def setUp(self):
session = (
'@UTF8\n'
'@Begin\n'
'@Languages:\tsme\n'
'@Date:\t12-SEP-1997\n'
'@Participants:\tMEM Mme_Manyili Grandmother , '
'CHI Hlobohang Target_Child\n'
'@ID:\tsme|Sesotho|MEM||female|||Grandmother|||\n'
'@ID:\tsme|Sesotho|CHI|2;2.||||Target_Child|||\n'
'@Birth of CHI:\t14-JAN-2006\n'
'@Birth of MEM:\t11-OCT-1974\n'
'@Media:\th2ab, audio\n'
'@Comment:\tall snd kana jmor cha ok Wakachi2002;\n'
'@Warning:\trecorded time: 1:00:00\n'
'@Comment:\tuses desu and V-masu\n'
'@Situation:\tAki and AMO preparing to look at book , '
'"Miichan no otsukai"\n'
'*MEM:\tke eng ? 0_8551\n'
'%gls:\tke eng ?\n'
'%cod:\tcp wh ?\n'
'%eng:\tWhat is it ?\n'
'%sit:\tPoints to tape\n'
'%com:\tis furious\n'
'%add:\tCHI\n'
'*CHI:\tke ntencha ncha . 8551_19738\n'
'%gls:\tke ntho e-ncha .\n'
'%cod:\tcp thing(9 , 10) 9-aj .\n'
'%eng:\tA new thing\n'
'%com:\ttest comment\n'
'*MEM:\tke eng ntho ena e? 19738_24653\n'
'%gls:\tke eng ntho ena e ?\n'
'%cod:\tcp wh thing(9 , 10) d9 ij ?\n'
'%eng:\tWhat is this thing ?\n'
'%sit:\tPoints to tape\n'
'*CHI:\te nte ena . 24300_28048\n'
'%gls:\tke ntho ena .\n'
'%cod:\tcp thing(9 , 10) d9 .\n'
'%eng:\tIt is this thing\n'
'*MEM:\tke khomba\n'
'\tkhomba . 28048_31840\n'
'%gls:\tkekumbakumba .\n'
'%cod:\tcp tape_recorder(9 , 10) .\n'
'%eng:\tIt is a stereo\n'
'@End')
self.reader = InuktitutReader(io.StringIO(session))
self.reader.load_next_record()
self.maxDiff = None
def get_reader(session_file):
return InuktitutReader(session_file)
def test_parse(self):
"""Test parse()."""
session_str = (
'@Participants:\tMAE Maemae Mother , RO Roro Target_Child\n'
'@ID:\tsme|Inuktitut|MAE||female|||Mother|||\n'
'@ID:\tsme|Inuktitut|RO||female|||Target_Child|||\n'
'*RO:\tAllaigutama .\n'
'%eng:\tGive me a comb .\n'
'%xmor:\tNR|ollaoguto^comb+NI|mim^MOD_SG .\n'
'%tim:\t00:01:32\n'
'%add:\tMAE\n'
'@End'
)
parser = InuktitutSessionParser(self.dummy_cha_path)
parser.reader = InuktitutReader(io.StringIO(session_str))
session = parser.parse()
utt = session.utterances[0]
utterance = [
utt.source_id == 'dummy_0',
utt.speaker.code == 'RO',
utt.addressee.code == 'MAE',
utt.childdirected is False,
utt.utterance_raw == 'Allaigutama .',
utt.utterance == 'Allaigutama',
utt.translation == 'Give me a comb .',
utt.morpheme_raw == 'NR|ollaoguto^comb+NI|mim^MOD_SG .',
utt.gloss_raw == 'NR|ollaoguto^comb+NI|mim^MOD_SG .',
utt.pos_raw == 'NR|ollaoguto^comb+NI|mim^MOD_SG .',
utt.sentence_type == 'default',
utt.start_raw == '00:01:32',
utt.end_raw == '',
utt.comment == '',
utt.warning == ''
]
w = utt.words[0]
words = [
w.word_language == '',
w.word == 'Allaigutama',
w.word_actual == 'Allaigutama',
w.word_target == 'Allaigutama',
w.warning == ''
]
m1 = utt.morphemes[0][0]
m2 = utt.morphemes[0][1]
morphemes = [
m1.morpheme_language == 'Inuktitut',
m1.morpheme == 'ollaoguto',
m1.gloss_raw == 'comb',
m1.pos_raw == 'NR',
m2.morpheme_language == 'Inuktitut',
m2.morpheme == 'mim',
m2.gloss_raw == 'MOD_SG',
m2.pos_raw == 'NI'
]
assert (False not in utterance
and False not in words
and False not in morphemes)
