spaCy/spacy/lang/id/lex_attrs.py

# coding: utf8
from __future__ import unicode_literals

from ...attrs import LIKE_NUM


_num_words = ['nol', 'satu', 'dua', 'tiga', 'empat', 'lima', 'enam', 'tujuh',
              'delapan', 'sembilan', 'sepuluh', 'sebelas', 'belas', 'puluh',
              'ratus', 'ribu', 'juta', 'miliar', 'biliun', 'triliun', 'kuadriliun',
              'kuintiliun', 'sekstiliun', 'septiliun', 'oktiliun', 'noniliun', 'desiliun']


def like_num(text):
    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


LEX_ATTRS = {
    LIKE_NUM: like_num
}