2018-07-25 00:38:44 +03:00
|
|
|
import pytest
|
|
|
|
from spacy.vocab import Vocab
|
|
|
|
from spacy.tokens import Doc
|
2020-04-14 20:15:52 +03:00
|
|
|
from spacy import util
|
2017-10-11 04:21:23 +03:00
|
|
|
|
|
|
|
|
|
|
|
@pytest.fixture
|
2020-08-07 16:27:13 +03:00
|
|
|
def vocab():
|
|
|
|
return Vocab()
|
2017-10-11 04:21:23 +03:00
|
|
|
|
|
|
|
|
|
|
|
def test_empty_doc(vocab):
|
|
|
|
doc = Doc(vocab)
|
|
|
|
assert len(doc) == 0
|
|
|
|
|
|
|
|
|
|
|
|
def test_single_word(vocab):
|
2018-11-27 03:09:36 +03:00
|
|
|
doc = Doc(vocab, words=["a"])
|
|
|
|
assert doc.text == "a "
|
|
|
|
doc = Doc(vocab, words=["a"], spaces=[False])
|
|
|
|
assert doc.text == "a"
|
2017-10-11 04:21:23 +03:00
|
|
|
|
|
|
|
|
2020-04-14 20:15:52 +03:00
|
|
|
def test_create_from_words_and_text(vocab):
|
|
|
|
# no whitespace in words
|
|
|
|
words = ["'", "dogs", "'", "run"]
|
|
|
|
text = " 'dogs'\n\nrun "
|
|
|
|
(words, spaces) = util.get_words_and_spaces(words, text)
|
|
|
|
doc = Doc(vocab, words=words, spaces=spaces)
|
|
|
|
assert [t.text for t in doc] == [" ", "'", "dogs", "'", "\n\n", "run", " "]
|
|
|
|
assert [t.whitespace_ for t in doc] == ["", "", "", "", "", " ", ""]
|
|
|
|
assert doc.text == text
|
2020-05-21 15:14:01 +03:00
|
|
|
assert [t.text for t in doc if not t.text.isspace()] == [
|
|
|
|
word for word in words if not word.isspace()
|
|
|
|
]
|
2020-04-14 20:15:52 +03:00
|
|
|
|
|
|
|
# partial whitespace in words
|
|
|
|
words = [" ", "'", "dogs", "'", "\n\n", "run", " "]
|
|
|
|
text = " 'dogs'\n\nrun "
|
|
|
|
(words, spaces) = util.get_words_and_spaces(words, text)
|
|
|
|
doc = Doc(vocab, words=words, spaces=spaces)
|
|
|
|
assert [t.text for t in doc] == [" ", "'", "dogs", "'", "\n\n", "run", " "]
|
|
|
|
assert [t.whitespace_ for t in doc] == ["", "", "", "", "", " ", ""]
|
|
|
|
assert doc.text == text
|
2020-05-21 15:14:01 +03:00
|
|
|
assert [t.text for t in doc if not t.text.isspace()] == [
|
|
|
|
word for word in words if not word.isspace()
|
|
|
|
]
|
2020-04-14 20:15:52 +03:00
|
|
|
|
|
|
|
# non-standard whitespace tokens
|
|
|
|
words = [" ", " ", "'", "dogs", "'", "\n\n", "run"]
|
|
|
|
text = " 'dogs'\n\nrun "
|
|
|
|
(words, spaces) = util.get_words_and_spaces(words, text)
|
|
|
|
doc = Doc(vocab, words=words, spaces=spaces)
|
|
|
|
assert [t.text for t in doc] == [" ", "'", "dogs", "'", "\n\n", "run", " "]
|
|
|
|
assert [t.whitespace_ for t in doc] == ["", "", "", "", "", " ", ""]
|
|
|
|
assert doc.text == text
|
2020-05-21 15:14:01 +03:00
|
|
|
assert [t.text for t in doc if not t.text.isspace()] == [
|
|
|
|
word for word in words if not word.isspace()
|
|
|
|
]
|
2020-04-14 20:15:52 +03:00
|
|
|
|
|
|
|
# mismatch between words and text
|
|
|
|
with pytest.raises(ValueError):
|
|
|
|
words = [" ", " ", "'", "dogs", "'", "\n\n", "run"]
|
|
|
|
text = " 'dogs'\n\nrun "
|
|
|
|
(words, spaces) = util.get_words_and_spaces(words + ["away"], text)
|