mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 19:39:13 +03:00
ea20b72c08
* Only split + prefix if not numbers * Make like_num work for prefixed numbers * Add test for like_num
33 lines
973 B
Python
33 lines
973 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...attrs import LIKE_NUM
|
|
|
|
|
|
_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']
|
|
|
|
|
|
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
|
|
}
|