mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 18:06:29 +03:00
17 lines
636 B
Python
17 lines
636 B
Python
|
# coding: utf8
|
||
|
|
from __future__ import unicode_literals
|
||
|
|
|
||
|
|
from ..punctuation import TOKENIZER_INFIXES
|
||
|
|
from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, CURRENCY
|
||
|
|
from ..char_classes import QUOTES, UNITS, ALPHA, ALPHA_LOWER, ALPHA_UPPER
|
||
|
|
|
||
|
|
_suffixes = (LIST_PUNCT + LIST_ELLIPSES + LIST_QUOTES +
|
||
|
|
[r'(?<=[0-9])\+',
|
||
|
|
r'(?<=[0-9])%', # 4% -> ["4", "%"]
|
||
|
|
# Persian is written from Right-To-Left
|
||
|
|
r'(?<=[0-9])(?:{})'.format(CURRENCY),
|
||
|
|
r'(?<=[0-9])(?:{})'.format(UNITS),
|
||
|
|
r'(?<=[{au}][{au}])\.'.format(au=ALPHA_UPPER)])
|
||
|
|
|
||
|
|
TOKENIZER_SUFFIXES = _suffixes
|