mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 21:57:15 +03:00
27 lines
591 B
Python
27 lines
591 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...attrs import LIKE_NUM
|
|
|
|
|
|
_num_words = ['không', 'một', 'hai', 'ba', 'bốn', 'năm', 'sáu', 'bẩy',
|
|
'tám', 'chín', 'mười', 'trăm', 'tỷ']
|
|
|
|
|
|
def like_num(text):
|
|
text = text.replace(',', '').replace('.', '')
|
|
if text.isdigit():
|
|
return True
|
|
if text.count('/') == 1:
|
|
num, denom = text.split('/')
|
|
if num.isdigit() and denom.isdigit():
|
|
return True
|
|
if text.lower() in _num_words:
|
|
return True
|
|
return False
|
|
|
|
|
|
LEX_ATTRS = {
|
|
LIKE_NUM: like_num
|
|
}
|