mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 09:56:28 +03:00
26 lines
710 B
Python
26 lines
710 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ..char_classes import LIST_ELLIPSES, LIST_ICONS
|
|
from ..char_classes import CONCAT_QUOTES, ALPHA, ALPHA_LOWER, ALPHA_UPPER
|
|
|
|
|
|
_quotes = CONCAT_QUOTES.replace("'", "")
|
|
|
|
_infixes = (
|
|
LIST_ELLIPSES
|
|
+ LIST_ICONS
|
|
+ [
|
|
r"(?<=[{al}])\.(?=[{au}])".format(al=ALPHA_LOWER, au=ALPHA_UPPER),
|
|
r"(?<=[{a}])[,!?](?=[{a}])".format(a=ALPHA),
|
|
r"(?<=[{a}])[:<>=](?=[{a}])".format(a=ALPHA),
|
|
r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
|
|
r"(?<=[{a}])([{q}\)\]\(\[])(?=[{a}])".format(a=ALPHA, q=_quotes),
|
|
r"(?<=[{a}])--(?=[{a}])".format(a=ALPHA),
|
|
r"(?<=[0-9])-(?=[0-9])",
|
|
]
|
|
)
|
|
|
|
|
|
TOKENIZER_INFIXES = _infixes
|