mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 12:18:04 +03:00
f7471abd82
* Add pkuseg and serialization support for Chinese
Add support for pkuseg alongside jieba
* Specify model through `Language` meta:
* split on characters (if no word segmentation packages are installed)
```
Chinese(meta={"tokenizer": {"config": {"use_jieba": False, "use_pkuseg": False}}})
```
* jieba (remains the default tokenizer if installed)
```
Chinese()
Chinese(meta={"tokenizer": {"config": {"use_jieba": True}}}) # explicit
```
* pkuseg
```
Chinese(meta={"tokenizer": {"config": {"pkuseg_model": "default", "use_jieba": False, "use_pkuseg": True}}})
```
* The new tokenizer setting `require_pkuseg` is used to override
`use_jieba` default, which is intended for models that provide a pkuseg
model:
```
nlp_pkuseg = Chinese(meta={"tokenizer": {"config": {"pkuseg_model": "default", "require_pkuseg": True}}})
nlp = Chinese() # has `use_jieba` as `True` by default
nlp.from_bytes(nlp_pkuseg.to_bytes()) # `require_pkuseg` overrides `use_jieba` when calling the tokenizer
```
Add support for serialization of tokenizer settings and pkuseg model, if
loaded
* Add sorting for `Language.to_bytes()` serialization of `Language.meta`
so that the (emptied, but still present) tokenizer metadata is in a
consistent position in the serialized data
Extend tests to cover all three tokenizer configurations and
serialization
* Fix from_disk and tests without jieba or pkuseg
* Load cfg first and only show error if `use_pkuseg`
* Fix blank/default initialization in serialization tests
* Explicitly initialize jieba's cache on init
* Add serialization for pkuseg pre/postprocessors
* Reformat pkuseg install message
39 lines
1.2 KiB
Python
39 lines
1.2 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
from spacy.lang.zh import Chinese
|
|
from ...util import make_tempdir
|
|
|
|
|
|
def zh_tokenizer_serialize(zh_tokenizer):
|
|
tokenizer_bytes = zh_tokenizer.to_bytes()
|
|
nlp = Chinese(meta={"tokenizer": {"config": {"use_jieba": False}}})
|
|
nlp.tokenizer.from_bytes(tokenizer_bytes)
|
|
assert tokenizer_bytes == nlp.tokenizer.to_bytes()
|
|
|
|
with make_tempdir() as d:
|
|
file_path = d / "tokenizer"
|
|
zh_tokenizer.to_disk(file_path)
|
|
nlp = Chinese(meta={"tokenizer": {"config": {"use_jieba": False}}})
|
|
nlp.tokenizer.from_disk(file_path)
|
|
assert tokenizer_bytes == nlp.tokenizer.to_bytes()
|
|
|
|
|
|
def test_zh_tokenizer_serialize_char(zh_tokenizer_char):
|
|
zh_tokenizer_serialize(zh_tokenizer_char)
|
|
|
|
|
|
def test_zh_tokenizer_serialize_jieba(zh_tokenizer_jieba):
|
|
zh_tokenizer_serialize(zh_tokenizer_jieba)
|
|
|
|
|
|
def test_zh_tokenizer_serialize_pkuseg(zh_tokenizer_pkuseg):
|
|
zh_tokenizer_serialize(zh_tokenizer_pkuseg)
|
|
|
|
|
|
@pytest.mark.slow
|
|
def test_zh_tokenizer_serialize_pkuseg_with_processors(zh_tokenizer_pkuseg):
|
|
nlp = Chinese(meta={"tokenizer": {"config": {"use_jieba": False, "use_pkuseg": True, "pkuseg_model": "medicine"}}})
|
|
zh_tokenizer_serialize(nlp.tokenizer)
|