def test_spacy(spacy_nlp):
from rasa_nlu.tokenizers.spacy_tokenizer import SpacyTokenizer
tk = SpacyTokenizer()
assert [t.text for t in tk.tokenize(spacy_nlp("Forecast for lunch"))] == ['Forecast', 'for', 'lunch']
assert [t.offset for t in tk.tokenize(spacy_nlp("Forecast for lunch"))] == [0, 9, 13]
assert [t.text for t in tk.tokenize(spacy_nlp("hey ńöñàśçií how're you?"))] == \
['hey', 'ńöñàśçií', 'how', '\'re', 'you', '?']
assert [t.offset for t in tk.tokenize(spacy_nlp("hey ńöñàśçií how're you?"))] == [0, 4, 13, 16, 20, 23]
def test_spacy(spacy_nlp):
from rasa_nlu.tokenizers.spacy_tokenizer import SpacyTokenizer
tk = SpacyTokenizer()
assert [t.text for t in tk.tokenize(spacy_nlp("Forecast for lunch"))
] == ['Forecast', 'for', 'lunch']
assert [t.offset for t in tk.tokenize(spacy_nlp("Forecast for lunch"))
] == [0, 9, 13]
assert [t.text for t in tk.tokenize(spacy_nlp("hey ńöñàśçií how're you?"))] == \
['hey', 'ńöñàśçií', 'how', '\'re', 'you', '?']
assert [
t.offset for t in tk.tokenize(spacy_nlp("hey ńöñàśçií how're you?"))
] == [0, 4, 13, 16, 20, 23]
def tokenize_sentence(sentence, expected_result, language):
from rasa_nlu.tokenizers.spacy_tokenizer import SpacyTokenizer
tk = SpacyTokenizer(language)
assert tk.tokenize(sentence) == expected_result
def tokenize_sentence(sentence, expected_result):
from rasa_nlu.tokenizers.spacy_tokenizer import SpacyTokenizer
tk = SpacyTokenizer(spacy_nlp_en)
assert tk.tokenize(sentence) == expected_result
def tokenize_sentence(sentence, expected_result):
from rasa_nlu.tokenizers.spacy_tokenizer import SpacyTokenizer
tk = SpacyTokenizer()
assert tk.tokenize(sentence, spacy_nlp) == expected_result