def setUpClass(cls):
session = ('@UTF8\n'
'@Begin\n'
'@Date:\t12-SEP-1997\n'
'@Media:\tmedia_filename, audio\n'
'@End')
cls.reader = CHATReader(io.StringIO(session))
def test_get_morpheme_language(self):
"""Test get_morpheme_language. Should return an empty string."""
seg = 'Hatschi'
gloss = 'sneeze'
pos = 'N'
actual_output = CHATReader.get_morpheme_language(seg, gloss, pos)
desired_output = ''
self.assertEqual(actual_output, desired_output)
def get_reader(session_file):
"""Return a CHATReader instance.
Returns:
acqdiv.parsers.chat.readers.reader.CHATReader:
The reader instance.
"""
return CHATReader(session_file)
def setUpClass(cls):
session = ('@UTF8\n'
'@Begin\n'
'@Participants:\tCHI Hlobohang Target_Child\n'
'@ID:\tsme|Sesotho|CHI|2;2.||||Target_Child|||\n'
'@Birth of CHI:\t14-JAN-2006\n'
'@End')
cls.reader = CHATReader(io.StringIO(session))
cls.reader.load_next_speaker()
def setUpClass(cls):
session = ('@UTF8\n'
'@Begin\n'
'*MEM:\t&foo ma(i)nline [: utterance]. \x150_1111\x15\n'
'%add:\tADD\n'
'%sit:\tThis is the situation\n'
'%act:\tThis is the action\n'
'%mor:\tThis is the morphology tier\n'
'%eng:\tThis is the translation.\n'
'%com:\tThis is the comment\n'
'%exp:\tThis is the explanation\n'
'@End')
cls.reader = CHATReader(io.StringIO(session))
cls.reader.load_next_record()
def setUpClass(cls):
session = ('@UTF8\n'
'@Begin\n'
'@Participants:\tMOT Kim Mother, CHI Daniel Target_Child\n'
'@ID:\t|English|MOT|||||Mother|||\n'
'@ID:\t|English|CHI|2;8.|male|||Target_Child|||\n'
'*MOT:\tThis is the first mainline of MOT .\n'
'%eng:\tThis is the translation\n'
'*CHI:\tThis is the first mainline of CHI .\n'
'%gls:\tThis is the gls tier\n'
'%cod:\tThis is the cod tier\n'
'*MOT:\tThis is the second mainline of MOT .\n'
'@End')
cls.reader = CHATReader(io.StringIO(session))
def test_get_session_metadata(self):
"""Test get_session_metadata with TestCHATParser.cha. (CHATParser)"""
session = ('@UTF8\n'
'@Begin\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'
'@End')
parser = CHATParser(self.dummy_cha_path)
parser.reader = CHATReader(io.StringIO(session))
session = parser.parse()
oracle = (session.source_id == 'dummy' and session.date == '1997-09-12'
and session.media_filename == 'h2ab')
assert oracle
def test_get_poses(self):
"""Test get_poses."""
pos_word = 'mor1-mor2-mor3'
actual_output = CHATReader.get_poses(pos_word)
desired_output = ['mor1', 'mor2', 'mor3']
return self.assertEqual(actual_output, desired_output)
def test_next_speaker(self):
"""Test next_speaker with test.cha. (CHATParser)"""
session = ('@UTF8\n'
'@Begin\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'
'@End')
parser = CHATParser(self.dummy_cha_path)
parser.reader = CHATReader(io.StringIO(session))
session = parser.parse()
speaker_mem = session.speakers[0]
speaker_chi = session.speakers[1]
actual_mem_dict = {
'speaker_label': speaker_mem.code,
'name': speaker_mem.name,
'age_raw': speaker_mem.age_raw,
'gender_raw': speaker_mem.gender_raw,
'role_raw': speaker_mem.role_raw,
'languages_spoken': speaker_mem.languages_spoken,
'birthdate': speaker_mem.birth_date
}
actual_chi_dict = {
'speaker_label': speaker_chi.code,
'name': speaker_chi.name,
'age_raw': speaker_chi.age_raw,
'gender_raw': speaker_chi.gender_raw,
'role_raw': speaker_chi.role_raw,
'languages_spoken': speaker_chi.languages_spoken,
'birthdate': speaker_chi.birth_date
}
mem_dict = {
'speaker_label': 'MEM',
'name': 'Mme_Manyili',
'age_raw': '',
'gender_raw': 'female',
'role_raw': 'Grandmother',
'languages_spoken': 'sme',
'birthdate': '1974-10-11'
}
chi_dict = {
'speaker_label': 'CHI',
'name': 'Hlobohang',
'age_raw': '2;2.',
'gender_raw': '',
'role_raw': 'Target_Child',
'languages_spoken': 'sme',
'birthdate': '2006-01-14'
}
actual_output = [actual_mem_dict, actual_chi_dict]
desired_output = [mem_dict, chi_dict]
self.assertEqual(actual_output, desired_output)
def test_get_main_morpheme(self):
"""Test get_main_morpheme."""
actual_output = CHATReader.get_main_morpheme()
desired_output = 'gloss'
self.assertEqual(actual_output, desired_output)
def test_get_pos_words(self):
"""Test get_pos_words."""
pos_tier = 'This is an example'
actual_output = CHATReader.get_seg_words(pos_tier)
desired_output = ['This', 'is', 'an', 'example']
self.assertEqual(actual_output, desired_output)
def test_get_morpheme_words_multiple_whitespaces(self):
"""Test get_morpheme_words."""
mor_tier = 'This is an example'
actual_output = CHATReader.get_morpheme_words(mor_tier)
desired_output = ['This', 'is', 'an', 'example']
self.assertEqual(actual_output, desired_output)
def test_get_word_language(self):
"""Test get_word_language."""
actual_output = CHATReader.get_word_language('dal')
desired_output = ''
self.assertEqual(actual_output, desired_output)
def test_get_standard_form(self):
"""Test get_standard_form."""
actual_output = CHATReader.get_standard_form()
desired_output = 'actual'
self.assertEqual(actual_output, desired_output)
def test_get_utterance_words_standard_case(self):
"""Test get_utterance_words for standard input."""
utterance = 'ke eng ntho ena e?'
actual_output = CHATReader.get_utterance_words(utterance)
desired_output = ['ke', 'eng', 'ntho', 'ena', 'e?']
self.assertEqual(actual_output, desired_output)
def test_get_utterance_words_empty_string(self):
"""Test get_utterance_words for standard input."""
utterance = ''
actual_output = CHATReader.get_utterance_words(utterance)
desired_output = []
self.assertEqual(actual_output, desired_output)
def test_get_utterance_words_multiple_blank_spaces(self):
"""Test get_utterance_words with multiple blank spaces."""
utterance = 'ke eng ntho ena e?'
actual_output = CHATReader.get_utterance_words(utterance)
desired_output = ['ke', 'eng', 'ntho', 'ena', 'e?']
self.assertEqual(actual_output, desired_output)
