mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 19:39:13 +03:00
db55577c45
* Remove unicode declarations * Remove Python 3.5 and 2.7 from CI * Don't require pathlib * Replace compat helpers * Remove OrderedDict * Use f-strings * Set Cython compiler language level * Fix typo * Re-add OrderedDict for Table * Update setup.cfg * Revert CONTRIBUTING.md * Revert lookups.md * Revert top-level.md * Small adjustments and docs [ci skip]
29 lines
778 B
Python
29 lines
778 B
Python
from spacy.lang.en import English
|
|
from spacy.tokens import Doc
|
|
from spacy.vocab import Vocab
|
|
|
|
|
|
def test_issue4133(en_vocab):
|
|
nlp = English()
|
|
vocab_bytes = nlp.vocab.to_bytes()
|
|
words = ["Apple", "is", "looking", "at", "buying", "a", "startup"]
|
|
pos = ["NOUN", "VERB", "ADP", "VERB", "PROPN", "NOUN", "ADP"]
|
|
doc = Doc(en_vocab, words=words)
|
|
for i, token in enumerate(doc):
|
|
token.pos_ = pos[i]
|
|
|
|
# usually this is already True when starting from proper models instead of blank English
|
|
doc.is_tagged = True
|
|
|
|
doc_bytes = doc.to_bytes()
|
|
|
|
vocab = Vocab()
|
|
vocab = vocab.from_bytes(vocab_bytes)
|
|
doc = Doc(vocab).from_bytes(doc_bytes)
|
|
|
|
actual = []
|
|
for token in doc:
|
|
actual.append(token.pos_)
|
|
|
|
assert actual == pos
|