def test_glossary_extractor(self) -> None:
t = Tokenizer()
g = ['New York', 'Shanghai', 'Los Angeles', 'Beijing']
ge = GlossaryExtractor(g, 'test_glossary', t, 2, False)
text = 'i live in los angeles. my hometown is Beijing'
tokens = t.tokenize(text)
test_result = [i.value for i in ge.extract(tokens)]
expected = ["Beijing", "Los Angeles"]
self.assertEqual(test_result, expected)
def test_glossary_extractor(self) -> None:
t = Tokenizer()
text = 'i live in los angeles. my hometown is Beijing. I love New York City.'
tokens = t.tokenize(text)
ge = GlossaryExtractor(self.glossary_1, 'test_glossary', t, 3, False)
results = [i.value for i in ge.extract(tokens)]
expected = ['Beijing', 'los angeles', 'New York']
self.assertEqual(results, expected)
def test_case_sensitive(self) -> None:
t = Tokenizer()
text = 'i live in los angeles. my hometown is Beijing. I love New York City.'
tokens = t.tokenize(text)
g = ['Beijing', 'Los Angeles', 'New York', 'Shanghai']
ge = GlossaryExtractor(g, 'test_glossary', t, 2, True)
results = [i.value for i in ge.extract(tokens)]
expected = ['Beijing', 'New York']
self.assertEqual(results, expected)
def setUp(self):
self.text = 'Napoléon Bonaparte was a French statesman and military leader who rose to prominence during the ' \
'French Revolution and led several successful campaigns during the French Revolutionary Wars. ' \
'As Napoleon, he was Emperor of the French from 1804 until 1814, and again briefly in 1815 during ' \
'the Hundred Days. Napoleon dominated European and global affairs for more than a decade while ' \
'leading France against a series of coalitions in the Napoleonic Wars. He won most of these wars ' \
'and the vast majority of his battles, building a large empire that ruled over continental Europe ' \
'before its final collapse in 1815. He is considered one of the greatest commanders in history, ' \
'and his wars and campaigns are studied at military schools worldwide. Napoleon\'s political and ' \
'cultural legacy has endured as one of the most celebrated and controversial leaders in human history.'
extractor = SpacyNerExtractor(extractor_name='spacy_ner_extractor')
self.results = extractor.extract(self.text)
glossary_1 = ['Beijing', 'Los Angeles', 'New York', 'Shanghai']
t = Tokenizer()
text = 'i live in los angeles. my hometown is Beijing. I love New York City.'
tokens = t.tokenize(text)
ge = GlossaryExtractor(glossary_1, 'test_glossary', t, 3, False)
self.results2 = ge.extract(tokens)