spaCy/spacy/lang/en/lex_attrs.py

24 lines
745 B
Python
Raw Normal View History

2017-05-08 13:47:25 +00:00
# coding: utf8
from __future__ import unicode_literals
# Number words
NUM_WORDS = set("""
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
""".split())
# Ordinal words
ORDINAL_WORDS = set("""
first second third fourth fifth sixth seventh eigth ninth tenth eleventh twelveth
thirteenth fourteenth fifteenth sixteenth sventeenth eighteenth nineteenth
twentieth thirtieth fortieth fiftieth sixtieth seventieth eightieth ninetieth
hundreth thousandth millionth billionth trillionth quadrillionth gajillionth
bazillionth
""".split())