mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 04:08:09 +03:00
fa3b8512da
Bundle everything in language_data to keep it consistent with other languages and make TOKENIZER_EXCEPTIONS importable from there.
12 lines
258 B
Python
12 lines
258 B
Python
# encoding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .stop_words import STOP_WORDS
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS, TOKEN_MATCH
|
|
|
|
|
|
STOP_WORDS = set(STOP_WORDS)
|
|
|
|
|
|
__all__ = ["STOP_WORDS", "TOKENIZER_EXCEPTIONS", "TOKEN_MATCH"]
|