mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 09:26:27 +03:00
33 lines
929 B
Python
33 lines
929 B
Python
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
|
|
from spacy.en import English
|
|
|
|
NLU = English()
|
|
|
|
|
|
def test_merge_tokens():
|
|
tokens = NLU(u'Los Angeles start.')
|
|
assert len(tokens) == 4
|
|
assert tokens[0].head.orth_ == 'Angeles'
|
|
assert tokens[1].head.orth_ == 'start'
|
|
tokens.merge(0, len('Los Angeles'), 'NNP', 'Los Angeles', 'GPE')
|
|
assert len(tokens) == 3
|
|
assert tokens[0].orth_ == 'Los Angeles'
|
|
assert tokens[0].head.orth_ == 'start'
|
|
|
|
|
|
def test_merge_heads():
|
|
tokens = NLU(u'I found a pilates class near work.')
|
|
assert len(tokens) == 8
|
|
tokens.merge(tokens[3].idx, tokens[4].idx + len(tokens[4]), tokens[4].tag_,
|
|
'pilates class', 'O')
|
|
assert len(tokens) == 7
|
|
assert tokens[0].head.i == 1
|
|
assert tokens[1].head.i == 1
|
|
assert tokens[2].head.i == 3
|
|
assert tokens[3].head.i == 1
|
|
assert tokens[4].head.i in [1, 3]
|
|
assert tokens[5].head.i == 4
|