spaCy/spacy/lang/ko/lex_attrs.py

68 lines
1.1 KiB
Python
Raw Normal View History

# coding: utf8
from __future__ import unicode_literals
from ...attrs import LIKE_NUM
_num_words = [
2019-11-20 15:15:24 +03:00
"",
"",
# Native Korean number system
"하나",
"",
"",
"",
"다섯",
"여섯",
"일곱",
"여덟",
"아홉",
"",
"스물",
"서른",
"마흔",
"",
"예순",
"일흔",
"여든",
"아흔",
# Sino-Korean number system
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"십만",
"백만",
"천만",
"일억",
"십억",
"백억",
]
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 any(char.lower() in _num_words for char in text):
return True
return False
LEX_ATTRS = {LIKE_NUM: like_num}