mirror of https://github.com/explosion/spaCy.git
30 lines
896 B
Python
30 lines
896 B
Python
from ...attrs import LIKE_NUM
|
|
|
|
# fmt: off
|
|
_num_words = [
|
|
"zero", "one", "two", "three", "four", "five", "six", "seven", "eight",
|
|
"nine", "ten", "eleven", "twelve", "thirteen", "fourteen", "fifteen",
|
|
"sixteen", "seventeen", "eighteen", "nineteen", "twenty", "thirty", "forty",
|
|
"fifty", "sixty", "seventy", "eighty", "ninety", "hundred", "thousand",
|
|
"million", "billion", "trillion", "quadrillion", "gajillion", "bazillion"
|
|
]
|
|
# fmt: on
|
|
|
|
|
|
def like_num(text: str) -> bool:
|
|
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}
|