mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-13 13:17:06 +03:00
17 lines
364 B
Python
17 lines
364 B
Python
# coding: utf8
|
||
from __future__ import unicode_literals
|
||
|
||
from ..punctuation import TOKENIZER_INFIXES
|
||
from ..char_classes import ALPHA
|
||
|
||
|
||
ELISION = " ' ’ ".strip().replace(" ", "")
|
||
HYPHENS = r"- – — ‐ ‑".strip().replace(" ", "")
|
||
|
||
|
||
_infixes = TOKENIZER_INFIXES + [
|
||
r"(?<=[{a}][{el}])(?=[{a}])".format(a=ALPHA, el=ELISION)
|
||
]
|
||
|
||
TOKENIZER_INFIXES = _infixes
|