mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 20:28:20 +03:00
3bf111585d
* Use `config` dict for tokenizer settings * Add serialization of split mode setting * Add tests for tokenizer split modes and serialization of split mode setting Based on #5561
38 lines
1.1 KiB
Python
38 lines
1.1 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
from spacy.lang.ja import Japanese
|
|
from ...util import make_tempdir
|
|
|
|
|
|
def test_ja_tokenizer_serialize(ja_tokenizer):
|
|
tokenizer_bytes = ja_tokenizer.to_bytes()
|
|
nlp = Japanese()
|
|
nlp.tokenizer.from_bytes(tokenizer_bytes)
|
|
assert tokenizer_bytes == nlp.tokenizer.to_bytes()
|
|
assert nlp.tokenizer.split_mode == None
|
|
|
|
with make_tempdir() as d:
|
|
file_path = d / "tokenizer"
|
|
ja_tokenizer.to_disk(file_path)
|
|
nlp = Japanese()
|
|
nlp.tokenizer.from_disk(file_path)
|
|
assert tokenizer_bytes == nlp.tokenizer.to_bytes()
|
|
assert nlp.tokenizer.split_mode == None
|
|
|
|
# split mode is (de)serialized correctly
|
|
nlp = Japanese(meta={"tokenizer": {"config": {"split_mode": "B"}}})
|
|
nlp_r = Japanese()
|
|
nlp_bytes = nlp.to_bytes()
|
|
nlp_r.from_bytes(nlp_bytes)
|
|
assert nlp_bytes == nlp_r.to_bytes()
|
|
assert nlp_r.tokenizer.split_mode == "B"
|
|
|
|
with make_tempdir() as d:
|
|
nlp.to_disk(d)
|
|
nlp_r = Japanese()
|
|
nlp_r.from_disk(d)
|
|
assert nlp_bytes == nlp_r.to_bytes()
|
|
assert nlp_r.tokenizer.split_mode == "B"
|