mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-15 06:09:01 +03:00
54 lines
919 B
Python
54 lines
919 B
Python
# coding: utf8
|
||
from __future__ import unicode_literals
|
||
|
||
from ...attrs import LIKE_NUM
|
||
|
||
|
||
# Thirteen, fifteen etc. are written separate: on üç
|
||
|
||
_num_words = [
|
||
"bir",
|
||
"iki",
|
||
"üç",
|
||
"dört",
|
||
"beş",
|
||
"altı",
|
||
"yedi",
|
||
"sekiz",
|
||
"dokuz",
|
||
"on",
|
||
"yirmi",
|
||
"otuz",
|
||
"kırk",
|
||
"elli",
|
||
"altmış",
|
||
"yetmiş",
|
||
"seksen",
|
||
"doksan",
|
||
"yüz",
|
||
"bin",
|
||
"milyon",
|
||
"milyar",
|
||
"trilyon",
|
||
"katrilyon",
|
||
"kentilyon",
|
||
]
|
||
|
||
|
||
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}
|