mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-28 10:56:31 +03:00
873c16a4df
* add malay lang * fix token len * black format * reformat conftest malay * remove exceptions not exist in dbp * format code
67 lines
1.2 KiB
Python
67 lines
1.2 KiB
Python
import unicodedata
|
|
|
|
from .punctuation import LIST_CURRENCY
|
|
from ...attrs import IS_CURRENCY, LIKE_NUM
|
|
|
|
|
|
_num_words = [
|
|
"kosong",
|
|
"satu",
|
|
"dua",
|
|
"tiga",
|
|
"empat",
|
|
"lima",
|
|
"enam",
|
|
"tujuh",
|
|
"lapan",
|
|
"sembilan",
|
|
"sepuluh",
|
|
"sebelas",
|
|
"belas",
|
|
"puluh",
|
|
"ratus",
|
|
"ribu",
|
|
"juta",
|
|
"billion",
|
|
"trillion",
|
|
"kuadrilion",
|
|
"kuintilion",
|
|
"sekstilion",
|
|
"septilion",
|
|
"oktilion",
|
|
"nonilion",
|
|
"desilion",
|
|
]
|
|
|
|
|
|
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
|
|
if text.count("-") == 1:
|
|
_, num = text.split("-")
|
|
if num.isdigit() or num in _num_words:
|
|
return True
|
|
return False
|
|
|
|
|
|
def is_currency(text):
|
|
if text in LIST_CURRENCY:
|
|
return True
|
|
|
|
for char in text:
|
|
if unicodedata.category(char) != "Sc":
|
|
return False
|
|
return True
|
|
|
|
|
|
LEX_ATTRS = {IS_CURRENCY: is_currency, LIKE_NUM: like_num}
|