spaCy/spacy/lang/tt/lex_attrs.py

62 lines
1.1 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# coding: utf8
from __future__ import unicode_literals
from ...attrs import LIKE_NUM
_num_words = [
"нуль",
"ноль",
"бер",
"ике",
"өч",
"дүрт",
"биш",
"алты",
"җиде",
"сигез",
"тугыз",
"ун",
"унбер",
"унике",
"унөч",
"ундүрт",
"унбиш",
"уналты",
"унҗиде",
"унсигез",
"унтугыз",
"егерме",
"утыз",
"кырык",
"илле",
"алтмыш",
"җитмеш",
"сиксән",
"туксан",
"йөз",
"мең",
"төмән",
"миллион",
"миллиард",
"триллион",
"триллиард",
]
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 in _num_words:
return True
return False
LEX_ATTRS = {LIKE_NUM: like_num}