mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 12:18:04 +03:00
61 lines
999 B
Python
61 lines
999 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...attrs import LIKE_NUM
|
|
|
|
|
|
_num_words = [
|
|
"sero",
|
|
"isa",
|
|
"dalawa",
|
|
"tatlo",
|
|
"apat",
|
|
"lima",
|
|
"anim",
|
|
"pito",
|
|
"walo",
|
|
"siyam",
|
|
"sampu",
|
|
"labing-isa",
|
|
"labindalawa",
|
|
"labintatlo",
|
|
"labing-apat",
|
|
"labinlima",
|
|
"labing-anim",
|
|
"labimpito",
|
|
"labing-walo",
|
|
"labinsiyam",
|
|
"dalawampu",
|
|
"tatlumpu",
|
|
"apatnapu",
|
|
"limampu",
|
|
"animnapu",
|
|
"pitumpu",
|
|
"walumpu",
|
|
"siyamnapu",
|
|
"daan",
|
|
"libo",
|
|
"milyon",
|
|
"bilyon",
|
|
"trilyon",
|
|
"quadrilyon",
|
|
"gajilyon",
|
|
"bazilyon",
|
|
]
|
|
|
|
|
|
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 in _num_words:
|
|
return True
|
|
return False
|
|
|
|
|
|
LEX_ATTRS = {LIKE_NUM: like_num}
|