output)
def test_parse(self):
"""Test parse()."""
session_str = ('tom20010724.cha:*MOT:\tdoozo . 4087868_4089193\n'
'%xtrn:\tn:prop|Hono-chan co:g|doozo .\n'
'%ort:\tホノちゃんどうぞ。\n'
'@End')
parser = JapaneseMiiProSessionParser(self.dummy_cha_path)
parser.reader = JapaneseMiiProReader(io.StringIO(session_str))
session = parser.parse()
utt = session.utterances[0]
utterance = [
utt.source_id == 'dummy_0', utt.addressee is None,
utt.utterance_raw == 'doozo .', utt.utterance == 'doozo',
utt.translation == '',
utt.morpheme_raw == 'n:prop|Hono-chan co:g|doozo .',
utt.gloss_raw == 'n:prop|Hono-chan co:g|doozo .',
utt.pos_raw == 'n:prop|Hono-chan co:g|doozo .',
utt.sentence_type == 'default', utt.start_raw == '4087868',
utt.end_raw == '4089193', utt.comment == '', utt.warning == ''
]
w = utt.words[0]
words = [
w.word_language == 'Japanese', w.word == 'doozo',
w.word_actual == 'doozo', w.word_target == 'doozo', w.warning == ''
]
m1 = utt.morphemes[0][0]
m2 = utt.morphemes[0][1]
m3 = utt.morphemes[1][0]
morphemes = [
m1.gloss_raw == '', m1.morpheme == 'Hono',
m1.morpheme_language == '', m1.pos_raw == 'n:prop',
m2.gloss_raw == 'chan', m2.morpheme == 'chan',
m2.morpheme_language == '', m2.pos_raw == 'sfx',
m3.gloss_raw == '', m3.morpheme == 'doozo',
m3.morpheme_language == '', m3.pos_raw == 'co:g'
]
assert (False not in utterance and False not in words
and False not in morphemes)
def test_iter_morphemes_stem_gloss(self):
"""Test iter_morphemes with stem and gloss."""
word = 'stem:POS|stem&FUS=stemgloss'
actual_output = list(JapaneseMiiProReader.iter_morphemes(word))
desired_output = [('stem&FUS', 'stemgloss', 'stem:POS')]
self.assertEqual(actual_output, desired_output)
def get_reader(session_file):
return JapaneseMiiProReader(session_file)