spaCy/spacy/lang/tl/lex_attrs.py
2019-02-08 14:14:49 +01:00

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}