ai-content-maker/.venv/Lib/site-packages/spacy/lang/sk/lex_attrs.py

60 lines
1.0 KiB
Python
Raw Normal View History

2024-05-03 04:18:51 +03:00
from ...attrs import LIKE_NUM
_num_words = [
"nula",
"jeden",
"dva",
"tri",
"štyri",
"päť",
"šesť",
"sedem",
"osem",
"deväť",
"desať",
"jedenásť",
"dvanásť",
"trinásť",
"štrnásť",
"pätnásť",
"šestnásť",
"sedemnásť",
"osemnásť",
"devätnásť",
"dvadsať",
"tridsať",
"štyridsať",
"päťdesiat",
"šesťdesiat",
"sedemdesiat",
"osemdesiat",
"deväťdesiat",
"sto",
"tisíc",
"milión",
"miliarda",
"bilión",
"biliarda",
"trilión",
"triliarda",
"kvadrilión",
]
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}