mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 17:36:30 +03:00
20 lines
577 B
Python
20 lines
577 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .. import language_data as base
|
|
from ..language_data import update_exc, strings_to_exc
|
|
|
|
from .stop_words import STOP_WORDS
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS, ORTH_ONLY
|
|
|
|
STOP_WORDS = set(STOP_WORDS)
|
|
|
|
|
|
TOKENIZER_EXCEPTIONS = dict(TOKENIZER_EXCEPTIONS)
|
|
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(ORTH_ONLY))
|
|
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.ABBREVIATIONS))
|
|
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.EMOTICONS))
|
|
|
|
|
|
__all__ = ["TOKENIZER_EXCEPTIONS", "STOP_WORDS"]
|