def test_punctuation(self):
self.assertEqual(
split_transcript('Méiyǒu, méiyǒu.'),
['Méi yǒu', ',', 'méi yǒu', '.'],
)
self.assertEqual(
split_transcript('Méi yǒu, méi yǒu.', grouped=False),
['Méi', 'yǒu', ',', 'méi', 'yǒu', '.'],
)
self.assertEqual(
split_transcript('(méi) yǒu', grouped=False),
['(', 'méi', ')', 'yǒu'],
)
def test_apostrophe(self):
self.assertEqual(split_transcript("yīlù píng'ān"),
['yī lù', 'píng ān'])
def test_you_er_yuan(self):
self.assertEqual(split_transcript("yòu'éryuán"), ["yòu ér yuán"])
def test_multisyllabic_words(self):
with patch('chinese.transcribe.config', {'transcription': 'Pinyin'}):
self.assertEqual(split_transcript('túshūguǎn'), ['tú shū guǎn'])
def test_ungrouped(self):
with patch('chinese.transcribe.config', {'transcription': 'Pinyin'}):
self.assertEqual(
split_transcript('hěn gāoxìng', grouped=False),
['hěn', 'gāo', 'xìng'],
)
def test_tone_number(self):
with patch('chinese.transcribe.config', {'transcription': 'Pinyin'}):
self.assertEqual(split_transcript('xian4zai4'), ['xian4 zai4'])
def test_muliple_words(self):
with patch('chinese.transcribe.config', {'transcription': 'Pinyin'}):
self.assertEqual(split_transcript('hěn gāoxìng'),
['hěn', 'gāo xìng'])
def test_regression_1(self):
self.assertEqual(split_transcript('chuángdān', 'pinyin'),
['chuáng dān'])
def test_tone_mark(self):
with patch('chinese.transcribe.config', {'transcription': 'Pinyin'}):
self.assertEqual(split_transcript('xiànzài'), ['xiàn zài'])
def test_apostrophe(self):
self.assertEqual(split_transcript("yīlù píng'ān", 'pinyin'),
['yī lù', 'píng ān'])
self.assertEqual(split_transcript("yòu'éryuán", 'pinyin'),
['yòu ér yuán'])
def test_issue_79(self):
self.assertEqual(split_transcript("xiá ài", 'pinyin'), ['xiá', 'ài'])
self.assertEqual(split_transcript("xiá'ài", 'pinyin'), ['xiá ài'])
self.assertEqual(split_transcript("xiáài", 'pinyin'), ['xiá ài'])
def test_ungrouped(self):
self.assertEqual(
split_transcript('hěn gāoxìng', 'pinyin', grouped=False),
['hěn', 'gāo', 'xìng'],
)
def test_multisyllabic_words(self):
self.assertEqual(split_transcript('túshūguǎn', 'pinyin'),
['tú shū guǎn'])
def test_muliple_words(self):
self.assertEqual(split_transcript('hěn gāoxìng', 'pinyin'),
['hěn', 'gāo xìng'])
def test_tone_number(self):
self.assertEqual(split_transcript('xian4zai4', 'pinyin'),
['xian4 zai4'])
def test_tone_mark(self):
self.assertEqual(split_transcript('xiànzài', 'pinyin'), ['xiàn zài'])
