mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 12:18:04 +03:00
48 lines
1.5 KiB
Python
48 lines
1.5 KiB
Python
|
# coding: utf8
|
||
|
|
from __future__ import unicode_literals
|
||
|
|
|
||
|
|
import pytest
|
||
|
|
from spacy.tokens import Doc
|
||
|
|
from spacy.displacy import render
|
||
|
|
from spacy.gold import iob_to_biluo
|
||
|
|
|
||
|
|
from ..util import add_vecs_to_vocab
|
||
|
|
|
||
|
|
|
||
|
|
def test_issue2219(en_vocab):
|
||
|
|
vectors = [("a", [1, 2, 3]), ("letter", [4, 5, 6])]
|
||
|
|
add_vecs_to_vocab(en_vocab, vectors)
|
||
|
|
[(word1, vec1), (word2, vec2)] = vectors
|
||
|
|
doc = Doc(en_vocab, words=[word1, word2])
|
||
|
|
assert doc[0].similarity(doc[1]) == doc[1].similarity(doc[0])
|
||
|
|
|
||
|
|
|
||
|
|
def test_issue2361(de_tokenizer):
|
||
|
|
chars = ('<', '>', '&', '"')
|
||
|
|
doc = de_tokenizer('< > & " ')
|
||
|
|
doc.is_parsed = True
|
||
|
|
doc.is_tagged = True
|
||
|
|
html = render(doc)
|
||
|
|
for char in chars:
|
||
|
|
assert char in html
|
||
|
|
|
||
|
|
|
||
|
|
def test_issue2385():
|
||
|
|
"""Test that IOB tags are correctly converted to BILUO tags."""
|
||
|
|
# fix bug in labels with a 'b' character
|
||
|
|
tags1 = ('B-BRAWLER', 'I-BRAWLER', 'I-BRAWLER')
|
||
|
|
assert iob_to_biluo(tags1) == ['B-BRAWLER', 'I-BRAWLER', 'L-BRAWLER']
|
||
|
|
# maintain support for iob1 format
|
||
|
|
tags2 = ('I-ORG', 'I-ORG', 'B-ORG')
|
||
|
|
assert iob_to_biluo(tags2) == ['B-ORG', 'L-ORG', 'U-ORG']
|
||
|
|
# maintain support for iob2 format
|
||
|
|
tags3 = ('B-PERSON', 'I-PERSON', 'B-PERSON')
|
||
|
|
assert iob_to_biluo(tags3) ==['B-PERSON', 'L-PERSON', 'U-PERSON']
|
||
|
|
|
||
|
|
|
||
|
|
@pytest.mark.parametrize('tags', [
|
||
|
|
('B-ORG', 'L-ORG'), ('B-PERSON', 'I-PERSON', 'L-PERSON'), ('U-BRAWLER', 'U-BRAWLER')])
|
||
|
|
def test_issue2385_biluo(tags):
|
||
|
|
"""Test that BILUO-compatible tags aren't modified."""
|
||
|
|
assert iob_to_biluo(tags) == list(tags)
|