def test_mitie_add_cls_token():
from rasa.nlu.tokenizers.mitie_tokenizer import MitieTokenizer
component_config = {"use_cls_token": True}
tk = MitieTokenizer(component_config)
text = "Forecast for lunch"
assert [t.text for t in tk.tokenize(text)] == [
"Forecast",
"for",
"lunch",
CLS_TOKEN,
]
assert [t.offset for t in tk.tokenize(text)] == [0, 9, 13, 19]
def test_mitie():
from rasa.nlu.tokenizers.mitie_tokenizer import MitieTokenizer
tk = MitieTokenizer()
text = "Forecast for lunch"
assert [t.text for t in tk.tokenize(text)] == \
['Forecast', 'for', 'lunch']
assert [t.offset for t in tk.tokenize(text)] == \
[0, 9, 13]
text = "hey ńöñàśçií how're you?"
assert [t.text for t in tk.tokenize(text)] == \
['hey', 'ńöñàśçií', 'how', '\'re', 'you', '?']
assert [t.offset for t in tk.tokenize(text)] == \
[0, 4, 13, 16, 20, 23]
def test_mitie(text, expected_tokens, expected_indices):
tk = MitieTokenizer()
tokens = tk.tokenize(Message(text), attribute=TEXT)
assert [t.text for t in tokens] == expected_tokens
assert [t.start for t in tokens] == [i[0] for i in expected_indices]
assert [t.end for t in tokens] == [i[1] for i in expected_indices]
def test_mitie():
from rasa.nlu.tokenizers.mitie_tokenizer import MitieTokenizer
tk = MitieTokenizer()
text = "Forecast for lunch"
assert [t.text for t in tk.tokenize(text)] == ["Forecast", "for", "lunch"]
assert [t.offset for t in tk.tokenize(text)] == [0, 9, 13]
text = "hey ńöñàśçií how're you?"
assert [t.text for t in tk.tokenize(text)] == [
"hey",
"ńöñàśçií",
"how",
"'re",
"you",
"?",
]
assert [t.offset for t in tk.tokenize(text)] == [0, 4, 13, 16, 20, 23]
