mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 12:18:04 +03:00
86eb817b74
* (#3803) Spanish like_num returning false for number-like token * (#3803) Spanish like_num now returning True for number-like token
60 lines
997 B
Python
60 lines
997 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...attrs import LIKE_NUM
|
|
|
|
|
|
_num_words = [
|
|
"cero",
|
|
"uno",
|
|
"dos",
|
|
"tres",
|
|
"cuatro",
|
|
"cinco",
|
|
"seis",
|
|
"siete",
|
|
"ocho",
|
|
"nueve",
|
|
"diez",
|
|
"once",
|
|
"doce",
|
|
"trece",
|
|
"catorce",
|
|
"quince",
|
|
"dieciséis",
|
|
"diecisiete",
|
|
"dieciocho",
|
|
"diecinueve",
|
|
"veinte",
|
|
"treinta",
|
|
"cuarenta",
|
|
"cincuenta",
|
|
"sesenta",
|
|
"setenta",
|
|
"ochenta",
|
|
"noventa",
|
|
"cien",
|
|
"mil",
|
|
"millón",
|
|
"billón",
|
|
"trillón",
|
|
]
|
|
|
|
|
|
def like_num(text):
|
|
if text.startswith(("+", "-", "±", "~")):
|
|
text = text[1:]
|
|
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}
|