mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 21:57:15 +03:00
9a016d17c2
* adding Sinhala language package, stop words, examples and lex_attrs. * Adding contributor agreement * Updating contributor agreement
29 lines
1.2 KiB
Python
29 lines
1.2 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...attrs import LIKE_NUM
|
|
|
|
_num_words = ['බින්දුව', 'බිංදුව', 'එක', 'දෙක', 'තුන', 'හතර', 'පහ', 'හය', 'හත',
|
|
'අට', 'නවය', 'නමය', 'දහය', 'එකොළහ', 'දොළහ', 'දහතුන', 'දහහතර',
|
|
'දාහතර', 'පහළව', 'පහළොව', 'දහසය', 'දහහත', 'දාහත', 'දහඅට',
|
|
'දහනවය', 'විස්ස', 'තිහ', 'හතළිහ', 'පනහ', 'හැට', 'හැත්තෑව', 'අසූව',
|
|
'අනූව', 'සියය', 'දහස', 'දාහ', 'ලක්ෂය', 'මිලියනය', 'කෝටිය',
|
|
'බිලියනය', 'ට්රිලියනය']
|
|
|
|
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
|
|
}
|