mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 10:26:35 +03:00
c5de9b463a
* Fix incorrect pickling of Japanese and Korean pipelines, which led to the entire pipeline being reset if pickled * Enable pickling of Vietnamese tokenizer * Update tokenizer APIs for Chinese, Japanese, Korean, Thai, and Vietnamese so that only the `Vocab` is required for initialization
25 lines
706 B
Python
25 lines
706 B
Python
import pickle
|
|
|
|
from spacy.lang.th import Thai
|
|
from ...util import make_tempdir
|
|
|
|
|
|
def test_th_tokenizer_serialize(th_tokenizer):
|
|
tokenizer_bytes = th_tokenizer.to_bytes()
|
|
nlp = Thai()
|
|
nlp.tokenizer.from_bytes(tokenizer_bytes)
|
|
assert tokenizer_bytes == nlp.tokenizer.to_bytes()
|
|
|
|
with make_tempdir() as d:
|
|
file_path = d / "tokenizer"
|
|
th_tokenizer.to_disk(file_path)
|
|
nlp = Thai()
|
|
nlp.tokenizer.from_disk(file_path)
|
|
assert tokenizer_bytes == nlp.tokenizer.to_bytes()
|
|
|
|
|
|
def test_th_tokenizer_pickle(th_tokenizer):
|
|
b = pickle.dumps(th_tokenizer)
|
|
th_tokenizer_re = pickle.loads(b)
|
|
assert th_tokenizer.to_bytes() == th_tokenizer_re.to_bytes()
|