mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-15 06:09:01 +03:00
e2b70df012
* Use isort with Black profile * isort all the things * Fix import cycles as a result of import sorting * Add DOCBIN_ALL_ATTRS type definition * Add isort to requirements * Remove isort from build dependencies check * Typo
59 lines
955 B
Python
59 lines
955 B
Python
from ...attrs import LIKE_NUM
|
|
|
|
_num_words = [
|
|
"zero",
|
|
"un",
|
|
"dos",
|
|
"tres",
|
|
"quatre",
|
|
"cinc",
|
|
"sis",
|
|
"set",
|
|
"vuit",
|
|
"nou",
|
|
"deu",
|
|
"onze",
|
|
"dotze",
|
|
"tretze",
|
|
"catorze",
|
|
"quinze",
|
|
"setze",
|
|
"disset",
|
|
"divuit",
|
|
"dinou",
|
|
"vint",
|
|
"trenta",
|
|
"quaranta",
|
|
"cinquanta",
|
|
"seixanta",
|
|
"setanta",
|
|
"vuitanta",
|
|
"noranta",
|
|
"cent",
|
|
"mil",
|
|
"milió",
|
|
"bilió",
|
|
"trilió",
|
|
"quatrilió",
|
|
"gazilió",
|
|
"bazilió",
|
|
]
|
|
|
|
|
|
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}
|